D: Co-author of German book ``Linux-Kernel-Programmierung''
D: Co-founder of Berlin Linux User Group
+N: Andrew Victor
+E: linux@maxim.org.za
+W: http://maxim.org.za/at91_26.html
+D: First maintainer of Atmel ARM-based SoC, aka AT91
+D: Introduced support for at91rm9200, the first chip of AT91 family
+S: South Africa
+
N: Riku Voipio
E: riku.voipio@iki.fi
D: Author of PCA9532 LED and Fintek f75375s hwmon driver
What: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}
Date: August 2008
KernelVersion: 2.6.27
-Contact: discuss@x86-64.org
+Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
Description: Disable L3 cache indices
These files exist in every CPU's cache/index3 directory. Each
Description: It shows the physical address of config table entry in the EFI
system table.
Users: Kexec
+
+What: /sys/firmware/efi/systab
+Date: April 2005
+Contact: linux-efi@vger.kernel.org
+Description: Displays the physical addresses of all EFI Configuration
+ Tables found via the EFI System Table. The order in
+ which the tables are printed forms an ABI and newer
+ versions are always printed first, i.e. ACPI20 comes
+ before ACPI.
+Users: dmidecode
--- /dev/null
+What: /sys/firmware/efi/esrt/
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: Provides userland access to read the EFI System Resource Table
+ (ESRT), a catalog of firmware for which can be updated with
+ the UEFI UpdateCapsule mechanism described in section 7.5 of
+ the UEFI Standard.
+Users: fwupdate - https://github.com/rhinstaller/fwupdate
+
+What: /sys/firmware/efi/esrt/fw_resource_count
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: The number of entries in the ESRT
+
+What: /sys/firmware/efi/esrt/fw_resource_count_max
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: The maximum number of entries that /could/ be registered
+ in the allocation the table is currently in. This is
+ really only useful to the system firmware itself.
+
+What: /sys/firmware/efi/esrt/fw_resource_version
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: The version of the ESRT structure provided by the firmware.
+
+What: /sys/firmware/efi/esrt/entries/entry$N/
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: Each ESRT entry is identified by a GUID, and each gets a
+ subdirectory under entries/ .
+ example: /sys/firmware/efi/esrt/entries/entry0/
+
+What: /sys/firmware/efi/esrt/entries/entry$N/fw_type
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: What kind of firmware entry this is:
+ 0 - Unknown
+ 1 - System Firmware
+ 2 - Device Firmware
+ 3 - UEFI Driver
+
+What: /sys/firmware/efi/esrt/entries/entry$N/fw_class
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: This is the entry's guid, and will match the directory name.
+
+What: /sys/firmware/efi/esrt/entries/entry$N/fw_version
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: The version of the firmware currently installed. This is a
+ 32-bit unsigned integer.
+
+What: /sys/firmware/efi/esrt/entries/entry$N/lowest_supported_fw_version
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: The lowest version of the firmware that can be installed.
+
+What: /sys/firmware/efi/esrt/entries/entry$N/capsule_flags
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: Flags that must be passed to UpdateCapsule()
+
+What: /sys/firmware/efi/esrt/entries/entry$N/last_attempt_version
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: The last firmware version for which an update was attempted.
+
+What: /sys/firmware/efi/esrt/entries/entry$N/last_attempt_status
+Date: February 2015
+Contact: Peter Jones <pjones@redhat.com>
+Description: The result of the last firmware update attempt for the
+ firmware resource entry.
+ 0 - Success
+ 1 - Insufficient resources
+ 2 - Incorrect version
+ 3 - Invalid format
+ 4 - Authentication error
+ 5 - AC power event
+ 6 - Battery power event
+
3. Resizeable Arrays
-Each of these situations are discussed below.
+Each of these three situations involves an RCU-protected pointer to an
+array that is separately indexed. It might be tempting to consider use
+of RCU to instead protect the index into an array, however, this use
+case is -not- supported. The problem with RCU-protected indexes into
+arrays is that compilers can play way too many optimization games with
+integers, which means that the rules governing handling of these indexes
+are far more trouble than they are worth. If RCU-protected indexes into
+arrays prove to be particularly valuable (which they have not thus far),
+explicit cooperation from the compiler will be required to permit them
+to be safely used.
+
+That aside, each of the three RCU-protected pointer situations are
+described in the following sections.
Situation 1: Hash Tables
Situation 3: Resizeable Arrays
Use of RCU for resizeable arrays is demonstrated by the grow_ary()
-function used by the System V IPC code. The array is used to map from
-semaphore, message-queue, and shared-memory IDs to the data structure
-that represents the corresponding IPC construct. The grow_ary()
+function formerly used by the System V IPC code. The array is used
+to map from semaphore, message-queue, and shared-memory IDs to the data
+structure that represents the corresponding IPC construct. The grow_ary()
function does not acquire any locks; instead its caller must hold the
ids->sem semaphore.
Use explicit check expression "c" along with
srcu_read_lock_held()(). This is useful in code that
is invoked by both SRCU readers and updaters.
- rcu_dereference_index_check(p, c):
- Use explicit check expression "c", but the caller
- must supply one of the rcu_read_lock_held() functions.
- This is useful in code that uses RCU-protected arrays
- that is invoked by both RCU readers and updaters.
rcu_dereference_raw(p):
Don't check. (Use sparingly, if at all.)
rcu_dereference_protected(p, c):
but retain the compiler constraints that prevent duplicating
or coalescsing. This is useful when when testing the
value of the pointer itself, for example, against NULL.
- rcu_access_index(idx):
- Return the value of the index and omit all barriers, but
- retain the compiler constraints that prevent duplicating
- or coalescsing. This is useful when when testing the
- value of the index itself, for example, against -1.
The rcu_dereference_check() check expression can be any boolean
expression, but would normally include a lockdep expression. However,
for an example where the compiler can in fact deduce the exact
value of the pointer, and thus cause misordering.
-o Do not use single-element RCU-protected arrays. The compiler
- is within its right to assume that the value of an index into
- such an array must necessarily evaluate to zero. The compiler
- could then substitute the constant zero for the computation, so
- that the array index no longer depended on the value returned
- by rcu_dereference(). If the array index no longer depends
- on rcu_dereference(), then both the compiler and the CPU
- are within their rights to order the array access before the
- rcu_dereference(), which can cause the array access to return
- garbage.
-
o Avoid cancellation when using the "+" and "-" infix arithmetic
operators. For example, for a given variable "x", avoid
"(x-x)". There are similar arithmetic pitfalls from other
dereferencing. For example, the following (rather improbable)
code is buggy:
- int a[2];
- int index;
- int force_zero_index = 1;
+ int *p;
+ int *q;
...
- r1 = rcu_dereference(i1)
- r2 = a[r1 && force_zero_index]; /* BUGGY!!! */
+ p = rcu_dereference(gp)
+ q = &global_q;
+ q += p != &oom_p1 && p != &oom_p2;
+ r1 = *q; /* BUGGY!!! */
The reason this is buggy is that "&&" and "||" are often compiled
using branches. While weak-memory machines such as ARM or PowerPC
">", ">=", "<", or "<=") when dereferencing. For example,
the following (quite strange) code is buggy:
- int a[2];
- int index;
- int flip_index = 0;
+ int *p;
+ int *q;
...
- r1 = rcu_dereference(i1)
- r2 = a[r1 != flip_index]; /* BUGGY!!! */
+ p = rcu_dereference(gp)
+ q = &global_q;
+ q += p > &oom_p;
+ r1 = *q; /* BUGGY!!! */
As before, the reason this is buggy is that relational operators
are often compiled using branches. And as before, although
pointer. Note that the volatile cast in rcu_dereference()
will normally prevent the compiler from knowing too much.
+ However, please note that if the compiler knows that the
+ pointer takes on only one of two values, a not-equal
+ comparison will provide exactly the information that the
+ compiler needs to deduce the value of the pointer.
+
o Disable any value-speculation optimizations that your compiler
might provide, especially if you are making use of feedback-based
optimizations that take data collected from prior runs. Such
If you are going to be fetching multiple fields from the
RCU-protected structure, using the local variable is of
course preferred. Repeated rcu_dereference() calls look
- ugly and incur unnecessary overhead on Alpha CPUs.
+ ugly, do not guarantee that the same pointer will be returned
+ if an update happened while in the critical section, and incur
+ unnecessary overhead on Alpha CPUs.
Note that the value returned by rcu_dereference() is valid
only within the enclosing RCU read-side critical section.
All: lockdep-checked RCU-protected pointer access
- rcu_access_index
rcu_access_pointer
- rcu_dereference_index_check
rcu_dereference_raw
rcu_lockdep_assert
rcu_sleep_check
GPIO support
~~~~~~~~~~~~
ACPI 5 introduced two new resources to describe GPIO connections: GpioIo
-and GpioInt. These resources are used be used to pass GPIO numbers used by
+and GpioInt. These resources can be used to pass GPIO numbers used by
the device to the driver. ACPI 5.1 extended this with _DSD (Device
Specific Data) which made it possible to name the GPIOs among other things.
_DSD Device Properties Related to GPIO
--------------------------------------
-With the release of ACPI 5.1 and the _DSD configuration objecte names
-can finally be given to GPIOs (and other things as well) returned by
-_CRS. Previously, we were only able to use an integer index to find
+With the release of ACPI 5.1, the _DSD configuration object finally
+allows names to be given to GPIOs (and other things as well) returned
+by _CRS. Previously, we were only able to use an integer index to find
the corresponding GPIO, which is pretty error prone (it depends on
the _CRS output ordering, for example).
Export CPU topology info via sysfs. Items (attributes) are similar
-to /proc/cpuinfo.
+to /proc/cpuinfo output of some architectures:
1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
internal kernel map of cpuX's hardware threads within the same
- core as cpuX
+ core as cpuX.
-5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+
+ human-readable list of cpuX's hardware threads within the same
+ core as cpuX.
+
+6) /sys/devices/system/cpu/cpuX/topology/core_siblings:
internal kernel map of cpuX's hardware threads within the same
physical_package_id.
-6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+7) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+
+ human-readable list of cpuX's hardware threads within the same
+ physical_package_id.
+
+8) /sys/devices/system/cpu/cpuX/topology/book_siblings:
internal kernel map of cpuX's hardware threads within the same
book_id.
+9) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+
+ human-readable list of cpuX's hardware threads within the same
+ book_id.
+
To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+drivers/base/topology.c, is to export the 6 or 9 attributes. The three book
related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
For an architecture to support this feature, it must define some of
#define topology_physical_package_id(cpu)
#define topology_core_id(cpu)
#define topology_book_id(cpu)
-#define topology_thread_cpumask(cpu)
+#define topology_sibling_cpumask(cpu)
#define topology_core_cpumask(cpu)
#define topology_book_cpumask(cpu)
-The type of **_id is int.
-The type of siblings is (const) struct cpumask *.
+The type of **_id macros is int.
+The type of **_cpumask macros is (const) struct cpumask *. The latter
+correspond with appropriate **_siblings sysfs attributes (except for
+topology_sibling_cpumask() which corresponds with thread_siblings).
To be consistent on all architectures, include/linux/topology.h
provides default definitions for any of the above macros that are
not defined by include/asm-XXX/topology.h:
1) physical_package_id: -1
2) core_id: 0
-3) thread_siblings: just the given CPU
-4) core_siblings: just the given CPU
+3) sibling_cpumask: just the given CPU
+4) core_cpumask: just the given CPU
For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
default definitions for topology_book_id() and topology_book_cpumask().
--- /dev/null
+* ARMv7M System Timer
+
+ARMv7-M includes a system timer, known as SysTick. Current driver only
+implements the clocksource feature.
+
+Required properties:
+- compatible : Should be "arm,armv7m-systick"
+- reg : The address range of the timer
+
+Required clocking property, have to be one of:
+- clocks : The input clock of the timer
+- clock-frequency : The rate in HZ in input of the ARM SysTick
+
+Examples:
+
+systick: timer@e000e010 {
+ compatible = "arm,armv7m-systick";
+ reg = <0xe000e010 0x10>;
+ clocks = <&clk_systick>;
+};
+
+systick: timer@e000e010 {
+ compatible = "arm,armv7m-systick";
+ reg = <0xe000e010 0x10>;
+ clock-frequency = <90000000>;
+};
Required properties:
- compatible : Should be "ti,omap3-l3-smx" for OMAP3 family
Should be "ti,omap4-l3-noc" for OMAP4 family
+ Should be "ti,omap5-l3-noc" for OMAP5 family
Should be "ti,dra7-l3-noc" for DRA7 family
Should be "ti,am4372-l3-noc" for AM43 family
- reg: Contains L3 register address range for each noc domain.
- #address-cells : shall be 1 (reg is used to encode clk id).
- clocks : shall be the master clock phandle.
e.g. clocks = <&mck>;
-- name: device tree node describing a specific system clock.
+- name: device tree node describing a specific peripheral clock.
* #clock-cells : from common clock binding; shall be set to 0.
* reg: peripheral id. See Atmel's datasheets to get a full
list of peripheral ids.
- #clock-cells: from common clock binding; shall be set to 1.
- clocks: from common clock binding; list of parent clock
handles, shall be xtal reference clock or xtal and clkin for
- si5351c only.
+ si5351c only. Corresponding clock input names are "xtal" and
+ "clkin" respectively.
- #address-cells: shall be set to 1.
- #size-cells: shall be set to 0.
/* connect xtal input to 25MHz reference */
clocks = <&ref25>;
+ clock-names = "xtal";
/* connect xtal input as source of pll0 and pll1 */
silabs,pll-source = <0 0>, <1 0>;
80 81 68 69
70 71 72 73
74 75 76 77>;
- interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty",
+ interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty",
"saif0", "saif1", "i2c0", "i2c1",
"auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx",
"auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx";
touchscreen-fuzz-x = <4>;
touchscreen-fuzz-y = <7>;
touchscreen-fuzz-pressure = <2>;
- touchscreen-max-x = <4096>;
- touchscreen-max-y = <4096>;
+ touchscreen-size-x = <4096>;
+ touchscreen-size-y = <4096>;
touchscreen-max-pressure = <2048>;
ti,x-plate-ohms = <280>;
--- /dev/null
+* MTD SPI driver for ST M25Pxx (and similar) serial flash chips
+
+Required properties:
+- #address-cells, #size-cells : Must be present if the device has sub-nodes
+ representing partitions.
+- compatible : May include a device-specific string consisting of the
+ manufacturer and name of the chip. Bear in mind the DT binding
+ is not Linux-only, but in case of Linux, see the "m25p_ids"
+ table in drivers/mtd/devices/m25p80.c for the list of supported
+ chips.
+ Must also include "jedec,spi-nor" for any SPI NOR flash that can
+ be identified by the JEDEC READ ID opcode (0x9F).
+- reg : Chip-Select number
+- spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at
+
+Optional properties:
+- m25p,fast-read : Use the "fast read" opcode to read data from the chip instead
+ of the usual "read" opcode. This opcode is not supported by
+ all chips and support for it can not be detected at runtime.
+ Refer to your chips' datasheet to check if this is supported
+ by your chip.
+
+Example:
+
+ flash: m25p80@0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "spansion,m25p80", "jedec,spi-nor";
+ reg = <0>;
+ spi-max-frequency = <40000000>;
+ m25p,fast-read;
+ };
+++ /dev/null
-* MTD SPI driver for ST M25Pxx (and similar) serial flash chips
-
-Required properties:
-- #address-cells, #size-cells : Must be present if the device has sub-nodes
- representing partitions.
-- compatible : May include a device-specific string consisting of the
- manufacturer and name of the chip. Bear in mind the DT binding
- is not Linux-only, but in case of Linux, see the "m25p_ids"
- table in drivers/mtd/devices/m25p80.c for the list of supported
- chips.
- Must also include "nor-jedec" for any SPI NOR flash that can be
- identified by the JEDEC READ ID opcode (0x9F).
-- reg : Chip-Select number
-- spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at
-
-Optional properties:
-- m25p,fast-read : Use the "fast read" opcode to read data from the chip instead
- of the usual "read" opcode. This opcode is not supported by
- all chips and support for it can not be detected at runtime.
- Refer to your chips' datasheet to check if this is supported
- by your chip.
-
-Example:
-
- flash: m25p80@0 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "spansion,m25p80", "nor-jedec";
- reg = <0>;
- spi-max-frequency = <40000000>;
- m25p,fast-read;
- };
Required properties:
- compatible: Should be "cdns,[<chip>-]{emac}"
Use "cdns,at91rm9200-emac" Atmel at91rm9200 SoC.
- or the generic form: "cdns,emac".
+ Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC.
+ Or the generic form: "cdns,emac".
- reg: Address and length of the register set for the device
- interrupts: Should contain macb interrupt
- phy-mode: see ethernet.txt file in the same directory.
--- /dev/null
+* NXP LPC3220 timer
+
+The NXP LPC3220 timer is used on a wide range of NXP SoCs. This
+includes LPC32xx, LPC178x, LPC18xx and LPC43xx parts.
+
+Required properties:
+- compatible:
+ Should be "nxp,lpc3220-timer".
+- reg:
+ Address and length of the register set.
+- interrupts:
+ Reference to the timer interrupt
+- clocks:
+ Should contain a reference to timer clock.
+- clock-names:
+ Should contain "timerclk".
+
+Example:
+
+timer1: timer@40085000 {
+ compatible = "nxp,lpc3220-timer";
+ reg = <0x40085000 0x1000>;
+ interrupts = <13>;
+ clocks = <&ccu1 CLK_CPU_TIMER1>;
+ clock-names = "timerclk";
+};
--- /dev/null
+. STMicroelectronics STM32 timer
+
+The STM32 MCUs family has several general-purpose 16 and 32 bits timers.
+
+Required properties:
+- compatible : Should be "st,stm32-timer"
+- reg : Address and length of the register set
+- clocks : Reference on the timer input clock
+- interrupts : Reference to the timer interrupt
+
+Optional properties:
+- resets: Reference to a reset controller asserting the timer
+
+Example:
+
+timer5: timer@40000c00 {
+ compatible = "st,stm32-timer";
+ reg = <0x40000c00 0x400>;
+ interrupts = <50>;
+ resets = <&rrc 259>;
+ clocks = <&clk_pmtr1>;
+};
- phys: phandle + phy specifier pair
- phy-names: must be "usb"
- dmas: Must contain a list of references to DMA specifiers.
- - dma-names : Must contain a list of DMA names:
- - tx0 ... tx<n>
- - rx0 ... rx<n>
- - This <n> means DnFIFO in USBHS module.
+ - dma-names : named "ch%d", where %d is the channel number ranging from zero
+ to the number of channels (DnFIFOs) minus one.
Example:
usbhs: usb@e6590000 {
int (*rename2) (struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
int (*readlink) (struct dentry *, char __user *,int);
- void * (*follow_link) (struct dentry *, struct nameidata *);
- void (*put_link) (struct dentry *, struct nameidata *, void *);
+ const char *(*follow_link) (struct dentry *, void **);
+ void (*put_link) (struct inode *, void *);
void (*truncate) (struct inode *);
int (*permission) (struct inode *, int, unsigned int);
int (*get_acl)(struct inode *, int);
-Support is available for filesystems that wish to do automounting support (such
-as kAFS which can be found in fs/afs/). This facility includes allowing
-in-kernel mounts to be performed and mountpoint degradation to be
-requested. The latter can also be requested by userspace.
+Support is available for filesystems that wish to do automounting
+support (such as kAFS which can be found in fs/afs/ and NFS in
+fs/nfs/). This facility includes allowing in-kernel mounts to be
+performed and mountpoint degradation to be requested. The latter can
+also be requested by userspace.
======================
IN-KERNEL AUTOMOUNTING
======================
-A filesystem can now mount another filesystem on one of its directories by the
-following procedure:
-
- (1) Give the directory a follow_link() operation.
-
- When the directory is accessed, the follow_link op will be called, and
- it will be provided with the location of the mountpoint in the nameidata
- structure (vfsmount and dentry).
-
- (2) Have the follow_link() op do the following steps:
-
- (a) Call vfs_kern_mount() to call the appropriate filesystem to set up a
- superblock and gain a vfsmount structure representing it.
-
- (b) Copy the nameidata provided as an argument and substitute the dentry
- argument into it the copy.
-
- (c) Call do_add_mount() to install the new vfsmount into the namespace's
- mountpoint tree, thus making it accessible to userspace. Use the
- nameidata set up in (b) as the destination.
-
- If the mountpoint will be automatically expired, then do_add_mount()
- should also be given the location of an expiration list (see further
- down).
-
- (d) Release the path in the nameidata argument and substitute in the new
- vfsmount and its root dentry. The ref counts on these will need
- incrementing.
+See section "Mount Traps" of Documentation/filesystems/autofs4.txt
Then from userspace, you can just do something like:
===========================
Automatic expiration of mountpoints is easy, provided you've mounted the
-mountpoint to be expired in the automounting procedure outlined above.
+mountpoint to be expired in the automounting procedure outlined separately.
To do expiration, you need to follow these steps:
- (3) Create at least one list off which the vfsmounts to be expired can be
- hung. Access to this list will be governed by the vfsmount_lock.
+ (1) Create at least one list off which the vfsmounts to be expired can be
+ hung.
- (4) In step (2c) above, the call to do_add_mount() should be provided with a
- pointer to this list. It will hang the vfsmount off of it if it succeeds.
+ (2) When a new mountpoint is created in the ->d_automount method, add
+ the mnt to the list using mnt_set_expiry()
+ mnt_set_expiry(newmnt, &afs_vfsmounts);
- (5) When you want mountpoints to be expired, call mark_mounts_for_expiry()
+ (3) When you want mountpoints to be expired, call mark_mounts_for_expiry()
with a pointer to this list. This will process the list, marking every
vfsmount thereon for potential expiry on the next call.
--
[mandatory]
->aio_read/->aio_write are gone. Use ->read_iter/->write_iter.
+---
+[recommended]
+ for embedded ("fast") symlinks just set inode->i_link to wherever the
+ symlink body is and use simple_follow_link() as ->follow_link().
+--
+[mandatory]
+ calling conventions for ->follow_link() have changed. Instead of returning
+ cookie and using nd_set_link() to store the body to traverse, we return
+ the body to traverse and store the cookie using explicit void ** argument.
+ nameidata isn't passed at all - nd_jump_link() doesn't need it and
+ nd_[gs]et_link() is gone.
+--
+[mandatory]
+ calling conventions for ->put_link() have changed. It gets inode instead of
+ dentry, it does not get nameidata at all and it gets called only when cookie
+ is non-NULL. Note that link body isn't available anymore, so if you need it,
+ store it as cookie.
int (*rename2) (struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
int (*readlink) (struct dentry *, char __user *,int);
- void * (*follow_link) (struct dentry *, struct nameidata *);
- void (*put_link) (struct dentry *, struct nameidata *, void *);
+ const char *(*follow_link) (struct dentry *, void **);
+ void (*put_link) (struct inode *, void *);
int (*permission) (struct inode *, int);
int (*get_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
follow_link: called by the VFS to follow a symbolic link to the
inode it points to. Only required if you want to support
- symbolic links. This method returns a void pointer cookie
- that is passed to put_link().
+ symbolic links. This method returns the symlink body
+ to traverse (and possibly resets the current position with
+ nd_jump_link()). If the body won't go away until the inode
+ is gone, nothing else is needed; if it needs to be otherwise
+ pinned, the data needed to release whatever we'd grabbed
+ is to be stored in void * variable passed by address to
+ follow_link() instance.
put_link: called by the VFS to release resources allocated by
- follow_link(). The cookie returned by follow_link() is passed
- to this method as the last parameter. It is used by
- filesystems such as NFS where page cache is not stable
- (i.e. page that was installed when the symbolic link walk
- started might not be in the page cache at the end of the
- walk).
+ follow_link(). The cookie stored by follow_link() is passed
+ to this method as the last parameter; only called when
+ cookie isn't NULL.
permission: called by the VFS to check for access rights on a POSIX-like
filesystem.
Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp432.html
* Texas Instruments TMP435
Prefix: 'tmp435'
- Addresses scanned: I2C 0x37, 0x48 - 0x4f
+ Addresses scanned: I2C 0x48 - 0x4f
Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp435.html
Authors:
===========
I2C slave backends behave like standard I2C clients. So, you can instantiate
-them like described in the document 'instantiating-devices'. A quick example
-for instantiating the slave-eeprom driver from userspace:
+them as described in the document 'instantiating-devices'. A quick example for
+instantiating the slave-eeprom driver from userspace at address 0x64 on bus 1:
- # echo 0-0064 > /sys/bus/i2c/drivers/i2c-slave-eeprom/bind
+ # echo slave-24c02 0x64 > /sys/bus/i2c/devices/i2c-1/new_device
Each backend should come with separate documentation to describe its specific
behaviour and setup.
cpuidle.off=1 [CPU_IDLE]
disable the cpuidle sub-system
+ cpu_init_udelay=N
+ [X86] Delay for N microsec between assert and de-assert
+ of APIC INIT to start processors. This delay occurs
+ on every CPU online, such as boot, and resume from suspend.
+ Default: 10000
+
cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
Format:
<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
Enable debug messages at boot time. See
Documentation/dynamic-debug-howto.txt for details.
+ nompx [X86] Disables Intel Memory Protection Extensions.
+ See Documentation/x86/intel_mpx.txt for more
+ information about the feature.
+
eagerfpu= [X86]
on enable eager fpu restore
off disable eager fpu restore
By default, super page will be supported if Intel IOMMU
has the capability. With this option, super page will
not be supported.
+ ecs_off [Default Off]
+ By default, extended context tables will be supported if
+ the hardware advertises that it has support both for the
+ extended tables themselves, and also PASID support. With
+ this option set, extended tables will not be used even
+ on hardware which claims to support them.
intel_idle.max_cstate= [KNL,HW,ACPI,X86]
0 disables intel_idle and fall back on acpi_idle.
Set maximum number of finished RCU callbacks to
process in one batch.
+ rcutree.dump_tree= [KNL]
+ Dump the structure of the rcu_node combining tree
+ out at early boot. This is used for diagnostic
+ purposes, to verify correct tree setup.
+
+ rcutree.gp_cleanup_delay= [KNL]
+ Set the number of jiffies to delay each step of
+ RCU grace-period cleanup. This only has effect
+ when CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP is set.
+
rcutree.gp_init_delay= [KNL]
Set the number of jiffies to delay each step of
RCU grace-period initialization. This only has
- effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT is
- set.
+ effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+ is set.
+
+ rcutree.gp_preinit_delay= [KNL]
+ Set the number of jiffies to delay each step of
+ RCU grace-period pre-initialization, that is,
+ the propagation of recent CPU-hotplug changes up
+ the rcu_node combining tree. This only has effect
+ when CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is set.
+
+ rcutree.rcu_fanout_exact= [KNL]
+ Disable autobalancing of the rcu_node combining
+ tree. This is used by rcutorture, and might
+ possibly be useful for architectures having high
+ cache-to-cache transfer latencies.
rcutree.rcu_fanout_leaf= [KNL]
Increase the number of CPUs assigned to each
test, hence the "fake".
rcutorture.nreaders= [KNL]
- Set number of RCU readers.
+ Set number of RCU readers. The value -1 selects
+ N-1, where N is the number of CPUs. A value
+ "n" less than -1 selects N-n-2, where N is again
+ the number of CPUs. For example, -2 selects N
+ (the number of CPUs), -3 selects N+1, and so on.
rcutorture.object_debug= [KNL]
Enable debug-object double-call_rcu() testing.
However, stores are not speculated. This means that ordering -is- provided
for load-store control dependencies, as in the following example:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
if (q) {
ACCESS_ONCE(b) = p;
}
-Control dependencies pair normally with other types of barriers.
-That said, please note that ACCESS_ONCE() is not optional! Without the
-ACCESS_ONCE(), might combine the load from 'a' with other loads from
-'a', and the store to 'b' with other stores to 'b', with possible highly
-counterintuitive effects on ordering.
+Control dependencies pair normally with other types of barriers. That
+said, please note that READ_ONCE_CTRL() is not optional! Without the
+READ_ONCE_CTRL(), the compiler might combine the load from 'a' with
+other loads from 'a', and the store to 'b' with other stores to 'b',
+with possible highly counterintuitive effects on ordering.
Worse yet, if the compiler is able to prove (say) that the value of
variable 'a' is always non-zero, it would be well within its rights
q = a;
b = p; /* BUG: Compiler and CPU can both reorder!!! */
-So don't leave out the ACCESS_ONCE().
+Finally, the READ_ONCE_CTRL() includes an smp_read_barrier_depends()
+that DEC Alpha needs in order to respect control depedencies.
+
+So don't leave out the READ_ONCE_CTRL().
It is tempting to try to enforce ordering on identical stores on both
branches of the "if" statement as follows:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
if (q) {
barrier();
ACCESS_ONCE(b) = p;
Unfortunately, current compilers will transform this as follows at high
optimization levels:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
barrier();
ACCESS_ONCE(b) = p; /* BUG: No ordering vs. load from a!!! */
if (q) {
In contrast, without explicit memory barriers, two-legged-if control
ordering is guaranteed only when the stores differ, for example:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
if (q) {
ACCESS_ONCE(b) = p;
do_something();
do_something_else();
}
-The initial ACCESS_ONCE() is still required to prevent the compiler from
-proving the value of 'a'.
+The initial READ_ONCE_CTRL() is still required to prevent the compiler
+from proving the value of 'a'.
In addition, you need to be careful what you do with the local variable 'q',
otherwise the compiler might be able to guess the value and again remove
the needed conditional. For example:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
if (q % MAX) {
ACCESS_ONCE(b) = p;
do_something();
equal to zero, in which case the compiler is within its rights to
transform the above code into the following:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
ACCESS_ONCE(b) = p;
do_something_else();
relying on this ordering, you should make sure that MAX is greater than
one, perhaps as follows:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
if (q % MAX) {
ACCESS_ONCE(b) = p;
You must also be careful not to rely too much on boolean short-circuit
evaluation. Consider this example:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
if (a || 1 > 0)
ACCESS_ONCE(b) = 1;
-Because the second condition is always true, the compiler can transform
-this example as following, defeating control dependency:
+Because the first condition cannot fault and the second condition is
+always true, the compiler can transform this example as following,
+defeating control dependency:
- q = ACCESS_ONCE(a);
+ q = READ_ONCE_CTRL(a);
ACCESS_ONCE(b) = 1;
This example underscores the need to ensure that the compiler cannot
x and y both being zero:
CPU 0 CPU 1
- ===================== =====================
- r1 = ACCESS_ONCE(x); r2 = ACCESS_ONCE(y);
+ ======================= =======================
+ r1 = READ_ONCE_CTRL(x); r2 = READ_ONCE_CTRL(y);
if (r1 > 0) if (r2 > 0)
ACCESS_ONCE(y) = 1; ACCESS_ONCE(x) = 1;
assertion can fail after the combined three-CPU example completes. If you
need the three-CPU example to provide ordering, you will need smp_mb()
between the loads and stores in the CPU 0 and CPU 1 code fragments,
-that is, just before or just after the "if" statements.
+that is, just before or just after the "if" statements. Furthermore,
+the original two-CPU example is very fragile and should be avoided.
These two examples are the LB and WWC litmus tests from this paper:
http://www.cl.cam.ac.uk/users/pes20/ppc-supplemental/test6.pdf and this
In summary:
+ (*) Control dependencies must be headed by READ_ONCE_CTRL().
+ Or, as a much less preferable alternative, interpose
+ be headed by READ_ONCE() or an ACCESS_ONCE() read and must
+ have smp_read_barrier_depends() between this read and the
+ control-dependent write.
+
(*) Control dependencies can order prior loads against later stores.
However, they do -not- guarantee any other sort of ordering:
Not prior loads against later loads, nor prior stores against
There are some more advanced barrier functions:
- (*) set_mb(var, value)
+ (*) smp_store_mb(var, value)
This assigns the value to the variable and then inserts a full memory
barrier after it, depending on the function. It isn't guaranteed to
Memory operations issued before the ACQUIRE may be completed after
the ACQUIRE operation has completed. An smp_mb__before_spinlock(),
- combined with a following ACQUIRE, orders prior loads against
- subsequent loads and stores and also orders prior stores against
- subsequent stores. Note that this is weaker than smp_mb()! The
- smp_mb__before_spinlock() primitive is free on many architectures.
+ combined with a following ACQUIRE, orders prior stores against
+ subsequent loads and stores. Note that this is weaker than smp_mb()!
+ The smp_mb__before_spinlock() primitive is free on many architectures.
(2) RELEASE operation implication:
CPU 1
===============================
set_current_state();
- set_mb();
+ smp_store_mb();
STORE current->state
<general barrier>
LOAD event_indicated
CPU 1 CPU 2
=============================== ===============================
set_current_state(); STORE event_indicated
- set_mb(); wake_up();
+ smp_store_mb(); wake_up();
STORE current->state <write barrier>
<general barrier> STORE current->state
LOAD event_indicated
files/UDP-Lite-HOWTO.txt
o The Wireshark UDP-Lite WiKi (with capture files):
- http://wiki.wireshark.org/Lightweight_User_Datagram_Protocol
+ https://wiki.wireshark.org/Lightweight_User_Datagram_Protocol
o The Protocol Spec, RFC 3828, http://www.ietf.org/rfc/rfc3828.txt
Note, some FPU functions are already explicitly preempt safe. For example,
kernel_fpu_begin and kernel_fpu_end will disable and enable preemption.
-However, math_state_restore must be called with preemption disabled.
+However, fpu__restore() must be called with preemption disabled.
RULE #3: Lock acquire and release must be performed by same task
1. Overview
2. Scheduling algorithm
3. Scheduling Real-Time Tasks
+ 3.1 Definitions
+ 3.2 Schedulability Analysis for Uniprocessor Systems
+ 3.3 Schedulability Analysis for Multiprocessor Systems
+ 3.4 Relationship with SCHED_DEADLINE Parameters
4. Bandwidth management
4.1 System-wide settings
4.2 Task interface
"deadline", to schedule tasks. A SCHED_DEADLINE task should receive
"runtime" microseconds of execution time every "period" microseconds, and
these "runtime" microseconds are available within "deadline" microseconds
- from the beginning of the period. In order to implement this behaviour,
+ from the beginning of the period. In order to implement this behavior,
every time the task wakes up, the scheduler computes a "scheduling deadline"
consistent with the guarantee (using the CBS[2,3] algorithm). Tasks are then
scheduled using EDF[1] on these scheduling deadlines (the task with the
"admission control" strategy (see Section "4. Bandwidth management") is used
(clearly, if the system is overloaded this guarantee cannot be respected).
- Summing up, the CBS[2,3] algorithms assigns scheduling deadlines to tasks so
+ Summing up, the CBS[2,3] algorithm assigns scheduling deadlines to tasks so
that each task runs for at most its runtime every period, avoiding any
interference between different tasks (bandwidth isolation), while the EDF[1]
algorithm selects the task with the earliest scheduling deadline as the one
In more details, the CBS algorithm assigns scheduling deadlines to
tasks in the following way:
- - Each SCHED_DEADLINE task is characterised by the "runtime",
+ - Each SCHED_DEADLINE task is characterized by the "runtime",
"deadline", and "period" parameters;
- The state of the task is described by a "scheduling deadline", and
then, if the scheduling deadline is smaller than the current time, or
this condition is verified, the scheduling deadline and the
- remaining runtime are re-initialised as
+ remaining runtime are re-initialized as
scheduling deadline = current time + deadline
remaining runtime = runtime
suited for periodic or sporadic real-time tasks that need guarantees on their
timing behavior, e.g., multimedia, streaming, control applications, etc.
+3.1 Definitions
+------------------------
+
A typical real-time task is composed of a repetition of computation phases
(task instances, or jobs) which are activated on a periodic or sporadic
fashion.
- Each job J_j (where J_j is the j^th job of the task) is characterised by an
+ Each job J_j (where J_j is the j^th job of the task) is characterized by an
arrival time r_j (the time when the job starts), an amount of computation
time c_j needed to finish the job, and a job absolute deadline d_j, which
is the time within which the job should be finished. The maximum execution
- time max_j{c_j} is called "Worst Case Execution Time" (WCET) for the task.
+ time max{c_j} is called "Worst Case Execution Time" (WCET) for the task.
A real-time task can be periodic with period P if r_{j+1} = r_j + P, or
sporadic with minimum inter-arrival time P is r_{j+1} >= r_j + P. Finally,
d_j = r_j + D, where D is the task's relative deadline.
- The utilisation of a real-time task is defined as the ratio between its
+ Summing up, a real-time task can be described as
+ Task = (WCET, D, P)
+
+ The utilization of a real-time task is defined as the ratio between its
WCET and its period (or minimum inter-arrival time), and represents
the fraction of CPU time needed to execute the task.
- If the total utilisation sum_i(WCET_i/P_i) is larger than M (with M equal
+ If the total utilization U=sum(WCET_i/P_i) is larger than M (with M equal
to the number of CPUs), then the scheduler is unable to respect all the
deadlines.
- Note that total utilisation is defined as the sum of the utilisations
+ Note that total utilization is defined as the sum of the utilizations
WCET_i/P_i over all the real-time tasks in the system. When considering
multiple real-time tasks, the parameters of the i-th task are indicated
with the "_i" suffix.
- Moreover, if the total utilisation is larger than M, then we risk starving
+ Moreover, if the total utilization is larger than M, then we risk starving
non- real-time tasks by real-time tasks.
- If, instead, the total utilisation is smaller than M, then non real-time
+ If, instead, the total utilization is smaller than M, then non real-time
tasks will not be starved and the system might be able to respect all the
deadlines.
As a matter of fact, in this case it is possible to provide an upper bound
More precisely, it can be proven that using a global EDF scheduler the
maximum tardiness of each task is smaller or equal than
((M − 1) · WCET_max − WCET_min)/(M − (M − 2) · U_max) + WCET_max
- where WCET_max = max_i{WCET_i} is the maximum WCET, WCET_min=min_i{WCET_i}
- is the minimum WCET, and U_max = max_i{WCET_i/P_i} is the maximum utilisation.
+ where WCET_max = max{WCET_i} is the maximum WCET, WCET_min=min{WCET_i}
+ is the minimum WCET, and U_max = max{WCET_i/P_i} is the maximum
+ utilization[12].
+
+3.2 Schedulability Analysis for Uniprocessor Systems
+------------------------
If M=1 (uniprocessor system), or in case of partitioned scheduling (each
real-time task is statically assigned to one and only one CPU), it is
possible to formally check if all the deadlines are respected.
If D_i = P_i for all tasks, then EDF is able to respect all the deadlines
- of all the tasks executing on a CPU if and only if the total utilisation
+ of all the tasks executing on a CPU if and only if the total utilization
of the tasks running on such a CPU is smaller or equal than 1.
If D_i != P_i for some task, then it is possible to define the density of
- a task as C_i/min{D_i,T_i}, and EDF is able to respect all the deadlines
- of all the tasks running on a CPU if the sum sum_i C_i/min{D_i,T_i} of the
- densities of the tasks running on such a CPU is smaller or equal than 1
- (notice that this condition is only sufficient, and not necessary).
+ a task as WCET_i/min{D_i,P_i}, and EDF is able to respect all the deadlines
+ of all the tasks running on a CPU if the sum of the densities of the tasks
+ running on such a CPU is smaller or equal than 1:
+ sum(WCET_i / min{D_i, P_i}) <= 1
+ It is important to notice that this condition is only sufficient, and not
+ necessary: there are task sets that are schedulable, but do not respect the
+ condition. For example, consider the task set {Task_1,Task_2} composed by
+ Task_1=(50ms,50ms,100ms) and Task_2=(10ms,100ms,100ms).
+ EDF is clearly able to schedule the two tasks without missing any deadline
+ (Task_1 is scheduled as soon as it is released, and finishes just in time
+ to respect its deadline; Task_2 is scheduled immediately after Task_1, hence
+ its response time cannot be larger than 50ms + 10ms = 60ms) even if
+ 50 / min{50,100} + 10 / min{100, 100} = 50 / 50 + 10 / 100 = 1.1
+ Of course it is possible to test the exact schedulability of tasks with
+ D_i != P_i (checking a condition that is both sufficient and necessary),
+ but this cannot be done by comparing the total utilization or density with
+ a constant. Instead, the so called "processor demand" approach can be used,
+ computing the total amount of CPU time h(t) needed by all the tasks to
+ respect all of their deadlines in a time interval of size t, and comparing
+ such a time with the interval size t. If h(t) is smaller than t (that is,
+ the amount of time needed by the tasks in a time interval of size t is
+ smaller than the size of the interval) for all the possible values of t, then
+ EDF is able to schedule the tasks respecting all of their deadlines. Since
+ performing this check for all possible values of t is impossible, it has been
+ proven[4,5,6] that it is sufficient to perform the test for values of t
+ between 0 and a maximum value L. The cited papers contain all of the
+ mathematical details and explain how to compute h(t) and L.
+ In any case, this kind of analysis is too complex as well as too
+ time-consuming to be performed on-line. Hence, as explained in Section
+ 4 Linux uses an admission test based on the tasks' utilizations.
+
+3.3 Schedulability Analysis for Multiprocessor Systems
+------------------------
On multiprocessor systems with global EDF scheduling (non partitioned
systems), a sufficient test for schedulability can not be based on the
- utilisations (it can be shown that task sets with utilisations slightly
- larger than 1 can miss deadlines regardless of the number of CPUs M).
- However, as previously stated, enforcing that the total utilisation is smaller
- than M is enough to guarantee that non real-time tasks are not starved and
- that the tardiness of real-time tasks has an upper bound.
+ utilizations or densities: it can be shown that even if D_i = P_i task
+ sets with utilizations slightly larger than 1 can miss deadlines regardless
+ of the number of CPUs.
+
+ Consider a set {Task_1,...Task_{M+1}} of M+1 tasks on a system with M
+ CPUs, with the first task Task_1=(P,P,P) having period, relative deadline
+ and WCET equal to P. The remaining M tasks Task_i=(e,P-1,P-1) have an
+ arbitrarily small worst case execution time (indicated as "e" here) and a
+ period smaller than the one of the first task. Hence, if all the tasks
+ activate at the same time t, global EDF schedules these M tasks first
+ (because their absolute deadlines are equal to t + P - 1, hence they are
+ smaller than the absolute deadline of Task_1, which is t + P). As a
+ result, Task_1 can be scheduled only at time t + e, and will finish at
+ time t + e + P, after its absolute deadline. The total utilization of the
+ task set is U = M · e / (P - 1) + P / P = M · e / (P - 1) + 1, and for small
+ values of e this can become very close to 1. This is known as "Dhall's
+ effect"[7]. Note: the example in the original paper by Dhall has been
+ slightly simplified here (for example, Dhall more correctly computed
+ lim_{e->0}U).
+
+ More complex schedulability tests for global EDF have been developed in
+ real-time literature[8,9], but they are not based on a simple comparison
+ between total utilization (or density) and a fixed constant. If all tasks
+ have D_i = P_i, a sufficient schedulability condition can be expressed in
+ a simple way:
+ sum(WCET_i / P_i) <= M - (M - 1) · U_max
+ where U_max = max{WCET_i / P_i}[10]. Notice that for U_max = 1,
+ M - (M - 1) · U_max becomes M - M + 1 = 1 and this schedulability condition
+ just confirms the Dhall's effect. A more complete survey of the literature
+ about schedulability tests for multi-processor real-time scheduling can be
+ found in [11].
+
+ As seen, enforcing that the total utilization is smaller than M does not
+ guarantee that global EDF schedules the tasks without missing any deadline
+ (in other words, global EDF is not an optimal scheduling algorithm). However,
+ a total utilization smaller than M is enough to guarantee that non real-time
+ tasks are not starved and that the tardiness of real-time tasks has an upper
+ bound[12] (as previously noted). Different bounds on the maximum tardiness
+ experienced by real-time tasks have been developed in various papers[13,14],
+ but the theoretical result that is important for SCHED_DEADLINE is that if
+ the total utilization is smaller or equal than M then the response times of
+ the tasks are limited.
+
+3.4 Relationship with SCHED_DEADLINE Parameters
+------------------------
- SCHED_DEADLINE can be used to schedule real-time tasks guaranteeing that
- the jobs' deadlines of a task are respected. In order to do this, a task
- must be scheduled by setting:
+ Finally, it is important to understand the relationship between the
+ SCHED_DEADLINE scheduling parameters described in Section 2 (runtime,
+ deadline and period) and the real-time task parameters (WCET, D, P)
+ described in this section. Note that the tasks' temporal constraints are
+ represented by its absolute deadlines d_j = r_j + D described above, while
+ SCHED_DEADLINE schedules the tasks according to scheduling deadlines (see
+ Section 2).
+ If an admission test is used to guarantee that the scheduling deadlines
+ are respected, then SCHED_DEADLINE can be used to schedule real-time tasks
+ guaranteeing that all the jobs' deadlines of a task are respected.
+ In order to do this, a task must be scheduled by setting:
- runtime >= WCET
- deadline = D
- period <= P
- IOW, if runtime >= WCET and if period is >= P, then the scheduling deadlines
+ IOW, if runtime >= WCET and if period is <= P, then the scheduling deadlines
and the absolute deadlines (d_j) coincide, so a proper admission control
allows to respect the jobs' absolute deadlines for this task (this is what is
called "hard schedulability property" and is an extension of Lemma 1 of [2]).
Symposium, 1998. http://retis.sssup.it/~giorgio/paps/1998/rtss98-cbs.pdf
3 - L. Abeni. Server Mechanisms for Multimedia Applications. ReTiS Lab
Technical Report. http://disi.unitn.it/~abeni/tr-98-01.pdf
+ 4 - J. Y. Leung and M.L. Merril. A Note on Preemptive Scheduling of
+ Periodic, Real-Time Tasks. Information Processing Letters, vol. 11,
+ no. 3, pp. 115-118, 1980.
+ 5 - S. K. Baruah, A. K. Mok and L. E. Rosier. Preemptively Scheduling
+ Hard-Real-Time Sporadic Tasks on One Processor. Proceedings of the
+ 11th IEEE Real-time Systems Symposium, 1990.
+ 6 - S. K. Baruah, L. E. Rosier and R. R. Howell. Algorithms and Complexity
+ Concerning the Preemptive Scheduling of Periodic Real-Time tasks on
+ One Processor. Real-Time Systems Journal, vol. 4, no. 2, pp 301-324,
+ 1990.
+ 7 - S. J. Dhall and C. L. Liu. On a real-time scheduling problem. Operations
+ research, vol. 26, no. 1, pp 127-140, 1978.
+ 8 - T. Baker. Multiprocessor EDF and Deadline Monotonic Schedulability
+ Analysis. Proceedings of the 24th IEEE Real-Time Systems Symposium, 2003.
+ 9 - T. Baker. An Analysis of EDF Schedulability on a Multiprocessor.
+ IEEE Transactions on Parallel and Distributed Systems, vol. 16, no. 8,
+ pp 760-768, 2005.
+ 10 - J. Goossens, S. Funk and S. Baruah, Priority-Driven Scheduling of
+ Periodic Task Systems on Multiprocessors. Real-Time Systems Journal,
+ vol. 25, no. 2–3, pp. 187–205, 2003.
+ 11 - R. Davis and A. Burns. A Survey of Hard Real-Time Scheduling for
+ Multiprocessor Systems. ACM Computing Surveys, vol. 43, no. 4, 2011.
+ http://www-users.cs.york.ac.uk/~robdavis/papers/MPSurveyv5.0.pdf
+ 12 - U. C. Devi and J. H. Anderson. Tardiness Bounds under Global EDF
+ Scheduling on a Multiprocessor. Real-Time Systems Journal, vol. 32,
+ no. 2, pp 133-189, 2008.
+ 13 - P. Valente and G. Lipari. An Upper Bound to the Lateness of Soft
+ Real-Time Tasks Scheduled by EDF on Multiprocessors. Proceedings of
+ the 26th IEEE Real-Time Systems Symposium, 2005.
+ 14 - J. Erickson, U. Devi and S. Baruah. Improved tardiness bounds for
+ Global EDF. Proceedings of the 22nd Euromicro Conference on
+ Real-Time Systems, 2010.
+
4. Bandwidth management
=======================
no guarantee can be given on the actual scheduling of the -deadline tasks.
As already stated in Section 3, a necessary condition to be respected to
- correctly schedule a set of real-time tasks is that the total utilisation
+ correctly schedule a set of real-time tasks is that the total utilization
is smaller than M. When talking about -deadline tasks, this requires that
the sum of the ratio between runtime and period for all tasks is smaller
- than M. Notice that the ratio runtime/period is equivalent to the utilisation
+ than M. Notice that the ratio runtime/period is equivalent to the utilization
of a "traditional" real-time task, and is also often referred to as
"bandwidth".
The interface used to control the CPU bandwidth that can be allocated
The system wide settings are configured under the /proc virtual file system.
For now the -rt knobs are used for -deadline admission control and the
- -deadline runtime is accounted against the -rt runtime. We realise that this
+ -deadline runtime is accounted against the -rt runtime. We realize that this
isn't entirely desirable; however, it is better to have a small interface for
now, and be able to change it easily later. The ideal situation (see 5.) is to
run -rt tasks from a -deadline server; in which case the -rt bandwidth is a
TTY_OTHER_CLOSED Device is a pty and the other side has closed.
+TTY_OTHER_DONE Device is a pty and the other side has closed and
+ all pending input processing has been completed.
+
TTY_NO_WRITE_SPLIT Prevent driver from splitting up writes into
smaller chunks.
a) Discovering and configuring TCMU uio devices
b) Waiting for events on the device(s)
c) Managing the command ring
-3) Command filtering and pass_level
-4) A final note
+3) A final note
TCM Userspace Design
/* Process events from cmd ring until we catch up with cmd_head */
while (ent != (void *)mb + mb->cmdr_off + mb->cmd_head) {
- if (tcmu_hdr_get_op(&ent->hdr) == TCMU_OP_CMD) {
+ if (tcmu_hdr_get_op(ent->hdr.len_op) == TCMU_OP_CMD) {
uint8_t *cdb = (void *)mb + ent->req.cdb_off;
bool success = true;
ent->rsp.scsi_status = SCSI_CHECK_CONDITION;
}
}
+ else if (tcmu_hdr_get_op(ent->hdr.len_op) != TCMU_OP_PAD) {
+ /* Tell the kernel we didn't handle unknown opcodes */
+ ent->hdr.uflags |= TCMU_UFLAG_UNKNOWN_OP;
+ }
else {
- /* Do nothing for PAD entries */
+ /* Do nothing for PAD entries except update cmd_tail */
}
/* update cmd_tail */
}
-Command filtering and pass_level
---------------------------------
-
-TCMU supports a "pass_level" option with valid values of 0 or 1. When
-the value is 0 (the default), nearly all SCSI commands received for
-the device are passed through to the handler. This allows maximum
-flexibility but increases the amount of code required by the handler,
-to support all mandatory SCSI commands. If pass_level is set to 1,
-then only IO-related commands are presented, and the rest are handled
-by LIO's in-kernel command emulation. The commands presented at level
-1 include all versions of:
-
-READ
-WRITE
-WRITE_VERIFY
-XDWRITEREAD
-WRITE_SAME
-COMPARE_AND_WRITE
-SYNCHRONIZE_CACHE
-UNMAP
-
-
A final note
------------
Contains the value of cr4.smep && !cr0.wp for which the page is valid
(pages for which this is true are different from other pages; see the
treatment of cr0.wp=0 below).
+ role.smap_andnot_wp:
+ Contains the value of cr4.smap && !cr0.wp for which the page is valid
+ (pages for which this is true are different from other pages; see the
+ treatment of cr0.wp=0 below).
gfn:
Either the guest page table containing the translations shadowed by this
page, or the base page frame for linear translations. See role.direct.
(user write faults generate a #PF)
-In the first case there is an additional complication if CR4.SMEP is
-enabled: since we've turned the page into a kernel page, the kernel may now
-execute it. We handle this by also setting spte.nx. If we get a user
-fetch or read fault, we'll change spte.u=1 and spte.nx=gpte.nx back.
+In the first case there are two additional complications:
+- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
+ the kernel may now execute it. We handle this by also setting spte.nx.
+ If we get a user fetch or read fault, we'll change spte.u=1 and
+ spte.nx=gpte.nx back.
+- if CR4.SMAP is disabled: since the page has been changed to a kernel
+ page, it can not be reused when CR4.SMAP is enabled. We set
+ CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
+ here we do not care the case that CR4.SMAP is enabled since KVM will
+ directly inject #PF to guest due to failed permission check.
To prevent an spte that was converted into a kernel page with cr0.wp=0
from being written by the kernel after cr0.wp has changed to 1, we make
o hdr.code32_start
o hdr.cmd_line_ptr
- o hdr.cmdline_size
o hdr.ramdisk_image (if applicable)
o hdr.ramdisk_size (if applicable)
- system_call: syscall instruction from 64-bit code.
- - ia32_syscall: int 0x80 from 32-bit or 64-bit code; compat syscall
+ - entry_INT80_compat: int 0x80 from 32-bit or 64-bit code; compat syscall
either way.
- - ia32_syscall, ia32_sysenter: syscall and sysenter from 32-bit
+ - entry_INT80_compat, ia32_sysenter: syscall and sysenter from 32-bit
code
- interrupt: An array of entries. Every IDT vector that doesn't
--- /dev/null
+Kernel stacks on x86-64 bit
+---------------------------
+
+Most of the text from Keith Owens, hacked by AK
+
+x86_64 page size (PAGE_SIZE) is 4K.
+
+Like all other architectures, x86_64 has a kernel stack for every
+active thread. These thread stacks are THREAD_SIZE (2*PAGE_SIZE) big.
+These stacks contain useful data as long as a thread is alive or a
+zombie. While the thread is in user space the kernel stack is empty
+except for the thread_info structure at the bottom.
+
+In addition to the per thread stacks, there are specialized stacks
+associated with each CPU. These stacks are only used while the kernel
+is in control on that CPU; when a CPU returns to user space the
+specialized stacks contain no useful data. The main CPU stacks are:
+
+* Interrupt stack. IRQSTACKSIZE
+
+ Used for external hardware interrupts. If this is the first external
+ hardware interrupt (i.e. not a nested hardware interrupt) then the
+ kernel switches from the current task to the interrupt stack. Like
+ the split thread and interrupt stacks on i386, this gives more room
+ for kernel interrupt processing without having to increase the size
+ of every per thread stack.
+
+ The interrupt stack is also used when processing a softirq.
+
+Switching to the kernel interrupt stack is done by software based on a
+per CPU interrupt nest counter. This is needed because x86-64 "IST"
+hardware stacks cannot nest without races.
+
+x86_64 also has a feature which is not available on i386, the ability
+to automatically switch to a new stack for designated events such as
+double fault or NMI, which makes it easier to handle these unusual
+events on x86_64. This feature is called the Interrupt Stack Table
+(IST). There can be up to 7 IST entries per CPU. The IST code is an
+index into the Task State Segment (TSS). The IST entries in the TSS
+point to dedicated stacks; each stack can be a different size.
+
+An IST is selected by a non-zero value in the IST field of an
+interrupt-gate descriptor. When an interrupt occurs and the hardware
+loads such a descriptor, the hardware automatically sets the new stack
+pointer based on the IST value, then invokes the interrupt handler. If
+the interrupt came from user mode, then the interrupt handler prologue
+will switch back to the per-thread stack. If software wants to allow
+nested IST interrupts then the handler must adjust the IST values on
+entry to and exit from the interrupt handler. (This is occasionally
+done, e.g. for debug exceptions.)
+
+Events with different IST codes (i.e. with different stacks) can be
+nested. For example, a debug interrupt can safely be interrupted by an
+NMI. arch/x86_64/kernel/entry.S::paranoidentry adjusts the stack
+pointers on entry to and exit from all IST events, in theory allowing
+IST events with the same code to be nested. However in most cases, the
+stack size allocated to an IST assumes no nesting for the same code.
+If that assumption is ever broken then the stacks will become corrupt.
+
+The currently assigned IST stacks are :-
+
+* DOUBLEFAULT_STACK. EXCEPTION_STKSZ (PAGE_SIZE).
+
+ Used for interrupt 8 - Double Fault Exception (#DF).
+
+ Invoked when handling one exception causes another exception. Happens
+ when the kernel is very confused (e.g. kernel stack pointer corrupt).
+ Using a separate stack allows the kernel to recover from it well enough
+ in many cases to still output an oops.
+
+* NMI_STACK. EXCEPTION_STKSZ (PAGE_SIZE).
+
+ Used for non-maskable interrupts (NMI).
+
+ NMI can be delivered at any time, including when the kernel is in the
+ middle of switching stacks. Using IST for NMI events avoids making
+ assumptions about the previous state of the kernel stack.
+
+* DEBUG_STACK. DEBUG_STKSZ
+
+ Used for hardware debug interrupts (interrupt 1) and for software
+ debug interrupts (INT3).
+
+ When debugging a kernel, debug interrupts (both hardware and
+ software) can occur at any time. Using IST for these interrupts
+ avoids making assumptions about the previous state of the kernel
+ stack.
+
+* MCE_STACK. EXCEPTION_STKSZ (PAGE_SIZE).
+
+ Used for interrupt 18 - Machine Check Exception (#MC).
+
+ MCE can be delivered at any time, including when the kernel is in the
+ middle of switching stacks. Using IST for MCE events avoids making
+ assumptions about the previous state of the kernel stack.
+
+For more details see the Intel IA32 or AMD AMD64 architecture manuals.
+
+
+Printing backtraces on x86
+--------------------------
+
+The question about the '?' preceding function names in an x86 stacktrace
+keeps popping up, here's an indepth explanation. It helps if the reader
+stares at print_context_stack() and the whole machinery in and around
+arch/x86/kernel/dumpstack.c.
+
+Adapted from Ingo's mail, Message-ID: <20150521101614.GA10889@gmail.com>:
+
+We always scan the full kernel stack for return addresses stored on
+the kernel stack(s) [*], from stack top to stack bottom, and print out
+anything that 'looks like' a kernel text address.
+
+If it fits into the frame pointer chain, we print it without a question
+mark, knowing that it's part of the real backtrace.
+
+If the address does not fit into our expected frame pointer chain we
+still print it, but we print a '?'. It can mean two things:
+
+ - either the address is not part of the call chain: it's just stale
+ values on the kernel stack, from earlier function calls. This is
+ the common case.
+
+ - or it is part of the call chain, but the frame pointer was not set
+ up properly within the function, so we don't recognize it.
+
+This way we will always print out the real call chain (plus a few more
+entries), regardless of whether the frame pointer was set up correctly
+or not - but in most cases we'll get the call chain right as well. The
+entries printed are strictly in stack order, so you can deduce more
+information from that as well.
+
+The most important property of this method is that we _never_ lose
+information: we always strive to print _all_ addresses on the stack(s)
+that look like kernel text addresses, so if debug information is wrong,
+we still print out the real call chain as well - just with more question
+marks than ideal.
+
+[*] For things like IRQ and IST stacks, we also scan those stacks, in
+ the right order, and try to cross from one stack into another
+ reconstructing the call chain. This works most of the time.
MTRR (Memory Type Range Register) control
-3 Jun 1999
-Richard Gooch
-<rgooch@atnf.csiro.au>
+
+Richard Gooch <rgooch@atnf.csiro.au> - 3 Jun 1999
+Luis R. Rodriguez <mcgrof@do-not-panic.com> - April 9, 2015
+
+===============================================================================
+Phasing out MTRR use
+
+MTRR use is replaced on modern x86 hardware with PAT. Over time the only type
+of effective MTRR that is expected to be supported will be for write-combining.
+As MTRR use is phased out device drivers should use arch_phys_wc_add() to make
+MTRR effective on non-PAT systems while a no-op on PAT enabled systems.
+
+For details refer to Documentation/x86/pat.txt.
+
+===============================================================================
On Intel P6 family processors (Pentium Pro, Pentium II and later)
the Memory Type Range Registers (MTRRs) may be used to control
PAT allows for different types of memory attributes. The most commonly used
ones that will be supported at this time are Write-back, Uncached,
-Write-combined and Uncached Minus.
+Write-combined, Write-through and Uncached Minus.
PAT APIs
| | | |
ioremap_cache | -- | WB | WB |
| | | |
+ioremap_uc | -- | UC | UC |
+ | | | |
ioremap_nocache | -- | UC- | UC- |
| | | |
ioremap_wc | -- | -- | WC |
| | | |
+ioremap_wt | -- | -- | WT |
+ | | | |
set_memory_uc | UC- | -- | -- |
set_memory_wb | | | |
| | | |
set_memory_wc | WC | -- | -- |
set_memory_wb | | | |
| | | |
+set_memory_wt | WT | -- | -- |
+ set_memory_wb | | | |
+ | | | |
pci sysfs resource | -- | -- | UC- |
| | | |
pci sysfs resource_wc | -- | -- | WC |
as step 0 above and also track the usage of those pages and use set_memory_wb()
before the page is freed to free pool.
-
+MTRR effects on PAT / non-PAT systems
+-------------------------------------
+
+The following table provides the effects of using write-combining MTRRs when
+using ioremap*() calls on x86 for both non-PAT and PAT systems. Ideally
+mtrr_add() usage will be phased out in favor of arch_phys_wc_add() which will
+be a no-op on PAT enabled systems. The region over which a arch_phys_wc_add()
+is made, should already have been ioremapped with WC attributes or PAT entries,
+this can be done by using ioremap_wc() / set_memory_wc(). Devices which
+combine areas of IO memory desired to remain uncacheable with areas where
+write-combining is desirable should consider use of ioremap_uc() followed by
+set_memory_wc() to white-list effective write-combined areas. Such use is
+nevertheless discouraged as the effective memory type is considered
+implementation defined, yet this strategy can be used as last resort on devices
+with size-constrained regions where otherwise MTRR write-combining would
+otherwise not be effective.
+
+----------------------------------------------------------------------
+MTRR Non-PAT PAT Linux ioremap value Effective memory type
+----------------------------------------------------------------------
+ Non-PAT | PAT
+ PAT
+ |PCD
+ ||PWT
+ |||
+WC 000 WB _PAGE_CACHE_MODE_WB WC | WC
+WC 001 WC _PAGE_CACHE_MODE_WC WC* | WC
+WC 010 UC- _PAGE_CACHE_MODE_UC_MINUS WC* | UC
+WC 011 UC _PAGE_CACHE_MODE_UC UC | UC
+----------------------------------------------------------------------
+
+(*) denotes implementation defined and is discouraged
Notes:
For example: If there is an existing uncached mapping, a new ioremap_wc can
return uncached mapping in place of write-combine requested.
-set_memory_[uc|wc] and set_memory_wb should be used in pairs, where driver will
-first make a region uc or wc and switch it back to wb after use.
+set_memory_[uc|wc|wt] and set_memory_wb should be used in pairs, where driver
+will first make a region uc, wc or wt and switch it back to wb after use.
Over time writes to /proc/mtrr will be deprecated in favor of using PAT based
interfaces. Users writing to /proc/mtrr are suggested to use above interfaces.
Drivers should use ioremap_[uc|wc] to access PCI BARs with [uc|wc] access
types.
-Drivers should use set_memory_[uc|wc] to set access type for RAM ranges.
+Drivers should use set_memory_[uc|wc|wt] to set access type for RAM ranges.
PAT debugging
(e.g. BIOS or hardware monitoring applications), conflicting
with OS's error handling, and you cannot deactivate the agent,
then this option will be a help.
+ mce=no_lmce
+ Do not opt-in to Local MCE delivery. Use legacy method
+ to broadcast MCEs.
mce=bootlog
Enable logging of machine checks left over from booting.
Disabled by default on AMD because some BIOS leave bogus ones.
+++ /dev/null
-Most of the text from Keith Owens, hacked by AK
-
-x86_64 page size (PAGE_SIZE) is 4K.
-
-Like all other architectures, x86_64 has a kernel stack for every
-active thread. These thread stacks are THREAD_SIZE (2*PAGE_SIZE) big.
-These stacks contain useful data as long as a thread is alive or a
-zombie. While the thread is in user space the kernel stack is empty
-except for the thread_info structure at the bottom.
-
-In addition to the per thread stacks, there are specialized stacks
-associated with each CPU. These stacks are only used while the kernel
-is in control on that CPU; when a CPU returns to user space the
-specialized stacks contain no useful data. The main CPU stacks are:
-
-* Interrupt stack. IRQSTACKSIZE
-
- Used for external hardware interrupts. If this is the first external
- hardware interrupt (i.e. not a nested hardware interrupt) then the
- kernel switches from the current task to the interrupt stack. Like
- the split thread and interrupt stacks on i386, this gives more room
- for kernel interrupt processing without having to increase the size
- of every per thread stack.
-
- The interrupt stack is also used when processing a softirq.
-
-Switching to the kernel interrupt stack is done by software based on a
-per CPU interrupt nest counter. This is needed because x86-64 "IST"
-hardware stacks cannot nest without races.
-
-x86_64 also has a feature which is not available on i386, the ability
-to automatically switch to a new stack for designated events such as
-double fault or NMI, which makes it easier to handle these unusual
-events on x86_64. This feature is called the Interrupt Stack Table
-(IST). There can be up to 7 IST entries per CPU. The IST code is an
-index into the Task State Segment (TSS). The IST entries in the TSS
-point to dedicated stacks; each stack can be a different size.
-
-An IST is selected by a non-zero value in the IST field of an
-interrupt-gate descriptor. When an interrupt occurs and the hardware
-loads such a descriptor, the hardware automatically sets the new stack
-pointer based on the IST value, then invokes the interrupt handler. If
-the interrupt came from user mode, then the interrupt handler prologue
-will switch back to the per-thread stack. If software wants to allow
-nested IST interrupts then the handler must adjust the IST values on
-entry to and exit from the interrupt handler. (This is occasionally
-done, e.g. for debug exceptions.)
-
-Events with different IST codes (i.e. with different stacks) can be
-nested. For example, a debug interrupt can safely be interrupted by an
-NMI. arch/x86_64/kernel/entry.S::paranoidentry adjusts the stack
-pointers on entry to and exit from all IST events, in theory allowing
-IST events with the same code to be nested. However in most cases, the
-stack size allocated to an IST assumes no nesting for the same code.
-If that assumption is ever broken then the stacks will become corrupt.
-
-The currently assigned IST stacks are :-
-
-* STACKFAULT_STACK. EXCEPTION_STKSZ (PAGE_SIZE).
-
- Used for interrupt 12 - Stack Fault Exception (#SS).
-
- This allows the CPU to recover from invalid stack segments. Rarely
- happens.
-
-* DOUBLEFAULT_STACK. EXCEPTION_STKSZ (PAGE_SIZE).
-
- Used for interrupt 8 - Double Fault Exception (#DF).
-
- Invoked when handling one exception causes another exception. Happens
- when the kernel is very confused (e.g. kernel stack pointer corrupt).
- Using a separate stack allows the kernel to recover from it well enough
- in many cases to still output an oops.
-
-* NMI_STACK. EXCEPTION_STKSZ (PAGE_SIZE).
-
- Used for non-maskable interrupts (NMI).
-
- NMI can be delivered at any time, including when the kernel is in the
- middle of switching stacks. Using IST for NMI events avoids making
- assumptions about the previous state of the kernel stack.
-
-* DEBUG_STACK. DEBUG_STKSZ
-
- Used for hardware debug interrupts (interrupt 1) and for software
- debug interrupts (INT3).
-
- When debugging a kernel, debug interrupts (both hardware and
- software) can occur at any time. Using IST for these interrupts
- avoids making assumptions about the previous state of the kernel
- stack.
-
-* MCE_STACK. EXCEPTION_STKSZ (PAGE_SIZE).
-
- Used for interrupt 18 - Machine Check Exception (#MC).
-
- MCE can be delivered at any time, including when the kernel is in the
- middle of switching stacks. Using IST for MCE events avoids making
- assumptions about the previous state of the kernel stack.
-
-For more details see the Intel IA32 or AMD AMD64 architecture manuals.
# Kbuild for top-level directory of the kernel
# This file takes care of the following:
# 1) Generate bounds.h
-# 2) Generate asm-offsets.h (may need bounds.h)
-# 3) Check for missing system calls
+# 2) Generate timeconst.h
+# 3) Generate asm-offsets.h (may need bounds.h and timeconst.h)
+# 4) Check for missing system calls
# Default sed regexp - multiline due to syntax constraints
define sed-y
$(call filechk,offsets,__LINUX_BOUNDS_H__)
#####
-# 2) Generate asm-offsets.h
+# 2) Generate timeconst.h
+
+timeconst-file := include/generated/timeconst.h
+
+#always += $(timeconst-file)
+targets += $(timeconst-file)
+
+quiet_cmd_gentimeconst = GEN $@
+define cmd_gentimeconst
+ (echo $(CONFIG_HZ) | bc -q $< ) > $@
+endef
+define filechk_gentimeconst
+ (echo $(CONFIG_HZ) | bc -q $< )
+endef
+
+$(obj)/$(timeconst-file): kernel/time/timeconst.bc FORCE
+ $(call filechk,gentimeconst)
+
+#####
+# 3) Generate asm-offsets.h
#
offsets-file := include/generated/asm-offsets.h
# We use internal kbuild rules to avoid the "is up to date" message from make
arch/$(SRCARCH)/kernel/asm-offsets.s: arch/$(SRCARCH)/kernel/asm-offsets.c \
- $(obj)/$(bounds-file) FORCE
+ $(obj)/$(timeconst-file) $(obj)/$(bounds-file) FORCE
$(Q)mkdir -p $(dir $@)
$(call if_changed_dep,cc_s_c)
$(call filechk,offsets,__ASM_OFFSETS_H__)
#####
-# 3) Check for missing system calls
+# 4) Check for missing system calls
#
always += missing-syscalls
missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE
$(call cmd,syscalls)
-# Keep these two files during make clean
-no-clean-files := $(bounds-file) $(offsets-file)
+# Keep these three files during make clean
+no-clean-files := $(bounds-file) $(offsets-file) $(timeconst-file)
or does something very odd once a month document it.
PLEASE remember that submissions must be made under the terms
- of the OSDL certificate of contribution and should include a
- Signed-off-by: line. The current version of this "Developer's
- Certificate of Origin" (DCO) is listed in the file
+ of the Linux Foundation certificate of contribution and should
+ include a Signed-off-by: line. The current version of this
+ "Developer's Certificate of Origin" (DCO) is listed in the file
Documentation/SubmittingPatches.
6. Make sure you have the right to send any changes you make. If you
F: arch/arm/mach-alpine/
ARM/ATMEL AT91RM9200 AND AT91SAM ARM ARCHITECTURES
-M: Andrew Victor <linux@maxim.org.za>
M: Nicolas Ferre <nicolas.ferre@atmel.com>
+M: Alexandre Belloni <alexandre.belloni@free-electrons.com>
M: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W: http://maxim.org.za/at91_26.html
W: http://www.linux4sam.org
S: Supported
F: arch/arm/mach-at91/
ARM/CORTINA SYSTEMS GEMINI ARM ARCHITECTURE
M: Hans Ulli Kroll <ulli.kroll@googlemail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-T: git git://git.berlios.de/gemini-board
+T: git git://github.com/ulli-kroll/linux.git
S: Maintained
F: arch/arm/mach-gemini/
F: drivers/clocksource/timer-atlas7.c
N: [^a-z]sirf
+ARM/CONEXANT DIGICOLOR MACHINE SUPPORT
+M: Baruch Siach <baruch@tkos.co.il>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+N: digicolor
+
ARM/EBSA110 MACHINE SUPPORT
M: Russell King <linux@arm.linux.org.uk>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
M: Philipp Zabel <philipp.zabel@gmail.com>
S: Maintained
-ARM/Marvell Armada 370 and Armada XP SOC support
+ARM/Marvell Kirkwood and Armada 370, 375, 38x, XP SOC support
M: Jason Cooper <jason@lakedaemon.net>
M: Andrew Lunn <andrew@lunn.ch>
M: Gregory Clement <gregory.clement@free-electrons.com>
S: Maintained
F: arch/arm/mach-mvebu/
F: drivers/rtc/rtc-armada38x.c
+F: arch/arm/boot/dts/armada*
+F: arch/arm/boot/dts/kirkwood*
+
ARM/Marvell Berlin SoC support
M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-berlin/
+F: arch/arm/boot/dts/berlin*
+
ARM/Marvell Dove/MV78xx0/Orion SOC support
M: Jason Cooper <jason@lakedaemon.net>
F: arch/arm/mach-mv78xx0/
F: arch/arm/mach-orion5x/
F: arch/arm/plat-orion/
+F: arch/arm/boot/dts/dove*
+F: arch/arm/boot/dts/orion5x*
+
ARM/Orion SoC/Technologic Systems TS-78xx platform support
M: Alexander Clouter <alex@digriz.org.uk>
ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
M: Kukjin Kim <kgene@kernel.org>
+M: Krzysztof Kozlowski <k.kozlowski@samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
S: Maintained
M: Dinh Nguyen <dinguyen@opensource.altera.com>
S: Maintained
F: arch/arm/mach-socfpga/
+F: arch/arm/boot/dts/socfpga*
+F: arch/arm/configs/socfpga_defconfig
W: http://www.rocketboards.org
-T: git://git.rocketboards.org/linux-socfpga.git
-T: git://git.rocketboards.org/linux-socfpga-next.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git
ARM/SOCFPGA CLOCK FRAMEWORK SUPPORT
M: Dinh Nguyen <dinguyen@opensource.altera.com>
F: drivers/net/wireless/b43legacy/
BACKLIGHT CLASS/SUBSYSTEM
-M: Jingoo Han <jg1.han@samsung.com>
+M: Jingoo Han <jingoohan1@gmail.com>
M: Lee Jones <lee.jones@linaro.org>
S: Maintained
F: drivers/video/backlight/
F: drivers/net/ethernet/broadcom/bnx2x/
BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE
-M: Christian Daudt <bcm@fixthebug.org>
M: Florian Fainelli <f.fainelli@gmail.com>
+M: Ray Jui <rjui@broadcom.com>
+M: Scott Branden <sbranden@broadcom.com>
L: bcm-kernel-feedback-list@broadcom.com
T: git git://github.com/broadcom/mach-bcm
S: Maintained
F: drivers/usb/gadget/udc/bcm63xx_udc.*
BROADCOM BCM7XXX ARM ARCHITECTURE
-M: Marc Carino <marc.ceeeee@gmail.com>
M: Brian Norris <computersforpeace@gmail.com>
M: Gregory Fong <gregory.0xf0@gmail.com>
M: Florian Fainelli <f.fainelli@gmail.com>
S: Supported
F: include/linux/capability.h
F: include/uapi/linux/capability.h
-F: security/capability.c
F: security/commoncap.c
F: kernel/capability.c
L: linux-embedded@vger.kernel.org
S: Maintained
-EMULEX LPFC FC SCSI DRIVER
-M: James Smart <james.smart@emulex.com>
+EMULEX/AVAGO LPFC FC/FCOE SCSI DRIVER
+M: James Smart <james.smart@avagotech.com>
+M: Dick Kennedy <dick.kennedy@avagotech.com>
L: linux-scsi@vger.kernel.org
-W: http://sourceforge.net/projects/lpfcxxxx
+W: http://www.avagotech.com
S: Supported
F: drivers/scsi/lpfc/
F: Documentation/extcon/
EXYNOS DP DRIVER
-M: Jingoo Han <jg1.han@samsung.com>
+M: Jingoo Han <jingoohan1@gmail.com>
L: dri-devel@lists.freedesktop.org
S: Maintained
F: drivers/gpu/drm/exynos/exynos_dp*
F: include/uapi/linux/gfs2_ondisk.h
GIGASET ISDN DRIVERS
-M: Hansjoerg Lipp <hjlipp@web.de>
-M: Tilman Schmidt <tilman@imap.cc>
+M: Paul Bolle <pebolle@tiscali.nl>
L: gigaset307x-common@lists.sourceforge.net
W: http://gigaset307x.sourceforge.net/
-S: Maintained
+S: Odd Fixes
F: Documentation/isdn/README.gigaset
F: drivers/isdn/gigaset/
F: include/uapi/linux/gigaset_dev.h
M: Guenter Roeck <linux@roeck-us.net>
L: lm-sensors@lm-sensors.org
W: http://www.lm-sensors.org/
-T: quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/
+T: quilt http://jdelvare.nerim.net/devel/linux/jdelvare-hwmon/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
S: Maintained
F: Documentation/hwmon/
F: drivers/video/fbdev/imsttfb.c
INFINIBAND SUBSYSTEM
-M: Roland Dreier <roland@kernel.org>
+M: Doug Ledford <dledford@redhat.com>
M: Sean Hefty <sean.hefty@intel.com>
M: Hal Rosenstock <hal.rosenstock@gmail.com>
L: linux-rdma@vger.kernel.org
W: http://www.openfabrics.org/
Q: http://patchwork.kernel.org/project/linux-rdma/list/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma.git
S: Supported
F: Documentation/infiniband/
F: drivers/infiniband/
F: include/uapi/linux/if_infiniband.h
+F: include/uapi/rdma/
+F: include/rdma/
INOTIFY
M: John McCutchan <john@johnmccutchan.com>
S: Maintained
F: arch/nios2/
+NOKIA N900 POWER SUPPLY DRIVERS
+M: Pali Rohár <pali.rohar@gmail.com>
+S: Maintained
+F: include/linux/power/bq2415x_charger.h
+F: include/linux/power/bq27x00_battery.h
+F: include/linux/power/isp1704_charger.h
+F: drivers/power/bq2415x_charger.c
+F: drivers/power/bq27x00_battery.c
+F: drivers/power/isp1704_charger.c
+F: drivers/power/rx51_battery.c
+
NTB DRIVER
M: Jon Mason <jdmason@kudzu.us>
M: Dave Jiang <dave.jiang@intel.com>
F: drivers/pci/host/*rcar*
PCI DRIVER FOR SAMSUNG EXYNOS
-M: Jingoo Han <jg1.han@samsung.com>
+M: Jingoo Han <jingoohan1@gmail.com>
L: linux-pci@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
F: drivers/pci/host/pci-exynos.c
PCI DRIVER FOR SYNOPSIS DESIGNWARE
-M: Jingoo Han <jg1.han@samsung.com>
+M: Jingoo Han <jingoohan1@gmail.com>
+M: Pratyush Anand <pratyush.anand@gmail.com>
L: linux-pci@vger.kernel.org
S: Maintained
F: drivers/pci/host/*designware*
F: drivers/pci/host/pci-host-generic.c
PCIE DRIVER FOR ST SPEAR13XX
+M: Pratyush Anand <pratyush.anand@gmail.com>
L: linux-pci@vger.kernel.org
-S: Orphan
+S: Maintained
F: drivers/pci/host/*spear*
PCMCIA SUBSYSTEM
PERFORMANCE EVENTS SUBSYSTEM
M: Peter Zijlstra <a.p.zijlstra@chello.nl>
-M: Paul Mackerras <paulus@samba.org>
M: Ingo Molnar <mingo@redhat.com>
M: Arnaldo Carvalho de Melo <acme@kernel.org>
L: linux-kernel@vger.kernel.org
F: sound/soc/samsung/
SAMSUNG FRAMEBUFFER DRIVER
-M: Jingoo Han <jg1.han@samsung.com>
+M: Jingoo Han <jingoohan1@gmail.com>
L: linux-fbdev@vger.kernel.org
S: Maintained
F: drivers/video/fbdev/s3c-fb.c
F: include/uapi/linux/phantom.h
SERVER ENGINES 10Gbps iSCSI - BladeEngine 2 DRIVER
-M: Jayamohan Kallickal <jayamohan.kallickal@emulex.com>
+M: Jayamohan Kallickal <jayamohan.kallickal@avagotech.com>
+M: Minh Tran <minh.tran@avagotech.com>
+M: John Soni Jose <sony.john-n@avagotech.com>
L: linux-scsi@vger.kernel.org
-W: http://www.emulex.com
+W: http://www.avagotech.com
S: Supported
F: drivers/scsi/be2iscsi/
-SERVER ENGINES 10Gbps NIC - BladeEngine 2 DRIVER
-M: Sathya Perla <sathya.perla@emulex.com>
-M: Subbu Seetharaman <subbu.seetharaman@emulex.com>
-M: Ajit Khaparde <ajit.khaparde@emulex.com>
+Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER
+M: Sathya Perla <sathya.perla@avagotech.com>
+M: Ajit Khaparde <ajit.khaparde@avagotech.com>
+M: Padmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
+M: Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
L: netdev@vger.kernel.org
W: http://www.emulex.com
S: Supported
F: include/uapi/linux/virtio_input.h
VIA RHINE NETWORK DRIVER
-M: Roger Luethi <rl@hellgate.ch>
-S: Maintained
+S: Orphan
F: drivers/net/ethernet/via/via-rhine.c
VIA SD/MMC CARD CONTROLLER DRIVER
L: linux-kernel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
S: Maintained
-F: arch/x86/vdso/
+F: arch/x86/entry/vdso/
XC2028/3028 TUNER DRIVER
M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
VERSION = 4
PATCHLEVEL = 1
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION =
NAME = Hurr durr I'ma sheep
# *DOCUMENTATION*
export srctree objtree VPATH
-
# SUBARCH tells the usermode build what the underlying arch is. That is set
# first, and if a usermode build is happening, the "ARCH=um" on the command
# line overrides the setting of ARCH below. If a native build is happening,
# Clear a bunch of variables before executing the submake
tools/: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/
tools/%: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/ $*
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/ $*
# Single targets
# ---------------------------------------------------------------------------
tools/bootpzh bootloader bootpheader bootpzheader
OBJSTRIP := $(obj)/tools/objstrip
+HOSTCFLAGS := -Wall -I$(objtree)/usr/include
+BOOTCFLAGS += -I$(obj) -I$(srctree)/$(obj)
+
# SRM bootable image. Copy to offset 512 of a partition.
$(obj)/bootimage: $(addprefix $(obj)/tools/,mkbb lxboot bootlx) $(obj)/vmlinux.nh
( cat $(obj)/tools/lxboot $(obj)/tools/bootlx $(obj)/vmlinux.nh ) > $@
$(obj)/tools/bootpzh: $(obj)/bootpzheader $(OBJSTRIP) FORCE
$(call if_changed,objstrip)
-LDFLAGS_bootloader := -static -uvsprintf -T #-N -relax
-LDFLAGS_bootpheader := -static -uvsprintf -T #-N -relax
-LDFLAGS_bootpzheader := -static -uvsprintf -T #-N -relax
+LDFLAGS_bootloader := -static -T # -N -relax
+LDFLAGS_bootloader := -static -T # -N -relax
+LDFLAGS_bootpheader := -static -T # -N -relax
+LDFLAGS_bootpzheader := -static -T # -N -relax
-OBJ_bootlx := $(obj)/head.o $(obj)/main.o
-OBJ_bootph := $(obj)/head.o $(obj)/bootp.o
-OBJ_bootpzh := $(obj)/head.o $(obj)/bootpz.o $(obj)/misc.o
+OBJ_bootlx := $(obj)/head.o $(obj)/stdio.o $(obj)/main.o
+OBJ_bootph := $(obj)/head.o $(obj)/stdio.o $(obj)/bootp.o
+OBJ_bootpzh := $(obj)/head.o $(obj)/stdio.o $(obj)/bootpz.o $(obj)/misc.o
$(obj)/bootloader: $(obj)/bootloader.lds $(OBJ_bootlx) $(LIBS_Y) FORCE
$(call if_changed,ld)
#include "ksize.h"
-extern int vsprintf(char *, const char *, va_list);
extern unsigned long switch_to_osf_pal(unsigned long nr,
struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa,
unsigned long *vptb);
--- /dev/null
+/*
+ * Copyright (C) Paul Mackerras 1997.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <stdarg.h>
+#include <stddef.h>
+
+size_t strnlen(const char * s, size_t count)
+{
+ const char *sc;
+
+ for (sc = s; count-- && *sc != '\0'; ++sc)
+ /* nothing */;
+ return sc - s;
+}
+
+# define do_div(n, base) ({ \
+ unsigned int __base = (base); \
+ unsigned int __rem; \
+ __rem = ((unsigned long long)(n)) % __base; \
+ (n) = ((unsigned long long)(n)) / __base; \
+ __rem; \
+})
+
+
+static int skip_atoi(const char **s)
+{
+ int i, c;
+
+ for (i = 0; '0' <= (c = **s) && c <= '9'; ++*s)
+ i = i*10 + c - '0';
+ return i;
+}
+
+#define ZEROPAD 1 /* pad with zero */
+#define SIGN 2 /* unsigned/signed long */
+#define PLUS 4 /* show plus */
+#define SPACE 8 /* space if plus */
+#define LEFT 16 /* left justified */
+#define SPECIAL 32 /* 0x */
+#define LARGE 64 /* use 'ABCDEF' instead of 'abcdef' */
+
+static char * number(char * str, unsigned long long num, int base, int size, int precision, int type)
+{
+ char c,sign,tmp[66];
+ const char *digits="0123456789abcdefghijklmnopqrstuvwxyz";
+ int i;
+
+ if (type & LARGE)
+ digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+ if (type & LEFT)
+ type &= ~ZEROPAD;
+ if (base < 2 || base > 36)
+ return 0;
+ c = (type & ZEROPAD) ? '0' : ' ';
+ sign = 0;
+ if (type & SIGN) {
+ if ((signed long long)num < 0) {
+ sign = '-';
+ num = - (signed long long)num;
+ size--;
+ } else if (type & PLUS) {
+ sign = '+';
+ size--;
+ } else if (type & SPACE) {
+ sign = ' ';
+ size--;
+ }
+ }
+ if (type & SPECIAL) {
+ if (base == 16)
+ size -= 2;
+ else if (base == 8)
+ size--;
+ }
+ i = 0;
+ if (num == 0)
+ tmp[i++]='0';
+ else while (num != 0) {
+ tmp[i++] = digits[do_div(num, base)];
+ }
+ if (i > precision)
+ precision = i;
+ size -= precision;
+ if (!(type&(ZEROPAD+LEFT)))
+ while(size-->0)
+ *str++ = ' ';
+ if (sign)
+ *str++ = sign;
+ if (type & SPECIAL) {
+ if (base==8)
+ *str++ = '0';
+ else if (base==16) {
+ *str++ = '0';
+ *str++ = digits[33];
+ }
+ }
+ if (!(type & LEFT))
+ while (size-- > 0)
+ *str++ = c;
+ while (i < precision--)
+ *str++ = '0';
+ while (i-- > 0)
+ *str++ = tmp[i];
+ while (size-- > 0)
+ *str++ = ' ';
+ return str;
+}
+
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+ int len;
+ unsigned long long num;
+ int i, base;
+ char * str;
+ const char *s;
+
+ int flags; /* flags to number() */
+
+ int field_width; /* width of output field */
+ int precision; /* min. # of digits for integers; max
+ number of chars for from string */
+ int qualifier; /* 'h', 'l', or 'L' for integer fields */
+ /* 'z' support added 23/7/1999 S.H. */
+ /* 'z' changed to 'Z' --davidm 1/25/99 */
+
+
+ for (str=buf ; *fmt ; ++fmt) {
+ if (*fmt != '%') {
+ *str++ = *fmt;
+ continue;
+ }
+
+ /* process flags */
+ flags = 0;
+ repeat:
+ ++fmt; /* this also skips first '%' */
+ switch (*fmt) {
+ case '-': flags |= LEFT; goto repeat;
+ case '+': flags |= PLUS; goto repeat;
+ case ' ': flags |= SPACE; goto repeat;
+ case '#': flags |= SPECIAL; goto repeat;
+ case '0': flags |= ZEROPAD; goto repeat;
+ }
+
+ /* get field width */
+ field_width = -1;
+ if ('0' <= *fmt && *fmt <= '9')
+ field_width = skip_atoi(&fmt);
+ else if (*fmt == '*') {
+ ++fmt;
+ /* it's the next argument */
+ field_width = va_arg(args, int);
+ if (field_width < 0) {
+ field_width = -field_width;
+ flags |= LEFT;
+ }
+ }
+
+ /* get the precision */
+ precision = -1;
+ if (*fmt == '.') {
+ ++fmt;
+ if ('0' <= *fmt && *fmt <= '9')
+ precision = skip_atoi(&fmt);
+ else if (*fmt == '*') {
+ ++fmt;
+ /* it's the next argument */
+ precision = va_arg(args, int);
+ }
+ if (precision < 0)
+ precision = 0;
+ }
+
+ /* get the conversion qualifier */
+ qualifier = -1;
+ if (*fmt == 'l' && *(fmt + 1) == 'l') {
+ qualifier = 'q';
+ fmt += 2;
+ } else if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L'
+ || *fmt == 'Z') {
+ qualifier = *fmt;
+ ++fmt;
+ }
+
+ /* default base */
+ base = 10;
+
+ switch (*fmt) {
+ case 'c':
+ if (!(flags & LEFT))
+ while (--field_width > 0)
+ *str++ = ' ';
+ *str++ = (unsigned char) va_arg(args, int);
+ while (--field_width > 0)
+ *str++ = ' ';
+ continue;
+
+ case 's':
+ s = va_arg(args, char *);
+ if (!s)
+ s = "<NULL>";
+
+ len = strnlen(s, precision);
+
+ if (!(flags & LEFT))
+ while (len < field_width--)
+ *str++ = ' ';
+ for (i = 0; i < len; ++i)
+ *str++ = *s++;
+ while (len < field_width--)
+ *str++ = ' ';
+ continue;
+
+ case 'p':
+ if (field_width == -1) {
+ field_width = 2*sizeof(void *);
+ flags |= ZEROPAD;
+ }
+ str = number(str,
+ (unsigned long) va_arg(args, void *), 16,
+ field_width, precision, flags);
+ continue;
+
+
+ case 'n':
+ if (qualifier == 'l') {
+ long * ip = va_arg(args, long *);
+ *ip = (str - buf);
+ } else if (qualifier == 'Z') {
+ size_t * ip = va_arg(args, size_t *);
+ *ip = (str - buf);
+ } else {
+ int * ip = va_arg(args, int *);
+ *ip = (str - buf);
+ }
+ continue;
+
+ case '%':
+ *str++ = '%';
+ continue;
+
+ /* integer number formats - set up the flags and "break" */
+ case 'o':
+ base = 8;
+ break;
+
+ case 'X':
+ flags |= LARGE;
+ case 'x':
+ base = 16;
+ break;
+
+ case 'd':
+ case 'i':
+ flags |= SIGN;
+ case 'u':
+ break;
+
+ default:
+ *str++ = '%';
+ if (*fmt)
+ *str++ = *fmt;
+ else
+ --fmt;
+ continue;
+ }
+ if (qualifier == 'l') {
+ num = va_arg(args, unsigned long);
+ if (flags & SIGN)
+ num = (signed long) num;
+ } else if (qualifier == 'q') {
+ num = va_arg(args, unsigned long long);
+ if (flags & SIGN)
+ num = (signed long long) num;
+ } else if (qualifier == 'Z') {
+ num = va_arg(args, size_t);
+ } else if (qualifier == 'h') {
+ num = (unsigned short) va_arg(args, int);
+ if (flags & SIGN)
+ num = (signed short) num;
+ } else {
+ num = va_arg(args, unsigned int);
+ if (flags & SIGN)
+ num = (signed int) num;
+ }
+ str = number(str, num, base, field_width, precision, flags);
+ }
+ *str = '\0';
+ return str-buf;
+}
+
+int sprintf(char * buf, const char *fmt, ...)
+{
+ va_list args;
+ int i;
+
+ va_start(args, fmt);
+ i=vsprintf(buf,fmt,args);
+ va_end(args);
+ return i;
+}
#include <linux/param.h>
#ifdef __ELF__
# include <linux/elf.h>
+# define elfhdr elf64_hdr
+# define elf_phdr elf64_phdr
+# define elf_check_arch(x) ((x)->e_machine == EM_ALPHA)
#endif
/* bootfile size must be multiple of BLOCK_SIZE: */
#undef __ASM__MB
#undef ____cmpxchg
-#define __HAVE_ARCH_CMPXCHG 1
-
#endif /* _ALPHA_CMPXCHG_H */
#define _ALPHA_TYPES_H
#include <asm-generic/int-ll64.h>
-#include <uapi/asm/types.h>
#endif /* _ALPHA_TYPES_H */
#include <uapi/asm/unistd.h>
-#define NR_SYSCALLS 511
+#define NR_SYSCALLS 514
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_STAT64
#define __NR_sched_setattr 508
#define __NR_sched_getattr 509
#define __NR_renameat2 510
+#define __NR_getrandom 511
+#define __NR_memfd_create 512
+#define __NR_execveat 513
#endif /* _UAPI_ALPHA_UNISTD_H */
* Error handling code supporting Alpha systems
*/
-#include <linux/init.h>
#include <linux/sched.h>
#include <asm/io.h>
#include <linux/ptrace.h>
#include <linux/interrupt.h>
#include <linux/random.h>
-#include <linux/init.h>
#include <linux/irq.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
if (tv) {
if (get_tv32((struct timeval *)&kts, tv))
return -EFAULT;
+ kts.tv_nsec *= 1000;
}
if (tz) {
if (copy_from_user(&ktz, tz, sizeof(*tz)))
return -EFAULT;
}
- kts.tv_nsec *= 1000;
-
return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
}
}
/*
- * Copy an alpha thread..
+ * Copy architecture-specific thread state
*/
-
int
copy_thread(unsigned long clone_flags, unsigned long usp,
- unsigned long arg,
+ unsigned long kthread_arg,
struct task_struct *p)
{
extern void ret_from_fork(void);
sizeof(struct switch_stack) + sizeof(struct pt_regs));
childstack->r26 = (unsigned long) ret_from_kernel_thread;
childstack->r9 = usp; /* function */
- childstack->r10 = arg;
+ childstack->r10 = kthread_arg;
childregs->hae = alpha_mv.hae_cache,
childti->pcb.usp = 0;
return 0;
enum ipi_message_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
- IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
};
return -EINVAL;
}
-\f
static void
send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
{
generic_smp_call_function_interrupt();
break;
- case IPI_CALL_FUNC_SINGLE:
- generic_smp_call_function_single_interrupt();
- break;
-
case IPI_CPU_STOP:
halt();
void arch_send_call_function_single_ipi(int cpu)
{
- send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+ send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
}
static void
return -ENODEV;
}
-
-module_init(srmcons_init);
+device_initcall(srmcons_init);
\f
/*
pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &intline);
irq = intline;
- msi_loc = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ msi_loc = dev->msi_cap;
msg_ctl = 0;
if (msi_loc)
pci_read_config_word(dev, msi_loc + PCI_MSI_FLAGS, &msg_ctl);
.quad sys_sched_setattr
.quad sys_sched_getattr
.quad sys_renameat2 /* 510 */
+ .quad sys_getrandom
+ .quad sys_memfd_create
+ .quad sys_execveat
.size sys_call_table, . - sys_call_table
.type sys_call_table, @object
#include <linux/tty.h>
#include <linux/delay.h>
#include <linux/module.h>
-#include <linux/init.h>
#include <linux/kallsyms.h>
#include <linux/ratelimit.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/module.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
/* If we're in an interrupt context, or have no user context,
we must not take the fault. */
- if (!mm || in_atomic())
+ if (!mm || faulthandler_disabled())
goto no_context;
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
*/
#include <linux/oprofile.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/ptrace.h>
source "lib/Kconfig.debug"
-config EARLY_PRINTK
- bool "Early printk" if EMBEDDED
- default y
- help
- Write kernel log output directly into the VGA buffer or to a serial
- port.
-
- This is useful for kernel debugging when your machine crashes very
- early before the console code is initialized. For normal operation
- it is not recommended because it looks ugly and doesn't cooperate
- with klogd/syslogd or the X server. You should normally N here,
- unless you want to debug such a crash.
-
config 16KSTACKS
bool "Use 16Kb for kernel stacks instead of 8Kb"
help
atomic_ops_unlock(flags); \
}
-#define ATOMIC_OP_RETURN(op, c_op) \
+#define ATOMIC_OP_RETURN(op, c_op, asm_op) \
static inline int atomic_##op##_return(int i, atomic_t *v) \
{ \
unsigned long flags; \
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
+ pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
ret = -ENOSYS;
}
- pagefault_enable(); /* subsumes preempt_enable() */
+ pagefault_enable();
if (!ret) {
switch (cmp) {
return ret;
}
-/* Compare-xchg with preemption disabled.
+/* Compare-xchg with pagefaults disabled.
* Notes:
* -Best-Effort: Exchg happens only if compare succeeds.
* If compare fails, returns; leaving retry/looping to upper layers
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
+ pagefault_disable();
/* TBD : can use llock/scond */
__asm__ __volatile__(
: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
: "cc", "memory");
- pagefault_enable(); /* subsumes preempt_enable() */
+ pagefault_enable();
*uval = val;
return val;
#define ioremap_nocache(phy, sz) ioremap(phy, sz)
#define ioremap_wc(phy, sz) ioremap(phy, sz)
+#define ioremap_wt(phy, sz) ioremap(phy, sz)
/* Change struct page to physical address */
#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)
* Machine specific helpers for Entire D-Cache or Per Line ops
*/
-static unsigned int __before_dc_op(const int op)
+static inline unsigned int __before_dc_op(const int op)
{
unsigned int reg = reg;
return reg;
}
-static void __after_dc_op(const int op, unsigned int reg)
+static inline void __after_dc_op(const int op, unsigned int reg)
{
if (op & OP_FLUSH) /* flush / flush-n-inv both wait */
while (read_aux_reg(ARC_REG_DC_CTRL) & DC_CTRL_FLUSH_STATUS);
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \
imx25-karo-tx25.dtb \
imx25-pdk.dtb
-dtb-$(CONFIG_SOC_IMX31) += \
+dtb-$(CONFIG_SOC_IMX27) += \
imx27-apf27.dtb \
imx27-apf27dev.dtb \
imx27-eukrea-mbimxsd27-baseboard.dtb \
/include/ "tps65217.dtsi"
&tps {
+ /*
+ * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only
+ * mode") at poweroff. Most BeagleBone versions do not support RTC-only
+ * mode and risk hardware damage if this mode is entered.
+ *
+ * For details, see linux-omap mailing list May 2015 thread
+ * [PATCH] ARM: dts: am335x-bone* enable pmic-shutdown-controller
+ * In particular, messages:
+ * http://www.spinics.net/lists/linux-omap/msg118585.html
+ * http://www.spinics.net/lists/linux-omap/msg118615.html
+ *
+ * You can override this later with
+ * &tps { /delete-property/ ti,pmic-shutdown-controller; }
+ * if you want to use RTC-only mode and made sure you are not affected
+ * by the hardware problems. (Tip: double-check by performing a current
+ * measurement after shutdown: it should be less than 1 mA.)
+ */
+ ti,pmic-shutdown-controller;
+
regulators {
dcdc1_reg: regulator@0 {
regulator-name = "vdds_dpr";
status = "okay";
};
};
-
-&rtc {
- system-power-controller;
-};
wlcore: wlcore@2 {
compatible = "ti,wl1271";
reg = <2>;
- interrupt-parent = <&gpio1>;
+ interrupt-parent = <&gpio0>;
interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; /* gpio 31 */
ref-clock-frequency = <38400000>;
};
#clock-cells = <0>;
compatible = "ti,am35xx-gate-clock";
clocks = <&ipss_ick>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <1>;
};
#clock-cells = <0>;
compatible = "ti,gate-clock";
clocks = <&rmii_ck>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <9>;
};
#clock-cells = <0>;
compatible = "ti,am35xx-gate-clock";
clocks = <&ipss_ick>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <2>;
};
#clock-cells = <0>;
compatible = "ti,gate-clock";
clocks = <&pclk_ck>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <10>;
};
#clock-cells = <0>;
compatible = "ti,am35xx-gate-clock";
clocks = <&ipss_ick>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <0>;
};
#clock-cells = <0>;
compatible = "ti,gate-clock";
clocks = <&sys_ck>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <8>;
};
#clock-cells = <0>;
compatible = "ti,am35xx-gate-clock";
clocks = <&sys_ck>;
- reg = <0x059c>;
+ reg = <0x032c>;
ti,bit-shift = <3>;
};
};
pinctrl-0 = <&matrix_keypad_pins>;
debounce-delay-ms = <5>;
- col-scan-delay-us = <1500>;
+ col-scan-delay-us = <5>;
row-gpios = <&gpio5 5 GPIO_ACTIVE_HIGH /* Bank5, pin5 */
&gpio5 6 GPIO_ACTIVE_HIGH>; /* Bank5, pin6 */
interrupt-parent = <&gpio0>;
interrupts = <31 0>;
- wake-gpios = <&gpio1 28 GPIO_ACTIVE_HIGH>;
+ reset-gpios = <&gpio1 28 GPIO_ACTIVE_LOW>;
touchscreen-size-x = <480>;
touchscreen-size-y = <272>;
aliases {
rtc0 = &mcp_rtc;
rtc1 = &tps659038_rtc;
+ rtc2 = &rtc;
};
memory {
gpio_fan: gpio_fan {
/* Based on 5v 500mA AFB02505HHB */
compatible = "gpio-fan";
- gpios = <&tps659038_gpio 1 GPIO_ACTIVE_HIGH>;
+ gpios = <&tps659038_gpio 2 GPIO_ACTIVE_HIGH>;
gpio-fan,speed-map = <0 0>,
<13000 1>;
#cooling-cells = <2>;
uart3_pins_default: uart3_pins_default {
pinctrl-single,pins = <
- 0x248 (PIN_INPUT_SLEW | MUX_MODE0) /* uart3_rxd.rxd */
- 0x24c (PIN_INPUT_SLEW | MUX_MODE0) /* uart3_txd.txd */
+ 0x3f8 (PIN_INPUT_SLEW | MUX_MODE2) /* uart2_ctsn.uart3_rxd */
+ 0x3fc (PIN_INPUT_SLEW | MUX_MODE1) /* uart2_rtsn.uart3_txd */
>;
};
mcp_rtc: rtc@6f {
compatible = "microchip,mcp7941x";
reg = <0x6f>;
- interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_LOW>; /* IRQ_SYS_1N */
+ interrupts = <GIC_SPI 2 IRQ_TYPE_EDGE_RISING>; /* IRQ_SYS_1N */
pinctrl-names = "default";
pinctrl-0 = <&mcp79410_pins_default>;
&uart3 {
status = "okay";
interrupts-extended = <&crossbar_mpu GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>,
- <&dra7_pmx_core 0x248>;
+ <&dra7_pmx_core 0x3f8>;
pinctrl-names = "default";
pinctrl-0 = <&uart3_pins_default>;
mainpll: mainpll {
compatible = "fixed-clock";
#clock-cells = <0>;
- clock-frequency = <2000000000>;
+ clock-frequency = <1000000000>;
};
/* 25 MHz reference crystal */
refclk: oscillator {
mainpll: mainpll {
compatible = "fixed-clock";
#clock-cells = <0>;
- clock-frequency = <2000000000>;
+ clock-frequency = <1000000000>;
};
/* 25 MHz reference crystal */
mainpll: mainpll {
compatible = "fixed-clock";
#clock-cells = <0>;
- clock-frequency = <2000000000>;
+ clock-frequency = <1000000000>;
};
};
};
internal-regs {
+ rtc@10300 {
+ /* No crystal connected to the internal RTC */
+ status = "disabled";
+ };
+
/* J10: VCC, NC, RX, NC, TX, GND */
serial@12000 {
status = "okay";
};
internal-regs {
+ rtc@10300 {
+ /* No crystal connected to the internal RTC */
+ status = "disabled";
+ };
serial@12000 {
status = "okay";
};
ti,hwmods = "usb_otg_hs";
usb0: usb@47401000 {
- compatible = "ti,musb-am33xx";
+ compatible = "ti,musb-dm816";
reg = <0x47401400 0x400
0x47401000 0x200>;
reg-names = "mc", "control";
};
usb1: usb@47401800 {
- compatible = "ti,musb-am33xx";
+ compatible = "ti,musb-dm816";
reg = <0x47401c00 0x400
0x47401800 0x200>;
reg-names = "mc", "control";
/* connect xtal input to 25MHz reference */
clocks = <&ref25>;
+ clock-names = "xtal";
/* connect xtal input as source of pll0 and pll1 */
silabs,pll-source = <0 0>, <1 0>;
ti,clock-cycles = <16>;
reg = <0x4ae07ddc 0x4>, <0x4ae07de0 0x4>,
- <0x4ae06014 0x4>, <0x4a003b20 0x8>,
+ <0x4ae06014 0x4>, <0x4a003b20 0xc>,
<0x4ae0c158 0x4>;
reg-names = "setup-address", "control-address",
"int-address", "efuse-address",
ti,clock-cycles = <16>;
reg = <0x4ae07e34 0x4>, <0x4ae07e24 0x4>,
- <0x4ae06010 0x4>, <0x4a0025cc 0x8>,
+ <0x4ae06010 0x4>, <0x4a0025cc 0xc>,
<0x4a002470 0x4>;
reg-names = "setup-address", "control-address",
"int-address", "efuse-address",
ti,clock-cycles = <16>;
reg = <0x4ae07e30 0x4>, <0x4ae07e20 0x4>,
- <0x4ae06010 0x4>, <0x4a0025e0 0x8>,
+ <0x4ae06010 0x4>, <0x4a0025e0 0xc>,
<0x4a00246c 0x4>;
reg-names = "setup-address", "control-address",
"int-address", "efuse-address",
ti,clock-cycles = <16>;
reg = <0x4ae07de4 0x4>, <0x4ae07de8 0x4>,
- <0x4ae06010 0x4>, <0x4a003b08 0x8>,
+ <0x4ae06010 0x4>, <0x4a003b08 0xc>,
<0x4ae0c154 0x4>;
reg-names = "setup-address", "control-address",
"int-address", "efuse-address",
status = "disabled";
};
- rtc@48838000 {
+ rtc: rtc@48838000 {
compatible = "ti,am3352-rtc";
reg = <0x48838000 0x100>;
interrupts = <GIC_SPI 217 IRQ_TYPE_LEVEL_HIGH>,
#include <dt-bindings/sound/samsung-i2s.h>
#include <dt-bindings/input/input.h>
+#include <dt-bindings/clock/maxim,max77686.h>
#include "exynos4412.dtsi"
/ {
rtc@10070000 {
status = "okay";
+ clocks = <&clock CLK_RTC>, <&max77686 MAX77686_CLK_AP>;
+ clock-names = "rtc", "rtc_src";
};
g2d@10800000 {
display-timings {
timing-0 {
- clock-frequency = <0>;
+ clock-frequency = <57153600>;
hactive = <720>;
vactive = <1280>;
hfront-porch = <5>;
num-slots = <1>;
broken-cd;
cap-sdio-irq;
+ keep-power-in-suspend;
card-detect-delay = <200>;
samsung,dw-mshc-ciu-div = <3>;
samsung,dw-mshc-sdr-timing = <2 3>;
num-slots = <1>;
broken-cd;
cap-sdio-irq;
+ keep-power-in-suspend;
card-detect-delay = <200>;
clock-frequency = <400000000>;
samsung,dw-mshc-ciu-div = <1>;
type = "active";
};
cpu-crit-0 {
- temperature = <1200000>; /* millicelsius */
+ temperature = <120000>; /* millicelsius */
hysteresis = <0>; /* millicelsius */
type = "critical";
};
clock-names = "dp";
phys = <&dp_phy>;
phy-names = "dp";
+ power-domains = <&disp_pd>;
};
mipi_phy: video-phy@10040714 {
type = "active";
};
cpu-crit-0 {
- temperature = <1050000>; /* millicelsius */
+ temperature = <105000>; /* millicelsius */
hysteresis = <0>; /* millicelsius */
type = "critical";
};
num-slots = <1>;
broken-cd;
cap-sdio-irq;
+ keep-power-in-suspend;
card-detect-delay = <200>;
clock-frequency = <400000000>;
samsung,dw-mshc-ciu-div = <1>;
*/
/dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
#include "imx23.dtsi"
/ {
ahb@80080000 {
usb0: usb@80080000 {
+ dr_mode = "host";
vbus-supply = <®_usb0_vbus>;
status = "okay";
};
user {
label = "green";
- gpios = <&gpio2 1 1>;
+ gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
};
};
};
pwm4: pwm@53fc8000 {
compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
+ #pwm-cells = <2>;
reg = <0x53fc8000 0x4000>;
clocks = <&clks 108>, <&clks 52>;
clock-names = "ipg", "per";
fec: ethernet@1002b000 {
compatible = "fsl,imx27-fec";
- reg = <0x1002b000 0x4000>;
+ reg = <0x1002b000 0x1000>;
interrupts = <50>;
clocks = <&clks IMX27_CLK_FEC_IPG_GATE>,
<&clks IMX27_CLK_FEC_AHB_GATE>;
80 81 68 69
70 71 72 73
74 75 76 77>;
- interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty",
+ interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty",
"saif0", "saif1", "i2c0", "i2c1",
"auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx",
"auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx";
regulator-min-microvolt = <5000000>;
regulator-max-microvolt = <5000000>;
gpio = <&gpio4 15 0>;
+ enable-active-high;
};
reg_usb_h1_vbus: regulator@1 {
regulator-min-microvolt = <5000000>;
regulator-max-microvolt = <5000000>;
gpio = <&gpio1 0 0>;
+ enable-active-high;
};
};
&i2c3 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c3>;
- pinctrl-assert-gpios = <&gpio5 4 GPIO_ACTIVE_HIGH>;
status = "okay";
max7310_a: gpio@30 {
nand@0,0 {
reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
nand-bus-width = <16>;
+ gpmc,device-width = <2>;
+ ti,nand-ecc-opt = "sw";
gpmc,sync-clk-ps = <0>;
gpmc,cs-on-ns = <0>;
DRVDD-supply = <&vmmc2>;
IOVDD-supply = <&vio>;
DVDD-supply = <&vio>;
+
+ ai3x-micbias-vg = <1>;
};
tlv320aic3x_aux: tlv320aic3x@19 {
DRVDD-supply = <&vmmc2>;
IOVDD-supply = <&vio>;
DVDD-supply = <&vio>;
+
+ ai3x-micbias-vg = <2>;
};
tsl2563: tsl2563@29 {
touchscreen-fuzz-x = <4>;
touchscreen-fuzz-y = <7>;
touchscreen-fuzz-pressure = <2>;
- touchscreen-max-x = <4096>;
- touchscreen-max-y = <4096>;
+ touchscreen-size-x = <4096>;
+ touchscreen-size-y = <4096>;
touchscreen-max-pressure = <2048>;
ti,x-plate-ohms = <280>;
};
mmu_isp: mmu@480bd400 {
+ #iommu-cells = <0>;
compatible = "ti,omap2-iommu";
reg = <0x480bd400 0x80>;
interrupts = <24>;
};
mmu_iva: mmu@5d000000 {
+ #iommu-cells = <0>;
compatible = "ti,omap2-iommu";
reg = <0x5d000000 0x80>;
interrupts = <28>;
* hierarchy.
*/
ocp {
- compatible = "ti,omap4-l3-noc", "simple-bus";
+ compatible = "ti,omap5-l3-noc", "simple-bus";
#address-cells = <1>;
#size-cells = <1>;
ranges;
compatible = "adi,adv7511w";
reg = <0x39>;
interrupt-parent = <&gpio3>;
- interrupts = <29 IRQ_TYPE_EDGE_FALLING>;
+ interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
adi,input-depth = <8>;
adi,input-colorspace = "rgb";
status = "disabled";
};
- vmmci: regulator-gpio {
- compatible = "regulator-gpio";
-
- regulator-min-microvolt = <1800000>;
- regulator-max-microvolt = <2900000>;
- regulator-name = "mmci-reg";
- regulator-type = "voltage";
-
- startup-delay-us = <100>;
- enable-active-high;
-
- states = <1800000 0x1
- 2900000 0x0>;
-
- status = "disabled";
- };
-
mcde@a0350000 {
compatible = "stericsson,mcde";
reg = <0xa0350000 0x1000>, /* MCDE */
pinctrl-1 = <&i2c3_sleep_mode>;
};
+ vmmci: regulator-gpio {
+ compatible = "regulator-gpio";
+
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <2900000>;
+ regulator-name = "mmci-reg";
+ regulator-type = "voltage";
+
+ startup-delay-us = <100>;
+ enable-active-high;
+
+ states = <1800000 0x1
+ 2900000 0x0>;
+ };
+
// External Micro SD slot
sdi0_per1@80126000 {
arm,primecell-periphid = <0x10480180>;
};
vmmci: regulator-gpio {
+ compatible = "regulator-gpio";
+
gpios = <&gpio7 4 0x4>;
enable-gpio = <&gpio6 25 0x4>;
+
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <2900000>;
+ regulator-name = "mmci-reg";
+ regulator-type = "voltage";
+
+ startup-delay-us = <100>;
+ enable-active-high;
+
+ states = <1800000 0x1
+ 2900000 0x0>;
};
// External Micro SD slot
<&tegra_car TEGRA124_CLK_PLL_U>,
<&tegra_car TEGRA124_CLK_USBD>;
clock-names = "reg", "pll_u", "utmi-pads";
- resets = <&tegra_car 59>, <&tegra_car 22>;
+ resets = <&tegra_car 22>, <&tegra_car 22>;
reset-names = "usb", "utmi-pads";
nvidia,hssync-start-delay = <0>;
nvidia,idle-wait-delay = <17>;
nvidia,hssquelch-level = <2>;
nvidia,hsdiscon-level = <5>;
nvidia,xcvr-hsslew = <12>;
+ nvidia,has-utmi-pad-registers;
status = "disabled";
};
<&tegra_car TEGRA124_CLK_PLL_U>,
<&tegra_car TEGRA124_CLK_USBD>;
clock-names = "reg", "pll_u", "utmi-pads";
- resets = <&tegra_car 22>, <&tegra_car 22>;
+ resets = <&tegra_car 58>, <&tegra_car 22>;
reset-names = "usb", "utmi-pads";
nvidia,hssync-start-delay = <0>;
nvidia,idle-wait-delay = <17>;
nvidia,hssquelch-level = <2>;
nvidia,hsdiscon-level = <5>;
nvidia,xcvr-hsslew = <12>;
- nvidia,has-utmi-pad-registers;
status = "disabled";
};
<&tegra_car TEGRA124_CLK_PLL_U>,
<&tegra_car TEGRA124_CLK_USBD>;
clock-names = "reg", "pll_u", "utmi-pads";
- resets = <&tegra_car 58>, <&tegra_car 22>;
+ resets = <&tegra_car 59>, <&tegra_car 22>;
reset-names = "usb", "utmi-pads";
nvidia,hssync-start-delay = <0>;
nvidia,idle-wait-delay = <17>;
compatible = "arm,cortex-a15-pmu";
interrupts = <0 68 4>,
<0 69 4>;
+ interrupt-affinity = <&cpu0>, <&cpu1>;
};
oscclk6a: oscclk6a {
#address-cells = <1>;
#size-cells = <0>;
- cpu@0 {
+ A9_0: cpu@0 {
device_type = "cpu";
compatible = "arm,cortex-a9";
reg = <0>;
next-level-cache = <&L2>;
};
- cpu@1 {
+ A9_1: cpu@1 {
device_type = "cpu";
compatible = "arm,cortex-a9";
reg = <1>;
next-level-cache = <&L2>;
};
- cpu@2 {
+ A9_2: cpu@2 {
device_type = "cpu";
compatible = "arm,cortex-a9";
reg = <2>;
next-level-cache = <&L2>;
};
- cpu@3 {
+ A9_3: cpu@3 {
device_type = "cpu";
compatible = "arm,cortex-a9";
reg = <3>;
compatible = "arm,pl310-cache";
reg = <0x1e00a000 0x1000>;
interrupts = <0 43 4>;
+ cache-unified;
cache-level = <2>;
arm,data-latency = <1 1 1>;
arm,tag-latency = <1 1 1>;
<0 61 4>,
<0 62 4>,
<0 63 4>;
+ interrupt-affinity = <&A9_0>, <&A9_1>, <&A9_2>, <&A9_3>;
+
};
dcc {
};
gem0: ethernet@e000b000 {
- compatible = "cdns,gem";
+ compatible = "cdns,zynq-gem";
reg = <0xe000b000 0x1000>;
status = "disabled";
interrupts = <0 22 4>;
};
gem1: ethernet@e000c000 {
- compatible = "cdns,gem";
+ compatible = "cdns,zynq-gem";
reg = <0xe000c000 0x1000>;
status = "disabled";
interrupts = <0 45 4>;
CONFIG_ARCH_KEYSTONE=y
CONFIG_ARCH_MESON=y
CONFIG_ARCH_MXC=y
+CONFIG_SOC_IMX50=y
CONFIG_SOC_IMX51=y
CONFIG_SOC_IMX53=y
CONFIG_SOC_IMX6Q=y
CONFIG_SOC_IMX6SL=y
+CONFIG_SOC_IMX6SX=y
CONFIG_SOC_VF610=y
+CONFIG_SOC_LS1021A=y
CONFIG_ARCH_OMAP3=y
CONFIG_ARCH_OMAP4=y
CONFIG_SOC_OMAP5=y
CONFIG_USB_EHCI_TEGRA=y
CONFIG_USB_EHCI_HCD_STI=y
CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_ISP1760=y
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_OHCI_HCD_STI=y
CONFIG_USB_OHCI_HCD_PLATFORM=y
CONFIG_DMA_OMAP=y
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_EXTCON=m
-CONFIG_EXTCON_GPIO=m
+CONFIG_EXTCON_USB_GPIO=m
CONFIG_EXTCON_PALMAS=m
CONFIG_TI_EMIF=m
CONFIG_PWM=y
#define read_barrier_depends() do { } while(0)
#define smp_read_barrier_depends() do { } while(0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
};
struct dma_iommu_mapping *
-arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size);
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size);
void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping);
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
+ preempt_disable();
__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
"1: " TUSER(ldr) " %1, [%4]\n"
" teq %1, %2\n"
: "cc", "memory");
*uval = val;
+ preempt_enable();
+
return ret;
}
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
+#ifndef CONFIG_SMP
+ preempt_disable();
+#endif
+ pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
ret = -ENOSYS;
}
- pagefault_enable(); /* subsumes preempt_enable() */
+ pagefault_enable();
+#ifndef CONFIG_SMP
+ preempt_enable();
+#endif
if (!ret) {
switch (cmp) {
#define ioremap_nocache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
#define ioremap_cache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
#define ioremap_wc(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_WC)
+#define ioremap_wt(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
#define iounmap __arm_iounmap
/*
#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id)
#define topology_core_id(cpu) (cpu_topology[cpu].core_id)
#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq @ disable interrupts
- ldr r1, [tsk, #TI_FLAGS]
+ ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
+ tst r1, #_TIF_SYSCALL_WORK
+ bne __sys_trace_return
tst r1, #_TIF_WORK_MASK
bne fast_work_pending
asm_trace_hardirqs_on
static int of_pmu_irq_cfg(struct platform_device *pdev)
{
- int i;
- int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+ int i, irq;
+ int *irqs;
+ /* Don't bother with PPIs; they're already affine */
+ irq = platform_get_irq(pdev, 0);
+ if (irq >= 0 && irq_is_percpu(irq))
+ return 0;
+
+ irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
if (!irqs)
return -ENOMEM;
i);
if (!dn) {
pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
- of_node_full_name(dn), i);
+ of_node_full_name(pdev->dev.of_node), i);
break;
}
extern struct cpuidle_exynos_data cpuidle_coupled_exynos_data;
+extern void exynos_set_delayed_reset_assertion(bool enable);
+
extern void s5p_init_cpu(void __iomem *cpuid_addr);
extern unsigned int samsung_rev(void);
extern void __iomem *cpu_boot_reg_base(void);
exynos_map_io();
}
+/*
+ * Set or clear the USE_DELAYED_RESET_ASSERTION option. Used by smp code
+ * and suspend.
+ *
+ * This is necessary only on Exynos4 SoCs. When system is running
+ * USE_DELAYED_RESET_ASSERTION should be set so the ARM CLK clock down
+ * feature could properly detect global idle state when secondary CPU is
+ * powered down.
+ *
+ * However this should not be set when such system is going into suspend.
+ */
+void exynos_set_delayed_reset_assertion(bool enable)
+{
+ if (of_machine_is_compatible("samsung,exynos4")) {
+ unsigned int tmp, core_id;
+
+ for (core_id = 0; core_id < num_possible_cpus(); core_id++) {
+ tmp = pmu_raw_readl(EXYNOS_ARM_CORE_OPTION(core_id));
+ if (enable)
+ tmp |= S5P_USE_DELAYED_RESET_ASSERTION;
+ else
+ tmp &= ~(S5P_USE_DELAYED_RESET_ASSERTION);
+ pmu_raw_writel(tmp, EXYNOS_ARM_CORE_OPTION(core_id));
+ }
+ }
+}
+
/*
* Apparently, these SoCs are not able to wake-up from suspend using
* the PMU. Too bad. Should they suddenly become capable of such a
extern void exynos4_secondary_startup(void);
-/*
- * Set or clear the USE_DELAYED_RESET_ASSERTION option, set on Exynos4 SoCs
- * during hot-(un)plugging CPUx.
- *
- * The feature can be cleared safely during first boot of secondary CPU.
- *
- * Exynos4 SoCs require setting USE_DELAYED_RESET_ASSERTION during powering
- * down a CPU so the CPU idle clock down feature could properly detect global
- * idle state when CPUx is off.
- */
-static void exynos_set_delayed_reset_assertion(u32 core_id, bool enable)
-{
- if (soc_is_exynos4()) {
- unsigned int tmp;
-
- tmp = pmu_raw_readl(EXYNOS_ARM_CORE_OPTION(core_id));
- if (enable)
- tmp |= S5P_USE_DELAYED_RESET_ASSERTION;
- else
- tmp &= ~(S5P_USE_DELAYED_RESET_ASSERTION);
- pmu_raw_writel(tmp, EXYNOS_ARM_CORE_OPTION(core_id));
- }
-}
-
#ifdef CONFIG_HOTPLUG_CPU
static inline void cpu_leave_lowpower(u32 core_id)
{
: "=&r" (v)
: "Ir" (CR_C), "Ir" (0x40)
: "cc");
-
- exynos_set_delayed_reset_assertion(core_id, false);
}
static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
/* Turn the CPU off on next WFI instruction. */
exynos_cpu_power_down(core_id);
- /*
- * Exynos4 SoCs require setting
- * USE_DELAYED_RESET_ASSERTION so the CPU idle
- * clock down feature could properly detect
- * global idle state when CPUx is off.
- */
- exynos_set_delayed_reset_assertion(core_id, true);
-
wfi();
if (pen_release == core_id) {
udelay(10);
}
- /* No harm if this is called during first boot of secondary CPU */
- exynos_set_delayed_reset_assertion(core_id, false);
-
/*
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
exynos_sysram_init();
+ exynos_set_delayed_reset_assertion(true);
+
if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
scu_enable(scu_base_addr());
args.np = np;
args.args_count = 0;
child_domain = of_genpd_get_from_provider(&args);
- if (!child_domain)
+ if (IS_ERR(child_domain))
continue;
if (of_parse_phandle_with_args(np, "power-domains",
continue;
parent_domain = of_genpd_get_from_provider(&args);
- if (!parent_domain)
+ if (IS_ERR(parent_domain))
continue;
if (pm_genpd_add_subdomain(parent_domain, child_domain))
static u32 exynos_irqwake_intmask = 0xffffffff;
static const struct exynos_wkup_irq exynos3250_wkup_irq[] = {
- { 105, BIT(1) }, /* RTC alarm */
- { 106, BIT(2) }, /* RTC tick */
+ { 73, BIT(1) }, /* RTC alarm */
+ { 74, BIT(2) }, /* RTC tick */
{ /* sentinel */ },
};
static void exynos_pm_prepare(void)
{
+ exynos_set_delayed_reset_assertion(false);
+
/* Set wake-up mask registers */
exynos_pm_set_wakeup_mask();
/* Clear SLEEP mode set in INFORM1 */
pmu_raw_writel(0x0, S5P_INFORM1);
+ exynos_set_delayed_reset_assertion(true);
}
static void exynos3250_pm_resume(void)
return;
}
- if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL)))
+ if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+ return;
+ }
pm_data = (const struct exynos_pm_data *) match->data;
#ifndef __GEMINI_COMMON_H__
#define __GEMINI_COMMON_H__
+#include <linux/reboot.h>
+
struct mtd_partition;
extern void gemini_map_io(void);
struct mtd_partition *parts,
unsigned int nr_parts);
-extern void gemini_restart(char mode, const char *cmd);
+extern void gemini_restart(enum reboot_mode mode, const char *cmd);
#endif /* __GEMINI_COMMON_H__ */
#include <mach/hardware.h>
#include <mach/global_reg.h>
-void gemini_restart(char mode, const char *cmd)
+#include "common.h"
+
+void gemini_restart(enum reboot_mode mode, const char *cmd)
{
__raw_writel(RESET_GLOBAL | RESET_CPU1,
IO_ADDRESS(GEMINI_GLOBAL_BASE) + GLOBAL_RESET);
/*
- * Copyright (C) 2010 Pengutronix, Wolfram Sang <w.sang@pengutronix.de>
+ * Copyright (C) 2010 Pengutronix, Wolfram Sang <kernel@pengutronix.de>
*
* This program is free software; you can redistribute it and/or modify it under
* the terms of the GNU General Public License version 2 as published by the
struct device_node *np;
np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpc");
- if (WARN_ON(!np ||
- !of_find_property(np, "interrupt-controller", NULL)))
- pr_warn("Outdated DT detected, system is about to crash!!!\n");
+ if (WARN_ON(!np))
+ return;
+
+ if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
+ pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+
+ /* map GPC, so that at least CPUidle and WARs keep working */
+ gpc_base = of_iomap(np, 0);
+ }
}
#ifdef CONFIG_PM_GENERIC_DOMAINS
struct regulator *pu_reg;
int ret;
+ /* bail out if DT too old and doesn't provide the necessary info */
+ if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells"))
+ return 0;
+
pu_reg = devm_regulator_get_optional(&pdev->dev, "pu");
if (PTR_ERR(pu_reg) == -ENODEV)
pu_reg = NULL;
*/
#define LINKS_PER_OCP_IF 2
+/*
+ * Address offset (in bytes) between the reset control and the reset
+ * status registers: 4 bytes on OMAP4
+ */
+#define OMAP4_RST_CTRL_ST_OFFSET 4
+
/**
* struct omap_hwmod_soc_ops - fn ptrs for some SoC-specific operations
* @enable_module: function to enable a module (via MODULEMODE)
if (ohri->st_shift)
pr_err("omap_hwmod: %s: %s: hwmod data error: OMAP4 does not support st_shift\n",
oh->name, ohri->name);
- return omap_prm_deassert_hardreset(ohri->rst_shift, 0,
+ return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->rst_shift,
oh->clkdm->pwrdm.ptr->prcm_partition,
oh->clkdm->pwrdm.ptr->prcm_offs,
- oh->prcm.omap4.rstctrl_offs, 0);
+ oh->prcm.omap4.rstctrl_offs,
+ oh->prcm.omap4.rstctrl_offs +
+ OMAP4_RST_CTRL_ST_OFFSET);
}
/**
oh->prcm.omap4.rstctrl_offs);
}
-/**
- * _am33xx_assert_hardreset - call AM33XX PRM hardreset fn with hwmod args
- * @oh: struct omap_hwmod * to assert hardreset
- * @ohri: hardreset line data
- *
- * Call am33xx_prminst_assert_hardreset() with parameters extracted
- * from the hwmod @oh and the hardreset line data @ohri. Only
- * intended for use as an soc_ops function pointer. Passes along the
- * return value from am33xx_prminst_assert_hardreset(). XXX This
- * function is scheduled for removal when the PRM code is moved into
- * drivers/.
- */
-static int _am33xx_assert_hardreset(struct omap_hwmod *oh,
- struct omap_hwmod_rst_info *ohri)
-
-{
- return omap_prm_assert_hardreset(ohri->rst_shift, 0,
- oh->clkdm->pwrdm.ptr->prcm_offs,
- oh->prcm.omap4.rstctrl_offs);
-}
-
/**
* _am33xx_deassert_hardreset - call AM33XX PRM hardreset fn with hwmod args
* @oh: struct omap_hwmod * to deassert hardreset
static int _am33xx_deassert_hardreset(struct omap_hwmod *oh,
struct omap_hwmod_rst_info *ohri)
{
- return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->st_shift, 0,
+ return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->st_shift,
+ oh->clkdm->pwrdm.ptr->prcm_partition,
oh->clkdm->pwrdm.ptr->prcm_offs,
oh->prcm.omap4.rstctrl_offs,
oh->prcm.omap4.rstst_offs);
}
-/**
- * _am33xx_is_hardreset_asserted - call AM33XX PRM hardreset fn with hwmod args
- * @oh: struct omap_hwmod * to test hardreset
- * @ohri: hardreset line data
- *
- * Call am33xx_prminst_is_hardreset_asserted() with parameters
- * extracted from the hwmod @oh and the hardreset line data @ohri.
- * Only intended for use as an soc_ops function pointer. Passes along
- * the return value from am33xx_prminst_is_hardreset_asserted(). XXX
- * This function is scheduled for removal when the PRM code is moved
- * into drivers/.
- */
-static int _am33xx_is_hardreset_asserted(struct omap_hwmod *oh,
- struct omap_hwmod_rst_info *ohri)
-{
- return omap_prm_is_hardreset_asserted(ohri->rst_shift, 0,
- oh->clkdm->pwrdm.ptr->prcm_offs,
- oh->prcm.omap4.rstctrl_offs);
-}
-
/* Public functions */
u32 omap_hwmod_read(struct omap_hwmod *oh, u16 reg_offs)
soc_ops.init_clkdm = _init_clkdm;
soc_ops.update_context_lost = _omap4_update_context_lost;
soc_ops.get_context_lost = _omap4_get_context_lost;
- } else if (soc_is_am43xx()) {
+ } else if (cpu_is_ti816x() || soc_is_am33xx() || soc_is_am43xx()) {
soc_ops.enable_module = _omap4_enable_module;
soc_ops.disable_module = _omap4_disable_module;
soc_ops.wait_target_ready = _omap4_wait_target_ready;
soc_ops.assert_hardreset = _omap4_assert_hardreset;
- soc_ops.deassert_hardreset = _omap4_deassert_hardreset;
- soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted;
- soc_ops.init_clkdm = _init_clkdm;
- } else if (cpu_is_ti816x() || soc_is_am33xx()) {
- soc_ops.enable_module = _omap4_enable_module;
- soc_ops.disable_module = _omap4_disable_module;
- soc_ops.wait_target_ready = _omap4_wait_target_ready;
- soc_ops.assert_hardreset = _am33xx_assert_hardreset;
soc_ops.deassert_hardreset = _am33xx_deassert_hardreset;
- soc_ops.is_hardreset_asserted = _am33xx_is_hardreset_asserted;
+ soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted;
soc_ops.init_clkdm = _init_clkdm;
} else {
WARN(1, "omap_hwmod: unknown SoC type\n");
},
};
+static struct omap_hwmod_class_sysconfig am43xx_vpfe_sysc = {
+ .rev_offs = 0x0,
+ .sysc_offs = 0x104,
+ .sysc_flags = SYSC_HAS_MIDLEMODE | SYSC_HAS_SIDLEMODE,
+ .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+ MSTANDBY_FORCE | MSTANDBY_SMART | MSTANDBY_NO),
+ .sysc_fields = &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class am43xx_vpfe_hwmod_class = {
+ .name = "vpfe",
+ .sysc = &am43xx_vpfe_sysc,
+};
+
+static struct omap_hwmod am43xx_vpfe0_hwmod = {
+ .name = "vpfe0",
+ .class = &am43xx_vpfe_hwmod_class,
+ .clkdm_name = "l3s_clkdm",
+ .prcm = {
+ .omap4 = {
+ .modulemode = MODULEMODE_SWCTRL,
+ .clkctrl_offs = AM43XX_CM_PER_VPFE0_CLKCTRL_OFFSET,
+ },
+ },
+};
+
+static struct omap_hwmod am43xx_vpfe1_hwmod = {
+ .name = "vpfe1",
+ .class = &am43xx_vpfe_hwmod_class,
+ .clkdm_name = "l3s_clkdm",
+ .prcm = {
+ .omap4 = {
+ .modulemode = MODULEMODE_SWCTRL,
+ .clkctrl_offs = AM43XX_CM_PER_VPFE1_CLKCTRL_OFFSET,
+ },
+ },
+};
+
/* Interfaces */
static struct omap_hwmod_ocp_if am43xx_l3_main__l4_hs = {
.master = &am33xx_l3_main_hwmod,
.user = OCP_USER_MPU | OCP_USER_SDMA,
};
+static struct omap_hwmod_ocp_if am43xx_l3__vpfe0 = {
+ .master = &am43xx_vpfe0_hwmod,
+ .slave = &am33xx_l3_main_hwmod,
+ .clk = "l3_gclk",
+ .user = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_ocp_if am43xx_l3__vpfe1 = {
+ .master = &am43xx_vpfe1_hwmod,
+ .slave = &am33xx_l3_main_hwmod,
+ .clk = "l3_gclk",
+ .user = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_ocp_if am43xx_l4_ls__vpfe0 = {
+ .master = &am33xx_l4_ls_hwmod,
+ .slave = &am43xx_vpfe0_hwmod,
+ .clk = "l4ls_gclk",
+ .user = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_ocp_if am43xx_l4_ls__vpfe1 = {
+ .master = &am33xx_l4_ls_hwmod,
+ .slave = &am43xx_vpfe1_hwmod,
+ .clk = "l4ls_gclk",
+ .user = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = {
&am33xx_l4_wkup__synctimer,
&am43xx_l4_ls__timer8,
&am43xx_l4_ls__dss_dispc,
&am43xx_l4_ls__dss_rfbi,
&am43xx_l4_ls__hdq1w,
+ &am43xx_l3__vpfe0,
+ &am43xx_l3__vpfe1,
+ &am43xx_l4_ls__vpfe0,
+ &am43xx_l4_ls__vpfe1,
NULL,
};
#define AM43XX_CM_PER_USBPHYOCP2SCP1_CLKCTRL_OFFSET 0x05C0
#define AM43XX_CM_PER_DSS_CLKCTRL_OFFSET 0x0a20
#define AM43XX_CM_PER_HDQ1W_CLKCTRL_OFFSET 0x04a0
-
+#define AM43XX_CM_PER_VPFE0_CLKCTRL_OFFSET 0x0068
+#define AM43XX_CM_PER_VPFE1_CLKCTRL_OFFSET 0x0070
#endif
#define OMAP3430_VC_CMD_ONLP_SHIFT 16
#define OMAP3430_VC_CMD_RET_SHIFT 8
#define OMAP3430_VC_CMD_OFF_SHIFT 0
+#define OMAP3430_SREN_MASK (1 << 4)
#define OMAP3430_HSEN_MASK (1 << 3)
#define OMAP3430_MCODE_MASK (0x7 << 0)
#define OMAP3430_VALID_MASK (1 << 24)
#define OMAP4430_GLOBAL_WARM_SW_RST_SHIFT 1
#define OMAP4430_GLOBAL_WUEN_MASK (1 << 16)
#define OMAP4430_HSMCODE_MASK (0x7 << 0)
+#define OMAP4430_SRMODEEN_MASK (1 << 4)
#define OMAP4430_HSMODEEN_MASK (1 << 3)
#define OMAP4430_HSSCLL_SHIFT 24
#define OMAP4430_ICEPICK_RST_SHIFT 9
return v;
}
-/*
- * Address offset (in bytes) between the reset control and the reset
- * status registers: 4 bytes on OMAP4
- */
-#define OMAP4_RST_CTRL_ST_OFFSET 4
-
/**
* omap4_prminst_is_hardreset_asserted - read the HW reset line state of
* submodules contained in the hwmod module
* omap4_prminst_deassert_hardreset - deassert a submodule hardreset line and
* wait
* @shift: register bit shift corresponding to the reset line to deassert
- * @st_shift: status bit offset, not used for OMAP4+
+ * @st_shift: status bit offset corresponding to the reset line
* @part: PRM partition
* @inst: PRM instance offset
* @rstctrl_offs: reset register offset
- * @st_offs: reset status register offset, not used for OMAP4+
+ * @rstst_offs: reset status register offset
*
* Some IPs like dsp, ipu or iva contain processors that require an HW
* reset line to be asserted / deasserted in order to fully enable the
* of reset, or -EBUSY if the submodule did not exit reset promptly.
*/
int omap4_prminst_deassert_hardreset(u8 shift, u8 st_shift, u8 part, s16 inst,
- u16 rstctrl_offs, u16 st_offs)
+ u16 rstctrl_offs, u16 rstst_offs)
{
int c;
u32 mask = 1 << shift;
- u16 rstst_offs = rstctrl_offs + OMAP4_RST_CTRL_ST_OFFSET;
+ u32 st_mask = 1 << st_shift;
/* Check the current status to avoid de-asserting the line twice */
if (omap4_prminst_is_hardreset_asserted(shift, part, inst,
return -EEXIST;
/* Clear the reset status by writing 1 to the status bit */
- omap4_prminst_rmw_inst_reg_bits(0xffffffff, mask, part, inst,
+ omap4_prminst_rmw_inst_reg_bits(0xffffffff, st_mask, part, inst,
rstst_offs);
/* de-assert the reset control line */
omap4_prminst_rmw_inst_reg_bits(mask, 0, part, inst, rstctrl_offs);
/* wait the status to be set */
- omap_test_timeout(omap4_prminst_is_hardreset_asserted(shift, part, inst,
- rstst_offs),
+ omap_test_timeout(omap4_prminst_is_hardreset_asserted(st_shift, part,
+ inst, rstst_offs),
MAX_MODULE_HARDRESET_WAIT, c);
return (c == MAX_MODULE_HARDRESET_WAIT) ? -EBUSY : 0;
*/
ldr r1, kernel_flush
blx r1
- /*
- * The kernel doesn't interwork: v7_flush_dcache_all in particluar will
- * always return in Thumb state when CONFIG_THUMB2_KERNEL is enabled.
- * This sequence switches back to ARM. Note that .align may insert a
- * nop: bx pc needs to be word-aligned in order to work.
- */
- THUMB( .thumb )
- THUMB( .align )
- THUMB( bx pc )
- THUMB( nop )
- .arm
-
b omap3_do_wfi
-
-/*
- * Local variables
- */
+ENDPROC(omap34xx_cpu_suspend)
omap3_do_wfi_sram_addr:
.word omap3_do_wfi_sram
kernel_flush:
* ===================================
*/
ldmfd sp!, {r4 - r11, pc} @ restore regs and return
-
-/*
- * Local variables
- */
+ENDPROC(omap3_do_wfi)
sdrc_power:
.word SDRC_POWER_V
cm_idlest1_core:
if (IS_ERR(src))
return PTR_ERR(src);
- if (clk_get_parent(timer->fclk) != src) {
- r = clk_set_parent(timer->fclk, src);
- if (r < 0) {
- pr_warn("%s: %s cannot set source\n", __func__,
- oh->name);
- clk_put(src);
- return r;
- }
+ r = clk_set_parent(timer->fclk, src);
+ if (r < 0) {
+ pr_warn("%s: %s cannot set source\n", __func__, oh->name);
+ clk_put(src);
+ return r;
}
clk_put(src);
* idle. And we can also scale voltages to zero for off-idle.
* Note that no actual voltage scaling during off-idle will
* happen unless the board specific twl4030 PMIC scripts are
- * loaded.
+ * loaded. See also omap_vc_i2c_init for comments regarding
+ * erratum i531.
*/
val = voltdm->read(OMAP3_PRM_VOLTCTRL_OFFSET);
if (!(val & OMAP3430_PRM_VOLTCTRL_SEL_OFF)) {
return;
}
+ /*
+ * Note that for omap3 OMAP3430_SREN_MASK clears SREN to work around
+ * erratum i531 "Extra Power Consumed When Repeated Start Operation
+ * Mode Is Enabled on I2C Interface Dedicated for Smart Reflex (I2C4)".
+ * Otherwise I2C4 eventually leads into about 23mW extra power being
+ * consumed even during off idle using VMODE.
+ */
i2c_high_speed = voltdm->pmic->i2c_high_speed;
if (i2c_high_speed)
- voltdm->rmw(vc->common->i2c_cfg_hsen_mask,
+ voltdm->rmw(vc->common->i2c_cfg_clear_mask,
vc->common->i2c_cfg_hsen_mask,
vc->common->i2c_cfg_reg);
* @cmd_ret_shift: RET field shift in PRM_VC_CMD_VAL_* register
* @cmd_off_shift: OFF field shift in PRM_VC_CMD_VAL_* register
* @i2c_cfg_reg: I2C configuration register offset
+ * @i2c_cfg_clear_mask: high-speed mode bit clear mask in I2C config register
* @i2c_cfg_hsen_mask: high-speed mode bit field mask in I2C config register
* @i2c_mcode_mask: MCODE field mask for I2C config register
*
u8 cmd_ret_shift;
u8 cmd_off_shift;
u8 i2c_cfg_reg;
+ u8 i2c_cfg_clear_mask;
u8 i2c_cfg_hsen_mask;
u8 i2c_mcode_mask;
};
.cmd_onlp_shift = OMAP3430_VC_CMD_ONLP_SHIFT,
.cmd_ret_shift = OMAP3430_VC_CMD_RET_SHIFT,
.cmd_off_shift = OMAP3430_VC_CMD_OFF_SHIFT,
+ .i2c_cfg_clear_mask = OMAP3430_SREN_MASK | OMAP3430_HSEN_MASK,
.i2c_cfg_hsen_mask = OMAP3430_HSEN_MASK,
.i2c_cfg_reg = OMAP3_PRM_VC_I2C_CFG_OFFSET,
.i2c_mcode_mask = OMAP3430_MCODE_MASK,
.cmd_ret_shift = OMAP4430_RET_SHIFT,
.cmd_off_shift = OMAP4430_OFF_SHIFT,
.i2c_cfg_reg = OMAP4_PRM_VC_CFG_I2C_MODE_OFFSET,
+ .i2c_cfg_clear_mask = OMAP4430_SRMODEEN_MASK | OMAP4430_HSMODEEN_MASK,
.i2c_cfg_hsen_mask = OMAP4430_HSMODEEN_MASK,
.i2c_mcode_mask = OMAP4430_HSMCODE_MASK,
};
config PXA310_ULPI
bool
+config PXA_SYSTEMS_CPLDS
+ tristate "Motherboard cplds"
+ default ARCH_LUBBOCK || MACH_MAINSTONE
+ help
+ This driver supports the Lubbock and Mainstone multifunction chip
+ found on the pxa25x development platform system (Lubbock) and pxa27x
+ development platform system (Mainstone). This IO board supports the
+ interrupts handling, ethernet controller, flash chips, etc ...
+
endif
obj-$(CONFIG_MACH_RAUMFELD_SPEAKER) += raumfeld.o
obj-$(CONFIG_MACH_ZIPIT2) += z2.o
+obj-$(CONFIG_PXA_SYSTEMS_CPLDS) += pxa_cplds_irqs.o
obj-$(CONFIG_TOSA_BT) += tosa-bt.o
#define LUB_GP __LUB_REG(LUBBOCK_FPGA_PHYS + 0x100)
/* Board specific IRQs */
-#define LUBBOCK_IRQ(x) (IRQ_BOARD_START + (x))
+#define LUBBOCK_NR_IRQS IRQ_BOARD_START
+
+#define LUBBOCK_IRQ(x) (LUBBOCK_NR_IRQS + (x))
#define LUBBOCK_SD_IRQ LUBBOCK_IRQ(0)
#define LUBBOCK_SA1111_IRQ LUBBOCK_IRQ(1)
#define LUBBOCK_USB_IRQ LUBBOCK_IRQ(2) /* usb connect */
#define LUBBOCK_USB_DISC_IRQ LUBBOCK_IRQ(6) /* usb disconnect */
#define LUBBOCK_LAST_IRQ LUBBOCK_IRQ(6)
-#define LUBBOCK_SA1111_IRQ_BASE (IRQ_BOARD_START + 16)
-#define LUBBOCK_NR_IRQS (IRQ_BOARD_START + 16 + 55)
+#define LUBBOCK_SA1111_IRQ_BASE (LUBBOCK_NR_IRQS + 32)
#ifndef __ASSEMBLY__
extern void lubbock_set_misc_wr(unsigned int mask, unsigned int set);
#define MST_PCMCIA_PWR_VCC_50 0x4 /* voltage VCC = 5.0V */
/* board specific IRQs */
-#define MAINSTONE_IRQ(x) (IRQ_BOARD_START + (x))
+#define MAINSTONE_NR_IRQS IRQ_BOARD_START
+
+#define MAINSTONE_IRQ(x) (MAINSTONE_NR_IRQS + (x))
#define MAINSTONE_MMC_IRQ MAINSTONE_IRQ(0)
#define MAINSTONE_USIM_IRQ MAINSTONE_IRQ(1)
#define MAINSTONE_USBC_IRQ MAINSTONE_IRQ(2)
#define MAINSTONE_S1_STSCHG_IRQ MAINSTONE_IRQ(14)
#define MAINSTONE_S1_IRQ MAINSTONE_IRQ(15)
-#define MAINSTONE_NR_IRQS (IRQ_BOARD_START + 16)
-
#endif
* published by the Free Software Foundation.
*/
#include <linux/gpio.h>
+#include <linux/gpio/machine.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
}
EXPORT_SYMBOL(lubbock_set_misc_wr);
-static unsigned long lubbock_irq_enabled;
-
-static void lubbock_mask_irq(struct irq_data *d)
-{
- int lubbock_irq = (d->irq - LUBBOCK_IRQ(0));
- LUB_IRQ_MASK_EN = (lubbock_irq_enabled &= ~(1 << lubbock_irq));
-}
-
-static void lubbock_unmask_irq(struct irq_data *d)
-{
- int lubbock_irq = (d->irq - LUBBOCK_IRQ(0));
- /* the irq can be acknowledged only if deasserted, so it's done here */
- LUB_IRQ_SET_CLR &= ~(1 << lubbock_irq);
- LUB_IRQ_MASK_EN = (lubbock_irq_enabled |= (1 << lubbock_irq));
-}
-
-static struct irq_chip lubbock_irq_chip = {
- .name = "FPGA",
- .irq_ack = lubbock_mask_irq,
- .irq_mask = lubbock_mask_irq,
- .irq_unmask = lubbock_unmask_irq,
-};
-
-static void lubbock_irq_handler(unsigned int irq, struct irq_desc *desc)
-{
- unsigned long pending = LUB_IRQ_SET_CLR & lubbock_irq_enabled;
- do {
- /* clear our parent irq */
- desc->irq_data.chip->irq_ack(&desc->irq_data);
- if (likely(pending)) {
- irq = LUBBOCK_IRQ(0) + __ffs(pending);
- generic_handle_irq(irq);
- }
- pending = LUB_IRQ_SET_CLR & lubbock_irq_enabled;
- } while (pending);
-}
-
-static void __init lubbock_init_irq(void)
-{
- int irq;
-
- pxa25x_init_irq();
-
- /* setup extra lubbock irqs */
- for (irq = LUBBOCK_IRQ(0); irq <= LUBBOCK_LAST_IRQ; irq++) {
- irq_set_chip_and_handler(irq, &lubbock_irq_chip,
- handle_level_irq);
- set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
- }
-
- irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), lubbock_irq_handler);
- irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING);
-}
-
-#ifdef CONFIG_PM
-
-static void lubbock_irq_resume(void)
-{
- LUB_IRQ_MASK_EN = lubbock_irq_enabled;
-}
-
-static struct syscore_ops lubbock_irq_syscore_ops = {
- .resume = lubbock_irq_resume,
-};
-
-static int __init lubbock_irq_device_init(void)
-{
- if (machine_is_lubbock()) {
- register_syscore_ops(&lubbock_irq_syscore_ops);
- return 0;
- }
- return -ENODEV;
-}
-
-device_initcall(lubbock_irq_device_init);
-
-#endif
-
static int lubbock_udc_is_connected(void)
{
return (LUB_MISC_RD & (1 << 9)) == 0;
},
};
+static struct resource lubbock_cplds_resources[] = {
+ [0] = {
+ .start = LUBBOCK_FPGA_PHYS + 0xc0,
+ .end = LUBBOCK_FPGA_PHYS + 0xe0 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = PXA_GPIO_TO_IRQ(0),
+ .end = PXA_GPIO_TO_IRQ(0),
+ .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
+ },
+ [2] = {
+ .start = LUBBOCK_IRQ(0),
+ .end = LUBBOCK_IRQ(6),
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct platform_device lubbock_cplds_device = {
+ .name = "pxa_cplds_irqs",
+ .id = -1,
+ .resource = &lubbock_cplds_resources[0],
+ .num_resources = 3,
+};
+
+
static struct platform_device *devices[] __initdata = {
&sa1111_device,
&smc91x_device,
&lubbock_flash_device[0],
&lubbock_flash_device[1],
+ &lubbock_cplds_device,
};
static struct pxafb_mode_info sharp_lm8v31_mode = {
/* Maintainer: MontaVista Software Inc. */
.map_io = lubbock_map_io,
.nr_irqs = LUBBOCK_NR_IRQS,
- .init_irq = lubbock_init_irq,
+ .init_irq = pxa25x_init_irq,
.handle_irq = pxa25x_handle_irq,
.init_time = pxa_timer_init,
.init_machine = lubbock_init,
* published by the Free Software Foundation.
*/
#include <linux/gpio.h>
+#include <linux/gpio/machine.h>
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/syscore_ops.h>
GPIO1_GPIO | WAKEUP_ON_EDGE_BOTH,
};
-static unsigned long mainstone_irq_enabled;
-
-static void mainstone_mask_irq(struct irq_data *d)
-{
- int mainstone_irq = (d->irq - MAINSTONE_IRQ(0));
- MST_INTMSKENA = (mainstone_irq_enabled &= ~(1 << mainstone_irq));
-}
-
-static void mainstone_unmask_irq(struct irq_data *d)
-{
- int mainstone_irq = (d->irq - MAINSTONE_IRQ(0));
- /* the irq can be acknowledged only if deasserted, so it's done here */
- MST_INTSETCLR &= ~(1 << mainstone_irq);
- MST_INTMSKENA = (mainstone_irq_enabled |= (1 << mainstone_irq));
-}
-
-static struct irq_chip mainstone_irq_chip = {
- .name = "FPGA",
- .irq_ack = mainstone_mask_irq,
- .irq_mask = mainstone_mask_irq,
- .irq_unmask = mainstone_unmask_irq,
-};
-
-static void mainstone_irq_handler(unsigned int irq, struct irq_desc *desc)
-{
- unsigned long pending = MST_INTSETCLR & mainstone_irq_enabled;
- do {
- /* clear useless edge notification */
- desc->irq_data.chip->irq_ack(&desc->irq_data);
- if (likely(pending)) {
- irq = MAINSTONE_IRQ(0) + __ffs(pending);
- generic_handle_irq(irq);
- }
- pending = MST_INTSETCLR & mainstone_irq_enabled;
- } while (pending);
-}
-
-static void __init mainstone_init_irq(void)
-{
- int irq;
-
- pxa27x_init_irq();
-
- /* setup extra Mainstone irqs */
- for(irq = MAINSTONE_IRQ(0); irq <= MAINSTONE_IRQ(15); irq++) {
- irq_set_chip_and_handler(irq, &mainstone_irq_chip,
- handle_level_irq);
- if (irq == MAINSTONE_IRQ(10) || irq == MAINSTONE_IRQ(14))
- set_irq_flags(irq, IRQF_VALID | IRQF_PROBE | IRQF_NOAUTOEN);
- else
- set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
- }
- set_irq_flags(MAINSTONE_IRQ(8), 0);
- set_irq_flags(MAINSTONE_IRQ(12), 0);
-
- MST_INTMSKENA = 0;
- MST_INTSETCLR = 0;
-
- irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), mainstone_irq_handler);
- irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING);
-}
-
-#ifdef CONFIG_PM
-
-static void mainstone_irq_resume(void)
-{
- MST_INTMSKENA = mainstone_irq_enabled;
-}
-
-static struct syscore_ops mainstone_irq_syscore_ops = {
- .resume = mainstone_irq_resume,
-};
-
-static int __init mainstone_irq_device_init(void)
-{
- if (machine_is_mainstone())
- register_syscore_ops(&mainstone_irq_syscore_ops);
-
- return 0;
-}
-
-device_initcall(mainstone_irq_device_init);
-
-#endif
-
-
static struct resource smc91x_resources[] = {
[0] = {
.start = (MST_ETH_PHYS + 0x300),
},
};
+static struct resource mst_cplds_resources[] = {
+ [0] = {
+ .start = MST_FPGA_PHYS + 0xc0,
+ .end = MST_FPGA_PHYS + 0xe0 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+ .start = PXA_GPIO_TO_IRQ(0),
+ .end = PXA_GPIO_TO_IRQ(0),
+ .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
+ },
+ [2] = {
+ .start = MAINSTONE_IRQ(0),
+ .end = MAINSTONE_IRQ(15),
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct platform_device mst_cplds_device = {
+ .name = "pxa_cplds_irqs",
+ .id = -1,
+ .resource = &mst_cplds_resources[0],
+ .num_resources = 3,
+};
+
static struct platform_device *platform_devices[] __initdata = {
&smc91x_device,
&mst_flash_device[0],
&mst_flash_device[1],
&mst_gpio_keys_device,
+ &mst_cplds_device,
};
static struct pxaohci_platform_data mainstone_ohci_platform_data = {
.atag_offset = 0x100, /* BLOB boot parameter setting */
.map_io = mainstone_map_io,
.nr_irqs = MAINSTONE_NR_IRQS,
- .init_irq = mainstone_init_irq,
+ .init_irq = pxa27x_init_irq,
.handle_irq = pxa27x_handle_irq,
.init_time = pxa_timer_init,
.init_machine = mainstone_init,
--- /dev/null
+/*
+ * Intel Reference Systems cplds
+ *
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * Cplds motherboard driver, supporting lubbock and mainstone SoC board.
+ */
+
+#include <linux/bitops.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+
+#define FPGA_IRQ_MASK_EN 0x0
+#define FPGA_IRQ_SET_CLR 0x10
+
+#define CPLDS_NB_IRQ 32
+
+struct cplds {
+ void __iomem *base;
+ int irq;
+ unsigned int irq_mask;
+ struct gpio_desc *gpio0;
+ struct irq_domain *irqdomain;
+};
+
+static irqreturn_t cplds_irq_handler(int in_irq, void *d)
+{
+ struct cplds *fpga = d;
+ unsigned long pending;
+ unsigned int bit;
+
+ pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask;
+ for_each_set_bit(bit, &pending, CPLDS_NB_IRQ)
+ generic_handle_irq(irq_find_mapping(fpga->irqdomain, bit));
+
+ return IRQ_HANDLED;
+}
+
+static void cplds_irq_mask_ack(struct irq_data *d)
+{
+ struct cplds *fpga = irq_data_get_irq_chip_data(d);
+ unsigned int cplds_irq = irqd_to_hwirq(d);
+ unsigned int set, bit = BIT(cplds_irq);
+
+ fpga->irq_mask &= ~bit;
+ writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
+ set = readl(fpga->base + FPGA_IRQ_SET_CLR);
+ writel(set & ~bit, fpga->base + FPGA_IRQ_SET_CLR);
+}
+
+static void cplds_irq_unmask(struct irq_data *d)
+{
+ struct cplds *fpga = irq_data_get_irq_chip_data(d);
+ unsigned int cplds_irq = irqd_to_hwirq(d);
+ unsigned int bit = BIT(cplds_irq);
+
+ fpga->irq_mask |= bit;
+ writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
+}
+
+static struct irq_chip cplds_irq_chip = {
+ .name = "pxa_cplds",
+ .irq_mask_ack = cplds_irq_mask_ack,
+ .irq_unmask = cplds_irq_unmask,
+ .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE,
+};
+
+static int cplds_irq_domain_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hwirq)
+{
+ struct cplds *fpga = d->host_data;
+
+ irq_set_chip_and_handler(irq, &cplds_irq_chip, handle_level_irq);
+ irq_set_chip_data(irq, fpga);
+
+ return 0;
+}
+
+static const struct irq_domain_ops cplds_irq_domain_ops = {
+ .xlate = irq_domain_xlate_twocell,
+ .map = cplds_irq_domain_map,
+};
+
+static int cplds_resume(struct platform_device *pdev)
+{
+ struct cplds *fpga = platform_get_drvdata(pdev);
+
+ writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
+
+ return 0;
+}
+
+static int cplds_probe(struct platform_device *pdev)
+{
+ struct resource *res;
+ struct cplds *fpga;
+ int ret;
+ int base_irq;
+ unsigned long irqflags = 0;
+
+ fpga = devm_kzalloc(&pdev->dev, sizeof(*fpga), GFP_KERNEL);
+ if (!fpga)
+ return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+ if (res) {
+ fpga->irq = (unsigned int)res->start;
+ irqflags = res->flags;
+ }
+ if (!fpga->irq)
+ return -ENODEV;
+
+ base_irq = platform_get_irq(pdev, 1);
+ if (base_irq < 0)
+ base_irq = 0;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ fpga->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(fpga->base))
+ return PTR_ERR(fpga->base);
+
+ platform_set_drvdata(pdev, fpga);
+
+ writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
+ writel(0, fpga->base + FPGA_IRQ_SET_CLR);
+
+ ret = devm_request_irq(&pdev->dev, fpga->irq, cplds_irq_handler,
+ irqflags, dev_name(&pdev->dev), fpga);
+ if (ret == -ENOSYS)
+ return -EPROBE_DEFER;
+
+ if (ret) {
+ dev_err(&pdev->dev, "couldn't request main irq%d: %d\n",
+ fpga->irq, ret);
+ return ret;
+ }
+
+ irq_set_irq_wake(fpga->irq, 1);
+ fpga->irqdomain = irq_domain_add_linear(pdev->dev.of_node,
+ CPLDS_NB_IRQ,
+ &cplds_irq_domain_ops, fpga);
+ if (!fpga->irqdomain)
+ return -ENODEV;
+
+ if (base_irq) {
+ ret = irq_create_strict_mappings(fpga->irqdomain, base_irq, 0,
+ CPLDS_NB_IRQ);
+ if (ret) {
+ dev_err(&pdev->dev, "couldn't create the irq mapping %d..%d\n",
+ base_irq, base_irq + CPLDS_NB_IRQ);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static int cplds_remove(struct platform_device *pdev)
+{
+ struct cplds *fpga = platform_get_drvdata(pdev);
+
+ irq_set_chip_and_handler(fpga->irq, NULL, NULL);
+
+ return 0;
+}
+
+static const struct of_device_id cplds_id_table[] = {
+ { .compatible = "intel,lubbock-cplds-irqs", },
+ { .compatible = "intel,mainstone-cplds-irqs", },
+ { }
+};
+MODULE_DEVICE_TABLE(of, cplds_id_table);
+
+static struct platform_driver cplds_driver = {
+ .driver = {
+ .name = "pxa_cplds_irqs",
+ .of_match_table = of_match_ptr(cplds_id_table),
+ },
+ .probe = cplds_probe,
+ .remove = cplds_remove,
+ .resume = cplds_resume,
+};
+
+module_platform_driver(cplds_driver);
+
+MODULE_DESCRIPTION("PXA Cplds interrupts driver");
+MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik@free.fr>");
+MODULE_LICENSE("GPL");
SGRF_PCLK_WDT_GATE | SGRF_FAST_BOOT_EN
| SGRF_PCLK_WDT_GATE_WRITE | SGRF_FAST_BOOT_EN_WRITE);
+ /*
+ * The dapswjdp can not auto reset before resume, that cause it may
+ * access some illegal address during resume. Let's disable it before
+ * suspend, and the MASKROM will enable it back.
+ */
+ regmap_write(sgrf_regmap, RK3288_SGRF_CPU_CON0, SGRF_DAPDEVICEEN_WRITE);
+
/* booting address of resuming system is from this register value */
regmap_write(sgrf_regmap, RK3288_SGRF_FAST_BOOT_ADDR,
rk3288_bootram_phy);
#define SGRF_FAST_BOOT_EN BIT(8)
#define SGRF_FAST_BOOT_EN_WRITE BIT(24)
+#define RK3288_SGRF_CPU_CON0 (0x40)
+#define SGRF_DAPDEVICEEN BIT(0)
+#define SGRF_DAPDEVICEEN_WRITE BIT(16)
+
#define RK3288_CRU_MODE_CON 0x50
#define RK3288_CRU_SEL0_CON 0x60
#define RK3288_CRU_SEL1_CON 0x64
#include "pm.h"
#define RK3288_GRF_SOC_CON0 0x244
+#define RK3288_TIMER6_7_PHYS 0xff810000
static void __init rockchip_timer_init(void)
{
if (of_machine_is_compatible("rockchip,rk3288")) {
struct regmap *grf;
+ void __iomem *reg_base;
+
+ /*
+ * Most/all uboot versions for rk3288 don't enable timer7
+ * which is needed for the architected timer to work.
+ * So make sure it is running during early boot.
+ */
+ reg_base = ioremap(RK3288_TIMER6_7_PHYS, SZ_16K);
+ if (reg_base) {
+ writel(0, reg_base + 0x30);
+ writel(0xffffffff, reg_base + 0x20);
+ writel(0xffffffff, reg_base + 0x24);
+ writel(1, reg_base + 0x30);
+ dsb();
+ iounmap(reg_base);
+ } else {
+ pr_err("rockchip: could not map timer7 registers\n");
+ }
/*
* Disable auto jtag/sdmmc switching that causes issues
* arm_iommu_attach_device function.
*/
struct dma_iommu_mapping *
-arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size)
{
unsigned int bits = size >> PAGE_SHIFT;
unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long);
int extensions = 1;
int err = -ENOMEM;
+ /* currently only 32-bit DMA address space is supported */
+ if (size > DMA_BIT_MASK(32) + 1)
+ return ERR_PTR(-ERANGE);
+
if (!bitmap_size)
return ERR_PTR(-EINVAL);
if (!iommu)
return false;
- /*
- * currently arm_iommu_create_mapping() takes a max of size_t
- * for size param. So check this limit for now.
- */
- if (size > SIZE_MAX)
- return false;
-
mapping = arm_iommu_create_mapping(dev->bus, dma_base, size);
if (IS_ERR(mapping)) {
pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
void *kmap;
int type;
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
int idx, type;
struct page *page = pfn_to_page(pfn);
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
}
/*
- * Find the first non-section-aligned page, and point
+ * Find the first non-pmd-aligned page, and point
* memblock_limit at it. This relies on rounding the
- * limit down to be section-aligned, which happens at
- * the end of this function.
+ * limit down to be pmd-aligned, which happens at the
+ * end of this function.
*
* With this algorithm, the start or end of almost any
- * bank can be non-section-aligned. The only exception
- * is that the start of the bank 0 must be section-
+ * bank can be non-pmd-aligned. The only exception is
+ * that the start of the bank 0 must be section-
* aligned, since otherwise memory would need to be
* allocated when mapping the start of bank 0, which
* occurs before any free memory is mapped.
*/
if (!memblock_limit) {
- if (!IS_ALIGNED(block_start, SECTION_SIZE))
+ if (!IS_ALIGNED(block_start, PMD_SIZE))
memblock_limit = block_start;
- else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+ else if (!IS_ALIGNED(block_end, PMD_SIZE))
memblock_limit = arm_lowmem_limit;
}
high_memory = __va(arm_lowmem_limit - 1) + 1;
/*
- * Round the memblock limit down to a section size. This
+ * Round the memblock limit down to a pmd size. This
* helps to ensure that we will allocate memory from the
- * last full section, which should be mapped.
+ * last full pmd, which should be mapped.
*/
if (memblock_limit)
- memblock_limit = round_down(memblock_limit, SECTION_SIZE);
+ memblock_limit = round_down(memblock_limit, PMD_SIZE);
if (!memblock_limit)
memblock_limit = arm_lowmem_limit;
*
* These are the low level assembler for performing cache and TLB
* functions on the arm1020.
- *
- * CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt
*/
#include <linux/linkage.h>
#include <linux/init.h>
*
* These are the low level assembler for performing cache and TLB
* functions on the arm1020e.
- *
- * CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt
*/
#include <linux/linkage.h>
#include <linux/init.h>
.type __arm925_setup, #function
__arm925_setup:
mov r0, #0
-#if defined(CONFIG_CPU_ICACHE_STREAMING_DISABLE)
- orr r0,r0,#1 << 7
-#endif
/* Transparent on, D-cache clean & flush mode. See NOTE2 above */
orr r0,r0,#1 << 1 @ transparent mode on
PMD_SECT_AP_WRITE | \
PMD_SECT_AP_READ
initfn __feroceon_setup, __\name\()_proc_info
- .long __feroceon_setup
.long cpu_arch_name
.long cpu_elf_name
.long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
#define SEEN_DATA (1 << (BPF_MEMWORDS + 3))
#define FLAG_NEED_X_RESET (1 << 0)
+#define FLAG_IMM_OVERFLOW (1 << 1)
struct jit_ctx {
const struct bpf_prog *skf;
/* PC in ARM mode == address of the instruction + 8 */
imm = offset - (8 + ctx->idx * 4);
+ if (imm & ~0xfff) {
+ /*
+ * literal pool is too far, signal it into flags. we
+ * can only detect it on the second pass unfortunately.
+ */
+ ctx->flags |= FLAG_IMM_OVERFLOW;
+ return 0;
+ }
+
return imm;
}
return;
}
#endif
- if (rm != ARM_R0)
- emit(ARM_MOV_R(ARM_R0, rm), ctx);
+
+ /*
+ * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4
+ * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into
+ * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm
+ * before using it as a source for ARM_R1.
+ *
+ * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is
+ * ARM_R5 (r_X) so there is no particular register overlap
+ * issues.
+ */
if (rn != ARM_R1)
emit(ARM_MOV_R(ARM_R1, rn), ctx);
+ if (rm != ARM_R0)
+ emit(ARM_MOV_R(ARM_R0, rm), ctx);
ctx->seen |= SEEN_CALL;
emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
default:
return -1;
}
+
+ if (ctx->flags & FLAG_IMM_OVERFLOW)
+ /*
+ * this instruction generated an overflow when
+ * trying to access the literal pool, so
+ * delegate this filter to the kernel interpreter.
+ */
+ return -1;
}
/* compute offsets only during the first pass */
ctx.idx = 0;
build_prologue(&ctx);
- build_body(&ctx);
+ if (build_body(&ctx) < 0) {
+#if __LINUX_ARM_ARCH__ < 7
+ if (ctx.imm_count)
+ kfree(ctx.imms);
+#endif
+ bpf_jit_binary_free(header);
+ goto out;
+ }
build_epilogue(&ctx);
flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
void xen_arch_post_suspend(int suspend_cancelled) { }
void xen_timer_resume(void) { }
void xen_arch_resume(void) { }
+void xen_arch_suspend(void) { }
/* In the hypervisor.S file. */
clock-output-names = "juno_mb:clk25mhz";
};
+ v2m_refclk1mhz: refclk1mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <1000000>;
+ clock-output-names = "juno_mb:refclk1mhz";
+ };
+
+ v2m_refclk32khz: refclk32khz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <32768>;
+ clock-output-names = "juno_mb:refclk32khz";
+ };
+
motherboard {
compatible = "arm,vexpress,v2p-p1", "simple-bus";
#address-cells = <2>; /* SMB chipselect number and offset */
#size-cells = <1>;
ranges = <0 3 0 0x200000>;
+ v2m_sysctl: sysctl@020000 {
+ compatible = "arm,sp810", "arm,primecell";
+ reg = <0x020000 0x1000>;
+ clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&mb_clk24mhz>;
+ clock-names = "refclk", "timclk", "apb_pclk";
+ #clock-cells = <1>;
+ clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+ };
+
mmci@050000 {
compatible = "arm,pl180", "arm,primecell";
reg = <0x050000 0x1000>;
compatible = "arm,sp804", "arm,primecell";
reg = <0x110000 0x10000>;
interrupts = <9>;
- clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
- clock-names = "timclken1", "apb_pclk";
+ clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&mb_clk24mhz>;
+ clock-names = "timclken1", "timclken2", "apb_pclk";
};
v2m_timer23: timer@120000 {
compatible = "arm,sp804", "arm,primecell";
reg = <0x120000 0x10000>;
interrupts = <9>;
- clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
- clock-names = "timclken1", "apb_pclk";
+ clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&mb_clk24mhz>;
+ clock-names = "timclken1", "timclken2", "apb_pclk";
};
rtc@170000 {
#include "mt8173.dtsi"
/ {
- model = "mediatek,mt8173-evb";
+ model = "MediaTek MT8173 evaluation board";
+ compatible = "mediatek,mt8173-evb", "mediatek,mt8173";
aliases {
serial0 = &uart0;
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+ put_unaligned_le32(ctx->crc, out);
+ return 0;
+}
+
+static int chksumc_final(struct shash_desc *desc, u8 *out)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
put_unaligned_le32(~ctx->crc, out);
return 0;
}
static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out)
{
- put_unaligned_le32(~crc32_arm64_le_hw(crc, data, len), out);
+ put_unaligned_le32(crc32_arm64_le_hw(crc, data, len), out);
return 0;
}
{
struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
+ mctx->key = 0;
+ return 0;
+}
+
+static int crc32c_cra_init(struct crypto_tfm *tfm)
+{
+ struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
+
mctx->key = ~0;
return 0;
}
.setkey = chksum_setkey,
.init = chksum_init,
.update = chksumc_update,
- .final = chksum_final,
+ .final = chksumc_final,
.finup = chksumc_finup,
.digest = chksumc_digest,
.descsize = sizeof(struct chksum_desc_ctx),
.cra_alignmask = 0,
.cra_ctxsize = sizeof(struct chksum_ctx),
.cra_module = THIS_MODULE,
- .cra_init = crc32_cra_init,
+ .cra_init = crc32c_cra_init,
}
};
static int sha1_ce_final(struct shash_desc *desc, u8 *out)
{
+ struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+
+ sctx->finalize = 0;
kernel_neon_begin_partial(16);
sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform);
kernel_neon_end();
static int sha256_ce_final(struct shash_desc *desc, u8 *out)
{
+ struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+
+ sctx->finalize = 0;
kernel_neon_begin_partial(28);
sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
kernel_neon_end();
#define read_barrier_depends() do { } while(0)
#define smp_read_barrier_depends() do { } while(0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define nop() asm volatile("nop");
#define smp_mb__before_atomic() smp_mb()
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
+ pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
ret = -ENOSYS;
}
- pagefault_enable(); /* subsumes preempt_enable() */
+ pagefault_enable();
if (!ret) {
switch (cmp) {
#define ioremap(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define ioremap_nocache(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
+#define ioremap_wt(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define iounmap __iounmap
/*
#define topology_physical_package_id(cpu) (cpu_topology[cpu].cluster_id)
#define topology_core_id(cpu) (cpu_topology[cpu].core_id)
#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
#include <asm/cacheflush.h>
#include <asm/alternative.h>
#include <asm/cpufeature.h>
-#include <asm/insn.h>
#include <linux/stop_machine.h>
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
struct alt_instr *end;
};
-/*
- * Decode the imm field of a b/bl instruction, and return the byte
- * offset as a signed value (so it can be used when computing a new
- * branch target).
- */
-static s32 get_branch_offset(u32 insn)
-{
- s32 imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn);
-
- /* sign-extend the immediate before turning it into a byte offset */
- return (imm << 6) >> 4;
-}
-
-static u32 get_alt_insn(u8 *insnptr, u8 *altinsnptr)
-{
- u32 insn;
-
- aarch64_insn_read(altinsnptr, &insn);
-
- /* Stop the world on instructions we don't support... */
- BUG_ON(aarch64_insn_is_cbz(insn));
- BUG_ON(aarch64_insn_is_cbnz(insn));
- BUG_ON(aarch64_insn_is_bcond(insn));
- /* ... and there is probably more. */
-
- if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) {
- enum aarch64_insn_branch_type type;
- unsigned long target;
-
- if (aarch64_insn_is_b(insn))
- type = AARCH64_INSN_BRANCH_NOLINK;
- else
- type = AARCH64_INSN_BRANCH_LINK;
-
- target = (unsigned long)altinsnptr + get_branch_offset(insn);
- insn = aarch64_insn_gen_branch_imm((unsigned long)insnptr,
- target, type);
- }
-
- return insn;
-}
-
static int __apply_alternatives(void *alt_region)
{
struct alt_instr *alt;
u8 *origptr, *replptr;
for (alt = region->begin; alt < region->end; alt++) {
- u32 insn;
- int i;
-
if (!cpus_have_cap(alt->cpufeature))
continue;
origptr = (u8 *)&alt->orig_offset + alt->orig_offset;
replptr = (u8 *)&alt->alt_offset + alt->alt_offset;
-
- for (i = 0; i < alt->alt_len; i += sizeof(insn)) {
- insn = get_alt_insn(origptr + i, replptr + i);
- aarch64_insn_write(origptr + i, insn);
- }
-
+ memcpy(origptr, replptr, alt->alt_len);
flush_icache_range((uintptr_t)origptr,
(uintptr_t)(origptr + alt->alt_len));
}
if (!cpu_pmu)
return -ENODEV;
- irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
- if (!irqs)
- return -ENOMEM;
-
/* Don't bother with PPIs; they're already affine */
irq = platform_get_irq(pdev, 0);
if (irq >= 0 && irq_is_percpu(irq))
return 0;
+ irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+ if (!irqs)
+ return -ENOMEM;
+
for (i = 0; i < pdev->num_resources; ++i) {
struct device_node *dn;
int cpu;
for (j = 0; j < pg_level[i].num; j++)
pg_level[i].mask |= pg_level[i].bits[j].mask;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
address_markers[VMEMMAP_START_NR].start_address =
(unsigned long)virt_to_page(PAGE_OFFSET);
address_markers[VMEMMAP_END_NR].start_address =
(unsigned long)virt_to_page(high_memory);
+#endif
pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
&ptdump_fops);
* If we're in an interrupt or have no user context, we must not take
* the fault.
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
return -EINVAL;
}
- imm64 = (u64)insn1.imm << 32 | imm;
+ imm64 = (u64)insn1.imm << 32 | (u32)imm;
emit_a64_mov_i64(dst, imm64, ctx);
return 1;
if something tries to do an invalid cmpxchg(). */
extern void __cmpxchg_called_with_bad_pointer(void);
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
__iounmap(addr)
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
#define cached(addr) P1SEGADDR(addr)
#define uncached(addr) P2SEGADDR(addr)
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
#include <linux/pagemap.h>
#include <linux/kdebug.h>
#include <linux/kprobes.h>
+#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/sysreg.h>
#include <asm/tlb.h>
-#include <asm/uaccess.h>
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, int trap)
* If we're in an interrupt or have no user context, we must
* not take the fault...
*/
- if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
+ if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM))
goto no_context;
local_irq_enable();
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/byteorder.h>
+#include <asm/def_LPBlackfin.h>
#define __raw_readb bfin_read8
#define __raw_readw bfin_read16
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <arch/system.h>
extern int find_fixup_code(struct pt_regs *);
info.si_code = SEGV_MAPERR;
/*
- * If we're in an interrupt or "atomic" operation or have no
+ * If we're in an interrupt, have pagefaults disabled or have no
* user context, we must not take the fault.
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
#ifdef __KERNEL__
+#define ARCH_HAS_IOREMAP_WT
+
#include <linux/types.h>
#include <asm/virtconvert.h>
#include <asm/string.h>
return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
}
-static inline void __iomem *ioremap_writethrough(unsigned long physaddr, unsigned long size)
+static inline void __iomem *ioremap_wt(unsigned long physaddr, unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
}
#include <linux/kernel.h>
#include <linux/ptrace.h>
#include <linux/hardirq.h>
+#include <linux/uaccess.h>
#include <asm/pgtable.h>
-#include <asm/uaccess.h>
#include <asm/gdb-stub.h>
/*****************************************************************************/
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(__frame))
unsigned long paddr;
int type;
+ preempt_disable();
pagefault_disable();
type = kmap_atomic_idx_push();
paddr = page_to_phys(page);
}
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
* looks just like atomic_cmpxchg on our arch currently with a bunch of
* variable casting.
*/
-#define __HAVE_ARCH_CMPXCHG 1
#define cmpxchg(ptr, old, new) \
({ \
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
___p1; \
})
-/*
- * XXX check on this ---I suspect what Linus really wants here is
- * acquire vs release semantics but we can't discuss this stuff with
- * Linus just yet. Grrr...
- */
-#define set_mb(var, value) do { (var) = (value); mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
/*
* The group barrier in front of the rsm & ssm are necessary to ensure
#ifndef __IA64_INTR_REMAPPING_H
#define __IA64_INTR_REMAPPING_H
#define irq_remapping_enabled 0
-#define dmar_alloc_hwirq create_irq
-#define dmar_free_hwirq destroy_irq
#endif
#define topology_physical_package_id(cpu) (cpu_data(cpu)->socket_id)
#define topology_core_id(cpu) (cpu_data(cpu)->core_id)
#define topology_core_cpumask(cpu) (&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
#endif
extern void arch_fix_phys_package_id(int num, u32 slot);
* indicated by comparing RETURN with OLD.
*/
-#define __HAVE_ARCH_CMPXCHG 1
-
/*
* This function doesn't exist, so you'll get a linker error
* if something tries to do an invalid cmpxchg().
.irq_retrigger = ia64_msi_retrigger_irq,
};
-static int
+static void
msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
{
struct irq_cfg *cfg = irq_cfg + irq;
MSI_DATA_LEVEL_ASSERT |
MSI_DATA_DELIVERY_FIXED |
MSI_DATA_VECTOR(cfg->vector);
- return 0;
}
-int arch_setup_dmar_msi(unsigned int irq)
+int dmar_alloc_hwirq(int id, int node, void *arg)
{
- int ret;
+ int irq;
struct msi_msg msg;
- ret = msi_compose_msg(NULL, irq, &msg);
- if (ret < 0)
- return ret;
- dmar_msi_write(irq, &msg);
- irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
- return 0;
+ irq = create_irq();
+ if (irq > 0) {
+ irq_set_handler_data(irq, arg);
+ irq_set_chip_and_handler_name(irq, &dmar_msi_type,
+ handle_edge_irq, "edge");
+ msi_compose_msg(NULL, irq, &msg);
+ dmar_msi_write(irq, &msg);
+ }
+
+ return irq;
+}
+
+void dmar_free_hwirq(int irq)
+{
+ irq_set_handler_data(irq, NULL);
+ destroy_irq(irq);
}
#endif /* CONFIG_INTEL_IOMMU */
volatile int ia64_cpu_to_sapicid[NR_CPUS];
EXPORT_SYMBOL(ia64_cpu_to_sapicid);
-static volatile cpumask_t cpu_callin_map;
+static cpumask_t cpu_callin_map;
struct smp_boot_data smp_boot_data __initdata;
for (timeout = 0; timeout < 100000; timeout++) {
if (cpumask_test_cpu(cpu, &cpu_callin_map))
break; /* It has booted */
+ barrier(); /* Make sure we re-read cpu_callin_map */
udelay(100);
}
Dprintk("\n");
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/prefetch.h>
+#include <linux/uaccess.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
-#include <asm/uaccess.h>
extern int die(char *, struct pt_regs *, long);
/*
* If we're in an interrupt or have no user context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
#ifdef CONFIG_VIRTUAL_MEM_MAP
int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
{
- struct pci_controller *controller = bridge->bus->sysdata;
-
- ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+ /*
+ * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+ * here, pci_create_root_bus() has been called by someone else and
+ * sysdata is likely to be different from what we expect. Let it go in
+ * that case.
+ */
+ if (!bridge->dev.parent) {
+ struct pci_controller *controller = bridge->bus->sysdata;
+ ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+ }
return 0;
}
((__typeof__(*(ptr)))__xchg_local((unsigned long)(x), (ptr), \
sizeof(*(ptr))))
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long
__cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new)
{
extern void iounmap(volatile void __iomem *addr);
#define ioremap_nocache(off,size) ioremap(off,size)
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
/*
* IO bus memory addresses are also 1:1 with the physical address
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space.
*
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space.
*
* strlen_user: - Get the size of a string in user space.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
/*
* For flush_tlb_others()
*/
-static volatile cpumask_t flush_cpumask;
+static cpumask_t flush_cpumask;
static struct mm_struct *flush_mm;
static struct vm_area_struct *flush_vma;
static volatile unsigned long flush_va;
*/
send_IPI_mask(&cpumask, INVALIDATE_TLB_IPI, 0);
- while (!cpumask_empty((cpumask_t*)&flush_cpumask)) {
+ while (!cpumask_empty(&flush_cpumask)) {
/* nothing. lockup detection does not belong here */
mb();
}
__flush_tlb_page(va);
}
}
- cpumask_clear_cpu(cpu_id, (cpumask_t*)&flush_cpumask);
+ cpumask_clear_cpu(cpu_id, &flush_cpumask);
}
/*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*/
#include <linux/vt_kern.h> /* For unblank_screen() */
#include <linux/highmem.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
#include <asm/m32r.h>
-#include <asm/uaccess.h>
#include <asm/hardirq.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
mm = tsk->mm;
/*
- * If we're in an interrupt or have no user context or are running in an
- * atomic region then we must not take the fault..
+ * If we're in an interrupt or have no user context or have pagefaults
+ * disabled then we must not take the fault.
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto bad_area_nosemaphore;
if (error_code & ACE_USERMODE)
* indicated by comparing RETURN with OLD.
*/
#ifdef CONFIG_RMW_INSNS
-#define __HAVE_ARCH_CMPXCHG 1
static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
unsigned long new, int size)
#ifdef __KERNEL__
+#define ARCH_HAS_IOREMAP_WT
+
#include <linux/compiler.h>
#include <asm/raw_io.h>
#include <asm/virtconvert.h>
{
return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
}
-static inline void __iomem *ioremap_writethrough(unsigned long physaddr,
+static inline void __iomem *ioremap_wt(unsigned long physaddr,
unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
#ifdef __KERNEL__
+#define ARCH_HAS_IOREMAP_WT
+
#include <asm/virtconvert.h>
#include <asm-generic/iomap.h>
{
return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
}
-static inline void *ioremap_writethrough(unsigned long physaddr, unsigned long size)
+static inline void *ioremap_wt(unsigned long physaddr, unsigned long size)
{
return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
}
#define _M68K_IRQFLAGS_H
#include <linux/types.h>
-#ifdef CONFIG_MMU
-#include <linux/preempt_mask.h>
-#endif
#include <linux/preempt.h>
#include <asm/thread_info.h>
#include <asm/entry.h>
#include <linux/ptrace.h>
#include <linux/interrupt.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
#include <asm/setup.h>
#include <asm/traps.h>
-#include <asm/uaccess.h>
#include <asm/pgalloc.h>
extern void die_if_kernel(char *, struct pt_regs *, long);
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
#define read_barrier_depends() do { } while (0)
#define smp_read_barrier_depends() do { } while (0)
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_store_release(p, v) \
do { \
return old;
}
-#define __HAVE_ARCH_CMPXCHG 1
-
#define cmpxchg(ptr, o, n) \
({ \
__typeof__(*(ptr)) _o_ = (o); \
#define ioremap_wc(offset, size) \
__ioremap((offset), (size), _PAGE_WR_COMBINE)
+#define ioremap_wt(offset, size) \
+ __ioremap((offset), (size), 0)
+
#define iounmap(addr) \
__iounmap(addr)
mm = tsk->mm;
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
unsigned long vaddr;
int type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
unsigned long vaddr;
int type;
+ preempt_disable();
pagefault_disable();
type = kmap_atomic_idx_push();
extern void iounmap(void __iomem *addr);
extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
-#define ioremap_writethrough(addr, size) ioremap((addr), (size))
#define ioremap_nocache(addr, size) ioremap((addr), (size))
#define ioremap_fullcache(addr, size) ioremap((addr), (size))
#define ioremap_wc(addr, size) ioremap((addr), (size))
+#define ioremap_wt(addr, size) ioremap((addr), (size))
#endif /* CONFIG_MMU */
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
is_write = 0;
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(faulthandler_disabled() || !mm)) {
if (kernel_mode(regs))
goto bad_area_nosemaphore;
- /* in_atomic() in user mode is really bad,
+ /* faulthandler_disabled() in user mode is really bad,
as is current->mm == NULL. */
- pr_emerg("Page fault in user mode with in_atomic(), mm = %p\n",
- mm);
+ pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n",
+ mm);
pr_emerg("r15 = %lx MSR = %lx\n",
regs->r15, regs->msr);
die("Weird page fault", regs, SIGSEGV);
unsigned long vaddr;
int idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
pagefault_enable();
+ preempt_enable();
return;
}
#endif
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
ifdef CONFIG_MIPS
CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \
- sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/")
+ sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g')
ifdef CONFIG_64BIT
CHECKFLAGS += -m64
endif
/*
* Atheros AR71XX/AR724X/AR913X specific prom routines
*
+ * Copyright (C) 2015 Laurent Fasnacht <l@libres.ch>
* Copyright (C) 2008-2010 Gabor Juhos <juhosg@openwrt.org>
* Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
*
{
fw_init_cmdline();
+#ifdef CONFIG_BLK_DEV_INITRD
/* Read the initrd address from the firmware environment */
initrd_start = fw_getenvl("initrd_start");
if (initrd_start) {
initrd_start = KSEG0ADDR(initrd_start);
initrd_end = initrd_start + fw_getenvl("initrd_size");
}
+#endif
}
void __init prom_free_prom_memory(void)
ddr_clk_rate = ath79_get_sys_clk_rate("ddr");
ref_clk_rate = ath79_get_sys_clk_rate("ref");
- pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz",
+ pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz\n",
cpu_clk_rate / 1000000, (cpu_clk_rate / 1000) % 1000,
ddr_clk_rate / 1000000, (ddr_clk_rate / 1000) % 1000,
ahb_clk_rate / 1000000, (ahb_clk_rate / 1000) % 1000,
# Makefile for the Cobalt micro systems family specific parts of the kernel
#
-obj-y := buttons.o irq.o lcd.o led.o reset.o rtc.o serial.o setup.o time.o
+obj-y := buttons.o irq.o lcd.o led.o mtd.o reset.o rtc.o serial.o setup.o time.o
obj-$(CONFIG_PCI) += pci.o
-obj-$(CONFIG_MTD_PHYSMAP) += mtd.o
CONFIG_USB_C67X00_HCD=m
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_ROOT_HUB_TT=y
-CONFIG_USB_ISP1760_HCD=m
+CONFIG_USB_ISP1760=m
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_UHCI_HCD=m
CONFIG_USB_R8A66597_HCD=m
#define __WEAK_LLSC_MB " \n"
#endif
-#define set_mb(var, value) \
- do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) \
+ do { WRITE_ONCE(var, value); smp_mb(); } while (0)
#define smp_llsc_mb() __asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))); \
})
-#define __HAVE_ARCH_CMPXCHG 1
-
#define __cmpxchg_asm(ld, st, m, old, new) \
({ \
__typeof(*(m)) __ret; \
\
current->thread.abi = &mips_abi; \
\
- current->thread.fpu.fcr31 = current_cpu_data.fpu_csr31; \
+ current->thread.fpu.fcr31 = boot_cpu_data.fpu_csr31; \
} while (0)
#endif /* CONFIG_32BIT */
else \
current->thread.abi = &mips_abi; \
\
- current->thread.fpu.fcr31 = current_cpu_data.fpu_csr31; \
+ current->thread.fpu.fcr31 = boot_cpu_data.fpu_csr31; \
\
p = personality(current->personality); \
if (p != PER_LINUX32 && p != PER_LINUX) \
#define _PAGE_PRESENT_SHIFT 0
#define _PAGE_PRESENT (1 << _PAGE_PRESENT_SHIFT)
/* R2 or later cores check for RI/XI support to determine _PAGE_READ */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
#define _PAGE_WRITE_SHIFT (_PAGE_PRESENT_SHIFT + 1)
#define _PAGE_WRITE (1 << _PAGE_WRITE_SHIFT)
#else
#define _PAGE_SPLITTING (1 << _PAGE_SPLITTING_SHIFT)
/* Only R2 or newer cores have the XI bit */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
#define _PAGE_NO_EXEC_SHIFT (_PAGE_SPLITTING_SHIFT + 1)
#else
#define _PAGE_GLOBAL_SHIFT (_PAGE_SPLITTING_SHIFT + 1)
#define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT)
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
#endif /* CONFIG_64BIT && CONFIG_MIPS_HUGE_TLB_SUPPORT */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
/* XI - page cannot be executed */
#ifndef _PAGE_NO_EXEC_SHIFT
#define _PAGE_NO_EXEC_SHIFT (_PAGE_MODIFIED_SHIFT + 1)
#define _PAGE_GLOBAL_SHIFT (_PAGE_NO_READ_SHIFT + 1)
#define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT)
-#else /* !CONFIG_CPU_MIPSR2 */
+#else /* !CONFIG_CPU_MIPSR2 && !CONFIG_CPU_MIPSR6 */
#define _PAGE_GLOBAL_SHIFT (_PAGE_MODIFIED_SHIFT + 1)
#define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT)
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
#define _PAGE_VALID_SHIFT (_PAGE_GLOBAL_SHIFT + 1)
#define _PAGE_VALID (1 << _PAGE_VALID_SHIFT)
*/
static inline uint64_t pte_to_entrylo(unsigned long pte_val)
{
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
if (cpu_has_rixi) {
int sa;
#ifdef CONFIG_32BIT
#define SMP_DUMP 0x8
#define SMP_ASK_C0COUNT 0x10
-extern volatile cpumask_t cpu_callin_map;
+extern cpumask_t cpu_callin_map;
/* Mask of CPUs which are currently definitely operating coherently */
extern cpumask_t cpu_coherent_mask;
if (test_and_clear_tsk_thread_flag(prev, TIF_USEDMSA)) \
__fpsave = FP_SAVE_VECTOR; \
(last) = resume(prev, next, task_thread_info(next), __fpsave); \
- disable_msa(); \
} while (0)
#define finish_arch_switch(prev) \
if (cpu_has_userlocal) \
write_c0_userlocal(current_thread_info()->tp_value); \
__restore_watch(); \
+ disable_msa(); \
} while (0)
#endif /* _ASM_SWITCH_TO_H */
#define topology_physical_package_id(cpu) (cpu_data[cpu].package)
#define topology_core_id(cpu) (cpu_data[cpu].core)
#define topology_core_cpumask(cpu) (&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu) (&cpu_sibling_map[cpu])
+#define topology_sibling_cpumask(cpu) (&cpu_sibling_map[cpu])
#endif
#endif /* __ASM_TOPOLOGY_H */
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space.
*
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space.
*
* strlen_user: - Get the size of a string in user space.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
* strnlen_user: - Get the size of a string in user space.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
{
unsigned long sr, mask, fcsr, fcsr0, fcsr1;
+ fcsr = c->fpu_csr31;
mask = FPU_CSR_ALL_X | FPU_CSR_ALL_E | FPU_CSR_ALL_S | FPU_CSR_RM;
sr = read_c0_status();
__enable_fpu(FPU_AS_IS);
- fcsr = read_32bit_cp1_register(CP1_STATUS);
-
fcsr0 = fcsr & mask;
write_32bit_cp1_register(CP1_STATUS, fcsr0);
fcsr0 = read_32bit_cp1_register(CP1_STATUS);
/* Lets see if this is an O32 ELF */
if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) {
- /* FR = 1 for N32 */
- if (ehdr32->e_flags & EF_MIPS_ABI2)
- state->overall_fp_mode = FP_FR1;
- else
- /* Set a good default FPU mode for O32 */
- state->overall_fp_mode = cpu_has_mips_r6 ?
- FP_FRE : FP_FR0;
-
if (ehdr32->e_flags & EF_MIPS_FP64) {
/*
* Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it
(char *)&abiflags,
sizeof(abiflags));
} else {
- /* FR=1 is really the only option for 64-bit */
- state->overall_fp_mode = FP_FR1;
-
if (phdr64->p_type != PT_MIPS_ABIFLAGS)
return 0;
if (phdr64->p_filesz < sizeof(abiflags))
struct elf32_hdr *ehdr = _ehdr;
struct mode_req prog_req, interp_req;
int fp_abi, interp_fp_abi, abi0, abi1, max_abi;
+ bool is_mips64;
if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
return 0;
abi0 = abi1 = fp_abi;
}
- /* ABI limits. O32 = FP_64A, N32/N64 = FP_SOFT */
- max_abi = ((ehdr->e_ident[EI_CLASS] == ELFCLASS32) &&
- (!(ehdr->e_flags & EF_MIPS_ABI2))) ?
- MIPS_ABI_FP_64A : MIPS_ABI_FP_SOFT;
+ is_mips64 = (ehdr->e_ident[EI_CLASS] == ELFCLASS64) ||
+ (ehdr->e_flags & EF_MIPS_ABI2);
+
+ if (is_mips64) {
+ /* MIPS64 code always uses FR=1, thus the default is easy */
+ state->overall_fp_mode = FP_FR1;
+
+ /* Disallow access to the various FPXX & FP64 ABIs */
+ max_abi = MIPS_ABI_FP_SOFT;
+ } else {
+ /* Default to a mode capable of running code expecting FR=0 */
+ state->overall_fp_mode = cpu_has_mips_r6 ? FP_FRE : FP_FR0;
+
+ /* Allow all ABIs we know about */
+ max_abi = MIPS_ABI_FP_64A;
+ }
if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) ||
(abi1 > max_abi && abi1 != MIPS_ABI_FP_UNKNOWN))
int kgdb_early_setup;
#endif
-static unsigned long irq_map[NR_IRQS / BITS_PER_LONG];
+static DECLARE_BITMAP(irq_map, NR_IRQS);
int allocate_irqno(void)
{
#endif
}
-#ifdef DEBUG_STACKOVERFLOW
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
static inline void check_stack_overflow(void)
{
unsigned long sp;
__get_user(value, data + 64);
fcr31 = child->thread.fpu.fcr31;
- mask = current_cpu_data.fpu_msk31;
+ mask = boot_cpu_data.fpu_msk31;
child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
/* FIR may not be written. */
extern int fpcsr_pending(unsigned int __user *fpcsr);
/* Make sure we will not lose FPU ownership */
-#ifdef CONFIG_PREEMPT
-#define lock_fpu_owner() preempt_disable()
-#define unlock_fpu_owner() preempt_enable()
-#else
-#define lock_fpu_owner() pagefault_disable()
-#define unlock_fpu_owner() pagefault_enable()
-#endif
+#define lock_fpu_owner() ({ preempt_disable(); pagefault_disable(); })
+#define unlock_fpu_owner() ({ pagefault_enable(); preempt_enable(); })
#endif /* __SIGNAL_COMMON_H */
static void bmips_wr_vec(unsigned long dst, char *start, char *end)
{
memcpy((void *)dst, start, end - start);
- dma_cache_wback((unsigned long)start, end - start);
+ dma_cache_wback(dst, end - start);
local_flush_icache_range(dst, dst + (end - start));
instruction_hazard();
}
#ifdef CONFIG_MIPS_MT_FPAFF
/* If we have an FPU, enroll ourselves in the FPU-full mask */
if (cpu_has_fpu)
- cpu_set(0, mt_fpu_cpumask);
+ cpumask_set_cpu(0, &mt_fpu_cpumask);
#endif /* CONFIG_MIPS_MT_FPAFF */
}
#include <asm/time.h>
#include <asm/setup.h>
-volatile cpumask_t cpu_callin_map; /* Bitmask of started secondaries */
+cpumask_t cpu_callin_map; /* Bitmask of started secondaries */
int __cpu_number_map[NR_CPUS]; /* Map physical to logical */
EXPORT_SYMBOL(__cpu_number_map);
/*
* Trust is futile. We should really have timeouts ...
*/
- while (!cpumask_test_cpu(cpu, &cpu_callin_map))
+ while (!cpumask_test_cpu(cpu, &cpu_callin_map)) {
udelay(100);
+ schedule();
+ }
synchronise_count_master(cpu);
return 0;
*/
printk("epc : %0*lx %pS\n", field, regs->cp0_epc,
(void *) regs->cp0_epc);
- printk(" %s\n", print_tainted());
printk("ra : %0*lx %pS\n", field, regs->regs[31],
(void *) regs->regs[31]);
{
unsigned long *gpr = &vcpu->arch.gprs[vcpu->arch.io_gpr];
enum emulation_result er = EMULATE_DONE;
- unsigned long curr_pc;
if (run->mmio.len > sizeof(*gpr)) {
kvm_err("Bad MMIO length: %d", run->mmio.len);
goto done;
}
- /*
- * Update PC and hold onto current PC in case there is
- * an error and we want to rollback the PC
- */
- curr_pc = vcpu->arch.pc;
er = update_pc(vcpu, vcpu->arch.pending_load_cause);
if (er == EMULATE_FAIL)
return er;
if (vcpu->mmio_needed == 2)
*gpr = *(int16_t *) run->mmio.data;
else
- *gpr = *(int16_t *) run->mmio.data;
+ *gpr = *(uint16_t *)run->mmio.data;
break;
case 1:
FEXPORT(__strnlen_\func\()_nocheck_asm)
move v0, a0
PTR_ADDU a1, a0 # stop pointer
-1: beq v0, a1, 1f # limit reached?
+1:
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
+ .set noat
+ li AT, 1
+#endif
+ beq v0, a1, 1f # limit reached?
.ifeqs "\func", "kernel"
EX(lb, t0, (v0), .Lfault\@)
.else
.endif
.set noreorder
bnez t0, 1b
-1: PTR_ADDIU v0, 1
+1:
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+ PTR_ADDIU v0, 1
+#else
+ PTR_ADDU v0, AT
+ .set at
+#endif
.set reorder
PTR_SUBU v0, a0
jr ra
#
obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
- bonito-irq.o mem.o machtype.o platform.o
+ bonito-irq.o mem.o machtype.o platform.o serial.o
obj-$(CONFIG_PCI) += pci.o
#
# Serial port support
#
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-loongson-serial-$(CONFIG_SERIAL_8250) := serial.o
-obj-y += $(loongson-serial-m) $(loongson-serial-y)
obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o
obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
if (action & SMP_ASK_C0COUNT) {
BUG_ON(cpu != 0);
c0count = read_c0_count();
- for (i = 1; i < loongson_sysconf.nr_cpus; i++)
+ for (i = 1; i < num_possible_cpus(); i++)
per_cpu(core0_c0count, i) = c0count;
}
}
break;
case FPCREG_RID:
- value = current_cpu_data.fpu_id;
+ value = boot_cpu_data.fpu_id;
break;
default:
(void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
/* Preserve read-only bits. */
- mask = current_cpu_data.fpu_msk31;
+ mask = boot_cpu_data.fpu_msk31;
fcr31 = (value & ~mask) | (fcr31 & mask);
break;
scache_size = addr;
c->scache.linesz = 16 << ((config & R4K_CONF_SB) >> 22);
c->scache.ways = 1;
- c->dcache.waybit = 0; /* does not matter */
+ c->scache.waybit = 0; /* does not matter */
return 1;
}
#include <linux/module.h>
#include <linux/kprobes.h>
#include <linux/perf_event.h>
+#include <linux/uaccess.h>
#include <asm/branch.h>
#include <asm/mmu_context.h>
-#include <asm/uaccess.h>
#include <asm/ptrace.h>
#include <asm/highmem.h> /* For VMALLOC_END */
#include <linux/kdebug.h>
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
unsigned long vaddr;
int idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
if (vaddr < FIXADDR_START) { // FIXME
pagefault_enable();
+ preempt_enable();
return;
}
#endif
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
unsigned long vaddr;
int idx, type;
+ preempt_disable();
pagefault_disable();
type = kmap_atomic_idx_push();
BUG_ON(Page_dcache_dirty(page));
+ preempt_disable();
pagefault_disable();
idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
idx += in_interrupt() ? FIX_N_COLOURS : 0;
write_c0_entryhi(old_ctx);
local_irq_restore(flags);
pagefault_enable();
+ preempt_enable();
}
void copy_user_highpage(struct page *to, struct page *from,
if (cpu_has_rixi) {
/*
- * Enable the no read, no exec bits, and enable large virtual
+ * Enable the no read, no exec bits, and enable large physical
* address.
*/
#ifdef CONFIG_64BIT
sp_off += config_enabled(CONFIG_64BIT) ?
(ARGS_USED_BY_JIT + 1) * RSIZE : RSIZE;
- /*
- * Subtract the bytes for the last registers since we only care about
- * the location on the stack pointer.
- */
- return sp_off - RSIZE;
+ return sp_off;
}
static void build_prologue(struct jit_ctx *ctx)
addr, (type >> ILL_ACC_OFF_S) & ILL_ACC_OFF_M,
type & ILL_ACC_LEN_M);
- rt_memc_w32(REG_ILL_ACC_TYPE, REG_ILL_ACC_TYPE);
+ rt_memc_w32(ILL_INT_STATUS, REG_ILL_ACC_TYPE);
return IRQ_HANDLED;
}
.resource = ip32_rtc_resources,
};
-+static int __init sgio2_rtc_devinit(void)
+static __init int sgio2_rtc_devinit(void)
{
return platform_device_register(&ip32_rtc_device);
}
-device_initcall(sgio2_cmos_devinit);
+device_initcall(sgio2_rtc_devinit);
unsigned long vaddr;
int idx, type;
+ preempt_disable();
pagefault_disable();
if (page < highmem_start_page)
return page_address(page);
if (vaddr < FIXADDR_START) { /* FIXME */
pagefault_enable();
+ preempt_enable();
return;
}
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
#endif /* __KERNEL__ */
}
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
static inline void iounmap(void __iomem *addr)
{
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/vt_kern.h> /* For unblank_screen() */
+#include <linux/uaccess.h>
-#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/hardirq.h>
#include <asm/cpu-regs.h>
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
}
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
/* Pages to physical address... */
#define page_to_phys(page) virt_to_phys(page_to_virt(page))
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
static inline void *kmap_atomic(struct page *page)
{
+ preempt_disable();
pagefault_disable();
return page_address(page);
}
{
flush_kernel_dcache_page_addr(addr);
pagefault_enable();
+ preempt_enable();
}
#define kmap_atomic_prot(page, prot) kmap_atomic(page)
#define xchg(ptr, x) \
((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-#define __HAVE_ARCH_CMPXCHG 1
-
/* bug catcher for when unsupported size is used - won't link */
extern void __cmpxchg_called_with_bad_pointer(void);
#define ELF_HWCAP 0
+#define STACK_RND_MASK (is_32bit_task() ? \
+ 0x7ff >> (PAGE_SHIFT - 12) : \
+ 0x3ffff >> (PAGE_SHIFT - 12))
+
struct mm_struct;
extern unsigned long arch_randomize_brk(struct mm_struct *);
#define arch_randomize_brk arch_randomize_brk
return 1;
}
+/*
+ * Copy architecture-specific thread state
+ */
int
copy_thread(unsigned long clone_flags, unsigned long usp,
- unsigned long arg, struct task_struct *p)
+ unsigned long kthread_arg, struct task_struct *p)
{
struct pt_regs *cregs = &(p->thread.regs);
void *stack = task_stack_page(p);
extern void * const child_return;
if (unlikely(p->flags & PF_KTHREAD)) {
+ /* kernel thread */
memset(cregs, 0, sizeof(struct pt_regs));
if (!usp) /* idle thread */
return 0;
-
- /* kernel thread */
/* Must exit via ret_from_kernel_thread in order
* to call schedule_tail()
*/
#else
cregs->gr[26] = usp;
#endif
- cregs->gr[25] = arg;
+ cregs->gr[25] = kthread_arg;
} else {
/* user thread */
/* usp must be word aligned. This also prevents users from
if (stack_base > STACK_SIZE_MAX)
stack_base = STACK_SIZE_MAX;
+ /* Add space for stack randomization. */
+ stack_base += (STACK_RND_MASK << PAGE_SHIFT);
+
return PAGE_ALIGN(STACK_TOP - stack_base);
}
#include <linux/console.h>
#include <linux/bug.h>
#include <linux/ratelimit.h>
+#include <linux/uaccess.h>
#include <asm/assembly.h>
-#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/traps.h>
* unless pagefault_disable() was called before.
*/
- if (fault_space == 0 && !in_atomic())
+ if (fault_space == 0 && !faulthandler_disabled())
{
pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
parisc_terminate("Kernel Fault", regs, code, fault_address);
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
-#include <asm/uaccess.h>
#include <asm/traps.h>
/* Various important other fields */
int fault;
unsigned int flags;
- if (in_atomic())
+ if (pagefault_disabled())
goto no_context;
tsk = current;
#define rmb() __asm__ __volatile__ ("sync" : : : "memory")
#define wmb() __asm__ __volatile__ ("sync" : : : "memory")
-#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
#ifdef __SUBARCH_HAS_LWSYNC
# define SMPWMB LWSYNC
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
+#define smp_mb__before_spinlock() smp_mb()
#endif /* _ASM_POWERPC_BARRIER_H */
* Compare and exchange - if *p == old, set it to new,
* and return the old value of *p.
*/
-#define __HAVE_ARCH_CMPXCHG 1
static __always_inline unsigned long
__cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
#include <asm/smp.h>
#define topology_physical_package_id(cpu) (cpu_to_chip_id(cpu))
-#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_core_id(cpu) (cpu_to_core_id(cpu))
#endif
uint64_t nip, uint64_t addr)
{
uint64_t srr1;
- int index = __this_cpu_inc_return(mce_nest_count);
+ int index = __this_cpu_inc_return(mce_nest_count) - 1;
struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
/*
if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
return;
- index = __this_cpu_inc_return(mce_queue_count);
+ index = __this_cpu_inc_return(mce_queue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
__this_cpu_dec(mce_queue_count);
*(.opd)
}
+ . = ALIGN(256);
.got : AT(ADDR(.got) - LOAD_OFFSET) {
__toc_start = .;
#ifndef CONFIG_RELOCATABLE
*/
static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
{
- struct kvm_vcpu *vcpu;
+ struct kvm_vcpu *vcpu, *vnext;
int i;
int srcu_idx;
*/
if ((threads_per_core > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
vcpu->arch.ret = -EBUSY;
kvmppc_remove_runnable(vc, vcpu);
wake_up(&vcpu->arch.cpu_run);
if (in_interrupt())
return 0;
- /* This acts as preempt_disable() as well and will make
- * enable_kernel_altivec(). We need to disable page faults
- * as they can call schedule and thus make us lose the VMX
- * context. So on page faults, we just fail which will cause
- * a fallback to the normal non-vmx copy.
+ preempt_disable();
+ /*
+ * We need to disable page faults as they can call schedule and
+ * thus make us lose the VMX context. So on page faults, we just
+ * fail which will cause a fallback to the normal non-vmx copy.
*/
pagefault_disable();
int exit_vmx_usercopy(void)
{
pagefault_enable();
+ preempt_enable();
return 0;
}
#include <linux/ratelimit.h>
#include <linux/context_tracking.h>
#include <linux/hugetlb.h>
+#include <linux/uaccess.h>
#include <asm/firmware.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
-#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/siginfo.h>
#include <asm/debug.h>
if (!arch_irq_disabled_regs(regs))
local_irq_enable();
- if (in_atomic() || mm == NULL) {
+ if (faulthandler_disabled() || mm == NULL) {
if (!user_mode(regs)) {
rc = SIGSEGV;
goto bail;
}
- /* in_atomic() in user mode is really bad,
+ /* faulthandler_disabled() in user mode is really bad,
as is current->mm == NULL. */
printk(KERN_EMERG "Page fault in user mode with "
- "in_atomic() = %d mm = %p\n", in_atomic(), mm);
+ "faulthandler_disabled() = %d mm = %p\n",
+ faulthandler_disabled(), mm);
printk(KERN_EMERG "NIP = %lx MSR = %lx\n",
regs->nip, regs->msr);
die("Weird page fault", regs, SIGSEGV);
unsigned long vaddr;
int idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
pagefault_enable();
+ preempt_enable();
return;
}
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
- pte_t *ptep;
- struct page *page;
+ pte_t *ptep, pte;
unsigned shift;
unsigned long mask, flags;
+ struct page *page = ERR_PTR(-EINVAL);
+
+ local_irq_save(flags);
+ ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+ if (!ptep)
+ goto no_page;
+ pte = READ_ONCE(*ptep);
/*
+ * Verify it is a huge page else bail.
* Transparent hugepages are handled by generic code. We can skip them
* here.
*/
- local_irq_save(flags);
- ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+ if (!shift || pmd_trans_huge(__pmd(pte_val(pte))))
+ goto no_page;
- /* Verify it is a huge page else bail. */
- if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep)) {
- local_irq_restore(flags);
- return ERR_PTR(-EINVAL);
+ if (!pte_present(pte)) {
+ page = NULL;
+ goto no_page;
}
mask = (1UL << shift) - 1;
- page = pte_page(*ptep);
+ page = pte_page(pte);
if (page)
page += (address & mask) / PAGE_SIZE;
+no_page:
local_irq_restore(flags);
return page;
}
* hash fault look at them.
*/
memset(pgtable, 0, PTE_FRAG_SIZE);
+ /*
+ * Serialize against find_linux_pte_or_hugepte which does lock-less
+ * lookup in page tables with local interrupts disabled. For huge pages
+ * it casts pmd_t to pte_t. Since format of pte_t is different from
+ * pmd_t we want to prevent transit from pmd pointing to page table
+ * to pmd pointing to huge page (and back) while interrupts are disabled.
+ * We clear pmd to possibly replace it with page table pointer in
+ * different code paths. So make sure we wait for the parallel
+ * find_linux_pte_or_hugepage to finish.
+ */
+ kick_all_cpus_sync();
return old_pmd;
}
static int mm_is_core_local(struct mm_struct *mm)
{
return cpumask_subset(mm_cpumask(mm),
- topology_thread_cpumask(smp_processor_id()));
+ topology_sibling_cpumask(smp_processor_id()));
}
struct tlb_flush_param {
#define GHASH_DIGEST_SIZE 16
struct ghash_ctx {
- u8 icv[16];
- u8 key[16];
+ u8 key[GHASH_BLOCK_SIZE];
};
struct ghash_desc_ctx {
+ u8 icv[GHASH_BLOCK_SIZE];
+ u8 key[GHASH_BLOCK_SIZE];
u8 buffer[GHASH_BLOCK_SIZE];
u32 bytes;
};
static int ghash_init(struct shash_desc *desc)
{
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+ struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
memset(dctx, 0, sizeof(*dctx));
+ memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE);
return 0;
}
}
memcpy(ctx->key, key, GHASH_BLOCK_SIZE);
- memset(ctx->icv, 0, GHASH_BLOCK_SIZE);
return 0;
}
const u8 *src, unsigned int srclen)
{
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
- struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
unsigned int n;
u8 *buf = dctx->buffer;
int ret;
src += n;
if (!dctx->bytes) {
- ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf,
+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf,
GHASH_BLOCK_SIZE);
if (ret != GHASH_BLOCK_SIZE)
return -EIO;
n = srclen & ~(GHASH_BLOCK_SIZE - 1);
if (n) {
- ret = crypt_s390_kimd(KIMD_GHASH, ctx, src, n);
+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, src, n);
if (ret != n)
return -EIO;
src += n;
return 0;
}
-static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+static int ghash_flush(struct ghash_desc_ctx *dctx)
{
u8 *buf = dctx->buffer;
int ret;
memset(pos, 0, dctx->bytes);
- ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, GHASH_BLOCK_SIZE);
+ ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE);
if (ret != GHASH_BLOCK_SIZE)
return -EIO;
+
+ dctx->bytes = 0;
}
- dctx->bytes = 0;
return 0;
}
static int ghash_final(struct shash_desc *desc, u8 *dst)
{
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
- struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
int ret;
- ret = ghash_flush(ctx, dctx);
+ ret = ghash_flush(dctx);
if (!ret)
- memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE);
+ memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE);
return ret;
}
/* fill page with urandom bytes */
get_random_bytes(pg, PAGE_SIZE);
/* exor page with stckf values */
- for (n = 0; n < sizeof(PAGE_SIZE/sizeof(u64)); n++) {
+ for (n = 0; n < PAGE_SIZE / sizeof(u64); n++) {
u64 *p = ((u64 *)pg) + n;
*p ^= get_tod_clock_fast();
}
#define smp_mb__before_atomic() smp_mb()
#define smp_mb__after_atomic() smp_mb()
-#define set_mb(var, value) do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
#define smp_store_release(p, v) \
do { \
__old; \
})
-#define __HAVE_ARCH_CMPXCHG
-
#define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn) \
({ \
register __typeof__(*(p1)) __old1 asm("2") = (o1); \
#define ioremap_nocache(addr, size) ioremap(addr, size)
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
{
return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
}
-static inline int pmd_pfn(pmd_t pmd)
+static inline unsigned long pmd_pfn(pmd_t pmd)
{
unsigned long origin_mask;
#define _ASM_S390_TIMEX_H
#include <asm/lowcore.h>
+#include <linux/time64.h>
/* The value of the TOD clock for 1.1.1970. */
#define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
void init_cpu_timer(void);
unsigned long long monotonic_clock(void);
-void tod_to_timeval(__u64, struct timespec *);
+void tod_to_timeval(__u64 todval, struct timespec64 *xt);
static inline
-void stck_to_timespec(unsigned long long stck, struct timespec *ts)
+void stck_to_timespec64(unsigned long long stck, struct timespec64 *ts)
{
tod_to_timeval(stck - TOD_UNIX_EPOCH, ts);
}
#define topology_physical_package_id(cpu) (per_cpu(cpu_topology, cpu).socket_id)
#define topology_thread_id(cpu) (per_cpu(cpu_topology, cpu).thread_id)
-#define topology_thread_cpumask(cpu) (&per_cpu(cpu_topology, cpu).thread_mask)
+#define topology_sibling_cpumask(cpu) \
+ (&per_cpu(cpu_topology, cpu).thread_mask)
#define topology_core_id(cpu) (per_cpu(cpu_topology, cpu).core_id)
#define topology_core_cpumask(cpu) (&per_cpu(cpu_topology, cpu).core_mask)
#define topology_book_id(cpu) (per_cpu(cpu_topology, cpu).book_id)
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space.
*
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space.
*
* strlen_user: - Get the size of a string in user space.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
int area, debug_entry_t * entry, char *out_buf)
{
- struct timespec time_spec;
+ struct timespec64 time_spec;
char *except_str;
unsigned long caller;
int rc = 0;
unsigned int level;
level = entry->id.fields.level;
- stck_to_timespec(entry->id.stck, &time_spec);
+ stck_to_timespec64(entry->id.stck, &time_spec);
if (entry->id.fields.exception)
except_str = "*";
else
except_str = "-";
caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN;
- rc += sprintf(out_buf, "%02i %011lu:%06lu %1u %1s %02i %p ",
- area, time_spec.tv_sec, time_spec.tv_nsec / 1000, level,
- except_str, entry->id.fields.cpuid, (void *) caller);
+ rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p ",
+ area, (long long)time_spec.tv_sec,
+ time_spec.tv_nsec / 1000, level, except_str,
+ entry->id.fields.cpuid, (void *)caller);
return rc;
}
EXPORT_SYMBOL(debug_dflt_header_fn);
}
EXPORT_SYMBOL(monotonic_clock);
-void tod_to_timeval(__u64 todval, struct timespec *xt)
+void tod_to_timeval(__u64 todval, struct timespec64 *xt)
{
unsigned long long sec;
static void etr_reset(void);
static void stp_reset(void);
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
{
tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts);
}
-void read_boot_clock(struct timespec *ts)
+void read_boot_clock64(struct timespec64 *ts)
{
tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts);
}
* user context.
*/
fault = VM_FAULT_BADCONTEXT;
- if (unlikely(!user_space_fault(regs) || in_atomic() || !mm))
+ if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm))
goto out;
address = trans_exc_code & __FAIL_ADDR_MASK;
* We get 160 bytes stack space from calling function, but only use
* 11 * 8 byte (old backchain + r15 - r6) for storing registers.
*/
-#define STK_OFF (MAX_BPF_STACK + 8 + 4 + 4 + (160 - 11 * 8))
+#define STK_SPACE (MAX_BPF_STACK + 8 + 4 + 4 + 160)
+#define STK_160_UNUSED (160 - 11 * 8)
+#define STK_OFF (STK_SPACE - STK_160_UNUSED)
#define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */
#define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */
}
/* Setup stack and backchain */
if (jit->seen & SEEN_STACK) {
- /* lgr %bfp,%r15 (BPF frame pointer) */
- EMIT4(0xb9040000, BPF_REG_FP, REG_15);
+ if (jit->seen & SEEN_FUNC)
+ /* lgr %w1,%r15 (backchain) */
+ EMIT4(0xb9040000, REG_W1, REG_15);
+ /* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */
+ EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED);
/* aghi %r15,-STK_OFF */
EMIT4_IMM(0xa70b0000, REG_15, -STK_OFF);
if (jit->seen & SEEN_FUNC)
- /* stg %bfp,152(%r15) (backchain) */
- EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_FP, REG_0,
+ /* stg %w1,152(%r15) (backchain) */
+ EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
REG_15, 152);
}
/*
/*
* Compile one eBPF instruction into s390x code
+ *
+ * NOTE: Use noinline because for gcov (-fprofile-arcs) gcc allocates a lot of
+ * stack space for the large switch statement.
*/
-static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
+static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
{
struct bpf_insn *insn = &fp->insnsi[i];
int jmp_off, last, insn_count = 1;
EMIT4(0xb9160000, dst_reg, rc_reg);
break;
}
- case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / (u32) src */
- case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % (u32) src */
+ case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */
+ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % src */
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
EMIT4_IMM(0xa7090000, REG_W0, 0);
/* lgr %w1,%dst */
EMIT4(0xb9040000, REG_W1, dst_reg);
- /* llgfr %dst,%src (u32 cast) */
- EMIT4(0xb9160000, dst_reg, src_reg);
/* dlgr %w0,%dst */
- EMIT4(0xb9870000, REG_W0, dst_reg);
+ EMIT4(0xb9870000, REG_W0, src_reg);
/* lgr %dst,%rc */
EMIT4(0xb9040000, dst_reg, rc_reg);
break;
EMIT4(0xb9160000, dst_reg, rc_reg);
break;
}
- case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / (u32) imm */
- case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % (u32) imm */
+ case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */
+ case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % imm */
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
EMIT4(0xb9040000, REG_W1, dst_reg);
/* dlg %w0,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
- EMIT_CONST_U64((u32) imm));
+ EMIT_CONST_U64(imm));
/* lgr %dst,%rc */
EMIT4(0xb9040000, dst_reg, rc_reg);
break;
(unsigned long)(o), \
(unsigned long)(n)))
-#define __HAVE_ARCH_CMPXCHG 1
-
#include <asm-generic/cmpxchg-local.h>
#endif /* _ASM_SCORE_CMPXCHG_H */
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
br r3
.section .fixup, "ax"
+99:
br r3
.previous
.section __ex_table, "a"
.align 2
-99:
.word 0b, 99b
.previous
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
+#include <linux/uaccess.h>
/*
* This routine handles page faults. It determines the address,
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (pagefault_disabled() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
#define ctrl_barrier() __asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
#endif
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
#include <asm-generic/barrier.h>
* if something tries to do an invalid cmpxchg(). */
extern void __cmpxchg_called_with_bad_pointer(void);
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
unsigned long new, int size)
{
#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <linux/kdebug.h>
+#include <linux/uaccess.h>
#include <asm/io_trapped.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
/*
* If we're in an interrupt, have no user context or are running
- * in an atomic region then we must not take the fault:
+ * with pagefaults disabled then we must not take the fault:
*/
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(faulthandler_disabled() || !mm)) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
#define dma_rmb() rmb()
#define dma_wmb() wmb()
-#define set_mb(__var, __value) \
- do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+#define smp_store_mb(__var, __value) \
+ do { WRITE_ONCE(__var, __value); membar_safe("#StoreLoad"); } while(0)
#ifdef CONFIG_SMP
#define smp_mb() mb()
*
* Cribbed from <asm-parisc/atomic.h>
*/
-#define __HAVE_ARCH_CMPXCHG 1
/* bug catcher for when unsupported size is used - won't link */
void __cmpxchg_called_with_bad_pointer(void);
#include <asm-generic/cmpxchg-local.h>
-#define __HAVE_ARCH_CMPXCHG 1
-
static inline unsigned long
__cmpxchg_u32(volatile int *m, int old, int new)
{
unsigned int icache_line_size;
unsigned int ecache_size;
unsigned int ecache_line_size;
- int core_id;
+ unsigned short sock_id;
+ unsigned short core_id;
int proc_id;
} cpuinfo_sparc;
void __iomem *ioremap(unsigned long offset, unsigned long size);
#define ioremap_nocache(X,Y) ioremap((X),(Y))
#define ioremap_wc(X,Y) ioremap((X),(Y))
+#define ioremap_wt(X,Y) ioremap((X),(Y))
void iounmap(volatile void __iomem *addr);
/* Create a virtual mapping cookie for an IO port range */
#define ioremap_nocache(X,Y) ioremap((X),(Y))
#define ioremap_wc(X,Y) ioremap((X),(Y))
+#define ioremap_wt(X,Y) ioremap((X),(Y))
static inline void iounmap(volatile void __iomem *addr)
{
" sllx %1, 32, %1\n"
" or %0, %1, %0\n"
" .previous\n"
+ " .section .sun_m7_2insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " sethi %%uhi(%4), %1\n"
+ " sethi %%hi(%4), %0\n"
+ " .word 662b\n"
+ " or %1, %%ulo(%4), %1\n"
+ " or %0, %%lo(%4), %0\n"
+ " .word 663b\n"
+ " sllx %1, 32, %1\n"
+ " or %0, %1, %0\n"
+ " .previous\n"
: "=r" (mask), "=r" (tmp)
: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
_PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
_PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
"i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
_PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
+ _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V),
+ "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
+ _PAGE_CP_4V | _PAGE_E_4V |
_PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));
return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
" andn %0, %4, %0\n"
" or %0, %5, %0\n"
" .previous\n"
+ " .section .sun_m7_2insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " andn %0, %6, %0\n"
+ " or %0, %5, %0\n"
+ " .previous\n"
: "=r" (val)
: "0" (val), "i" (_PAGE_CP_4U | _PAGE_CV_4U), "i" (_PAGE_E_4U),
- "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V));
+ "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V),
+ "i" (_PAGE_CP_4V));
return __pgprot(val);
}
#ifdef CONFIG_SMP
#define topology_physical_package_id(cpu) (cpu_data(cpu).proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).core_id)
-#define topology_core_cpumask(cpu) (&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu) (&cpu_core_sib_map[cpu])
+#define topology_sibling_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
#endif /* CONFIG_SMP */
extern cpumask_t cpu_core_map[NR_CPUS];
+extern cpumask_t cpu_core_sib_map[NR_CPUS];
static inline const struct cpumask *cpu_coregroup_mask(int cpu)
{
return &cpu_core_map[cpu];
};
extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
__sun4v_2insn_patch_end;
+extern struct sun4v_2insn_patch_entry __sun_m7_2insn_patch,
+ __sun_m7_2insn_patch_end;
#endif /* !(__ASSEMBLY__) */
struct sun4v_1insn_patch_entry *);
void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
struct sun4v_2insn_patch_entry *);
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+ struct sun4v_2insn_patch_entry *);
extern unsigned int dcache_parity_tl1_occurred;
extern unsigned int icache_parity_tl1_occurred;
err = -ENOMEM;
goto err1;
}
- memset(grpci2priv, 0, sizeof(*grpci2priv));
priv->regs = regs;
priv->irq = ofdev->archdata.irqs[0]; /* BASE IRQ */
priv->irq_mode = (capability & STS_IRQMODE) >> STS_IRQMODE_BIT;
}
}
-static void mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
+static void find_back_node_value(struct mdesc_handle *hp, u64 node,
+ char *srch_val,
+ void (*func)(struct mdesc_handle *, u64, int),
+ u64 val, int depth)
{
- u64 a;
-
- mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) {
- u64 t = mdesc_arc_target(hp, a);
- const char *name;
- const u64 *id;
+ u64 arc;
- name = mdesc_node_name(hp, t);
- if (!strcmp(name, "cpu")) {
- id = mdesc_get_property(hp, t, "id", NULL);
- if (*id < NR_CPUS)
- cpu_data(*id).core_id = core_id;
- } else {
- u64 j;
+ /* Since we have an estimate of recursion depth, do a sanity check. */
+ if (depth == 0)
+ return;
- mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_BACK) {
- u64 n = mdesc_arc_target(hp, j);
- const char *n_name;
+ mdesc_for_each_arc(arc, hp, node, MDESC_ARC_TYPE_BACK) {
+ u64 n = mdesc_arc_target(hp, arc);
+ const char *name = mdesc_node_name(hp, n);
- n_name = mdesc_node_name(hp, n);
- if (strcmp(n_name, "cpu"))
- continue;
+ if (!strcmp(srch_val, name))
+ (*func)(hp, n, val);
- id = mdesc_get_property(hp, n, "id", NULL);
- if (*id < NR_CPUS)
- cpu_data(*id).core_id = core_id;
- }
- }
+ find_back_node_value(hp, n, srch_val, func, val, depth-1);
}
}
+static void __mark_core_id(struct mdesc_handle *hp, u64 node,
+ int core_id)
+{
+ const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+ if (*id < num_possible_cpus())
+ cpu_data(*id).core_id = core_id;
+}
+
+static void __mark_sock_id(struct mdesc_handle *hp, u64 node,
+ int sock_id)
+{
+ const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+ if (*id < num_possible_cpus())
+ cpu_data(*id).sock_id = sock_id;
+}
+
+static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
+ int core_id)
+{
+ find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10);
+}
+
+static void mark_sock_ids(struct mdesc_handle *hp, u64 mp,
+ int sock_id)
+{
+ find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10);
+}
+
static void set_core_ids(struct mdesc_handle *hp)
{
int idx;
u64 mp;
idx = 1;
+
+ /* Identify unique cores by looking for cpus backpointed to by
+ * level 1 instruction caches.
+ */
mdesc_for_each_node_by_name(hp, mp, "cache") {
const u64 *level;
const char *type;
continue;
mark_core_ids(hp, mp, idx);
+ idx++;
+ }
+}
+
+static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
+{
+ u64 mp;
+ int idx = 1;
+ int fnd = 0;
+
+ /* Identify unique sockets by looking for cpus backpointed to by
+ * shared level n caches.
+ */
+ mdesc_for_each_node_by_name(hp, mp, "cache") {
+ const u64 *cur_lvl;
+
+ cur_lvl = mdesc_get_property(hp, mp, "level", NULL);
+ if (*cur_lvl != level)
+ continue;
+
+ mark_sock_ids(hp, mp, idx);
+ idx++;
+ fnd = 1;
+ }
+ return fnd;
+}
+
+static void set_sock_ids_by_socket(struct mdesc_handle *hp, u64 mp)
+{
+ int idx = 1;
+ mdesc_for_each_node_by_name(hp, mp, "socket") {
+ u64 a;
+
+ mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) {
+ u64 t = mdesc_arc_target(hp, a);
+ const char *name;
+ const u64 *id;
+
+ name = mdesc_node_name(hp, t);
+ if (strcmp(name, "cpu"))
+ continue;
+
+ id = mdesc_get_property(hp, t, "id", NULL);
+ if (*id < num_possible_cpus())
+ cpu_data(*id).sock_id = idx;
+ }
idx++;
}
}
+static void set_sock_ids(struct mdesc_handle *hp)
+{
+ u64 mp;
+
+ /* If machine description exposes sockets data use it.
+ * Otherwise fallback to use shared L3 or L2 caches.
+ */
+ mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets");
+ if (mp != MDESC_NODE_NULL)
+ return set_sock_ids_by_socket(hp, mp);
+
+ if (!set_sock_ids_by_cache(hp, 3))
+ set_sock_ids_by_cache(hp, 2);
+}
+
static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
{
u64 a;
continue;
mark_proc_ids(hp, mp, idx);
-
idx++;
}
}
set_core_ids(hp);
set_proc_ids(hp);
+ set_sock_ids(hp);
mdesc_release(hp);
subsys_initcall(pcibios_init);
#ifdef CONFIG_SYSFS
+
+#define SLOT_NAME_SIZE 11 /* Max decimal digits + null in u32 */
+
+static void pcie_bus_slot_names(struct pci_bus *pbus)
+{
+ struct pci_dev *pdev;
+ struct pci_bus *bus;
+
+ list_for_each_entry(pdev, &pbus->devices, bus_list) {
+ char name[SLOT_NAME_SIZE];
+ struct pci_slot *pci_slot;
+ const u32 *slot_num;
+ int len;
+
+ slot_num = of_get_property(pdev->dev.of_node,
+ "physical-slot#", &len);
+
+ if (slot_num == NULL || len != 4)
+ continue;
+
+ snprintf(name, sizeof(name), "%u", slot_num[0]);
+ pci_slot = pci_create_slot(pbus, slot_num[0], name, NULL);
+
+ if (IS_ERR(pci_slot))
+ pr_err("PCI: pci_create_slot returned %ld.\n",
+ PTR_ERR(pci_slot));
+ }
+
+ list_for_each_entry(bus, &pbus->children, node)
+ pcie_bus_slot_names(bus);
+}
+
static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus)
{
const struct pci_slot_names {
while ((pbus = pci_find_next_bus(pbus)) != NULL) {
struct device_node *node;
+ struct pci_dev *pdev;
+
+ pdev = list_first_entry(&pbus->devices, struct pci_dev,
+ bus_list);
- if (pbus->self) {
- /* PCI->PCI bridge */
- node = pbus->self->dev.of_node;
+ if (pdev && pci_is_pcie(pdev)) {
+ pcie_bus_slot_names(pbus);
} else {
- struct pci_pbm_info *pbm = pbus->sysdata;
- /* Host PCI controller */
- node = pbm->op->dev.of_node;
- }
+ if (pbus->self) {
+
+ /* PCI->PCI bridge */
+ node = pbus->self->dev.of_node;
+
+ } else {
+ struct pci_pbm_info *pbm = pbus->sysdata;
- pci_bus_slot_names(node, pbus);
+ /* Host PCI controller */
+ node = pbm->op->dev.of_node;
+ }
+
+ pci_bus_slot_names(node, pbus);
+ }
}
return 0;
}
}
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+ struct sun4v_2insn_patch_entry *end)
+{
+ while (start < end) {
+ unsigned long addr = start->addr;
+
+ *(unsigned int *) (addr + 0) = start->insns[0];
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 0));
+
+ *(unsigned int *) (addr + 4) = start->insns[1];
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 4));
+
+ start++;
+ }
+}
+
static void __init sun4v_patch(void)
{
extern void sun4v_hvapi_init(void);
sun4v_patch_2insn_range(&__sun4v_2insn_patch,
&__sun4v_2insn_patch_end);
+ if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7)
+ sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
+ &__sun_m7_2insn_patch_end);
sun4v_hvapi_init();
}
cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = {
+ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL(cpu_core_sib_map);
static cpumask_t smp_commenced_mask;
}
}
+ for_each_present_cpu(i) {
+ unsigned int j;
+
+ for_each_present_cpu(j) {
+ if (cpu_data(i).sock_id == cpu_data(j).sock_id)
+ cpumask_set_cpu(j, &cpu_core_sib_map[i]);
+ }
+ }
+
for_each_present_cpu(i) {
unsigned int j;
*(.pause_3insn_patch)
__pause_3insn_patch_end = .;
}
+ .sun_m7_2insn_patch : {
+ __sun_m7_2insn_patch = .;
+ *(.sun_m7_2insn_patch)
+ __sun_m7_2insn_patch_end = .;
+ }
PERCPU_SECTION(SMP_CACHE_BYTES)
. = ALIGN(PAGE_SIZE);
#include <linux/perf_event.h>
#include <linux/interrupt.h>
#include <linux/kdebug.h>
+#include <linux/uaccess.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/setup.h>
#include <asm/smp.h>
#include <asm/traps.h>
-#include <asm/uaccess.h>
#include "mm_32.h"
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (pagefault_disabled() || !mm)
goto no_context;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
#include <linux/kdebug.h>
#include <linux/percpu.h>
#include <linux/context_tracking.h>
+#include <linux/uaccess.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/openprom.h>
#include <asm/oplib.h>
-#include <asm/uaccess.h>
#include <asm/asi.h>
#include <asm/lsu.h>
#include <asm/sections.h>
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto intr_or_no_mm;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
unsigned long vaddr;
long idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
if (vaddr < FIXADDR_START) { // FIXME
pagefault_enable();
+ preempt_enable();
return;
}
kmap_atomic_idx_pop();
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
#include "init_64.h"
unsigned long kern_linear_pte_xor[4] __read_mostly;
+static unsigned long page_cache4v_flag;
/* A bitmap, two bits for every 256MB of physical memory. These two
* bits determine what page size we use for kernel linear
static void __init sun4v_linear_pte_xor_finalize(void)
{
+ unsigned long pagecv_flag;
+
+ /* Bit 9 of TTE is no longer CV bit on M7 processor and it instead
+ * enables MCD error. Do not set bit 9 on M7 processor.
+ */
+ switch (sun4v_chip_type) {
+ case SUN4V_CHIP_SPARC_M7:
+ pagecv_flag = 0x00;
+ break;
+ default:
+ pagecv_flag = _PAGE_CV_4V;
+ break;
+ }
#ifndef CONFIG_DEBUG_PAGEALLOC
if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) {
kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[1] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[1] = kern_linear_pte_xor[0];
if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) {
kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[2] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[2] = kern_linear_pte_xor[1];
if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) {
kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^
PAGE_OFFSET;
- kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ kern_linear_pte_xor[3] |= (_PAGE_CP_4V | pagecv_flag |
_PAGE_P_4V | _PAGE_W_4V);
} else {
kern_linear_pte_xor[3] = kern_linear_pte_xor[2];
return available;
}
+#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U)
+#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V)
+#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
+#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
+#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
+#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
+
/* We need to exclude reserved regions. This exclusion will include
* vmlinux and initrd. To be more precise the initrd size could be used to
* compute a new lower limit because it is freed later during initialization.
memset(swapper_4m_tsb, 0x40, sizeof(swapper_4m_tsb));
#endif
+ /* TTE.cv bit on sparc v9 occupies the same position as TTE.mcde
+ * bit on M7 processor. This is a conflicting usage of the same
+ * bit. Enabling TTE.cv on M7 would turn on Memory Corruption
+ * Detection error on all pages and this will lead to problems
+ * later. Kernel does not run with MCD enabled and hence rest
+ * of the required steps to fully configure memory corruption
+ * detection are not taken. We need to ensure TTE.mcde is not
+ * set on M7 processor. Compute the value of cacheability
+ * flag for use later taking this into consideration.
+ */
+ switch (sun4v_chip_type) {
+ case SUN4V_CHIP_SPARC_M7:
+ page_cache4v_flag = _PAGE_CP_4V;
+ break;
+ default:
+ page_cache4v_flag = _PAGE_CACHE_4V;
+ break;
+ }
+
if (tlb_type == hypervisor)
sun4v_pgprot_init();
else
}
#endif
-#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U)
-#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V)
-#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
-#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
-#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
-#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
-
pgprot_t PAGE_KERNEL __read_mostly;
EXPORT_SYMBOL(PAGE_KERNEL);
_PAGE_P_4U | _PAGE_W_4U);
if (tlb_type == hypervisor)
pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
- _PAGE_CP_4V | _PAGE_CV_4V |
- _PAGE_P_4V | _PAGE_W_4V);
+ page_cache4v_flag | _PAGE_P_4V | _PAGE_W_4V);
pte_base |= _PAGE_PMD_HUGE;
int i;
PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4V | _PAGE_VALID |
- _PAGE_CACHE_4V | _PAGE_P_4V |
+ page_cache4v_flag | _PAGE_P_4V |
__ACCESS_BITS_4V | __DIRTY_BITS_4V |
_PAGE_EXEC_4V);
PAGE_KERNEL_LOCKED = PAGE_KERNEL;
_PAGE_IE = _PAGE_IE_4V;
_PAGE_E = _PAGE_E_4V;
- _PAGE_CACHE = _PAGE_CACHE_4V;
+ _PAGE_CACHE = page_cache4v_flag;
#ifdef CONFIG_DEBUG_PAGEALLOC
kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET;
kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^
PAGE_OFFSET;
#endif
- kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V |
- _PAGE_P_4V | _PAGE_W_4V);
+ kern_linear_pte_xor[0] |= (page_cache4v_flag | _PAGE_P_4V |
+ _PAGE_W_4V);
for (i = 1; i < 4; i++)
kern_linear_pte_xor[i] = kern_linear_pte_xor[0];
_PAGE_SZ4MB_4V | _PAGE_SZ512K_4V |
_PAGE_SZ64K_4V | _PAGE_SZ8K_4V);
- page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | _PAGE_CACHE_4V;
- page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | page_cache4v_flag;
+ page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_WRITE_4V | _PAGE_EXEC_4V);
- page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_EXEC_4V);
- page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
__ACCESS_BITS_4V | _PAGE_EXEC_4V);
page_exec_bit = _PAGE_EXEC_4V;
_PAGE_EXEC_4U | _PAGE_L_4U | _PAGE_W_4U);
if (tlb_type == hypervisor)
val = (_PAGE_VALID | _PAGE_SZ4MB_4V |
- _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V |
+ page_cache4v_flag | _PAGE_P_4V |
_PAGE_EXEC_4V | _PAGE_W_4V);
return val | paddr;
struct mm_struct *mm = current->mm;
struct tsb_config *tp;
- if (in_atomic() || !mm) {
+ if (faulthandler_disabled() || !mm) {
const struct exception_table_entry *entry;
entry = search_exception_tables(regs->tpc);
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-/* Define this to indicate that cmpxchg is an efficient operation. */
-#define __HAVE_ARCH_CMPXCHG
-
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_TILE_ATOMIC_64_H */
#define ioremap_nocache(physaddr, size) ioremap(physaddr, size)
#define ioremap_wc(physaddr, size) ioremap(physaddr, size)
-#define ioremap_writethrough(physaddr, size) ioremap(physaddr, size)
+#define ioremap_wt(physaddr, size) ioremap(physaddr, size)
#define ioremap_fullcache(physaddr, size) ioremap(physaddr, size)
#define mmiowb()
#define topology_physical_package_id(cpu) ((void)(cpu), 0)
#define topology_core_id(cpu) (cpu)
#define topology_core_cpumask(cpu) ((void)(cpu), cpu_online_mask)
-#define topology_thread_cpumask(cpu) cpumask_of(cpu)
+#define topology_sibling_cpumask(cpu) cpumask_of(cpu)
#endif
#endif /* _ASM_TILE_TOPOLOGY_H */
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to user space. Caller must check
* the specified blocks with access_ok() before calling this function.
/*
* If we're in an interrupt, have no user context or are running in an
- * atomic region then we must not take the fault.
+ * region with pagefaults disabled then we must not take the fault.
*/
- if (in_atomic() || !mm) {
+ if (pagefault_disabled() || !mm) {
vma = NULL; /* happy compiler */
goto bad_area_nosemaphore;
}
int idx, type;
pte_t *pte;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
/* Avoid icache flushes by disallowing atomic executable mappings. */
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
#include <linux/sched.h>
#include <linux/hardirq.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
#include <asm/current.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
*code_out = SEGV_MAPERR;
/*
- * If the fault was during atomic operation, don't take the fault, just
+ * If the fault was with pagefaults disabled, don't take the fault, just
* fail.
*/
- if (in_atomic())
+ if (faulthandler_disabled())
goto out_nosemaphore;
if (is_user)
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
+
+obj-y += entry/
+
obj-$(CONFIG_KVM) += kvm/
# Xen paravirtualization support
obj-y += mm/
obj-y += crypto/
-obj-y += vdso/
+
obj-$(CONFIG_IA32_EMULATION) += ia32/
obj-y += platform/
config X86_32
def_bool y
depends on !64BIT
- select CLKSRC_I8253
- select HAVE_UID16
config X86_64
def_bool y
depends on 64BIT
- select X86_DEV_DMA_OPS
- select ARCH_USE_CMPXCHG_LOCKREF
- select HAVE_LIVEPATCH
### Arch settings
config X86
def_bool y
- select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
- select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
+ select ACPI_LEGACY_TABLES_LOOKUP if ACPI
+ select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
+ select ANON_INODES
+ select ARCH_CLOCKSOURCE_DATA
+ select ARCH_DISCARD_MEMBLOCK
+ select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+ select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_SG_CHAIN
+ select ARCH_HAVE_NMI_SAFE_CMPXCHG
+ select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
- select HAVE_AOUT if X86_32
- select HAVE_UNSTABLE_SCHED_CLOCK
- select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
- select ARCH_SUPPORTS_INT128 if X86_64
- select HAVE_IDE
- select HAVE_OPROFILE
- select HAVE_PCSPKR_PLATFORM
- select HAVE_PERF_EVENTS
- select HAVE_IOREMAP_PROT
- select HAVE_KPROBES
- select HAVE_MEMBLOCK
- select HAVE_MEMBLOCK_NODE_MAP
- select ARCH_DISCARD_MEMBLOCK
- select ARCH_WANT_OPTIONAL_GPIOLIB
+ select ARCH_SUPPORTS_ATOMIC_RMW
+ select ARCH_SUPPORTS_INT128 if X86_64
+ select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
+ select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_CMPXCHG_LOCKREF if X86_64
+ select ARCH_USE_QUEUED_RWLOCKS
+ select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_WANT_FRAME_POINTERS
- select HAVE_DMA_ATTRS
- select HAVE_DMA_CONTIGUOUS
- select HAVE_KRETPROBES
+ select ARCH_WANT_IPC_PARSE_VERSION if X86_32
+ select ARCH_WANT_OPTIONAL_GPIOLIB
+ select BUILDTIME_EXTABLE_SORT
+ select CLKEVT_I8253
+ select CLKSRC_I8253 if X86_32
+ select CLOCKSOURCE_VALIDATE_LAST_CYCLE
+ select CLOCKSOURCE_WATCHDOG
+ select CLONE_BACKWARDS if X86_32
+ select COMPAT_OLD_SIGACTION if IA32_EMULATION
+ select DCACHE_WORD_ACCESS
+ select GENERIC_CLOCKEVENTS
+ select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
+ select GENERIC_CLOCKEVENTS_MIN_ADJUST
+ select GENERIC_CMOS_UPDATE
+ select GENERIC_CPU_AUTOPROBE
select GENERIC_EARLY_IOREMAP
- select HAVE_OPTPROBES
- select HAVE_KPROBES_ON_FTRACE
- select HAVE_FTRACE_MCOUNT_RECORD
- select HAVE_FENTRY if X86_64
+ select GENERIC_FIND_FIRST_BIT
+ select GENERIC_IOMAP
+ select GENERIC_IRQ_PROBE
+ select GENERIC_IRQ_SHOW
+ select GENERIC_PENDING_IRQ if SMP
+ select GENERIC_SMP_IDLE_THREAD
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
+ select GENERIC_TIME_VSYSCALL
+ select HAVE_ACPI_APEI if ACPI
+ select HAVE_ACPI_APEI_NMI if ACPI
+ select HAVE_ALIGNED_STRUCT_PAGE if SLUB
+ select HAVE_AOUT if X86_32
+ select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
+ select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+ select HAVE_ARCH_KGDB
+ select HAVE_ARCH_KMEMCHECK
+ select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_SOFT_DIRTY if X86_64
+ select HAVE_ARCH_TRACEHOOK
+ select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_BPF_JIT if X86_64
+ select HAVE_CC_STACKPROTECTOR
+ select HAVE_CMPXCHG_DOUBLE
+ select HAVE_CMPXCHG_LOCAL
+ select HAVE_CONTEXT_TRACKING if X86_64
select HAVE_C_RECORDMCOUNT
+ select HAVE_DEBUG_KMEMLEAK
+ select HAVE_DEBUG_STACKOVERFLOW
+ select HAVE_DMA_API_DEBUG
+ select HAVE_DMA_ATTRS
+ select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
- select HAVE_FUNCTION_TRACER
- select HAVE_FUNCTION_GRAPH_TRACER
- select HAVE_FUNCTION_GRAPH_FP_TEST
- select HAVE_SYSCALL_TRACEPOINTS
- select SYSCTL_EXCEPTION_TRACE
- select HAVE_KVM
- select HAVE_ARCH_KGDB
- select HAVE_ARCH_TRACEHOOK
- select HAVE_GENERIC_DMA_COHERENT if X86_32
select HAVE_EFFICIENT_UNALIGNED_ACCESS
- select USER_STACKTRACE_SUPPORT
- select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_DMA_API_DEBUG
- select HAVE_KERNEL_GZIP
+ select HAVE_FENTRY if X86_64
+ select HAVE_FTRACE_MCOUNT_RECORD
+ select HAVE_FUNCTION_GRAPH_FP_TEST
+ select HAVE_FUNCTION_GRAPH_TRACER
+ select HAVE_FUNCTION_TRACER
+ select HAVE_GENERIC_DMA_COHERENT if X86_32
+ select HAVE_HW_BREAKPOINT
+ select HAVE_IDE
+ select HAVE_IOREMAP_PROT
+ select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
+ select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_KERNEL_BZIP2
+ select HAVE_KERNEL_GZIP
+ select HAVE_KERNEL_LZ4
select HAVE_KERNEL_LZMA
- select HAVE_KERNEL_XZ
select HAVE_KERNEL_LZO
- select HAVE_KERNEL_LZ4
- select HAVE_HW_BREAKPOINT
+ select HAVE_KERNEL_XZ
+ select HAVE_KPROBES
+ select HAVE_KPROBES_ON_FTRACE
+ select HAVE_KRETPROBES
+ select HAVE_KVM
+ select HAVE_LIVEPATCH if X86_64
+ select HAVE_MEMBLOCK
+ select HAVE_MEMBLOCK_NODE_MAP
select HAVE_MIXED_BREAKPOINTS_REGS
- select PERF_EVENTS
+ select HAVE_OPROFILE
+ select HAVE_OPTPROBES
+ select HAVE_PCSPKR_PLATFORM
+ select HAVE_PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
- select HAVE_DEBUG_KMEMLEAK
- select ANON_INODES
- select HAVE_ALIGNED_STRUCT_PAGE if SLUB
- select HAVE_CMPXCHG_LOCAL
- select HAVE_CMPXCHG_DOUBLE
- select HAVE_ARCH_KMEMCHECK
- select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+ select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_SYSCALL_TRACEPOINTS
+ select HAVE_UID16 if X86_32
+ select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_USER_RETURN_NOTIFIER
- select ARCH_HAS_ELF_RANDOMIZE
- select HAVE_ARCH_JUMP_LABEL
- select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select SPARSE_IRQ
- select GENERIC_FIND_FIRST_BIT
- select GENERIC_IRQ_PROBE
- select GENERIC_PENDING_IRQ if SMP
- select GENERIC_IRQ_SHOW
- select GENERIC_CLOCKEVENTS_MIN_ADJUST
select IRQ_FORCED_THREADING
- select HAVE_BPF_JIT if X86_64
- select HAVE_ARCH_TRANSPARENT_HUGEPAGE
- select HAVE_ARCH_HUGE_VMAP if X86_64 || (X86_32 && X86_PAE)
- select ARCH_HAS_SG_CHAIN
- select CLKEVT_I8253
- select ARCH_HAVE_NMI_SAFE_CMPXCHG
- select GENERIC_IOMAP
- select DCACHE_WORD_ACCESS
- select GENERIC_SMP_IDLE_THREAD
- select ARCH_WANT_IPC_PARSE_VERSION if X86_32
- select HAVE_ARCH_SECCOMP_FILTER
- select BUILDTIME_EXTABLE_SORT
- select GENERIC_CMOS_UPDATE
- select HAVE_ARCH_SOFT_DIRTY if X86_64
- select CLOCKSOURCE_WATCHDOG
- select GENERIC_CLOCKEVENTS
- select ARCH_CLOCKSOURCE_DATA
- select CLOCKSOURCE_VALIDATE_LAST_CYCLE
- select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
- select GENERIC_TIME_VSYSCALL
- select GENERIC_STRNCPY_FROM_USER
- select GENERIC_STRNLEN_USER
- select HAVE_CONTEXT_TRACKING if X86_64
- select HAVE_IRQ_TIME_ACCOUNTING
- select VIRT_TO_BUS
- select MODULES_USE_ELF_REL if X86_32
- select MODULES_USE_ELF_RELA if X86_64
- select CLONE_BACKWARDS if X86_32
- select ARCH_USE_BUILTIN_BSWAP
- select ARCH_USE_QUEUE_RWLOCK
- select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
- select OLD_SIGACTION if X86_32
- select COMPAT_OLD_SIGACTION if IA32_EMULATION
+ select MODULES_USE_ELF_RELA if X86_64
+ select MODULES_USE_ELF_REL if X86_32
+ select OLD_SIGACTION if X86_32
+ select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
+ select PERF_EVENTS
select RTC_LIB
- select HAVE_DEBUG_STACKOVERFLOW
- select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
- select HAVE_CC_STACKPROTECTOR
- select GENERIC_CPU_AUTOPROBE
- select HAVE_ARCH_AUDITSYSCALL
- select ARCH_SUPPORTS_ATOMIC_RMW
- select HAVE_ACPI_APEI if ACPI
- select HAVE_ACPI_APEI_NMI if ACPI
- select ACPI_LEGACY_TABLES_LOOKUP if ACPI
- select X86_FEATURE_NAMES if PROC_FS
+ select SPARSE_IRQ
select SRCU
+ select SYSCTL_EXCEPTION_TRACE
+ select USER_STACKTRACE_SUPPORT
+ select VIRT_TO_BUS
+ select X86_DEV_DMA_OPS if X86_64
+ select X86_FEATURE_NAMES if PROC_FS
config INSTRUCTION_DECODER
def_bool y
def_bool y
depends on X86_64 && SMP
-config X86_HT
- def_bool y
- depends on SMP
-
config X86_32_LAZY_GS
def_bool y
depends on X86_32 && !CC_STACKPROTECTOR
config X86_X2APIC
bool "Support x2apic"
- depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP
+ depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
---help---
This enables x2apic support on CPUs that have this feature.
depends on X86_EXTENDED_PLATFORM
depends on NUMA
depends on X86_X2APIC
+ depends on PCI
---help---
This option is needed in order to support SGI Ultraviolet systems.
If you don't have one of these, you should say N here.
select X86_REBOOTFIXUPS
select OF
select OF_EARLY_FLATTREE
- select IRQ_DOMAIN
---help---
Select for the Intel CE media processor (CE4100) SOC.
This option compiles in support for the CE4100 SOC for settop
config PARAVIRT_SPINLOCKS
bool "Paravirtualization layer for spinlocks"
depends on PARAVIRT && SMP
- select UNINLINE_SPIN_UNLOCK
+ select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS
---help---
Paravirtualized spinlocks allow a pvops backend to replace the
spinlock implementation with something virtualization-friendly
default "1" if !SMP
default "8192" if MAXSMP
default "32" if SMP && X86_BIGSMP
- default "8" if SMP
+ default "8" if SMP && X86_32
+ default "64" if SMP
---help---
This allows you to specify the maximum number of CPUs which this
kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum
- supported value is 4096, otherwise the maximum value is 512. The
+ supported value is 8192, otherwise the maximum value is 512. The
minimum value which makes sense is 2.
This is purely to save memory - each supported CPU adds
config SCHED_SMT
bool "SMT (Hyperthreading) scheduler support"
- depends on X86_HT
+ depends on SMP
---help---
SMT scheduler support improves the CPU scheduler's decision making
when dealing with Intel Pentium 4 chips with HyperThreading at a
config SCHED_MC
def_bool y
prompt "Multi-core scheduler support"
- depends on X86_HT
+ depends on SMP
---help---
Multi-core scheduler support improves the CPU scheduler's decision
making when dealing with multi-core CPU chips at a cost of slightly
config X86_LOCAL_APIC
def_bool y
depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
- select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+ select IRQ_DOMAIN_HIERARCHY
+ select PCI_MSI_IRQ_DOMAIN if PCI_MSI
config X86_IO_APIC
def_bool y
depends on X86_LOCAL_APIC || X86_UP_IOAPIC
- select IRQ_DOMAIN
config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
bool "Reroute for broken boot IRQs"
If unsure, say N.
+config X86_DEBUG_FPU
+ bool "Debug the x86 FPU code"
+ depends on DEBUG_KERNEL
+ default y
+ ---help---
+ If this option is enabled then there will be extra sanity
+ checks and (boot time) debug printouts added to the kernel.
+ This debugging adds some small amount of runtime overhead
+ to the kernel.
+
+ If unsure, say N.
+
+config PUNIT_ATOM_DEBUG
+ tristate "ATOM Punit debug driver"
+ select DEBUG_FS
+ select IOSF_MBI
+ ---help---
+ This is a debug driver, which gets the power states
+ of all Punit North Complex devices. The power states of
+ each device is exposed as part of the debugfs interface.
+ The current power state can be read from
+ /sys/kernel/debug/punit_atom/dev_power_state
+
endmenu
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
+ # Align jump targets to 1 byte, not the default 16 bytes:
+ KBUILD_CFLAGS += -falign-jumps=1
+
+ # Pack loops tightly as well:
+ KBUILD_CFLAGS += -falign-loops=1
+
# Don't autogenerate traditional x87 instructions
KBUILD_CFLAGS += $(call cc-option,-mno-80387)
KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
# Use -mpreferred-stack-boundary=3 if supported.
KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
+ # Use -mskip-rax-setup if supported.
+ KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
+
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
sp-$(CONFIG_X86_32) := esp
sp-$(CONFIG_X86_64) := rsp
-# do binutils support CFI?
-cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
-# is .cfi_signal_frame supported too?
-cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
-cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
-
# does binutils support specific instructions?
asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_AFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_CFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
LDFLAGS := -m elf_$(UTS_MACHINE)
# Syscall table generation
archheaders:
- $(Q)$(MAKE) $(build)=arch/x86/syscalls all
+ $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
archprepare:
ifeq ($(CONFIG_KEXEC_FILE),y)
PHONY += vdso_install
vdso_install:
- $(Q)$(MAKE) $(build)=arch/x86/vdso $@
+ $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@
archclean:
$(Q)rm -rf $(objtree)/arch/i386
#define BOOT_COMPRESSED_MISC_H
/*
- * we have to be careful, because no indirections are allowed here, and
- * paravirt_ops is a kind of one. As it will only run in baremetal anyway,
- * we just keep it from happening
+ * Special hack: we have to be careful, because no indirections are allowed here,
+ * and paravirt_ops is a kind of one. As it will only run in baremetal anyway,
+ * we just keep it from happening. (This list needs to be extended when new
+ * paravirt and debugging variants are added.)
*/
#undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_SPINLOCKS
#undef CONFIG_KASAN
-#ifdef CONFIG_X86_32
-#define _ASM_X86_DESC_H 1
-#endif
#include <linux/linkage.h>
#include <linux/screen_info.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
#include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/aes.h>
#include <crypto/ablk_helper.h>
#include <crypto/scatterwalk.h>
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/camellia.h>
#include <asm/crypto/glue_helper.h>
static int __init camellia_aesni_init(void)
{
- u64 xcr0;
+ const char *feature_name;
if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
pr_info("AVX2 or AES-NI instructions are not detected.\n");
return -ENODEV;
}
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX2 detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/camellia.h>
#include <asm/crypto/glue_helper.h>
static int __init camellia_aesni_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
- pr_info("AVX or AES-NI instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
#include <crypto/cast5.h>
#include <crypto/cryptd.h>
#include <crypto/ctr.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/glue_helper.h>
#define CAST5_PARALLEL_BLOCKS 16
static int __init cast5_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_osxsave) {
- pr_info("AVX instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/glue_helper.h>
#define CAST6_PARALLEL_BLOCKS 8
static int __init cast6_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_osxsave) {
- pr_info("AVX instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
#include <asm/cpufeature.h>
#include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#define CHKSUM_BLOCK_SIZE 1
#define CHKSUM_DIGEST_SIZE 4
#include <asm/cpufeature.h>
#include <asm/cpu_device_id.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#define CHKSUM_BLOCK_SIZE 1
#define CHKSUM_DIGEST_SIZE 4
#include <linux/init.h>
#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/cpufeature.h>
#include <asm/cpu_device_id.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
struct crypto_fpu_ctx {
struct crypto_blkcipher *child;
#include <crypto/cryptd.h>
#include <crypto/gf128mul.h>
#include <crypto/internal/hash.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/cpu_device_id.h>
#define GHASH_BLOCK_SIZE 16
#include <crypto/lrw.h>
#include <crypto/xts.h>
#include <crypto/serpent.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/serpent-avx.h>
#include <asm/crypto/glue_helper.h>
static int __init init(void)
{
- u64 xcr0;
+ const char *feature_name;
if (!cpu_has_avx2 || !cpu_has_osxsave) {
pr_info("AVX2 instructions are not detected.\n");
return -ENODEV;
}
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/serpent-avx.h>
#include <asm/crypto/glue_helper.h>
static int __init serpent_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_osxsave) {
- printk(KERN_INFO "AVX instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- printk(KERN_INFO "AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
#include <crypto/mcryptd.h>
#include <crypto/crypto_wq.h>
#include <asm/byteorder.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
#include <linux/hardirq.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/api.h>
#include "sha_mb_ctx.h"
#define FLUSH_INTERVAL 1000 /* in usec */
#include <linux/types.h>
#include <crypto/sha.h>
#include <crypto/sha1_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
#ifdef CONFIG_AS_AVX
static bool __init avx_usable(void)
{
- u64 xcr0;
-
- if (!cpu_has_avx || !cpu_has_osxsave)
- return false;
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
-
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+ if (cpu_has_avx)
+ pr_info("AVX detected but unusable.\n");
return false;
}
#include <linux/types.h>
#include <crypto/sha.h>
#include <crypto/sha256_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <linux/string.h>
asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data,
#ifdef CONFIG_AS_AVX
static bool __init avx_usable(void)
{
- u64 xcr0;
-
- if (!cpu_has_avx || !cpu_has_osxsave)
- return false;
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
-
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+ if (cpu_has_avx)
+ pr_info("AVX detected but unusable.\n");
return false;
}
#include <linux/types.h>
#include <crypto/sha.h>
#include <crypto/sha512_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <linux/string.h>
#ifdef CONFIG_AS_AVX
static bool __init avx_usable(void)
{
- u64 xcr0;
-
- if (!cpu_has_avx || !cpu_has_osxsave)
- return false;
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- pr_info("AVX detected but unusable.\n");
-
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+ if (cpu_has_avx)
+ pr_info("AVX detected but unusable.\n");
return false;
}
#include <crypto/ctr.h>
#include <crypto/lrw.h>
#include <crypto/xts.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
#include <asm/crypto/twofish.h>
#include <asm/crypto/glue_helper.h>
#include <crypto/scatterwalk.h>
static int __init twofish_init(void)
{
- u64 xcr0;
+ const char *feature_name;
- if (!cpu_has_avx || !cpu_has_osxsave) {
- printk(KERN_INFO "AVX instructions are not detected.\n");
- return -ENODEV;
- }
-
- xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
- printk(KERN_INFO "AVX detected but unusable.\n");
+ if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+ pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
--- /dev/null
+#
+# Makefile for the x86 low level entry code
+#
+obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+
+obj-y += vdso/
+obj-y += vsyscall/
+
+obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o
+
--- /dev/null
+/*
+
+ x86 function call convention, 64-bit:
+ -------------------------------------
+ arguments | callee-saved | extra caller-saved | return
+ [callee-clobbered] | | [callee-clobbered] |
+ ---------------------------------------------------------------------------
+ rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11 | rax, rdx [**]
+
+ ( rsp is obviously invariant across normal function calls. (gcc can 'merge'
+ functions when it sees tail-call optimization possibilities) rflags is
+ clobbered. Leftover arguments are passed over the stack frame.)
+
+ [*] In the frame-pointers case rbp is fixed to the stack frame.
+
+ [**] for struct return values wider than 64 bits the return convention is a
+ bit more complex: up to 128 bits width we return small structures
+ straight in rax, rdx. For structures larger than that (3 words or
+ larger) the caller puts a pointer to an on-stack return struct
+ [allocated in the caller's stack frame] into the first argument - i.e.
+ into rdi. All other arguments shift up by one in this case.
+ Fortunately this case is rare in the kernel.
+
+For 32-bit we have the following conventions - kernel is built with
+-mregparm=3 and -freg-struct-return:
+
+ x86 function calling convention, 32-bit:
+ ----------------------------------------
+ arguments | callee-saved | extra caller-saved | return
+ [callee-clobbered] | | [callee-clobbered] |
+ -------------------------------------------------------------------------
+ eax edx ecx | ebx edi esi ebp [*] | <none> | eax, edx [**]
+
+ ( here too esp is obviously invariant across normal function calls. eflags
+ is clobbered. Leftover arguments are passed over the stack frame. )
+
+ [*] In the frame-pointers case ebp is fixed to the stack frame.
+
+ [**] We build with -freg-struct-return, which on 32-bit means similar
+ semantics as on 64-bit: edx can be used for a second return value
+ (i.e. covering integer and structure sizes up to 64 bits) - after that
+ it gets more complex and more expensive: 3-word or larger struct returns
+ get done in the caller's frame and the pointer to the return struct goes
+ into regparm0, i.e. eax - the other arguments shift up and the
+ function's register parameters degenerate to regparm=2 in essence.
+
+*/
+
+#ifdef CONFIG_X86_64
+
+/*
+ * 64-bit system call stack frame layout defines and helpers,
+ * for assembly code:
+ */
+
+/* The layout forms the "struct pt_regs" on the stack: */
+/*
+ * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
+ * unless syscall needs a complete, fully filled "struct pt_regs".
+ */
+#define R15 0*8
+#define R14 1*8
+#define R13 2*8
+#define R12 3*8
+#define RBP 4*8
+#define RBX 5*8
+/* These regs are callee-clobbered. Always saved on kernel entry. */
+#define R11 6*8
+#define R10 7*8
+#define R9 8*8
+#define R8 9*8
+#define RAX 10*8
+#define RCX 11*8
+#define RDX 12*8
+#define RSI 13*8
+#define RDI 14*8
+/*
+ * On syscall entry, this is syscall#. On CPU exception, this is error code.
+ * On hw interrupt, it's IRQ number:
+ */
+#define ORIG_RAX 15*8
+/* Return frame for iretq */
+#define RIP 16*8
+#define CS 17*8
+#define EFLAGS 18*8
+#define RSP 19*8
+#define SS 20*8
+
+#define SIZEOF_PTREGS 21*8
+
+ .macro ALLOC_PT_GPREGS_ON_STACK addskip=0
+ addq $-(15*8+\addskip), %rsp
+ .endm
+
+ .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
+ .if \r11
+ movq %r11, 6*8+\offset(%rsp)
+ .endif
+ .if \r8910
+ movq %r10, 7*8+\offset(%rsp)
+ movq %r9, 8*8+\offset(%rsp)
+ movq %r8, 9*8+\offset(%rsp)
+ .endif
+ .if \rax
+ movq %rax, 10*8+\offset(%rsp)
+ .endif
+ .if \rcx
+ movq %rcx, 11*8+\offset(%rsp)
+ .endif
+ movq %rdx, 12*8+\offset(%rsp)
+ movq %rsi, 13*8+\offset(%rsp)
+ movq %rdi, 14*8+\offset(%rsp)
+ .endm
+ .macro SAVE_C_REGS offset=0
+ SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
+ .endm
+ .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0
+ SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1
+ .endm
+ .macro SAVE_C_REGS_EXCEPT_R891011
+ SAVE_C_REGS_HELPER 0, 1, 1, 0, 0
+ .endm
+ .macro SAVE_C_REGS_EXCEPT_RCX_R891011
+ SAVE_C_REGS_HELPER 0, 1, 0, 0, 0
+ .endm
+ .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11
+ SAVE_C_REGS_HELPER 0, 0, 0, 1, 0
+ .endm
+
+ .macro SAVE_EXTRA_REGS offset=0
+ movq %r15, 0*8+\offset(%rsp)
+ movq %r14, 1*8+\offset(%rsp)
+ movq %r13, 2*8+\offset(%rsp)
+ movq %r12, 3*8+\offset(%rsp)
+ movq %rbp, 4*8+\offset(%rsp)
+ movq %rbx, 5*8+\offset(%rsp)
+ .endm
+ .macro SAVE_EXTRA_REGS_RBP offset=0
+ movq %rbp, 4*8+\offset(%rsp)
+ .endm
+
+ .macro RESTORE_EXTRA_REGS offset=0
+ movq 0*8+\offset(%rsp), %r15
+ movq 1*8+\offset(%rsp), %r14
+ movq 2*8+\offset(%rsp), %r13
+ movq 3*8+\offset(%rsp), %r12
+ movq 4*8+\offset(%rsp), %rbp
+ movq 5*8+\offset(%rsp), %rbx
+ .endm
+
+ .macro ZERO_EXTRA_REGS
+ xorl %r15d, %r15d
+ xorl %r14d, %r14d
+ xorl %r13d, %r13d
+ xorl %r12d, %r12d
+ xorl %ebp, %ebp
+ xorl %ebx, %ebx
+ .endm
+
+ .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
+ .if \rstor_r11
+ movq 6*8(%rsp), %r11
+ .endif
+ .if \rstor_r8910
+ movq 7*8(%rsp), %r10
+ movq 8*8(%rsp), %r9
+ movq 9*8(%rsp), %r8
+ .endif
+ .if \rstor_rax
+ movq 10*8(%rsp), %rax
+ .endif
+ .if \rstor_rcx
+ movq 11*8(%rsp), %rcx
+ .endif
+ .if \rstor_rdx
+ movq 12*8(%rsp), %rdx
+ .endif
+ movq 13*8(%rsp), %rsi
+ movq 14*8(%rsp), %rdi
+ .endm
+ .macro RESTORE_C_REGS
+ RESTORE_C_REGS_HELPER 1,1,1,1,1
+ .endm
+ .macro RESTORE_C_REGS_EXCEPT_RAX
+ RESTORE_C_REGS_HELPER 0,1,1,1,1
+ .endm
+ .macro RESTORE_C_REGS_EXCEPT_RCX
+ RESTORE_C_REGS_HELPER 1,0,1,1,1
+ .endm
+ .macro RESTORE_C_REGS_EXCEPT_R11
+ RESTORE_C_REGS_HELPER 1,1,0,1,1
+ .endm
+ .macro RESTORE_C_REGS_EXCEPT_RCX_R11
+ RESTORE_C_REGS_HELPER 1,0,0,1,1
+ .endm
+ .macro RESTORE_RSI_RDI
+ RESTORE_C_REGS_HELPER 0,0,0,0,0
+ .endm
+ .macro RESTORE_RSI_RDI_RDX
+ RESTORE_C_REGS_HELPER 0,0,0,0,1
+ .endm
+
+ .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
+ subq $-(15*8+\addskip), %rsp
+ .endm
+
+ .macro icebp
+ .byte 0xf1
+ .endm
+
+#else /* CONFIG_X86_64 */
+
+/*
+ * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
+ * are different from the entry_32.S versions in not changing the segment
+ * registers. So only suitable for in kernel use, not when transitioning
+ * from or to user space. The resulting stack frame is not a standard
+ * pt_regs frame. The main use case is calling C code from assembler
+ * when all the registers need to be preserved.
+ */
+
+ .macro SAVE_ALL
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ .endm
+
+ .macro RESTORE_ALL
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+ .endm
+
+#endif /* CONFIG_X86_64 */
+
--- /dev/null
+/*
+ * Copyright (C) 1991,1992 Linus Torvalds
+ *
+ * entry_32.S contains the system-call and low-level fault and trap handling routines.
+ *
+ * Stack layout in 'syscall_exit':
+ * ptrace needs to have all registers on the stack.
+ * If the order here is changed, it needs to be
+ * updated in fork.c:copy_process(), signal.c:do_signal(),
+ * ptrace.c and ptrace.h
+ *
+ * 0(%esp) - %ebx
+ * 4(%esp) - %ecx
+ * 8(%esp) - %edx
+ * C(%esp) - %esi
+ * 10(%esp) - %edi
+ * 14(%esp) - %ebp
+ * 18(%esp) - %eax
+ * 1C(%esp) - %ds
+ * 20(%esp) - %es
+ * 24(%esp) - %fs
+ * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
+ * 2C(%esp) - orig_eax
+ * 30(%esp) - %eip
+ * 34(%esp) - %cs
+ * 38(%esp) - %eflags
+ * 3C(%esp) - %oldesp
+ * 40(%esp) - %oldss
+ */
+
+#include <linux/linkage.h>
+#include <linux/err.h>
+#include <asm/thread_info.h>
+#include <asm/irqflags.h>
+#include <asm/errno.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+#include <asm/ftrace.h>
+#include <asm/irq_vectors.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE 0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysenter_audit syscall_trace_entry
+# define sysexit_audit syscall_exit_work
+#endif
+
+ .section .entry.text, "ax"
+
+/*
+ * We use macros for low-level operations which need to be overridden
+ * for paravirtualization. The following will never clobber any registers:
+ * INTERRUPT_RETURN (aka. "iret")
+ * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
+ * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
+ *
+ * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
+ * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
+ * Allowing a register to be clobbered can shrink the paravirt replacement
+ * enough to patch inline, increasing performance.
+ */
+
+#ifdef CONFIG_PREEMPT
+# define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
+#else
+# define preempt_stop(clobbers)
+# define resume_kernel restore_all
+#endif
+
+.macro TRACE_IRQS_IRET
+#ifdef CONFIG_TRACE_IRQFLAGS
+ testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off?
+ jz 1f
+ TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+/*
+ * User gs save/restore
+ *
+ * %gs is used for userland TLS and kernel only uses it for stack
+ * canary which is required to be at %gs:20 by gcc. Read the comment
+ * at the top of stackprotector.h for more info.
+ *
+ * Local labels 98 and 99 are used.
+ */
+#ifdef CONFIG_X86_32_LAZY_GS
+
+ /* unfortunately push/pop can't be no-op */
+.macro PUSH_GS
+ pushl $0
+.endm
+.macro POP_GS pop=0
+ addl $(4 + \pop), %esp
+.endm
+.macro POP_GS_EX
+.endm
+
+ /* all the rest are no-op */
+.macro PTGS_TO_GS
+.endm
+.macro PTGS_TO_GS_EX
+.endm
+.macro GS_TO_REG reg
+.endm
+.macro REG_TO_PTGS reg
+.endm
+.macro SET_KERNEL_GS reg
+.endm
+
+#else /* CONFIG_X86_32_LAZY_GS */
+
+.macro PUSH_GS
+ pushl %gs
+.endm
+
+.macro POP_GS pop=0
+98: popl %gs
+ .if \pop <> 0
+ add $\pop, %esp
+ .endif
+.endm
+.macro POP_GS_EX
+.pushsection .fixup, "ax"
+99: movl $0, (%esp)
+ jmp 98b
+.popsection
+ _ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro PTGS_TO_GS
+98: mov PT_GS(%esp), %gs
+.endm
+.macro PTGS_TO_GS_EX
+.pushsection .fixup, "ax"
+99: movl $0, PT_GS(%esp)
+ jmp 98b
+.popsection
+ _ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro GS_TO_REG reg
+ movl %gs, \reg
+.endm
+.macro REG_TO_PTGS reg
+ movl \reg, PT_GS(%esp)
+.endm
+.macro SET_KERNEL_GS reg
+ movl $(__KERNEL_STACK_CANARY), \reg
+ movl \reg, %gs
+.endm
+
+#endif /* CONFIG_X86_32_LAZY_GS */
+
+.macro SAVE_ALL
+ cld
+ PUSH_GS
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ movl $(__USER_DS), %edx
+ movl %edx, %ds
+ movl %edx, %es
+ movl $(__KERNEL_PERCPU), %edx
+ movl %edx, %fs
+ SET_KERNEL_GS %edx
+.endm
+
+.macro RESTORE_INT_REGS
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+.endm
+
+.macro RESTORE_REGS pop=0
+ RESTORE_INT_REGS
+1: popl %ds
+2: popl %es
+3: popl %fs
+ POP_GS \pop
+.pushsection .fixup, "ax"
+4: movl $0, (%esp)
+ jmp 1b
+5: movl $0, (%esp)
+ jmp 2b
+6: movl $0, (%esp)
+ jmp 3b
+.popsection
+ _ASM_EXTABLE(1b, 4b)
+ _ASM_EXTABLE(2b, 5b)
+ _ASM_EXTABLE(3b, 6b)
+ POP_GS_EX
+.endm
+
+ENTRY(ret_from_fork)
+ pushl %eax
+ call schedule_tail
+ GET_THREAD_INFO(%ebp)
+ popl %eax
+ pushl $0x0202 # Reset kernel eflags
+ popfl
+ jmp syscall_exit
+END(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+ pushl %eax
+ call schedule_tail
+ GET_THREAD_INFO(%ebp)
+ popl %eax
+ pushl $0x0202 # Reset kernel eflags
+ popfl
+ movl PT_EBP(%esp), %eax
+ call *PT_EBX(%esp)
+ movl $0, PT_EAX(%esp)
+ jmp syscall_exit
+ENDPROC(ret_from_kernel_thread)
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+ # userspace resumption stub bypassing syscall exit tracing
+ ALIGN
+ret_from_exception:
+ preempt_stop(CLBR_ANY)
+ret_from_intr:
+ GET_THREAD_INFO(%ebp)
+#ifdef CONFIG_VM86
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
+#else
+ /*
+ * We can be coming here from child spawned by kernel_thread().
+ */
+ movl PT_CS(%esp), %eax
+ andl $SEGMENT_RPL_MASK, %eax
+#endif
+ cmpl $USER_RPL, %eax
+ jb resume_kernel # not returning to v8086 or userspace
+
+ENTRY(resume_userspace)
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ andl $_TIF_WORK_MASK, %ecx # is there any work to be done on
+ # int/exception return?
+ jne work_pending
+ jmp restore_all
+END(ret_from_exception)
+
+#ifdef CONFIG_PREEMPT
+ENTRY(resume_kernel)
+ DISABLE_INTERRUPTS(CLBR_ANY)
+need_resched:
+ cmpl $0, PER_CPU_VAR(__preempt_count)
+ jnz restore_all
+ testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
+ jz restore_all
+ call preempt_schedule_irq
+ jmp need_resched
+END(resume_kernel)
+#endif
+
+/*
+ * SYSENTER_RETURN points to after the SYSENTER instruction
+ * in the vsyscall page. See vsyscall-sysentry.S, which defines
+ * the symbol.
+ */
+
+ # SYSENTER call handler stub
+ENTRY(entry_SYSENTER_32)
+ movl TSS_sysenter_sp0(%esp), %esp
+sysenter_past_esp:
+ /*
+ * Interrupts are disabled here, but we can't trace it until
+ * enough kernel state to call TRACE_IRQS_OFF can be called - but
+ * we immediately enable interrupts at that point anyway.
+ */
+ pushl $__USER_DS
+ pushl %ebp
+ pushfl
+ orl $X86_EFLAGS_IF, (%esp)
+ pushl $__USER_CS
+ /*
+ * Push current_thread_info()->sysenter_return to the stack.
+ * A tiny bit of offset fixup is necessary: TI_sysenter_return
+ * is relative to thread_info, which is at the bottom of the
+ * kernel stack page. 4*4 means the 4 words pushed above;
+ * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
+ * and THREAD_SIZE takes us to the bottom.
+ */
+ pushl ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
+
+ pushl %eax
+ SAVE_ALL
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+/*
+ * Load the potential sixth argument from user stack.
+ * Careful about security.
+ */
+ cmpl $__PAGE_OFFSET-3, %ebp
+ jae syscall_fault
+ ASM_STAC
+1: movl (%ebp), %ebp
+ ASM_CLAC
+ movl %ebp, PT_EBP(%esp)
+ _ASM_EXTABLE(1b, syscall_fault)
+
+ GET_THREAD_INFO(%ebp)
+
+ testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+ jnz sysenter_audit
+sysenter_do_call:
+ cmpl $(NR_syscalls), %eax
+ jae sysenter_badsys
+ call *sys_call_table(, %eax, 4)
+sysenter_after_call:
+ movl %eax, PT_EAX(%esp)
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $_TIF_ALLWORK_MASK, %ecx
+ jnz sysexit_audit
+sysenter_exit:
+/* if something modifies registers it must also disable sysexit */
+ movl PT_EIP(%esp), %edx
+ movl PT_OLDESP(%esp), %ecx
+ xorl %ebp, %ebp
+ TRACE_IRQS_ON
+1: mov PT_FS(%esp), %fs
+ PTGS_TO_GS
+ ENABLE_INTERRUPTS_SYSEXIT
+
+#ifdef CONFIG_AUDITSYSCALL
+sysenter_audit:
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), TI_flags(%ebp)
+ jnz syscall_trace_entry
+ /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
+ movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */
+ /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
+ pushl PT_ESI(%esp) /* a3: 5th arg */
+ pushl PT_EDX+4(%esp) /* a2: 4th arg */
+ call __audit_syscall_entry
+ popl %ecx /* get that remapped edx off the stack */
+ popl %ecx /* get that remapped esi off the stack */
+ movl PT_EAX(%esp), %eax /* reload syscall number */
+ jmp sysenter_do_call
+
+sysexit_audit:
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+ jnz syscall_exit_work
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_ANY)
+ movl %eax, %edx /* second arg, syscall return value */
+ cmpl $-MAX_ERRNO, %eax /* is it an error ? */
+ setbe %al /* 1 if so, 0 if not */
+ movzbl %al, %eax /* zero-extend that */
+ call __audit_syscall_exit
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+ jnz syscall_exit_work
+ movl PT_EAX(%esp), %eax /* reload syscall return value */
+ jmp sysenter_exit
+#endif
+
+.pushsection .fixup, "ax"
+2: movl $0, PT_FS(%esp)
+ jmp 1b
+.popsection
+ _ASM_EXTABLE(1b, 2b)
+ PTGS_TO_GS_EX
+ENDPROC(entry_SYSENTER_32)
+
+ # system call handler stub
+ENTRY(entry_INT80_32)
+ ASM_CLAC
+ pushl %eax # save orig_eax
+ SAVE_ALL
+ GET_THREAD_INFO(%ebp)
+ # system call tracing in operation / emulation
+ testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+ jnz syscall_trace_entry
+ cmpl $(NR_syscalls), %eax
+ jae syscall_badsys
+syscall_call:
+ call *sys_call_table(, %eax, 4)
+syscall_after_call:
+ movl %eax, PT_EAX(%esp) # store the return value
+syscall_exit:
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ testl $_TIF_ALLWORK_MASK, %ecx # current->work
+ jnz syscall_exit_work
+
+restore_all:
+ TRACE_IRQS_IRET
+restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
+ /*
+ * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+ * are returning to the kernel.
+ * See comments in process.c:copy_thread() for details.
+ */
+ movb PT_OLDSS(%esp), %ah
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+ cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
+ je ldt_ss # returning to user-space with LDT SS
+#endif
+restore_nocheck:
+ RESTORE_REGS 4 # skip orig_eax/error_code
+irq_return:
+ INTERRUPT_RETURN
+.section .fixup, "ax"
+ENTRY(iret_exc )
+ pushl $0 # no error code
+ pushl $do_iret_error
+ jmp error_code
+.previous
+ _ASM_EXTABLE(irq_return, iret_exc)
+
+#ifdef CONFIG_X86_ESPFIX32
+ldt_ss:
+#ifdef CONFIG_PARAVIRT
+ /*
+ * The kernel can't run on a non-flat stack if paravirt mode
+ * is active. Rather than try to fixup the high bits of
+ * ESP, bypass this code entirely. This may break DOSemu
+ * and/or Wine support in a paravirt VM, although the option
+ * is still available to implement the setting of the high
+ * 16-bits in the INTERRUPT_RETURN paravirt-op.
+ */
+ cmpl $0, pv_info+PARAVIRT_enabled
+ jne restore_nocheck
+#endif
+
+/*
+ * Setup and switch to ESPFIX stack
+ *
+ * We're returning to userspace with a 16 bit stack. The CPU will not
+ * restore the high word of ESP for us on executing iret... This is an
+ * "official" bug of all the x86-compatible CPUs, which we can work
+ * around to make dosemu and wine happy. We do this by preloading the
+ * high word of ESP with the high word of the userspace ESP while
+ * compensating for the offset by changing to the ESPFIX segment with
+ * a base address that matches for the difference.
+ */
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+ mov %esp, %edx /* load kernel esp */
+ mov PT_OLDESP(%esp), %eax /* load userspace esp */
+ mov %dx, %ax /* eax: new kernel esp */
+ sub %eax, %edx /* offset (low word is 0) */
+ shr $16, %edx
+ mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
+ mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
+ pushl $__ESPFIX_SS
+ pushl %eax /* new kernel esp */
+ /*
+ * Disable interrupts, but do not irqtrace this section: we
+ * will soon execute iret and the tracer was already set to
+ * the irqstate after the IRET:
+ */
+ DISABLE_INTERRUPTS(CLBR_EAX)
+ lss (%esp), %esp /* switch to espfix segment */
+ jmp restore_nocheck
+#endif
+ENDPROC(entry_INT80_32)
+
+ # perform work that needs to be done immediately before resumption
+ ALIGN
+work_pending:
+ testb $_TIF_NEED_RESCHED, %cl
+ jz work_notifysig
+work_resched:
+ call schedule
+ LOCKDEP_SYS_EXIT
+ DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
+ # setting need_resched or sigpending
+ # between sampling and the iret
+ TRACE_IRQS_OFF
+ movl TI_flags(%ebp), %ecx
+ andl $_TIF_WORK_MASK, %ecx # is there any work to be done other
+ # than syscall tracing?
+ jz restore_all
+ testb $_TIF_NEED_RESCHED, %cl
+ jnz work_resched
+
+work_notifysig: # deal with pending signals and
+ # notify-resume requests
+#ifdef CONFIG_VM86
+ testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
+ movl %esp, %eax
+ jnz work_notifysig_v86 # returning to kernel-space or
+ # vm86-space
+1:
+#else
+ movl %esp, %eax
+#endif
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ movb PT_CS(%esp), %bl
+ andb $SEGMENT_RPL_MASK, %bl
+ cmpb $USER_RPL, %bl
+ jb resume_kernel
+ xorl %edx, %edx
+ call do_notify_resume
+ jmp resume_userspace
+
+#ifdef CONFIG_VM86
+ ALIGN
+work_notifysig_v86:
+ pushl %ecx # save ti_flags for do_notify_resume
+ call save_v86_state # %eax contains pt_regs pointer
+ popl %ecx
+ movl %eax, %esp
+ jmp 1b
+#endif
+END(work_pending)
+
+ # perform syscall exit tracing
+ ALIGN
+syscall_trace_entry:
+ movl $-ENOSYS, PT_EAX(%esp)
+ movl %esp, %eax
+ call syscall_trace_enter
+ /* What it returned is what we'll actually use. */
+ cmpl $(NR_syscalls), %eax
+ jnae syscall_call
+ jmp syscall_exit
+END(syscall_trace_entry)
+
+ # perform syscall exit tracing
+ ALIGN
+syscall_exit_work:
+ testl $_TIF_WORK_SYSCALL_EXIT, %ecx
+ jz work_pending
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call
+ # schedule() instead
+ movl %esp, %eax
+ call syscall_trace_leave
+ jmp resume_userspace
+END(syscall_exit_work)
+
+syscall_fault:
+ ASM_CLAC
+ GET_THREAD_INFO(%ebp)
+ movl $-EFAULT, PT_EAX(%esp)
+ jmp resume_userspace
+END(syscall_fault)
+
+syscall_badsys:
+ movl $-ENOSYS, %eax
+ jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+ movl $-ENOSYS, %eax
+ jmp sysenter_after_call
+END(sysenter_badsys)
+
+.macro FIXUP_ESPFIX_STACK
+/*
+ * Switch back for ESPFIX stack to the normal zerobased stack
+ *
+ * We can't call C functions using the ESPFIX stack. This code reads
+ * the high word of the segment base from the GDT and swiches to the
+ * normal stack and adjusts ESP with the matching offset.
+ */
+#ifdef CONFIG_X86_ESPFIX32
+ /* fixup the stack */
+ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
+ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+ shl $16, %eax
+ addl %esp, %eax /* the adjusted stack pointer */
+ pushl $__KERNEL_DS
+ pushl %eax
+ lss (%esp), %esp /* switch to the normal stack segment */
+#endif
+.endm
+.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
+ movl %ss, %eax
+ /* see if on espfix stack */
+ cmpw $__ESPFIX_SS, %ax
+ jne 27f
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ /* switch to normal stack */
+ FIXUP_ESPFIX_STACK
+27:
+#endif
+.endm
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+ .align 8
+ENTRY(irq_entries_start)
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ pushl $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_interrupt
+ .align 8
+ .endr
+END(irq_entries_start)
+
+/*
+ * the CPU automatically disables interrupts when executing an IRQ vector,
+ * so IRQ-flags tracing has to follow that:
+ */
+ .p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+ ASM_CLAC
+ addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ movl %esp, %eax
+ call do_IRQ
+ jmp ret_from_intr
+ENDPROC(common_interrupt)
+
+#define BUILD_INTERRUPT3(name, nr, fn) \
+ENTRY(name) \
+ ASM_CLAC; \
+ pushl $~(nr); \
+ SAVE_ALL; \
+ TRACE_IRQS_OFF \
+ movl %esp, %eax; \
+ call fn; \
+ jmp ret_from_intr; \
+ENDPROC(name)
+
+
+#ifdef CONFIG_TRACING
+# define TRACE_BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
+#else
+# define TRACE_BUILD_INTERRUPT(name, nr)
+#endif
+
+#define BUILD_INTERRUPT(name, nr) \
+ BUILD_INTERRUPT3(name, nr, smp_##name); \
+ TRACE_BUILD_INTERRUPT(name, nr)
+
+/* The include is where all of the SMP etc. interrupts come from */
+#include <asm/entry_arch.h>
+
+ENTRY(coprocessor_error)
+ ASM_CLAC
+ pushl $0
+ pushl $do_coprocessor_error
+ jmp error_code
+END(coprocessor_error)
+
+ENTRY(simd_coprocessor_error)
+ ASM_CLAC
+ pushl $0
+#ifdef CONFIG_X86_INVD_BUG
+ /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
+ ALTERNATIVE "pushl $do_general_protection", \
+ "pushl $do_simd_coprocessor_error", \
+ X86_FEATURE_XMM
+#else
+ pushl $do_simd_coprocessor_error
+#endif
+ jmp error_code
+END(simd_coprocessor_error)
+
+ENTRY(device_not_available)
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+ pushl $do_device_not_available
+ jmp error_code
+END(device_not_available)
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
+ iret
+ _ASM_EXTABLE(native_iret, iret_exc)
+END(native_iret)
+
+ENTRY(native_irq_enable_sysexit)
+ sti
+ sysexit
+END(native_irq_enable_sysexit)
+#endif
+
+ENTRY(overflow)
+ ASM_CLAC
+ pushl $0
+ pushl $do_overflow
+ jmp error_code
+END(overflow)
+
+ENTRY(bounds)
+ ASM_CLAC
+ pushl $0
+ pushl $do_bounds
+ jmp error_code
+END(bounds)
+
+ENTRY(invalid_op)
+ ASM_CLAC
+ pushl $0
+ pushl $do_invalid_op
+ jmp error_code
+END(invalid_op)
+
+ENTRY(coprocessor_segment_overrun)
+ ASM_CLAC
+ pushl $0
+ pushl $do_coprocessor_segment_overrun
+ jmp error_code
+END(coprocessor_segment_overrun)
+
+ENTRY(invalid_TSS)
+ ASM_CLAC
+ pushl $do_invalid_TSS
+ jmp error_code
+END(invalid_TSS)
+
+ENTRY(segment_not_present)
+ ASM_CLAC
+ pushl $do_segment_not_present
+ jmp error_code
+END(segment_not_present)
+
+ENTRY(stack_segment)
+ ASM_CLAC
+ pushl $do_stack_segment
+ jmp error_code
+END(stack_segment)
+
+ENTRY(alignment_check)
+ ASM_CLAC
+ pushl $do_alignment_check
+ jmp error_code
+END(alignment_check)
+
+ENTRY(divide_error)
+ ASM_CLAC
+ pushl $0 # no error code
+ pushl $do_divide_error
+ jmp error_code
+END(divide_error)
+
+#ifdef CONFIG_X86_MCE
+ENTRY(machine_check)
+ ASM_CLAC
+ pushl $0
+ pushl machine_check_vector
+ jmp error_code
+END(machine_check)
+#endif
+
+ENTRY(spurious_interrupt_bug)
+ ASM_CLAC
+ pushl $0
+ pushl $do_spurious_interrupt_bug
+ jmp error_code
+END(spurious_interrupt_bug)
+
+#ifdef CONFIG_XEN
+/*
+ * Xen doesn't set %esp to be precisely what the normal SYSENTER
+ * entry point expects, so fix it up before using the normal path.
+ */
+ENTRY(xen_sysenter_target)
+ addl $5*4, %esp /* remove xen-provided frame */
+ jmp sysenter_past_esp
+
+ENTRY(xen_hypervisor_callback)
+ pushl $-1 /* orig_ax = -1 => not a system call */
+ SAVE_ALL
+ TRACE_IRQS_OFF
+
+ /*
+ * Check to see if we got the event in the critical
+ * region in xen_iret_direct, after we've reenabled
+ * events and checked for pending events. This simulates
+ * iret instruction's behaviour where it delivers a
+ * pending interrupt when enabling interrupts:
+ */
+ movl PT_EIP(%esp), %eax
+ cmpl $xen_iret_start_crit, %eax
+ jb 1f
+ cmpl $xen_iret_end_crit, %eax
+ jae 1f
+
+ jmp xen_iret_crit_fixup
+
+ENTRY(xen_do_upcall)
+1: mov %esp, %eax
+ call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
+ jmp ret_from_intr
+ENDPROC(xen_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ * 1. Fault while reloading DS, ES, FS or GS
+ * 2. Fault while executing IRET
+ * Category 1 we fix up by reattempting the load, and zeroing the segment
+ * register if the load fails.
+ * Category 2 we fix up by jumping to do_iret_error. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by maintaining a status value in EAX.
+ */
+ENTRY(xen_failsafe_callback)
+ pushl %eax
+ movl $1, %eax
+1: mov 4(%esp), %ds
+2: mov 8(%esp), %es
+3: mov 12(%esp), %fs
+4: mov 16(%esp), %gs
+ /* EAX == 0 => Category 1 (Bad segment)
+ EAX != 0 => Category 2 (Bad IRET) */
+ testl %eax, %eax
+ popl %eax
+ lea 16(%esp), %esp
+ jz 5f
+ jmp iret_exc
+5: pushl $-1 /* orig_ax = -1 => not a system call */
+ SAVE_ALL
+ jmp ret_from_exception
+
+.section .fixup, "ax"
+6: xorl %eax, %eax
+ movl %eax, 4(%esp)
+ jmp 1b
+7: xorl %eax, %eax
+ movl %eax, 8(%esp)
+ jmp 2b
+8: xorl %eax, %eax
+ movl %eax, 12(%esp)
+ jmp 3b
+9: xorl %eax, %eax
+ movl %eax, 16(%esp)
+ jmp 4b
+.previous
+ _ASM_EXTABLE(1b, 6b)
+ _ASM_EXTABLE(2b, 7b)
+ _ASM_EXTABLE(3b, 8b)
+ _ASM_EXTABLE(4b, 9b)
+ENDPROC(xen_failsafe_callback)
+
+BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+ xen_evtchn_do_upcall)
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+ hyperv_vector_handler)
+
+#endif /* CONFIG_HYPERV */
+
+#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+ ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ pushl $0 /* Pass NULL as regs pointer */
+ movl 4*4(%esp), %eax
+ movl 0x4(%ebp), %edx
+ movl function_trace_op, %ecx
+ subl $MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+ call ftrace_stub
+
+ addl $4, %esp /* skip NULL pointer */
+ popl %edx
+ popl %ecx
+ popl %eax
+ftrace_ret:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ jmp ftrace_stub
+#endif
+
+.globl ftrace_stub
+ftrace_stub:
+ ret
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+ pushf /* push flags before compare (in cs location) */
+
+ /*
+ * i386 does not save SS and ESP when coming from kernel.
+ * Instead, to get sp, ®s->sp is used (see ptrace.h).
+ * Unfortunately, that means eflags must be at the same location
+ * as the current return ip is. We move the return ip into the
+ * ip location, and move flags into the return ip location.
+ */
+ pushl 4(%esp) /* save return ip into ip slot */
+
+ pushl $0 /* Load 0 into orig_ax */
+ pushl %gs
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+
+ movl 13*4(%esp), %eax /* Get the saved flags */
+ movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
+ /* clobbering return ip */
+ movl $__KERNEL_CS, 13*4(%esp)
+
+ movl 12*4(%esp), %eax /* Load ip (1st parameter) */
+ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
+ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
+ movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+ pushl %esp /* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ addl $4, %esp /* Skip pt_regs */
+ movl 14*4(%esp), %eax /* Move flags back into cs */
+ movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
+ movl 12*4(%esp), %eax /* Get return ip from regs->ip */
+ movl %eax, 14*4(%esp) /* Put return ip back for ret */
+
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+ popl %ds
+ popl %es
+ popl %fs
+ popl %gs
+ addl $8, %esp /* Skip orig_ax and ip */
+ popf /* Pop flags at end (no addl to corrupt flags) */
+ jmp ftrace_ret
+
+ popf
+ jmp ftrace_stub
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(mcount)
+ cmpl $__PAGE_OFFSET, %esp
+ jb ftrace_stub /* Paging not enabled yet? */
+
+ cmpl $ftrace_stub, ftrace_trace_function
+ jnz trace
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ cmpl $ftrace_stub, ftrace_graph_return
+ jnz ftrace_graph_caller
+
+ cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
+ jnz ftrace_graph_caller
+#endif
+.globl ftrace_stub
+ftrace_stub:
+ ret
+
+ /* taken from glibc */
+trace:
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ movl 0xc(%esp), %eax
+ movl 0x4(%ebp), %edx
+ subl $MCOUNT_INSN_SIZE, %eax
+
+ call *ftrace_trace_function
+
+ popl %edx
+ popl %ecx
+ popl %eax
+ jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ movl 0xc(%esp), %eax
+ lea 0x4(%ebp), %edx
+ movl (%ebp), %ecx
+ subl $MCOUNT_INSN_SIZE, %eax
+ call prepare_ftrace_return
+ popl %edx
+ popl %ecx
+ popl %eax
+ ret
+END(ftrace_graph_caller)
+
+.globl return_to_handler
+return_to_handler:
+ pushl %eax
+ pushl %edx
+ movl %ebp, %eax
+ call ftrace_return_to_handler
+ movl %eax, %ecx
+ popl %edx
+ popl %eax
+ jmp *%ecx
+#endif
+
+#ifdef CONFIG_TRACING
+ENTRY(trace_page_fault)
+ ASM_CLAC
+ pushl $trace_do_page_fault
+ jmp error_code
+END(trace_page_fault)
+#endif
+
+ENTRY(page_fault)
+ ASM_CLAC
+ pushl $do_page_fault
+ ALIGN
+error_code:
+ /* the function address is in %gs's slot on the stack */
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ cld
+ movl $(__KERNEL_PERCPU), %ecx
+ movl %ecx, %fs
+ UNWIND_ESPFIX_STACK
+ GS_TO_REG %ecx
+ movl PT_GS(%esp), %edi # get the function address
+ movl PT_ORIG_EAX(%esp), %edx # get the error code
+ movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
+ REG_TO_PTGS %ecx
+ SET_KERNEL_GS %ecx
+ movl $(__USER_DS), %ecx
+ movl %ecx, %ds
+ movl %ecx, %es
+ TRACE_IRQS_OFF
+ movl %esp, %eax # pt_regs pointer
+ call *%edi
+ jmp ret_from_exception
+END(page_fault)
+
+/*
+ * Debug traps and NMI can happen at the one SYSENTER instruction
+ * that sets up the real kernel stack. Check here, since we can't
+ * allow the wrong stack to be used.
+ *
+ * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
+ * already pushed 3 words if it hits on the sysenter instruction:
+ * eflags, cs and eip.
+ *
+ * We just load the right stack, and push the three (known) values
+ * by hand onto the new stack - while updating the return eip past
+ * the instruction that would have done it for sysenter.
+ */
+.macro FIX_STACK offset ok label
+ cmpw $__KERNEL_CS, 4(%esp)
+ jne \ok
+\label:
+ movl TSS_sysenter_sp0 + \offset(%esp), %esp
+ pushfl
+ pushl $__KERNEL_CS
+ pushl $sysenter_past_esp
+.endm
+
+ENTRY(debug)
+ ASM_CLAC
+ cmpl $entry_SYSENTER_32, (%esp)
+ jne debug_stack_correct
+ FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
+debug_stack_correct:
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ xorl %edx, %edx # error code 0
+ movl %esp, %eax # pt_regs pointer
+ call do_debug
+ jmp ret_from_exception
+END(debug)
+
+/*
+ * NMI is doubly nasty. It can happen _while_ we're handling
+ * a debug fault, and the debug fault hasn't yet been able to
+ * clear up the stack. So we first check whether we got an
+ * NMI on the sysenter entry path, but after that we need to
+ * check whether we got an NMI on the debug path where the debug
+ * fault happened on the sysenter path.
+ */
+ENTRY(nmi)
+ ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
+ pushl %eax
+ movl %ss, %eax
+ cmpw $__ESPFIX_SS, %ax
+ popl %eax
+ je nmi_espfix_stack
+#endif
+ cmpl $entry_SYSENTER_32, (%esp)
+ je nmi_stack_fixup
+ pushl %eax
+ movl %esp, %eax
+ /*
+ * Do not access memory above the end of our stack page,
+ * it might not exist.
+ */
+ andl $(THREAD_SIZE-1), %eax
+ cmpl $(THREAD_SIZE-20), %eax
+ popl %eax
+ jae nmi_stack_correct
+ cmpl $entry_SYSENTER_32, 12(%esp)
+ je nmi_debug_stack_check
+nmi_stack_correct:
+ pushl %eax
+ SAVE_ALL
+ xorl %edx, %edx # zero error code
+ movl %esp, %eax # pt_regs pointer
+ call do_nmi
+ jmp restore_all_notrace
+
+nmi_stack_fixup:
+ FIX_STACK 12, nmi_stack_correct, 1
+ jmp nmi_stack_correct
+
+nmi_debug_stack_check:
+ cmpw $__KERNEL_CS, 16(%esp)
+ jne nmi_stack_correct
+ cmpl $debug, (%esp)
+ jb nmi_stack_correct
+ cmpl $debug_esp_fix_insn, (%esp)
+ ja nmi_stack_correct
+ FIX_STACK 24, nmi_stack_correct, 1
+ jmp nmi_stack_correct
+
+#ifdef CONFIG_X86_ESPFIX32
+nmi_espfix_stack:
+ /*
+ * create the pointer to lss back
+ */
+ pushl %ss
+ pushl %esp
+ addl $4, (%esp)
+ /* copy the iret frame of 12 bytes */
+ .rept 3
+ pushl 16(%esp)
+ .endr
+ pushl %eax
+ SAVE_ALL
+ FIXUP_ESPFIX_STACK # %eax == %esp
+ xorl %edx, %edx # zero error code
+ call do_nmi
+ RESTORE_REGS
+ lss 12+4(%esp), %esp # back to espfix stack
+ jmp irq_return
+#endif
+END(nmi)
+
+ENTRY(int3)
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+ SAVE_ALL
+ TRACE_IRQS_OFF
+ xorl %edx, %edx # zero error code
+ movl %esp, %eax # pt_regs pointer
+ call do_int3
+ jmp ret_from_exception
+END(int3)
+
+ENTRY(general_protection)
+ pushl $do_general_protection
+ jmp error_code
+END(general_protection)
+
+#ifdef CONFIG_KVM_GUEST
+ENTRY(async_page_fault)
+ ASM_CLAC
+ pushl $do_async_page_fault
+ jmp error_code
+END(async_page_fault)
+#endif
--- /dev/null
+/*
+ * linux/arch/x86_64/entry.S
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
+ * Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
+ *
+ * entry.S contains the system-call and fault low-level handling routines.
+ *
+ * Some of this is documented in Documentation/x86/entry_64.txt
+ *
+ * A note on terminology:
+ * - iret frame: Architecture defined interrupt frame from SS to RIP
+ * at the top of the kernel process stack.
+ *
+ * Some macro usage:
+ * - ENTRY/END: Define functions in the symbol table.
+ * - TRACE_IRQ_*: Trace hardirq state for lock debugging.
+ * - idtentry: Define exception entry points.
+ */
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/cache.h>
+#include <asm/errno.h>
+#include "calling.h"
+#include <asm/asm-offsets.h>
+#include <asm/msr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/hw_irq.h>
+#include <asm/page_types.h>
+#include <asm/irqflags.h>
+#include <asm/paravirt.h>
+#include <asm/percpu.h>
+#include <asm/asm.h>
+#include <asm/context_tracking.h>
+#include <asm/smap.h>
+#include <asm/pgtable_types.h>
+#include <linux/err.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_64BIT 0x80000000
+#define __AUDIT_ARCH_LE 0x40000000
+
+.code64
+.section .entry.text, "ax"
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret64)
+ swapgs
+ sysretq
+ENDPROC(native_usergs_sysret64)
+#endif /* CONFIG_PARAVIRT */
+
+.macro TRACE_IRQS_IRETQ
+#ifdef CONFIG_TRACE_IRQFLAGS
+ bt $9, EFLAGS(%rsp) /* interrupts off? */
+ jnc 1f
+ TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+/*
+ * When dynamic function tracer is enabled it will add a breakpoint
+ * to all locations that it is about to modify, sync CPUs, update
+ * all the code, sync CPUs, then remove the breakpoints. In this time
+ * if lockdep is enabled, it might jump back into the debug handler
+ * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
+ *
+ * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
+ * make sure the stack pointer does not get reset back to the top
+ * of the debug stack, and instead just reuses the current stack.
+ */
+#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
+
+.macro TRACE_IRQS_OFF_DEBUG
+ call debug_stack_set_zero
+ TRACE_IRQS_OFF
+ call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_ON_DEBUG
+ call debug_stack_set_zero
+ TRACE_IRQS_ON
+ call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_IRETQ_DEBUG
+ bt $9, EFLAGS(%rsp) /* interrupts off? */
+ jnc 1f
+ TRACE_IRQS_ON_DEBUG
+1:
+.endm
+
+#else
+# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ
+#endif
+
+/*
+ * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
+ *
+ * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Registers on entry:
+ * rax system call number
+ * rcx return address
+ * r11 saved rflags (note: r11 is callee-clobbered register in C ABI)
+ * rdi arg0
+ * rsi arg1
+ * rdx arg2
+ * r10 arg3 (needs to be moved to rcx to conform to C ABI)
+ * r8 arg4
+ * r9 arg5
+ * (note: r12-r15, rbp, rbx are callee-preserved in C ABI)
+ *
+ * Only called from user space.
+ *
+ * When user can change pt_regs->foo always force IRET. That is because
+ * it deals with uncanonical addresses better. SYSRET has trouble
+ * with them due to bugs in both AMD and Intel CPUs.
+ */
+
+ENTRY(entry_SYSCALL_64)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ SWAPGS_UNSAFE_STACK
+ /*
+ * A hypervisor implementation might want to use a label
+ * after the swapgs, so that it can do the swapgs
+ * for the guest and jump here on syscall.
+ */
+GLOBAL(entry_SYSCALL_64_after_swapgs)
+
+ movq %rsp, PER_CPU_VAR(rsp_scratch)
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER_DS /* pt_regs->ss */
+ pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
+ /*
+ * Re-enable interrupts.
+ * We use 'rsp_scratch' as a scratch space, hence irq-off block above
+ * must execute atomically in the face of possible interrupt-driven
+ * task preemption. We must enable interrupts only after we're done
+ * with using rsp_scratch:
+ */
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ pushq %r8 /* pt_regs->r8 */
+ pushq %r9 /* pt_regs->r9 */
+ pushq %r10 /* pt_regs->r10 */
+ pushq %r11 /* pt_regs->r11 */
+ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz tracesys
+entry_SYSCALL_64_fastpath:
+#if __SYSCALL_MASK == ~0
+ cmpq $__NR_syscall_max, %rax
+#else
+ andl $__SYSCALL_MASK, %eax
+ cmpl $__NR_syscall_max, %eax
+#endif
+ ja 1f /* return -ENOSYS (already in pt_regs->ax) */
+ movq %r10, %rcx
+ call *sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+/*
+ * Syscall return path ending with SYSRET (fast path).
+ * Has incompletely filled pt_regs.
+ */
+ LOCKDEP_SYS_EXIT
+ /*
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ DISABLE_INTERRUPTS(CLBR_NONE)
+
+ /*
+ * We must check ti flags with interrupts (or at least preemption)
+ * off because we must *never* return to userspace without
+ * processing exit work that is enqueued if we're preempted here.
+ * In particular, returning to userspace with any of the one-shot
+ * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+ * very bad.
+ */
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */
+
+ RESTORE_C_REGS_EXCEPT_RCX_R11
+ movq RIP(%rsp), %rcx
+ movq EFLAGS(%rsp), %r11
+ movq RSP(%rsp), %rsp
+ /*
+ * 64-bit SYSRET restores rip from rcx,
+ * rflags from r11 (but RF and VM bits are forced to 0),
+ * cs and ss are loaded from MSRs.
+ * Restoration of rflags re-enables interrupts.
+ *
+ * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+ * descriptor is not reinitialized. This means that we should
+ * avoid SYSRET with SS == NULL, which could happen if we schedule,
+ * exit the kernel, and re-enter using an interrupt vector. (All
+ * interrupt entries on x86_64 set SS to NULL.) We prevent that
+ * from happening by reloading SS in __switch_to. (Actually
+ * detecting the failure in 64-bit userspace is tricky but can be
+ * done.)
+ */
+ USERGS_SYSRET64
+
+ /* Do syscall entry tracing */
+tracesys:
+ movq %rsp, %rdi
+ movl $AUDIT_ARCH_X86_64, %esi
+ call syscall_trace_enter_phase1
+ test %rax, %rax
+ jnz tracesys_phase2 /* if needed, run the slow path */
+ RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */
+ movq ORIG_RAX(%rsp), %rax
+ jmp entry_SYSCALL_64_fastpath /* and return to the fast path */
+
+tracesys_phase2:
+ SAVE_EXTRA_REGS
+ movq %rsp, %rdi
+ movl $AUDIT_ARCH_X86_64, %esi
+ movq %rax, %rdx
+ call syscall_trace_enter_phase2
+
+ /*
+ * Reload registers from stack in case ptrace changed them.
+ * We don't reload %rax because syscall_trace_entry_phase2() returned
+ * the value it wants us to use in the table lookup.
+ */
+ RESTORE_C_REGS_EXCEPT_RAX
+ RESTORE_EXTRA_REGS
+#if __SYSCALL_MASK == ~0
+ cmpq $__NR_syscall_max, %rax
+#else
+ andl $__SYSCALL_MASK, %eax
+ cmpl $__NR_syscall_max, %eax
+#endif
+ ja 1f /* return -ENOSYS (already in pt_regs->ax) */
+ movq %r10, %rcx /* fixup for C */
+ call *sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ /* Use IRET because user could have changed pt_regs->foo */
+
+/*
+ * Syscall return path ending with IRET.
+ * Has correct iret frame.
+ */
+GLOBAL(int_ret_from_sys_call)
+ DISABLE_INTERRUPTS(CLBR_NONE)
+int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
+ TRACE_IRQS_OFF
+ movl $_TIF_ALLWORK_MASK, %edi
+ /* edi: mask to check */
+GLOBAL(int_with_check)
+ LOCKDEP_SYS_EXIT_IRQ
+ GET_THREAD_INFO(%rcx)
+ movl TI_flags(%rcx), %edx
+ andl %edi, %edx
+ jnz int_careful
+ andl $~TS_COMPAT, TI_status(%rcx)
+ jmp syscall_return
+
+ /*
+ * Either reschedule or signal or syscall exit tracking needed.
+ * First do a reschedule test.
+ * edx: work, edi: workmask
+ */
+int_careful:
+ bt $TIF_NEED_RESCHED, %edx
+ jnc int_very_careful
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ pushq %rdi
+ SCHEDULE_USER
+ popq %rdi
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ jmp int_with_check
+
+ /* handle signals and tracing -- both require a full pt_regs */
+int_very_careful:
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ SAVE_EXTRA_REGS
+ /* Check for syscall exit trace */
+ testl $_TIF_WORK_SYSCALL_EXIT, %edx
+ jz int_signal
+ pushq %rdi
+ leaq 8(%rsp), %rdi /* &ptregs -> arg1 */
+ call syscall_trace_leave
+ popq %rdi
+ andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU), %edi
+ jmp int_restore_rest
+
+int_signal:
+ testl $_TIF_DO_NOTIFY_MASK, %edx
+ jz 1f
+ movq %rsp, %rdi /* &ptregs -> arg1 */
+ xorl %esi, %esi /* oldset -> arg2 */
+ call do_notify_resume
+1: movl $_TIF_WORK_MASK, %edi
+int_restore_rest:
+ RESTORE_EXTRA_REGS
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ jmp int_with_check
+
+syscall_return:
+ /* The IRETQ could re-enable interrupts: */
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_IRETQ
+
+ /*
+ * Try to use SYSRET instead of IRET if we're returning to
+ * a completely clean 64-bit userspace context.
+ */
+ movq RCX(%rsp), %rcx
+ movq RIP(%rsp), %r11
+ cmpq %rcx, %r11 /* RCX == RIP */
+ jne opportunistic_sysret_failed
+
+ /*
+ * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
+ * in kernel space. This essentially lets the user take over
+ * the kernel, since userspace controls RSP.
+ *
+ * If width of "canonical tail" ever becomes variable, this will need
+ * to be updated to remain correct on both old and new CPUs.
+ */
+ .ifne __VIRTUAL_MASK_SHIFT - 47
+ .error "virtual address width changed -- SYSRET checks need update"
+ .endif
+
+ /* Change top 16 bits to be the sign-extension of 47th bit */
+ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+ sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+
+ /* If this changed %rcx, it was not canonical */
+ cmpq %rcx, %r11
+ jne opportunistic_sysret_failed
+
+ cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ movq R11(%rsp), %r11
+ cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */
+ jne opportunistic_sysret_failed
+
+ /*
+ * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
+ * restoring TF results in a trap from userspace immediately after
+ * SYSRET. This would cause an infinite loop whenever #DB happens
+ * with register state that satisfies the opportunistic SYSRET
+ * conditions. For example, single-stepping this user code:
+ *
+ * movq $stuck_here, %rcx
+ * pushfq
+ * popq %r11
+ * stuck_here:
+ *
+ * would never get past 'stuck_here'.
+ */
+ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
+ jnz opportunistic_sysret_failed
+
+ /* nothing to check for RSP */
+
+ cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ /*
+ * We win! This label is here just for ease of understanding
+ * perf profiles. Nothing jumps here.
+ */
+syscall_return_via_sysret:
+ /* rcx and r11 are already restored (see code above) */
+ RESTORE_C_REGS_EXCEPT_RCX_R11
+ movq RSP(%rsp), %rsp
+ USERGS_SYSRET64
+
+opportunistic_sysret_failed:
+ SWAPGS
+ jmp restore_c_regs_and_iret
+END(entry_SYSCALL_64)
+
+
+ .macro FORK_LIKE func
+ENTRY(stub_\func)
+ SAVE_EXTRA_REGS 8
+ jmp sys_\func
+END(stub_\func)
+ .endm
+
+ FORK_LIKE clone
+ FORK_LIKE fork
+ FORK_LIKE vfork
+
+ENTRY(stub_execve)
+ call sys_execve
+return_from_execve:
+ testl %eax, %eax
+ jz 1f
+ /* exec failed, can use fast SYSRET code path in this case */
+ ret
+1:
+ /* must use IRET code path (pt_regs->cs may have changed) */
+ addq $8, %rsp
+ ZERO_EXTRA_REGS
+ movq %rax, RAX(%rsp)
+ jmp int_ret_from_sys_call
+END(stub_execve)
+/*
+ * Remaining execve stubs are only 7 bytes long.
+ * ENTRY() often aligns to 16 bytes, which in this case has no benefits.
+ */
+ .align 8
+GLOBAL(stub_execveat)
+ call sys_execveat
+ jmp return_from_execve
+END(stub_execveat)
+
+#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
+ .align 8
+GLOBAL(stub_x32_execve)
+GLOBAL(stub32_execve)
+ call compat_sys_execve
+ jmp return_from_execve
+END(stub32_execve)
+END(stub_x32_execve)
+ .align 8
+GLOBAL(stub_x32_execveat)
+GLOBAL(stub32_execveat)
+ call compat_sys_execveat
+ jmp return_from_execve
+END(stub32_execveat)
+END(stub_x32_execveat)
+#endif
+
+/*
+ * sigreturn is special because it needs to restore all registers on return.
+ * This cannot be done with SYSRET, so use the IRET return path instead.
+ */
+ENTRY(stub_rt_sigreturn)
+ /*
+ * SAVE_EXTRA_REGS result is not normally needed:
+ * sigreturn overwrites all pt_regs->GPREGS.
+ * But sigreturn can fail (!), and there is no easy way to detect that.
+ * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error,
+ * we SAVE_EXTRA_REGS here.
+ */
+ SAVE_EXTRA_REGS 8
+ call sys_rt_sigreturn
+return_from_stub:
+ addq $8, %rsp
+ RESTORE_EXTRA_REGS
+ movq %rax, RAX(%rsp)
+ jmp int_ret_from_sys_call
+END(stub_rt_sigreturn)
+
+#ifdef CONFIG_X86_X32_ABI
+ENTRY(stub_x32_rt_sigreturn)
+ SAVE_EXTRA_REGS 8
+ call sys32_x32_rt_sigreturn
+ jmp return_from_stub
+END(stub_x32_rt_sigreturn)
+#endif
+
+/*
+ * A newly forked process directly context switches into this address.
+ *
+ * rdi: prev task we switched from
+ */
+ENTRY(ret_from_fork)
+
+ LOCK ; btr $TIF_FORK, TI_flags(%r8)
+
+ pushq $0x0002
+ popfq /* reset kernel eflags */
+
+ call schedule_tail /* rdi: 'prev' task parameter */
+
+ RESTORE_EXTRA_REGS
+
+ testb $3, CS(%rsp) /* from kernel_thread? */
+
+ /*
+ * By the time we get here, we have no idea whether our pt_regs,
+ * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+ * the slow path, or one of the 32-bit compat paths.
+ * Use IRET code path to return, since it can safely handle
+ * all of the above.
+ */
+ jnz int_ret_from_sys_call
+
+ /*
+ * We came from kernel_thread
+ * nb: we depend on RESTORE_EXTRA_REGS above
+ */
+ movq %rbp, %rdi
+ call *%rbx
+ movl $0, RAX(%rsp)
+ RESTORE_EXTRA_REGS
+ jmp int_ret_from_sys_call
+END(ret_from_fork)
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+ .align 8
+ENTRY(irq_entries_start)
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ pushq $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_interrupt
+ .align 8
+ .endr
+END(irq_entries_start)
+
+/*
+ * Interrupt entry/exit.
+ *
+ * Interrupt entry points save only callee clobbered registers in fast path.
+ *
+ * Entry runs with interrupts off.
+ */
+
+/* 0(%rsp): ~(interrupt number) */
+ .macro interrupt func
+ cld
+ /*
+ * Since nothing in interrupt handling code touches r12...r15 members
+ * of "struct pt_regs", and since interrupts can nest, we can save
+ * four stack slots and simultaneously provide
+ * an unwind-friendly stack layout by saving "truncated" pt_regs
+ * exactly up to rbp slot, without these members.
+ */
+ ALLOC_PT_GPREGS_ON_STACK -RBP
+ SAVE_C_REGS -RBP
+ /* this goes to 0(%rsp) for unwinder, not for saving the value: */
+ SAVE_EXTRA_REGS_RBP -RBP
+
+ leaq -RBP(%rsp), %rdi /* arg1 for \func (pointer to pt_regs) */
+
+ testb $3, CS-RBP(%rsp)
+ jz 1f
+ SWAPGS
+1:
+ /*
+ * Save previous stack pointer, optionally switch to interrupt stack.
+ * irq_count is used to check if a CPU is already on an interrupt stack
+ * or not. While this is essentially redundant with preempt_count it is
+ * a little cheaper to use a separate counter in the PDA (short of
+ * moving irq_enter into assembly, which would be too much work)
+ */
+ movq %rsp, %rsi
+ incl PER_CPU_VAR(irq_count)
+ cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp
+ pushq %rsi
+ /* We entered an interrupt context - irqs are off: */
+ TRACE_IRQS_OFF
+
+ call \func
+ .endm
+
+ /*
+ * The interrupt stubs push (~vector+0x80) onto the stack and
+ * then jump to common_interrupt.
+ */
+ .p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+ ASM_CLAC
+ addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
+ interrupt do_IRQ
+ /* 0(%rsp): old RSP */
+ret_from_intr:
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ decl PER_CPU_VAR(irq_count)
+
+ /* Restore saved previous stack */
+ popq %rsi
+ /* return code expects complete pt_regs - adjust rsp accordingly: */
+ leaq -RBP(%rsi), %rsp
+
+ testb $3, CS(%rsp)
+ jz retint_kernel
+ /* Interrupt came from user space */
+retint_user:
+ GET_THREAD_INFO(%rcx)
+
+ /* %rcx: thread info. Interrupts are off. */
+retint_with_reschedule:
+ movl $_TIF_WORK_MASK, %edi
+retint_check:
+ LOCKDEP_SYS_EXIT_IRQ
+ movl TI_flags(%rcx), %edx
+ andl %edi, %edx
+ jnz retint_careful
+
+retint_swapgs: /* return to user-space */
+ /*
+ * The iretq could re-enable interrupts:
+ */
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_IRETQ
+
+ SWAPGS
+ jmp restore_c_regs_and_iret
+
+/* Returning to kernel space */
+retint_kernel:
+#ifdef CONFIG_PREEMPT
+ /* Interrupts are off */
+ /* Check if we need preemption */
+ bt $9, EFLAGS(%rsp) /* were interrupts off? */
+ jnc 1f
+0: cmpl $0, PER_CPU_VAR(__preempt_count)
+ jnz 1f
+ call preempt_schedule_irq
+ jmp 0b
+1:
+#endif
+ /*
+ * The iretq could re-enable interrupts:
+ */
+ TRACE_IRQS_IRETQ
+
+/*
+ * At this label, code paths which return to kernel and to user,
+ * which come from interrupts/exception and from syscalls, merge.
+ */
+restore_c_regs_and_iret:
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
+ INTERRUPT_RETURN
+
+ENTRY(native_iret)
+ /*
+ * Are we returning to a stack segment from the LDT? Note: in
+ * 64-bit mode SS:RSP on the exception stack is always valid.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ testb $4, (SS-RIP)(%rsp)
+ jnz native_irq_return_ldt
+#endif
+
+.global native_irq_return_iret
+native_irq_return_iret:
+ /*
+ * This may fault. Non-paranoid faults on return to userspace are
+ * handled by fixup_bad_iret. These include #SS, #GP, and #NP.
+ * Double-faults due to espfix64 are handled in do_double_fault.
+ * Other faults here are fatal.
+ */
+ iretq
+
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+ pushq %rax
+ pushq %rdi
+ SWAPGS
+ movq PER_CPU_VAR(espfix_waddr), %rdi
+ movq %rax, (0*8)(%rdi) /* RAX */
+ movq (2*8)(%rsp), %rax /* RIP */
+ movq %rax, (1*8)(%rdi)
+ movq (3*8)(%rsp), %rax /* CS */
+ movq %rax, (2*8)(%rdi)
+ movq (4*8)(%rsp), %rax /* RFLAGS */
+ movq %rax, (3*8)(%rdi)
+ movq (6*8)(%rsp), %rax /* SS */
+ movq %rax, (5*8)(%rdi)
+ movq (5*8)(%rsp), %rax /* RSP */
+ movq %rax, (4*8)(%rdi)
+ andl $0xffff0000, %eax
+ popq %rdi
+ orq PER_CPU_VAR(espfix_stack), %rax
+ SWAPGS
+ movq %rax, %rsp
+ popq %rax
+ jmp native_irq_return_iret
+#endif
+
+ /* edi: workmask, edx: work */
+retint_careful:
+ bt $TIF_NEED_RESCHED, %edx
+ jnc retint_signal
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ pushq %rdi
+ SCHEDULE_USER
+ popq %rdi
+ GET_THREAD_INFO(%rcx)
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ jmp retint_check
+
+retint_signal:
+ testl $_TIF_DO_NOTIFY_MASK, %edx
+ jz retint_swapgs
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ SAVE_EXTRA_REGS
+ movq $-1, ORIG_RAX(%rsp)
+ xorl %esi, %esi /* oldset */
+ movq %rsp, %rdi /* &pt_regs */
+ call do_notify_resume
+ RESTORE_EXTRA_REGS
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ GET_THREAD_INFO(%rcx)
+ jmp retint_with_reschedule
+
+END(common_interrupt)
+
+/*
+ * APIC interrupts.
+ */
+.macro apicinterrupt3 num sym do_sym
+ENTRY(\sym)
+ ASM_CLAC
+ pushq $~(\num)
+.Lcommon_\sym:
+ interrupt \do_sym
+ jmp ret_from_intr
+END(\sym)
+.endm
+
+#ifdef CONFIG_TRACING
+#define trace(sym) trace_##sym
+#define smp_trace(sym) smp_trace_##sym
+
+.macro trace_apicinterrupt num sym
+apicinterrupt3 \num trace(\sym) smp_trace(\sym)
+.endm
+#else
+.macro trace_apicinterrupt num sym do_sym
+.endm
+#endif
+
+.macro apicinterrupt num sym do_sym
+apicinterrupt3 \num \sym \do_sym
+trace_apicinterrupt \num \sym
+.endm
+
+#ifdef CONFIG_SMP
+apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
+apicinterrupt3 REBOOT_VECTOR reboot_interrupt smp_reboot_interrupt
+#endif
+
+#ifdef CONFIG_X86_UV
+apicinterrupt3 UV_BAU_MESSAGE uv_bau_message_intr1 uv_bau_message_interrupt
+#endif
+
+apicinterrupt LOCAL_TIMER_VECTOR apic_timer_interrupt smp_apic_timer_interrupt
+apicinterrupt X86_PLATFORM_IPI_VECTOR x86_platform_ipi smp_x86_platform_ipi
+
+#ifdef CONFIG_HAVE_KVM
+apicinterrupt3 POSTED_INTR_VECTOR kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi
+#endif
+
+#ifdef CONFIG_X86_MCE_THRESHOLD
+apicinterrupt THRESHOLD_APIC_VECTOR threshold_interrupt smp_threshold_interrupt
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+apicinterrupt DEFERRED_ERROR_VECTOR deferred_error_interrupt smp_deferred_error_interrupt
+#endif
+
+#ifdef CONFIG_X86_THERMAL_VECTOR
+apicinterrupt THERMAL_APIC_VECTOR thermal_interrupt smp_thermal_interrupt
+#endif
+
+#ifdef CONFIG_SMP
+apicinterrupt CALL_FUNCTION_SINGLE_VECTOR call_function_single_interrupt smp_call_function_single_interrupt
+apicinterrupt CALL_FUNCTION_VECTOR call_function_interrupt smp_call_function_interrupt
+apicinterrupt RESCHEDULE_VECTOR reschedule_interrupt smp_reschedule_interrupt
+#endif
+
+apicinterrupt ERROR_APIC_VECTOR error_interrupt smp_error_interrupt
+apicinterrupt SPURIOUS_APIC_VECTOR spurious_interrupt smp_spurious_interrupt
+
+#ifdef CONFIG_IRQ_WORK
+apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt
+#endif
+
+/*
+ * Exception entry points.
+ */
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
+
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
+ENTRY(\sym)
+ /* Sanity check */
+ .if \shift_ist != -1 && \paranoid == 0
+ .error "using shift_ist requires paranoid=1"
+ .endif
+
+ ASM_CLAC
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
+
+ .ifeq \has_error_code
+ pushq $-1 /* ORIG_RAX: no syscall to restart */
+ .endif
+
+ ALLOC_PT_GPREGS_ON_STACK
+
+ .if \paranoid
+ .if \paranoid == 1
+ testb $3, CS(%rsp) /* If coming from userspace, switch stacks */
+ jnz 1f
+ .endif
+ call paranoid_entry
+ .else
+ call error_entry
+ .endif
+ /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
+
+ .if \paranoid
+ .if \shift_ist != -1
+ TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */
+ .else
+ TRACE_IRQS_OFF
+ .endif
+ .endif
+
+ movq %rsp, %rdi /* pt_regs pointer */
+
+ .if \has_error_code
+ movq ORIG_RAX(%rsp), %rsi /* get error code */
+ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
+ .else
+ xorl %esi, %esi /* no error code */
+ .endif
+
+ .if \shift_ist != -1
+ subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+ .endif
+
+ call \do_sym
+
+ .if \shift_ist != -1
+ addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+ .endif
+
+ /* these procedures expect "no swapgs" flag in ebx */
+ .if \paranoid
+ jmp paranoid_exit
+ .else
+ jmp error_exit
+ .endif
+
+ .if \paranoid == 1
+ /*
+ * Paranoid entry from userspace. Switch stacks and treat it
+ * as a normal entry. This means that paranoid handlers
+ * run in real process context if user_mode(regs).
+ */
+1:
+ call error_entry
+
+
+ movq %rsp, %rdi /* pt_regs pointer */
+ call sync_regs
+ movq %rax, %rsp /* switch stack */
+
+ movq %rsp, %rdi /* pt_regs pointer */
+
+ .if \has_error_code
+ movq ORIG_RAX(%rsp), %rsi /* get error code */
+ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
+ .else
+ xorl %esi, %esi /* no error code */
+ .endif
+
+ call \do_sym
+
+ jmp error_exit /* %ebx: no swapgs flag */
+ .endif
+END(\sym)
+.endm
+
+#ifdef CONFIG_TRACING
+.macro trace_idtentry sym do_sym has_error_code:req
+idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code
+idtentry \sym \do_sym has_error_code=\has_error_code
+.endm
+#else
+.macro trace_idtentry sym do_sym has_error_code:req
+idtentry \sym \do_sym has_error_code=\has_error_code
+.endm
+#endif
+
+idtentry divide_error do_divide_error has_error_code=0
+idtentry overflow do_overflow has_error_code=0
+idtentry bounds do_bounds has_error_code=0
+idtentry invalid_op do_invalid_op has_error_code=0
+idtentry device_not_available do_device_not_available has_error_code=0
+idtentry double_fault do_double_fault has_error_code=1 paranoid=2
+idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
+idtentry invalid_TSS do_invalid_TSS has_error_code=1
+idtentry segment_not_present do_segment_not_present has_error_code=1
+idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
+idtentry coprocessor_error do_coprocessor_error has_error_code=0
+idtentry alignment_check do_alignment_check has_error_code=1
+idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
+
+
+ /*
+ * Reload gs selector with exception handling
+ * edi: new selector
+ */
+ENTRY(native_load_gs_index)
+ pushfq
+ DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
+ SWAPGS
+gs_change:
+ movl %edi, %gs
+2: mfence /* workaround */
+ SWAPGS
+ popfq
+ ret
+END(native_load_gs_index)
+
+ _ASM_EXTABLE(gs_change, bad_gs)
+ .section .fixup, "ax"
+ /* running with kernelgs */
+bad_gs:
+ SWAPGS /* switch back to user gs */
+ xorl %eax, %eax
+ movl %eax, %gs
+ jmp 2b
+ .previous
+
+/* Call softirq on interrupt stack. Interrupts are off. */
+ENTRY(do_softirq_own_stack)
+ pushq %rbp
+ mov %rsp, %rbp
+ incl PER_CPU_VAR(irq_count)
+ cmove PER_CPU_VAR(irq_stack_ptr), %rsp
+ push %rbp /* frame pointer backlink */
+ call __do_softirq
+ leaveq
+ decl PER_CPU_VAR(irq_count)
+ ret
+END(do_softirq_own_stack)
+
+#ifdef CONFIG_XEN
+idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
+
+/*
+ * A note on the "critical region" in our callback handler.
+ * We want to avoid stacking callback handlers due to events occurring
+ * during handling of the last event. To do this, we keep events disabled
+ * until we've done all processing. HOWEVER, we must enable events before
+ * popping the stack frame (can't be done atomically) and so it would still
+ * be possible to get enough handler activations to overflow the stack.
+ * Although unlikely, bugs of that kind are hard to track down, so we'd
+ * like to avoid the possibility.
+ * So, on entry to the handler we detect whether we interrupted an
+ * existing activation in its critical region -- if so, we pop the current
+ * activation and restart the handler using the previous one.
+ */
+ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */
+
+/*
+ * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
+ * see the correct pointer to the pt_regs
+ */
+ movq %rdi, %rsp /* we don't return, adjust the stack frame */
+11: incl PER_CPU_VAR(irq_count)
+ movq %rsp, %rbp
+ cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp
+ pushq %rbp /* frame pointer backlink */
+ call xen_evtchn_do_upcall
+ popq %rsp
+ decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
+ jmp error_exit
+END(xen_do_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ * 1. Fault while reloading DS, ES, FS or GS
+ * 2. Fault while executing IRET
+ * Category 1 we do not need to fix up as Xen has already reloaded all segment
+ * registers that could be reloaded and zeroed the others.
+ * Category 2 we fix up by killing the current process. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by comparing each saved segment register
+ * with its current contents: any discrepancy means we in category 1.
+ */
+ENTRY(xen_failsafe_callback)
+ movl %ds, %ecx
+ cmpw %cx, 0x10(%rsp)
+ jne 1f
+ movl %es, %ecx
+ cmpw %cx, 0x18(%rsp)
+ jne 1f
+ movl %fs, %ecx
+ cmpw %cx, 0x20(%rsp)
+ jne 1f
+ movl %gs, %ecx
+ cmpw %cx, 0x28(%rsp)
+ jne 1f
+ /* All segments match their saved values => Category 2 (Bad IRET). */
+ movq (%rsp), %rcx
+ movq 8(%rsp), %r11
+ addq $0x30, %rsp
+ pushq $0 /* RIP */
+ pushq %r11
+ pushq %rcx
+ jmp general_protection
+1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
+ movq (%rsp), %rcx
+ movq 8(%rsp), %r11
+ addq $0x30, %rsp
+ pushq $-1 /* orig_ax = -1 => not a system call */
+ ALLOC_PT_GPREGS_ON_STACK
+ SAVE_C_REGS
+ SAVE_EXTRA_REGS
+ jmp error_exit
+END(xen_failsafe_callback)
+
+apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
+ xen_hvm_callback_vector xen_evtchn_do_upcall
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
+ hyperv_callback_vector hyperv_vector_handler
+#endif /* CONFIG_HYPERV */
+
+idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry stack_segment do_stack_segment has_error_code=1
+
+#ifdef CONFIG_XEN
+idtentry xen_debug do_debug has_error_code=0
+idtentry xen_int3 do_int3 has_error_code=0
+idtentry xen_stack_segment do_stack_segment has_error_code=1
+#endif
+
+idtentry general_protection do_general_protection has_error_code=1
+trace_idtentry page_fault do_page_fault has_error_code=1
+
+#ifdef CONFIG_KVM_GUEST
+idtentry async_page_fault do_async_page_fault has_error_code=1
+#endif
+
+#ifdef CONFIG_X86_MCE
+idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
+#endif
+
+/*
+ * Save all registers in pt_regs, and switch gs if needed.
+ * Use slow, but surefire "are we in kernel?" check.
+ * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ */
+ENTRY(paranoid_entry)
+ cld
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
+ movl $1, %ebx
+ movl $MSR_GS_BASE, %ecx
+ rdmsr
+ testl %edx, %edx
+ js 1f /* negative -> in kernel */
+ SWAPGS
+ xorl %ebx, %ebx
+1: ret
+END(paranoid_entry)
+
+/*
+ * "Paranoid" exit path from exception stack. This is invoked
+ * only on return from non-NMI IST interrupts that came
+ * from kernel space.
+ *
+ * We may be returning to very strange contexts (e.g. very early
+ * in syscall entry), so checking for preemption here would
+ * be complicated. Fortunately, we there's no good reason
+ * to try to handle preemption here.
+ *
+ * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
+ */
+ENTRY(paranoid_exit)
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF_DEBUG
+ testl %ebx, %ebx /* swapgs needed? */
+ jnz paranoid_exit_no_swapgs
+ TRACE_IRQS_IRETQ
+ SWAPGS_UNSAFE_STACK
+ jmp paranoid_exit_restore
+paranoid_exit_no_swapgs:
+ TRACE_IRQS_IRETQ_DEBUG
+paranoid_exit_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
+ INTERRUPT_RETURN
+END(paranoid_exit)
+
+/*
+ * Save all registers in pt_regs, and switch gs if needed.
+ * Return: EBX=0: came from user mode; EBX=1: otherwise
+ */
+ENTRY(error_entry)
+ cld
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
+ xorl %ebx, %ebx
+ testb $3, CS+8(%rsp)
+ jz error_kernelspace
+
+ /* We entered from user mode */
+ SWAPGS
+
+error_entry_done:
+ TRACE_IRQS_OFF
+ ret
+
+ /*
+ * There are two places in the kernel that can potentially fault with
+ * usergs. Handle them here. B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
+ */
+error_kernelspace:
+ incl %ebx
+ leaq native_irq_return_iret(%rip), %rcx
+ cmpq %rcx, RIP+8(%rsp)
+ je error_bad_iret
+ movl %ecx, %eax /* zero extend */
+ cmpq %rax, RIP+8(%rsp)
+ je bstep_iret
+ cmpq $gs_change, RIP+8(%rsp)
+ jne error_entry_done
+
+ /*
+ * hack: gs_change can fail with user gsbase. If this happens, fix up
+ * gsbase and proceed. We'll fix up the exception and land in
+ * gs_change's error handler with kernel gsbase.
+ */
+ SWAPGS
+ jmp error_entry_done
+
+bstep_iret:
+ /* Fix truncated RIP */
+ movq %rcx, RIP+8(%rsp)
+ /* fall through */
+
+error_bad_iret:
+ /*
+ * We came from an IRET to user mode, so we have user gsbase.
+ * Switch to kernel gsbase:
+ */
+ SWAPGS
+
+ /*
+ * Pretend that the exception came from user mode: set up pt_regs
+ * as if we faulted immediately after IRET and clear EBX so that
+ * error_exit knows that we will be returning to user mode.
+ */
+ mov %rsp, %rdi
+ call fixup_bad_iret
+ mov %rax, %rsp
+ decl %ebx
+ jmp error_entry_done
+END(error_entry)
+
+
+/*
+ * On entry, EBS is a "return to kernel mode" flag:
+ * 1: already in kernel mode, don't need SWAPGS
+ * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
+ */
+ENTRY(error_exit)
+ movl %ebx, %eax
+ RESTORE_EXTRA_REGS
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl %eax, %eax
+ jnz retint_kernel
+ jmp retint_user
+END(error_exit)
+
+/* Runs on exception stack */
+ENTRY(nmi)
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
+ /*
+ * We allow breakpoints in NMIs. If a breakpoint occurs, then
+ * the iretq it performs will take us out of NMI context.
+ * This means that we can have nested NMIs where the next
+ * NMI is using the top of the stack of the previous NMI. We
+ * can't let it execute because the nested NMI will corrupt the
+ * stack of the previous NMI. NMI handlers are not re-entrant
+ * anyway.
+ *
+ * To handle this case we do the following:
+ * Check the a special location on the stack that contains
+ * a variable that is set when NMIs are executing.
+ * The interrupted task's stack is also checked to see if it
+ * is an NMI stack.
+ * If the variable is not set and the stack is not the NMI
+ * stack then:
+ * o Set the special variable on the stack
+ * o Copy the interrupt frame into a "saved" location on the stack
+ * o Copy the interrupt frame into a "copy" location on the stack
+ * o Continue processing the NMI
+ * If the variable is set or the previous stack is the NMI stack:
+ * o Modify the "copy" location to jump to the repeate_nmi
+ * o return back to the first NMI
+ *
+ * Now on exit of the first NMI, we first clear the stack variable
+ * The NMI stack will tell any nested NMIs at that point that it is
+ * nested. Then we pop the stack normally with iret, and if there was
+ * a nested NMI that updated the copy interrupt stack frame, a
+ * jump will be made to the repeat_nmi code that will handle the second
+ * NMI.
+ */
+
+ /* Use %rdx as our temp variable throughout */
+ pushq %rdx
+
+ /*
+ * If %cs was not the kernel segment, then the NMI triggered in user
+ * space, which means it is definitely not nested.
+ */
+ cmpl $__KERNEL_CS, 16(%rsp)
+ jne first_nmi
+
+ /*
+ * Check the special variable on the stack to see if NMIs are
+ * executing.
+ */
+ cmpl $1, -8(%rsp)
+ je nested_nmi
+
+ /*
+ * Now test if the previous stack was an NMI stack.
+ * We need the double check. We check the NMI stack to satisfy the
+ * race when the first NMI clears the variable before returning.
+ * We check the variable because the first NMI could be in a
+ * breakpoint routine using a breakpoint stack.
+ */
+ lea 6*8(%rsp), %rdx
+ /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
+ cmpq %rdx, 4*8(%rsp)
+ /* If the stack pointer is above the NMI stack, this is a normal NMI */
+ ja first_nmi
+
+ subq $EXCEPTION_STKSZ, %rdx
+ cmpq %rdx, 4*8(%rsp)
+ /* If it is below the NMI stack, it is a normal NMI */
+ jb first_nmi
+ /* Ah, it is within the NMI stack, treat it as nested */
+
+nested_nmi:
+ /*
+ * Do nothing if we interrupted the fixup in repeat_nmi.
+ * It's about to repeat the NMI handler, so we are fine
+ * with ignoring this one.
+ */
+ movq $repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja 1f
+ movq $end_repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja nested_nmi_out
+
+1:
+ /* Set up the interrupted NMIs stack to jump to repeat_nmi */
+ leaq -1*8(%rsp), %rdx
+ movq %rdx, %rsp
+ leaq -10*8(%rsp), %rdx
+ pushq $__KERNEL_DS
+ pushq %rdx
+ pushfq
+ pushq $__KERNEL_CS
+ pushq $repeat_nmi
+
+ /* Put stack back */
+ addq $(6*8), %rsp
+
+nested_nmi_out:
+ popq %rdx
+
+ /* No need to check faults here */
+ INTERRUPT_RETURN
+
+first_nmi:
+ /*
+ * Because nested NMIs will use the pushed location that we
+ * stored in rdx, we must keep that space available.
+ * Here's what our stack frame will look like:
+ * +-------------------------+
+ * | original SS |
+ * | original Return RSP |
+ * | original RFLAGS |
+ * | original CS |
+ * | original RIP |
+ * +-------------------------+
+ * | temp storage for rdx |
+ * +-------------------------+
+ * | NMI executing variable |
+ * +-------------------------+
+ * | copied SS |
+ * | copied Return RSP |
+ * | copied RFLAGS |
+ * | copied CS |
+ * | copied RIP |
+ * +-------------------------+
+ * | Saved SS |
+ * | Saved Return RSP |
+ * | Saved RFLAGS |
+ * | Saved CS |
+ * | Saved RIP |
+ * +-------------------------+
+ * | pt_regs |
+ * +-------------------------+
+ *
+ * The saved stack frame is used to fix up the copied stack frame
+ * that a nested NMI may change to make the interrupted NMI iret jump
+ * to the repeat_nmi. The original stack frame and the temp storage
+ * is also used by nested NMIs and can not be trusted on exit.
+ */
+ /* Do not pop rdx, nested NMIs will corrupt that part of the stack */
+ movq (%rsp), %rdx
+
+ /* Set the NMI executing variable on the stack. */
+ pushq $1
+
+ /* Leave room for the "copied" frame */
+ subq $(5*8), %rsp
+
+ /* Copy the stack frame to the Saved frame */
+ .rept 5
+ pushq 11*8(%rsp)
+ .endr
+
+ /* Everything up to here is safe from nested NMIs */
+
+ /*
+ * If there was a nested NMI, the first NMI's iret will return
+ * here. But NMIs are still enabled and we can take another
+ * nested NMI. The nested NMI checks the interrupted RIP to see
+ * if it is between repeat_nmi and end_repeat_nmi, and if so
+ * it will just return, as we are about to repeat an NMI anyway.
+ * This makes it safe to copy to the stack frame that a nested
+ * NMI will update.
+ */
+repeat_nmi:
+ /*
+ * Update the stack variable to say we are still in NMI (the update
+ * is benign for the non-repeat case, where 1 was pushed just above
+ * to this very stack slot).
+ */
+ movq $1, 10*8(%rsp)
+
+ /* Make another copy, this one may be modified by nested NMIs */
+ addq $(10*8), %rsp
+ .rept 5
+ pushq -6*8(%rsp)
+ .endr
+ subq $(5*8), %rsp
+end_repeat_nmi:
+
+ /*
+ * Everything below this point can be preempted by a nested
+ * NMI if the first NMI took an exception and reset our iret stack
+ * so that we repeat another NMI.
+ */
+ pushq $-1 /* ORIG_RAX: no syscall to restart */
+ ALLOC_PT_GPREGS_ON_STACK
+
+ /*
+ * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
+ * as we should not be calling schedule in NMI context.
+ * Even with normal interrupts enabled. An NMI should not be
+ * setting NEED_RESCHED or anything that normal interrupts and
+ * exceptions might do.
+ */
+ call paranoid_entry
+
+ /*
+ * Save off the CR2 register. If we take a page fault in the NMI then
+ * it could corrupt the CR2 value. If the NMI preempts a page fault
+ * handler before it was able to read the CR2 register, and then the
+ * NMI itself takes a page fault, the page fault that was preempted
+ * will read the information from the NMI page fault and not the
+ * origin fault. Save it off and restore it if it changes.
+ * Use the r12 callee-saved register.
+ */
+ movq %cr2, %r12
+
+ /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
+ movq %rsp, %rdi
+ movq $-1, %rsi
+ call do_nmi
+
+ /* Did the NMI take a page fault? Restore cr2 if it did */
+ movq %cr2, %rcx
+ cmpq %rcx, %r12
+ je 1f
+ movq %r12, %cr2
+1:
+ testl %ebx, %ebx /* swapgs needed? */
+ jnz nmi_restore
+nmi_swapgs:
+ SWAPGS_UNSAFE_STACK
+nmi_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ /* Pop the extra iret frame at once */
+ REMOVE_PT_GPREGS_FROM_STACK 6*8
+
+ /* Clear the NMI executing stack variable */
+ movq $0, 5*8(%rsp)
+ INTERRUPT_RETURN
+END(nmi)
+
+ENTRY(ignore_sysret)
+ mov $-ENOSYS, %eax
+ sysret
+END(ignore_sysret)
--- /dev/null
+/*
+ * Compatibility mode system call entry point for x86-64.
+ *
+ * Copyright 2000-2002 Andi Kleen, SuSE Labs.
+ */
+#include "calling.h"
+#include <asm/asm-offsets.h>
+#include <asm/current.h>
+#include <asm/errno.h>
+#include <asm/ia32_unistd.h>
+#include <asm/thread_info.h>
+#include <asm/segment.h>
+#include <asm/irqflags.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <linux/linkage.h>
+#include <linux/err.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE 0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysexit_audit ia32_ret_from_sys_call
+# define sysretl_audit ia32_ret_from_sys_call
+#endif
+
+ .section .entry.text, "ax"
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret32)
+ swapgs
+ sysretl
+ENDPROC(native_usergs_sysret32)
+#endif
+
+/*
+ * 32-bit SYSENTER instruction entry.
+ *
+ * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
+ * IF and VM in rflags are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old rip (!!!) and rflags.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp user stack
+ * 0(%ebp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSENTER_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ SWAPGS_UNSAFE_STACK
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %ebp, %ebp
+ movl %eax, %eax
+
+ movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER32_DS /* pt_regs->ss */
+ pushq %rbp /* pt_regs->sp */
+ pushfq /* pt_regs->flags */
+ pushq $__USER32_CS /* pt_regs->cs */
+ pushq %r10 /* pt_regs->ip = thread_info->sysenter_return */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ cld
+ sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+ /*
+ * no need to do an access_ok check here because rbp has been
+ * 32-bit zero extended
+ */
+ ASM_STAC
+1: movl (%rbp), %ebp
+ _ASM_EXTABLE(1b, ia32_badarg)
+ ASM_CLAC
+
+ /*
+ * Sysenter doesn't filter flags, so we need to clear NT
+ * ourselves. To save a few cycles, we can check whether
+ * NT was set instead of doing an unconditional popfq.
+ */
+ testl $X86_EFLAGS_NT, EFLAGS(%rsp)
+ jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysenter_tracesys
+
+sysenter_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+sysenter_dispatch:
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysexit_audit
+sysexit_from_sys_call:
+ /*
+ * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
+ * NMI between STI and SYSEXIT has poorly specified behavior,
+ * and and NMI followed by an IRQ with usergs is fatal. So
+ * we just pretend we're using SYSEXIT but we really use
+ * SYSRETL instead.
+ *
+ * This code path is still called 'sysexit' because it pairs
+ * with 'sysenter' and it uses the SYSENTER calling convention.
+ */
+ andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ movl RIP(%rsp), %ecx /* User %eip */
+ RESTORE_RSI_RDI
+ xorl %edx, %edx /* Do not leak kernel information */
+ xorq %r8, %r8
+ xorq %r9, %r9
+ xorq %r10, %r10
+ movl EFLAGS(%rsp), %r11d /* User eflags */
+ TRACE_IRQS_ON
+
+ /*
+ * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT,
+ * since it avoids a dicey window with interrupts enabled.
+ */
+ movl RSP(%rsp), %esp
+
+ /*
+ * USERGS_SYSRET32 does:
+ * gsbase = user's gs base
+ * eip = ecx
+ * rflags = r11
+ * cs = __USER32_CS
+ * ss = __USER_DS
+ *
+ * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
+ *
+ * pop %ebp
+ * pop %edx
+ * pop %ecx
+ *
+ * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
+ * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's
+ * address (already known to user code), and R12-R15 are
+ * callee-saved and therefore don't contain any interesting
+ * kernel data.
+ */
+ USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+ .macro auditsys_entry_common
+ /*
+ * At this point, registers hold syscall args in the 32-bit syscall ABI:
+ * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
+ *
+ * We want to pass them to __audit_syscall_entry(), which is a 64-bit
+ * C function with 5 parameters, so shuffle them to match what
+ * the function expects: RDI,RSI,RDX,RCX,R8.
+ */
+ movl %esi, %r8d /* arg5 (R8 ) <= 4th syscall arg (ESI) */
+ xchg %ecx, %edx /* arg4 (RCX) <= 3rd syscall arg (EDX) */
+ /* arg3 (RDX) <= 2nd syscall arg (ECX) */
+ movl %ebx, %esi /* arg2 (RSI) <= 1st syscall arg (EBX) */
+ movl %eax, %edi /* arg1 (RDI) <= syscall number (EAX) */
+ call __audit_syscall_entry
+
+ /*
+ * We are going to jump back to the syscall dispatch code.
+ * Prepare syscall args as required by the 64-bit C ABI.
+ * Registers clobbered by __audit_syscall_entry() are
+ * loaded from pt_regs on stack:
+ */
+ movl ORIG_RAX(%rsp), %eax /* syscall number */
+ movl %ebx, %edi /* arg1 */
+ movl RCX(%rsp), %esi /* arg2 */
+ movl RDX(%rsp), %edx /* arg3 */
+ movl RSI(%rsp), %ecx /* arg4 */
+ movl RDI(%rsp), %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ .endm
+
+ .macro auditsys_exit exit
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz ia32_ret_from_sys_call
+ TRACE_IRQS_ON
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ movl %eax, %esi /* second arg, syscall return value */
+ cmpl $-MAX_ERRNO, %eax /* is it an error ? */
+ jbe 1f
+ movslq %eax, %rsi /* if error sign extend to 64 bits */
+1: setbe %al /* 1 if error, 0 if not */
+ movzbl %al, %edi /* zero-extend that into %edi */
+ call __audit_syscall_exit
+ movq RAX(%rsp), %rax /* reload syscall return value */
+ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz \exit
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ jmp int_with_check
+ .endm
+
+sysenter_auditsys:
+ auditsys_entry_common
+ jmp sysenter_dispatch
+
+sysexit_audit:
+ auditsys_exit sysexit_from_sys_call
+#endif
+
+sysenter_fix_flags:
+ pushq $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+ popfq
+ jmp sysenter_flags_fixed
+
+sysenter_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz sysenter_auditsys
+#endif
+ SAVE_EXTRA_REGS
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+
+ /* Reload arg registers from stack. (see sysenter_tracesys) */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+
+ RESTORE_EXTRA_REGS
+ jmp sysenter_do_call
+ENDPROC(entry_SYSENTER_compat)
+
+/*
+ * 32-bit SYSCALL instruction entry.
+ *
+ * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Note: rflags saving+masking-with-MSR happens only in Long mode
+ * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
+ * Don't get confused: rflags saving+masking depends on Long Mode Active bit
+ * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
+ * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
+ *
+ * Arguments:
+ * eax system call number
+ * ecx return address
+ * ebx arg1
+ * ebp arg2 (note: not saved in the stack frame, should not be touched)
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * esp user stack
+ * 0(%esp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSCALL_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ SWAPGS_UNSAFE_STACK
+ movl %esp, %r8d
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %eax, %eax
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER32_DS /* pt_regs->ss */
+ pushq %r8 /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER32_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rbp /* pt_regs->cx */
+ movl %ebp, %ecx
+ pushq $-ENOSYS /* pt_regs->ax */
+ sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+ /*
+ * No need to do an access_ok check here because r8 has been
+ * 32-bit zero extended:
+ */
+ ASM_STAC
+1: movl (%r8), %ebp
+ _ASM_EXTABLE(1b, ia32_badarg)
+ ASM_CLAC
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz cstar_tracesys
+
+cstar_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+
+cstar_dispatch:
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ movl RCX(%rsp), %ebp
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz sysretl_audit
+
+sysretl_from_sys_call:
+ andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ RESTORE_RSI_RDI_RDX
+ movl RIP(%rsp), %ecx
+ movl EFLAGS(%rsp), %r11d
+ xorq %r10, %r10
+ xorq %r9, %r9
+ xorq %r8, %r8
+ TRACE_IRQS_ON
+ movl RSP(%rsp), %esp
+ /*
+ * 64-bit->32-bit SYSRET restores eip from ecx,
+ * eflags from r11 (but RF and VM bits are forced to 0),
+ * cs and ss are loaded from MSRs.
+ * (Note: 32-bit->32-bit SYSRET is different: since r11
+ * does not exist, it merely sets eflags.IF=1).
+ *
+ * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+ * descriptor is not reinitialized. This means that we must
+ * avoid SYSRET with SS == NULL, which could happen if we schedule,
+ * exit the kernel, and re-enter using an interrupt vector. (All
+ * interrupt entries on x86_64 set SS to NULL.) We prevent that
+ * from happening by reloading SS in __switch_to.
+ */
+ USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+cstar_auditsys:
+ auditsys_entry_common
+ jmp cstar_dispatch
+
+sysretl_audit:
+ auditsys_exit sysretl_from_sys_call
+#endif
+
+cstar_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jz cstar_auditsys
+#endif
+ SAVE_EXTRA_REGS
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+
+ /* Reload arg registers from stack. (see sysenter_tracesys) */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+
+ RESTORE_EXTRA_REGS
+ jmp cstar_do_call
+END(entry_SYSCALL_compat)
+
+ia32_badarg:
+ ASM_CLAC
+ movq $-EFAULT, RAX(%rsp)
+ia32_ret_from_sys_call:
+ xorl %eax, %eax /* Do not leak kernel information */
+ movq %rax, R11(%rsp)
+ movq %rax, R10(%rsp)
+ movq %rax, R9(%rsp)
+ movq %rax, R8(%rsp)
+ jmp int_ret_from_sys_call
+
+/*
+ * Emulated IA32 system calls via int 0x80.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp arg6 (note: not saved in the stack frame, should not be touched)
+ *
+ * Notes:
+ * Uses the same stack frame as the x86-64 version.
+ * All registers except eax must be saved (but ptrace may violate that).
+ * Arguments are zero extended. For system calls that want sign extension and
+ * take long arguments a wrapper is needed. Most calls can just be called
+ * directly.
+ * Assumes it is only called from user space and entered with interrupts off.
+ */
+
+ENTRY(entry_INT80_compat)
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
+ SWAPGS
+ ENABLE_INTERRUPTS(CLBR_NONE)
+
+ /* Zero-extending 32-bit regs, do not remove */
+ movl %eax, %eax
+
+ /* Construct struct pt_regs on stack (iret frame is already on stack) */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq %rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ pushq $0 /* pt_regs->r8 */
+ pushq $0 /* pt_regs->r9 */
+ pushq $0 /* pt_regs->r10 */
+ pushq $0 /* pt_regs->r11 */
+ cld
+ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+
+ orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz ia32_tracesys
+
+ia32_do_call:
+ /* 32-bit syscall -> 64-bit C ABI argument conversion */
+ movl %edi, %r8d /* arg5 */
+ movl %ebp, %r9d /* arg6 */
+ xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
+ movl %ebx, %edi /* arg1 */
+ movl %edx, %edx /* arg3 (zero extension) */
+ cmpq $(IA32_NR_syscalls-1), %rax
+ ja 1f
+
+ call *ia32_sys_call_table(, %rax, 8)
+ movq %rax, RAX(%rsp)
+1:
+ jmp int_ret_from_sys_call
+
+ia32_tracesys:
+ SAVE_EXTRA_REGS
+ movq %rsp, %rdi /* &pt_regs -> arg1 */
+ call syscall_trace_enter
+ /*
+ * Reload arg registers from stack in case ptrace changed them.
+ * Don't reload %eax because syscall_trace_enter() returned
+ * the %rax value we should see. But do truncate it to 32 bits.
+ * If it's -1 to make us punt the syscall, then (u32)-1 is still
+ * an appropriately invalid value.
+ */
+ movl RCX(%rsp), %ecx
+ movl RDX(%rsp), %edx
+ movl RSI(%rsp), %esi
+ movl RDI(%rsp), %edi
+ movl %eax, %eax /* zero extension */
+ RESTORE_EXTRA_REGS
+ jmp ia32_do_call
+END(entry_INT80_compat)
+
+ .macro PTREGSCALL label, func
+ ALIGN
+GLOBAL(\label)
+ leaq \func(%rip), %rax
+ jmp ia32_ptregs_common
+ .endm
+
+ PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
+ PTREGSCALL stub32_sigreturn, sys32_sigreturn
+ PTREGSCALL stub32_fork, sys_fork
+ PTREGSCALL stub32_vfork, sys_vfork
+
+ ALIGN
+GLOBAL(stub32_clone)
+ leaq sys_clone(%rip), %rax
+ /*
+ * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
+ * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
+ *
+ * The native 64-bit kernel's sys_clone() implements the latter,
+ * so we need to swap arguments here before calling it:
+ */
+ xchg %r8, %rcx
+ jmp ia32_ptregs_common
+
+ ALIGN
+ia32_ptregs_common:
+ SAVE_EXTRA_REGS 8
+ call *%rax
+ RESTORE_EXTRA_REGS 8
+ ret
+END(ia32_ptregs_common)
--- /dev/null
+/* System call table for i386. */
+
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <linux/cache.h>
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_IA32_EMULATION
+#define SYM(sym, compat) compat
+#else
+#define SYM(sym, compat) sym
+#define ia32_sys_call_table sys_call_table
+#define __NR_syscall_compat_max __NR_syscall_max
+#endif
+
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
+#include <asm/syscalls_32.h>
+#undef __SYSCALL_I386
+
+#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat),
+
+typedef asmlinkage void (*sys_call_ptr_t)(void);
+
+extern asmlinkage void sys_ni_syscall(void);
+
+__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
+ /*
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
+ [0 ... __NR_syscall_compat_max] = &sys_ni_syscall,
+#include <asm/syscalls_32.h>
+};
--- /dev/null
+/* System call table for x86-64. */
+
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <linux/cache.h>
+#include <asm/asm-offsets.h>
+#include <asm/syscall.h>
+
+#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
+
+#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
+#include <asm/syscalls_64.h>
+#undef __SYSCALL_64
+
+#define __SYSCALL_64(nr, sym, compat) [nr] = sym,
+
+extern void sys_ni_syscall(void);
+
+asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
+ /*
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
+ [0 ... __NR_syscall_max] = &sys_ni_syscall,
+#include <asm/syscalls_64.h>
+};
--- /dev/null
+out := $(obj)/../../include/generated/asm
+uapi := $(obj)/../../include/generated/uapi/asm
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
+ $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)')
+
+syscall32 := $(srctree)/$(src)/syscall_32.tbl
+syscall64 := $(srctree)/$(src)/syscall_64.tbl
+
+syshdr := $(srctree)/$(src)/syscallhdr.sh
+systbl := $(srctree)/$(src)/syscalltbl.sh
+
+quiet_cmd_syshdr = SYSHDR $@
+ cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \
+ '$(syshdr_abi_$(basetarget))' \
+ '$(syshdr_pfx_$(basetarget))' \
+ '$(syshdr_offset_$(basetarget))'
+quiet_cmd_systbl = SYSTBL $@
+ cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@
+
+quiet_cmd_hypercalls = HYPERCALLS $@
+ cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<,$^)
+
+syshdr_abi_unistd_32 := i386
+$(uapi)/unistd_32.h: $(syscall32) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_32_ia32 := i386
+syshdr_pfx_unistd_32_ia32 := ia32_
+$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_x32 := common,x32
+syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT
+$(uapi)/unistd_x32.h: $(syscall64) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_64 := common,64
+$(uapi)/unistd_64.h: $(syscall64) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_64_x32 := x32
+syshdr_pfx_unistd_64_x32 := x32_
+$(out)/unistd_64_x32.h: $(syscall64) $(syshdr)
+ $(call if_changed,syshdr)
+
+$(out)/syscalls_32.h: $(syscall32) $(systbl)
+ $(call if_changed,systbl)
+$(out)/syscalls_64.h: $(syscall64) $(systbl)
+ $(call if_changed,systbl)
+
+$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh
+ $(call if_changed,hypercalls)
+
+$(out)/xen-hypercalls.h: $(srctree)/include/xen/interface/xen*.h
+
+uapisyshdr-y += unistd_32.h unistd_64.h unistd_x32.h
+syshdr-y += syscalls_32.h
+syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h
+syshdr-$(CONFIG_X86_64) += syscalls_64.h
+syshdr-$(CONFIG_XEN) += xen-hypercalls.h
+
+targets += $(uapisyshdr-y) $(syshdr-y)
+
+PHONY += all
+all: $(addprefix $(uapi)/,$(uapisyshdr-y))
+all: $(addprefix $(out)/,$(syshdr-y))
+ @:
--- /dev/null
+#
+# 32-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point> <compat entry point>
+#
+# The abi is always "i386" for this file.
+#
+0 i386 restart_syscall sys_restart_syscall
+1 i386 exit sys_exit
+2 i386 fork sys_fork stub32_fork
+3 i386 read sys_read
+4 i386 write sys_write
+5 i386 open sys_open compat_sys_open
+6 i386 close sys_close
+7 i386 waitpid sys_waitpid sys32_waitpid
+8 i386 creat sys_creat
+9 i386 link sys_link
+10 i386 unlink sys_unlink
+11 i386 execve sys_execve stub32_execve
+12 i386 chdir sys_chdir
+13 i386 time sys_time compat_sys_time
+14 i386 mknod sys_mknod
+15 i386 chmod sys_chmod
+16 i386 lchown sys_lchown16
+17 i386 break
+18 i386 oldstat sys_stat
+19 i386 lseek sys_lseek compat_sys_lseek
+20 i386 getpid sys_getpid
+21 i386 mount sys_mount compat_sys_mount
+22 i386 umount sys_oldumount
+23 i386 setuid sys_setuid16
+24 i386 getuid sys_getuid16
+25 i386 stime sys_stime compat_sys_stime
+26 i386 ptrace sys_ptrace compat_sys_ptrace
+27 i386 alarm sys_alarm
+28 i386 oldfstat sys_fstat
+29 i386 pause sys_pause
+30 i386 utime sys_utime compat_sys_utime
+31 i386 stty
+32 i386 gtty
+33 i386 access sys_access
+34 i386 nice sys_nice
+35 i386 ftime
+36 i386 sync sys_sync
+37 i386 kill sys_kill
+38 i386 rename sys_rename
+39 i386 mkdir sys_mkdir
+40 i386 rmdir sys_rmdir
+41 i386 dup sys_dup
+42 i386 pipe sys_pipe
+43 i386 times sys_times compat_sys_times
+44 i386 prof
+45 i386 brk sys_brk
+46 i386 setgid sys_setgid16
+47 i386 getgid sys_getgid16
+48 i386 signal sys_signal
+49 i386 geteuid sys_geteuid16
+50 i386 getegid sys_getegid16
+51 i386 acct sys_acct
+52 i386 umount2 sys_umount
+53 i386 lock
+54 i386 ioctl sys_ioctl compat_sys_ioctl
+55 i386 fcntl sys_fcntl compat_sys_fcntl64
+56 i386 mpx
+57 i386 setpgid sys_setpgid
+58 i386 ulimit
+59 i386 oldolduname sys_olduname
+60 i386 umask sys_umask
+61 i386 chroot sys_chroot
+62 i386 ustat sys_ustat compat_sys_ustat
+63 i386 dup2 sys_dup2
+64 i386 getppid sys_getppid
+65 i386 getpgrp sys_getpgrp
+66 i386 setsid sys_setsid
+67 i386 sigaction sys_sigaction compat_sys_sigaction
+68 i386 sgetmask sys_sgetmask
+69 i386 ssetmask sys_ssetmask
+70 i386 setreuid sys_setreuid16
+71 i386 setregid sys_setregid16
+72 i386 sigsuspend sys_sigsuspend sys_sigsuspend
+73 i386 sigpending sys_sigpending compat_sys_sigpending
+74 i386 sethostname sys_sethostname
+75 i386 setrlimit sys_setrlimit compat_sys_setrlimit
+76 i386 getrlimit sys_old_getrlimit compat_sys_old_getrlimit
+77 i386 getrusage sys_getrusage compat_sys_getrusage
+78 i386 gettimeofday sys_gettimeofday compat_sys_gettimeofday
+79 i386 settimeofday sys_settimeofday compat_sys_settimeofday
+80 i386 getgroups sys_getgroups16
+81 i386 setgroups sys_setgroups16
+82 i386 select sys_old_select compat_sys_old_select
+83 i386 symlink sys_symlink
+84 i386 oldlstat sys_lstat
+85 i386 readlink sys_readlink
+86 i386 uselib sys_uselib
+87 i386 swapon sys_swapon
+88 i386 reboot sys_reboot
+89 i386 readdir sys_old_readdir compat_sys_old_readdir
+90 i386 mmap sys_old_mmap sys32_mmap
+91 i386 munmap sys_munmap
+92 i386 truncate sys_truncate compat_sys_truncate
+93 i386 ftruncate sys_ftruncate compat_sys_ftruncate
+94 i386 fchmod sys_fchmod
+95 i386 fchown sys_fchown16
+96 i386 getpriority sys_getpriority
+97 i386 setpriority sys_setpriority
+98 i386 profil
+99 i386 statfs sys_statfs compat_sys_statfs
+100 i386 fstatfs sys_fstatfs compat_sys_fstatfs
+101 i386 ioperm sys_ioperm
+102 i386 socketcall sys_socketcall compat_sys_socketcall
+103 i386 syslog sys_syslog
+104 i386 setitimer sys_setitimer compat_sys_setitimer
+105 i386 getitimer sys_getitimer compat_sys_getitimer
+106 i386 stat sys_newstat compat_sys_newstat
+107 i386 lstat sys_newlstat compat_sys_newlstat
+108 i386 fstat sys_newfstat compat_sys_newfstat
+109 i386 olduname sys_uname
+110 i386 iopl sys_iopl
+111 i386 vhangup sys_vhangup
+112 i386 idle
+113 i386 vm86old sys_vm86old sys_ni_syscall
+114 i386 wait4 sys_wait4 compat_sys_wait4
+115 i386 swapoff sys_swapoff
+116 i386 sysinfo sys_sysinfo compat_sys_sysinfo
+117 i386 ipc sys_ipc compat_sys_ipc
+118 i386 fsync sys_fsync
+119 i386 sigreturn sys_sigreturn stub32_sigreturn
+120 i386 clone sys_clone stub32_clone
+121 i386 setdomainname sys_setdomainname
+122 i386 uname sys_newuname
+123 i386 modify_ldt sys_modify_ldt
+124 i386 adjtimex sys_adjtimex compat_sys_adjtimex
+125 i386 mprotect sys_mprotect
+126 i386 sigprocmask sys_sigprocmask compat_sys_sigprocmask
+127 i386 create_module
+128 i386 init_module sys_init_module
+129 i386 delete_module sys_delete_module
+130 i386 get_kernel_syms
+131 i386 quotactl sys_quotactl sys32_quotactl
+132 i386 getpgid sys_getpgid
+133 i386 fchdir sys_fchdir
+134 i386 bdflush sys_bdflush
+135 i386 sysfs sys_sysfs
+136 i386 personality sys_personality
+137 i386 afs_syscall
+138 i386 setfsuid sys_setfsuid16
+139 i386 setfsgid sys_setfsgid16
+140 i386 _llseek sys_llseek
+141 i386 getdents sys_getdents compat_sys_getdents
+142 i386 _newselect sys_select compat_sys_select
+143 i386 flock sys_flock
+144 i386 msync sys_msync
+145 i386 readv sys_readv compat_sys_readv
+146 i386 writev sys_writev compat_sys_writev
+147 i386 getsid sys_getsid
+148 i386 fdatasync sys_fdatasync
+149 i386 _sysctl sys_sysctl compat_sys_sysctl
+150 i386 mlock sys_mlock
+151 i386 munlock sys_munlock
+152 i386 mlockall sys_mlockall
+153 i386 munlockall sys_munlockall
+154 i386 sched_setparam sys_sched_setparam
+155 i386 sched_getparam sys_sched_getparam
+156 i386 sched_setscheduler sys_sched_setscheduler
+157 i386 sched_getscheduler sys_sched_getscheduler
+158 i386 sched_yield sys_sched_yield
+159 i386 sched_get_priority_max sys_sched_get_priority_max
+160 i386 sched_get_priority_min sys_sched_get_priority_min
+161 i386 sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval
+162 i386 nanosleep sys_nanosleep compat_sys_nanosleep
+163 i386 mremap sys_mremap
+164 i386 setresuid sys_setresuid16
+165 i386 getresuid sys_getresuid16
+166 i386 vm86 sys_vm86 sys_ni_syscall
+167 i386 query_module
+168 i386 poll sys_poll
+169 i386 nfsservctl
+170 i386 setresgid sys_setresgid16
+171 i386 getresgid sys_getresgid16
+172 i386 prctl sys_prctl
+173 i386 rt_sigreturn sys_rt_sigreturn stub32_rt_sigreturn
+174 i386 rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction
+175 i386 rt_sigprocmask sys_rt_sigprocmask
+176 i386 rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending
+177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait
+178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
+179 i386 rt_sigsuspend sys_rt_sigsuspend
+180 i386 pread64 sys_pread64 sys32_pread
+181 i386 pwrite64 sys_pwrite64 sys32_pwrite
+182 i386 chown sys_chown16
+183 i386 getcwd sys_getcwd
+184 i386 capget sys_capget
+185 i386 capset sys_capset
+186 i386 sigaltstack sys_sigaltstack compat_sys_sigaltstack
+187 i386 sendfile sys_sendfile compat_sys_sendfile
+188 i386 getpmsg
+189 i386 putpmsg
+190 i386 vfork sys_vfork stub32_vfork
+191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit
+192 i386 mmap2 sys_mmap_pgoff
+193 i386 truncate64 sys_truncate64 sys32_truncate64
+194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64
+195 i386 stat64 sys_stat64 sys32_stat64
+196 i386 lstat64 sys_lstat64 sys32_lstat64
+197 i386 fstat64 sys_fstat64 sys32_fstat64
+198 i386 lchown32 sys_lchown
+199 i386 getuid32 sys_getuid
+200 i386 getgid32 sys_getgid
+201 i386 geteuid32 sys_geteuid
+202 i386 getegid32 sys_getegid
+203 i386 setreuid32 sys_setreuid
+204 i386 setregid32 sys_setregid
+205 i386 getgroups32 sys_getgroups
+206 i386 setgroups32 sys_setgroups
+207 i386 fchown32 sys_fchown
+208 i386 setresuid32 sys_setresuid
+209 i386 getresuid32 sys_getresuid
+210 i386 setresgid32 sys_setresgid
+211 i386 getresgid32 sys_getresgid
+212 i386 chown32 sys_chown
+213 i386 setuid32 sys_setuid
+214 i386 setgid32 sys_setgid
+215 i386 setfsuid32 sys_setfsuid
+216 i386 setfsgid32 sys_setfsgid
+217 i386 pivot_root sys_pivot_root
+218 i386 mincore sys_mincore
+219 i386 madvise sys_madvise
+220 i386 getdents64 sys_getdents64 compat_sys_getdents64
+221 i386 fcntl64 sys_fcntl64 compat_sys_fcntl64
+# 222 is unused
+# 223 is unused
+224 i386 gettid sys_gettid
+225 i386 readahead sys_readahead sys32_readahead
+226 i386 setxattr sys_setxattr
+227 i386 lsetxattr sys_lsetxattr
+228 i386 fsetxattr sys_fsetxattr
+229 i386 getxattr sys_getxattr
+230 i386 lgetxattr sys_lgetxattr
+231 i386 fgetxattr sys_fgetxattr
+232 i386 listxattr sys_listxattr
+233 i386 llistxattr sys_llistxattr
+234 i386 flistxattr sys_flistxattr
+235 i386 removexattr sys_removexattr
+236 i386 lremovexattr sys_lremovexattr
+237 i386 fremovexattr sys_fremovexattr
+238 i386 tkill sys_tkill
+239 i386 sendfile64 sys_sendfile64
+240 i386 futex sys_futex compat_sys_futex
+241 i386 sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity
+242 i386 sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity
+243 i386 set_thread_area sys_set_thread_area
+244 i386 get_thread_area sys_get_thread_area
+245 i386 io_setup sys_io_setup compat_sys_io_setup
+246 i386 io_destroy sys_io_destroy
+247 i386 io_getevents sys_io_getevents compat_sys_io_getevents
+248 i386 io_submit sys_io_submit compat_sys_io_submit
+249 i386 io_cancel sys_io_cancel
+250 i386 fadvise64 sys_fadvise64 sys32_fadvise64
+# 251 is available for reuse (was briefly sys_set_zone_reclaim)
+252 i386 exit_group sys_exit_group
+253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie
+254 i386 epoll_create sys_epoll_create
+255 i386 epoll_ctl sys_epoll_ctl
+256 i386 epoll_wait sys_epoll_wait
+257 i386 remap_file_pages sys_remap_file_pages
+258 i386 set_tid_address sys_set_tid_address
+259 i386 timer_create sys_timer_create compat_sys_timer_create
+260 i386 timer_settime sys_timer_settime compat_sys_timer_settime
+261 i386 timer_gettime sys_timer_gettime compat_sys_timer_gettime
+262 i386 timer_getoverrun sys_timer_getoverrun
+263 i386 timer_delete sys_timer_delete
+264 i386 clock_settime sys_clock_settime compat_sys_clock_settime
+265 i386 clock_gettime sys_clock_gettime compat_sys_clock_gettime
+266 i386 clock_getres sys_clock_getres compat_sys_clock_getres
+267 i386 clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep
+268 i386 statfs64 sys_statfs64 compat_sys_statfs64
+269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
+270 i386 tgkill sys_tgkill
+271 i386 utimes sys_utimes compat_sys_utimes
+272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64
+273 i386 vserver
+274 i386 mbind sys_mbind
+275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
+276 i386 set_mempolicy sys_set_mempolicy
+277 i386 mq_open sys_mq_open compat_sys_mq_open
+278 i386 mq_unlink sys_mq_unlink
+279 i386 mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend
+280 i386 mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive
+281 i386 mq_notify sys_mq_notify compat_sys_mq_notify
+282 i386 mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr
+283 i386 kexec_load sys_kexec_load compat_sys_kexec_load
+284 i386 waitid sys_waitid compat_sys_waitid
+# 285 sys_setaltroot
+286 i386 add_key sys_add_key
+287 i386 request_key sys_request_key
+288 i386 keyctl sys_keyctl
+289 i386 ioprio_set sys_ioprio_set
+290 i386 ioprio_get sys_ioprio_get
+291 i386 inotify_init sys_inotify_init
+292 i386 inotify_add_watch sys_inotify_add_watch
+293 i386 inotify_rm_watch sys_inotify_rm_watch
+294 i386 migrate_pages sys_migrate_pages
+295 i386 openat sys_openat compat_sys_openat
+296 i386 mkdirat sys_mkdirat
+297 i386 mknodat sys_mknodat
+298 i386 fchownat sys_fchownat
+299 i386 futimesat sys_futimesat compat_sys_futimesat
+300 i386 fstatat64 sys_fstatat64 sys32_fstatat
+301 i386 unlinkat sys_unlinkat
+302 i386 renameat sys_renameat
+303 i386 linkat sys_linkat
+304 i386 symlinkat sys_symlinkat
+305 i386 readlinkat sys_readlinkat
+306 i386 fchmodat sys_fchmodat
+307 i386 faccessat sys_faccessat
+308 i386 pselect6 sys_pselect6 compat_sys_pselect6
+309 i386 ppoll sys_ppoll compat_sys_ppoll
+310 i386 unshare sys_unshare
+311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list
+312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list
+313 i386 splice sys_splice
+314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range
+315 i386 tee sys_tee
+316 i386 vmsplice sys_vmsplice compat_sys_vmsplice
+317 i386 move_pages sys_move_pages compat_sys_move_pages
+318 i386 getcpu sys_getcpu
+319 i386 epoll_pwait sys_epoll_pwait
+320 i386 utimensat sys_utimensat compat_sys_utimensat
+321 i386 signalfd sys_signalfd compat_sys_signalfd
+322 i386 timerfd_create sys_timerfd_create
+323 i386 eventfd sys_eventfd
+324 i386 fallocate sys_fallocate sys32_fallocate
+325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime
+326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime
+327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4
+328 i386 eventfd2 sys_eventfd2
+329 i386 epoll_create1 sys_epoll_create1
+330 i386 dup3 sys_dup3
+331 i386 pipe2 sys_pipe2
+332 i386 inotify_init1 sys_inotify_init1
+333 i386 preadv sys_preadv compat_sys_preadv
+334 i386 pwritev sys_pwritev compat_sys_pwritev
+335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
+336 i386 perf_event_open sys_perf_event_open
+337 i386 recvmmsg sys_recvmmsg compat_sys_recvmmsg
+338 i386 fanotify_init sys_fanotify_init
+339 i386 fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark
+340 i386 prlimit64 sys_prlimit64
+341 i386 name_to_handle_at sys_name_to_handle_at
+342 i386 open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at
+343 i386 clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime
+344 i386 syncfs sys_syncfs
+345 i386 sendmmsg sys_sendmmsg compat_sys_sendmmsg
+346 i386 setns sys_setns
+347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv
+348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
+349 i386 kcmp sys_kcmp
+350 i386 finit_module sys_finit_module
+351 i386 sched_setattr sys_sched_setattr
+352 i386 sched_getattr sys_sched_getattr
+353 i386 renameat2 sys_renameat2
+354 i386 seccomp sys_seccomp
+355 i386 getrandom sys_getrandom
+356 i386 memfd_create sys_memfd_create
+357 i386 bpf sys_bpf
+358 i386 execveat sys_execveat stub32_execveat
--- /dev/null
+#
+# 64-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point>
+#
+# The abi is "common", "64" or "x32" for this file.
+#
+0 common read sys_read
+1 common write sys_write
+2 common open sys_open
+3 common close sys_close
+4 common stat sys_newstat
+5 common fstat sys_newfstat
+6 common lstat sys_newlstat
+7 common poll sys_poll
+8 common lseek sys_lseek
+9 common mmap sys_mmap
+10 common mprotect sys_mprotect
+11 common munmap sys_munmap
+12 common brk sys_brk
+13 64 rt_sigaction sys_rt_sigaction
+14 common rt_sigprocmask sys_rt_sigprocmask
+15 64 rt_sigreturn stub_rt_sigreturn
+16 64 ioctl sys_ioctl
+17 common pread64 sys_pread64
+18 common pwrite64 sys_pwrite64
+19 64 readv sys_readv
+20 64 writev sys_writev
+21 common access sys_access
+22 common pipe sys_pipe
+23 common select sys_select
+24 common sched_yield sys_sched_yield
+25 common mremap sys_mremap
+26 common msync sys_msync
+27 common mincore sys_mincore
+28 common madvise sys_madvise
+29 common shmget sys_shmget
+30 common shmat sys_shmat
+31 common shmctl sys_shmctl
+32 common dup sys_dup
+33 common dup2 sys_dup2
+34 common pause sys_pause
+35 common nanosleep sys_nanosleep
+36 common getitimer sys_getitimer
+37 common alarm sys_alarm
+38 common setitimer sys_setitimer
+39 common getpid sys_getpid
+40 common sendfile sys_sendfile64
+41 common socket sys_socket
+42 common connect sys_connect
+43 common accept sys_accept
+44 common sendto sys_sendto
+45 64 recvfrom sys_recvfrom
+46 64 sendmsg sys_sendmsg
+47 64 recvmsg sys_recvmsg
+48 common shutdown sys_shutdown
+49 common bind sys_bind
+50 common listen sys_listen
+51 common getsockname sys_getsockname
+52 common getpeername sys_getpeername
+53 common socketpair sys_socketpair
+54 64 setsockopt sys_setsockopt
+55 64 getsockopt sys_getsockopt
+56 common clone stub_clone
+57 common fork stub_fork
+58 common vfork stub_vfork
+59 64 execve stub_execve
+60 common exit sys_exit
+61 common wait4 sys_wait4
+62 common kill sys_kill
+63 common uname sys_newuname
+64 common semget sys_semget
+65 common semop sys_semop
+66 common semctl sys_semctl
+67 common shmdt sys_shmdt
+68 common msgget sys_msgget
+69 common msgsnd sys_msgsnd
+70 common msgrcv sys_msgrcv
+71 common msgctl sys_msgctl
+72 common fcntl sys_fcntl
+73 common flock sys_flock
+74 common fsync sys_fsync
+75 common fdatasync sys_fdatasync
+76 common truncate sys_truncate
+77 common ftruncate sys_ftruncate
+78 common getdents sys_getdents
+79 common getcwd sys_getcwd
+80 common chdir sys_chdir
+81 common fchdir sys_fchdir
+82 common rename sys_rename
+83 common mkdir sys_mkdir
+84 common rmdir sys_rmdir
+85 common creat sys_creat
+86 common link sys_link
+87 common unlink sys_unlink
+88 common symlink sys_symlink
+89 common readlink sys_readlink
+90 common chmod sys_chmod
+91 common fchmod sys_fchmod
+92 common chown sys_chown
+93 common fchown sys_fchown
+94 common lchown sys_lchown
+95 common umask sys_umask
+96 common gettimeofday sys_gettimeofday
+97 common getrlimit sys_getrlimit
+98 common getrusage sys_getrusage
+99 common sysinfo sys_sysinfo
+100 common times sys_times
+101 64 ptrace sys_ptrace
+102 common getuid sys_getuid
+103 common syslog sys_syslog
+104 common getgid sys_getgid
+105 common setuid sys_setuid
+106 common setgid sys_setgid
+107 common geteuid sys_geteuid
+108 common getegid sys_getegid
+109 common setpgid sys_setpgid
+110 common getppid sys_getppid
+111 common getpgrp sys_getpgrp
+112 common setsid sys_setsid
+113 common setreuid sys_setreuid
+114 common setregid sys_setregid
+115 common getgroups sys_getgroups
+116 common setgroups sys_setgroups
+117 common setresuid sys_setresuid
+118 common getresuid sys_getresuid
+119 common setresgid sys_setresgid
+120 common getresgid sys_getresgid
+121 common getpgid sys_getpgid
+122 common setfsuid sys_setfsuid
+123 common setfsgid sys_setfsgid
+124 common getsid sys_getsid
+125 common capget sys_capget
+126 common capset sys_capset
+127 64 rt_sigpending sys_rt_sigpending
+128 64 rt_sigtimedwait sys_rt_sigtimedwait
+129 64 rt_sigqueueinfo sys_rt_sigqueueinfo
+130 common rt_sigsuspend sys_rt_sigsuspend
+131 64 sigaltstack sys_sigaltstack
+132 common utime sys_utime
+133 common mknod sys_mknod
+134 64 uselib
+135 common personality sys_personality
+136 common ustat sys_ustat
+137 common statfs sys_statfs
+138 common fstatfs sys_fstatfs
+139 common sysfs sys_sysfs
+140 common getpriority sys_getpriority
+141 common setpriority sys_setpriority
+142 common sched_setparam sys_sched_setparam
+143 common sched_getparam sys_sched_getparam
+144 common sched_setscheduler sys_sched_setscheduler
+145 common sched_getscheduler sys_sched_getscheduler
+146 common sched_get_priority_max sys_sched_get_priority_max
+147 common sched_get_priority_min sys_sched_get_priority_min
+148 common sched_rr_get_interval sys_sched_rr_get_interval
+149 common mlock sys_mlock
+150 common munlock sys_munlock
+151 common mlockall sys_mlockall
+152 common munlockall sys_munlockall
+153 common vhangup sys_vhangup
+154 common modify_ldt sys_modify_ldt
+155 common pivot_root sys_pivot_root
+156 64 _sysctl sys_sysctl
+157 common prctl sys_prctl
+158 common arch_prctl sys_arch_prctl
+159 common adjtimex sys_adjtimex
+160 common setrlimit sys_setrlimit
+161 common chroot sys_chroot
+162 common sync sys_sync
+163 common acct sys_acct
+164 common settimeofday sys_settimeofday
+165 common mount sys_mount
+166 common umount2 sys_umount
+167 common swapon sys_swapon
+168 common swapoff sys_swapoff
+169 common reboot sys_reboot
+170 common sethostname sys_sethostname
+171 common setdomainname sys_setdomainname
+172 common iopl sys_iopl
+173 common ioperm sys_ioperm
+174 64 create_module
+175 common init_module sys_init_module
+176 common delete_module sys_delete_module
+177 64 get_kernel_syms
+178 64 query_module
+179 common quotactl sys_quotactl
+180 64 nfsservctl
+181 common getpmsg
+182 common putpmsg
+183 common afs_syscall
+184 common tuxcall
+185 common security
+186 common gettid sys_gettid
+187 common readahead sys_readahead
+188 common setxattr sys_setxattr
+189 common lsetxattr sys_lsetxattr
+190 common fsetxattr sys_fsetxattr
+191 common getxattr sys_getxattr
+192 common lgetxattr sys_lgetxattr
+193 common fgetxattr sys_fgetxattr
+194 common listxattr sys_listxattr
+195 common llistxattr sys_llistxattr
+196 common flistxattr sys_flistxattr
+197 common removexattr sys_removexattr
+198 common lremovexattr sys_lremovexattr
+199 common fremovexattr sys_fremovexattr
+200 common tkill sys_tkill
+201 common time sys_time
+202 common futex sys_futex
+203 common sched_setaffinity sys_sched_setaffinity
+204 common sched_getaffinity sys_sched_getaffinity
+205 64 set_thread_area
+206 64 io_setup sys_io_setup
+207 common io_destroy sys_io_destroy
+208 common io_getevents sys_io_getevents
+209 64 io_submit sys_io_submit
+210 common io_cancel sys_io_cancel
+211 64 get_thread_area
+212 common lookup_dcookie sys_lookup_dcookie
+213 common epoll_create sys_epoll_create
+214 64 epoll_ctl_old
+215 64 epoll_wait_old
+216 common remap_file_pages sys_remap_file_pages
+217 common getdents64 sys_getdents64
+218 common set_tid_address sys_set_tid_address
+219 common restart_syscall sys_restart_syscall
+220 common semtimedop sys_semtimedop
+221 common fadvise64 sys_fadvise64
+222 64 timer_create sys_timer_create
+223 common timer_settime sys_timer_settime
+224 common timer_gettime sys_timer_gettime
+225 common timer_getoverrun sys_timer_getoverrun
+226 common timer_delete sys_timer_delete
+227 common clock_settime sys_clock_settime
+228 common clock_gettime sys_clock_gettime
+229 common clock_getres sys_clock_getres
+230 common clock_nanosleep sys_clock_nanosleep
+231 common exit_group sys_exit_group
+232 common epoll_wait sys_epoll_wait
+233 common epoll_ctl sys_epoll_ctl
+234 common tgkill sys_tgkill
+235 common utimes sys_utimes
+236 64 vserver
+237 common mbind sys_mbind
+238 common set_mempolicy sys_set_mempolicy
+239 common get_mempolicy sys_get_mempolicy
+240 common mq_open sys_mq_open
+241 common mq_unlink sys_mq_unlink
+242 common mq_timedsend sys_mq_timedsend
+243 common mq_timedreceive sys_mq_timedreceive
+244 64 mq_notify sys_mq_notify
+245 common mq_getsetattr sys_mq_getsetattr
+246 64 kexec_load sys_kexec_load
+247 64 waitid sys_waitid
+248 common add_key sys_add_key
+249 common request_key sys_request_key
+250 common keyctl sys_keyctl
+251 common ioprio_set sys_ioprio_set
+252 common ioprio_get sys_ioprio_get
+253 common inotify_init sys_inotify_init
+254 common inotify_add_watch sys_inotify_add_watch
+255 common inotify_rm_watch sys_inotify_rm_watch
+256 common migrate_pages sys_migrate_pages
+257 common openat sys_openat
+258 common mkdirat sys_mkdirat
+259 common mknodat sys_mknodat
+260 common fchownat sys_fchownat
+261 common futimesat sys_futimesat
+262 common newfstatat sys_newfstatat
+263 common unlinkat sys_unlinkat
+264 common renameat sys_renameat
+265 common linkat sys_linkat
+266 common symlinkat sys_symlinkat
+267 common readlinkat sys_readlinkat
+268 common fchmodat sys_fchmodat
+269 common faccessat sys_faccessat
+270 common pselect6 sys_pselect6
+271 common ppoll sys_ppoll
+272 common unshare sys_unshare
+273 64 set_robust_list sys_set_robust_list
+274 64 get_robust_list sys_get_robust_list
+275 common splice sys_splice
+276 common tee sys_tee
+277 common sync_file_range sys_sync_file_range
+278 64 vmsplice sys_vmsplice
+279 64 move_pages sys_move_pages
+280 common utimensat sys_utimensat
+281 common epoll_pwait sys_epoll_pwait
+282 common signalfd sys_signalfd
+283 common timerfd_create sys_timerfd_create
+284 common eventfd sys_eventfd
+285 common fallocate sys_fallocate
+286 common timerfd_settime sys_timerfd_settime
+287 common timerfd_gettime sys_timerfd_gettime
+288 common accept4 sys_accept4
+289 common signalfd4 sys_signalfd4
+290 common eventfd2 sys_eventfd2
+291 common epoll_create1 sys_epoll_create1
+292 common dup3 sys_dup3
+293 common pipe2 sys_pipe2
+294 common inotify_init1 sys_inotify_init1
+295 64 preadv sys_preadv
+296 64 pwritev sys_pwritev
+297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo
+298 common perf_event_open sys_perf_event_open
+299 64 recvmmsg sys_recvmmsg
+300 common fanotify_init sys_fanotify_init
+301 common fanotify_mark sys_fanotify_mark
+302 common prlimit64 sys_prlimit64
+303 common name_to_handle_at sys_name_to_handle_at
+304 common open_by_handle_at sys_open_by_handle_at
+305 common clock_adjtime sys_clock_adjtime
+306 common syncfs sys_syncfs
+307 64 sendmmsg sys_sendmmsg
+308 common setns sys_setns
+309 common getcpu sys_getcpu
+310 64 process_vm_readv sys_process_vm_readv
+311 64 process_vm_writev sys_process_vm_writev
+312 common kcmp sys_kcmp
+313 common finit_module sys_finit_module
+314 common sched_setattr sys_sched_setattr
+315 common sched_getattr sys_sched_getattr
+316 common renameat2 sys_renameat2
+317 common seccomp sys_seccomp
+318 common getrandom sys_getrandom
+319 common memfd_create sys_memfd_create
+320 common kexec_file_load sys_kexec_file_load
+321 common bpf sys_bpf
+322 64 execveat stub_execveat
+
+#
+# x32-specific system call numbers start at 512 to avoid cache impact
+# for native 64-bit operation.
+#
+512 x32 rt_sigaction compat_sys_rt_sigaction
+513 x32 rt_sigreturn stub_x32_rt_sigreturn
+514 x32 ioctl compat_sys_ioctl
+515 x32 readv compat_sys_readv
+516 x32 writev compat_sys_writev
+517 x32 recvfrom compat_sys_recvfrom
+518 x32 sendmsg compat_sys_sendmsg
+519 x32 recvmsg compat_sys_recvmsg
+520 x32 execve stub_x32_execve
+521 x32 ptrace compat_sys_ptrace
+522 x32 rt_sigpending compat_sys_rt_sigpending
+523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait
+524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo
+525 x32 sigaltstack compat_sys_sigaltstack
+526 x32 timer_create compat_sys_timer_create
+527 x32 mq_notify compat_sys_mq_notify
+528 x32 kexec_load compat_sys_kexec_load
+529 x32 waitid compat_sys_waitid
+530 x32 set_robust_list compat_sys_set_robust_list
+531 x32 get_robust_list compat_sys_get_robust_list
+532 x32 vmsplice compat_sys_vmsplice
+533 x32 move_pages compat_sys_move_pages
+534 x32 preadv compat_sys_preadv64
+535 x32 pwritev compat_sys_pwritev64
+536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
+537 x32 recvmmsg compat_sys_recvmmsg
+538 x32 sendmmsg compat_sys_sendmmsg
+539 x32 process_vm_readv compat_sys_process_vm_readv
+540 x32 process_vm_writev compat_sys_process_vm_writev
+541 x32 setsockopt compat_sys_setsockopt
+542 x32 getsockopt compat_sys_getsockopt
+543 x32 io_setup compat_sys_io_setup
+544 x32 io_submit compat_sys_io_submit
+545 x32 execveat stub_x32_execveat
--- /dev/null
+#!/bin/sh
+
+in="$1"
+out="$2"
+my_abis=`echo "($3)" | tr ',' '|'`
+prefix="$4"
+offset="$5"
+
+fileguard=_ASM_X86_`basename "$out" | sed \
+ -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
+ -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'`
+grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
+ echo "#ifndef ${fileguard}"
+ echo "#define ${fileguard} 1"
+ echo ""
+
+ while read nr abi name entry ; do
+ if [ -z "$offset" ]; then
+ echo "#define __NR_${prefix}${name} $nr"
+ else
+ echo "#define __NR_${prefix}${name} ($offset + $nr)"
+ fi
+ done
+
+ echo ""
+ echo "#endif /* ${fileguard} */"
+) > "$out"
--- /dev/null
+#!/bin/sh
+
+in="$1"
+out="$2"
+
+grep '^[0-9]' "$in" | sort -n | (
+ while read nr abi name entry compat; do
+ abi=`echo "$abi" | tr '[a-z]' '[A-Z]'`
+ if [ -n "$compat" ]; then
+ echo "__SYSCALL_${abi}($nr, $entry, $compat)"
+ elif [ -n "$entry" ]; then
+ echo "__SYSCALL_${abi}($nr, $entry, $entry)"
+ fi
+ done
+) > "$out"
--- /dev/null
+/*
+ * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash)
+ * Copyright 2008 by Steven Rostedt, Red Hat, Inc
+ * (inspired by Andi Kleen's thunk_64.S)
+ * Subject to the GNU public license, v.2. No warranty of any kind.
+ */
+ #include <linux/linkage.h>
+ #include <asm/asm.h>
+
+ /* put return address in eax (arg1) */
+ .macro THUNK name, func, put_ret_addr_in_eax=0
+ .globl \name
+\name:
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+
+ .if \put_ret_addr_in_eax
+ /* Place EIP in the arg1 */
+ movl 3*4(%esp), %eax
+ .endif
+
+ call \func
+ popl %edx
+ popl %ecx
+ popl %eax
+ ret
+ _ASM_NOKPROBE(\name)
+ .endm
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+ THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
+ THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
+#endif
+
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+ THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
+#endif
+
--- /dev/null
+/*
+ * Save registers before calling assembly functions. This avoids
+ * disturbance of register allocation in some inline assembly constructs.
+ * Copyright 2001,2002 by Andi Kleen, SuSE Labs.
+ * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc.
+ * Subject to the GNU public license, v.2. No warranty of any kind.
+ */
+#include <linux/linkage.h>
+#include "calling.h"
+#include <asm/asm.h>
+
+ /* rdi: arg1 ... normal C conventions. rax is saved/restored. */
+ .macro THUNK name, func, put_ret_addr_in_rdi=0
+ .globl \name
+\name:
+
+ /* this one pushes 9 elems, the next one would be %rIP */
+ pushq %rdi
+ pushq %rsi
+ pushq %rdx
+ pushq %rcx
+ pushq %rax
+ pushq %r8
+ pushq %r9
+ pushq %r10
+ pushq %r11
+
+ .if \put_ret_addr_in_rdi
+ /* 9*8(%rsp) is return addr on stack */
+ movq 9*8(%rsp), %rdi
+ .endif
+
+ call \func
+ jmp restore
+ _ASM_NOKPROBE(\name)
+ .endm
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+ THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
+ THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
+#endif
+
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+ THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
+#endif
+
+#if defined(CONFIG_TRACE_IRQFLAGS) \
+ || defined(CONFIG_DEBUG_LOCK_ALLOC) \
+ || defined(CONFIG_PREEMPT)
+restore:
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+ popq %rdi
+ ret
+ _ASM_NOKPROBE(restore)
+#endif
--- /dev/null
+vdso.lds
+vdsox32.lds
+vdso32-syscall-syms.lds
+vdso32-sysenter-syms.lds
+vdso32-int80-syms.lds
+vdso-image-*.c
+vdso2c
--- /dev/null
+#
+# Building vDSO images for x86.
+#
+
+KBUILD_CFLAGS += $(DISABLE_LTO)
+KASAN_SANITIZE := n
+
+VDSO64-$(CONFIG_X86_64) := y
+VDSOX32-$(CONFIG_X86_X32_ABI) := y
+VDSO32-$(CONFIG_X86_32) := y
+VDSO32-$(CONFIG_COMPAT) := y
+
+# files to link into the vdso
+vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
+
+# files to link into kernel
+obj-y += vma.o
+
+# vDSO images to build
+vdso_img-$(VDSO64-y) += 64
+vdso_img-$(VDSOX32-y) += x32
+vdso_img-$(VDSO32-y) += 32-int80
+vdso_img-$(CONFIG_COMPAT) += 32-syscall
+vdso_img-$(VDSO32-y) += 32-sysenter
+
+obj-$(VDSO32-y) += vdso32-setup.o
+
+vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+
+$(obj)/vdso.o: $(obj)/vdso.so
+
+targets += vdso.lds $(vobjs-y)
+
+# Build the vDSO image C files and link them in.
+vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
+vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c)
+vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
+obj-y += $(vdso_img_objs)
+targets += $(vdso_img_cfiles)
+targets += $(vdso_img_sodbg)
+.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c) \
+ $(vdso_img-y:%=$(obj)/vdso%.so)
+
+export CPPFLAGS_vdso.lds += -P -C
+
+VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
+ -Wl,--no-undefined \
+ -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
+ $(DISABLE_LTO)
+
+$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
+ $(call if_changed,vdso)
+
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi
+hostprogs-y += vdso2c
+
+quiet_cmd_vdso2c = VDSO2C $@
+define cmd_vdso2c
+ $(obj)/vdso2c $< $(<:%.dbg=%) $@
+endef
+
+$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
+ $(call if_changed,vdso2c)
+
+#
+# Don't omit frame pointers for ease of userspace debugging, but do
+# optimize sibling calls.
+#
+CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
+ -fno-omit-frame-pointer -foptimize-sibling-calls \
+ -DDISABLE_BRANCH_PROFILING
+
+$(vobjs): KBUILD_CFLAGS += $(CFL)
+
+#
+# vDSO code runs in userspace and -pg doesn't help with profiling anyway.
+#
+CFLAGS_REMOVE_vdso-note.o = -pg
+CFLAGS_REMOVE_vclock_gettime.o = -pg
+CFLAGS_REMOVE_vgetcpu.o = -pg
+CFLAGS_REMOVE_vvar.o = -pg
+
+#
+# X32 processes use x32 vDSO to access 64bit kernel data.
+#
+# Build x32 vDSO image:
+# 1. Compile x32 vDSO as 64bit.
+# 2. Convert object files to x32.
+# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes
+# so that it can reach 64bit address space with 64bit pointers.
+#
+
+CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
+VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
+ -Wl,-soname=linux-vdso.so.1 \
+ -Wl,-z,max-page-size=4096 \
+ -Wl,-z,common-page-size=4096
+
+# 64-bit objects to re-brand as x32
+vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y))
+
+# x32-rebranded versions
+vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o)
+
+# same thing, but in the output directory
+vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
+
+# Convert 64bit object file to x32 for x32 vDSO.
+quiet_cmd_x32 = X32 $@
+ cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@
+
+$(obj)/%-x32.o: $(obj)/%.o FORCE
+ $(call if_changed,x32)
+
+targets += vdsox32.lds $(vobjx32s-y)
+
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg
+ $(call if_changed,objcopy)
+
+$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
+ $(call if_changed,vdso)
+
+#
+# Build multiple 32-bit vDSO images to choose from at boot time.
+#
+vdso32.so-$(VDSO32-y) += int80
+vdso32.so-$(CONFIG_COMPAT) += syscall
+vdso32.so-$(VDSO32-y) += sysenter
+
+vdso32-images = $(vdso32.so-y:%=vdso32-%.so)
+
+CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
+VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
+
+# This makes sure the $(obj) subdirectory exists even though vdso32/
+# is not a kbuild sub-make subdirectory.
+override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
+
+targets += vdso32/vdso32.lds
+targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o)
+targets += vdso32/vclock_gettime.o
+
+$(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%)
+
+KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
+$(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
+$(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32
+
+KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
+KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
+KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
+KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
+KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
+
+$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
+ $(obj)/vdso32/vdso32.lds \
+ $(obj)/vdso32/vclock_gettime.o \
+ $(obj)/vdso32/note.o \
+ $(obj)/vdso32/%.o
+ $(call if_changed,vdso)
+
+#
+# The DSO images are built using a special linker script.
+#
+quiet_cmd_vdso = VDSO $@
+ cmd_vdso = $(CC) -nostdlib -o $@ \
+ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
+ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
+ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
+
+VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
+ $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS)
+GCOV_PROFILE := n
+
+#
+# Install the unstripped copies of vdso*.so. If our toolchain supports
+# build-id, install .build-id links as well.
+#
+quiet_cmd_vdso_install = INSTALL $(@:install_%=%)
+define cmd_vdso_install
+ cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \
+ if readelf -n $< |grep -q 'Build ID'; then \
+ buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \
+ first=`echo $$buildid | cut -b-2`; \
+ last=`echo $$buildid | cut -b3-`; \
+ mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \
+ ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \
+ fi
+endef
+
+vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%)
+
+$(MODLIB)/vdso: FORCE
+ @mkdir -p $(MODLIB)/vdso
+
+$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE
+ $(call cmd,vdso_install)
+
+PHONY += vdso_install $(vdso_img_insttargets)
+vdso_install: $(vdso_img_insttargets) FORCE
+
+clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* vdso-image-*.c vdsox32.so*
--- /dev/null
+#!/bin/sh
+nm="$1"
+file="$2"
+$nm "$file" | grep '^ *U' > /dev/null 2>&1
+if [ $? -eq 1 ]; then
+ exit 0
+else
+ echo "$file: undefined symbols found" >&2
+ exit 1
+fi
--- /dev/null
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Fast user context implementation of clock_gettime, gettimeofday, and time.
+ *
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ *
+ * The code should have no internal unresolved relocations.
+ * Check with readelf after changing.
+ */
+
+#include <uapi/linux/time.h>
+#include <asm/vgtod.h>
+#include <asm/hpet.h>
+#include <asm/vvar.h>
+#include <asm/unistd.h>
+#include <asm/msr.h>
+#include <linux/math64.h>
+#include <linux/time.h>
+
+#define gtod (&VVAR(vsyscall_gtod_data))
+
+extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts);
+extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
+extern time_t __vdso_time(time_t *t);
+
+#ifdef CONFIG_HPET_TIMER
+extern u8 hpet_page
+ __attribute__((visibility("hidden")));
+
+static notrace cycle_t vread_hpet(void)
+{
+ return *(const volatile u32 *)(&hpet_page + HPET_COUNTER);
+}
+#endif
+
+#ifndef BUILD_VDSO32
+
+#include <linux/kernel.h>
+#include <asm/vsyscall.h>
+#include <asm/fixmap.h>
+#include <asm/pvclock.h>
+
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+ long ret;
+ asm("syscall" : "=a" (ret) :
+ "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+ return ret;
+}
+
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
+{
+ long ret;
+
+ asm("syscall" : "=a" (ret) :
+ "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+ return ret;
+}
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+
+static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
+{
+ const struct pvclock_vsyscall_time_info *pvti_base;
+ int idx = cpu / (PAGE_SIZE/PVTI_SIZE);
+ int offset = cpu % (PAGE_SIZE/PVTI_SIZE);
+
+ BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END);
+
+ pvti_base = (struct pvclock_vsyscall_time_info *)
+ __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx);
+
+ return &pvti_base[offset];
+}
+
+static notrace cycle_t vread_pvclock(int *mode)
+{
+ const struct pvclock_vsyscall_time_info *pvti;
+ cycle_t ret;
+ u64 last;
+ u32 version;
+ u8 flags;
+ unsigned cpu, cpu1;
+
+
+ /*
+ * Note: hypervisor must guarantee that:
+ * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
+ * 2. that per-CPU pvclock time info is updated if the
+ * underlying CPU changes.
+ * 3. that version is increased whenever underlying CPU
+ * changes.
+ *
+ */
+ do {
+ cpu = __getcpu() & VGETCPU_CPU_MASK;
+ /* TODO: We can put vcpu id into higher bits of pvti.version.
+ * This will save a couple of cycles by getting rid of
+ * __getcpu() calls (Gleb).
+ */
+
+ pvti = get_pvti(cpu);
+
+ version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
+
+ /*
+ * Test we're still on the cpu as well as the version.
+ * We could have been migrated just after the first
+ * vgetcpu but before fetching the version, so we
+ * wouldn't notice a version change.
+ */
+ cpu1 = __getcpu() & VGETCPU_CPU_MASK;
+ } while (unlikely(cpu != cpu1 ||
+ (pvti->pvti.version & 1) ||
+ pvti->pvti.version != version));
+
+ if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
+ *mode = VCLOCK_NONE;
+
+ /* refer to tsc.c read_tsc() comment for rationale */
+ last = gtod->cycle_last;
+
+ if (likely(ret >= last))
+ return ret;
+
+ return last;
+}
+#endif
+
+#else
+
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+ long ret;
+
+ asm(
+ "mov %%ebx, %%edx \n"
+ "mov %2, %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret)
+ : "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+ : "memory", "edx");
+ return ret;
+}
+
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
+{
+ long ret;
+
+ asm(
+ "mov %%ebx, %%edx \n"
+ "mov %2, %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret)
+ : "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+ : "memory", "edx");
+ return ret;
+}
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+
+static notrace cycle_t vread_pvclock(int *mode)
+{
+ *mode = VCLOCK_NONE;
+ return 0;
+}
+#endif
+
+#endif
+
+notrace static cycle_t vread_tsc(void)
+{
+ cycle_t ret;
+ u64 last;
+
+ /*
+ * Empirically, a fence (of type that depends on the CPU)
+ * before rdtsc is enough to ensure that rdtsc is ordered
+ * with respect to loads. The various CPU manuals are unclear
+ * as to whether rdtsc can be reordered with later loads,
+ * but no one has ever seen it happen.
+ */
+ rdtsc_barrier();
+ ret = (cycle_t)__native_read_tsc();
+
+ last = gtod->cycle_last;
+
+ if (likely(ret >= last))
+ return ret;
+
+ /*
+ * GCC likes to generate cmov here, but this branch is extremely
+ * predictable (it's just a funciton of time and the likely is
+ * very likely) and there's a data dependence, so force GCC
+ * to generate a branch instead. I don't barrier() because
+ * we don't actually need a barrier, and if this function
+ * ever gets inlined it will generate worse code.
+ */
+ asm volatile ("");
+ return last;
+}
+
+notrace static inline u64 vgetsns(int *mode)
+{
+ u64 v;
+ cycles_t cycles;
+
+ if (gtod->vclock_mode == VCLOCK_TSC)
+ cycles = vread_tsc();
+#ifdef CONFIG_HPET_TIMER
+ else if (gtod->vclock_mode == VCLOCK_HPET)
+ cycles = vread_hpet();
+#endif
+#ifdef CONFIG_PARAVIRT_CLOCK
+ else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
+ cycles = vread_pvclock(mode);
+#endif
+ else
+ return 0;
+ v = (cycles - gtod->cycle_last) & gtod->mask;
+ return v * gtod->mult;
+}
+
+/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
+notrace static int __always_inline do_realtime(struct timespec *ts)
+{
+ unsigned long seq;
+ u64 ns;
+ int mode;
+
+ do {
+ seq = gtod_read_begin(gtod);
+ mode = gtod->vclock_mode;
+ ts->tv_sec = gtod->wall_time_sec;
+ ns = gtod->wall_time_snsec;
+ ns += vgetsns(&mode);
+ ns >>= gtod->shift;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+
+ ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;
+
+ return mode;
+}
+
+notrace static int __always_inline do_monotonic(struct timespec *ts)
+{
+ unsigned long seq;
+ u64 ns;
+ int mode;
+
+ do {
+ seq = gtod_read_begin(gtod);
+ mode = gtod->vclock_mode;
+ ts->tv_sec = gtod->monotonic_time_sec;
+ ns = gtod->monotonic_time_snsec;
+ ns += vgetsns(&mode);
+ ns >>= gtod->shift;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+
+ ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;
+
+ return mode;
+}
+
+notrace static void do_realtime_coarse(struct timespec *ts)
+{
+ unsigned long seq;
+ do {
+ seq = gtod_read_begin(gtod);
+ ts->tv_sec = gtod->wall_time_coarse_sec;
+ ts->tv_nsec = gtod->wall_time_coarse_nsec;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+}
+
+notrace static void do_monotonic_coarse(struct timespec *ts)
+{
+ unsigned long seq;
+ do {
+ seq = gtod_read_begin(gtod);
+ ts->tv_sec = gtod->monotonic_time_coarse_sec;
+ ts->tv_nsec = gtod->monotonic_time_coarse_nsec;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+}
+
+notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+{
+ switch (clock) {
+ case CLOCK_REALTIME:
+ if (do_realtime(ts) == VCLOCK_NONE)
+ goto fallback;
+ break;
+ case CLOCK_MONOTONIC:
+ if (do_monotonic(ts) == VCLOCK_NONE)
+ goto fallback;
+ break;
+ case CLOCK_REALTIME_COARSE:
+ do_realtime_coarse(ts);
+ break;
+ case CLOCK_MONOTONIC_COARSE:
+ do_monotonic_coarse(ts);
+ break;
+ default:
+ goto fallback;
+ }
+
+ return 0;
+fallback:
+ return vdso_fallback_gettime(clock, ts);
+}
+int clock_gettime(clockid_t, struct timespec *)
+ __attribute__((weak, alias("__vdso_clock_gettime")));
+
+notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ if (likely(tv != NULL)) {
+ if (unlikely(do_realtime((struct timespec *)tv) == VCLOCK_NONE))
+ return vdso_fallback_gtod(tv, tz);
+ tv->tv_usec /= 1000;
+ }
+ if (unlikely(tz != NULL)) {
+ tz->tz_minuteswest = gtod->tz_minuteswest;
+ tz->tz_dsttime = gtod->tz_dsttime;
+ }
+
+ return 0;
+}
+int gettimeofday(struct timeval *, struct timezone *)
+ __attribute__((weak, alias("__vdso_gettimeofday")));
+
+/*
+ * This will break when the xtime seconds get inaccurate, but that is
+ * unlikely
+ */
+notrace time_t __vdso_time(time_t *t)
+{
+ /* This is atomic on x86 so we don't need any locks. */
+ time_t result = ACCESS_ONCE(gtod->wall_time_sec);
+
+ if (t)
+ *t = result;
+ return result;
+}
+int time(time_t *t)
+ __attribute__((weak, alias("__vdso_time")));
--- /dev/null
+#include <asm/vdso.h>
+
+/*
+ * Linker script for vDSO. This is an ELF shared object prelinked to
+ * its virtual address, and with only one read-only segment.
+ * This script controls its layout.
+ */
+
+#if defined(BUILD_VDSO64)
+# define SHDR_SIZE 64
+#elif defined(BUILD_VDSO32) || defined(BUILD_VDSOX32)
+# define SHDR_SIZE 40
+#else
+# error unknown VDSO target
+#endif
+
+#define NUM_FAKE_SHDRS 13
+
+SECTIONS
+{
+ /*
+ * User/kernel shared data is before the vDSO. This may be a little
+ * uglier than putting it after the vDSO, but it avoids issues with
+ * non-allocatable things that dangle past the end of the PT_LOAD
+ * segment.
+ */
+
+ vvar_start = . - 2 * PAGE_SIZE;
+ vvar_page = vvar_start;
+
+ /* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset;
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
+#undef EMIT_VVAR
+
+ hpet_page = vvar_start + PAGE_SIZE;
+
+ . = SIZEOF_HEADERS;
+
+ .hash : { *(.hash) } :text
+ .gnu.hash : { *(.gnu.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .gnu.version : { *(.gnu.version) }
+ .gnu.version_d : { *(.gnu.version_d) }
+ .gnu.version_r : { *(.gnu.version_r) }
+
+ .dynamic : { *(.dynamic) } :text :dynamic
+
+ .rodata : {
+ *(.rodata*)
+ *(.data*)
+ *(.sdata*)
+ *(.got.plt) *(.got)
+ *(.gnu.linkonce.d.*)
+ *(.bss*)
+ *(.dynbss*)
+ *(.gnu.linkonce.b.*)
+
+ /*
+ * Ideally this would live in a C file, but that won't
+ * work cleanly for x32 until we start building the x32
+ * C code using an x32 toolchain.
+ */
+ VDSO_FAKE_SECTION_TABLE_START = .;
+ . = . + NUM_FAKE_SHDRS * SHDR_SIZE;
+ VDSO_FAKE_SECTION_TABLE_END = .;
+ } :text
+
+ .fake_shstrtab : { *(.fake_shstrtab) } :text
+
+
+ .note : { *(.note.*) } :text :note
+
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+
+
+ /*
+ * Text is well-separated from actual data: there's plenty of
+ * stuff that isn't used at runtime in between.
+ */
+
+ .text : { *(.text*) } :text =0x90909090,
+
+ /*
+ * At the end so that eu-elflint stays happy when vdso2c strips
+ * these. A better implementation would avoid allocating space
+ * for these.
+ */
+ .altinstructions : { *(.altinstructions) } :text
+ .altinstr_replacement : { *(.altinstr_replacement) } :text
+
+ /DISCARD/ : {
+ *(.discard)
+ *(.discard.*)
+ *(__bug_table)
+ }
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME 0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+ text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+ eh_frame_hdr PT_GNU_EH_FRAME;
+}
--- /dev/null
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+ELFNOTE_START(Linux, 0, "a")
+ .long LINUX_VERSION_CODE
+ELFNOTE_END
--- /dev/null
+/*
+ * Linker script for 64-bit vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#define BUILD_VDSO64
+
+#include "vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+ LINUX_2.6 {
+ global:
+ clock_gettime;
+ __vdso_clock_gettime;
+ gettimeofday;
+ __vdso_gettimeofday;
+ getcpu;
+ __vdso_getcpu;
+ time;
+ __vdso_time;
+ local: *;
+ };
+}
--- /dev/null
+/*
+ * vdso2c - A vdso image preparation tool
+ * Copyright (c) 2014 Andy Lutomirski and others
+ * Licensed under the GPL v2
+ *
+ * vdso2c requires stripped and unstripped input. It would be trivial
+ * to fully strip the input in here, but, for reasons described below,
+ * we need to write a section table. Doing this is more or less
+ * equivalent to dropping all non-allocatable sections, but it's
+ * easier to let objcopy handle that instead of doing it ourselves.
+ * If we ever need to do something fancier than what objcopy provides,
+ * it would be straightforward to add here.
+ *
+ * We're keep a section table for a few reasons:
+ *
+ * The Go runtime had a couple of bugs: it would read the section
+ * table to try to figure out how many dynamic symbols there were (it
+ * shouldn't have looked at the section table at all) and, if there
+ * were no SHT_SYNDYM section table entry, it would use an
+ * uninitialized value for the number of symbols. An empty DYNSYM
+ * table would work, but I see no reason not to write a valid one (and
+ * keep full performance for old Go programs). This hack is only
+ * needed on x86_64.
+ *
+ * The bug was introduced on 2012-08-31 by:
+ * https://code.google.com/p/go/source/detail?r=56ea40aac72b
+ * and was fixed on 2014-06-13 by:
+ * https://code.google.com/p/go/source/detail?r=fc1cd5e12595
+ *
+ * Binutils has issues debugging the vDSO: it reads the section table to
+ * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which
+ * would break build-id if we removed the section table. Binutils
+ * also requires that shstrndx != 0. See:
+ * https://sourceware.org/bugzilla/show_bug.cgi?id=17064
+ *
+ * elfutils might not look for PT_NOTE if there is a section table at
+ * all. I don't know whether this matters for any practical purpose.
+ *
+ * For simplicity, rather than hacking up a partial section table, we
+ * just write a mostly complete one. We omit non-dynamic symbols,
+ * though, since they're rather large.
+ *
+ * Once binutils gets fixed, we might be able to drop this for all but
+ * the 64-bit vdso, since build-id only works in kernel RPMs, and
+ * systems that update to new enough kernel RPMs will likely update
+ * binutils in sync. build-id has never worked for home-built kernel
+ * RPMs without manual symlinking, and I suspect that no one ever does
+ * that.
+ */
+
+#include <inttypes.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <fcntl.h>
+#include <err.h>
+
+#include <sys/mman.h>
+#include <sys/types.h>
+
+#include <tools/le_byteshift.h>
+
+#include <linux/elf.h>
+#include <linux/types.h>
+
+const char *outfilename;
+
+/* Symbols that we need in vdso2c. */
+enum {
+ sym_vvar_start,
+ sym_vvar_page,
+ sym_hpet_page,
+ sym_VDSO_FAKE_SECTION_TABLE_START,
+ sym_VDSO_FAKE_SECTION_TABLE_END,
+};
+
+const int special_pages[] = {
+ sym_vvar_page,
+ sym_hpet_page,
+};
+
+struct vdso_sym {
+ const char *name;
+ bool export;
+};
+
+struct vdso_sym required_syms[] = {
+ [sym_vvar_start] = {"vvar_start", true},
+ [sym_vvar_page] = {"vvar_page", true},
+ [sym_hpet_page] = {"hpet_page", true},
+ [sym_VDSO_FAKE_SECTION_TABLE_START] = {
+ "VDSO_FAKE_SECTION_TABLE_START", false
+ },
+ [sym_VDSO_FAKE_SECTION_TABLE_END] = {
+ "VDSO_FAKE_SECTION_TABLE_END", false
+ },
+ {"VDSO32_NOTE_MASK", true},
+ {"VDSO32_SYSENTER_RETURN", true},
+ {"__kernel_vsyscall", true},
+ {"__kernel_sigreturn", true},
+ {"__kernel_rt_sigreturn", true},
+};
+
+__attribute__((format(printf, 1, 2))) __attribute__((noreturn))
+static void fail(const char *format, ...)
+{
+ va_list ap;
+ va_start(ap, format);
+ fprintf(stderr, "Error: ");
+ vfprintf(stderr, format, ap);
+ if (outfilename)
+ unlink(outfilename);
+ exit(1);
+ va_end(ap);
+}
+
+/*
+ * Evil macros for little-endian reads and writes
+ */
+#define GLE(x, bits, ifnot) \
+ __builtin_choose_expr( \
+ (sizeof(*(x)) == bits/8), \
+ (__typeof__(*(x)))get_unaligned_le##bits(x), ifnot)
+
+extern void bad_get_le(void);
+#define LAST_GLE(x) \
+ __builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le())
+
+#define GET_LE(x) \
+ GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x))))
+
+#define PLE(x, val, bits, ifnot) \
+ __builtin_choose_expr( \
+ (sizeof(*(x)) == bits/8), \
+ put_unaligned_le##bits((val), (x)), ifnot)
+
+extern void bad_put_le(void);
+#define LAST_PLE(x, val) \
+ __builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le())
+
+#define PUT_LE(x, val) \
+ PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val))))
+
+
+#define NSYMS (sizeof(required_syms) / sizeof(required_syms[0]))
+
+#define BITSFUNC3(name, bits, suffix) name##bits##suffix
+#define BITSFUNC2(name, bits, suffix) BITSFUNC3(name, bits, suffix)
+#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS, )
+
+#define INT_BITS BITSFUNC2(int, ELF_BITS, _t)
+
+#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
+#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
+#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
+
+#define ELF_BITS 64
+#include "vdso2c.h"
+#undef ELF_BITS
+
+#define ELF_BITS 32
+#include "vdso2c.h"
+#undef ELF_BITS
+
+static void go(void *raw_addr, size_t raw_len,
+ void *stripped_addr, size_t stripped_len,
+ FILE *outfile, const char *name)
+{
+ Elf64_Ehdr *hdr = (Elf64_Ehdr *)raw_addr;
+
+ if (hdr->e_ident[EI_CLASS] == ELFCLASS64) {
+ go64(raw_addr, raw_len, stripped_addr, stripped_len,
+ outfile, name);
+ } else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) {
+ go32(raw_addr, raw_len, stripped_addr, stripped_len,
+ outfile, name);
+ } else {
+ fail("unknown ELF class\n");
+ }
+}
+
+static void map_input(const char *name, void **addr, size_t *len, int prot)
+{
+ off_t tmp_len;
+
+ int fd = open(name, O_RDONLY);
+ if (fd == -1)
+ err(1, "%s", name);
+
+ tmp_len = lseek(fd, 0, SEEK_END);
+ if (tmp_len == (off_t)-1)
+ err(1, "lseek");
+ *len = (size_t)tmp_len;
+
+ *addr = mmap(NULL, tmp_len, prot, MAP_PRIVATE, fd, 0);
+ if (*addr == MAP_FAILED)
+ err(1, "mmap");
+
+ close(fd);
+}
+
+int main(int argc, char **argv)
+{
+ size_t raw_len, stripped_len;
+ void *raw_addr, *stripped_addr;
+ FILE *outfile;
+ char *name, *tmp;
+ int namelen;
+
+ if (argc != 4) {
+ printf("Usage: vdso2c RAW_INPUT STRIPPED_INPUT OUTPUT\n");
+ return 1;
+ }
+
+ /*
+ * Figure out the struct name. If we're writing to a .so file,
+ * generate raw output insted.
+ */
+ name = strdup(argv[3]);
+ namelen = strlen(name);
+ if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) {
+ name = NULL;
+ } else {
+ tmp = strrchr(name, '/');
+ if (tmp)
+ name = tmp + 1;
+ tmp = strchr(name, '.');
+ if (tmp)
+ *tmp = '\0';
+ for (tmp = name; *tmp; tmp++)
+ if (*tmp == '-')
+ *tmp = '_';
+ }
+
+ map_input(argv[1], &raw_addr, &raw_len, PROT_READ);
+ map_input(argv[2], &stripped_addr, &stripped_len, PROT_READ);
+
+ outfilename = argv[3];
+ outfile = fopen(outfilename, "w");
+ if (!outfile)
+ err(1, "%s", argv[2]);
+
+ go(raw_addr, raw_len, stripped_addr, stripped_len, outfile, name);
+
+ munmap(raw_addr, raw_len);
+ munmap(stripped_addr, stripped_len);
+ fclose(outfile);
+
+ return 0;
+}
--- /dev/null
+/*
+ * This file is included twice from vdso2c.c. It generates code for 32-bit
+ * and 64-bit vDSOs. We need both for 64-bit builds, since 32-bit vDSOs
+ * are built for 32-bit userspace.
+ */
+
+static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
+ void *stripped_addr, size_t stripped_len,
+ FILE *outfile, const char *name)
+{
+ int found_load = 0;
+ unsigned long load_size = -1; /* Work around bogus warning */
+ unsigned long mapping_size;
+ ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr;
+ int i;
+ unsigned long j;
+ ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
+ *alt_sec = NULL;
+ ELF(Dyn) *dyn = 0, *dyn_end = 0;
+ const char *secstrings;
+ INT_BITS syms[NSYMS] = {};
+
+ ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff));
+
+ /* Walk the segment table. */
+ for (i = 0; i < GET_LE(&hdr->e_phnum); i++) {
+ if (GET_LE(&pt[i].p_type) == PT_LOAD) {
+ if (found_load)
+ fail("multiple PT_LOAD segs\n");
+
+ if (GET_LE(&pt[i].p_offset) != 0 ||
+ GET_LE(&pt[i].p_vaddr) != 0)
+ fail("PT_LOAD in wrong place\n");
+
+ if (GET_LE(&pt[i].p_memsz) != GET_LE(&pt[i].p_filesz))
+ fail("cannot handle memsz != filesz\n");
+
+ load_size = GET_LE(&pt[i].p_memsz);
+ found_load = 1;
+ } else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) {
+ dyn = raw_addr + GET_LE(&pt[i].p_offset);
+ dyn_end = raw_addr + GET_LE(&pt[i].p_offset) +
+ GET_LE(&pt[i].p_memsz);
+ }
+ }
+ if (!found_load)
+ fail("no PT_LOAD seg\n");
+
+ if (stripped_len < load_size)
+ fail("stripped input is too short\n");
+
+ /* Walk the dynamic table */
+ for (i = 0; dyn + i < dyn_end &&
+ GET_LE(&dyn[i].d_tag) != DT_NULL; i++) {
+ typeof(dyn[i].d_tag) tag = GET_LE(&dyn[i].d_tag);
+ if (tag == DT_REL || tag == DT_RELSZ || tag == DT_RELA ||
+ tag == DT_RELENT || tag == DT_TEXTREL)
+ fail("vdso image contains dynamic relocations\n");
+ }
+
+ /* Walk the section table */
+ secstrings_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
+ GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx);
+ secstrings = raw_addr + GET_LE(&secstrings_hdr->sh_offset);
+ for (i = 0; i < GET_LE(&hdr->e_shnum); i++) {
+ ELF(Shdr) *sh = raw_addr + GET_LE(&hdr->e_shoff) +
+ GET_LE(&hdr->e_shentsize) * i;
+ if (GET_LE(&sh->sh_type) == SHT_SYMTAB)
+ symtab_hdr = sh;
+
+ if (!strcmp(secstrings + GET_LE(&sh->sh_name),
+ ".altinstructions"))
+ alt_sec = sh;
+ }
+
+ if (!symtab_hdr)
+ fail("no symbol table\n");
+
+ strtab_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
+ GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link);
+
+ /* Walk the symbol table */
+ for (i = 0;
+ i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize);
+ i++) {
+ int k;
+ ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
+ GET_LE(&symtab_hdr->sh_entsize) * i;
+ const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) +
+ GET_LE(&sym->st_name);
+
+ for (k = 0; k < NSYMS; k++) {
+ if (!strcmp(name, required_syms[k].name)) {
+ if (syms[k]) {
+ fail("duplicate symbol %s\n",
+ required_syms[k].name);
+ }
+
+ /*
+ * Careful: we use negative addresses, but
+ * st_value is unsigned, so we rely
+ * on syms[k] being a signed type of the
+ * correct width.
+ */
+ syms[k] = GET_LE(&sym->st_value);
+ }
+ }
+ }
+
+ /* Validate mapping addresses. */
+ for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
+ INT_BITS symval = syms[special_pages[i]];
+
+ if (!symval)
+ continue; /* The mapping isn't used; ignore it. */
+
+ if (symval % 4096)
+ fail("%s must be a multiple of 4096\n",
+ required_syms[i].name);
+ if (symval + 4096 < syms[sym_vvar_start])
+ fail("%s underruns vvar_start\n",
+ required_syms[i].name);
+ if (symval + 4096 > 0)
+ fail("%s is on the wrong side of the vdso text\n",
+ required_syms[i].name);
+ }
+ if (syms[sym_vvar_start] % 4096)
+ fail("vvar_begin must be a multiple of 4096\n");
+
+ if (!name) {
+ fwrite(stripped_addr, stripped_len, 1, outfile);
+ return;
+ }
+
+ mapping_size = (stripped_len + 4095) / 4096 * 4096;
+
+ fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n");
+ fprintf(outfile, "#include <linux/linkage.h>\n");
+ fprintf(outfile, "#include <asm/page_types.h>\n");
+ fprintf(outfile, "#include <asm/vdso.h>\n");
+ fprintf(outfile, "\n");
+ fprintf(outfile,
+ "static unsigned char raw_data[%lu] __page_aligned_data = {",
+ mapping_size);
+ for (j = 0; j < stripped_len; j++) {
+ if (j % 10 == 0)
+ fprintf(outfile, "\n\t");
+ fprintf(outfile, "0x%02X, ",
+ (int)((unsigned char *)stripped_addr)[j]);
+ }
+ fprintf(outfile, "\n};\n\n");
+
+ fprintf(outfile, "static struct page *pages[%lu];\n\n",
+ mapping_size / 4096);
+
+ fprintf(outfile, "const struct vdso_image %s = {\n", name);
+ fprintf(outfile, "\t.data = raw_data,\n");
+ fprintf(outfile, "\t.size = %lu,\n", mapping_size);
+ fprintf(outfile, "\t.text_mapping = {\n");
+ fprintf(outfile, "\t\t.name = \"[vdso]\",\n");
+ fprintf(outfile, "\t\t.pages = pages,\n");
+ fprintf(outfile, "\t},\n");
+ if (alt_sec) {
+ fprintf(outfile, "\t.alt = %lu,\n",
+ (unsigned long)GET_LE(&alt_sec->sh_offset));
+ fprintf(outfile, "\t.alt_len = %lu,\n",
+ (unsigned long)GET_LE(&alt_sec->sh_size));
+ }
+ for (i = 0; i < NSYMS; i++) {
+ if (required_syms[i].export && syms[i])
+ fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n",
+ required_syms[i].name, (int64_t)syms[i]);
+ }
+ fprintf(outfile, "};\n");
+}
--- /dev/null
+/*
+ * (C) Copyright 2002 Linus Torvalds
+ * Portions based on the vdso-randomization code from exec-shield:
+ * Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
+ *
+ * This file contains the needed initializations to support sysenter.
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/mm_types.h>
+
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+#include <asm/vdso.h>
+
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_DEFAULT 0
+#else
+#define VDSO_DEFAULT 1
+#endif
+
+/*
+ * Should the kernel map a VDSO page into processes and pass its
+ * address down to glibc upon exec()?
+ */
+unsigned int __read_mostly vdso32_enabled = VDSO_DEFAULT;
+
+static int __init vdso32_setup(char *s)
+{
+ vdso32_enabled = simple_strtoul(s, NULL, 0);
+
+ if (vdso32_enabled > 1)
+ pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+
+ return 1;
+}
+
+/*
+ * For consistency, the argument vdso32=[012] affects the 32-bit vDSO
+ * behavior on both 64-bit and 32-bit kernels.
+ * On 32-bit kernels, vdso=[012] means the same thing.
+ */
+__setup("vdso32=", vdso32_setup);
+
+#ifdef CONFIG_X86_32
+__setup_param("vdso=", vdso_setup, vdso32_setup, 0);
+#endif
+
+#ifdef CONFIG_X86_64
+
+#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32))
+#define vdso32_syscall() (boot_cpu_has(X86_FEATURE_SYSCALL32))
+
+#else /* CONFIG_X86_32 */
+
+#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SEP))
+#define vdso32_syscall() (0)
+
+#endif /* CONFIG_X86_64 */
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+const struct vdso_image *selected_vdso32;
+#endif
+
+int __init sysenter_setup(void)
+{
+#ifdef CONFIG_COMPAT
+ if (vdso32_syscall())
+ selected_vdso32 = &vdso_image_32_syscall;
+ else
+#endif
+ if (vdso32_sysenter())
+ selected_vdso32 = &vdso_image_32_sysenter;
+ else
+ selected_vdso32 = &vdso_image_32_int80;
+
+ init_vdso_image(selected_vdso32);
+
+ return 0;
+}
+
+#ifdef CONFIG_X86_64
+
+subsys_initcall(sysenter_setup);
+
+#ifdef CONFIG_SYSCTL
+/* Register vsyscall32 into the ABI table */
+#include <linux/sysctl.h>
+
+static struct ctl_table abi_table2[] = {
+ {
+ .procname = "vsyscall32",
+ .data = &vdso32_enabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {}
+};
+
+static struct ctl_table abi_root_table2[] = {
+ {
+ .procname = "abi",
+ .mode = 0555,
+ .child = abi_table2
+ },
+ {}
+};
+
+static __init int ia32_binfmt_init(void)
+{
+ register_sysctl_table(abi_root_table2);
+ return 0;
+}
+__initcall(ia32_binfmt_init);
+#endif /* CONFIG_SYSCTL */
+
+#endif /* CONFIG_X86_64 */
--- /dev/null
+vdso32.lds
--- /dev/null
+/*
+ * Code for the vDSO. This version uses the old int $0x80 method.
+ *
+ * First get the common code for the sigreturn entry points.
+ * This must come first.
+ */
+#include "sigreturn.S"
+
+ .text
+ .globl __kernel_vsyscall
+ .type __kernel_vsyscall,@function
+ ALIGN
+__kernel_vsyscall:
+.LSTART_vsyscall:
+ int $0x80
+ ret
+.LEND_vsyscall:
+ .size __kernel_vsyscall,.-.LSTART_vsyscall
+ .previous
+
+ .section .eh_frame,"a",@progbits
+.LSTARTFRAMEDLSI:
+ .long .LENDCIEDLSI-.LSTARTCIEDLSI
+.LSTARTCIEDLSI:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zR" /* NUL-terminated augmentation string */
+ .uleb128 1 /* Code alignment factor */
+ .sleb128 -4 /* Data alignment factor */
+ .byte 8 /* Return address register column */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+ .byte 0x0c /* DW_CFA_def_cfa */
+ .uleb128 4
+ .uleb128 4
+ .byte 0x88 /* DW_CFA_offset, column 0x8 */
+ .uleb128 1
+ .align 4
+.LENDCIEDLSI:
+ .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
+.LSTARTFDEDLSI:
+ .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
+ .long .LSTART_vsyscall-. /* PC-relative start address */
+ .long .LEND_vsyscall-.LSTART_vsyscall
+ .uleb128 0
+ .align 4
+.LENDFDEDLSI:
+ .previous
+
+ /*
+ * Pad out the segment to match the size of the sysenter.S version.
+ */
+VDSO32_vsyscall_eh_frame_size = 0x40
+ .section .data,"aw",@progbits
+ .space VDSO32_vsyscall_eh_frame_size-(.LENDFDEDLSI-.LSTARTFRAMEDLSI), 0
+ .previous
--- /dev/null
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+/* Ideally this would use UTS_NAME, but using a quoted string here
+ doesn't work. Remember to change this when changing the
+ kernel's name. */
+ELFNOTE_START(Linux, 0, "a")
+ .long LINUX_VERSION_CODE
+ELFNOTE_END
+
+#ifdef CONFIG_XEN
+/*
+ * Add a special note telling glibc's dynamic linker a fake hardware
+ * flavor that it will use to choose the search path for libraries in the
+ * same way it uses real hardware capabilities like "mmx".
+ * We supply "nosegneg" as the fake capability, to indicate that we
+ * do not like negative offsets in instructions using segment overrides,
+ * since we implement those inefficiently. This makes it possible to
+ * install libraries optimized to avoid those access patterns in someplace
+ * like /lib/i686/tls/nosegneg. Note that an /etc/ld.so.conf.d/file
+ * corresponding to the bits here is needed to make ldconfig work right.
+ * It should contain:
+ * hwcap 1 nosegneg
+ * to match the mapping of bit to name that we give here.
+ *
+ * At runtime, the fake hardware feature will be considered to be present
+ * if its bit is set in the mask word. So, we start with the mask 0, and
+ * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen.
+ */
+
+#include "../../xen/vdso.h" /* Defines VDSO_NOTE_NONEGSEG_BIT. */
+
+ELFNOTE_START(GNU, 2, "a")
+ .long 1 /* ncaps */
+VDSO32_NOTE_MASK: /* Symbol used by arch/x86/xen/setup.c */
+ .long 0 /* mask */
+ .byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg" /* bit, name */
+ELFNOTE_END
+#endif
--- /dev/null
+/*
+ * Common code for the sigreturn entry points in vDSO images.
+ * So far this code is the same for both int80 and sysenter versions.
+ * This file is #include'd by int80.S et al to define them first thing.
+ * The kernel assumes that the addresses of these routines are constant
+ * for all vDSO implementations.
+ */
+
+#include <linux/linkage.h>
+#include <asm/unistd_32.h>
+#include <asm/asm-offsets.h>
+
+#ifndef SYSCALL_ENTER_KERNEL
+#define SYSCALL_ENTER_KERNEL int $0x80
+#endif
+
+ .text
+ .globl __kernel_sigreturn
+ .type __kernel_sigreturn,@function
+ nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
+ ALIGN
+__kernel_sigreturn:
+.LSTART_sigreturn:
+ popl %eax /* XXX does this mean it needs unwind info? */
+ movl $__NR_sigreturn, %eax
+ SYSCALL_ENTER_KERNEL
+.LEND_sigreturn:
+ nop
+ .size __kernel_sigreturn,.-.LSTART_sigreturn
+
+ .globl __kernel_rt_sigreturn
+ .type __kernel_rt_sigreturn,@function
+ ALIGN
+__kernel_rt_sigreturn:
+.LSTART_rt_sigreturn:
+ movl $__NR_rt_sigreturn, %eax
+ SYSCALL_ENTER_KERNEL
+.LEND_rt_sigreturn:
+ nop
+ .size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn
+ .previous
+
+ .section .eh_frame,"a",@progbits
+.LSTARTFRAMEDLSI1:
+ .long .LENDCIEDLSI1-.LSTARTCIEDLSI1
+.LSTARTCIEDLSI1:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zRS" /* NUL-terminated augmentation string */
+ .uleb128 1 /* Code alignment factor */
+ .sleb128 -4 /* Data alignment factor */
+ .byte 8 /* Return address register column */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+ .byte 0 /* DW_CFA_nop */
+ .align 4
+.LENDCIEDLSI1:
+ .long .LENDFDEDLSI1-.LSTARTFDEDLSI1 /* Length FDE */
+.LSTARTFDEDLSI1:
+ .long .LSTARTFDEDLSI1-.LSTARTFRAMEDLSI1 /* CIE pointer */
+ /* HACK: The dwarf2 unwind routines will subtract 1 from the
+ return address to get an address in the middle of the
+ presumed call instruction. Since we didn't get here via
+ a call, we need to include the nop before the real start
+ to make up for it. */
+ .long .LSTART_sigreturn-1-. /* PC-relative start address */
+ .long .LEND_sigreturn-.LSTART_sigreturn+1
+ .uleb128 0 /* Augmentation */
+ /* What follows are the instructions for the table generation.
+ We record the locations of each register saved. This is
+ complicated by the fact that the "CFA" is always assumed to
+ be the value of the stack pointer in the caller. This means
+ that we must define the CFA of this body of code to be the
+ saved value of the stack pointer in the sigcontext. Which
+ also means that there is no fixed relation to the other
+ saved registers, which means that we must use DW_CFA_expression
+ to compute their addresses. It also means that when we
+ adjust the stack with the popl, we have to do it all over again. */
+
+#define do_cfa_expr(offset) \
+ .byte 0x0f; /* DW_CFA_def_cfa_expression */ \
+ .uleb128 1f-0f; /* length */ \
+0: .byte 0x74; /* DW_OP_breg4 */ \
+ .sleb128 offset; /* offset */ \
+ .byte 0x06; /* DW_OP_deref */ \
+1:
+
+#define do_expr(regno, offset) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno; /* regno */ \
+ .uleb128 1f-0f; /* length */ \
+0: .byte 0x74; /* DW_OP_breg4 */ \
+ .sleb128 offset; /* offset */ \
+1:
+
+ do_cfa_expr(IA32_SIGCONTEXT_sp+4)
+ do_expr(0, IA32_SIGCONTEXT_ax+4)
+ do_expr(1, IA32_SIGCONTEXT_cx+4)
+ do_expr(2, IA32_SIGCONTEXT_dx+4)
+ do_expr(3, IA32_SIGCONTEXT_bx+4)
+ do_expr(5, IA32_SIGCONTEXT_bp+4)
+ do_expr(6, IA32_SIGCONTEXT_si+4)
+ do_expr(7, IA32_SIGCONTEXT_di+4)
+ do_expr(8, IA32_SIGCONTEXT_ip+4)
+
+ .byte 0x42 /* DW_CFA_advance_loc 2 -- nop; popl eax. */
+
+ do_cfa_expr(IA32_SIGCONTEXT_sp)
+ do_expr(0, IA32_SIGCONTEXT_ax)
+ do_expr(1, IA32_SIGCONTEXT_cx)
+ do_expr(2, IA32_SIGCONTEXT_dx)
+ do_expr(3, IA32_SIGCONTEXT_bx)
+ do_expr(5, IA32_SIGCONTEXT_bp)
+ do_expr(6, IA32_SIGCONTEXT_si)
+ do_expr(7, IA32_SIGCONTEXT_di)
+ do_expr(8, IA32_SIGCONTEXT_ip)
+
+ .align 4
+.LENDFDEDLSI1:
+
+ .long .LENDFDEDLSI2-.LSTARTFDEDLSI2 /* Length FDE */
+.LSTARTFDEDLSI2:
+ .long .LSTARTFDEDLSI2-.LSTARTFRAMEDLSI1 /* CIE pointer */
+ /* HACK: See above wrt unwind library assumptions. */
+ .long .LSTART_rt_sigreturn-1-. /* PC-relative start address */
+ .long .LEND_rt_sigreturn-.LSTART_rt_sigreturn+1
+ .uleb128 0 /* Augmentation */
+ /* What follows are the instructions for the table generation.
+ We record the locations of each register saved. This is
+ slightly less complicated than the above, since we don't
+ modify the stack pointer in the process. */
+
+ do_cfa_expr(IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_sp)
+ do_expr(0, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ax)
+ do_expr(1, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_cx)
+ do_expr(2, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_dx)
+ do_expr(3, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bx)
+ do_expr(5, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bp)
+ do_expr(6, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_si)
+ do_expr(7, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_di)
+ do_expr(8, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ip)
+
+ .align 4
+.LENDFDEDLSI2:
+ .previous
--- /dev/null
+/*
+ * Code for the vDSO. This version uses the syscall instruction.
+ *
+ * First get the common code for the sigreturn entry points.
+ * This must come first.
+ */
+#define SYSCALL_ENTER_KERNEL syscall
+#include "sigreturn.S"
+
+#include <asm/segment.h>
+
+ .text
+ .globl __kernel_vsyscall
+ .type __kernel_vsyscall,@function
+ ALIGN
+__kernel_vsyscall:
+.LSTART_vsyscall:
+ push %ebp
+.Lpush_ebp:
+ movl %ecx, %ebp
+ syscall
+ movl %ebp, %ecx
+ popl %ebp
+.Lpop_ebp:
+ ret
+.LEND_vsyscall:
+ .size __kernel_vsyscall,.-.LSTART_vsyscall
+
+ .section .eh_frame,"a",@progbits
+.LSTARTFRAME:
+ .long .LENDCIE-.LSTARTCIE
+.LSTARTCIE:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zR" /* NUL-terminated augmentation string */
+ .uleb128 1 /* Code alignment factor */
+ .sleb128 -4 /* Data alignment factor */
+ .byte 8 /* Return address register column */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+ .byte 0x0c /* DW_CFA_def_cfa */
+ .uleb128 4
+ .uleb128 4
+ .byte 0x88 /* DW_CFA_offset, column 0x8 */
+ .uleb128 1
+ .align 4
+.LENDCIE:
+
+ .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */
+.LSTARTFDE1:
+ .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */
+ .long .LSTART_vsyscall-. /* PC-relative start address */
+ .long .LEND_vsyscall-.LSTART_vsyscall
+ .uleb128 0 /* Augmentation length */
+ /* What follows are the instructions for the table generation.
+ We have to record all changes of the stack pointer. */
+ .byte 0x40 + .Lpush_ebp-.LSTART_vsyscall /* DW_CFA_advance_loc */
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .uleb128 8
+ .byte 0x85, 0x02 /* DW_CFA_offset %ebp -8 */
+ .byte 0x40 + .Lpop_ebp-.Lpush_ebp /* DW_CFA_advance_loc */
+ .byte 0xc5 /* DW_CFA_restore %ebp */
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .uleb128 4
+ .align 4
+.LENDFDE1:
+ .previous
+
+ /*
+ * Pad out the segment to match the size of the sysenter.S version.
+ */
+VDSO32_vsyscall_eh_frame_size = 0x40
+ .section .data,"aw",@progbits
+ .space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0
+ .previous
--- /dev/null
+/*
+ * Code for the vDSO. This version uses the sysenter instruction.
+ *
+ * First get the common code for the sigreturn entry points.
+ * This must come first.
+ */
+#include "sigreturn.S"
+
+/*
+ * The caller puts arg2 in %ecx, which gets pushed. The kernel will use
+ * %ecx itself for arg2. The pushing is because the sysexit instruction
+ * (found in entry.S) requires that we clobber %ecx with the desired %esp.
+ * User code might expect that %ecx is unclobbered though, as it would be
+ * for returning via the iret instruction, so we must push and pop.
+ *
+ * The caller puts arg3 in %edx, which the sysexit instruction requires
+ * for %eip. Thus, exactly as for arg2, we must push and pop.
+ *
+ * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter
+ * instruction clobbers %esp, the user's %esp won't even survive entry
+ * into the kernel. We store %esp in %ebp. Code in entry.S must fetch
+ * arg6 from the stack.
+ *
+ * You can not use this vsyscall for the clone() syscall because the
+ * three words on the parent stack do not get copied to the child.
+ */
+ .text
+ .globl __kernel_vsyscall
+ .type __kernel_vsyscall,@function
+ ALIGN
+__kernel_vsyscall:
+.LSTART_vsyscall:
+ push %ecx
+.Lpush_ecx:
+ push %edx
+.Lpush_edx:
+ push %ebp
+.Lenter_kernel:
+ movl %esp,%ebp
+ sysenter
+
+ /* 7: align return point with nop's to make disassembly easier */
+ .space 7,0x90
+
+ /* 14: System call restart point is here! (SYSENTER_RETURN-2) */
+ int $0x80
+ /* 16: System call normal return point is here! */
+VDSO32_SYSENTER_RETURN: /* Symbol used by sysenter.c via vdso32-syms.h */
+ pop %ebp
+.Lpop_ebp:
+ pop %edx
+.Lpop_edx:
+ pop %ecx
+.Lpop_ecx:
+ ret
+.LEND_vsyscall:
+ .size __kernel_vsyscall,.-.LSTART_vsyscall
+ .previous
+
+ .section .eh_frame,"a",@progbits
+.LSTARTFRAMEDLSI:
+ .long .LENDCIEDLSI-.LSTARTCIEDLSI
+.LSTARTCIEDLSI:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zR" /* NUL-terminated augmentation string */
+ .uleb128 1 /* Code alignment factor */
+ .sleb128 -4 /* Data alignment factor */
+ .byte 8 /* Return address register column */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
+ .byte 0x0c /* DW_CFA_def_cfa */
+ .uleb128 4
+ .uleb128 4
+ .byte 0x88 /* DW_CFA_offset, column 0x8 */
+ .uleb128 1
+ .align 4
+.LENDCIEDLSI:
+ .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
+.LSTARTFDEDLSI:
+ .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
+ .long .LSTART_vsyscall-. /* PC-relative start address */
+ .long .LEND_vsyscall-.LSTART_vsyscall
+ .uleb128 0
+ /* What follows are the instructions for the table generation.
+ We have to record all changes of the stack pointer. */
+ .byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x08 /* RA at offset 8 now */
+ .byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x0c /* RA at offset 12 now */
+ .byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x10 /* RA at offset 16 now */
+ .byte 0x85, 0x04 /* DW_CFA_offset %ebp -16 */
+ /* Finally the epilogue. */
+ .byte 0x40 + (.Lpop_ebp-.Lenter_kernel) /* DW_CFA_advance_loc */
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x0c /* RA at offset 12 now */
+ .byte 0xc5 /* DW_CFA_restore %ebp */
+ .byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x08 /* RA at offset 8 now */
+ .byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */
+ .byte 0x0e /* DW_CFA_def_cfa_offset */
+ .byte 0x04 /* RA at offset 4 now */
+ .align 4
+.LENDFDEDLSI:
+ .previous
+
+ /*
+ * Emit a symbol with the size of this .eh_frame data,
+ * to verify it matches the other versions.
+ */
+VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI)
--- /dev/null
+#define BUILD_VDSO32
+
+#ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
+#undef CONFIG_OPTIMIZE_INLINING
+#endif
+
+#undef CONFIG_X86_PPRO_FENCE
+
+#ifdef CONFIG_X86_64
+
+/*
+ * in case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel
+ * configuration
+ */
+#undef CONFIG_64BIT
+#undef CONFIG_X86_64
+#undef CONFIG_ILLEGAL_POINTER_VALUE
+#undef CONFIG_SPARSEMEM_VMEMMAP
+#undef CONFIG_NR_CPUS
+
+#define CONFIG_X86_32 1
+#define CONFIG_PAGE_OFFSET 0
+#define CONFIG_ILLEGAL_POINTER_VALUE 0
+#define CONFIG_NR_CPUS 1
+
+#define BUILD_VDSO32_64
+
+#endif
+
+#include "../vclock_gettime.c"
--- /dev/null
+#include "../vdso-fakesections.c"
--- /dev/null
+/*
+ * Linker script for 32-bit vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#include <asm/page.h>
+
+#define BUILD_VDSO32
+
+#include "../vdso-layout.lds.S"
+
+/* The ELF entry point can be used to set the AT_SYSINFO value. */
+ENTRY(__kernel_vsyscall);
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION
+{
+ LINUX_2.6 {
+ global:
+ __vdso_clock_gettime;
+ __vdso_gettimeofday;
+ __vdso_time;
+ };
+
+ LINUX_2.5 {
+ global:
+ __kernel_vsyscall;
+ __kernel_sigreturn;
+ __kernel_rt_sigreturn;
+ local: *;
+ };
+}
--- /dev/null
+/*
+ * Linker script for x32 vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#define BUILD_VDSOX32
+
+#include "vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+ LINUX_2.6 {
+ global:
+ __vdso_clock_gettime;
+ __vdso_gettimeofday;
+ __vdso_getcpu;
+ __vdso_time;
+ local: *;
+ };
+}
--- /dev/null
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Fast user context implementation of getcpu()
+ */
+
+#include <linux/kernel.h>
+#include <linux/getcpu.h>
+#include <linux/time.h>
+#include <asm/vgtod.h>
+
+notrace long
+__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
+{
+ unsigned int p;
+
+ p = __getcpu();
+
+ if (cpu)
+ *cpu = p & VGETCPU_CPU_MASK;
+ if (node)
+ *node = p >> 12;
+ return 0;
+}
+
+long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
+ __attribute__((weak, alias("__vdso_getcpu")));
--- /dev/null
+/*
+ * Copyright 2007 Andi Kleen, SUSE Labs.
+ * Subject to the GPL, v.2
+ *
+ * This contains most of the x86 vDSO kernel-side code.
+ */
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/random.h>
+#include <linux/elf.h>
+#include <linux/cpu.h>
+#include <asm/vgtod.h>
+#include <asm/proto.h>
+#include <asm/vdso.h>
+#include <asm/vvar.h>
+#include <asm/page.h>
+#include <asm/hpet.h>
+#include <asm/desc.h>
+
+#if defined(CONFIG_X86_64)
+unsigned int __read_mostly vdso64_enabled = 1;
+#endif
+
+void __init init_vdso_image(const struct vdso_image *image)
+{
+ int i;
+ int npages = (image->size) / PAGE_SIZE;
+
+ BUG_ON(image->size % PAGE_SIZE != 0);
+ for (i = 0; i < npages; i++)
+ image->text_mapping.pages[i] =
+ virt_to_page(image->data + i*PAGE_SIZE);
+
+ apply_alternatives((struct alt_instr *)(image->data + image->alt),
+ (struct alt_instr *)(image->data + image->alt +
+ image->alt_len));
+}
+
+struct linux_binprm;
+
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset. This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top. This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
+static unsigned long vdso_addr(unsigned long start, unsigned len)
+{
+#ifdef CONFIG_X86_32
+ return 0;
+#else
+ unsigned long addr, end;
+ unsigned offset;
+
+ /*
+ * Round up the start address. It can start out unaligned as a result
+ * of stack start randomization.
+ */
+ start = PAGE_ALIGN(start);
+
+ /* Round the lowest possible end address up to a PMD boundary. */
+ end = (start + len + PMD_SIZE - 1) & PMD_MASK;
+ if (end >= TASK_SIZE_MAX)
+ end = TASK_SIZE_MAX;
+ end -= len;
+
+ if (end > start) {
+ offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+ addr = start + (offset << PAGE_SHIFT);
+ } else {
+ addr = start;
+ }
+
+ /*
+ * Forcibly align the final address in case we have a hardware
+ * issue that requires alignment for performance reasons.
+ */
+ addr = align_vdso_addr(addr);
+
+ return addr;
+#endif
+}
+
+static int map_vdso(const struct vdso_image *image, bool calculate_addr)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ unsigned long addr, text_start;
+ int ret = 0;
+ static struct page *no_pages[] = {NULL};
+ static struct vm_special_mapping vvar_mapping = {
+ .name = "[vvar]",
+ .pages = no_pages,
+ };
+
+ if (calculate_addr) {
+ addr = vdso_addr(current->mm->start_stack,
+ image->size - image->sym_vvar_start);
+ } else {
+ addr = 0;
+ }
+
+ down_write(&mm->mmap_sem);
+
+ addr = get_unmapped_area(NULL, addr,
+ image->size - image->sym_vvar_start, 0, 0);
+ if (IS_ERR_VALUE(addr)) {
+ ret = addr;
+ goto up_fail;
+ }
+
+ text_start = addr - image->sym_vvar_start;
+ current->mm->context.vdso = (void __user *)text_start;
+
+ /*
+ * MAYWRITE to allow gdb to COW and set breakpoints
+ */
+ vma = _install_special_mapping(mm,
+ text_start,
+ image->size,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+ &image->text_mapping);
+
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
+ goto up_fail;
+ }
+
+ vma = _install_special_mapping(mm,
+ addr,
+ -image->sym_vvar_start,
+ VM_READ|VM_MAYREAD,
+ &vvar_mapping);
+
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
+ goto up_fail;
+ }
+
+ if (image->sym_vvar_page)
+ ret = remap_pfn_range(vma,
+ text_start + image->sym_vvar_page,
+ __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
+ PAGE_SIZE,
+ PAGE_READONLY);
+
+ if (ret)
+ goto up_fail;
+
+#ifdef CONFIG_HPET_TIMER
+ if (hpet_address && image->sym_hpet_page) {
+ ret = io_remap_pfn_range(vma,
+ text_start + image->sym_hpet_page,
+ hpet_address >> PAGE_SHIFT,
+ PAGE_SIZE,
+ pgprot_noncached(PAGE_READONLY));
+
+ if (ret)
+ goto up_fail;
+ }
+#endif
+
+up_fail:
+ if (ret)
+ current->mm->context.vdso = NULL;
+
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+static int load_vdso32(void)
+{
+ int ret;
+
+ if (vdso32_enabled != 1) /* Other values all mean "disabled" */
+ return 0;
+
+ ret = map_vdso(selected_vdso32, false);
+ if (ret)
+ return ret;
+
+ if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN)
+ current_thread_info()->sysenter_return =
+ current->mm->context.vdso +
+ selected_vdso32->sym_VDSO32_SYSENTER_RETURN;
+
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_X86_64
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+ if (!vdso64_enabled)
+ return 0;
+
+ return map_vdso(&vdso_image_64, true);
+}
+
+#ifdef CONFIG_COMPAT
+int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp)
+{
+#ifdef CONFIG_X86_X32_ABI
+ if (test_thread_flag(TIF_X32)) {
+ if (!vdso64_enabled)
+ return 0;
+
+ return map_vdso(&vdso_image_x32, true);
+ }
+#endif
+
+ return load_vdso32();
+}
+#endif
+#else
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+ return load_vdso32();
+}
+#endif
+
+#ifdef CONFIG_X86_64
+static __init int vdso_setup(char *s)
+{
+ vdso64_enabled = simple_strtoul(s, NULL, 0);
+ return 0;
+}
+__setup("vdso=", vdso_setup);
+#endif
+
+#ifdef CONFIG_X86_64
+static void vgetcpu_cpu_init(void *arg)
+{
+ int cpu = smp_processor_id();
+ struct desc_struct d = { };
+ unsigned long node = 0;
+#ifdef CONFIG_NUMA
+ node = cpu_to_node(cpu);
+#endif
+ if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
+ write_rdtscp_aux((node << 12) | cpu);
+
+ /*
+ * Store cpu number in limit so that it can be loaded
+ * quickly in user space in vgetcpu. (12 bits for the CPU
+ * and 8 bits for the node)
+ */
+ d.limit0 = cpu | ((node & 0xf) << 12);
+ d.limit = node >> 4;
+ d.type = 5; /* RO data, expand down, accessed */
+ d.dpl = 3; /* Visible to user code */
+ d.s = 1; /* Not a system segment */
+ d.p = 1; /* Present */
+ d.d = 1; /* 32-bit */
+
+ write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
+}
+
+static int
+vgetcpu_cpu_notifier(struct notifier_block *n, unsigned long action, void *arg)
+{
+ long cpu = (long)arg;
+
+ if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
+ smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
+
+ return NOTIFY_DONE;
+}
+
+static int __init init_vdso(void)
+{
+ init_vdso_image(&vdso_image_64);
+
+#ifdef CONFIG_X86_X32_ABI
+ init_vdso_image(&vdso_image_x32);
+#endif
+
+ cpu_notifier_register_begin();
+
+ on_each_cpu(vgetcpu_cpu_init, NULL, 1);
+ /* notifier priority > KVM */
+ __hotcpu_notifier(vgetcpu_cpu_notifier, 30);
+
+ cpu_notifier_register_done();
+
+ return 0;
+}
+subsys_initcall(init_vdso);
+#endif /* CONFIG_X86_64 */
--- /dev/null
+#
+# Makefile for the x86 low level vsyscall code
+#
+obj-y := vsyscall_gtod.o
+
+obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
+
--- /dev/null
+/*
+ * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
+ *
+ * Based on the original implementation which is:
+ * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ * Parts of the original code have been moved to arch/x86/vdso/vma.c
+ *
+ * This file implements vsyscall emulation. vsyscalls are a legacy ABI:
+ * Userspace can request certain kernel services by calling fixed
+ * addresses. This concept is problematic:
+ *
+ * - It interferes with ASLR.
+ * - It's awkward to write code that lives in kernel addresses but is
+ * callable by userspace at fixed addresses.
+ * - The whole concept is impossible for 32-bit compat userspace.
+ * - UML cannot easily virtualize a vsyscall.
+ *
+ * As of mid-2014, I believe that there is no new userspace code that
+ * will use a vsyscall if the vDSO is present. I hope that there will
+ * soon be no new userspace code that will ever use a vsyscall.
+ *
+ * The code in this file emulates vsyscalls when notified of a page
+ * fault to a vsyscall address.
+ */
+
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <linux/syscalls.h>
+#include <linux/ratelimit.h>
+
+#include <asm/vsyscall.h>
+#include <asm/unistd.h>
+#include <asm/fixmap.h>
+#include <asm/traps.h>
+
+#define CREATE_TRACE_POINTS
+#include "vsyscall_trace.h"
+
+static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
+
+static int __init vsyscall_setup(char *str)
+{
+ if (str) {
+ if (!strcmp("emulate", str))
+ vsyscall_mode = EMULATE;
+ else if (!strcmp("native", str))
+ vsyscall_mode = NATIVE;
+ else if (!strcmp("none", str))
+ vsyscall_mode = NONE;
+ else
+ return -EINVAL;
+
+ return 0;
+ }
+
+ return -EINVAL;
+}
+early_param("vsyscall", vsyscall_setup);
+
+static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
+ const char *message)
+{
+ if (!show_unhandled_signals)
+ return;
+
+ printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+ level, current->comm, task_pid_nr(current),
+ message, regs->ip, regs->cs,
+ regs->sp, regs->ax, regs->si, regs->di);
+}
+
+static int addr_to_vsyscall_nr(unsigned long addr)
+{
+ int nr;
+
+ if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
+ return -EINVAL;
+
+ nr = (addr & 0xC00UL) >> 10;
+ if (nr >= 3)
+ return -EINVAL;
+
+ return nr;
+}
+
+static bool write_ok_or_segv(unsigned long ptr, size_t size)
+{
+ /*
+ * XXX: if access_ok, get_user, and put_user handled
+ * sig_on_uaccess_error, this could go away.
+ */
+
+ if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) {
+ siginfo_t info;
+ struct thread_struct *thread = ¤t->thread;
+
+ thread->error_code = 6; /* user fault, no page, write */
+ thread->cr2 = ptr;
+ thread->trap_nr = X86_TRAP_PF;
+
+ memset(&info, 0, sizeof(info));
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ info.si_code = SEGV_MAPERR;
+ info.si_addr = (void __user *)ptr;
+
+ force_sig_info(SIGSEGV, &info, current);
+ return false;
+ } else {
+ return true;
+ }
+}
+
+bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
+{
+ struct task_struct *tsk;
+ unsigned long caller;
+ int vsyscall_nr, syscall_nr, tmp;
+ int prev_sig_on_uaccess_error;
+ long ret;
+
+ /*
+ * No point in checking CS -- the only way to get here is a user mode
+ * trap to a high address, which means that we're in 64-bit user code.
+ */
+
+ WARN_ON_ONCE(address != regs->ip);
+
+ if (vsyscall_mode == NONE) {
+ warn_bad_vsyscall(KERN_INFO, regs,
+ "vsyscall attempted with vsyscall=none");
+ return false;
+ }
+
+ vsyscall_nr = addr_to_vsyscall_nr(address);
+
+ trace_emulate_vsyscall(vsyscall_nr);
+
+ if (vsyscall_nr < 0) {
+ warn_bad_vsyscall(KERN_WARNING, regs,
+ "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
+ goto sigsegv;
+ }
+
+ if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
+ warn_bad_vsyscall(KERN_WARNING, regs,
+ "vsyscall with bad stack (exploit attempt?)");
+ goto sigsegv;
+ }
+
+ tsk = current;
+
+ /*
+ * Check for access_ok violations and find the syscall nr.
+ *
+ * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
+ * 64-bit, so we don't need to special-case it here. For all the
+ * vsyscalls, NULL means "don't write anything" not "write it at
+ * address 0".
+ */
+ switch (vsyscall_nr) {
+ case 0:
+ if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
+ !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_gettimeofday;
+ break;
+
+ case 1:
+ if (!write_ok_or_segv(regs->di, sizeof(time_t))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_time;
+ break;
+
+ case 2:
+ if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
+ !write_ok_or_segv(regs->si, sizeof(unsigned))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_getcpu;
+ break;
+ }
+
+ /*
+ * Handle seccomp. regs->ip must be the original value.
+ * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt.
+ *
+ * We could optimize the seccomp disabled case, but performance
+ * here doesn't matter.
+ */
+ regs->orig_ax = syscall_nr;
+ regs->ax = -ENOSYS;
+ tmp = secure_computing();
+ if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
+ warn_bad_vsyscall(KERN_DEBUG, regs,
+ "seccomp tried to change syscall nr or ip");
+ do_exit(SIGSYS);
+ }
+ regs->orig_ax = -1;
+ if (tmp)
+ goto do_ret; /* skip requested */
+
+ /*
+ * With a real vsyscall, page faults cause SIGSEGV. We want to
+ * preserve that behavior to make writing exploits harder.
+ */
+ prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error;
+ current_thread_info()->sig_on_uaccess_error = 1;
+
+ ret = -EFAULT;
+ switch (vsyscall_nr) {
+ case 0:
+ ret = sys_gettimeofday(
+ (struct timeval __user *)regs->di,
+ (struct timezone __user *)regs->si);
+ break;
+
+ case 1:
+ ret = sys_time((time_t __user *)regs->di);
+ break;
+
+ case 2:
+ ret = sys_getcpu((unsigned __user *)regs->di,
+ (unsigned __user *)regs->si,
+ NULL);
+ break;
+ }
+
+ current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error;
+
+check_fault:
+ if (ret == -EFAULT) {
+ /* Bad news -- userspace fed a bad pointer to a vsyscall. */
+ warn_bad_vsyscall(KERN_INFO, regs,
+ "vsyscall fault (exploit attempt?)");
+
+ /*
+ * If we failed to generate a signal for any reason,
+ * generate one here. (This should be impossible.)
+ */
+ if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
+ !sigismember(&tsk->pending.signal, SIGSEGV)))
+ goto sigsegv;
+
+ return true; /* Don't emulate the ret. */
+ }
+
+ regs->ax = ret;
+
+do_ret:
+ /* Emulate a ret instruction. */
+ regs->ip = caller;
+ regs->sp += 8;
+ return true;
+
+sigsegv:
+ force_sig(SIGSEGV, current);
+ return true;
+}
+
+/*
+ * A pseudo VMA to allow ptrace access for the vsyscall page. This only
+ * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
+ * not need special handling anymore:
+ */
+static const char *gate_vma_name(struct vm_area_struct *vma)
+{
+ return "[vsyscall]";
+}
+static struct vm_operations_struct gate_vma_ops = {
+ .name = gate_vma_name,
+};
+static struct vm_area_struct gate_vma = {
+ .vm_start = VSYSCALL_ADDR,
+ .vm_end = VSYSCALL_ADDR + PAGE_SIZE,
+ .vm_page_prot = PAGE_READONLY_EXEC,
+ .vm_flags = VM_READ | VM_EXEC,
+ .vm_ops = &gate_vma_ops,
+};
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+#ifdef CONFIG_IA32_EMULATION
+ if (!mm || mm->context.ia32_compat)
+ return NULL;
+#endif
+ if (vsyscall_mode == NONE)
+ return NULL;
+ return &gate_vma;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+ struct vm_area_struct *vma = get_gate_vma(mm);
+
+ if (!vma)
+ return 0;
+
+ return (addr >= vma->vm_start) && (addr < vma->vm_end);
+}
+
+/*
+ * Use this when you have no reliable mm, typically from interrupt
+ * context. It is less reliable than using a task's mm and may give
+ * false positives.
+ */
+int in_gate_area_no_mm(unsigned long addr)
+{
+ return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
+}
+
+void __init map_vsyscall(void)
+{
+ extern char __vsyscall_page;
+ unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
+
+ if (vsyscall_mode != NONE)
+ __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
+ vsyscall_mode == NATIVE
+ ? PAGE_KERNEL_VSYSCALL
+ : PAGE_KERNEL_VVAR);
+
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
+ (unsigned long)VSYSCALL_ADDR);
+}
--- /dev/null
+/*
+ * vsyscall_emu_64.S: Vsyscall emulation page
+ *
+ * Copyright (c) 2011 Andy Lutomirski
+ *
+ * Subject to the GNU General Public License, version 2
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/irq_vectors.h>
+#include <asm/page_types.h>
+#include <asm/unistd_64.h>
+
+__PAGE_ALIGNED_DATA
+ .globl __vsyscall_page
+ .balign PAGE_SIZE, 0xcc
+ .type __vsyscall_page, @object
+__vsyscall_page:
+
+ mov $__NR_gettimeofday, %rax
+ syscall
+ ret
+
+ .balign 1024, 0xcc
+ mov $__NR_time, %rax
+ syscall
+ ret
+
+ .balign 1024, 0xcc
+ mov $__NR_getcpu, %rax
+ syscall
+ ret
+
+ .balign 4096, 0xcc
+
+ .size __vsyscall_page, 4096
--- /dev/null
+/*
+ * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ * Modified for x86 32 bit architecture by
+ * Stefani Seibold <stefani@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ *
+ * Thanks to hpa@transmeta.com for some useful hint.
+ * Special thanks to Ingo Molnar for his early experience with
+ * a different vsyscall implementation for Linux/IA32 and for the name.
+ *
+ */
+
+#include <linux/timekeeper_internal.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
+
+void update_vsyscall_tz(void)
+{
+ vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest;
+ vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime;
+}
+
+void update_vsyscall(struct timekeeper *tk)
+{
+ struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
+
+ gtod_write_begin(vdata);
+
+ /* copy vsyscall data */
+ vdata->vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
+ vdata->cycle_last = tk->tkr_mono.cycle_last;
+ vdata->mask = tk->tkr_mono.mask;
+ vdata->mult = tk->tkr_mono.mult;
+ vdata->shift = tk->tkr_mono.shift;
+
+ vdata->wall_time_sec = tk->xtime_sec;
+ vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec;
+
+ vdata->monotonic_time_sec = tk->xtime_sec
+ + tk->wall_to_monotonic.tv_sec;
+ vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec
+ + ((u64)tk->wall_to_monotonic.tv_nsec
+ << tk->tkr_mono.shift);
+ while (vdata->monotonic_time_snsec >=
+ (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
+ vdata->monotonic_time_snsec -=
+ ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
+ vdata->monotonic_time_sec++;
+ }
+
+ vdata->wall_time_coarse_sec = tk->xtime_sec;
+ vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >>
+ tk->tkr_mono.shift);
+
+ vdata->monotonic_time_coarse_sec =
+ vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
+ vdata->monotonic_time_coarse_nsec =
+ vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
+
+ while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) {
+ vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC;
+ vdata->monotonic_time_coarse_sec++;
+ }
+
+ gtod_write_end(vdata);
+}
--- /dev/null
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vsyscall
+
+#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VSYSCALL_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(emulate_vsyscall,
+
+ TP_PROTO(int nr),
+
+ TP_ARGS(nr),
+
+ TP_STRUCT__entry(__field(int, nr)),
+
+ TP_fast_assign(
+ __entry->nr = nr;
+ ),
+
+ TP_printk("nr = %d", __entry->nr)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/
+#define TRACE_INCLUDE_FILE vsyscall_trace
+#include <trace/define_trace.h>
# Makefile for the ia32 kernel emulation subsystem.
#
-obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o
+obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_signal.o
obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
#include <linux/binfmts.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
#include <asm/ptrace.h>
#include <asm/ia32_unistd.h>
#include <asm/user32.h>
buf = compat_ptr(tmp);
} get_user_catch(err);
- err |= restore_xstate_sig(buf, 1);
+ err |= fpu__restore_sig(buf, 1);
force_iret();
size_t frame_size,
void __user **fpstate)
{
+ struct fpu *fpu = ¤t->thread.fpu;
unsigned long sp;
/* Default to using normal stack */
ksig->ka.sa.sa_restorer)
sp = (unsigned long) ksig->ka.sa.sa_restorer;
- if (used_math()) {
+ if (fpu->fpstate_active) {
unsigned long fx_aligned, math_size;
- sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size);
+ sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
*fpstate = (struct _fpstate_ia32 __user *) sp;
- if (save_xstate_sig(*fpstate, (void __user *)fx_aligned,
+ if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
math_size) < 0)
return (void __user *) -1L;
}
+++ /dev/null
-/*
- * Compatibility mode system call entry point for x86-64.
- *
- * Copyright 2000-2002 Andi Kleen, SuSE Labs.
- */
-
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm-offsets.h>
-#include <asm/current.h>
-#include <asm/errno.h>
-#include <asm/ia32_unistd.h>
-#include <asm/thread_info.h>
-#include <asm/segment.h>
-#include <asm/irqflags.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-#include <linux/linkage.h>
-#include <linux/err.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE 0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysexit_audit ia32_ret_from_sys_call
-#define sysretl_audit ia32_ret_from_sys_call
-#endif
-
- .section .entry.text, "ax"
-
- /* clobbers %rax */
- .macro CLEAR_RREGS _r9=rax
- xorl %eax,%eax
- movq %rax,R11(%rsp)
- movq %rax,R10(%rsp)
- movq %\_r9,R9(%rsp)
- movq %rax,R8(%rsp)
- .endm
-
- /*
- * Reload arg registers from stack in case ptrace changed them.
- * We don't reload %eax because syscall_trace_enter() returned
- * the %rax value we should see. Instead, we just truncate that
- * value to 32 bits again as we did on entry from user mode.
- * If it's a new value set by user_regset during entry tracing,
- * this matches the normal truncation of the user-mode value.
- * If it's -1 to make us punt the syscall, then (u32)-1 is still
- * an appropriately invalid value.
- */
- .macro LOAD_ARGS32 _r9=0
- .if \_r9
- movl R9(%rsp),%r9d
- .endif
- movl RCX(%rsp),%ecx
- movl RDX(%rsp),%edx
- movl RSI(%rsp),%esi
- movl RDI(%rsp),%edi
- movl %eax,%eax /* zero extension */
- .endm
-
- .macro CFI_STARTPROC32 simple
- CFI_STARTPROC \simple
- CFI_UNDEFINED r8
- CFI_UNDEFINED r9
- CFI_UNDEFINED r10
- CFI_UNDEFINED r11
- CFI_UNDEFINED r12
- CFI_UNDEFINED r13
- CFI_UNDEFINED r14
- CFI_UNDEFINED r15
- .endm
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret32)
- swapgs
- sysretl
-ENDPROC(native_usergs_sysret32)
-
-ENTRY(native_irq_enable_sysexit)
- swapgs
- sti
- sysexit
-ENDPROC(native_irq_enable_sysexit)
-#endif
-
-/*
- * 32bit SYSENTER instruction entry.
- *
- * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
- * IF and VM in rflags are cleared (IOW: interrupts are off).
- * SYSENTER does not save anything on the stack,
- * and does not save old rip (!!!) and rflags.
- *
- * Arguments:
- * eax system call number
- * ebx arg1
- * ecx arg2
- * edx arg3
- * esi arg4
- * edi arg5
- * ebp user stack
- * 0(%ebp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_sysenter_target)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rsp,rbp
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- SWAPGS_UNSAFE_STACK
- movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %ebp, %ebp
- movl %eax, %eax
-
- movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
- CFI_REGISTER rip,r10
-
- /* Construct struct pt_regs on stack */
- pushq_cfi $__USER32_DS /* pt_regs->ss */
- pushq_cfi %rbp /* pt_regs->sp */
- CFI_REL_OFFSET rsp,0
- pushfq_cfi /* pt_regs->flags */
- pushq_cfi $__USER32_CS /* pt_regs->cs */
- pushq_cfi %r10 /* pt_regs->ip = thread_info->sysenter_return */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi_reg rax /* pt_regs->ax */
- cld
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- /*
- * no need to do an access_ok check here because rbp has been
- * 32bit zero extended
- */
- ASM_STAC
-1: movl (%rbp),%ebp
- _ASM_EXTABLE(1b,ia32_badarg)
- ASM_CLAC
-
- /*
- * Sysenter doesn't filter flags, so we need to clear NT
- * ourselves. To save a few cycles, we can check whether
- * NT was set instead of doing an unconditional popfq.
- */
- testl $X86_EFLAGS_NT,EFLAGS(%rsp)
- jnz sysenter_fix_flags
-sysenter_flags_fixed:
-
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- CFI_REMEMBER_STATE
- jnz sysenter_tracesys
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
-sysenter_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- movl %ebp,%r9d /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
-sysenter_dispatch:
- call *ia32_sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysexit_audit
-sysexit_from_sys_call:
- /*
- * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
- * NMI between STI and SYSEXIT has poorly specified behavior,
- * and and NMI followed by an IRQ with usergs is fatal. So
- * we just pretend we're using SYSEXIT but we really use
- * SYSRETL instead.
- *
- * This code path is still called 'sysexit' because it pairs
- * with 'sysenter' and it uses the SYSENTER calling convention.
- */
- andl $~TS_COMPAT,ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- movl RIP(%rsp),%ecx /* User %eip */
- CFI_REGISTER rip,rcx
- RESTORE_RSI_RDI
- xorl %edx,%edx /* avoid info leaks */
- xorq %r8,%r8
- xorq %r9,%r9
- xorq %r10,%r10
- movl EFLAGS(%rsp),%r11d /* User eflags */
- /*CFI_RESTORE rflags*/
- TRACE_IRQS_ON
-
- /*
- * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT,
- * since it avoids a dicey window with interrupts enabled.
- */
- movl RSP(%rsp),%esp
-
- /*
- * USERGS_SYSRET32 does:
- * gsbase = user's gs base
- * eip = ecx
- * rflags = r11
- * cs = __USER32_CS
- * ss = __USER_DS
- *
- * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
- *
- * pop %ebp
- * pop %edx
- * pop %ecx
- *
- * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
- * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's
- * address (already known to user code), and R12-R15 are
- * callee-saved and therefore don't contain any interesting
- * kernel data.
- */
- USERGS_SYSRET32
-
- CFI_RESTORE_STATE
-
-#ifdef CONFIG_AUDITSYSCALL
- .macro auditsys_entry_common
- movl %esi,%r8d /* 5th arg: 4th syscall arg */
- movl %ecx,%r9d /*swap with edx*/
- movl %edx,%ecx /* 4th arg: 3rd syscall arg */
- movl %r9d,%edx /* 3rd arg: 2nd syscall arg */
- movl %ebx,%esi /* 2nd arg: 1st syscall arg */
- movl %eax,%edi /* 1st arg: syscall number */
- call __audit_syscall_entry
- movl RAX(%rsp),%eax /* reload syscall number */
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
- movl %ebx,%edi /* reload 1st syscall arg */
- movl RCX(%rsp),%esi /* reload 2nd syscall arg */
- movl RDX(%rsp),%edx /* reload 3rd syscall arg */
- movl RSI(%rsp),%ecx /* reload 4th syscall arg */
- movl RDI(%rsp),%r8d /* reload 5th syscall arg */
- .endm
-
- .macro auditsys_exit exit
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz ia32_ret_from_sys_call
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- movl %eax,%esi /* second arg, syscall return value */
- cmpl $-MAX_ERRNO,%eax /* is it an error ? */
- jbe 1f
- movslq %eax, %rsi /* if error sign extend to 64 bits */
-1: setbe %al /* 1 if error, 0 if not */
- movzbl %al,%edi /* zero-extend that into %edi */
- call __audit_syscall_exit
- movq RAX(%rsp),%rax /* reload syscall return value */
- movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz \exit
- CLEAR_RREGS
- jmp int_with_check
- .endm
-
-sysenter_auditsys:
- auditsys_entry_common
- movl %ebp,%r9d /* reload 6th syscall arg */
- jmp sysenter_dispatch
-
-sysexit_audit:
- auditsys_exit sysexit_from_sys_call
-#endif
-
-sysenter_fix_flags:
- pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
- popfq_cfi
- jmp sysenter_flags_fixed
-
-sysenter_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz sysenter_auditsys
-#endif
- SAVE_EXTRA_REGS
- CLEAR_RREGS
- movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
- jmp sysenter_do_call
- CFI_ENDPROC
-ENDPROC(ia32_sysenter_target)
-
-/*
- * 32bit SYSCALL instruction entry.
- *
- * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
- * then loads new ss, cs, and rip from previously programmed MSRs.
- * rflags gets masked by a value from another MSR (so CLD and CLAC
- * are not needed). SYSCALL does not save anything on the stack
- * and does not change rsp.
- *
- * Note: rflags saving+masking-with-MSR happens only in Long mode
- * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it).
- * Don't get confused: rflags saving+masking depends on Long Mode Active bit
- * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
- * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
- *
- * Arguments:
- * eax system call number
- * ecx return address
- * ebx arg1
- * ebp arg2 (note: not saved in the stack frame, should not be touched)
- * edx arg3
- * esi arg4
- * edi arg5
- * esp user stack
- * 0(%esp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_cstar_target)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rip,rcx
- /*CFI_REGISTER rflags,r11*/
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- SWAPGS_UNSAFE_STACK
- movl %esp,%r8d
- CFI_REGISTER rsp,r8
- movq PER_CPU_VAR(kernel_stack),%rsp
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %eax,%eax
-
- /* Construct struct pt_regs on stack */
- pushq_cfi $__USER32_DS /* pt_regs->ss */
- pushq_cfi %r8 /* pt_regs->sp */
- CFI_REL_OFFSET rsp,0
- pushq_cfi %r11 /* pt_regs->flags */
- pushq_cfi $__USER32_CS /* pt_regs->cs */
- pushq_cfi %rcx /* pt_regs->ip */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rbp /* pt_regs->cx */
- movl %ebp,%ecx
- pushq_cfi_reg rax /* pt_regs->ax */
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- /*
- * no need to do an access_ok check here because r8 has been
- * 32bit zero extended
- */
- ASM_STAC
-1: movl (%r8),%r9d
- _ASM_EXTABLE(1b,ia32_badarg)
- ASM_CLAC
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- CFI_REMEMBER_STATE
- jnz cstar_tracesys
- cmpq $IA32_NR_syscalls-1,%rax
- ja ia32_badsys
-cstar_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- /* r9 already loaded */ /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
-cstar_dispatch:
- call *ia32_sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysretl_audit
-sysretl_from_sys_call:
- andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- RESTORE_RSI_RDI_RDX
- movl RIP(%rsp),%ecx
- CFI_REGISTER rip,rcx
- movl EFLAGS(%rsp),%r11d
- /*CFI_REGISTER rflags,r11*/
- xorq %r10,%r10
- xorq %r9,%r9
- xorq %r8,%r8
- TRACE_IRQS_ON
- movl RSP(%rsp),%esp
- CFI_RESTORE rsp
- /*
- * 64bit->32bit SYSRET restores eip from ecx,
- * eflags from r11 (but RF and VM bits are forced to 0),
- * cs and ss are loaded from MSRs.
- * (Note: 32bit->32bit SYSRET is different: since r11
- * does not exist, it merely sets eflags.IF=1).
- *
- * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
- * descriptor is not reinitialized. This means that we must
- * avoid SYSRET with SS == NULL, which could happen if we schedule,
- * exit the kernel, and re-enter using an interrupt vector. (All
- * interrupt entries on x86_64 set SS to NULL.) We prevent that
- * from happening by reloading SS in __switch_to.
- */
- USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-cstar_auditsys:
- CFI_RESTORE_STATE
- movl %r9d,R9(%rsp) /* register to be clobbered by call */
- auditsys_entry_common
- movl R9(%rsp),%r9d /* reload 6th syscall arg */
- jmp cstar_dispatch
-
-sysretl_audit:
- auditsys_exit sysretl_from_sys_call
-#endif
-
-cstar_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz cstar_auditsys
-#endif
- xchgl %r9d,%ebp
- SAVE_EXTRA_REGS
- CLEAR_RREGS r9
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- xchgl %ebp,%r9d
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
- jmp cstar_do_call
-END(ia32_cstar_target)
-
-ia32_badarg:
- ASM_CLAC
- movq $-EFAULT,%rax
- jmp ia32_sysret
- CFI_ENDPROC
-
-/*
- * Emulated IA32 system calls via int 0x80.
- *
- * Arguments:
- * eax system call number
- * ebx arg1
- * ecx arg2
- * edx arg3
- * esi arg4
- * edi arg5
- * ebp arg6 (note: not saved in the stack frame, should not be touched)
- *
- * Notes:
- * Uses the same stack frame as the x86-64 version.
- * All registers except eax must be saved (but ptrace may violate that).
- * Arguments are zero extended. For system calls that want sign extension and
- * take long arguments a wrapper is needed. Most calls can just be called
- * directly.
- * Assumes it is only called from user space and entered with interrupts off.
- */
-
-ENTRY(ia32_syscall)
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,5*8
- /*CFI_REL_OFFSET ss,4*8 */
- CFI_REL_OFFSET rsp,3*8
- /*CFI_REL_OFFSET rflags,2*8 */
- /*CFI_REL_OFFSET cs,1*8 */
- CFI_REL_OFFSET rip,0*8
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- PARAVIRT_ADJUST_EXCEPTION_FRAME
- SWAPGS
- ENABLE_INTERRUPTS(CLBR_NONE)
-
- /* Zero-extending 32-bit regs, do not remove */
- movl %eax,%eax
-
- /* Construct struct pt_regs on stack (iret frame is already on stack) */
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi_reg rax /* pt_regs->ax */
- cld
- sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 10*8
-
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz ia32_tracesys
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
-ia32_do_call:
- /* 32bit syscall -> 64bit C ABI argument conversion */
- movl %edi,%r8d /* arg5 */
- movl %ebp,%r9d /* arg6 */
- xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
- movl %ebx,%edi /* arg1 */
- movl %edx,%edx /* arg3 (zero extension) */
- call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
-ia32_sysret:
- movq %rax,RAX(%rsp)
-ia32_ret_from_sys_call:
- CLEAR_RREGS
- jmp int_ret_from_sys_call
-
-ia32_tracesys:
- SAVE_EXTRA_REGS
- CLEAR_RREGS
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
- movq %rsp,%rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
- RESTORE_EXTRA_REGS
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
- jmp ia32_do_call
-END(ia32_syscall)
-
-ia32_badsys:
- movq $0,ORIG_RAX(%rsp)
- movq $-ENOSYS,%rax
- jmp ia32_sysret
-
- CFI_ENDPROC
-
- .macro PTREGSCALL label, func
- ALIGN
-GLOBAL(\label)
- leaq \func(%rip),%rax
- jmp ia32_ptregs_common
- .endm
-
- CFI_STARTPROC32
-
- PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
- PTREGSCALL stub32_sigreturn, sys32_sigreturn
- PTREGSCALL stub32_fork, sys_fork
- PTREGSCALL stub32_vfork, sys_vfork
-
- ALIGN
-GLOBAL(stub32_clone)
- leaq sys_clone(%rip),%rax
- mov %r8, %rcx
- jmp ia32_ptregs_common
-
- ALIGN
-ia32_ptregs_common:
- CFI_ENDPROC
- CFI_STARTPROC32 simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,SIZEOF_PTREGS
- CFI_REL_OFFSET rax,RAX
- CFI_REL_OFFSET rcx,RCX
- CFI_REL_OFFSET rdx,RDX
- CFI_REL_OFFSET rsi,RSI
- CFI_REL_OFFSET rdi,RDI
- CFI_REL_OFFSET rip,RIP
-/* CFI_REL_OFFSET cs,CS*/
-/* CFI_REL_OFFSET rflags,EFLAGS*/
- CFI_REL_OFFSET rsp,RSP
-/* CFI_REL_OFFSET ss,SS*/
- SAVE_EXTRA_REGS 8
- call *%rax
- RESTORE_EXTRA_REGS 8
- ret
- CFI_ENDPROC
-END(ia32_ptregs_common)
.endm
#endif
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
.long \orig - .
.long \alt - .
.byte \pad_len
.endm
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
.macro ALTERNATIVE oldinstr, newinstr, feature
140:
\oldinstr
*/
#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
140:
\oldinstr
u8 padlen; /* length of build-time padding */
} __packed;
+/*
+ * Debug flag that can be tested to see whether alternative
+ * instructions were patched in already:
+ */
+extern int alternatives_patched;
+
extern void alternative_instructions(void);
extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
return 0;
}
+static inline bool amd_gart_present(void)
+{
+ /* GART present only on Fam15h, upto model 0fh */
+ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+ (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
+ return true;
+
+ return false;
+}
+
#else
#define amd_nb_num(x) 0
#define amd_nb_has_feature(x) false
#define node_to_amd_nb(x) NULL
+#define amd_gart_present(x) false
#endif
entering_irq();
}
+static inline void ipi_entering_ack_irq(void)
+{
+ ack_APIC_irq();
+ irq_enter();
+}
+
static inline void exiting_irq(void)
{
irq_exit();
_ASM_ALIGN ; \
_ASM_PTR (entry); \
.popsection
+
+.macro ALIGN_DESTINATION
+ /* check for bad alignment of destination */
+ movl %edi,%ecx
+ andl $7,%ecx
+ jz 102f /* already aligned */
+ subl $8,%ecx
+ negl %ecx
+ subl %ecx,%edx
+100: movb (%rsi),%al
+101: movb %al,(%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz 100b
+102:
+ .section .fixup,"ax"
+103: addl %ecx,%edx /* ecx is zerorest also */
+ jmp copy_user_handle_tail
+ .previous
+
+ _ASM_EXTABLE(100b,103b)
+ _ASM_EXTABLE(101b,103b)
+ .endm
+
#else
# define _ASM_EXTABLE(from,to) \
" .pushsection \"__ex_table\",\"a\"\n" \
*
* Atomically reads the value of @v.
*/
-static inline int atomic_read(const atomic_t *v)
+static __always_inline int atomic_read(const atomic_t *v)
{
return ACCESS_ONCE((v)->counter);
}
*
* Atomically sets the value of @v to @i.
*/
-static inline void atomic_set(atomic_t *v, int i)
+static __always_inline void atomic_set(atomic_t *v, int i)
{
v->counter = i;
}
*
* Atomically adds @i to @v.
*/
-static inline void atomic_add(int i, atomic_t *v)
+static __always_inline void atomic_add(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "addl %1,%0"
: "+m" (v->counter)
*
* Atomically subtracts @i from @v.
*/
-static inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void atomic_sub(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "subl %1,%0"
: "+m" (v->counter)
* true if the result is zero, or false for all
* other cases.
*/
-static inline int atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
}
*
* Atomically increments @v by 1.
*/
-static inline void atomic_inc(atomic_t *v)
+static __always_inline void atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
: "+m" (v->counter));
*
* Atomically decrements @v by 1.
*/
-static inline void atomic_dec(atomic_t *v)
+static __always_inline void atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
: "+m" (v->counter));
* returns true if the result is 0, or false for all other
* cases.
*/
-static inline int atomic_dec_and_test(atomic_t *v)
+static __always_inline int atomic_dec_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
}
* and returns true if the result is zero, or false for all
* other cases.
*/
-static inline int atomic_inc_and_test(atomic_t *v)
+static __always_inline int atomic_inc_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
}
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
-static inline int atomic_add_negative(int i, atomic_t *v)
+static __always_inline int atomic_add_negative(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
}
*
* Atomically adds @i to @v and returns @i + @v
*/
-static inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int atomic_add_return(int i, atomic_t *v)
{
return i + xadd(&v->counter, i);
}
*
* Atomically subtracts @i from @v and returns @v - @i
*/
-static inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int atomic_sub_return(int i, atomic_t *v)
{
return atomic_add_return(-i, v);
}
#define atomic_inc_return(v) (atomic_add_return(1, v))
#define atomic_dec_return(v) (atomic_sub_return(1, v))
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
{
return cmpxchg(&v->counter, old, new);
}
* Atomically adds @a to @v, so long as @v was not already @u.
* Returns the old value of @v.
*/
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
{
int c, old;
c = atomic_read(v);
* Atomically adds 1 to @v
* Returns the new value of @u
*/
-static inline short int atomic_inc_short(short int *v)
+static __always_inline short int atomic_inc_short(short int *v)
{
asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
return *v;
*
* Atomically adds @i to @v.
*/
-static inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void atomic64_add(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "addq %1,%0"
: "=m" (v->counter)
*
* Atomically increments @v by 1.
*/
-static inline void atomic64_inc(atomic64_t *v)
+static __always_inline void atomic64_inc(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "incq %0"
: "=m" (v->counter)
*
* Atomically decrements @v by 1.
*/
-static inline void atomic64_dec(atomic64_t *v)
+static __always_inline void atomic64_dec(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "decq %0"
: "=m" (v->counter)
*
* Atomically adds @i to @v and returns @i + @v
*/
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long atomic64_add_return(long i, atomic64_t *v)
{
return i + xadd(&v->counter, i);
}
#define smp_mb() mb()
#define smp_rmb() dma_rmb()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* !SMP */
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
#endif /* SMP */
#define read_barrier_depends() do { } while (0)
/*
* The set_memory_* API can be used to change various attributes of a virtual
* address range. The attributes include:
- * Cachability : UnCached, WriteCombining, WriteBack
+ * Cachability : UnCached, WriteCombining, WriteThrough, WriteBack
* Executability : eXeutable, NoteXecutable
* Read/Write : ReadOnly, ReadWrite
* Presence : NotPresent
int _set_memory_uc(unsigned long addr, int numpages);
int _set_memory_wc(unsigned long addr, int numpages);
+int _set_memory_wt(unsigned long addr, int numpages);
int _set_memory_wb(unsigned long addr, int numpages);
int set_memory_uc(unsigned long addr, int numpages);
int set_memory_wc(unsigned long addr, int numpages);
+int set_memory_wt(unsigned long addr, int numpages);
int set_memory_wb(unsigned long addr, int numpages);
int set_memory_x(unsigned long addr, int numpages);
int set_memory_nx(unsigned long addr, int numpages);
int set_memory_array_uc(unsigned long *addr, int addrinarray);
int set_memory_array_wc(unsigned long *addr, int addrinarray);
+int set_memory_array_wt(unsigned long *addr, int addrinarray);
int set_memory_array_wb(unsigned long *addr, int addrinarray);
int set_pages_array_uc(struct page **pages, int addrinarray);
int set_pages_array_wc(struct page **pages, int addrinarray);
+int set_pages_array_wt(struct page **pages, int addrinarray);
int set_pages_array_wb(struct page **pages, int addrinarray);
/*
+++ /dev/null
-/*
-
- x86 function call convention, 64-bit:
- -------------------------------------
- arguments | callee-saved | extra caller-saved | return
- [callee-clobbered] | | [callee-clobbered] |
- ---------------------------------------------------------------------------
- rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11 | rax, rdx [**]
-
- ( rsp is obviously invariant across normal function calls. (gcc can 'merge'
- functions when it sees tail-call optimization possibilities) rflags is
- clobbered. Leftover arguments are passed over the stack frame.)
-
- [*] In the frame-pointers case rbp is fixed to the stack frame.
-
- [**] for struct return values wider than 64 bits the return convention is a
- bit more complex: up to 128 bits width we return small structures
- straight in rax, rdx. For structures larger than that (3 words or
- larger) the caller puts a pointer to an on-stack return struct
- [allocated in the caller's stack frame] into the first argument - i.e.
- into rdi. All other arguments shift up by one in this case.
- Fortunately this case is rare in the kernel.
-
-For 32-bit we have the following conventions - kernel is built with
--mregparm=3 and -freg-struct-return:
-
- x86 function calling convention, 32-bit:
- ----------------------------------------
- arguments | callee-saved | extra caller-saved | return
- [callee-clobbered] | | [callee-clobbered] |
- -------------------------------------------------------------------------
- eax edx ecx | ebx edi esi ebp [*] | <none> | eax, edx [**]
-
- ( here too esp is obviously invariant across normal function calls. eflags
- is clobbered. Leftover arguments are passed over the stack frame. )
-
- [*] In the frame-pointers case ebp is fixed to the stack frame.
-
- [**] We build with -freg-struct-return, which on 32-bit means similar
- semantics as on 64-bit: edx can be used for a second return value
- (i.e. covering integer and structure sizes up to 64 bits) - after that
- it gets more complex and more expensive: 3-word or larger struct returns
- get done in the caller's frame and the pointer to the return struct goes
- into regparm0, i.e. eax - the other arguments shift up and the
- function's register parameters degenerate to regparm=2 in essence.
-
-*/
-
-#include <asm/dwarf2.h>
-
-#ifdef CONFIG_X86_64
-
-/*
- * 64-bit system call stack frame layout defines and helpers,
- * for assembly code:
- */
-
-/* The layout forms the "struct pt_regs" on the stack: */
-/*
- * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
- * unless syscall needs a complete, fully filled "struct pt_regs".
- */
-#define R15 0*8
-#define R14 1*8
-#define R13 2*8
-#define R12 3*8
-#define RBP 4*8
-#define RBX 5*8
-/* These regs are callee-clobbered. Always saved on kernel entry. */
-#define R11 6*8
-#define R10 7*8
-#define R9 8*8
-#define R8 9*8
-#define RAX 10*8
-#define RCX 11*8
-#define RDX 12*8
-#define RSI 13*8
-#define RDI 14*8
-/*
- * On syscall entry, this is syscall#. On CPU exception, this is error code.
- * On hw interrupt, it's IRQ number:
- */
-#define ORIG_RAX 15*8
-/* Return frame for iretq */
-#define RIP 16*8
-#define CS 17*8
-#define EFLAGS 18*8
-#define RSP 19*8
-#define SS 20*8
-
-#define SIZEOF_PTREGS 21*8
-
- .macro ALLOC_PT_GPREGS_ON_STACK addskip=0
- subq $15*8+\addskip, %rsp
- CFI_ADJUST_CFA_OFFSET 15*8+\addskip
- .endm
-
- .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
- .if \r11
- movq_cfi r11, 6*8+\offset
- .endif
- .if \r8910
- movq_cfi r10, 7*8+\offset
- movq_cfi r9, 8*8+\offset
- movq_cfi r8, 9*8+\offset
- .endif
- .if \rax
- movq_cfi rax, 10*8+\offset
- .endif
- .if \rcx
- movq_cfi rcx, 11*8+\offset
- .endif
- movq_cfi rdx, 12*8+\offset
- movq_cfi rsi, 13*8+\offset
- movq_cfi rdi, 14*8+\offset
- .endm
- .macro SAVE_C_REGS offset=0
- SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
- .endm
- .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0
- SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1
- .endm
- .macro SAVE_C_REGS_EXCEPT_R891011
- SAVE_C_REGS_HELPER 0, 1, 1, 0, 0
- .endm
- .macro SAVE_C_REGS_EXCEPT_RCX_R891011
- SAVE_C_REGS_HELPER 0, 1, 0, 0, 0
- .endm
- .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11
- SAVE_C_REGS_HELPER 0, 0, 0, 1, 0
- .endm
-
- .macro SAVE_EXTRA_REGS offset=0
- movq_cfi r15, 0*8+\offset
- movq_cfi r14, 1*8+\offset
- movq_cfi r13, 2*8+\offset
- movq_cfi r12, 3*8+\offset
- movq_cfi rbp, 4*8+\offset
- movq_cfi rbx, 5*8+\offset
- .endm
- .macro SAVE_EXTRA_REGS_RBP offset=0
- movq_cfi rbp, 4*8+\offset
- .endm
-
- .macro RESTORE_EXTRA_REGS offset=0
- movq_cfi_restore 0*8+\offset, r15
- movq_cfi_restore 1*8+\offset, r14
- movq_cfi_restore 2*8+\offset, r13
- movq_cfi_restore 3*8+\offset, r12
- movq_cfi_restore 4*8+\offset, rbp
- movq_cfi_restore 5*8+\offset, rbx
- .endm
-
- .macro ZERO_EXTRA_REGS
- xorl %r15d, %r15d
- xorl %r14d, %r14d
- xorl %r13d, %r13d
- xorl %r12d, %r12d
- xorl %ebp, %ebp
- xorl %ebx, %ebx
- .endm
-
- .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
- .if \rstor_r11
- movq_cfi_restore 6*8, r11
- .endif
- .if \rstor_r8910
- movq_cfi_restore 7*8, r10
- movq_cfi_restore 8*8, r9
- movq_cfi_restore 9*8, r8
- .endif
- .if \rstor_rax
- movq_cfi_restore 10*8, rax
- .endif
- .if \rstor_rcx
- movq_cfi_restore 11*8, rcx
- .endif
- .if \rstor_rdx
- movq_cfi_restore 12*8, rdx
- .endif
- movq_cfi_restore 13*8, rsi
- movq_cfi_restore 14*8, rdi
- .endm
- .macro RESTORE_C_REGS
- RESTORE_C_REGS_HELPER 1,1,1,1,1
- .endm
- .macro RESTORE_C_REGS_EXCEPT_RAX
- RESTORE_C_REGS_HELPER 0,1,1,1,1
- .endm
- .macro RESTORE_C_REGS_EXCEPT_RCX
- RESTORE_C_REGS_HELPER 1,0,1,1,1
- .endm
- .macro RESTORE_C_REGS_EXCEPT_R11
- RESTORE_C_REGS_HELPER 1,1,0,1,1
- .endm
- .macro RESTORE_C_REGS_EXCEPT_RCX_R11
- RESTORE_C_REGS_HELPER 1,0,0,1,1
- .endm
- .macro RESTORE_RSI_RDI
- RESTORE_C_REGS_HELPER 0,0,0,0,0
- .endm
- .macro RESTORE_RSI_RDI_RDX
- RESTORE_C_REGS_HELPER 0,0,0,0,1
- .endm
-
- .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
- addq $15*8+\addskip, %rsp
- CFI_ADJUST_CFA_OFFSET -(15*8+\addskip)
- .endm
-
- .macro icebp
- .byte 0xf1
- .endm
-
-#else /* CONFIG_X86_64 */
-
-/*
- * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
- * are different from the entry_32.S versions in not changing the segment
- * registers. So only suitable for in kernel use, not when transitioning
- * from or to user space. The resulting stack frame is not a standard
- * pt_regs frame. The main use case is calling C code from assembler
- * when all the registers need to be preserved.
- */
-
- .macro SAVE_ALL
- pushl_cfi_reg eax
- pushl_cfi_reg ebp
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg edx
- pushl_cfi_reg ecx
- pushl_cfi_reg ebx
- .endm
-
- .macro RESTORE_ALL
- popl_cfi_reg ebx
- popl_cfi_reg ecx
- popl_cfi_reg edx
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi_reg ebp
- popl_cfi_reg eax
- .endm
-
-#endif /* CONFIG_X86_64 */
-
#include <linux/compiler.h>
#include <asm/alternative.h> /* Provides LOCK_PREFIX */
-#define __HAVE_ARCH_CMPXCHG 1
-
/*
* Non-existant functions to indicate usage errors at link time
* (or compile-time if the compiler implements __compiletime_error().
#include <linux/kernel.h>
#include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <crypto/b128ops.h>
typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
#define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL)
-static inline void *
+void *
dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, struct dma_attrs *attrs)
-{
- struct dma_map_ops *ops = get_dma_ops(dev);
- void *memory;
-
- gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
- if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
- return memory;
-
- if (!dev)
- dev = &x86_dma_fallback_dev;
-
- if (!is_device_dma_capable(dev))
- return NULL;
-
- if (!ops->alloc)
- return NULL;
-
- memory = ops->alloc(dev, size, dma_handle,
- dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
- debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
-
- return memory;
-}
+ gfp_t gfp, struct dma_attrs *attrs);
#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
-static inline void dma_free_attrs(struct device *dev, size_t size,
- void *vaddr, dma_addr_t bus,
- struct dma_attrs *attrs)
-{
- struct dma_map_ops *ops = get_dma_ops(dev);
-
- WARN_ON(irqs_disabled()); /* for portability */
-
- if (dma_release_from_coherent(dev, get_order(size), vaddr))
- return;
-
- debug_dma_free_coherent(dev, size, vaddr, bus);
- if (ops->free)
- ops->free(dev, size, vaddr, bus, attrs);
-}
+void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t bus,
+ struct dma_attrs *attrs);
#endif
+++ /dev/null
-#ifndef _ASM_X86_DWARF2_H
-#define _ASM_X86_DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
- * Macros for dwarf2 CFI unwind table entries.
- * See "as.info" for details on these pseudo ops. Unfortunately
- * they are only supported in very new binutils, so define them
- * away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-#define CFI_ESCAPE .cfi_escape
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
- /*
- * Emit CFI data in .debug_frame sections, not .eh_frame sections.
- * The latter we currently just discard since we don't do DWARF
- * unwinding at runtime. So only the offline DWARF information is
- * useful to anyone. Note we should not use this directive if this
- * file is used in the vDSO assembly, or if vmlinux.lds.S gets
- * changed so it doesn't discard .eh_frame.
- */
- .cfi_sections .debug_frame
-#endif
-
-#else
-
-/*
- * Due to the structure of pre-exisiting code, don't use assembler line
- * comment character # to ignore the arguments. Instead, use a dummy macro.
- */
-.macro cfi_ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC cfi_ignore
-#define CFI_ENDPROC cfi_ignore
-#define CFI_DEF_CFA cfi_ignore
-#define CFI_DEF_CFA_REGISTER cfi_ignore
-#define CFI_DEF_CFA_OFFSET cfi_ignore
-#define CFI_ADJUST_CFA_OFFSET cfi_ignore
-#define CFI_OFFSET cfi_ignore
-#define CFI_REL_OFFSET cfi_ignore
-#define CFI_REGISTER cfi_ignore
-#define CFI_RESTORE cfi_ignore
-#define CFI_REMEMBER_STATE cfi_ignore
-#define CFI_RESTORE_STATE cfi_ignore
-#define CFI_UNDEFINED cfi_ignore
-#define CFI_ESCAPE cfi_ignore
-#define CFI_SIGNAL_FRAME cfi_ignore
-
-#endif
-
-/*
- * An attempt to make CFI annotations more or less
- * correct and shorter. It is implied that you know
- * what you're doing if you use them.
- */
-#ifdef __ASSEMBLY__
-#ifdef CONFIG_X86_64
- .macro pushq_cfi reg
- pushq \reg
- CFI_ADJUST_CFA_OFFSET 8
- .endm
-
- .macro pushq_cfi_reg reg
- pushq %\reg
- CFI_ADJUST_CFA_OFFSET 8
- CFI_REL_OFFSET \reg, 0
- .endm
-
- .macro popq_cfi reg
- popq \reg
- CFI_ADJUST_CFA_OFFSET -8
- .endm
-
- .macro popq_cfi_reg reg
- popq %\reg
- CFI_ADJUST_CFA_OFFSET -8
- CFI_RESTORE \reg
- .endm
-
- .macro pushfq_cfi
- pushfq
- CFI_ADJUST_CFA_OFFSET 8
- .endm
-
- .macro popfq_cfi
- popfq
- CFI_ADJUST_CFA_OFFSET -8
- .endm
-
- .macro movq_cfi reg offset=0
- movq %\reg, \offset(%rsp)
- CFI_REL_OFFSET \reg, \offset
- .endm
-
- .macro movq_cfi_restore offset reg
- movq \offset(%rsp), %\reg
- CFI_RESTORE \reg
- .endm
-#else /*!CONFIG_X86_64*/
- .macro pushl_cfi reg
- pushl \reg
- CFI_ADJUST_CFA_OFFSET 4
- .endm
-
- .macro pushl_cfi_reg reg
- pushl %\reg
- CFI_ADJUST_CFA_OFFSET 4
- CFI_REL_OFFSET \reg, 0
- .endm
-
- .macro popl_cfi reg
- popl \reg
- CFI_ADJUST_CFA_OFFSET -4
- .endm
-
- .macro popl_cfi_reg reg
- popl %\reg
- CFI_ADJUST_CFA_OFFSET -4
- CFI_RESTORE \reg
- .endm
-
- .macro pushfl_cfi
- pushfl
- CFI_ADJUST_CFA_OFFSET 4
- .endm
-
- .macro popfl_cfi
- popfl
- CFI_ADJUST_CFA_OFFSET -4
- .endm
-
- .macro movl_cfi reg offset=0
- movl %\reg, \offset(%esp)
- CFI_REL_OFFSET \reg, \offset
- .endm
-
- .macro movl_cfi_restore offset reg
- movl \offset(%esp), %\reg
- CFI_RESTORE \reg
- .endm
-#endif /*!CONFIG_X86_64*/
-#endif /*__ASSEMBLY__*/
-
-#endif /* _ASM_X86_DWARF2_H */
#ifndef _ASM_X86_EFI_H
#define _ASM_X86_EFI_H
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/pgtable.h>
/*
#ifdef CONFIG_HAVE_KVM
BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
smp_kvm_posted_intr_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
+ smp_kvm_posted_intr_wakeup_ipi)
#endif
/*
BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
#endif
+#ifdef CONFIG_X86_MCE_AMD
+BUILD_INTERRUPT(deferred_error_interrupt, DEFERRED_ERROR_VECTOR)
+#endif
#endif
+++ /dev/null
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _FPU_INTERNAL_H
-#define _FPU_INTERNAL_H
-
-#include <linux/kernel_stat.h>
-#include <linux/regset.h>
-#include <linux/compat.h>
-#include <linux/slab.h>
-#include <asm/asm.h>
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/uaccess.h>
-#include <asm/xsave.h>
-#include <asm/smap.h>
-
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-struct ksignal;
-int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
- compat_sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct ksignal *ksig,
- compat_sigset_t *set, struct pt_regs *regs);
-#else
-# define user_i387_ia32_struct user_i387_struct
-# define user32_fxsr_struct user_fxsr_struct
-# define ia32_setup_frame __setup_frame
-# define ia32_setup_rt_frame __setup_rt_frame
-#endif
-
-extern unsigned int mxcsr_feature_mask;
-extern void fpu_init(void);
-extern void eager_fpu_init(void);
-
-DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
-
-extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
- struct task_struct *tsk);
-extern void convert_to_fxsr(struct task_struct *tsk,
- const struct user_i387_ia32_struct *env);
-
-extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
- xstateregs_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
- xstateregs_set;
-
-/*
- * xstateregs_active == fpregs_active. Please refer to the comment
- * at the definition of fpregs_active.
- */
-#define xstateregs_active fpregs_active
-
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-/*
- * Must be run with preemption disabled: this clears the fpu_owner_task,
- * on this CPU.
- *
- * This will disable any lazy FPU state restore of the current FPU state,
- * but if the current thread owns the FPU, it will still be saved by.
- */
-static inline void __cpu_disable_lazy_restore(unsigned int cpu)
-{
- per_cpu(fpu_owner_task, cpu) = NULL;
-}
-
-/*
- * Used to indicate that the FPU state in memory is newer than the FPU
- * state in registers, and the FPU state should be reloaded next time the
- * task is run. Only safe on the current task, or non-running tasks.
- */
-static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk)
-{
- tsk->thread.fpu.last_cpu = ~0;
-}
-
-static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
-{
- return new == this_cpu_read_stable(fpu_owner_task) &&
- cpu == new->thread.fpu.last_cpu;
-}
-
-static inline int is_ia32_compat_frame(void)
-{
- return config_enabled(CONFIG_IA32_EMULATION) &&
- test_thread_flag(TIF_IA32);
-}
-
-static inline int is_ia32_frame(void)
-{
- return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
-}
-
-static inline int is_x32_frame(void)
-{
- return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
-}
-
-#define X87_FSW_ES (1 << 7) /* Exception Summary */
-
-static __always_inline __pure bool use_eager_fpu(void)
-{
- return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
-}
-
-static __always_inline __pure bool use_xsaveopt(void)
-{
- return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
-}
-
-static __always_inline __pure bool use_xsave(void)
-{
- return static_cpu_has_safe(X86_FEATURE_XSAVE);
-}
-
-static __always_inline __pure bool use_fxsr(void)
-{
- return static_cpu_has_safe(X86_FEATURE_FXSR);
-}
-
-static inline void fx_finit(struct i387_fxsave_struct *fx)
-{
- fx->cwd = 0x37f;
- fx->mxcsr = MXCSR_DEFAULT;
-}
-
-extern void __sanitize_i387_state(struct task_struct *);
-
-static inline void sanitize_i387_state(struct task_struct *tsk)
-{
- if (!use_xsaveopt())
- return;
- __sanitize_i387_state(tsk);
-}
-
-#define user_insn(insn, output, input...) \
-({ \
- int err; \
- asm volatile(ASM_STAC "\n" \
- "1:" #insn "\n\t" \
- "2: " ASM_CLAC "\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err), output \
- : "0"(0), input); \
- err; \
-})
-
-#define check_insn(insn, output, input...) \
-({ \
- int err; \
- asm volatile("1:" #insn "\n\t" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err), output \
- : "0"(0), input); \
- err; \
-})
-
-static inline int fsave_user(struct i387_fsave_struct __user *fx)
-{
- return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
-}
-
-static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
-{
- if (config_enabled(CONFIG_X86_32))
- return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
- else if (config_enabled(CONFIG_AS_FXSAVEQ))
- return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
-
- /* See comment in fpu_fxsave() below. */
- return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
-}
-
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
- if (config_enabled(CONFIG_X86_32))
- return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
- else if (config_enabled(CONFIG_AS_FXSAVEQ))
- return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
- /* See comment in fpu_fxsave() below. */
- return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
- "m" (*fx));
-}
-
-static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
-{
- if (config_enabled(CONFIG_X86_32))
- return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
- else if (config_enabled(CONFIG_AS_FXSAVEQ))
- return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
- /* See comment in fpu_fxsave() below. */
- return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
- "m" (*fx));
-}
-
-static inline int frstor_checking(struct i387_fsave_struct *fx)
-{
- return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int frstor_user(struct i387_fsave_struct __user *fx)
-{
- return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
- if (config_enabled(CONFIG_X86_32))
- asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
- else if (config_enabled(CONFIG_AS_FXSAVEQ))
- asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave));
- else {
- /* Using "rex64; fxsave %0" is broken because, if the memory
- * operand uses any extended registers for addressing, a second
- * REX prefix will be generated (to the assembler, rex64
- * followed by semicolon is a separate instruction), and hence
- * the 64-bitness is lost.
- *
- * Using "fxsaveq %0" would be the ideal choice, but is only
- * supported starting with gas 2.16.
- *
- * Using, as a workaround, the properly prefixed form below
- * isn't accepted by any binutils version so far released,
- * complaining that the same type of prefix is used twice if
- * an extended register is needed for addressing (fix submitted
- * to mainline 2005-11-21).
- *
- * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
- *
- * This, however, we can work around by forcing the compiler to
- * select an addressing mode that doesn't require extended
- * registers.
- */
- asm volatile( "rex64/fxsave (%[fx])"
- : "=m" (fpu->state->fxsave)
- : [fx] "R" (&fpu->state->fxsave));
- }
-}
-
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact.
- */
-static inline int fpu_save_init(struct fpu *fpu)
-{
- if (use_xsave()) {
- fpu_xsave(fpu);
-
- /*
- * xsave header may indicate the init state of the FP.
- */
- if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
- return 1;
- } else if (use_fxsr()) {
- fpu_fxsave(fpu);
- } else {
- asm volatile("fnsave %[fx]; fwait"
- : [fx] "=m" (fpu->state->fsave));
- return 0;
- }
-
- /*
- * If exceptions are pending, we need to clear them so
- * that we don't randomly get exceptions later.
- *
- * FIXME! Is this perhaps only true for the old-style
- * irq13 case? Maybe we could leave the x87 state
- * intact otherwise?
- */
- if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
- asm volatile("fnclex");
- return 0;
- }
- return 1;
-}
-
-static inline int __save_init_fpu(struct task_struct *tsk)
-{
- return fpu_save_init(&tsk->thread.fpu);
-}
-
-static inline int fpu_restore_checking(struct fpu *fpu)
-{
- if (use_xsave())
- return fpu_xrstor_checking(&fpu->state->xsave);
- else if (use_fxsr())
- return fxrstor_checking(&fpu->state->fxsave);
- else
- return frstor_checking(&fpu->state->fsave);
-}
-
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
- /*
- * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
- * pending. Clear the x87 state here by setting it to fixed values.
- * "m" is a random variable that should be in L1.
- */
- if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
- asm volatile(
- "fnclex\n\t"
- "emms\n\t"
- "fildl %P[addr]" /* set F?P to defined value */
- : : [addr] "m" (tsk->thread.fpu.has_fpu));
- }
-
- return fpu_restore_checking(&tsk->thread.fpu);
-}
-
-/*
- * Software FPU state helpers. Careful: these need to
- * be preemption protection *and* they need to be
- * properly paired with the CR0.TS changes!
- */
-static inline int __thread_has_fpu(struct task_struct *tsk)
-{
- return tsk->thread.fpu.has_fpu;
-}
-
-/* Must be paired with an 'stts' after! */
-static inline void __thread_clear_has_fpu(struct task_struct *tsk)
-{
- tsk->thread.fpu.has_fpu = 0;
- this_cpu_write(fpu_owner_task, NULL);
-}
-
-/* Must be paired with a 'clts' before! */
-static inline void __thread_set_has_fpu(struct task_struct *tsk)
-{
- tsk->thread.fpu.has_fpu = 1;
- this_cpu_write(fpu_owner_task, tsk);
-}
-
-/*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
- * These generally need preemption protection to work,
- * do try to avoid using these on their own.
- */
-static inline void __thread_fpu_end(struct task_struct *tsk)
-{
- __thread_clear_has_fpu(tsk);
- if (!use_eager_fpu())
- stts();
-}
-
-static inline void __thread_fpu_begin(struct task_struct *tsk)
-{
- if (!use_eager_fpu())
- clts();
- __thread_set_has_fpu(tsk);
-}
-
-static inline void drop_fpu(struct task_struct *tsk)
-{
- /*
- * Forget coprocessor state..
- */
- preempt_disable();
- tsk->thread.fpu_counter = 0;
-
- if (__thread_has_fpu(tsk)) {
- /* Ignore delayed exceptions from user space */
- asm volatile("1: fwait\n"
- "2:\n"
- _ASM_EXTABLE(1b, 2b));
- __thread_fpu_end(tsk);
- }
-
- clear_stopped_child_used_math(tsk);
- preempt_enable();
-}
-
-static inline void restore_init_xstate(void)
-{
- if (use_xsave())
- xrstor_state(init_xstate_buf, -1);
- else
- fxrstor_checking(&init_xstate_buf->i387);
-}
-
-/*
- * Reset the FPU state in the eager case and drop it in the lazy case (later use
- * will reinit it).
- */
-static inline void fpu_reset_state(struct task_struct *tsk)
-{
- if (!use_eager_fpu())
- drop_fpu(tsk);
- else
- restore_init_xstate();
-}
-
-/*
- * FPU state switching for scheduling.
- *
- * This is a two-stage process:
- *
- * - switch_fpu_prepare() saves the old state and
- * sets the new state of the CR0.TS bit. This is
- * done within the context of the old process.
- *
- * - switch_fpu_finish() restores the new state as
- * necessary.
- */
-typedef struct { int preload; } fpu_switch_t;
-
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
-{
- fpu_switch_t fpu;
-
- /*
- * If the task has used the math, pre-load the FPU on xsave processors
- * or if the past 5 consecutive context-switches used math.
- */
- fpu.preload = tsk_used_math(new) &&
- (use_eager_fpu() || new->thread.fpu_counter > 5);
-
- if (__thread_has_fpu(old)) {
- if (!__save_init_fpu(old))
- task_disable_lazy_fpu_restore(old);
- else
- old->thread.fpu.last_cpu = cpu;
-
- /* But leave fpu_owner_task! */
- old->thread.fpu.has_fpu = 0;
-
- /* Don't change CR0.TS if we just switch! */
- if (fpu.preload) {
- new->thread.fpu_counter++;
- __thread_set_has_fpu(new);
- prefetch(new->thread.fpu.state);
- } else if (!use_eager_fpu())
- stts();
- } else {
- old->thread.fpu_counter = 0;
- task_disable_lazy_fpu_restore(old);
- if (fpu.preload) {
- new->thread.fpu_counter++;
- if (fpu_lazy_restore(new, cpu))
- fpu.preload = 0;
- else
- prefetch(new->thread.fpu.state);
- __thread_fpu_begin(new);
- }
- }
- return fpu;
-}
-
-/*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
- */
-static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
-{
- if (fpu.preload) {
- if (unlikely(restore_fpu_checking(new)))
- fpu_reset_state(new);
- }
-}
-
-/*
- * Signal frame handlers...
- */
-extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
-extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
-
-static inline int xstate_sigframe_size(void)
-{
- return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
-}
-
-static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
-{
- void __user *buf_fx = buf;
- int size = xstate_sigframe_size();
-
- if (ia32_frame && use_fxsr()) {
- buf_fx = buf + sizeof(struct i387_fsave_struct);
- size += sizeof(struct i387_fsave_struct);
- }
-
- return __restore_xstate_sig(buf, buf_fx, size);
-}
-
-/*
- * Needs to be preemption-safe.
- *
- * NOTE! user_fpu_begin() must be used only immediately before restoring
- * the save state. It does not do any saving/restoring on its own. In
- * lazy FPU mode, it is just an optimization to avoid a #NM exception,
- * the task can lose the FPU right after preempt_enable().
- */
-static inline void user_fpu_begin(void)
-{
- preempt_disable();
- if (!user_has_fpu())
- __thread_fpu_begin(current);
- preempt_enable();
-}
-
-static inline void __save_fpu(struct task_struct *tsk)
-{
- if (use_xsave()) {
- if (unlikely(system_state == SYSTEM_BOOTING))
- xsave_state_booting(&tsk->thread.fpu.state->xsave, -1);
- else
- xsave_state(&tsk->thread.fpu.state->xsave, -1);
- } else
- fpu_fxsave(&tsk->thread.fpu);
-}
-
-/*
- * i387 state interaction
- */
-static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
-{
- if (cpu_has_fxsr) {
- return tsk->thread.fpu.state->fxsave.cwd;
- } else {
- return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
- }
-}
-
-static inline unsigned short get_fpu_swd(struct task_struct *tsk)
-{
- if (cpu_has_fxsr) {
- return tsk->thread.fpu.state->fxsave.swd;
- } else {
- return (unsigned short)tsk->thread.fpu.state->fsave.swd;
- }
-}
-
-static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
-{
- if (cpu_has_xmm) {
- return tsk->thread.fpu.state->fxsave.mxcsr;
- } else {
- return MXCSR_DEFAULT;
- }
-}
-
-static bool fpu_allocated(struct fpu *fpu)
-{
- return fpu->state != NULL;
-}
-
-static inline int fpu_alloc(struct fpu *fpu)
-{
- if (fpu_allocated(fpu))
- return 0;
- fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
- if (!fpu->state)
- return -ENOMEM;
- WARN_ON((unsigned long)fpu->state & 15);
- return 0;
-}
-
-static inline void fpu_free(struct fpu *fpu)
-{
- if (fpu->state) {
- kmem_cache_free(task_xstate_cachep, fpu->state);
- fpu->state = NULL;
- }
-}
-
-static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
-{
- if (use_eager_fpu()) {
- memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
- __save_fpu(dst);
- } else {
- struct fpu *dfpu = &dst->thread.fpu;
- struct fpu *sfpu = &src->thread.fpu;
-
- unlazy_fpu(src);
- memcpy(dfpu->state, sfpu->state, xstate_size);
- }
-}
-
-static inline unsigned long
-alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
- unsigned long *size)
-{
- unsigned long frame_size = xstate_sigframe_size();
-
- *buf_fx = sp = round_down(sp - frame_size, 64);
- if (ia32_frame && use_fxsr()) {
- frame_size += sizeof(struct i387_fsave_struct);
- sp -= sizeof(struct i387_fsave_struct);
- }
-
- *size = frame_size;
- return sp;
-}
-
-#endif
--- /dev/null
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_API_H
+#define _ASM_X86_FPU_API_H
+
+/*
+ * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
+ * and they don't touch the preempt state on their own.
+ * If you enable preemption after __kernel_fpu_begin(), preempt notifier
+ * should call the __kernel_fpu_end() to prevent the kernel/user FPU
+ * state from getting corrupted. KVM for example uses this model.
+ *
+ * All other cases use kernel_fpu_begin/end() which disable preemption
+ * during kernel FPU usage.
+ */
+extern void __kernel_fpu_begin(void);
+extern void __kernel_fpu_end(void);
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
+extern bool irq_fpu_usable(void);
+
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context as well. To prevent these kernel instructions
+ * in interrupt context interacting wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+extern int irq_ts_save(void);
+extern void irq_ts_restore(int TS_state);
+
+/*
+ * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
+ *
+ * If 'feature_name' is set then put a human-readable description of
+ * the feature there as well - this can be used to print error (or success)
+ * messages.
+ */
+extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
+
+#endif /* _ASM_X86_FPU_API_H */
--- /dev/null
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_INTERNAL_H
+#define _ASM_X86_FPU_INTERNAL_H
+
+#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/user.h>
+#include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
+
+/*
+ * High level FPU state handling functions:
+ */
+extern void fpu__activate_curr(struct fpu *fpu);
+extern void fpu__activate_fpstate_read(struct fpu *fpu);
+extern void fpu__activate_fpstate_write(struct fpu *fpu);
+extern void fpu__save(struct fpu *fpu);
+extern void fpu__restore(struct fpu *fpu);
+extern int fpu__restore_sig(void __user *buf, int ia32_frame);
+extern void fpu__drop(struct fpu *fpu);
+extern int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
+extern void fpu__clear(struct fpu *fpu);
+extern int fpu__exception_code(struct fpu *fpu, int trap_nr);
+extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
+
+/*
+ * Boot time FPU initialization functions:
+ */
+extern void fpu__init_cpu(void);
+extern void fpu__init_system_xstate(void);
+extern void fpu__init_cpu_xstate(void);
+extern void fpu__init_system(struct cpuinfo_x86 *c);
+extern void fpu__init_check_bugs(void);
+extern void fpu__resume_cpu(void);
+
+/*
+ * Debugging facility:
+ */
+#ifdef CONFIG_X86_DEBUG_FPU
+# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
+#else
+# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+#endif
+
+/*
+ * FPU related CPU feature flag helper routines:
+ */
+static __always_inline __pure bool use_eager_fpu(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
+}
+
+static __always_inline __pure bool use_xsaveopt(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_FXSR);
+}
+
+/*
+ * fpstate handling functions:
+ */
+
+extern union fpregs_state init_fpstate;
+
+extern void fpstate_init(union fpregs_state *state);
+#ifdef CONFIG_MATH_EMULATION
+extern void fpstate_init_soft(struct swregs_state *soft);
+#else
+static inline void fpstate_init_soft(struct swregs_state *soft) {}
+#endif
+static inline void fpstate_init_fxstate(struct fxregs_state *fx)
+{
+ fx->cwd = 0x37f;
+ fx->mxcsr = MXCSR_DEFAULT;
+}
+extern void fpstate_sanitize_xstate(struct fpu *fpu);
+
+#define user_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile(ASM_STAC "\n" \
+ "1:" #insn "\n\t" \
+ "2: " ASM_CLAC "\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+#define check_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+static inline int copy_fregs_to_user(struct fregs_state __user *fx)
+{
+ return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
+{
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+ /* See comment in copy_fxregs_to_kernel() below. */
+ return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
+}
+
+static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
+{
+ int err;
+
+ if (config_enabled(CONFIG_X86_32)) {
+ err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ } else {
+ if (config_enabled(CONFIG_AS_FXSAVEQ)) {
+ err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+ } else {
+ /* See comment in copy_fxregs_to_kernel() below. */
+ err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+ }
+ }
+ /* Copying from a kernel buffer to FPU registers should never fail: */
+ WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
+{
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+ /* See comment in copy_fxregs_to_kernel() below. */
+ return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+ "m" (*fx));
+}
+
+static inline void copy_kernel_to_fregs(struct fregs_state *fx)
+{
+ int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+ WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fregs(struct fregs_state __user *fx)
+{
+ return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void copy_fxregs_to_kernel(struct fpu *fpu)
+{
+ if (config_enabled(CONFIG_X86_32))
+ asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
+ else {
+ /* Using "rex64; fxsave %0" is broken because, if the memory
+ * operand uses any extended registers for addressing, a second
+ * REX prefix will be generated (to the assembler, rex64
+ * followed by semicolon is a separate instruction), and hence
+ * the 64-bitness is lost.
+ *
+ * Using "fxsaveq %0" would be the ideal choice, but is only
+ * supported starting with gas 2.16.
+ *
+ * Using, as a workaround, the properly prefixed form below
+ * isn't accepted by any binutils version so far released,
+ * complaining that the same type of prefix is used twice if
+ * an extended register is needed for addressing (fix submitted
+ * to mainline 2005-11-21).
+ *
+ * asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave));
+ *
+ * This, however, we can work around by forcing the compiler to
+ * select an addressing mode that doesn't require extended
+ * registers.
+ */
+ asm volatile( "rex64/fxsave (%[fx])"
+ : "=m" (fpu->state.fxsave)
+ : [fx] "R" (&fpu->state.fxsave));
+ }
+}
+
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+/* xstate instruction fault handler: */
+#define xstate_fault(__err) \
+ \
+ ".section .fixup,\"ax\"\n" \
+ \
+ "3: movl $-2,%[_err]\n" \
+ " jmp 2b\n" \
+ \
+ ".previous\n" \
+ \
+ _ASM_EXTABLE(1b, 3b) \
+ : [_err] "=r" (__err)
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
+{
+ u64 mask = -1;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ WARN_ON(system_state != SYSTEM_BOOTING);
+
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ asm volatile("1:"XSAVES"\n\t"
+ "2:\n\t"
+ xstate_fault(err)
+ : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory");
+ else
+ asm volatile("1:"XSAVE"\n\t"
+ "2:\n\t"
+ xstate_fault(err)
+ : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory");
+
+ /* We should never fault when copying to a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
+{
+ u64 mask = -1;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ WARN_ON(system_state != SYSTEM_BOOTING);
+
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ asm volatile("1:"XRSTORS"\n\t"
+ "2:\n\t"
+ xstate_fault(err)
+ : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory");
+ else
+ asm volatile("1:"XRSTOR"\n\t"
+ "2:\n\t"
+ xstate_fault(err)
+ : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory");
+
+ /* We should never fault when copying from a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * Save processor xstate to xsave area.
+ */
+static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
+{
+ u64 mask = -1;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ WARN_ON(!alternatives_patched);
+
+ /*
+ * If xsaves is enabled, xsaves replaces xsaveopt because
+ * it supports compact format and supervisor states in addition to
+ * modified optimization in xsaveopt.
+ *
+ * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
+ * because xsaveopt supports modified optimization which is not
+ * supported by xsave.
+ *
+ * If none of xsaves and xsaveopt is enabled, use xsave.
+ */
+ alternative_input_2(
+ "1:"XSAVE,
+ XSAVEOPT,
+ X86_FEATURE_XSAVEOPT,
+ XSAVES,
+ X86_FEATURE_XSAVES,
+ [xstate] "D" (xstate), "a" (lmask), "d" (hmask) :
+ "memory");
+ asm volatile("2:\n\t"
+ xstate_fault(err)
+ : "0" (err)
+ : "memory");
+
+ /* We should never fault when copying to a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * Restore processor xstate from xsave area.
+ */
+static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
+{
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ /*
+ * Use xrstors to restore context if it is enabled. xrstors supports
+ * compacted format of xsave area which is not supported by xrstor.
+ */
+ alternative_input(
+ "1: " XRSTOR,
+ XRSTORS,
+ X86_FEATURE_XSAVES,
+ "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask)
+ : "memory");
+
+ asm volatile("2:\n"
+ xstate_fault(err)
+ : "0" (err)
+ : "memory");
+
+ /* We should never fault when copying from a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for
+ * backward compatibility for old applications which don't understand
+ * compacted format of xsave area.
+ */
+static inline int copy_xregs_to_user(struct xregs_state __user *buf)
+{
+ int err;
+
+ /*
+ * Clear the xsave header first, so that reserved fields are
+ * initialized to zero.
+ */
+ err = __clear_user(&buf->header, sizeof(buf->header));
+ if (unlikely(err))
+ return -EFAULT;
+
+ __asm__ __volatile__(ASM_STAC "\n"
+ "1:"XSAVE"\n"
+ "2: " ASM_CLAC "\n"
+ xstate_fault(err)
+ : "D" (buf), "a" (-1), "d" (-1), "0" (err)
+ : "memory");
+ return err;
+}
+
+/*
+ * Restore xstate from user space xsave area.
+ */
+static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
+{
+ struct xregs_state *xstate = ((__force struct xregs_state *)buf);
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ __asm__ __volatile__(ASM_STAC "\n"
+ "1:"XRSTOR"\n"
+ "2: " ASM_CLAC "\n"
+ xstate_fault(err)
+ : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err)
+ : "memory"); /* memory required? */
+ return err;
+}
+
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+ if (likely(use_xsave())) {
+ copy_xregs_to_kernel(&fpu->state.xsave);
+ return 1;
+ }
+
+ if (likely(use_fxsr())) {
+ copy_fxregs_to_kernel(fpu);
+ return 1;
+ }
+
+ /*
+ * Legacy FPU register saving, FNSAVE always clears FPU registers,
+ * so we have to mark them inactive:
+ */
+ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+ return 0;
+}
+
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+ if (use_xsave()) {
+ copy_kernel_to_xregs(&fpstate->xsave, -1);
+ } else {
+ if (use_fxsr())
+ copy_kernel_to_fxregs(&fpstate->fxsave);
+ else
+ copy_kernel_to_fregs(&fpstate->fsave);
+ }
+}
+
+static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+ /*
+ * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
+ * pending. Clear the x87 state here by setting it to fixed values.
+ * "m" is a random variable that should be in L1.
+ */
+ if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
+ asm volatile(
+ "fnclex\n\t"
+ "emms\n\t"
+ "fildl %P[addr]" /* set F?P to defined value */
+ : : [addr] "m" (fpstate));
+ }
+
+ __copy_kernel_to_fpregs(fpstate);
+}
+
+extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+
+/*
+ * FPU context switch related helper methods:
+ */
+
+DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/*
+ * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx,
+ * on this CPU.
+ *
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
+ */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+ per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
+}
+
+static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
+{
+ return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+}
+
+
+/*
+ * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
+ * idiom, which is then paired with the sw-flag (fpregs_active) later on:
+ */
+
+static inline void __fpregs_activate_hw(void)
+{
+ if (!use_eager_fpu())
+ clts();
+}
+
+static inline void __fpregs_deactivate_hw(void)
+{
+ if (!use_eager_fpu())
+ stts();
+}
+
+/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
+static inline void __fpregs_deactivate(struct fpu *fpu)
+{
+ WARN_ON_FPU(!fpu->fpregs_active);
+
+ fpu->fpregs_active = 0;
+ this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+}
+
+/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
+static inline void __fpregs_activate(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu->fpregs_active);
+
+ fpu->fpregs_active = 1;
+ this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+}
+
+/*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ */
+static inline int fpregs_active(void)
+{
+ return current->thread.fpu.fpregs_active;
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void fpregs_activate(struct fpu *fpu)
+{
+ __fpregs_activate_hw();
+ __fpregs_activate(fpu);
+}
+
+static inline void fpregs_deactivate(struct fpu *fpu)
+{
+ __fpregs_deactivate(fpu);
+ __fpregs_deactivate_hw();
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ * - switch_fpu_prepare() saves the old state and
+ * sets the new state of the CR0.TS bit. This is
+ * done within the context of the old process.
+ *
+ * - switch_fpu_finish() restores the new state as
+ * necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+static inline fpu_switch_t
+switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
+{
+ fpu_switch_t fpu;
+
+ /*
+ * If the task has used the math, pre-load the FPU on xsave processors
+ * or if the past 5 consecutive context-switches used math.
+ */
+ fpu.preload = new_fpu->fpstate_active &&
+ (use_eager_fpu() || new_fpu->counter > 5);
+
+ if (old_fpu->fpregs_active) {
+ if (!copy_fpregs_to_fpstate(old_fpu))
+ old_fpu->last_cpu = -1;
+ else
+ old_fpu->last_cpu = cpu;
+
+ /* But leave fpu_fpregs_owner_ctx! */
+ old_fpu->fpregs_active = 0;
+
+ /* Don't change CR0.TS if we just switch! */
+ if (fpu.preload) {
+ new_fpu->counter++;
+ __fpregs_activate(new_fpu);
+ prefetch(&new_fpu->state);
+ } else {
+ __fpregs_deactivate_hw();
+ }
+ } else {
+ old_fpu->counter = 0;
+ old_fpu->last_cpu = -1;
+ if (fpu.preload) {
+ new_fpu->counter++;
+ if (fpu_want_lazy_restore(new_fpu, cpu))
+ fpu.preload = 0;
+ else
+ prefetch(&new_fpu->state);
+ fpregs_activate(new_fpu);
+ }
+ }
+ return fpu;
+}
+
+/*
+ * Misc helper functions:
+ */
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch)
+{
+ if (fpu_switch.preload)
+ copy_kernel_to_fpregs(&new_fpu->state);
+}
+
+/*
+ * Needs to be preemption-safe.
+ *
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * the save state. It does not do any saving/restoring on its own. In
+ * lazy FPU mode, it is just an optimization to avoid a #NM exception,
+ * the task can lose the FPU right after preempt_enable().
+ */
+static inline void user_fpu_begin(void)
+{
+ struct fpu *fpu = ¤t->thread.fpu;
+
+ preempt_disable();
+ if (!fpregs_active())
+ fpregs_activate(fpu);
+ preempt_enable();
+}
+
+/*
+ * MXCSR and XCR definitions:
+ */
+
+extern unsigned int mxcsr_feature_mask;
+
+#define XCR_XFEATURE_ENABLED_MASK 0x00000000
+
+static inline u64 xgetbv(u32 index)
+{
+ u32 eax, edx;
+
+ asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
+ : "=a" (eax), "=d" (edx)
+ : "c" (index));
+ return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+ u32 eax = value;
+ u32 edx = value >> 32;
+
+ asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
+ : : "a" (eax), "d" (edx), "c" (index));
+}
+
+#endif /* _ASM_X86_FPU_INTERNAL_H */
--- /dev/null
+/*
+ * FPU regset handling methods:
+ */
+#ifndef _ASM_X86_FPU_REGSET_H
+#define _ASM_X86_FPU_REGSET_H
+
+#include <linux/regset.h>
+
+extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+ xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+ xstateregs_set;
+
+/*
+ * xstateregs_active == regset_fpregs_active. Please refer to the comment
+ * at the definition of regset_fpregs_active.
+ */
+#define xstateregs_active regset_fpregs_active
+
+#endif /* _ASM_X86_FPU_REGSET_H */
--- /dev/null
+/*
+ * x86 FPU signal frame handling methods:
+ */
+#ifndef _ASM_X86_FPU_SIGNAL_H
+#define _ASM_X86_FPU_SIGNAL_H
+
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+struct ksignal;
+int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
+ compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct ksignal *ksig,
+ compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct user_i387_struct
+# define user32_fxsr_struct user_fxsr_struct
+# define ia32_setup_frame __setup_frame
+# define ia32_setup_rt_frame __setup_rt_frame
+#endif
+
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+ struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env);
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+ unsigned long *buf_fx, unsigned long *size);
+
+extern void fpu__init_prepare_fx_sw_frame(void);
+
+#endif /* _ASM_X86_FPU_SIGNAL_H */
--- /dev/null
+/*
+ * FPU data structures:
+ */
+#ifndef _ASM_X86_FPU_H
+#define _ASM_X86_FPU_H
+
+/*
+ * The legacy x87 FPU state format, as saved by FSAVE and
+ * restored by the FRSTOR instructions:
+ */
+struct fregs_state {
+ u32 cwd; /* FPU Control Word */
+ u32 swd; /* FPU Status Word */
+ u32 twd; /* FPU Tag Word */
+ u32 fip; /* FPU IP Offset */
+ u32 fcs; /* FPU IP Selector */
+ u32 foo; /* FPU Operand Pointer Offset */
+ u32 fos; /* FPU Operand Pointer Selector */
+
+ /* 8*10 bytes for each FP-reg = 80 bytes: */
+ u32 st_space[20];
+
+ /* Software status information [not touched by FSAVE]: */
+ u32 status;
+};
+
+/*
+ * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and
+ * restored by the FXRSTOR instructions. It's similar to the FSAVE
+ * format, but differs in some areas, plus has extensions at
+ * the end for the XMM registers.
+ */
+struct fxregs_state {
+ u16 cwd; /* Control Word */
+ u16 swd; /* Status Word */
+ u16 twd; /* Tag Word */
+ u16 fop; /* Last Instruction Opcode */
+ union {
+ struct {
+ u64 rip; /* Instruction Pointer */
+ u64 rdp; /* Data Pointer */
+ };
+ struct {
+ u32 fip; /* FPU IP Offset */
+ u32 fcs; /* FPU IP Selector */
+ u32 foo; /* FPU Operand Offset */
+ u32 fos; /* FPU Operand Selector */
+ };
+ };
+ u32 mxcsr; /* MXCSR Register State */
+ u32 mxcsr_mask; /* MXCSR Mask */
+
+ /* 8*16 bytes for each FP-reg = 128 bytes: */
+ u32 st_space[32];
+
+ /* 16*16 bytes for each XMM-reg = 256 bytes: */
+ u32 xmm_space[64];
+
+ u32 padding[12];
+
+ union {
+ u32 padding1[12];
+ u32 sw_reserved[12];
+ };
+
+} __attribute__((aligned(16)));
+
+/* Default value for fxregs_state.mxcsr: */
+#define MXCSR_DEFAULT 0x1f80
+
+/*
+ * Software based FPU emulation state. This is arbitrary really,
+ * it matches the x87 format to make it easier to understand:
+ */
+struct swregs_state {
+ u32 cwd;
+ u32 swd;
+ u32 twd;
+ u32 fip;
+ u32 fcs;
+ u32 foo;
+ u32 fos;
+ /* 8*10 bytes for each FP-reg = 80 bytes: */
+ u32 st_space[20];
+ u8 ftop;
+ u8 changed;
+ u8 lookahead;
+ u8 no_update;
+ u8 rm;
+ u8 alimit;
+ struct math_emu_info *info;
+ u32 entry_eip;
+};
+
+/*
+ * List of XSAVE features Linux knows about:
+ */
+enum xfeature_bit {
+ XSTATE_BIT_FP,
+ XSTATE_BIT_SSE,
+ XSTATE_BIT_YMM,
+ XSTATE_BIT_BNDREGS,
+ XSTATE_BIT_BNDCSR,
+ XSTATE_BIT_OPMASK,
+ XSTATE_BIT_ZMM_Hi256,
+ XSTATE_BIT_Hi16_ZMM,
+
+ XFEATURES_NR_MAX,
+};
+
+#define XSTATE_FP (1 << XSTATE_BIT_FP)
+#define XSTATE_SSE (1 << XSTATE_BIT_SSE)
+#define XSTATE_YMM (1 << XSTATE_BIT_YMM)
+#define XSTATE_BNDREGS (1 << XSTATE_BIT_BNDREGS)
+#define XSTATE_BNDCSR (1 << XSTATE_BIT_BNDCSR)
+#define XSTATE_OPMASK (1 << XSTATE_BIT_OPMASK)
+#define XSTATE_ZMM_Hi256 (1 << XSTATE_BIT_ZMM_Hi256)
+#define XSTATE_Hi16_ZMM (1 << XSTATE_BIT_Hi16_ZMM)
+
+#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE)
+#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/*
+ * There are 16x 256-bit AVX registers named YMM0-YMM15.
+ * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15)
+ * and are stored in 'struct fxregs_state::xmm_space[]'.
+ *
+ * The high 128 bits are stored here:
+ * 16x 128 bits == 256 bytes.
+ */
+struct ymmh_struct {
+ u8 ymmh_space[256];
+};
+
+/* We don't support LWP yet: */
+struct lwp_struct {
+ u8 reserved[128];
+};
+
+/* Intel MPX support: */
+struct bndreg {
+ u64 lower_bound;
+ u64 upper_bound;
+} __packed;
+
+struct bndcsr {
+ u64 bndcfgu;
+ u64 bndstatus;
+} __packed;
+
+struct mpx_struct {
+ struct bndreg bndreg[4];
+ struct bndcsr bndcsr;
+};
+
+struct xstate_header {
+ u64 xfeatures;
+ u64 xcomp_bv;
+ u64 reserved[6];
+} __attribute__((packed));
+
+/* New processor state extensions should be added here: */
+#define XSTATE_RESERVE (sizeof(struct ymmh_struct) + \
+ sizeof(struct lwp_struct) + \
+ sizeof(struct mpx_struct) )
+/*
+ * This is our most modern FPU state format, as saved by the XSAVE
+ * and restored by the XRSTOR instructions.
+ *
+ * It consists of a legacy fxregs portion, an xstate header and
+ * subsequent fixed size areas as defined by the xstate header.
+ * Not all CPUs support all the extensions.
+ */
+struct xregs_state {
+ struct fxregs_state i387;
+ struct xstate_header header;
+ u8 __reserved[XSTATE_RESERVE];
+} __attribute__ ((packed, aligned (64)));
+
+/*
+ * This is a union of all the possible FPU state formats
+ * put together, so that we can pick the right one runtime.
+ *
+ * The size of the structure is determined by the largest
+ * member - which is the xsave area:
+ */
+union fpregs_state {
+ struct fregs_state fsave;
+ struct fxregs_state fxsave;
+ struct swregs_state soft;
+ struct xregs_state xsave;
+};
+
+/*
+ * Highest level per task FPU state data structure that
+ * contains the FPU register state plus various FPU
+ * state fields:
+ */
+struct fpu {
+ /*
+ * @state:
+ *
+ * In-memory copy of all FPU registers that we save/restore
+ * over context switches. If the task is using the FPU then
+ * the registers in the FPU are more recent than this state
+ * copy. If the task context-switches away then they get
+ * saved here and represent the FPU state.
+ *
+ * After context switches there may be a (short) time period
+ * during which the in-FPU hardware registers are unchanged
+ * and still perfectly match this state, if the tasks
+ * scheduled afterwards are not using the FPU.
+ *
+ * This is the 'lazy restore' window of optimization, which
+ * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
+ *
+ * We detect whether a subsequent task uses the FPU via setting
+ * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
+ *
+ * During this window, if the task gets scheduled again, we
+ * might be able to skip having to do a restore from this
+ * memory buffer to the hardware registers - at the cost of
+ * incurring the overhead of #NM fault traps.
+ *
+ * Note that on modern CPUs that support the XSAVEOPT (or other
+ * optimized XSAVE instructions), we don't use #NM traps anymore,
+ * as the hardware can track whether FPU registers need saving
+ * or not. On such CPUs we activate the non-lazy ('eagerfpu')
+ * logic, which unconditionally saves/restores all FPU state
+ * across context switches. (if FPU state exists.)
+ */
+ union fpregs_state state;
+
+ /*
+ * @last_cpu:
+ *
+ * Records the last CPU on which this context was loaded into
+ * FPU registers. (In the lazy-restore case we might be
+ * able to reuse FPU registers across multiple context switches
+ * this way, if no intermediate task used the FPU.)
+ *
+ * A value of -1 is used to indicate that the FPU state in context
+ * memory is newer than the FPU state in registers, and that the
+ * FPU state should be reloaded next time the task is run.
+ */
+ unsigned int last_cpu;
+
+ /*
+ * @fpstate_active:
+ *
+ * This flag indicates whether this context is active: if the task
+ * is not running then we can restore from this context, if the task
+ * is running then we should save into this context.
+ */
+ unsigned char fpstate_active;
+
+ /*
+ * @fpregs_active:
+ *
+ * This flag determines whether a given context is actively
+ * loaded into the FPU's registers and that those registers
+ * represent the task's current FPU state.
+ *
+ * Note the interaction with fpstate_active:
+ *
+ * # task does not use the FPU:
+ * fpstate_active == 0
+ *
+ * # task uses the FPU and regs are active:
+ * fpstate_active == 1 && fpregs_active == 1
+ *
+ * # the regs are inactive but still match fpstate:
+ * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
+ *
+ * The third state is what we use for the lazy restore optimization
+ * on lazy-switching CPUs.
+ */
+ unsigned char fpregs_active;
+
+ /*
+ * @counter:
+ *
+ * This counter contains the number of consecutive context switches
+ * during which the FPU stays used. If this is over a threshold, the
+ * lazy FPU restore logic becomes eager, to save the trap overhead.
+ * This is an unsigned char so that after 256 iterations the counter
+ * wraps and the context switch behavior turns lazy again; this is to
+ * deal with bursty apps that only use the FPU for a short time:
+ */
+ unsigned char counter;
+};
+
+#endif /* _ASM_X86_FPU_H */
--- /dev/null
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+
+/* Bit 63 of XCR0 is reserved for future expansion */
+#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63)))
+
+#define XSTATE_CPUID 0x0000000d
+
+#define FXSAVE_SIZE 512
+
+#define XSAVE_HDR_SIZE 64
+#define XSAVE_HDR_OFFSET FXSAVE_SIZE
+
+#define XSAVE_YMM_SIZE 256
+#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
+
+/* Supported features which support lazy state saving */
+#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
+ | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/* Supported features which require eager state saving */
+#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR)
+
+/* All currently supported features */
+#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX "0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern unsigned int xstate_size;
+extern u64 xfeatures_mask;
+extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+
+extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
+
+void *get_xsave_addr(struct xregs_state *xsave, int xstate);
+const void *get_xsave_field_ptr(int xstate_field);
+
+#endif
#ifdef __ASSEMBLY__
#include <asm/asm.h>
-#include <asm/dwarf2.h>
/* The annotation hides the frame from the unwinder and makes it look
like a ordinary ebp save/restore. This avoids some special cases for
frame pointer later */
#ifdef CONFIG_FRAME_POINTER
.macro FRAME
- __ASM_SIZE(push,_cfi) %__ASM_REG(bp)
- CFI_REL_OFFSET __ASM_REG(bp), 0
+ __ASM_SIZE(push,) %__ASM_REG(bp)
__ASM_SIZE(mov) %__ASM_REG(sp), %__ASM_REG(bp)
.endm
.macro ENDFRAME
- __ASM_SIZE(pop,_cfi) %__ASM_REG(bp)
- CFI_RESTORE __ASM_REG(bp)
+ __ASM_SIZE(pop,) %__ASM_REG(bp)
.endm
#else
.macro FRAME
#endif
#ifdef CONFIG_HAVE_KVM
unsigned int kvm_posted_intr_ipis;
+ unsigned int kvm_posted_intr_wakeup_ipis;
#endif
unsigned int x86_platform_ipis; /* arch dependent */
unsigned int apic_perf_irqs;
#ifdef CONFIG_X86_MCE_THRESHOLD
unsigned int irq_threshold_count;
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ unsigned int irq_deferred_error_count;
+#endif
#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
unsigned int irq_hv_callback_count;
#endif
extern void force_hpet_resume(void);
struct irq_data;
+struct hpet_dev;
+struct irq_domain;
+
extern void hpet_msi_unmask(struct irq_data *data);
extern void hpet_msi_mask(struct irq_data *data);
-struct hpet_dev;
extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
-
-#ifdef CONFIG_PCI_MSI
-extern int default_setup_hpet_msi(unsigned int irq, unsigned int id);
-#else
-static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id)
-{
- return -EINVAL;
-}
-#endif
+extern struct irq_domain *hpet_create_irq_domain(int hpet_id);
+extern int hpet_assign_irq(struct irq_domain *domain,
+ struct hpet_dev *dev, int dev_num);
#ifdef CONFIG_HPET_EMULATE_RTC
extern asmlinkage void apic_timer_interrupt(void);
extern asmlinkage void x86_platform_ipi(void);
extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
extern asmlinkage void error_interrupt(void);
extern asmlinkage void irq_work_interrupt(void);
extern asmlinkage void thermal_interrupt(void);
extern asmlinkage void reschedule_interrupt(void);
-extern asmlinkage void invalidate_interrupt(void);
-extern asmlinkage void invalidate_interrupt0(void);
-extern asmlinkage void invalidate_interrupt1(void);
-extern asmlinkage void invalidate_interrupt2(void);
-extern asmlinkage void invalidate_interrupt3(void);
-extern asmlinkage void invalidate_interrupt4(void);
-extern asmlinkage void invalidate_interrupt5(void);
-extern asmlinkage void invalidate_interrupt6(void);
-extern asmlinkage void invalidate_interrupt7(void);
-extern asmlinkage void invalidate_interrupt8(void);
-extern asmlinkage void invalidate_interrupt9(void);
-extern asmlinkage void invalidate_interrupt10(void);
-extern asmlinkage void invalidate_interrupt11(void);
-extern asmlinkage void invalidate_interrupt12(void);
-extern asmlinkage void invalidate_interrupt13(void);
-extern asmlinkage void invalidate_interrupt14(void);
-extern asmlinkage void invalidate_interrupt15(void);
-extern asmlinkage void invalidate_interrupt16(void);
-extern asmlinkage void invalidate_interrupt17(void);
-extern asmlinkage void invalidate_interrupt18(void);
-extern asmlinkage void invalidate_interrupt19(void);
-extern asmlinkage void invalidate_interrupt20(void);
-extern asmlinkage void invalidate_interrupt21(void);
-extern asmlinkage void invalidate_interrupt22(void);
-extern asmlinkage void invalidate_interrupt23(void);
-extern asmlinkage void invalidate_interrupt24(void);
-extern asmlinkage void invalidate_interrupt25(void);
-extern asmlinkage void invalidate_interrupt26(void);
-extern asmlinkage void invalidate_interrupt27(void);
-extern asmlinkage void invalidate_interrupt28(void);
-extern asmlinkage void invalidate_interrupt29(void);
-extern asmlinkage void invalidate_interrupt30(void);
-extern asmlinkage void invalidate_interrupt31(void);
-
extern asmlinkage void irq_move_cleanup_interrupt(void);
extern asmlinkage void reboot_interrupt(void);
extern asmlinkage void threshold_interrupt(void);
+extern asmlinkage void deferred_error_interrupt(void);
extern asmlinkage void call_function_interrupt(void);
extern asmlinkage void call_function_single_interrupt(void);
extern void trace_thermal_interrupt(void);
extern void trace_reschedule_interrupt(void);
extern void trace_threshold_interrupt(void);
+extern void trace_deferred_error_interrupt(void);
extern void trace_call_function_interrupt(void);
extern void trace_call_function_single_interrupt(void);
#define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt
#define trace_reboot_interrupt reboot_interrupt
#define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
+#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
#endif /* CONFIG_TRACING */
-#ifdef CONFIG_IRQ_REMAP
-/* Intel specific interrupt remapping information */
-struct irq_2_iommu {
- struct intel_iommu *iommu;
- u16 irte_index;
- u16 sub_handle;
- u8 irte_mask;
-};
-
-/* AMD specific interrupt remapping information */
-struct irq_2_irte {
- u16 devid; /* Device ID for IRTE table */
- u16 index; /* Index into IRTE table*/
-};
-#endif /* CONFIG_IRQ_REMAP */
-
#ifdef CONFIG_X86_LOCAL_APIC
struct irq_data;
+struct pci_dev;
+struct msi_desc;
+
+enum irq_alloc_type {
+ X86_IRQ_ALLOC_TYPE_IOAPIC = 1,
+ X86_IRQ_ALLOC_TYPE_HPET,
+ X86_IRQ_ALLOC_TYPE_MSI,
+ X86_IRQ_ALLOC_TYPE_MSIX,
+ X86_IRQ_ALLOC_TYPE_DMAR,
+ X86_IRQ_ALLOC_TYPE_UV,
+};
-struct irq_cfg {
- cpumask_var_t domain;
- cpumask_var_t old_domain;
- u8 vector;
- u8 move_in_progress : 1;
-#ifdef CONFIG_IRQ_REMAP
- u8 remapped : 1;
+struct irq_alloc_info {
+ enum irq_alloc_type type;
+ u32 flags;
+ const struct cpumask *mask; /* CPU mask for vector allocation */
union {
- struct irq_2_iommu irq_2_iommu;
- struct irq_2_irte irq_2_irte;
- };
+ int unused;
+#ifdef CONFIG_HPET_TIMER
+ struct {
+ int hpet_id;
+ int hpet_index;
+ void *hpet_data;
+ };
#endif
- union {
-#ifdef CONFIG_X86_IO_APIC
+#ifdef CONFIG_PCI_MSI
struct {
- struct list_head irq_2_pin;
+ struct pci_dev *msi_dev;
+ irq_hw_number_t msi_hwirq;
+ };
+#endif
+#ifdef CONFIG_X86_IO_APIC
+ struct {
+ int ioapic_id;
+ int ioapic_pin;
+ int ioapic_node;
+ u32 ioapic_trigger : 1;
+ u32 ioapic_polarity : 1;
+ u32 ioapic_valid : 1;
+ struct IO_APIC_route_entry *ioapic_entry;
+ };
+#endif
+#ifdef CONFIG_DMAR_TABLE
+ struct {
+ int dmar_id;
+ void *dmar_data;
+ };
+#endif
+#ifdef CONFIG_HT_IRQ
+ struct {
+ int ht_pos;
+ int ht_idx;
+ struct pci_dev *ht_dev;
+ void *ht_update;
+ };
+#endif
+#ifdef CONFIG_X86_UV
+ struct {
+ int uv_limit;
+ int uv_blade;
+ unsigned long uv_offset;
+ char *uv_name;
};
#endif
};
};
+struct irq_cfg {
+ unsigned int dest_apicid;
+ u8 vector;
+};
+
extern struct irq_cfg *irq_cfg(unsigned int irq);
extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
-extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
extern void lock_vector_lock(void);
extern void unlock_vector_lock(void);
-extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
-extern void clear_irq_vector(int irq, struct irq_cfg *cfg);
extern void setup_vector_irq(int cpu);
#ifdef CONFIG_SMP
extern void send_cleanup_vector(struct irq_cfg *);
static inline void irq_complete_move(struct irq_cfg *c) { }
#endif
-extern int apic_retrigger_irq(struct irq_data *data);
extern void apic_ack_edge(struct irq_data *data);
-extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- unsigned int *dest_id);
#else /* CONFIG_X86_LOCAL_APIC */
static inline void lock_vector_lock(void) {}
static inline void unlock_vector_lock(void) {}
extern atomic_t irq_err_count;
extern atomic_t irq_mis_count;
-/* EISA */
-extern void eisa_set_level_irq(unsigned int irq);
+extern void elcr_set_level_irq(unsigned int irq);
/* SMP */
extern __visible void smp_apic_timer_interrupt(struct pt_regs *);
extern __visible void smp_reschedule_interrupt(struct pt_regs *);
extern __visible void smp_call_function_interrupt(struct pt_regs *);
extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
-extern __visible void smp_invalidate_interrupt(struct pt_regs *);
#endif
extern char irq_entries_start[];
+++ /dev/null
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _ASM_X86_I387_H
-#define _ASM_X86_I387_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/hardirq.h>
-
-struct pt_regs;
-struct user_i387_struct;
-
-extern int init_fpu(struct task_struct *child);
-extern void fpu_finit(struct fpu *fpu);
-extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
-extern void math_state_restore(void);
-
-extern bool irq_fpu_usable(void);
-
-/*
- * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
- * and they don't touch the preempt state on their own.
- * If you enable preemption after __kernel_fpu_begin(), preempt notifier
- * should call the __kernel_fpu_end() to prevent the kernel/user FPU
- * state from getting corrupted. KVM for example uses this model.
- *
- * All other cases use kernel_fpu_begin/end() which disable preemption
- * during kernel FPU usage.
- */
-extern void __kernel_fpu_begin(void);
-extern void __kernel_fpu_end(void);
-
-static inline void kernel_fpu_begin(void)
-{
- preempt_disable();
- WARN_ON_ONCE(!irq_fpu_usable());
- __kernel_fpu_begin();
-}
-
-static inline void kernel_fpu_end(void)
-{
- __kernel_fpu_end();
- preempt_enable();
-}
-
-/* Must be called with preempt disabled */
-extern void kernel_fpu_disable(void);
-extern void kernel_fpu_enable(void);
-
-/*
- * Some instructions like VIA's padlock instructions generate a spurious
- * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context as well. To prevent these kernel instructions
- * in interrupt context interacting wrongly with other user/kernel fpu usage, we
- * should use them only in the context of irq_ts_save/restore()
- */
-static inline int irq_ts_save(void)
-{
- /*
- * If in process context and not atomic, we can take a spurious DNA fault.
- * Otherwise, doing clts() in process context requires disabling preemption
- * or some heavy lifting like kernel_fpu_begin()
- */
- if (!in_atomic())
- return 0;
-
- if (read_cr0() & X86_CR0_TS) {
- clts();
- return 1;
- }
-
- return 0;
-}
-
-static inline void irq_ts_restore(int TS_state)
-{
- if (TS_state)
- stts();
-}
-
-/*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int user_has_fpu(void)
-{
- return current->thread.fpu.has_fpu;
-}
-
-extern void unlazy_fpu(struct task_struct *tsk);
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_I387_H */
*/
#define ARCH_HAS_IOREMAP_WC
+#define ARCH_HAS_IOREMAP_WT
#include <linux/string.h>
#include <linux/compiler.h>
#include <asm/page.h>
#include <asm/early_ioremap.h>
+#include <asm/pgtable_types.h>
#define build_mmio_read(name, size, type, reg, barrier) \
static inline type name(const volatile void __iomem *addr) \
* look at pci_iomap().
*/
extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
unsigned long prot_val);
#include <asm-generic/iomap.h>
-#include <linux/vmalloc.h>
-
/*
* Convert a virtual cached pointer to an uncached pointer
*/
extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
enum page_cache_mode pcm);
extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
extern bool is_early_ioremap_ptep(pte_t *ptep);
#define IO_SPACE_LIMIT 0xffff
#ifdef CONFIG_MTRR
+extern int __must_check arch_phys_wc_index(int handle);
+#define arch_phys_wc_index arch_phys_wc_index
+
extern int __must_check arch_phys_wc_add(unsigned long base,
unsigned long size);
extern void arch_phys_wc_del(int handle);
index : 15;
} __attribute__ ((packed));
-#define IOAPIC_AUTO -1
-#define IOAPIC_EDGE 0
-#define IOAPIC_LEVEL 1
+struct irq_alloc_info;
+struct ioapic_domain_cfg;
+
+#define IOAPIC_AUTO -1
+#define IOAPIC_EDGE 0
+#define IOAPIC_LEVEL 1
+
+#define IOAPIC_MASKED 1
+#define IOAPIC_UNMASKED 0
+
+#define IOAPIC_POL_HIGH 0
+#define IOAPIC_POL_LOW 1
+
+#define IOAPIC_DEST_MODE_PHYSICAL 0
+#define IOAPIC_DEST_MODE_LOGICAL 1
+
#define IOAPIC_MAP_ALLOC 0x1
#define IOAPIC_MAP_CHECK 0x2
extern int mpc_ioapic_id(int ioapic);
extern unsigned int mpc_ioapic_addr(int ioapic);
-extern struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic);
-
-#define MP_MAX_IOAPIC_PIN 127
/* # of MP IRQ source entries */
extern int mp_irq_entries;
/* MP IRQ source entries */
extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
-/* Older SiS APIC requires we rewrite the index register */
-extern int sis_apic_bug;
-
/* 1 if "noapic" boot option passed */
extern int skip_ioapic_setup;
/* -1 if "noapic" boot option passed */
extern int noioapicreroute;
+extern u32 gsi_top;
+
extern unsigned long io_apic_irqs;
#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs))
extern void ioapic_insert_resources(void);
extern int arch_early_ioapic_init(void);
-extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
- unsigned int, int,
- struct io_apic_irq_attr *);
-extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg);
-
-extern void native_eoi_ioapic_pin(int apic, int pin, int vector);
-
extern int save_ioapic_entries(void);
extern void mask_ioapic_entries(void);
extern int restore_ioapic_entries(void);
extern void setup_ioapic_ids_from_mpc(void);
extern void setup_ioapic_ids_from_mpc_nocheck(void);
-struct io_apic_irq_attr {
- int ioapic;
- int ioapic_pin;
- int trigger;
- int polarity;
-};
-
-enum ioapic_domain_type {
- IOAPIC_DOMAIN_INVALID,
- IOAPIC_DOMAIN_LEGACY,
- IOAPIC_DOMAIN_STRICT,
- IOAPIC_DOMAIN_DYNAMIC,
-};
-
-struct device_node;
-struct irq_domain;
-struct irq_domain_ops;
-
-struct ioapic_domain_cfg {
- enum ioapic_domain_type type;
- const struct irq_domain_ops *ops;
- struct device_node *dev;
-};
-
-struct mp_ioapic_gsi{
- u32 gsi_base;
- u32 gsi_end;
-};
-extern u32 gsi_top;
-
extern int mp_find_ioapic(u32 gsi);
extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
-extern u32 mp_pin_to_gsi(int ioapic, int pin);
-extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
+extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+ struct irq_alloc_info *info);
extern void mp_unmap_irq(int irq);
extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
struct ioapic_domain_cfg *cfg);
extern int mp_unregister_ioapic(u32 gsi_base);
extern int mp_ioapic_registered(u32 gsi_base);
-extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
- irq_hw_number_t hwirq);
-extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
-extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node);
-extern void __init pre_init_apic_IRQ0(void);
+
+extern void ioapic_set_alloc_attr(struct irq_alloc_info *info,
+ int node, int trigger, int polarity);
extern void mp_save_irq(struct mpc_intsrc *m);
extern void disable_ioapic_support(void);
-extern void __init native_io_apic_init_mappings(void);
+extern void __init io_apic_init_mappings(void);
extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg);
-extern void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int val);
-extern void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
extern void native_disable_io_apic(void);
-extern void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern void intel_ir_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern int native_ioapic_set_affinity(struct irq_data *,
- const struct cpumask *,
- bool);
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
{
return x86_io_apic_ops.read(apic, reg);
}
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
-{
- x86_io_apic_ops.write(apic, reg, value);
-}
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
- x86_io_apic_ops.modify(apic, reg, value);
-}
-
-extern void io_apic_eoi(unsigned int apic, unsigned int vector);
-
extern void setup_IO_APIC(void);
extern void enable_IO_APIC(void);
extern void disable_IO_APIC(void);
static inline void print_IO_APICs(void) {}
#define gsi_top (NR_IRQS_LEGACY)
static inline int mp_find_ioapic(u32 gsi) { return 0; }
-static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; }
-static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; }
+static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+ struct irq_alloc_info *info)
+{
+ return gsi;
+}
+
static inline void mp_unmap_irq(int irq) { }
static inline int save_ioapic_entries(void)
return -ENOMEM;
}
-static inline void mp_save_irq(struct mpc_intsrc *m) { };
+static inline void mp_save_irq(struct mpc_intsrc *m) { }
static inline void disable_ioapic_support(void) { }
-#define native_io_apic_init_mappings NULL
+static inline void io_apic_init_mappings(void) { }
#define native_io_apic_read NULL
-#define native_io_apic_write NULL
-#define native_io_apic_modify NULL
#define native_disable_io_apic NULL
-#define native_io_apic_print_entries NULL
-#define native_ioapic_set_affinity NULL
-#define native_setup_ioapic_entry NULL
-#define native_eoi_ioapic_pin NULL
static inline void setup_IO_APIC(void) { }
static inline void enable_IO_APIC(void) { }
extern void irq_force_complete_move(int);
#endif
+#ifdef CONFIG_HAVE_KVM
+extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
+#endif
+
extern void (*x86_platform_ipi_callback)(void);
extern void native_init_IRQ(void);
extern bool handle_irq(unsigned irq, struct pt_regs *regs);
#ifndef __X86_IRQ_REMAPPING_H
#define __X86_IRQ_REMAPPING_H
+#include <asm/irqdomain.h>
+#include <asm/hw_irq.h>
#include <asm/io_apic.h>
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_chip;
struct msi_msg;
-struct pci_dev;
-struct irq_cfg;
+struct irq_alloc_info;
+
+enum irq_remap_cap {
+ IRQ_POSTING_CAP = 0,
+};
#ifdef CONFIG_IRQ_REMAP
+extern bool irq_remapping_cap(enum irq_remap_cap cap);
extern void set_irq_remapping_broken(void);
extern int irq_remapping_prepare(void);
extern int irq_remapping_enable(void);
extern void irq_remapping_disable(void);
extern int irq_remapping_reenable(int);
extern int irq_remap_enable_fault_handling(void);
-extern int setup_ioapic_remapped_entry(int irq,
- struct IO_APIC_route_entry *entry,
- unsigned int destination,
- int vector,
- struct io_apic_irq_attr *attr);
-extern void free_remapped_irq(int irq);
-extern void compose_remapped_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id);
-extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id);
extern void panic_if_irq_remap(const char *msg);
-extern bool setup_remapped_irq(int irq,
- struct irq_cfg *cfg,
- struct irq_chip *chip);
-void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+extern struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info);
+extern struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info);
+
+/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */
+extern struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent);
+
+/* Get parent irqdomain for interrupt remapping irqdomain */
+static inline struct irq_domain *arch_get_ir_parent_domain(void)
+{
+ return x86_vector_domain;
+}
+
+struct vcpu_data {
+ u64 pi_desc_addr; /* Physical address of PI Descriptor */
+ u32 vector; /* Guest vector of the interrupt */
+};
#else /* CONFIG_IRQ_REMAP */
+static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
static inline void set_irq_remapping_broken(void) { }
static inline int irq_remapping_prepare(void) { return -ENODEV; }
static inline int irq_remapping_enable(void) { return -ENODEV; }
static inline void irq_remapping_disable(void) { }
static inline int irq_remapping_reenable(int eim) { return -ENODEV; }
static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; }
-static inline int setup_ioapic_remapped_entry(int irq,
- struct IO_APIC_route_entry *entry,
- unsigned int destination,
- int vector,
- struct io_apic_irq_attr *attr)
-{
- return -ENODEV;
-}
-static inline void free_remapped_irq(int irq) { }
-static inline void compose_remapped_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
-{
-}
-static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
- return -ENODEV;
-}
static inline void panic_if_irq_remap(const char *msg)
{
}
-static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
{
+ return NULL;
}
-static inline bool setup_remapped_irq(int irq,
- struct irq_cfg *cfg,
- struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
{
- return false;
+ return NULL;
}
-#endif /* CONFIG_IRQ_REMAP */
-
-#define dmar_alloc_hwirq() irq_alloc_hwirq(-1)
-#define dmar_free_hwirq irq_free_hwirq
+#endif /* CONFIG_IRQ_REMAP */
#endif /* __X86_IRQ_REMAPPING_H */
#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR
#define IA32_SYSCALL_VECTOR 0x80
-#ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR 0x80
-#endif
/*
* Vectors 0x30-0x3f are used for ISA interrupts.
* round up to the next 16-vector boundary
*/
-#define IRQ0_VECTOR ((FIRST_EXTERNAL_VECTOR + 16) & ~15)
-
-#define IRQ1_VECTOR (IRQ0_VECTOR + 1)
-#define IRQ2_VECTOR (IRQ0_VECTOR + 2)
-#define IRQ3_VECTOR (IRQ0_VECTOR + 3)
-#define IRQ4_VECTOR (IRQ0_VECTOR + 4)
-#define IRQ5_VECTOR (IRQ0_VECTOR + 5)
-#define IRQ6_VECTOR (IRQ0_VECTOR + 6)
-#define IRQ7_VECTOR (IRQ0_VECTOR + 7)
-#define IRQ8_VECTOR (IRQ0_VECTOR + 8)
-#define IRQ9_VECTOR (IRQ0_VECTOR + 9)
-#define IRQ10_VECTOR (IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR (IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR (IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR (IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR (IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR (IRQ0_VECTOR + 15)
+#define ISA_IRQ_VECTOR(irq) (((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq)
/*
* Special IRQ vectors used by the SMP architecture, 0xf0-0xff
*/
#define X86_PLATFORM_IPI_VECTOR 0xf7
-/* Vector for KVM to deliver posted interrupt IPI */
-#ifdef CONFIG_HAVE_KVM
-#define POSTED_INTR_VECTOR 0xf2
-#endif
-
+#define POSTED_INTR_WAKEUP_VECTOR 0xf1
/*
* IRQ work vector:
*/
#define IRQ_WORK_VECTOR 0xf6
#define UV_BAU_MESSAGE 0xf5
+#define DEFERRED_ERROR_VECTOR 0xf4
/* Vector on which hypervisor callbacks will be delivered */
#define HYPERVISOR_CALLBACK_VECTOR 0xf3
+/* Vector for KVM to deliver posted interrupt IPI */
+#ifdef CONFIG_HAVE_KVM
+#define POSTED_INTR_VECTOR 0xf2
+#endif
+
/*
* Local APIC timer IRQ vector is on a different priority level,
* to work around the 'lost local interrupt if more than 2 IRQ
* static arrays.
*/
-#define NR_IRQS_LEGACY 16
+#define NR_IRQS_LEGACY 16
-#define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS )
+#define CPU_VECTOR_LIMIT (64 * NR_CPUS)
+#define IO_APIC_VECTOR_LIMIT (32 * MAX_IO_APICS)
-#ifdef CONFIG_X86_IO_APIC
-# define CPU_VECTOR_LIMIT (64 * NR_CPUS)
-# define NR_IRQS \
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI)
+#define NR_IRQS \
(CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \
(NR_VECTORS + CPU_VECTOR_LIMIT) : \
(NR_VECTORS + IO_APIC_VECTOR_LIMIT))
-#else /* !CONFIG_X86_IO_APIC: */
-# define NR_IRQS NR_IRQS_LEGACY
+#elif defined(CONFIG_X86_IO_APIC)
+#define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#elif defined(CONFIG_PCI_MSI)
+#define NR_IRQS (NR_VECTORS + CPU_VECTOR_LIMIT)
+#else
+#define NR_IRQS NR_IRQS_LEGACY
#endif
#endif /* _ASM_X86_IRQ_VECTORS_H */
--- /dev/null
+#ifndef _ASM_IRQDOMAIN_H
+#define _ASM_IRQDOMAIN_H
+
+#include <linux/irqdomain.h>
+#include <asm/hw_irq.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+enum {
+ /* Allocate contiguous CPU vectors */
+ X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1,
+};
+
+extern struct irq_domain *x86_vector_domain;
+
+extern void init_irq_alloc_info(struct irq_alloc_info *info,
+ const struct cpumask *mask);
+extern void copy_irq_alloc_info(struct irq_alloc_info *dst,
+ struct irq_alloc_info *src);
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#ifdef CONFIG_X86_IO_APIC
+struct device_node;
+struct irq_data;
+
+enum ioapic_domain_type {
+ IOAPIC_DOMAIN_INVALID,
+ IOAPIC_DOMAIN_LEGACY,
+ IOAPIC_DOMAIN_STRICT,
+ IOAPIC_DOMAIN_DYNAMIC,
+};
+
+struct ioapic_domain_cfg {
+ enum ioapic_domain_type type;
+ const struct irq_domain_ops *ops;
+ struct device_node *dev;
+};
+
+extern const struct irq_domain_ops mp_ioapic_irqdomain_ops;
+
+extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg);
+extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs);
+extern void mp_irqdomain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data);
+extern void mp_irqdomain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data);
+extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
+#endif /* CONFIG_X86_IO_APIC */
+
+#ifdef CONFIG_PCI_MSI
+extern void arch_init_msi_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_msi_domain(struct irq_domain *domain) { }
+#endif
+
+#ifdef CONFIG_HT_IRQ
+extern void arch_init_htirq_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_htirq_domain(struct irq_domain *domain) { }
+#endif
+
+#endif
unsigned nxe:1;
unsigned cr0_wp:1;
unsigned smep_andnot_wp:1;
+ unsigned smap_andnot_wp:1;
};
};
struct kvm_mmu_memory_cache mmu_page_header_cache;
struct fpu guest_fpu;
+ bool eager_fpu;
u64 xcr0;
u64 guest_supported_xcr0;
u32 guest_xstate_size;
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+ void (*fpu_activate)(struct kvm_vcpu *vcpu);
void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
void (*tlb_flush)(struct kvm_vcpu *vcpu);
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
-int fx_init(struct kvm_vcpu *vcpu);
-
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
const u8 *new, int bytes);
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */
#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */
+#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */
/* MCG_STATUS register defines */
#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */
#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */
#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */
+#define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */
+
+/* MCG_EXT_CTL register defines */
+#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */
/* MCi_STATUS register defines */
#define MCI_STATUS_VAL (1ULL<<63) /* valid error */
struct mca_config {
bool dont_log_ce;
bool cmci_disabled;
+ bool lmce_disabled;
bool ignore_ce;
bool disabled;
bool ser;
};
struct mce_vendor_flags {
- __u64 overflow_recov : 1, /* cpuid_ebx(80000007) */
- __reserved_0 : 63;
+ /*
+ * overflow recovery cpuid bit indicates that overflow
+ * conditions are not fatal
+ */
+ __u64 overflow_recov : 1,
+
+ /*
+ * SUCCOR stands for S/W UnCorrectable error COntainment
+ * and Recovery. It indicates support for data poisoning
+ * in HW and deferred error interrupts.
+ */
+ succor : 1,
+ __reserved_0 : 62;
};
extern struct mce_vendor_flags mce_flags;
void cmci_reenable(void);
void cmci_rediscover(void);
void cmci_recheck(void);
+void lmce_clear(void);
+void lmce_enable(void);
#else
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
static inline void cmci_clear(void) {}
static inline void cmci_reenable(void) {}
static inline void cmci_rediscover(void) {}
static inline void cmci_recheck(void) {}
+static inline void lmce_clear(void) {}
+static inline void lmce_enable(void) {}
#endif
#ifdef CONFIG_X86_MCE_AMD
extern void (*mce_threshold_vector)(void);
extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
+/* Deferred error interrupt handler */
+extern void (*deferred_error_int_vector)(void);
+
/*
* Thermal handler
*/
#ifndef _ASM_X86_MICROCODE_H
#define _ASM_X86_MICROCODE_H
+#include <linux/earlycpio.h>
+
#define native_rdmsr(msr, val1, val2) \
do { \
u64 __val = native_read_msr((msr)); \
extern void load_ucode_ap(void);
extern int __init save_microcode_in_initrd(void);
void reload_early_microcode(void);
+extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
#else
static inline void __init load_ucode_bsp(void) {}
static inline void load_ucode_ap(void) {}
return 0;
}
static inline void reload_early_microcode(void) {}
+static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+ return false;
+}
#endif
-
#endif /* _ASM_X86_MICROCODE_H */
extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
#ifdef CONFIG_MICROCODE_AMD_EARLY
-extern void __init load_ucode_amd_bsp(void);
+extern void __init load_ucode_amd_bsp(unsigned int family);
extern void load_ucode_amd_ap(void);
extern int __init save_microcode_in_initrd_amd(void);
void reload_ucode_amd(void);
#else
-static inline void __init load_ucode_amd_bsp(void) {}
+static inline void __init load_ucode_amd_bsp(unsigned int family) {}
static inline void load_ucode_amd_ap(void) {}
static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; }
void reload_ucode_amd(void) {}
(((struct microcode_intel *)mc)->hdr.datasize ? \
((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE)
-#define sigmatch(s1, s2, p1, p2) \
- (((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0))))
-
#define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
-extern int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc);
+extern int has_newer_microcode(void *mc, unsigned int csig, int cpf, int rev);
extern int microcode_sanity_check(void *mc, int print_err);
-extern int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc);
-
-static inline int
-revision_is_newer(struct microcode_header_intel *mc_header, int rev)
-{
- return (mc_header->rev <= rev) ? 0 : 1;
-}
+extern int find_matching_signature(void *mc, unsigned int csig, int cpf);
#ifdef CONFIG_MICROCODE_INTEL_EARLY
extern void __init load_ucode_intel_bsp(void);
paravirt_arch_exit_mmap(mm);
}
+#ifdef CONFIG_X86_64
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+ return !config_enabled(CONFIG_IA32_EMULATION) ||
+ !(mm->context.ia32_compat == TIF_IA32);
+}
+#else
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+ return false;
+}
+#endif
+
static inline void arch_bprm_mm_init(struct mm_struct *mm,
struct vm_area_struct *vma)
{
#define MPX_BNDCFG_ENABLE_FLAG 0x1
#define MPX_BD_ENTRY_VALID_FLAG 0x1
-#ifdef CONFIG_X86_64
-
-/* upper 28 bits [47:20] of the virtual address in 64-bit used to
- * index into bounds directory (BD).
- */
-#define MPX_BD_ENTRY_OFFSET 28
-#define MPX_BD_ENTRY_SHIFT 3
-/* bits [19:3] of the virtual address in 64-bit used to index into
- * bounds table (BT).
+/*
+ * The upper 28 bits [47:20] of the virtual address in 64-bit
+ * are used to index into bounds directory (BD).
+ *
+ * The directory is 2G (2^31) in size, and with 8-byte entries
+ * it has 2^28 entries.
*/
-#define MPX_BT_ENTRY_OFFSET 17
-#define MPX_BT_ENTRY_SHIFT 5
-#define MPX_IGN_BITS 3
-#define MPX_BD_ENTRY_TAIL 3
+#define MPX_BD_SIZE_BYTES_64 (1UL<<31)
+#define MPX_BD_ENTRY_BYTES_64 8
+#define MPX_BD_NR_ENTRIES_64 (MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64)
-#else
-
-#define MPX_BD_ENTRY_OFFSET 20
-#define MPX_BD_ENTRY_SHIFT 2
-#define MPX_BT_ENTRY_OFFSET 10
-#define MPX_BT_ENTRY_SHIFT 4
-#define MPX_IGN_BITS 2
-#define MPX_BD_ENTRY_TAIL 2
+/*
+ * The 32-bit directory is 4MB (2^22) in size, and with 4-byte
+ * entries it has 2^20 entries.
+ */
+#define MPX_BD_SIZE_BYTES_32 (1UL<<22)
+#define MPX_BD_ENTRY_BYTES_32 4
+#define MPX_BD_NR_ENTRIES_32 (MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32)
-#endif
+/*
+ * A 64-bit table is 4MB total in size, and an entry is
+ * 4 64-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_64 (1UL<<22)
+#define MPX_BT_ENTRY_BYTES_64 32
+#define MPX_BT_NR_ENTRIES_64 (MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64)
-#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
-#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
+/*
+ * A 32-bit table is 16kB total in size, and an entry is
+ * 4 32-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_32 (1UL<<14)
+#define MPX_BT_ENTRY_BYTES_32 16
+#define MPX_BT_NR_ENTRIES_32 (MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32)
#define MPX_BNDSTA_TAIL 2
#define MPX_BNDCFG_TAIL 12
#define MPX_BNDSTA_ADDR_MASK (~((1UL<<MPX_BNDSTA_TAIL)-1))
-#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
-#define MPX_BT_ADDR_MASK (~((1UL<<MPX_BD_ENTRY_TAIL)-1))
-
#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
#define MPX_BNDSTA_ERROR_CODE 0x3
-#define MPX_BD_ENTRY_MASK ((1<<MPX_BD_ENTRY_OFFSET)-1)
-#define MPX_BT_ENTRY_MASK ((1<<MPX_BT_ENTRY_OFFSET)-1)
-#define MPX_GET_BD_ENTRY_OFFSET(addr) ((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
- MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
-#define MPX_GET_BT_ENTRY_OFFSET(addr) ((((addr)>>MPX_IGN_BITS) & \
- MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
-
#ifdef CONFIG_X86_INTEL_MPX
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf);
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs);
+int mpx_handle_bd_fault(void);
static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
{
return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long start, unsigned long end);
#else
-static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf)
+static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
{
return NULL;
}
-static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+static inline int mpx_handle_bd_fault(void)
{
return -EINVAL;
}
--- /dev/null
+#ifndef _ASM_X86_MSI_H
+#define _ASM_X86_MSI_H
+#include <asm/hw_irq.h>
+
+typedef struct irq_alloc_info msi_alloc_info_t;
+
+#endif /* _ASM_X86_MSI_H */
--- /dev/null
+#ifndef _ASM_X86_MSR_INDEX_H
+#define _ASM_X86_MSR_INDEX_H
+
+/* CPU model specific register (MSR) numbers */
+
+/* x86-64 specific MSRs */
+#define MSR_EFER 0xc0000080 /* extended feature register */
+#define MSR_STAR 0xc0000081 /* legacy mode SYSCALL target */
+#define MSR_LSTAR 0xc0000082 /* long mode SYSCALL target */
+#define MSR_CSTAR 0xc0000083 /* compat mode SYSCALL target */
+#define MSR_SYSCALL_MASK 0xc0000084 /* EFLAGS mask for syscall */
+#define MSR_FS_BASE 0xc0000100 /* 64bit FS base */
+#define MSR_GS_BASE 0xc0000101 /* 64bit GS base */
+#define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX 0xc0000103 /* Auxiliary TSC */
+
+/* EFER bits: */
+#define _EFER_SCE 0 /* SYSCALL/SYSRET */
+#define _EFER_LME 8 /* Long mode enable */
+#define _EFER_LMA 10 /* Long mode active (read-only) */
+#define _EFER_NX 11 /* No execute enable */
+#define _EFER_SVME 12 /* Enable virtualization */
+#define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */
+#define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */
+
+#define EFER_SCE (1<<_EFER_SCE)
+#define EFER_LME (1<<_EFER_LME)
+#define EFER_LMA (1<<_EFER_LMA)
+#define EFER_NX (1<<_EFER_NX)
+#define EFER_SVME (1<<_EFER_SVME)
+#define EFER_LMSLE (1<<_EFER_LMSLE)
+#define EFER_FFXSR (1<<_EFER_FFXSR)
+
+/* Intel MSRs. Some also available on other CPUs */
+#define MSR_IA32_PERFCTR0 0x000000c1
+#define MSR_IA32_PERFCTR1 0x000000c2
+#define MSR_FSB_FREQ 0x000000cd
+#define MSR_NHM_PLATFORM_INFO 0x000000ce
+
+#define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2
+#define NHM_C3_AUTO_DEMOTE (1UL << 25)
+#define NHM_C1_AUTO_DEMOTE (1UL << 26)
+#define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25)
+#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
+#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
+
+#define MSR_PLATFORM_INFO 0x000000ce
+#define MSR_MTRRcap 0x000000fe
+#define MSR_IA32_BBL_CR_CTL 0x00000119
+#define MSR_IA32_BBL_CR_CTL3 0x0000011e
+
+#define MSR_IA32_SYSENTER_CS 0x00000174
+#define MSR_IA32_SYSENTER_ESP 0x00000175
+#define MSR_IA32_SYSENTER_EIP 0x00000176
+
+#define MSR_IA32_MCG_CAP 0x00000179
+#define MSR_IA32_MCG_STATUS 0x0000017a
+#define MSR_IA32_MCG_CTL 0x0000017b
+#define MSR_IA32_MCG_EXT_CTL 0x000004d0
+
+#define MSR_OFFCORE_RSP_0 0x000001a6
+#define MSR_OFFCORE_RSP_1 0x000001a7
+#define MSR_NHM_TURBO_RATIO_LIMIT 0x000001ad
+#define MSR_IVT_TURBO_RATIO_LIMIT 0x000001ae
+#define MSR_TURBO_RATIO_LIMIT 0x000001ad
+#define MSR_TURBO_RATIO_LIMIT1 0x000001ae
+#define MSR_TURBO_RATIO_LIMIT2 0x000001af
+
+#define MSR_LBR_SELECT 0x000001c8
+#define MSR_LBR_TOS 0x000001c9
+#define MSR_LBR_NHM_FROM 0x00000680
+#define MSR_LBR_NHM_TO 0x000006c0
+#define MSR_LBR_CORE_FROM 0x00000040
+#define MSR_LBR_CORE_TO 0x00000060
+
+#define MSR_IA32_PEBS_ENABLE 0x000003f1
+#define MSR_IA32_DS_AREA 0x00000600
+#define MSR_IA32_PERF_CAPABILITIES 0x00000345
+#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
+
+#define MSR_IA32_RTIT_CTL 0x00000570
+#define RTIT_CTL_TRACEEN BIT(0)
+#define RTIT_CTL_OS BIT(2)
+#define RTIT_CTL_USR BIT(3)
+#define RTIT_CTL_CR3EN BIT(7)
+#define RTIT_CTL_TOPA BIT(8)
+#define RTIT_CTL_TSC_EN BIT(10)
+#define RTIT_CTL_DISRETC BIT(11)
+#define RTIT_CTL_BRANCH_EN BIT(13)
+#define MSR_IA32_RTIT_STATUS 0x00000571
+#define RTIT_STATUS_CONTEXTEN BIT(1)
+#define RTIT_STATUS_TRIGGEREN BIT(2)
+#define RTIT_STATUS_ERROR BIT(4)
+#define RTIT_STATUS_STOPPED BIT(5)
+#define MSR_IA32_RTIT_CR3_MATCH 0x00000572
+#define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560
+#define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561
+
+#define MSR_MTRRfix64K_00000 0x00000250
+#define MSR_MTRRfix16K_80000 0x00000258
+#define MSR_MTRRfix16K_A0000 0x00000259
+#define MSR_MTRRfix4K_C0000 0x00000268
+#define MSR_MTRRfix4K_C8000 0x00000269
+#define MSR_MTRRfix4K_D0000 0x0000026a
+#define MSR_MTRRfix4K_D8000 0x0000026b
+#define MSR_MTRRfix4K_E0000 0x0000026c
+#define MSR_MTRRfix4K_E8000 0x0000026d
+#define MSR_MTRRfix4K_F0000 0x0000026e
+#define MSR_MTRRfix4K_F8000 0x0000026f
+#define MSR_MTRRdefType 0x000002ff
+
+#define MSR_IA32_CR_PAT 0x00000277
+
+#define MSR_IA32_DEBUGCTLMSR 0x000001d9
+#define MSR_IA32_LASTBRANCHFROMIP 0x000001db
+#define MSR_IA32_LASTBRANCHTOIP 0x000001dc
+#define MSR_IA32_LASTINTFROMIP 0x000001dd
+#define MSR_IA32_LASTINTTOIP 0x000001de
+
+/* DEBUGCTLMSR bits (others vary by model): */
+#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
+#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */
+#define DEBUGCTLMSR_TR (1UL << 6)
+#define DEBUGCTLMSR_BTS (1UL << 7)
+#define DEBUGCTLMSR_BTINT (1UL << 8)
+#define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9)
+#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11)
+
+#define MSR_IA32_POWER_CTL 0x000001fc
+
+#define MSR_IA32_MC0_CTL 0x00000400
+#define MSR_IA32_MC0_STATUS 0x00000401
+#define MSR_IA32_MC0_ADDR 0x00000402
+#define MSR_IA32_MC0_MISC 0x00000403
+
+/* C-state Residency Counters */
+#define MSR_PKG_C3_RESIDENCY 0x000003f8
+#define MSR_PKG_C6_RESIDENCY 0x000003f9
+#define MSR_PKG_C7_RESIDENCY 0x000003fa
+#define MSR_CORE_C3_RESIDENCY 0x000003fc
+#define MSR_CORE_C6_RESIDENCY 0x000003fd
+#define MSR_CORE_C7_RESIDENCY 0x000003fe
+#define MSR_KNL_CORE_C6_RESIDENCY 0x000003ff
+#define MSR_PKG_C2_RESIDENCY 0x0000060d
+#define MSR_PKG_C8_RESIDENCY 0x00000630
+#define MSR_PKG_C9_RESIDENCY 0x00000631
+#define MSR_PKG_C10_RESIDENCY 0x00000632
+
+/* Run Time Average Power Limiting (RAPL) Interface */
+
+#define MSR_RAPL_POWER_UNIT 0x00000606
+
+#define MSR_PKG_POWER_LIMIT 0x00000610
+#define MSR_PKG_ENERGY_STATUS 0x00000611
+#define MSR_PKG_PERF_STATUS 0x00000613
+#define MSR_PKG_POWER_INFO 0x00000614
+
+#define MSR_DRAM_POWER_LIMIT 0x00000618
+#define MSR_DRAM_ENERGY_STATUS 0x00000619
+#define MSR_DRAM_PERF_STATUS 0x0000061b
+#define MSR_DRAM_POWER_INFO 0x0000061c
+
+#define MSR_PP0_POWER_LIMIT 0x00000638
+#define MSR_PP0_ENERGY_STATUS 0x00000639
+#define MSR_PP0_POLICY 0x0000063a
+#define MSR_PP0_PERF_STATUS 0x0000063b
+
+#define MSR_PP1_POWER_LIMIT 0x00000640
+#define MSR_PP1_ENERGY_STATUS 0x00000641
+#define MSR_PP1_POLICY 0x00000642
+
+#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658
+#define MSR_PKG_ANY_CORE_C0_RES 0x00000659
+#define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A
+#define MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B
+
+#define MSR_CORE_C1_RES 0x00000660
+
+#define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668
+#define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669
+
+#define MSR_CORE_PERF_LIMIT_REASONS 0x00000690
+#define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0
+#define MSR_RING_PERF_LIMIT_REASONS 0x000006B1
+
+/* Hardware P state interface */
+#define MSR_PPERF 0x0000064e
+#define MSR_PERF_LIMIT_REASONS 0x0000064f
+#define MSR_PM_ENABLE 0x00000770
+#define MSR_HWP_CAPABILITIES 0x00000771
+#define MSR_HWP_REQUEST_PKG 0x00000772
+#define MSR_HWP_INTERRUPT 0x00000773
+#define MSR_HWP_REQUEST 0x00000774
+#define MSR_HWP_STATUS 0x00000777
+
+/* CPUID.6.EAX */
+#define HWP_BASE_BIT (1<<7)
+#define HWP_NOTIFICATIONS_BIT (1<<8)
+#define HWP_ACTIVITY_WINDOW_BIT (1<<9)
+#define HWP_ENERGY_PERF_PREFERENCE_BIT (1<<10)
+#define HWP_PACKAGE_LEVEL_REQUEST_BIT (1<<11)
+
+/* IA32_HWP_CAPABILITIES */
+#define HWP_HIGHEST_PERF(x) (x & 0xff)
+#define HWP_GUARANTEED_PERF(x) ((x & (0xff << 8)) >>8)
+#define HWP_MOSTEFFICIENT_PERF(x) ((x & (0xff << 16)) >>16)
+#define HWP_LOWEST_PERF(x) ((x & (0xff << 24)) >>24)
+
+/* IA32_HWP_REQUEST */
+#define HWP_MIN_PERF(x) (x & 0xff)
+#define HWP_MAX_PERF(x) ((x & 0xff) << 8)
+#define HWP_DESIRED_PERF(x) ((x & 0xff) << 16)
+#define HWP_ENERGY_PERF_PREFERENCE(x) ((x & 0xff) << 24)
+#define HWP_ACTIVITY_WINDOW(x) ((x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x) ((x & 0x1) << 42)
+
+/* IA32_HWP_STATUS */
+#define HWP_GUARANTEED_CHANGE(x) (x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM(x) (x & 0x4)
+
+/* IA32_HWP_INTERRUPT */
+#define HWP_CHANGE_TO_GUARANTEED_INT(x) (x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM_INT(x) (x & 0x2)
+
+#define MSR_AMD64_MC0_MASK 0xc0010044
+
+#define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x))
+#define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x))
+#define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x))
+#define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x))
+
+#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x))
+
+/* These are consecutive and not in the normal 4er MCE bank block */
+#define MSR_IA32_MC0_CTL2 0x00000280
+#define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x))
+
+#define MSR_P6_PERFCTR0 0x000000c1
+#define MSR_P6_PERFCTR1 0x000000c2
+#define MSR_P6_EVNTSEL0 0x00000186
+#define MSR_P6_EVNTSEL1 0x00000187
+
+#define MSR_KNC_PERFCTR0 0x00000020
+#define MSR_KNC_PERFCTR1 0x00000021
+#define MSR_KNC_EVNTSEL0 0x00000028
+#define MSR_KNC_EVNTSEL1 0x00000029
+
+/* Alternative perfctr range with full access. */
+#define MSR_IA32_PMC0 0x000004c1
+
+/* AMD64 MSRs. Not complete. See the architecture manual for a more
+ complete list. */
+
+#define MSR_AMD64_PATCH_LEVEL 0x0000008b
+#define MSR_AMD64_TSC_RATIO 0xc0000104
+#define MSR_AMD64_NB_CFG 0xc001001f
+#define MSR_AMD64_PATCH_LOADER 0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
+#define MSR_AMD64_OSVW_STATUS 0xc0010141
+#define MSR_AMD64_LS_CFG 0xc0011020
+#define MSR_AMD64_DC_CFG 0xc0011022
+#define MSR_AMD64_BU_CFG2 0xc001102a
+#define MSR_AMD64_IBSFETCHCTL 0xc0011030
+#define MSR_AMD64_IBSFETCHLINAD 0xc0011031
+#define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032
+#define MSR_AMD64_IBSFETCH_REG_COUNT 3
+#define MSR_AMD64_IBSFETCH_REG_MASK ((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
+#define MSR_AMD64_IBSOPCTL 0xc0011033
+#define MSR_AMD64_IBSOPRIP 0xc0011034
+#define MSR_AMD64_IBSOPDATA 0xc0011035
+#define MSR_AMD64_IBSOPDATA2 0xc0011036
+#define MSR_AMD64_IBSOPDATA3 0xc0011037
+#define MSR_AMD64_IBSDCLINAD 0xc0011038
+#define MSR_AMD64_IBSDCPHYSAD 0xc0011039
+#define MSR_AMD64_IBSOP_REG_COUNT 7
+#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
+#define MSR_AMD64_IBSCTL 0xc001103a
+#define MSR_AMD64_IBSBRTARGET 0xc001103b
+#define MSR_AMD64_IBSOPDATA4 0xc001103d
+#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
+
+/* Fam 16h MSRs */
+#define MSR_F16H_L2I_PERF_CTL 0xc0010230
+#define MSR_F16H_L2I_PERF_CTR 0xc0010231
+#define MSR_F16H_DR1_ADDR_MASK 0xc0011019
+#define MSR_F16H_DR2_ADDR_MASK 0xc001101a
+#define MSR_F16H_DR3_ADDR_MASK 0xc001101b
+#define MSR_F16H_DR0_ADDR_MASK 0xc0011027
+
+/* Fam 15h MSRs */
+#define MSR_F15H_PERF_CTL 0xc0010200
+#define MSR_F15H_PERF_CTR 0xc0010201
+#define MSR_F15H_NB_PERF_CTL 0xc0010240
+#define MSR_F15H_NB_PERF_CTR 0xc0010241
+
+/* Fam 10h MSRs */
+#define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058
+#define FAM10H_MMIO_CONF_ENABLE (1<<0)
+#define FAM10H_MMIO_CONF_BUSRANGE_MASK 0xf
+#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
+#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL
+#define FAM10H_MMIO_CONF_BASE_SHIFT 20
+#define MSR_FAM10H_NODE_ID 0xc001100c
+
+/* K8 MSRs */
+#define MSR_K8_TOP_MEM1 0xc001001a
+#define MSR_K8_TOP_MEM2 0xc001001d
+#define MSR_K8_SYSCFG 0xc0010010
+#define MSR_K8_INT_PENDING_MSG 0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK 0x18000000
+#define MSR_K8_TSEG_ADDR 0xc0010112
+#define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */
+#define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */
+#define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */
+
+/* K7 MSRs */
+#define MSR_K7_EVNTSEL0 0xc0010000
+#define MSR_K7_PERFCTR0 0xc0010004
+#define MSR_K7_EVNTSEL1 0xc0010001
+#define MSR_K7_PERFCTR1 0xc0010005
+#define MSR_K7_EVNTSEL2 0xc0010002
+#define MSR_K7_PERFCTR2 0xc0010006
+#define MSR_K7_EVNTSEL3 0xc0010003
+#define MSR_K7_PERFCTR3 0xc0010007
+#define MSR_K7_CLK_CTL 0xc001001b
+#define MSR_K7_HWCR 0xc0010015
+#define MSR_K7_FID_VID_CTL 0xc0010041
+#define MSR_K7_FID_VID_STATUS 0xc0010042
+
+/* K6 MSRs */
+#define MSR_K6_WHCR 0xc0000082
+#define MSR_K6_UWCCR 0xc0000085
+#define MSR_K6_EPMR 0xc0000086
+#define MSR_K6_PSOR 0xc0000087
+#define MSR_K6_PFIR 0xc0000088
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1 0x00000107
+#define MSR_IDT_FCR2 0x00000108
+#define MSR_IDT_FCR3 0x00000109
+#define MSR_IDT_FCR4 0x0000010a
+
+#define MSR_IDT_MCR0 0x00000110
+#define MSR_IDT_MCR1 0x00000111
+#define MSR_IDT_MCR2 0x00000112
+#define MSR_IDT_MCR3 0x00000113
+#define MSR_IDT_MCR4 0x00000114
+#define MSR_IDT_MCR5 0x00000115
+#define MSR_IDT_MCR6 0x00000116
+#define MSR_IDT_MCR7 0x00000117
+#define MSR_IDT_MCR_CTRL 0x00000120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR 0x00001107
+#define MSR_VIA_LONGHAUL 0x0000110a
+#define MSR_VIA_RNG 0x0000110b
+#define MSR_VIA_BCR2 0x00001147
+
+/* Transmeta defined MSRs */
+#define MSR_TMTA_LONGRUN_CTRL 0x80868010
+#define MSR_TMTA_LONGRUN_FLAGS 0x80868011
+#define MSR_TMTA_LRTI_READOUT 0x80868018
+#define MSR_TMTA_LRTI_VOLT_MHZ 0x8086801a
+
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR 0x00000000
+#define MSR_IA32_P5_MC_TYPE 0x00000001
+#define MSR_IA32_TSC 0x00000010
+#define MSR_IA32_PLATFORM_ID 0x00000017
+#define MSR_IA32_EBL_CR_POWERON 0x0000002a
+#define MSR_EBC_FREQUENCY_ID 0x0000002c
+#define MSR_SMI_COUNT 0x00000034
+#define MSR_IA32_FEATURE_CONTROL 0x0000003a
+#define MSR_IA32_TSC_ADJUST 0x0000003b
+#define MSR_IA32_BNDCFGS 0x00000d90
+
+#define MSR_IA32_XSS 0x00000da0
+
+#define FEATURE_CONTROL_LOCKED (1<<0)
+#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1)
+#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2)
+#define FEATURE_CONTROL_LMCE (1<<20)
+
+#define MSR_IA32_APICBASE 0x0000001b
+#define MSR_IA32_APICBASE_BSP (1<<8)
+#define MSR_IA32_APICBASE_ENABLE (1<<11)
+#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
+
+#define MSR_IA32_TSCDEADLINE 0x000006e0
+
+#define MSR_IA32_UCODE_WRITE 0x00000079
+#define MSR_IA32_UCODE_REV 0x0000008b
+
+#define MSR_IA32_SMM_MONITOR_CTL 0x0000009b
+#define MSR_IA32_SMBASE 0x0000009e
+
+#define MSR_IA32_PERF_STATUS 0x00000198
+#define MSR_IA32_PERF_CTL 0x00000199
+#define INTEL_PERF_CTL_MASK 0xffff
+#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064
+#define MSR_AMD_PERF_STATUS 0xc0010063
+#define MSR_AMD_PERF_CTL 0xc0010062
+
+#define MSR_IA32_MPERF 0x000000e7
+#define MSR_IA32_APERF 0x000000e8
+
+#define MSR_IA32_THERM_CONTROL 0x0000019a
+#define MSR_IA32_THERM_INTERRUPT 0x0000019b
+
+#define THERM_INT_HIGH_ENABLE (1 << 0)
+#define THERM_INT_LOW_ENABLE (1 << 1)
+#define THERM_INT_PLN_ENABLE (1 << 24)
+
+#define MSR_IA32_THERM_STATUS 0x0000019c
+
+#define THERM_STATUS_PROCHOT (1 << 0)
+#define THERM_STATUS_POWER_LIMIT (1 << 10)
+
+#define MSR_THERM2_CTL 0x0000019d
+
+#define MSR_THERM2_CTL_TM_SELECT (1ULL << 16)
+
+#define MSR_IA32_MISC_ENABLE 0x000001a0
+
+#define MSR_IA32_TEMPERATURE_TARGET 0x000001a2
+
+#define MSR_MISC_PWR_MGMT 0x000001aa
+
+#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
+#define ENERGY_PERF_BIAS_PERFORMANCE 0
+#define ENERGY_PERF_BIAS_NORMAL 6
+#define ENERGY_PERF_BIAS_POWERSAVE 15
+
+#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1
+
+#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0)
+#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10)
+
+#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2
+
+#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0)
+#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1)
+#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24)
+
+/* Thermal Thresholds Support */
+#define THERM_INT_THRESHOLD0_ENABLE (1 << 15)
+#define THERM_SHIFT_THRESHOLD0 8
+#define THERM_MASK_THRESHOLD0 (0x7f << THERM_SHIFT_THRESHOLD0)
+#define THERM_INT_THRESHOLD1_ENABLE (1 << 23)
+#define THERM_SHIFT_THRESHOLD1 16
+#define THERM_MASK_THRESHOLD1 (0x7f << THERM_SHIFT_THRESHOLD1)
+#define THERM_STATUS_THRESHOLD0 (1 << 6)
+#define THERM_LOG_THRESHOLD0 (1 << 7)
+#define THERM_STATUS_THRESHOLD1 (1 << 8)
+#define THERM_LOG_THRESHOLD1 (1 << 9)
+
+/* MISC_ENABLE bits: architectural */
+#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT 0
+#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
+#define MSR_IA32_MISC_ENABLE_TCC_BIT 1
+#define MSR_IA32_MISC_ENABLE_TCC (1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
+#define MSR_IA32_MISC_ENABLE_EMON_BIT 7
+#define MSR_IA32_MISC_ENABLE_EMON (1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT 11
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT 12
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT 16
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
+#define MSR_IA32_MISC_ENABLE_MWAIT_BIT 18
+#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT 22
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT 23
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT 34
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
+
+/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT 2
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT (1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
+#define MSR_IA32_MISC_ENABLE_TM1_BIT 3
+#define MSR_IA32_MISC_ENABLE_TM1 (1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT 4
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT 6
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT 8
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT 9
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_BIT 10
+#define MSR_IA32_MISC_ENABLE_FERR (1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT 10
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX (1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
+#define MSR_IA32_MISC_ENABLE_TM2_BIT 13
+#define MSR_IA32_MISC_ENABLE_TM2 (1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT 19
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT 20
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT 24
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT (1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT 37
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT 38
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
+
+#define MSR_IA32_TSC_DEADLINE 0x000006E0
+
+/* P4/Xeon+ specific */
+#define MSR_IA32_MCG_EAX 0x00000180
+#define MSR_IA32_MCG_EBX 0x00000181
+#define MSR_IA32_MCG_ECX 0x00000182
+#define MSR_IA32_MCG_EDX 0x00000183
+#define MSR_IA32_MCG_ESI 0x00000184
+#define MSR_IA32_MCG_EDI 0x00000185
+#define MSR_IA32_MCG_EBP 0x00000186
+#define MSR_IA32_MCG_ESP 0x00000187
+#define MSR_IA32_MCG_EFLAGS 0x00000188
+#define MSR_IA32_MCG_EIP 0x00000189
+#define MSR_IA32_MCG_RESERVED 0x0000018a
+
+/* Pentium IV performance counter MSRs */
+#define MSR_P4_BPU_PERFCTR0 0x00000300
+#define MSR_P4_BPU_PERFCTR1 0x00000301
+#define MSR_P4_BPU_PERFCTR2 0x00000302
+#define MSR_P4_BPU_PERFCTR3 0x00000303
+#define MSR_P4_MS_PERFCTR0 0x00000304
+#define MSR_P4_MS_PERFCTR1 0x00000305
+#define MSR_P4_MS_PERFCTR2 0x00000306
+#define MSR_P4_MS_PERFCTR3 0x00000307
+#define MSR_P4_FLAME_PERFCTR0 0x00000308
+#define MSR_P4_FLAME_PERFCTR1 0x00000309
+#define MSR_P4_FLAME_PERFCTR2 0x0000030a
+#define MSR_P4_FLAME_PERFCTR3 0x0000030b
+#define MSR_P4_IQ_PERFCTR0 0x0000030c
+#define MSR_P4_IQ_PERFCTR1 0x0000030d
+#define MSR_P4_IQ_PERFCTR2 0x0000030e
+#define MSR_P4_IQ_PERFCTR3 0x0000030f
+#define MSR_P4_IQ_PERFCTR4 0x00000310
+#define MSR_P4_IQ_PERFCTR5 0x00000311
+#define MSR_P4_BPU_CCCR0 0x00000360
+#define MSR_P4_BPU_CCCR1 0x00000361
+#define MSR_P4_BPU_CCCR2 0x00000362
+#define MSR_P4_BPU_CCCR3 0x00000363
+#define MSR_P4_MS_CCCR0 0x00000364
+#define MSR_P4_MS_CCCR1 0x00000365
+#define MSR_P4_MS_CCCR2 0x00000366
+#define MSR_P4_MS_CCCR3 0x00000367
+#define MSR_P4_FLAME_CCCR0 0x00000368
+#define MSR_P4_FLAME_CCCR1 0x00000369
+#define MSR_P4_FLAME_CCCR2 0x0000036a
+#define MSR_P4_FLAME_CCCR3 0x0000036b
+#define MSR_P4_IQ_CCCR0 0x0000036c
+#define MSR_P4_IQ_CCCR1 0x0000036d
+#define MSR_P4_IQ_CCCR2 0x0000036e
+#define MSR_P4_IQ_CCCR3 0x0000036f
+#define MSR_P4_IQ_CCCR4 0x00000370
+#define MSR_P4_IQ_CCCR5 0x00000371
+#define MSR_P4_ALF_ESCR0 0x000003ca
+#define MSR_P4_ALF_ESCR1 0x000003cb
+#define MSR_P4_BPU_ESCR0 0x000003b2
+#define MSR_P4_BPU_ESCR1 0x000003b3
+#define MSR_P4_BSU_ESCR0 0x000003a0
+#define MSR_P4_BSU_ESCR1 0x000003a1
+#define MSR_P4_CRU_ESCR0 0x000003b8
+#define MSR_P4_CRU_ESCR1 0x000003b9
+#define MSR_P4_CRU_ESCR2 0x000003cc
+#define MSR_P4_CRU_ESCR3 0x000003cd
+#define MSR_P4_CRU_ESCR4 0x000003e0
+#define MSR_P4_CRU_ESCR5 0x000003e1
+#define MSR_P4_DAC_ESCR0 0x000003a8
+#define MSR_P4_DAC_ESCR1 0x000003a9
+#define MSR_P4_FIRM_ESCR0 0x000003a4
+#define MSR_P4_FIRM_ESCR1 0x000003a5
+#define MSR_P4_FLAME_ESCR0 0x000003a6
+#define MSR_P4_FLAME_ESCR1 0x000003a7
+#define MSR_P4_FSB_ESCR0 0x000003a2
+#define MSR_P4_FSB_ESCR1 0x000003a3
+#define MSR_P4_IQ_ESCR0 0x000003ba
+#define MSR_P4_IQ_ESCR1 0x000003bb
+#define MSR_P4_IS_ESCR0 0x000003b4
+#define MSR_P4_IS_ESCR1 0x000003b5
+#define MSR_P4_ITLB_ESCR0 0x000003b6
+#define MSR_P4_ITLB_ESCR1 0x000003b7
+#define MSR_P4_IX_ESCR0 0x000003c8
+#define MSR_P4_IX_ESCR1 0x000003c9
+#define MSR_P4_MOB_ESCR0 0x000003aa
+#define MSR_P4_MOB_ESCR1 0x000003ab
+#define MSR_P4_MS_ESCR0 0x000003c0
+#define MSR_P4_MS_ESCR1 0x000003c1
+#define MSR_P4_PMH_ESCR0 0x000003ac
+#define MSR_P4_PMH_ESCR1 0x000003ad
+#define MSR_P4_RAT_ESCR0 0x000003bc
+#define MSR_P4_RAT_ESCR1 0x000003bd
+#define MSR_P4_SAAT_ESCR0 0x000003ae
+#define MSR_P4_SAAT_ESCR1 0x000003af
+#define MSR_P4_SSU_ESCR0 0x000003be
+#define MSR_P4_SSU_ESCR1 0x000003bf /* guess: not in manual */
+
+#define MSR_P4_TBPU_ESCR0 0x000003c2
+#define MSR_P4_TBPU_ESCR1 0x000003c3
+#define MSR_P4_TC_ESCR0 0x000003c4
+#define MSR_P4_TC_ESCR1 0x000003c5
+#define MSR_P4_U2L_ESCR0 0x000003b0
+#define MSR_P4_U2L_ESCR1 0x000003b1
+
+#define MSR_P4_PEBS_MATRIX_VERT 0x000003f2
+
+/* Intel Core-based CPU performance counters */
+#define MSR_CORE_PERF_FIXED_CTR0 0x00000309
+#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a
+#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d
+#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e
+#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390
+
+/* Geode defined MSRs */
+#define MSR_GEODE_BUSCONT_CONF0 0x00001900
+
+/* Intel VT MSRs */
+#define MSR_IA32_VMX_BASIC 0x00000480
+#define MSR_IA32_VMX_PINBASED_CTLS 0x00000481
+#define MSR_IA32_VMX_PROCBASED_CTLS 0x00000482
+#define MSR_IA32_VMX_EXIT_CTLS 0x00000483
+#define MSR_IA32_VMX_ENTRY_CTLS 0x00000484
+#define MSR_IA32_VMX_MISC 0x00000485
+#define MSR_IA32_VMX_CR0_FIXED0 0x00000486
+#define MSR_IA32_VMX_CR0_FIXED1 0x00000487
+#define MSR_IA32_VMX_CR4_FIXED0 0x00000488
+#define MSR_IA32_VMX_CR4_FIXED1 0x00000489
+#define MSR_IA32_VMX_VMCS_ENUM 0x0000048a
+#define MSR_IA32_VMX_PROCBASED_CTLS2 0x0000048b
+#define MSR_IA32_VMX_EPT_VPID_CAP 0x0000048c
+#define MSR_IA32_VMX_TRUE_PINBASED_CTLS 0x0000048d
+#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e
+#define MSR_IA32_VMX_TRUE_EXIT_CTLS 0x0000048f
+#define MSR_IA32_VMX_TRUE_ENTRY_CTLS 0x00000490
+#define MSR_IA32_VMX_VMFUNC 0x00000491
+
+/* VMX_BASIC bits and bitmasks */
+#define VMX_BASIC_VMCS_SIZE_SHIFT 32
+#define VMX_BASIC_TRUE_CTLS (1ULL << 55)
+#define VMX_BASIC_64 0x0001000000000000LLU
+#define VMX_BASIC_MEM_TYPE_SHIFT 50
+#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU
+#define VMX_BASIC_MEM_TYPE_WB 6LLU
+#define VMX_BASIC_INOUT 0x0040000000000000LLU
+
+/* MSR_IA32_VMX_MISC bits */
+#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
+#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
+/* AMD-V MSRs */
+
+#define MSR_VM_CR 0xc0010114
+#define MSR_VM_IGNNE 0xc0010115
+#define MSR_VM_HSAVE_PA 0xc0010117
+
+#endif /* _ASM_X86_MSR_INDEX_H */
#ifndef _ASM_X86_MSR_H
#define _ASM_X86_MSR_H
-#include <uapi/asm/msr.h>
+#include "msr-index.h"
#ifndef __ASSEMBLY__
#include <asm/asm.h>
#include <asm/errno.h>
#include <asm/cpumask.h>
+#include <uapi/asm/msr.h>
struct msr {
union {
#endif /* !CONFIG_PARAVIRT */
-#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \
- (u32)((val) >> 32))
+/*
+ * 64-bit version of wrmsr_safe():
+ */
+static inline int wrmsrl_safe(u32 msr, u64 val)
+{
+ return wrmsr_safe(msr, (u32)val, (u32)(val >> 32));
+}
#define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high))
* arch_phys_wc_add and arch_phys_wc_del.
*/
# ifdef CONFIG_MTRR
-extern u8 mtrr_type_lookup(u64 addr, u64 end);
+extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform);
extern void mtrr_save_fixed_ranges(void *);
extern void mtrr_save_state(void);
extern int mtrr_add(unsigned long base, unsigned long size,
extern void mtrr_bp_restore(void);
extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
extern int amd_special_default_mtrr(void);
-extern int phys_wc_to_mtrr_index(int handle);
# else
-static inline u8 mtrr_type_lookup(u64 addr, u64 end)
+static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform)
{
/*
* Return no-MTRRs:
*/
- return 0xff;
+ return MTRR_TYPE_INVALID;
}
#define mtrr_save_fixed_ranges(arg) do {} while (0)
#define mtrr_save_state() do {} while (0)
static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
{
}
-static inline int phys_wc_to_mtrr_index(int handle)
-{
- return -1;
-}
#define mtrr_ap_init() do {} while (0)
#define mtrr_bp_init() do {} while (0)
_IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry32)
#endif /* CONFIG_COMPAT */
+/* Bit fields for enabled in struct mtrr_state_type */
+#define MTRR_STATE_MTRR_FIXED_ENABLED 0x01
+#define MTRR_STATE_MTRR_ENABLED 0x02
+
#endif /* _ASM_X86_MTRR_H */
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
+ u32 val)
+{
+ PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val);
+}
+
+static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
+{
+ PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock);
+}
+
+static __always_inline void pv_wait(u8 *ptr, u8 val)
+{
+ PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+}
+
+static __always_inline void pv_kick(int cpu)
+{
+ PVOP_VCALL1(pv_lock_ops.kick, cpu);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
__ticket_t ticket)
{
PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
}
-#endif
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+#endif /* SMP && PARAVIRT_SPINLOCKS */
#ifdef CONFIG_X86_32
#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
u64 (*read_pmc)(int counter);
unsigned long long (*read_tscp)(unsigned int *aux);
+#ifdef CONFIG_X86_32
/*
* Atomically enable interrupts and return to userspace. This
- * is only ever used to return to 32-bit processes; in a
- * 64-bit kernel, it's used for 32-on-64 compat processes, but
- * never native 64-bit processes. (Jump, not call.)
+ * is only used in 32-bit kernels. 64-bit kernels use
+ * usergs_sysret32 instead.
*/
void (*irq_enable_sysexit)(void);
+#endif
/*
* Switch to usermode gs and return to 64-bit usermode using
typedef u16 __ticket_t;
#endif
+struct qspinlock;
+
struct pv_lock_ops {
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
+ struct paravirt_callee_save queued_spin_unlock;
+
+ void (*wait)(u8 *ptr, u8 val);
+ void (*kick)(int cpu);
+#else /* !CONFIG_QUEUED_SPINLOCKS */
struct paravirt_callee_save lock_spinning;
void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
};
/* This contains all the paravirt structures: we get a convenient
#include <linux/types.h>
#include <asm/pgtable_types.h>
-#ifdef CONFIG_X86_PAT
-extern int pat_enabled;
-#else
-static const int pat_enabled;
-#endif
-
+bool pat_enabled(void);
extern void pat_init(void);
-void pat_init_cache_modes(void);
+void pat_init_cache_modes(u64);
extern int reserve_memtype(u64 start, u64 end,
enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
#ifdef CONFIG_PCI_MSI
/* implemented in arch/x86/kernel/apic/io_apic. */
struct msi_desc;
-void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq,
- unsigned int dest, struct msi_msg *msg, u8 hpet_id);
int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
void native_teardown_msi_irq(unsigned int irq);
void native_restore_msi_irqs(struct pci_dev *dev);
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- unsigned int irq_base, unsigned int irq_offset);
#else
-#define native_compose_msi_msg NULL
#define native_setup_msi_irqs NULL
#define native_teardown_msi_irq NULL
#endif
* requested memtype:
* - request is uncached, return cannot be write-back
* - request is write-combine, return cannot be write-back
+ * - request is write-through, return cannot be write-back
+ * - request is write-through, return cannot be write-combine
*/
if ((pcm == _PAGE_CACHE_MODE_UC_MINUS &&
new_pcm == _PAGE_CACHE_MODE_WB) ||
(pcm == _PAGE_CACHE_MODE_WC &&
- new_pcm == _PAGE_CACHE_MODE_WB)) {
+ new_pcm == _PAGE_CACHE_MODE_WB) ||
+ (pcm == _PAGE_CACHE_MODE_WT &&
+ new_pcm == _PAGE_CACHE_MODE_WB) ||
+ (pcm == _PAGE_CACHE_MODE_WT &&
+ new_pcm == _PAGE_CACHE_MODE_WC)) {
return 0;
}
#define pgprot_writecombine pgprot_writecombine
extern pgprot_t pgprot_writecombine(pgprot_t prot);
+#define pgprot_writethrough pgprot_writethrough
+extern pgprot_t pgprot_writethrough(pgprot_t prot);
+
/* Indicate that x86 has its own track and untrack pfn vma functions */
#define __HAVE_PFNMAP_TRACKING
extern asmlinkage void ___preempt_schedule(void);
# define __preempt_schedule() asm ("call ___preempt_schedule")
extern asmlinkage void preempt_schedule(void);
-# ifdef CONFIG_CONTEXT_TRACKING
- extern asmlinkage void ___preempt_schedule_context(void);
-# define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
- extern asmlinkage void preempt_schedule_context(void);
-# endif
+ extern asmlinkage void ___preempt_schedule_notrace(void);
+# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace")
+ extern asmlinkage void preempt_schedule_notrace(void);
#endif
#endif /* __ASM_PREEMPT_H */
#include <asm/desc_defs.h>
#include <asm/nops.h>
#include <asm/special_insns.h>
+#include <asm/fpu/types.h>
#include <linux/personality.h>
#include <linux/cpumask.h>
return pc;
}
+/*
+ * These alignment constraints are for performance in the vSMP case,
+ * but in the task_struct case we must also meet hardware imposed
+ * alignment requirements of the FPU state:
+ */
#ifdef CONFIG_X86_VSMP
# define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT)
# define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT)
#else
-# define ARCH_MIN_TASKALIGN 16
+# define ARCH_MIN_TASKALIGN __alignof__(union fpregs_state)
# define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif
#define cache_line_size() (boot_cpu_data.x86_cache_alignment)
extern void cpu_detect(struct cpuinfo_x86 *c);
-extern void fpu_detect(struct cpuinfo_x86 *c);
extern void early_cpu_init(void);
extern void identify_boot_cpu(void);
unsigned long ist[7];
};
-#define MXCSR_DEFAULT 0x1f80
-
-struct i387_fsave_struct {
- u32 cwd; /* FPU Control Word */
- u32 swd; /* FPU Status Word */
- u32 twd; /* FPU Tag Word */
- u32 fip; /* FPU IP Offset */
- u32 fcs; /* FPU IP Selector */
- u32 foo; /* FPU Operand Pointer Offset */
- u32 fos; /* FPU Operand Pointer Selector */
-
- /* 8*10 bytes for each FP-reg = 80 bytes: */
- u32 st_space[20];
-
- /* Software status information [not touched by FSAVE ]: */
- u32 status;
-};
-
-struct i387_fxsave_struct {
- u16 cwd; /* Control Word */
- u16 swd; /* Status Word */
- u16 twd; /* Tag Word */
- u16 fop; /* Last Instruction Opcode */
- union {
- struct {
- u64 rip; /* Instruction Pointer */
- u64 rdp; /* Data Pointer */
- };
- struct {
- u32 fip; /* FPU IP Offset */
- u32 fcs; /* FPU IP Selector */
- u32 foo; /* FPU Operand Offset */
- u32 fos; /* FPU Operand Selector */
- };
- };
- u32 mxcsr; /* MXCSR Register State */
- u32 mxcsr_mask; /* MXCSR Mask */
-
- /* 8*16 bytes for each FP-reg = 128 bytes: */
- u32 st_space[32];
-
- /* 16*16 bytes for each XMM-reg = 256 bytes: */
- u32 xmm_space[64];
-
- u32 padding[12];
-
- union {
- u32 padding1[12];
- u32 sw_reserved[12];
- };
-
-} __attribute__((aligned(16)));
-
-struct i387_soft_struct {
- u32 cwd;
- u32 swd;
- u32 twd;
- u32 fip;
- u32 fcs;
- u32 foo;
- u32 fos;
- /* 8*10 bytes for each FP-reg = 80 bytes: */
- u32 st_space[20];
- u8 ftop;
- u8 changed;
- u8 lookahead;
- u8 no_update;
- u8 rm;
- u8 alimit;
- struct math_emu_info *info;
- u32 entry_eip;
-};
-
-struct ymmh_struct {
- /* 16 * 16 bytes for each YMMH-reg = 256 bytes */
- u32 ymmh_space[64];
-};
-
-/* We don't support LWP yet: */
-struct lwp_struct {
- u8 reserved[128];
-};
-
-struct bndreg {
- u64 lower_bound;
- u64 upper_bound;
-} __packed;
-
-struct bndcsr {
- u64 bndcfgu;
- u64 bndstatus;
-} __packed;
-
-struct xsave_hdr_struct {
- u64 xstate_bv;
- u64 xcomp_bv;
- u64 reserved[6];
-} __attribute__((packed));
-
-struct xsave_struct {
- struct i387_fxsave_struct i387;
- struct xsave_hdr_struct xsave_hdr;
- struct ymmh_struct ymmh;
- struct lwp_struct lwp;
- struct bndreg bndreg[4];
- struct bndcsr bndcsr;
- /* new processor state extensions will go here */
-} __attribute__ ((packed, aligned (64)));
-
-union thread_xstate {
- struct i387_fsave_struct fsave;
- struct i387_fxsave_struct fxsave;
- struct i387_soft_struct soft;
- struct xsave_struct xsave;
-};
-
-struct fpu {
- unsigned int last_cpu;
- unsigned int has_fpu;
- union thread_xstate *state;
-};
-
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(struct orig_ist, orig_ist);
#endif /* X86_64 */
extern unsigned int xstate_size;
-extern void free_thread_xstate(struct task_struct *);
-extern struct kmem_cache *task_xstate_cachep;
struct perf_event;
unsigned long fs;
#endif
unsigned long gs;
+
+ /* Floating point and extended processor state */
+ struct fpu fpu;
+
/* Save middle states of ptrace breakpoints */
struct perf_event *ptrace_bps[HBP_NUM];
/* Debug status used for traps, single steps, etc... */
unsigned long cr2;
unsigned long trap_nr;
unsigned long error_code;
- /* floating point and extended processor state */
- struct fpu fpu;
#ifdef CONFIG_X86_32
/* Virtual 86 mode info */
struct vm86_struct __user *vm86_info;
unsigned long iopl;
/* Max allowed port in the bitmap, in bytes: */
unsigned io_bitmap_max;
- /*
- * fpu_counter contains the number of consecutive context switches
- * that the FPU is used. If this is over a threshold, the lazy fpu
- * saving becomes unlazy to save the trap. This is an unsigned char
- * so that after 256 times the counter wraps and the behavior turns
- * lazy again; this to deal with bursty apps that only use FPU for
- * a short time
- */
- unsigned char fpu_counter;
};
/*
extern int set_tsc_mode(unsigned int val);
/* Register/unregister a process' MPX related resource */
-#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk))
-#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk))
+#define MPX_ENABLE_MANAGEMENT() mpx_enable_management()
+#define MPX_DISABLE_MANAGEMENT() mpx_disable_management()
#ifdef CONFIG_X86_INTEL_MPX
-extern int mpx_enable_management(struct task_struct *tsk);
-extern int mpx_disable_management(struct task_struct *tsk);
+extern int mpx_enable_management(void);
+extern int mpx_disable_management(void);
#else
-static inline int mpx_enable_management(struct task_struct *tsk)
+static inline int mpx_enable_management(void)
{
return -EINVAL;
}
-static inline int mpx_disable_management(struct task_struct *tsk)
+static inline int mpx_disable_management(void)
{
return -EINVAL;
}
#endif /* CONFIG_X86_INTEL_MPX */
extern u16 amd_get_nb_id(int cpu);
+extern u32 amd_get_nodes_per_socket(void);
static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
{
/* misc architecture specific prototypes */
-void system_call(void);
void syscall_init(void);
-void ia32_syscall(void);
-void ia32_cstar_target(void);
-void ia32_sysenter_target(void);
+void entry_SYSCALL_64(void);
+void entry_SYSCALL_compat(void);
+void entry_INT80_32(void);
+void entry_INT80_compat(void);
+void entry_SYSENTER_32(void);
+void entry_SYSENTER_compat(void);
void x86_configure_nx(void);
void x86_report_nx(void);
static inline int user_mode(struct pt_regs *regs)
{
#ifdef CONFIG_X86_32
- return (regs->cs & SEGMENT_RPL_MASK) == USER_RPL;
+ return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL;
#else
return !!(regs->cs & 3);
#endif
--- /dev/null
+#ifndef _ASM_X86_QSPINLOCK_H
+#define _ASM_X86_QSPINLOCK_H
+
+#include <asm/cpufeature.h>
+#include <asm-generic/qspinlock_types.h>
+#include <asm/paravirt.h>
+
+#define queued_spin_unlock queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * A smp_store_release() on the least-significant byte.
+ */
+static inline void native_queued_spin_unlock(struct qspinlock *lock)
+{
+ smp_store_release((u8 *)lock, 0);
+}
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+
+static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+ pv_queued_spin_lock_slowpath(lock, val);
+}
+
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ pv_queued_spin_unlock(lock);
+}
+#else
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ native_queued_spin_unlock(lock);
+}
+#endif
+
+#define virt_queued_spin_lock virt_queued_spin_lock
+
+static inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+ if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+ return false;
+
+ while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0)
+ cpu_relax();
+
+ return true;
+}
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_X86_QSPINLOCK_H */
--- /dev/null
+#ifndef __ASM_QSPINLOCK_PARAVIRT_H
+#define __ASM_QSPINLOCK_PARAVIRT_H
+
+PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
+
+#endif
#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8)
#ifdef __KERNEL__
+
+/*
+ * early_idt_handler_array is an array of entry points referenced in the
+ * early IDT. For simplicity, it's a real array with one entry point
+ * every nine bytes. That leaves room for an optional 'push $0' if the
+ * vector has no error code (two bytes), a 'push $vector_number' (two
+ * bytes), and a jump to the common entry code (up to five bytes).
+ */
+#define EARLY_IDT_HANDLER_SIZE 9
+
#ifndef __ASSEMBLY__
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
+extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
#ifdef CONFIG_TRACING
-# define trace_early_idt_handlers early_idt_handlers
+# define trace_early_idt_handler_array early_idt_handler_array
#endif
/*
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
/*
* may_use_simd - whether it is allowable at this time to issue SIMD
DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
-static inline struct cpumask *cpu_sibling_mask(int cpu)
-{
- return per_cpu(cpu_sibling_map, cpu);
-}
-
-static inline struct cpumask *cpu_core_mask(int cpu)
-{
- return per_cpu(cpu_core_map, cpu);
-}
-
static inline struct cpumask *cpu_llc_shared_mask(int cpu)
{
return per_cpu(cpu_llc_shared_map, cpu);
: [pax] "a" (p));
}
+/**
+ * pcommit_sfence() - persistent commit and fence
+ *
+ * The PCOMMIT instruction ensures that data that has been flushed from the
+ * processor's cache hierarchy with CLWB, CLFLUSHOPT or CLFLUSH is accepted to
+ * memory and is durable on the DIMM. The primary use case for this is
+ * persistent memory.
+ *
+ * This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH and PCOMMIT
+ * with appropriate fencing.
+ *
+ * Example:
+ * void flush_and_commit_buffer(void *vaddr, unsigned int size)
+ * {
+ * unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+ * void *vend = vaddr + size;
+ * void *p;
+ *
+ * for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+ * p < vend; p += boot_cpu_data.x86_clflush_size)
+ * clwb(p);
+ *
+ * // SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes
+ * // MFENCE via mb() also works
+ * wmb();
+ *
+ * // PCOMMIT and the required SFENCE for ordering
+ * pcommit_sfence();
+ * }
+ *
+ * After this function completes the data pointed to by 'vaddr' has been
+ * accepted to memory and will be durable if the 'vaddr' points to persistent
+ * memory.
+ *
+ * PCOMMIT must always be ordered by an MFENCE or SFENCE, so to help simplify
+ * things we include both the PCOMMIT and the required SFENCE in the
+ * alternatives generated by pcommit_sfence().
+ */
static inline void pcommit_sfence(void)
{
alternative(ASM_NOP7,
extern struct static_key paravirt_ticketlocks_enabled;
static __always_inline bool static_key_false(struct static_key *key);
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm/qspinlock.h>
+#else
+
#ifdef CONFIG_PARAVIRT_SPINLOCKS
static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
cpu_relax();
}
}
+#endif /* CONFIG_QUEUED_SPINLOCKS */
/*
* Read-write spinlocks, allowing multiple readers
#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm-generic/qspinlock_types.h>
+#else
typedef struct arch_spinlock {
union {
__ticketpair_t head_tail;
} arch_spinlock_t;
#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
#include <asm-generic/qrwlock_types.h>
#include <asm/processor.h>
#include <asm/percpu.h>
#include <asm/desc.h>
+
#include <linux/random.h>
+#include <linux/sched.h>
/*
* 24 byte read-only segment initializer for stack canary. Linker
#define _ASM_X86_SUSPEND_32_H
#include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
/* image of the saved processor state */
struct saved_context {
#define _ASM_X86_SUSPEND_64_H
#include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
/*
* Image of the saved processor state, used by the low level ACPI suspend to
*/
#ifndef __ASSEMBLY__
-DECLARE_PER_CPU(unsigned long, kernel_stack);
-
static inline struct thread_info *current_thread_info(void)
{
return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE);
#else /* !__ASSEMBLY__ */
+#ifdef CONFIG_X86_64
+# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+#endif
+
/* Load thread_info address into "reg" */
#define GET_THREAD_INFO(reg) \
- _ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
+ _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
_ASM_SUB $(THREAD_SIZE),reg ;
/*
#define _ASM_X86_TOPOLOGY_H
#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
# define ENABLE_TOPO_DEFINES
# endif
#else
#ifdef ENABLE_TOPO_DEFINES
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
#endif
static inline void arch_fix_phys_package_id(int num, u32 slot)
*/
DEFINE_IRQ_VECTOR_EVENT(threshold_apic);
+/*
+ * deferred_error_apic - called when entering/exiting a deferred apic interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic);
+
/*
* thermal_apic - called when entering/exiting a thermal apic interrupt
* vector handler
--- /dev/null
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mpx
+
+#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MPX_H
+
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_X86_INTEL_MPX
+
+TRACE_EVENT(mpx_bounds_register_exception,
+
+ TP_PROTO(void *addr_referenced,
+ const struct bndreg *bndreg),
+ TP_ARGS(addr_referenced, bndreg),
+
+ TP_STRUCT__entry(
+ __field(void *, addr_referenced)
+ __field(u64, lower_bound)
+ __field(u64, upper_bound)
+ ),
+
+ TP_fast_assign(
+ __entry->addr_referenced = addr_referenced;
+ __entry->lower_bound = bndreg->lower_bound;
+ __entry->upper_bound = bndreg->upper_bound;
+ ),
+ /*
+ * Note that we are printing out the '~' of the upper
+ * bounds register here. It is actually stored in its
+ * one's complement form so that its 'init' state
+ * corresponds to all 0's. But, that looks like
+ * gibberish when printed out, so print out the 1's
+ * complement instead of the actual value here. Note
+ * though that you still need to specify filters for the
+ * actual value, not the displayed one.
+ */
+ TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx",
+ __entry->addr_referenced,
+ __entry->lower_bound,
+ ~__entry->upper_bound
+ )
+);
+
+TRACE_EVENT(bounds_exception_mpx,
+
+ TP_PROTO(const struct bndcsr *bndcsr),
+ TP_ARGS(bndcsr),
+
+ TP_STRUCT__entry(
+ __field(u64, bndcfgu)
+ __field(u64, bndstatus)
+ ),
+
+ TP_fast_assign(
+ /* need to get rid of the 'const' on bndcsr */
+ __entry->bndcfgu = (u64)bndcsr->bndcfgu;
+ __entry->bndstatus = (u64)bndcsr->bndstatus;
+ ),
+
+ TP_printk("bndcfgu:0x%llx bndstatus:0x%llx",
+ __entry->bndcfgu,
+ __entry->bndstatus)
+);
+
+DECLARE_EVENT_CLASS(mpx_range_trace,
+
+ TP_PROTO(unsigned long start,
+ unsigned long end),
+ TP_ARGS(start, end),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, start)
+ __field(unsigned long, end)
+ ),
+
+ TP_fast_assign(
+ __entry->start = start;
+ __entry->end = end;
+ ),
+
+ TP_printk("[0x%p:0x%p]",
+ (void *)__entry->start,
+ (void *)__entry->end
+ )
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap,
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end)
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_search,
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end)
+);
+
+TRACE_EVENT(mpx_new_bounds_table,
+
+ TP_PROTO(unsigned long table_vaddr),
+ TP_ARGS(table_vaddr),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, table_vaddr)
+ ),
+
+ TP_fast_assign(
+ __entry->table_vaddr = table_vaddr;
+ ),
+
+ TP_printk("table vaddr:%p", (void *)__entry->table_vaddr)
+);
+
+#else
+
+/*
+ * This gets used outside of MPX-specific code, so we need a stub.
+ */
+static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr)
+{
+}
+
+#endif /* CONFIG_X86_INTEL_MPX */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE mpx
+#endif /* _TRACE_MPX_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
void math_emulate(struct math_emu_info *);
#ifndef CONFIG_X86_32
asmlinkage void smp_thermal_interrupt(void);
-asmlinkage void mce_threshold_interrupt(void);
+asmlinkage void smp_threshold_interrupt(void);
+asmlinkage void smp_deferred_error_interrupt(void);
#endif
extern enum ctx_state ist_enter(struct pt_regs *regs);
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Checks if a pointer to a block of memory in user space is valid.
*
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
__put_user_size(*(u32 *)from, (u32 __user *)to,
4, ret, 4);
return ret;
+ case 8:
+ __put_user_size(*(u64 *)from, (u64 __user *)to,
+ 8, ret, 8);
+ return ret;
}
}
return __copy_to_user_ll(to, from, n);
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space. Caller must check
* the specified block with access_ok() before calling this function.
__u32 ymmh_space[64];
};
-struct user_xsave_hdr {
- __u64 xstate_bv;
+struct user_xstate_header {
+ __u64 xfeatures;
__u64 reserved1[2];
__u64 reserved2[5];
};
* particular process/thread.
*
* Also when the user modifies certain state FP/SSE/etc through the
- * ptrace interface, they must ensure that the xsave_hdr.xstate_bv
+ * ptrace interface, they must ensure that the header.xfeatures
* bytes[512..519] of the memory layout are updated correspondingly.
* i.e., for example when FP state is modified to a non-init state,
- * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to
- * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc.
+ * header.xfeatures's bit 0 must be set to '1', when SSE is modified to
+ * non-init state, header.xfeatures's bit 1 must to be set to '1', etc.
*/
#define USER_XSTATE_FX_SW_WORDS 6
#define USER_XSTATE_XCR0_WORD 0
__u64 fpx_space[58];
__u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS];
} i387;
- struct user_xsave_hdr xsave_hdr;
+ struct user_xstate_header header;
struct user_ymmh_regs ymmh;
/* further processor state extensions go here */
};
};
struct pci_dev;
-struct msi_msg;
struct x86_msi_ops {
int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
- void (*compose_msi_msg)(struct pci_dev *dev, unsigned int irq,
- unsigned int dest, struct msi_msg *msg,
- u8 hpet_id);
void (*teardown_msi_irq)(unsigned int irq);
void (*teardown_msi_irqs)(struct pci_dev *dev);
void (*restore_msi_irqs)(struct pci_dev *dev);
- int (*setup_hpet_msi)(unsigned int irq, unsigned int id);
};
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_data;
-struct cpumask;
-
struct x86_io_apic_ops {
- void (*init) (void);
unsigned int (*read) (unsigned int apic, unsigned int reg);
- void (*write) (unsigned int apic, unsigned int reg, unsigned int value);
- void (*modify) (unsigned int apic, unsigned int reg, unsigned int value);
void (*disable)(void);
- void (*print_entries)(unsigned int apic, unsigned int nr_entries);
- int (*set_affinity)(struct irq_data *data,
- const struct cpumask *mask,
- bool force);
- int (*setup_entry)(int irq, struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr);
- void (*eoi_ioapic_pin)(int apic, int pin, int vector);
};
extern struct x86_init_ops x86_init;
+++ /dev/null
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- * Copyright 2008 rPath, Inc. - All Rights Reserved
- *
- * This file is part of the Linux kernel, and is made available under
- * the terms of the GNU General Public License version 2 or (at your
- * option) any later version; incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * asm-x86/xcr.h
- *
- * Definitions for the eXtended Control Register instructions
- */
-
-#ifndef _ASM_X86_XCR_H
-#define _ASM_X86_XCR_H
-
-#define XCR_XFEATURE_ENABLED_MASK 0x00000000
-
-#ifdef __KERNEL__
-# ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-
-static inline u64 xgetbv(u32 index)
-{
- u32 eax, edx;
-
- asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
- : "=a" (eax), "=d" (edx)
- : "c" (index));
- return eax + ((u64)edx << 32);
-}
-
-static inline void xsetbv(u32 index, u64 value)
-{
- u32 eax = value;
- u32 edx = value >> 32;
-
- asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
- : : "a" (eax), "d" (edx), "c" (index));
-}
-
-# endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_XCR_H */
* no advantages to be gotten from x86-64 here anyways.
*/
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#ifdef CONFIG_X86_32
/* reduce register pressure */
#define XO3(x, y) " pxor 8*("#x")(%4), %%mm"#y" ;\n"
#define XO4(x, y) " pxor 8*("#x")(%5), %%mm"#y" ;\n"
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
static void
xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
#ifdef CONFIG_AS_AVX
#include <linux/compiler.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#define BLOCK4(i) \
BLOCK(32 * i, 0) \
+++ /dev/null
-#ifndef __ASM_X86_XSAVE_H
-#define __ASM_X86_XSAVE_H
-
-#include <linux/types.h>
-#include <asm/processor.h>
-
-#define XSTATE_CPUID 0x0000000d
-
-#define XSTATE_FP 0x1
-#define XSTATE_SSE 0x2
-#define XSTATE_YMM 0x4
-#define XSTATE_BNDREGS 0x8
-#define XSTATE_BNDCSR 0x10
-#define XSTATE_OPMASK 0x20
-#define XSTATE_ZMM_Hi256 0x40
-#define XSTATE_Hi16_ZMM 0x80
-
-#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE)
-#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-/* Bit 63 of XCR0 is reserved for future expansion */
-#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63)))
-
-#define FXSAVE_SIZE 512
-
-#define XSAVE_HDR_SIZE 64
-#define XSAVE_HDR_OFFSET FXSAVE_SIZE
-
-#define XSAVE_YMM_SIZE 256
-#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
-
-/* Supported features which support lazy state saving */
-#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
- | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-
-/* Supported features which require eager state saving */
-#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR)
-
-/* All currently supported features */
-#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER)
-
-#ifdef CONFIG_X86_64
-#define REX_PREFIX "0x48, "
-#else
-#define REX_PREFIX
-#endif
-
-extern unsigned int xstate_size;
-extern u64 pcntxt_mask;
-extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
-extern struct xsave_struct *init_xstate_buf;
-
-extern void xsave_init(void);
-extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
-extern int init_fpu(struct task_struct *child);
-
-/* These macros all use (%edi)/(%rdi) as the single memory argument. */
-#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
-#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
-#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
-#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
-#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
-
-#define xstate_fault ".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err)
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err = 0;
-
- WARN_ON(system_state != SYSTEM_BOOTING);
-
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- asm volatile("1:"XSAVES"\n\t"
- "2:\n\t"
- xstate_fault
- : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
- else
- asm volatile("1:"XSAVE"\n\t"
- "2:\n\t"
- xstate_fault
- : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
- return err;
-}
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err = 0;
-
- WARN_ON(system_state != SYSTEM_BOOTING);
-
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- asm volatile("1:"XRSTORS"\n\t"
- "2:\n\t"
- xstate_fault
- : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
- else
- asm volatile("1:"XRSTOR"\n\t"
- "2:\n\t"
- xstate_fault
- : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
- return err;
-}
-
-/*
- * Save processor xstate to xsave area.
- */
-static inline int xsave_state(struct xsave_struct *fx, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err = 0;
-
- /*
- * If xsaves is enabled, xsaves replaces xsaveopt because
- * it supports compact format and supervisor states in addition to
- * modified optimization in xsaveopt.
- *
- * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
- * because xsaveopt supports modified optimization which is not
- * supported by xsave.
- *
- * If none of xsaves and xsaveopt is enabled, use xsave.
- */
- alternative_input_2(
- "1:"XSAVE,
- XSAVEOPT,
- X86_FEATURE_XSAVEOPT,
- XSAVES,
- X86_FEATURE_XSAVES,
- [fx] "D" (fx), "a" (lmask), "d" (hmask) :
- "memory");
- asm volatile("2:\n\t"
- xstate_fault
- : "0" (0)
- : "memory");
-
- return err;
-}
-
-/*
- * Restore processor xstate from xsave area.
- */
-static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
-{
- int err = 0;
- u32 lmask = mask;
- u32 hmask = mask >> 32;
-
- /*
- * Use xrstors to restore context if it is enabled. xrstors supports
- * compacted format of xsave area which is not supported by xrstor.
- */
- alternative_input(
- "1: " XRSTOR,
- XRSTORS,
- X86_FEATURE_XSAVES,
- "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
-
- asm volatile("2:\n"
- xstate_fault
- : "0" (0)
- : "memory");
-
- return err;
-}
-
-/*
- * Save xstate context for old process during context switch.
- */
-static inline void fpu_xsave(struct fpu *fpu)
-{
- xsave_state(&fpu->state->xsave, -1);
-}
-
-/*
- * Restore xstate context for new process during context switch.
- */
-static inline int fpu_xrstor_checking(struct xsave_struct *fx)
-{
- return xrstor_state(fx, -1);
-}
-
-/*
- * Save xstate to user space xsave area.
- *
- * We don't use modified optimization because xrstor/xrstors might track
- * a different application.
- *
- * We don't use compacted format xsave area for
- * backward compatibility for old applications which don't understand
- * compacted format of xsave area.
- */
-static inline int xsave_user(struct xsave_struct __user *buf)
-{
- int err;
-
- /*
- * Clear the xsave header first, so that reserved fields are
- * initialized to zero.
- */
- err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
- if (unlikely(err))
- return -EFAULT;
-
- __asm__ __volatile__(ASM_STAC "\n"
- "1:"XSAVE"\n"
- "2: " ASM_CLAC "\n"
- xstate_fault
- : "D" (buf), "a" (-1), "d" (-1), "0" (0)
- : "memory");
- return err;
-}
-
-/*
- * Restore xstate from user space xsave area.
- */
-static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
-{
- int err = 0;
- struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
- u32 lmask = mask;
- u32 hmask = mask >> 32;
-
- __asm__ __volatile__(ASM_STAC "\n"
- "1:"XRSTOR"\n"
- "2: " ASM_CLAC "\n"
- xstate_fault
- : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
- : "memory"); /* memory required? */
- return err;
-}
-
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate);
-void setup_xstate_comp(void);
-
-#endif
+++ /dev/null
-#ifndef _ASM_X86_MSR_INDEX_H
-#define _ASM_X86_MSR_INDEX_H
-
-/* CPU model specific register (MSR) numbers */
-
-/* x86-64 specific MSRs */
-#define MSR_EFER 0xc0000080 /* extended feature register */
-#define MSR_STAR 0xc0000081 /* legacy mode SYSCALL target */
-#define MSR_LSTAR 0xc0000082 /* long mode SYSCALL target */
-#define MSR_CSTAR 0xc0000083 /* compat mode SYSCALL target */
-#define MSR_SYSCALL_MASK 0xc0000084 /* EFLAGS mask for syscall */
-#define MSR_FS_BASE 0xc0000100 /* 64bit FS base */
-#define MSR_GS_BASE 0xc0000101 /* 64bit GS base */
-#define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */
-#define MSR_TSC_AUX 0xc0000103 /* Auxiliary TSC */
-
-/* EFER bits: */
-#define _EFER_SCE 0 /* SYSCALL/SYSRET */
-#define _EFER_LME 8 /* Long mode enable */
-#define _EFER_LMA 10 /* Long mode active (read-only) */
-#define _EFER_NX 11 /* No execute enable */
-#define _EFER_SVME 12 /* Enable virtualization */
-#define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */
-#define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */
-
-#define EFER_SCE (1<<_EFER_SCE)
-#define EFER_LME (1<<_EFER_LME)
-#define EFER_LMA (1<<_EFER_LMA)
-#define EFER_NX (1<<_EFER_NX)
-#define EFER_SVME (1<<_EFER_SVME)
-#define EFER_LMSLE (1<<_EFER_LMSLE)
-#define EFER_FFXSR (1<<_EFER_FFXSR)
-
-/* Intel MSRs. Some also available on other CPUs */
-#define MSR_IA32_PERFCTR0 0x000000c1
-#define MSR_IA32_PERFCTR1 0x000000c2
-#define MSR_FSB_FREQ 0x000000cd
-#define MSR_NHM_PLATFORM_INFO 0x000000ce
-
-#define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2
-#define NHM_C3_AUTO_DEMOTE (1UL << 25)
-#define NHM_C1_AUTO_DEMOTE (1UL << 26)
-#define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25)
-#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
-
-#define MSR_PLATFORM_INFO 0x000000ce
-#define MSR_MTRRcap 0x000000fe
-#define MSR_IA32_BBL_CR_CTL 0x00000119
-#define MSR_IA32_BBL_CR_CTL3 0x0000011e
-
-#define MSR_IA32_SYSENTER_CS 0x00000174
-#define MSR_IA32_SYSENTER_ESP 0x00000175
-#define MSR_IA32_SYSENTER_EIP 0x00000176
-
-#define MSR_IA32_MCG_CAP 0x00000179
-#define MSR_IA32_MCG_STATUS 0x0000017a
-#define MSR_IA32_MCG_CTL 0x0000017b
-
-#define MSR_OFFCORE_RSP_0 0x000001a6
-#define MSR_OFFCORE_RSP_1 0x000001a7
-#define MSR_NHM_TURBO_RATIO_LIMIT 0x000001ad
-#define MSR_IVT_TURBO_RATIO_LIMIT 0x000001ae
-#define MSR_TURBO_RATIO_LIMIT 0x000001ad
-#define MSR_TURBO_RATIO_LIMIT1 0x000001ae
-#define MSR_TURBO_RATIO_LIMIT2 0x000001af
-
-#define MSR_LBR_SELECT 0x000001c8
-#define MSR_LBR_TOS 0x000001c9
-#define MSR_LBR_NHM_FROM 0x00000680
-#define MSR_LBR_NHM_TO 0x000006c0
-#define MSR_LBR_CORE_FROM 0x00000040
-#define MSR_LBR_CORE_TO 0x00000060
-
-#define MSR_IA32_PEBS_ENABLE 0x000003f1
-#define MSR_IA32_DS_AREA 0x00000600
-#define MSR_IA32_PERF_CAPABILITIES 0x00000345
-#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
-
-#define MSR_IA32_RTIT_CTL 0x00000570
-#define RTIT_CTL_TRACEEN BIT(0)
-#define RTIT_CTL_OS BIT(2)
-#define RTIT_CTL_USR BIT(3)
-#define RTIT_CTL_CR3EN BIT(7)
-#define RTIT_CTL_TOPA BIT(8)
-#define RTIT_CTL_TSC_EN BIT(10)
-#define RTIT_CTL_DISRETC BIT(11)
-#define RTIT_CTL_BRANCH_EN BIT(13)
-#define MSR_IA32_RTIT_STATUS 0x00000571
-#define RTIT_STATUS_CONTEXTEN BIT(1)
-#define RTIT_STATUS_TRIGGEREN BIT(2)
-#define RTIT_STATUS_ERROR BIT(4)
-#define RTIT_STATUS_STOPPED BIT(5)
-#define MSR_IA32_RTIT_CR3_MATCH 0x00000572
-#define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560
-#define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561
-
-#define MSR_MTRRfix64K_00000 0x00000250
-#define MSR_MTRRfix16K_80000 0x00000258
-#define MSR_MTRRfix16K_A0000 0x00000259
-#define MSR_MTRRfix4K_C0000 0x00000268
-#define MSR_MTRRfix4K_C8000 0x00000269
-#define MSR_MTRRfix4K_D0000 0x0000026a
-#define MSR_MTRRfix4K_D8000 0x0000026b
-#define MSR_MTRRfix4K_E0000 0x0000026c
-#define MSR_MTRRfix4K_E8000 0x0000026d
-#define MSR_MTRRfix4K_F0000 0x0000026e
-#define MSR_MTRRfix4K_F8000 0x0000026f
-#define MSR_MTRRdefType 0x000002ff
-
-#define MSR_IA32_CR_PAT 0x00000277
-
-#define MSR_IA32_DEBUGCTLMSR 0x000001d9
-#define MSR_IA32_LASTBRANCHFROMIP 0x000001db
-#define MSR_IA32_LASTBRANCHTOIP 0x000001dc
-#define MSR_IA32_LASTINTFROMIP 0x000001dd
-#define MSR_IA32_LASTINTTOIP 0x000001de
-
-/* DEBUGCTLMSR bits (others vary by model): */
-#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
-#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */
-#define DEBUGCTLMSR_TR (1UL << 6)
-#define DEBUGCTLMSR_BTS (1UL << 7)
-#define DEBUGCTLMSR_BTINT (1UL << 8)
-#define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9)
-#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10)
-#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11)
-
-#define MSR_IA32_POWER_CTL 0x000001fc
-
-#define MSR_IA32_MC0_CTL 0x00000400
-#define MSR_IA32_MC0_STATUS 0x00000401
-#define MSR_IA32_MC0_ADDR 0x00000402
-#define MSR_IA32_MC0_MISC 0x00000403
-
-/* C-state Residency Counters */
-#define MSR_PKG_C3_RESIDENCY 0x000003f8
-#define MSR_PKG_C6_RESIDENCY 0x000003f9
-#define MSR_PKG_C7_RESIDENCY 0x000003fa
-#define MSR_CORE_C3_RESIDENCY 0x000003fc
-#define MSR_CORE_C6_RESIDENCY 0x000003fd
-#define MSR_CORE_C7_RESIDENCY 0x000003fe
-#define MSR_PKG_C2_RESIDENCY 0x0000060d
-#define MSR_PKG_C8_RESIDENCY 0x00000630
-#define MSR_PKG_C9_RESIDENCY 0x00000631
-#define MSR_PKG_C10_RESIDENCY 0x00000632
-
-/* Run Time Average Power Limiting (RAPL) Interface */
-
-#define MSR_RAPL_POWER_UNIT 0x00000606
-
-#define MSR_PKG_POWER_LIMIT 0x00000610
-#define MSR_PKG_ENERGY_STATUS 0x00000611
-#define MSR_PKG_PERF_STATUS 0x00000613
-#define MSR_PKG_POWER_INFO 0x00000614
-
-#define MSR_DRAM_POWER_LIMIT 0x00000618
-#define MSR_DRAM_ENERGY_STATUS 0x00000619
-#define MSR_DRAM_PERF_STATUS 0x0000061b
-#define MSR_DRAM_POWER_INFO 0x0000061c
-
-#define MSR_PP0_POWER_LIMIT 0x00000638
-#define MSR_PP0_ENERGY_STATUS 0x00000639
-#define MSR_PP0_POLICY 0x0000063a
-#define MSR_PP0_PERF_STATUS 0x0000063b
-
-#define MSR_PP1_POWER_LIMIT 0x00000640
-#define MSR_PP1_ENERGY_STATUS 0x00000641
-#define MSR_PP1_POLICY 0x00000642
-
-#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658
-#define MSR_PKG_ANY_CORE_C0_RES 0x00000659
-#define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A
-#define MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B
-
-#define MSR_CORE_C1_RES 0x00000660
-
-#define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668
-#define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669
-
-#define MSR_CORE_PERF_LIMIT_REASONS 0x00000690
-#define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0
-#define MSR_RING_PERF_LIMIT_REASONS 0x000006B1
-
-/* Hardware P state interface */
-#define MSR_PPERF 0x0000064e
-#define MSR_PERF_LIMIT_REASONS 0x0000064f
-#define MSR_PM_ENABLE 0x00000770
-#define MSR_HWP_CAPABILITIES 0x00000771
-#define MSR_HWP_REQUEST_PKG 0x00000772
-#define MSR_HWP_INTERRUPT 0x00000773
-#define MSR_HWP_REQUEST 0x00000774
-#define MSR_HWP_STATUS 0x00000777
-
-/* CPUID.6.EAX */
-#define HWP_BASE_BIT (1<<7)
-#define HWP_NOTIFICATIONS_BIT (1<<8)
-#define HWP_ACTIVITY_WINDOW_BIT (1<<9)
-#define HWP_ENERGY_PERF_PREFERENCE_BIT (1<<10)
-#define HWP_PACKAGE_LEVEL_REQUEST_BIT (1<<11)
-
-/* IA32_HWP_CAPABILITIES */
-#define HWP_HIGHEST_PERF(x) (x & 0xff)
-#define HWP_GUARANTEED_PERF(x) ((x & (0xff << 8)) >>8)
-#define HWP_MOSTEFFICIENT_PERF(x) ((x & (0xff << 16)) >>16)
-#define HWP_LOWEST_PERF(x) ((x & (0xff << 24)) >>24)
-
-/* IA32_HWP_REQUEST */
-#define HWP_MIN_PERF(x) (x & 0xff)
-#define HWP_MAX_PERF(x) ((x & 0xff) << 8)
-#define HWP_DESIRED_PERF(x) ((x & 0xff) << 16)
-#define HWP_ENERGY_PERF_PREFERENCE(x) ((x & 0xff) << 24)
-#define HWP_ACTIVITY_WINDOW(x) ((x & 0xff3) << 32)
-#define HWP_PACKAGE_CONTROL(x) ((x & 0x1) << 42)
-
-/* IA32_HWP_STATUS */
-#define HWP_GUARANTEED_CHANGE(x) (x & 0x1)
-#define HWP_EXCURSION_TO_MINIMUM(x) (x & 0x4)
-
-/* IA32_HWP_INTERRUPT */
-#define HWP_CHANGE_TO_GUARANTEED_INT(x) (x & 0x1)
-#define HWP_EXCURSION_TO_MINIMUM_INT(x) (x & 0x2)
-
-#define MSR_AMD64_MC0_MASK 0xc0010044
-
-#define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x))
-#define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x))
-#define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x))
-#define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x))
-
-#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x))
-
-/* These are consecutive and not in the normal 4er MCE bank block */
-#define MSR_IA32_MC0_CTL2 0x00000280
-#define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x))
-
-#define MSR_P6_PERFCTR0 0x000000c1
-#define MSR_P6_PERFCTR1 0x000000c2
-#define MSR_P6_EVNTSEL0 0x00000186
-#define MSR_P6_EVNTSEL1 0x00000187
-
-#define MSR_KNC_PERFCTR0 0x00000020
-#define MSR_KNC_PERFCTR1 0x00000021
-#define MSR_KNC_EVNTSEL0 0x00000028
-#define MSR_KNC_EVNTSEL1 0x00000029
-
-/* Alternative perfctr range with full access. */
-#define MSR_IA32_PMC0 0x000004c1
-
-/* AMD64 MSRs. Not complete. See the architecture manual for a more
- complete list. */
-
-#define MSR_AMD64_PATCH_LEVEL 0x0000008b
-#define MSR_AMD64_TSC_RATIO 0xc0000104
-#define MSR_AMD64_NB_CFG 0xc001001f
-#define MSR_AMD64_PATCH_LOADER 0xc0010020
-#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
-#define MSR_AMD64_OSVW_STATUS 0xc0010141
-#define MSR_AMD64_LS_CFG 0xc0011020
-#define MSR_AMD64_DC_CFG 0xc0011022
-#define MSR_AMD64_BU_CFG2 0xc001102a
-#define MSR_AMD64_IBSFETCHCTL 0xc0011030
-#define MSR_AMD64_IBSFETCHLINAD 0xc0011031
-#define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032
-#define MSR_AMD64_IBSFETCH_REG_COUNT 3
-#define MSR_AMD64_IBSFETCH_REG_MASK ((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
-#define MSR_AMD64_IBSOPCTL 0xc0011033
-#define MSR_AMD64_IBSOPRIP 0xc0011034
-#define MSR_AMD64_IBSOPDATA 0xc0011035
-#define MSR_AMD64_IBSOPDATA2 0xc0011036
-#define MSR_AMD64_IBSOPDATA3 0xc0011037
-#define MSR_AMD64_IBSDCLINAD 0xc0011038
-#define MSR_AMD64_IBSDCPHYSAD 0xc0011039
-#define MSR_AMD64_IBSOP_REG_COUNT 7
-#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
-#define MSR_AMD64_IBSCTL 0xc001103a
-#define MSR_AMD64_IBSBRTARGET 0xc001103b
-#define MSR_AMD64_IBSOPDATA4 0xc001103d
-#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
-
-/* Fam 16h MSRs */
-#define MSR_F16H_L2I_PERF_CTL 0xc0010230
-#define MSR_F16H_L2I_PERF_CTR 0xc0010231
-#define MSR_F16H_DR1_ADDR_MASK 0xc0011019
-#define MSR_F16H_DR2_ADDR_MASK 0xc001101a
-#define MSR_F16H_DR3_ADDR_MASK 0xc001101b
-#define MSR_F16H_DR0_ADDR_MASK 0xc0011027
-
-/* Fam 15h MSRs */
-#define MSR_F15H_PERF_CTL 0xc0010200
-#define MSR_F15H_PERF_CTR 0xc0010201
-#define MSR_F15H_NB_PERF_CTL 0xc0010240
-#define MSR_F15H_NB_PERF_CTR 0xc0010241
-
-/* Fam 10h MSRs */
-#define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058
-#define FAM10H_MMIO_CONF_ENABLE (1<<0)
-#define FAM10H_MMIO_CONF_BUSRANGE_MASK 0xf
-#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
-#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL
-#define FAM10H_MMIO_CONF_BASE_SHIFT 20
-#define MSR_FAM10H_NODE_ID 0xc001100c
-
-/* K8 MSRs */
-#define MSR_K8_TOP_MEM1 0xc001001a
-#define MSR_K8_TOP_MEM2 0xc001001d
-#define MSR_K8_SYSCFG 0xc0010010
-#define MSR_K8_INT_PENDING_MSG 0xc0010055
-/* C1E active bits in int pending message */
-#define K8_INTP_C1E_ACTIVE_MASK 0x18000000
-#define MSR_K8_TSEG_ADDR 0xc0010112
-#define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */
-#define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */
-#define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */
-
-/* K7 MSRs */
-#define MSR_K7_EVNTSEL0 0xc0010000
-#define MSR_K7_PERFCTR0 0xc0010004
-#define MSR_K7_EVNTSEL1 0xc0010001
-#define MSR_K7_PERFCTR1 0xc0010005
-#define MSR_K7_EVNTSEL2 0xc0010002
-#define MSR_K7_PERFCTR2 0xc0010006
-#define MSR_K7_EVNTSEL3 0xc0010003
-#define MSR_K7_PERFCTR3 0xc0010007
-#define MSR_K7_CLK_CTL 0xc001001b
-#define MSR_K7_HWCR 0xc0010015
-#define MSR_K7_FID_VID_CTL 0xc0010041
-#define MSR_K7_FID_VID_STATUS 0xc0010042
-
-/* K6 MSRs */
-#define MSR_K6_WHCR 0xc0000082
-#define MSR_K6_UWCCR 0xc0000085
-#define MSR_K6_EPMR 0xc0000086
-#define MSR_K6_PSOR 0xc0000087
-#define MSR_K6_PFIR 0xc0000088
-
-/* Centaur-Hauls/IDT defined MSRs. */
-#define MSR_IDT_FCR1 0x00000107
-#define MSR_IDT_FCR2 0x00000108
-#define MSR_IDT_FCR3 0x00000109
-#define MSR_IDT_FCR4 0x0000010a
-
-#define MSR_IDT_MCR0 0x00000110
-#define MSR_IDT_MCR1 0x00000111
-#define MSR_IDT_MCR2 0x00000112
-#define MSR_IDT_MCR3 0x00000113
-#define MSR_IDT_MCR4 0x00000114
-#define MSR_IDT_MCR5 0x00000115
-#define MSR_IDT_MCR6 0x00000116
-#define MSR_IDT_MCR7 0x00000117
-#define MSR_IDT_MCR_CTRL 0x00000120
-
-/* VIA Cyrix defined MSRs*/
-#define MSR_VIA_FCR 0x00001107
-#define MSR_VIA_LONGHAUL 0x0000110a
-#define MSR_VIA_RNG 0x0000110b
-#define MSR_VIA_BCR2 0x00001147
-
-/* Transmeta defined MSRs */
-#define MSR_TMTA_LONGRUN_CTRL 0x80868010
-#define MSR_TMTA_LONGRUN_FLAGS 0x80868011
-#define MSR_TMTA_LRTI_READOUT 0x80868018
-#define MSR_TMTA_LRTI_VOLT_MHZ 0x8086801a
-
-/* Intel defined MSRs. */
-#define MSR_IA32_P5_MC_ADDR 0x00000000
-#define MSR_IA32_P5_MC_TYPE 0x00000001
-#define MSR_IA32_TSC 0x00000010
-#define MSR_IA32_PLATFORM_ID 0x00000017
-#define MSR_IA32_EBL_CR_POWERON 0x0000002a
-#define MSR_EBC_FREQUENCY_ID 0x0000002c
-#define MSR_SMI_COUNT 0x00000034
-#define MSR_IA32_FEATURE_CONTROL 0x0000003a
-#define MSR_IA32_TSC_ADJUST 0x0000003b
-#define MSR_IA32_BNDCFGS 0x00000d90
-
-#define MSR_IA32_XSS 0x00000da0
-
-#define FEATURE_CONTROL_LOCKED (1<<0)
-#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1)
-#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2)
-
-#define MSR_IA32_APICBASE 0x0000001b
-#define MSR_IA32_APICBASE_BSP (1<<8)
-#define MSR_IA32_APICBASE_ENABLE (1<<11)
-#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
-
-#define MSR_IA32_TSCDEADLINE 0x000006e0
-
-#define MSR_IA32_UCODE_WRITE 0x00000079
-#define MSR_IA32_UCODE_REV 0x0000008b
-
-#define MSR_IA32_SMM_MONITOR_CTL 0x0000009b
-#define MSR_IA32_SMBASE 0x0000009e
-
-#define MSR_IA32_PERF_STATUS 0x00000198
-#define MSR_IA32_PERF_CTL 0x00000199
-#define INTEL_PERF_CTL_MASK 0xffff
-#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064
-#define MSR_AMD_PERF_STATUS 0xc0010063
-#define MSR_AMD_PERF_CTL 0xc0010062
-
-#define MSR_IA32_MPERF 0x000000e7
-#define MSR_IA32_APERF 0x000000e8
-
-#define MSR_IA32_THERM_CONTROL 0x0000019a
-#define MSR_IA32_THERM_INTERRUPT 0x0000019b
-
-#define THERM_INT_HIGH_ENABLE (1 << 0)
-#define THERM_INT_LOW_ENABLE (1 << 1)
-#define THERM_INT_PLN_ENABLE (1 << 24)
-
-#define MSR_IA32_THERM_STATUS 0x0000019c
-
-#define THERM_STATUS_PROCHOT (1 << 0)
-#define THERM_STATUS_POWER_LIMIT (1 << 10)
-
-#define MSR_THERM2_CTL 0x0000019d
-
-#define MSR_THERM2_CTL_TM_SELECT (1ULL << 16)
-
-#define MSR_IA32_MISC_ENABLE 0x000001a0
-
-#define MSR_IA32_TEMPERATURE_TARGET 0x000001a2
-
-#define MSR_MISC_PWR_MGMT 0x000001aa
-
-#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
-#define ENERGY_PERF_BIAS_PERFORMANCE 0
-#define ENERGY_PERF_BIAS_NORMAL 6
-#define ENERGY_PERF_BIAS_POWERSAVE 15
-
-#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1
-
-#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0)
-#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10)
-
-#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2
-
-#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0)
-#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1)
-#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24)
-
-/* Thermal Thresholds Support */
-#define THERM_INT_THRESHOLD0_ENABLE (1 << 15)
-#define THERM_SHIFT_THRESHOLD0 8
-#define THERM_MASK_THRESHOLD0 (0x7f << THERM_SHIFT_THRESHOLD0)
-#define THERM_INT_THRESHOLD1_ENABLE (1 << 23)
-#define THERM_SHIFT_THRESHOLD1 16
-#define THERM_MASK_THRESHOLD1 (0x7f << THERM_SHIFT_THRESHOLD1)
-#define THERM_STATUS_THRESHOLD0 (1 << 6)
-#define THERM_LOG_THRESHOLD0 (1 << 7)
-#define THERM_STATUS_THRESHOLD1 (1 << 8)
-#define THERM_LOG_THRESHOLD1 (1 << 9)
-
-/* MISC_ENABLE bits: architectural */
-#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT 0
-#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
-#define MSR_IA32_MISC_ENABLE_TCC_BIT 1
-#define MSR_IA32_MISC_ENABLE_TCC (1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
-#define MSR_IA32_MISC_ENABLE_EMON_BIT 7
-#define MSR_IA32_MISC_ENABLE_EMON (1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT 11
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT 12
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT 16
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
-#define MSR_IA32_MISC_ENABLE_MWAIT_BIT 18
-#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT 22
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT 23
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT 34
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
-
-/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT 2
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT (1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
-#define MSR_IA32_MISC_ENABLE_TM1_BIT 3
-#define MSR_IA32_MISC_ENABLE_TM1 (1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT 4
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT 6
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT 8
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT 9
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_FERR_BIT 10
-#define MSR_IA32_MISC_ENABLE_FERR (1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT 10
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX (1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
-#define MSR_IA32_MISC_ENABLE_TM2_BIT 13
-#define MSR_IA32_MISC_ENABLE_TM2 (1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT 19
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT 20
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT 24
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT (1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT 37
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT 38
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
-
-#define MSR_IA32_TSC_DEADLINE 0x000006E0
-
-/* P4/Xeon+ specific */
-#define MSR_IA32_MCG_EAX 0x00000180
-#define MSR_IA32_MCG_EBX 0x00000181
-#define MSR_IA32_MCG_ECX 0x00000182
-#define MSR_IA32_MCG_EDX 0x00000183
-#define MSR_IA32_MCG_ESI 0x00000184
-#define MSR_IA32_MCG_EDI 0x00000185
-#define MSR_IA32_MCG_EBP 0x00000186
-#define MSR_IA32_MCG_ESP 0x00000187
-#define MSR_IA32_MCG_EFLAGS 0x00000188
-#define MSR_IA32_MCG_EIP 0x00000189
-#define MSR_IA32_MCG_RESERVED 0x0000018a
-
-/* Pentium IV performance counter MSRs */
-#define MSR_P4_BPU_PERFCTR0 0x00000300
-#define MSR_P4_BPU_PERFCTR1 0x00000301
-#define MSR_P4_BPU_PERFCTR2 0x00000302
-#define MSR_P4_BPU_PERFCTR3 0x00000303
-#define MSR_P4_MS_PERFCTR0 0x00000304
-#define MSR_P4_MS_PERFCTR1 0x00000305
-#define MSR_P4_MS_PERFCTR2 0x00000306
-#define MSR_P4_MS_PERFCTR3 0x00000307
-#define MSR_P4_FLAME_PERFCTR0 0x00000308
-#define MSR_P4_FLAME_PERFCTR1 0x00000309
-#define MSR_P4_FLAME_PERFCTR2 0x0000030a
-#define MSR_P4_FLAME_PERFCTR3 0x0000030b
-#define MSR_P4_IQ_PERFCTR0 0x0000030c
-#define MSR_P4_IQ_PERFCTR1 0x0000030d
-#define MSR_P4_IQ_PERFCTR2 0x0000030e
-#define MSR_P4_IQ_PERFCTR3 0x0000030f
-#define MSR_P4_IQ_PERFCTR4 0x00000310
-#define MSR_P4_IQ_PERFCTR5 0x00000311
-#define MSR_P4_BPU_CCCR0 0x00000360
-#define MSR_P4_BPU_CCCR1 0x00000361
-#define MSR_P4_BPU_CCCR2 0x00000362
-#define MSR_P4_BPU_CCCR3 0x00000363
-#define MSR_P4_MS_CCCR0 0x00000364
-#define MSR_P4_MS_CCCR1 0x00000365
-#define MSR_P4_MS_CCCR2 0x00000366
-#define MSR_P4_MS_CCCR3 0x00000367
-#define MSR_P4_FLAME_CCCR0 0x00000368
-#define MSR_P4_FLAME_CCCR1 0x00000369
-#define MSR_P4_FLAME_CCCR2 0x0000036a
-#define MSR_P4_FLAME_CCCR3 0x0000036b
-#define MSR_P4_IQ_CCCR0 0x0000036c
-#define MSR_P4_IQ_CCCR1 0x0000036d
-#define MSR_P4_IQ_CCCR2 0x0000036e
-#define MSR_P4_IQ_CCCR3 0x0000036f
-#define MSR_P4_IQ_CCCR4 0x00000370
-#define MSR_P4_IQ_CCCR5 0x00000371
-#define MSR_P4_ALF_ESCR0 0x000003ca
-#define MSR_P4_ALF_ESCR1 0x000003cb
-#define MSR_P4_BPU_ESCR0 0x000003b2
-#define MSR_P4_BPU_ESCR1 0x000003b3
-#define MSR_P4_BSU_ESCR0 0x000003a0
-#define MSR_P4_BSU_ESCR1 0x000003a1
-#define MSR_P4_CRU_ESCR0 0x000003b8
-#define MSR_P4_CRU_ESCR1 0x000003b9
-#define MSR_P4_CRU_ESCR2 0x000003cc
-#define MSR_P4_CRU_ESCR3 0x000003cd
-#define MSR_P4_CRU_ESCR4 0x000003e0
-#define MSR_P4_CRU_ESCR5 0x000003e1
-#define MSR_P4_DAC_ESCR0 0x000003a8
-#define MSR_P4_DAC_ESCR1 0x000003a9
-#define MSR_P4_FIRM_ESCR0 0x000003a4
-#define MSR_P4_FIRM_ESCR1 0x000003a5
-#define MSR_P4_FLAME_ESCR0 0x000003a6
-#define MSR_P4_FLAME_ESCR1 0x000003a7
-#define MSR_P4_FSB_ESCR0 0x000003a2
-#define MSR_P4_FSB_ESCR1 0x000003a3
-#define MSR_P4_IQ_ESCR0 0x000003ba
-#define MSR_P4_IQ_ESCR1 0x000003bb
-#define MSR_P4_IS_ESCR0 0x000003b4
-#define MSR_P4_IS_ESCR1 0x000003b5
-#define MSR_P4_ITLB_ESCR0 0x000003b6
-#define MSR_P4_ITLB_ESCR1 0x000003b7
-#define MSR_P4_IX_ESCR0 0x000003c8
-#define MSR_P4_IX_ESCR1 0x000003c9
-#define MSR_P4_MOB_ESCR0 0x000003aa
-#define MSR_P4_MOB_ESCR1 0x000003ab
-#define MSR_P4_MS_ESCR0 0x000003c0
-#define MSR_P4_MS_ESCR1 0x000003c1
-#define MSR_P4_PMH_ESCR0 0x000003ac
-#define MSR_P4_PMH_ESCR1 0x000003ad
-#define MSR_P4_RAT_ESCR0 0x000003bc
-#define MSR_P4_RAT_ESCR1 0x000003bd
-#define MSR_P4_SAAT_ESCR0 0x000003ae
-#define MSR_P4_SAAT_ESCR1 0x000003af
-#define MSR_P4_SSU_ESCR0 0x000003be
-#define MSR_P4_SSU_ESCR1 0x000003bf /* guess: not in manual */
-
-#define MSR_P4_TBPU_ESCR0 0x000003c2
-#define MSR_P4_TBPU_ESCR1 0x000003c3
-#define MSR_P4_TC_ESCR0 0x000003c4
-#define MSR_P4_TC_ESCR1 0x000003c5
-#define MSR_P4_U2L_ESCR0 0x000003b0
-#define MSR_P4_U2L_ESCR1 0x000003b1
-
-#define MSR_P4_PEBS_MATRIX_VERT 0x000003f2
-
-/* Intel Core-based CPU performance counters */
-#define MSR_CORE_PERF_FIXED_CTR0 0x00000309
-#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a
-#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b
-#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d
-#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e
-#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f
-#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390
-
-/* Geode defined MSRs */
-#define MSR_GEODE_BUSCONT_CONF0 0x00001900
-
-/* Intel VT MSRs */
-#define MSR_IA32_VMX_BASIC 0x00000480
-#define MSR_IA32_VMX_PINBASED_CTLS 0x00000481
-#define MSR_IA32_VMX_PROCBASED_CTLS 0x00000482
-#define MSR_IA32_VMX_EXIT_CTLS 0x00000483
-#define MSR_IA32_VMX_ENTRY_CTLS 0x00000484
-#define MSR_IA32_VMX_MISC 0x00000485
-#define MSR_IA32_VMX_CR0_FIXED0 0x00000486
-#define MSR_IA32_VMX_CR0_FIXED1 0x00000487
-#define MSR_IA32_VMX_CR4_FIXED0 0x00000488
-#define MSR_IA32_VMX_CR4_FIXED1 0x00000489
-#define MSR_IA32_VMX_VMCS_ENUM 0x0000048a
-#define MSR_IA32_VMX_PROCBASED_CTLS2 0x0000048b
-#define MSR_IA32_VMX_EPT_VPID_CAP 0x0000048c
-#define MSR_IA32_VMX_TRUE_PINBASED_CTLS 0x0000048d
-#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e
-#define MSR_IA32_VMX_TRUE_EXIT_CTLS 0x0000048f
-#define MSR_IA32_VMX_TRUE_ENTRY_CTLS 0x00000490
-#define MSR_IA32_VMX_VMFUNC 0x00000491
-
-/* VMX_BASIC bits and bitmasks */
-#define VMX_BASIC_VMCS_SIZE_SHIFT 32
-#define VMX_BASIC_TRUE_CTLS (1ULL << 55)
-#define VMX_BASIC_64 0x0001000000000000LLU
-#define VMX_BASIC_MEM_TYPE_SHIFT 50
-#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU
-#define VMX_BASIC_MEM_TYPE_WB 6LLU
-#define VMX_BASIC_INOUT 0x0040000000000000LLU
-
-/* MSR_IA32_VMX_MISC bits */
-#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
-#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
-/* AMD-V MSRs */
-
-#define MSR_VM_CR 0xc0010114
-#define MSR_VM_IGNNE 0xc0010115
-#define MSR_VM_HSAVE_PA 0xc0010117
-
-#endif /* _ASM_X86_MSR_INDEX_H */
#ifndef _UAPI_ASM_X86_MSR_H
#define _UAPI_ASM_X86_MSR_H
-#include <asm/msr-index.h>
-
#ifndef __ASSEMBLY__
#include <linux/types.h>
#define MTRRIOC_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
#define MTRRIOC_KILL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry)
-/* These are the region types */
+/* MTRR memory types, which are defined in SDM */
#define MTRR_TYPE_UNCACHABLE 0
#define MTRR_TYPE_WRCOMB 1
/*#define MTRR_TYPE_ 2*/
#define MTRR_TYPE_WRBACK 6
#define MTRR_NUM_TYPES 7
+/*
+ * Invalid MTRR memory type. mtrr_type_lookup() returns this value when
+ * MTRRs are disabled. Note, this value is allocated from the reserved
+ * values (0x7-0xff) of the MTRR memory types.
+ */
+#define MTRR_TYPE_INVALID 0xff
#endif /* _UAPI_ASM_X86_MTRR_H */
__u32 extended_size; /* total size of the layout referred by
* fpstate pointer in the sigcontext.
*/
- __u64 xstate_bv;
+ __u64 xfeatures;
/* feature bit mask (including fp/sse/extended
* state) that is present in the memory
* layout.
#endif /* !__i386__ */
-struct _xsave_hdr {
- __u64 xstate_bv;
+struct _header {
+ __u64 xfeatures;
__u64 reserved1[2];
__u64 reserved2[5];
};
*/
struct _xstate {
struct _fpstate fpstate;
- struct _xsave_hdr xstate_hdr;
+ struct _header xstate_hdr;
struct _ymmh_state ymmh;
/* new processor state extensions go here */
};
CFLAGS_irq.o := -I$(src)/../include/asm/trace
-obj-y := process_$(BITS).o signal.o entry_$(BITS).o
+obj-y := process_$(BITS).o signal.o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o
obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o
obj-$(CONFIG_X86_32) += i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += mcount_64.o
-obj-y += syscall_$(BITS).o vsyscall_gtod.o
-obj-$(CONFIG_IA32_EMULATION) += syscall_32.o
-obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
obj-y += resource.o
obj-y += process.o
-obj-y += i387.o xsave.o
+obj-y += fpu/
obj-y += ptrace.o
obj-$(CONFIG_X86_32) += tls.o
obj-$(CONFIG_IA32_EMULATION) += tls.o
#include <linux/module.h>
#include <linux/dmi.h>
#include <linux/irq.h>
-#include <linux/irqdomain.h>
#include <linux/slab.h>
#include <linux/bootmem.h>
#include <linux/ioport.h>
#include <linux/pci.h>
+#include <asm/irqdomain.h>
#include <asm/pci_x86.h>
#include <asm/pgtable.h>
#include <asm/io_apic.h>
return 0;
}
-static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
- int polarity)
-{
- int irq, node;
-
- if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
- return gsi;
-
- trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
- polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
- node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
- if (mp_set_gsi_attr(gsi, trigger, polarity, node)) {
- pr_warn("Failed to set pin attr for GSI%d\n", gsi);
- return -1;
- }
-
- irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC);
- if (irq < 0)
- return irq;
-
- /* Don't set up the ACPI SCI because it's already set up */
- if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi)
- mp_config_acpi_gsi(dev, gsi, trigger, polarity);
-
- return irq;
-}
-
-static void mp_unregister_gsi(u32 gsi)
-{
- int irq;
-
- if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
- return;
-
- irq = mp_map_gsi_to_irq(gsi, 0);
- if (irq > 0)
- mp_unmap_irq(irq);
-}
-
-static struct irq_domain_ops acpi_irqdomain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
-};
-
static int __init
acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
{
struct acpi_madt_io_apic *ioapic = NULL;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_DYNAMIC,
- .ops = &acpi_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
ioapic = (struct acpi_madt_io_apic *)header;
* Make sure all (legacy) PCI IRQs are set as level-triggered.
*/
if (trigger == ACPI_LEVEL_SENSITIVE)
- eisa_set_level_irq(gsi);
+ elcr_set_level_irq(gsi);
#endif
return gsi;
int trigger, int polarity)
{
int irq = gsi;
-
#ifdef CONFIG_X86_IO_APIC
+ int node;
+ struct irq_alloc_info info;
+
+ node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
+ trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
+ polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
+ ioapic_set_alloc_attr(&info, node, trigger, polarity);
+
mutex_lock(&acpi_ioapic_lock);
- irq = mp_register_gsi(dev, gsi, trigger, polarity);
+ irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
+ /* Don't set up the ACPI SCI because it's already set up */
+ if (irq >= 0 && enable_update_mptable &&
+ acpi_gbl_FADT.sci_interrupt != gsi)
+ mp_config_acpi_gsi(dev, gsi, trigger, polarity);
mutex_unlock(&acpi_ioapic_lock);
#endif
static void acpi_unregister_gsi_ioapic(u32 gsi)
{
#ifdef CONFIG_X86_IO_APIC
+ int irq;
+
mutex_lock(&acpi_ioapic_lock);
- mp_unregister_gsi(gsi);
+ irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+ if (irq > 0)
+ mp_unmap_irq(irq);
mutex_unlock(&acpi_ioapic_lock);
#endif
}
u64 addr;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_DYNAMIC,
- .ops = &acpi_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr);
pushfq
popq pt_regs_flags(%rax)
- movq $resume_point, saved_rip(%rip)
+ movq $.Lresume_point, saved_rip(%rip)
movq %rsp, saved_rsp
movq %rbp, saved_rbp
xorl %eax, %eax
call x86_acpi_enter_sleep_state
/* in case something went wrong, restore the machine status and go on */
- jmp resume_point
+ jmp .Lresume_point
.align 4
-resume_point:
+.Lresume_point:
/* We don't restore %rax, it must be 0 anyway */
movq $saved_context, %rax
movq saved_context_cr4(%rax), %rbx
#include <asm/io.h>
#include <asm/fixmap.h>
+int __read_mostly alternatives_patched;
+
+EXPORT_SYMBOL_GPL(alternatives_patched);
+
#define MAX_PATCH_LEN (255-1)
static int __initdata_or_module debug_alternative;
#endif
}
break;
+
+ case X86_VENDOR_AMD:
+ if (boot_cpu_data.x86 > 0xf) {
+ ideal_nops = p6_nops;
+ return;
+ }
+
+ /* fall through */
+
default:
#ifdef CONFIG_X86_64
ideal_nops = k8_nops;
apply_paravirt(__parainstructions, __parainstructions_end);
restart_nmi();
+ alternatives_patched = 1;
}
/**
next_northbridge(link, amd_nb_link_ids);
}
- /* GART present only on Fam15h upto model 0fh */
- if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
- (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
+ if (amd_gart_present())
amd_northbridges.flags |= AMD_NB_GART;
/*
static void apbt_setup_irq(struct apbt_dev *adev)
{
- /* timer0 irq has been setup early */
- if (adev->irq == 0)
- return;
-
irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
}
u64 aper_base = 0, last_aper_base = 0;
int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0;
+ if (!amd_gart_present())
+ return;
+
if (!early_pci_allowed())
return;
int fix, slot, valid_agp = 0;
int i, node;
+ if (!amd_gart_present())
+ return -ENODEV;
+
if (gart_iommu_aperture_disabled || !fix_aperture ||
!early_pci_allowed())
return -ENODEV;
force_iommu ||
valid_agp ||
fallback_aper_force) {
- pr_info("Your BIOS doesn't leave a aperture memory hole\n");
+ pr_info("Your BIOS doesn't leave an aperture memory hole\n");
pr_info("Please enable the IOMMU option in the BIOS setup\n");
pr_info("This costs you %dMB of RAM\n",
32 << fallback_aper_order);
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Add support of hierarchical irqdomain
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
#include <linux/device.h>
#include <linux/pci.h>
#include <linux/htirq.h>
+#include <asm/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/hypertransport.h>
+static struct irq_domain *htirq_domain;
+
/*
* Hypertransport interrupt support
*/
-static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
-{
- struct ht_irq_msg msg;
-
- fetch_ht_irq_msg(irq, &msg);
-
- msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
- msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
-
- msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
- msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
-
- write_ht_irq_msg(irq, &msg);
-}
-
static int
ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest;
+ struct irq_data *parent = data->parent_data;
int ret;
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- target_ht_irq(data->irq, dest, cfg->vector);
- return IRQ_SET_MASK_OK_NOCOPY;
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret >= 0) {
+ struct ht_irq_msg msg;
+ struct irq_cfg *cfg = irqd_cfg(data);
+
+ fetch_ht_irq_msg(data->irq, &msg);
+ msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK |
+ HT_IRQ_LOW_DEST_ID_MASK);
+ msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) |
+ HT_IRQ_LOW_DEST_ID(cfg->dest_apicid);
+ msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+ msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
+ write_ht_irq_msg(data->irq, &msg);
+ }
+
+ return ret;
}
static struct irq_chip ht_irq_chip = {
.name = "PCI-HT",
.irq_mask = mask_ht_irq,
.irq_unmask = unmask_ht_irq,
- .irq_ack = apic_ack_edge,
+ .irq_ack = irq_chip_ack_parent,
.irq_set_affinity = ht_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
+static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- struct irq_cfg *cfg;
- struct ht_irq_msg msg;
- unsigned dest;
- int err;
+ struct ht_irq_cfg *ht_cfg;
+ struct irq_alloc_info *info = arg;
+ struct pci_dev *dev;
+ irq_hw_number_t hwirq;
+ int ret;
- if (disable_apic)
- return -ENXIO;
+ if (nr_irqs > 1 || !info)
+ return -EINVAL;
- cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, apic->target_cpus());
- if (err)
- return err;
+ dev = info->ht_dev;
+ hwirq = (info->ht_idx & 0xFF) |
+ PCI_DEVID(dev->bus->number, dev->devfn) << 8 |
+ (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24;
+ if (irq_find_mapping(domain, hwirq) > 0)
+ return -EEXIST;
- err = apic->cpu_mask_to_apicid_and(cfg->domain,
- apic->target_cpus(), &dest);
- if (err)
- return err;
+ ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL);
+ if (!ht_cfg)
+ return -ENOMEM;
- msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+ if (ret < 0) {
+ kfree(ht_cfg);
+ return ret;
+ }
+
+ /* Initialize msg to a value that will never match the first write. */
+ ht_cfg->msg.address_lo = 0xffffffff;
+ ht_cfg->msg.address_hi = 0xffffffff;
+ ht_cfg->dev = info->ht_dev;
+ ht_cfg->update = info->ht_update;
+ ht_cfg->pos = info->ht_pos;
+ ht_cfg->idx = 0x10 + (info->ht_idx * 2);
+ irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg,
+ handle_edge_irq, ht_cfg, "edge");
+
+ return 0;
+}
+
+static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
+{
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+ BUG_ON(nr_irqs != 1);
+ kfree(irq_data->chip_data);
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
+}
+static void htirq_domain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct ht_irq_msg msg;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
+
+ msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
msg.address_lo =
HT_IRQ_LOW_BASE |
- HT_IRQ_LOW_DEST_ID(dest) |
+ HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
HT_IRQ_LOW_VECTOR(cfg->vector) |
((apic->irq_dest_mode == 0) ?
HT_IRQ_LOW_DM_PHYSICAL :
HT_IRQ_LOW_MT_FIXED :
HT_IRQ_LOW_MT_ARBITRATED) |
HT_IRQ_LOW_IRQ_MASKED;
+ write_ht_irq_msg(irq_data->irq, &msg);
+}
- write_ht_irq_msg(irq, &msg);
+static void htirq_domain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct ht_irq_msg msg;
- irq_set_chip_and_handler_name(irq, &ht_irq_chip,
- handle_edge_irq, "edge");
+ memset(&msg, 0, sizeof(msg));
+ write_ht_irq_msg(irq_data->irq, &msg);
+}
- dev_dbg(&dev->dev, "irq %d for HT\n", irq);
+static const struct irq_domain_ops htirq_domain_ops = {
+ .alloc = htirq_domain_alloc,
+ .free = htirq_domain_free,
+ .activate = htirq_domain_activate,
+ .deactivate = htirq_domain_deactivate,
+};
- return 0;
+void arch_init_htirq_domain(struct irq_domain *parent)
+{
+ if (disable_apic)
+ return;
+
+ htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL);
+ if (!htirq_domain)
+ pr_warn("failed to initialize irqdomain for HTIRQ.\n");
+ else
+ htirq_domain->parent = parent;
+}
+
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+ ht_irq_update_t *update)
+{
+ struct irq_alloc_info info;
+
+ if (!htirq_domain)
+ return -ENOSYS;
+
+ init_irq_alloc_info(&info, NULL);
+ info.ht_idx = idx;
+ info.ht_pos = pos;
+ info.ht_dev = dev;
+ info.ht_update = update;
+
+ return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev),
+ &info);
+}
+
+void arch_teardown_ht_irq(unsigned int irq)
+{
+ irq_domain_free_irqs(irq, 1);
}
* and Rolf G. Tews
* for testing these extensively
* Paul Diefenbaugh : Added full ACPI support
+ *
+ * Historical information which is worth to be preserved:
+ *
+ * - SiS APIC rmw bug:
+ *
+ * We used to have a workaround for a bug in SiS chips which
+ * required to rewrite the index register for a read-modify-write
+ * operation as the chip lost the index information which was
+ * setup for the read already. We cache the data now, so that
+ * workaround has been removed.
*/
#include <linux/mm.h>
#include <linux/acpi.h>
#include <linux/module.h>
#include <linux/syscore_ops.h>
-#include <linux/irqdomain.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/jiffies.h> /* time_after() */
#include <linux/slab.h>
#include <linux/bootmem.h>
+#include <asm/irqdomain.h>
#include <asm/idle.h>
#include <asm/io.h>
#include <asm/smp.h>
#define for_each_ioapic_pin(idx, pin) \
for_each_ioapic((idx)) \
for_each_pin((idx), (pin))
-
#define for_each_irq_pin(entry, head) \
list_for_each_entry(entry, &head, list)
-/*
- * Is the SiS APIC rmw bug present ?
- * -1 = don't know, 0 = no, 1 = yes
- */
-int sis_apic_bug = -1;
-
static DEFINE_RAW_SPINLOCK(ioapic_lock);
static DEFINE_MUTEX(ioapic_mutex);
static unsigned int ioapic_dynirq_base;
static int ioapic_initialized;
-struct mp_pin_info {
+struct irq_pin_list {
+ struct list_head list;
+ int apic, pin;
+};
+
+struct mp_chip_data {
+ struct list_head irq_2_pin;
+ struct IO_APIC_route_entry entry;
int trigger;
int polarity;
- int node;
- int set;
u32 count;
+ bool isa_irq;
+};
+
+struct mp_ioapic_gsi {
+ u32 gsi_base;
+ u32 gsi_end;
};
static struct ioapic {
struct mp_ioapic_gsi gsi_config;
struct ioapic_domain_cfg irqdomain_cfg;
struct irq_domain *irqdomain;
- struct mp_pin_info *pin_info;
struct resource *iomem_res;
} ioapics[MAX_IO_APICS];
return ioapics[ioapic_idx].mp_config.apicaddr;
}
-struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
+static inline struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
{
return &ioapics[ioapic_idx].gsi_config;
}
return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
}
-u32 mp_pin_to_gsi(int ioapic, int pin)
+static inline u32 mp_pin_to_gsi(int ioapic, int pin)
{
return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin;
}
+static inline bool mp_is_legacy_irq(int irq)
+{
+ return irq >= 0 && irq < nr_legacy_irqs();
+}
+
/*
* Initialize all legacy IRQs and all pins on the first IOAPIC
* if we have legacy interrupt controller. Kernel boot option "pirq="
if (!nr_legacy_irqs())
return 0;
- return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs());
-}
-
-static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin)
-{
- return ioapics[ioapic_idx].pin_info + pin;
+ return ioapic == 0 || mp_is_legacy_irq(irq);
}
static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic)
panic("Max # of irq sources exceeded!!\n");
}
-struct irq_pin_list {
- struct list_head list;
- int apic, pin;
-};
-
-static struct irq_pin_list *alloc_irq_pin_list(int node)
-{
- return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
-}
-
static void alloc_ioapic_saved_registers(int idx)
{
size_t size;
int __init arch_early_ioapic_init(void)
{
- struct irq_cfg *cfg;
- int i, node = cpu_to_node(0);
+ int i;
if (!nr_legacy_irqs())
io_apic_irqs = ~0UL;
for_each_ioapic(i)
alloc_ioapic_saved_registers(i);
- /*
- * For legacy IRQ's, start with assigning irq0 to irq15 to
- * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
- */
- for (i = 0; i < nr_legacy_irqs(); i++) {
- cfg = alloc_irq_and_cfg_at(i, node);
- cfg->vector = IRQ0_VECTOR + i;
- cpumask_setall(cfg->domain);
- }
-
return 0;
}
+ (mpc_ioapic_addr(idx) & ~PAGE_MASK);
}
-void io_apic_eoi(unsigned int apic, unsigned int vector)
+static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(vector, &io_apic->eoi);
return readl(&io_apic->data);
}
-void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void io_apic_write(unsigned int apic, unsigned int reg,
+ unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(value, &io_apic->data);
}
-/*
- * Re-write a value: to be used for read-modify-write
- * cycles where the read already set up the index register.
- *
- * Older SiS APIC requires we rewrite the index register
- */
-void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
- struct io_apic __iomem *io_apic = io_apic_base(apic);
-
- if (sis_apic_bug)
- writel(reg, &io_apic->index);
- writel(value, &io_apic->data);
-}
-
union entry_union {
struct { u32 w1, w2; };
struct IO_APIC_route_entry entry;
static void ioapic_mask_entry(int apic, int pin)
{
unsigned long flags;
- union entry_union eu = { .entry.mask = 1 };
+ union entry_union eu = { .entry.mask = IOAPIC_MASKED };
raw_spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic, 0x10 + 2*pin, eu.w1);
* shared ISA-space IRQs, so we have to support them. We are super
* fast in the common case, and fast for shared ISA-space IRQs.
*/
-static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct mp_chip_data *data,
+ int node, int apic, int pin)
{
struct irq_pin_list *entry;
/* don't allow duplicates */
- for_each_irq_pin(entry, cfg->irq_2_pin)
+ for_each_irq_pin(entry, data->irq_2_pin)
if (entry->apic == apic && entry->pin == pin)
return 0;
- entry = alloc_irq_pin_list(node);
+ entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node);
if (!entry) {
pr_err("can not alloc irq_pin_list (%d,%d,%d)\n",
node, apic, pin);
}
entry->apic = apic;
entry->pin = pin;
+ list_add_tail(&entry->list, &data->irq_2_pin);
- list_add_tail(&entry->list, &cfg->irq_2_pin);
return 0;
}
-static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
+static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin)
{
struct irq_pin_list *tmp, *entry;
- list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list)
+ list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list)
if (entry->apic == apic && entry->pin == pin) {
list_del(&entry->list);
kfree(entry);
}
}
-static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static void add_pin_to_irq_node(struct mp_chip_data *data,
+ int node, int apic, int pin)
{
- if (__add_pin_to_irq_node(cfg, node, apic, pin))
+ if (__add_pin_to_irq_node(data, node, apic, pin))
panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
}
/*
* Reroute an IRQ to a different pin.
*/
-static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
+static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node,
int oldapic, int oldpin,
int newapic, int newpin)
{
struct irq_pin_list *entry;
- for_each_irq_pin(entry, cfg->irq_2_pin) {
+ for_each_irq_pin(entry, data->irq_2_pin) {
if (entry->apic == oldapic && entry->pin == oldpin) {
entry->apic = newapic;
entry->pin = newpin;
}
/* old apic/pin didn't exist, so just add new ones */
- add_pin_to_irq_node(cfg, node, newapic, newpin);
-}
-
-static void __io_apic_modify_irq(struct irq_pin_list *entry,
- int mask_and, int mask_or,
- void (*final)(struct irq_pin_list *entry))
-{
- unsigned int reg, pin;
-
- pin = entry->pin;
- reg = io_apic_read(entry->apic, 0x10 + pin * 2);
- reg &= mask_and;
- reg |= mask_or;
- io_apic_modify(entry->apic, 0x10 + pin * 2, reg);
- if (final)
- final(entry);
+ add_pin_to_irq_node(data, node, newapic, newpin);
}
-static void io_apic_modify_irq(struct irq_cfg *cfg,
+static void io_apic_modify_irq(struct mp_chip_data *data,
int mask_and, int mask_or,
void (*final)(struct irq_pin_list *entry))
{
+ union entry_union eu;
struct irq_pin_list *entry;
- for_each_irq_pin(entry, cfg->irq_2_pin)
- __io_apic_modify_irq(entry, mask_and, mask_or, final);
+ eu.entry = data->entry;
+ eu.w1 &= mask_and;
+ eu.w1 |= mask_or;
+ data->entry = eu.entry;
+
+ for_each_irq_pin(entry, data->irq_2_pin) {
+ io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1);
+ if (final)
+ final(entry);
+ }
}
static void io_apic_sync(struct irq_pin_list *entry)
readl(&io_apic->data);
}
-static void mask_ioapic(struct irq_cfg *cfg)
+static void mask_ioapic_irq(struct irq_data *irq_data)
{
+ struct mp_chip_data *data = irq_data->chip_data;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+ io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void mask_ioapic_irq(struct irq_data *data)
+static void __unmask_ioapic(struct mp_chip_data *data)
{
- mask_ioapic(irqd_cfg(data));
+ io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL);
}
-static void __unmask_ioapic(struct irq_cfg *cfg)
-{
- io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
-static void unmask_ioapic(struct irq_cfg *cfg)
+static void unmask_ioapic_irq(struct irq_data *irq_data)
{
+ struct mp_chip_data *data = irq_data->chip_data;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- __unmask_ioapic(cfg);
+ __unmask_ioapic(data);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void unmask_ioapic_irq(struct irq_data *data)
-{
- unmask_ioapic(irqd_cfg(data));
-}
-
/*
* IO-APIC versions below 0x20 don't support EOI register.
* For the record, here is the information about various versions:
* Otherwise, we simulate the EOI message manually by changing the trigger
* mode to edge and then back to level, with RTE being masked during this.
*/
-void native_eoi_ioapic_pin(int apic, int pin, int vector)
+static void __eoi_ioapic_pin(int apic, int pin, int vector)
{
if (mpc_ioapic_ver(apic) >= 0x20) {
io_apic_eoi(apic, vector);
/*
* Mask the entry and change the trigger mode to edge.
*/
- entry1.mask = 1;
+ entry1.mask = IOAPIC_MASKED;
entry1.trigger = IOAPIC_EDGE;
__ioapic_write_entry(apic, pin, entry1);
}
}
-void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+void eoi_ioapic_pin(int vector, struct mp_chip_data *data)
{
- struct irq_pin_list *entry;
unsigned long flags;
+ struct irq_pin_list *entry;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- for_each_irq_pin(entry, cfg->irq_2_pin)
- x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin,
- cfg->vector);
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __eoi_ioapic_pin(entry->apic, entry->pin, vector);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
* Make sure the entry is masked and re-read the contents to check
* if it is a level triggered pin and if the remote-IRR is set.
*/
- if (!entry.mask) {
- entry.mask = 1;
+ if (entry.mask == IOAPIC_UNMASKED) {
+ entry.mask = IOAPIC_MASKED;
ioapic_write_entry(apic, pin, entry);
entry = ioapic_read_entry(apic, pin);
}
* doesn't clear the remote-IRR if the trigger mode is not
* set to level.
*/
- if (!entry.trigger) {
+ if (entry.trigger == IOAPIC_EDGE) {
entry.trigger = IOAPIC_LEVEL;
ioapic_write_entry(apic, pin, entry);
}
-
raw_spin_lock_irqsave(&ioapic_lock, flags);
- x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector);
+ __eoi_ioapic_pin(apic, pin, entry.vector);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
struct IO_APIC_route_entry entry;
entry = ioapics[apic].saved_registers[pin];
- if (!entry.mask) {
- entry.mask = 1;
+ if (entry.mask == IOAPIC_UNMASKED) {
+ entry.mask = IOAPIC_MASKED;
ioapic_write_entry(apic, pin, entry);
}
}
#endif
-/* ISA interrupts are always polarity zero edge triggered,
+/* ISA interrupts are always active high edge triggered,
* when listed as conforming in the MP table. */
-#define default_ISA_trigger(idx) (0)
-#define default_ISA_polarity(idx) (0)
+#define default_ISA_trigger(idx) (IOAPIC_EDGE)
+#define default_ISA_polarity(idx) (IOAPIC_POL_HIGH)
/* EISA interrupts are always polarity zero and can be edge or level
* trigger depending on the ELCR value. If an interrupt is listed as
#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq))
#define default_EISA_polarity(idx) default_ISA_polarity(idx)
-/* PCI interrupts are always polarity one level triggered,
+/* PCI interrupts are always active low level triggered,
* when listed as conforming in the MP table. */
-#define default_PCI_trigger(idx) (1)
-#define default_PCI_polarity(idx) (1)
+#define default_PCI_trigger(idx) (IOAPIC_LEVEL)
+#define default_PCI_polarity(idx) (IOAPIC_POL_LOW)
static int irq_polarity(int idx)
{
int bus = mp_irqs[idx].srcbus;
- int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].irqflag & 3)
- {
- case 0: /* conforms, ie. bus-type dependent polarity */
- if (test_bit(bus, mp_bus_not_pci))
- polarity = default_ISA_polarity(idx);
- else
- polarity = default_PCI_polarity(idx);
- break;
- case 1: /* high active */
- {
- polarity = 0;
- break;
- }
- case 2: /* reserved */
- {
- pr_warn("broken BIOS!!\n");
- polarity = 1;
- break;
- }
- case 3: /* low active */
- {
- polarity = 1;
- break;
- }
- default: /* invalid */
- {
- pr_warn("broken BIOS!!\n");
- polarity = 1;
- break;
- }
+ switch (mp_irqs[idx].irqflag & 0x03) {
+ case 0:
+ /* conforms to spec, ie. bus-type dependent polarity */
+ if (test_bit(bus, mp_bus_not_pci))
+ return default_ISA_polarity(idx);
+ else
+ return default_PCI_polarity(idx);
+ case 1:
+ return IOAPIC_POL_HIGH;
+ case 2:
+ pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
+ case 3:
+ default: /* Pointless default required due to do gcc stupidity */
+ return IOAPIC_POL_LOW;
+ }
+}
+
+#ifdef CONFIG_EISA
+static int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+ switch (mp_bus_id_to_type[bus]) {
+ case MP_BUS_PCI:
+ case MP_BUS_ISA:
+ return trigger;
+ case MP_BUS_EISA:
+ return default_EISA_trigger(idx);
}
- return polarity;
+ pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus);
+ return IOAPIC_LEVEL;
}
+#else
+static inline int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+ return trigger;
+}
+#endif
static int irq_trigger(int idx)
{
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].irqflag>>2) & 3)
- {
- case 0: /* conforms, ie. bus-type dependent */
- if (test_bit(bus, mp_bus_not_pci))
- trigger = default_ISA_trigger(idx);
- else
- trigger = default_PCI_trigger(idx);
-#ifdef CONFIG_EISA
- switch (mp_bus_id_to_type[bus]) {
- case MP_BUS_ISA: /* ISA pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_EISA: /* EISA pin */
- {
- trigger = default_EISA_trigger(idx);
- break;
- }
- case MP_BUS_PCI: /* PCI pin */
- {
- /* set before the switch */
- break;
- }
- default:
- {
- pr_warn("broken BIOS!!\n");
- trigger = 1;
- break;
- }
- }
+ switch ((mp_irqs[idx].irqflag >> 2) & 0x03) {
+ case 0:
+ /* conforms to spec, ie. bus-type dependent trigger mode */
+ if (test_bit(bus, mp_bus_not_pci))
+ trigger = default_ISA_trigger(idx);
+ else
+ trigger = default_PCI_trigger(idx);
+ /* Take EISA into account */
+ return eisa_irq_trigger(idx, bus, trigger);
+ case 1:
+ return IOAPIC_EDGE;
+ case 2:
+ pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
+ case 3:
+ default: /* Pointless default required due to do gcc stupidity */
+ return IOAPIC_LEVEL;
+ }
+}
+
+void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node,
+ int trigger, int polarity)
+{
+ init_irq_alloc_info(info, NULL);
+ info->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ info->ioapic_node = node;
+ info->ioapic_trigger = trigger;
+ info->ioapic_polarity = polarity;
+ info->ioapic_valid = 1;
+}
+
+#ifndef CONFIG_ACPI
+int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity);
#endif
- break;
- case 1: /* edge */
- {
- trigger = 0;
- break;
- }
- case 2: /* reserved */
- {
- pr_warn("broken BIOS!!\n");
- trigger = 1;
- break;
- }
- case 3: /* level */
- {
- trigger = 1;
- break;
- }
- default: /* invalid */
- {
- pr_warn("broken BIOS!!\n");
- trigger = 0;
- break;
+
+static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst,
+ struct irq_alloc_info *src,
+ u32 gsi, int ioapic_idx, int pin)
+{
+ int trigger, polarity;
+
+ copy_irq_alloc_info(dst, src);
+ dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ dst->ioapic_id = mpc_ioapic_id(ioapic_idx);
+ dst->ioapic_pin = pin;
+ dst->ioapic_valid = 1;
+ if (src && src->ioapic_valid) {
+ dst->ioapic_node = src->ioapic_node;
+ dst->ioapic_trigger = src->ioapic_trigger;
+ dst->ioapic_polarity = src->ioapic_polarity;
+ } else {
+ dst->ioapic_node = NUMA_NO_NODE;
+ if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) {
+ dst->ioapic_trigger = trigger;
+ dst->ioapic_polarity = polarity;
+ } else {
+ /*
+ * PCI interrupts are always active low level
+ * triggered.
+ */
+ dst->ioapic_trigger = IOAPIC_LEVEL;
+ dst->ioapic_polarity = IOAPIC_POL_LOW;
}
}
- return trigger;
}
-static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin)
+static int ioapic_alloc_attr_node(struct irq_alloc_info *info)
+{
+ return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE;
+}
+
+static void mp_register_handler(unsigned int irq, unsigned long trigger)
+{
+ irq_flow_handler_t hdl;
+ bool fasteoi;
+
+ if (trigger) {
+ irq_set_status_flags(irq, IRQ_LEVEL);
+ fasteoi = true;
+ } else {
+ irq_clear_status_flags(irq, IRQ_LEVEL);
+ fasteoi = false;
+ }
+
+ hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
+ __irq_set_handler(irq, hdl, 0, fasteoi ? "fasteoi" : "edge");
+}
+
+static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
{
+ struct mp_chip_data *data = irq_get_chip_data(irq);
+
+ /*
+ * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger
+ * and polarity attirbutes. So allow the first user to reprogram the
+ * pin with real trigger and polarity attributes.
+ */
+ if (irq < nr_legacy_irqs() && data->count == 1) {
+ if (info->ioapic_trigger != data->trigger)
+ mp_register_handler(irq, data->trigger);
+ data->entry.trigger = data->trigger = info->ioapic_trigger;
+ data->entry.polarity = data->polarity = info->ioapic_polarity;
+ }
+
+ return data->trigger == info->ioapic_trigger &&
+ data->polarity == info->ioapic_polarity;
+}
+
+static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi,
+ struct irq_alloc_info *info)
+{
+ bool legacy = false;
int irq = -1;
- int ioapic = (int)(long)domain->host_data;
int type = ioapics[ioapic].irqdomain_cfg.type;
switch (type) {
case IOAPIC_DOMAIN_LEGACY:
/*
- * Dynamically allocate IRQ number for non-ISA IRQs in the first 16
- * GSIs on some weird platforms.
+ * Dynamically allocate IRQ number for non-ISA IRQs in the first
+ * 16 GSIs on some weird platforms.
*/
- if (gsi < nr_legacy_irqs())
- irq = irq_create_mapping(domain, pin);
- else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
+ if (!ioapic_initialized || gsi >= nr_legacy_irqs())
irq = gsi;
+ legacy = mp_is_legacy_irq(irq);
break;
case IOAPIC_DOMAIN_STRICT:
- if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
- irq = gsi;
+ irq = gsi;
break;
case IOAPIC_DOMAIN_DYNAMIC:
- irq = irq_create_mapping(domain, pin);
break;
default:
WARN(1, "ioapic: unknown irqdomain type %d\n", type);
- break;
+ return -1;
+ }
+
+ return __irq_domain_alloc_irqs(domain, irq, 1,
+ ioapic_alloc_attr_node(info),
+ info, legacy);
+}
+
+/*
+ * Need special handling for ISA IRQs because there may be multiple IOAPIC pins
+ * sharing the same ISA IRQ number and irqdomain only supports 1:1 mapping
+ * between IOAPIC pin and IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are
+ * used for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
+ * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are available, and
+ * some BIOSes may use MP Interrupt Source records to override IRQ numbers for
+ * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be
+ * multiple pins sharing the same legacy IRQ number when ACPI is disabled.
+ */
+static int alloc_isa_irq_from_domain(struct irq_domain *domain,
+ int irq, int ioapic, int pin,
+ struct irq_alloc_info *info)
+{
+ struct mp_chip_data *data;
+ struct irq_data *irq_data = irq_get_irq_data(irq);
+ int node = ioapic_alloc_attr_node(info);
+
+ /*
+ * Legacy ISA IRQ has already been allocated, just add pin to
+ * the pin list assoicated with this IRQ and program the IOAPIC
+ * entry. The IOAPIC entry
+ */
+ if (irq_data && irq_data->parent_data) {
+ if (!mp_check_pin_attr(irq, info))
+ return -EBUSY;
+ if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic,
+ info->ioapic_pin))
+ return -ENOMEM;
+ } else {
+ irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true);
+ if (irq >= 0) {
+ irq_data = irq_domain_get_irq_data(domain, irq);
+ data = irq_data->chip_data;
+ data->isa_irq = true;
+ }
}
- return irq > 0 ? irq : -1;
+ return irq;
}
static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
- unsigned int flags)
+ unsigned int flags, struct irq_alloc_info *info)
{
int irq;
+ bool legacy = false;
+ struct irq_alloc_info tmp;
+ struct mp_chip_data *data;
struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
- struct mp_pin_info *info = mp_pin_info(ioapic, pin);
if (!domain)
- return -1;
+ return -ENOSYS;
- mutex_lock(&ioapic_mutex);
-
- /*
- * Don't use irqdomain to manage ISA IRQs because there may be
- * multiple IOAPIC pins sharing the same ISA IRQ number and
- * irqdomain only supports 1:1 mapping between IOAPIC pin and
- * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used
- * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
- * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are
- * available, and some BIOSes may use MP Interrupt Source records
- * to override IRQ numbers for PIRQs instead of reprogramming
- * the interrupt routing logic. Thus there may be multiple pins
- * sharing the same legacy IRQ number when ACPI is disabled.
- */
if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
irq = mp_irqs[idx].srcbusirq;
- if (flags & IOAPIC_MAP_ALLOC) {
- if (info->count == 0 &&
- mp_irqdomain_map(domain, irq, pin) != 0)
- irq = -1;
+ legacy = mp_is_legacy_irq(irq);
+ }
- /* special handling for timer IRQ0 */
+ mutex_lock(&ioapic_mutex);
+ if (!(flags & IOAPIC_MAP_ALLOC)) {
+ if (!legacy) {
+ irq = irq_find_mapping(domain, pin);
if (irq == 0)
- info->count++;
+ irq = -ENOENT;
}
} else {
- irq = irq_find_mapping(domain, pin);
- if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC))
- irq = alloc_irq_from_domain(domain, gsi, pin);
- }
-
- if (flags & IOAPIC_MAP_ALLOC) {
- /* special handling for legacy IRQs */
- if (irq < nr_legacy_irqs() && info->count == 1 &&
- mp_irqdomain_map(domain, irq, pin) != 0)
- irq = -1;
-
- if (irq > 0)
- info->count++;
- else if (info->count == 0)
- info->set = 0;
+ ioapic_copy_alloc_attr(&tmp, info, gsi, ioapic, pin);
+ if (legacy)
+ irq = alloc_isa_irq_from_domain(domain, irq,
+ ioapic, pin, &tmp);
+ else if ((irq = irq_find_mapping(domain, pin)) == 0)
+ irq = alloc_irq_from_domain(domain, ioapic, gsi, &tmp);
+ else if (!mp_check_pin_attr(irq, &tmp))
+ irq = -EBUSY;
+ if (irq >= 0) {
+ data = irq_get_chip_data(irq);
+ data->count++;
+ }
}
-
mutex_unlock(&ioapic_mutex);
- return irq > 0 ? irq : -1;
+ return irq;
}
static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
}
#endif
- return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+ return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, NULL);
}
-int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
+int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info)
{
int ioapic, pin, idx;
if ((flags & IOAPIC_MAP_CHECK) && idx < 0)
return -1;
- return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+ return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info);
}
void mp_unmap_irq(int irq)
{
- struct irq_data *data = irq_get_irq_data(irq);
- struct mp_pin_info *info;
- int ioapic, pin;
+ struct irq_data *irq_data = irq_get_irq_data(irq);
+ struct mp_chip_data *data;
- if (!data || !data->domain)
+ if (!irq_data || !irq_data->domain)
return;
- ioapic = (int)(long)data->domain->host_data;
- pin = (int)data->hwirq;
- info = mp_pin_info(ioapic, pin);
+ data = irq_data->chip_data;
+ if (!data || data->isa_irq)
+ return;
mutex_lock(&ioapic_mutex);
- if (--info->count == 0) {
- info->set = 0;
- if (irq < nr_legacy_irqs() &&
- ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY)
- mp_irqdomain_unmap(data->domain, irq);
- else
- irq_dispose_mapping(irq);
- }
+ if (--data->count == 0)
+ irq_domain_free_irqs(irq, 1);
mutex_unlock(&ioapic_mutex);
}
}
EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-static struct irq_chip ioapic_chip;
+static struct irq_chip ioapic_chip, ioapic_ir_chip;
#ifdef CONFIG_X86_32
static inline int IO_APIC_irq_trigger(int irq)
}
#endif
-static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
- unsigned long trigger)
-{
- struct irq_chip *chip = &ioapic_chip;
- irq_flow_handler_t hdl;
- bool fasteoi;
-
- if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
- trigger == IOAPIC_LEVEL) {
- irq_set_status_flags(irq, IRQ_LEVEL);
- fasteoi = true;
- } else {
- irq_clear_status_flags(irq, IRQ_LEVEL);
- fasteoi = false;
- }
-
- if (setup_remapped_irq(irq, cfg, chip))
- fasteoi = trigger != 0;
-
- hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
- irq_set_chip_and_handler_name(irq, chip, hdl,
- fasteoi ? "fasteoi" : "edge");
-}
-
-int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
-{
- memset(entry, 0, sizeof(*entry));
-
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->dest = destination;
- entry->vector = vector;
- entry->mask = 0; /* enable IRQ */
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
-
- /*
- * Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
-
- return 0;
-}
-
-static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
- struct io_apic_irq_attr *attr)
-{
- struct IO_APIC_route_entry entry;
- unsigned int dest;
-
- if (!IO_APIC_IRQ(irq))
- return;
-
- if (assign_irq_vector(irq, cfg, apic->target_cpus()))
- return;
-
- if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(),
- &dest)) {
- pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n",
- mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
- clear_irq_vector(irq, cfg);
-
- return;
- }
-
- apic_printk(APIC_VERBOSE,KERN_DEBUG
- "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
- "IRQ %d Mode:%i Active:%i Dest:%d)\n",
- attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin,
- cfg->vector, irq, attr->trigger, attr->polarity, dest);
-
- if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) {
- pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n",
- mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
- clear_irq_vector(irq, cfg);
-
- return;
- }
-
- ioapic_register_intr(irq, cfg, attr->trigger);
- if (irq < nr_legacy_irqs())
- legacy_pic->mask(irq);
-
- ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry);
-}
-
static void __init setup_IO_APIC_irqs(void)
{
unsigned int ioapic, pin;
}
}
-/*
- * Set up the timer pin, possibly with the 8259A-master behind.
- */
-static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
- unsigned int pin, int vector)
-{
- struct IO_APIC_route_entry entry;
- unsigned int dest;
-
- memset(&entry, 0, sizeof(entry));
-
- /*
- * We use logical delivery to get the timer IRQ
- * to the first CPU.
- */
- if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(),
- apic->target_cpus(), &dest)))
- dest = BAD_APICID;
-
- entry.dest_mode = apic->irq_dest_mode;
- entry.mask = 0; /* don't mask IRQ for edge */
- entry.dest = dest;
- entry.delivery_mode = apic->irq_delivery_mode;
- entry.polarity = 0;
- entry.trigger = 0;
- entry.vector = vector;
-
- /*
- * The timer IRQ doesn't have to know that behind the
- * scene we may have a 8259A-master in AEOI mode ...
- */
- irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
- "edge");
-
- /*
- * Add it to the IO-APIC irq-routing table:
- */
- ioapic_write_entry(ioapic_idx, pin, entry);
-}
-
-void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
+void ioapic_zap_locks(void)
{
- int i;
-
- pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n");
-
- for (i = 0; i <= nr_entries; i++) {
- struct IO_APIC_route_entry entry;
-
- entry = ioapic_read_entry(apic, i);
-
- pr_debug(" %02x %02X ", i, entry.dest);
- pr_cont("%1d %1d %1d %1d %1d "
- "%1d %1d %02X\n",
- entry.mask,
- entry.trigger,
- entry.irr,
- entry.polarity,
- entry.delivery_status,
- entry.dest_mode,
- entry.delivery_mode,
- entry.vector);
- }
+ raw_spin_lock_init(&ioapic_lock);
}
-void intel_ir_io_apic_print_entries(unsigned int apic,
- unsigned int nr_entries)
+static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
{
int i;
+ char buf[256];
+ struct IO_APIC_route_entry entry;
+ struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry;
- pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n");
-
+ printk(KERN_DEBUG "IOAPIC %d:\n", apic);
for (i = 0; i <= nr_entries; i++) {
- struct IR_IO_APIC_route_entry *ir_entry;
- struct IO_APIC_route_entry entry;
-
entry = ioapic_read_entry(apic, i);
-
- ir_entry = (struct IR_IO_APIC_route_entry *)&entry;
-
- pr_debug(" %02x %04X ", i, ir_entry->index);
- pr_cont("%1d %1d %1d %1d %1d "
- "%1d %1d %X %02X\n",
- ir_entry->format,
- ir_entry->mask,
- ir_entry->trigger,
- ir_entry->irr,
- ir_entry->polarity,
- ir_entry->delivery_status,
- ir_entry->index2,
- ir_entry->zero,
- ir_entry->vector);
+ snprintf(buf, sizeof(buf),
+ " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)",
+ i,
+ entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ",
+ entry.trigger == IOAPIC_LEVEL ? "level" : "edge ",
+ entry.polarity == IOAPIC_POL_LOW ? "low " : "high",
+ entry.vector, entry.irr, entry.delivery_status);
+ if (ir_entry->format)
+ printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n",
+ buf, (ir_entry->index << 15) | ir_entry->index,
+ ir_entry->zero);
+ else
+ printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n",
+ buf,
+ entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ?
+ "logical " : "physical",
+ entry.dest, entry.delivery_mode);
}
}
-void ioapic_zap_locks(void)
-{
- raw_spin_lock_init(&ioapic_lock);
-}
-
static void __init print_IO_APIC(int ioapic_idx)
{
union IO_APIC_reg_00 reg_00;
}
printk(KERN_DEBUG ".... IRQ redirection table:\n");
-
- x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries);
+ io_apic_print_entries(ioapic_idx, reg_01.bits.entries);
}
void __init print_IO_APICs(void)
{
int ioapic_idx;
- struct irq_cfg *cfg;
unsigned int irq;
- struct irq_chip *chip;
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for_each_ioapic(ioapic_idx)
printk(KERN_DEBUG "IRQ to pin mappings:\n");
for_each_active_irq(irq) {
struct irq_pin_list *entry;
+ struct irq_chip *chip;
+ struct mp_chip_data *data;
chip = irq_get_chip(irq);
- if (chip != &ioapic_chip)
+ if (chip != &ioapic_chip && chip != &ioapic_ir_chip)
continue;
-
- cfg = irq_cfg(irq);
- if (!cfg)
+ data = irq_get_chip_data(irq);
+ if (!data)
continue;
- if (list_empty(&cfg->irq_2_pin))
+ if (list_empty(&data->irq_2_pin))
continue;
+
printk(KERN_DEBUG "IRQ%d ", irq);
- for_each_irq_pin(entry, cfg->irq_2_pin)
+ for_each_irq_pin(entry, data->irq_2_pin)
pr_cont("-> %d:%d", entry->apic, entry->pin);
pr_cont("\n");
}
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
- entry.mask = 0; /* Enabled */
- entry.trigger = 0; /* Edge */
- entry.irr = 0;
- entry.polarity = 0; /* High */
- entry.delivery_status = 0;
- entry.dest_mode = 0; /* Physical */
- entry.delivery_mode = dest_ExtINT; /* ExtInt */
- entry.vector = 0;
- entry.dest = read_apic_id();
+ entry.mask = IOAPIC_UNMASKED;
+ entry.trigger = IOAPIC_EDGE;
+ entry.polarity = IOAPIC_POL_HIGH;
+ entry.dest_mode = IOAPIC_DEST_MODE_PHYSICAL;
+ entry.delivery_mode = dest_ExtINT;
+ entry.dest = read_apic_id();
/*
* Add it to the IO-APIC irq-routing table:
if (cpu_has_apic || apic_from_smp_config())
disconnect_bsp_APIC(ioapic_i8259.pin != -1);
-
}
/*
* This is not complete - we should be able to fake
* an edge even if it isn't on the 8259A...
*/
-
static unsigned int startup_ioapic_irq(struct irq_data *data)
{
int was_pending = 0, irq = data->irq;
if (legacy_pic->irq_pending(irq))
was_pending = 1;
}
- __unmask_ioapic(irqd_cfg(data));
+ __unmask_ioapic(data->chip_data);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return was_pending;
}
-/*
- * Level and edge triggered IO-APIC interrupts need different handling,
- * so we use two separate IRQ descriptors. Edge triggered IRQs can be
- * handled with the level-triggered descriptor, but that one has slightly
- * more overhead. Level-triggered interrupts cannot be handled with the
- * edge-triggered handler, without risking IRQ storms and other ugly
- * races.
- */
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
- int apic, pin;
- struct irq_pin_list *entry;
- u8 vector = cfg->vector;
-
- for_each_irq_pin(entry, cfg->irq_2_pin) {
- unsigned int reg;
-
- apic = entry->apic;
- pin = entry->pin;
-
- io_apic_write(apic, 0x11 + pin*2, dest);
- reg = io_apic_read(apic, 0x10 + pin*2);
- reg &= ~IO_APIC_REDIR_VECTOR_MASK;
- reg |= vector;
- io_apic_modify(apic, 0x10 + pin*2, reg);
- }
-}
-
-int native_ioapic_set_affinity(struct irq_data *data,
- const struct cpumask *mask,
- bool force)
-{
- unsigned int dest, irq = data->irq;
- unsigned long flags;
- int ret;
-
- if (!config_enabled(CONFIG_SMP))
- return -EPERM;
-
- raw_spin_lock_irqsave(&ioapic_lock, flags);
- ret = apic_set_affinity(data, mask, &dest);
- if (!ret) {
- /* Only the high 8 bits are valid. */
- dest = SET_APIC_LOGICAL_ID(dest);
- __target_IO_APIC_irq(irq, dest, irqd_cfg(data));
- ret = IRQ_SET_MASK_OK_NOCOPY;
- }
- raw_spin_unlock_irqrestore(&ioapic_lock, flags);
- return ret;
-}
-
atomic_t irq_mis_count;
#ifdef CONFIG_GENERIC_PENDING_IRQ
-static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
+static bool io_apic_level_ack_pending(struct mp_chip_data *data)
{
struct irq_pin_list *entry;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- for_each_irq_pin(entry, cfg->irq_2_pin) {
+ for_each_irq_pin(entry, data->irq_2_pin) {
unsigned int reg;
int pin;
return false;
}
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
{
/* If we are moving the irq we need to mask it */
if (unlikely(irqd_is_setaffinity_pending(data))) {
- mask_ioapic(cfg);
+ mask_ioapic_irq(data);
return true;
}
return false;
}
-static inline void ioapic_irqd_unmask(struct irq_data *data,
- struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
{
if (unlikely(masked)) {
/* Only migrate the irq if the ack has been received.
* accurate and is causing problems then it is a hardware bug
* and you can go talk to the chipset vendor about it.
*/
- if (!io_apic_level_ack_pending(cfg))
+ if (!io_apic_level_ack_pending(data->chip_data))
irq_move_masked_irq(data);
- unmask_ioapic(cfg);
+ unmask_ioapic_irq(data);
}
}
#else
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
{
return false;
}
-static inline void ioapic_irqd_unmask(struct irq_data *data,
- struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
{
}
#endif
-static void ack_ioapic_level(struct irq_data *data)
+static void ioapic_ack_level(struct irq_data *irq_data)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- int i, irq = data->irq;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
unsigned long v;
bool masked;
+ int i;
irq_complete_move(cfg);
- masked = ioapic_irqd_mask(data, cfg);
+ masked = ioapic_irqd_mask(irq_data);
/*
* It appears there is an erratum which affects at least version 0x11
*/
if (!(v & (1 << (i & 0x1f)))) {
atomic_inc(&irq_mis_count);
+ eoi_ioapic_pin(cfg->vector, irq_data->chip_data);
+ }
+
+ ioapic_irqd_unmask(irq_data, masked);
+}
+
+static void ioapic_ir_ack_level(struct irq_data *irq_data)
+{
+ struct mp_chip_data *data = irq_data->chip_data;
+
+ /*
+ * Intr-remapping uses pin number as the virtual vector
+ * in the RTE. Actual vector is programmed in
+ * intr-remapping table entry. Hence for the io-apic
+ * EOI we use the pin number.
+ */
+ ack_APIC_irq();
+ eoi_ioapic_pin(data->entry.vector, data);
+}
- eoi_ioapic_irq(irq, cfg);
+static int ioapic_set_affinity(struct irq_data *irq_data,
+ const struct cpumask *mask, bool force)
+{
+ struct irq_data *parent = irq_data->parent_data;
+ struct mp_chip_data *data = irq_data->chip_data;
+ struct irq_pin_list *entry;
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ int ret;
+
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
+ cfg = irqd_cfg(irq_data);
+ data->entry.dest = cfg->dest_apicid;
+ data->entry.vector = cfg->vector;
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __ioapic_write_entry(entry->apic, entry->pin,
+ data->entry);
}
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
- ioapic_irqd_unmask(data, cfg, masked);
+ return ret;
}
static struct irq_chip ioapic_chip __read_mostly = {
.irq_startup = startup_ioapic_irq,
.irq_mask = mask_ioapic_irq,
.irq_unmask = unmask_ioapic_irq,
- .irq_ack = apic_ack_edge,
- .irq_eoi = ack_ioapic_level,
- .irq_set_affinity = native_ioapic_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_eoi = ioapic_ack_level,
+ .irq_set_affinity = ioapic_set_affinity,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+static struct irq_chip ioapic_ir_chip __read_mostly = {
+ .name = "IR-IO-APIC",
+ .irq_startup = startup_ioapic_irq,
+ .irq_mask = mask_ioapic_irq,
+ .irq_unmask = unmask_ioapic_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_eoi = ioapic_ir_ack_level,
+ .irq_set_affinity = ioapic_set_affinity,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
memset(&entry1, 0, sizeof(entry1));
- entry1.dest_mode = 0; /* physical delivery */
- entry1.mask = 0; /* unmask IRQ now */
+ entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL;
+ entry1.mask = IOAPIC_UNMASKED;
entry1.dest = hard_smp_processor_id();
entry1.delivery_mode = dest_ExtINT;
entry1.polarity = entry0.polarity;
- entry1.trigger = 0;
+ entry1.trigger = IOAPIC_EDGE;
entry1.vector = 0;
ioapic_write_entry(apic, pin, entry1);
}
early_param("disable_timer_pin_1", disable_timer_pin_setup);
+static int mp_alloc_timer_irq(int ioapic, int pin)
+{
+ int irq = -1;
+ struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
+
+ if (domain) {
+ struct irq_alloc_info info;
+
+ ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0);
+ info.ioapic_id = mpc_ioapic_id(ioapic);
+ info.ioapic_pin = pin;
+ mutex_lock(&ioapic_mutex);
+ irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info);
+ mutex_unlock(&ioapic_mutex);
+ }
+
+ return irq;
+}
+
/*
* This code may look a bit paranoid, but it's supposed to cooperate with
* a wide range of boards and BIOS bugs. Fortunately only the timer IRQ
*/
static inline void __init check_timer(void)
{
- struct irq_cfg *cfg = irq_cfg(0);
+ struct irq_data *irq_data = irq_get_irq_data(0);
+ struct mp_chip_data *data = irq_data->chip_data;
+ struct irq_cfg *cfg = irqd_cfg(irq_data);
int node = cpu_to_node(0);
int apic1, pin1, apic2, pin2;
unsigned long flags;
* get/set the timer IRQ vector:
*/
legacy_pic->mask(0);
- assign_irq_vector(0, cfg, apic->target_cpus());
/*
* As IRQ0 is to be enabled in the 8259A, the virtual
}
if (pin1 != -1) {
- /*
- * Ok, does IRQ0 through the IOAPIC work?
- */
+ /* Ok, does IRQ0 through the IOAPIC work? */
if (no_pin1) {
- add_pin_to_irq_node(cfg, node, apic1, pin1);
- setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+ mp_alloc_timer_irq(apic1, pin1);
} else {
- /* for edge trigger, setup_ioapic_irq already
- * leave it unmasked.
+ /*
+ * for edge trigger, it's already unmasked,
* so only need to unmask if it is level-trigger
* do we really have level trigger timer?
*/
int idx;
idx = find_irq_entry(apic1, pin1, mp_INT);
if (idx != -1 && irq_trigger(idx))
- unmask_ioapic(cfg);
+ unmask_ioapic_irq(irq_get_chip_data(0));
}
+ irq_domain_activate_irq(irq_data);
if (timer_irq_works()) {
if (disable_timer_pin_1 > 0)
clear_IO_APIC_pin(0, pin1);
/*
* legacy devices should be connected to IO APIC #0
*/
- replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
- setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+ irq_domain_activate_irq(irq_data);
legacy_pic->unmask(0);
if (timer_irq_works()) {
apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
static int mp_irqdomain_create(int ioapic)
{
- size_t size;
+ struct irq_alloc_info info;
+ struct irq_domain *parent;
int hwirqs = mp_ioapic_pin_count(ioapic);
struct ioapic *ip = &ioapics[ioapic];
struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg;
struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic);
- size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic);
- ip->pin_info = kzalloc(size, GFP_KERNEL);
- if (!ip->pin_info)
- return -ENOMEM;
-
if (cfg->type == IOAPIC_DOMAIN_INVALID)
return 0;
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+ info.ioapic_id = mpc_ioapic_id(ioapic);
+ parent = irq_remapping_get_ir_irq_domain(&info);
+ if (!parent)
+ parent = x86_vector_domain;
+
ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops,
(void *)(long)ioapic);
- if(!ip->irqdomain) {
- kfree(ip->pin_info);
- ip->pin_info = NULL;
+ if (!ip->irqdomain)
return -ENOMEM;
- }
+
+ ip->irqdomain->parent = parent;
if (cfg->type == IOAPIC_DOMAIN_LEGACY ||
cfg->type == IOAPIC_DOMAIN_STRICT)
ioapic_dynirq_base = max(ioapic_dynirq_base,
gsi_cfg->gsi_end + 1);
- if (gsi_cfg->gsi_base == 0)
- irq_set_default_host(ip->irqdomain);
-
return 0;
}
irq_domain_remove(ioapics[idx].irqdomain);
ioapics[idx].irqdomain = NULL;
}
- kfree(ioapics[idx].pin_info);
- ioapics[idx].pin_info = NULL;
}
void __init setup_IO_APIC(void)
ioapic_initialized = 1;
}
-/*
- * Called after all the initialization is done. If we didn't find any
- * APIC bugs then we can allow the modify fast path
- */
-
-static int __init io_apic_bug_finalize(void)
-{
- if (sis_apic_bug == -1)
- sis_apic_bug = 0;
- return 0;
-}
-
-late_initcall(io_apic_bug_finalize);
-
static void resume_ioapic_id(int ioapic_idx)
{
unsigned long flags;
device_initcall(ioapic_init_ops);
-static int
-io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
-{
- struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
- int ret;
-
- if (!cfg)
- return -EINVAL;
- ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin);
- if (!ret)
- setup_ioapic_irq(irq, cfg, attr);
- return ret;
-}
-
static int io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
else
mask = apic->target_cpus();
- x86_io_apic_ops.set_affinity(idata, mask, false);
+ irq_set_affinity(irq, mask);
}
}
return res;
}
-void __init native_io_apic_init_mappings(void)
+void __init io_apic_init_mappings(void)
{
unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
struct resource *ioapic_res;
{
int ioapic, pin;
int found = 0;
- struct mp_pin_info *pin_info;
for_each_ioapic(ioapic)
if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) {
}
for_each_pin(ioapic, pin) {
- pin_info = mp_pin_info(ioapic, pin);
- if (pin_info->count) {
- pr_warn("pin%d on IOAPIC%d is still in use.\n",
- pin, ioapic);
- return -EBUSY;
+ u32 gsi = mp_pin_to_gsi(ioapic, pin);
+ int irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+ struct mp_chip_data *data;
+
+ if (irq >= 0) {
+ data = irq_get_chip_data(irq);
+ if (data && data->count) {
+ pr_warn("pin%d on IOAPIC%d is still in use.\n",
+ pin, ioapic);
+ return -EBUSY;
+ }
}
}
return 0;
}
-static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
- int ioapic, int ioapic_pin,
- int trigger, int polarity)
+static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data,
+ struct irq_alloc_info *info)
{
- irq_attr->ioapic = ioapic;
- irq_attr->ioapic_pin = ioapic_pin;
- irq_attr->trigger = trigger;
- irq_attr->polarity = polarity;
+ if (info && info->ioapic_valid) {
+ data->trigger = info->ioapic_trigger;
+ data->polarity = info->ioapic_polarity;
+ } else if (acpi_get_override_irq(gsi, &data->trigger,
+ &data->polarity) < 0) {
+ /* PCI interrupts are always active low level triggered. */
+ data->trigger = IOAPIC_LEVEL;
+ data->polarity = IOAPIC_POL_LOW;
+ }
}
-int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
- irq_hw_number_t hwirq)
+static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data,
+ struct IO_APIC_route_entry *entry)
{
- int ioapic = (int)(long)domain->host_data;
- struct mp_pin_info *info = mp_pin_info(ioapic, hwirq);
- struct io_apic_irq_attr attr;
+ memset(entry, 0, sizeof(*entry));
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->dest = cfg->dest_apicid;
+ entry->vector = cfg->vector;
+ entry->trigger = data->trigger;
+ entry->polarity = data->polarity;
+ /*
+ * Mask level triggered irqs. Edge triggered irqs are masked
+ * by the irq core code in case they fire.
+ */
+ if (data->trigger == IOAPIC_LEVEL)
+ entry->mask = IOAPIC_MASKED;
+ else
+ entry->mask = IOAPIC_UNMASKED;
+}
- /* Get default attribute if not set by caller yet */
- if (!info->set) {
- u32 gsi = mp_pin_to_gsi(ioapic, hwirq);
+int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ int ret, ioapic, pin;
+ struct irq_cfg *cfg;
+ struct irq_data *irq_data;
+ struct mp_chip_data *data;
+ struct irq_alloc_info *info = arg;
- if (acpi_get_override_irq(gsi, &info->trigger,
- &info->polarity) < 0) {
- /*
- * PCI interrupts are always polarity one level
- * triggered.
- */
- info->trigger = 1;
- info->polarity = 1;
- }
- info->node = NUMA_NO_NODE;
+ if (!info || nr_irqs > 1)
+ return -EINVAL;
+ irq_data = irq_domain_get_irq_data(domain, virq);
+ if (!irq_data)
+ return -EINVAL;
- /*
- * setup_IO_APIC_irqs() programs all legacy IRQs with default
- * trigger and polarity attributes. Don't set the flag for that
- * case so the first legacy IRQ user could reprogram the pin
- * with real trigger and polarity attributes.
- */
- if (virq >= nr_legacy_irqs() || info->count)
- info->set = 1;
- }
- set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger,
- info->polarity);
+ ioapic = mp_irqdomain_ioapic_idx(domain);
+ pin = info->ioapic_pin;
+ if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0)
+ return -EEXIST;
- return io_apic_setup_irq_pin(virq, info->node, &attr);
-}
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
-void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq)
-{
- struct irq_data *data = irq_get_irq_data(virq);
- struct irq_cfg *cfg = irq_cfg(virq);
- int ioapic = (int)(long)domain->host_data;
- int pin = (int)data->hwirq;
+ info->ioapic_entry = &data->entry;
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+ if (ret < 0) {
+ kfree(data);
+ return ret;
+ }
+
+ INIT_LIST_HEAD(&data->irq_2_pin);
+ irq_data->hwirq = info->ioapic_pin;
+ irq_data->chip = (domain->parent == x86_vector_domain) ?
+ &ioapic_chip : &ioapic_ir_chip;
+ irq_data->chip_data = data;
+ mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info);
+
+ cfg = irqd_cfg(irq_data);
+ add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin);
+ if (info->ioapic_entry)
+ mp_setup_entry(cfg, data, info->ioapic_entry);
+ mp_register_handler(virq, data->trigger);
+ if (virq < nr_legacy_irqs())
+ legacy_pic->mask(virq);
+
+ apic_printk(APIC_VERBOSE, KERN_DEBUG
+ "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n",
+ ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector,
+ virq, data->trigger, data->polarity, cfg->dest_apicid);
- ioapic_mask_entry(ioapic, pin);
- __remove_pin_from_irq(cfg, ioapic, pin);
- WARN_ON(!list_empty(&cfg->irq_2_pin));
- arch_teardown_hwirq(virq);
+ return 0;
}
-int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
+void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
{
- int ret = 0;
- int ioapic, pin;
- struct mp_pin_info *info;
+ struct irq_data *irq_data;
+ struct mp_chip_data *data;
- ioapic = mp_find_ioapic(gsi);
- if (ioapic < 0)
- return -ENODEV;
-
- pin = mp_find_ioapic_pin(ioapic, gsi);
- info = mp_pin_info(ioapic, pin);
- trigger = trigger ? 1 : 0;
- polarity = polarity ? 1 : 0;
-
- mutex_lock(&ioapic_mutex);
- if (!info->set) {
- info->trigger = trigger;
- info->polarity = polarity;
- info->node = node;
- info->set = 1;
- } else if (info->trigger != trigger || info->polarity != polarity) {
- ret = -EBUSY;
+ BUG_ON(nr_irqs != 1);
+ irq_data = irq_domain_get_irq_data(domain, virq);
+ if (irq_data && irq_data->chip_data) {
+ data = irq_data->chip_data;
+ __remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain),
+ (int)irq_data->hwirq);
+ WARN_ON(!list_empty(&data->irq_2_pin));
+ kfree(irq_data->chip_data);
}
- mutex_unlock(&ioapic_mutex);
-
- return ret;
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
}
-/* Enable IOAPIC early just for system timer */
-void __init pre_init_apic_IRQ0(void)
+void mp_irqdomain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
- struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
+ unsigned long flags;
+ struct irq_pin_list *entry;
+ struct mp_chip_data *data = irq_data->chip_data;
- printk(KERN_INFO "Early APIC setup for system timer0\n");
-#ifndef CONFIG_SMP
- physid_set_mask_of_physid(boot_cpu_physical_apicid,
- &phys_cpu_present_map);
-#endif
- setup_local_APIC();
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ for_each_irq_pin(entry, data->irq_2_pin)
+ __ioapic_write_entry(entry->apic, entry->pin, data->entry);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+}
- io_apic_setup_irq_pin(0, 0, &attr);
- irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
- "edge");
+void mp_irqdomain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ /* It won't be called for IRQ with multiple IOAPIC pins associated */
+ ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain),
+ (int)irq_data->hwirq);
+}
+
+int mp_irqdomain_ioapic_idx(struct irq_domain *domain)
+{
+ return (int)(long)domain->host_data;
}
+
+const struct irq_domain_ops mp_ioapic_irqdomain_ops = {
+ .alloc = mp_irqdomain_alloc,
+ .free = mp_irqdomain_free,
+ .activate = mp_irqdomain_activate,
+ .deactivate = mp_irqdomain_deactivate,
+};
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Convert to hierarchical irqdomain
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
#include <linux/dmar.h>
#include <linux/hpet.h>
#include <linux/msi.h>
+#include <asm/irqdomain.h>
#include <asm/msidef.h>
#include <asm/hpet.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/irq_remapping.h>
-void native_compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
+static struct irq_domain *msi_default_domain;
+
+static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
{
- struct irq_cfg *cfg = irq_cfg(irq);
+ struct irq_cfg *cfg = irqd_cfg(data);
msg->address_hi = MSI_ADDR_BASE_HI;
if (x2apic_enabled())
- msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
+ msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid);
msg->address_lo =
MSI_ADDR_BASE_LO |
((apic->irq_delivery_mode != dest_LowestPrio) ?
MSI_ADDR_REDIRECTION_CPU :
MSI_ADDR_REDIRECTION_LOWPRI) |
- MSI_ADDR_DEST_ID(dest);
+ MSI_ADDR_DEST_ID(cfg->dest_apicid);
msg->data =
MSI_DATA_TRIGGER_EDGE |
MSI_DATA_VECTOR(cfg->vector);
}
-static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
- struct msi_msg *msg, u8 hpet_id)
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip pci_msi_controller = {
+ .name = "PCI-MSI",
+ .irq_unmask = pci_msi_unmask_irq,
+ .irq_mask = pci_msi_mask_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
- struct irq_cfg *cfg;
- int err;
- unsigned dest;
+ struct irq_domain *domain;
+ struct irq_alloc_info info;
- if (disable_apic)
- return -ENXIO;
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_MSI;
+ info.msi_dev = dev;
- cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, apic->target_cpus());
- if (err)
- return err;
+ domain = irq_remapping_get_irq_domain(&info);
+ if (domain == NULL)
+ domain = msi_default_domain;
+ if (domain == NULL)
+ return -ENOSYS;
- err = apic->cpu_mask_to_apicid_and(cfg->domain,
- apic->target_cpus(), &dest);
- if (err)
- return err;
+ return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
+}
- x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
+void native_teardown_msi_irq(unsigned int irq)
+{
+ irq_domain_free_irqs(irq, 1);
+}
- return 0;
+static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
+{
+ return arg->msi_hwirq;
}
-static int
-msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
+static int pci_msi_prepare(struct irq_domain *domain, struct device *dev,
+ int nvec, msi_alloc_info_t *arg)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- struct msi_msg msg;
- unsigned int dest;
- int ret;
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct msi_desc *desc = first_pci_msi_entry(pdev);
+
+ init_irq_alloc_info(arg, NULL);
+ arg->msi_dev = pdev;
+ if (desc->msi_attrib.is_msix) {
+ arg->type = X86_IRQ_ALLOC_TYPE_MSIX;
+ } else {
+ arg->type = X86_IRQ_ALLOC_TYPE_MSI;
+ arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+ }
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
+ return 0;
+}
- __get_cached_msi_msg(data->msi_desc, &msg);
+static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+ arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
+}
+
+static struct msi_domain_ops pci_msi_domain_ops = {
+ .get_hwirq = pci_msi_get_hwirq,
+ .msi_prepare = pci_msi_prepare,
+ .set_desc = pci_msi_set_desc,
+};
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+static struct msi_domain_info pci_msi_domain_info = {
+ .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_PCI_MSIX,
+ .ops = &pci_msi_domain_ops,
+ .chip = &pci_msi_controller,
+ .handler = handle_edge_irq,
+ .handler_name = "edge",
+};
- __pci_write_msi_msg(data->msi_desc, &msg);
+void arch_init_msi_domain(struct irq_domain *parent)
+{
+ if (disable_apic)
+ return;
- return IRQ_SET_MASK_OK_NOCOPY;
+ msi_default_domain = pci_msi_create_irq_domain(NULL,
+ &pci_msi_domain_info, parent);
+ if (!msi_default_domain)
+ pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
}
-/*
- * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI or MSI-X Capability Structure.
- */
-static struct irq_chip msi_chip = {
- .name = "PCI-MSI",
+#ifdef CONFIG_IRQ_REMAP
+static struct irq_chip pci_msi_ir_controller = {
+ .name = "IR-PCI-MSI",
.irq_unmask = pci_msi_unmask_irq,
.irq_mask = pci_msi_mask_irq,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- unsigned int irq_base, unsigned int irq_offset)
-{
- struct irq_chip *chip = &msi_chip;
- struct msi_msg msg;
- unsigned int irq = irq_base + irq_offset;
- int ret;
-
- ret = msi_compose_msg(dev, irq, &msg, -1);
- if (ret < 0)
- return ret;
-
- irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
-
- /*
- * MSI-X message is written per-IRQ, the offset is always 0.
- * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
- */
- if (!irq_offset)
- pci_write_msi_msg(irq, &msg);
+static struct msi_domain_info pci_msi_ir_domain_info = {
+ .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+ .ops = &pci_msi_domain_ops,
+ .chip = &pci_msi_ir_controller,
+ .handler = handle_edge_irq,
+ .handler_name = "edge",
+};
- setup_remapped_irq(irq, irq_cfg(irq), chip);
+struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent)
+{
+ return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent);
+}
+#endif
- irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
+#ifdef CONFIG_DMAR_TABLE
+static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
+{
+ dmar_msi_write(data->irq, msg);
+}
- dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq);
+static struct irq_chip dmar_msi_controller = {
+ .name = "DMAR-MSI",
+ .irq_unmask = dmar_msi_unmask,
+ .irq_mask = dmar_msi_mask,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_set_affinity = msi_domain_set_affinity,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
+ .irq_write_msi_msg = dmar_msi_write_msg,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
- return 0;
+static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
+{
+ return arg->dmar_id;
}
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+static int dmar_msi_init(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq,
+ irq_hw_number_t hwirq, msi_alloc_info_t *arg)
{
- struct msi_desc *msidesc;
- unsigned int irq;
- int node, ret;
+ irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL,
+ handle_edge_irq, arg->dmar_data, "edge");
- /* Multiple MSI vectors only supported with interrupt remapping */
- if (type == PCI_CAP_ID_MSI && nvec > 1)
- return 1;
+ return 0;
+}
- node = dev_to_node(&dev->dev);
+static struct msi_domain_ops dmar_msi_domain_ops = {
+ .get_hwirq = dmar_msi_get_hwirq,
+ .msi_init = dmar_msi_init,
+};
- list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = irq_alloc_hwirq(node);
- if (!irq)
- return -ENOSPC;
+static struct msi_domain_info dmar_msi_domain_info = {
+ .ops = &dmar_msi_domain_ops,
+ .chip = &dmar_msi_controller,
+};
- ret = setup_msi_irq(dev, msidesc, irq, 0);
- if (ret < 0) {
- irq_free_hwirq(irq);
- return ret;
- }
+static struct irq_domain *dmar_get_irq_domain(void)
+{
+ static struct irq_domain *dmar_domain;
+ static DEFINE_MUTEX(dmar_lock);
- }
- return 0;
-}
+ mutex_lock(&dmar_lock);
+ if (dmar_domain == NULL)
+ dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info,
+ x86_vector_domain);
+ mutex_unlock(&dmar_lock);
-void native_teardown_msi_irq(unsigned int irq)
-{
- irq_free_hwirq(irq);
+ return dmar_domain;
}
-#ifdef CONFIG_DMAR_TABLE
-static int
-dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
+int dmar_alloc_hwirq(int id, int node, void *arg)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest, irq = data->irq;
- struct msi_msg msg;
- int ret;
-
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
+ struct irq_domain *domain = dmar_get_irq_domain();
+ struct irq_alloc_info info;
- dmar_msi_read(irq, &msg);
+ if (!domain)
+ return -1;
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
- msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_DMAR;
+ info.dmar_id = id;
+ info.dmar_data = arg;
- dmar_msi_write(irq, &msg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
+ return irq_domain_alloc_irqs(domain, 1, node, &info);
}
-static struct irq_chip dmar_msi_type = {
- .name = "DMAR_MSI",
- .irq_unmask = dmar_msi_unmask,
- .irq_mask = dmar_msi_mask,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = dmar_msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
- .flags = IRQCHIP_SKIP_SET_WAKE,
-};
-
-int arch_setup_dmar_msi(unsigned int irq)
+void dmar_free_hwirq(int irq)
{
- int ret;
- struct msi_msg msg;
-
- ret = msi_compose_msg(NULL, irq, &msg, -1);
- if (ret < 0)
- return ret;
- dmar_msi_write(irq, &msg);
- irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
- return 0;
+ irq_domain_free_irqs(irq, 1);
}
#endif
* MSI message composition
*/
#ifdef CONFIG_HPET_TIMER
+static inline int hpet_dev_id(struct irq_domain *domain)
+{
+ struct msi_domain_info *info = msi_get_domain_info(domain);
+
+ return (int)(long)info->data;
+}
-static int hpet_msi_set_affinity(struct irq_data *data,
- const struct cpumask *mask, bool force)
+static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- struct msi_msg msg;
- unsigned int dest;
- int ret;
+ hpet_msi_write(data->handler_data, msg);
+}
- ret = apic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
+static struct irq_chip hpet_msi_controller = {
+ .name = "HPET-MSI",
+ .irq_unmask = hpet_msi_unmask,
+ .irq_mask = hpet_msi_mask,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_set_affinity = msi_domain_set_affinity,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_compose_msi_msg = irq_msi_compose_msg,
+ .irq_write_msi_msg = hpet_msi_write_msg,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
- hpet_msi_read(data->handler_data, &msg);
+static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
+ msi_alloc_info_t *arg)
+{
+ return arg->hpet_index;
+}
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+static int hpet_msi_init(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq,
+ irq_hw_number_t hwirq, msi_alloc_info_t *arg)
+{
+ irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+ irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL,
+ handle_edge_irq, arg->hpet_data, "edge");
- hpet_msi_write(data->handler_data, &msg);
+ return 0;
+}
- return IRQ_SET_MASK_OK_NOCOPY;
+static void hpet_msi_free(struct irq_domain *domain,
+ struct msi_domain_info *info, unsigned int virq)
+{
+ irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
}
-static struct irq_chip hpet_msi_type = {
- .name = "HPET_MSI",
- .irq_unmask = hpet_msi_unmask,
- .irq_mask = hpet_msi_mask,
- .irq_ack = apic_ack_edge,
- .irq_set_affinity = hpet_msi_set_affinity,
- .irq_retrigger = apic_retrigger_irq,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+static struct msi_domain_ops hpet_msi_domain_ops = {
+ .get_hwirq = hpet_msi_get_hwirq,
+ .msi_init = hpet_msi_init,
+ .msi_free = hpet_msi_free,
+};
+
+static struct msi_domain_info hpet_msi_domain_info = {
+ .ops = &hpet_msi_domain_ops,
+ .chip = &hpet_msi_controller,
};
-int default_setup_hpet_msi(unsigned int irq, unsigned int id)
+struct irq_domain *hpet_create_irq_domain(int hpet_id)
{
- struct irq_chip *chip = &hpet_msi_type;
- struct msi_msg msg;
- int ret;
+ struct irq_domain *parent;
+ struct irq_alloc_info info;
+ struct msi_domain_info *domain_info;
+
+ if (x86_vector_domain == NULL)
+ return NULL;
+
+ domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL);
+ if (!domain_info)
+ return NULL;
+
+ *domain_info = hpet_msi_domain_info;
+ domain_info->data = (void *)(long)hpet_id;
+
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_HPET;
+ info.hpet_id = hpet_id;
+ parent = irq_remapping_get_ir_irq_domain(&info);
+ if (parent == NULL)
+ parent = x86_vector_domain;
+ else
+ hpet_msi_controller.name = "IR-HPET-MSI";
+
+ return msi_create_irq_domain(NULL, domain_info, parent);
+}
- ret = msi_compose_msg(NULL, irq, &msg, id);
- if (ret < 0)
- return ret;
+int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev,
+ int dev_num)
+{
+ struct irq_alloc_info info;
- hpet_msi_write(irq_get_handler_data(irq), &msg);
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- setup_remapped_irq(irq, irq_cfg(irq), chip);
+ init_irq_alloc_info(&info, NULL);
+ info.type = X86_IRQ_ALLOC_TYPE_HPET;
+ info.hpet_data = dev;
+ info.hpet_id = hpet_dev_id(domain);
+ info.hpet_index = dev_num;
- irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
- return 0;
+ return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info);
}
#endif
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ * Enable support of hierarchical irqdomains
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compiler.h>
-#include <linux/irqdomain.h>
#include <linux/slab.h>
+#include <asm/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/i8259.h>
#include <asm/desc.h>
#include <asm/irq_remapping.h>
+struct apic_chip_data {
+ struct irq_cfg cfg;
+ cpumask_var_t domain;
+ cpumask_var_t old_domain;
+ u8 move_in_progress : 1;
+};
+
+struct irq_domain *x86_vector_domain;
static DEFINE_RAW_SPINLOCK(vector_lock);
+static cpumask_var_t vector_cpumask;
+static struct irq_chip lapic_controller;
+#ifdef CONFIG_X86_IO_APIC
+static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
+#endif
void lock_vector_lock(void)
{
raw_spin_unlock(&vector_lock);
}
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data)
{
- return irq_get_chip_data(irq);
+ if (!irq_data)
+ return NULL;
+
+ while (irq_data->parent_data)
+ irq_data = irq_data->parent_data;
+
+ return irq_data->chip_data;
}
struct irq_cfg *irqd_cfg(struct irq_data *irq_data)
{
- return irq_data->chip_data;
+ struct apic_chip_data *data = apic_chip_data(irq_data);
+
+ return data ? &data->cfg : NULL;
}
-static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+struct irq_cfg *irq_cfg(unsigned int irq)
{
- struct irq_cfg *cfg;
+ return irqd_cfg(irq_get_irq_data(irq));
+}
- cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
- if (!cfg)
+static struct apic_chip_data *alloc_apic_chip_data(int node)
+{
+ struct apic_chip_data *data;
+
+ data = kzalloc_node(sizeof(*data), GFP_KERNEL, node);
+ if (!data)
return NULL;
- if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
- goto out_cfg;
- if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+ if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node))
+ goto out_data;
+ if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node))
goto out_domain;
-#ifdef CONFIG_X86_IO_APIC
- INIT_LIST_HEAD(&cfg->irq_2_pin);
-#endif
- return cfg;
+ return data;
out_domain:
- free_cpumask_var(cfg->domain);
-out_cfg:
- kfree(cfg);
+ free_cpumask_var(data->domain);
+out_data:
+ kfree(data);
return NULL;
}
-struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
+static void free_apic_chip_data(struct apic_chip_data *data)
{
- int res = irq_alloc_desc_at(at, node);
- struct irq_cfg *cfg;
-
- if (res < 0) {
- if (res != -EEXIST)
- return NULL;
- cfg = irq_cfg(at);
- if (cfg)
- return cfg;
+ if (data) {
+ free_cpumask_var(data->domain);
+ free_cpumask_var(data->old_domain);
+ kfree(data);
}
-
- cfg = alloc_irq_cfg(at, node);
- if (cfg)
- irq_set_chip_data(at, cfg);
- else
- irq_free_desc(at);
- return cfg;
-}
-
-static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
-{
- if (!cfg)
- return;
- irq_set_chip_data(at, NULL);
- free_cpumask_var(cfg->domain);
- free_cpumask_var(cfg->old_domain);
- kfree(cfg);
}
-static int
-__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int __assign_irq_vector(int irq, struct apic_chip_data *d,
+ const struct cpumask *mask)
{
/*
* NOTE! The local APIC isn't very good at handling
static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
static int current_offset = VECTOR_OFFSET_START % 16;
int cpu, err;
- cpumask_var_t tmp_mask;
- if (cfg->move_in_progress)
+ if (d->move_in_progress)
return -EBUSY;
- if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
- return -ENOMEM;
-
/* Only try and allocate irqs on cpus that are present */
err = -ENOSPC;
- cpumask_clear(cfg->old_domain);
+ cpumask_clear(d->old_domain);
cpu = cpumask_first_and(mask, cpu_online_mask);
while (cpu < nr_cpu_ids) {
int new_cpu, vector, offset;
- apic->vector_allocation_domain(cpu, tmp_mask, mask);
+ apic->vector_allocation_domain(cpu, vector_cpumask, mask);
- if (cpumask_subset(tmp_mask, cfg->domain)) {
+ if (cpumask_subset(vector_cpumask, d->domain)) {
err = 0;
- if (cpumask_equal(tmp_mask, cfg->domain))
+ if (cpumask_equal(vector_cpumask, d->domain))
break;
/*
* New cpumask using the vector is a proper subset of
* the current in use mask. So cleanup the vector
* allocation for the members that are not used anymore.
*/
- cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
- cfg->move_in_progress =
- cpumask_intersects(cfg->old_domain, cpu_online_mask);
- cpumask_and(cfg->domain, cfg->domain, tmp_mask);
+ cpumask_andnot(d->old_domain, d->domain,
+ vector_cpumask);
+ d->move_in_progress =
+ cpumask_intersects(d->old_domain, cpu_online_mask);
+ cpumask_and(d->domain, d->domain, vector_cpumask);
break;
}
}
if (unlikely(current_vector == vector)) {
- cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
- cpumask_andnot(tmp_mask, mask, cfg->old_domain);
- cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
+ cpumask_or(d->old_domain, d->old_domain,
+ vector_cpumask);
+ cpumask_andnot(vector_cpumask, mask, d->old_domain);
+ cpu = cpumask_first_and(vector_cpumask,
+ cpu_online_mask);
continue;
}
if (test_bit(vector, used_vectors))
goto next;
- for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
+ for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
if (per_cpu(vector_irq, new_cpu)[vector] >
VECTOR_UNDEFINED)
goto next;
/* Found one! */
current_vector = vector;
current_offset = offset;
- if (cfg->vector) {
- cpumask_copy(cfg->old_domain, cfg->domain);
- cfg->move_in_progress =
- cpumask_intersects(cfg->old_domain, cpu_online_mask);
+ if (d->cfg.vector) {
+ cpumask_copy(d->old_domain, d->domain);
+ d->move_in_progress =
+ cpumask_intersects(d->old_domain, cpu_online_mask);
}
- for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+ for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
per_cpu(vector_irq, new_cpu)[vector] = irq;
- cfg->vector = vector;
- cpumask_copy(cfg->domain, tmp_mask);
+ d->cfg.vector = vector;
+ cpumask_copy(d->domain, vector_cpumask);
err = 0;
break;
}
- free_cpumask_var(tmp_mask);
+
+ if (!err) {
+ /* cache destination APIC IDs into cfg->dest_apicid */
+ err = apic->cpu_mask_to_apicid_and(mask, d->domain,
+ &d->cfg.dest_apicid);
+ }
return err;
}
-int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int assign_irq_vector(int irq, struct apic_chip_data *data,
+ const struct cpumask *mask)
{
int err;
unsigned long flags;
raw_spin_lock_irqsave(&vector_lock, flags);
- err = __assign_irq_vector(irq, cfg, mask);
+ err = __assign_irq_vector(irq, data, mask);
raw_spin_unlock_irqrestore(&vector_lock, flags);
return err;
}
-void clear_irq_vector(int irq, struct irq_cfg *cfg)
+static int assign_irq_vector_policy(int irq, int node,
+ struct apic_chip_data *data,
+ struct irq_alloc_info *info)
+{
+ if (info && info->mask)
+ return assign_irq_vector(irq, data, info->mask);
+ if (node != NUMA_NO_NODE &&
+ assign_irq_vector(irq, data, cpumask_of_node(node)) == 0)
+ return 0;
+ return assign_irq_vector(irq, data, apic->target_cpus());
+}
+
+static void clear_irq_vector(int irq, struct apic_chip_data *data)
{
int cpu, vector;
unsigned long flags;
raw_spin_lock_irqsave(&vector_lock, flags);
- BUG_ON(!cfg->vector);
+ BUG_ON(!data->cfg.vector);
- vector = cfg->vector;
- for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ vector = data->cfg.vector;
+ for_each_cpu_and(cpu, data->domain, cpu_online_mask)
per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
- cfg->vector = 0;
- cpumask_clear(cfg->domain);
+ data->cfg.vector = 0;
+ cpumask_clear(data->domain);
- if (likely(!cfg->move_in_progress)) {
+ if (likely(!data->move_in_progress)) {
raw_spin_unlock_irqrestore(&vector_lock, flags);
return;
}
- for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
if (per_cpu(vector_irq, cpu)[vector] != irq)
break;
}
}
- cfg->move_in_progress = 0;
+ data->move_in_progress = 0;
raw_spin_unlock_irqrestore(&vector_lock, flags);
}
+void init_irq_alloc_info(struct irq_alloc_info *info,
+ const struct cpumask *mask)
+{
+ memset(info, 0, sizeof(*info));
+ info->mask = mask;
+}
+
+void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
+{
+ if (src)
+ *dst = *src;
+ else
+ memset(dst, 0, sizeof(*dst));
+}
+
+static void x86_vector_free_irqs(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs)
+{
+ struct irq_data *irq_data;
+ int i;
+
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
+ if (irq_data && irq_data->chip_data) {
+ clear_irq_vector(virq + i, irq_data->chip_data);
+ free_apic_chip_data(irq_data->chip_data);
+#ifdef CONFIG_X86_IO_APIC
+ if (virq + i < nr_legacy_irqs())
+ legacy_irq_data[virq + i] = NULL;
+#endif
+ irq_domain_reset_irq_data(irq_data);
+ }
+ }
+}
+
+static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ struct irq_alloc_info *info = arg;
+ struct apic_chip_data *data;
+ struct irq_data *irq_data;
+ int i, err;
+
+ if (disable_apic)
+ return -ENXIO;
+
+ /* Currently vector allocator can't guarantee contiguous allocations */
+ if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1)
+ return -ENOSYS;
+
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ BUG_ON(!irq_data);
+#ifdef CONFIG_X86_IO_APIC
+ if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i])
+ data = legacy_irq_data[virq + i];
+ else
+#endif
+ data = alloc_apic_chip_data(irq_data->node);
+ if (!data) {
+ err = -ENOMEM;
+ goto error;
+ }
+
+ irq_data->chip = &lapic_controller;
+ irq_data->chip_data = data;
+ irq_data->hwirq = virq + i;
+ err = assign_irq_vector_policy(virq, irq_data->node, data,
+ info);
+ if (err)
+ goto error;
+ }
+
+ return 0;
+
+error:
+ x86_vector_free_irqs(domain, virq, i + 1);
+ return err;
+}
+
+static const struct irq_domain_ops x86_vector_domain_ops = {
+ .alloc = x86_vector_alloc_irqs,
+ .free = x86_vector_free_irqs,
+};
+
int __init arch_probe_nr_irqs(void)
{
int nr;
return nr_legacy_irqs();
}
+#ifdef CONFIG_X86_IO_APIC
+static void init_legacy_irqs(void)
+{
+ int i, node = cpu_to_node(0);
+ struct apic_chip_data *data;
+
+ /*
+ * For legacy IRQ's, start with assigning irq0 to irq15 to
+ * ISA_IRQ_VECTOR(i) for all cpu's.
+ */
+ for (i = 0; i < nr_legacy_irqs(); i++) {
+ data = legacy_irq_data[i] = alloc_apic_chip_data(node);
+ BUG_ON(!data);
+
+ data->cfg.vector = ISA_IRQ_VECTOR(i);
+ cpumask_setall(data->domain);
+ irq_set_chip_data(i, data);
+ }
+}
+#else
+static void init_legacy_irqs(void) { }
+#endif
+
int __init arch_early_irq_init(void)
{
+ init_legacy_irqs();
+
+ x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops,
+ NULL);
+ BUG_ON(x86_vector_domain == NULL);
+ irq_set_default_host(x86_vector_domain);
+
+ arch_init_msi_domain(x86_vector_domain);
+ arch_init_htirq_domain(x86_vector_domain);
+
+ BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+
return arch_early_ioapic_init();
}
{
/* Initialize vector_irq on a new cpu */
int irq, vector;
- struct irq_cfg *cfg;
+ struct apic_chip_data *data;
/*
* vector_lock will make sure that we don't run into irq vector
raw_spin_lock(&vector_lock);
/* Mark the inuse vectors */
for_each_active_irq(irq) {
- cfg = irq_cfg(irq);
- if (!cfg)
+ data = apic_chip_data(irq_get_irq_data(irq));
+ if (!data)
continue;
- if (!cpumask_test_cpu(cpu, cfg->domain))
+ if (!cpumask_test_cpu(cpu, data->domain))
continue;
- vector = cfg->vector;
+ vector = data->cfg.vector;
per_cpu(vector_irq, cpu)[vector] = irq;
}
/* Mark the free vectors */
if (irq <= VECTOR_UNDEFINED)
continue;
- cfg = irq_cfg(irq);
- if (!cpumask_test_cpu(cpu, cfg->domain))
+ data = apic_chip_data(irq_get_irq_data(irq));
+ if (!cpumask_test_cpu(cpu, data->domain))
per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
}
raw_spin_unlock(&vector_lock);
* legacy vector to irq mapping:
*/
for (irq = 0; irq < nr_legacy_irqs(); irq++)
- per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+ per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq;
__setup_vector_irq(cpu);
}
-int apic_retrigger_irq(struct irq_data *data)
+static int apic_retrigger_irq(struct irq_data *irq_data)
{
- struct irq_cfg *cfg = irqd_cfg(data);
+ struct apic_chip_data *data = apic_chip_data(irq_data);
unsigned long flags;
int cpu;
raw_spin_lock_irqsave(&vector_lock, flags);
- cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
- apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
+ cpu = cpumask_first_and(data->domain, cpu_online_mask);
+ apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector);
raw_spin_unlock_irqrestore(&vector_lock, flags);
return 1;
ack_APIC_irq();
}
-/*
- * Either sets data->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves data->affinity untouched.
- */
-int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- unsigned int *dest_id)
+static int apic_set_affinity(struct irq_data *irq_data,
+ const struct cpumask *dest, bool force)
{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int irq = data->irq;
- int err;
+ struct apic_chip_data *data = irq_data->chip_data;
+ int err, irq = irq_data->irq;
if (!config_enabled(CONFIG_SMP))
return -EPERM;
- if (!cpumask_intersects(mask, cpu_online_mask))
+ if (!cpumask_intersects(dest, cpu_online_mask))
return -EINVAL;
- err = assign_irq_vector(irq, cfg, mask);
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
+ err = assign_irq_vector(irq, data, dest);
if (err) {
- if (assign_irq_vector(irq, cfg, data->affinity))
+ struct irq_data *top = irq_get_irq_data(irq);
+
+ if (assign_irq_vector(irq, data, top->affinity))
pr_err("Failed to recover vector for irq %d\n", irq);
return err;
}
- cpumask_copy(data->affinity, mask);
-
- return 0;
+ return IRQ_SET_MASK_OK;
}
+static struct irq_chip lapic_controller = {
+ .irq_ack = apic_ack_edge,
+ .irq_set_affinity = apic_set_affinity,
+ .irq_retrigger = apic_retrigger_irq,
+};
+
#ifdef CONFIG_SMP
-void send_cleanup_vector(struct irq_cfg *cfg)
+static void __send_cleanup_vector(struct apic_chip_data *data)
{
cpumask_var_t cleanup_mask;
if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
unsigned int i;
- for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ for_each_cpu_and(i, data->old_domain, cpu_online_mask)
apic->send_IPI_mask(cpumask_of(i),
IRQ_MOVE_CLEANUP_VECTOR);
} else {
- cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+ cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
free_cpumask_var(cleanup_mask);
}
- cfg->move_in_progress = 0;
+ data->move_in_progress = 0;
+}
+
+void send_cleanup_vector(struct irq_cfg *cfg)
+{
+ struct apic_chip_data *data;
+
+ data = container_of(cfg, struct apic_chip_data, cfg);
+ if (data->move_in_progress)
+ __send_cleanup_vector(data);
}
asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
{
unsigned vector, me;
- ack_APIC_irq();
- irq_enter();
- exit_idle();
+ entering_ack_irq();
me = smp_processor_id();
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
int irq;
unsigned int irr;
struct irq_desc *desc;
- struct irq_cfg *cfg;
+ struct apic_chip_data *data;
irq = __this_cpu_read(vector_irq[vector]);
if (!desc)
continue;
- cfg = irq_cfg(irq);
- if (!cfg)
+ data = apic_chip_data(&desc->irq_data);
+ if (!data)
continue;
raw_spin_lock(&desc->lock);
* Check if the irq migration is in progress. If so, we
* haven't received the cleanup request yet for this irq.
*/
- if (cfg->move_in_progress)
+ if (data->move_in_progress)
goto unlock;
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+ if (vector == data->cfg.vector &&
+ cpumask_test_cpu(me, data->domain))
goto unlock;
irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
raw_spin_unlock(&desc->lock);
}
- irq_exit();
+ exiting_irq();
}
static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
{
unsigned me;
+ struct apic_chip_data *data;
- if (likely(!cfg->move_in_progress))
+ data = container_of(cfg, struct apic_chip_data, cfg);
+ if (likely(!data->move_in_progress))
return;
me = smp_processor_id();
-
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
- send_cleanup_vector(cfg);
+ if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain))
+ __send_cleanup_vector(data);
}
void irq_complete_move(struct irq_cfg *cfg)
{
struct irq_cfg *cfg = irq_cfg(irq);
- if (!cfg)
- return;
-
- __irq_complete_move(cfg, cfg->vector);
+ if (cfg)
+ __irq_complete_move(cfg, cfg->vector);
}
#endif
-/*
- * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
- */
-int arch_setup_hwirq(unsigned int irq, int node)
-{
- struct irq_cfg *cfg;
- unsigned long flags;
- int ret;
-
- cfg = alloc_irq_cfg(irq, node);
- if (!cfg)
- return -ENOMEM;
-
- raw_spin_lock_irqsave(&vector_lock, flags);
- ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
- raw_spin_unlock_irqrestore(&vector_lock, flags);
-
- if (!ret)
- irq_set_chip_data(irq, cfg);
- else
- free_irq_cfg(irq, cfg);
- return ret;
-}
-
-void arch_teardown_hwirq(unsigned int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- free_remapped_irq(irq);
- clear_irq_vector(irq, cfg);
- free_irq_cfg(irq, cfg);
-}
-
static void __init print_APIC_field(int base)
{
int i;
static bool x2apic_fadt_phys(void)
{
+#ifdef CONFIG_ACPI
if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
printk(KERN_DEBUG "System requires x2apic physical mode\n");
return true;
}
+#endif
return false;
}
OFFSET(pbe_orig_address, pbe, orig_address);
OFFSET(pbe_next, pbe, next);
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+ BLANK();
+ OFFSET(IA32_SIGCONTEXT_ax, sigcontext_ia32, ax);
+ OFFSET(IA32_SIGCONTEXT_bx, sigcontext_ia32, bx);
+ OFFSET(IA32_SIGCONTEXT_cx, sigcontext_ia32, cx);
+ OFFSET(IA32_SIGCONTEXT_dx, sigcontext_ia32, dx);
+ OFFSET(IA32_SIGCONTEXT_si, sigcontext_ia32, si);
+ OFFSET(IA32_SIGCONTEXT_di, sigcontext_ia32, di);
+ OFFSET(IA32_SIGCONTEXT_bp, sigcontext_ia32, bp);
+ OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp);
+ OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip);
+
+ BLANK();
+ OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+
+ BLANK();
+ OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
+#endif
+
#ifdef CONFIG_PARAVIRT
BLANK();
OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+#ifdef CONFIG_X86_32
OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+#endif
OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
#endif
void foo(void)
{
- OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax);
- OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx);
- OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx);
- OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx);
- OFFSET(IA32_SIGCONTEXT_si, sigcontext, si);
- OFFSET(IA32_SIGCONTEXT_di, sigcontext, di);
- OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp);
- OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp);
- OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip);
- BLANK();
-
OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
BLANK();
- OFFSET(TI_sysenter_return, thread_info, sysenter_return);
- OFFSET(TI_cpu, thread_info, cpu);
- BLANK();
-
OFFSET(PT_EBX, pt_regs, bx);
OFFSET(PT_ECX, pt_regs, cx);
OFFSET(PT_EDX, pt_regs, dx);
OFFSET(PT_OLDSS, pt_regs, ss);
BLANK();
- OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
- BLANK();
-
OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
BLANK();
BLANK();
#endif
-#ifdef CONFIG_IA32_EMULATION
- OFFSET(TI_sysenter_return, thread_info, sysenter_return);
- BLANK();
-
-#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry)
- ENTRY(ax);
- ENTRY(bx);
- ENTRY(cx);
- ENTRY(dx);
- ENTRY(si);
- ENTRY(di);
- ENTRY(bp);
- ENTRY(sp);
- ENTRY(ip);
- BLANK();
-#undef ENTRY
-
- OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
- BLANK();
-#endif
-
#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
ENTRY(bx);
ENTRY(cx);
DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
DEFINE(NR_syscalls, sizeof(syscalls_64));
- DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1);
+ DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1);
DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
return 0;
#include "cpu.h"
+/*
+ * nodes_per_socket: Stores the number of nodes per socket.
+ * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
+ * Node Identifiers[10:8]
+ */
+static u32 nodes_per_socket = 1;
+
static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
{
u32 gprs[8] = { 0 };
* Assumption: Number of cores in each internal node is the same.
* (2) AMD processors supporting compute units
*/
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
static void amd_get_topology(struct cpuinfo_x86 *c)
{
- u32 nodes, cores_per_cu = 1;
+ u32 cores_per_cu = 1;
u8 node_id;
int cpu = smp_processor_id();
u32 eax, ebx, ecx, edx;
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- nodes = ((ecx >> 8) & 7) + 1;
+ nodes_per_socket = ((ecx >> 8) & 7) + 1;
node_id = ecx & 7;
/* get compute unit information */
u64 value;
rdmsrl(MSR_FAM10H_NODE_ID, value);
- nodes = ((value >> 3) & 7) + 1;
+ nodes_per_socket = ((value >> 3) & 7) + 1;
node_id = value & 7;
} else
return;
/* fixup multi-node processor information */
- if (nodes > 1) {
+ if (nodes_per_socket > 1) {
u32 cores_per_node;
u32 cus_per_node;
set_cpu_cap(c, X86_FEATURE_AMD_DCM);
- cores_per_node = c->x86_max_cores / nodes;
+ cores_per_node = c->x86_max_cores / nodes_per_socket;
cus_per_node = cores_per_node / cores_per_cu;
/* store NodeID, use llc_shared_map to store sibling info */
*/
static void amd_detect_cmp(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
}
EXPORT_SYMBOL_GPL(amd_get_nb_id);
+u32 amd_get_nodes_per_socket(void)
+{
+ return nodes_per_socket;
+}
+EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket);
+
static void srat_detect_node(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_NUMA
static void early_init_amd_mc(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned bits, ecx;
/* Multi core CPU? */
set_cpu_cap(c, X86_FEATURE_K6_MTRR);
#endif
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
- /* check CPU config space for extended APIC ID */
- if (cpu_has_apic && c->x86 >= 0xf) {
+ /*
+ * ApicID can always be treated as an 8-bit value for AMD APIC versions
+ * >= 0x10, but even old K8s came out of reset with version 0x10. So, we
+ * can safely set X86_FEATURE_EXTD_APICID unconditionally for families
+ * after 16h.
+ */
+ if (cpu_has_apic && c->x86 > 0x16) {
+ set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+ } else if (cpu_has_apic && c->x86 >= 0xf) {
+ /* check CPU config space for extended APIC ID */
unsigned int val;
val = read_pci_config(0, 24, 0, 0x68);
if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
#include <asm/bugs.h>
#include <asm/processor.h>
#include <asm/processor-flags.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
#include <asm/msr.h>
#include <asm/paravirt.h>
#include <asm/alternative.h>
-static double __initdata x = 4195835.0;
-static double __initdata y = 3145727.0;
-
-/*
- * This used to check for exceptions..
- * However, it turns out that to support that,
- * the XMM trap handlers basically had to
- * be buggy. So let's have a correct XMM trap
- * handler, and forget about printing out
- * some status at boot.
- *
- * We should really only care about bugs here
- * anyway. Not features.
- */
-static void __init check_fpu(void)
-{
- s32 fdiv_bug;
-
- kernel_fpu_begin();
-
- /*
- * trap_init() enabled FXSR and company _before_ testing for FP
- * problems here.
- *
- * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
- */
- __asm__("fninit\n\t"
- "fldl %1\n\t"
- "fdivl %2\n\t"
- "fmull %2\n\t"
- "fldl %1\n\t"
- "fsubp %%st,%%st(1)\n\t"
- "fistpl %0\n\t"
- "fwait\n\t"
- "fninit"
- : "=m" (*&fdiv_bug)
- : "m" (*&x), "m" (*&y));
-
- kernel_fpu_end();
-
- if (fdiv_bug) {
- set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
- pr_warn("Hmm, FPU with FDIV bug\n");
- }
-}
-
void __init check_bugs(void)
{
identify_boot_cpu();
'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
alternative_instructions();
- /*
- * kernel_fpu_begin/end() in check_fpu() relies on the patched
- * alternative instructions.
- */
- if (cpu_has_fpu)
- check_fpu();
+ fpu__init_check_bugs();
}
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/string.h>
+#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <asm/setup.h>
#include <asm/apic.h>
#include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/mtrr.h>
#include <linux/numa.h>
#include <asm/asm.h>
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
-static int __init x86_xsave_setup(char *s)
+static int __init x86_mpx_setup(char *s)
{
+ /* require an exact match without trailing characters */
if (strlen(s))
return 0;
- setup_clear_cpu_cap(X86_FEATURE_XSAVE);
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
- setup_clear_cpu_cap(X86_FEATURE_XSAVES);
- setup_clear_cpu_cap(X86_FEATURE_AVX);
- setup_clear_cpu_cap(X86_FEATURE_AVX2);
- return 1;
-}
-__setup("noxsave", x86_xsave_setup);
-static int __init x86_xsaveopt_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
- return 1;
-}
-__setup("noxsaveopt", x86_xsaveopt_setup);
+ /* do not emit a message if the feature is not present */
+ if (!boot_cpu_has(X86_FEATURE_MPX))
+ return 1;
-static int __init x86_xsaves_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+ setup_clear_cpu_cap(X86_FEATURE_MPX);
+ pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
return 1;
}
-__setup("noxsaves", x86_xsaves_setup);
+__setup("nompx", x86_mpx_setup);
#ifdef CONFIG_X86_32
static int cachesize_override = -1;
}
__setup("cachesize=", cachesize_setup);
-static int __init x86_fxsr_setup(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_FXSR);
- setup_clear_cpu_cap(X86_FEATURE_XMM);
- return 1;
-}
-__setup("nofxsr", x86_fxsr_setup);
-
static int __init x86_sep_setup(char *s)
{
setup_clear_cpu_cap(X86_FEATURE_SEP);
static void get_model_name(struct cpuinfo_x86 *c)
{
unsigned int *v;
- char *p, *q;
+ char *p, *q, *s;
if (c->extended_cpuid_level < 0x80000004)
return;
cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
c->x86_model_id[48] = 0;
- /*
- * Intel chips right-justify this string for some dumb reason;
- * undo that brain damage:
- */
- p = q = &c->x86_model_id[0];
+ /* Trim whitespace */
+ p = q = s = &c->x86_model_id[0];
+
while (*p == ' ')
p++;
- if (p != q) {
- while (*p)
- *q++ = *p++;
- while (q <= &c->x86_model_id[48])
- *q++ = '\0'; /* Zero-pad the rest */
+
+ while (*p) {
+ /* Note the last non-whitespace index */
+ if (!isspace(*p))
+ s = q;
+
+ *q++ = *p++;
}
+
+ *(s + 1) = '\0';
}
void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
void detect_ht(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
u32 eax, ebx, ecx, edx;
int index_msb, core_bits;
static bool printed;
cpu_detect(c);
get_cpu_vendor(c);
get_cpu_cap(c);
- fpu_detect(c);
+ fpu__init_system(c);
if (this_cpu->c_early_init)
this_cpu->c_early_init(c);
if (c->cpuid_level >= 0x00000001) {
c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
# else
c->apicid = c->initial_apicid;
(unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
0);
- wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);
+ wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
out:
put_cpu();
printk(KERN_CONT "%s ", vendor);
if (c->x86_model_id[0])
- printk(KERN_CONT "%s", strim(c->x86_model_id));
+ printk(KERN_CONT "%s", c->x86_model_id);
else
printk(KERN_CONT "%d86", c->x86);
}
__setup("clearcpuid=", setup_disablecpuid);
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
- (unsigned long)&init_thread_union + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
#ifdef CONFIG_X86_64
struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
EXPORT_PER_CPU_SYMBOL(__preempt_count);
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
-
/*
* Special IST stacks which the CPU switches to when it calls
* an IST-marked descriptor entry. Up to 7 stacks (hardware
* set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
*/
wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32);
- wrmsrl(MSR_LSTAR, system_call);
+ wrmsrl(MSR_LSTAR, entry_SYSCALL_64);
#ifdef CONFIG_IA32_EMULATION
- wrmsrl(MSR_CSTAR, ia32_cstar_target);
+ wrmsrl(MSR_CSTAR, entry_SYSCALL_compat);
/*
* This only works on Intel CPUs.
* On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
*/
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
#else
wrmsrl(MSR_CSTAR, ignore_sysret);
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
EXPORT_PER_CPU_SYMBOL(current_task);
DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
EXPORT_PER_CPU_SYMBOL(__preempt_count);
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
/*
* On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
clear_all_debug_regs();
dbg_restore_debug_regs();
- fpu_init();
+ fpu__init_cpu();
if (is_uv_system())
uv_cpu_init();
clear_all_debug_regs();
dbg_restore_debug_regs();
- fpu_init();
+ fpu__init_cpu();
}
#endif
unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
unsigned int cpu = c->cpu_index;
#endif
if (new_l2) {
l2 = new_l2;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
per_cpu(cpu_llc_id, cpu) = l2_id;
#endif
}
if (new_l3) {
l3 = new_l3;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
per_cpu(cpu_llc_id, cpu) = l3_id;
#endif
}
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
/*
* If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
* turns means that the only possibility is SMT (as indicated in
static DEFINE_MUTEX(mce_chrdev_read_mutex);
#define rcu_dereference_check_mce(p) \
- rcu_dereference_index_check((p), \
- rcu_read_lock_sched_held() || \
- lockdep_is_held(&mce_chrdev_read_mutex))
+({ \
+ rcu_lockdep_assert(rcu_read_lock_sched_held() || \
+ lockdep_is_held(&mce_chrdev_read_mutex), \
+ "suspicious rcu_dereference_check_mce() usage"); \
+ smp_load_acquire(&(p)); \
+})
#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
struct pt_regs *regs)
{
int i, ret = 0;
+ char *tmp;
for (i = 0; i < mca_cfg.banks; i++) {
m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
if (quirk_no_way_out)
quirk_no_way_out(i, m, regs);
}
- if (mce_severity(m, mca_cfg.tolerant, msg, true) >=
- MCE_PANIC_SEVERITY)
+
+ if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+ *msg = tmp;
ret = 1;
+ }
}
return ret;
}
char *msg = "Unknown";
u64 recover_paddr = ~0ull;
int flags = MF_ACTION_REQUIRED;
+ int lmce = 0;
prev_state = ist_enter(regs);
kill_it = 1;
/*
- * Go through all the banks in exclusion of the other CPUs.
- * This way we don't report duplicated events on shared banks
- * because the first one to see it will clear it.
+ * Check if this MCE is signaled to only this logical processor
*/
- order = mce_start(&no_way_out);
+ if (m.mcgstatus & MCG_STATUS_LMCES)
+ lmce = 1;
+ else {
+ /*
+ * Go through all the banks in exclusion of the other CPUs.
+ * This way we don't report duplicated events on shared banks
+ * because the first one to see it will clear it.
+ * If this is a Local MCE, then no need to perform rendezvous.
+ */
+ order = mce_start(&no_way_out);
+ }
+
for (i = 0; i < cfg->banks; i++) {
__clear_bit(i, toclear);
if (!test_bit(i, valid_banks))
* Do most of the synchronization with other CPUs.
* When there's any problem use only local no_way_out state.
*/
- if (mce_end(order) < 0)
- no_way_out = worst >= MCE_PANIC_SEVERITY;
+ if (!lmce) {
+ if (mce_end(order) < 0)
+ no_way_out = worst >= MCE_PANIC_SEVERITY;
+ } else {
+ /*
+ * Local MCE skipped calling mce_reign()
+ * If we found a fatal error, we need to panic here.
+ */
+ if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
+ mce_panic("Machine check from unknown source",
+ NULL, NULL);
+ }
/*
* At insane "tolerant" levels we take no action. Otherwise
mce_intel_feature_init(c);
mce_adjust_timer = cmci_intel_adjust_timer;
break;
- case X86_VENDOR_AMD:
+
+ case X86_VENDOR_AMD: {
+ u32 ebx = cpuid_ebx(0x80000007);
+
mce_amd_feature_init(c);
- mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1;
+ mce_flags.overflow_recov = !!(ebx & BIT(0));
+ mce_flags.succor = !!(ebx & BIT(1));
break;
+ }
+
default:
break;
}
static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &mce_chrdev_wait, wait);
- if (rcu_access_index(mcelog.next))
+ if (READ_ONCE(mcelog.next))
return POLLIN | POLLRDNORM;
if (!mce_apei_read_done && apei_check_mce())
return POLLIN | POLLRDNORM;
}
EXPORT_SYMBOL_GPL(register_mce_write_callback);
-ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
- size_t usize, loff_t *off)
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+ size_t usize, loff_t *off)
{
if (mce_write)
return mce_write(filp, ubuf, usize, off);
/*
* mce=off Disables machine check
* mce=no_cmci Disables CMCI
+ * mce=no_lmce Disables LMCE
* mce=dont_log_ce Clears corrected events silently, no log created for CEs.
* mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
* mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
cfg->disabled = true;
else if (!strcmp(str, "no_cmci"))
cfg->cmci_disabled = true;
+ else if (!strcmp(str, "no_lmce"))
+ cfg->lmce_disabled = true;
else if (!strcmp(str, "dont_log_ce"))
cfg->dont_log_ce = true;
else if (!strcmp(str, "ignore_ce"))
else if (!strcmp(str, "bios_cmci_threshold"))
cfg->bios_cmci_threshold = true;
else if (isdigit(str[0])) {
- get_option(&str, &(cfg->tolerant));
- if (*str == ',') {
- ++str;
+ if (get_option(&str, &cfg->tolerant) == 2)
get_option(&str, &(cfg->monarch_timeout));
- }
} else {
pr_info("mce argument %s ignored. Please use /sys\n", str);
return 0;
/*
- * (c) 2005-2012 Advanced Micro Devices, Inc.
+ * (c) 2005-2015 Advanced Micro Devices, Inc.
* Your use of this code is subject to the terms and conditions of the
* GNU general public license version 2. See "COPYING" or
* http://www.gnu.org/licenses/gpl.html
*
* Written by Jacob Shin - AMD, Inc.
- *
* Maintained by: Borislav Petkov <bp@alien8.de>
*
- * April 2006
- * - added support for AMD Family 0x10 processors
- * May 2012
- * - major scrubbing
- *
- * All MC4_MISCi registers are shared between multi-cores
+ * All MC4_MISCi registers are shared between cores on a node.
*/
#include <linux/interrupt.h>
#include <linux/notifier.h>
#include <asm/idle.h>
#include <asm/mce.h>
#include <asm/msr.h>
+#include <asm/trace/irq_vectors.h>
#define NR_BLOCKS 9
#define THRESHOLD_MAX 0xFFF
#define MASK_BLKPTR_LO 0xFF000000
#define MCG_XBLK_ADDR 0xC0000400
+/* Deferred error settings */
+#define MSR_CU_DEF_ERR 0xC0000410
+#define MASK_DEF_LVTOFF 0x000000F0
+#define MASK_DEF_INT_TYPE 0x00000006
+#define DEF_LVT_OFF 0x2
+#define DEF_INT_TYPE_APIC 0x2
+
static const char * const th_names[] = {
"load_store",
"insn_fetch",
static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */
static void amd_threshold_interrupt(void);
+static void amd_deferred_error_interrupt(void);
+
+static void default_deferred_error_interrupt(void)
+{
+ pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR);
+}
+void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
/*
* CPU Initialization
threshold_restart_bank(&tr);
};
-static int setup_APIC_mce(int reserved, int new)
+static int setup_APIC_mce_threshold(int reserved, int new)
{
if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
APIC_EILVT_MSG_FIX, 0))
return reserved;
}
+static int setup_APIC_deferred_error(int reserved, int new)
+{
+ if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
+ APIC_EILVT_MSG_FIX, 0))
+ return new;
+
+ return reserved;
+}
+
+static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
+{
+ u32 low = 0, high = 0;
+ int def_offset = -1, def_new;
+
+ if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
+ return;
+
+ def_new = (low & MASK_DEF_LVTOFF) >> 4;
+ if (!(low & MASK_DEF_LVTOFF)) {
+ pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
+ def_new = DEF_LVT_OFF;
+ low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
+ }
+
+ def_offset = setup_APIC_deferred_error(def_offset, def_new);
+ if ((def_offset == def_new) &&
+ (deferred_error_int_vector != amd_deferred_error_interrupt))
+ deferred_error_int_vector = amd_deferred_error_interrupt;
+
+ low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+ wrmsr(MSR_CU_DEF_ERR, low, high);
+}
+
/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
b.interrupt_enable = 1;
new = (high & MASK_LVTOFF_HI) >> 20;
- offset = setup_APIC_mce(offset, new);
+ offset = setup_APIC_mce_threshold(offset, new);
if ((offset == new) &&
(mce_threshold_vector != amd_threshold_interrupt))
mce_threshold_block_init(&b, offset);
}
}
+
+ if (mce_flags.succor)
+ deferred_error_interrupt_enable(c);
+}
+
+static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
+{
+ struct mce m;
+ u64 status;
+
+ rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+ if (!(status & MCI_STATUS_VAL))
+ return;
+
+ mce_setup(&m);
+
+ m.status = status;
+ m.bank = bank;
+
+ if (threshold_err)
+ m.misc = misc;
+
+ if (m.status & MCI_STATUS_ADDRV)
+ rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr);
+
+ mce_log(&m);
+ wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+}
+
+static inline void __smp_deferred_error_interrupt(void)
+{
+ inc_irq_stat(irq_deferred_error_count);
+ deferred_error_int_vector();
+}
+
+asmlinkage __visible void smp_deferred_error_interrupt(void)
+{
+ entering_irq();
+ __smp_deferred_error_interrupt();
+ exiting_ack_irq();
+}
+
+asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
+{
+ entering_irq();
+ trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
+ __smp_deferred_error_interrupt();
+ trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
+ exiting_ack_irq();
+}
+
+/* APIC interrupt handler for deferred errors */
+static void amd_deferred_error_interrupt(void)
+{
+ u64 status;
+ unsigned int bank;
+
+ for (bank = 0; bank < mca_cfg.banks; ++bank) {
+ rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+
+ if (!(status & MCI_STATUS_VAL) ||
+ !(status & MCI_STATUS_DEFERRED))
+ continue;
+
+ __log_error(bank, false, 0);
+ break;
+ }
}
/*
* the interrupt goes off when error_count reaches threshold_limit.
* the handler will simply log mcelog w/ software defined bank number.
*/
+
static void amd_threshold_interrupt(void)
{
u32 low = 0, high = 0, address = 0;
int cpu = smp_processor_id();
unsigned int bank, block;
- struct mce m;
/* assume first bank caused it */
for (bank = 0; bank < mca_cfg.banks; ++bank) {
return;
log:
- mce_setup(&m);
- rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status);
- if (!(m.status & MCI_STATUS_VAL))
- return;
- m.misc = ((u64)high << 32) | low;
- m.bank = bank;
- mce_log(&m);
-
- wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+ __log_error(bank, true, ((u64)high << 32) | low);
}
/*
return !!(cap & MCG_CMCI_P);
}
+static bool lmce_supported(void)
+{
+ u64 tmp;
+
+ if (mca_cfg.lmce_disabled)
+ return false;
+
+ rdmsrl(MSR_IA32_MCG_CAP, tmp);
+
+ /*
+ * LMCE depends on recovery support in the processor. Hence both
+ * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP.
+ */
+ if ((tmp & (MCG_SER_P | MCG_LMCE_P)) !=
+ (MCG_SER_P | MCG_LMCE_P))
+ return false;
+
+ /*
+ * BIOS should indicate support for LMCE by setting bit 20 in
+ * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will
+ * generate a #GP fault.
+ */
+ rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp);
+ if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) ==
+ (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE))
+ return true;
+
+ return false;
+}
+
bool mce_intel_cmci_poll(void)
{
if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
cmci_recheck();
}
+void intel_init_lmce(void)
+{
+ u64 val;
+
+ if (!lmce_supported())
+ return;
+
+ rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+
+ if (!(val & MCG_EXT_CTL_LMCE_EN))
+ wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+}
+
void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
intel_init_thermal(c);
intel_init_cmci();
+ intel_init_lmce();
}
}
}
-void __init load_ucode_amd_bsp(void)
+static bool __init load_builtin_amd_microcode(struct cpio_data *cp,
+ unsigned int family)
+{
+#ifdef CONFIG_X86_64
+ char fw_name[36] = "amd-ucode/microcode_amd.bin";
+
+ if (family >= 0x15)
+ snprintf(fw_name, sizeof(fw_name),
+ "amd-ucode/microcode_amd_fam%.2xh.bin", family);
+
+ return get_builtin_firmware(cp, fw_name);
+#else
+ return false;
+#endif
+}
+
+void __init load_ucode_amd_bsp(unsigned int family)
{
struct cpio_data cp;
void **data;
#endif
cp = find_ucode_in_initrd();
- if (!cp.data)
- return;
+ if (!cp.data) {
+ if (!load_builtin_amd_microcode(&cp, family))
+ return;
+ }
*data = cp.data;
*size = cp.size;
/*
- * Intel CPU Microcode Update Driver for Linux
+ * CPU Microcode Update Driver for Linux
*
- * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- * 2006 Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * 2006 Shaohua Li <shaohua.li@intel.com>
+ * 2013-2015 Borislav Petkov <bp@alien8.de>
*
- * This driver allows to upgrade microcode on Intel processors
- * belonging to IA-32 family - PentiumPro, Pentium II,
- * Pentium III, Xeon, Pentium 4, etc.
+ * This driver allows to upgrade microcode on x86 processors.
*
- * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- * Software Developer's Manual
- * Order Number 253668 or free download from:
- *
- * http://developer.intel.com/Assets/PDF/manual/253668.pdf
- *
- * For more information, go to http://www.urbanmyth.org/microcode
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Initial release.
- * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Added read() support + cleanups.
- * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Added 'device trimming' support. open(O_WRONLY) zeroes
- * and frees the saved copy of applied microcode.
- * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Made to use devfs (/dev/cpu/microcode) + cleanups.
- * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com>
- * Added misc device support (now uses both devfs and misc).
- * Added MICROCODE_IOCFREE ioctl to clear memory.
- * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com>
- * Messages for error cases (non Intel & no suitable microcode).
- * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- * Removed ->release(). Removed exclusive open and status bitmap.
- * Added microcode_rwsem to serialize read()/write()/ioctl().
- * Removed global kernel lock usage.
- * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- * Write 0 to 0x8B msr and then cpuid before reading revision,
- * so that it works even if there were no update done by the
- * BIOS. Otherwise, reading from 0x8B gives junk (which happened
- * to be 0 on my machine which is why it worked even when I
- * disabled update by the BIOS)
- * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- * Tigran Aivazian <tigran@veritas.com>
- * Intel Pentium 4 processor support and bugfixes.
- * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- * Bugfix for HT (Hyper-Threading) enabled processors
- * whereby processor resources are shared by all logical processors
- * in a single CPU package.
- * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- * Tigran Aivazian <tigran@veritas.com>,
- * Serialize updates as required on HT processors due to
- * speculative nature of implementation.
- * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- * Fix the panic when writing zero-length microcode chunk.
- * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- * Jun Nakajima <jun.nakajima@intel.com>
- * Support for the microcode updates in the new format.
- * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- * because we no longer hold a copy of applied microcode
- * in kernel memory.
- * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- * Fix sigmatch() macro to handle old CPUs with pf == 0.
- * Thanks to Stuart Swales for pointing out this bug.
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
*
* Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
* H Peter Anvin" <hpa@zytor.com>
+ * (C) 2015 Borislav Petkov <bp@alien8.de>
*
* This driver allows to early upgrade microcode on Intel processors
* belonging to IA-32 family - PentiumPro, Pentium II,
* 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
+#include <linux/firmware.h>
#include <asm/microcode.h>
#include <asm/microcode_intel.h>
#include <asm/microcode_amd.h>
return *res;
}
+extern struct builtin_fw __start_builtin_fw[];
+extern struct builtin_fw __end_builtin_fw[];
+
+bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+#ifdef CONFIG_FW_LOADER
+ struct builtin_fw *b_fw;
+
+ for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) {
+ if (!strcmp(name, b_fw->name)) {
+ cd->size = b_fw->size;
+ cd->data = b_fw->data;
+ return true;
+ }
+ }
+#endif
+ return false;
+}
+
void __init load_ucode_bsp(void)
{
- int vendor, family;
+ int vendor;
+ unsigned int family;
if (check_loader_disabled_bsp())
return;
break;
case X86_VENDOR_AMD:
if (family >= 0x10)
- load_ucode_amd_bsp();
+ load_ucode_amd_bsp(family);
break;
default:
break;
/*
- * Intel CPU Microcode Update Driver for Linux
+ * Intel CPU Microcode Update Driver for Linux
*
- * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- * 2006 Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * 2006 Shaohua Li <shaohua.li@intel.com>
*
- * This driver allows to upgrade microcode on Intel processors
- * belonging to IA-32 family - PentiumPro, Pentium II,
- * Pentium III, Xeon, Pentium 4, etc.
- *
- * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- * Software Developer's Manual
- * Order Number 253668 or free download from:
- *
- * http://developer.intel.com/Assets/PDF/manual/253668.pdf
- *
- * For more information, go to http://www.urbanmyth.org/microcode
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Initial release.
- * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Added read() support + cleanups.
- * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Added 'device trimming' support. open(O_WRONLY) zeroes
- * and frees the saved copy of applied microcode.
- * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- * Made to use devfs (/dev/cpu/microcode) + cleanups.
- * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com>
- * Added misc device support (now uses both devfs and misc).
- * Added MICROCODE_IOCFREE ioctl to clear memory.
- * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com>
- * Messages for error cases (non Intel & no suitable microcode).
- * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- * Removed ->release(). Removed exclusive open and status bitmap.
- * Added microcode_rwsem to serialize read()/write()/ioctl().
- * Removed global kernel lock usage.
- * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- * Write 0 to 0x8B msr and then cpuid before reading revision,
- * so that it works even if there were no update done by the
- * BIOS. Otherwise, reading from 0x8B gives junk (which happened
- * to be 0 on my machine which is why it worked even when I
- * disabled update by the BIOS)
- * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- * Tigran Aivazian <tigran@veritas.com>
- * Intel Pentium 4 processor support and bugfixes.
- * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- * Bugfix for HT (Hyper-Threading) enabled processors
- * whereby processor resources are shared by all logical processors
- * in a single CPU package.
- * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- * Tigran Aivazian <tigran@veritas.com>,
- * Serialize updates as required on HT processors due to
- * speculative nature of implementation.
- * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- * Fix the panic when writing zero-length microcode chunk.
- * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- * Jun Nakajima <jun.nakajima@intel.com>
- * Support for the microcode updates in the new format.
- * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- * because we no longer hold a copy of applied microcode
- * in kernel memory.
- * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- * Fix sigmatch() macro to handle old CPUs with pf == 0.
- * Thanks to Stuart Swales for pointing out this bug.
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
cpf = cpu_sig.pf;
crev = cpu_sig.rev;
- return get_matching_microcode(csig, cpf, crev, mc_intel);
+ return has_newer_microcode(mc_intel, csig, cpf, crev);
}
static int apply_microcode_intel(int cpu)
csig = uci->cpu_sig.sig;
cpf = uci->cpu_sig.pf;
- if (get_matching_microcode(csig, cpf, new_rev, mc)) {
+ if (has_newer_microcode(mc, csig, cpf, new_rev)) {
vfree(new_mc);
new_rev = mc_header.rev;
new_mc = mc;
ucode_ptr = saved[i];
mc_hdr = (struct microcode_header_intel *)ucode_ptr;
- ret = get_matching_microcode(uci->cpu_sig.sig,
- uci->cpu_sig.pf,
- new_rev,
- ucode_ptr);
+ ret = has_newer_microcode(ucode_ptr,
+ uci->cpu_sig.sig,
+ uci->cpu_sig.pf,
+ new_rev);
if (!ret)
continue;
u8 *ucode_ptr, unsigned int num_saved)
{
struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
- unsigned int sig, pf, new_rev;
+ unsigned int sig, pf;
int found = 0, i;
mc_hdr = (struct microcode_header_intel *)ucode_ptr;
mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i];
sig = mc_saved_hdr->sig;
pf = mc_saved_hdr->pf;
- new_rev = mc_hdr->rev;
- if (!get_matching_sig(sig, pf, new_rev, ucode_ptr))
+ if (!find_matching_signature(ucode_ptr, sig, pf))
continue;
found = 1;
- if (!revision_is_newer(mc_hdr, new_rev))
+ if (mc_hdr->rev <= mc_saved_hdr->rev)
continue;
/*
EXPORT_SYMBOL_GPL(save_mc_for_early);
#endif
+static bool __init load_builtin_intel_microcode(struct cpio_data *cp)
+{
+#ifdef CONFIG_X86_64
+ unsigned int eax = 0x00000001, ebx, ecx = 0, edx;
+ unsigned int family, model, stepping;
+ char name[30];
+
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+
+ family = __x86_family(eax);
+ model = x86_model(eax);
+ stepping = eax & 0xf;
+
+ sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping);
+
+ return get_builtin_firmware(cp, name);
+#else
+ return false;
+#endif
+}
+
static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
static __init enum ucode_state
scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
cd.size = 0;
cd = find_cpio_data(p, (void *)start, size, &offset);
- if (!cd.data)
- return UCODE_ERROR;
+ if (!cd.data) {
+ if (!load_builtin_intel_microcode(&cd))
+ return UCODE_ERROR;
+ }
return get_matching_model_microcode(0, start, cd.data, cd.size,
mc_saved_data, initrd, uci);
#include <asm/processor.h>
#include <asm/msr.h>
-static inline int
-update_match_cpu(unsigned int csig, unsigned int cpf,
- unsigned int sig, unsigned int pf)
+static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
+ unsigned int s2, unsigned int p2)
{
- return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1;
+ if (s1 != s2)
+ return false;
+
+ /* Processor flags are either both 0 ... */
+ if (!p1 && !p2)
+ return true;
+
+ /* ... or they intersect. */
+ return p1 & p2;
}
int microcode_sanity_check(void *mc, int print_err)
/*
* Returns 1 if update has been found, 0 otherwise.
*/
-int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
+int find_matching_signature(void *mc, unsigned int csig, int cpf)
{
- struct microcode_header_intel *mc_header = mc;
- struct extended_sigtable *ext_header;
- unsigned long total_size = get_totalsize(mc_header);
- int ext_sigcount, i;
+ struct microcode_header_intel *mc_hdr = mc;
+ struct extended_sigtable *ext_hdr;
struct extended_signature *ext_sig;
+ int i;
- if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf))
+ if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
return 1;
/* Look for ext. headers: */
- if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
+ if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE)
return 0;
- ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
- ext_sigcount = ext_header->count;
- ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+ ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE;
+ ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
- for (i = 0; i < ext_sigcount; i++) {
- if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf))
+ for (i = 0; i < ext_hdr->count; i++) {
+ if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
return 1;
ext_sig++;
}
/*
* Returns 1 if update has been found, 0 otherwise.
*/
-int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc)
+int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
{
struct microcode_header_intel *mc_hdr = mc;
- if (!revision_is_newer(mc_hdr, rev))
+ if (mc_hdr->rev <= new_rev)
return 0;
- return get_matching_sig(csig, cpf, rev, mc);
+ return find_matching_signature(mc, csig, cpf);
}
-EXPORT_SYMBOL_GPL(get_matching_microcode);
+EXPORT_SYMBOL_GPL(has_newer_microcode);
{
struct pt_regs *old_regs = set_irq_regs(regs);
- irq_enter();
- exit_idle();
-
+ entering_irq();
inc_irq_stat(irq_hv_callback_count);
if (vmbus_handler)
vmbus_handler();
- irq_exit();
+ exiting_irq();
set_irq_regs(old_regs);
}
continue;
base = range_state[i].base_pfn;
if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed &&
- (mtrr_state.enabled & 1)) {
+ (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+ (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
/* Var MTRR contains UC entry below 1M? Skip it: */
printk(BIOS_BUG_MSG, i);
if (base + size <= (1<<(20-PAGE_SHIFT)))
return 0;
}
-/*
- * Error/Semi-error returns:
- * 0xFF - when MTRR is not enabled
- * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
- * corresponds only to [start:*partial_end].
- * Caller has to lookup again for [*partial_end:end].
+/**
+ * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries
+ *
+ * Return the MTRR fixed memory type of 'start'.
+ *
+ * MTRR fixed entries are divided into the following ways:
+ * 0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges
+ * 0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges
+ * 0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges
+ *
+ * Return Values:
+ * MTRR_TYPE_(type) - Matched memory type
+ * MTRR_TYPE_INVALID - Unmatched
+ */
+static u8 mtrr_type_lookup_fixed(u64 start, u64 end)
+{
+ int idx;
+
+ if (start >= 0x100000)
+ return MTRR_TYPE_INVALID;
+
+ /* 0x0 - 0x7FFFF */
+ if (start < 0x80000) {
+ idx = 0;
+ idx += (start >> 16);
+ return mtrr_state.fixed_ranges[idx];
+ /* 0x80000 - 0xBFFFF */
+ } else if (start < 0xC0000) {
+ idx = 1 * 8;
+ idx += ((start - 0x80000) >> 14);
+ return mtrr_state.fixed_ranges[idx];
+ }
+
+ /* 0xC0000 - 0xFFFFF */
+ idx = 3 * 8;
+ idx += ((start - 0xC0000) >> 12);
+ return mtrr_state.fixed_ranges[idx];
+}
+
+/**
+ * mtrr_type_lookup_variable - look up memory type in MTRR variable entries
+ *
+ * Return Value:
+ * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched)
+ *
+ * Output Arguments:
+ * repeat - Set to 1 when [start:end] spanned across MTRR range and type
+ * returned corresponds only to [start:*partial_end]. Caller has
+ * to lookup again for [*partial_end:end].
+ *
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ * region is fully covered by a single MTRR entry or the default
+ * type.
*/
-static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
+static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
+ int *repeat, u8 *uniform)
{
int i;
u64 base, mask;
u8 prev_match, curr_match;
*repeat = 0;
- if (!mtrr_state_set)
- return 0xFF;
-
- if (!mtrr_state.enabled)
- return 0xFF;
+ *uniform = 1;
- /* Make end inclusive end, instead of exclusive */
+ /* Make end inclusive instead of exclusive */
end--;
- /* Look in fixed ranges. Just return the type as per start */
- if (mtrr_state.have_fixed && (start < 0x100000)) {
- int idx;
-
- if (start < 0x80000) {
- idx = 0;
- idx += (start >> 16);
- return mtrr_state.fixed_ranges[idx];
- } else if (start < 0xC0000) {
- idx = 1 * 8;
- idx += ((start - 0x80000) >> 14);
- return mtrr_state.fixed_ranges[idx];
- } else if (start < 0x1000000) {
- idx = 3 * 8;
- idx += ((start - 0xC0000) >> 12);
- return mtrr_state.fixed_ranges[idx];
- }
- }
-
- /*
- * Look in variable ranges
- * Look of multiple ranges matching this address and pick type
- * as per MTRR precedence
- */
- if (!(mtrr_state.enabled & 2))
- return mtrr_state.def_type;
-
- prev_match = 0xFF;
+ prev_match = MTRR_TYPE_INVALID;
for (i = 0; i < num_var_ranges; ++i) {
- unsigned short start_state, end_state;
+ unsigned short start_state, end_state, inclusive;
if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11)))
continue;
start_state = ((start & mask) == (base & mask));
end_state = ((end & mask) == (base & mask));
+ inclusive = ((start < base) && (end > base));
- if (start_state != end_state) {
+ if ((start_state != end_state) || inclusive) {
/*
* We have start:end spanning across an MTRR.
- * We split the region into
- * either
- * (start:mtrr_end) (mtrr_end:end)
- * or
- * (start:mtrr_start) (mtrr_start:end)
+ * We split the region into either
+ *
+ * - start_state:1
+ * (start:mtrr_end)(mtrr_end:end)
+ * - end_state:1
+ * (start:mtrr_start)(mtrr_start:end)
+ * - inclusive:1
+ * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end)
+ *
* depending on kind of overlap.
- * Return the type for first region and a pointer to
- * the start of second region so that caller will
- * lookup again on the second region.
- * Note: This way we handle multiple overlaps as well.
+ *
+ * Return the type of the first region and a pointer
+ * to the start of next region so that caller will be
+ * advised to lookup again after having adjusted start
+ * and end.
+ *
+ * Note: This way we handle overlaps with multiple
+ * entries and the default type properly.
*/
if (start_state)
*partial_end = base + get_mtrr_size(mask);
end = *partial_end - 1; /* end is inclusive */
*repeat = 1;
+ *uniform = 0;
}
if ((start & mask) != (base & mask))
continue;
curr_match = mtrr_state.var_ranges[i].base_lo & 0xff;
- if (prev_match == 0xFF) {
+ if (prev_match == MTRR_TYPE_INVALID) {
prev_match = curr_match;
continue;
}
+ *uniform = 0;
if (check_type_overlap(&prev_match, &curr_match))
return curr_match;
}
- if (mtrr_tom2) {
- if (start >= (1ULL<<32) && (end < mtrr_tom2))
- return MTRR_TYPE_WRBACK;
- }
-
- if (prev_match != 0xFF)
+ if (prev_match != MTRR_TYPE_INVALID)
return prev_match;
return mtrr_state.def_type;
}
-/*
- * Returns the effective MTRR type for the region
- * Error return:
- * 0xFF - when MTRR is not enabled
+/**
+ * mtrr_type_lookup - look up memory type in MTRR
+ *
+ * Return Values:
+ * MTRR_TYPE_(type) - The effective MTRR type for the region
+ * MTRR_TYPE_INVALID - MTRR is disabled
+ *
+ * Output Argument:
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ * region is fully covered by a single MTRR entry or the default
+ * type.
*/
-u8 mtrr_type_lookup(u64 start, u64 end)
+u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
{
- u8 type, prev_type;
+ u8 type, prev_type, is_uniform = 1, dummy;
int repeat;
u64 partial_end;
- type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+ if (!mtrr_state_set)
+ return MTRR_TYPE_INVALID;
+
+ if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED))
+ return MTRR_TYPE_INVALID;
+
+ /*
+ * Look up the fixed ranges first, which take priority over
+ * the variable ranges.
+ */
+ if ((start < 0x100000) &&
+ (mtrr_state.have_fixed) &&
+ (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
+ is_uniform = 0;
+ type = mtrr_type_lookup_fixed(start, end);
+ goto out;
+ }
+
+ /*
+ * Look up the variable ranges. Look of multiple ranges matching
+ * this address and pick type as per MTRR precedence.
+ */
+ type = mtrr_type_lookup_variable(start, end, &partial_end,
+ &repeat, &is_uniform);
/*
* Common path is with repeat = 0.
* However, we can have cases where [start:end] spans across some
- * MTRR range. Do repeated lookups for that case here.
+ * MTRR ranges and/or the default type. Do repeated lookups for
+ * that case here.
*/
while (repeat) {
prev_type = type;
start = partial_end;
- type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+ is_uniform = 0;
+ type = mtrr_type_lookup_variable(start, end, &partial_end,
+ &repeat, &dummy);
if (check_type_overlap(&prev_type, &type))
- return type;
+ goto out;
}
+ if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2))
+ type = MTRR_TYPE_WRBACK;
+
+out:
+ *uniform = is_uniform;
return type;
}
mtrr_attrib_to_str(mtrr_state.def_type));
if (mtrr_state.have_fixed) {
pr_debug("MTRR fixed ranges %sabled:\n",
- mtrr_state.enabled & 1 ? "en" : "dis");
+ ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+ (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ?
+ "en" : "dis");
print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
for (i = 0; i < 2; ++i)
print_fixed(0x80000 + i * 0x20000, 0x04000,
print_fixed_last();
}
pr_debug("MTRR variable ranges %sabled:\n",
- mtrr_state.enabled & 2 ? "en" : "dis");
+ mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis");
high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4;
for (i = 0; i < num_var_ranges; ++i) {
}
/* Grab all of the MTRR state for this CPU into *state */
-void __init get_mtrr_state(void)
+bool __init get_mtrr_state(void)
{
struct mtrr_var_range *vrs;
unsigned long flags;
post_set();
local_irq_restore(flags);
+
+ return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
}
/* Some BIOS's are messed up and don't set all MTRRs the same! */
#define MTRR_TO_PHYS_WC_OFFSET 1000
u32 num_var_ranges;
+static bool __mtrr_enabled;
+
+static bool mtrr_enabled(void)
+{
+ return __mtrr_enabled;
+}
unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
static DEFINE_MUTEX(mtrr_mutex);
int i, replace, error;
mtrr_type ltype;
- if (!mtrr_if)
+ if (!mtrr_enabled())
return -ENXIO;
error = mtrr_if->validate_add_page(base, size, type);
int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
bool increment)
{
+ if (!mtrr_enabled())
+ return -ENODEV;
if (mtrr_check(base, size))
return -EINVAL;
return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
unsigned long lbase, lsize;
int error = -EINVAL;
- if (!mtrr_if)
- return -ENXIO;
+ if (!mtrr_enabled())
+ return -ENODEV;
max = num_var_ranges;
/* No CPU hotplug when we change MTRR entries */
*/
int mtrr_del(int reg, unsigned long base, unsigned long size)
{
+ if (!mtrr_enabled())
+ return -ENODEV;
if (mtrr_check(base, size))
return -EINVAL;
return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
* attempts to add a WC MTRR covering size bytes starting at base and
* logs an error if this fails.
*
+ * The called should provide a power of two size on an equivalent
+ * power of two boundary.
+ *
* Drivers must store the return value to pass to mtrr_del_wc_if_needed,
* but drivers should not try to interpret that return value.
*/
{
int ret;
- if (pat_enabled)
+ if (pat_enabled() || !mtrr_enabled())
return 0; /* Success! (We don't need to do anything.) */
ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true);
EXPORT_SYMBOL(arch_phys_wc_del);
/*
- * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value
+ * arch_phys_wc_index - translates arch_phys_wc_add's return value
* @handle: Return value from arch_phys_wc_add
*
* This will turn the return value from arch_phys_wc_add into an mtrr
* in printk line. Alas there is an illegitimate use in some ancient
* drm ioctls.
*/
-int phys_wc_to_mtrr_index(int handle)
+int arch_phys_wc_index(int handle)
{
if (handle < MTRR_TO_PHYS_WC_OFFSET)
return -1;
else
return handle - MTRR_TO_PHYS_WC_OFFSET;
}
-EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index);
+EXPORT_SYMBOL_GPL(arch_phys_wc_index);
/*
* HACK ALERT!
}
if (mtrr_if) {
+ __mtrr_enabled = true;
set_num_var_ranges();
init_table();
if (use_intel()) {
- get_mtrr_state();
+ /* BIOS may override */
+ __mtrr_enabled = get_mtrr_state();
if (mtrr_cleanup(phys_addr)) {
changed_by_mtrr_cleanup = 1;
}
}
}
+
+ if (!mtrr_enabled())
+ pr_info("MTRR: Disabled\n");
}
void mtrr_ap_init(void)
{
+ if (!mtrr_enabled())
+ return;
+
if (!use_intel() || mtrr_aps_delayed_init)
return;
/*
{
int first_cpu;
+ if (!mtrr_enabled())
+ return;
+
get_online_cpus();
first_cpu = cpumask_first(cpu_online_mask);
smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
void set_mtrr_aps_delayed_init(void)
{
+ if (!mtrr_enabled())
+ return;
if (!use_intel())
return;
*/
void mtrr_aps_init(void)
{
- if (!use_intel())
+ if (!use_intel() || !mtrr_enabled())
return;
/*
void mtrr_bp_restore(void)
{
- if (!use_intel())
+ if (!use_intel() || !mtrr_enabled())
return;
mtrr_if->set_all();
static int __init mtrr_init_finialize(void)
{
- if (!mtrr_if)
+ if (!mtrr_enabled())
return 0;
if (use_intel()) {
void fill_mtrr_var_range(unsigned int index,
u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
-void get_mtrr_state(void);
+bool get_mtrr_state(void);
extern void set_mtrr_ops(const struct mtrr_ops *ops);
}
static atomic_t active_events;
+static atomic_t pmc_refcount;
static DEFINE_MUTEX(pmc_reserve_mutex);
#ifdef CONFIG_X86_LOCAL_APIC
u64 val, val_fail, val_new= ~0;
int i, reg, reg_fail, ret = 0;
int bios_fail = 0;
+ int reg_safe = -1;
/*
* Check to see if the BIOS enabled any of the counters, if so
bios_fail = 1;
val_fail = val;
reg_fail = reg;
+ } else {
+ reg_safe = i;
}
}
}
}
+ /*
+ * If all the counters are enabled, the below test will always
+ * fail. The tools will also become useless in this scenario.
+ * Just fail and disable the hardware counters.
+ */
+
+ if (reg_safe == -1) {
+ reg = reg_safe;
+ goto msr_fail;
+ }
+
/*
* Read the current value, change it and read it back to see if it
* matches, this is needed to detect certain hardware emulators
* (qemu/kvm) that don't trap on the MSR access and always return 0s.
*/
- reg = x86_pmu_event_addr(0);
+ reg = x86_pmu_event_addr(reg_safe);
if (rdmsrl_safe(reg, &val))
goto msr_fail;
val ^= 0xffffUL;
static void hw_perf_event_destroy(struct perf_event *event)
{
- if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
- release_pmc_hardware();
- release_ds_buffers();
- mutex_unlock(&pmc_reserve_mutex);
- }
+ x86_release_hardware();
+ atomic_dec(&active_events);
}
void hw_perf_lbr_event_destroy(struct perf_event *event)
return x86_pmu_extra_regs(val, event);
}
+int x86_reserve_hardware(void)
+{
+ int err = 0;
+
+ if (!atomic_inc_not_zero(&pmc_refcount)) {
+ mutex_lock(&pmc_reserve_mutex);
+ if (atomic_read(&pmc_refcount) == 0) {
+ if (!reserve_pmc_hardware())
+ err = -EBUSY;
+ else
+ reserve_ds_buffers();
+ }
+ if (!err)
+ atomic_inc(&pmc_refcount);
+ mutex_unlock(&pmc_reserve_mutex);
+ }
+
+ return err;
+}
+
+void x86_release_hardware(void)
+{
+ if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) {
+ release_pmc_hardware();
+ release_ds_buffers();
+ mutex_unlock(&pmc_reserve_mutex);
+ }
+}
+
/*
* Check if we can create event of a certain type (that no conflicting events
* are present).
return 0;
mutex_lock(&pmc_reserve_mutex);
- for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++)
+ for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
goto out;
+ }
atomic_inc(&x86_pmu.lbr_exclusive[what]);
ret = 0;
out:
mutex_unlock(&pmc_reserve_mutex);
+
+ /*
+ * Assuming that all exclusive events will share the PMI handler
+ * (which checks active_events for whether there is work to do),
+ * we can bump active_events counter right here, except for
+ * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init()
+ * path, which already bumps active_events for them.
+ */
+ if (!ret && what != x86_lbr_exclusive_lbr)
+ atomic_inc(&active_events);
+
return ret;
}
void x86_del_exclusive(unsigned int what)
{
atomic_dec(&x86_pmu.lbr_exclusive[what]);
+ atomic_dec(&active_events);
}
int x86_setup_perfctr(struct perf_event *event)
if (!x86_pmu_initialized())
return -ENODEV;
- err = 0;
- if (!atomic_inc_not_zero(&active_events)) {
- mutex_lock(&pmc_reserve_mutex);
- if (atomic_read(&active_events) == 0) {
- if (!reserve_pmc_hardware())
- err = -EBUSY;
- else
- reserve_ds_buffers();
- }
- if (!err)
- atomic_inc(&active_events);
- mutex_unlock(&pmc_reserve_mutex);
- }
+ err = x86_reserve_hardware();
if (err)
return err;
+ atomic_inc(&active_events);
event->destroy = hw_perf_event_destroy;
event->hw.idx = -1;
int event; /* event index */
int counter; /* counter index */
int unassigned; /* number of events to be assigned left */
+ int nr_gp; /* number of GP counters used */
unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
};
struct perf_sched {
int max_weight;
int max_events;
- struct perf_event **events;
- struct sched_state state;
+ int max_gp;
int saved_states;
+ struct event_constraint **constraints;
+ struct sched_state state;
struct sched_state saved[SCHED_STATES_MAX];
};
/*
* Initialize interator that runs through all events and counters.
*/
-static void perf_sched_init(struct perf_sched *sched, struct perf_event **events,
- int num, int wmin, int wmax)
+static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints,
+ int num, int wmin, int wmax, int gpmax)
{
int idx;
memset(sched, 0, sizeof(*sched));
sched->max_events = num;
sched->max_weight = wmax;
- sched->events = events;
+ sched->max_gp = gpmax;
+ sched->constraints = constraints;
for (idx = 0; idx < num; idx++) {
- if (events[idx]->hw.constraint->weight == wmin)
+ if (constraints[idx]->weight == wmin)
break;
}
if (sched->state.event >= sched->max_events)
return false;
- c = sched->events[sched->state.event]->hw.constraint;
+ c = sched->constraints[sched->state.event];
/* Prefer fixed purpose counters */
if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
idx = INTEL_PMC_IDX_FIXED;
goto done;
}
}
+
/* Grab the first unused counter starting with idx */
idx = sched->state.counter;
for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
- if (!__test_and_set_bit(idx, sched->state.used))
+ if (!__test_and_set_bit(idx, sched->state.used)) {
+ if (sched->state.nr_gp++ >= sched->max_gp)
+ return false;
+
goto done;
+ }
}
return false;
if (sched->state.weight > sched->max_weight)
return false;
}
- c = sched->events[sched->state.event]->hw.constraint;
+ c = sched->constraints[sched->state.event];
} while (c->weight != sched->state.weight);
sched->state.counter = 0; /* start with first counter */
/*
* Assign a counter for each event.
*/
-int perf_assign_events(struct perf_event **events, int n,
- int wmin, int wmax, int *assign)
+int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int gpmax, int *assign)
{
struct perf_sched sched;
- perf_sched_init(&sched, events, n, wmin, wmax);
+ perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax);
do {
if (!perf_sched_find_counter(&sched))
x86_pmu.start_scheduling(cpuc);
for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
- hwc = &cpuc->event_list[i]->hw;
+ cpuc->event_constraint[i] = NULL;
c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
- hwc->constraint = c;
+ cpuc->event_constraint[i] = c;
wmin = min(wmin, c->weight);
wmax = max(wmax, c->weight);
*/
for (i = 0; i < n; i++) {
hwc = &cpuc->event_list[i]->hw;
- c = hwc->constraint;
+ c = cpuc->event_constraint[i];
/* never assigned */
if (hwc->idx == -1)
}
/* slow path */
- if (i != n)
- unsched = perf_assign_events(cpuc->event_list, n, wmin,
- wmax, assign);
+ if (i != n) {
+ int gpmax = x86_pmu.num_counters;
+
+ /*
+ * Do not allow scheduling of more than half the available
+ * generic counters.
+ *
+ * This helps avoid counter starvation of sibling thread by
+ * ensuring at most half the counters cannot be in exclusive
+ * mode. There is no designated counters for the limits. Any
+ * N/2 counters can be used. This helps with events with
+ * specific counter constraints.
+ */
+ if (is_ht_workaround_enabled() && !cpuc->is_fake &&
+ READ_ONCE(cpuc->excl_cntrs->exclusive_present))
+ gpmax /= 2;
+
+ unsched = perf_assign_events(cpuc->event_constraint, n, wmin,
+ wmax, gpmax, assign);
+ }
/*
* In case of success (unsched = 0), mark events as committed,
e = cpuc->event_list[i];
e->hw.flags |= PERF_X86_EVENT_COMMITTED;
if (x86_pmu.commit_scheduling)
- x86_pmu.commit_scheduling(cpuc, e, assign[i]);
+ x86_pmu.commit_scheduling(cpuc, i, assign[i]);
}
- }
-
- if (!assign || unsched) {
-
+ } else {
for (i = 0; i < n; i++) {
e = cpuc->event_list[i];
/*
per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
- /*
- * The hw event starts counting from this event offset,
- * mark it to be able to extra future deltas:
- */
- local64_set(&hwc->prev_count, (u64)-left);
+ if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) ||
+ local64_read(&hwc->prev_count) != (u64)-left) {
+ /*
+ * The hw event starts counting from this event offset,
+ * mark it to be able to extra future deltas:
+ */
+ local64_set(&hwc->prev_count, (u64)-left);
- wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+ wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+ }
/*
* Due to erratum on certan cpu we need
x86_pmu.put_event_constraints(cpuc, event);
/* Delete the array entry. */
- while (++i < cpuc->n_events)
+ while (++i < cpuc->n_events) {
cpuc->event_list[i-1] = cpuc->event_list[i];
+ cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
+ }
--cpuc->n_events;
perf_event_update_userpage(event);
u64 finish_clock;
int ret;
+ /*
+ * All PMUs/events that share this PMI handler should make sure to
+ * increment active_events for their events.
+ */
if (!atomic_read(&active_events))
return NMI_DONE;
#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */
#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */
#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */
struct amd_nb {
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8
+/*
+ * Flags PEBS can handle without an PMI.
+ *
+ * TID can only be handled by flushing at context switch.
+ *
+ */
+#define PEBS_FREERUNNING_FLAGS \
+ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
+ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
+ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
+ PERF_SAMPLE_TRANSACTION)
+
/*
* A debug store configuration.
*
};
struct intel_excl_states {
- enum intel_excl_state_type init_state[X86_PMC_IDX_MAX];
enum intel_excl_state_type state[X86_PMC_IDX_MAX];
- int num_alloc_cntrs;/* #counters allocated */
- int max_alloc_cntrs;/* max #counters allowed */
bool sched_started; /* true if scheduling has started */
};
struct intel_excl_states states[2];
+ union {
+ u16 has_exclusive[2];
+ u32 exclusive_present;
+ };
+
int refcnt; /* per-core: #HT threads */
unsigned core_id; /* per-core: core id */
};
added in the current transaction */
int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
u64 tags[X86_PMC_IDX_MAX];
+
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+ struct event_constraint *event_constraint[X86_PMC_IDX_MAX];
+
+ int n_excl; /* the number of exclusive events */
unsigned int group_flag;
int is_fake;
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
- void (*commit_scheduling)(struct cpu_hw_events *cpuc,
- struct perf_event *event,
- int cntr);
-
void (*start_scheduling)(struct cpu_hw_events *cpuc);
+ void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
+
void (*stop_scheduling)(struct cpu_hw_events *cpuc);
struct event_constraint *event_constraints;
void x86_del_exclusive(unsigned int what);
+int x86_reserve_hardware(void);
+
+void x86_release_hardware(void);
+
void hw_perf_lbr_event_destroy(struct perf_event *event);
int x86_setup_perfctr(struct perf_event *event);
void x86_pmu_enable_all(int added);
-int perf_assign_events(struct perf_event **events, int n,
- int wmin, int wmax, int *assign);
+int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int gpmax, int *assign);
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
void x86_pmu_stop(struct perf_event *event, int flags);
void intel_pmu_pebs_disable_all(void);
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
return NULL;
}
+static inline int is_ht_workaround_enabled(void)
+{
+ return 0;
+}
#endif /* CONFIG_CPU_SUP_INTEL */
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
- [ C(RESULT_MISS) ] = SLM_DMND_READ|SLM_LLC_MISS,
+ [ C(RESULT_MISS) ] = 0,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
[ C(OP_READ) ] = {
/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0,
},
[ C(OP_WRITE) ] = {
/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(ITLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
- [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */
+ [ C(RESULT_MISS) ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = -1,
intel_start_scheduling(struct cpu_hw_events *cpuc)
{
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct intel_excl_states *xl, *xlo;
+ struct intel_excl_states *xl;
int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid; /* sibling thread */
/*
* nothing needed if in group validation mode
/*
* no exclusion needed
*/
- if (!excl_cntrs)
+ if (WARN_ON_ONCE(!excl_cntrs))
return;
- xlo = &excl_cntrs->states[o_tid];
xl = &excl_cntrs->states[tid];
xl->sched_started = true;
- xl->num_alloc_cntrs = 0;
/*
* lock shared state until we are done scheduling
* in stop_event_scheduling()
* makes scheduling appear as a transaction
*/
- WARN_ON_ONCE(!irqs_disabled());
raw_spin_lock(&excl_cntrs->lock);
+}
- /*
- * save initial state of sibling thread
- */
- memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state));
+static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+ struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
+ struct event_constraint *c = cpuc->event_constraint[idx];
+ struct intel_excl_states *xl;
+ int tid = cpuc->excl_thread_id;
+
+ if (cpuc->is_fake || !is_ht_workaround_enabled())
+ return;
+
+ if (WARN_ON_ONCE(!excl_cntrs))
+ return;
+
+ if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
+ return;
+
+ xl = &excl_cntrs->states[tid];
+
+ lockdep_assert_held(&excl_cntrs->lock);
+
+ if (c->flags & PERF_X86_EVENT_EXCL)
+ xl->state[cntr] = INTEL_EXCL_EXCLUSIVE;
+ else
+ xl->state[cntr] = INTEL_EXCL_SHARED;
}
static void
intel_stop_scheduling(struct cpu_hw_events *cpuc)
{
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct intel_excl_states *xl, *xlo;
+ struct intel_excl_states *xl;
int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid; /* sibling thread */
/*
* nothing needed if in group validation mode
/*
* no exclusion needed
*/
- if (!excl_cntrs)
+ if (WARN_ON_ONCE(!excl_cntrs))
return;
- xlo = &excl_cntrs->states[o_tid];
xl = &excl_cntrs->states[tid];
- /*
- * make new sibling thread state visible
- */
- memcpy(xlo->state, xlo->init_state, sizeof(xlo->state));
-
xl->sched_started = false;
/*
* release shared state lock (acquired in intel_start_scheduling())
intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
int idx, struct event_constraint *c)
{
- struct event_constraint *cx;
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct intel_excl_states *xl, *xlo;
- int is_excl, i;
+ struct intel_excl_states *xlo;
int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid; /* alternate */
+ int is_excl, i;
/*
* validating a group does not require
/*
* no exclusion needed
*/
- if (!excl_cntrs)
+ if (WARN_ON_ONCE(!excl_cntrs))
return c;
- /*
- * event requires exclusive counter access
- * across HT threads
- */
- is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
- /*
- * xl = state of current HT
- * xlo = state of sibling HT
- */
- xl = &excl_cntrs->states[tid];
- xlo = &excl_cntrs->states[o_tid];
-
- /*
- * do not allow scheduling of more than max_alloc_cntrs
- * which is set to half the available generic counters.
- * this helps avoid counter starvation of sibling thread
- * by ensuring at most half the counters cannot be in
- * exclusive mode. There is not designated counters for the
- * limits. Any N/2 counters can be used. This helps with
- * events with specifix counter constraints
- */
- if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs)
- return &emptyconstraint;
-
- cx = c;
/*
* because we modify the constraint, we need
* been cloned (marked dynamic)
*/
if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
-
- /* sanity check */
- if (idx < 0)
- return &emptyconstraint;
+ struct event_constraint *cx;
/*
* grab pre-allocated constraint entry
* initialize dynamic constraint
* with static constraint
*/
- memcpy(cx, c, sizeof(*cx));
+ *cx = *c;
/*
* mark constraint as dynamic, so we
* can free it later on
*/
cx->flags |= PERF_X86_EVENT_DYNAMIC;
+ c = cx;
}
/*
* of this function
*/
+ /*
+ * state of sibling HT
+ */
+ xlo = &excl_cntrs->states[tid ^ 1];
+
+ /*
+ * event requires exclusive counter access
+ * across HT threads
+ */
+ is_excl = c->flags & PERF_X86_EVENT_EXCL;
+ if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
+ event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
+ if (!cpuc->n_excl++)
+ WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
+ }
+
/*
* Modify static constraint with current dynamic
* state of thread
* SHARED : sibling counter measuring non-exclusive event
* UNUSED : sibling counter unused
*/
- for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) {
+ for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
/*
* exclusive event in sibling counter
* our corresponding counter cannot be used
* regardless of our event
*/
- if (xl->state[i] == INTEL_EXCL_EXCLUSIVE)
- __clear_bit(i, cx->idxmsk);
+ if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+ __clear_bit(i, c->idxmsk);
/*
* if measuring an exclusive event, sibling
* measuring non-exclusive, then counter cannot
* be used
*/
- if (is_excl && xl->state[i] == INTEL_EXCL_SHARED)
- __clear_bit(i, cx->idxmsk);
+ if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+ __clear_bit(i, c->idxmsk);
}
/*
* recompute actual bit weight for scheduling algorithm
*/
- cx->weight = hweight64(cx->idxmsk64);
+ c->weight = hweight64(c->idxmsk64);
/*
* if we return an empty mask, then switch
* back to static empty constraint to avoid
* the cost of freeing later on
*/
- if (cx->weight == 0)
- cx = &emptyconstraint;
+ if (c->weight == 0)
+ c = &emptyconstraint;
- return cx;
+ return c;
}
static struct event_constraint *
intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
{
- struct event_constraint *c1 = event->hw.constraint;
+ struct event_constraint *c1 = cpuc->event_constraint[idx];
struct event_constraint *c2;
/*
{
struct hw_perf_event *hwc = &event->hw;
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct intel_excl_states *xlo, *xl;
- unsigned long flags = 0; /* keep compiler happy */
int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid;
+ struct intel_excl_states *xl;
/*
* nothing needed if in group validation mode
if (cpuc->is_fake)
return;
- WARN_ON_ONCE(!excl_cntrs);
-
- if (!excl_cntrs)
+ if (WARN_ON_ONCE(!excl_cntrs))
return;
- xl = &excl_cntrs->states[tid];
- xlo = &excl_cntrs->states[o_tid];
+ if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
+ hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
+ if (!--cpuc->n_excl)
+ WRITE_ONCE(excl_cntrs->has_exclusive[tid], 0);
+ }
/*
- * put_constraint may be called from x86_schedule_events()
- * which already has the lock held so here make locking
- * conditional
+ * If event was actually assigned, then mark the counter state as
+ * unused now.
*/
- if (!xl->sched_started)
- raw_spin_lock_irqsave(&excl_cntrs->lock, flags);
+ if (hwc->idx >= 0) {
+ xl = &excl_cntrs->states[tid];
- /*
- * if event was actually assigned, then mark the
- * counter state as unused now
- */
- if (hwc->idx >= 0)
- xlo->state[hwc->idx] = INTEL_EXCL_UNUSED;
+ /*
+ * put_constraint may be called from x86_schedule_events()
+ * which already has the lock held so here make locking
+ * conditional.
+ */
+ if (!xl->sched_started)
+ raw_spin_lock(&excl_cntrs->lock);
+
+ xl->state[hwc->idx] = INTEL_EXCL_UNUSED;
- if (!xl->sched_started)
- raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags);
+ if (!xl->sched_started)
+ raw_spin_unlock(&excl_cntrs->lock);
+ }
}
static void
static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
struct perf_event *event)
{
- struct event_constraint *c = event->hw.constraint;
-
intel_put_shared_regs_event_constraints(cpuc, event);
/*
* all events are subject to and must call the
* put_excl_constraints() routine
*/
- if (c && cpuc->excl_cntrs)
+ if (cpuc->excl_cntrs)
intel_put_excl_constraints(cpuc, event);
-
- /* cleanup dynamic constraint */
- if (c && (c->flags & PERF_X86_EVENT_DYNAMIC))
- event->hw.constraint = NULL;
-}
-
-static void intel_commit_scheduling(struct cpu_hw_events *cpuc,
- struct perf_event *event, int cntr)
-{
- struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
- struct event_constraint *c = event->hw.constraint;
- struct intel_excl_states *xlo, *xl;
- int tid = cpuc->excl_thread_id;
- int o_tid = 1 - tid;
- int is_excl;
-
- if (cpuc->is_fake || !c)
- return;
-
- is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
- if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
- return;
-
- WARN_ON_ONCE(!excl_cntrs);
-
- if (!excl_cntrs)
- return;
-
- xl = &excl_cntrs->states[tid];
- xlo = &excl_cntrs->states[o_tid];
-
- WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock));
-
- if (cntr >= 0) {
- if (is_excl)
- xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE;
- else
- xlo->init_state[cntr] = INTEL_EXCL_SHARED;
- }
}
static void intel_pebs_aliases_core2(struct perf_event *event)
if (ret)
return ret;
- if (event->attr.precise_ip && x86_pmu.pebs_aliases)
- x86_pmu.pebs_aliases(event);
+ if (event->attr.precise_ip) {
+ if (!event->attr.freq) {
+ event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
+ if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS))
+ event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+ }
+ if (x86_pmu.pebs_aliases)
+ x86_pmu.pebs_aliases(event);
+ }
if (needs_branch_stack(event)) {
ret = intel_pmu_setup_lbr_filter(event);
static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
{
struct intel_excl_cntrs *c;
- int i;
c = kzalloc_node(sizeof(struct intel_excl_cntrs),
GFP_KERNEL, cpu_to_node(cpu));
if (c) {
raw_spin_lock_init(&c->lock);
- for (i = 0; i < X86_PMC_IDX_MAX; i++) {
- c->states[0].state[i] = INTEL_EXCL_UNUSED;
- c->states[0].init_state[i] = INTEL_EXCL_UNUSED;
-
- c->states[1].state[i] = INTEL_EXCL_UNUSED;
- c->states[1].init_state[i] = INTEL_EXCL_UNUSED;
- }
c->core_id = -1;
}
return c;
if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
- for_each_cpu(i, topology_thread_cpumask(cpu)) {
+ for_each_cpu(i, topology_sibling_cpumask(cpu)) {
struct intel_shared_regs *pc;
pc = per_cpu(cpu_hw_events, i).shared_regs;
cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
- int h = x86_pmu.num_counters >> 1;
-
- for_each_cpu(i, topology_thread_cpumask(cpu)) {
+ for_each_cpu(i, topology_sibling_cpumask(cpu)) {
struct intel_excl_cntrs *c;
c = per_cpu(cpu_hw_events, i).excl_cntrs;
}
cpuc->excl_cntrs->core_id = core_id;
cpuc->excl_cntrs->refcnt++;
- /*
- * set hard limit to half the number of generic counters
- */
- cpuc->excl_cntrs->states[0].max_alloc_cntrs = h;
- cpuc->excl_cntrs->states[1].max_alloc_cntrs = h;
}
}
fini_debug_store_on_cpu(cpu);
}
+static void intel_pmu_sched_task(struct perf_event_context *ctx,
+ bool sched_in)
+{
+ if (x86_pmu.pebs_active)
+ intel_pmu_pebs_sched_task(ctx, sched_in);
+ if (x86_pmu.lbr_nr)
+ intel_pmu_lbr_sched_task(ctx, sched_in);
+}
+
PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
PMU_FORMAT_ATTR(ldlat, "config1:0-15");
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
.guest_get_msrs = intel_guest_get_msrs,
- .sched_task = intel_pmu_lbr_sched_task,
+ .sched_task = intel_pmu_sched_task,
};
static __init void intel_clovertown_quirk(void)
{
x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED;
- x86_pmu.commit_scheduling = intel_commit_scheduling;
x86_pmu.start_scheduling = intel_start_scheduling;
+ x86_pmu.commit_scheduling = intel_commit_scheduling;
x86_pmu.stop_scheduling = intel_stop_scheduling;
}
case 61: /* 14nm Broadwell Core-M */
case 86: /* 14nm Broadwell Xeon D */
+ case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+ case 79: /* 14nm Broadwell Server */
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
* counter, so do not extend mask to generic counters
*/
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if (c->cmask != FIXED_EVENT_FLAGS
- || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
- continue;
+ if (c->cmask == FIXED_EVENT_FLAGS
+ && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+ c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
}
-
- c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
- c->weight += x86_pmu.num_counters;
+ c->idxmsk64 &=
+ ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+ c->weight = hweight64(c->idxmsk64);
}
}
if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED))
return 0;
- w = cpumask_weight(topology_thread_cpumask(cpu));
+ w = cpumask_weight(topology_sibling_cpumask(cpu));
if (w > 1) {
pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n");
return 0;
x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
- x86_pmu.commit_scheduling = NULL;
x86_pmu.start_scheduling = NULL;
+ x86_pmu.commit_scheduling = NULL;
x86_pmu.stop_scheduling = NULL;
watchdog_nmi_enable_all();
static void bts_event_destroy(struct perf_event *event)
{
+ x86_release_hardware();
x86_del_exclusive(x86_lbr_exclusive_bts);
}
static int bts_event_init(struct perf_event *event)
{
+ int ret;
+
if (event->attr.type != bts_pmu.type)
return -ENOENT;
if (x86_add_exclusive(x86_lbr_exclusive_bts))
return -EBUSY;
+ ret = x86_reserve_hardware();
+ if (ret) {
+ x86_del_exclusive(x86_lbr_exclusive_bts);
+ return ret;
+ }
+
event->destroy = bts_event_destroy;
return 0;
#define MSR_IA32_QM_CTR 0x0c8e
#define MSR_IA32_QM_EVTSEL 0x0c8d
-static unsigned int cqm_max_rmid = -1;
+static u32 cqm_max_rmid = -1;
static unsigned int cqm_l3_scale; /* supposedly cacheline size */
-struct intel_cqm_state {
- raw_spinlock_t lock;
- int rmid;
- int cnt;
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid: The cached Resource Monitoring ID
+ * @closid: The cached Class Of Service ID
+ * @rmid_usecnt: The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+ u32 rmid;
+ u32 closid;
+ int rmid_usecnt;
};
-static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
+/*
+ * The cached intel_pqr_state is strictly per CPU and can never be
+ * updated from a remote CPU. Both functions which modify the state
+ * (intel_cqm_event_start and intel_cqm_event_stop) are called with
+ * interrupts disabled, which is sufficient for the protection.
+ */
+static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
/*
* Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
* near-zero occupancy value, i.e. no cachelines are tagged with this
* RMID, once __intel_cqm_rmid_rotate() returns.
*/
-static unsigned int intel_cqm_rotation_rmid;
+static u32 intel_cqm_rotation_rmid;
#define INVALID_RMID (-1)
* Likewise, an rmid value of -1 is used to indicate "no rmid currently
* assigned" and is used as part of the rotation code.
*/
-static inline bool __rmid_valid(unsigned int rmid)
+static inline bool __rmid_valid(u32 rmid)
{
if (!rmid || rmid == INVALID_RMID)
return false;
return true;
}
-static u64 __rmid_read(unsigned int rmid)
+static u64 __rmid_read(u32 rmid)
{
u64 val;
};
struct cqm_rmid_entry {
- unsigned int rmid;
+ u32 rmid;
enum rmid_recycle_state state;
struct list_head list;
unsigned long queue_time;
*/
static struct cqm_rmid_entry **cqm_rmid_ptrs;
-static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
+static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid)
{
struct cqm_rmid_entry *entry;
*
* We expect to be called with cache_mutex held.
*/
-static int __get_rmid(void)
+static u32 __get_rmid(void)
{
struct cqm_rmid_entry *entry;
return entry->rmid;
}
-static void __put_rmid(unsigned int rmid)
+static void __put_rmid(u32 rmid)
{
struct cqm_rmid_entry *entry;
}
struct rmid_read {
- unsigned int rmid;
+ u32 rmid;
atomic64_t value;
};
/*
* Exchange the RMID of a group of events.
*/
-static unsigned int
-intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid)
+static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
{
struct perf_event *event;
- unsigned int old_rmid = group->hw.cqm_rmid;
struct list_head *head = &group->hw.cqm_group_entry;
+ u32 old_rmid = group->hw.cqm_rmid;
lockdep_assert_held(&cache_mutex);
* If we have group events waiting for an RMID that don't conflict with
* events already running, assign @rmid.
*/
-static bool intel_cqm_sched_in_event(unsigned int rmid)
+static bool intel_cqm_sched_in_event(u32 rmid)
{
struct perf_event *leader, *event;
static void __intel_cqm_pick_and_rotate(struct perf_event *next)
{
struct perf_event *rotor;
- unsigned int rmid;
+ u32 rmid;
lockdep_assert_held(&cache_mutex);
static void intel_cqm_sched_out_conflicting_events(struct perf_event *event)
{
struct perf_event *group, *g;
- unsigned int rmid;
+ u32 rmid;
lockdep_assert_held(&cache_mutex);
struct perf_event **group)
{
struct perf_event *iter;
- unsigned int rmid;
bool conflict = false;
+ u32 rmid;
list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
rmid = iter->hw.cqm_rmid;
static void intel_cqm_event_read(struct perf_event *event)
{
unsigned long flags;
- unsigned int rmid;
+ u32 rmid;
u64 val;
/*
static void intel_cqm_event_start(struct perf_event *event, int mode)
{
- struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
- unsigned int rmid = event->hw.cqm_rmid;
- unsigned long flags;
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+ u32 rmid = event->hw.cqm_rmid;
if (!(event->hw.cqm_state & PERF_HES_STOPPED))
return;
event->hw.cqm_state &= ~PERF_HES_STOPPED;
- raw_spin_lock_irqsave(&state->lock, flags);
-
- if (state->cnt++)
- WARN_ON_ONCE(state->rmid != rmid);
- else
+ if (state->rmid_usecnt++) {
+ if (!WARN_ON_ONCE(state->rmid != rmid))
+ return;
+ } else {
WARN_ON_ONCE(state->rmid);
+ }
state->rmid = rmid;
- wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid);
-
- raw_spin_unlock_irqrestore(&state->lock, flags);
+ wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid);
}
static void intel_cqm_event_stop(struct perf_event *event, int mode)
{
- struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
- unsigned long flags;
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
if (event->hw.cqm_state & PERF_HES_STOPPED)
return;
event->hw.cqm_state |= PERF_HES_STOPPED;
- raw_spin_lock_irqsave(&state->lock, flags);
intel_cqm_event_read(event);
- if (!--state->cnt) {
+ if (!--state->rmid_usecnt) {
state->rmid = 0;
- wrmsrl(MSR_IA32_PQR_ASSOC, 0);
+ wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid);
} else {
WARN_ON_ONCE(!state->rmid);
}
-
- raw_spin_unlock_irqrestore(&state->lock, flags);
}
static int intel_cqm_event_add(struct perf_event *event, int mode)
{
unsigned long flags;
- unsigned int rmid;
+ u32 rmid;
raw_spin_lock_irqsave(&cache_lock, flags);
return 0;
}
-static void intel_cqm_event_del(struct perf_event *event, int mode)
-{
- intel_cqm_event_stop(event, mode);
-}
-
static void intel_cqm_event_destroy(struct perf_event *event)
{
struct perf_event *group_other = NULL;
list_replace(&event->hw.cqm_groups_entry,
&group_other->hw.cqm_groups_entry);
} else {
- unsigned int rmid = event->hw.cqm_rmid;
+ u32 rmid = event->hw.cqm_rmid;
if (__rmid_valid(rmid))
__put_rmid(rmid);
.task_ctx_nr = perf_sw_context,
.event_init = intel_cqm_event_init,
.add = intel_cqm_event_add,
- .del = intel_cqm_event_del,
+ .del = intel_cqm_event_stop,
.start = intel_cqm_event_start,
.stop = intel_cqm_event_stop,
.read = intel_cqm_event_read,
static void intel_cqm_cpu_prepare(unsigned int cpu)
{
- struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
+ struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu);
- raw_spin_lock_init(&state->lock);
state->rmid = 0;
- state->cnt = 0;
+ state->closid = 0;
+ state->rmid_usecnt = 0;
WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
#define BTS_RECORD_SIZE 24
#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE PAGE_SIZE
+#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
#define PEBS_FIXUP_SIZE PAGE_SIZE
/*
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
int node = cpu_to_node(cpu);
- int max, thresh = 1; /* always use a single PEBS record */
+ int max;
void *buffer, *ibuffer;
if (!x86_pmu.pebs)
ds->pebs_absolute_maximum = ds->pebs_buffer_base +
max * x86_pmu.pebs_record_size;
- ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
- thresh * x86_pmu.pebs_record_size;
-
return 0;
}
return 1;
}
+static inline void intel_pmu_drain_pebs_buffer(void)
+{
+ struct pt_regs regs;
+
+ x86_pmu.drain_pebs(®s);
+}
+
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+ if (!sched_in)
+ intel_pmu_drain_pebs_buffer();
+}
+
/*
* PEBS
*/
return &emptyconstraint;
}
+static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+{
+ return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+}
+
void intel_pmu_pebs_enable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
+ struct debug_store *ds = cpuc->ds;
+ bool first_pebs;
+ u64 threshold;
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
+ first_pebs = !pebs_is_enabled(cpuc);
cpuc->pebs_enabled |= 1ULL << hwc->idx;
if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
+
+ /*
+ * When the event is constrained enough we can use a larger
+ * threshold and run the event with less frequent PMI.
+ */
+ if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
+ threshold = ds->pebs_absolute_maximum -
+ x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+
+ if (first_pebs)
+ perf_sched_cb_inc(event->ctx->pmu);
+ } else {
+ threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+
+ /*
+ * If not all events can use larger buffer,
+ * roll back to threshold = 1
+ */
+ if (!first_pebs &&
+ (ds->pebs_interrupt_threshold > threshold))
+ perf_sched_cb_dec(event->ctx->pmu);
+ }
+
+ /* Use auto-reload if possible to save a MSR write in the PMI */
+ if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+ ds->pebs_event_reset[hwc->idx] =
+ (u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+ }
+
+ if (first_pebs || ds->pebs_interrupt_threshold > threshold)
+ ds->pebs_interrupt_threshold = threshold;
}
void intel_pmu_pebs_disable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
+ struct debug_store *ds = cpuc->ds;
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
- if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
- else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST)
+ else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled &= ~(1ULL << 63);
+ if (ds->pebs_interrupt_threshold >
+ ds->pebs_buffer_base + x86_pmu.pebs_record_size) {
+ intel_pmu_drain_pebs_buffer();
+ if (!pebs_is_enabled(cpuc))
+ perf_sched_cb_dec(event->ctx->pmu);
+ }
+
if (cpuc->enabled)
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
return txn;
}
-static void __intel_pmu_pebs_event(struct perf_event *event,
- struct pt_regs *iregs, void *__pebs)
+static void setup_pebs_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
#define PERF_X86_EVENT_PEBS_HSW_PREC \
(PERF_X86_EVENT_PEBS_ST_HSW | \
*/
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_hsw *pebs = __pebs;
- struct perf_sample_data data;
- struct pt_regs regs;
u64 sample_type;
int fll, fst, dsrc;
int fl = event->hw.flags;
- if (!intel_pmu_save_and_restart(event))
+ if (pebs == NULL)
return;
sample_type = event->attr.sample_type;
fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
- perf_sample_data_init(&data, 0, event->hw.last_period);
+ perf_sample_data_init(data, 0, event->hw.last_period);
- data.period = event->hw.last_period;
+ data->period = event->hw.last_period;
/*
* Use latency for weight (only avail with PEBS-LL)
*/
if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
- data.weight = pebs->lat;
+ data->weight = pebs->lat;
/*
* data.data_src encodes the data source
val = precise_datala_hsw(event, pebs->dse);
else if (fst)
val = precise_store_data(pebs->dse);
- data.data_src.val = val;
+ data->data_src.val = val;
}
/*
* PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
* A possible PERF_SAMPLE_REGS will have to transfer all regs.
*/
- regs = *iregs;
- regs.flags = pebs->flags;
- set_linear_ip(®s, pebs->ip);
- regs.bp = pebs->bp;
- regs.sp = pebs->sp;
+ *regs = *iregs;
+ regs->flags = pebs->flags;
+ set_linear_ip(regs, pebs->ip);
+ regs->bp = pebs->bp;
+ regs->sp = pebs->sp;
if (sample_type & PERF_SAMPLE_REGS_INTR) {
- regs.ax = pebs->ax;
- regs.bx = pebs->bx;
- regs.cx = pebs->cx;
- regs.dx = pebs->dx;
- regs.si = pebs->si;
- regs.di = pebs->di;
- regs.bp = pebs->bp;
- regs.sp = pebs->sp;
-
- regs.flags = pebs->flags;
+ regs->ax = pebs->ax;
+ regs->bx = pebs->bx;
+ regs->cx = pebs->cx;
+ regs->dx = pebs->dx;
+ regs->si = pebs->si;
+ regs->di = pebs->di;
+ regs->bp = pebs->bp;
+ regs->sp = pebs->sp;
+
+ regs->flags = pebs->flags;
#ifndef CONFIG_X86_32
- regs.r8 = pebs->r8;
- regs.r9 = pebs->r9;
- regs.r10 = pebs->r10;
- regs.r11 = pebs->r11;
- regs.r12 = pebs->r12;
- regs.r13 = pebs->r13;
- regs.r14 = pebs->r14;
- regs.r15 = pebs->r15;
+ regs->r8 = pebs->r8;
+ regs->r9 = pebs->r9;
+ regs->r10 = pebs->r10;
+ regs->r11 = pebs->r11;
+ regs->r12 = pebs->r12;
+ regs->r13 = pebs->r13;
+ regs->r14 = pebs->r14;
+ regs->r15 = pebs->r15;
#endif
}
if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
- regs.ip = pebs->real_ip;
- regs.flags |= PERF_EFLAGS_EXACT;
- } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s))
- regs.flags |= PERF_EFLAGS_EXACT;
+ regs->ip = pebs->real_ip;
+ regs->flags |= PERF_EFLAGS_EXACT;
+ } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
+ regs->flags |= PERF_EFLAGS_EXACT;
else
- regs.flags &= ~PERF_EFLAGS_EXACT;
+ regs->flags &= ~PERF_EFLAGS_EXACT;
if ((sample_type & PERF_SAMPLE_ADDR) &&
x86_pmu.intel_cap.pebs_format >= 1)
- data.addr = pebs->dla;
+ data->addr = pebs->dla;
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
- data.weight = intel_hsw_weight(pebs);
+ data->weight = intel_hsw_weight(pebs);
if (sample_type & PERF_SAMPLE_TRANSACTION)
- data.txn = intel_hsw_transaction(pebs);
+ data->txn = intel_hsw_transaction(pebs);
}
if (has_branch_stack(event))
- data.br_stack = &cpuc->lbr_stack;
+ data->br_stack = &cpuc->lbr_stack;
+}
+
+static inline void *
+get_next_pebs_record_by_bit(void *base, void *top, int bit)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ void *at;
+ u64 pebs_status;
+
+ if (base == NULL)
+ return NULL;
+
+ for (at = base; at < top; at += x86_pmu.pebs_record_size) {
+ struct pebs_record_nhm *p = at;
- if (perf_event_overflow(event, &data, ®s))
+ if (test_bit(bit, (unsigned long *)&p->status)) {
+ /* PEBS v3 has accurate status bits */
+ if (x86_pmu.intel_cap.pebs_format >= 3)
+ return at;
+
+ if (p->status == (1 << bit))
+ return at;
+
+ /* clear non-PEBS bit and re-check */
+ pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+ if (pebs_status == (1 << bit))
+ return at;
+ }
+ }
+ return NULL;
+}
+
+static void __intel_pmu_pebs_event(struct perf_event *event,
+ struct pt_regs *iregs,
+ void *base, void *top,
+ int bit, int count)
+{
+ struct perf_sample_data data;
+ struct pt_regs regs;
+ void *at = get_next_pebs_record_by_bit(base, top, bit);
+
+ if (!intel_pmu_save_and_restart(event) &&
+ !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD))
+ return;
+
+ while (count > 1) {
+ setup_pebs_sample_data(event, iregs, at, &data, ®s);
+ perf_event_output(event, &data, ®s);
+ at += x86_pmu.pebs_record_size;
+ at = get_next_pebs_record_by_bit(at, top, bit);
+ count--;
+ }
+
+ setup_pebs_sample_data(event, iregs, at, &data, ®s);
+
+ /*
+ * All but the last records are processed.
+ * The last one is left to be able to call the overflow handler.
+ */
+ if (perf_event_overflow(event, &data, ®s)) {
x86_pmu_stop(event, 0);
+ return;
+ }
+
}
static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
if (!event->attr.precise_ip)
return;
- n = top - at;
+ n = (top - at) / x86_pmu.pebs_record_size;
if (n <= 0)
return;
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(n > 1, "bad leftover pebs %d\n", n);
- at += n - 1;
-
- __intel_pmu_pebs_event(event, iregs, at);
+ __intel_pmu_pebs_event(event, iregs, at, top, 0, n);
}
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
- struct perf_event *event = NULL;
- void *at, *top;
- u64 status = 0;
- int bit;
+ struct perf_event *event;
+ void *base, *at, *top;
+ short counts[MAX_PEBS_EVENTS] = {};
+ short error[MAX_PEBS_EVENTS] = {};
+ int bit, i;
if (!x86_pmu.pebs_active)
return;
- at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+ base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
ds->pebs_index = ds->pebs_buffer_base;
- if (unlikely(at > top))
+ if (unlikely(base >= top))
return;
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
- "Unexpected number of pebs records %ld\n",
- (long)(top - at) / x86_pmu.pebs_record_size);
-
- for (; at < top; at += x86_pmu.pebs_record_size) {
+ for (at = base; at < top; at += x86_pmu.pebs_record_size) {
struct pebs_record_nhm *p = at;
- for_each_set_bit(bit, (unsigned long *)&p->status,
- x86_pmu.max_pebs_events) {
- event = cpuc->events[bit];
- if (!test_bit(bit, cpuc->active_mask))
- continue;
-
- WARN_ON_ONCE(!event);
+ /* PEBS v3 has accurate status bits */
+ if (x86_pmu.intel_cap.pebs_format >= 3) {
+ for_each_set_bit(bit, (unsigned long *)&p->status,
+ MAX_PEBS_EVENTS)
+ counts[bit]++;
- if (!event->attr.precise_ip)
- continue;
+ continue;
+ }
- if (__test_and_set_bit(bit, (unsigned long *)&status))
+ bit = find_first_bit((unsigned long *)&p->status,
+ x86_pmu.max_pebs_events);
+ if (bit >= x86_pmu.max_pebs_events)
+ continue;
+ if (!test_bit(bit, cpuc->active_mask))
+ continue;
+ /*
+ * The PEBS hardware does not deal well with the situation
+ * when events happen near to each other and multiple bits
+ * are set. But it should happen rarely.
+ *
+ * If these events include one PEBS and multiple non-PEBS
+ * events, it doesn't impact PEBS record. The record will
+ * be handled normally. (slow path)
+ *
+ * If these events include two or more PEBS events, the
+ * records for the events can be collapsed into a single
+ * one, and it's not possible to reconstruct all events
+ * that caused the PEBS record. It's called collision.
+ * If collision happened, the record will be dropped.
+ *
+ */
+ if (p->status != (1 << bit)) {
+ u64 pebs_status;
+
+ /* slow path */
+ pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+ if (pebs_status != (1 << bit)) {
+ for_each_set_bit(i, (unsigned long *)&pebs_status,
+ MAX_PEBS_EVENTS)
+ error[i]++;
continue;
-
- break;
+ }
}
+ counts[bit]++;
+ }
- if (!event || bit >= x86_pmu.max_pebs_events)
+ for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+ if ((counts[bit] == 0) && (error[bit] == 0))
continue;
+ event = cpuc->events[bit];
+ WARN_ON_ONCE(!event);
+ WARN_ON_ONCE(!event->attr.precise_ip);
- __intel_pmu_pebs_event(event, iregs, at);
+ /* log dropped samples number */
+ if (error[bit])
+ perf_log_lost_samples(event, error[bit]);
+
+ if (counts[bit]) {
+ __intel_pmu_pebs_event(event, iregs, base,
+ top, bit, counts[bit]);
+ }
}
}
X86_BR_NO_TX = 1 << 14,/* not in transaction */
X86_BR_ZERO_CALL = 1 << 15,/* zero length call */
X86_BR_CALL_STACK = 1 << 16,/* call stack */
+ X86_BR_IND_JMP = 1 << 17,/* indirect jump */
};
#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
X86_BR_IRQ |\
X86_BR_ABORT |\
X86_BR_IND_CALL |\
+ X86_BR_IND_JMP |\
X86_BR_ZERO_CALL)
#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct x86_perf_task_context *task_ctx;
- if (!x86_pmu.lbr_nr)
- return;
-
/*
* If LBR callstack feature is enabled and the stack was saved when
* the task was scheduled out, restore the stack. Otherwise flush
X86_BR_CALL_STACK;
}
+ if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
+ mask |= X86_BR_IND_JMP;
+
/*
* stash actual user request into reg, it may
* be used by fixup code for some CPU
break;
case 4:
case 5:
- ret = X86_BR_JMP;
+ ret = X86_BR_IND_JMP;
break;
}
break;
*/
[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC,
+ [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
};
static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
| LBR_FAR,
[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL,
[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC,
+ [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
};
static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC,
[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL
| LBR_RETURN | LBR_CALL_STACK,
+ [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
};
/* core */
de_attr->attr.attr.name = pt_caps[i].name;
- sysfs_attr_init(&de_attrs->attr.attr);
+ sysfs_attr_init(&de_attr->attr.attr);
de_attr->attr.attr.mode = S_IRUGO;
de_attr->attr.show = pt_cap_show;
* These all are cpu affine and operate on a local PT
*/
-static bool pt_is_running(void)
-{
- u64 ctl;
-
- rdmsrl(MSR_IA32_RTIT_CTL, ctl);
-
- return !!(ctl & RTIT_CTL_TRACEEN);
-}
-
static void pt_config(struct perf_event *event)
{
u64 reg;
* @handle: Current output handle.
*
* Place INT and STOP marks to prevent overwriting old data that the consumer
- * hasn't yet collected.
+ * hasn't yet collected and waking up the consumer after a certain fraction of
+ * the buffer has filled up. Only needed and sensible for non-snapshot counters.
+ *
+ * This obviously relies on buf::head to figure out buffer markers, so it has
+ * to be called after pt_buffer_reset_offsets() and before the hardware tracing
+ * is enabled.
*/
static int pt_buffer_reset_markers(struct pt_buffer *buf,
struct perf_output_handle *handle)
{
- unsigned long idx, npages, end;
-
- if (buf->snapshot)
- return 0;
+ unsigned long head = local64_read(&buf->head);
+ unsigned long idx, npages, wakeup;
/* can't stop in the middle of an output region */
if (buf->output_off + handle->size + 1 <
buf->topa_index[buf->stop_pos]->stop = 0;
buf->topa_index[buf->intr_pos]->intr = 0;
- if (pt_cap_get(PT_CAP_topa_multiple_entries)) {
- npages = (handle->size + 1) >> PAGE_SHIFT;
- end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages;
- /*if (end > handle->wakeup >> PAGE_SHIFT)
- end = handle->wakeup >> PAGE_SHIFT;*/
- idx = end & (buf->nr_pages - 1);
- buf->stop_pos = idx;
- idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1;
- idx &= buf->nr_pages - 1;
- buf->intr_pos = idx;
- }
+ /* how many pages till the STOP marker */
+ npages = handle->size >> PAGE_SHIFT;
+
+ /* if it's on a page boundary, fill up one more page */
+ if (!offset_in_page(head + handle->size + 1))
+ npages++;
+
+ idx = (head >> PAGE_SHIFT) + npages;
+ idx &= buf->nr_pages - 1;
+ buf->stop_pos = idx;
+
+ wakeup = handle->wakeup >> PAGE_SHIFT;
+
+ /* in the worst case, wake up the consumer one page before hard stop */
+ idx = (head >> PAGE_SHIFT) + npages - 1;
+ if (idx > wakeup)
+ idx = wakeup;
+
+ idx &= buf->nr_pages - 1;
+ buf->intr_pos = idx;
buf->topa_index[buf->stop_pos]->stop = 1;
buf->topa_index[buf->intr_pos]->intr = 1;
struct topa *cur = buf->first, *prev = buf->last;
struct topa_entry *te_cur = TOPA_ENTRY(cur, 0),
*te_prev = TOPA_ENTRY(prev, prev->last - 1);
- int pg = 0, idx = 0, ntopa = 0;
+ int pg = 0, idx = 0;
while (pg < buf->nr_pages) {
int tidx;
/* advance to next topa table */
idx = 0;
cur = list_entry(cur->list.next, struct topa, list);
- ntopa++;
- } else
+ } else {
idx++;
+ }
te_cur = TOPA_ENTRY(cur, idx);
}
* @head: Write pointer (aux_head) from AUX buffer.
*
* Find the ToPA table and entry corresponding to given @head and set buffer's
- * "current" pointers accordingly.
+ * "current" pointers accordingly. This is done after we have obtained the
+ * current aux_head position from a successful call to perf_aux_output_begin()
+ * to make sure the hardware is writing to the right place.
+ *
+ * This function modifies buf::{cur,cur_idx,output_off} that will be programmed
+ * into PT msrs when the tracing is enabled and buf::head and buf::data_size,
+ * which are used to determine INT and STOP markers' locations by a subsequent
+ * call to pt_buffer_reset_markers().
*/
static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
{
}
pt_buffer_reset_offsets(buf, pt->handle.head);
+ /* snapshot counters don't use PMI, so it's safe */
ret = pt_buffer_reset_markers(buf, &pt->handle);
if (ret) {
perf_aux_output_end(&pt->handle, 0, true);
struct pt *pt = this_cpu_ptr(&pt_ctx);
struct pt_buffer *buf = perf_get_aux(&pt->handle);
- if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) {
+ if (!buf || pt_buffer_is_full(buf, pt)) {
event->hw.state = PERF_HES_STOPPED;
return;
}
event->hw.state = PERF_HES_STOPPED;
if (mode & PERF_EF_UPDATE) {
- struct pt *pt = this_cpu_ptr(&pt_ctx);
struct pt_buffer *buf = perf_get_aux(&pt->handle);
if (!buf)
static void rapl_start_hrtimer(struct rapl_pmu *pmu)
{
- __hrtimer_start_range_ns(&pmu->hrtimer,
- pmu->timer_interval, 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&pmu->hrtimer, pmu->timer_interval,
+ HRTIMER_MODE_REL_PINNED);
}
static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
break;
case 60: /* Haswell */
case 69: /* Haswell-Celeron */
+ case 61: /* Broadwell */
rapl_cntr_mask = RAPL_IDX_HSW;
rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
break;
void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
{
- __hrtimer_start_range_ns(&box->hrtimer,
- ns_to_ktime(box->hrtimer_duration), 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
+ HRTIMER_MODE_REL_PINNED);
}
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
- hwc = &box->event_list[i]->hw;
c = uncore_get_event_constraint(box, box->event_list[i]);
- hwc->constraint = c;
+ box->event_constraint[i] = c;
wmin = min(wmin, c->weight);
wmax = max(wmax, c->weight);
}
/* fastpath, try to reuse previous register */
for (i = 0; i < n; i++) {
hwc = &box->event_list[i]->hw;
- c = hwc->constraint;
+ c = box->event_constraint[i];
/* never assigned */
if (hwc->idx == -1)
}
/* slow path */
if (i != n)
- ret = perf_assign_events(box->event_list, n,
- wmin, wmax, assign);
+ ret = perf_assign_events(box->event_constraint, n,
+ wmin, wmax, n, assign);
if (!assign || ret) {
for (i = 0; i < n; i++)
box->phys_id = phys_id;
box->pci_dev = pdev;
box->pmu = pmu;
+ uncore_box_init(box);
pci_set_drvdata(pdev, box);
raw_spin_lock(&uncore_box_lock);
case 69: /* Haswell Celeron */
ret = hsw_uncore_pci_init();
break;
+ case 61: /* Broadwell */
+ ret = bdw_uncore_pci_init();
+ break;
default:
return 0;
}
pmu = &type->pmus[j];
box = *per_cpu_ptr(pmu->box, cpu);
/* called by uncore_cpu_init? */
- if (box && box->phys_id >= 0)
+ if (box && box->phys_id >= 0) {
+ uncore_box_init(box);
continue;
+ }
for_each_online_cpu(k) {
exist = *per_cpu_ptr(pmu->box, k);
}
}
- if (box)
+ if (box) {
box->phys_id = phys_id;
+ uncore_box_init(box);
+ }
}
}
return 0;
atomic_t refcnt;
struct perf_event *events[UNCORE_PMC_IDX_MAX];
struct perf_event *event_list[UNCORE_PMC_IDX_MAX];
+ struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX];
unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
u64 tags[UNCORE_PMC_IDX_MAX];
struct pci_dev *pci_dev;
return box->pmu->type->num_counters;
}
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
- if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
- if (box->pmu->type->ops->init_box)
- box->pmu->type->ops->init_box(box);
- }
-}
-
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
static inline void uncore_enable_box(struct intel_uncore_box *box)
{
- uncore_box_init(box);
-
if (box->pmu->type->ops->enable_box)
box->pmu->type->ops->enable_box(box);
}
return box->pmu->type->ops->read_counter(box, event);
}
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+ if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+ if (box->pmu->type->ops->init_box)
+ box->pmu->type->ops->init_box(box);
+ }
+}
+
static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
{
return (box->phys_id < 0);
int snb_uncore_pci_init(void);
int ivb_uncore_pci_init(void);
int hsw_uncore_pci_init(void);
+int bdw_uncore_pci_init(void);
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
{ /* end: all zeroes */ },
};
+static const struct pci_device_id bdw_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
.id_table = hsw_uncore_pci_ids,
};
+static struct pci_driver bdw_uncore_pci_driver = {
+ .name = "bdw_uncore",
+ .id_table = bdw_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */
IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */
+ IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */
{ /* end marker */ }
};
return imc_uncore_pci_init();
}
+int bdw_uncore_pci_init(void)
+{
+ return imc_uncore_pci_init();
+}
+
/* end of Sandy Bridge uncore support */
/* Nehalem uncore support */
((1ULL << (n)) - 1)))
/* Haswell-EP Ubox */
-#define HSWEP_U_MSR_PMON_CTR0 0x705
-#define HSWEP_U_MSR_PMON_CTL0 0x709
+#define HSWEP_U_MSR_PMON_CTR0 0x709
+#define HSWEP_U_MSR_PMON_CTL0 0x705
#define HSWEP_U_MSR_PMON_FILTER 0x707
#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL 0x703
.name = "cbox",
.num_counters = 4,
.num_boxes = 18,
- .perf_ctr_bits = 44,
+ .perf_ctr_bits = 48,
.event_ctl = HSWEP_C0_MSR_PMON_CTL0,
.perf_ctr = HSWEP_C0_MSR_PMON_CTR0,
.event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
{
#ifdef CONFIG_SMP
seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
- seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu)));
+ seq_printf(m, "siblings\t: %d\n",
+ cpumask_weight(topology_core_cpumask(cpu)));
seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
seq_printf(m, "apicid\t\t: %d\n", c->apicid);
#include <linux/elfcore.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
#include <asm/processor.h>
#include <asm/hardirq.h>
#include <linux/bootmem.h>
#include <linux/export.h>
#include <linux/io.h>
-#include <linux/irqdomain.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/of.h>
#include <linux/of_pci.h>
#include <linux/initrd.h>
+#include <asm/irqdomain.h>
#include <asm/hpet.h>
#include <asm/apic.h>
#include <asm/pci_x86.h>
},
};
-static int ioapic_xlate(struct irq_domain *domain,
- struct device_node *controller,
- const u32 *intspec, u32 intsize,
- irq_hw_number_t *out_hwirq, u32 *out_type)
+static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
+ struct of_phandle_args *irq_data = (void *)arg;
struct of_ioapic_type *it;
- u32 line, idx, gsi;
+ struct irq_alloc_info tmp;
- if (WARN_ON(intsize < 2))
+ if (WARN_ON(irq_data->args_count < 2))
return -EINVAL;
-
- line = intspec[0];
-
- if (intspec[1] >= ARRAY_SIZE(of_ioapic_type))
+ if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type))
return -EINVAL;
- it = &of_ioapic_type[intspec[1]];
+ it = &of_ioapic_type[irq_data->args[1]];
+ ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity);
+ tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
+ tmp.ioapic_pin = irq_data->args[0];
- idx = (u32)(long)domain->host_data;
- gsi = mp_pin_to_gsi(idx, line);
- if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0)))
- return -EBUSY;
-
- *out_hwirq = line;
- *out_type = it->out_type;
- return 0;
+ return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp);
}
-const struct irq_domain_ops ioapic_irq_domain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
- .xlate = ioapic_xlate,
+static const struct irq_domain_ops ioapic_irq_domain_ops = {
+ .alloc = dt_irqdomain_alloc,
+ .free = mp_irqdomain_free,
+ .activate = mp_irqdomain_activate,
+ .deactivate = mp_irqdomain_deactivate,
};
static void __init dtb_add_ioapic(struct device_node *dn)
{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
QFLAG_APPLY_ONCE, intel_graphics_stolen },
/*
- * HPET on current version of Baytrail platform has accuracy
- * problems, disable it for now:
+ * HPET on the current version of the Baytrail platform has accuracy
+ * problems: it will halt in deep idle state - so we disable it.
+ *
+ * More details can be found in section 18.10.1.3 of the datasheet:
+ *
+ * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/atom-z8000-datasheet-vol-1.pdf
*/
{ PCI_VENDOR_ID_INTEL, 0x0f00,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+++ /dev/null
-/*
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
-
-/*
- * entry.S contains the system-call and fault low-level handling routines.
- * This also contains the timer-interrupt handler, as well as all interrupts
- * and faults that can result in a task-switch.
- *
- * NOTE: This code handles signal-recognition, which happens every time
- * after a timer-interrupt and after each system call.
- *
- * I changed all the .align's to 4 (16 byte alignment), as that's faster
- * on a 486.
- *
- * Stack layout in 'syscall_exit':
- * ptrace needs to have all regs on the stack.
- * if the order here is changed, it needs to be
- * updated in fork.c:copy_process, signal.c:do_signal,
- * ptrace.c and ptrace.h
- *
- * 0(%esp) - %ebx
- * 4(%esp) - %ecx
- * 8(%esp) - %edx
- * C(%esp) - %esi
- * 10(%esp) - %edi
- * 14(%esp) - %ebp
- * 18(%esp) - %eax
- * 1C(%esp) - %ds
- * 20(%esp) - %es
- * 24(%esp) - %fs
- * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
- * 2C(%esp) - orig_eax
- * 30(%esp) - %eip
- * 34(%esp) - %cs
- * 38(%esp) - %eflags
- * 3C(%esp) - %oldesp
- * 40(%esp) - %oldss
- *
- * "current" is in register %ebx during any slow entries.
- */
-
-#include <linux/linkage.h>
-#include <linux/err.h>
-#include <asm/thread_info.h>
-#include <asm/irqflags.h>
-#include <asm/errno.h>
-#include <asm/segment.h>
-#include <asm/smp.h>
-#include <asm/page_types.h>
-#include <asm/percpu.h>
-#include <asm/dwarf2.h>
-#include <asm/processor-flags.h>
-#include <asm/ftrace.h>
-#include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
-#include <asm/alternative-asm.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE 0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysenter_audit syscall_trace_entry
-#define sysexit_audit syscall_exit_work
-#endif
-
- .section .entry.text, "ax"
-
-/*
- * We use macros for low-level operations which need to be overridden
- * for paravirtualization. The following will never clobber any registers:
- * INTERRUPT_RETURN (aka. "iret")
- * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
- * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
- *
- * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
- * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
- * Allowing a register to be clobbered can shrink the paravirt replacement
- * enough to patch inline, increasing performance.
- */
-
-#ifdef CONFIG_PREEMPT
-#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
-#else
-#define preempt_stop(clobbers)
-#define resume_kernel restore_all
-#endif
-
-.macro TRACE_IRQS_IRET
-#ifdef CONFIG_TRACE_IRQFLAGS
- testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off?
- jz 1f
- TRACE_IRQS_ON
-1:
-#endif
-.endm
-
-/*
- * User gs save/restore
- *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc. Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
- */
-#ifdef CONFIG_X86_32_LAZY_GS
-
- /* unfortunately push/pop can't be no-op */
-.macro PUSH_GS
- pushl_cfi $0
-.endm
-.macro POP_GS pop=0
- addl $(4 + \pop), %esp
- CFI_ADJUST_CFA_OFFSET -(4 + \pop)
-.endm
-.macro POP_GS_EX
-.endm
-
- /* all the rest are no-op */
-.macro PTGS_TO_GS
-.endm
-.macro PTGS_TO_GS_EX
-.endm
-.macro GS_TO_REG reg
-.endm
-.macro REG_TO_PTGS reg
-.endm
-.macro SET_KERNEL_GS reg
-.endm
-
-#else /* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
- pushl_cfi %gs
- /*CFI_REL_OFFSET gs, 0*/
-.endm
-
-.macro POP_GS pop=0
-98: popl_cfi %gs
- /*CFI_RESTORE gs*/
- .if \pop <> 0
- add $\pop, %esp
- CFI_ADJUST_CFA_OFFSET -\pop
- .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99: movl $0, (%esp)
- jmp 98b
-.popsection
- _ASM_EXTABLE(98b,99b)
-.endm
-
-.macro PTGS_TO_GS
-98: mov PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99: movl $0, PT_GS(%esp)
- jmp 98b
-.popsection
- _ASM_EXTABLE(98b,99b)
-.endm
-
-.macro GS_TO_REG reg
- movl %gs, \reg
- /*CFI_REGISTER gs, \reg*/
-.endm
-.macro REG_TO_PTGS reg
- movl \reg, PT_GS(%esp)
- /*CFI_REL_OFFSET gs, PT_GS*/
-.endm
-.macro SET_KERNEL_GS reg
- movl $(__KERNEL_STACK_CANARY), \reg
- movl \reg, %gs
-.endm
-
-#endif /* CONFIG_X86_32_LAZY_GS */
-
-.macro SAVE_ALL
- cld
- PUSH_GS
- pushl_cfi %fs
- /*CFI_REL_OFFSET fs, 0;*/
- pushl_cfi %es
- /*CFI_REL_OFFSET es, 0;*/
- pushl_cfi %ds
- /*CFI_REL_OFFSET ds, 0;*/
- pushl_cfi %eax
- CFI_REL_OFFSET eax, 0
- pushl_cfi %ebp
- CFI_REL_OFFSET ebp, 0
- pushl_cfi %edi
- CFI_REL_OFFSET edi, 0
- pushl_cfi %esi
- CFI_REL_OFFSET esi, 0
- pushl_cfi %edx
- CFI_REL_OFFSET edx, 0
- pushl_cfi %ecx
- CFI_REL_OFFSET ecx, 0
- pushl_cfi %ebx
- CFI_REL_OFFSET ebx, 0
- movl $(__USER_DS), %edx
- movl %edx, %ds
- movl %edx, %es
- movl $(__KERNEL_PERCPU), %edx
- movl %edx, %fs
- SET_KERNEL_GS %edx
-.endm
-
-.macro RESTORE_INT_REGS
- popl_cfi %ebx
- CFI_RESTORE ebx
- popl_cfi %ecx
- CFI_RESTORE ecx
- popl_cfi %edx
- CFI_RESTORE edx
- popl_cfi %esi
- CFI_RESTORE esi
- popl_cfi %edi
- CFI_RESTORE edi
- popl_cfi %ebp
- CFI_RESTORE ebp
- popl_cfi %eax
- CFI_RESTORE eax
-.endm
-
-.macro RESTORE_REGS pop=0
- RESTORE_INT_REGS
-1: popl_cfi %ds
- /*CFI_RESTORE ds;*/
-2: popl_cfi %es
- /*CFI_RESTORE es;*/
-3: popl_cfi %fs
- /*CFI_RESTORE fs;*/
- POP_GS \pop
-.pushsection .fixup, "ax"
-4: movl $0, (%esp)
- jmp 1b
-5: movl $0, (%esp)
- jmp 2b
-6: movl $0, (%esp)
- jmp 3b
-.popsection
- _ASM_EXTABLE(1b,4b)
- _ASM_EXTABLE(2b,5b)
- _ASM_EXTABLE(3b,6b)
- POP_GS_EX
-.endm
-
-.macro RING0_INT_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 3*4
- /*CFI_OFFSET cs, -2*4;*/
- CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_EC_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 4*4
- /*CFI_OFFSET cs, -2*4;*/
- CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_PTREGS_FRAME
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, PT_OLDESP-PT_EBX
- /*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/
- CFI_OFFSET eip, PT_EIP-PT_OLDESP
- /*CFI_OFFSET es, PT_ES-PT_OLDESP;*/
- /*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/
- CFI_OFFSET eax, PT_EAX-PT_OLDESP
- CFI_OFFSET ebp, PT_EBP-PT_OLDESP
- CFI_OFFSET edi, PT_EDI-PT_OLDESP
- CFI_OFFSET esi, PT_ESI-PT_OLDESP
- CFI_OFFSET edx, PT_EDX-PT_OLDESP
- CFI_OFFSET ecx, PT_ECX-PT_OLDESP
- CFI_OFFSET ebx, PT_EBX-PT_OLDESP
-.endm
-
-ENTRY(ret_from_fork)
- CFI_STARTPROC
- pushl_cfi %eax
- call schedule_tail
- GET_THREAD_INFO(%ebp)
- popl_cfi %eax
- pushl_cfi $0x0202 # Reset kernel eflags
- popfl_cfi
- jmp syscall_exit
- CFI_ENDPROC
-END(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
- CFI_STARTPROC
- pushl_cfi %eax
- call schedule_tail
- GET_THREAD_INFO(%ebp)
- popl_cfi %eax
- pushl_cfi $0x0202 # Reset kernel eflags
- popfl_cfi
- movl PT_EBP(%esp),%eax
- call *PT_EBX(%esp)
- movl $0,PT_EAX(%esp)
- jmp syscall_exit
- CFI_ENDPROC
-ENDPROC(ret_from_kernel_thread)
-
-/*
- * Return to user mode is not as complex as all this looks,
- * but we want the default path for a system call return to
- * go as quickly as possible which is why some of this is
- * less clear than it otherwise should be.
- */
-
- # userspace resumption stub bypassing syscall exit tracing
- ALIGN
- RING0_PTREGS_FRAME
-ret_from_exception:
- preempt_stop(CLBR_ANY)
-ret_from_intr:
- GET_THREAD_INFO(%ebp)
-#ifdef CONFIG_VM86
- movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
- movb PT_CS(%esp), %al
- andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
-#else
- /*
- * We can be coming here from child spawned by kernel_thread().
- */
- movl PT_CS(%esp), %eax
- andl $SEGMENT_RPL_MASK, %eax
-#endif
- cmpl $USER_RPL, %eax
- jb resume_kernel # not returning to v8086 or userspace
-
-ENTRY(resume_userspace)
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- andl $_TIF_WORK_MASK, %ecx # is there any work to be done on
- # int/exception return?
- jne work_pending
- jmp restore_all
-END(ret_from_exception)
-
-#ifdef CONFIG_PREEMPT
-ENTRY(resume_kernel)
- DISABLE_INTERRUPTS(CLBR_ANY)
-need_resched:
- cmpl $0,PER_CPU_VAR(__preempt_count)
- jnz restore_all
- testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ?
- jz restore_all
- call preempt_schedule_irq
- jmp need_resched
-END(resume_kernel)
-#endif
- CFI_ENDPROC
-
-/* SYSENTER_RETURN points to after the "sysenter" instruction in
- the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */
-
- # sysenter call handler stub
-ENTRY(ia32_sysenter_target)
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA esp, 0
- CFI_REGISTER esp, ebp
- movl TSS_sysenter_sp0(%esp),%esp
-sysenter_past_esp:
- /*
- * Interrupts are disabled here, but we can't trace it until
- * enough kernel state to call TRACE_IRQS_OFF can be called - but
- * we immediately enable interrupts at that point anyway.
- */
- pushl_cfi $__USER_DS
- /*CFI_REL_OFFSET ss, 0*/
- pushl_cfi %ebp
- CFI_REL_OFFSET esp, 0
- pushfl_cfi
- orl $X86_EFLAGS_IF, (%esp)
- pushl_cfi $__USER_CS
- /*CFI_REL_OFFSET cs, 0*/
- /*
- * Push current_thread_info()->sysenter_return to the stack.
- * A tiny bit of offset fixup is necessary: TI_sysenter_return
- * is relative to thread_info, which is at the bottom of the
- * kernel stack page. 4*4 means the 4 words pushed above;
- * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
- * and THREAD_SIZE takes us to the bottom.
- */
- pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
- CFI_REL_OFFSET eip, 0
-
- pushl_cfi %eax
- SAVE_ALL
- ENABLE_INTERRUPTS(CLBR_NONE)
-
-/*
- * Load the potential sixth argument from user stack.
- * Careful about security.
- */
- cmpl $__PAGE_OFFSET-3,%ebp
- jae syscall_fault
- ASM_STAC
-1: movl (%ebp),%ebp
- ASM_CLAC
- movl %ebp,PT_EBP(%esp)
- _ASM_EXTABLE(1b,syscall_fault)
-
- GET_THREAD_INFO(%ebp)
-
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
- jnz sysenter_audit
-sysenter_do_call:
- cmpl $(NR_syscalls), %eax
- jae sysenter_badsys
- call *sys_call_table(,%eax,4)
-sysenter_after_call:
- movl %eax,PT_EAX(%esp)
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $_TIF_ALLWORK_MASK, %ecx
- jnz sysexit_audit
-sysenter_exit:
-/* if something modifies registers it must also disable sysexit */
- movl PT_EIP(%esp), %edx
- movl PT_OLDESP(%esp), %ecx
- xorl %ebp,%ebp
- TRACE_IRQS_ON
-1: mov PT_FS(%esp), %fs
- PTGS_TO_GS
- ENABLE_INTERRUPTS_SYSEXIT
-
-#ifdef CONFIG_AUDITSYSCALL
-sysenter_audit:
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
- jnz syscall_trace_entry
- /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
- movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */
- /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
- pushl_cfi PT_ESI(%esp) /* a3: 5th arg */
- pushl_cfi PT_EDX+4(%esp) /* a2: 4th arg */
- call __audit_syscall_entry
- popl_cfi %ecx /* get that remapped edx off the stack */
- popl_cfi %ecx /* get that remapped esi off the stack */
- movl PT_EAX(%esp),%eax /* reload syscall number */
- jmp sysenter_do_call
-
-sysexit_audit:
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
- jnz syscall_exit_work
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_ANY)
- movl %eax,%edx /* second arg, syscall return value */
- cmpl $-MAX_ERRNO,%eax /* is it an error ? */
- setbe %al /* 1 if so, 0 if not */
- movzbl %al,%eax /* zero-extend that */
- call __audit_syscall_exit
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
- jnz syscall_exit_work
- movl PT_EAX(%esp),%eax /* reload syscall return value */
- jmp sysenter_exit
-#endif
-
- CFI_ENDPROC
-.pushsection .fixup,"ax"
-2: movl $0,PT_FS(%esp)
- jmp 1b
-.popsection
- _ASM_EXTABLE(1b,2b)
- PTGS_TO_GS_EX
-ENDPROC(ia32_sysenter_target)
-
- # system call handler stub
-ENTRY(system_call)
- RING0_INT_FRAME # can't unwind into user space anyway
- ASM_CLAC
- pushl_cfi %eax # save orig_eax
- SAVE_ALL
- GET_THREAD_INFO(%ebp)
- # system call tracing in operation / emulation
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
- jnz syscall_trace_entry
- cmpl $(NR_syscalls), %eax
- jae syscall_badsys
-syscall_call:
- call *sys_call_table(,%eax,4)
-syscall_after_call:
- movl %eax,PT_EAX(%esp) # store the return value
-syscall_exit:
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $_TIF_ALLWORK_MASK, %ecx # current->work
- jnz syscall_exit_work
-
-restore_all:
- TRACE_IRQS_IRET
-restore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
- movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
- # Warning: PT_OLDSS(%esp) contains the wrong/random values if we
- # are returning to the kernel.
- # See comments in process.c:copy_thread() for details.
- movb PT_OLDSS(%esp), %ah
- movb PT_CS(%esp), %al
- andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
- cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
- CFI_REMEMBER_STATE
- je ldt_ss # returning to user-space with LDT SS
-#endif
-restore_nocheck:
- RESTORE_REGS 4 # skip orig_eax/error_code
-irq_return:
- INTERRUPT_RETURN
-.section .fixup,"ax"
-ENTRY(iret_exc)
- pushl $0 # no error code
- pushl $do_iret_error
- jmp error_code
-.previous
- _ASM_EXTABLE(irq_return,iret_exc)
-
-#ifdef CONFIG_X86_ESPFIX32
- CFI_RESTORE_STATE
-ldt_ss:
-#ifdef CONFIG_PARAVIRT
- /*
- * The kernel can't run on a non-flat stack if paravirt mode
- * is active. Rather than try to fixup the high bits of
- * ESP, bypass this code entirely. This may break DOSemu
- * and/or Wine support in a paravirt VM, although the option
- * is still available to implement the setting of the high
- * 16-bits in the INTERRUPT_RETURN paravirt-op.
- */
- cmpl $0, pv_info+PARAVIRT_enabled
- jne restore_nocheck
-#endif
-
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
- mov %esp, %edx /* load kernel esp */
- mov PT_OLDESP(%esp), %eax /* load userspace esp */
- mov %dx, %ax /* eax: new kernel esp */
- sub %eax, %edx /* offset (low word is 0) */
- shr $16, %edx
- mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
- mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
- pushl_cfi $__ESPFIX_SS
- pushl_cfi %eax /* new kernel esp */
- /* Disable interrupts, but do not irqtrace this section: we
- * will soon execute iret and the tracer was already set to
- * the irqstate after the iret */
- DISABLE_INTERRUPTS(CLBR_EAX)
- lss (%esp), %esp /* switch to espfix segment */
- CFI_ADJUST_CFA_OFFSET -8
- jmp restore_nocheck
-#endif
- CFI_ENDPROC
-ENDPROC(system_call)
-
- # perform work that needs to be done immediately before resumption
- ALIGN
- RING0_PTREGS_FRAME # can't unwind into user space anyway
-work_pending:
- testb $_TIF_NEED_RESCHED, %cl
- jz work_notifysig
-work_resched:
- call schedule
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt
- # setting need_resched or sigpending
- # between sampling and the iret
- TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- andl $_TIF_WORK_MASK, %ecx # is there any work to be done other
- # than syscall tracing?
- jz restore_all
- testb $_TIF_NEED_RESCHED, %cl
- jnz work_resched
-
-work_notifysig: # deal with pending signals and
- # notify-resume requests
-#ifdef CONFIG_VM86
- testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
- movl %esp, %eax
- jnz work_notifysig_v86 # returning to kernel-space or
- # vm86-space
-1:
-#else
- movl %esp, %eax
-#endif
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- movb PT_CS(%esp), %bl
- andb $SEGMENT_RPL_MASK, %bl
- cmpb $USER_RPL, %bl
- jb resume_kernel
- xorl %edx, %edx
- call do_notify_resume
- jmp resume_userspace
-
-#ifdef CONFIG_VM86
- ALIGN
-work_notifysig_v86:
- pushl_cfi %ecx # save ti_flags for do_notify_resume
- call save_v86_state # %eax contains pt_regs pointer
- popl_cfi %ecx
- movl %eax, %esp
- jmp 1b
-#endif
-END(work_pending)
-
- # perform syscall exit tracing
- ALIGN
-syscall_trace_entry:
- movl $-ENOSYS,PT_EAX(%esp)
- movl %esp, %eax
- call syscall_trace_enter
- /* What it returned is what we'll actually use. */
- cmpl $(NR_syscalls), %eax
- jnae syscall_call
- jmp syscall_exit
-END(syscall_trace_entry)
-
- # perform syscall exit tracing
- ALIGN
-syscall_exit_work:
- testl $_TIF_WORK_SYSCALL_EXIT, %ecx
- jz work_pending
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call
- # schedule() instead
- movl %esp, %eax
- call syscall_trace_leave
- jmp resume_userspace
-END(syscall_exit_work)
- CFI_ENDPROC
-
- RING0_INT_FRAME # can't unwind into user space anyway
-syscall_fault:
- ASM_CLAC
- GET_THREAD_INFO(%ebp)
- movl $-EFAULT,PT_EAX(%esp)
- jmp resume_userspace
-END(syscall_fault)
-
-syscall_badsys:
- movl $-ENOSYS,%eax
- jmp syscall_after_call
-END(syscall_badsys)
-
-sysenter_badsys:
- movl $-ENOSYS,%eax
- jmp sysenter_after_call
-END(sysenter_badsys)
- CFI_ENDPROC
-
-.macro FIXUP_ESPFIX_STACK
-/*
- * Switch back for ESPFIX stack to the normal zerobased stack
- *
- * We can't call C functions using the ESPFIX stack. This code reads
- * the high word of the segment base from the GDT and swiches to the
- * normal stack and adjusts ESP with the matching offset.
- */
-#ifdef CONFIG_X86_ESPFIX32
- /* fixup the stack */
- mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
- mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
- shl $16, %eax
- addl %esp, %eax /* the adjusted stack pointer */
- pushl_cfi $__KERNEL_DS
- pushl_cfi %eax
- lss (%esp), %esp /* switch to the normal stack segment */
- CFI_ADJUST_CFA_OFFSET -8
-#endif
-.endm
-.macro UNWIND_ESPFIX_STACK
-#ifdef CONFIG_X86_ESPFIX32
- movl %ss, %eax
- /* see if on espfix stack */
- cmpw $__ESPFIX_SS, %ax
- jne 27f
- movl $__KERNEL_DS, %eax
- movl %eax, %ds
- movl %eax, %es
- /* switch to normal stack */
- FIXUP_ESPFIX_STACK
-27:
-#endif
-.endm
-
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
- .align 8
-ENTRY(irq_entries_start)
- RING0_INT_FRAME
- vector=FIRST_EXTERNAL_VECTOR
- .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
- pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */
- vector=vector+1
- jmp common_interrupt
- CFI_ADJUST_CFA_OFFSET -4
- .align 8
- .endr
-END(irq_entries_start)
-
-/*
- * the CPU automatically disables interrupts when executing an IRQ vector,
- * so IRQ-flags tracing has to follow that:
- */
- .p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
- ASM_CLAC
- addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */
- SAVE_ALL
- TRACE_IRQS_OFF
- movl %esp,%eax
- call do_IRQ
- jmp ret_from_intr
-ENDPROC(common_interrupt)
- CFI_ENDPROC
-
-#define BUILD_INTERRUPT3(name, nr, fn) \
-ENTRY(name) \
- RING0_INT_FRAME; \
- ASM_CLAC; \
- pushl_cfi $~(nr); \
- SAVE_ALL; \
- TRACE_IRQS_OFF \
- movl %esp,%eax; \
- call fn; \
- jmp ret_from_intr; \
- CFI_ENDPROC; \
-ENDPROC(name)
-
-
-#ifdef CONFIG_TRACING
-#define TRACE_BUILD_INTERRUPT(name, nr) \
- BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
-#else
-#define TRACE_BUILD_INTERRUPT(name, nr)
-#endif
-
-#define BUILD_INTERRUPT(name, nr) \
- BUILD_INTERRUPT3(name, nr, smp_##name); \
- TRACE_BUILD_INTERRUPT(name, nr)
-
-/* The include is where all of the SMP etc. interrupts come from */
-#include <asm/entry_arch.h>
-
-ENTRY(coprocessor_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_coprocessor_error
- jmp error_code
- CFI_ENDPROC
-END(coprocessor_error)
-
-ENTRY(simd_coprocessor_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
-#ifdef CONFIG_X86_INVD_BUG
- /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
- ALTERNATIVE "pushl_cfi $do_general_protection", \
- "pushl $do_simd_coprocessor_error", \
- X86_FEATURE_XMM
-#else
- pushl_cfi $do_simd_coprocessor_error
-#endif
- jmp error_code
- CFI_ENDPROC
-END(simd_coprocessor_error)
-
-ENTRY(device_not_available)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $-1 # mark this as an int
- pushl_cfi $do_device_not_available
- jmp error_code
- CFI_ENDPROC
-END(device_not_available)
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
- iret
- _ASM_EXTABLE(native_iret, iret_exc)
-END(native_iret)
-
-ENTRY(native_irq_enable_sysexit)
- sti
- sysexit
-END(native_irq_enable_sysexit)
-#endif
-
-ENTRY(overflow)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_overflow
- jmp error_code
- CFI_ENDPROC
-END(overflow)
-
-ENTRY(bounds)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_bounds
- jmp error_code
- CFI_ENDPROC
-END(bounds)
-
-ENTRY(invalid_op)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_invalid_op
- jmp error_code
- CFI_ENDPROC
-END(invalid_op)
-
-ENTRY(coprocessor_segment_overrun)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_coprocessor_segment_overrun
- jmp error_code
- CFI_ENDPROC
-END(coprocessor_segment_overrun)
-
-ENTRY(invalid_TSS)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_invalid_TSS
- jmp error_code
- CFI_ENDPROC
-END(invalid_TSS)
-
-ENTRY(segment_not_present)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_segment_not_present
- jmp error_code
- CFI_ENDPROC
-END(segment_not_present)
-
-ENTRY(stack_segment)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_stack_segment
- jmp error_code
- CFI_ENDPROC
-END(stack_segment)
-
-ENTRY(alignment_check)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_alignment_check
- jmp error_code
- CFI_ENDPROC
-END(alignment_check)
-
-ENTRY(divide_error)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0 # no error code
- pushl_cfi $do_divide_error
- jmp error_code
- CFI_ENDPROC
-END(divide_error)
-
-#ifdef CONFIG_X86_MCE
-ENTRY(machine_check)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi machine_check_vector
- jmp error_code
- CFI_ENDPROC
-END(machine_check)
-#endif
-
-ENTRY(spurious_interrupt_bug)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $0
- pushl_cfi $do_spurious_interrupt_bug
- jmp error_code
- CFI_ENDPROC
-END(spurious_interrupt_bug)
-
-#ifdef CONFIG_XEN
-/* Xen doesn't set %esp to be precisely what the normal sysenter
- entrypoint expects, so fix it up before using the normal path. */
-ENTRY(xen_sysenter_target)
- RING0_INT_FRAME
- addl $5*4, %esp /* remove xen-provided frame */
- CFI_ADJUST_CFA_OFFSET -5*4
- jmp sysenter_past_esp
- CFI_ENDPROC
-
-ENTRY(xen_hypervisor_callback)
- CFI_STARTPROC
- pushl_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
- TRACE_IRQS_OFF
-
- /* Check to see if we got the event in the critical
- region in xen_iret_direct, after we've reenabled
- events and checked for pending events. This simulates
- iret instruction's behaviour where it delivers a
- pending interrupt when enabling interrupts. */
- movl PT_EIP(%esp),%eax
- cmpl $xen_iret_start_crit,%eax
- jb 1f
- cmpl $xen_iret_end_crit,%eax
- jae 1f
-
- jmp xen_iret_crit_fixup
-
-ENTRY(xen_do_upcall)
-1: mov %esp, %eax
- call xen_evtchn_do_upcall
-#ifndef CONFIG_PREEMPT
- call xen_maybe_preempt_hcall
-#endif
- jmp ret_from_intr
- CFI_ENDPROC
-ENDPROC(xen_hypervisor_callback)
-
-# Hypervisor uses this for application faults while it executes.
-# We get here for two reasons:
-# 1. Fault while reloading DS, ES, FS or GS
-# 2. Fault while executing IRET
-# Category 1 we fix up by reattempting the load, and zeroing the segment
-# register if the load fails.
-# Category 2 we fix up by jumping to do_iret_error. We cannot use the
-# normal Linux return path in this case because if we use the IRET hypercall
-# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
-# We distinguish between categories by maintaining a status value in EAX.
-ENTRY(xen_failsafe_callback)
- CFI_STARTPROC
- pushl_cfi %eax
- movl $1,%eax
-1: mov 4(%esp),%ds
-2: mov 8(%esp),%es
-3: mov 12(%esp),%fs
-4: mov 16(%esp),%gs
- /* EAX == 0 => Category 1 (Bad segment)
- EAX != 0 => Category 2 (Bad IRET) */
- testl %eax,%eax
- popl_cfi %eax
- lea 16(%esp),%esp
- CFI_ADJUST_CFA_OFFSET -16
- jz 5f
- jmp iret_exc
-5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
- jmp ret_from_exception
- CFI_ENDPROC
-
-.section .fixup,"ax"
-6: xorl %eax,%eax
- movl %eax,4(%esp)
- jmp 1b
-7: xorl %eax,%eax
- movl %eax,8(%esp)
- jmp 2b
-8: xorl %eax,%eax
- movl %eax,12(%esp)
- jmp 3b
-9: xorl %eax,%eax
- movl %eax,16(%esp)
- jmp 4b
-.previous
- _ASM_EXTABLE(1b,6b)
- _ASM_EXTABLE(2b,7b)
- _ASM_EXTABLE(3b,8b)
- _ASM_EXTABLE(4b,9b)
-ENDPROC(xen_failsafe_callback)
-
-BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
- xen_evtchn_do_upcall)
-
-#endif /* CONFIG_XEN */
-
-#if IS_ENABLED(CONFIG_HYPERV)
-
-BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
- hyperv_vector_handler)
-
-#endif /* CONFIG_HYPERV */
-
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(mcount)
- ret
-END(mcount)
-
-ENTRY(ftrace_caller)
- pushl %eax
- pushl %ecx
- pushl %edx
- pushl $0 /* Pass NULL as regs pointer */
- movl 4*4(%esp), %eax
- movl 0x4(%ebp), %edx
- movl function_trace_op, %ecx
- subl $MCOUNT_INSN_SIZE, %eax
-
-.globl ftrace_call
-ftrace_call:
- call ftrace_stub
-
- addl $4,%esp /* skip NULL pointer */
- popl %edx
- popl %ecx
- popl %eax
-ftrace_ret:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
- jmp ftrace_stub
-#endif
-
-.globl ftrace_stub
-ftrace_stub:
- ret
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
- pushf /* push flags before compare (in cs location) */
-
- /*
- * i386 does not save SS and ESP when coming from kernel.
- * Instead, to get sp, ®s->sp is used (see ptrace.h).
- * Unfortunately, that means eflags must be at the same location
- * as the current return ip is. We move the return ip into the
- * ip location, and move flags into the return ip location.
- */
- pushl 4(%esp) /* save return ip into ip slot */
-
- pushl $0 /* Load 0 into orig_ax */
- pushl %gs
- pushl %fs
- pushl %es
- pushl %ds
- pushl %eax
- pushl %ebp
- pushl %edi
- pushl %esi
- pushl %edx
- pushl %ecx
- pushl %ebx
-
- movl 13*4(%esp), %eax /* Get the saved flags */
- movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
- /* clobbering return ip */
- movl $__KERNEL_CS,13*4(%esp)
-
- movl 12*4(%esp), %eax /* Load ip (1st parameter) */
- subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
- movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
- movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
- pushl %esp /* Save pt_regs as 4th parameter */
-
-GLOBAL(ftrace_regs_call)
- call ftrace_stub
-
- addl $4, %esp /* Skip pt_regs */
- movl 14*4(%esp), %eax /* Move flags back into cs */
- movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
- movl 12*4(%esp), %eax /* Get return ip from regs->ip */
- movl %eax, 14*4(%esp) /* Put return ip back for ret */
-
- popl %ebx
- popl %ecx
- popl %edx
- popl %esi
- popl %edi
- popl %ebp
- popl %eax
- popl %ds
- popl %es
- popl %fs
- popl %gs
- addl $8, %esp /* Skip orig_ax and ip */
- popf /* Pop flags at end (no addl to corrupt flags) */
- jmp ftrace_ret
-
- popf
- jmp ftrace_stub
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(mcount)
- cmpl $__PAGE_OFFSET, %esp
- jb ftrace_stub /* Paging not enabled yet? */
-
- cmpl $ftrace_stub, ftrace_trace_function
- jnz trace
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- cmpl $ftrace_stub, ftrace_graph_return
- jnz ftrace_graph_caller
-
- cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
- jnz ftrace_graph_caller
-#endif
-.globl ftrace_stub
-ftrace_stub:
- ret
-
- /* taken from glibc */
-trace:
- pushl %eax
- pushl %ecx
- pushl %edx
- movl 0xc(%esp), %eax
- movl 0x4(%ebp), %edx
- subl $MCOUNT_INSN_SIZE, %eax
-
- call *ftrace_trace_function
-
- popl %edx
- popl %ecx
- popl %eax
- jmp ftrace_stub
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
- pushl %eax
- pushl %ecx
- pushl %edx
- movl 0xc(%esp), %eax
- lea 0x4(%ebp), %edx
- movl (%ebp), %ecx
- subl $MCOUNT_INSN_SIZE, %eax
- call prepare_ftrace_return
- popl %edx
- popl %ecx
- popl %eax
- ret
-END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
- pushl %eax
- pushl %edx
- movl %ebp, %eax
- call ftrace_return_to_handler
- movl %eax, %ecx
- popl %edx
- popl %eax
- jmp *%ecx
-#endif
-
-#ifdef CONFIG_TRACING
-ENTRY(trace_page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $trace_do_page_fault
- jmp error_code
- CFI_ENDPROC
-END(trace_page_fault)
-#endif
-
-ENTRY(page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_page_fault
- ALIGN
-error_code:
- /* the function address is in %gs's slot on the stack */
- pushl_cfi %fs
- /*CFI_REL_OFFSET fs, 0*/
- pushl_cfi %es
- /*CFI_REL_OFFSET es, 0*/
- pushl_cfi %ds
- /*CFI_REL_OFFSET ds, 0*/
- pushl_cfi_reg eax
- pushl_cfi_reg ebp
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg edx
- pushl_cfi_reg ecx
- pushl_cfi_reg ebx
- cld
- movl $(__KERNEL_PERCPU), %ecx
- movl %ecx, %fs
- UNWIND_ESPFIX_STACK
- GS_TO_REG %ecx
- movl PT_GS(%esp), %edi # get the function address
- movl PT_ORIG_EAX(%esp), %edx # get the error code
- movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
- REG_TO_PTGS %ecx
- SET_KERNEL_GS %ecx
- movl $(__USER_DS), %ecx
- movl %ecx, %ds
- movl %ecx, %es
- TRACE_IRQS_OFF
- movl %esp,%eax # pt_regs pointer
- call *%edi
- jmp ret_from_exception
- CFI_ENDPROC
-END(page_fault)
-
-/*
- * Debug traps and NMI can happen at the one SYSENTER instruction
- * that sets up the real kernel stack. Check here, since we can't
- * allow the wrong stack to be used.
- *
- * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
- * already pushed 3 words if it hits on the sysenter instruction:
- * eflags, cs and eip.
- *
- * We just load the right stack, and push the three (known) values
- * by hand onto the new stack - while updating the return eip past
- * the instruction that would have done it for sysenter.
- */
-.macro FIX_STACK offset ok label
- cmpw $__KERNEL_CS, 4(%esp)
- jne \ok
-\label:
- movl TSS_sysenter_sp0 + \offset(%esp), %esp
- CFI_DEF_CFA esp, 0
- CFI_UNDEFINED eip
- pushfl_cfi
- pushl_cfi $__KERNEL_CS
- pushl_cfi $sysenter_past_esp
- CFI_REL_OFFSET eip, 0
-.endm
-
-ENTRY(debug)
- RING0_INT_FRAME
- ASM_CLAC
- cmpl $ia32_sysenter_target,(%esp)
- jne debug_stack_correct
- FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
-debug_stack_correct:
- pushl_cfi $-1 # mark this as an int
- SAVE_ALL
- TRACE_IRQS_OFF
- xorl %edx,%edx # error code 0
- movl %esp,%eax # pt_regs pointer
- call do_debug
- jmp ret_from_exception
- CFI_ENDPROC
-END(debug)
-
-/*
- * NMI is doubly nasty. It can happen _while_ we're handling
- * a debug fault, and the debug fault hasn't yet been able to
- * clear up the stack. So we first check whether we got an
- * NMI on the sysenter entry path, but after that we need to
- * check whether we got an NMI on the debug path where the debug
- * fault happened on the sysenter path.
- */
-ENTRY(nmi)
- RING0_INT_FRAME
- ASM_CLAC
-#ifdef CONFIG_X86_ESPFIX32
- pushl_cfi %eax
- movl %ss, %eax
- cmpw $__ESPFIX_SS, %ax
- popl_cfi %eax
- je nmi_espfix_stack
-#endif
- cmpl $ia32_sysenter_target,(%esp)
- je nmi_stack_fixup
- pushl_cfi %eax
- movl %esp,%eax
- /* Do not access memory above the end of our stack page,
- * it might not exist.
- */
- andl $(THREAD_SIZE-1),%eax
- cmpl $(THREAD_SIZE-20),%eax
- popl_cfi %eax
- jae nmi_stack_correct
- cmpl $ia32_sysenter_target,12(%esp)
- je nmi_debug_stack_check
-nmi_stack_correct:
- /* We have a RING0_INT_FRAME here */
- pushl_cfi %eax
- SAVE_ALL
- xorl %edx,%edx # zero error code
- movl %esp,%eax # pt_regs pointer
- call do_nmi
- jmp restore_all_notrace
- CFI_ENDPROC
-
-nmi_stack_fixup:
- RING0_INT_FRAME
- FIX_STACK 12, nmi_stack_correct, 1
- jmp nmi_stack_correct
-
-nmi_debug_stack_check:
- /* We have a RING0_INT_FRAME here */
- cmpw $__KERNEL_CS,16(%esp)
- jne nmi_stack_correct
- cmpl $debug,(%esp)
- jb nmi_stack_correct
- cmpl $debug_esp_fix_insn,(%esp)
- ja nmi_stack_correct
- FIX_STACK 24, nmi_stack_correct, 1
- jmp nmi_stack_correct
-
-#ifdef CONFIG_X86_ESPFIX32
-nmi_espfix_stack:
- /* We have a RING0_INT_FRAME here.
- *
- * create the pointer to lss back
- */
- pushl_cfi %ss
- pushl_cfi %esp
- addl $4, (%esp)
- /* copy the iret frame of 12 bytes */
- .rept 3
- pushl_cfi 16(%esp)
- .endr
- pushl_cfi %eax
- SAVE_ALL
- FIXUP_ESPFIX_STACK # %eax == %esp
- xorl %edx,%edx # zero error code
- call do_nmi
- RESTORE_REGS
- lss 12+4(%esp), %esp # back to espfix stack
- CFI_ADJUST_CFA_OFFSET -24
- jmp irq_return
-#endif
- CFI_ENDPROC
-END(nmi)
-
-ENTRY(int3)
- RING0_INT_FRAME
- ASM_CLAC
- pushl_cfi $-1 # mark this as an int
- SAVE_ALL
- TRACE_IRQS_OFF
- xorl %edx,%edx # zero error code
- movl %esp,%eax # pt_regs pointer
- call do_int3
- jmp ret_from_exception
- CFI_ENDPROC
-END(int3)
-
-ENTRY(general_protection)
- RING0_EC_FRAME
- pushl_cfi $do_general_protection
- jmp error_code
- CFI_ENDPROC
-END(general_protection)
-
-#ifdef CONFIG_KVM_GUEST
-ENTRY(async_page_fault)
- RING0_EC_FRAME
- ASM_CLAC
- pushl_cfi $do_async_page_fault
- jmp error_code
- CFI_ENDPROC
-END(async_page_fault)
-#endif
-
+++ /dev/null
-/*
- * linux/arch/x86_64/entry.S
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
- * Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
- */
-
-/*
- * entry.S contains the system-call and fault low-level handling routines.
- *
- * Some of this is documented in Documentation/x86/entry_64.txt
- *
- * NOTE: This code handles signal-recognition, which happens every time
- * after an interrupt and after each system call.
- *
- * A note on terminology:
- * - iret frame: Architecture defined interrupt frame from SS to RIP
- * at the top of the kernel process stack.
- *
- * Some macro usage:
- * - CFI macros are used to generate dwarf2 unwind information for better
- * backtraces. They don't change any code.
- * - ENTRY/END Define functions in the symbol table.
- * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging.
- * - idtentry - Define exception entry points.
- */
-
-#include <linux/linkage.h>
-#include <asm/segment.h>
-#include <asm/cache.h>
-#include <asm/errno.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm-offsets.h>
-#include <asm/msr.h>
-#include <asm/unistd.h>
-#include <asm/thread_info.h>
-#include <asm/hw_irq.h>
-#include <asm/page_types.h>
-#include <asm/irqflags.h>
-#include <asm/paravirt.h>
-#include <asm/percpu.h>
-#include <asm/asm.h>
-#include <asm/context_tracking.h>
-#include <asm/smap.h>
-#include <asm/pgtable_types.h>
-#include <linux/err.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_64BIT 0x80000000
-#define __AUDIT_ARCH_LE 0x40000000
-
- .code64
- .section .entry.text, "ax"
-
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret64)
- swapgs
- sysretq
-ENDPROC(native_usergs_sysret64)
-#endif /* CONFIG_PARAVIRT */
-
-
-.macro TRACE_IRQS_IRETQ
-#ifdef CONFIG_TRACE_IRQFLAGS
- bt $9,EFLAGS(%rsp) /* interrupts off? */
- jnc 1f
- TRACE_IRQS_ON
-1:
-#endif
-.endm
-
-/*
- * When dynamic function tracer is enabled it will add a breakpoint
- * to all locations that it is about to modify, sync CPUs, update
- * all the code, sync CPUs, then remove the breakpoints. In this time
- * if lockdep is enabled, it might jump back into the debug handler
- * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
- *
- * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
- * make sure the stack pointer does not get reset back to the top
- * of the debug stack, and instead just reuses the current stack.
- */
-#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
-
-.macro TRACE_IRQS_OFF_DEBUG
- call debug_stack_set_zero
- TRACE_IRQS_OFF
- call debug_stack_reset
-.endm
-
-.macro TRACE_IRQS_ON_DEBUG
- call debug_stack_set_zero
- TRACE_IRQS_ON
- call debug_stack_reset
-.endm
-
-.macro TRACE_IRQS_IRETQ_DEBUG
- bt $9,EFLAGS(%rsp) /* interrupts off? */
- jnc 1f
- TRACE_IRQS_ON_DEBUG
-1:
-.endm
-
-#else
-# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF
-# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON
-# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ
-#endif
-
-/*
- * empty frame
- */
- .macro EMPTY_FRAME start=1 offset=0
- .if \start
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,8+\offset
- .else
- CFI_DEF_CFA_OFFSET 8+\offset
- .endif
- .endm
-
-/*
- * initial frame state for interrupts (and exceptions without error code)
- */
- .macro INTR_FRAME start=1 offset=0
- EMPTY_FRAME \start, 5*8+\offset
- /*CFI_REL_OFFSET ss, 4*8+\offset*/
- CFI_REL_OFFSET rsp, 3*8+\offset
- /*CFI_REL_OFFSET rflags, 2*8+\offset*/
- /*CFI_REL_OFFSET cs, 1*8+\offset*/
- CFI_REL_OFFSET rip, 0*8+\offset
- .endm
-
-/*
- * initial frame state for exceptions with error code (and interrupts
- * with vector already pushed)
- */
- .macro XCPT_FRAME start=1 offset=0
- INTR_FRAME \start, 1*8+\offset
- .endm
-
-/*
- * frame that enables passing a complete pt_regs to a C function.
- */
- .macro DEFAULT_FRAME start=1 offset=0
- XCPT_FRAME \start, ORIG_RAX+\offset
- CFI_REL_OFFSET rdi, RDI+\offset
- CFI_REL_OFFSET rsi, RSI+\offset
- CFI_REL_OFFSET rdx, RDX+\offset
- CFI_REL_OFFSET rcx, RCX+\offset
- CFI_REL_OFFSET rax, RAX+\offset
- CFI_REL_OFFSET r8, R8+\offset
- CFI_REL_OFFSET r9, R9+\offset
- CFI_REL_OFFSET r10, R10+\offset
- CFI_REL_OFFSET r11, R11+\offset
- CFI_REL_OFFSET rbx, RBX+\offset
- CFI_REL_OFFSET rbp, RBP+\offset
- CFI_REL_OFFSET r12, R12+\offset
- CFI_REL_OFFSET r13, R13+\offset
- CFI_REL_OFFSET r14, R14+\offset
- CFI_REL_OFFSET r15, R15+\offset
- .endm
-
-/*
- * 64bit SYSCALL instruction entry. Up to 6 arguments in registers.
- *
- * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
- * then loads new ss, cs, and rip from previously programmed MSRs.
- * rflags gets masked by a value from another MSR (so CLD and CLAC
- * are not needed). SYSCALL does not save anything on the stack
- * and does not change rsp.
- *
- * Registers on entry:
- * rax system call number
- * rcx return address
- * r11 saved rflags (note: r11 is callee-clobbered register in C ABI)
- * rdi arg0
- * rsi arg1
- * rdx arg2
- * r10 arg3 (needs to be moved to rcx to conform to C ABI)
- * r8 arg4
- * r9 arg5
- * (note: r12-r15,rbp,rbx are callee-preserved in C ABI)
- *
- * Only called from user space.
- *
- * When user can change pt_regs->foo always force IRET. That is because
- * it deals with uncanonical addresses better. SYSRET has trouble
- * with them due to bugs in both AMD and Intel CPUs.
- */
-
-ENTRY(system_call)
- CFI_STARTPROC simple
- CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,0
- CFI_REGISTER rip,rcx
- /*CFI_REGISTER rflags,r11*/
-
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- SWAPGS_UNSAFE_STACK
- /*
- * A hypervisor implementation might want to use a label
- * after the swapgs, so that it can do the swapgs
- * for the guest and jump here on syscall.
- */
-GLOBAL(system_call_after_swapgs)
-
- movq %rsp,PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack),%rsp
-
- /* Construct struct pt_regs on stack */
- pushq_cfi $__USER_DS /* pt_regs->ss */
- pushq_cfi PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
- /*
- * Re-enable interrupts.
- * We use 'rsp_scratch' as a scratch space, hence irq-off block above
- * must execute atomically in the face of possible interrupt-driven
- * task preemption. We must enable interrupts only after we're done
- * with using rsp_scratch:
- */
- ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %r11 /* pt_regs->flags */
- pushq_cfi $__USER_CS /* pt_regs->cs */
- pushq_cfi %rcx /* pt_regs->ip */
- CFI_REL_OFFSET rip,0
- pushq_cfi_reg rax /* pt_regs->orig_ax */
- pushq_cfi_reg rdi /* pt_regs->di */
- pushq_cfi_reg rsi /* pt_regs->si */
- pushq_cfi_reg rdx /* pt_regs->dx */
- pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi $-ENOSYS /* pt_regs->ax */
- pushq_cfi_reg r8 /* pt_regs->r8 */
- pushq_cfi_reg r9 /* pt_regs->r9 */
- pushq_cfi_reg r10 /* pt_regs->r10 */
- pushq_cfi_reg r11 /* pt_regs->r11 */
- sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */
- CFI_ADJUST_CFA_OFFSET 6*8
-
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz tracesys
-system_call_fastpath:
-#if __SYSCALL_MASK == ~0
- cmpq $__NR_syscall_max,%rax
-#else
- andl $__SYSCALL_MASK,%eax
- cmpl $__NR_syscall_max,%eax
-#endif
- ja 1f /* return -ENOSYS (already in pt_regs->ax) */
- movq %r10,%rcx
- call *sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
-1:
-/*
- * Syscall return path ending with SYSRET (fast path).
- * Has incompletely filled pt_regs.
- */
- LOCKDEP_SYS_EXIT
- /*
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
- DISABLE_INTERRUPTS(CLBR_NONE)
-
- /*
- * We must check ti flags with interrupts (or at least preemption)
- * off because we must *never* return to userspace without
- * processing exit work that is enqueued if we're preempted here.
- * In particular, returning to userspace with any of the one-shot
- * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
- * very bad.
- */
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */
-
- CFI_REMEMBER_STATE
-
- RESTORE_C_REGS_EXCEPT_RCX_R11
- movq RIP(%rsp),%rcx
- CFI_REGISTER rip,rcx
- movq EFLAGS(%rsp),%r11
- /*CFI_REGISTER rflags,r11*/
- movq RSP(%rsp),%rsp
- /*
- * 64bit SYSRET restores rip from rcx,
- * rflags from r11 (but RF and VM bits are forced to 0),
- * cs and ss are loaded from MSRs.
- * Restoration of rflags re-enables interrupts.
- *
- * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
- * descriptor is not reinitialized. This means that we should
- * avoid SYSRET with SS == NULL, which could happen if we schedule,
- * exit the kernel, and re-enter using an interrupt vector. (All
- * interrupt entries on x86_64 set SS to NULL.) We prevent that
- * from happening by reloading SS in __switch_to. (Actually
- * detecting the failure in 64-bit userspace is tricky but can be
- * done.)
- */
- USERGS_SYSRET64
-
- CFI_RESTORE_STATE
-
- /* Do syscall entry tracing */
-tracesys:
- movq %rsp, %rdi
- movl $AUDIT_ARCH_X86_64, %esi
- call syscall_trace_enter_phase1
- test %rax, %rax
- jnz tracesys_phase2 /* if needed, run the slow path */
- RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */
- movq ORIG_RAX(%rsp), %rax
- jmp system_call_fastpath /* and return to the fast path */
-
-tracesys_phase2:
- SAVE_EXTRA_REGS
- movq %rsp, %rdi
- movl $AUDIT_ARCH_X86_64, %esi
- movq %rax,%rdx
- call syscall_trace_enter_phase2
-
- /*
- * Reload registers from stack in case ptrace changed them.
- * We don't reload %rax because syscall_trace_entry_phase2() returned
- * the value it wants us to use in the table lookup.
- */
- RESTORE_C_REGS_EXCEPT_RAX
- RESTORE_EXTRA_REGS
-#if __SYSCALL_MASK == ~0
- cmpq $__NR_syscall_max,%rax
-#else
- andl $__SYSCALL_MASK,%eax
- cmpl $__NR_syscall_max,%eax
-#endif
- ja 1f /* return -ENOSYS (already in pt_regs->ax) */
- movq %r10,%rcx /* fixup for C */
- call *sys_call_table(,%rax,8)
- movq %rax,RAX(%rsp)
-1:
- /* Use IRET because user could have changed pt_regs->foo */
-
-/*
- * Syscall return path ending with IRET.
- * Has correct iret frame.
- */
-GLOBAL(int_ret_from_sys_call)
- DISABLE_INTERRUPTS(CLBR_NONE)
-int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
- TRACE_IRQS_OFF
- movl $_TIF_ALLWORK_MASK,%edi
- /* edi: mask to check */
-GLOBAL(int_with_check)
- LOCKDEP_SYS_EXIT_IRQ
- GET_THREAD_INFO(%rcx)
- movl TI_flags(%rcx),%edx
- andl %edi,%edx
- jnz int_careful
- andl $~TS_COMPAT,TI_status(%rcx)
- jmp syscall_return
-
- /* Either reschedule or signal or syscall exit tracking needed. */
- /* First do a reschedule test. */
- /* edx: work, edi: workmask */
-int_careful:
- bt $TIF_NEED_RESCHED,%edx
- jnc int_very_careful
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %rdi
- SCHEDULE_USER
- popq_cfi %rdi
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- jmp int_with_check
-
- /* handle signals and tracing -- both require a full pt_regs */
-int_very_careful:
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_EXTRA_REGS
- /* Check for syscall exit trace */
- testl $_TIF_WORK_SYSCALL_EXIT,%edx
- jz int_signal
- pushq_cfi %rdi
- leaq 8(%rsp),%rdi # &ptregs -> arg1
- call syscall_trace_leave
- popq_cfi %rdi
- andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
- jmp int_restore_rest
-
-int_signal:
- testl $_TIF_DO_NOTIFY_MASK,%edx
- jz 1f
- movq %rsp,%rdi # &ptregs -> arg1
- xorl %esi,%esi # oldset -> arg2
- call do_notify_resume
-1: movl $_TIF_WORK_MASK,%edi
-int_restore_rest:
- RESTORE_EXTRA_REGS
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- jmp int_with_check
-
-syscall_return:
- /* The IRETQ could re-enable interrupts: */
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_IRETQ
-
- /*
- * Try to use SYSRET instead of IRET if we're returning to
- * a completely clean 64-bit userspace context.
- */
- movq RCX(%rsp),%rcx
- cmpq %rcx,RIP(%rsp) /* RCX == RIP */
- jne opportunistic_sysret_failed
-
- /*
- * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
- * in kernel space. This essentially lets the user take over
- * the kernel, since userspace controls RSP. It's not worth
- * testing for canonicalness exactly -- this check detects any
- * of the 17 high bits set, which is true for non-canonical
- * or kernel addresses. (This will pessimize vsyscall=native.
- * Big deal.)
- *
- * If virtual addresses ever become wider, this will need
- * to be updated to remain correct on both old and new CPUs.
- */
- .ifne __VIRTUAL_MASK_SHIFT - 47
- .error "virtual address width changed -- SYSRET checks need update"
- .endif
- shr $__VIRTUAL_MASK_SHIFT, %rcx
- jnz opportunistic_sysret_failed
-
- cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */
- jne opportunistic_sysret_failed
-
- movq R11(%rsp),%r11
- cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */
- jne opportunistic_sysret_failed
-
- /*
- * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
- * restoring TF results in a trap from userspace immediately after
- * SYSRET. This would cause an infinite loop whenever #DB happens
- * with register state that satisfies the opportunistic SYSRET
- * conditions. For example, single-stepping this user code:
- *
- * movq $stuck_here,%rcx
- * pushfq
- * popq %r11
- * stuck_here:
- *
- * would never get past 'stuck_here'.
- */
- testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
- jnz opportunistic_sysret_failed
-
- /* nothing to check for RSP */
-
- cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */
- jne opportunistic_sysret_failed
-
- /*
- * We win! This label is here just for ease of understanding
- * perf profiles. Nothing jumps here.
- */
-syscall_return_via_sysret:
- CFI_REMEMBER_STATE
- /* r11 is already restored (see code above) */
- RESTORE_C_REGS_EXCEPT_R11
- movq RSP(%rsp),%rsp
- USERGS_SYSRET64
- CFI_RESTORE_STATE
-
-opportunistic_sysret_failed:
- SWAPGS
- jmp restore_c_regs_and_iret
- CFI_ENDPROC
-END(system_call)
-
-
- .macro FORK_LIKE func
-ENTRY(stub_\func)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8 /* offset 8: return address */
- SAVE_EXTRA_REGS 8
- jmp sys_\func
- CFI_ENDPROC
-END(stub_\func)
- .endm
-
- FORK_LIKE clone
- FORK_LIKE fork
- FORK_LIKE vfork
-
-ENTRY(stub_execve)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call sys_execve
-return_from_execve:
- testl %eax, %eax
- jz 1f
- /* exec failed, can use fast SYSRET code path in this case */
- ret
-1:
- /* must use IRET code path (pt_regs->cs may have changed) */
- addq $8, %rsp
- CFI_ADJUST_CFA_OFFSET -8
- ZERO_EXTRA_REGS
- movq %rax,RAX(%rsp)
- jmp int_ret_from_sys_call
- CFI_ENDPROC
-END(stub_execve)
-/*
- * Remaining execve stubs are only 7 bytes long.
- * ENTRY() often aligns to 16 bytes, which in this case has no benefits.
- */
- .align 8
-GLOBAL(stub_execveat)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call sys_execveat
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_execveat)
-
-#ifdef CONFIG_X86_X32_ABI
- .align 8
-GLOBAL(stub_x32_execve)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call compat_sys_execve
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_x32_execve)
- .align 8
-GLOBAL(stub_x32_execveat)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call compat_sys_execveat
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_x32_execveat)
-#endif
-
-#ifdef CONFIG_IA32_EMULATION
- .align 8
-GLOBAL(stub32_execve)
- CFI_STARTPROC
- call compat_sys_execve
- jmp return_from_execve
- CFI_ENDPROC
-END(stub32_execve)
- .align 8
-GLOBAL(stub32_execveat)
- CFI_STARTPROC
- call compat_sys_execveat
- jmp return_from_execve
- CFI_ENDPROC
-END(stub32_execveat)
-#endif
-
-/*
- * sigreturn is special because it needs to restore all registers on return.
- * This cannot be done with SYSRET, so use the IRET return path instead.
- */
-ENTRY(stub_rt_sigreturn)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- /*
- * SAVE_EXTRA_REGS result is not normally needed:
- * sigreturn overwrites all pt_regs->GPREGS.
- * But sigreturn can fail (!), and there is no easy way to detect that.
- * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error,
- * we SAVE_EXTRA_REGS here.
- */
- SAVE_EXTRA_REGS 8
- call sys_rt_sigreturn
-return_from_stub:
- addq $8, %rsp
- CFI_ADJUST_CFA_OFFSET -8
- RESTORE_EXTRA_REGS
- movq %rax,RAX(%rsp)
- jmp int_ret_from_sys_call
- CFI_ENDPROC
-END(stub_rt_sigreturn)
-
-#ifdef CONFIG_X86_X32_ABI
-ENTRY(stub_x32_rt_sigreturn)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- SAVE_EXTRA_REGS 8
- call sys32_x32_rt_sigreturn
- jmp return_from_stub
- CFI_ENDPROC
-END(stub_x32_rt_sigreturn)
-#endif
-
-/*
- * A newly forked process directly context switches into this address.
- *
- * rdi: prev task we switched from
- */
-ENTRY(ret_from_fork)
- DEFAULT_FRAME
-
- LOCK ; btr $TIF_FORK,TI_flags(%r8)
-
- pushq_cfi $0x0002
- popfq_cfi # reset kernel eflags
-
- call schedule_tail # rdi: 'prev' task parameter
-
- RESTORE_EXTRA_REGS
-
- testl $3,CS(%rsp) # from kernel_thread?
-
- /*
- * By the time we get here, we have no idea whether our pt_regs,
- * ti flags, and ti status came from the 64-bit SYSCALL fast path,
- * the slow path, or one of the ia32entry paths.
- * Use IRET code path to return, since it can safely handle
- * all of the above.
- */
- jnz int_ret_from_sys_call
-
- /* We came from kernel_thread */
- /* nb: we depend on RESTORE_EXTRA_REGS above */
- movq %rbp, %rdi
- call *%rbx
- movl $0, RAX(%rsp)
- RESTORE_EXTRA_REGS
- jmp int_ret_from_sys_call
- CFI_ENDPROC
-END(ret_from_fork)
-
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
- .align 8
-ENTRY(irq_entries_start)
- INTR_FRAME
- vector=FIRST_EXTERNAL_VECTOR
- .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
- pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */
- vector=vector+1
- jmp common_interrupt
- CFI_ADJUST_CFA_OFFSET -8
- .align 8
- .endr
- CFI_ENDPROC
-END(irq_entries_start)
-
-/*
- * Interrupt entry/exit.
- *
- * Interrupt entry points save only callee clobbered registers in fast path.
- *
- * Entry runs with interrupts off.
- */
-
-/* 0(%rsp): ~(interrupt number) */
- .macro interrupt func
- cld
- /*
- * Since nothing in interrupt handling code touches r12...r15 members
- * of "struct pt_regs", and since interrupts can nest, we can save
- * four stack slots and simultaneously provide
- * an unwind-friendly stack layout by saving "truncated" pt_regs
- * exactly up to rbp slot, without these members.
- */
- ALLOC_PT_GPREGS_ON_STACK -RBP
- SAVE_C_REGS -RBP
- /* this goes to 0(%rsp) for unwinder, not for saving the value: */
- SAVE_EXTRA_REGS_RBP -RBP
-
- leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */
-
- testl $3, CS-RBP(%rsp)
- je 1f
- SWAPGS
-1:
- /*
- * Save previous stack pointer, optionally switch to interrupt stack.
- * irq_count is used to check if a CPU is already on an interrupt stack
- * or not. While this is essentially redundant with preempt_count it is
- * a little cheaper to use a separate counter in the PDA (short of
- * moving irq_enter into assembly, which would be too much work)
- */
- movq %rsp, %rsi
- incl PER_CPU_VAR(irq_count)
- cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
- CFI_DEF_CFA_REGISTER rsi
- pushq %rsi
- /*
- * For debugger:
- * "CFA (Current Frame Address) is the value on stack + offset"
- */
- CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
- 0x77 /* DW_OP_breg7 (rsp) */, 0, \
- 0x06 /* DW_OP_deref */, \
- 0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \
- 0x22 /* DW_OP_plus */
- /* We entered an interrupt context - irqs are off: */
- TRACE_IRQS_OFF
-
- call \func
- .endm
-
- /*
- * The interrupt stubs push (~vector+0x80) onto the stack and
- * then jump to common_interrupt.
- */
- .p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
- XCPT_FRAME
- ASM_CLAC
- addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
- interrupt do_IRQ
- /* 0(%rsp): old RSP */
-ret_from_intr:
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- decl PER_CPU_VAR(irq_count)
-
- /* Restore saved previous stack */
- popq %rsi
- CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */
- /* return code expects complete pt_regs - adjust rsp accordingly: */
- leaq -RBP(%rsi),%rsp
- CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET RBP
-
- testl $3,CS(%rsp)
- je retint_kernel
- /* Interrupt came from user space */
-
- GET_THREAD_INFO(%rcx)
- /*
- * %rcx: thread info. Interrupts off.
- */
-retint_with_reschedule:
- movl $_TIF_WORK_MASK,%edi
-retint_check:
- LOCKDEP_SYS_EXIT_IRQ
- movl TI_flags(%rcx),%edx
- andl %edi,%edx
- CFI_REMEMBER_STATE
- jnz retint_careful
-
-retint_swapgs: /* return to user-space */
- /*
- * The iretq could re-enable interrupts:
- */
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_IRETQ
-
- SWAPGS
- jmp restore_c_regs_and_iret
-
-/* Returning to kernel space */
-retint_kernel:
-#ifdef CONFIG_PREEMPT
- /* Interrupts are off */
- /* Check if we need preemption */
- bt $9,EFLAGS(%rsp) /* interrupts were off? */
- jnc 1f
-0: cmpl $0,PER_CPU_VAR(__preempt_count)
- jnz 1f
- call preempt_schedule_irq
- jmp 0b
-1:
-#endif
- /*
- * The iretq could re-enable interrupts:
- */
- TRACE_IRQS_IRETQ
-
-/*
- * At this label, code paths which return to kernel and to user,
- * which come from interrupts/exception and from syscalls, merge.
- */
-restore_c_regs_and_iret:
- RESTORE_C_REGS
- REMOVE_PT_GPREGS_FROM_STACK 8
-
-irq_return:
- INTERRUPT_RETURN
-
-ENTRY(native_iret)
- /*
- * Are we returning to a stack segment from the LDT? Note: in
- * 64-bit mode SS:RSP on the exception stack is always valid.
- */
-#ifdef CONFIG_X86_ESPFIX64
- testb $4,(SS-RIP)(%rsp)
- jnz native_irq_return_ldt
-#endif
-
-.global native_irq_return_iret
-native_irq_return_iret:
- /*
- * This may fault. Non-paranoid faults on return to userspace are
- * handled by fixup_bad_iret. These include #SS, #GP, and #NP.
- * Double-faults due to espfix64 are handled in do_double_fault.
- * Other faults here are fatal.
- */
- iretq
-
-#ifdef CONFIG_X86_ESPFIX64
-native_irq_return_ldt:
- pushq_cfi %rax
- pushq_cfi %rdi
- SWAPGS
- movq PER_CPU_VAR(espfix_waddr),%rdi
- movq %rax,(0*8)(%rdi) /* RAX */
- movq (2*8)(%rsp),%rax /* RIP */
- movq %rax,(1*8)(%rdi)
- movq (3*8)(%rsp),%rax /* CS */
- movq %rax,(2*8)(%rdi)
- movq (4*8)(%rsp),%rax /* RFLAGS */
- movq %rax,(3*8)(%rdi)
- movq (6*8)(%rsp),%rax /* SS */
- movq %rax,(5*8)(%rdi)
- movq (5*8)(%rsp),%rax /* RSP */
- movq %rax,(4*8)(%rdi)
- andl $0xffff0000,%eax
- popq_cfi %rdi
- orq PER_CPU_VAR(espfix_stack),%rax
- SWAPGS
- movq %rax,%rsp
- popq_cfi %rax
- jmp native_irq_return_iret
-#endif
-
- /* edi: workmask, edx: work */
-retint_careful:
- CFI_RESTORE_STATE
- bt $TIF_NEED_RESCHED,%edx
- jnc retint_signal
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %rdi
- SCHEDULE_USER
- popq_cfi %rdi
- GET_THREAD_INFO(%rcx)
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- jmp retint_check
-
-retint_signal:
- testl $_TIF_DO_NOTIFY_MASK,%edx
- jz retint_swapgs
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_EXTRA_REGS
- movq $-1,ORIG_RAX(%rsp)
- xorl %esi,%esi # oldset
- movq %rsp,%rdi # &pt_regs
- call do_notify_resume
- RESTORE_EXTRA_REGS
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- GET_THREAD_INFO(%rcx)
- jmp retint_with_reschedule
-
- CFI_ENDPROC
-END(common_interrupt)
-
-/*
- * APIC interrupts.
- */
-.macro apicinterrupt3 num sym do_sym
-ENTRY(\sym)
- INTR_FRAME
- ASM_CLAC
- pushq_cfi $~(\num)
-.Lcommon_\sym:
- interrupt \do_sym
- jmp ret_from_intr
- CFI_ENDPROC
-END(\sym)
-.endm
-
-#ifdef CONFIG_TRACING
-#define trace(sym) trace_##sym
-#define smp_trace(sym) smp_trace_##sym
-
-.macro trace_apicinterrupt num sym
-apicinterrupt3 \num trace(\sym) smp_trace(\sym)
-.endm
-#else
-.macro trace_apicinterrupt num sym do_sym
-.endm
-#endif
-
-.macro apicinterrupt num sym do_sym
-apicinterrupt3 \num \sym \do_sym
-trace_apicinterrupt \num \sym
-.endm
-
-#ifdef CONFIG_SMP
-apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \
- irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
-apicinterrupt3 REBOOT_VECTOR \
- reboot_interrupt smp_reboot_interrupt
-#endif
-
-#ifdef CONFIG_X86_UV
-apicinterrupt3 UV_BAU_MESSAGE \
- uv_bau_message_intr1 uv_bau_message_interrupt
-#endif
-apicinterrupt LOCAL_TIMER_VECTOR \
- apic_timer_interrupt smp_apic_timer_interrupt
-apicinterrupt X86_PLATFORM_IPI_VECTOR \
- x86_platform_ipi smp_x86_platform_ipi
-
-#ifdef CONFIG_HAVE_KVM
-apicinterrupt3 POSTED_INTR_VECTOR \
- kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
-#endif
-
-#ifdef CONFIG_X86_MCE_THRESHOLD
-apicinterrupt THRESHOLD_APIC_VECTOR \
- threshold_interrupt smp_threshold_interrupt
-#endif
-
-#ifdef CONFIG_X86_THERMAL_VECTOR
-apicinterrupt THERMAL_APIC_VECTOR \
- thermal_interrupt smp_thermal_interrupt
-#endif
-
-#ifdef CONFIG_SMP
-apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
- call_function_single_interrupt smp_call_function_single_interrupt
-apicinterrupt CALL_FUNCTION_VECTOR \
- call_function_interrupt smp_call_function_interrupt
-apicinterrupt RESCHEDULE_VECTOR \
- reschedule_interrupt smp_reschedule_interrupt
-#endif
-
-apicinterrupt ERROR_APIC_VECTOR \
- error_interrupt smp_error_interrupt
-apicinterrupt SPURIOUS_APIC_VECTOR \
- spurious_interrupt smp_spurious_interrupt
-
-#ifdef CONFIG_IRQ_WORK
-apicinterrupt IRQ_WORK_VECTOR \
- irq_work_interrupt smp_irq_work_interrupt
-#endif
-
-/*
- * Exception entry points.
- */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
-
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
-ENTRY(\sym)
- /* Sanity check */
- .if \shift_ist != -1 && \paranoid == 0
- .error "using shift_ist requires paranoid=1"
- .endif
-
- .if \has_error_code
- XCPT_FRAME
- .else
- INTR_FRAME
- .endif
-
- ASM_CLAC
- PARAVIRT_ADJUST_EXCEPTION_FRAME
-
- .ifeq \has_error_code
- pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
- .endif
-
- ALLOC_PT_GPREGS_ON_STACK
-
- .if \paranoid
- .if \paranoid == 1
- CFI_REMEMBER_STATE
- testl $3, CS(%rsp) /* If coming from userspace, switch */
- jnz 1f /* stacks. */
- .endif
- call paranoid_entry
- .else
- call error_entry
- .endif
- /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
-
- DEFAULT_FRAME 0
-
- .if \paranoid
- .if \shift_ist != -1
- TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */
- .else
- TRACE_IRQS_OFF
- .endif
- .endif
-
- movq %rsp,%rdi /* pt_regs pointer */
-
- .if \has_error_code
- movq ORIG_RAX(%rsp),%rsi /* get error code */
- movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
- .else
- xorl %esi,%esi /* no error code */
- .endif
-
- .if \shift_ist != -1
- subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
- .endif
-
- call \do_sym
-
- .if \shift_ist != -1
- addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
- .endif
-
- /* these procedures expect "no swapgs" flag in ebx */
- .if \paranoid
- jmp paranoid_exit
- .else
- jmp error_exit
- .endif
-
- .if \paranoid == 1
- CFI_RESTORE_STATE
- /*
- * Paranoid entry from userspace. Switch stacks and treat it
- * as a normal entry. This means that paranoid handlers
- * run in real process context if user_mode(regs).
- */
-1:
- call error_entry
-
- DEFAULT_FRAME 0
-
- movq %rsp,%rdi /* pt_regs pointer */
- call sync_regs
- movq %rax,%rsp /* switch stack */
-
- movq %rsp,%rdi /* pt_regs pointer */
-
- .if \has_error_code
- movq ORIG_RAX(%rsp),%rsi /* get error code */
- movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
- .else
- xorl %esi,%esi /* no error code */
- .endif
-
- call \do_sym
-
- jmp error_exit /* %ebx: no swapgs flag */
- .endif
-
- CFI_ENDPROC
-END(\sym)
-.endm
-
-#ifdef CONFIG_TRACING
-.macro trace_idtentry sym do_sym has_error_code:req
-idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code
-idtentry \sym \do_sym has_error_code=\has_error_code
-.endm
-#else
-.macro trace_idtentry sym do_sym has_error_code:req
-idtentry \sym \do_sym has_error_code=\has_error_code
-.endm
-#endif
-
-idtentry divide_error do_divide_error has_error_code=0
-idtentry overflow do_overflow has_error_code=0
-idtentry bounds do_bounds has_error_code=0
-idtentry invalid_op do_invalid_op has_error_code=0
-idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault do_double_fault has_error_code=1 paranoid=2
-idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
-idtentry invalid_TSS do_invalid_TSS has_error_code=1
-idtentry segment_not_present do_segment_not_present has_error_code=1
-idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
-idtentry coprocessor_error do_coprocessor_error has_error_code=0
-idtentry alignment_check do_alignment_check has_error_code=1
-idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
-
-
- /* Reload gs selector with exception handling */
- /* edi: new selector */
-ENTRY(native_load_gs_index)
- CFI_STARTPROC
- pushfq_cfi
- DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
- SWAPGS
-gs_change:
- movl %edi,%gs
-2: mfence /* workaround */
- SWAPGS
- popfq_cfi
- ret
- CFI_ENDPROC
-END(native_load_gs_index)
-
- _ASM_EXTABLE(gs_change,bad_gs)
- .section .fixup,"ax"
- /* running with kernelgs */
-bad_gs:
- SWAPGS /* switch back to user gs */
- xorl %eax,%eax
- movl %eax,%gs
- jmp 2b
- .previous
-
-/* Call softirq on interrupt stack. Interrupts are off. */
-ENTRY(do_softirq_own_stack)
- CFI_STARTPROC
- pushq_cfi %rbp
- CFI_REL_OFFSET rbp,0
- mov %rsp,%rbp
- CFI_DEF_CFA_REGISTER rbp
- incl PER_CPU_VAR(irq_count)
- cmove PER_CPU_VAR(irq_stack_ptr),%rsp
- push %rbp # backlink for old unwinder
- call __do_softirq
- leaveq
- CFI_RESTORE rbp
- CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET -8
- decl PER_CPU_VAR(irq_count)
- ret
- CFI_ENDPROC
-END(do_softirq_own_stack)
-
-#ifdef CONFIG_XEN
-idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
-
-/*
- * A note on the "critical region" in our callback handler.
- * We want to avoid stacking callback handlers due to events occurring
- * during handling of the last event. To do this, we keep events disabled
- * until we've done all processing. HOWEVER, we must enable events before
- * popping the stack frame (can't be done atomically) and so it would still
- * be possible to get enough handler activations to overflow the stack.
- * Although unlikely, bugs of that kind are hard to track down, so we'd
- * like to avoid the possibility.
- * So, on entry to the handler we detect whether we interrupted an
- * existing activation in its critical region -- if so, we pop the current
- * activation and restart the handler using the previous one.
- */
-ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs)
- CFI_STARTPROC
-/*
- * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
- * see the correct pointer to the pt_regs
- */
- movq %rdi, %rsp # we don't return, adjust the stack frame
- CFI_ENDPROC
- DEFAULT_FRAME
-11: incl PER_CPU_VAR(irq_count)
- movq %rsp,%rbp
- CFI_DEF_CFA_REGISTER rbp
- cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
- pushq %rbp # backlink for old unwinder
- call xen_evtchn_do_upcall
- popq %rsp
- CFI_DEF_CFA_REGISTER rsp
- decl PER_CPU_VAR(irq_count)
-#ifndef CONFIG_PREEMPT
- call xen_maybe_preempt_hcall
-#endif
- jmp error_exit
- CFI_ENDPROC
-END(xen_do_hypervisor_callback)
-
-/*
- * Hypervisor uses this for application faults while it executes.
- * We get here for two reasons:
- * 1. Fault while reloading DS, ES, FS or GS
- * 2. Fault while executing IRET
- * Category 1 we do not need to fix up as Xen has already reloaded all segment
- * registers that could be reloaded and zeroed the others.
- * Category 2 we fix up by killing the current process. We cannot use the
- * normal Linux return path in this case because if we use the IRET hypercall
- * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
- * We distinguish between categories by comparing each saved segment register
- * with its current contents: any discrepancy means we in category 1.
- */
-ENTRY(xen_failsafe_callback)
- INTR_FRAME 1 (6*8)
- /*CFI_REL_OFFSET gs,GS*/
- /*CFI_REL_OFFSET fs,FS*/
- /*CFI_REL_OFFSET es,ES*/
- /*CFI_REL_OFFSET ds,DS*/
- CFI_REL_OFFSET r11,8
- CFI_REL_OFFSET rcx,0
- movw %ds,%cx
- cmpw %cx,0x10(%rsp)
- CFI_REMEMBER_STATE
- jne 1f
- movw %es,%cx
- cmpw %cx,0x18(%rsp)
- jne 1f
- movw %fs,%cx
- cmpw %cx,0x20(%rsp)
- jne 1f
- movw %gs,%cx
- cmpw %cx,0x28(%rsp)
- jne 1f
- /* All segments match their saved values => Category 2 (Bad IRET). */
- movq (%rsp),%rcx
- CFI_RESTORE rcx
- movq 8(%rsp),%r11
- CFI_RESTORE r11
- addq $0x30,%rsp
- CFI_ADJUST_CFA_OFFSET -0x30
- pushq_cfi $0 /* RIP */
- pushq_cfi %r11
- pushq_cfi %rcx
- jmp general_protection
- CFI_RESTORE_STATE
-1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
- movq (%rsp),%rcx
- CFI_RESTORE rcx
- movq 8(%rsp),%r11
- CFI_RESTORE r11
- addq $0x30,%rsp
- CFI_ADJUST_CFA_OFFSET -0x30
- pushq_cfi $-1 /* orig_ax = -1 => not a system call */
- ALLOC_PT_GPREGS_ON_STACK
- SAVE_C_REGS
- SAVE_EXTRA_REGS
- jmp error_exit
- CFI_ENDPROC
-END(xen_failsafe_callback)
-
-apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
- xen_hvm_callback_vector xen_evtchn_do_upcall
-
-#endif /* CONFIG_XEN */
-
-#if IS_ENABLED(CONFIG_HYPERV)
-apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
- hyperv_callback_vector hyperv_vector_handler
-#endif /* CONFIG_HYPERV */
-
-idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry stack_segment do_stack_segment has_error_code=1
-#ifdef CONFIG_XEN
-idtentry xen_debug do_debug has_error_code=0
-idtentry xen_int3 do_int3 has_error_code=0
-idtentry xen_stack_segment do_stack_segment has_error_code=1
-#endif
-idtentry general_protection do_general_protection has_error_code=1
-trace_idtentry page_fault do_page_fault has_error_code=1
-#ifdef CONFIG_KVM_GUEST
-idtentry async_page_fault do_async_page_fault has_error_code=1
-#endif
-#ifdef CONFIG_X86_MCE
-idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
-#endif
-
-/*
- * Save all registers in pt_regs, and switch gs if needed.
- * Use slow, but surefire "are we in kernel?" check.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
- */
-ENTRY(paranoid_entry)
- XCPT_FRAME 1 15*8
- cld
- SAVE_C_REGS 8
- SAVE_EXTRA_REGS 8
- movl $1,%ebx
- movl $MSR_GS_BASE,%ecx
- rdmsr
- testl %edx,%edx
- js 1f /* negative -> in kernel */
- SWAPGS
- xorl %ebx,%ebx
-1: ret
- CFI_ENDPROC
-END(paranoid_entry)
-
-/*
- * "Paranoid" exit path from exception stack. This is invoked
- * only on return from non-NMI IST interrupts that came
- * from kernel space.
- *
- * We may be returning to very strange contexts (e.g. very early
- * in syscall entry), so checking for preemption here would
- * be complicated. Fortunately, we there's no good reason
- * to try to handle preemption here.
- */
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
-ENTRY(paranoid_exit)
- DEFAULT_FRAME
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF_DEBUG
- testl %ebx,%ebx /* swapgs needed? */
- jnz paranoid_exit_no_swapgs
- TRACE_IRQS_IRETQ
- SWAPGS_UNSAFE_STACK
- jmp paranoid_exit_restore
-paranoid_exit_no_swapgs:
- TRACE_IRQS_IRETQ_DEBUG
-paranoid_exit_restore:
- RESTORE_EXTRA_REGS
- RESTORE_C_REGS
- REMOVE_PT_GPREGS_FROM_STACK 8
- INTERRUPT_RETURN
- CFI_ENDPROC
-END(paranoid_exit)
-
-/*
- * Save all registers in pt_regs, and switch gs if needed.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
- */
-ENTRY(error_entry)
- XCPT_FRAME 1 15*8
- cld
- SAVE_C_REGS 8
- SAVE_EXTRA_REGS 8
- xorl %ebx,%ebx
- testl $3,CS+8(%rsp)
- je error_kernelspace
-error_swapgs:
- SWAPGS
-error_sti:
- TRACE_IRQS_OFF
- ret
-
- /*
- * There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. B stepping K8s sometimes report a
- * truncated RIP for IRET exceptions returning to compat mode. Check
- * for these here too.
- */
-error_kernelspace:
- CFI_REL_OFFSET rcx, RCX+8
- incl %ebx
- leaq native_irq_return_iret(%rip),%rcx
- cmpq %rcx,RIP+8(%rsp)
- je error_bad_iret
- movl %ecx,%eax /* zero extend */
- cmpq %rax,RIP+8(%rsp)
- je bstep_iret
- cmpq $gs_change,RIP+8(%rsp)
- je error_swapgs
- jmp error_sti
-
-bstep_iret:
- /* Fix truncated RIP */
- movq %rcx,RIP+8(%rsp)
- /* fall through */
-
-error_bad_iret:
- SWAPGS
- mov %rsp,%rdi
- call fixup_bad_iret
- mov %rax,%rsp
- decl %ebx /* Return to usergs */
- jmp error_sti
- CFI_ENDPROC
-END(error_entry)
-
-
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
-ENTRY(error_exit)
- DEFAULT_FRAME
- movl %ebx,%eax
- RESTORE_EXTRA_REGS
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- GET_THREAD_INFO(%rcx)
- testl %eax,%eax
- jne retint_kernel
- LOCKDEP_SYS_EXIT_IRQ
- movl TI_flags(%rcx),%edx
- movl $_TIF_WORK_MASK,%edi
- andl %edi,%edx
- jnz retint_careful
- jmp retint_swapgs
- CFI_ENDPROC
-END(error_exit)
-
-/* Runs on exception stack */
-ENTRY(nmi)
- INTR_FRAME
- PARAVIRT_ADJUST_EXCEPTION_FRAME
- /*
- * We allow breakpoints in NMIs. If a breakpoint occurs, then
- * the iretq it performs will take us out of NMI context.
- * This means that we can have nested NMIs where the next
- * NMI is using the top of the stack of the previous NMI. We
- * can't let it execute because the nested NMI will corrupt the
- * stack of the previous NMI. NMI handlers are not re-entrant
- * anyway.
- *
- * To handle this case we do the following:
- * Check the a special location on the stack that contains
- * a variable that is set when NMIs are executing.
- * The interrupted task's stack is also checked to see if it
- * is an NMI stack.
- * If the variable is not set and the stack is not the NMI
- * stack then:
- * o Set the special variable on the stack
- * o Copy the interrupt frame into a "saved" location on the stack
- * o Copy the interrupt frame into a "copy" location on the stack
- * o Continue processing the NMI
- * If the variable is set or the previous stack is the NMI stack:
- * o Modify the "copy" location to jump to the repeate_nmi
- * o return back to the first NMI
- *
- * Now on exit of the first NMI, we first clear the stack variable
- * The NMI stack will tell any nested NMIs at that point that it is
- * nested. Then we pop the stack normally with iret, and if there was
- * a nested NMI that updated the copy interrupt stack frame, a
- * jump will be made to the repeat_nmi code that will handle the second
- * NMI.
- */
-
- /* Use %rdx as our temp variable throughout */
- pushq_cfi %rdx
- CFI_REL_OFFSET rdx, 0
-
- /*
- * If %cs was not the kernel segment, then the NMI triggered in user
- * space, which means it is definitely not nested.
- */
- cmpl $__KERNEL_CS, 16(%rsp)
- jne first_nmi
-
- /*
- * Check the special variable on the stack to see if NMIs are
- * executing.
- */
- cmpl $1, -8(%rsp)
- je nested_nmi
-
- /*
- * Now test if the previous stack was an NMI stack.
- * We need the double check. We check the NMI stack to satisfy the
- * race when the first NMI clears the variable before returning.
- * We check the variable because the first NMI could be in a
- * breakpoint routine using a breakpoint stack.
- */
- lea 6*8(%rsp), %rdx
- /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
- cmpq %rdx, 4*8(%rsp)
- /* If the stack pointer is above the NMI stack, this is a normal NMI */
- ja first_nmi
- subq $EXCEPTION_STKSZ, %rdx
- cmpq %rdx, 4*8(%rsp)
- /* If it is below the NMI stack, it is a normal NMI */
- jb first_nmi
- /* Ah, it is within the NMI stack, treat it as nested */
-
- CFI_REMEMBER_STATE
-
-nested_nmi:
- /*
- * Do nothing if we interrupted the fixup in repeat_nmi.
- * It's about to repeat the NMI handler, so we are fine
- * with ignoring this one.
- */
- movq $repeat_nmi, %rdx
- cmpq 8(%rsp), %rdx
- ja 1f
- movq $end_repeat_nmi, %rdx
- cmpq 8(%rsp), %rdx
- ja nested_nmi_out
-
-1:
- /* Set up the interrupted NMIs stack to jump to repeat_nmi */
- leaq -1*8(%rsp), %rdx
- movq %rdx, %rsp
- CFI_ADJUST_CFA_OFFSET 1*8
- leaq -10*8(%rsp), %rdx
- pushq_cfi $__KERNEL_DS
- pushq_cfi %rdx
- pushfq_cfi
- pushq_cfi $__KERNEL_CS
- pushq_cfi $repeat_nmi
-
- /* Put stack back */
- addq $(6*8), %rsp
- CFI_ADJUST_CFA_OFFSET -6*8
-
-nested_nmi_out:
- popq_cfi %rdx
- CFI_RESTORE rdx
-
- /* No need to check faults here */
- INTERRUPT_RETURN
-
- CFI_RESTORE_STATE
-first_nmi:
- /*
- * Because nested NMIs will use the pushed location that we
- * stored in rdx, we must keep that space available.
- * Here's what our stack frame will look like:
- * +-------------------------+
- * | original SS |
- * | original Return RSP |
- * | original RFLAGS |
- * | original CS |
- * | original RIP |
- * +-------------------------+
- * | temp storage for rdx |
- * +-------------------------+
- * | NMI executing variable |
- * +-------------------------+
- * | copied SS |
- * | copied Return RSP |
- * | copied RFLAGS |
- * | copied CS |
- * | copied RIP |
- * +-------------------------+
- * | Saved SS |
- * | Saved Return RSP |
- * | Saved RFLAGS |
- * | Saved CS |
- * | Saved RIP |
- * +-------------------------+
- * | pt_regs |
- * +-------------------------+
- *
- * The saved stack frame is used to fix up the copied stack frame
- * that a nested NMI may change to make the interrupted NMI iret jump
- * to the repeat_nmi. The original stack frame and the temp storage
- * is also used by nested NMIs and can not be trusted on exit.
- */
- /* Do not pop rdx, nested NMIs will corrupt that part of the stack */
- movq (%rsp), %rdx
- CFI_RESTORE rdx
-
- /* Set the NMI executing variable on the stack. */
- pushq_cfi $1
-
- /*
- * Leave room for the "copied" frame
- */
- subq $(5*8), %rsp
- CFI_ADJUST_CFA_OFFSET 5*8
-
- /* Copy the stack frame to the Saved frame */
- .rept 5
- pushq_cfi 11*8(%rsp)
- .endr
- CFI_DEF_CFA_OFFSET 5*8
-
- /* Everything up to here is safe from nested NMIs */
-
- /*
- * If there was a nested NMI, the first NMI's iret will return
- * here. But NMIs are still enabled and we can take another
- * nested NMI. The nested NMI checks the interrupted RIP to see
- * if it is between repeat_nmi and end_repeat_nmi, and if so
- * it will just return, as we are about to repeat an NMI anyway.
- * This makes it safe to copy to the stack frame that a nested
- * NMI will update.
- */
-repeat_nmi:
- /*
- * Update the stack variable to say we are still in NMI (the update
- * is benign for the non-repeat case, where 1 was pushed just above
- * to this very stack slot).
- */
- movq $1, 10*8(%rsp)
-
- /* Make another copy, this one may be modified by nested NMIs */
- addq $(10*8), %rsp
- CFI_ADJUST_CFA_OFFSET -10*8
- .rept 5
- pushq_cfi -6*8(%rsp)
- .endr
- subq $(5*8), %rsp
- CFI_DEF_CFA_OFFSET 5*8
-end_repeat_nmi:
-
- /*
- * Everything below this point can be preempted by a nested
- * NMI if the first NMI took an exception and reset our iret stack
- * so that we repeat another NMI.
- */
- pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
- ALLOC_PT_GPREGS_ON_STACK
-
- /*
- * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
- * as we should not be calling schedule in NMI context.
- * Even with normal interrupts enabled. An NMI should not be
- * setting NEED_RESCHED or anything that normal interrupts and
- * exceptions might do.
- */
- call paranoid_entry
- DEFAULT_FRAME 0
-
- /*
- * Save off the CR2 register. If we take a page fault in the NMI then
- * it could corrupt the CR2 value. If the NMI preempts a page fault
- * handler before it was able to read the CR2 register, and then the
- * NMI itself takes a page fault, the page fault that was preempted
- * will read the information from the NMI page fault and not the
- * origin fault. Save it off and restore it if it changes.
- * Use the r12 callee-saved register.
- */
- movq %cr2, %r12
-
- /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
- movq %rsp,%rdi
- movq $-1,%rsi
- call do_nmi
-
- /* Did the NMI take a page fault? Restore cr2 if it did */
- movq %cr2, %rcx
- cmpq %rcx, %r12
- je 1f
- movq %r12, %cr2
-1:
-
- testl %ebx,%ebx /* swapgs needed? */
- jnz nmi_restore
-nmi_swapgs:
- SWAPGS_UNSAFE_STACK
-nmi_restore:
- RESTORE_EXTRA_REGS
- RESTORE_C_REGS
- /* Pop the extra iret frame at once */
- REMOVE_PT_GPREGS_FROM_STACK 6*8
-
- /* Clear the NMI executing stack variable */
- movq $0, 5*8(%rsp)
- jmp irq_return
- CFI_ENDPROC
-END(nmi)
-
-ENTRY(ignore_sysret)
- CFI_STARTPROC
- mov $-ENOSYS,%eax
- sysret
- CFI_ENDPROC
-END(ignore_sysret)
-
--- /dev/null
+#
+# Build rules for the FPU support code:
+#
+
+obj-y += init.o bugs.o core.o regset.o signal.o xstate.o
--- /dev/null
+/*
+ * x86 FPU bug checks:
+ */
+#include <asm/fpu/internal.h>
+
+/*
+ * Boot time CPU/FPU FDIV bug detection code:
+ */
+
+static double __initdata x = 4195835.0;
+static double __initdata y = 3145727.0;
+
+/*
+ * This used to check for exceptions..
+ * However, it turns out that to support that,
+ * the XMM trap handlers basically had to
+ * be buggy. So let's have a correct XMM trap
+ * handler, and forget about printing out
+ * some status at boot.
+ *
+ * We should really only care about bugs here
+ * anyway. Not features.
+ */
+static void __init check_fpu(void)
+{
+ u32 cr0_saved;
+ s32 fdiv_bug;
+
+ /* We might have CR0::TS set already, clear it: */
+ cr0_saved = read_cr0();
+ write_cr0(cr0_saved & ~X86_CR0_TS);
+
+ kernel_fpu_begin();
+
+ /*
+ * trap_init() enabled FXSR and company _before_ testing for FP
+ * problems here.
+ *
+ * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
+ */
+ __asm__("fninit\n\t"
+ "fldl %1\n\t"
+ "fdivl %2\n\t"
+ "fmull %2\n\t"
+ "fldl %1\n\t"
+ "fsubp %%st,%%st(1)\n\t"
+ "fistpl %0\n\t"
+ "fwait\n\t"
+ "fninit"
+ : "=m" (*&fdiv_bug)
+ : "m" (*&x), "m" (*&y));
+
+ kernel_fpu_end();
+
+ write_cr0(cr0_saved);
+
+ if (fdiv_bug) {
+ set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
+ pr_warn("Hmm, FPU with FDIV bug\n");
+ }
+}
+
+void __init fpu__init_check_bugs(void)
+{
+ /*
+ * kernel_fpu_begin/end() in check_fpu() relies on the patched
+ * alternative instructions.
+ */
+ if (cpu_has_fpu)
+ check_fpu();
+}
--- /dev/null
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/regset.h>
+#include <asm/fpu/signal.h>
+#include <asm/traps.h>
+
+#include <linux/hardirq.h>
+
+/*
+ * Represents the initial FPU state. It's mostly (but not completely) zeroes,
+ * depending on the FPU hardware format:
+ */
+union fpregs_state init_fpstate __read_mostly;
+
+/*
+ * Track whether the kernel is using the FPU state
+ * currently.
+ *
+ * This flag is used:
+ *
+ * - by IRQ context code to potentially use the FPU
+ * if it's unused.
+ *
+ * - to debug kernel_fpu_begin()/end() correctness
+ */
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+/*
+ * Track which context is using the FPU on the CPU:
+ */
+DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+static void kernel_fpu_disable(void)
+{
+ WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
+ this_cpu_write(in_kernel_fpu, true);
+}
+
+static void kernel_fpu_enable(void)
+{
+ WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+ this_cpu_write(in_kernel_fpu, false);
+}
+
+static bool kernel_fpu_disabled(void)
+{
+ return this_cpu_read(in_kernel_fpu);
+}
+
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: the thread must not have fpu (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return true; in the likely case
+ * the thread has FPU but we are not going to set/clear TS.
+ */
+static bool interrupted_kernel_fpu_idle(void)
+{
+ if (kernel_fpu_disabled())
+ return false;
+
+ if (use_eager_fpu())
+ return true;
+
+ return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static bool interrupted_user_mode(void)
+{
+ struct pt_regs *regs = get_irq_regs();
+ return regs && user_mode(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+bool irq_fpu_usable(void)
+{
+ return !in_interrupt() ||
+ interrupted_user_mode() ||
+ interrupted_kernel_fpu_idle();
+}
+EXPORT_SYMBOL(irq_fpu_usable);
+
+void __kernel_fpu_begin(void)
+{
+ struct fpu *fpu = ¤t->thread.fpu;
+
+ WARN_ON_FPU(!irq_fpu_usable());
+
+ kernel_fpu_disable();
+
+ if (fpu->fpregs_active) {
+ copy_fpregs_to_fpstate(fpu);
+ } else {
+ this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+ __fpregs_activate_hw();
+ }
+}
+EXPORT_SYMBOL(__kernel_fpu_begin);
+
+void __kernel_fpu_end(void)
+{
+ struct fpu *fpu = ¤t->thread.fpu;
+
+ if (fpu->fpregs_active)
+ copy_kernel_to_fpregs(&fpu->state);
+ else
+ __fpregs_deactivate_hw();
+
+ kernel_fpu_enable();
+}
+EXPORT_SYMBOL(__kernel_fpu_end);
+
+void kernel_fpu_begin(void)
+{
+ preempt_disable();
+ __kernel_fpu_begin();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+ __kernel_fpu_end();
+ preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);
+
+/*
+ * CR0::TS save/restore functions:
+ */
+int irq_ts_save(void)
+{
+ /*
+ * If in process context and not atomic, we can take a spurious DNA fault.
+ * Otherwise, doing clts() in process context requires disabling preemption
+ * or some heavy lifting like kernel_fpu_begin()
+ */
+ if (!in_atomic())
+ return 0;
+
+ if (read_cr0() & X86_CR0_TS) {
+ clts();
+ return 1;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(irq_ts_save);
+
+void irq_ts_restore(int TS_state)
+{
+ if (TS_state)
+ stts();
+}
+EXPORT_SYMBOL_GPL(irq_ts_restore);
+
+/*
+ * Save the FPU state (mark it for reload if necessary):
+ *
+ * This only ever gets called for the current task.
+ */
+void fpu__save(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != ¤t->thread.fpu);
+
+ preempt_disable();
+ if (fpu->fpregs_active) {
+ if (!copy_fpregs_to_fpstate(fpu))
+ fpregs_deactivate(fpu);
+ }
+ preempt_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__save);
+
+/*
+ * Legacy x87 fpstate state init:
+ */
+static inline void fpstate_init_fstate(struct fregs_state *fp)
+{
+ fp->cwd = 0xffff037fu;
+ fp->swd = 0xffff0000u;
+ fp->twd = 0xffffffffu;
+ fp->fos = 0xffff0000u;
+}
+
+void fpstate_init(union fpregs_state *state)
+{
+ if (!cpu_has_fpu) {
+ fpstate_init_soft(&state->soft);
+ return;
+ }
+
+ memset(state, 0, xstate_size);
+
+ if (cpu_has_fxsr)
+ fpstate_init_fxstate(&state->fxsave);
+ else
+ fpstate_init_fstate(&state->fsave);
+}
+EXPORT_SYMBOL_GPL(fpstate_init);
+
+/*
+ * Copy the current task's FPU state to a new task's FPU context.
+ *
+ * In both the 'eager' and the 'lazy' case we save hardware registers
+ * directly to the destination buffer.
+ */
+static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+ WARN_ON_FPU(src_fpu != ¤t->thread.fpu);
+
+ /*
+ * Don't let 'init optimized' areas of the XSAVE area
+ * leak into the child task:
+ */
+ if (use_eager_fpu())
+ memset(&dst_fpu->state.xsave, 0, xstate_size);
+
+ /*
+ * Save current FPU registers directly into the child
+ * FPU context, without any memory-to-memory copying.
+ *
+ * If the FPU context got destroyed in the process (FNSAVE
+ * done on old CPUs) then copy it back into the source
+ * context and mark the current task for lazy restore.
+ *
+ * We have to do all this with preemption disabled,
+ * mostly because of the FNSAVE case, because in that
+ * case we must not allow preemption in the window
+ * between the FNSAVE and us marking the context lazy.
+ *
+ * It shouldn't be an issue as even FNSAVE is plenty
+ * fast in terms of critical section length.
+ */
+ preempt_disable();
+ if (!copy_fpregs_to_fpstate(dst_fpu)) {
+ memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
+ fpregs_deactivate(src_fpu);
+ }
+ preempt_enable();
+}
+
+int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+ dst_fpu->counter = 0;
+ dst_fpu->fpregs_active = 0;
+ dst_fpu->last_cpu = -1;
+
+ if (src_fpu->fpstate_active)
+ fpu_copy(dst_fpu, src_fpu);
+
+ return 0;
+}
+
+/*
+ * Activate the current task's in-memory FPU context,
+ * if it has not been used before:
+ */
+void fpu__activate_curr(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != ¤t->thread.fpu);
+
+ if (!fpu->fpstate_active) {
+ fpstate_init(&fpu->state);
+
+ /* Safe to do for the current task: */
+ fpu->fpstate_active = 1;
+ }
+}
+EXPORT_SYMBOL_GPL(fpu__activate_curr);
+
+/*
+ * This function must be called before we read a task's fpstate.
+ *
+ * If the task has not used the FPU before then initialize its
+ * fpstate.
+ *
+ * If the task has used the FPU before then save it.
+ */
+void fpu__activate_fpstate_read(struct fpu *fpu)
+{
+ /*
+ * If fpregs are active (in the current CPU), then
+ * copy them to the fpstate:
+ */
+ if (fpu->fpregs_active) {
+ fpu__save(fpu);
+ } else {
+ if (!fpu->fpstate_active) {
+ fpstate_init(&fpu->state);
+
+ /* Safe to do for current and for stopped child tasks: */
+ fpu->fpstate_active = 1;
+ }
+ }
+}
+
+/*
+ * This function must be called before we write a task's fpstate.
+ *
+ * If the task has used the FPU before then unlazy it.
+ * If the task has not used the FPU before then initialize its fpstate.
+ *
+ * After this function call, after registers in the fpstate are
+ * modified and the child task has woken up, the child task will
+ * restore the modified FPU state from the modified context. If we
+ * didn't clear its lazy status here then the lazy in-registers
+ * state pending on its former CPU could be restored, corrupting
+ * the modifications.
+ */
+void fpu__activate_fpstate_write(struct fpu *fpu)
+{
+ /*
+ * Only stopped child tasks can be used to modify the FPU
+ * state in the fpstate buffer:
+ */
+ WARN_ON_FPU(fpu == ¤t->thread.fpu);
+
+ if (fpu->fpstate_active) {
+ /* Invalidate any lazy state: */
+ fpu->last_cpu = -1;
+ } else {
+ fpstate_init(&fpu->state);
+
+ /* Safe to do for stopped child tasks: */
+ fpu->fpstate_active = 1;
+ }
+}
+
+/*
+ * 'fpu__restore()' is called to copy FPU registers from
+ * the FPU fpstate to the live hw registers and to activate
+ * access to the hardware registers, so that FPU instructions
+ * can be used afterwards.
+ *
+ * Must be called with kernel preemption disabled (for example
+ * with local interrupts disabled, as it is in the case of
+ * do_device_not_available()).
+ */
+void fpu__restore(struct fpu *fpu)
+{
+ fpu__activate_curr(fpu);
+
+ /* Avoid __kernel_fpu_begin() right after fpregs_activate() */
+ kernel_fpu_disable();
+ fpregs_activate(fpu);
+ copy_kernel_to_fpregs(&fpu->state);
+ fpu->counter++;
+ kernel_fpu_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__restore);
+
+/*
+ * Drops current FPU state: deactivates the fpregs and
+ * the fpstate. NOTE: it still leaves previous contents
+ * in the fpregs in the eager-FPU case.
+ *
+ * This function can be used in cases where we know that
+ * a state-restore is coming: either an explicit one,
+ * or a reschedule.
+ */
+void fpu__drop(struct fpu *fpu)
+{
+ preempt_disable();
+ fpu->counter = 0;
+
+ if (fpu->fpregs_active) {
+ /* Ignore delayed exceptions from user space */
+ asm volatile("1: fwait\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b));
+ fpregs_deactivate(fpu);
+ }
+
+ fpu->fpstate_active = 0;
+
+ preempt_enable();
+}
+
+/*
+ * Clear FPU registers by setting them up from
+ * the init fpstate:
+ */
+static inline void copy_init_fpstate_to_fpregs(void)
+{
+ if (use_xsave())
+ copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+ else
+ copy_kernel_to_fxregs(&init_fpstate.fxsave);
+}
+
+/*
+ * Clear the FPU state back to init state.
+ *
+ * Called by sys_execve(), by the signal handler code and by various
+ * error paths.
+ */
+void fpu__clear(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */
+
+ if (!use_eager_fpu()) {
+ /* FPU state will be reallocated lazily at the first use. */
+ fpu__drop(fpu);
+ } else {
+ if (!fpu->fpstate_active) {
+ fpu__activate_curr(fpu);
+ user_fpu_begin();
+ }
+ copy_init_fpstate_to_fpregs();
+ }
+}
+
+/*
+ * x87 math exception handling:
+ */
+
+static inline unsigned short get_fpu_cwd(struct fpu *fpu)
+{
+ if (cpu_has_fxsr) {
+ return fpu->state.fxsave.cwd;
+ } else {
+ return (unsigned short)fpu->state.fsave.cwd;
+ }
+}
+
+static inline unsigned short get_fpu_swd(struct fpu *fpu)
+{
+ if (cpu_has_fxsr) {
+ return fpu->state.fxsave.swd;
+ } else {
+ return (unsigned short)fpu->state.fsave.swd;
+ }
+}
+
+static inline unsigned short get_fpu_mxcsr(struct fpu *fpu)
+{
+ if (cpu_has_xmm) {
+ return fpu->state.fxsave.mxcsr;
+ } else {
+ return MXCSR_DEFAULT;
+ }
+}
+
+int fpu__exception_code(struct fpu *fpu, int trap_nr)
+{
+ int err;
+
+ if (trap_nr == X86_TRAP_MF) {
+ unsigned short cwd, swd;
+ /*
+ * (~cwd & swd) will mask out exceptions that are not set to unmasked
+ * status. 0x3f is the exception bits in these regs, 0x200 is the
+ * C1 reg you need in case of a stack fault, 0x040 is the stack
+ * fault bit. We should only be taking one exception at a time,
+ * so if this combination doesn't produce any single exception,
+ * then we have a bad program that isn't synchronizing its FPU usage
+ * and it will suffer the consequences since we won't be able to
+ * fully reproduce the context of the exception
+ */
+ cwd = get_fpu_cwd(fpu);
+ swd = get_fpu_swd(fpu);
+
+ err = swd & ~cwd;
+ } else {
+ /*
+ * The SIMD FPU exceptions are handled a little differently, as there
+ * is only a single status/control register. Thus, to determine which
+ * unmasked exception was caught we must mask the exception mask bits
+ * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+ */
+ unsigned short mxcsr = get_fpu_mxcsr(fpu);
+ err = ~(mxcsr >> 7) & mxcsr;
+ }
+
+ if (err & 0x001) { /* Invalid op */
+ /*
+ * swd & 0x240 == 0x040: Stack Underflow
+ * swd & 0x240 == 0x240: Stack Overflow
+ * User must clear the SF bit (0x40) if set
+ */
+ return FPE_FLTINV;
+ } else if (err & 0x004) { /* Divide by Zero */
+ return FPE_FLTDIV;
+ } else if (err & 0x008) { /* Overflow */
+ return FPE_FLTOVF;
+ } else if (err & 0x012) { /* Denormal, Underflow */
+ return FPE_FLTUND;
+ } else if (err & 0x020) { /* Precision */
+ return FPE_FLTRES;
+ }
+
+ /*
+ * If we're using IRQ 13, or supposedly even some trap
+ * X86_TRAP_MF implementations, it's possible
+ * we get a spurious trap, which is not an error.
+ */
+ return 0;
+}
--- /dev/null
+/*
+ * x86 FPU boot time init code:
+ */
+#include <asm/fpu/internal.h>
+#include <asm/tlbflush.h>
+
+/*
+ * Initialize the TS bit in CR0 according to the style of context-switches
+ * we are using:
+ */
+static void fpu__init_cpu_ctx_switch(void)
+{
+ if (!cpu_has_eager_fpu)
+ stts();
+ else
+ clts();
+}
+
+/*
+ * Initialize the registers found in all CPUs, CR0 and CR4:
+ */
+static void fpu__init_cpu_generic(void)
+{
+ unsigned long cr0;
+ unsigned long cr4_mask = 0;
+
+ if (cpu_has_fxsr)
+ cr4_mask |= X86_CR4_OSFXSR;
+ if (cpu_has_xmm)
+ cr4_mask |= X86_CR4_OSXMMEXCPT;
+ if (cr4_mask)
+ cr4_set_bits(cr4_mask);
+
+ cr0 = read_cr0();
+ cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+ if (!cpu_has_fpu)
+ cr0 |= X86_CR0_EM;
+ write_cr0(cr0);
+
+ /* Flush out any pending x87 state: */
+ asm volatile ("fninit");
+}
+
+/*
+ * Enable all supported FPU features. Called when a CPU is brought online:
+ */
+void fpu__init_cpu(void)
+{
+ fpu__init_cpu_generic();
+ fpu__init_cpu_xstate();
+ fpu__init_cpu_ctx_switch();
+}
+
+/*
+ * The earliest FPU detection code.
+ *
+ * Set the X86_FEATURE_FPU CPU-capability bit based on
+ * trying to execute an actual sequence of FPU instructions:
+ */
+static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+{
+ unsigned long cr0;
+ u16 fsw, fcw;
+
+ fsw = fcw = 0xffff;
+
+ cr0 = read_cr0();
+ cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
+ write_cr0(cr0);
+
+ asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+ : "+m" (fsw), "+m" (fcw));
+
+ if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+ set_cpu_cap(c, X86_FEATURE_FPU);
+ else
+ clear_cpu_cap(c, X86_FEATURE_FPU);
+
+#ifndef CONFIG_MATH_EMULATION
+ if (!cpu_has_fpu) {
+ pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
+ for (;;)
+ asm volatile("hlt");
+ }
+#endif
+}
+
+/*
+ * Boot time FPU feature detection code:
+ */
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+
+static void __init fpu__init_system_mxcsr(void)
+{
+ unsigned int mask = 0;
+
+ if (cpu_has_fxsr) {
+ struct fxregs_state fx_tmp __aligned(32) = { };
+
+ asm volatile("fxsave %0" : "+m" (fx_tmp));
+
+ mask = fx_tmp.mxcsr_mask;
+
+ /*
+ * If zero then use the default features mask,
+ * which has all features set, except the
+ * denormals-are-zero feature bit:
+ */
+ if (mask == 0)
+ mask = 0x0000ffbf;
+ }
+ mxcsr_feature_mask &= mask;
+}
+
+/*
+ * Once per bootup FPU initialization sequences that will run on most x86 CPUs:
+ */
+static void __init fpu__init_system_generic(void)
+{
+ /*
+ * Set up the legacy init FPU context. (xstate init might overwrite this
+ * with a more modern format, if the CPU supports it.)
+ */
+ fpstate_init_fxstate(&init_fpstate.fxsave);
+
+ fpu__init_system_mxcsr();
+}
+
+/*
+ * Size of the FPU context state. All tasks in the system use the
+ * same context size, regardless of what portion they use.
+ * This is inherent to the XSAVE architecture which puts all state
+ * components into a single, continuous memory block:
+ */
+unsigned int xstate_size;
+EXPORT_SYMBOL_GPL(xstate_size);
+
+/*
+ * Set up the xstate_size based on the legacy FPU context size.
+ *
+ * We set this up first, and later it will be overwritten by
+ * fpu__init_system_xstate() if the CPU knows about xstates.
+ */
+static void __init fpu__init_system_xstate_size_legacy(void)
+{
+ static int on_boot_cpu = 1;
+
+ WARN_ON_FPU(!on_boot_cpu);
+ on_boot_cpu = 0;
+
+ /*
+ * Note that xstate_size might be overwriten later during
+ * fpu__init_system_xstate().
+ */
+
+ if (!cpu_has_fpu) {
+ /*
+ * Disable xsave as we do not support it if i387
+ * emulation is enabled.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+ xstate_size = sizeof(struct swregs_state);
+ } else {
+ if (cpu_has_fxsr)
+ xstate_size = sizeof(struct fxregs_state);
+ else
+ xstate_size = sizeof(struct fregs_state);
+ }
+ /*
+ * Quirk: we don't yet handle the XSAVES* instructions
+ * correctly, as we don't correctly convert between
+ * standard and compacted format when interfacing
+ * with user-space - so disable it for now.
+ *
+ * The difference is small: with recent CPUs the
+ * compacted format is only marginally smaller than
+ * the standard FPU state format.
+ *
+ * ( This is easy to backport while we are fixing
+ * XSAVES* support. )
+ */
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+}
+
+/*
+ * FPU context switching strategies:
+ *
+ * Against popular belief, we don't do lazy FPU saves, due to the
+ * task migration complications it brings on SMP - we only do
+ * lazy FPU restores.
+ *
+ * 'lazy' is the traditional strategy, which is based on setting
+ * CR0::TS to 1 during context-switch (instead of doing a full
+ * restore of the FPU state), which causes the first FPU instruction
+ * after the context switch (whenever it is executed) to fault - at
+ * which point we lazily restore the FPU state into FPU registers.
+ *
+ * Tasks are of course under no obligation to execute FPU instructions,
+ * so it can easily happen that another context-switch occurs without
+ * a single FPU instruction being executed. If we eventually switch
+ * back to the original task (that still owns the FPU) then we have
+ * not only saved the restores along the way, but we also have the
+ * FPU ready to be used for the original task.
+ *
+ * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * state during every context switch, regardless of whether the task
+ * has used FPU instructions in that time slice or not. This is done
+ * because modern FPU context saving instructions are able to optimize
+ * state saving and restoration in hardware: they can detect both
+ * unused and untouched FPU state and optimize accordingly.
+ *
+ * [ Note that even in 'lazy' mode we might optimize context switches
+ * to use 'eager' restores, if we detect that a task is using the FPU
+ * frequently. See the fpu->counter logic in fpu/internal.h for that. ]
+ */
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+
+static int __init eager_fpu_setup(char *s)
+{
+ if (!strcmp(s, "on"))
+ eagerfpu = ENABLE;
+ else if (!strcmp(s, "off"))
+ eagerfpu = DISABLE;
+ else if (!strcmp(s, "auto"))
+ eagerfpu = AUTO;
+ return 1;
+}
+__setup("eagerfpu=", eager_fpu_setup);
+
+/*
+ * Pick the FPU context switching strategy:
+ */
+static void __init fpu__init_system_ctx_switch(void)
+{
+ static bool on_boot_cpu = 1;
+
+ WARN_ON_FPU(!on_boot_cpu);
+ on_boot_cpu = 0;
+
+ WARN_ON_FPU(current->thread.fpu.fpstate_active);
+ current_thread_info()->status = 0;
+
+ /* Auto enable eagerfpu for xsaveopt */
+ if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+ eagerfpu = ENABLE;
+
+ if (xfeatures_mask & XSTATE_EAGER) {
+ if (eagerfpu == DISABLE) {
+ pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
+ xfeatures_mask & XSTATE_EAGER);
+ xfeatures_mask &= ~XSTATE_EAGER;
+ } else {
+ eagerfpu = ENABLE;
+ }
+ }
+
+ if (eagerfpu == ENABLE)
+ setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+
+ printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy");
+}
+
+/*
+ * Called on the boot CPU once per system bootup, to set up the initial
+ * FPU state that is later cloned into all processes:
+ */
+void __init fpu__init_system(struct cpuinfo_x86 *c)
+{
+ fpu__init_system_early_generic(c);
+
+ /*
+ * The FPU has to be operational for some of the
+ * later FPU init activities:
+ */
+ fpu__init_cpu();
+
+ /*
+ * But don't leave CR0::TS set yet, as some of the FPU setup
+ * methods depend on being able to execute FPU instructions
+ * that will fault on a set TS, such as the FXSAVE in
+ * fpu__init_system_mxcsr().
+ */
+ clts();
+
+ fpu__init_system_generic();
+ fpu__init_system_xstate_size_legacy();
+ fpu__init_system_xstate();
+
+ fpu__init_system_ctx_switch();
+}
+
+/*
+ * Boot parameter to turn off FPU support and fall back to math-emu:
+ */
+static int __init no_387(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_FPU);
+ return 1;
+}
+__setup("no387", no_387);
+
+/*
+ * Disable all xstate CPU features:
+ */
+static int __init x86_noxsave_setup(char *s)
+{
+ if (strlen(s))
+ return 0;
+
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+ setup_clear_cpu_cap(X86_FEATURE_AVX);
+ setup_clear_cpu_cap(X86_FEATURE_AVX2);
+
+ return 1;
+}
+__setup("noxsave", x86_noxsave_setup);
+
+/*
+ * Disable the XSAVEOPT instruction specifically:
+ */
+static int __init x86_noxsaveopt_setup(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+ return 1;
+}
+__setup("noxsaveopt", x86_noxsaveopt_setup);
+
+/*
+ * Disable the XSAVES instruction:
+ */
+static int __init x86_noxsaves_setup(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+
+ return 1;
+}
+__setup("noxsaves", x86_noxsaves_setup);
+
+/*
+ * Disable FX save/restore and SSE support:
+ */
+static int __init x86_nofxsr_setup(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_FXSR);
+ setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
+ setup_clear_cpu_cap(X86_FEATURE_XMM);
+
+ return 1;
+}
+__setup("nofxsr", x86_nofxsr_setup);
--- /dev/null
+/*
+ * FPU register's regset abstraction, for ptrace, core dumps, etc.
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+/*
+ * The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
+ * as the "regset->n" for the xstate regset will be updated based on the feature
+ * capabilites supported by the xsave.
+ */
+int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+ struct fpu *target_fpu = &target->thread.fpu;
+
+ return target_fpu->fpstate_active ? regset->n : 0;
+}
+
+int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+ struct fpu *target_fpu = &target->thread.fpu;
+
+ return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0;
+}
+
+int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+
+ if (!cpu_has_fxsr)
+ return -ENODEV;
+
+ fpu__activate_fpstate_read(fpu);
+ fpstate_sanitize_xstate(fpu);
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &fpu->state.fxsave, 0, -1);
+}
+
+int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ int ret;
+
+ if (!cpu_has_fxsr)
+ return -ENODEV;
+
+ fpu__activate_fpstate_write(fpu);
+ fpstate_sanitize_xstate(fpu);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &fpu->state.fxsave, 0, -1);
+
+ /*
+ * mxcsr reserved bits must be masked to zero for security reasons.
+ */
+ fpu->state.fxsave.mxcsr &= mxcsr_feature_mask;
+
+ /*
+ * update the header bits in the xsave header, indicating the
+ * presence of FP and SSE state.
+ */
+ if (cpu_has_xsave)
+ fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE;
+
+ return ret;
+}
+
+int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct xregs_state *xsave;
+ int ret;
+
+ if (!cpu_has_xsave)
+ return -ENODEV;
+
+ fpu__activate_fpstate_read(fpu);
+
+ xsave = &fpu->state.xsave;
+
+ /*
+ * Copy the 48bytes defined by the software first into the xstate
+ * memory layout in the thread struct, so that we can copy the entire
+ * xstateregs to the user using one user_regset_copyout().
+ */
+ memcpy(&xsave->i387.sw_reserved,
+ xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
+ /*
+ * Copy the xstate memory layout.
+ */
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+ return ret;
+}
+
+int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct xregs_state *xsave;
+ int ret;
+
+ if (!cpu_has_xsave)
+ return -ENODEV;
+
+ fpu__activate_fpstate_write(fpu);
+
+ xsave = &fpu->state.xsave;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+ /*
+ * mxcsr reserved bits must be masked to zero for security reasons.
+ */
+ xsave->i387.mxcsr &= mxcsr_feature_mask;
+ xsave->header.xfeatures &= xfeatures_mask;
+ /*
+ * These bits must be zero.
+ */
+ memset(&xsave->header.reserved, 0, 48);
+
+ return ret;
+}
+
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
+{
+ unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+ /* Transform each pair of bits into 01 (valid) or 00 (empty) */
+ tmp = ~twd;
+ tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+ /* and move the valid bits to the lower byte. */
+ tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+ tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+ tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+
+ return tmp;
+}
+
+#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16)
+#define FP_EXP_TAG_VALID 0
+#define FP_EXP_TAG_ZERO 1
+#define FP_EXP_TAG_SPECIAL 2
+#define FP_EXP_TAG_EMPTY 3
+
+static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave)
+{
+ struct _fpxreg *st;
+ u32 tos = (fxsave->swd >> 11) & 7;
+ u32 twd = (unsigned long) fxsave->twd;
+ u32 tag;
+ u32 ret = 0xffff0000u;
+ int i;
+
+ for (i = 0; i < 8; i++, twd >>= 1) {
+ if (twd & 0x1) {
+ st = FPREG_ADDR(fxsave, (i - tos) & 7);
+
+ switch (st->exponent & 0x7fff) {
+ case 0x7fff:
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ case 0x0000:
+ if (!st->significand[0] &&
+ !st->significand[1] &&
+ !st->significand[2] &&
+ !st->significand[3])
+ tag = FP_EXP_TAG_ZERO;
+ else
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ default:
+ if (st->significand[3] & 0x8000)
+ tag = FP_EXP_TAG_VALID;
+ else
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ }
+ } else {
+ tag = FP_EXP_TAG_EMPTY;
+ }
+ ret |= tag << (2 * i);
+ }
+ return ret;
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+void
+convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
+{
+ struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+ struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
+ struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
+ int i;
+
+ env->cwd = fxsave->cwd | 0xffff0000u;
+ env->swd = fxsave->swd | 0xffff0000u;
+ env->twd = twd_fxsr_to_i387(fxsave);
+
+#ifdef CONFIG_X86_64
+ env->fip = fxsave->rip;
+ env->foo = fxsave->rdp;
+ /*
+ * should be actually ds/cs at fpu exception time, but
+ * that information is not available in 64bit mode.
+ */
+ env->fcs = task_pt_regs(tsk)->cs;
+ if (tsk == current) {
+ savesegment(ds, env->fos);
+ } else {
+ env->fos = tsk->thread.ds;
+ }
+ env->fos |= 0xffff0000;
+#else
+ env->fip = fxsave->fip;
+ env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
+ env->foo = fxsave->foo;
+ env->fos = fxsave->fos;
+#endif
+
+ for (i = 0; i < 8; ++i)
+ memcpy(&to[i], &from[i], sizeof(to[0]));
+}
+
+void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env)
+
+{
+ struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+ struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
+ struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
+ int i;
+
+ fxsave->cwd = env->cwd;
+ fxsave->swd = env->swd;
+ fxsave->twd = twd_i387_to_fxsr(env->twd);
+ fxsave->fop = (u16) ((u32) env->fcs >> 16);
+#ifdef CONFIG_X86_64
+ fxsave->rip = env->fip;
+ fxsave->rdp = env->foo;
+ /* cs and ds ignored */
+#else
+ fxsave->fip = env->fip;
+ fxsave->fcs = (env->fcs & 0xffff);
+ fxsave->foo = env->foo;
+ fxsave->fos = env->fos;
+#endif
+
+ for (i = 0; i < 8; ++i)
+ memcpy(&to[i], &from[i], sizeof(from[0]));
+}
+
+int fpregs_get(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct user_i387_ia32_struct env;
+
+ fpu__activate_fpstate_read(fpu);
+
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
+
+ if (!cpu_has_fxsr)
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &fpu->state.fsave, 0,
+ -1);
+
+ fpstate_sanitize_xstate(fpu);
+
+ if (kbuf && pos == 0 && count == sizeof(env)) {
+ convert_from_fxsr(kbuf, target);
+ return 0;
+ }
+
+ convert_from_fxsr(&env, target);
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+}
+
+int fpregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct user_i387_ia32_struct env;
+ int ret;
+
+ fpu__activate_fpstate_write(fpu);
+ fpstate_sanitize_xstate(fpu);
+
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
+
+ if (!cpu_has_fxsr)
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &fpu->state.fsave, 0,
+ -1);
+
+ if (pos > 0 || count < sizeof(env))
+ convert_from_fxsr(&env, target);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+ if (!ret)
+ convert_to_fxsr(target, &env);
+
+ /*
+ * update the header bit in the xsave header, indicating the
+ * presence of FP.
+ */
+ if (cpu_has_xsave)
+ fpu->state.xsave.header.xfeatures |= XSTATE_FP;
+ return ret;
+}
+
+/*
+ * FPU state for core dumps.
+ * This is only used for a.out dumps now.
+ * It is declared generically using elf_fpregset_t (which is
+ * struct user_i387_struct) but is in fact only used for 32-bit
+ * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
+ */
+int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
+{
+ struct task_struct *tsk = current;
+ struct fpu *fpu = &tsk->thread.fpu;
+ int fpvalid;
+
+ fpvalid = fpu->fpstate_active;
+ if (fpvalid)
+ fpvalid = !fpregs_get(tsk, NULL,
+ 0, sizeof(struct user_i387_ia32_struct),
+ ufpu, NULL);
+
+ return fpvalid;
+}
+EXPORT_SYMBOL(dump_fpu);
+
+#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
--- /dev/null
+/*
+ * FPU signal frame handling routines.
+ */
+
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/sigframe.h>
+
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
+
+/*
+ * Check for the presence of extended state information in the
+ * user fpstate pointer in the sigcontext.
+ */
+static inline int check_for_xstate(struct fxregs_state __user *buf,
+ void __user *fpstate,
+ struct _fpx_sw_bytes *fx_sw)
+{
+ int min_xstate_size = sizeof(struct fxregs_state) +
+ sizeof(struct xstate_header);
+ unsigned int magic2;
+
+ if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+ return -1;
+
+ /* Check for the first magic field and other error scenarios. */
+ if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+ fx_sw->xstate_size < min_xstate_size ||
+ fx_sw->xstate_size > xstate_size ||
+ fx_sw->xstate_size > fx_sw->extended_size)
+ return -1;
+
+ /*
+ * Check for the presence of second magic word at the end of memory
+ * layout. This detects the case where the user just copied the legacy
+ * fpstate layout with out copying the extended state information
+ * in the memory layout.
+ */
+ if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+ || magic2 != FP_XSTATE_MAGIC2)
+ return -1;
+
+ return 0;
+}
+
+/*
+ * Signal frame handlers.
+ */
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
+{
+ if (use_fxsr()) {
+ struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+ struct user_i387_ia32_struct env;
+ struct _fpstate_ia32 __user *fp = buf;
+
+ convert_from_fxsr(&env, tsk);
+
+ if (__copy_to_user(buf, &env, sizeof(env)) ||
+ __put_user(xsave->i387.swd, &fp->status) ||
+ __put_user(X86_FXSR_MAGIC, &fp->magic))
+ return -1;
+ } else {
+ struct fregs_state __user *fp = buf;
+ u32 swd;
+ if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
+ return -1;
+ }
+
+ return 0;
+}
+
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
+{
+ struct xregs_state __user *x = buf;
+ struct _fpx_sw_bytes *sw_bytes;
+ u32 xfeatures;
+ int err;
+
+ /* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+ sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+ err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
+
+ if (!use_xsave())
+ return err;
+
+ err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
+
+ /*
+ * Read the xfeatures which we copied (directly from the cpu or
+ * from the state in task struct) to the user buffers.
+ */
+ err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+ /*
+ * For legacy compatible, we always set FP/SSE bits in the bit
+ * vector while saving the state to the user context. This will
+ * enable us capturing any changes(during sigreturn) to
+ * the FP/SSE bits by the legacy applications which don't touch
+ * xfeatures in the xsave header.
+ *
+ * xsave aware apps can change the xfeatures in the xsave
+ * header as well as change any contents in the memory layout.
+ * xrestore as part of sigreturn will capture all the changes.
+ */
+ xfeatures |= XSTATE_FPSSE;
+
+ err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+ return err;
+}
+
+static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
+{
+ int err;
+
+ if (use_xsave())
+ err = copy_xregs_to_user(buf);
+ else if (use_fxsr())
+ err = copy_fxregs_to_user((struct fxregs_state __user *) buf);
+ else
+ err = copy_fregs_to_user((struct fregs_state __user *) buf);
+
+ if (unlikely(err) && __clear_user(buf, xstate_size))
+ err = -EFAULT;
+ return err;
+}
+
+/*
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ * state is copied.
+ * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ * buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ * buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
+ */
+int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+{
+ struct xregs_state *xsave = ¤t->thread.fpu.state.xsave;
+ struct task_struct *tsk = current;
+ int ia32_fxstate = (buf != buf_fx);
+
+ ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+ config_enabled(CONFIG_IA32_EMULATION));
+
+ if (!access_ok(VERIFY_WRITE, buf, size))
+ return -EACCES;
+
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return fpregs_soft_get(current, NULL, 0,
+ sizeof(struct user_i387_ia32_struct), NULL,
+ (struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+ if (fpregs_active()) {
+ /* Save the live register state to the user directly. */
+ if (copy_fpregs_to_sigframe(buf_fx))
+ return -1;
+ /* Update the thread's fxstate to save the fsave header. */
+ if (ia32_fxstate)
+ copy_fxregs_to_kernel(&tsk->thread.fpu);
+ } else {
+ fpstate_sanitize_xstate(&tsk->thread.fpu);
+ if (__copy_to_user(buf_fx, xsave, xstate_size))
+ return -1;
+ }
+
+ /* Save the fsave header for the 32-bit frames. */
+ if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+ return -1;
+
+ if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+ return -1;
+
+ return 0;
+}
+
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+ struct user_i387_ia32_struct *ia32_env,
+ u64 xfeatures, int fx_only)
+{
+ struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+ struct xstate_header *header = &xsave->header;
+
+ if (use_xsave()) {
+ /* These bits must be zero. */
+ memset(header->reserved, 0, 48);
+
+ /*
+ * Init the state that is not present in the memory
+ * layout and not enabled by the OS.
+ */
+ if (fx_only)
+ header->xfeatures = XSTATE_FPSSE;
+ else
+ header->xfeatures &= (xfeatures_mask & xfeatures);
+ }
+
+ if (use_fxsr()) {
+ /*
+ * mscsr reserved bits must be masked to zero for security
+ * reasons.
+ */
+ xsave->i387.mxcsr &= mxcsr_feature_mask;
+
+ convert_to_fxsr(tsk, ia32_env);
+ }
+}
+
+/*
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
+ */
+static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
+{
+ if (use_xsave()) {
+ if ((unsigned long)buf % 64 || fx_only) {
+ u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE;
+ copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+ return copy_user_to_fxregs(buf);
+ } else {
+ u64 init_bv = xfeatures_mask & ~xbv;
+ if (unlikely(init_bv))
+ copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+ return copy_user_to_xregs(buf, xbv);
+ }
+ } else if (use_fxsr()) {
+ return copy_user_to_fxregs(buf);
+ } else
+ return copy_user_to_fregs(buf);
+}
+
+static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
+{
+ int ia32_fxstate = (buf != buf_fx);
+ struct task_struct *tsk = current;
+ struct fpu *fpu = &tsk->thread.fpu;
+ int state_size = xstate_size;
+ u64 xfeatures = 0;
+ int fx_only = 0;
+
+ ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+ config_enabled(CONFIG_IA32_EMULATION));
+
+ if (!buf) {
+ fpu__clear(fpu);
+ return 0;
+ }
+
+ if (!access_ok(VERIFY_READ, buf, size))
+ return -EACCES;
+
+ fpu__activate_curr(fpu);
+
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return fpregs_soft_set(current, NULL,
+ 0, sizeof(struct user_i387_ia32_struct),
+ NULL, buf) != 0;
+
+ if (use_xsave()) {
+ struct _fpx_sw_bytes fx_sw_user;
+ if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+ /*
+ * Couldn't find the extended state information in the
+ * memory layout. Restore just the FP/SSE and init all
+ * the other extended state.
+ */
+ state_size = sizeof(struct fxregs_state);
+ fx_only = 1;
+ } else {
+ state_size = fx_sw_user.xstate_size;
+ xfeatures = fx_sw_user.xfeatures;
+ }
+ }
+
+ if (ia32_fxstate) {
+ /*
+ * For 32-bit frames with fxstate, copy the user state to the
+ * thread's fpu state, reconstruct fxstate from the fsave
+ * header. Sanitize the copied state etc.
+ */
+ struct fpu *fpu = &tsk->thread.fpu;
+ struct user_i387_ia32_struct env;
+ int err = 0;
+
+ /*
+ * Drop the current fpu which clears fpu->fpstate_active. This ensures
+ * that any context-switch during the copy of the new state,
+ * avoids the intermediate state from getting restored/saved.
+ * Thus avoiding the new restored state from getting corrupted.
+ * We will be ready to restore/save the state only after
+ * fpu->fpstate_active is again set.
+ */
+ fpu__drop(fpu);
+
+ if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) ||
+ __copy_from_user(&env, buf, sizeof(env))) {
+ fpstate_init(&fpu->state);
+ err = -1;
+ } else {
+ sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
+ }
+
+ fpu->fpstate_active = 1;
+ if (use_eager_fpu()) {
+ preempt_disable();
+ fpu__restore(fpu);
+ preempt_enable();
+ }
+
+ return err;
+ } else {
+ /*
+ * For 64-bit frames and 32-bit fsave frames, restore the user
+ * state to the registers directly (with exceptions handled).
+ */
+ user_fpu_begin();
+ if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
+ fpu__clear(fpu);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static inline int xstate_sigframe_size(void)
+{
+ return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+/*
+ * Restore FPU state from a sigframe:
+ */
+int fpu__restore_sig(void __user *buf, int ia32_frame)
+{
+ void __user *buf_fx = buf;
+ int size = xstate_sigframe_size();
+
+ if (ia32_frame && use_fxsr()) {
+ buf_fx = buf + sizeof(struct fregs_state);
+ size += sizeof(struct fregs_state);
+ }
+
+ return __fpu__restore_sig(buf, buf_fx, size);
+}
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+ unsigned long *buf_fx, unsigned long *size)
+{
+ unsigned long frame_size = xstate_sigframe_size();
+
+ *buf_fx = sp = round_down(sp - frame_size, 64);
+ if (ia32_frame && use_fxsr()) {
+ frame_size += sizeof(struct fregs_state);
+ sp -= sizeof(struct fregs_state);
+ }
+
+ *size = frame_size;
+
+ return sp;
+}
+/*
+ * Prepare the SW reserved portion of the fxsave memory layout, indicating
+ * the presence of the extended state information in the memory layout
+ * pointed by the fpstate pointer in the sigcontext.
+ * This will be saved when ever the FP and extended state context is
+ * saved on the user stack during the signal handler delivery to the user.
+ */
+void fpu__init_prepare_fx_sw_frame(void)
+{
+ int fsave_header_size = sizeof(struct fregs_state);
+ int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
+
+ if (config_enabled(CONFIG_X86_32))
+ size += fsave_header_size;
+
+ fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
+ fx_sw_reserved.extended_size = size;
+ fx_sw_reserved.xfeatures = xfeatures_mask;
+ fx_sw_reserved.xstate_size = xstate_size;
+
+ if (config_enabled(CONFIG_IA32_EMULATION)) {
+ fx_sw_reserved_ia32 = fx_sw_reserved;
+ fx_sw_reserved_ia32.extended_size += fsave_header_size;
+ }
+}
+
--- /dev/null
+/*
+ * xsave/xrstor support.
+ *
+ * Author: Suresh Siddha <suresh.b.siddha@intel.com>
+ */
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/api.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/tlbflush.h>
+
+static const char *xfeature_names[] =
+{
+ "x87 floating point registers" ,
+ "SSE registers" ,
+ "AVX registers" ,
+ "MPX bounds registers" ,
+ "MPX CSR" ,
+ "AVX-512 opmask" ,
+ "AVX-512 Hi256" ,
+ "AVX-512 ZMM_Hi256" ,
+ "unknown xstate feature" ,
+};
+
+/*
+ * Mask of xstate features supported by the CPU and the kernel:
+ */
+u64 xfeatures_mask __read_mostly;
+
+static unsigned int xstate_offsets[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_sizes[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
+
+/* The number of supported xfeatures in xfeatures_mask: */
+static unsigned int xfeatures_nr;
+
+/*
+ * Return whether the system supports a given xfeature.
+ *
+ * Also return the name of the (most advanced) feature that the caller requested:
+ */
+int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
+{
+ u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+
+ if (unlikely(feature_name)) {
+ long xfeature_idx, max_idx;
+ u64 xfeatures_print;
+ /*
+ * So we use FLS here to be able to print the most advanced
+ * feature that was requested but is missing. So if a driver
+ * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the
+ * missing AVX feature - this is the most informative message
+ * to users:
+ */
+ if (xfeatures_missing)
+ xfeatures_print = xfeatures_missing;
+ else
+ xfeatures_print = xfeatures_needed;
+
+ xfeature_idx = fls64(xfeatures_print)-1;
+ max_idx = ARRAY_SIZE(xfeature_names)-1;
+ xfeature_idx = min(xfeature_idx, max_idx);
+
+ *feature_name = xfeature_names[xfeature_idx];
+ }
+
+ if (xfeatures_missing)
+ return 0;
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
+
+/*
+ * When executing XSAVEOPT (or other optimized XSAVE instructions), if
+ * a processor implementation detects that an FPU state component is still
+ * (or is again) in its initialized state, it may clear the corresponding
+ * bit in the header.xfeatures field, and can skip the writeout of registers
+ * to the corresponding memory layout.
+ *
+ * This means that when the bit is zero, the state component might still contain
+ * some previous - non-initialized register state.
+ *
+ * Before writing xstate information to user-space we sanitize those components,
+ * to always ensure that the memory layout of a feature will be in the init state
+ * if the corresponding header bit is zero. This is to ensure that user-space doesn't
+ * see some stale state in the memory layout during signal handling, debugging etc.
+ */
+void fpstate_sanitize_xstate(struct fpu *fpu)
+{
+ struct fxregs_state *fx = &fpu->state.fxsave;
+ int feature_bit;
+ u64 xfeatures;
+
+ if (!use_xsaveopt())
+ return;
+
+ xfeatures = fpu->state.xsave.header.xfeatures;
+
+ /*
+ * None of the feature bits are in init state. So nothing else
+ * to do for us, as the memory layout is up to date.
+ */
+ if ((xfeatures & xfeatures_mask) == xfeatures_mask)
+ return;
+
+ /*
+ * FP is in init state
+ */
+ if (!(xfeatures & XSTATE_FP)) {
+ fx->cwd = 0x37f;
+ fx->swd = 0;
+ fx->twd = 0;
+ fx->fop = 0;
+ fx->rip = 0;
+ fx->rdp = 0;
+ memset(&fx->st_space[0], 0, 128);
+ }
+
+ /*
+ * SSE is in init state
+ */
+ if (!(xfeatures & XSTATE_SSE))
+ memset(&fx->xmm_space[0], 0, 256);
+
+ /*
+ * First two features are FPU and SSE, which above we handled
+ * in a special way already:
+ */
+ feature_bit = 0x2;
+ xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+
+ /*
+ * Update all the remaining memory layouts according to their
+ * standard xstate layout, if their header bit is in the init
+ * state:
+ */
+ while (xfeatures) {
+ if (xfeatures & 0x1) {
+ int offset = xstate_offsets[feature_bit];
+ int size = xstate_sizes[feature_bit];
+
+ memcpy((void *)fx + offset,
+ (void *)&init_fpstate.xsave + offset,
+ size);
+ }
+
+ xfeatures >>= 1;
+ feature_bit++;
+ }
+}
+
+/*
+ * Enable the extended processor state save/restore feature.
+ * Called once per CPU onlining.
+ */
+void fpu__init_cpu_xstate(void)
+{
+ if (!cpu_has_xsave || !xfeatures_mask)
+ return;
+
+ cr4_set_bits(X86_CR4_OSXSAVE);
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Record the offsets and sizes of various xstates contained
+ * in the XSAVE state memory layout.
+ *
+ * ( Note that certain features might be non-present, for them
+ * we'll have 0 offset and 0 size. )
+ */
+static void __init setup_xstate_features(void)
+{
+ u32 eax, ebx, ecx, edx, leaf;
+
+ xfeatures_nr = fls64(xfeatures_mask);
+
+ for (leaf = 2; leaf < xfeatures_nr; leaf++) {
+ cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
+
+ xstate_offsets[leaf] = ebx;
+ xstate_sizes[leaf] = eax;
+
+ printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax);
+ }
+}
+
+static void __init print_xstate_feature(u64 xstate_mask)
+{
+ const char *feature_name;
+
+ if (cpu_has_xfeatures(xstate_mask, &feature_name))
+ pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name);
+}
+
+/*
+ * Print out all the supported xstate features:
+ */
+static void __init print_xstate_features(void)
+{
+ print_xstate_feature(XSTATE_FP);
+ print_xstate_feature(XSTATE_SSE);
+ print_xstate_feature(XSTATE_YMM);
+ print_xstate_feature(XSTATE_BNDREGS);
+ print_xstate_feature(XSTATE_BNDCSR);
+ print_xstate_feature(XSTATE_OPMASK);
+ print_xstate_feature(XSTATE_ZMM_Hi256);
+ print_xstate_feature(XSTATE_Hi16_ZMM);
+}
+
+/*
+ * This function sets up offsets and sizes of all extended states in
+ * xsave area. This supports both standard format and compacted format
+ * of the xsave aread.
+ */
+static void __init setup_xstate_comp(void)
+{
+ unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8];
+ int i;
+
+ /*
+ * The FP xstates and SSE xstates are legacy states. They are always
+ * in the fixed offsets in the xsave area in either compacted form
+ * or standard form.
+ */
+ xstate_comp_offsets[0] = 0;
+ xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
+
+ if (!cpu_has_xsaves) {
+ for (i = 2; i < xfeatures_nr; i++) {
+ if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+ xstate_comp_offsets[i] = xstate_offsets[i];
+ xstate_comp_sizes[i] = xstate_sizes[i];
+ }
+ }
+ return;
+ }
+
+ xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+ for (i = 2; i < xfeatures_nr; i++) {
+ if (test_bit(i, (unsigned long *)&xfeatures_mask))
+ xstate_comp_sizes[i] = xstate_sizes[i];
+ else
+ xstate_comp_sizes[i] = 0;
+
+ if (i > 2)
+ xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
+ + xstate_comp_sizes[i-1];
+
+ }
+}
+
+/*
+ * setup the xstate image representing the init state
+ */
+static void __init setup_init_fpu_buf(void)
+{
+ static int on_boot_cpu = 1;
+
+ WARN_ON_FPU(!on_boot_cpu);
+ on_boot_cpu = 0;
+
+ if (!cpu_has_xsave)
+ return;
+
+ setup_xstate_features();
+ print_xstate_features();
+
+ if (cpu_has_xsaves) {
+ init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
+ init_fpstate.xsave.header.xfeatures = xfeatures_mask;
+ }
+
+ /*
+ * Init all the features state with header_bv being 0x0
+ */
+ copy_kernel_to_xregs_booting(&init_fpstate.xsave);
+
+ /*
+ * Dump the init state again. This is to identify the init state
+ * of any feature which is not represented by all zero's.
+ */
+ copy_xregs_to_kernel_booting(&init_fpstate.xsave);
+}
+
+/*
+ * Calculate total size of enabled xstates in XCR0/xfeatures_mask.
+ */
+static void __init init_xstate_size(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ int i;
+
+ if (!cpu_has_xsaves) {
+ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+ xstate_size = ebx;
+ return;
+ }
+
+ xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+ for (i = 2; i < 64; i++) {
+ if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+ cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+ xstate_size += eax;
+ }
+ }
+}
+
+/*
+ * Enable and initialize the xsave feature.
+ * Called once per system bootup.
+ */
+void __init fpu__init_system_xstate(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ static int on_boot_cpu = 1;
+
+ WARN_ON_FPU(!on_boot_cpu);
+ on_boot_cpu = 0;
+
+ if (!cpu_has_xsave) {
+ pr_info("x86/fpu: Legacy x87 FPU detected.\n");
+ return;
+ }
+
+ if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
+ WARN_ON_FPU(1);
+ return;
+ }
+
+ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+ xfeatures_mask = eax + ((u64)edx << 32);
+
+ if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
+ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+ BUG();
+ }
+
+ /* Support only the state known to the OS: */
+ xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+
+ /* Enable xstate instructions to be able to continue with initialization: */
+ fpu__init_cpu_xstate();
+
+ /* Recompute the context size for enabled features: */
+ init_xstate_size();
+
+ update_regset_xstate_info(xstate_size, xfeatures_mask);
+ fpu__init_prepare_fx_sw_frame();
+ setup_init_fpu_buf();
+ setup_xstate_comp();
+
+ pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is 0x%x bytes, using '%s' format.\n",
+ xfeatures_mask,
+ xstate_size,
+ cpu_has_xsaves ? "compacted" : "standard");
+}
+
+/*
+ * Restore minimal FPU state after suspend:
+ */
+void fpu__resume_cpu(void)
+{
+ /*
+ * Restore XCR0 on xsave capable CPUs:
+ */
+ if (cpu_has_xsave)
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Given the xsave area and a state inside, this function returns the
+ * address of the state.
+ *
+ * This is the API that is called to get xstate address in either
+ * standard format or compacted format of xsave area.
+ *
+ * Note that if there is no data for the field in the xsave buffer
+ * this will return NULL.
+ *
+ * Inputs:
+ * xstate: the thread's storage area for all FPU data
+ * xstate_feature: state which is defined in xsave.h (e.g.
+ * XSTATE_FP, XSTATE_SSE, etc...)
+ * Output:
+ * address of the state in the xsave area, or NULL if the
+ * field is not present in the xsave buffer.
+ */
+void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
+{
+ int feature_nr = fls64(xstate_feature) - 1;
+ /*
+ * Do we even *have* xsave state?
+ */
+ if (!boot_cpu_has(X86_FEATURE_XSAVE))
+ return NULL;
+
+ xsave = ¤t->thread.fpu.state.xsave;
+ /*
+ * We should not ever be requesting features that we
+ * have not enabled. Remember that pcntxt_mask is
+ * what we write to the XCR0 register.
+ */
+ WARN_ONCE(!(xfeatures_mask & xstate_feature),
+ "get of unsupported state");
+ /*
+ * This assumes the last 'xsave*' instruction to
+ * have requested that 'xstate_feature' be saved.
+ * If it did not, we might be seeing and old value
+ * of the field in the buffer.
+ *
+ * This can happen because the last 'xsave' did not
+ * request that this feature be saved (unlikely)
+ * or because the "init optimization" caused it
+ * to not be saved.
+ */
+ if (!(xsave->header.xfeatures & xstate_feature))
+ return NULL;
+
+ return (void *)xsave + xstate_comp_offsets[feature_nr];
+}
+EXPORT_SYMBOL_GPL(get_xsave_addr);
+
+/*
+ * This wraps up the common operations that need to occur when retrieving
+ * data from xsave state. It first ensures that the current task was
+ * using the FPU and retrieves the data in to a buffer. It then calculates
+ * the offset of the requested field in the buffer.
+ *
+ * This function is safe to call whether the FPU is in use or not.
+ *
+ * Note that this only works on the current task.
+ *
+ * Inputs:
+ * @xsave_state: state which is defined in xsave.h (e.g. XSTATE_FP,
+ * XSTATE_SSE, etc...)
+ * Output:
+ * address of the state in the xsave area or NULL if the state
+ * is not present or is in its 'init state'.
+ */
+const void *get_xsave_field_ptr(int xsave_state)
+{
+ struct fpu *fpu = ¤t->thread.fpu;
+
+ if (!fpu->fpstate_active)
+ return NULL;
+ /*
+ * fpu__save() takes the CPU's xstate registers
+ * and saves them off to the 'fpu memory buffer.
+ */
+ fpu__save(fpu);
+
+ return get_xsave_addr(&fpu->state.xsave, xsave_state);
+}
clear_bss();
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
- set_intr_gate(i, early_idt_handlers[i]);
+ set_intr_gate(i, early_idt_handler_array[i]);
load_idt((const struct desc_ptr *)&idt_descr);
copy_bootdata(__va(real_mode_data));
#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
#endif
-/* Number of possible pages in the lowmem region */
-LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
-
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
+
/* Enough space to fit pagetables for the low memory linear map */
MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
__INIT
setup_once:
/*
- * Set up a idt with 256 entries pointing to ignore_int,
- * interrupt gates. It doesn't actually load idt - that needs
- * to be done on each CPU. Interrupts are enabled elsewhere,
- * when we can be relatively sure everything is ok.
+ * Set up a idt with 256 interrupt gates that push zero if there
+ * is no error code and then jump to early_idt_handler_common.
+ * It doesn't actually load the idt - that needs to be done on
+ * each CPU. Interrupts are enabled elsewhere, when we can be
+ * relatively sure everything is ok.
*/
movl $idt_table,%edi
- movl $early_idt_handlers,%eax
+ movl $early_idt_handler_array,%eax
movl $NUM_EXCEPTION_VECTORS,%ecx
1:
movl %eax,(%edi)
movl %eax,4(%edi)
/* interrupt gate, dpl=0, present */
movl $(0x8E000000 + __KERNEL_CS),2(%edi)
- addl $9,%eax
+ addl $EARLY_IDT_HANDLER_SIZE,%eax
addl $8,%edi
loop 1b
andl $0,setup_once_ref /* Once is enough, thanks */
ret
-ENTRY(early_idt_handlers)
+ENTRY(early_idt_handler_array)
# 36(%esp) %eflags
# 32(%esp) %cs
# 28(%esp) %eip
# 24(%rsp) error code
i = 0
.rept NUM_EXCEPTION_VECTORS
- .if (EXCEPTION_ERRCODE_MASK >> i) & 1
- ASM_NOP2
- .else
+ .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
pushl $0 # Dummy error code, to make stack frame uniform
.endif
pushl $i # 20(%esp) Vector number
- jmp early_idt_handler
+ jmp early_idt_handler_common
i = i + 1
+ .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
.endr
-ENDPROC(early_idt_handlers)
+ENDPROC(early_idt_handler_array)
- /* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+ /*
+ * The stack is the hardware frame, an error code or zero, and the
+ * vector number.
+ */
cld
cmpl $2,(%esp) # X86_TRAP_NMI
- je is_nmi # Ignore NMI
+ je .Lis_nmi # Ignore NMI
cmpl $2,%ss:early_recursion_flag
je hlt_loop
pop %ecx
pop %eax
decl %ss:early_recursion_flag
-is_nmi:
+.Lis_nmi:
addl $8,%esp /* drop vector number and error code */
iret
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
/* This is the default interrupt "handler" :-) */
ALIGN
jmp bad_address
__INIT
- .globl early_idt_handlers
-early_idt_handlers:
+ENTRY(early_idt_handler_array)
# 104(%rsp) %rflags
# 96(%rsp) %cs
# 88(%rsp) %rip
# 80(%rsp) error code
i = 0
.rept NUM_EXCEPTION_VECTORS
- .if (EXCEPTION_ERRCODE_MASK >> i) & 1
- ASM_NOP2
- .else
+ .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
pushq $0 # Dummy error code, to make stack frame uniform
.endif
pushq $i # 72(%rsp) Vector number
- jmp early_idt_handler
+ jmp early_idt_handler_common
i = i + 1
+ .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
.endr
+ENDPROC(early_idt_handler_array)
-/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+ /*
+ * The stack is the hardware frame, an error code or zero, and the
+ * vector number.
+ */
cld
cmpl $2,(%rsp) # X86_TRAP_NMI
- je is_nmi # Ignore NMI
+ je .Lis_nmi # Ignore NMI
cmpl $2,early_recursion_flag(%rip)
jz 1f
popq %rcx
popq %rax
decl early_recursion_flag(%rip)
-is_nmi:
+.Lis_nmi:
addq $16,%rsp # drop vector number and error code
INTERRUPT_RETURN
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
__INITDATA
#include <linux/pm.h>
#include <linux/io.h>
+#include <asm/irqdomain.h>
#include <asm/fixmap.h>
#include <asm/hpet.h>
#include <asm/time.h>
printk(KERN_DEBUG "hpet clockevent registered\n");
}
-static int hpet_setup_msi_irq(unsigned int irq);
-
static void hpet_set_mode(enum clock_event_mode mode,
struct clock_event_device *evt, int timer)
{
hpet_enable_legacy_int();
} else {
struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
- hpet_setup_msi_irq(hdev->irq);
+ irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
disable_irq(hdev->irq);
irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
enable_irq(hdev->irq);
static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
static struct hpet_dev *hpet_devs;
+static struct irq_domain *hpet_domain;
void hpet_msi_unmask(struct irq_data *data)
{
return hpet_next_event(delta, evt, hdev->num);
}
-static int hpet_setup_msi_irq(unsigned int irq)
-{
- if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) {
- irq_free_hwirq(irq);
- return -EINVAL;
- }
- return 0;
-}
-
-static int hpet_assign_irq(struct hpet_dev *dev)
-{
- unsigned int irq = irq_alloc_hwirq(-1);
-
- if (!irq)
- return -EINVAL;
-
- irq_set_handler_data(irq, dev);
-
- if (hpet_setup_msi_irq(irq))
- return -EINVAL;
-
- dev->irq = irq;
- return 0;
-}
-
static irqreturn_t hpet_interrupt_handler(int irq, void *data)
{
struct hpet_dev *dev = (struct hpet_dev *)data;
if (!(hdev->flags & HPET_DEV_VALID))
return;
- if (hpet_setup_msi_irq(hdev->irq))
- return;
-
hdev->cpu = cpu;
per_cpu(cpu_hpet_dev, cpu) = hdev;
evt->name = hdev->name;
unsigned int id;
unsigned int num_timers;
unsigned int num_timers_used = 0;
- int i;
+ int i, irq;
if (hpet_msi_disable)
return;
num_timers++; /* Value read out starts from 0 */
hpet_print_config();
+ hpet_domain = hpet_create_irq_domain(hpet_blockid);
+ if (!hpet_domain)
+ return;
+
hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL);
if (!hpet_devs)
return;
hdev->flags = 0;
if (cfg & HPET_TN_PERIODIC_CAP)
hdev->flags |= HPET_DEV_PERI_CAP;
+ sprintf(hdev->name, "hpet%d", i);
hdev->num = i;
- sprintf(hdev->name, "hpet%d", i);
- if (hpet_assign_irq(hdev))
+ irq = hpet_assign_irq(hpet_domain, hdev, hdev->num);
+ if (irq <= 0)
continue;
+ hdev->irq = irq;
hdev->flags |= HPET_DEV_FSB_CAP;
hdev->flags |= HPET_DEV_VALID;
num_timers_used++;
}
#else
-static int hpet_setup_msi_irq(unsigned int irq)
-{
- return 0;
-}
static void hpet_msi_capability_lookup(unsigned int start_timer)
{
return;
#ifdef CONFIG_PREEMPT
EXPORT_SYMBOL(___preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
-EXPORT_SYMBOL(___preempt_schedule_context);
-#endif
+EXPORT_SYMBOL(___preempt_schedule_notrace);
#endif
+++ /dev/null
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- * Gareth Hughes <gareth@valinux.com>, May 2000
- */
-#include <linux/module.h>
-#include <linux/regset.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-
-#include <asm/sigcontext.h>
-#include <asm/processor.h>
-#include <asm/math_emu.h>
-#include <asm/tlbflush.h>
-#include <asm/uaccess.h>
-#include <asm/ptrace.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/user.h>
-
-static DEFINE_PER_CPU(bool, in_kernel_fpu);
-
-void kernel_fpu_disable(void)
-{
- WARN_ON(this_cpu_read(in_kernel_fpu));
- this_cpu_write(in_kernel_fpu, true);
-}
-
-void kernel_fpu_enable(void)
-{
- this_cpu_write(in_kernel_fpu, false);
-}
-
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- *
- * Except for the eagerfpu case when we return true; in the likely case
- * the thread has FPU but we are not going to set/clear TS.
- */
-static inline bool interrupted_kernel_fpu_idle(void)
-{
- if (this_cpu_read(in_kernel_fpu))
- return false;
-
- if (use_eager_fpu())
- return true;
-
- return !__thread_has_fpu(current) &&
- (read_cr0() & X86_CR0_TS);
-}
-
-/*
- * Were we in user mode (or vm86 mode) when we were
- * interrupted?
- *
- * Doing kernel_fpu_begin/end() is ok if we are running
- * in an interrupt context from user mode - we'll just
- * save the FPU state as required.
- */
-static inline bool interrupted_user_mode(void)
-{
- struct pt_regs *regs = get_irq_regs();
- return regs && user_mode(regs);
-}
-
-/*
- * Can we use the FPU in kernel mode with the
- * whole "kernel_fpu_begin/end()" sequence?
- *
- * It's always ok in process context (ie "not interrupt")
- * but it is sometimes ok even from an irq.
- */
-bool irq_fpu_usable(void)
-{
- return !in_interrupt() ||
- interrupted_user_mode() ||
- interrupted_kernel_fpu_idle();
-}
-EXPORT_SYMBOL(irq_fpu_usable);
-
-void __kernel_fpu_begin(void)
-{
- struct task_struct *me = current;
-
- this_cpu_write(in_kernel_fpu, true);
-
- if (__thread_has_fpu(me)) {
- __save_init_fpu(me);
- } else {
- this_cpu_write(fpu_owner_task, NULL);
- if (!use_eager_fpu())
- clts();
- }
-}
-EXPORT_SYMBOL(__kernel_fpu_begin);
-
-void __kernel_fpu_end(void)
-{
- struct task_struct *me = current;
-
- if (__thread_has_fpu(me)) {
- if (WARN_ON(restore_fpu_checking(me)))
- fpu_reset_state(me);
- } else if (!use_eager_fpu()) {
- stts();
- }
-
- this_cpu_write(in_kernel_fpu, false);
-}
-EXPORT_SYMBOL(__kernel_fpu_end);
-
-void unlazy_fpu(struct task_struct *tsk)
-{
- preempt_disable();
- if (__thread_has_fpu(tsk)) {
- if (use_eager_fpu()) {
- __save_fpu(tsk);
- } else {
- __save_init_fpu(tsk);
- __thread_fpu_end(tsk);
- }
- }
- preempt_enable();
-}
-EXPORT_SYMBOL(unlazy_fpu);
-
-unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
-unsigned int xstate_size;
-EXPORT_SYMBOL_GPL(xstate_size);
-static struct i387_fxsave_struct fx_scratch;
-
-static void mxcsr_feature_mask_init(void)
-{
- unsigned long mask = 0;
-
- if (cpu_has_fxsr) {
- memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
- asm volatile("fxsave %0" : "+m" (fx_scratch));
- mask = fx_scratch.mxcsr_mask;
- if (mask == 0)
- mask = 0x0000ffbf;
- }
- mxcsr_feature_mask &= mask;
-}
-
-static void init_thread_xstate(void)
-{
- /*
- * Note that xstate_size might be overwriten later during
- * xsave_init().
- */
-
- if (!cpu_has_fpu) {
- /*
- * Disable xsave as we do not support it if i387
- * emulation is enabled.
- */
- setup_clear_cpu_cap(X86_FEATURE_XSAVE);
- setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
- xstate_size = sizeof(struct i387_soft_struct);
- return;
- }
-
- if (cpu_has_fxsr)
- xstate_size = sizeof(struct i387_fxsave_struct);
- else
- xstate_size = sizeof(struct i387_fsave_struct);
-}
-
-/*
- * Called at bootup to set up the initial FPU state that is later cloned
- * into all processes.
- */
-
-void fpu_init(void)
-{
- unsigned long cr0;
- unsigned long cr4_mask = 0;
-
-#ifndef CONFIG_MATH_EMULATION
- if (!cpu_has_fpu) {
- pr_emerg("No FPU found and no math emulation present\n");
- pr_emerg("Giving up\n");
- for (;;)
- asm volatile("hlt");
- }
-#endif
- if (cpu_has_fxsr)
- cr4_mask |= X86_CR4_OSFXSR;
- if (cpu_has_xmm)
- cr4_mask |= X86_CR4_OSXMMEXCPT;
- if (cr4_mask)
- cr4_set_bits(cr4_mask);
-
- cr0 = read_cr0();
- cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
- if (!cpu_has_fpu)
- cr0 |= X86_CR0_EM;
- write_cr0(cr0);
-
- /*
- * init_thread_xstate is only called once to avoid overriding
- * xstate_size during boot time or during CPU hotplug.
- */
- if (xstate_size == 0)
- init_thread_xstate();
-
- mxcsr_feature_mask_init();
- xsave_init();
- eager_fpu_init();
-}
-
-void fpu_finit(struct fpu *fpu)
-{
- if (!cpu_has_fpu) {
- finit_soft_fpu(&fpu->state->soft);
- return;
- }
-
- memset(fpu->state, 0, xstate_size);
-
- if (cpu_has_fxsr) {
- fx_finit(&fpu->state->fxsave);
- } else {
- struct i387_fsave_struct *fp = &fpu->state->fsave;
- fp->cwd = 0xffff037fu;
- fp->swd = 0xffff0000u;
- fp->twd = 0xffffffffu;
- fp->fos = 0xffff0000u;
- }
-}
-EXPORT_SYMBOL_GPL(fpu_finit);
-
-/*
- * The _current_ task is using the FPU for the first time
- * so initialize it and set the mxcsr to its default
- * value at reset if we support XMM instructions and then
- * remember the current task has used the FPU.
- */
-int init_fpu(struct task_struct *tsk)
-{
- int ret;
-
- if (tsk_used_math(tsk)) {
- if (cpu_has_fpu && tsk == current)
- unlazy_fpu(tsk);
- task_disable_lazy_fpu_restore(tsk);
- return 0;
- }
-
- /*
- * Memory allocation at the first usage of the FPU and other state.
- */
- ret = fpu_alloc(&tsk->thread.fpu);
- if (ret)
- return ret;
-
- fpu_finit(&tsk->thread.fpu);
-
- set_stopped_child_used_math(tsk);
- return 0;
-}
-EXPORT_SYMBOL_GPL(init_fpu);
-
-/*
- * The xstateregs_active() routine is the same as the fpregs_active() routine,
- * as the "regset->n" for the xstate regset will be updated based on the feature
- * capabilites supported by the xsave.
- */
-int fpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
- return tsk_used_math(target) ? regset->n : 0;
-}
-
-int xfpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
- return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0;
-}
-
-int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_fxsr)
- return -ENODEV;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- sanitize_i387_state(target);
-
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fxsave, 0, -1);
-}
-
-int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
-
- if (!cpu_has_fxsr)
- return -ENODEV;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- sanitize_i387_state(target);
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fxsave, 0, -1);
-
- /*
- * mxcsr reserved bits must be masked to zero for security reasons.
- */
- target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
-
- /*
- * update the header bits in the xsave header, indicating the
- * presence of FP and SSE state.
- */
- if (cpu_has_xsave)
- target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
- return ret;
-}
-
-int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- struct xsave_struct *xsave;
- int ret;
-
- if (!cpu_has_xsave)
- return -ENODEV;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- xsave = &target->thread.fpu.state->xsave;
-
- /*
- * Copy the 48bytes defined by the software first into the xstate
- * memory layout in the thread struct, so that we can copy the entire
- * xstateregs to the user using one user_regset_copyout().
- */
- memcpy(&xsave->i387.sw_reserved,
- xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
- /*
- * Copy the xstate memory layout.
- */
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
- return ret;
-}
-
-int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- struct xsave_struct *xsave;
- int ret;
-
- if (!cpu_has_xsave)
- return -ENODEV;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- xsave = &target->thread.fpu.state->xsave;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
- /*
- * mxcsr reserved bits must be masked to zero for security reasons.
- */
- xsave->i387.mxcsr &= mxcsr_feature_mask;
- xsave->xsave_hdr.xstate_bv &= pcntxt_mask;
- /*
- * These bits must be zero.
- */
- memset(&xsave->xsave_hdr.reserved, 0, 48);
- return ret;
-}
-
-#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-
-/*
- * FPU tag word conversions.
- */
-
-static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
-{
- unsigned int tmp; /* to avoid 16 bit prefixes in the code */
-
- /* Transform each pair of bits into 01 (valid) or 00 (empty) */
- tmp = ~twd;
- tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
- /* and move the valid bits to the lower byte. */
- tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
- tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
- tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
-
- return tmp;
-}
-
-#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16)
-#define FP_EXP_TAG_VALID 0
-#define FP_EXP_TAG_ZERO 1
-#define FP_EXP_TAG_SPECIAL 2
-#define FP_EXP_TAG_EMPTY 3
-
-static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
-{
- struct _fpxreg *st;
- u32 tos = (fxsave->swd >> 11) & 7;
- u32 twd = (unsigned long) fxsave->twd;
- u32 tag;
- u32 ret = 0xffff0000u;
- int i;
-
- for (i = 0; i < 8; i++, twd >>= 1) {
- if (twd & 0x1) {
- st = FPREG_ADDR(fxsave, (i - tos) & 7);
-
- switch (st->exponent & 0x7fff) {
- case 0x7fff:
- tag = FP_EXP_TAG_SPECIAL;
- break;
- case 0x0000:
- if (!st->significand[0] &&
- !st->significand[1] &&
- !st->significand[2] &&
- !st->significand[3])
- tag = FP_EXP_TAG_ZERO;
- else
- tag = FP_EXP_TAG_SPECIAL;
- break;
- default:
- if (st->significand[3] & 0x8000)
- tag = FP_EXP_TAG_VALID;
- else
- tag = FP_EXP_TAG_SPECIAL;
- break;
- }
- } else {
- tag = FP_EXP_TAG_EMPTY;
- }
- ret |= tag << (2 * i);
- }
- return ret;
-}
-
-/*
- * FXSR floating point environment conversions.
- */
-
-void
-convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
-{
- struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
- struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
- struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
- int i;
-
- env->cwd = fxsave->cwd | 0xffff0000u;
- env->swd = fxsave->swd | 0xffff0000u;
- env->twd = twd_fxsr_to_i387(fxsave);
-
-#ifdef CONFIG_X86_64
- env->fip = fxsave->rip;
- env->foo = fxsave->rdp;
- /*
- * should be actually ds/cs at fpu exception time, but
- * that information is not available in 64bit mode.
- */
- env->fcs = task_pt_regs(tsk)->cs;
- if (tsk == current) {
- savesegment(ds, env->fos);
- } else {
- env->fos = tsk->thread.ds;
- }
- env->fos |= 0xffff0000;
-#else
- env->fip = fxsave->fip;
- env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
- env->foo = fxsave->foo;
- env->fos = fxsave->fos;
-#endif
-
- for (i = 0; i < 8; ++i)
- memcpy(&to[i], &from[i], sizeof(to[0]));
-}
-
-void convert_to_fxsr(struct task_struct *tsk,
- const struct user_i387_ia32_struct *env)
-
-{
- struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
- struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
- struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
- int i;
-
- fxsave->cwd = env->cwd;
- fxsave->swd = env->swd;
- fxsave->twd = twd_i387_to_fxsr(env->twd);
- fxsave->fop = (u16) ((u32) env->fcs >> 16);
-#ifdef CONFIG_X86_64
- fxsave->rip = env->fip;
- fxsave->rdp = env->foo;
- /* cs and ds ignored */
-#else
- fxsave->fip = env->fip;
- fxsave->fcs = (env->fcs & 0xffff);
- fxsave->foo = env->foo;
- fxsave->fos = env->fos;
-#endif
-
- for (i = 0; i < 8; ++i)
- memcpy(&to[i], &from[i], sizeof(from[0]));
-}
-
-int fpregs_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf)
-{
- struct user_i387_ia32_struct env;
- int ret;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
-
- if (!cpu_has_fxsr)
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fsave, 0,
- -1);
-
- sanitize_i387_state(target);
-
- if (kbuf && pos == 0 && count == sizeof(env)) {
- convert_from_fxsr(kbuf, target);
- return 0;
- }
-
- convert_from_fxsr(&env, target);
-
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
-}
-
-int fpregs_set(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- struct user_i387_ia32_struct env;
- int ret;
-
- ret = init_fpu(target);
- if (ret)
- return ret;
-
- sanitize_i387_state(target);
-
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
-
- if (!cpu_has_fxsr)
- return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fsave, 0,
- -1);
-
- if (pos > 0 || count < sizeof(env))
- convert_from_fxsr(&env, target);
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
- if (!ret)
- convert_to_fxsr(target, &env);
-
- /*
- * update the header bit in the xsave header, indicating the
- * presence of FP.
- */
- if (cpu_has_xsave)
- target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP;
- return ret;
-}
-
-/*
- * FPU state for core dumps.
- * This is only used for a.out dumps now.
- * It is declared generically using elf_fpregset_t (which is
- * struct user_i387_struct) but is in fact only used for 32-bit
- * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
- */
-int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu)
-{
- struct task_struct *tsk = current;
- int fpvalid;
-
- fpvalid = !!used_math();
- if (fpvalid)
- fpvalid = !fpregs_get(tsk, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- fpu, NULL);
-
- return fpvalid;
-}
-EXPORT_SYMBOL(dump_fpu);
-
-#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
-
-static int __init no_387(char *s)
-{
- setup_clear_cpu_cap(X86_FEATURE_FPU);
- return 1;
-}
-
-__setup("no387", no_387);
-
-void fpu_detect(struct cpuinfo_x86 *c)
-{
- unsigned long cr0;
- u16 fsw, fcw;
-
- fsw = fcw = 0xffff;
-
- cr0 = read_cr0();
- cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
- write_cr0(cr0);
-
- asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
- : "+m" (fsw), "+m" (fcw));
-
- if (fsw == 0 && (fcw & 0x103f) == 0x003f)
- set_cpu_cap(c, X86_FEATURE_FPU);
- else
- clear_cpu_cap(c, X86_FEATURE_FPU);
-
- /* The final cr0 value is set in fpu_init() */
-}
*/
outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */
- /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
- outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+ /* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */
+ outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR);
/* 8259A-1 (the master) has a slave on IR2 */
outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);
outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */
- /* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */
- outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
+ /* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */
+ outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR);
/* 8259A-2 is a slave on master's IR2 */
outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
/* (slave's support for AEOI in flat mode is to be investigated) */
#define CREATE_TRACE_POINTS
#include <asm/trace/irq_vectors.h>
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
+
atomic_t irq_err_count;
/* Function pointer for generic interrupt vector handling */
seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
seq_puts(p, " Threshold APIC interrupts\n");
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ seq_printf(p, "%*s: ", prec, "DFR");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count);
+ seq_puts(p, " Deferred Error APIC interrupts\n");
+#endif
#ifdef CONFIG_X86_MCE
seq_printf(p, "%*s: ", prec, "MCE");
for_each_online_cpu(j)
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
+#endif
+#ifdef CONFIG_HAVE_KVM
+ seq_printf(p, "%*s: ", prec, "PIN");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
+ seq_puts(p, " Posted-interrupt notification event\n");
+
+ seq_printf(p, "%*s: ", prec, "PIW");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->kvm_posted_intr_wakeup_ipis);
+ seq_puts(p, " Posted-interrupt wakeup event\n");
#endif
return 0;
}
unsigned vector = ~regs->orig_ax;
unsigned irq;
- irq_enter();
- exit_idle();
+ entering_irq();
irq = __this_cpu_read(vector_irq[vector]);
}
}
- irq_exit();
+ exiting_irq();
set_irq_regs(old_regs);
return 1;
}
#ifdef CONFIG_HAVE_KVM
+static void dummy_handler(void) {}
+static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler;
+
+void kvm_set_posted_intr_wakeup_handler(void (*handler)(void))
+{
+ if (handler)
+ kvm_posted_intr_wakeup_handler = handler;
+ else
+ kvm_posted_intr_wakeup_handler = dummy_handler;
+}
+EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler);
+
/*
* Handler for POSTED_INTERRUPT_VECTOR.
*/
{
struct pt_regs *old_regs = set_irq_regs(regs);
- ack_APIC_irq();
-
- irq_enter();
-
- exit_idle();
-
+ entering_ack_irq();
inc_irq_stat(kvm_posted_intr_ipis);
+ exiting_irq();
+ set_irq_regs(old_regs);
+}
- irq_exit();
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ entering_ack_irq();
+ inc_irq_stat(kvm_posted_intr_wakeup_ipis);
+ kvm_posted_intr_wakeup_handler();
+ exiting_irq();
set_irq_regs(old_regs);
}
#endif
#include <asm/apic.h>
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
#ifdef CONFIG_DEBUG_STACKOVERFLOW
int sysctl_panic_on_stackoverflow __read_mostly;
#include <asm/idle.h>
#include <asm/apic.h>
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
int sysctl_panic_on_stackoverflow;
/*
#include <asm/apic.h>
#include <asm/trace/irq_vectors.h>
-static inline void irq_work_entering_irq(void)
-{
- irq_enter();
- ack_APIC_irq();
-}
-
static inline void __smp_irq_work_interrupt(void)
{
inc_irq_stat(apic_irq_work_irqs);
__visible void smp_irq_work_interrupt(struct pt_regs *regs)
{
- irq_work_entering_irq();
+ ipi_entering_ack_irq();
__smp_irq_work_interrupt();
exiting_irq();
}
__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
{
- irq_work_entering_irq();
+ ipi_entering_ack_irq();
trace_irq_work_entry(IRQ_WORK_VECTOR);
__smp_irq_work_interrupt();
trace_irq_work_exit(IRQ_WORK_VECTOR);
int i;
/*
- * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
+ * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15.
* If these IRQ's are handled by legacy interrupt-controllers like PIC,
* then this configuration will likely be static after the boot. If
* these IRQ's are handled by more mordern controllers like IO-APIC,
* irq's migrate etc.
*/
for (i = 0; i < nr_legacy_irqs(); i++)
- per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i;
+ per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i;
x86_init.irqs.intr_init();
}
alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
#endif
+#ifdef CONFIG_X86_MCE_AMD
+ alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt);
+#endif
+
#ifdef CONFIG_X86_LOCAL_APIC
/* self generated IPI for local APIC timer */
alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
#ifdef CONFIG_HAVE_KVM
/* IPI for KVM to deliver posted interrupt */
alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
+ /* IPI for KVM to deliver interrupt to wake up tasks */
+ alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
#endif
/* IPI vectors for APIC spurious and error interrupts */
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void kvm_wait(u8 *ptr, u8 val)
+{
+ unsigned long flags;
+
+ if (in_nmi())
+ return;
+
+ local_irq_save(flags);
+
+ if (READ_ONCE(*ptr) != val)
+ goto out;
+
+ /*
+ * halt until it's our turn and kicked. Note that we do safe halt
+ * for irq enabled case to avoid hang when lock info is overwritten
+ * in irq spinlock slowpath and no spurious interrupt occur to save us.
+ */
+ if (arch_irqs_disabled_flags(flags))
+ halt();
+ else
+ safe_halt();
+
+out:
+ local_irq_restore(flags);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
enum kvm_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
}
}
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ __pv_init_lock_hash();
+ pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_lock_ops.wait = kvm_wait;
+ pv_lock_ops.kick = kvm_kick_cpu;
+#else /* !CONFIG_QUEUED_SPINLOCKS */
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
pv_lock_ops.unlock_kick = kvm_unlock_kick;
+#endif
}
static __init int kvm_spinlock_init_jump(void)
#include <linux/ftrace.h>
#include <linux/io.h>
#include <linux/suspend.h>
+#include <linux/vmalloc.h>
#include <asm/init.h>
#include <asm/pgtable.h>
#include <linux/module.h>
#include <linux/smp.h>
#include <linux/pci.h>
-#include <linux/irqdomain.h>
+#include <asm/irqdomain.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
#include <asm/pgalloc.h>
pr_warn("Unknown bustype %s - ignoring\n", str);
}
-static struct irq_domain_ops mp_ioapic_irqdomain_ops = {
- .map = mp_irqdomain_map,
- .unmap = mp_irqdomain_unmap,
-};
-
static void __init MP_ioapic_info(struct mpc_ioapic *m)
{
struct ioapic_domain_cfg cfg = {
#include <asm/paravirt.h>
+#ifdef CONFIG_QUEUED_SPINLOCKS
+__visible void __native_queued_spin_unlock(struct qspinlock *lock)
+{
+ native_queued_spin_unlock(lock);
+}
+
+PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
+
+bool pv_is_native_spin_unlock(void)
+{
+ return pv_lock_ops.queued_spin_unlock.func ==
+ __raw_callee_save___native_queued_spin_unlock;
+}
+#endif
+
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+ .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
+ .wait = paravirt_nop,
+ .kick = paravirt_nop,
+#else /* !CONFIG_QUEUED_SPINLOCKS */
.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
.unlock_kick = paravirt_nop,
-#endif
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+#endif /* SMP */
};
EXPORT_SYMBOL(pv_lock_ops);
ret = paravirt_patch_ident_64(insnbuf, len);
else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
+#ifdef CONFIG_X86_32
type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
+#endif
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
/* If operation requires a jmp, then jmp */
.load_sp0 = native_load_sp0,
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+#if defined(CONFIG_X86_32)
.irq_enable_sysexit = native_irq_enable_sysexit,
#endif
#ifdef CONFIG_X86_64
DEF_NATIVE(pv_cpu_ops, clts, "clts");
DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
+#endif
+
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
{
/* arg in %eax, return in %eax */
return 0;
}
+extern bool pv_is_native_spin_unlock(void);
+
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
{
PATCH_SITE(pv_mmu_ops, write_cr3);
PATCH_SITE(pv_cpu_ops, clts);
PATCH_SITE(pv_cpu_ops, read_tsc);
-
- patch_site:
- ret = paravirt_patch_insns(ibuf, len, start, end);
- break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+ case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+ if (pv_is_native_spin_unlock()) {
+ start = start_pv_lock_ops_queued_spin_unlock;
+ end = end_pv_lock_ops_queued_spin_unlock;
+ goto patch_site;
+ }
+#endif
default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
+
+patch_site:
+ ret = paravirt_patch_insns(ibuf, len, start, end);
+ break;
}
#undef PATCH_SITE
return ret;
DEF_NATIVE(, mov32, "mov %edi, %eax");
DEF_NATIVE(, mov64, "mov %rdi, %rax");
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
+#endif
+
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
{
return paravirt_patch_insns(insnbuf, len,
start__mov64, end__mov64);
}
+extern bool pv_is_native_spin_unlock(void);
+
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
{
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_irq_ops, irq_enable);
PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
PATCH_SITE(pv_cpu_ops, usergs_sysret32);
PATCH_SITE(pv_cpu_ops, usergs_sysret64);
PATCH_SITE(pv_cpu_ops, swapgs);
PATCH_SITE(pv_cpu_ops, clts);
PATCH_SITE(pv_mmu_ops, flush_tlb_single);
PATCH_SITE(pv_cpu_ops, wbinvd);
-
- patch_site:
- ret = paravirt_patch_insns(ibuf, len, start, end);
- break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+ case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+ if (pv_is_native_spin_unlock()) {
+ start = start_pv_lock_ops_queued_spin_unlock;
+ end = end_pv_lock_ops_queued_spin_unlock;
+ goto patch_site;
+ }
+#endif
default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
+
+patch_site:
+ ret = paravirt_patch_insns(ibuf, len, start, end);
+ break;
}
#undef PATCH_SITE
return ret;
free_pages((unsigned long)vaddr, get_order(size));
}
+void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, struct dma_attrs *attrs)
+{
+ struct dma_map_ops *ops = get_dma_ops(dev);
+ void *memory;
+
+ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+
+ if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+ return memory;
+
+ if (!dev)
+ dev = &x86_dma_fallback_dev;
+
+ if (!is_device_dma_capable(dev))
+ return NULL;
+
+ if (!ops->alloc)
+ return NULL;
+
+ memory = ops->alloc(dev, size, dma_handle,
+ dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
+ debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
+
+ return memory;
+}
+EXPORT_SYMBOL(dma_alloc_attrs);
+
+void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t bus,
+ struct dma_attrs *attrs)
+{
+ struct dma_map_ops *ops = get_dma_ops(dev);
+
+ WARN_ON(irqs_disabled()); /* for portability */
+
+ if (dma_release_from_coherent(dev, get_order(size), vaddr))
+ return;
+
+ debug_dma_free_coherent(dev, size, vaddr, bus);
+ if (ops->free)
+ ops->free(dev, size, vaddr, bus, attrs);
+}
+EXPORT_SYMBOL(dma_free_attrs);
+
/*
* See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
* parameter documentation.
{
void *vaddr;
+ /*
+ * Don't print a warning when the first allocation attempt fails.
+ * swiotlb_alloc_coherent() will print a warning when the DMA
+ * memory allocation ultimately failed.
+ */
+ flags |= __GFP_NOWARN;
+
vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
attrs);
if (vaddr)
#include <asm/idle.h>
#include <asm/uaccess.h>
#include <asm/mwait.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/debugreg.h>
#include <asm/nmi.h>
#include <asm/tlbflush.h>
EXPORT_SYMBOL_GPL(idle_notifier_unregister);
#endif
-struct kmem_cache *task_xstate_cachep;
-EXPORT_SYMBOL_GPL(task_xstate_cachep);
-
/*
* this gets called so that we can store lazy state into memory and copy the
* current task into the new thread.
{
*dst = *src;
- dst->thread.fpu_counter = 0;
- dst->thread.fpu.has_fpu = 0;
- dst->thread.fpu.state = NULL;
- task_disable_lazy_fpu_restore(dst);
- if (tsk_used_math(src)) {
- int err = fpu_alloc(&dst->thread.fpu);
- if (err)
- return err;
- fpu_copy(dst, src);
- }
- return 0;
-}
-
-void free_thread_xstate(struct task_struct *tsk)
-{
- fpu_free(&tsk->thread.fpu);
-}
-
-void arch_release_task_struct(struct task_struct *tsk)
-{
- free_thread_xstate(tsk);
-}
-
-void arch_task_cache_init(void)
-{
- task_xstate_cachep =
- kmem_cache_create("task_xstate", xstate_size,
- __alignof__(union thread_xstate),
- SLAB_PANIC | SLAB_NOTRACK, NULL);
- setup_xstate_comp();
+ return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
}
/*
struct task_struct *me = current;
struct thread_struct *t = &me->thread;
unsigned long *bp = t->io_bitmap_ptr;
+ struct fpu *fpu = &t->fpu;
if (bp) {
struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
kfree(bp);
}
- drop_fpu(me);
+ fpu__drop(fpu);
}
void flush_thread(void)
flush_ptrace_hw_breakpoint(tsk);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
- if (!use_eager_fpu()) {
- /* FPU state will be reallocated lazily at the first use. */
- drop_fpu(tsk);
- free_thread_xstate(tsk);
- } else {
- if (!tsk_used_math(tsk)) {
- /* kthread execs. TODO: cleanup this horror. */
- if (WARN_ON(init_fpu(tsk)))
- force_sig(SIGKILL, tsk);
- user_fpu_begin();
- }
- restore_init_xstate();
- }
+ fpu__clear(&tsk->thread.fpu);
}
static void hard_disable_TSC(void)
}
/*
- * MONITOR/MWAIT with no hints, used for default default C1 state.
- * This invokes MWAIT with interrutps enabled and no flags,
- * which is backwards compatible with the original MWAIT implementation.
+ * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT
+ * with interrupts enabled and no flags, which is backwards compatible with the
+ * original MWAIT implementation.
*/
-
static void mwait_idle(void)
{
if (!current_set_polling_and_test()) {
#include <asm/pgtable.h>
#include <asm/ldt.h>
#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/desc.h>
#ifdef CONFIG_MATH_EMULATION
#include <asm/math_emu.h>
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread,
- *next = &next_p->thread;
+ *next = &next_p->thread;
+ struct fpu *prev_fpu = &prev->fpu;
+ struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
- fpu_switch_t fpu;
+ fpu_switch_t fpu_switch;
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
- fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+ fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
/*
* Save away %gs. No need to save %fs, as it was saved on the
* Leave lazy mode, flushing any hypercalls made here.
* This must be done before restoring TLS segments so
* the GDT and LDT are properly updated, and must be
- * done before math_state_restore, so the TS bit is up
+ * done before fpu__restore(), so the TS bit is up
* to date.
*/
arch_end_context_switch(next_p);
/*
- * Reload esp0, kernel_stack, and current_top_of_stack. This changes
+ * Reload esp0 and cpu_current_top_of_stack. This changes
* current_thread_info().
*/
load_sp0(tss, next);
- this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) +
- THREAD_SIZE);
this_cpu_write(cpu_current_top_of_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE);
if (prev->gs | next->gs)
lazy_load_gs(next->gs);
- switch_fpu_finish(next_p, fpu);
+ switch_fpu_finish(next_fpu, fpu_switch);
this_cpu_write(current_task, next_p);
#include <asm/pgtable.h>
#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
{
struct thread_struct *prev = &prev_p->thread;
struct thread_struct *next = &next_p->thread;
+ struct fpu *prev_fpu = &prev->fpu;
+ struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
unsigned fsindex, gsindex;
- fpu_switch_t fpu;
+ fpu_switch_t fpu_switch;
- fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+ fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
/* We must save %fs and %gs before load_TLS() because
* %fs and %gs may be cleared by load_TLS().
* Leave lazy mode, flushing any hypercalls made here. This
* must be done after loading TLS entries in the GDT but before
* loading segments that might reference them, and and it must
- * be done before math_state_restore, so the TS bit is up to
+ * be done before fpu__restore(), so the TS bit is up to
* date.
*/
arch_end_context_switch(next_p);
wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
prev->gsindex = gsindex;
- switch_fpu_finish(next_p, fpu);
+ switch_fpu_finish(next_fpu, fpu_switch);
/*
* Switch the PDA and FPU contexts.
/* Reload esp0 and ss1. This changes current_thread_info(). */
load_sp0(tss, next);
- this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) + THREAD_SIZE);
-
/*
* Now maybe reload the debug registers and handle I/O bitmaps
*/
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/ptrace.h>
-#include <linux/regset.h>
#include <linux/tracehook.h>
#include <linux/user.h>
#include <linux/elf.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
#include <asm/debugreg.h>
#include <asm/ldt.h>
#include <asm/desc.h>
.core_note_type = NT_PRFPREG,
.n = sizeof(struct user_i387_struct) / sizeof(long),
.size = sizeof(long), .align = sizeof(long),
- .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+ .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
},
[REGSET_XSTATE] = {
.core_note_type = NT_X86_XSTATE,
.core_note_type = NT_PRFPREG,
.n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
.size = sizeof(u32), .align = sizeof(u32),
- .active = fpregs_active, .get = fpregs_get, .set = fpregs_set
+ .active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set
},
[REGSET_XFP] = {
.core_note_type = NT_PRXFPREG,
.n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
.size = sizeof(u32), .align = sizeof(u32),
- .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+ .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
},
[REGSET_XSTATE] = {
.core_note_type = NT_X86_XSTATE,
if (ret != 0) {
/*
* two parts from lib/swiotlb.c:
- * swiotlb size: user specified with swiotlb= or default.
- * swiotlb overflow buffer: now is hardcoded to 32k.
- * We round it to 8M for other buffers that
- * may need to stay low too.
+ * -swiotlb size: user-specified with swiotlb= or default.
+ *
+ * -swiotlb overflow buffer: now hardcoded to 32k. We round it
+ * to 8M for other buffers that may need to stay low too. Also
+ * make sure we allocate enough extra low memory so that we
+ * don't run out of DMA buffers for 32-bit devices.
*/
- low_size = swiotlb_size_or_default() + (8UL<<20);
+ low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20);
auto_set = true;
} else {
/* passed with crashkernel=0,low ? */
init_cpu_to_node();
init_apic_mappings();
- if (x86_io_apic_ops.init)
- x86_io_apic_ops.init();
+ io_apic_init_mappings();
kvm_guest_init();
#include <asm/processor.h>
#include <asm/ucontext.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
#include <asm/vdso.h>
#include <asm/mce.h>
#include <asm/sighandling.h>
get_user_ex(buf, &sc->fpstate);
} get_user_catch(err);
- err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
+ err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32));
force_iret();
unsigned long sp = regs->sp;
unsigned long buf_fx = 0;
int onsigstack = on_sig_stack(sp);
+ struct fpu *fpu = ¤t->thread.fpu;
/* redzone */
if (config_enabled(CONFIG_X86_64))
}
}
- if (used_math()) {
- sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
- &buf_fx, &math_size);
+ if (fpu->fpstate_active) {
+ sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+ &buf_fx, &math_size);
*fpstate = (void __user *)sp;
}
return (void __user *)-1L;
/* save i387 and extended state */
- if (used_math() &&
- save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
+ if (fpu->fpstate_active &&
+ copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
return (void __user *)-1L;
return (void __user *)sp;
return 0;
}
+static inline int is_ia32_compat_frame(void)
+{
+ return config_enabled(CONFIG_IA32_EMULATION) &&
+ test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+ return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+ return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
static int
setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
{
handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
bool stepping, failed;
+ struct fpu *fpu = ¤t->thread.fpu;
/* Are we from a system call? */
if (syscall_get_nr(current, regs) >= 0) {
/*
* Ensure the signal handler starts with the new fpu state.
*/
- if (used_math())
- fpu_reset_state(current);
+ if (fpu->fpstate_active)
+ fpu__clear(fpu);
}
signal_setup_done(failed, ksig, stepping);
}
asmlinkage __visible void smp_reboot_interrupt(void)
{
- ack_APIC_irq();
- irq_enter();
+ ipi_entering_ack_irq();
stop_this_cpu(NULL);
irq_exit();
}
*/
}
-static inline void smp_entering_irq(void)
-{
- ack_APIC_irq();
- irq_enter();
-}
-
__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
{
/*
* scheduler_ipi(). This is OK, since those functions are allowed
* to nest.
*/
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_reschedule_entry(RESCHEDULE_VECTOR);
__smp_reschedule_interrupt();
trace_reschedule_exit(RESCHEDULE_VECTOR);
__visible void smp_call_function_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
__smp_call_function_interrupt();
exiting_irq();
}
__visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_call_function_entry(CALL_FUNCTION_VECTOR);
__smp_call_function_interrupt();
trace_call_function_exit(CALL_FUNCTION_VECTOR);
__visible void smp_call_function_single_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
__smp_call_function_single_interrupt();
exiting_irq();
}
__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
{
- smp_entering_irq();
+ ipi_entering_ack_irq();
trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
__smp_call_function_single_interrupt();
trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
#include <asm/mwait.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
}
-#define link_mask(_m, c1, c2) \
+#define link_mask(mfunc, c1, c2) \
do { \
- cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \
- cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \
+ cpumask_set_cpu((c1), mfunc(c2)); \
+ cpumask_set_cpu((c2), mfunc(c1)); \
} while (0)
static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
if (!has_mp) {
- cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+ cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
- cpumask_set_cpu(cpu, cpu_core_mask(cpu));
+ cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
c->booted_cores = 1;
return;
}
o = &cpu_data(i);
if ((i == cpu) || (has_smt && match_smt(c, o)))
- link_mask(sibling, cpu, i);
+ link_mask(topology_sibling_cpumask, cpu, i);
if ((i == cpu) || (has_mp && match_llc(c, o)))
- link_mask(llc_shared, cpu, i);
+ link_mask(cpu_llc_shared_mask, cpu, i);
}
/*
* This needs a separate iteration over the cpus because we rely on all
- * cpu_sibling_mask links to be set-up.
+ * topology_sibling_cpumask links to be set-up.
*/
for_each_cpu(i, cpu_sibling_setup_mask) {
o = &cpu_data(i);
if ((i == cpu) || (has_mp && match_die(c, o))) {
- link_mask(core, cpu, i);
+ link_mask(topology_core_cpumask, cpu, i);
/*
* Does this new cpu bringup a new core?
*/
- if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) {
+ if (cpumask_weight(
+ topology_sibling_cpumask(cpu)) == 1) {
/*
* for each core in package, increment
* the booted_cores for this new cpu
*/
- if (cpumask_first(cpu_sibling_mask(i)) == i)
+ if (cpumask_first(
+ topology_sibling_cpumask(i)) == i)
c->booted_cores++;
/*
* increment the core count for all
}
}
+/*
+ * The Multiprocessor Specification 1.4 (1997) example code suggests
+ * that there should be a 10ms delay between the BSP asserting INIT
+ * and de-asserting INIT, when starting a remote processor.
+ * But that slows boot and resume on modern processors, which include
+ * many cores and don't require that delay.
+ *
+ * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
+ * Modern processor families are quirked to remove the delay entirely.
+ */
+#define UDELAY_10MS_DEFAULT 10000
+
+static unsigned int init_udelay = UDELAY_10MS_DEFAULT;
+
+static int __init cpu_init_udelay(char *str)
+{
+ get_option(&str, &init_udelay);
+
+ return 0;
+}
+early_param("cpu_init_udelay", cpu_init_udelay);
+
+static void __init smp_quirk_init_udelay(void)
+{
+ /* if cmdline changed it from default, leave it alone */
+ if (init_udelay != UDELAY_10MS_DEFAULT)
+ return;
+
+ /* if modern processor, use no delay */
+ if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+ ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+ init_udelay = 0;
+}
+
/*
* Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
* INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
static int
wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
- unsigned long send_status, accept_status = 0;
+ unsigned long send_status = 0, accept_status = 0;
int maxlvt, num_starts, j;
maxlvt = lapic_get_maxlvt();
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
- mdelay(10);
+ udelay(init_udelay);
pr_debug("Deasserting INIT\n");
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
+
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
accept_status = (apic_read(APIC_ESR) & 0xEF);
clear_tsk_thread_flag(idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
#endif
- per_cpu(kernel_stack, cpu) =
- (unsigned long)task_stack_page(idle) + THREAD_SIZE;
}
/*
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
else
physid_set_mask_of_physid(0, &phys_cpu_present_map);
- cpumask_set_cpu(0, cpu_sibling_mask(0));
- cpumask_set_cpu(0, cpu_core_mask(0));
+ cpumask_set_cpu(0, topology_sibling_cpumask(0));
+ cpumask_set_cpu(0, topology_core_cpumask(0));
}
enum {
uv_system_init();
set_mtrr_aps_delayed_init();
+
+ smp_quirk_init_udelay();
}
void arch_enable_nonboot_cpus_begin(void)
int sibling;
struct cpuinfo_x86 *c = &cpu_data(cpu);
- for_each_cpu(sibling, cpu_core_mask(cpu)) {
- cpumask_clear_cpu(cpu, cpu_core_mask(sibling));
+ for_each_cpu(sibling, topology_core_cpumask(cpu)) {
+ cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
/*/
* last thread sibling in this cpu core going down
*/
- if (cpumask_weight(cpu_sibling_mask(cpu)) == 1)
+ if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1)
cpu_data(sibling).booted_cores--;
}
- for_each_cpu(sibling, cpu_sibling_mask(cpu))
- cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+ for_each_cpu(sibling, topology_sibling_cpumask(cpu))
+ cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
cpumask_clear(cpu_llc_shared_mask(cpu));
- cpumask_clear(cpu_sibling_mask(cpu));
- cpumask_clear(cpu_core_mask(cpu));
+ cpumask_clear(topology_sibling_cpumask(cpu));
+ cpumask_clear(topology_core_cpumask(cpu));
c->phys_proc_id = 0;
c->cpu_core_id = 0;
cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
+++ /dev/null
-/* System call table for i386. */
-
-#include <linux/linkage.h>
-#include <linux/sys.h>
-#include <linux/cache.h>
-#include <asm/asm-offsets.h>
-
-#ifdef CONFIG_IA32_EMULATION
-#define SYM(sym, compat) compat
-#else
-#define SYM(sym, compat) sym
-#define ia32_sys_call_table sys_call_table
-#define __NR_ia32_syscall_max __NR_syscall_max
-#endif
-
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
-#include <asm/syscalls_32.h>
-#undef __SYSCALL_I386
-
-#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat),
-
-typedef asmlinkage void (*sys_call_ptr_t)(void);
-
-extern asmlinkage void sys_ni_syscall(void);
-
-__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
- /*
- * Smells like a compiler bug -- it doesn't work
- * when the & below is removed.
- */
- [0 ... __NR_ia32_syscall_max] = &sys_ni_syscall,
-#include <asm/syscalls_32.h>
-};
+++ /dev/null
-/* System call table for x86-64. */
-
-#include <linux/linkage.h>
-#include <linux/sys.h>
-#include <linux/cache.h>
-#include <asm/asm-offsets.h>
-#include <asm/syscall.h>
-
-#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
-
-#ifdef CONFIG_X86_X32_ABI
-# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
-#else
-# define __SYSCALL_X32(nr, sym, compat) /* nothing */
-#endif
-
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
-#include <asm/syscalls_64.h>
-#undef __SYSCALL_64
-
-#define __SYSCALL_64(nr, sym, compat) [nr] = sym,
-
-extern void sys_ni_syscall(void);
-
-asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
- /*
- * Smells like a compiler bug -- it doesn't work
- * when the & below is removed.
- */
- [0 ... __NR_syscall_max] = &sys_ni_syscall,
-#include <asm/syscalls_64.h>
-};
#include <asm/ftrace.h>
#include <asm/traps.h>
#include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
#include <asm/mce.h>
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
#include <asm/alternative.h>
+#include <asm/fpu/xstate.h>
+#include <asm/trace/mpx.h>
#include <asm/mpx.h>
#ifdef CONFIG_X86_64
#else
#include <asm/processor-flags.h>
#include <asm/setup.h>
-
-asmlinkage int system_call(void);
+#include <asm/proto.h>
#endif
/* Must be page-aligned because the real IDT is used in a fixmap. */
dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
{
- struct task_struct *tsk = current;
- struct xsave_struct *xsave_buf;
enum ctx_state prev_state;
- struct bndcsr *bndcsr;
+ const struct bndcsr *bndcsr;
siginfo_t *info;
prev_state = exception_enter();
/*
* We need to look at BNDSTATUS to resolve this exception.
- * It is not directly accessible, though, so we need to
- * do an xsave and then pull it out of the xsave buffer.
+ * A NULL here might mean that it is in its 'init state',
+ * which is all zeros which indicates MPX was not
+ * responsible for the exception.
*/
- fpu_save_init(&tsk->thread.fpu);
- xsave_buf = &(tsk->thread.fpu.state->xsave);
- bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
if (!bndcsr)
goto exit_trap;
+ trace_bounds_exception_mpx(bndcsr);
/*
* The error code field of the BNDSTATUS register communicates status
* information of a bound range exception #BR or operation involving
*/
switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
case 2: /* Bound directory has invalid entry. */
- if (mpx_handle_bd_fault(xsave_buf))
+ if (mpx_handle_bd_fault())
goto exit_trap;
break; /* Success, it was handled */
case 1: /* Bound violation. */
- info = mpx_generate_siginfo(regs, xsave_buf);
+ info = mpx_generate_siginfo(regs);
if (IS_ERR(info)) {
/*
* We failed to decode the MPX instruction. Act as if
static void math_error(struct pt_regs *regs, int error_code, int trapnr)
{
struct task_struct *task = current;
+ struct fpu *fpu = &task->thread.fpu;
siginfo_t info;
- unsigned short err;
char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
"simd exception";
return;
conditional_sti(regs);
- if (!user_mode(regs))
- {
+ if (!user_mode(regs)) {
if (!fixup_exception(regs)) {
task->thread.error_code = error_code;
task->thread.trap_nr = trapnr;
/*
* Save the info for the exception handler and clear the error.
*/
- unlazy_fpu(task);
- task->thread.trap_nr = trapnr;
+ fpu__save(fpu);
+
+ task->thread.trap_nr = trapnr;
task->thread.error_code = error_code;
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
- if (trapnr == X86_TRAP_MF) {
- unsigned short cwd, swd;
- /*
- * (~cwd & swd) will mask out exceptions that are not set to unmasked
- * status. 0x3f is the exception bits in these regs, 0x200 is the
- * C1 reg you need in case of a stack fault, 0x040 is the stack
- * fault bit. We should only be taking one exception at a time,
- * so if this combination doesn't produce any single exception,
- * then we have a bad program that isn't synchronizing its FPU usage
- * and it will suffer the consequences since we won't be able to
- * fully reproduce the context of the exception
- */
- cwd = get_fpu_cwd(task);
- swd = get_fpu_swd(task);
+ info.si_signo = SIGFPE;
+ info.si_errno = 0;
+ info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
- err = swd & ~cwd;
- } else {
- /*
- * The SIMD FPU exceptions are handled a little differently, as there
- * is only a single status/control register. Thus, to determine which
- * unmasked exception was caught we must mask the exception mask bits
- * at 0x1f80, and then use these to mask the exception bits at 0x3f.
- */
- unsigned short mxcsr = get_fpu_mxcsr(task);
- err = ~(mxcsr >> 7) & mxcsr;
- }
+ info.si_code = fpu__exception_code(fpu, trapnr);
- if (err & 0x001) { /* Invalid op */
- /*
- * swd & 0x240 == 0x040: Stack Underflow
- * swd & 0x240 == 0x240: Stack Overflow
- * User must clear the SF bit (0x40) if set
- */
- info.si_code = FPE_FLTINV;
- } else if (err & 0x004) { /* Divide by Zero */
- info.si_code = FPE_FLTDIV;
- } else if (err & 0x008) { /* Overflow */
- info.si_code = FPE_FLTOVF;
- } else if (err & 0x012) { /* Denormal, Underflow */
- info.si_code = FPE_FLTUND;
- } else if (err & 0x020) { /* Precision */
- info.si_code = FPE_FLTRES;
- } else {
- /*
- * If we're using IRQ 13, or supposedly even some trap
- * X86_TRAP_MF implementations, it's possible
- * we get a spurious trap, which is not an error.
- */
+ /* Retry when we get spurious exceptions: */
+ if (!info.si_code)
return;
- }
+
force_sig_info(SIGFPE, &info, task);
}
do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
{
conditional_sti(regs);
-#if 0
- /* No need to warn about this any longer. */
- pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n");
-#endif
-}
-
-asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void)
-{
}
-asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
-{
-}
-
-/*
- * 'math_state_restore()' saves the current math information in the
- * old math state array, and gets the new ones from the current task
- *
- * Careful.. There are problems with IBM-designed IRQ13 behaviour.
- * Don't touch unless you *really* know how it works.
- *
- * Must be called with kernel preemption disabled (eg with local
- * local interrupts as in the case of do_device_not_available).
- */
-void math_state_restore(void)
-{
- struct task_struct *tsk = current;
-
- if (!tsk_used_math(tsk)) {
- local_irq_enable();
- /*
- * does a slab alloc which can sleep
- */
- if (init_fpu(tsk)) {
- /*
- * ran out of memory!
- */
- do_group_exit(SIGKILL);
- return;
- }
- local_irq_disable();
- }
-
- /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */
- kernel_fpu_disable();
- __thread_fpu_begin(tsk);
- if (unlikely(restore_fpu_checking(tsk))) {
- fpu_reset_state(tsk);
- force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
- } else {
- tsk->thread.fpu_counter++;
- }
- kernel_fpu_enable();
-}
-EXPORT_SYMBOL_GPL(math_state_restore);
-
dotraplinkage void
do_device_not_available(struct pt_regs *regs, long error_code)
{
return;
}
#endif
- math_state_restore(); /* interrupts still off */
+ fpu__restore(¤t->thread.fpu); /* interrupts still off */
#ifdef CONFIG_X86_32
conditional_sti(regs);
#endif
set_bit(i, used_vectors);
#ifdef CONFIG_IA32_EMULATION
- set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
+ set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat);
set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
#ifdef CONFIG_X86_32
- set_system_trap_gate(SYSCALL_VECTOR, &system_call);
- set_bit(SYSCALL_VECTOR, used_vectors);
+ set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32);
+ set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
/*
*/
static inline unsigned int loop_timeout(int cpu)
{
- return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20;
+ return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20;
}
/*
#include <linux/kdebug.h>
#include <asm/processor.h>
#include <asm/insn.h>
+#include <asm/mmu_context.h>
/* Post-execution fixups. */
}
#ifdef CONFIG_X86_64
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
- return !config_enabled(CONFIG_IA32_EMULATION) ||
- !(mm->context.ia32_compat == TIF_IA32);
-}
/*
* If arch_uprobe->insn doesn't use rip-relative addressing, return
* immediately. Otherwise, rewrite the instruction so that it accesses
}
}
#else /* 32-bit: */
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
- return false;
-}
/*
* No RIP-relative addressing on 32-bit
*/
+++ /dev/null
-/*
- * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
- *
- * Based on the original implementation which is:
- * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
- * Copyright 2003 Andi Kleen, SuSE Labs.
- *
- * Parts of the original code have been moved to arch/x86/vdso/vma.c
- *
- * This file implements vsyscall emulation. vsyscalls are a legacy ABI:
- * Userspace can request certain kernel services by calling fixed
- * addresses. This concept is problematic:
- *
- * - It interferes with ASLR.
- * - It's awkward to write code that lives in kernel addresses but is
- * callable by userspace at fixed addresses.
- * - The whole concept is impossible for 32-bit compat userspace.
- * - UML cannot easily virtualize a vsyscall.
- *
- * As of mid-2014, I believe that there is no new userspace code that
- * will use a vsyscall if the vDSO is present. I hope that there will
- * soon be no new userspace code that will ever use a vsyscall.
- *
- * The code in this file emulates vsyscalls when notified of a page
- * fault to a vsyscall address.
- */
-
-#include <linux/kernel.h>
-#include <linux/timer.h>
-#include <linux/syscalls.h>
-#include <linux/ratelimit.h>
-
-#include <asm/vsyscall.h>
-#include <asm/unistd.h>
-#include <asm/fixmap.h>
-#include <asm/traps.h>
-
-#define CREATE_TRACE_POINTS
-#include "vsyscall_trace.h"
-
-static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
-
-static int __init vsyscall_setup(char *str)
-{
- if (str) {
- if (!strcmp("emulate", str))
- vsyscall_mode = EMULATE;
- else if (!strcmp("native", str))
- vsyscall_mode = NATIVE;
- else if (!strcmp("none", str))
- vsyscall_mode = NONE;
- else
- return -EINVAL;
-
- return 0;
- }
-
- return -EINVAL;
-}
-early_param("vsyscall", vsyscall_setup);
-
-static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
- const char *message)
-{
- if (!show_unhandled_signals)
- return;
-
- printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
- level, current->comm, task_pid_nr(current),
- message, regs->ip, regs->cs,
- regs->sp, regs->ax, regs->si, regs->di);
-}
-
-static int addr_to_vsyscall_nr(unsigned long addr)
-{
- int nr;
-
- if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
- return -EINVAL;
-
- nr = (addr & 0xC00UL) >> 10;
- if (nr >= 3)
- return -EINVAL;
-
- return nr;
-}
-
-static bool write_ok_or_segv(unsigned long ptr, size_t size)
-{
- /*
- * XXX: if access_ok, get_user, and put_user handled
- * sig_on_uaccess_error, this could go away.
- */
-
- if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) {
- siginfo_t info;
- struct thread_struct *thread = ¤t->thread;
-
- thread->error_code = 6; /* user fault, no page, write */
- thread->cr2 = ptr;
- thread->trap_nr = X86_TRAP_PF;
-
- memset(&info, 0, sizeof(info));
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = SEGV_MAPERR;
- info.si_addr = (void __user *)ptr;
-
- force_sig_info(SIGSEGV, &info, current);
- return false;
- } else {
- return true;
- }
-}
-
-bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
-{
- struct task_struct *tsk;
- unsigned long caller;
- int vsyscall_nr, syscall_nr, tmp;
- int prev_sig_on_uaccess_error;
- long ret;
-
- /*
- * No point in checking CS -- the only way to get here is a user mode
- * trap to a high address, which means that we're in 64-bit user code.
- */
-
- WARN_ON_ONCE(address != regs->ip);
-
- if (vsyscall_mode == NONE) {
- warn_bad_vsyscall(KERN_INFO, regs,
- "vsyscall attempted with vsyscall=none");
- return false;
- }
-
- vsyscall_nr = addr_to_vsyscall_nr(address);
-
- trace_emulate_vsyscall(vsyscall_nr);
-
- if (vsyscall_nr < 0) {
- warn_bad_vsyscall(KERN_WARNING, regs,
- "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
- goto sigsegv;
- }
-
- if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
- warn_bad_vsyscall(KERN_WARNING, regs,
- "vsyscall with bad stack (exploit attempt?)");
- goto sigsegv;
- }
-
- tsk = current;
-
- /*
- * Check for access_ok violations and find the syscall nr.
- *
- * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
- * 64-bit, so we don't need to special-case it here. For all the
- * vsyscalls, NULL means "don't write anything" not "write it at
- * address 0".
- */
- switch (vsyscall_nr) {
- case 0:
- if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
- !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
- ret = -EFAULT;
- goto check_fault;
- }
-
- syscall_nr = __NR_gettimeofday;
- break;
-
- case 1:
- if (!write_ok_or_segv(regs->di, sizeof(time_t))) {
- ret = -EFAULT;
- goto check_fault;
- }
-
- syscall_nr = __NR_time;
- break;
-
- case 2:
- if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
- !write_ok_or_segv(regs->si, sizeof(unsigned))) {
- ret = -EFAULT;
- goto check_fault;
- }
-
- syscall_nr = __NR_getcpu;
- break;
- }
-
- /*
- * Handle seccomp. regs->ip must be the original value.
- * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt.
- *
- * We could optimize the seccomp disabled case, but performance
- * here doesn't matter.
- */
- regs->orig_ax = syscall_nr;
- regs->ax = -ENOSYS;
- tmp = secure_computing();
- if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
- warn_bad_vsyscall(KERN_DEBUG, regs,
- "seccomp tried to change syscall nr or ip");
- do_exit(SIGSYS);
- }
- regs->orig_ax = -1;
- if (tmp)
- goto do_ret; /* skip requested */
-
- /*
- * With a real vsyscall, page faults cause SIGSEGV. We want to
- * preserve that behavior to make writing exploits harder.
- */
- prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error;
- current_thread_info()->sig_on_uaccess_error = 1;
-
- ret = -EFAULT;
- switch (vsyscall_nr) {
- case 0:
- ret = sys_gettimeofday(
- (struct timeval __user *)regs->di,
- (struct timezone __user *)regs->si);
- break;
-
- case 1:
- ret = sys_time((time_t __user *)regs->di);
- break;
-
- case 2:
- ret = sys_getcpu((unsigned __user *)regs->di,
- (unsigned __user *)regs->si,
- NULL);
- break;
- }
-
- current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error;
-
-check_fault:
- if (ret == -EFAULT) {
- /* Bad news -- userspace fed a bad pointer to a vsyscall. */
- warn_bad_vsyscall(KERN_INFO, regs,
- "vsyscall fault (exploit attempt?)");
-
- /*
- * If we failed to generate a signal for any reason,
- * generate one here. (This should be impossible.)
- */
- if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
- !sigismember(&tsk->pending.signal, SIGSEGV)))
- goto sigsegv;
-
- return true; /* Don't emulate the ret. */
- }
-
- regs->ax = ret;
-
-do_ret:
- /* Emulate a ret instruction. */
- regs->ip = caller;
- regs->sp += 8;
- return true;
-
-sigsegv:
- force_sig(SIGSEGV, current);
- return true;
-}
-
-/*
- * A pseudo VMA to allow ptrace access for the vsyscall page. This only
- * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
- * not need special handling anymore:
- */
-static const char *gate_vma_name(struct vm_area_struct *vma)
-{
- return "[vsyscall]";
-}
-static struct vm_operations_struct gate_vma_ops = {
- .name = gate_vma_name,
-};
-static struct vm_area_struct gate_vma = {
- .vm_start = VSYSCALL_ADDR,
- .vm_end = VSYSCALL_ADDR + PAGE_SIZE,
- .vm_page_prot = PAGE_READONLY_EXEC,
- .vm_flags = VM_READ | VM_EXEC,
- .vm_ops = &gate_vma_ops,
-};
-
-struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
-{
-#ifdef CONFIG_IA32_EMULATION
- if (!mm || mm->context.ia32_compat)
- return NULL;
-#endif
- if (vsyscall_mode == NONE)
- return NULL;
- return &gate_vma;
-}
-
-int in_gate_area(struct mm_struct *mm, unsigned long addr)
-{
- struct vm_area_struct *vma = get_gate_vma(mm);
-
- if (!vma)
- return 0;
-
- return (addr >= vma->vm_start) && (addr < vma->vm_end);
-}
-
-/*
- * Use this when you have no reliable mm, typically from interrupt
- * context. It is less reliable than using a task's mm and may give
- * false positives.
- */
-int in_gate_area_no_mm(unsigned long addr)
-{
- return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
-}
-
-void __init map_vsyscall(void)
-{
- extern char __vsyscall_page;
- unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
-
- if (vsyscall_mode != NONE)
- __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
- vsyscall_mode == NATIVE
- ? PAGE_KERNEL_VSYSCALL
- : PAGE_KERNEL_VVAR);
-
- BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
- (unsigned long)VSYSCALL_ADDR);
-}
+++ /dev/null
-/*
- * vsyscall_emu_64.S: Vsyscall emulation page
- *
- * Copyright (c) 2011 Andy Lutomirski
- *
- * Subject to the GNU General Public License, version 2
- */
-
-#include <linux/linkage.h>
-
-#include <asm/irq_vectors.h>
-#include <asm/page_types.h>
-#include <asm/unistd_64.h>
-
-__PAGE_ALIGNED_DATA
- .globl __vsyscall_page
- .balign PAGE_SIZE, 0xcc
- .type __vsyscall_page, @object
-__vsyscall_page:
-
- mov $__NR_gettimeofday, %rax
- syscall
- ret
-
- .balign 1024, 0xcc
- mov $__NR_time, %rax
- syscall
- ret
-
- .balign 1024, 0xcc
- mov $__NR_getcpu, %rax
- syscall
- ret
-
- .balign 4096, 0xcc
-
- .size __vsyscall_page, 4096
+++ /dev/null
-/*
- * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
- * Copyright 2003 Andi Kleen, SuSE Labs.
- *
- * Modified for x86 32 bit architecture by
- * Stefani Seibold <stefani@seibold.net>
- * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
- *
- * Thanks to hpa@transmeta.com for some useful hint.
- * Special thanks to Ingo Molnar for his early experience with
- * a different vsyscall implementation for Linux/IA32 and for the name.
- *
- */
-
-#include <linux/timekeeper_internal.h>
-#include <asm/vgtod.h>
-#include <asm/vvar.h>
-
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
-
-void update_vsyscall_tz(void)
-{
- vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest;
- vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime;
-}
-
-void update_vsyscall(struct timekeeper *tk)
-{
- struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
-
- gtod_write_begin(vdata);
-
- /* copy vsyscall data */
- vdata->vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
- vdata->cycle_last = tk->tkr_mono.cycle_last;
- vdata->mask = tk->tkr_mono.mask;
- vdata->mult = tk->tkr_mono.mult;
- vdata->shift = tk->tkr_mono.shift;
-
- vdata->wall_time_sec = tk->xtime_sec;
- vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec;
-
- vdata->monotonic_time_sec = tk->xtime_sec
- + tk->wall_to_monotonic.tv_sec;
- vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec
- + ((u64)tk->wall_to_monotonic.tv_nsec
- << tk->tkr_mono.shift);
- while (vdata->monotonic_time_snsec >=
- (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
- vdata->monotonic_time_snsec -=
- ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
- vdata->monotonic_time_sec++;
- }
-
- vdata->wall_time_coarse_sec = tk->xtime_sec;
- vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >>
- tk->tkr_mono.shift);
-
- vdata->monotonic_time_coarse_sec =
- vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
- vdata->monotonic_time_coarse_nsec =
- vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
-
- while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) {
- vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC;
- vdata->monotonic_time_coarse_sec++;
- }
-
- gtod_write_end(vdata);
-}
+++ /dev/null
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM vsyscall
-
-#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
-#define __VSYSCALL_TRACE_H
-
-#include <linux/tracepoint.h>
-
-TRACE_EVENT(emulate_vsyscall,
-
- TP_PROTO(int nr),
-
- TP_ARGS(nr),
-
- TP_STRUCT__entry(__field(int, nr)),
-
- TP_fast_assign(
- __entry->nr = nr;
- ),
-
- TP_printk("nr = %d", __entry->nr)
-);
-
-#endif
-
-#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../arch/x86/kernel
-#define TRACE_INCLUDE_FILE vsyscall_trace
-#include <trace/define_trace.h>
#ifdef CONFIG_PREEMPT
EXPORT_SYMBOL(___preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
-EXPORT_SYMBOL(___preempt_schedule_context);
-#endif
+EXPORT_SYMBOL(___preempt_schedule_notrace);
#endif
#if defined(CONFIG_PCI_MSI)
struct x86_msi_ops x86_msi = {
.setup_msi_irqs = native_setup_msi_irqs,
- .compose_msi_msg = native_compose_msi_msg,
.teardown_msi_irq = native_teardown_msi_irq,
.teardown_msi_irqs = default_teardown_msi_irqs,
.restore_msi_irqs = default_restore_msi_irqs,
- .setup_hpet_msi = default_setup_hpet_msi,
};
/* MSI arch specific hooks */
#endif
struct x86_io_apic_ops x86_io_apic_ops = {
- .init = native_io_apic_init_mappings,
.read = native_io_apic_read,
- .write = native_io_apic_write,
- .modify = native_io_apic_modify,
.disable = native_disable_io_apic,
- .print_entries = native_io_apic_print_entries,
- .set_affinity = native_ioapic_set_affinity,
- .setup_entry = native_setup_ioapic_entry,
- .eoi_ioapic_pin = native_eoi_ioapic_pin,
};
+++ /dev/null
-/*
- * xsave/xrstor support.
- *
- * Author: Suresh Siddha <suresh.b.siddha@intel.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/bootmem.h>
-#include <linux/compat.h>
-#include <linux/cpu.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/sigframe.h>
-#include <asm/tlbflush.h>
-#include <asm/xcr.h>
-
-/*
- * Supported feature mask by the CPU and the kernel.
- */
-u64 pcntxt_mask;
-
-/*
- * Represents init state for the supported extended state.
- */
-struct xsave_struct *init_xstate_buf;
-
-static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
-static unsigned int *xstate_offsets, *xstate_sizes;
-static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8];
-static unsigned int xstate_features;
-
-/*
- * If a processor implementation discern that a processor state component is
- * in its initialized state it may modify the corresponding bit in the
- * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory
- * layout in the case of xsaveopt. While presenting the xstate information to
- * the user, we always ensure that the memory layout of a feature will be in
- * the init state if the corresponding header bit is zero. This is to ensure
- * that the user doesn't see some stale state in the memory layout during
- * signal handling, debugging etc.
- */
-void __sanitize_i387_state(struct task_struct *tsk)
-{
- struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
- int feature_bit = 0x2;
- u64 xstate_bv;
-
- if (!fx)
- return;
-
- xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
-
- /*
- * None of the feature bits are in init state. So nothing else
- * to do for us, as the memory layout is up to date.
- */
- if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
- return;
-
- /*
- * FP is in init state
- */
- if (!(xstate_bv & XSTATE_FP)) {
- fx->cwd = 0x37f;
- fx->swd = 0;
- fx->twd = 0;
- fx->fop = 0;
- fx->rip = 0;
- fx->rdp = 0;
- memset(&fx->st_space[0], 0, 128);
- }
-
- /*
- * SSE is in init state
- */
- if (!(xstate_bv & XSTATE_SSE))
- memset(&fx->xmm_space[0], 0, 256);
-
- xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2;
-
- /*
- * Update all the other memory layouts for which the corresponding
- * header bit is in the init state.
- */
- while (xstate_bv) {
- if (xstate_bv & 0x1) {
- int offset = xstate_offsets[feature_bit];
- int size = xstate_sizes[feature_bit];
-
- memcpy(((void *) fx) + offset,
- ((void *) init_xstate_buf) + offset,
- size);
- }
-
- xstate_bv >>= 1;
- feature_bit++;
- }
-}
-
-/*
- * Check for the presence of extended state information in the
- * user fpstate pointer in the sigcontext.
- */
-static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
- void __user *fpstate,
- struct _fpx_sw_bytes *fx_sw)
-{
- int min_xstate_size = sizeof(struct i387_fxsave_struct) +
- sizeof(struct xsave_hdr_struct);
- unsigned int magic2;
-
- if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
- return -1;
-
- /* Check for the first magic field and other error scenarios. */
- if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
- fx_sw->xstate_size < min_xstate_size ||
- fx_sw->xstate_size > xstate_size ||
- fx_sw->xstate_size > fx_sw->extended_size)
- return -1;
-
- /*
- * Check for the presence of second magic word at the end of memory
- * layout. This detects the case where the user just copied the legacy
- * fpstate layout with out copying the extended state information
- * in the memory layout.
- */
- if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
- || magic2 != FP_XSTATE_MAGIC2)
- return -1;
-
- return 0;
-}
-
-/*
- * Signal frame handlers.
- */
-static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
-{
- if (use_fxsr()) {
- struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
- struct user_i387_ia32_struct env;
- struct _fpstate_ia32 __user *fp = buf;
-
- convert_from_fxsr(&env, tsk);
-
- if (__copy_to_user(buf, &env, sizeof(env)) ||
- __put_user(xsave->i387.swd, &fp->status) ||
- __put_user(X86_FXSR_MAGIC, &fp->magic))
- return -1;
- } else {
- struct i387_fsave_struct __user *fp = buf;
- u32 swd;
- if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
- return -1;
- }
-
- return 0;
-}
-
-static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
-{
- struct xsave_struct __user *x = buf;
- struct _fpx_sw_bytes *sw_bytes;
- u32 xstate_bv;
- int err;
-
- /* Setup the bytes not touched by the [f]xsave and reserved for SW. */
- sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
- err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
-
- if (!use_xsave())
- return err;
-
- err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
-
- /*
- * Read the xstate_bv which we copied (directly from the cpu or
- * from the state in task struct) to the user buffers.
- */
- err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
-
- /*
- * For legacy compatible, we always set FP/SSE bits in the bit
- * vector while saving the state to the user context. This will
- * enable us capturing any changes(during sigreturn) to
- * the FP/SSE bits by the legacy applications which don't touch
- * xstate_bv in the xsave header.
- *
- * xsave aware apps can change the xstate_bv in the xsave
- * header as well as change any contents in the memory layout.
- * xrestore as part of sigreturn will capture all the changes.
- */
- xstate_bv |= XSTATE_FPSSE;
-
- err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
-
- return err;
-}
-
-static inline int save_user_xstate(struct xsave_struct __user *buf)
-{
- int err;
-
- if (use_xsave())
- err = xsave_user(buf);
- else if (use_fxsr())
- err = fxsave_user((struct i387_fxsave_struct __user *) buf);
- else
- err = fsave_user((struct i387_fsave_struct __user *) buf);
-
- if (unlikely(err) && __clear_user(buf, xstate_size))
- err = -EFAULT;
- return err;
-}
-
-/*
- * Save the fpu, extended register state to the user signal frame.
- *
- * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
- * state is copied.
- * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
- *
- * buf == buf_fx for 64-bit frames and 32-bit fsave frame.
- * buf != buf_fx for 32-bit frames with fxstate.
- *
- * If the fpu, extended register state is live, save the state directly
- * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
- * copy the thread's fpu state to the user frame starting at 'buf_fx'.
- *
- * If this is a 32-bit frame with fxstate, put a fsave header before
- * the aligned state at 'buf_fx'.
- *
- * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
- * indicating the absence/presence of the extended state to the user.
- */
-int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
-{
- struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave;
- struct task_struct *tsk = current;
- int ia32_fxstate = (buf != buf_fx);
-
- ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
- config_enabled(CONFIG_IA32_EMULATION));
-
- if (!access_ok(VERIFY_WRITE, buf, size))
- return -EACCES;
-
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_get(current, NULL, 0,
- sizeof(struct user_i387_ia32_struct), NULL,
- (struct _fpstate_ia32 __user *) buf) ? -1 : 1;
-
- if (user_has_fpu()) {
- /* Save the live register state to the user directly. */
- if (save_user_xstate(buf_fx))
- return -1;
- /* Update the thread's fxstate to save the fsave header. */
- if (ia32_fxstate)
- fpu_fxsave(&tsk->thread.fpu);
- } else {
- sanitize_i387_state(tsk);
- if (__copy_to_user(buf_fx, xsave, xstate_size))
- return -1;
- }
-
- /* Save the fsave header for the 32-bit frames. */
- if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
- return -1;
-
- if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
- return -1;
-
- return 0;
-}
-
-static inline void
-sanitize_restored_xstate(struct task_struct *tsk,
- struct user_i387_ia32_struct *ia32_env,
- u64 xstate_bv, int fx_only)
-{
- struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
- struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
-
- if (use_xsave()) {
- /* These bits must be zero. */
- memset(xsave_hdr->reserved, 0, 48);
-
- /*
- * Init the state that is not present in the memory
- * layout and not enabled by the OS.
- */
- if (fx_only)
- xsave_hdr->xstate_bv = XSTATE_FPSSE;
- else
- xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
- }
-
- if (use_fxsr()) {
- /*
- * mscsr reserved bits must be masked to zero for security
- * reasons.
- */
- xsave->i387.mxcsr &= mxcsr_feature_mask;
-
- convert_to_fxsr(tsk, ia32_env);
- }
-}
-
-/*
- * Restore the extended state if present. Otherwise, restore the FP/SSE state.
- */
-static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
-{
- if (use_xsave()) {
- if ((unsigned long)buf % 64 || fx_only) {
- u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
- xrstor_state(init_xstate_buf, init_bv);
- return fxrstor_user(buf);
- } else {
- u64 init_bv = pcntxt_mask & ~xbv;
- if (unlikely(init_bv))
- xrstor_state(init_xstate_buf, init_bv);
- return xrestore_user(buf, xbv);
- }
- } else if (use_fxsr()) {
- return fxrstor_user(buf);
- } else
- return frstor_user(buf);
-}
-
-int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
-{
- int ia32_fxstate = (buf != buf_fx);
- struct task_struct *tsk = current;
- int state_size = xstate_size;
- u64 xstate_bv = 0;
- int fx_only = 0;
-
- ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
- config_enabled(CONFIG_IA32_EMULATION));
-
- if (!buf) {
- fpu_reset_state(tsk);
- return 0;
- }
-
- if (!access_ok(VERIFY_READ, buf, size))
- return -EACCES;
-
- if (!used_math() && init_fpu(tsk))
- return -1;
-
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_set(current, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- NULL, buf) != 0;
-
- if (use_xsave()) {
- struct _fpx_sw_bytes fx_sw_user;
- if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
- /*
- * Couldn't find the extended state information in the
- * memory layout. Restore just the FP/SSE and init all
- * the other extended state.
- */
- state_size = sizeof(struct i387_fxsave_struct);
- fx_only = 1;
- } else {
- state_size = fx_sw_user.xstate_size;
- xstate_bv = fx_sw_user.xstate_bv;
- }
- }
-
- if (ia32_fxstate) {
- /*
- * For 32-bit frames with fxstate, copy the user state to the
- * thread's fpu state, reconstruct fxstate from the fsave
- * header. Sanitize the copied state etc.
- */
- struct fpu *fpu = &tsk->thread.fpu;
- struct user_i387_ia32_struct env;
- int err = 0;
-
- /*
- * Drop the current fpu which clears used_math(). This ensures
- * that any context-switch during the copy of the new state,
- * avoids the intermediate state from getting restored/saved.
- * Thus avoiding the new restored state from getting corrupted.
- * We will be ready to restore/save the state only after
- * set_used_math() is again set.
- */
- drop_fpu(tsk);
-
- if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
- __copy_from_user(&env, buf, sizeof(env))) {
- fpu_finit(fpu);
- err = -1;
- } else {
- sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
- }
-
- set_used_math();
- if (use_eager_fpu()) {
- preempt_disable();
- math_state_restore();
- preempt_enable();
- }
-
- return err;
- } else {
- /*
- * For 64-bit frames and 32-bit fsave frames, restore the user
- * state to the registers directly (with exceptions handled).
- */
- user_fpu_begin();
- if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
- fpu_reset_state(tsk);
- return -1;
- }
- }
-
- return 0;
-}
-
-/*
- * Prepare the SW reserved portion of the fxsave memory layout, indicating
- * the presence of the extended state information in the memory layout
- * pointed by the fpstate pointer in the sigcontext.
- * This will be saved when ever the FP and extended state context is
- * saved on the user stack during the signal handler delivery to the user.
- */
-static void prepare_fx_sw_frame(void)
-{
- int fsave_header_size = sizeof(struct i387_fsave_struct);
- int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
-
- if (config_enabled(CONFIG_X86_32))
- size += fsave_header_size;
-
- fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
- fx_sw_reserved.extended_size = size;
- fx_sw_reserved.xstate_bv = pcntxt_mask;
- fx_sw_reserved.xstate_size = xstate_size;
-
- if (config_enabled(CONFIG_IA32_EMULATION)) {
- fx_sw_reserved_ia32 = fx_sw_reserved;
- fx_sw_reserved_ia32.extended_size += fsave_header_size;
- }
-}
-
-/*
- * Enable the extended processor state save/restore feature
- */
-static inline void xstate_enable(void)
-{
- cr4_set_bits(X86_CR4_OSXSAVE);
- xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-}
-
-/*
- * Record the offsets and sizes of different state managed by the xsave
- * memory layout.
- */
-static void __init setup_xstate_features(void)
-{
- int eax, ebx, ecx, edx, leaf = 0x2;
-
- xstate_features = fls64(pcntxt_mask);
- xstate_offsets = alloc_bootmem(xstate_features * sizeof(int));
- xstate_sizes = alloc_bootmem(xstate_features * sizeof(int));
-
- do {
- cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
-
- if (eax == 0)
- break;
-
- xstate_offsets[leaf] = ebx;
- xstate_sizes[leaf] = eax;
-
- leaf++;
- } while (1);
-}
-
-/*
- * This function sets up offsets and sizes of all extended states in
- * xsave area. This supports both standard format and compacted format
- * of the xsave aread.
- *
- * Input: void
- * Output: void
- */
-void setup_xstate_comp(void)
-{
- unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8];
- int i;
-
- /*
- * The FP xstates and SSE xstates are legacy states. They are always
- * in the fixed offsets in the xsave area in either compacted form
- * or standard form.
- */
- xstate_comp_offsets[0] = 0;
- xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space);
-
- if (!cpu_has_xsaves) {
- for (i = 2; i < xstate_features; i++) {
- if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
- xstate_comp_offsets[i] = xstate_offsets[i];
- xstate_comp_sizes[i] = xstate_sizes[i];
- }
- }
- return;
- }
-
- xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
- for (i = 2; i < xstate_features; i++) {
- if (test_bit(i, (unsigned long *)&pcntxt_mask))
- xstate_comp_sizes[i] = xstate_sizes[i];
- else
- xstate_comp_sizes[i] = 0;
-
- if (i > 2)
- xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
- + xstate_comp_sizes[i-1];
-
- }
-}
-
-/*
- * setup the xstate image representing the init state
- */
-static void __init setup_init_fpu_buf(void)
-{
- /*
- * Setup init_xstate_buf to represent the init state of
- * all the features managed by the xsave
- */
- init_xstate_buf = alloc_bootmem_align(xstate_size,
- __alignof__(struct xsave_struct));
- fx_finit(&init_xstate_buf->i387);
-
- if (!cpu_has_xsave)
- return;
-
- setup_xstate_features();
-
- if (cpu_has_xsaves) {
- init_xstate_buf->xsave_hdr.xcomp_bv =
- (u64)1 << 63 | pcntxt_mask;
- init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask;
- }
-
- /*
- * Init all the features state with header_bv being 0x0
- */
- xrstor_state_booting(init_xstate_buf, -1);
- /*
- * Dump the init state again. This is to identify the init state
- * of any feature which is not represented by all zero's.
- */
- xsave_state_booting(init_xstate_buf, -1);
-}
-
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
-static int __init eager_fpu_setup(char *s)
-{
- if (!strcmp(s, "on"))
- eagerfpu = ENABLE;
- else if (!strcmp(s, "off"))
- eagerfpu = DISABLE;
- else if (!strcmp(s, "auto"))
- eagerfpu = AUTO;
- return 1;
-}
-__setup("eagerfpu=", eager_fpu_setup);
-
-
-/*
- * Calculate total size of enabled xstates in XCR0/pcntxt_mask.
- */
-static void __init init_xstate_size(void)
-{
- unsigned int eax, ebx, ecx, edx;
- int i;
-
- if (!cpu_has_xsaves) {
- cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- xstate_size = ebx;
- return;
- }
-
- xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
- for (i = 2; i < 64; i++) {
- if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
- cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
- xstate_size += eax;
- }
- }
-}
-
-/*
- * Enable and initialize the xsave feature.
- */
-static void __init xstate_enable_boot_cpu(void)
-{
- unsigned int eax, ebx, ecx, edx;
-
- if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
- WARN(1, KERN_ERR "XSTATE_CPUID missing\n");
- return;
- }
-
- cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- pcntxt_mask = eax + ((u64)edx << 32);
-
- if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
- pr_err("FP/SSE not shown under xsave features 0x%llx\n",
- pcntxt_mask);
- BUG();
- }
-
- /*
- * Support only the state known to OS.
- */
- pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
-
- xstate_enable();
-
- /*
- * Recompute the context size for enabled features
- */
- init_xstate_size();
-
- update_regset_xstate_info(xstate_size, pcntxt_mask);
- prepare_fx_sw_frame();
- setup_init_fpu_buf();
-
- /* Auto enable eagerfpu for xsaveopt */
- if (cpu_has_xsaveopt && eagerfpu != DISABLE)
- eagerfpu = ENABLE;
-
- if (pcntxt_mask & XSTATE_EAGER) {
- if (eagerfpu == DISABLE) {
- pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n",
- pcntxt_mask & XSTATE_EAGER);
- pcntxt_mask &= ~XSTATE_EAGER;
- } else {
- eagerfpu = ENABLE;
- }
- }
-
- pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n",
- pcntxt_mask, xstate_size,
- cpu_has_xsaves ? "compacted form" : "standard form");
-}
-
-/*
- * For the very first instance, this calls xstate_enable_boot_cpu();
- * for all subsequent instances, this calls xstate_enable().
- *
- * This is somewhat obfuscated due to the lack of powerful enough
- * overrides for the section checks.
- */
-void xsave_init(void)
-{
- static __refdata void (*next_func)(void) = xstate_enable_boot_cpu;
- void (*this_func)(void);
-
- if (!cpu_has_xsave)
- return;
-
- this_func = next_func;
- next_func = xstate_enable;
- this_func();
-}
-
-/*
- * setup_init_fpu_buf() is __init and it is OK to call it here because
- * init_xstate_buf will be unset only once during boot.
- */
-void __init_refok eager_fpu_init(void)
-{
- WARN_ON(used_math());
- current_thread_info()->status = 0;
-
- if (eagerfpu == ENABLE)
- setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
-
- if (!cpu_has_eager_fpu) {
- stts();
- return;
- }
-
- if (!init_xstate_buf)
- setup_init_fpu_buf();
-}
-
-/*
- * Given the xsave area and a state inside, this function returns the
- * address of the state.
- *
- * This is the API that is called to get xstate address in either
- * standard format or compacted format of xsave area.
- *
- * Inputs:
- * xsave: base address of the xsave area;
- * xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE,
- * etc.)
- * Output:
- * address of the state in the xsave area.
- */
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
-{
- int feature = fls64(xstate) - 1;
- if (!test_bit(feature, (unsigned long *)&pcntxt_mask))
- return NULL;
-
- return (void *)xsave + xstate_comp_offsets[feature];
-}
-EXPORT_SYMBOL_GPL(get_xsave_addr);
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
#include <asm/user.h>
-#include <asm/xsave.h>
+#include <asm/fpu/xstate.h>
#include "cpuid.h"
#include "lapic.h"
#include "mmu.h"
if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
+ vcpu->arch.eager_fpu = guest_cpuid_has_mpx(vcpu);
+
/*
* The existing code assumes virtual address is 48-bit in the canonical
* address checks; exit if it is ever changed.
best = kvm_find_cpuid_entry(vcpu, 7, 0);
return best && (best->ebx & bit(X86_FEATURE_RTM));
}
+
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 7, 0);
+ return best && (best->ebx & bit(X86_FEATURE_MPX));
+}
#endif
apic->divide_count);
}
+static void apic_update_lvtt(struct kvm_lapic *apic)
+{
+ u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) &
+ apic->lapic_timer.timer_mode_mask;
+
+ if (apic->lapic_timer.timer_mode != timer_mode) {
+ apic->lapic_timer.timer_mode = timer_mode;
+ hrtimer_cancel(&apic->lapic_timer.timer);
+ }
+}
+
static void apic_timer_expired(struct kvm_lapic *apic)
{
struct kvm_vcpu *vcpu = apic->vcpu;
apic_set_reg(apic, APIC_LVTT + 0x10 * i,
lvt_val | APIC_LVT_MASKED);
}
+ apic_update_lvtt(apic);
atomic_set(&apic->lapic_timer.pending, 0);
}
break;
- case APIC_LVTT: {
- u32 timer_mode = val & apic->lapic_timer.timer_mode_mask;
-
- if (apic->lapic_timer.timer_mode != timer_mode) {
- apic->lapic_timer.timer_mode = timer_mode;
- hrtimer_cancel(&apic->lapic_timer.timer);
- }
-
+ case APIC_LVTT:
if (!kvm_apic_sw_enabled(apic))
val |= APIC_LVT_MASKED;
val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
apic_set_reg(apic, APIC_LVTT, val);
+ apic_update_lvtt(apic);
break;
- }
case APIC_TMICT:
if (apic_lvtt_tscdeadline(apic))
for (i = 0; i < APIC_LVT_NUM; i++)
apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
- apic->lapic_timer.timer_mode = 0;
+ apic_update_lvtt(apic);
apic_set_reg(apic, APIC_LVT0,
SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
apic_update_ppr(apic);
hrtimer_cancel(&apic->lapic_timer.timer);
+ apic_update_lvtt(apic);
update_divide_count(apic);
start_apic_timer(apic);
apic->irr_pending = true;
}
}
-void update_permission_bitmask(struct kvm_vcpu *vcpu,
- struct kvm_mmu *mmu, bool ept)
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu, bool ept)
{
unsigned bit, byte, pfec;
u8 map;
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
{
bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+ bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
struct kvm_mmu *context = &vcpu->arch.mmu;
MMU_WARN_ON(VALID_PAGE(context->root_hpa));
context->base_role.cr0_wp = is_write_protection(vcpu);
context->base_role.smep_andnot_wp
= smep && !is_write_protection(vcpu);
+ context->base_role.smap_andnot_wp
+ = smap && !is_write_protection(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
const u8 *new, int bytes)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
- union kvm_mmu_page_role mask = { .word = 0 };
struct kvm_mmu_page *sp;
LIST_HEAD(invalid_list);
u64 entry, gentry, *spte;
int npte;
bool remote_flush, local_flush, zap_page;
+ union kvm_mmu_page_role mask = { };
+
+ mask.cr0_wp = 1;
+ mask.cr4_pae = 1;
+ mask.nxe = 1;
+ mask.smep_andnot_wp = 1;
+ mask.smap_andnot_wp = 1;
/*
* If we don't have indirect shadow pages, it means no page is
++vcpu->kvm->stat.mmu_pte_write;
kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
- mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (detect_write_misaligned(sp, gpa, bytes) ||
detect_write_flooding(sp)) {
int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
-void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- bool ept);
static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
{
int index = (pfec >> 1) +
(smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
+ WARN_ON(pfec & PFERR_RSVD_MASK);
+
return (mmu->permissions[index] >> pte_access) & 1;
}
mmu_is_nested(vcpu));
if (likely(r != RET_MMIO_PF_INVALID))
return r;
+
+ /*
+ * page fault with PFEC.RSVD = 1 is caused by shadow
+ * page fault, should not be used to walk guest page
+ * table.
+ */
+ error_code &= ~PFERR_RSVD_MASK;
};
r = mmu_topup_memory_caches(vcpu);
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
+ .fpu_activate = svm_fpu_activate,
.fpu_deactivate = svm_fpu_deactivate,
.tlb_flush = svm_flush_tlb,
#include <asm/vmx.h>
#include <asm/virtext.h>
#include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
+#include <asm/fpu/internal.h>
#include <asm/perf_event.h>
#include <asm/debugreg.h>
#include <asm/kexec.h>
* If the FPU is not active (through the host task or
* the guest vcpu), then restore the cr0.TS bit.
*/
- if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+ if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded)
stts();
load_gdt(this_cpu_ptr(&host_gdt));
}
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
+ .fpu_activate = vmx_fpu_activate,
.fpu_deactivate = vmx_fpu_deactivate,
.tlb_flush = vmx_flush_tlb,
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h> /* Ugh! */
-#include <asm/xcr.h>
+#include <linux/kernel_stat.h>
+#include <asm/fpu/internal.h> /* Ugh! */
#include <asm/pvclock.h>
#include <asm/div64.h>
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long old_cr4 = kvm_read_cr4(vcpu);
- unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE |
- X86_CR4_PAE | X86_CR4_SMEP;
+ unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+ X86_CR4_SMEP | X86_CR4_SMAP;
+
if (cr4 & CR4_RESERVED_BITS)
return 1;
(!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
kvm_mmu_reset_context(vcpu);
- if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
- update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
-
if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
kvm_update_cpuid(vcpu);
static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
{
- struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
- u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+ struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
+ u64 xstate_bv = xsave->header.xfeatures;
u64 valid;
/*
static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
{
- struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+ struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
u64 valid;
memcpy(xsave, src, XSAVE_HDR_OFFSET);
/* Set XSTATE_BV and possibly XCOMP_BV. */
- xsave->xsave_hdr.xstate_bv = xstate_bv;
+ xsave->header.xfeatures = xstate_bv;
if (cpu_has_xsaves)
- xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+ xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
/*
* Copy each region from the non-compacted offset to the
fill_xsave((u8 *) guest_xsave->region, vcpu);
} else {
memcpy(guest_xsave->region,
- &vcpu->arch.guest_fpu.state->fxsave,
- sizeof(struct i387_fxsave_struct));
+ &vcpu->arch.guest_fpu.state.fxsave,
+ sizeof(struct fxregs_state));
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
XSTATE_FPSSE;
}
} else {
if (xstate_bv & ~XSTATE_FPSSE)
return -EINVAL;
- memcpy(&vcpu->arch.guest_fpu.state->fxsave,
- guest_xsave->region, sizeof(struct i387_fxsave_struct));
+ memcpy(&vcpu->arch.guest_fpu.state.fxsave,
+ guest_xsave->region, sizeof(struct fxregs_state));
}
return 0;
}
return;
page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+ if (is_error_page(page))
+ return;
kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
/*
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
+ struct fpu *fpu = ¤t->thread.fpu;
int r;
sigset_t sigsaved;
- if (!tsk_used_math(current) && init_fpu(current))
- return -ENOMEM;
+ fpu__activate_curr(fpu);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct i387_fxsave_struct *fxsave =
- &vcpu->arch.guest_fpu.state->fxsave;
+ struct fxregs_state *fxsave =
+ &vcpu->arch.guest_fpu.state.fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct i387_fxsave_struct *fxsave =
- &vcpu->arch.guest_fpu.state->fxsave;
+ struct fxregs_state *fxsave =
+ &vcpu->arch.guest_fpu.state.fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
return 0;
}
-int fx_init(struct kvm_vcpu *vcpu)
+static void fx_init(struct kvm_vcpu *vcpu)
{
- int err;
-
- err = fpu_alloc(&vcpu->arch.guest_fpu);
- if (err)
- return err;
-
- fpu_finit(&vcpu->arch.guest_fpu);
+ fpstate_init(&vcpu->arch.guest_fpu.state);
if (cpu_has_xsaves)
- vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+ vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
host_xcr0 | XSTATE_COMPACTION_ENABLED;
/*
vcpu->arch.xcr0 = XSTATE_FP;
vcpu->arch.cr0 |= X86_CR0_ET;
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(fx_init);
-
-static void fx_free(struct kvm_vcpu *vcpu)
-{
- fpu_free(&vcpu->arch.guest_fpu);
}
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
kvm_put_guest_xcr0(vcpu);
vcpu->guest_fpu_loaded = 1;
__kernel_fpu_begin();
- fpu_restore_checking(&vcpu->arch.guest_fpu);
+ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
trace_kvm_fpu(1);
}
return;
vcpu->guest_fpu_loaded = 0;
- fpu_save_init(&vcpu->arch.guest_fpu);
+ copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
__kernel_fpu_end();
++vcpu->stat.fpu_reload;
- kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+ if (!vcpu->arch.eager_fpu)
+ kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+
trace_kvm_fpu(0);
}
kvmclock_reset(vcpu);
free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
- fx_free(vcpu);
kvm_x86_ops->vcpu_free(vcpu);
}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
unsigned int id)
{
+ struct kvm_vcpu *vcpu;
+
if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
printk_once(KERN_WARNING
"kvm: SMP vm created on host with unstable TSC; "
"guest TSC will not be reliable\n");
- return kvm_x86_ops->vcpu_create(kvm, id);
+
+ vcpu = kvm_x86_ops->vcpu_create(kvm, id);
+
+ /*
+ * Activate fpu unconditionally in case the guest needs eager FPU. It will be
+ * deactivated soon if it doesn't.
+ */
+ kvm_x86_ops->fpu_activate(vcpu);
+ return vcpu;
}
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
- fx_free(vcpu);
kvm_x86_ops->vcpu_free(vcpu);
}
goto fail_free_mce_banks;
}
- r = fx_init(vcpu);
- if (r)
- goto fail_free_wbinvd_dirty_mask;
+ fx_init(vcpu);
vcpu->arch.ia32_tsc_adjust_msr = 0x0;
vcpu->arch.pv_time_enabled = false;
kvm_pmu_init(vcpu);
return 0;
-fail_free_wbinvd_dirty_mask:
- free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
+
fail_free_mce_banks:
kfree(vcpu->arch.mce_banks);
fail_free_lapic:
#include <asm/e820.h>
#include <asm/mce.h>
#include <asm/io.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/stackprotector.h>
#include <asm/reboot.h> /* for struct machine_ops */
#include <asm/kvm_para.h>
.noirq_iret = (u32)lguest_noirq_iret,
.kernel_address = PAGE_OFFSET,
.blocked_interrupts = { 1 }, /* Block timer interrupts */
- .syscall_vec = SYSCALL_VECTOR,
+ .syscall_vec = IA32_SYSCALL_VECTOR,
};
/*G:037
for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
/* Some systems map "vectors" to interrupts weirdly. Not us! */
__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
- if (i != SYSCALL_VECTOR)
+ if (i != IA32_SYSCALL_VECTOR)
set_intr_gate(i, irq_entries_start +
8 * (i - FIRST_EXTERNAL_VECTOR));
}
obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
lib-y := delay.o misc.o cmdline.o
-lib-y += thunk_$(BITS).o
lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
lib-y += clear_page_64.o copy_page_64.o
lib-y += memmove_64.o memset_64.o
- lib-y += copy_user_64.o copy_user_nocache_64.o
+ lib-y += copy_user_64.o
lib-y += cmpxchg16b_emu.o
endif
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
/* if you want SMP support, implement these with real spinlocks */
.macro LOCK reg
- pushfl_cfi
+ pushfl
cli
.endm
.macro UNLOCK reg
- popfl_cfi
+ popfl
.endm
#define BEGIN(op) \
.macro endp; \
- CFI_ENDPROC; \
ENDPROC(atomic64_##op##_386); \
.purgem endp; \
.endm; \
ENTRY(atomic64_##op##_386); \
- CFI_STARTPROC; \
LOCK v;
#define ENDP endp
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
.macro read64 reg
movl %ebx, %eax
.endm
ENTRY(atomic64_read_cx8)
- CFI_STARTPROC
-
read64 %ecx
ret
- CFI_ENDPROC
ENDPROC(atomic64_read_cx8)
ENTRY(atomic64_set_cx8)
- CFI_STARTPROC
-
1:
/* we don't need LOCK_PREFIX since aligned 64-bit writes
* are atomic on 586 and newer */
jne 1b
ret
- CFI_ENDPROC
ENDPROC(atomic64_set_cx8)
ENTRY(atomic64_xchg_cx8)
- CFI_STARTPROC
-
1:
LOCK_PREFIX
cmpxchg8b (%esi)
jne 1b
ret
- CFI_ENDPROC
ENDPROC(atomic64_xchg_cx8)
.macro addsub_return func ins insc
ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebp
- pushl_cfi_reg ebx
- pushl_cfi_reg esi
- pushl_cfi_reg edi
+ pushl %ebp
+ pushl %ebx
+ pushl %esi
+ pushl %edi
movl %eax, %esi
movl %edx, %edi
10:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg edi
- popl_cfi_reg esi
- popl_cfi_reg ebx
- popl_cfi_reg ebp
+ popl %edi
+ popl %esi
+ popl %ebx
+ popl %ebp
ret
- CFI_ENDPROC
ENDPROC(atomic64_\func\()_return_cx8)
.endm
.macro incdec_return func ins insc
ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
10:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_\func\()_return_cx8)
.endm
incdec_return dec sub sbb
ENTRY(atomic64_dec_if_positive_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
2:
movl %ebx, %eax
movl %ecx, %edx
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_dec_if_positive_cx8)
ENTRY(atomic64_add_unless_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebp
- pushl_cfi_reg ebx
+ pushl %ebp
+ pushl %ebx
/* these just push these two parameters on the stack */
- pushl_cfi_reg edi
- pushl_cfi_reg ecx
+ pushl %edi
+ pushl %ecx
movl %eax, %ebp
movl %edx, %edi
movl $1, %eax
3:
addl $8, %esp
- CFI_ADJUST_CFA_OFFSET -8
- popl_cfi_reg ebx
- popl_cfi_reg ebp
+ popl %ebx
+ popl %ebp
ret
4:
cmpl %edx, 4(%esp)
jne 2b
xorl %eax, %eax
jmp 3b
- CFI_ENDPROC
ENDPROC(atomic64_add_unless_cx8)
ENTRY(atomic64_inc_not_zero_cx8)
- CFI_STARTPROC
- pushl_cfi_reg ebx
+ pushl %ebx
read64 %esi
1:
movl $1, %eax
3:
- popl_cfi_reg ebx
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(atomic64_inc_not_zero_cx8)
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/errno.h>
#include <asm/asm.h>
* alignment for the unrolled loop.
*/
ENTRY(csum_partial)
- CFI_STARTPROC
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %esi
+ pushl %ebx
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
movl 12(%esp),%esi # Function arg: unsigned char *buff
jz 8f
roll $8, %eax
8:
- popl_cfi_reg ebx
- popl_cfi_reg esi
+ popl %ebx
+ popl %esi
ret
- CFI_ENDPROC
ENDPROC(csum_partial)
#else
/* Version for PentiumII/PPro */
ENTRY(csum_partial)
- CFI_STARTPROC
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %esi
+ pushl %ebx
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
movl 12(%esp),%esi # Function arg: const unsigned char *buf
jz 90f
roll $8, %eax
90:
- popl_cfi_reg ebx
- popl_cfi_reg esi
+ popl %ebx
+ popl %esi
ret
- CFI_ENDPROC
ENDPROC(csum_partial)
#endif
#define FP 12
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
subl $4,%esp
- CFI_ADJUST_CFA_OFFSET 4
- pushl_cfi_reg edi
- pushl_cfi_reg esi
- pushl_cfi_reg ebx
+ pushl %edi
+ pushl %esi
+ pushl %ebx
movl ARGBASE+16(%esp),%eax # sum
movl ARGBASE+12(%esp),%ecx # len
movl ARGBASE+4(%esp),%esi # src
.previous
- popl_cfi_reg ebx
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi %ecx # equivalent to addl $4,%esp
+ popl %ebx
+ popl %esi
+ popl %edi
+ popl %ecx # equivalent to addl $4,%esp
ret
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
#else
#define ARGBASE 12
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
- pushl_cfi_reg ebx
- pushl_cfi_reg edi
- pushl_cfi_reg esi
+ pushl %ebx
+ pushl %edi
+ pushl %esi
movl ARGBASE+4(%esp),%esi #src
movl ARGBASE+8(%esp),%edi #dst
movl ARGBASE+12(%esp),%ecx #len
jmp 7b
.previous
- popl_cfi_reg esi
- popl_cfi_reg edi
- popl_cfi_reg ebx
+ popl %esi
+ popl %edi
+ popl %ebx
ret
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
#undef ROUND
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
* %rdi - page
*/
ENTRY(clear_page)
- CFI_STARTPROC
ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \
"jmp clear_page_c_e", X86_FEATURE_ERMS
xorl %eax,%eax
rep stosq
ret
- CFI_ENDPROC
ENDPROC(clear_page)
ENTRY(clear_page_orig)
- CFI_STARTPROC
xorl %eax,%eax
movl $4096/64,%ecx
jnz .Lloop
nop
ret
- CFI_ENDPROC
ENDPROC(clear_page_orig)
ENTRY(clear_page_c_e)
- CFI_STARTPROC
movl $4096,%ecx
xorl %eax,%eax
rep stosb
ret
- CFI_ENDPROC
ENDPROC(clear_page_c_e)
*
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/percpu.h>
.text
* %al : Operation successful
*/
ENTRY(this_cpu_cmpxchg16b_emu)
-CFI_STARTPROC
#
# Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
# *atomic* on a single cpu (as provided by the this_cpu_xx class of
# macros).
#
- pushfq_cfi
+ pushfq
cli
cmpq PER_CPU_VAR((%rsi)), %rax
movq %rbx, PER_CPU_VAR((%rsi))
movq %rcx, PER_CPU_VAR(8(%rsi))
- CFI_REMEMBER_STATE
- popfq_cfi
+ popfq
mov $1, %al
ret
- CFI_RESTORE_STATE
.Lnot_same:
- popfq_cfi
+ popfq
xor %al,%al
ret
-CFI_ENDPROC
-
ENDPROC(this_cpu_cmpxchg16b_emu)
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
.text
* %ecx : high 32 bits of new value
*/
ENTRY(cmpxchg8b_emu)
-CFI_STARTPROC
#
# Emulate 'cmpxchg8b (%esi)' on UP except we don't
# set the whole ZF thing (caller will just compare
# eax:edx with the expected value)
#
- pushfl_cfi
+ pushfl
cli
cmpl (%esi), %eax
movl %ebx, (%esi)
movl %ecx, 4(%esi)
- CFI_REMEMBER_STATE
- popfl_cfi
+ popfl
ret
- CFI_RESTORE_STATE
.Lnot_same:
movl (%esi), %eax
.Lhalf_same:
movl 4(%esi), %edx
- popfl_cfi
+ popfl
ret
-CFI_ENDPROC
ENDPROC(cmpxchg8b_emu)
/* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
*/
ALIGN
ENTRY(copy_page)
- CFI_STARTPROC
ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
movl $4096/8, %ecx
rep movsq
ret
- CFI_ENDPROC
ENDPROC(copy_page)
ENTRY(copy_page_regs)
- CFI_STARTPROC
subq $2*8, %rsp
- CFI_ADJUST_CFA_OFFSET 2*8
movq %rbx, (%rsp)
- CFI_REL_OFFSET rbx, 0
movq %r12, 1*8(%rsp)
- CFI_REL_OFFSET r12, 1*8
movl $(4096/64)-5, %ecx
.p2align 4
jnz .Loop2
movq (%rsp), %rbx
- CFI_RESTORE rbx
movq 1*8(%rsp), %r12
- CFI_RESTORE r12
addq $2*8, %rsp
- CFI_ADJUST_CFA_OFFSET -2*8
ret
- CFI_ENDPROC
ENDPROC(copy_page_regs)
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/current.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/asm.h>
#include <asm/smap.h>
- .macro ALIGN_DESTINATION
- /* check for bad alignment of destination */
- movl %edi,%ecx
- andl $7,%ecx
- jz 102f /* already aligned */
- subl $8,%ecx
- negl %ecx
- subl %ecx,%edx
-100: movb (%rsi),%al
-101: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 100b
-102:
- .section .fixup,"ax"
-103: addl %ecx,%edx /* ecx is zerorest also */
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
- .endm
-
/* Standard copy_to_user with segment limit checking */
ENTRY(_copy_to_user)
- CFI_STARTPROC
GET_THREAD_INFO(%rax)
movq %rdi,%rcx
addq %rdx,%rcx
X86_FEATURE_REP_GOOD, \
"jmp copy_user_enhanced_fast_string", \
X86_FEATURE_ERMS
- CFI_ENDPROC
ENDPROC(_copy_to_user)
/* Standard copy_from_user with segment limit checking */
ENTRY(_copy_from_user)
- CFI_STARTPROC
GET_THREAD_INFO(%rax)
movq %rsi,%rcx
addq %rdx,%rcx
X86_FEATURE_REP_GOOD, \
"jmp copy_user_enhanced_fast_string", \
X86_FEATURE_ERMS
- CFI_ENDPROC
ENDPROC(_copy_from_user)
.section .fixup,"ax"
/* must zero dest */
ENTRY(bad_from_user)
bad_from_user:
- CFI_STARTPROC
movl %edx,%ecx
xorl %eax,%eax
rep
bad_to_user:
movl %edx,%eax
ret
- CFI_ENDPROC
ENDPROC(bad_from_user)
.previous
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_unrolled)
- CFI_STARTPROC
ASM_STAC
cmpl $8,%edx
jb 20f /* less then 8 bytes, go to byte copy loop */
_ASM_EXTABLE(19b,40b)
_ASM_EXTABLE(21b,50b)
_ASM_EXTABLE(22b,50b)
- CFI_ENDPROC
ENDPROC(copy_user_generic_unrolled)
/* Some CPUs run faster using the string copy instructions.
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_string)
- CFI_STARTPROC
ASM_STAC
cmpl $8,%edx
jb 2f /* less than 8 bytes, go to byte copy loop */
_ASM_EXTABLE(1b,11b)
_ASM_EXTABLE(3b,12b)
- CFI_ENDPROC
ENDPROC(copy_user_generic_string)
/*
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_enhanced_fast_string)
- CFI_STARTPROC
ASM_STAC
movl %edx,%ecx
1: rep
.previous
_ASM_EXTABLE(1b,12b)
- CFI_ENDPROC
ENDPROC(copy_user_enhanced_fast_string)
+
+/*
+ * copy_user_nocache - Uncached memory copy with exception handling
+ * This will force destination/source out of cache for more performance.
+ */
+ENTRY(__copy_user_nocache)
+ ASM_STAC
+ cmpl $8,%edx
+ jb 20f /* less then 8 bytes, go to byte copy loop */
+ ALIGN_DESTINATION
+ movl %edx,%ecx
+ andl $63,%edx
+ shrl $6,%ecx
+ jz 17f
+1: movq (%rsi),%r8
+2: movq 1*8(%rsi),%r9
+3: movq 2*8(%rsi),%r10
+4: movq 3*8(%rsi),%r11
+5: movnti %r8,(%rdi)
+6: movnti %r9,1*8(%rdi)
+7: movnti %r10,2*8(%rdi)
+8: movnti %r11,3*8(%rdi)
+9: movq 4*8(%rsi),%r8
+10: movq 5*8(%rsi),%r9
+11: movq 6*8(%rsi),%r10
+12: movq 7*8(%rsi),%r11
+13: movnti %r8,4*8(%rdi)
+14: movnti %r9,5*8(%rdi)
+15: movnti %r10,6*8(%rdi)
+16: movnti %r11,7*8(%rdi)
+ leaq 64(%rsi),%rsi
+ leaq 64(%rdi),%rdi
+ decl %ecx
+ jnz 1b
+17: movl %edx,%ecx
+ andl $7,%edx
+ shrl $3,%ecx
+ jz 20f
+18: movq (%rsi),%r8
+19: movnti %r8,(%rdi)
+ leaq 8(%rsi),%rsi
+ leaq 8(%rdi),%rdi
+ decl %ecx
+ jnz 18b
+20: andl %edx,%edx
+ jz 23f
+ movl %edx,%ecx
+21: movb (%rsi),%al
+22: movb %al,(%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz 21b
+23: xorl %eax,%eax
+ ASM_CLAC
+ sfence
+ ret
+
+ .section .fixup,"ax"
+30: shll $6,%ecx
+ addl %ecx,%edx
+ jmp 60f
+40: lea (%rdx,%rcx,8),%rdx
+ jmp 60f
+50: movl %ecx,%edx
+60: sfence
+ jmp copy_user_handle_tail
+ .previous
+
+ _ASM_EXTABLE(1b,30b)
+ _ASM_EXTABLE(2b,30b)
+ _ASM_EXTABLE(3b,30b)
+ _ASM_EXTABLE(4b,30b)
+ _ASM_EXTABLE(5b,30b)
+ _ASM_EXTABLE(6b,30b)
+ _ASM_EXTABLE(7b,30b)
+ _ASM_EXTABLE(8b,30b)
+ _ASM_EXTABLE(9b,30b)
+ _ASM_EXTABLE(10b,30b)
+ _ASM_EXTABLE(11b,30b)
+ _ASM_EXTABLE(12b,30b)
+ _ASM_EXTABLE(13b,30b)
+ _ASM_EXTABLE(14b,30b)
+ _ASM_EXTABLE(15b,30b)
+ _ASM_EXTABLE(16b,30b)
+ _ASM_EXTABLE(18b,40b)
+ _ASM_EXTABLE(19b,40b)
+ _ASM_EXTABLE(21b,50b)
+ _ASM_EXTABLE(22b,50b)
+ENDPROC(__copy_user_nocache)
+++ /dev/null
-/*
- * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
- * Copyright 2002 Andi Kleen, SuSE Labs.
- * Subject to the GNU Public License v2.
- *
- * Functions to copy from and to user space.
- */
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-
-#define FIX_ALIGNMENT 1
-
-#include <asm/current.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
- .macro ALIGN_DESTINATION
-#ifdef FIX_ALIGNMENT
- /* check for bad alignment of destination */
- movl %edi,%ecx
- andl $7,%ecx
- jz 102f /* already aligned */
- subl $8,%ecx
- negl %ecx
- subl %ecx,%edx
-100: movb (%rsi),%al
-101: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 100b
-102:
- .section .fixup,"ax"
-103: addl %ecx,%edx /* ecx is zerorest also */
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
-#endif
- .endm
-
-/*
- * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
- */
-ENTRY(__copy_user_nocache)
- CFI_STARTPROC
- ASM_STAC
- cmpl $8,%edx
- jb 20f /* less then 8 bytes, go to byte copy loop */
- ALIGN_DESTINATION
- movl %edx,%ecx
- andl $63,%edx
- shrl $6,%ecx
- jz 17f
-1: movq (%rsi),%r8
-2: movq 1*8(%rsi),%r9
-3: movq 2*8(%rsi),%r10
-4: movq 3*8(%rsi),%r11
-5: movnti %r8,(%rdi)
-6: movnti %r9,1*8(%rdi)
-7: movnti %r10,2*8(%rdi)
-8: movnti %r11,3*8(%rdi)
-9: movq 4*8(%rsi),%r8
-10: movq 5*8(%rsi),%r9
-11: movq 6*8(%rsi),%r10
-12: movq 7*8(%rsi),%r11
-13: movnti %r8,4*8(%rdi)
-14: movnti %r9,5*8(%rdi)
-15: movnti %r10,6*8(%rdi)
-16: movnti %r11,7*8(%rdi)
- leaq 64(%rsi),%rsi
- leaq 64(%rdi),%rdi
- decl %ecx
- jnz 1b
-17: movl %edx,%ecx
- andl $7,%edx
- shrl $3,%ecx
- jz 20f
-18: movq (%rsi),%r8
-19: movnti %r8,(%rdi)
- leaq 8(%rsi),%rsi
- leaq 8(%rdi),%rdi
- decl %ecx
- jnz 18b
-20: andl %edx,%edx
- jz 23f
- movl %edx,%ecx
-21: movb (%rsi),%al
-22: movb %al,(%rdi)
- incq %rsi
- incq %rdi
- decl %ecx
- jnz 21b
-23: xorl %eax,%eax
- ASM_CLAC
- sfence
- ret
-
- .section .fixup,"ax"
-30: shll $6,%ecx
- addl %ecx,%edx
- jmp 60f
-40: lea (%rdx,%rcx,8),%rdx
- jmp 60f
-50: movl %ecx,%edx
-60: sfence
- jmp copy_user_handle_tail
- .previous
-
- _ASM_EXTABLE(1b,30b)
- _ASM_EXTABLE(2b,30b)
- _ASM_EXTABLE(3b,30b)
- _ASM_EXTABLE(4b,30b)
- _ASM_EXTABLE(5b,30b)
- _ASM_EXTABLE(6b,30b)
- _ASM_EXTABLE(7b,30b)
- _ASM_EXTABLE(8b,30b)
- _ASM_EXTABLE(9b,30b)
- _ASM_EXTABLE(10b,30b)
- _ASM_EXTABLE(11b,30b)
- _ASM_EXTABLE(12b,30b)
- _ASM_EXTABLE(13b,30b)
- _ASM_EXTABLE(14b,30b)
- _ASM_EXTABLE(15b,30b)
- _ASM_EXTABLE(16b,30b)
- _ASM_EXTABLE(18b,40b)
- _ASM_EXTABLE(19b,40b)
- _ASM_EXTABLE(21b,50b)
- _ASM_EXTABLE(22b,50b)
- CFI_ENDPROC
-ENDPROC(__copy_user_nocache)
* for more details. No warranty for anything given at all.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/errno.h>
#include <asm/asm.h>
ENTRY(csum_partial_copy_generic)
- CFI_STARTPROC
cmpl $3*64, %edx
jle .Lignore
.Lignore:
subq $7*8, %rsp
- CFI_ADJUST_CFA_OFFSET 7*8
movq %rbx, 2*8(%rsp)
- CFI_REL_OFFSET rbx, 2*8
movq %r12, 3*8(%rsp)
- CFI_REL_OFFSET r12, 3*8
movq %r14, 4*8(%rsp)
- CFI_REL_OFFSET r14, 4*8
movq %r13, 5*8(%rsp)
- CFI_REL_OFFSET r13, 5*8
movq %rbp, 6*8(%rsp)
- CFI_REL_OFFSET rbp, 6*8
movq %r8, (%rsp)
movq %r9, 1*8(%rsp)
addl %ebx, %eax
adcl %r9d, %eax /* carry */
- CFI_REMEMBER_STATE
.Lende:
movq 2*8(%rsp), %rbx
- CFI_RESTORE rbx
movq 3*8(%rsp), %r12
- CFI_RESTORE r12
movq 4*8(%rsp), %r14
- CFI_RESTORE r14
movq 5*8(%rsp), %r13
- CFI_RESTORE r13
movq 6*8(%rsp), %rbp
- CFI_RESTORE rbp
addq $7*8, %rsp
- CFI_ADJUST_CFA_OFFSET -7*8
ret
- CFI_RESTORE_STATE
/* Exception handlers. Very simple, zeroing is done in the wrappers */
.Lbad_source:
jz .Lende
movl $-EFAULT, (%rax)
jmp .Lende
- CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/page_types.h>
#include <asm/errno.h>
#include <asm/asm-offsets.h>
.text
ENTRY(__get_user_1)
- CFI_STARTPROC
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_1)
ENTRY(__get_user_2)
- CFI_STARTPROC
add $1,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_2)
ENTRY(__get_user_4)
- CFI_STARTPROC
add $3,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
xor %eax,%eax
ASM_CLAC
ret
- CFI_ENDPROC
ENDPROC(__get_user_4)
ENTRY(__get_user_8)
- CFI_STARTPROC
#ifdef CONFIG_X86_64
add $7,%_ASM_AX
jc bad_get_user
ASM_CLAC
ret
#endif
- CFI_ENDPROC
ENDPROC(__get_user_8)
bad_get_user:
- CFI_STARTPROC
xor %edx,%edx
mov $(-EFAULT),%_ASM_AX
ASM_CLAC
ret
- CFI_ENDPROC
END(bad_get_user)
#ifdef CONFIG_X86_32
bad_get_user_8:
- CFI_STARTPROC
xor %edx,%edx
xor %ecx,%ecx
mov $(-EFAULT),%_ASM_AX
ASM_CLAC
ret
- CFI_ENDPROC
END(bad_get_user_8)
#endif
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
/*
* override generic version in lib/iomap_copy.c
*/
ENTRY(__iowrite32_copy)
- CFI_STARTPROC
movl %edx,%ecx
rep movsd
ret
- CFI_ENDPROC
ENDPROC(__iowrite32_copy)
#include <linux/linkage.h>
#include <asm/cpufeature.h>
-#include <asm/dwarf2.h>
#include <asm/alternative-asm.h>
/*
ENDPROC(memcpy_erms)
ENTRY(memcpy_orig)
- CFI_STARTPROC
movq %rdi, %rax
cmpq $0x20, %rdx
.Lend:
retq
- CFI_ENDPROC
ENDPROC(memcpy_orig)
* - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
ENTRY(memmove)
ENTRY(__memmove)
- CFI_STARTPROC
/* Handle more 32 bytes in loop */
mov %rdi, %rax
movb %r11b, (%rdi)
13:
retq
- CFI_ENDPROC
ENDPROC(__memmove)
ENDPROC(memmove)
/* Copyright 2002 Andi Kleen, SuSE Labs */
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
ENDPROC(memset_erms)
ENTRY(memset_orig)
- CFI_STARTPROC
movq %rdi,%r10
/* expand byte value */
movl %edi,%r9d
andl $7,%r9d
jnz .Lbad_alignment
- CFI_REMEMBER_STATE
.Lafter_bad_alignment:
movq %rdx,%rcx
movq %r10,%rax
ret
- CFI_RESTORE_STATE
.Lbad_alignment:
cmpq $7,%rdx
jbe .Lhandle_7
subq %r8,%rdx
jmp .Lafter_bad_alignment
.Lfinal:
- CFI_ENDPROC
ENDPROC(memset_orig)
#include <linux/sched.h>
#include <linux/types.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#include <asm/asm.h>
void *_mmx_memcpy(void *to, const void *from, size_t len)
#include <linux/linkage.h>
#include <linux/errno.h>
-#include <asm/dwarf2.h>
#include <asm/asm.h>
#include <asm/msr.h>
*/
.macro op_safe_regs op
ENTRY(\op\()_safe_regs)
- CFI_STARTPROC
- pushq_cfi_reg rbx
- pushq_cfi_reg rbp
+ pushq %rbx
+ pushq %rbp
movq %rdi, %r10 /* Save pointer */
xorl %r11d, %r11d /* Return value */
movl (%rdi), %eax
movl 20(%rdi), %ebp
movl 24(%rdi), %esi
movl 28(%rdi), %edi
- CFI_REMEMBER_STATE
1: \op
2: movl %eax, (%r10)
movl %r11d, %eax /* Return value */
movl %ebp, 20(%r10)
movl %esi, 24(%r10)
movl %edi, 28(%r10)
- popq_cfi_reg rbp
- popq_cfi_reg rbx
+ popq %rbp
+ popq %rbx
ret
3:
- CFI_RESTORE_STATE
movl $-EIO, %r11d
jmp 2b
_ASM_EXTABLE(1b, 3b)
- CFI_ENDPROC
ENDPROC(\op\()_safe_regs)
.endm
.macro op_safe_regs op
ENTRY(\op\()_safe_regs)
- CFI_STARTPROC
- pushl_cfi_reg ebx
- pushl_cfi_reg ebp
- pushl_cfi_reg esi
- pushl_cfi_reg edi
- pushl_cfi $0 /* Return value */
- pushl_cfi %eax
+ pushl %ebx
+ pushl %ebp
+ pushl %esi
+ pushl %edi
+ pushl $0 /* Return value */
+ pushl %eax
movl 4(%eax), %ecx
movl 8(%eax), %edx
movl 12(%eax), %ebx
movl 24(%eax), %esi
movl 28(%eax), %edi
movl (%eax), %eax
- CFI_REMEMBER_STATE
1: \op
-2: pushl_cfi %eax
+2: pushl %eax
movl 4(%esp), %eax
- popl_cfi (%eax)
+ popl (%eax)
addl $4, %esp
- CFI_ADJUST_CFA_OFFSET -4
movl %ecx, 4(%eax)
movl %edx, 8(%eax)
movl %ebx, 12(%eax)
movl %ebp, 20(%eax)
movl %esi, 24(%eax)
movl %edi, 28(%eax)
- popl_cfi %eax
- popl_cfi_reg edi
- popl_cfi_reg esi
- popl_cfi_reg ebp
- popl_cfi_reg ebx
+ popl %eax
+ popl %edi
+ popl %esi
+ popl %ebp
+ popl %ebx
ret
3:
- CFI_RESTORE_STATE
movl $-EIO, 4(%esp)
jmp 2b
_ASM_EXTABLE(1b, 3b)
- CFI_ENDPROC
ENDPROC(\op\()_safe_regs)
.endm
* return value.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
#include <asm/thread_info.h>
#include <asm/errno.h>
#include <asm/asm.h>
* as they get called from within inline assembly.
*/
-#define ENTER CFI_STARTPROC ; \
- GET_THREAD_INFO(%_ASM_BX)
+#define ENTER GET_THREAD_INFO(%_ASM_BX)
#define EXIT ASM_CLAC ; \
- ret ; \
- CFI_ENDPROC
+ ret
.text
ENTRY(__put_user_1)
ENDPROC(__put_user_8)
bad_put_user:
- CFI_STARTPROC
movl $-EFAULT,%eax
EXIT
END(bad_put_user)
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
#define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg)
#define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l)
*/
#define save_common_regs \
- pushl_cfi_reg ecx
+ pushl %ecx
#define restore_common_regs \
- popl_cfi_reg ecx
+ popl %ecx
/* Avoid uglifying the argument copying x86-64 needs to do. */
.macro movq src, dst
*/
#define save_common_regs \
- pushq_cfi_reg rdi; \
- pushq_cfi_reg rsi; \
- pushq_cfi_reg rcx; \
- pushq_cfi_reg r8; \
- pushq_cfi_reg r9; \
- pushq_cfi_reg r10; \
- pushq_cfi_reg r11
+ pushq %rdi; \
+ pushq %rsi; \
+ pushq %rcx; \
+ pushq %r8; \
+ pushq %r9; \
+ pushq %r10; \
+ pushq %r11
#define restore_common_regs \
- popq_cfi_reg r11; \
- popq_cfi_reg r10; \
- popq_cfi_reg r9; \
- popq_cfi_reg r8; \
- popq_cfi_reg rcx; \
- popq_cfi_reg rsi; \
- popq_cfi_reg rdi
+ popq %r11; \
+ popq %r10; \
+ popq %r9; \
+ popq %r8; \
+ popq %rcx; \
+ popq %rsi; \
+ popq %rdi
#endif
/* Fix up special calling conventions */
ENTRY(call_rwsem_down_read_failed)
- CFI_STARTPROC
save_common_regs
- __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(push,) %__ASM_REG(dx)
movq %rax,%rdi
call rwsem_down_read_failed
- __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(pop,) %__ASM_REG(dx)
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_down_read_failed)
ENTRY(call_rwsem_down_write_failed)
- CFI_STARTPROC
save_common_regs
movq %rax,%rdi
call rwsem_down_write_failed
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_down_write_failed)
ENTRY(call_rwsem_wake)
- CFI_STARTPROC
/* do nothing if still outstanding active readers */
__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
jnz 1f
call rwsem_wake
restore_common_regs
1: ret
- CFI_ENDPROC
ENDPROC(call_rwsem_wake)
ENTRY(call_rwsem_downgrade_wake)
- CFI_STARTPROC
save_common_regs
- __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(push,) %__ASM_REG(dx)
movq %rax,%rdi
call rwsem_downgrade_wake
- __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+ __ASM_SIZE(pop,) %__ASM_REG(dx)
restore_common_regs
ret
- CFI_ENDPROC
ENDPROC(call_rwsem_downgrade_wake)
+++ /dev/null
-/*
- * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash)
- * Copyright 2008 by Steven Rostedt, Red Hat, Inc
- * (inspired by Andi Kleen's thunk_64.S)
- * Subject to the GNU public license, v.2. No warranty of any kind.
- */
- #include <linux/linkage.h>
- #include <asm/asm.h>
- #include <asm/dwarf2.h>
-
- /* put return address in eax (arg1) */
- .macro THUNK name, func, put_ret_addr_in_eax=0
- .globl \name
-\name:
- CFI_STARTPROC
- pushl_cfi_reg eax
- pushl_cfi_reg ecx
- pushl_cfi_reg edx
-
- .if \put_ret_addr_in_eax
- /* Place EIP in the arg1 */
- movl 3*4(%esp), %eax
- .endif
-
- call \func
- popl_cfi_reg edx
- popl_cfi_reg ecx
- popl_cfi_reg eax
- ret
- CFI_ENDPROC
- _ASM_NOKPROBE(\name)
- .endm
-
-#ifdef CONFIG_TRACE_IRQFLAGS
- THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
- THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
-#endif
-
-#ifdef CONFIG_PREEMPT
- THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
- THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
-#endif
-
+++ /dev/null
-/*
- * Save registers before calling assembly functions. This avoids
- * disturbance of register allocation in some inline assembly constructs.
- * Copyright 2001,2002 by Andi Kleen, SuSE Labs.
- * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc.
- * Subject to the GNU public license, v.2. No warranty of any kind.
- */
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm.h>
-
- /* rdi: arg1 ... normal C conventions. rax is saved/restored. */
- .macro THUNK name, func, put_ret_addr_in_rdi=0
- .globl \name
-\name:
- CFI_STARTPROC
-
- /* this one pushes 9 elems, the next one would be %rIP */
- pushq_cfi_reg rdi
- pushq_cfi_reg rsi
- pushq_cfi_reg rdx
- pushq_cfi_reg rcx
- pushq_cfi_reg rax
- pushq_cfi_reg r8
- pushq_cfi_reg r9
- pushq_cfi_reg r10
- pushq_cfi_reg r11
-
- .if \put_ret_addr_in_rdi
- /* 9*8(%rsp) is return addr on stack */
- movq_cfi_restore 9*8, rdi
- .endif
-
- call \func
- jmp restore
- CFI_ENDPROC
- _ASM_NOKPROBE(\name)
- .endm
-
-#ifdef CONFIG_TRACE_IRQFLAGS
- THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
- THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
-#endif
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
-#endif
-
-#ifdef CONFIG_PREEMPT
- THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
- THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
-#endif
-
-#if defined(CONFIG_TRACE_IRQFLAGS) \
- || defined(CONFIG_DEBUG_LOCK_ALLOC) \
- || defined(CONFIG_PREEMPT)
- CFI_STARTPROC
- CFI_ADJUST_CFA_OFFSET 9*8
-restore:
- popq_cfi_reg r11
- popq_cfi_reg r10
- popq_cfi_reg r9
- popq_cfi_reg r8
- popq_cfi_reg rax
- popq_cfi_reg rcx
- popq_cfi_reg rdx
- popq_cfi_reg rsi
- popq_cfi_reg rdi
- ret
- CFI_ENDPROC
- _ASM_NOKPROBE(restore)
-#endif
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from kernel space to user space.
*
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Copy data from user space to kernel space.
*
}
/* Needs to be externally visible */
-void finit_soft_fpu(struct i387_soft_struct *soft)
+void fpstate_init_soft(struct swregs_state *soft)
{
struct address *oaddr, *iaddr;
memset(soft, 0, sizeof(*soft));
void finit(void)
{
- finit_soft_fpu(¤t->thread.fpu.state->soft);
+ fpstate_init_soft(¤t->thread.fpu.state.soft);
}
/*
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/user.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
#include "fpu_system.h"
#include "fpu_emu.h"
unsigned long code_base = 0;
unsigned long code_limit = 0; /* Initialized to stop compiler warnings */
struct desc_struct code_descriptor;
+ struct fpu *fpu = ¤t->thread.fpu;
- if (!used_math()) {
- if (init_fpu(current)) {
- do_group_exit(SIGKILL);
- return;
- }
- }
+ fpu__activate_curr(fpu);
#ifdef RE_ENTRANT_CHECKING
if (emulating) {
#endif /* PARANOID */
}
-#define S387 ((struct i387_soft_struct *)s387)
+#define S387 ((struct swregs_state *)s387)
#define sstatus_word() \
((S387->swd & ~SW_Top & 0xffff) | ((S387->ftop << SW_Top_Shift) & SW_Top))
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+ struct swregs_state *s387 = &target->thread.fpu.state.soft;
void *space = s387->st_space;
int ret;
int offset, other, i, tags, regnr, tag, newtop;
RE_ENTRANT_CHECK_OFF;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, s387, 0,
- offsetof(struct i387_soft_struct, st_space));
+ offsetof(struct swregs_state, st_space));
RE_ENTRANT_CHECK_ON;
if (ret)
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
- struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+ struct swregs_state *s387 = &target->thread.fpu.state.soft;
const void *space = s387->st_space;
int ret;
int offset = (S387->ftop & 7) * 10, other = 80 - offset;
#endif /* PECULIAR_486 */
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, s387, 0,
- offsetof(struct i387_soft_struct, st_space));
+ offsetof(struct swregs_state, st_space));
/* Copy all registers in stack order. */
if (!ret)
#define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \
== (1 << 10))
-#define I387 (current->thread.fpu.state)
+#define I387 (¤t->thread.fpu.state)
#define FPU_info (I387->soft.info)
#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs))
#include <linux/hugetlb.h> /* hstate_index_to_shift */
#include <linux/prefetch.h> /* prefetchw */
#include <linux/context_tracking.h> /* exception_enter(), ... */
+#include <linux/uaccess.h> /* faulthandler_disabled() */
#include <asm/traps.h> /* dotraplinkage, ... */
#include <asm/pgalloc.h> /* pgd_*(), ... */
/*
* If we're in an interrupt, have no user context or are running
- * in an atomic region then we must not take the fault:
+ * in a region with pagefaults disabled then we must not take the fault
*/
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(faulthandler_disabled() || !mm)) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
unsigned long vaddr;
int idx, type;
- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
#endif
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
*/
uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
[_PAGE_CACHE_MODE_WB ] = 0 | 0 ,
- [_PAGE_CACHE_MODE_WC ] = _PAGE_PWT | 0 ,
+ [_PAGE_CACHE_MODE_WC ] = 0 | _PAGE_PCD,
[_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD,
[_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD,
[_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD,
uint8_t __pte2cachemode_tbl[8] = {
[__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB,
- [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_WC,
+ [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC,
[__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
- [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC,
+ [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
};
unsigned long vaddr;
int idx, type;
+ preempt_disable();
pagefault_disable();
type = kmap_atomic_idx_push();
iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
{
/*
- * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
- * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
- * MTRR is UC or WC. UC_MINUS gets the real intention, of the
- * user, which is "WC if the MTRR is WC, UC if you can't do that."
+ * For non-PAT systems, translate non-WB request to UC- just in
+ * case the caller set the PWT bit to prot directly without using
+ * pgprot_writecombine(). UC- translates to uncached if the MTRR
+ * is UC or WC. UC- gets the real intention, of the user, which is
+ * "WC if the MTRR is WC, UC if you can't do that."
*/
- if (!pat_enabled && pgprot_val(prot) ==
- (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC)))
+ if (!pat_enabled() && pgprot2cachemode(prot) != _PAGE_CACHE_MODE_WB)
prot = __pgprot(__PAGE_KERNEL |
cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL_GPL(iounmap_atomic);
case _PAGE_CACHE_MODE_WC:
err = _set_memory_wc(vaddr, nrpages);
break;
+ case _PAGE_CACHE_MODE_WT:
+ err = _set_memory_wt(vaddr, nrpages);
+ break;
case _PAGE_CACHE_MODE_WB:
err = _set_memory_wb(vaddr, nrpages);
break;
prot = __pgprot(pgprot_val(prot) |
cachemode2protval(_PAGE_CACHE_MODE_WC));
break;
+ case _PAGE_CACHE_MODE_WT:
+ prot = __pgprot(pgprot_val(prot) |
+ cachemode2protval(_PAGE_CACHE_MODE_WT));
+ break;
case _PAGE_CACHE_MODE_WB:
break;
}
{
/*
* Ideally, this should be:
- * pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
+ * pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
*
* Till we fix all X drivers to use ioremap_wc(), we will use
- * UC MINUS.
+ * UC MINUS. Drivers that are certain they need or can already
+ * be converted over to strong UC can use ioremap_uc().
*/
enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
}
EXPORT_SYMBOL(ioremap_nocache);
+/**
+ * ioremap_uc - map bus memory into CPU space as strongly uncachable
+ * @phys_addr: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * ioremap_uc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked with a strong
+ * preference as completely uncachable on the CPU when possible. For non-PAT
+ * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT
+ * systems this will set the PAT entry for the pages as strong UC. This call
+ * will honor existing caching rules from things like the PCI bus. Note that
+ * there are other caches and buffers on many busses. In particular driver
+ * authors should read up on PCI writes.
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size)
+{
+ enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC;
+
+ return __ioremap_caller(phys_addr, size, pcm,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL_GPL(ioremap_uc);
+
/**
* ioremap_wc - map memory into CPU space write combined
* @phys_addr: bus address of the memory
*/
void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
{
- if (pat_enabled)
- return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
__builtin_return_address(0));
- else
- return ioremap_nocache(phys_addr, size);
}
EXPORT_SYMBOL(ioremap_wc);
+/**
+ * ioremap_wt - map memory into CPU space write through
+ * @phys_addr: bus address of the memory
+ * @size: size of the resource to map
+ *
+ * This version of ioremap ensures that the memory is marked write through.
+ * Write through stores data into memory while keeping the cache up-to-date.
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size)
+{
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
{
return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
}
EXPORT_SYMBOL(iounmap);
-int arch_ioremap_pud_supported(void)
+int __init arch_ioremap_pud_supported(void)
{
#ifdef CONFIG_X86_64
return cpu_has_gbpages;
#endif
}
-int arch_ioremap_pmd_supported(void)
+int __init arch_ioremap_pmd_supported(void)
{
return cpu_has_pse;
}
{
unsigned long start = phys & PAGE_MASK;
unsigned long offset = phys & ~PAGE_MASK;
- unsigned long vaddr;
+ void *vaddr;
/* If page is RAM, we can use __va. Otherwise ioremap and unmap. */
if (page_is_ram(start >> PAGE_SHIFT))
return __va(phys);
- vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE);
+ vaddr = ioremap_cache(start, PAGE_SIZE);
/* Only add the offset on success and return NULL if the ioremap() failed: */
if (vaddr)
vaddr += offset;
- return (void *)vaddr;
+ return vaddr;
}
void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
return;
iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK));
- return;
}
static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;
#include <linux/syscalls.h>
#include <linux/sched/sysctl.h>
-#include <asm/i387.h>
#include <asm/insn.h>
#include <asm/mman.h>
#include <asm/mmu_context.h>
#include <asm/mpx.h>
#include <asm/processor.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace/mpx.h>
static const char *mpx_mapping_name(struct vm_area_struct *vma)
{
return (vma->vm_ops == &mpx_vma_ops);
}
+static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
+{
+ if (is_64bit_mm(mm))
+ return MPX_BD_SIZE_BYTES_64;
+ else
+ return MPX_BD_SIZE_BYTES_32;
+}
+
+static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
+{
+ if (is_64bit_mm(mm))
+ return MPX_BT_SIZE_BYTES_64;
+ else
+ return MPX_BT_SIZE_BYTES_32;
+}
+
/*
* This is really a simplified "vm_mmap". it only handles MPX
* bounds tables (the bounds directory is user-allocated).
vm_flags_t vm_flags;
struct vm_area_struct *vma;
- /* Only bounds table and bounds directory can be allocated here */
- if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES)
+ /* Only bounds table can be allocated here */
+ if (len != mpx_bt_size_bytes(mm))
return -EINVAL;
down_write(&mm->mmap_sem);
*
* The caller is expected to kfree() the returned siginfo_t.
*/
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf)
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
{
- struct bndreg *bndregs, *bndreg;
+ const struct bndreg *bndregs, *bndreg;
siginfo_t *info = NULL;
struct insn insn;
uint8_t bndregno;
err = -EINVAL;
goto err_out;
}
- /* get the bndregs _area_ of the xsave structure */
- bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+ /* get bndregs field from current task's xsave area */
+ bndregs = get_xsave_field_ptr(XSTATE_BNDREGS);
if (!bndregs) {
err = -EINVAL;
goto err_out;
err = -EINVAL;
goto err_out;
}
+ trace_mpx_bounds_register_exception(info->si_addr, bndreg);
return info;
err_out:
/* info might be NULL, but kfree() handles that */
return ERR_PTR(err);
}
-static __user void *task_get_bounds_dir(struct task_struct *tsk)
+static __user void *mpx_get_bounds_dir(void)
{
- struct bndcsr *bndcsr;
+ const struct bndcsr *bndcsr;
if (!cpu_feature_enabled(X86_FEATURE_MPX))
return MPX_INVALID_BOUNDS_DIR;
- /*
- * 32-bit binaries on 64-bit kernels are currently
- * unsupported.
- */
- if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
- return MPX_INVALID_BOUNDS_DIR;
/*
* The bounds directory pointer is stored in a register
* only accessible if we first do an xsave.
*/
- fpu_save_init(&tsk->thread.fpu);
- bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
if (!bndcsr)
return MPX_INVALID_BOUNDS_DIR;
(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
}
-int mpx_enable_management(struct task_struct *tsk)
+int mpx_enable_management(void)
{
void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
- struct mm_struct *mm = tsk->mm;
+ struct mm_struct *mm = current->mm;
int ret = 0;
/*
* directory into XSAVE/XRSTOR Save Area and enable MPX through
* XRSTOR instruction.
*
- * fpu_xsave() is expected to be very expensive. Storing the bounds
- * directory here means that we do not have to do xsave in the unmap
- * path; we can just use mm->bd_addr instead.
+ * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
+ * expected to be relatively expensive. Storing the bounds
+ * directory here means that we do not have to do xsave in the
+ * unmap path; we can just use mm->bd_addr instead.
*/
- bd_base = task_get_bounds_dir(tsk);
+ bd_base = mpx_get_bounds_dir();
down_write(&mm->mmap_sem);
mm->bd_addr = bd_base;
if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
return ret;
}
-int mpx_disable_management(struct task_struct *tsk)
+int mpx_disable_management(void)
{
struct mm_struct *mm = current->mm;
return 0;
}
+static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
+ unsigned long *curval,
+ unsigned long __user *addr,
+ unsigned long old_val, unsigned long new_val)
+{
+ int ret;
+ /*
+ * user_atomic_cmpxchg_inatomic() actually uses sizeof()
+ * the pointer that we pass to it to figure out how much
+ * data to cmpxchg. We have to be careful here not to
+ * pass a pointer to a 64-bit data type when we only want
+ * a 32-bit copy.
+ */
+ if (is_64bit_mm(mm)) {
+ ret = user_atomic_cmpxchg_inatomic(curval,
+ addr, old_val, new_val);
+ } else {
+ u32 uninitialized_var(curval_32);
+ u32 old_val_32 = old_val;
+ u32 new_val_32 = new_val;
+ u32 __user *addr_32 = (u32 __user *)addr;
+
+ ret = user_atomic_cmpxchg_inatomic(&curval_32,
+ addr_32, old_val_32, new_val_32);
+ *curval = curval_32;
+ }
+ return ret;
+}
+
/*
- * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
- * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * With 32-bit mode, a bounds directory is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
* and the size of each bounds table is 4MB.
*/
-static int allocate_bt(long __user *bd_entry)
+static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
{
unsigned long expected_old_val = 0;
unsigned long actual_old_val = 0;
unsigned long bt_addr;
+ unsigned long bd_new_entry;
int ret = 0;
/*
* Carve the virtual space out of userspace for the new
* bounds table:
*/
- bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+ bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
if (IS_ERR((void *)bt_addr))
return PTR_ERR((void *)bt_addr);
/*
* Set the valid flag (kinda like _PAGE_PRESENT in a pte)
*/
- bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+ bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
/*
* Go poke the address of the new bounds table in to the
* mmap_sem at this point, unlike some of the other part
* of the MPX code that have to pagefault_disable().
*/
- ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
- expected_old_val, bt_addr);
+ ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, bd_entry,
+ expected_old_val, bd_new_entry);
if (ret)
goto out_unmap;
ret = -EINVAL;
goto out_unmap;
}
+ trace_mpx_new_bounds_table(bt_addr);
return 0;
out_unmap:
- vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+ vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
return ret;
}
* bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
* and the size of each bound table is 4MB.
*/
-static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+static int do_mpx_bt_fault(void)
{
unsigned long bd_entry, bd_base;
- struct bndcsr *bndcsr;
+ const struct bndcsr *bndcsr;
+ struct mm_struct *mm = current->mm;
- bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
if (!bndcsr)
return -EINVAL;
/*
* the directory is.
*/
if ((bd_entry < bd_base) ||
- (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+ (bd_entry >= bd_base + mpx_bd_size_bytes(mm)))
return -EINVAL;
- return allocate_bt((long __user *)bd_entry);
+ return allocate_bt(mm, (long __user *)bd_entry);
}
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+int mpx_handle_bd_fault(void)
{
/*
* Userspace never asked us to manage the bounds tables,
if (!kernel_managing_mpx_tables(current->mm))
return -EINVAL;
- if (do_mpx_bt_fault(xsave_buf)) {
+ if (do_mpx_bt_fault()) {
force_sig(SIGSEGV, current);
/*
* The force_sig() is essentially "handling" this
return 0;
}
+static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
+ unsigned long bd_entry)
+{
+ unsigned long bt_addr = bd_entry;
+ int align_to_bytes;
+ /*
+ * Bit 0 in a bt_entry is always the valid bit.
+ */
+ bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
+ /*
+ * Tables are naturally aligned at 8-byte boundaries
+ * on 64-bit and 4-byte boundaries on 32-bit. The
+ * documentation makes it appear that the low bits
+ * are ignored by the hardware, so we do the same.
+ */
+ if (is_64bit_mm(mm))
+ align_to_bytes = 8;
+ else
+ align_to_bytes = 4;
+ bt_addr &= ~(align_to_bytes-1);
+ return bt_addr;
+}
+
/*
* Get the base of bounds tables pointed by specific bounds
* directory entry.
*/
static int get_bt_addr(struct mm_struct *mm,
- long __user *bd_entry, unsigned long *bt_addr)
+ long __user *bd_entry_ptr,
+ unsigned long *bt_addr_result)
{
int ret;
int valid_bit;
+ unsigned long bd_entry;
+ unsigned long bt_addr;
- if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+ if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr)))
return -EFAULT;
while (1) {
int need_write = 0;
pagefault_disable();
- ret = get_user(*bt_addr, bd_entry);
+ ret = get_user(bd_entry, bd_entry_ptr);
pagefault_enable();
if (!ret)
break;
if (ret == -EFAULT)
- ret = mpx_resolve_fault(bd_entry, need_write);
+ ret = mpx_resolve_fault(bd_entry_ptr, need_write);
/*
* If we could not resolve the fault, consider it
* userspace's fault and error out.
return ret;
}
- valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
- *bt_addr &= MPX_BT_ADDR_MASK;
+ valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
+ bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);
/*
* When the kernel is managing bounds tables, a bounds directory
* data in the address field, we know something is wrong. This
* -EINVAL return will cause a SIGSEGV.
*/
- if (!valid_bit && *bt_addr)
+ if (!valid_bit && bt_addr)
return -EINVAL;
/*
* Do we have an completely zeroed bt entry? That is OK. It
if (!valid_bit)
return -ENOENT;
+ *bt_addr_result = bt_addr;
return 0;
}
+static inline int bt_entry_size_bytes(struct mm_struct *mm)
+{
+ if (is_64bit_mm(mm))
+ return MPX_BT_ENTRY_BYTES_64;
+ else
+ return MPX_BT_ENTRY_BYTES_32;
+}
+
+/*
+ * Take a virtual address and turns it in to the offset in bytes
+ * inside of the bounds table where the bounds table entry
+ * controlling 'addr' can be found.
+ */
+static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
+ unsigned long addr)
+{
+ unsigned long bt_table_nr_entries;
+ unsigned long offset = addr;
+
+ if (is_64bit_mm(mm)) {
+ /* Bottom 3 bits are ignored on 64-bit */
+ offset >>= 3;
+ bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
+ } else {
+ /* Bottom 2 bits are ignored on 32-bit */
+ offset >>= 2;
+ bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
+ }
+ /*
+ * We know the size of the table in to which we are
+ * indexing, and we have eliminated all the low bits
+ * which are ignored for indexing.
+ *
+ * Mask out all the high bits which we do not need
+ * to index in to the table. Note that the tables
+ * are always powers of two so this gives us a proper
+ * mask.
+ */
+ offset &= (bt_table_nr_entries-1);
+ /*
+ * We now have an entry offset in terms of *entries* in
+ * the table. We need to scale it back up to bytes.
+ */
+ offset *= bt_entry_size_bytes(mm);
+ return offset;
+}
+
+/*
+ * How much virtual address space does a single bounds
+ * directory entry cover?
+ *
+ * Note, we need a long long because 4GB doesn't fit in
+ * to a long on 32-bit.
+ */
+static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
+{
+ unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+ if (is_64bit_mm(mm))
+ return virt_space / MPX_BD_NR_ENTRIES_64;
+ else
+ return virt_space / MPX_BD_NR_ENTRIES_32;
+}
+
/*
* Free the backing physical pages of bounds table 'bt_addr'.
* Assume start...end is within that bounds table.
*/
-static int zap_bt_entries(struct mm_struct *mm,
+static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
unsigned long bt_addr,
- unsigned long start, unsigned long end)
+ unsigned long start_mapping, unsigned long end_mapping)
{
struct vm_area_struct *vma;
unsigned long addr, len;
+ unsigned long start;
+ unsigned long end;
+
+ /*
+ * if we 'end' on a boundary, the offset will be 0 which
+ * is not what we want. Back it up a byte to get the
+ * last bt entry. Then once we have the entry itself,
+ * move 'end' back up by the table entry size.
+ */
+ start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping);
+ end = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1);
+ /*
+ * Move end back up by one entry. Among other things
+ * this ensures that it remains page-aligned and does
+ * not screw up zap_page_range()
+ */
+ end += bt_entry_size_bytes(mm);
/*
* Find the first overlapping vma. If vma->vm_start > start, there
return -EINVAL;
/*
- * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+ * A NUMA policy on a VM_MPX VMA could cause this bounds table to
* be split. So we need to look across the entire 'start -> end'
* range of this bounds table, find all of the VM_MPX VMAs, and
* zap only those.
len = min(vma->vm_end, end) - addr;
zap_page_range(vma, addr, len, NULL);
+ trace_mpx_unmap_zap(addr, addr+len);
vma = vma->vm_next;
addr = vma->vm_start;
}
-
return 0;
}
-static int unmap_single_bt(struct mm_struct *mm,
+static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
+ unsigned long addr)
+{
+ /*
+ * There are several ways to derive the bd offsets. We
+ * use the following approach here:
+ * 1. We know the size of the virtual address space
+ * 2. We know the number of entries in a bounds table
+ * 3. We know that each entry covers a fixed amount of
+ * virtual address space.
+ * So, we can just divide the virtual address by the
+ * virtual space used by one entry to determine which
+ * entry "controls" the given virtual address.
+ */
+ if (is_64bit_mm(mm)) {
+ int bd_entry_size = 8; /* 64-bit pointer */
+ /*
+ * Take the 64-bit addressing hole in to account.
+ */
+ addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
+ return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+ } else {
+ int bd_entry_size = 4; /* 32-bit pointer */
+ /*
+ * 32-bit has no hole so this case needs no mask
+ */
+ return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+ }
+ /*
+ * The two return calls above are exact copies. If we
+ * pull out a single copy and put it in here, gcc won't
+ * realize that we're doing a power-of-2 divide and use
+ * shifts. It uses a real divide. If we put them up
+ * there, it manages to figure it out (gcc 4.8.3).
+ */
+}
+
+static int unmap_entire_bt(struct mm_struct *mm,
long __user *bd_entry, unsigned long bt_addr)
{
unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
- unsigned long actual_old_val = 0;
+ unsigned long uninitialized_var(actual_old_val);
int ret;
while (1) {
int need_write = 1;
+ unsigned long cleared_bd_entry = 0;
pagefault_disable();
- ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
- expected_old_val, 0);
+ ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
+ bd_entry, expected_old_val, cleared_bd_entry);
pagefault_enable();
if (!ret)
break;
if (actual_old_val != expected_old_val) {
/*
* Someone else raced with us to unmap the table.
- * There was no bounds table pointed to by the
- * directory, so declare success. Somebody freed
- * it.
+ * That is OK, since we were both trying to do
+ * the same thing. Declare success.
*/
if (!actual_old_val)
return 0;
*/
return -EINVAL;
}
-
/*
* Note, we are likely being called under do_munmap() already. To
* avoid recursion, do_munmap() will check whether it comes
* from one bounds table through VM_MPX flag.
*/
- return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES);
+ return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
}
-/*
- * If the bounds table pointed by bounds directory 'bd_entry' is
- * not shared, unmap this whole bounds table. Otherwise, only free
- * those backing physical pages of bounds table entries covered
- * in this virtual address region start...end.
- */
-static int unmap_shared_bt(struct mm_struct *mm,
- long __user *bd_entry, unsigned long start,
- unsigned long end, bool prev_shared, bool next_shared)
+static int try_unmap_single_bt(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
{
- unsigned long bt_addr;
- int ret;
-
- ret = get_bt_addr(mm, bd_entry, &bt_addr);
+ struct vm_area_struct *next;
+ struct vm_area_struct *prev;
/*
- * We could see an "error" ret for not-present bounds
- * tables (not really an error), or actual errors, but
- * stop unmapping either way.
+ * "bta" == Bounds Table Area: the area controlled by the
+ * bounds table that we are unmapping.
*/
- if (ret)
- return ret;
-
- if (prev_shared && next_shared)
- ret = zap_bt_entries(mm, bt_addr,
- bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
- bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
- else if (prev_shared)
- ret = zap_bt_entries(mm, bt_addr,
- bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
- bt_addr+MPX_BT_SIZE_BYTES);
- else if (next_shared)
- ret = zap_bt_entries(mm, bt_addr, bt_addr,
- bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
- else
- ret = unmap_single_bt(mm, bd_entry, bt_addr);
-
- return ret;
-}
-
-/*
- * A virtual address region being munmap()ed might share bounds table
- * with adjacent VMAs. We only need to free the backing physical
- * memory of these shared bounds tables entries covered in this virtual
- * address region.
- */
-static int unmap_edge_bts(struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
+ unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1);
+ unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm);
+ unsigned long uninitialized_var(bt_addr);
+ void __user *bde_vaddr;
int ret;
- long __user *bde_start, *bde_end;
- struct vm_area_struct *prev, *next;
- bool prev_shared = false, next_shared = false;
-
- bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
- bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-
/*
- * Check whether bde_start and bde_end are shared with adjacent
- * VMAs.
- *
- * We already unliked the VMAs from the mm's rbtree so 'start'
+ * We already unlinked the VMAs from the mm's rbtree so 'start'
* is guaranteed to be in a hole. This gets us the first VMA
* before the hole in to 'prev' and the next VMA after the hole
* in to 'next'.
*/
next = find_vma_prev(mm, start, &prev);
- if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
- == bde_start)
- prev_shared = true;
- if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
- == bde_end)
- next_shared = true;
-
/*
- * This virtual address region being munmap()ed is only
- * covered by one bounds table.
- *
- * In this case, if this table is also shared with adjacent
- * VMAs, only part of the backing physical memory of the bounds
- * table need be freeed. Otherwise the whole bounds table need
- * be unmapped.
- */
- if (bde_start == bde_end) {
- return unmap_shared_bt(mm, bde_start, start, end,
- prev_shared, next_shared);
+ * Do not count other MPX bounds table VMAs as neighbors.
+ * Although theoretically possible, we do not allow bounds
+ * tables for bounds tables so our heads do not explode.
+ * If we count them as neighbors here, we may end up with
+ * lots of tables even though we have no actual table
+ * entries in use.
+ */
+ while (next && is_mpx_vma(next))
+ next = next->vm_next;
+ while (prev && is_mpx_vma(prev))
+ prev = prev->vm_prev;
+ /*
+ * We know 'start' and 'end' lie within an area controlled
+ * by a single bounds table. See if there are any other
+ * VMAs controlled by that bounds table. If there are not
+ * then we can "expand" the are we are unmapping to possibly
+ * cover the entire table.
+ */
+ next = find_vma_prev(mm, start, &prev);
+ if ((!prev || prev->vm_end <= bta_start_vaddr) &&
+ (!next || next->vm_start >= bta_end_vaddr)) {
+ /*
+ * No neighbor VMAs controlled by same bounds
+ * table. Try to unmap the whole thing
+ */
+ start = bta_start_vaddr;
+ end = bta_end_vaddr;
}
+ bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
+ ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
/*
- * If more than one bounds tables are covered in this virtual
- * address region being munmap()ed, we need to separately check
- * whether bde_start and bde_end are shared with adjacent VMAs.
+ * No bounds table there, so nothing to unmap.
*/
- ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
- if (ret)
- return ret;
- ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+ if (ret == -ENOENT) {
+ ret = 0;
+ return 0;
+ }
if (ret)
return ret;
-
- return 0;
+ /*
+ * We are unmapping an entire table. Either because the
+ * unmap that started this whole process was large enough
+ * to cover an entire table, or that the unmap was small
+ * but was the area covered by a bounds table.
+ */
+ if ((start == bta_start_vaddr) &&
+ (end == bta_end_vaddr))
+ return unmap_entire_bt(mm, bde_vaddr, bt_addr);
+ return zap_bt_entries_mapping(mm, bt_addr, start, end);
}
static int mpx_unmap_tables(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
- int ret;
- long __user *bd_entry, *bde_start, *bde_end;
- unsigned long bt_addr;
-
- /*
- * "Edge" bounds tables are those which are being used by the region
- * (start -> end), but that may be shared with adjacent areas. If they
- * turn out to be completely unshared, they will be freed. If they are
- * shared, we will free the backing store (like an MADV_DONTNEED) for
- * areas used by this region.
- */
- ret = unmap_edge_bts(mm, start, end);
- switch (ret) {
- /* non-present tables are OK */
- case 0:
- case -ENOENT:
- /* Success, or no tables to unmap */
- break;
- case -EINVAL:
- case -EFAULT:
- default:
- return ret;
- }
-
- /*
- * Only unmap the bounds table that are
- * 1. fully covered
- * 2. not at the edges of the mapping, even if full aligned
- */
- bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
- bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
- for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
- ret = get_bt_addr(mm, bd_entry, &bt_addr);
- switch (ret) {
- case 0:
- break;
- case -ENOENT:
- /* No table here, try the next one */
- continue;
- case -EINVAL:
- case -EFAULT:
- default:
- /*
- * Note: we are being strict here.
- * Any time we run in to an issue
- * unmapping tables, we stop and
- * SIGSEGV.
- */
- return ret;
- }
-
- ret = unmap_single_bt(mm, bd_entry, bt_addr);
+ unsigned long one_unmap_start;
+ trace_mpx_unmap_search(start, end);
+
+ one_unmap_start = start;
+ while (one_unmap_start < end) {
+ int ret;
+ unsigned long next_unmap_start = ALIGN(one_unmap_start+1,
+ bd_entry_virt_space(mm));
+ unsigned long one_unmap_end = end;
+ /*
+ * if the end is beyond the current bounds table,
+ * move it back so we only deal with a single one
+ * at a time
+ */
+ if (one_unmap_end > next_unmap_start)
+ one_unmap_end = next_unmap_start;
+ ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end);
if (ret)
return ret;
- }
+ one_unmap_start = next_unmap_start;
+ }
return 0;
}
#include <linux/random.h>
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/vmalloc.h>
#include <asm/cacheflush.h>
#include <asm/pgtable.h>
#include <linux/percpu.h>
#include <linux/gfp.h>
#include <linux/pci.h>
+#include <linux/vmalloc.h>
#include <asm/e820.h>
#include <asm/processor.h>
*/
void clflush_cache_range(void *vaddr, unsigned int size)
{
- void *vend = vaddr + size - 1;
+ unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+ void *vend = vaddr + size;
+ void *p;
mb();
- for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
- clflushopt(vaddr);
- /*
- * Flush any possible final partial cacheline:
- */
- clflushopt(vend);
+ for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+ p < vend; p += boot_cpu_data.x86_clflush_size)
+ clflushopt(p);
mb();
}
phys_addr_t phys_addr;
unsigned long offset;
enum pg_level level;
- unsigned long psize;
unsigned long pmask;
pte_t *pte;
pte = lookup_address(virt_addr, &level);
BUG_ON(!pte);
- psize = page_level_size(level);
pmask = page_level_mask(level);
offset = virt_addr & ~pmask;
phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
{
/*
* for now UC MINUS. see comments in ioremap_nocache()
+ * If you really need strong UC use ioremap_uc(), but note
+ * that you cannot override IO areas with set_memory_*() as
+ * these helpers cannot work with IO memory.
*/
return change_page_attr_set(&addr, numpages,
cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
static int _set_memory_array(unsigned long *addr, int addrinarray,
enum page_cache_mode new_type)
{
+ enum page_cache_mode set_type;
int i, j;
int ret;
- /*
- * for now UC MINUS. see comments in ioremap_nocache()
- */
for (i = 0; i < addrinarray; i++) {
ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
new_type, NULL);
goto out_free;
}
+ /* If WC, set to UC- first and then WC */
+ set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+ _PAGE_CACHE_MODE_UC_MINUS : new_type;
+
ret = change_page_attr_set(addr, addrinarray,
- cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
- 1);
+ cachemode2pgprot(set_type), 1);
if (!ret && new_type == _PAGE_CACHE_MODE_WC)
ret = change_page_attr_set_clr(addr, addrinarray,
}
EXPORT_SYMBOL(set_memory_array_wc);
+int set_memory_array_wt(unsigned long *addr, int addrinarray)
+{
+ return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WT);
+}
+EXPORT_SYMBOL_GPL(set_memory_array_wt);
+
int _set_memory_wc(unsigned long addr, int numpages)
{
int ret;
{
int ret;
- if (!pat_enabled)
- return set_memory_uc(addr, numpages);
-
ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
_PAGE_CACHE_MODE_WC, NULL);
if (ret)
- goto out_err;
+ return ret;
ret = _set_memory_wc(addr, numpages);
if (ret)
- goto out_free;
-
- return 0;
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
-out_free:
- free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
-out_err:
return ret;
}
EXPORT_SYMBOL(set_memory_wc);
+int _set_memory_wt(unsigned long addr, int numpages)
+{
+ return change_page_attr_set(&addr, numpages,
+ cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0);
+}
+
+int set_memory_wt(unsigned long addr, int numpages)
+{
+ int ret;
+
+ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+ _PAGE_CACHE_MODE_WT, NULL);
+ if (ret)
+ return ret;
+
+ ret = _set_memory_wt(addr, numpages);
+ if (ret)
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(set_memory_wt);
+
int _set_memory_wb(unsigned long addr, int numpages)
{
/* WB cache mode is hard wired to all cache attribute bits being 0 */
{
unsigned long start;
unsigned long end;
+ enum page_cache_mode set_type;
int i;
int free_idx;
int ret;
goto err_out;
}
+ /* If WC, set to UC- first and then WC */
+ set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+ _PAGE_CACHE_MODE_UC_MINUS : new_type;
+
ret = cpa_set_pages_array(pages, addrinarray,
- cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS));
+ cachemode2pgprot(set_type));
if (!ret && new_type == _PAGE_CACHE_MODE_WC)
ret = change_page_attr_set_clr(NULL, addrinarray,
cachemode2pgprot(
}
EXPORT_SYMBOL(set_pages_array_wc);
+int set_pages_array_wt(struct page **pages, int addrinarray)
+{
+ return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WT);
+}
+EXPORT_SYMBOL_GPL(set_pages_array_wt);
+
int set_pages_wb(struct page *page, int numpages)
{
unsigned long addr = (unsigned long)page_address(page);
#include "pat_internal.h"
#include "mm_internal.h"
-#ifdef CONFIG_X86_PAT
-int __read_mostly pat_enabled = 1;
+#undef pr_fmt
+#define pr_fmt(fmt) "" fmt
+
+static bool boot_cpu_done;
+
+static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
static inline void pat_disable(const char *reason)
{
- pat_enabled = 0;
- printk(KERN_INFO "%s\n", reason);
+ __pat_enabled = 0;
+ pr_info("x86/PAT: %s\n", reason);
}
static int __init nopat(char *str)
return 0;
}
early_param("nopat", nopat);
-#else
-static inline void pat_disable(const char *reason)
+
+bool pat_enabled(void)
{
- (void)reason;
+ return !!__pat_enabled;
}
-#endif
-
+EXPORT_SYMBOL_GPL(pat_enabled);
int pat_debug_enable;
}
__setup("debugpat", pat_debug_setup);
-static u64 __read_mostly boot_pat_state;
-
#ifdef CONFIG_X86_PAT
/*
- * X86 PAT uses page flags WC and Uncached together to keep track of
- * memory type of pages that have backing page struct. X86 PAT supports 3
- * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and
- * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not
- * been changed from its default (value of -1 used to denote this).
- * Note we do not support _PAGE_CACHE_MODE_UC here.
+ * X86 PAT uses page flags arch_1 and uncached together to keep track of
+ * memory type of pages that have backing page struct.
+ *
+ * X86 PAT supports 4 different memory types:
+ * - _PAGE_CACHE_MODE_WB
+ * - _PAGE_CACHE_MODE_WC
+ * - _PAGE_CACHE_MODE_UC_MINUS
+ * - _PAGE_CACHE_MODE_WT
+ *
+ * _PAGE_CACHE_MODE_WB is the default type.
*/
-#define _PGMT_DEFAULT 0
+#define _PGMT_WB 0
#define _PGMT_WC (1UL << PG_arch_1)
#define _PGMT_UC_MINUS (1UL << PG_uncached)
-#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_WT (1UL << PG_uncached | 1UL << PG_arch_1)
#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1)
#define _PGMT_CLEAR_MASK (~_PGMT_MASK)
{
unsigned long pg_flags = pg->flags & _PGMT_MASK;
- if (pg_flags == _PGMT_DEFAULT)
- return -1;
+ if (pg_flags == _PGMT_WB)
+ return _PAGE_CACHE_MODE_WB;
else if (pg_flags == _PGMT_WC)
return _PAGE_CACHE_MODE_WC;
else if (pg_flags == _PGMT_UC_MINUS)
return _PAGE_CACHE_MODE_UC_MINUS;
else
- return _PAGE_CACHE_MODE_WB;
+ return _PAGE_CACHE_MODE_WT;
}
static inline void set_page_memtype(struct page *pg,
case _PAGE_CACHE_MODE_UC_MINUS:
memtype_flags = _PGMT_UC_MINUS;
break;
- case _PAGE_CACHE_MODE_WB:
- memtype_flags = _PGMT_WB;
+ case _PAGE_CACHE_MODE_WT:
+ memtype_flags = _PGMT_WT;
break;
+ case _PAGE_CACHE_MODE_WB:
default:
- memtype_flags = _PGMT_DEFAULT;
+ memtype_flags = _PGMT_WB;
break;
}
* configuration.
* Using lower indices is preferred, so we start with highest index.
*/
-void pat_init_cache_modes(void)
+void pat_init_cache_modes(u64 pat)
{
- int i;
enum page_cache_mode cache;
char pat_msg[33];
- u64 pat;
+ int i;
- rdmsrl(MSR_IA32_CR_PAT, pat);
pat_msg[32] = 0;
for (i = 7; i >= 0; i--) {
cache = pat_get_cache_mode((pat >> (i * 8)) & 7,
pat_msg + 4 * i);
update_cache_mode_entry(i, cache);
}
- pr_info("PAT configuration [0-7]: %s\n", pat_msg);
+ pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
}
#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8))
-void pat_init(void)
+static void pat_bsp_init(u64 pat)
{
- u64 pat;
- bool boot_cpu = !boot_pat_state;
+ u64 tmp_pat;
- if (!pat_enabled)
+ if (!cpu_has_pat) {
+ pat_disable("PAT not supported by CPU.");
return;
+ }
- if (!cpu_has_pat) {
- if (!boot_pat_state) {
- pat_disable("PAT not supported by CPU.");
- return;
- } else {
- /*
- * If this happens we are on a secondary CPU, but
- * switched to PAT on the boot CPU. We have no way to
- * undo PAT.
- */
- printk(KERN_ERR "PAT enabled, "
- "but not supported by secondary CPU\n");
- BUG();
- }
+ if (!pat_enabled())
+ goto done;
+
+ rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
+ if (!tmp_pat) {
+ pat_disable("PAT MSR is 0, disabled.");
+ return;
}
- /* Set PWT to Write-Combining. All other bits stay the same */
- /*
- * PTE encoding used in Linux:
- * PAT
- * |PCD
- * ||PWT
- * |||
- * 000 WB _PAGE_CACHE_WB
- * 001 WC _PAGE_CACHE_WC
- * 010 UC- _PAGE_CACHE_UC_MINUS
- * 011 UC _PAGE_CACHE_UC
- * PAT bit unused
- */
- pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
- PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
-
- /* Boot CPU check */
- if (!boot_pat_state) {
- rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
- if (!boot_pat_state) {
- pat_disable("PAT read returns always zero, disabled.");
- return;
- }
+ wrmsrl(MSR_IA32_CR_PAT, pat);
+
+done:
+ pat_init_cache_modes(pat);
+}
+
+static void pat_ap_init(u64 pat)
+{
+ if (!pat_enabled())
+ return;
+
+ if (!cpu_has_pat) {
+ /*
+ * If this happens we are on a secondary CPU, but switched to
+ * PAT on the boot CPU. We have no way to undo PAT.
+ */
+ panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n");
}
wrmsrl(MSR_IA32_CR_PAT, pat);
+}
+
+void pat_init(void)
+{
+ u64 pat;
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (!pat_enabled()) {
+ /*
+ * No PAT. Emulate the PAT table that corresponds to the two
+ * cache bits, PWT (Write Through) and PCD (Cache Disable). This
+ * setup is the same as the BIOS default setup when the system
+ * has PAT but the "nopat" boot option has been specified. This
+ * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+ *
+ * PTE encoding:
+ *
+ * PCD
+ * |PWT PAT
+ * || slot
+ * 00 0 WB : _PAGE_CACHE_MODE_WB
+ * 01 1 WT : _PAGE_CACHE_MODE_WT
+ * 10 2 UC-: _PAGE_CACHE_MODE_UC_MINUS
+ * 11 3 UC : _PAGE_CACHE_MODE_UC
+ *
+ * NOTE: When WC or WP is used, it is redirected to UC- per
+ * the default setup in __cachemode2pte_tbl[].
+ */
+ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
+ PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
- if (boot_cpu)
- pat_init_cache_modes();
+ } else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+ (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+ ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+ /*
+ * PAT support with the lower four entries. Intel Pentium 2,
+ * 3, M, and 4 are affected by PAT errata, which makes the
+ * upper four entries unusable. To be on the safe side, we don't
+ * use those.
+ *
+ * PTE encoding:
+ * PAT
+ * |PCD
+ * ||PWT PAT
+ * ||| slot
+ * 000 0 WB : _PAGE_CACHE_MODE_WB
+ * 001 1 WC : _PAGE_CACHE_MODE_WC
+ * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS
+ * 011 3 UC : _PAGE_CACHE_MODE_UC
+ * PAT bit unused
+ *
+ * NOTE: When WT or WP is used, it is redirected to UC- per
+ * the default setup in __cachemode2pte_tbl[].
+ */
+ pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+ PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
+ } else {
+ /*
+ * Full PAT support. We put WT in slot 7 to improve
+ * robustness in the presence of errata that might cause
+ * the high PAT bit to be ignored. This way, a buggy slot 7
+ * access will hit slot 3, and slot 3 is UC, so at worst
+ * we lose performance without causing a correctness issue.
+ * Pentium 4 erratum N46 is an example for such an erratum,
+ * although we try not to use PAT at all on affected CPUs.
+ *
+ * PTE encoding:
+ * PAT
+ * |PCD
+ * ||PWT PAT
+ * ||| slot
+ * 000 0 WB : _PAGE_CACHE_MODE_WB
+ * 001 1 WC : _PAGE_CACHE_MODE_WC
+ * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS
+ * 011 3 UC : _PAGE_CACHE_MODE_UC
+ * 100 4 WB : Reserved
+ * 101 5 WC : Reserved
+ * 110 6 UC-: Reserved
+ * 111 7 WT : _PAGE_CACHE_MODE_WT
+ *
+ * The reserved slots are unused, but mapped to their
+ * corresponding types in the presence of PAT errata.
+ */
+ pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+ PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT);
+ }
+
+ if (!boot_cpu_done) {
+ pat_bsp_init(pat);
+ boot_cpu_done = true;
+ } else {
+ pat_ap_init(pat);
+ }
}
#undef PAT
* request is for WB.
*/
if (req_type == _PAGE_CACHE_MODE_WB) {
- u8 mtrr_type;
+ u8 mtrr_type, uniform;
- mtrr_type = mtrr_type_lookup(start, end);
+ mtrr_type = mtrr_type_lookup(start, end, &uniform);
if (mtrr_type != MTRR_TYPE_WRBACK)
return _PAGE_CACHE_MODE_UC_MINUS;
/*
* For RAM pages, we use page flags to mark the pages with appropriate type.
- * Here we do two pass:
- * - Find the memtype of all the pages in the range, look for any conflicts
- * - In case of no conflicts, set the new memtype for pages in the range
+ * The page flags are limited to four types, WB (default), WC, WT and UC-.
+ * WP request fails with -EINVAL, and UC gets redirected to UC-. Setting
+ * a new memory type is only allowed for a page mapped with the default WB
+ * type.
+ *
+ * Here we do two passes:
+ * - Find the memtype of all the pages in the range, look for any conflicts.
+ * - In case of no conflicts, set the new memtype for pages in the range.
*/
static int reserve_ram_pages_type(u64 start, u64 end,
enum page_cache_mode req_type,
struct page *page;
u64 pfn;
+ if (req_type == _PAGE_CACHE_MODE_WP) {
+ if (new_type)
+ *new_type = _PAGE_CACHE_MODE_UC_MINUS;
+ return -EINVAL;
+ }
+
if (req_type == _PAGE_CACHE_MODE_UC) {
/* We do not support strong UC */
WARN_ON_ONCE(1);
page = pfn_to_page(pfn);
type = get_page_memtype(page);
- if (type != -1) {
- pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
+ if (type != _PAGE_CACHE_MODE_WB) {
+ pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
start, end - 1, type, req_type);
if (new_type)
*new_type = type;
for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
page = pfn_to_page(pfn);
- set_page_memtype(page, -1);
+ set_page_memtype(page, _PAGE_CACHE_MODE_WB);
}
return 0;
}
* - _PAGE_CACHE_MODE_WC
* - _PAGE_CACHE_MODE_UC_MINUS
* - _PAGE_CACHE_MODE_UC
+ * - _PAGE_CACHE_MODE_WT
*
* If new_type is NULL, function will return an error if it cannot reserve the
* region with req_type. If new_type is non-NULL, function will return
BUG_ON(start >= end); /* end is exclusive */
- if (!pat_enabled) {
+ if (!pat_enabled()) {
/* This is identical to page table setting without PAT */
- if (new_type) {
- if (req_type == _PAGE_CACHE_MODE_WC)
- *new_type = _PAGE_CACHE_MODE_UC_MINUS;
- else
- *new_type = req_type;
- }
+ if (new_type)
+ *new_type = req_type;
return 0;
}
err = rbt_memtype_check_insert(new, new_type);
if (err) {
- printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
- start, end - 1,
- cattr_name(new->type), cattr_name(req_type));
+ pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
+ start, end - 1,
+ cattr_name(new->type), cattr_name(req_type));
kfree(new);
spin_unlock(&memtype_lock);
int is_range_ram;
struct memtype *entry;
- if (!pat_enabled)
+ if (!pat_enabled())
return 0;
/* Low ISA region is always mapped WB. No need to track */
spin_unlock(&memtype_lock);
if (!entry) {
- printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
- current->comm, current->pid, start, end - 1);
+ pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
+ current->comm, current->pid, start, end - 1);
return -EINVAL;
}
* Only to be called when PAT is enabled
*
* Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS
- * or _PAGE_CACHE_MODE_UC
+ * or _PAGE_CACHE_MODE_WT.
*/
static enum page_cache_mode lookup_memtype(u64 paddr)
{
if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
struct page *page;
- page = pfn_to_page(paddr >> PAGE_SHIFT);
- rettype = get_page_memtype(page);
- /*
- * -1 from get_page_memtype() implies RAM page is in its
- * default state and not reserved, and hence of type WB
- */
- if (rettype == -1)
- rettype = _PAGE_CACHE_MODE_WB;
- return rettype;
+ page = pfn_to_page(paddr >> PAGE_SHIFT);
+ return get_page_memtype(page);
}
spin_lock(&memtype_lock);
u64 to = from + size;
u64 cursor = from;
- if (!pat_enabled)
+ if (!pat_enabled())
return 1;
while (cursor < to) {
if (!devmem_is_allowed(pfn)) {
- printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
- current->comm, from, to - 1);
+ pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
+ current->comm, from, to - 1);
return 0;
}
cursor += PAGE_SIZE;
* caching for the high addresses through the KEN pin, but
* we maintain the tradition of paranoia in this code.
*/
- if (!pat_enabled &&
+ if (!pat_enabled() &&
!(boot_cpu_has(X86_FEATURE_MTRR) ||
boot_cpu_has(X86_FEATURE_K6_MTRR) ||
boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
size;
if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) {
- printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
- "for [mem %#010Lx-%#010Lx]\n",
+ pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n",
current->comm, current->pid,
cattr_name(pcm),
base, (unsigned long long)(base + size-1));
* the type requested matches the type of first page in the range.
*/
if (is_ram) {
- if (!pat_enabled)
+ if (!pat_enabled())
return 0;
pcm = lookup_memtype(paddr);
if (want_pcm != pcm) {
- printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
+ pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
cattr_name(want_pcm),
(unsigned long long)paddr,
if (strict_prot ||
!is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
free_memtype(paddr, paddr + size);
- printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
- " for [mem %#010Lx-%#010Lx], got %s\n",
- current->comm, current->pid,
- cattr_name(want_pcm),
- (unsigned long long)paddr,
- (unsigned long long)(paddr + size - 1),
- cattr_name(pcm));
+ pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n",
+ current->comm, current->pid,
+ cattr_name(want_pcm),
+ (unsigned long long)paddr,
+ (unsigned long long)(paddr + size - 1),
+ cattr_name(pcm));
return -EINVAL;
}
/*
return ret;
}
- if (!pat_enabled)
+ if (!pat_enabled())
return 0;
/*
{
enum page_cache_mode pcm;
- if (!pat_enabled)
+ if (!pat_enabled())
return 0;
/* Set prot based on lookup */
pgprot_t pgprot_writecombine(pgprot_t prot)
{
- if (pat_enabled)
- return __pgprot(pgprot_val(prot) |
+ return __pgprot(pgprot_val(prot) |
cachemode2protval(_PAGE_CACHE_MODE_WC));
- else
- return pgprot_noncached(prot);
}
EXPORT_SYMBOL_GPL(pgprot_writecombine);
+pgprot_t pgprot_writethrough(pgprot_t prot)
+{
+ return __pgprot(pgprot_val(prot) |
+ cachemode2protval(_PAGE_CACHE_MODE_WT));
+}
+EXPORT_SYMBOL_GPL(pgprot_writethrough);
+
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
static struct memtype *memtype_get_idx(loff_t pos)
static int __init pat_memtype_list_init(void)
{
- if (pat_enabled) {
+ if (pat_enabled()) {
debugfs_create_file("pat_memtype_list", S_IRUSR,
arch_debugfs_dir, NULL, &memtype_fops);
}
extern int pat_debug_enable;
#define dprintk(fmt, arg...) \
- do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)
+ do { if (pat_debug_enable) pr_info("x86/PAT: " fmt, ##arg); } while (0)
struct memtype {
u64 start;
return 0;
failure:
- printk(KERN_INFO "%s:%d conflicting memory types "
- "%Lx-%Lx %s<->%s\n", current->comm, current->pid, start,
- end, cattr_name(found_type), cattr_name(match->type));
+ pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
+ current->comm, current->pid, start, end,
+ cattr_name(found_type), cattr_name(match->type));
return -EBUSY;
}
}
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+/**
+ * pud_set_huge - setup kernel PUD mapping
+ *
+ * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
+ * function sets up a huge page only if any of the following conditions are met:
+ *
+ * - MTRRs are disabled, or
+ *
+ * - MTRRs are enabled and the range is completely covered by a single MTRR, or
+ *
+ * - MTRRs are enabled and the corresponding MTRR memory type is WB, which
+ * has no effect on the requested PAT memory type.
+ *
+ * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger
+ * page mapping attempt fails.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
- u8 mtrr;
+ u8 mtrr, uniform;
- /*
- * Do not use a huge page when the range is covered by non-WB type
- * of MTRRs.
- */
- mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE);
- if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+ mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform);
+ if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+ (mtrr != MTRR_TYPE_WRBACK))
return 0;
prot = pgprot_4k_2_large(prot);
return 1;
}
+/**
+ * pmd_set_huge - setup kernel PMD mapping
+ *
+ * See text over pud_set_huge() above.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
{
- u8 mtrr;
+ u8 mtrr, uniform;
- /*
- * Do not use a huge page when the range is covered by non-WB type
- * of MTRRs.
- */
- mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE);
- if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+ mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform);
+ if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+ (mtrr != MTRR_TYPE_WRBACK)) {
+ pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n",
+ __func__, addr, addr + PMD_SIZE);
return 0;
+ }
prot = pgprot_4k_2_large(prot);
return 1;
}
+/**
+ * pud_clear_huge - clear kernel PUD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PUD map is found).
+ */
int pud_clear_huge(pud_t *pud)
{
if (pud_large(*pud)) {
return 0;
}
+/**
+ * pmd_clear_huge - clear kernel PMD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PMD map is found).
+ */
int pmd_clear_huge(pmd_t *pmd)
{
if (pmd_large(*pmd)) {
* of the License.
*/
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
/*
* Calling convention :
if (is_ereg(dst_reg))
EMIT1(0x41);
EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+
+ /* emit 'movzwl eax, ax' */
+ if (is_ereg(dst_reg))
+ EMIT3(0x45, 0x0F, 0xB7);
+ else
+ EMIT2(0x0F, 0xB7);
+ EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
/* emit 'bswap eax' to swap lower 4 bytes */
break;
case BPF_ALU | BPF_END | BPF_FROM_LE:
+ switch (imm32) {
+ case 16:
+ /* emit 'movzwl eax, ax' to zero extend 16-bit
+ * into 64 bit
+ */
+ if (is_ereg(dst_reg))
+ EMIT3(0x45, 0x0F, 0xB7);
+ else
+ EMIT2(0x0F, 0xB7);
+ EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
+ break;
+ case 32:
+ /* emit 'mov eax, eax' to clear upper 32-bits */
+ if (is_ereg(dst_reg))
+ EMIT1(0x45);
+ EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
+ break;
+ case 64:
+ /* nop */
+ break;
+ }
break;
/* ST: *(u8*)(dst_reg + off) = imm */
}
ctx.cleanup_addr = proglen;
- for (pass = 0; pass < 10; pass++) {
+ /* JITed image shrinks with every pass and the loop iterates
+ * until the image stops shrinking. Very large bpf programs
+ * may converge on the last pass. In such case do one more
+ * pass to emit the final image
+ */
+ for (pass = 0; pass < 10 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
image = NULL;
kfree(info);
}
+/*
+ * An IO port or MMIO resource assigned to a PCI host bridge may be
+ * consumed by the host bridge itself or available to its child
+ * bus/devices. The ACPI specification defines a bit (Producer/Consumer)
+ * to tell whether the resource is consumed by the host bridge itself,
+ * but firmware hasn't used that bit consistently, so we can't rely on it.
+ *
+ * On x86 and IA64 platforms, all IO port and MMIO resources are assumed
+ * to be available to child bus/devices except one special case:
+ * IO port [0xCF8-0xCFF] is consumed by the host bridge itself
+ * to access PCI configuration space.
+ *
+ * So explicitly filter out PCI CFG IO ports[0xCF8-0xCFF].
+ */
+static bool resource_is_pcicfg_ioport(struct resource *res)
+{
+ return (res->flags & IORESOURCE_IO) &&
+ res->start == 0xCF8 && res->end == 0xCFF;
+}
+
static void probe_pci_root_info(struct pci_root_info *info,
struct acpi_device *device,
int busnum, int domain,
"no IO and memory resources present in _CRS\n");
else
resource_list_for_each_entry_safe(entry, tmp, list) {
- if ((entry->res->flags & IORESOURCE_WINDOW) == 0 ||
- (entry->res->flags & IORESOURCE_DISABLED))
+ if ((entry->res->flags & IORESOURCE_DISABLED) ||
+ resource_is_pcicfg_ioport(entry->res))
resource_list_destroy_entry(entry);
else
entry->res->name = info->name;
int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
{
- struct pci_sysdata *sd = bridge->bus->sysdata;
-
- ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+ /*
+ * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+ * here, pci_create_root_bus() has been called by someone else and
+ * sysdata is likely to be different from what we expect. Let it go in
+ * that case.
+ */
+ if (!bridge->dev.parent) {
+ struct pci_sysdata *sd = bridge->bus->sysdata;
+ ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+ }
return 0;
}
* Caller can followup with UC MINUS request and add a WC mtrr if there
* is a free mtrr slot.
*/
- if (!pat_enabled && write_combine)
+ if (!pat_enabled() && write_combine)
return -EINVAL;
- if (pat_enabled && write_combine)
+ if (pat_enabled() && write_combine)
prot |= cachemode2protval(_PAGE_CACHE_MODE_WC);
- else if (pat_enabled || boot_cpu_data.x86 > 3)
+ else if (pat_enabled() || boot_cpu_data.x86 > 3)
/*
* ioremap() and ioremap_nocache() defaults to UC MINUS for now.
* To avoid attribute conflicts, request UC MINUS here
static int intel_mid_pci_irq_enable(struct pci_dev *dev)
{
+ struct irq_alloc_info info;
int polarity;
if (dev->irq_managed && dev->irq > 0)
polarity = 0; /* active high */
else
polarity = 1; /* active low */
+ ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity);
/*
* MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
* IOAPIC RTE entries, so we just enable RTE for the device.
*/
- if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev)))
- return -EBUSY;
- if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
+ if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info) < 0)
return -EBUSY;
dev->irq_managed = 1;
/*
* Code for querying and setting of IRQ routes on various interrupt routers.
+ * PIC Edge/Level Control Registers (ELCR) 0x4d0 & 0x4d1.
*/
-void eisa_set_level_irq(unsigned int irq)
+void elcr_set_level_irq(unsigned int irq)
{
unsigned char mask = 1 << (irq & 7);
unsigned int port = 0x4d0 + (irq >> 3);
unsigned char val;
- static u16 eisa_irq_mask;
+ static u16 elcr_irq_mask;
- if (irq >= 16 || (1 << irq) & eisa_irq_mask)
+ if (irq >= 16 || (1 << irq) & elcr_irq_mask)
return;
- eisa_irq_mask |= (1 << irq);
+ elcr_irq_mask |= (1 << irq);
printk(KERN_DEBUG "PCI: setting IRQ %u as level-triggered\n", irq);
val = inb(port);
if (!(val & mask)) {
} else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
msg = "found";
- eisa_set_level_irq(irq);
+ elcr_set_level_irq(irq);
} else if (newirq && r->set &&
(dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
if (r->set(pirq_router_dev, dev, pirq, newirq)) {
- eisa_set_level_irq(newirq);
+ elcr_set_level_irq(newirq);
msg = "assigned";
irq = newirq;
}
# Platform specific code goes here
+obj-y += atom/
obj-y += ce4100/
obj-y += efi/
obj-y += geode/
--- /dev/null
+obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o
--- /dev/null
+/*
+ * Intel SOC Punit device state debug driver
+ * Punit controls power management for North Complex devices (Graphics
+ * blocks, Image Signal Processing, video processing, display, DSP etc.)
+ *
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/io.h>
+#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
+
+/* Side band Interface port */
+#define PUNIT_PORT 0x04
+/* Power gate status reg */
+#define PWRGT_STATUS 0x61
+/* Subsystem config/status Video processor */
+#define VED_SS_PM0 0x32
+/* Subsystem config/status ISP (Image Signal Processor) */
+#define ISP_SS_PM0 0x39
+/* Subsystem config/status Input/output controller */
+#define MIO_SS_PM 0x3B
+/* Shift bits for getting status for video, isp and i/o */
+#define SSS_SHIFT 24
+/* Shift bits for getting status for graphics rendering */
+#define RENDER_POS 0
+/* Shift bits for getting status for media control */
+#define MEDIA_POS 2
+/* Shift bits for getting status for Valley View/Baytrail display */
+#define VLV_DISPLAY_POS 6
+/* Subsystem config/status display for Cherry Trail SOC */
+#define CHT_DSP_SSS 0x36
+/* Shift bits for getting status for display */
+#define CHT_DSP_SSS_POS 16
+
+struct punit_device {
+ char *name;
+ int reg;
+ int sss_pos;
+};
+
+static const struct punit_device punit_device_byt[] = {
+ { "GFX RENDER", PWRGT_STATUS, RENDER_POS },
+ { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS },
+ { "DISPLAY", PWRGT_STATUS, VLV_DISPLAY_POS },
+ { "VED", VED_SS_PM0, SSS_SHIFT },
+ { "ISP", ISP_SS_PM0, SSS_SHIFT },
+ { "MIO", MIO_SS_PM, SSS_SHIFT },
+ { NULL }
+};
+
+static const struct punit_device punit_device_cht[] = {
+ { "GFX RENDER", PWRGT_STATUS, RENDER_POS },
+ { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS },
+ { "DISPLAY", CHT_DSP_SSS, CHT_DSP_SSS_POS },
+ { "VED", VED_SS_PM0, SSS_SHIFT },
+ { "ISP", ISP_SS_PM0, SSS_SHIFT },
+ { "MIO", MIO_SS_PM, SSS_SHIFT },
+ { NULL }
+};
+
+static const char * const dstates[] = {"D0", "D0i1", "D0i2", "D0i3"};
+
+static int punit_dev_state_show(struct seq_file *seq_file, void *unused)
+{
+ u32 punit_pwr_status;
+ struct punit_device *punit_devp = seq_file->private;
+ int index;
+ int status;
+
+ seq_puts(seq_file, "\n\nPUNIT NORTH COMPLEX DEVICES :\n");
+ while (punit_devp->name) {
+ status = iosf_mbi_read(PUNIT_PORT, BT_MBI_PMC_READ,
+ punit_devp->reg,
+ &punit_pwr_status);
+ if (status) {
+ seq_printf(seq_file, "%9s : Read Failed\n",
+ punit_devp->name);
+ } else {
+ index = (punit_pwr_status >> punit_devp->sss_pos) & 3;
+ seq_printf(seq_file, "%9s : %s\n", punit_devp->name,
+ dstates[index]);
+ }
+ punit_devp++;
+ }
+
+ return 0;
+}
+
+static int punit_dev_state_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, punit_dev_state_show, inode->i_private);
+}
+
+static const struct file_operations punit_dev_state_ops = {
+ .open = punit_dev_state_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static struct dentry *punit_dbg_file;
+
+static int punit_dbgfs_register(struct punit_device *punit_device)
+{
+ static struct dentry *dev_state;
+
+ punit_dbg_file = debugfs_create_dir("punit_atom", NULL);
+ if (!punit_dbg_file)
+ return -ENXIO;
+
+ dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO,
+ punit_dbg_file, punit_device,
+ &punit_dev_state_ops);
+ if (!dev_state) {
+ pr_err("punit_dev_state register failed\n");
+ debugfs_remove(punit_dbg_file);
+ return -ENXIO;
+ }
+
+ return 0;
+}
+
+static void punit_dbgfs_unregister(void)
+{
+ debugfs_remove_recursive(punit_dbg_file);
+}
+
+#define ICPU(model, drv_data) \
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\
+ (kernel_ulong_t)&drv_data }
+
+static const struct x86_cpu_id intel_punit_cpu_ids[] = {
+ ICPU(55, punit_device_byt), /* Valleyview, Bay Trail */
+ ICPU(76, punit_device_cht), /* Braswell, Cherry Trail */
+ {}
+};
+
+MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids);
+
+static int __init punit_atom_debug_init(void)
+{
+ const struct x86_cpu_id *id;
+ int ret;
+
+ id = x86_match_cpu(intel_punit_cpu_ids);
+ if (!id)
+ return -ENODEV;
+
+ ret = punit_dbgfs_register((struct punit_device *)id->driver_data);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static void __exit punit_atom_debug_exit(void)
+{
+ punit_dbgfs_unregister();
+}
+
+module_init(punit_atom_debug_init);
+module_exit(punit_atom_debug_exit);
+
+MODULE_AUTHOR("Kumar P, Mahesh <mahesh.kumar.p@intel.com>");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_DESCRIPTION("Driver for Punit devices states debugging");
+MODULE_LICENSE("GPL v2");
if (efi_enabled(EFI_DBG))
print_efi_memmap();
+
+ efi_esrt_init();
}
void __init efi_late_init(void)
static int tangier_probe(struct platform_device *pdev)
{
int gsi;
+ struct irq_alloc_info info;
struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
if (!pdata)
/* IOAPIC builds identity mapping between GSI and IRQ on MID */
gsi = pdata->irq;
- if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) ||
- mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) {
+ ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0);
+ if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) {
dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
gsi);
return -EINVAL;
return 0;
}
+static void __init intel_mid_setup_bp_timer(void)
+{
+ apbt_time_init();
+ setup_boot_APIC_clock();
+}
+
static void __init intel_mid_time_init(void)
{
sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
+
switch (intel_mid_timer_options) {
case INTEL_MID_TIMER_APBT_ONLY:
break;
case INTEL_MID_TIMER_LAPIC_APBT:
- x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+ /* Use apbt and local apic */
+ x86_init.timers.setup_percpu_clockev = intel_mid_setup_bp_timer;
x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
- break;
+ return;
default:
if (!boot_cpu_has(X86_FEATURE_ARAT))
break;
+ /* Lapic only, no apbt */
x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
return;
}
- /* we need at least one APB timer */
- pre_init_apic_IRQ0();
- apbt_time_init();
+
+ x86_init.timers.setup_percpu_clockev = apbt_time_init;
}
static void intel_mid_arch_setup(void)
pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n",
totallen, (u32)pentry->phys_addr,
pentry->freq_hz, pentry->irq);
- if (!pentry->irq)
- continue;
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
-/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
- mp_irq.irqflag = 5;
- mp_irq.srcbus = MP_BUS_ISA;
- mp_irq.srcbusirq = pentry->irq; /* IRQ */
- mp_irq.dstapic = MP_APIC_ALL;
- mp_irq.dstirq = pentry->irq;
- mp_save_irq(&mp_irq);
- mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ /* triggering mode edge bit 2-3, active high polarity bit 0-1 */
+ mp_irq.irqflag = 5;
+ mp_irq.srcbus = MP_BUS_ISA;
+ mp_irq.srcbusirq = pentry->irq; /* IRQ */
+ mp_irq.dstapic = MP_APIC_ALL;
+ mp_irq.dstirq = pentry->irq;
+ mp_save_irq(&mp_irq);
+ mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
}
return 0;
mp_irq.dstapic = MP_APIC_ALL;
mp_irq.dstirq = pentry->irq;
mp_save_irq(&mp_irq);
- mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+ mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
}
return 0;
}
struct devs_id *dev = NULL;
int num, i, ret;
int polarity;
+ struct irq_alloc_info info;
sb = (struct sfi_table_simple *)table;
num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
polarity = 1;
}
- ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE);
- if (ret == 0)
- ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC);
+ ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity);
+ ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info);
WARN_ON(ret < 0);
}
#include <linux/init.h>
#include <linux/sfi.h>
#include <linux/io.h>
-#include <linux/irqdomain.h>
+#include <asm/irqdomain.h>
#include <asm/io_apic.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
-static struct irq_domain_ops sfi_ioapic_irqdomain_ops = {
- .map = mp_irqdomain_map,
-};
static int __init sfi_parse_ioapic(struct sfi_table_header *table)
{
int i, num;
struct ioapic_domain_cfg cfg = {
.type = IOAPIC_DOMAIN_STRICT,
- .ops = &sfi_ioapic_irqdomain_ops,
+ .ops = &mp_ioapic_irqdomain_ops,
};
sb = (struct sfi_table_simple *)table;
#include <linux/slab.h>
#include <linux/irq.h>
+#include <asm/irqdomain.h>
#include <asm/apic.h>
#include <asm/uv/uv_irq.h>
#include <asm/uv/uv_hub.h>
/* MMR offset and pnode of hub sourcing interrupts for a given irq */
-struct uv_irq_2_mmr_pnode{
- struct rb_node list;
+struct uv_irq_2_mmr_pnode {
unsigned long offset;
int pnode;
- int irq;
};
-static DEFINE_SPINLOCK(uv_irq_lock);
-static struct rb_root uv_irq_root;
+static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info)
+{
+ unsigned long mmr_value;
+ struct uv_IO_APIC_route_entry *entry;
+
+ BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
+ sizeof(unsigned long));
+
+ mmr_value = 0;
+ entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+ entry->vector = cfg->vector;
+ entry->delivery_mode = apic->irq_delivery_mode;
+ entry->dest_mode = apic->irq_dest_mode;
+ entry->polarity = 0;
+ entry->trigger = 0;
+ entry->mask = 0;
+ entry->dest = cfg->dest_apicid;
-static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
+ uv_write_global_mmr64(info->pnode, info->offset, mmr_value);
+}
static void uv_noop(struct irq_data *data) { }
ack_APIC_irq();
}
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
+{
+ struct irq_data *parent = data->parent_data;
+ struct irq_cfg *cfg = irqd_cfg(data);
+ int ret;
+
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret >= 0) {
+ uv_program_mmr(cfg, data->chip_data);
+ send_cleanup_vector(cfg);
+ }
+
+ return ret;
+}
+
static struct irq_chip uv_irq_chip = {
.name = "UV-CORE",
.irq_mask = uv_noop,
.irq_set_affinity = uv_set_irq_affinity,
};
-/*
- * Add offset and pnode information of the hub sourcing interrupts to the
- * rb tree for a specific irq.
- */
-static int uv_set_irq_2_mmr_info(int irq, unsigned long offset, unsigned blade)
+static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- struct rb_node **link = &uv_irq_root.rb_node;
- struct rb_node *parent = NULL;
- struct uv_irq_2_mmr_pnode *n;
- struct uv_irq_2_mmr_pnode *e;
- unsigned long irqflags;
-
- n = kmalloc_node(sizeof(struct uv_irq_2_mmr_pnode), GFP_KERNEL,
- uv_blade_to_memory_nid(blade));
- if (!n)
+ struct uv_irq_2_mmr_pnode *chip_data;
+ struct irq_alloc_info *info = arg;
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+ int ret;
+
+ if (nr_irqs > 1 || !info || info->type != X86_IRQ_ALLOC_TYPE_UV)
+ return -EINVAL;
+
+ chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL,
+ irq_data->node);
+ if (!chip_data)
return -ENOMEM;
- n->irq = irq;
- n->offset = offset;
- n->pnode = uv_blade_to_pnode(blade);
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- /* Find the right place in the rbtree: */
- while (*link) {
- parent = *link;
- e = rb_entry(parent, struct uv_irq_2_mmr_pnode, list);
-
- if (unlikely(irq == e->irq)) {
- /* irq entry exists */
- e->pnode = uv_blade_to_pnode(blade);
- e->offset = offset;
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- kfree(n);
- return 0;
- }
-
- if (irq < e->irq)
- link = &(*link)->rb_left;
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+ if (ret >= 0) {
+ if (info->uv_limit == UV_AFFINITY_CPU)
+ irq_set_status_flags(virq, IRQ_NO_BALANCING);
else
- link = &(*link)->rb_right;
+ irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+
+ chip_data->pnode = uv_blade_to_pnode(info->uv_blade);
+ chip_data->offset = info->uv_offset;
+ irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data,
+ handle_percpu_irq, NULL, info->uv_name);
+ } else {
+ kfree(chip_data);
}
- /* Insert the node into the rbtree. */
- rb_link_node(&n->list, parent, link);
- rb_insert_color(&n->list, &uv_irq_root);
-
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return 0;
+ return ret;
}
-/* Retrieve offset and pnode information from the rb tree for a specific irq */
-int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode)
+static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
{
- struct uv_irq_2_mmr_pnode *e;
- struct rb_node *n;
- unsigned long irqflags;
-
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- n = uv_irq_root.rb_node;
- while (n) {
- e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
-
- if (e->irq == irq) {
- *offset = e->offset;
- *pnode = e->pnode;
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return 0;
- }
-
- if (irq < e->irq)
- n = n->rb_left;
- else
- n = n->rb_right;
- }
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- return -1;
+ struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+ BUG_ON(nr_irqs != 1);
+ kfree(irq_data->chip_data);
+ irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
+ irq_clear_status_flags(virq, IRQ_NO_BALANCING);
+ irq_domain_free_irqs_top(domain, virq, nr_irqs);
}
/*
* Re-target the irq to the specified CPU and enable the specified MMR located
* on the specified blade to allow the sending of MSIs to the specified CPU.
*/
-static int
-arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
- unsigned long mmr_offset, int limit)
+static void uv_domain_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
- const struct cpumask *eligible_cpu = cpumask_of(cpu);
- struct irq_cfg *cfg = irq_cfg(irq);
- unsigned long mmr_value;
- struct uv_IO_APIC_route_entry *entry;
- int mmr_pnode, err;
- unsigned int dest;
-
- BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
- sizeof(unsigned long));
-
- err = assign_irq_vector(irq, cfg, eligible_cpu);
- if (err != 0)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest);
- if (err != 0)
- return err;
-
- if (limit == UV_AFFINITY_CPU)
- irq_set_status_flags(irq, IRQ_NO_BALANCING);
- else
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-
- irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
- irq_name);
-
- mmr_value = 0;
- entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
- entry->vector = cfg->vector;
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->polarity = 0;
- entry->trigger = 0;
- entry->mask = 0;
- entry->dest = dest;
-
- mmr_pnode = uv_blade_to_pnode(mmr_blade);
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
-
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
-
- return irq;
+ uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
}
/*
* Disable the specified MMR located on the specified blade so that MSIs are
* longer allowed to be sent.
*/
-static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset)
+static void uv_domain_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
unsigned long mmr_value;
struct uv_IO_APIC_route_entry *entry;
- BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
- sizeof(unsigned long));
-
mmr_value = 0;
entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
entry->mask = 1;
-
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+ uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
}
-static int
-uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest;
- unsigned long mmr_value, mmr_offset;
- struct uv_IO_APIC_route_entry *entry;
- int mmr_pnode;
-
- if (apic_set_affinity(data, mask, &dest))
- return -1;
-
- mmr_value = 0;
- entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-
- entry->vector = cfg->vector;
- entry->delivery_mode = apic->irq_delivery_mode;
- entry->dest_mode = apic->irq_dest_mode;
- entry->polarity = 0;
- entry->trigger = 0;
- entry->mask = 0;
- entry->dest = dest;
-
- /* Get previously stored MMR and pnode of hub sourcing interrupts */
- if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
- return -1;
-
- uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+static const struct irq_domain_ops uv_domain_ops = {
+ .alloc = uv_domain_alloc,
+ .free = uv_domain_free,
+ .activate = uv_domain_activate,
+ .deactivate = uv_domain_deactivate,
+};
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
+static struct irq_domain *uv_get_irq_domain(void)
+{
+ static struct irq_domain *uv_domain;
+ static DEFINE_MUTEX(uv_lock);
+
+ mutex_lock(&uv_lock);
+ if (uv_domain == NULL) {
+ uv_domain = irq_domain_add_tree(NULL, &uv_domain_ops, NULL);
+ if (uv_domain)
+ uv_domain->parent = x86_vector_domain;
+ }
+ mutex_unlock(&uv_lock);
- return IRQ_SET_MASK_OK_NOCOPY;
+ return uv_domain;
}
/*
int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
unsigned long mmr_offset, int limit)
{
- int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade));
+ struct irq_alloc_info info;
+ struct irq_domain *domain = uv_get_irq_domain();
- if (!irq)
- return -EBUSY;
+ if (!domain)
+ return -ENOMEM;
- ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset,
- limit);
- if (ret == irq)
- uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade);
- else
- irq_free_hwirq(irq);
+ init_irq_alloc_info(&info, cpumask_of(cpu));
+ info.type = X86_IRQ_ALLOC_TYPE_UV;
+ info.uv_limit = limit;
+ info.uv_blade = mmr_blade;
+ info.uv_offset = mmr_offset;
+ info.uv_name = irq_name;
- return ret;
+ return irq_domain_alloc_irqs(domain, 1,
+ uv_blade_to_memory_nid(mmr_blade), &info);
}
EXPORT_SYMBOL_GPL(uv_setup_irq);
*/
void uv_teardown_irq(unsigned int irq)
{
- struct uv_irq_2_mmr_pnode *e;
- struct rb_node *n;
- unsigned long irqflags;
-
- spin_lock_irqsave(&uv_irq_lock, irqflags);
- n = uv_irq_root.rb_node;
- while (n) {
- e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
- if (e->irq == irq) {
- arch_disable_uv_irq(e->pnode, e->offset);
- rb_erase(n, &uv_irq_root);
- kfree(e);
- break;
- }
- if (irq < e->irq)
- n = n->rb_left;
- else
- n = n->rb_right;
- }
- spin_unlock_irqrestore(&uv_irq_lock, irqflags);
- irq_free_hwirq(irq);
+ irq_domain_free_irqs(irq, 1);
}
EXPORT_SYMBOL_GPL(uv_teardown_irq);
#include <asm/mtrr.h>
#include <asm/page.h>
#include <asm/mce.h>
-#include <asm/xcr.h>
#include <asm/suspend.h>
+#include <asm/fpu/internal.h>
#include <asm/debugreg.h>
-#include <asm/fpu-internal.h> /* pcntxt_mask */
#include <asm/cpu.h>
#ifdef CONFIG_X86_32
#endif
load_TR_desc(); /* This does ltr */
load_LDT(¤t->active_mm->context); /* This does lldt */
+
+ fpu__resume_cpu();
}
/**
wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
#endif
- /*
- * restore XCR0 for xsave capable cpu's.
- */
- if (cpu_has_xsave)
- xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-
fix_processor_context();
do_fpu_end();
/* code below has been relocated to a safe page */
ENTRY(core_restore_code)
-loop:
+.Lloop:
testq %rdx, %rdx
- jz done
+ jz .Ldone
/* get addresses from the pbe and copy the page */
movq pbe_address(%rdx), %rsi
/* progress to the next pbe */
movq pbe_next(%rdx), %rdx
- jmp loop
-done:
+ jmp .Lloop
+.Ldone:
/* jump to the restore_registers address from the image header */
jmpq *%rax
/*
+++ /dev/null
-out := $(obj)/../include/generated/asm
-uapi := $(obj)/../include/generated/uapi/asm
-
-# Create output directory if not already present
-_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
- $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)')
-
-syscall32 := $(srctree)/$(src)/syscall_32.tbl
-syscall64 := $(srctree)/$(src)/syscall_64.tbl
-
-syshdr := $(srctree)/$(src)/syscallhdr.sh
-systbl := $(srctree)/$(src)/syscalltbl.sh
-
-quiet_cmd_syshdr = SYSHDR $@
- cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \
- '$(syshdr_abi_$(basetarget))' \
- '$(syshdr_pfx_$(basetarget))' \
- '$(syshdr_offset_$(basetarget))'
-quiet_cmd_systbl = SYSTBL $@
- cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@
-
-quiet_cmd_hypercalls = HYPERCALLS $@
- cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<,$^)
-
-syshdr_abi_unistd_32 := i386
-$(uapi)/unistd_32.h: $(syscall32) $(syshdr)
- $(call if_changed,syshdr)
-
-syshdr_abi_unistd_32_ia32 := i386
-syshdr_pfx_unistd_32_ia32 := ia32_
-$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr)
- $(call if_changed,syshdr)
-
-syshdr_abi_unistd_x32 := common,x32
-syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT
-$(uapi)/unistd_x32.h: $(syscall64) $(syshdr)
- $(call if_changed,syshdr)
-
-syshdr_abi_unistd_64 := common,64
-$(uapi)/unistd_64.h: $(syscall64) $(syshdr)
- $(call if_changed,syshdr)
-
-syshdr_abi_unistd_64_x32 := x32
-syshdr_pfx_unistd_64_x32 := x32_
-$(out)/unistd_64_x32.h: $(syscall64) $(syshdr)
- $(call if_changed,syshdr)
-
-$(out)/syscalls_32.h: $(syscall32) $(systbl)
- $(call if_changed,systbl)
-$(out)/syscalls_64.h: $(syscall64) $(systbl)
- $(call if_changed,systbl)
-
-$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh
- $(call if_changed,hypercalls)
-
-$(out)/xen-hypercalls.h: $(srctree)/include/xen/interface/xen*.h
-
-uapisyshdr-y += unistd_32.h unistd_64.h unistd_x32.h
-syshdr-y += syscalls_32.h
-syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h
-syshdr-$(CONFIG_X86_64) += syscalls_64.h
-syshdr-$(CONFIG_XEN) += xen-hypercalls.h
-
-targets += $(uapisyshdr-y) $(syshdr-y)
-
-PHONY += all
-all: $(addprefix $(uapi)/,$(uapisyshdr-y))
-all: $(addprefix $(out)/,$(syshdr-y))
- @:
+++ /dev/null
-#
-# 32-bit system call numbers and entry vectors
-#
-# The format is:
-# <number> <abi> <name> <entry point> <compat entry point>
-#
-# The abi is always "i386" for this file.
-#
-0 i386 restart_syscall sys_restart_syscall
-1 i386 exit sys_exit
-2 i386 fork sys_fork stub32_fork
-3 i386 read sys_read
-4 i386 write sys_write
-5 i386 open sys_open compat_sys_open
-6 i386 close sys_close
-7 i386 waitpid sys_waitpid sys32_waitpid
-8 i386 creat sys_creat
-9 i386 link sys_link
-10 i386 unlink sys_unlink
-11 i386 execve sys_execve stub32_execve
-12 i386 chdir sys_chdir
-13 i386 time sys_time compat_sys_time
-14 i386 mknod sys_mknod
-15 i386 chmod sys_chmod
-16 i386 lchown sys_lchown16
-17 i386 break
-18 i386 oldstat sys_stat
-19 i386 lseek sys_lseek compat_sys_lseek
-20 i386 getpid sys_getpid
-21 i386 mount sys_mount compat_sys_mount
-22 i386 umount sys_oldumount
-23 i386 setuid sys_setuid16
-24 i386 getuid sys_getuid16
-25 i386 stime sys_stime compat_sys_stime
-26 i386 ptrace sys_ptrace compat_sys_ptrace
-27 i386 alarm sys_alarm
-28 i386 oldfstat sys_fstat
-29 i386 pause sys_pause
-30 i386 utime sys_utime compat_sys_utime
-31 i386 stty
-32 i386 gtty
-33 i386 access sys_access
-34 i386 nice sys_nice
-35 i386 ftime
-36 i386 sync sys_sync
-37 i386 kill sys_kill
-38 i386 rename sys_rename
-39 i386 mkdir sys_mkdir
-40 i386 rmdir sys_rmdir
-41 i386 dup sys_dup
-42 i386 pipe sys_pipe
-43 i386 times sys_times compat_sys_times
-44 i386 prof
-45 i386 brk sys_brk
-46 i386 setgid sys_setgid16
-47 i386 getgid sys_getgid16
-48 i386 signal sys_signal
-49 i386 geteuid sys_geteuid16
-50 i386 getegid sys_getegid16
-51 i386 acct sys_acct
-52 i386 umount2 sys_umount
-53 i386 lock
-54 i386 ioctl sys_ioctl compat_sys_ioctl
-55 i386 fcntl sys_fcntl compat_sys_fcntl64
-56 i386 mpx
-57 i386 setpgid sys_setpgid
-58 i386 ulimit
-59 i386 oldolduname sys_olduname
-60 i386 umask sys_umask
-61 i386 chroot sys_chroot
-62 i386 ustat sys_ustat compat_sys_ustat
-63 i386 dup2 sys_dup2
-64 i386 getppid sys_getppid
-65 i386 getpgrp sys_getpgrp
-66 i386 setsid sys_setsid
-67 i386 sigaction sys_sigaction compat_sys_sigaction
-68 i386 sgetmask sys_sgetmask
-69 i386 ssetmask sys_ssetmask
-70 i386 setreuid sys_setreuid16
-71 i386 setregid sys_setregid16
-72 i386 sigsuspend sys_sigsuspend sys_sigsuspend
-73 i386 sigpending sys_sigpending compat_sys_sigpending
-74 i386 sethostname sys_sethostname
-75 i386 setrlimit sys_setrlimit compat_sys_setrlimit
-76 i386 getrlimit sys_old_getrlimit compat_sys_old_getrlimit
-77 i386 getrusage sys_getrusage compat_sys_getrusage
-78 i386 gettimeofday sys_gettimeofday compat_sys_gettimeofday
-79 i386 settimeofday sys_settimeofday compat_sys_settimeofday
-80 i386 getgroups sys_getgroups16
-81 i386 setgroups sys_setgroups16
-82 i386 select sys_old_select compat_sys_old_select
-83 i386 symlink sys_symlink
-84 i386 oldlstat sys_lstat
-85 i386 readlink sys_readlink
-86 i386 uselib sys_uselib
-87 i386 swapon sys_swapon
-88 i386 reboot sys_reboot
-89 i386 readdir sys_old_readdir compat_sys_old_readdir
-90 i386 mmap sys_old_mmap sys32_mmap
-91 i386 munmap sys_munmap
-92 i386 truncate sys_truncate compat_sys_truncate
-93 i386 ftruncate sys_ftruncate compat_sys_ftruncate
-94 i386 fchmod sys_fchmod
-95 i386 fchown sys_fchown16
-96 i386 getpriority sys_getpriority
-97 i386 setpriority sys_setpriority
-98 i386 profil
-99 i386 statfs sys_statfs compat_sys_statfs
-100 i386 fstatfs sys_fstatfs compat_sys_fstatfs
-101 i386 ioperm sys_ioperm
-102 i386 socketcall sys_socketcall compat_sys_socketcall
-103 i386 syslog sys_syslog
-104 i386 setitimer sys_setitimer compat_sys_setitimer
-105 i386 getitimer sys_getitimer compat_sys_getitimer
-106 i386 stat sys_newstat compat_sys_newstat
-107 i386 lstat sys_newlstat compat_sys_newlstat
-108 i386 fstat sys_newfstat compat_sys_newfstat
-109 i386 olduname sys_uname
-110 i386 iopl sys_iopl
-111 i386 vhangup sys_vhangup
-112 i386 idle
-113 i386 vm86old sys_vm86old sys_ni_syscall
-114 i386 wait4 sys_wait4 compat_sys_wait4
-115 i386 swapoff sys_swapoff
-116 i386 sysinfo sys_sysinfo compat_sys_sysinfo
-117 i386 ipc sys_ipc compat_sys_ipc
-118 i386 fsync sys_fsync
-119 i386 sigreturn sys_sigreturn stub32_sigreturn
-120 i386 clone sys_clone stub32_clone
-121 i386 setdomainname sys_setdomainname
-122 i386 uname sys_newuname
-123 i386 modify_ldt sys_modify_ldt
-124 i386 adjtimex sys_adjtimex compat_sys_adjtimex
-125 i386 mprotect sys_mprotect
-126 i386 sigprocmask sys_sigprocmask compat_sys_sigprocmask
-127 i386 create_module
-128 i386 init_module sys_init_module
-129 i386 delete_module sys_delete_module
-130 i386 get_kernel_syms
-131 i386 quotactl sys_quotactl sys32_quotactl
-132 i386 getpgid sys_getpgid
-133 i386 fchdir sys_fchdir
-134 i386 bdflush sys_bdflush
-135 i386 sysfs sys_sysfs
-136 i386 personality sys_personality
-137 i386 afs_syscall
-138 i386 setfsuid sys_setfsuid16
-139 i386 setfsgid sys_setfsgid16
-140 i386 _llseek sys_llseek
-141 i386 getdents sys_getdents compat_sys_getdents
-142 i386 _newselect sys_select compat_sys_select
-143 i386 flock sys_flock
-144 i386 msync sys_msync
-145 i386 readv sys_readv compat_sys_readv
-146 i386 writev sys_writev compat_sys_writev
-147 i386 getsid sys_getsid
-148 i386 fdatasync sys_fdatasync
-149 i386 _sysctl sys_sysctl compat_sys_sysctl
-150 i386 mlock sys_mlock
-151 i386 munlock sys_munlock
-152 i386 mlockall sys_mlockall
-153 i386 munlockall sys_munlockall
-154 i386 sched_setparam sys_sched_setparam
-155 i386 sched_getparam sys_sched_getparam
-156 i386 sched_setscheduler sys_sched_setscheduler
-157 i386 sched_getscheduler sys_sched_getscheduler
-158 i386 sched_yield sys_sched_yield
-159 i386 sched_get_priority_max sys_sched_get_priority_max
-160 i386 sched_get_priority_min sys_sched_get_priority_min
-161 i386 sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval
-162 i386 nanosleep sys_nanosleep compat_sys_nanosleep
-163 i386 mremap sys_mremap
-164 i386 setresuid sys_setresuid16
-165 i386 getresuid sys_getresuid16
-166 i386 vm86 sys_vm86 sys_ni_syscall
-167 i386 query_module
-168 i386 poll sys_poll
-169 i386 nfsservctl
-170 i386 setresgid sys_setresgid16
-171 i386 getresgid sys_getresgid16
-172 i386 prctl sys_prctl
-173 i386 rt_sigreturn sys_rt_sigreturn stub32_rt_sigreturn
-174 i386 rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction
-175 i386 rt_sigprocmask sys_rt_sigprocmask
-176 i386 rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending
-177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait
-178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
-179 i386 rt_sigsuspend sys_rt_sigsuspend
-180 i386 pread64 sys_pread64 sys32_pread
-181 i386 pwrite64 sys_pwrite64 sys32_pwrite
-182 i386 chown sys_chown16
-183 i386 getcwd sys_getcwd
-184 i386 capget sys_capget
-185 i386 capset sys_capset
-186 i386 sigaltstack sys_sigaltstack compat_sys_sigaltstack
-187 i386 sendfile sys_sendfile compat_sys_sendfile
-188 i386 getpmsg
-189 i386 putpmsg
-190 i386 vfork sys_vfork stub32_vfork
-191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit
-192 i386 mmap2 sys_mmap_pgoff
-193 i386 truncate64 sys_truncate64 sys32_truncate64
-194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64
-195 i386 stat64 sys_stat64 sys32_stat64
-196 i386 lstat64 sys_lstat64 sys32_lstat64
-197 i386 fstat64 sys_fstat64 sys32_fstat64
-198 i386 lchown32 sys_lchown
-199 i386 getuid32 sys_getuid
-200 i386 getgid32 sys_getgid
-201 i386 geteuid32 sys_geteuid
-202 i386 getegid32 sys_getegid
-203 i386 setreuid32 sys_setreuid
-204 i386 setregid32 sys_setregid
-205 i386 getgroups32 sys_getgroups
-206 i386 setgroups32 sys_setgroups
-207 i386 fchown32 sys_fchown
-208 i386 setresuid32 sys_setresuid
-209 i386 getresuid32 sys_getresuid
-210 i386 setresgid32 sys_setresgid
-211 i386 getresgid32 sys_getresgid
-212 i386 chown32 sys_chown
-213 i386 setuid32 sys_setuid
-214 i386 setgid32 sys_setgid
-215 i386 setfsuid32 sys_setfsuid
-216 i386 setfsgid32 sys_setfsgid
-217 i386 pivot_root sys_pivot_root
-218 i386 mincore sys_mincore
-219 i386 madvise sys_madvise
-220 i386 getdents64 sys_getdents64 compat_sys_getdents64
-221 i386 fcntl64 sys_fcntl64 compat_sys_fcntl64
-# 222 is unused
-# 223 is unused
-224 i386 gettid sys_gettid
-225 i386 readahead sys_readahead sys32_readahead
-226 i386 setxattr sys_setxattr
-227 i386 lsetxattr sys_lsetxattr
-228 i386 fsetxattr sys_fsetxattr
-229 i386 getxattr sys_getxattr
-230 i386 lgetxattr sys_lgetxattr
-231 i386 fgetxattr sys_fgetxattr
-232 i386 listxattr sys_listxattr
-233 i386 llistxattr sys_llistxattr
-234 i386 flistxattr sys_flistxattr
-235 i386 removexattr sys_removexattr
-236 i386 lremovexattr sys_lremovexattr
-237 i386 fremovexattr sys_fremovexattr
-238 i386 tkill sys_tkill
-239 i386 sendfile64 sys_sendfile64
-240 i386 futex sys_futex compat_sys_futex
-241 i386 sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity
-242 i386 sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity
-243 i386 set_thread_area sys_set_thread_area
-244 i386 get_thread_area sys_get_thread_area
-245 i386 io_setup sys_io_setup compat_sys_io_setup
-246 i386 io_destroy sys_io_destroy
-247 i386 io_getevents sys_io_getevents compat_sys_io_getevents
-248 i386 io_submit sys_io_submit compat_sys_io_submit
-249 i386 io_cancel sys_io_cancel
-250 i386 fadvise64 sys_fadvise64 sys32_fadvise64
-# 251 is available for reuse (was briefly sys_set_zone_reclaim)
-252 i386 exit_group sys_exit_group
-253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie
-254 i386 epoll_create sys_epoll_create
-255 i386 epoll_ctl sys_epoll_ctl
-256 i386 epoll_wait sys_epoll_wait
-257 i386 remap_file_pages sys_remap_file_pages
-258 i386 set_tid_address sys_set_tid_address
-259 i386 timer_create sys_timer_create compat_sys_timer_create
-260 i386 timer_settime sys_timer_settime compat_sys_timer_settime
-261 i386 timer_gettime sys_timer_gettime compat_sys_timer_gettime
-262 i386 timer_getoverrun sys_timer_getoverrun
-263 i386 timer_delete sys_timer_delete
-264 i386 clock_settime sys_clock_settime compat_sys_clock_settime
-265 i386 clock_gettime sys_clock_gettime compat_sys_clock_gettime
-266 i386 clock_getres sys_clock_getres compat_sys_clock_getres
-267 i386 clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep
-268 i386 statfs64 sys_statfs64 compat_sys_statfs64
-269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
-270 i386 tgkill sys_tgkill
-271 i386 utimes sys_utimes compat_sys_utimes
-272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64
-273 i386 vserver
-274 i386 mbind sys_mbind
-275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
-276 i386 set_mempolicy sys_set_mempolicy
-277 i386 mq_open sys_mq_open compat_sys_mq_open
-278 i386 mq_unlink sys_mq_unlink
-279 i386 mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend
-280 i386 mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive
-281 i386 mq_notify sys_mq_notify compat_sys_mq_notify
-282 i386 mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr
-283 i386 kexec_load sys_kexec_load compat_sys_kexec_load
-284 i386 waitid sys_waitid compat_sys_waitid
-# 285 sys_setaltroot
-286 i386 add_key sys_add_key
-287 i386 request_key sys_request_key
-288 i386 keyctl sys_keyctl
-289 i386 ioprio_set sys_ioprio_set
-290 i386 ioprio_get sys_ioprio_get
-291 i386 inotify_init sys_inotify_init
-292 i386 inotify_add_watch sys_inotify_add_watch
-293 i386 inotify_rm_watch sys_inotify_rm_watch
-294 i386 migrate_pages sys_migrate_pages
-295 i386 openat sys_openat compat_sys_openat
-296 i386 mkdirat sys_mkdirat
-297 i386 mknodat sys_mknodat
-298 i386 fchownat sys_fchownat
-299 i386 futimesat sys_futimesat compat_sys_futimesat
-300 i386 fstatat64 sys_fstatat64 sys32_fstatat
-301 i386 unlinkat sys_unlinkat
-302 i386 renameat sys_renameat
-303 i386 linkat sys_linkat
-304 i386 symlinkat sys_symlinkat
-305 i386 readlinkat sys_readlinkat
-306 i386 fchmodat sys_fchmodat
-307 i386 faccessat sys_faccessat
-308 i386 pselect6 sys_pselect6 compat_sys_pselect6
-309 i386 ppoll sys_ppoll compat_sys_ppoll
-310 i386 unshare sys_unshare
-311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list
-312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list
-313 i386 splice sys_splice
-314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range
-315 i386 tee sys_tee
-316 i386 vmsplice sys_vmsplice compat_sys_vmsplice
-317 i386 move_pages sys_move_pages compat_sys_move_pages
-318 i386 getcpu sys_getcpu
-319 i386 epoll_pwait sys_epoll_pwait
-320 i386 utimensat sys_utimensat compat_sys_utimensat
-321 i386 signalfd sys_signalfd compat_sys_signalfd
-322 i386 timerfd_create sys_timerfd_create
-323 i386 eventfd sys_eventfd
-324 i386 fallocate sys_fallocate sys32_fallocate
-325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime
-326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime
-327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4
-328 i386 eventfd2 sys_eventfd2
-329 i386 epoll_create1 sys_epoll_create1
-330 i386 dup3 sys_dup3
-331 i386 pipe2 sys_pipe2
-332 i386 inotify_init1 sys_inotify_init1
-333 i386 preadv sys_preadv compat_sys_preadv
-334 i386 pwritev sys_pwritev compat_sys_pwritev
-335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
-336 i386 perf_event_open sys_perf_event_open
-337 i386 recvmmsg sys_recvmmsg compat_sys_recvmmsg
-338 i386 fanotify_init sys_fanotify_init
-339 i386 fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark
-340 i386 prlimit64 sys_prlimit64
-341 i386 name_to_handle_at sys_name_to_handle_at
-342 i386 open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at
-343 i386 clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime
-344 i386 syncfs sys_syncfs
-345 i386 sendmmsg sys_sendmmsg compat_sys_sendmmsg
-346 i386 setns sys_setns
-347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv
-348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
-349 i386 kcmp sys_kcmp
-350 i386 finit_module sys_finit_module
-351 i386 sched_setattr sys_sched_setattr
-352 i386 sched_getattr sys_sched_getattr
-353 i386 renameat2 sys_renameat2
-354 i386 seccomp sys_seccomp
-355 i386 getrandom sys_getrandom
-356 i386 memfd_create sys_memfd_create
-357 i386 bpf sys_bpf
-358 i386 execveat sys_execveat stub32_execveat
+++ /dev/null
-#
-# 64-bit system call numbers and entry vectors
-#
-# The format is:
-# <number> <abi> <name> <entry point>
-#
-# The abi is "common", "64" or "x32" for this file.
-#
-0 common read sys_read
-1 common write sys_write
-2 common open sys_open
-3 common close sys_close
-4 common stat sys_newstat
-5 common fstat sys_newfstat
-6 common lstat sys_newlstat
-7 common poll sys_poll
-8 common lseek sys_lseek
-9 common mmap sys_mmap
-10 common mprotect sys_mprotect
-11 common munmap sys_munmap
-12 common brk sys_brk
-13 64 rt_sigaction sys_rt_sigaction
-14 common rt_sigprocmask sys_rt_sigprocmask
-15 64 rt_sigreturn stub_rt_sigreturn
-16 64 ioctl sys_ioctl
-17 common pread64 sys_pread64
-18 common pwrite64 sys_pwrite64
-19 64 readv sys_readv
-20 64 writev sys_writev
-21 common access sys_access
-22 common pipe sys_pipe
-23 common select sys_select
-24 common sched_yield sys_sched_yield
-25 common mremap sys_mremap
-26 common msync sys_msync
-27 common mincore sys_mincore
-28 common madvise sys_madvise
-29 common shmget sys_shmget
-30 common shmat sys_shmat
-31 common shmctl sys_shmctl
-32 common dup sys_dup
-33 common dup2 sys_dup2
-34 common pause sys_pause
-35 common nanosleep sys_nanosleep
-36 common getitimer sys_getitimer
-37 common alarm sys_alarm
-38 common setitimer sys_setitimer
-39 common getpid sys_getpid
-40 common sendfile sys_sendfile64
-41 common socket sys_socket
-42 common connect sys_connect
-43 common accept sys_accept
-44 common sendto sys_sendto
-45 64 recvfrom sys_recvfrom
-46 64 sendmsg sys_sendmsg
-47 64 recvmsg sys_recvmsg
-48 common shutdown sys_shutdown
-49 common bind sys_bind
-50 common listen sys_listen
-51 common getsockname sys_getsockname
-52 common getpeername sys_getpeername
-53 common socketpair sys_socketpair
-54 64 setsockopt sys_setsockopt
-55 64 getsockopt sys_getsockopt
-56 common clone stub_clone
-57 common fork stub_fork
-58 common vfork stub_vfork
-59 64 execve stub_execve
-60 common exit sys_exit
-61 common wait4 sys_wait4
-62 common kill sys_kill
-63 common uname sys_newuname
-64 common semget sys_semget
-65 common semop sys_semop
-66 common semctl sys_semctl
-67 common shmdt sys_shmdt
-68 common msgget sys_msgget
-69 common msgsnd sys_msgsnd
-70 common msgrcv sys_msgrcv
-71 common msgctl sys_msgctl
-72 common fcntl sys_fcntl
-73 common flock sys_flock
-74 common fsync sys_fsync
-75 common fdatasync sys_fdatasync
-76 common truncate sys_truncate
-77 common ftruncate sys_ftruncate
-78 common getdents sys_getdents
-79 common getcwd sys_getcwd
-80 common chdir sys_chdir
-81 common fchdir sys_fchdir
-82 common rename sys_rename
-83 common mkdir sys_mkdir
-84 common rmdir sys_rmdir
-85 common creat sys_creat
-86 common link sys_link
-87 common unlink sys_unlink
-88 common symlink sys_symlink
-89 common readlink sys_readlink
-90 common chmod sys_chmod
-91 common fchmod sys_fchmod
-92 common chown sys_chown
-93 common fchown sys_fchown
-94 common lchown sys_lchown
-95 common umask sys_umask
-96 common gettimeofday sys_gettimeofday
-97 common getrlimit sys_getrlimit
-98 common getrusage sys_getrusage
-99 common sysinfo sys_sysinfo
-100 common times sys_times
-101 64 ptrace sys_ptrace
-102 common getuid sys_getuid
-103 common syslog sys_syslog
-104 common getgid sys_getgid
-105 common setuid sys_setuid
-106 common setgid sys_setgid
-107 common geteuid sys_geteuid
-108 common getegid sys_getegid
-109 common setpgid sys_setpgid
-110 common getppid sys_getppid
-111 common getpgrp sys_getpgrp
-112 common setsid sys_setsid
-113 common setreuid sys_setreuid
-114 common setregid sys_setregid
-115 common getgroups sys_getgroups
-116 common setgroups sys_setgroups
-117 common setresuid sys_setresuid
-118 common getresuid sys_getresuid
-119 common setresgid sys_setresgid
-120 common getresgid sys_getresgid
-121 common getpgid sys_getpgid
-122 common setfsuid sys_setfsuid
-123 common setfsgid sys_setfsgid
-124 common getsid sys_getsid
-125 common capget sys_capget
-126 common capset sys_capset
-127 64 rt_sigpending sys_rt_sigpending
-128 64 rt_sigtimedwait sys_rt_sigtimedwait
-129 64 rt_sigqueueinfo sys_rt_sigqueueinfo
-130 common rt_sigsuspend sys_rt_sigsuspend
-131 64 sigaltstack sys_sigaltstack
-132 common utime sys_utime
-133 common mknod sys_mknod
-134 64 uselib
-135 common personality sys_personality
-136 common ustat sys_ustat
-137 common statfs sys_statfs
-138 common fstatfs sys_fstatfs
-139 common sysfs sys_sysfs
-140 common getpriority sys_getpriority
-141 common setpriority sys_setpriority
-142 common sched_setparam sys_sched_setparam
-143 common sched_getparam sys_sched_getparam
-144 common sched_setscheduler sys_sched_setscheduler
-145 common sched_getscheduler sys_sched_getscheduler
-146 common sched_get_priority_max sys_sched_get_priority_max
-147 common sched_get_priority_min sys_sched_get_priority_min
-148 common sched_rr_get_interval sys_sched_rr_get_interval
-149 common mlock sys_mlock
-150 common munlock sys_munlock
-151 common mlockall sys_mlockall
-152 common munlockall sys_munlockall
-153 common vhangup sys_vhangup
-154 common modify_ldt sys_modify_ldt
-155 common pivot_root sys_pivot_root
-156 64 _sysctl sys_sysctl
-157 common prctl sys_prctl
-158 common arch_prctl sys_arch_prctl
-159 common adjtimex sys_adjtimex
-160 common setrlimit sys_setrlimit
-161 common chroot sys_chroot
-162 common sync sys_sync
-163 common acct sys_acct
-164 common settimeofday sys_settimeofday
-165 common mount sys_mount
-166 common umount2 sys_umount
-167 common swapon sys_swapon
-168 common swapoff sys_swapoff
-169 common reboot sys_reboot
-170 common sethostname sys_sethostname
-171 common setdomainname sys_setdomainname
-172 common iopl sys_iopl
-173 common ioperm sys_ioperm
-174 64 create_module
-175 common init_module sys_init_module
-176 common delete_module sys_delete_module
-177 64 get_kernel_syms
-178 64 query_module
-179 common quotactl sys_quotactl
-180 64 nfsservctl
-181 common getpmsg
-182 common putpmsg
-183 common afs_syscall
-184 common tuxcall
-185 common security
-186 common gettid sys_gettid
-187 common readahead sys_readahead
-188 common setxattr sys_setxattr
-189 common lsetxattr sys_lsetxattr
-190 common fsetxattr sys_fsetxattr
-191 common getxattr sys_getxattr
-192 common lgetxattr sys_lgetxattr
-193 common fgetxattr sys_fgetxattr
-194 common listxattr sys_listxattr
-195 common llistxattr sys_llistxattr
-196 common flistxattr sys_flistxattr
-197 common removexattr sys_removexattr
-198 common lremovexattr sys_lremovexattr
-199 common fremovexattr sys_fremovexattr
-200 common tkill sys_tkill
-201 common time sys_time
-202 common futex sys_futex
-203 common sched_setaffinity sys_sched_setaffinity
-204 common sched_getaffinity sys_sched_getaffinity
-205 64 set_thread_area
-206 64 io_setup sys_io_setup
-207 common io_destroy sys_io_destroy
-208 common io_getevents sys_io_getevents
-209 64 io_submit sys_io_submit
-210 common io_cancel sys_io_cancel
-211 64 get_thread_area
-212 common lookup_dcookie sys_lookup_dcookie
-213 common epoll_create sys_epoll_create
-214 64 epoll_ctl_old
-215 64 epoll_wait_old
-216 common remap_file_pages sys_remap_file_pages
-217 common getdents64 sys_getdents64
-218 common set_tid_address sys_set_tid_address
-219 common restart_syscall sys_restart_syscall
-220 common semtimedop sys_semtimedop
-221 common fadvise64 sys_fadvise64
-222 64 timer_create sys_timer_create
-223 common timer_settime sys_timer_settime
-224 common timer_gettime sys_timer_gettime
-225 common timer_getoverrun sys_timer_getoverrun
-226 common timer_delete sys_timer_delete
-227 common clock_settime sys_clock_settime
-228 common clock_gettime sys_clock_gettime
-229 common clock_getres sys_clock_getres
-230 common clock_nanosleep sys_clock_nanosleep
-231 common exit_group sys_exit_group
-232 common epoll_wait sys_epoll_wait
-233 common epoll_ctl sys_epoll_ctl
-234 common tgkill sys_tgkill
-235 common utimes sys_utimes
-236 64 vserver
-237 common mbind sys_mbind
-238 common set_mempolicy sys_set_mempolicy
-239 common get_mempolicy sys_get_mempolicy
-240 common mq_open sys_mq_open
-241 common mq_unlink sys_mq_unlink
-242 common mq_timedsend sys_mq_timedsend
-243 common mq_timedreceive sys_mq_timedreceive
-244 64 mq_notify sys_mq_notify
-245 common mq_getsetattr sys_mq_getsetattr
-246 64 kexec_load sys_kexec_load
-247 64 waitid sys_waitid
-248 common add_key sys_add_key
-249 common request_key sys_request_key
-250 common keyctl sys_keyctl
-251 common ioprio_set sys_ioprio_set
-252 common ioprio_get sys_ioprio_get
-253 common inotify_init sys_inotify_init
-254 common inotify_add_watch sys_inotify_add_watch
-255 common inotify_rm_watch sys_inotify_rm_watch
-256 common migrate_pages sys_migrate_pages
-257 common openat sys_openat
-258 common mkdirat sys_mkdirat
-259 common mknodat sys_mknodat
-260 common fchownat sys_fchownat
-261 common futimesat sys_futimesat
-262 common newfstatat sys_newfstatat
-263 common unlinkat sys_unlinkat
-264 common renameat sys_renameat
-265 common linkat sys_linkat
-266 common symlinkat sys_symlinkat
-267 common readlinkat sys_readlinkat
-268 common fchmodat sys_fchmodat
-269 common faccessat sys_faccessat
-270 common pselect6 sys_pselect6
-271 common ppoll sys_ppoll
-272 common unshare sys_unshare
-273 64 set_robust_list sys_set_robust_list
-274 64 get_robust_list sys_get_robust_list
-275 common splice sys_splice
-276 common tee sys_tee
-277 common sync_file_range sys_sync_file_range
-278 64 vmsplice sys_vmsplice
-279 64 move_pages sys_move_pages
-280 common utimensat sys_utimensat
-281 common epoll_pwait sys_epoll_pwait
-282 common signalfd sys_signalfd
-283 common timerfd_create sys_timerfd_create
-284 common eventfd sys_eventfd
-285 common fallocate sys_fallocate
-286 common timerfd_settime sys_timerfd_settime
-287 common timerfd_gettime sys_timerfd_gettime
-288 common accept4 sys_accept4
-289 common signalfd4 sys_signalfd4
-290 common eventfd2 sys_eventfd2
-291 common epoll_create1 sys_epoll_create1
-292 common dup3 sys_dup3
-293 common pipe2 sys_pipe2
-294 common inotify_init1 sys_inotify_init1
-295 64 preadv sys_preadv
-296 64 pwritev sys_pwritev
-297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo
-298 common perf_event_open sys_perf_event_open
-299 64 recvmmsg sys_recvmmsg
-300 common fanotify_init sys_fanotify_init
-301 common fanotify_mark sys_fanotify_mark
-302 common prlimit64 sys_prlimit64
-303 common name_to_handle_at sys_name_to_handle_at
-304 common open_by_handle_at sys_open_by_handle_at
-305 common clock_adjtime sys_clock_adjtime
-306 common syncfs sys_syncfs
-307 64 sendmmsg sys_sendmmsg
-308 common setns sys_setns
-309 common getcpu sys_getcpu
-310 64 process_vm_readv sys_process_vm_readv
-311 64 process_vm_writev sys_process_vm_writev
-312 common kcmp sys_kcmp
-313 common finit_module sys_finit_module
-314 common sched_setattr sys_sched_setattr
-315 common sched_getattr sys_sched_getattr
-316 common renameat2 sys_renameat2
-317 common seccomp sys_seccomp
-318 common getrandom sys_getrandom
-319 common memfd_create sys_memfd_create
-320 common kexec_file_load sys_kexec_file_load
-321 common bpf sys_bpf
-322 64 execveat stub_execveat
-
-#
-# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation.
-#
-512 x32 rt_sigaction compat_sys_rt_sigaction
-513 x32 rt_sigreturn stub_x32_rt_sigreturn
-514 x32 ioctl compat_sys_ioctl
-515 x32 readv compat_sys_readv
-516 x32 writev compat_sys_writev
-517 x32 recvfrom compat_sys_recvfrom
-518 x32 sendmsg compat_sys_sendmsg
-519 x32 recvmsg compat_sys_recvmsg
-520 x32 execve stub_x32_execve
-521 x32 ptrace compat_sys_ptrace
-522 x32 rt_sigpending compat_sys_rt_sigpending
-523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait
-524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo
-525 x32 sigaltstack compat_sys_sigaltstack
-526 x32 timer_create compat_sys_timer_create
-527 x32 mq_notify compat_sys_mq_notify
-528 x32 kexec_load compat_sys_kexec_load
-529 x32 waitid compat_sys_waitid
-530 x32 set_robust_list compat_sys_set_robust_list
-531 x32 get_robust_list compat_sys_get_robust_list
-532 x32 vmsplice compat_sys_vmsplice
-533 x32 move_pages compat_sys_move_pages
-534 x32 preadv compat_sys_preadv64
-535 x32 pwritev compat_sys_pwritev64
-536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
-537 x32 recvmmsg compat_sys_recvmmsg
-538 x32 sendmmsg compat_sys_sendmmsg
-539 x32 process_vm_readv compat_sys_process_vm_readv
-540 x32 process_vm_writev compat_sys_process_vm_writev
-541 x32 setsockopt compat_sys_setsockopt
-542 x32 getsockopt compat_sys_getsockopt
-543 x32 io_setup compat_sys_io_setup
-544 x32 io_submit compat_sys_io_submit
-545 x32 execveat stub_x32_execveat
+++ /dev/null
-#!/bin/sh
-
-in="$1"
-out="$2"
-my_abis=`echo "($3)" | tr ',' '|'`
-prefix="$4"
-offset="$5"
-
-fileguard=_ASM_X86_`basename "$out" | sed \
- -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
- -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'`
-grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
- echo "#ifndef ${fileguard}"
- echo "#define ${fileguard} 1"
- echo ""
-
- while read nr abi name entry ; do
- if [ -z "$offset" ]; then
- echo "#define __NR_${prefix}${name} $nr"
- else
- echo "#define __NR_${prefix}${name} ($offset + $nr)"
- fi
- done
-
- echo ""
- echo "#endif /* ${fileguard} */"
-) > "$out"
+++ /dev/null
-#!/bin/sh
-
-in="$1"
-out="$2"
-
-grep '^[0-9]' "$in" | sort -n | (
- while read nr abi name entry compat; do
- abi=`echo "$abi" | tr '[a-z]' '[A-Z]'`
- if [ -n "$compat" ]; then
- echo "__SYSCALL_${abi}($nr, $entry, $compat)"
- elif [ -n "$entry" ]; then
- echo "__SYSCALL_${abi}($nr, $entry, $entry)"
- fi
- done
-) > "$out"
obj-y += syscalls_64.o vdso/
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \
../lib/rwsem.o
endif
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
#define read_barrier_depends() do { } while (0)
#define smp_read_barrier_depends() do { } while (0)
+++ /dev/null
-vdso.lds
-vdsox32.lds
-vdso32-syscall-syms.lds
-vdso32-sysenter-syms.lds
-vdso32-int80-syms.lds
-vdso-image-*.c
-vdso2c
+++ /dev/null
-#
-# Building vDSO images for x86.
-#
-
-KBUILD_CFLAGS += $(DISABLE_LTO)
-KASAN_SANITIZE := n
-
-VDSO64-$(CONFIG_X86_64) := y
-VDSOX32-$(CONFIG_X86_X32_ABI) := y
-VDSO32-$(CONFIG_X86_32) := y
-VDSO32-$(CONFIG_COMPAT) := y
-
-# files to link into the vdso
-vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
-
-# files to link into kernel
-obj-y += vma.o
-
-# vDSO images to build
-vdso_img-$(VDSO64-y) += 64
-vdso_img-$(VDSOX32-y) += x32
-vdso_img-$(VDSO32-y) += 32-int80
-vdso_img-$(CONFIG_COMPAT) += 32-syscall
-vdso_img-$(VDSO32-y) += 32-sysenter
-
-obj-$(VDSO32-y) += vdso32-setup.o
-
-vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
-
-$(obj)/vdso.o: $(obj)/vdso.so
-
-targets += vdso.lds $(vobjs-y)
-
-# Build the vDSO image C files and link them in.
-vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
-vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c)
-vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
-obj-y += $(vdso_img_objs)
-targets += $(vdso_img_cfiles)
-targets += $(vdso_img_sodbg)
-.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c) \
- $(vdso_img-y:%=$(obj)/vdso%.so)
-
-export CPPFLAGS_vdso.lds += -P -C
-
-VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
- -Wl,--no-undefined \
- -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
- $(DISABLE_LTO)
-
-$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
- $(call if_changed,vdso)
-
-HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi
-hostprogs-y += vdso2c
-
-quiet_cmd_vdso2c = VDSO2C $@
-define cmd_vdso2c
- $(obj)/vdso2c $< $(<:%.dbg=%) $@
-endef
-
-$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
- $(call if_changed,vdso2c)
-
-#
-# Don't omit frame pointers for ease of userspace debugging, but do
-# optimize sibling calls.
-#
-CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
- $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
- -fno-omit-frame-pointer -foptimize-sibling-calls \
- -DDISABLE_BRANCH_PROFILING
-
-$(vobjs): KBUILD_CFLAGS += $(CFL)
-
-#
-# vDSO code runs in userspace and -pg doesn't help with profiling anyway.
-#
-CFLAGS_REMOVE_vdso-note.o = -pg
-CFLAGS_REMOVE_vclock_gettime.o = -pg
-CFLAGS_REMOVE_vgetcpu.o = -pg
-CFLAGS_REMOVE_vvar.o = -pg
-
-#
-# X32 processes use x32 vDSO to access 64bit kernel data.
-#
-# Build x32 vDSO image:
-# 1. Compile x32 vDSO as 64bit.
-# 2. Convert object files to x32.
-# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes
-# so that it can reach 64bit address space with 64bit pointers.
-#
-
-CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
- -Wl,-soname=linux-vdso.so.1 \
- -Wl,-z,max-page-size=4096 \
- -Wl,-z,common-page-size=4096
-
-# 64-bit objects to re-brand as x32
-vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y))
-
-# x32-rebranded versions
-vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o)
-
-# same thing, but in the output directory
-vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
-
-# Convert 64bit object file to x32 for x32 vDSO.
-quiet_cmd_x32 = X32 $@
- cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@
-
-$(obj)/%-x32.o: $(obj)/%.o FORCE
- $(call if_changed,x32)
-
-targets += vdsox32.lds $(vobjx32s-y)
-
-$(obj)/%.so: OBJCOPYFLAGS := -S
-$(obj)/%.so: $(obj)/%.so.dbg
- $(call if_changed,objcopy)
-
-$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
- $(call if_changed,vdso)
-
-#
-# Build multiple 32-bit vDSO images to choose from at boot time.
-#
-vdso32.so-$(VDSO32-y) += int80
-vdso32.so-$(CONFIG_COMPAT) += syscall
-vdso32.so-$(VDSO32-y) += sysenter
-
-vdso32-images = $(vdso32.so-y:%=vdso32-%.so)
-
-CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
-
-# This makes sure the $(obj) subdirectory exists even though vdso32/
-# is not a kbuild sub-make subdirectory.
-override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
-
-targets += vdso32/vdso32.lds
-targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o)
-targets += vdso32/vclock_gettime.o
-
-$(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%)
-
-KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
-$(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
-$(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32
-
-KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
-KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
-KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
-KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
-KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
-KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
-KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
-KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
-KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
-
-$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
- $(obj)/vdso32/vdso32.lds \
- $(obj)/vdso32/vclock_gettime.o \
- $(obj)/vdso32/note.o \
- $(obj)/vdso32/%.o
- $(call if_changed,vdso)
-
-#
-# The DSO images are built using a special linker script.
-#
-quiet_cmd_vdso = VDSO $@
- cmd_vdso = $(CC) -nostdlib -o $@ \
- $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
- -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
- sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
-
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
- $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS)
-GCOV_PROFILE := n
-
-#
-# Install the unstripped copies of vdso*.so. If our toolchain supports
-# build-id, install .build-id links as well.
-#
-quiet_cmd_vdso_install = INSTALL $(@:install_%=%)
-define cmd_vdso_install
- cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \
- if readelf -n $< |grep -q 'Build ID'; then \
- buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \
- first=`echo $$buildid | cut -b-2`; \
- last=`echo $$buildid | cut -b3-`; \
- mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \
- ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \
- fi
-endef
-
-vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%)
-
-$(MODLIB)/vdso: FORCE
- @mkdir -p $(MODLIB)/vdso
-
-$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE
- $(call cmd,vdso_install)
-
-PHONY += vdso_install $(vdso_img_insttargets)
-vdso_install: $(vdso_img_insttargets) FORCE
-
-clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* vdso-image-*.c vdsox32.so*
+++ /dev/null
-#!/bin/sh
-nm="$1"
-file="$2"
-$nm "$file" | grep '^ *U' > /dev/null 2>&1
-if [ $? -eq 1 ]; then
- exit 0
-else
- echo "$file: undefined symbols found" >&2
- exit 1
-fi
+++ /dev/null
-/*
- * Copyright 2006 Andi Kleen, SUSE Labs.
- * Subject to the GNU Public License, v.2
- *
- * Fast user context implementation of clock_gettime, gettimeofday, and time.
- *
- * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
- * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
- *
- * The code should have no internal unresolved relocations.
- * Check with readelf after changing.
- */
-
-#include <uapi/linux/time.h>
-#include <asm/vgtod.h>
-#include <asm/hpet.h>
-#include <asm/vvar.h>
-#include <asm/unistd.h>
-#include <asm/msr.h>
-#include <linux/math64.h>
-#include <linux/time.h>
-
-#define gtod (&VVAR(vsyscall_gtod_data))
-
-extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts);
-extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
-extern time_t __vdso_time(time_t *t);
-
-#ifdef CONFIG_HPET_TIMER
-extern u8 hpet_page
- __attribute__((visibility("hidden")));
-
-static notrace cycle_t vread_hpet(void)
-{
- return *(const volatile u32 *)(&hpet_page + HPET_COUNTER);
-}
-#endif
-
-#ifndef BUILD_VDSO32
-
-#include <linux/kernel.h>
-#include <asm/vsyscall.h>
-#include <asm/fixmap.h>
-#include <asm/pvclock.h>
-
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
-{
- long ret;
- asm("syscall" : "=a" (ret) :
- "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
- return ret;
-}
-
-notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
-{
- long ret;
-
- asm("syscall" : "=a" (ret) :
- "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
- return ret;
-}
-
-#ifdef CONFIG_PARAVIRT_CLOCK
-
-static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
-{
- const struct pvclock_vsyscall_time_info *pvti_base;
- int idx = cpu / (PAGE_SIZE/PVTI_SIZE);
- int offset = cpu % (PAGE_SIZE/PVTI_SIZE);
-
- BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END);
-
- pvti_base = (struct pvclock_vsyscall_time_info *)
- __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx);
-
- return &pvti_base[offset];
-}
-
-static notrace cycle_t vread_pvclock(int *mode)
-{
- const struct pvclock_vsyscall_time_info *pvti;
- cycle_t ret;
- u64 last;
- u32 version;
- u8 flags;
- unsigned cpu, cpu1;
-
-
- /*
- * Note: hypervisor must guarantee that:
- * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
- * 2. that per-CPU pvclock time info is updated if the
- * underlying CPU changes.
- * 3. that version is increased whenever underlying CPU
- * changes.
- *
- */
- do {
- cpu = __getcpu() & VGETCPU_CPU_MASK;
- /* TODO: We can put vcpu id into higher bits of pvti.version.
- * This will save a couple of cycles by getting rid of
- * __getcpu() calls (Gleb).
- */
-
- pvti = get_pvti(cpu);
-
- version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
-
- /*
- * Test we're still on the cpu as well as the version.
- * We could have been migrated just after the first
- * vgetcpu but before fetching the version, so we
- * wouldn't notice a version change.
- */
- cpu1 = __getcpu() & VGETCPU_CPU_MASK;
- } while (unlikely(cpu != cpu1 ||
- (pvti->pvti.version & 1) ||
- pvti->pvti.version != version));
-
- if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
- *mode = VCLOCK_NONE;
-
- /* refer to tsc.c read_tsc() comment for rationale */
- last = gtod->cycle_last;
-
- if (likely(ret >= last))
- return ret;
-
- return last;
-}
-#endif
-
-#else
-
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
-{
- long ret;
-
- asm(
- "mov %%ebx, %%edx \n"
- "mov %2, %%ebx \n"
- "call __kernel_vsyscall \n"
- "mov %%edx, %%ebx \n"
- : "=a" (ret)
- : "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
- : "memory", "edx");
- return ret;
-}
-
-notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
-{
- long ret;
-
- asm(
- "mov %%ebx, %%edx \n"
- "mov %2, %%ebx \n"
- "call __kernel_vsyscall \n"
- "mov %%edx, %%ebx \n"
- : "=a" (ret)
- : "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
- : "memory", "edx");
- return ret;
-}
-
-#ifdef CONFIG_PARAVIRT_CLOCK
-
-static notrace cycle_t vread_pvclock(int *mode)
-{
- *mode = VCLOCK_NONE;
- return 0;
-}
-#endif
-
-#endif
-
-notrace static cycle_t vread_tsc(void)
-{
- cycle_t ret;
- u64 last;
-
- /*
- * Empirically, a fence (of type that depends on the CPU)
- * before rdtsc is enough to ensure that rdtsc is ordered
- * with respect to loads. The various CPU manuals are unclear
- * as to whether rdtsc can be reordered with later loads,
- * but no one has ever seen it happen.
- */
- rdtsc_barrier();
- ret = (cycle_t)__native_read_tsc();
-
- last = gtod->cycle_last;
-
- if (likely(ret >= last))
- return ret;
-
- /*
- * GCC likes to generate cmov here, but this branch is extremely
- * predictable (it's just a funciton of time and the likely is
- * very likely) and there's a data dependence, so force GCC
- * to generate a branch instead. I don't barrier() because
- * we don't actually need a barrier, and if this function
- * ever gets inlined it will generate worse code.
- */
- asm volatile ("");
- return last;
-}
-
-notrace static inline u64 vgetsns(int *mode)
-{
- u64 v;
- cycles_t cycles;
-
- if (gtod->vclock_mode == VCLOCK_TSC)
- cycles = vread_tsc();
-#ifdef CONFIG_HPET_TIMER
- else if (gtod->vclock_mode == VCLOCK_HPET)
- cycles = vread_hpet();
-#endif
-#ifdef CONFIG_PARAVIRT_CLOCK
- else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
- cycles = vread_pvclock(mode);
-#endif
- else
- return 0;
- v = (cycles - gtod->cycle_last) & gtod->mask;
- return v * gtod->mult;
-}
-
-/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
-notrace static int __always_inline do_realtime(struct timespec *ts)
-{
- unsigned long seq;
- u64 ns;
- int mode;
-
- do {
- seq = gtod_read_begin(gtod);
- mode = gtod->vclock_mode;
- ts->tv_sec = gtod->wall_time_sec;
- ns = gtod->wall_time_snsec;
- ns += vgetsns(&mode);
- ns >>= gtod->shift;
- } while (unlikely(gtod_read_retry(gtod, seq)));
-
- ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
- ts->tv_nsec = ns;
-
- return mode;
-}
-
-notrace static int __always_inline do_monotonic(struct timespec *ts)
-{
- unsigned long seq;
- u64 ns;
- int mode;
-
- do {
- seq = gtod_read_begin(gtod);
- mode = gtod->vclock_mode;
- ts->tv_sec = gtod->monotonic_time_sec;
- ns = gtod->monotonic_time_snsec;
- ns += vgetsns(&mode);
- ns >>= gtod->shift;
- } while (unlikely(gtod_read_retry(gtod, seq)));
-
- ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
- ts->tv_nsec = ns;
-
- return mode;
-}
-
-notrace static void do_realtime_coarse(struct timespec *ts)
-{
- unsigned long seq;
- do {
- seq = gtod_read_begin(gtod);
- ts->tv_sec = gtod->wall_time_coarse_sec;
- ts->tv_nsec = gtod->wall_time_coarse_nsec;
- } while (unlikely(gtod_read_retry(gtod, seq)));
-}
-
-notrace static void do_monotonic_coarse(struct timespec *ts)
-{
- unsigned long seq;
- do {
- seq = gtod_read_begin(gtod);
- ts->tv_sec = gtod->monotonic_time_coarse_sec;
- ts->tv_nsec = gtod->monotonic_time_coarse_nsec;
- } while (unlikely(gtod_read_retry(gtod, seq)));
-}
-
-notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
-{
- switch (clock) {
- case CLOCK_REALTIME:
- if (do_realtime(ts) == VCLOCK_NONE)
- goto fallback;
- break;
- case CLOCK_MONOTONIC:
- if (do_monotonic(ts) == VCLOCK_NONE)
- goto fallback;
- break;
- case CLOCK_REALTIME_COARSE:
- do_realtime_coarse(ts);
- break;
- case CLOCK_MONOTONIC_COARSE:
- do_monotonic_coarse(ts);
- break;
- default:
- goto fallback;
- }
-
- return 0;
-fallback:
- return vdso_fallback_gettime(clock, ts);
-}
-int clock_gettime(clockid_t, struct timespec *)
- __attribute__((weak, alias("__vdso_clock_gettime")));
-
-notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
-{
- if (likely(tv != NULL)) {
- if (unlikely(do_realtime((struct timespec *)tv) == VCLOCK_NONE))
- return vdso_fallback_gtod(tv, tz);
- tv->tv_usec /= 1000;
- }
- if (unlikely(tz != NULL)) {
- tz->tz_minuteswest = gtod->tz_minuteswest;
- tz->tz_dsttime = gtod->tz_dsttime;
- }
-
- return 0;
-}
-int gettimeofday(struct timeval *, struct timezone *)
- __attribute__((weak, alias("__vdso_gettimeofday")));
-
-/*
- * This will break when the xtime seconds get inaccurate, but that is
- * unlikely
- */
-notrace time_t __vdso_time(time_t *t)
-{
- /* This is atomic on x86 so we don't need any locks. */
- time_t result = ACCESS_ONCE(gtod->wall_time_sec);
-
- if (t)
- *t = result;
- return result;
-}
-int time(time_t *t)
- __attribute__((weak, alias("__vdso_time")));
+++ /dev/null
-#include <asm/vdso.h>
-
-/*
- * Linker script for vDSO. This is an ELF shared object prelinked to
- * its virtual address, and with only one read-only segment.
- * This script controls its layout.
- */
-
-#if defined(BUILD_VDSO64)
-# define SHDR_SIZE 64
-#elif defined(BUILD_VDSO32) || defined(BUILD_VDSOX32)
-# define SHDR_SIZE 40
-#else
-# error unknown VDSO target
-#endif
-
-#define NUM_FAKE_SHDRS 13
-
-SECTIONS
-{
- /*
- * User/kernel shared data is before the vDSO. This may be a little
- * uglier than putting it after the vDSO, but it avoids issues with
- * non-allocatable things that dangle past the end of the PT_LOAD
- * segment.
- */
-
- vvar_start = . - 2 * PAGE_SIZE;
- vvar_page = vvar_start;
-
- /* Place all vvars at the offsets in asm/vvar.h. */
-#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset;
-#define __VVAR_KERNEL_LDS
-#include <asm/vvar.h>
-#undef __VVAR_KERNEL_LDS
-#undef EMIT_VVAR
-
- hpet_page = vvar_start + PAGE_SIZE;
-
- . = SIZEOF_HEADERS;
-
- .hash : { *(.hash) } :text
- .gnu.hash : { *(.gnu.hash) }
- .dynsym : { *(.dynsym) }
- .dynstr : { *(.dynstr) }
- .gnu.version : { *(.gnu.version) }
- .gnu.version_d : { *(.gnu.version_d) }
- .gnu.version_r : { *(.gnu.version_r) }
-
- .dynamic : { *(.dynamic) } :text :dynamic
-
- .rodata : {
- *(.rodata*)
- *(.data*)
- *(.sdata*)
- *(.got.plt) *(.got)
- *(.gnu.linkonce.d.*)
- *(.bss*)
- *(.dynbss*)
- *(.gnu.linkonce.b.*)
-
- /*
- * Ideally this would live in a C file, but that won't
- * work cleanly for x32 until we start building the x32
- * C code using an x32 toolchain.
- */
- VDSO_FAKE_SECTION_TABLE_START = .;
- . = . + NUM_FAKE_SHDRS * SHDR_SIZE;
- VDSO_FAKE_SECTION_TABLE_END = .;
- } :text
-
- .fake_shstrtab : { *(.fake_shstrtab) } :text
-
-
- .note : { *(.note.*) } :text :note
-
- .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
- .eh_frame : { KEEP (*(.eh_frame)) } :text
-
-
- /*
- * Text is well-separated from actual data: there's plenty of
- * stuff that isn't used at runtime in between.
- */
-
- .text : { *(.text*) } :text =0x90909090,
-
- /*
- * At the end so that eu-elflint stays happy when vdso2c strips
- * these. A better implementation would avoid allocating space
- * for these.
- */
- .altinstructions : { *(.altinstructions) } :text
- .altinstr_replacement : { *(.altinstr_replacement) } :text
-
- /DISCARD/ : {
- *(.discard)
- *(.discard.*)
- *(__bug_table)
- }
-}
-
-/*
- * Very old versions of ld do not recognize this name token; use the constant.
- */
-#define PT_GNU_EH_FRAME 0x6474e550
-
-/*
- * We must supply the ELF program headers explicitly to get just one
- * PT_LOAD segment, and set the flags explicitly to make segments read-only.
- */
-PHDRS
-{
- text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
- dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
- note PT_NOTE FLAGS(4); /* PF_R */
- eh_frame_hdr PT_GNU_EH_FRAME;
-}
+++ /dev/null
-/*
- * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
- * Here we can supply some information useful to userland.
- */
-
-#include <linux/uts.h>
-#include <linux/version.h>
-#include <linux/elfnote.h>
-
-ELFNOTE_START(Linux, 0, "a")
- .long LINUX_VERSION_CODE
-ELFNOTE_END
+++ /dev/null
-/*
- * Linker script for 64-bit vDSO.
- * We #include the file to define the layout details.
- *
- * This file defines the version script giving the user-exported symbols in
- * the DSO.
- */
-
-#define BUILD_VDSO64
-
-#include "vdso-layout.lds.S"
-
-/*
- * This controls what userland symbols we export from the vDSO.
- */
-VERSION {
- LINUX_2.6 {
- global:
- clock_gettime;
- __vdso_clock_gettime;
- gettimeofday;
- __vdso_gettimeofday;
- getcpu;
- __vdso_getcpu;
- time;
- __vdso_time;
- local: *;
- };
-}
+++ /dev/null
-/*
- * vdso2c - A vdso image preparation tool
- * Copyright (c) 2014 Andy Lutomirski and others
- * Licensed under the GPL v2
- *
- * vdso2c requires stripped and unstripped input. It would be trivial
- * to fully strip the input in here, but, for reasons described below,
- * we need to write a section table. Doing this is more or less
- * equivalent to dropping all non-allocatable sections, but it's
- * easier to let objcopy handle that instead of doing it ourselves.
- * If we ever need to do something fancier than what objcopy provides,
- * it would be straightforward to add here.
- *
- * We're keep a section table for a few reasons:
- *
- * The Go runtime had a couple of bugs: it would read the section
- * table to try to figure out how many dynamic symbols there were (it
- * shouldn't have looked at the section table at all) and, if there
- * were no SHT_SYNDYM section table entry, it would use an
- * uninitialized value for the number of symbols. An empty DYNSYM
- * table would work, but I see no reason not to write a valid one (and
- * keep full performance for old Go programs). This hack is only
- * needed on x86_64.
- *
- * The bug was introduced on 2012-08-31 by:
- * https://code.google.com/p/go/source/detail?r=56ea40aac72b
- * and was fixed on 2014-06-13 by:
- * https://code.google.com/p/go/source/detail?r=fc1cd5e12595
- *
- * Binutils has issues debugging the vDSO: it reads the section table to
- * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which
- * would break build-id if we removed the section table. Binutils
- * also requires that shstrndx != 0. See:
- * https://sourceware.org/bugzilla/show_bug.cgi?id=17064
- *
- * elfutils might not look for PT_NOTE if there is a section table at
- * all. I don't know whether this matters for any practical purpose.
- *
- * For simplicity, rather than hacking up a partial section table, we
- * just write a mostly complete one. We omit non-dynamic symbols,
- * though, since they're rather large.
- *
- * Once binutils gets fixed, we might be able to drop this for all but
- * the 64-bit vdso, since build-id only works in kernel RPMs, and
- * systems that update to new enough kernel RPMs will likely update
- * binutils in sync. build-id has never worked for home-built kernel
- * RPMs without manual symlinking, and I suspect that no one ever does
- * that.
- */
-
-#include <inttypes.h>
-#include <stdint.h>
-#include <unistd.h>
-#include <stdarg.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
-#include <fcntl.h>
-#include <err.h>
-
-#include <sys/mman.h>
-#include <sys/types.h>
-
-#include <tools/le_byteshift.h>
-
-#include <linux/elf.h>
-#include <linux/types.h>
-
-const char *outfilename;
-
-/* Symbols that we need in vdso2c. */
-enum {
- sym_vvar_start,
- sym_vvar_page,
- sym_hpet_page,
- sym_VDSO_FAKE_SECTION_TABLE_START,
- sym_VDSO_FAKE_SECTION_TABLE_END,
-};
-
-const int special_pages[] = {
- sym_vvar_page,
- sym_hpet_page,
-};
-
-struct vdso_sym {
- const char *name;
- bool export;
-};
-
-struct vdso_sym required_syms[] = {
- [sym_vvar_start] = {"vvar_start", true},
- [sym_vvar_page] = {"vvar_page", true},
- [sym_hpet_page] = {"hpet_page", true},
- [sym_VDSO_FAKE_SECTION_TABLE_START] = {
- "VDSO_FAKE_SECTION_TABLE_START", false
- },
- [sym_VDSO_FAKE_SECTION_TABLE_END] = {
- "VDSO_FAKE_SECTION_TABLE_END", false
- },
- {"VDSO32_NOTE_MASK", true},
- {"VDSO32_SYSENTER_RETURN", true},
- {"__kernel_vsyscall", true},
- {"__kernel_sigreturn", true},
- {"__kernel_rt_sigreturn", true},
-};
-
-__attribute__((format(printf, 1, 2))) __attribute__((noreturn))
-static void fail(const char *format, ...)
-{
- va_list ap;
- va_start(ap, format);
- fprintf(stderr, "Error: ");
- vfprintf(stderr, format, ap);
- if (outfilename)
- unlink(outfilename);
- exit(1);
- va_end(ap);
-}
-
-/*
- * Evil macros for little-endian reads and writes
- */
-#define GLE(x, bits, ifnot) \
- __builtin_choose_expr( \
- (sizeof(*(x)) == bits/8), \
- (__typeof__(*(x)))get_unaligned_le##bits(x), ifnot)
-
-extern void bad_get_le(void);
-#define LAST_GLE(x) \
- __builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le())
-
-#define GET_LE(x) \
- GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x))))
-
-#define PLE(x, val, bits, ifnot) \
- __builtin_choose_expr( \
- (sizeof(*(x)) == bits/8), \
- put_unaligned_le##bits((val), (x)), ifnot)
-
-extern void bad_put_le(void);
-#define LAST_PLE(x, val) \
- __builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le())
-
-#define PUT_LE(x, val) \
- PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val))))
-
-
-#define NSYMS (sizeof(required_syms) / sizeof(required_syms[0]))
-
-#define BITSFUNC3(name, bits, suffix) name##bits##suffix
-#define BITSFUNC2(name, bits, suffix) BITSFUNC3(name, bits, suffix)
-#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS, )
-
-#define INT_BITS BITSFUNC2(int, ELF_BITS, _t)
-
-#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
-#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
-#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
-
-#define ELF_BITS 64
-#include "vdso2c.h"
-#undef ELF_BITS
-
-#define ELF_BITS 32
-#include "vdso2c.h"
-#undef ELF_BITS
-
-static void go(void *raw_addr, size_t raw_len,
- void *stripped_addr, size_t stripped_len,
- FILE *outfile, const char *name)
-{
- Elf64_Ehdr *hdr = (Elf64_Ehdr *)raw_addr;
-
- if (hdr->e_ident[EI_CLASS] == ELFCLASS64) {
- go64(raw_addr, raw_len, stripped_addr, stripped_len,
- outfile, name);
- } else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) {
- go32(raw_addr, raw_len, stripped_addr, stripped_len,
- outfile, name);
- } else {
- fail("unknown ELF class\n");
- }
-}
-
-static void map_input(const char *name, void **addr, size_t *len, int prot)
-{
- off_t tmp_len;
-
- int fd = open(name, O_RDONLY);
- if (fd == -1)
- err(1, "%s", name);
-
- tmp_len = lseek(fd, 0, SEEK_END);
- if (tmp_len == (off_t)-1)
- err(1, "lseek");
- *len = (size_t)tmp_len;
-
- *addr = mmap(NULL, tmp_len, prot, MAP_PRIVATE, fd, 0);
- if (*addr == MAP_FAILED)
- err(1, "mmap");
-
- close(fd);
-}
-
-int main(int argc, char **argv)
-{
- size_t raw_len, stripped_len;
- void *raw_addr, *stripped_addr;
- FILE *outfile;
- char *name, *tmp;
- int namelen;
-
- if (argc != 4) {
- printf("Usage: vdso2c RAW_INPUT STRIPPED_INPUT OUTPUT\n");
- return 1;
- }
-
- /*
- * Figure out the struct name. If we're writing to a .so file,
- * generate raw output insted.
- */
- name = strdup(argv[3]);
- namelen = strlen(name);
- if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) {
- name = NULL;
- } else {
- tmp = strrchr(name, '/');
- if (tmp)
- name = tmp + 1;
- tmp = strchr(name, '.');
- if (tmp)
- *tmp = '\0';
- for (tmp = name; *tmp; tmp++)
- if (*tmp == '-')
- *tmp = '_';
- }
-
- map_input(argv[1], &raw_addr, &raw_len, PROT_READ);
- map_input(argv[2], &stripped_addr, &stripped_len, PROT_READ);
-
- outfilename = argv[3];
- outfile = fopen(outfilename, "w");
- if (!outfile)
- err(1, "%s", argv[2]);
-
- go(raw_addr, raw_len, stripped_addr, stripped_len, outfile, name);
-
- munmap(raw_addr, raw_len);
- munmap(stripped_addr, stripped_len);
- fclose(outfile);
-
- return 0;
-}
+++ /dev/null
-/*
- * This file is included twice from vdso2c.c. It generates code for 32-bit
- * and 64-bit vDSOs. We need both for 64-bit builds, since 32-bit vDSOs
- * are built for 32-bit userspace.
- */
-
-static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
- void *stripped_addr, size_t stripped_len,
- FILE *outfile, const char *name)
-{
- int found_load = 0;
- unsigned long load_size = -1; /* Work around bogus warning */
- unsigned long mapping_size;
- ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr;
- int i;
- unsigned long j;
- ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
- *alt_sec = NULL;
- ELF(Dyn) *dyn = 0, *dyn_end = 0;
- const char *secstrings;
- INT_BITS syms[NSYMS] = {};
-
- ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff));
-
- /* Walk the segment table. */
- for (i = 0; i < GET_LE(&hdr->e_phnum); i++) {
- if (GET_LE(&pt[i].p_type) == PT_LOAD) {
- if (found_load)
- fail("multiple PT_LOAD segs\n");
-
- if (GET_LE(&pt[i].p_offset) != 0 ||
- GET_LE(&pt[i].p_vaddr) != 0)
- fail("PT_LOAD in wrong place\n");
-
- if (GET_LE(&pt[i].p_memsz) != GET_LE(&pt[i].p_filesz))
- fail("cannot handle memsz != filesz\n");
-
- load_size = GET_LE(&pt[i].p_memsz);
- found_load = 1;
- } else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) {
- dyn = raw_addr + GET_LE(&pt[i].p_offset);
- dyn_end = raw_addr + GET_LE(&pt[i].p_offset) +
- GET_LE(&pt[i].p_memsz);
- }
- }
- if (!found_load)
- fail("no PT_LOAD seg\n");
-
- if (stripped_len < load_size)
- fail("stripped input is too short\n");
-
- /* Walk the dynamic table */
- for (i = 0; dyn + i < dyn_end &&
- GET_LE(&dyn[i].d_tag) != DT_NULL; i++) {
- typeof(dyn[i].d_tag) tag = GET_LE(&dyn[i].d_tag);
- if (tag == DT_REL || tag == DT_RELSZ || tag == DT_RELA ||
- tag == DT_RELENT || tag == DT_TEXTREL)
- fail("vdso image contains dynamic relocations\n");
- }
-
- /* Walk the section table */
- secstrings_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
- GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx);
- secstrings = raw_addr + GET_LE(&secstrings_hdr->sh_offset);
- for (i = 0; i < GET_LE(&hdr->e_shnum); i++) {
- ELF(Shdr) *sh = raw_addr + GET_LE(&hdr->e_shoff) +
- GET_LE(&hdr->e_shentsize) * i;
- if (GET_LE(&sh->sh_type) == SHT_SYMTAB)
- symtab_hdr = sh;
-
- if (!strcmp(secstrings + GET_LE(&sh->sh_name),
- ".altinstructions"))
- alt_sec = sh;
- }
-
- if (!symtab_hdr)
- fail("no symbol table\n");
-
- strtab_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
- GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link);
-
- /* Walk the symbol table */
- for (i = 0;
- i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize);
- i++) {
- int k;
- ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
- GET_LE(&symtab_hdr->sh_entsize) * i;
- const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) +
- GET_LE(&sym->st_name);
-
- for (k = 0; k < NSYMS; k++) {
- if (!strcmp(name, required_syms[k].name)) {
- if (syms[k]) {
- fail("duplicate symbol %s\n",
- required_syms[k].name);
- }
-
- /*
- * Careful: we use negative addresses, but
- * st_value is unsigned, so we rely
- * on syms[k] being a signed type of the
- * correct width.
- */
- syms[k] = GET_LE(&sym->st_value);
- }
- }
- }
-
- /* Validate mapping addresses. */
- for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
- INT_BITS symval = syms[special_pages[i]];
-
- if (!symval)
- continue; /* The mapping isn't used; ignore it. */
-
- if (symval % 4096)
- fail("%s must be a multiple of 4096\n",
- required_syms[i].name);
- if (symval + 4096 < syms[sym_vvar_start])
- fail("%s underruns vvar_start\n",
- required_syms[i].name);
- if (symval + 4096 > 0)
- fail("%s is on the wrong side of the vdso text\n",
- required_syms[i].name);
- }
- if (syms[sym_vvar_start] % 4096)
- fail("vvar_begin must be a multiple of 4096\n");
-
- if (!name) {
- fwrite(stripped_addr, stripped_len, 1, outfile);
- return;
- }
-
- mapping_size = (stripped_len + 4095) / 4096 * 4096;
-
- fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n");
- fprintf(outfile, "#include <linux/linkage.h>\n");
- fprintf(outfile, "#include <asm/page_types.h>\n");
- fprintf(outfile, "#include <asm/vdso.h>\n");
- fprintf(outfile, "\n");
- fprintf(outfile,
- "static unsigned char raw_data[%lu] __page_aligned_data = {",
- mapping_size);
- for (j = 0; j < stripped_len; j++) {
- if (j % 10 == 0)
- fprintf(outfile, "\n\t");
- fprintf(outfile, "0x%02X, ",
- (int)((unsigned char *)stripped_addr)[j]);
- }
- fprintf(outfile, "\n};\n\n");
-
- fprintf(outfile, "static struct page *pages[%lu];\n\n",
- mapping_size / 4096);
-
- fprintf(outfile, "const struct vdso_image %s = {\n", name);
- fprintf(outfile, "\t.data = raw_data,\n");
- fprintf(outfile, "\t.size = %lu,\n", mapping_size);
- fprintf(outfile, "\t.text_mapping = {\n");
- fprintf(outfile, "\t\t.name = \"[vdso]\",\n");
- fprintf(outfile, "\t\t.pages = pages,\n");
- fprintf(outfile, "\t},\n");
- if (alt_sec) {
- fprintf(outfile, "\t.alt = %lu,\n",
- (unsigned long)GET_LE(&alt_sec->sh_offset));
- fprintf(outfile, "\t.alt_len = %lu,\n",
- (unsigned long)GET_LE(&alt_sec->sh_size));
- }
- for (i = 0; i < NSYMS; i++) {
- if (required_syms[i].export && syms[i])
- fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n",
- required_syms[i].name, (int64_t)syms[i]);
- }
- fprintf(outfile, "};\n");
-}
+++ /dev/null
-/*
- * (C) Copyright 2002 Linus Torvalds
- * Portions based on the vdso-randomization code from exec-shield:
- * Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
- *
- * This file contains the needed initializations to support sysenter.
- */
-
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/kernel.h>
-#include <linux/mm_types.h>
-
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-#include <asm/vdso.h>
-
-#ifdef CONFIG_COMPAT_VDSO
-#define VDSO_DEFAULT 0
-#else
-#define VDSO_DEFAULT 1
-#endif
-
-/*
- * Should the kernel map a VDSO page into processes and pass its
- * address down to glibc upon exec()?
- */
-unsigned int __read_mostly vdso32_enabled = VDSO_DEFAULT;
-
-static int __init vdso32_setup(char *s)
-{
- vdso32_enabled = simple_strtoul(s, NULL, 0);
-
- if (vdso32_enabled > 1)
- pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
-
- return 1;
-}
-
-/*
- * For consistency, the argument vdso32=[012] affects the 32-bit vDSO
- * behavior on both 64-bit and 32-bit kernels.
- * On 32-bit kernels, vdso=[012] means the same thing.
- */
-__setup("vdso32=", vdso32_setup);
-
-#ifdef CONFIG_X86_32
-__setup_param("vdso=", vdso_setup, vdso32_setup, 0);
-#endif
-
-#ifdef CONFIG_X86_64
-
-#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32))
-#define vdso32_syscall() (boot_cpu_has(X86_FEATURE_SYSCALL32))
-
-#else /* CONFIG_X86_32 */
-
-#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SEP))
-#define vdso32_syscall() (0)
-
-#endif /* CONFIG_X86_64 */
-
-#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
-const struct vdso_image *selected_vdso32;
-#endif
-
-int __init sysenter_setup(void)
-{
-#ifdef CONFIG_COMPAT
- if (vdso32_syscall())
- selected_vdso32 = &vdso_image_32_syscall;
- else
-#endif
- if (vdso32_sysenter())
- selected_vdso32 = &vdso_image_32_sysenter;
- else
- selected_vdso32 = &vdso_image_32_int80;
-
- init_vdso_image(selected_vdso32);
-
- return 0;
-}
-
-#ifdef CONFIG_X86_64
-
-subsys_initcall(sysenter_setup);
-
-#ifdef CONFIG_SYSCTL
-/* Register vsyscall32 into the ABI table */
-#include <linux/sysctl.h>
-
-static struct ctl_table abi_table2[] = {
- {
- .procname = "vsyscall32",
- .data = &vdso32_enabled,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {}
-};
-
-static struct ctl_table abi_root_table2[] = {
- {
- .procname = "abi",
- .mode = 0555,
- .child = abi_table2
- },
- {}
-};
-
-static __init int ia32_binfmt_init(void)
-{
- register_sysctl_table(abi_root_table2);
- return 0;
-}
-__initcall(ia32_binfmt_init);
-#endif /* CONFIG_SYSCTL */
-
-#endif /* CONFIG_X86_64 */
+++ /dev/null
-vdso32.lds
+++ /dev/null
-/*
- * Code for the vDSO. This version uses the old int $0x80 method.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#include "sigreturn.S"
-
- .text
- .globl __kernel_vsyscall
- .type __kernel_vsyscall,@function
- ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
- int $0x80
- ret
-.LEND_vsyscall:
- .size __kernel_vsyscall,.-.LSTART_vsyscall
- .previous
-
- .section .eh_frame,"a",@progbits
-.LSTARTFRAMEDLSI:
- .long .LENDCIEDLSI-.LSTARTCIEDLSI
-.LSTARTCIEDLSI:
- .long 0 /* CIE ID */
- .byte 1 /* Version number */
- .string "zR" /* NUL-terminated augmentation string */
- .uleb128 1 /* Code alignment factor */
- .sleb128 -4 /* Data alignment factor */
- .byte 8 /* Return address register column */
- .uleb128 1 /* Augmentation value length */
- .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
- .byte 0x0c /* DW_CFA_def_cfa */
- .uleb128 4
- .uleb128 4
- .byte 0x88 /* DW_CFA_offset, column 0x8 */
- .uleb128 1
- .align 4
-.LENDCIEDLSI:
- .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
-.LSTARTFDEDLSI:
- .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
- .long .LSTART_vsyscall-. /* PC-relative start address */
- .long .LEND_vsyscall-.LSTART_vsyscall
- .uleb128 0
- .align 4
-.LENDFDEDLSI:
- .previous
-
- /*
- * Pad out the segment to match the size of the sysenter.S version.
- */
-VDSO32_vsyscall_eh_frame_size = 0x40
- .section .data,"aw",@progbits
- .space VDSO32_vsyscall_eh_frame_size-(.LENDFDEDLSI-.LSTARTFRAMEDLSI), 0
- .previous
+++ /dev/null
-/*
- * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
- * Here we can supply some information useful to userland.
- */
-
-#include <linux/version.h>
-#include <linux/elfnote.h>
-
-/* Ideally this would use UTS_NAME, but using a quoted string here
- doesn't work. Remember to change this when changing the
- kernel's name. */
-ELFNOTE_START(Linux, 0, "a")
- .long LINUX_VERSION_CODE
-ELFNOTE_END
-
-#ifdef CONFIG_XEN
-/*
- * Add a special note telling glibc's dynamic linker a fake hardware
- * flavor that it will use to choose the search path for libraries in the
- * same way it uses real hardware capabilities like "mmx".
- * We supply "nosegneg" as the fake capability, to indicate that we
- * do not like negative offsets in instructions using segment overrides,
- * since we implement those inefficiently. This makes it possible to
- * install libraries optimized to avoid those access patterns in someplace
- * like /lib/i686/tls/nosegneg. Note that an /etc/ld.so.conf.d/file
- * corresponding to the bits here is needed to make ldconfig work right.
- * It should contain:
- * hwcap 1 nosegneg
- * to match the mapping of bit to name that we give here.
- *
- * At runtime, the fake hardware feature will be considered to be present
- * if its bit is set in the mask word. So, we start with the mask 0, and
- * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen.
- */
-
-#include "../../xen/vdso.h" /* Defines VDSO_NOTE_NONEGSEG_BIT. */
-
-ELFNOTE_START(GNU, 2, "a")
- .long 1 /* ncaps */
-VDSO32_NOTE_MASK: /* Symbol used by arch/x86/xen/setup.c */
- .long 0 /* mask */
- .byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg" /* bit, name */
-ELFNOTE_END
-#endif
+++ /dev/null
-/*
- * Common code for the sigreturn entry points in vDSO images.
- * So far this code is the same for both int80 and sysenter versions.
- * This file is #include'd by int80.S et al to define them first thing.
- * The kernel assumes that the addresses of these routines are constant
- * for all vDSO implementations.
- */
-
-#include <linux/linkage.h>
-#include <asm/unistd_32.h>
-#include <asm/asm-offsets.h>
-
-#ifndef SYSCALL_ENTER_KERNEL
-#define SYSCALL_ENTER_KERNEL int $0x80
-#endif
-
- .text
- .globl __kernel_sigreturn
- .type __kernel_sigreturn,@function
- nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
- ALIGN
-__kernel_sigreturn:
-.LSTART_sigreturn:
- popl %eax /* XXX does this mean it needs unwind info? */
- movl $__NR_sigreturn, %eax
- SYSCALL_ENTER_KERNEL
-.LEND_sigreturn:
- nop
- .size __kernel_sigreturn,.-.LSTART_sigreturn
-
- .globl __kernel_rt_sigreturn
- .type __kernel_rt_sigreturn,@function
- ALIGN
-__kernel_rt_sigreturn:
-.LSTART_rt_sigreturn:
- movl $__NR_rt_sigreturn, %eax
- SYSCALL_ENTER_KERNEL
-.LEND_rt_sigreturn:
- nop
- .size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn
- .previous
-
- .section .eh_frame,"a",@progbits
-.LSTARTFRAMEDLSI1:
- .long .LENDCIEDLSI1-.LSTARTCIEDLSI1
-.LSTARTCIEDLSI1:
- .long 0 /* CIE ID */
- .byte 1 /* Version number */
- .string "zRS" /* NUL-terminated augmentation string */
- .uleb128 1 /* Code alignment factor */
- .sleb128 -4 /* Data alignment factor */
- .byte 8 /* Return address register column */
- .uleb128 1 /* Augmentation value length */
- .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
- .byte 0 /* DW_CFA_nop */
- .align 4
-.LENDCIEDLSI1:
- .long .LENDFDEDLSI1-.LSTARTFDEDLSI1 /* Length FDE */
-.LSTARTFDEDLSI1:
- .long .LSTARTFDEDLSI1-.LSTARTFRAMEDLSI1 /* CIE pointer */
- /* HACK: The dwarf2 unwind routines will subtract 1 from the
- return address to get an address in the middle of the
- presumed call instruction. Since we didn't get here via
- a call, we need to include the nop before the real start
- to make up for it. */
- .long .LSTART_sigreturn-1-. /* PC-relative start address */
- .long .LEND_sigreturn-.LSTART_sigreturn+1
- .uleb128 0 /* Augmentation */
- /* What follows are the instructions for the table generation.
- We record the locations of each register saved. This is
- complicated by the fact that the "CFA" is always assumed to
- be the value of the stack pointer in the caller. This means
- that we must define the CFA of this body of code to be the
- saved value of the stack pointer in the sigcontext. Which
- also means that there is no fixed relation to the other
- saved registers, which means that we must use DW_CFA_expression
- to compute their addresses. It also means that when we
- adjust the stack with the popl, we have to do it all over again. */
-
-#define do_cfa_expr(offset) \
- .byte 0x0f; /* DW_CFA_def_cfa_expression */ \
- .uleb128 1f-0f; /* length */ \
-0: .byte 0x74; /* DW_OP_breg4 */ \
- .sleb128 offset; /* offset */ \
- .byte 0x06; /* DW_OP_deref */ \
-1:
-
-#define do_expr(regno, offset) \
- .byte 0x10; /* DW_CFA_expression */ \
- .uleb128 regno; /* regno */ \
- .uleb128 1f-0f; /* length */ \
-0: .byte 0x74; /* DW_OP_breg4 */ \
- .sleb128 offset; /* offset */ \
-1:
-
- do_cfa_expr(IA32_SIGCONTEXT_sp+4)
- do_expr(0, IA32_SIGCONTEXT_ax+4)
- do_expr(1, IA32_SIGCONTEXT_cx+4)
- do_expr(2, IA32_SIGCONTEXT_dx+4)
- do_expr(3, IA32_SIGCONTEXT_bx+4)
- do_expr(5, IA32_SIGCONTEXT_bp+4)
- do_expr(6, IA32_SIGCONTEXT_si+4)
- do_expr(7, IA32_SIGCONTEXT_di+4)
- do_expr(8, IA32_SIGCONTEXT_ip+4)
-
- .byte 0x42 /* DW_CFA_advance_loc 2 -- nop; popl eax. */
-
- do_cfa_expr(IA32_SIGCONTEXT_sp)
- do_expr(0, IA32_SIGCONTEXT_ax)
- do_expr(1, IA32_SIGCONTEXT_cx)
- do_expr(2, IA32_SIGCONTEXT_dx)
- do_expr(3, IA32_SIGCONTEXT_bx)
- do_expr(5, IA32_SIGCONTEXT_bp)
- do_expr(6, IA32_SIGCONTEXT_si)
- do_expr(7, IA32_SIGCONTEXT_di)
- do_expr(8, IA32_SIGCONTEXT_ip)
-
- .align 4
-.LENDFDEDLSI1:
-
- .long .LENDFDEDLSI2-.LSTARTFDEDLSI2 /* Length FDE */
-.LSTARTFDEDLSI2:
- .long .LSTARTFDEDLSI2-.LSTARTFRAMEDLSI1 /* CIE pointer */
- /* HACK: See above wrt unwind library assumptions. */
- .long .LSTART_rt_sigreturn-1-. /* PC-relative start address */
- .long .LEND_rt_sigreturn-.LSTART_rt_sigreturn+1
- .uleb128 0 /* Augmentation */
- /* What follows are the instructions for the table generation.
- We record the locations of each register saved. This is
- slightly less complicated than the above, since we don't
- modify the stack pointer in the process. */
-
- do_cfa_expr(IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_sp)
- do_expr(0, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ax)
- do_expr(1, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_cx)
- do_expr(2, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_dx)
- do_expr(3, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bx)
- do_expr(5, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bp)
- do_expr(6, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_si)
- do_expr(7, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_di)
- do_expr(8, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ip)
-
- .align 4
-.LENDFDEDLSI2:
- .previous
+++ /dev/null
-/*
- * Code for the vDSO. This version uses the syscall instruction.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#define SYSCALL_ENTER_KERNEL syscall
-#include "sigreturn.S"
-
-#include <asm/segment.h>
-
- .text
- .globl __kernel_vsyscall
- .type __kernel_vsyscall,@function
- ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
- push %ebp
-.Lpush_ebp:
- movl %ecx, %ebp
- syscall
- movl %ebp, %ecx
- popl %ebp
-.Lpop_ebp:
- ret
-.LEND_vsyscall:
- .size __kernel_vsyscall,.-.LSTART_vsyscall
-
- .section .eh_frame,"a",@progbits
-.LSTARTFRAME:
- .long .LENDCIE-.LSTARTCIE
-.LSTARTCIE:
- .long 0 /* CIE ID */
- .byte 1 /* Version number */
- .string "zR" /* NUL-terminated augmentation string */
- .uleb128 1 /* Code alignment factor */
- .sleb128 -4 /* Data alignment factor */
- .byte 8 /* Return address register column */
- .uleb128 1 /* Augmentation value length */
- .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
- .byte 0x0c /* DW_CFA_def_cfa */
- .uleb128 4
- .uleb128 4
- .byte 0x88 /* DW_CFA_offset, column 0x8 */
- .uleb128 1
- .align 4
-.LENDCIE:
-
- .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */
-.LSTARTFDE1:
- .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */
- .long .LSTART_vsyscall-. /* PC-relative start address */
- .long .LEND_vsyscall-.LSTART_vsyscall
- .uleb128 0 /* Augmentation length */
- /* What follows are the instructions for the table generation.
- We have to record all changes of the stack pointer. */
- .byte 0x40 + .Lpush_ebp-.LSTART_vsyscall /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .uleb128 8
- .byte 0x85, 0x02 /* DW_CFA_offset %ebp -8 */
- .byte 0x40 + .Lpop_ebp-.Lpush_ebp /* DW_CFA_advance_loc */
- .byte 0xc5 /* DW_CFA_restore %ebp */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .uleb128 4
- .align 4
-.LENDFDE1:
- .previous
-
- /*
- * Pad out the segment to match the size of the sysenter.S version.
- */
-VDSO32_vsyscall_eh_frame_size = 0x40
- .section .data,"aw",@progbits
- .space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0
- .previous
+++ /dev/null
-/*
- * Code for the vDSO. This version uses the sysenter instruction.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#include "sigreturn.S"
-
-/*
- * The caller puts arg2 in %ecx, which gets pushed. The kernel will use
- * %ecx itself for arg2. The pushing is because the sysexit instruction
- * (found in entry.S) requires that we clobber %ecx with the desired %esp.
- * User code might expect that %ecx is unclobbered though, as it would be
- * for returning via the iret instruction, so we must push and pop.
- *
- * The caller puts arg3 in %edx, which the sysexit instruction requires
- * for %eip. Thus, exactly as for arg2, we must push and pop.
- *
- * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter
- * instruction clobbers %esp, the user's %esp won't even survive entry
- * into the kernel. We store %esp in %ebp. Code in entry.S must fetch
- * arg6 from the stack.
- *
- * You can not use this vsyscall for the clone() syscall because the
- * three words on the parent stack do not get copied to the child.
- */
- .text
- .globl __kernel_vsyscall
- .type __kernel_vsyscall,@function
- ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
- push %ecx
-.Lpush_ecx:
- push %edx
-.Lpush_edx:
- push %ebp
-.Lenter_kernel:
- movl %esp,%ebp
- sysenter
-
- /* 7: align return point with nop's to make disassembly easier */
- .space 7,0x90
-
- /* 14: System call restart point is here! (SYSENTER_RETURN-2) */
- int $0x80
- /* 16: System call normal return point is here! */
-VDSO32_SYSENTER_RETURN: /* Symbol used by sysenter.c via vdso32-syms.h */
- pop %ebp
-.Lpop_ebp:
- pop %edx
-.Lpop_edx:
- pop %ecx
-.Lpop_ecx:
- ret
-.LEND_vsyscall:
- .size __kernel_vsyscall,.-.LSTART_vsyscall
- .previous
-
- .section .eh_frame,"a",@progbits
-.LSTARTFRAMEDLSI:
- .long .LENDCIEDLSI-.LSTARTCIEDLSI
-.LSTARTCIEDLSI:
- .long 0 /* CIE ID */
- .byte 1 /* Version number */
- .string "zR" /* NUL-terminated augmentation string */
- .uleb128 1 /* Code alignment factor */
- .sleb128 -4 /* Data alignment factor */
- .byte 8 /* Return address register column */
- .uleb128 1 /* Augmentation value length */
- .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
- .byte 0x0c /* DW_CFA_def_cfa */
- .uleb128 4
- .uleb128 4
- .byte 0x88 /* DW_CFA_offset, column 0x8 */
- .uleb128 1
- .align 4
-.LENDCIEDLSI:
- .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
-.LSTARTFDEDLSI:
- .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
- .long .LSTART_vsyscall-. /* PC-relative start address */
- .long .LEND_vsyscall-.LSTART_vsyscall
- .uleb128 0
- /* What follows are the instructions for the table generation.
- We have to record all changes of the stack pointer. */
- .byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x08 /* RA at offset 8 now */
- .byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x0c /* RA at offset 12 now */
- .byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x10 /* RA at offset 16 now */
- .byte 0x85, 0x04 /* DW_CFA_offset %ebp -16 */
- /* Finally the epilogue. */
- .byte 0x40 + (.Lpop_ebp-.Lenter_kernel) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x0c /* RA at offset 12 now */
- .byte 0xc5 /* DW_CFA_restore %ebp */
- .byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x08 /* RA at offset 8 now */
- .byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x04 /* RA at offset 4 now */
- .align 4
-.LENDFDEDLSI:
- .previous
-
- /*
- * Emit a symbol with the size of this .eh_frame data,
- * to verify it matches the other versions.
- */
-VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI)
+++ /dev/null
-#define BUILD_VDSO32
-
-#ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
-#undef CONFIG_OPTIMIZE_INLINING
-#endif
-
-#undef CONFIG_X86_PPRO_FENCE
-
-#ifdef CONFIG_X86_64
-
-/*
- * in case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel
- * configuration
- */
-#undef CONFIG_64BIT
-#undef CONFIG_X86_64
-#undef CONFIG_ILLEGAL_POINTER_VALUE
-#undef CONFIG_SPARSEMEM_VMEMMAP
-#undef CONFIG_NR_CPUS
-
-#define CONFIG_X86_32 1
-#define CONFIG_PAGE_OFFSET 0
-#define CONFIG_ILLEGAL_POINTER_VALUE 0
-#define CONFIG_NR_CPUS 1
-
-#define BUILD_VDSO32_64
-
-#endif
-
-#include "../vclock_gettime.c"
+++ /dev/null
-#include "../vdso-fakesections.c"
+++ /dev/null
-/*
- * Linker script for 32-bit vDSO.
- * We #include the file to define the layout details.
- *
- * This file defines the version script giving the user-exported symbols in
- * the DSO.
- */
-
-#include <asm/page.h>
-
-#define BUILD_VDSO32
-
-#include "../vdso-layout.lds.S"
-
-/* The ELF entry point can be used to set the AT_SYSINFO value. */
-ENTRY(__kernel_vsyscall);
-
-/*
- * This controls what userland symbols we export from the vDSO.
- */
-VERSION
-{
- LINUX_2.6 {
- global:
- __vdso_clock_gettime;
- __vdso_gettimeofday;
- __vdso_time;
- };
-
- LINUX_2.5 {
- global:
- __kernel_vsyscall;
- __kernel_sigreturn;
- __kernel_rt_sigreturn;
- local: *;
- };
-}
+++ /dev/null
-/*
- * Linker script for x32 vDSO.
- * We #include the file to define the layout details.
- *
- * This file defines the version script giving the user-exported symbols in
- * the DSO.
- */
-
-#define BUILD_VDSOX32
-
-#include "vdso-layout.lds.S"
-
-/*
- * This controls what userland symbols we export from the vDSO.
- */
-VERSION {
- LINUX_2.6 {
- global:
- __vdso_clock_gettime;
- __vdso_gettimeofday;
- __vdso_getcpu;
- __vdso_time;
- local: *;
- };
-}
+++ /dev/null
-/*
- * Copyright 2006 Andi Kleen, SUSE Labs.
- * Subject to the GNU Public License, v.2
- *
- * Fast user context implementation of getcpu()
- */
-
-#include <linux/kernel.h>
-#include <linux/getcpu.h>
-#include <linux/time.h>
-#include <asm/vgtod.h>
-
-notrace long
-__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
-{
- unsigned int p;
-
- p = __getcpu();
-
- if (cpu)
- *cpu = p & VGETCPU_CPU_MASK;
- if (node)
- *node = p >> 12;
- return 0;
-}
-
-long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
- __attribute__((weak, alias("__vdso_getcpu")));
+++ /dev/null
-/*
- * Copyright 2007 Andi Kleen, SUSE Labs.
- * Subject to the GPL, v.2
- *
- * This contains most of the x86 vDSO kernel-side code.
- */
-#include <linux/mm.h>
-#include <linux/err.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/random.h>
-#include <linux/elf.h>
-#include <linux/cpu.h>
-#include <asm/vgtod.h>
-#include <asm/proto.h>
-#include <asm/vdso.h>
-#include <asm/vvar.h>
-#include <asm/page.h>
-#include <asm/hpet.h>
-#include <asm/desc.h>
-
-#if defined(CONFIG_X86_64)
-unsigned int __read_mostly vdso64_enabled = 1;
-#endif
-
-void __init init_vdso_image(const struct vdso_image *image)
-{
- int i;
- int npages = (image->size) / PAGE_SIZE;
-
- BUG_ON(image->size % PAGE_SIZE != 0);
- for (i = 0; i < npages; i++)
- image->text_mapping.pages[i] =
- virt_to_page(image->data + i*PAGE_SIZE);
-
- apply_alternatives((struct alt_instr *)(image->data + image->alt),
- (struct alt_instr *)(image->data + image->alt +
- image->alt_len));
-}
-
-struct linux_binprm;
-
-/*
- * Put the vdso above the (randomized) stack with another randomized
- * offset. This way there is no hole in the middle of address space.
- * To save memory make sure it is still in the same PTE as the stack
- * top. This doesn't give that many random bits.
- *
- * Note that this algorithm is imperfect: the distribution of the vdso
- * start address within a PMD is biased toward the end.
- *
- * Only used for the 64-bit and x32 vdsos.
- */
-static unsigned long vdso_addr(unsigned long start, unsigned len)
-{
-#ifdef CONFIG_X86_32
- return 0;
-#else
- unsigned long addr, end;
- unsigned offset;
-
- /*
- * Round up the start address. It can start out unaligned as a result
- * of stack start randomization.
- */
- start = PAGE_ALIGN(start);
-
- /* Round the lowest possible end address up to a PMD boundary. */
- end = (start + len + PMD_SIZE - 1) & PMD_MASK;
- if (end >= TASK_SIZE_MAX)
- end = TASK_SIZE_MAX;
- end -= len;
-
- if (end > start) {
- offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
- addr = start + (offset << PAGE_SHIFT);
- } else {
- addr = start;
- }
-
- /*
- * Forcibly align the final address in case we have a hardware
- * issue that requires alignment for performance reasons.
- */
- addr = align_vdso_addr(addr);
-
- return addr;
-#endif
-}
-
-static int map_vdso(const struct vdso_image *image, bool calculate_addr)
-{
- struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
- unsigned long addr, text_start;
- int ret = 0;
- static struct page *no_pages[] = {NULL};
- static struct vm_special_mapping vvar_mapping = {
- .name = "[vvar]",
- .pages = no_pages,
- };
-
- if (calculate_addr) {
- addr = vdso_addr(current->mm->start_stack,
- image->size - image->sym_vvar_start);
- } else {
- addr = 0;
- }
-
- down_write(&mm->mmap_sem);
-
- addr = get_unmapped_area(NULL, addr,
- image->size - image->sym_vvar_start, 0, 0);
- if (IS_ERR_VALUE(addr)) {
- ret = addr;
- goto up_fail;
- }
-
- text_start = addr - image->sym_vvar_start;
- current->mm->context.vdso = (void __user *)text_start;
-
- /*
- * MAYWRITE to allow gdb to COW and set breakpoints
- */
- vma = _install_special_mapping(mm,
- text_start,
- image->size,
- VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
- &image->text_mapping);
-
- if (IS_ERR(vma)) {
- ret = PTR_ERR(vma);
- goto up_fail;
- }
-
- vma = _install_special_mapping(mm,
- addr,
- -image->sym_vvar_start,
- VM_READ|VM_MAYREAD,
- &vvar_mapping);
-
- if (IS_ERR(vma)) {
- ret = PTR_ERR(vma);
- goto up_fail;
- }
-
- if (image->sym_vvar_page)
- ret = remap_pfn_range(vma,
- text_start + image->sym_vvar_page,
- __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
- PAGE_SIZE,
- PAGE_READONLY);
-
- if (ret)
- goto up_fail;
-
-#ifdef CONFIG_HPET_TIMER
- if (hpet_address && image->sym_hpet_page) {
- ret = io_remap_pfn_range(vma,
- text_start + image->sym_hpet_page,
- hpet_address >> PAGE_SHIFT,
- PAGE_SIZE,
- pgprot_noncached(PAGE_READONLY));
-
- if (ret)
- goto up_fail;
- }
-#endif
-
-up_fail:
- if (ret)
- current->mm->context.vdso = NULL;
-
- up_write(&mm->mmap_sem);
- return ret;
-}
-
-#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
-static int load_vdso32(void)
-{
- int ret;
-
- if (vdso32_enabled != 1) /* Other values all mean "disabled" */
- return 0;
-
- ret = map_vdso(selected_vdso32, false);
- if (ret)
- return ret;
-
- if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN)
- current_thread_info()->sysenter_return =
- current->mm->context.vdso +
- selected_vdso32->sym_VDSO32_SYSENTER_RETURN;
-
- return 0;
-}
-#endif
-
-#ifdef CONFIG_X86_64
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
-{
- if (!vdso64_enabled)
- return 0;
-
- return map_vdso(&vdso_image_64, true);
-}
-
-#ifdef CONFIG_COMPAT
-int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
- int uses_interp)
-{
-#ifdef CONFIG_X86_X32_ABI
- if (test_thread_flag(TIF_X32)) {
- if (!vdso64_enabled)
- return 0;
-
- return map_vdso(&vdso_image_x32, true);
- }
-#endif
-
- return load_vdso32();
-}
-#endif
-#else
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
-{
- return load_vdso32();
-}
-#endif
-
-#ifdef CONFIG_X86_64
-static __init int vdso_setup(char *s)
-{
- vdso64_enabled = simple_strtoul(s, NULL, 0);
- return 0;
-}
-__setup("vdso=", vdso_setup);
-#endif
-
-#ifdef CONFIG_X86_64
-static void vgetcpu_cpu_init(void *arg)
-{
- int cpu = smp_processor_id();
- struct desc_struct d = { };
- unsigned long node = 0;
-#ifdef CONFIG_NUMA
- node = cpu_to_node(cpu);
-#endif
- if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
- write_rdtscp_aux((node << 12) | cpu);
-
- /*
- * Store cpu number in limit so that it can be loaded
- * quickly in user space in vgetcpu. (12 bits for the CPU
- * and 8 bits for the node)
- */
- d.limit0 = cpu | ((node & 0xf) << 12);
- d.limit = node >> 4;
- d.type = 5; /* RO data, expand down, accessed */
- d.dpl = 3; /* Visible to user code */
- d.s = 1; /* Not a system segment */
- d.p = 1; /* Present */
- d.d = 1; /* 32-bit */
-
- write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
-}
-
-static int
-vgetcpu_cpu_notifier(struct notifier_block *n, unsigned long action, void *arg)
-{
- long cpu = (long)arg;
-
- if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
- smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
-
- return NOTIFY_DONE;
-}
-
-static int __init init_vdso(void)
-{
- init_vdso_image(&vdso_image_64);
-
-#ifdef CONFIG_X86_X32_ABI
- init_vdso_image(&vdso_image_x32);
-#endif
-
- cpu_notifier_register_begin();
-
- on_each_cpu(vgetcpu_cpu_init, NULL, 1);
- /* notifier priority > KVM */
- __hotcpu_notifier(vgetcpu_cpu_notifier, 30);
-
- cpu_notifier_register_done();
-
- return 0;
-}
-subsys_initcall(init_vdso);
-#endif /* CONFIG_X86_64 */
.read_tscp = native_read_tscp,
.iret = xen_iret,
- .irq_enable_sysexit = xen_sysexit,
#ifdef CONFIG_X86_64
.usergs_sysret32 = xen_sysret32,
.usergs_sysret64 = xen_sysret64,
+#else
+ .irq_enable_sysexit = xen_sysexit,
#endif
.load_tr_desc = paravirt_nop,
return;
/*
* For BSP, PSE PGE are set in probe_page_size_mask(), for APs
- * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
+ * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
*/
if (cpu_has_pse)
cr4_set_bits_and_update_boot(X86_CR4_PSE);
{
struct physdev_set_iopl set_iopl;
unsigned long initrd_start = 0;
+ u64 pat;
int rc;
if (!xen_start_info)
* Modify the cache mode translation tables to match Xen's PAT
* configuration.
*/
-
- pat_init_cache_modes();
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ pat_init_cache_modes(pat);
/* keep using Xen gdt for now; no urgent need to change it */
#include <linux/seq_file.h>
#include <linux/bootmem.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
#include <asm/cache.h>
#include <asm/setup.h>
#include "xen-ops.h"
#include "debugfs.h"
+static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
+static DEFINE_PER_CPU(char *, irq_name);
+static bool xen_pvspin = true;
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void xen_qlock_kick(int cpu)
+{
+ xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
+}
+
+/*
+ * Halt the current CPU & release it back to the host
+ */
+static void xen_qlock_wait(u8 *byte, u8 val)
+{
+ int irq = __this_cpu_read(lock_kicker_irq);
+
+ /* If kicker interrupts not initialized yet, just spin */
+ if (irq == -1)
+ return;
+
+ /* clear pending */
+ xen_clear_irq_pending(irq);
+ barrier();
+
+ /*
+ * We check the byte value after clearing pending IRQ to make sure
+ * that we won't miss a wakeup event because of the clearing.
+ *
+ * The sync_clear_bit() call in xen_clear_irq_pending() is atomic.
+ * So it is effectively a memory barrier for x86.
+ */
+ if (READ_ONCE(*byte) != val)
+ return;
+
+ /*
+ * If an interrupt happens here, it will leave the wakeup irq
+ * pending, which will cause xen_poll_irq() to return
+ * immediately.
+ */
+
+ /* Block until irq becomes pending (or perhaps a spurious wakeup) */
+ xen_poll_irq(irq);
+}
+
+#else /* CONFIG_QUEUED_SPINLOCKS */
+
enum xen_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
__ticket_t want;
};
-static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(char *, irq_name);
static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
static cpumask_t waiting_cpus;
-static bool xen_pvspin = true;
__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
{
int irq = __this_cpu_read(lock_kicker_irq);
}
}
}
+#endif /* CONFIG_QUEUED_SPINLOCKS */
static irqreturn_t dummy_handler(int irq, void *dev_id)
{
return;
}
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ __pv_init_lock_hash();
+ pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_lock_ops.wait = xen_qlock_wait;
+ pv_lock_ops.kick = xen_qlock_kick;
+#else
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
pv_lock_ops.unlock_kick = xen_unlock_kick;
+#endif
}
/*
}
early_param("xen_nopvspin", xen_parse_nopvspin);
-#ifdef CONFIG_XEN_DEBUG_FS
+#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS)
static struct dentry *d_spin_debug;
#include <asm/percpu.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
#include <xen/interface/xen.h>
ENDPATCH(xen_iret)
RELOC(xen_iret, 1b+1)
-/*
- * sysexit is not used for 64-bit processes, so it's only ever used to
- * return to 32-bit compat userspace.
- */
-ENTRY(xen_sysexit)
- pushq $__USER32_DS
- pushq %rcx
- pushq $X86_EFLAGS_IF
- pushq $__USER32_CS
- pushq %rdx
-
- pushq $0
-1: jmp hypercall_iret
-ENDPATCH(xen_sysexit)
-RELOC(xen_sysexit, 1b+1)
-
ENTRY(xen_sysret64)
/*
* We're already on the usermode stack at this point, but
* still with the kernel gs, so we can easily switch back
*/
movq %rsp, PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack), %rsp
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq $__USER_DS
pushq PER_CPU_VAR(rsp_scratch)
* still with the kernel gs, so we can easily switch back
*/
movq %rsp, PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(kernel_stack), %rsp
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq $__USER32_DS
pushq PER_CPU_VAR(rsp_scratch)
/* Normal 64-bit system call target */
ENTRY(xen_syscall_target)
undo_xen_syscall
- jmp system_call_after_swapgs
+ jmp entry_SYSCALL_64_after_swapgs
ENDPROC(xen_syscall_target)
#ifdef CONFIG_IA32_EMULATION
/* 32-bit compat syscall target */
ENTRY(xen_syscall32_target)
undo_xen_syscall
- jmp ia32_cstar_target
+ jmp entry_SYSCALL_compat
ENDPROC(xen_syscall32_target)
/* 32-bit compat sysenter target */
ENTRY(xen_sysenter_target)
undo_xen_syscall
- jmp ia32_sysenter_target
+ jmp entry_SYSENTER_compat
ENDPROC(xen_sysenter_target)
#else /* !CONFIG_IA32_EMULATION */
/* These are not functions, and cannot be called normally */
__visible void xen_iret(void);
+#ifdef CONFIG_X86_32
__visible void xen_sysexit(void);
+#endif
__visible void xen_sysret32(void);
__visible void xen_sysret64(void);
__visible void xen_adjust_exception_frame(void);
return -EINVAL;
}
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag,
+ struct dma_attrs *attrs)
+{
+ return NULL;
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
+{
+}
+
#endif /* _XTENSA_DMA_MAPPING_H */
}
#define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
{
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/hardirq.h>
+#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/hardirq.h>
-#include <asm/uaccess.h>
#include <asm/pgalloc.h>
DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST;
/* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm) {
+ if (faulthandler_disabled() || !mm) {
bad_page_fault(regs, address, SIGSEGV);
return;
}
enum fixed_addresses idx;
unsigned long vaddr;
+ preempt_disable();
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
}
pagefault_enable();
+ preempt_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
q->queue_lock = &q->__queue_lock;
spin_unlock_irq(lock);
+ bdi_destroy(&q->backing_dev_info);
+
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
}
EXPORT_SYMBOL(blk_init_queue_node);
+static void blk_queue_bio(struct request_queue *q, struct bio *bio);
+
struct request_queue *
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
spinlock_t *lock)
blk_rq_bio_prep(req->q, req, bio);
}
-void blk_queue_bio(struct request_queue *q, struct bio *bio)
+static void blk_queue_bio(struct request_queue *q, struct bio *bio)
{
const bool sync = !!(bio->bi_rw & REQ_SYNC);
struct blk_plug *plug;
spin_unlock_irq(q->queue_lock);
}
}
-EXPORT_SYMBOL_GPL(blk_queue_bio); /* for device mapper only */
/*
* If bio->bi_dev is a partition, remap the location
{
unsigned int ret;
- ret = cpumask_first(topology_thread_cpumask(cpu));
+ ret = cpumask_first(topology_sibling_cpumask(cpu));
if (ret < nr_cpu_ids)
return ret;
data.next = blk_rq_timeout(round_jiffies_up(data.next));
mod_timer(&q->timeout, data.next);
} else {
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_tag_idle(hctx);
+ queue_for_each_hw_ctx(q, hctx, i) {
+ /* the hctx may be unmapped, so check it here */
+ if (blk_mq_hw_queue_mapped(hctx))
+ blk_mq_tag_idle(hctx);
+ }
}
}
spin_lock(&hctx->lock);
list_splice(&rq_list, &hctx->dispatch);
spin_unlock(&hctx->lock);
+ /*
+ * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but
+ * it's possible the queue is stopped and restarted again
+ * before this. Queue restart will dispatch requests. And since
+ * requests in rq_list aren't added into hctx->dispatch yet,
+ * the requests in rq_list might get lost.
+ *
+ * blk_mq_run_hw_queue() already checks the STOPPED bit
+ **/
+ blk_mq_run_hw_queue(hctx, true);
}
}
return NOTIFY_OK;
}
-static int blk_mq_hctx_cpu_online(struct blk_mq_hw_ctx *hctx, int cpu)
-{
- struct request_queue *q = hctx->queue;
- struct blk_mq_tag_set *set = q->tag_set;
-
- if (set->tags[hctx->queue_num])
- return NOTIFY_OK;
-
- set->tags[hctx->queue_num] = blk_mq_init_rq_map(set, hctx->queue_num);
- if (!set->tags[hctx->queue_num])
- return NOTIFY_STOP;
-
- hctx->tags = set->tags[hctx->queue_num];
- return NOTIFY_OK;
-}
-
static int blk_mq_hctx_notify(void *data, unsigned long action,
unsigned int cpu)
{
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
return blk_mq_hctx_cpu_offline(hctx, cpu);
- else if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
- return blk_mq_hctx_cpu_online(hctx, cpu);
+
+ /*
+ * In case of CPU online, tags may be reallocated
+ * in blk_mq_map_swqueue() after mapping is updated.
+ */
return NOTIFY_OK;
}
+/* hctx->ctxs will be freed in queue's release handler */
static void blk_mq_exit_hctx(struct request_queue *q,
struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
blk_free_flush_queue(hctx->fq);
- kfree(hctx->ctxs);
blk_mq_free_bitmap(&hctx->ctx_map);
}
unsigned int i;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
+ struct blk_mq_tag_set *set = q->tag_set;
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
* disable it and free the request entries.
*/
if (!hctx->nr_ctx) {
- struct blk_mq_tag_set *set = q->tag_set;
-
if (set->tags[i]) {
blk_mq_free_rq_map(set, set->tags[i], i);
set->tags[i] = NULL;
- hctx->tags = NULL;
}
+ hctx->tags = NULL;
continue;
}
+ /* unmapped hw queue can be remapped after CPU topo changed */
+ if (!set->tags[i])
+ set->tags[i] = blk_mq_init_rq_map(set, i);
+ hctx->tags = set->tags[i];
+ WARN_ON(!hctx->tags);
+
/*
* Set the map size to the number of mapped software queues.
* This is more accurate and more efficient than looping
unsigned int i;
/* hctx kobj stays in hctx */
- queue_for_each_hw_ctx(q, hctx, i)
+ queue_for_each_hw_ctx(q, hctx, i) {
+ if (!hctx)
+ continue;
+ kfree(hctx->ctxs);
kfree(hctx);
+ }
kfree(q->queue_hw_ctx);
*/
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_freeze_queue_start(q);
- list_for_each_entry(q, &all_q_list, all_q_node)
+ list_for_each_entry(q, &all_q_list, all_q_node) {
blk_mq_freeze_queue_wait(q);
+ /*
+ * timeout handler can't touch hw queue during the
+ * reinitialization
+ */
+ del_timer_sync(&q->timeout);
+ }
+
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_queue_reinit(q);
blk_trace_shutdown(q);
- bdi_destroy(&q->backing_dev_info);
-
ida_simple_remove(&blk_queue_ida, q->id);
call_rcu(&q->rcu_head, blk_free_queue_rcu);
}
if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
continue;
- inc_zone_page_state(to->bv_page, NR_BOUNCE);
to->bv_page = mempool_alloc(pool, q->bounce_gfp);
+ inc_zone_page_state(to->bv_page, NR_BOUNCE);
if (rw == WRITE) {
char *vto, *vfrom;
eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node);
if (unlikely(!eq))
- goto err;
+ return NULL;
eq->type = e;
kobject_init(&eq->kobj, &elv_ktype);
hash_init(eq->hash);
return eq;
-err:
- kfree(eq);
- elevator_put(e);
- return NULL;
}
EXPORT_SYMBOL(elevator_alloc);
/* allocate ext devt */
idr_preload(GFP_KERNEL);
- spin_lock(&ext_devt_lock);
+ spin_lock_bh(&ext_devt_lock);
idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
- spin_unlock(&ext_devt_lock);
+ spin_unlock_bh(&ext_devt_lock);
idr_preload_end();
if (idx < 0)
return;
if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
- spin_lock(&ext_devt_lock);
+ spin_lock_bh(&ext_devt_lock);
idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
- spin_unlock(&ext_devt_lock);
+ spin_unlock_bh(&ext_devt_lock);
}
}
disk->flags &= ~GENHD_FL_UP;
sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
- bdi_unregister(&disk->queue->backing_dev_info);
blk_unregister_queue(disk);
blk_unregister_region(disk_devt(disk), disk->minors);
} else {
struct hd_struct *part;
- spin_lock(&ext_devt_lock);
+ spin_lock_bh(&ext_devt_lock);
part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
if (part && get_disk(part_to_disk(part))) {
*partno = part->partno;
disk = part_to_disk(part);
}
- spin_unlock(&ext_devt_lock);
+ spin_unlock_bh(&ext_devt_lock);
}
return disk;
This option enables the user-spaces interface for random
number generator algorithms.
-config CRYPTO_USER_API_AEAD
- tristate "User-space interface for AEAD cipher algorithms"
- depends on NET
- select CRYPTO_AEAD
- select CRYPTO_USER_API
- help
- This option enables the user-spaces interface for AEAD
- cipher algorithms.
-
config CRYPTO_HASH_INFO
bool
/*
* RSGL_MAX_ENTRIES is an artificial limit where user space at maximum
* can cause the kernel to allocate RSGL_MAX_ENTRIES * ALG_MAX_PAGES
- * bytes
+ * pages
*/
#define RSGL_MAX_ENTRIES ALG_MAX_PAGES
struct af_alg_sgl rsgl[RSGL_MAX_ENTRIES];
if (err < 0)
goto unlock;
usedpages += err;
- /* chain the new scatterlist with initial list */
+ /* chain the new scatterlist with previous one */
if (cnt)
- scatterwalk_crypto_chain(ctx->rsgl[0].sg,
- ctx->rsgl[cnt].sg, 1,
- sg_nents(ctx->rsgl[cnt-1].sg));
+ af_alg_link_sg(&ctx->rsgl[cnt-1], &ctx->rsgl[cnt]);
+
/* we do not need more iovecs as we have sufficient memory */
if (outlen <= usedpages)
break;
mutex_lock(&round_robin_lock);
cpumask_clear(tmp);
for_each_cpu(cpu, pad_busy_cpus)
- cpumask_or(tmp, tmp, topology_thread_cpumask(cpu));
+ cpumask_or(tmp, tmp, topology_sibling_cpumask(cpu));
cpumask_andnot(tmp, cpu_online_mask, tmp);
/* avoid HT sibilings if possible */
if (cpumask_empty(tmp))
{"PNPb006"},
/* cs423x-pnpbios */
{"CSC0100"},
+ {"CSC0103"},
+ {"CSC0110"},
{"CSC0000"},
{"GIM0100"}, /* Guillemot Turtlebeach something appears to be cs4232 compatible */
/* es18xx-pnpbios */
{"_SB_", ACPI_TYPE_DEVICE, NULL},
{"_SI_", ACPI_TYPE_LOCAL_SCOPE, NULL},
{"_TZ_", ACPI_TYPE_DEVICE, NULL},
- /*
- * March, 2015:
- * The _REV object is in the process of being deprecated, because
- * other ACPI implementations permanently return 2. Thus, it
- * has little or no value. Return 2 for compatibility with
- * other ACPI implementations.
- */
- {"_REV", ACPI_TYPE_INTEGER, ACPI_CAST_PTR(char, 2)},
+ {"_REV", ACPI_TYPE_INTEGER, (char *)ACPI_CA_SUPPORT_LEVEL},
{"_OS_", ACPI_TYPE_STRING, ACPI_OS_NAME},
- {"_GL_", ACPI_TYPE_MUTEX, ACPI_CAST_PTR(char, 1)},
+ {"_GL_", ACPI_TYPE_MUTEX, (char *)1},
#if !defined (ACPI_NO_METHOD_EXECUTION) || defined (ACPI_CONSTANT_EVAL_ONLY)
- {"_OSI", ACPI_TYPE_METHOD, ACPI_CAST_PTR(char, 1)},
+ {"_OSI", ACPI_TYPE_METHOD, (char *)1},
#endif
/* Table terminator */
#include <linux/nmi.h>
#include <linux/hardirq.h>
#include <linux/pstore.h>
+#include <linux/vmalloc.h>
#include <acpi/apei.h>
#include "apei-internal.h"
request_mem_region(addr, length, desc);
}
-static int __init acpi_reserve_resources(void)
+static void __init acpi_reserve_resources(void)
{
acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length,
"ACPI PM1a_EVT_BLK");
if (!(acpi_gbl_FADT.gpe1_block_length & 0x1))
acpi_request_region(&acpi_gbl_FADT.xgpe1_block,
acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK");
-
- return 0;
}
-device_initcall(acpi_reserve_resources);
void acpi_os_printf(const char *fmt, ...)
{
acpi_status __init acpi_os_initialize1(void)
{
+ acpi_reserve_resources();
kacpid_wq = alloc_workqueue("kacpid", 0, 1);
kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
* @ares: Input ACPI resource object.
* @types: Valid resource types of IORESOURCE_XXX
*
- * This is a hepler function to support acpi_dev_get_resources(), which filters
+ * This is a helper function to support acpi_dev_get_resources(), which filters
* ACPI resource objects according to resource types.
*/
int acpi_dev_filter_resource_type(struct acpi_resource *ares,
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/interrupt.h>
+#include <linux/dmi.h>
#include "sbshc.h"
#define PREFIX "ACPI: "
ACPI_SMB_ALARM_DATA = 0x26, /* 2 bytes alarm data */
};
+static bool macbook;
+
static inline int smb_hc_read(struct acpi_smb_hc *hc, u8 address, u8 *data)
{
return ec_read(hc->offset + address, data);
}
mutex_lock(&hc->lock);
+ if (macbook)
+ udelay(5);
if (smb_hc_read(hc, ACPI_SMB_PROTOCOL, &temp))
goto end;
if (temp) {
acpi_handle handle, acpi_ec_query_func func,
void *data);
+static int macbook_dmi_match(const struct dmi_system_id *d)
+{
+ pr_debug("Detected MacBook, enabling workaround\n");
+ macbook = true;
+ return 0;
+}
+
+static struct dmi_system_id acpi_smbus_dmi_table[] = {
+ { macbook_dmi_match, "Apple MacBook", {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBook") },
+ },
+ { },
+};
+
static int acpi_smbus_hc_add(struct acpi_device *device)
{
int status;
unsigned long long val;
struct acpi_smb_hc *hc;
+ dmi_check_system(acpi_smbus_dmi_table);
+
if (!device)
return -EINVAL;
config SATA_DWC
tristate "DesignWare Cores SATA support"
depends on 460EX
+ select DW_DMAC
help
This option enables support for the on-chip SATA controller of the
AppliedMicro processor 460EX.
If unsure, say N.
-config PATA_SCC
- tristate "Toshiba's Cell Reference Set IDE support"
- depends on PCI && PPC_CELLEB
- help
- This option enables support for the built-in IDE controller on
- Toshiba Cell Reference Board.
-
- If unsure, say N.
-
config PATA_SCH
tristate "Intel SCH PATA support"
depends on PCI
obj-$(CONFIG_PATA_RADISYS) += pata_radisys.o
obj-$(CONFIG_PATA_RDC) += pata_rdc.o
obj-$(CONFIG_PATA_SC1200) += pata_sc1200.o
-obj-$(CONFIG_PATA_SCC) += pata_scc.o
obj-$(CONFIG_PATA_SCH) += pata_sch.o
obj-$(CONFIG_PATA_SERVERWORKS) += pata_serverworks.o
obj-$(CONFIG_PATA_SIL680) += pata_sil680.o
board_ahci_yes_fbs,
/* board IDs for specific chipsets in alphabetical order */
+ board_ahci_avn,
board_ahci_mcp65,
board_ahci_mcp77,
board_ahci_mcp89,
static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
unsigned long deadline);
+static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
+ unsigned long deadline);
static void ahci_mcp89_apple_enable(struct pci_dev *pdev);
static bool is_mcp89_apple(struct pci_dev *pdev);
static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class,
.hardreset = ahci_p5wdh_hardreset,
};
+static struct ata_port_operations ahci_avn_ops = {
+ .inherits = &ahci_ops,
+ .hardreset = ahci_avn_hardreset,
+};
+
static const struct ata_port_info ahci_port_info[] = {
/* by features */
[board_ahci] = {
.port_ops = &ahci_ops,
},
/* by chipsets */
+ [board_ahci_avn] = {
+ .flags = AHCI_FLAG_COMMON,
+ .pio_mask = ATA_PIO4,
+ .udma_mask = ATA_UDMA6,
+ .port_ops = &ahci_avn_ops,
+ },
[board_ahci_mcp65] = {
AHCI_HFLAGS (AHCI_HFLAG_NO_FPDMA_AA | AHCI_HFLAG_NO_PMP |
AHCI_HFLAG_YES_NCQ),
{ PCI_VDEVICE(INTEL, 0x1f27), board_ahci }, /* Avoton RAID */
{ PCI_VDEVICE(INTEL, 0x1f2e), board_ahci }, /* Avoton RAID */
{ PCI_VDEVICE(INTEL, 0x1f2f), board_ahci }, /* Avoton RAID */
- { PCI_VDEVICE(INTEL, 0x1f32), board_ahci }, /* Avoton AHCI */
- { PCI_VDEVICE(INTEL, 0x1f33), board_ahci }, /* Avoton AHCI */
- { PCI_VDEVICE(INTEL, 0x1f34), board_ahci }, /* Avoton RAID */
- { PCI_VDEVICE(INTEL, 0x1f35), board_ahci }, /* Avoton RAID */
- { PCI_VDEVICE(INTEL, 0x1f36), board_ahci }, /* Avoton RAID */
- { PCI_VDEVICE(INTEL, 0x1f37), board_ahci }, /* Avoton RAID */
- { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci }, /* Avoton RAID */
- { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci }, /* Avoton RAID */
+ { PCI_VDEVICE(INTEL, 0x1f32), board_ahci_avn }, /* Avoton AHCI */
+ { PCI_VDEVICE(INTEL, 0x1f33), board_ahci_avn }, /* Avoton AHCI */
+ { PCI_VDEVICE(INTEL, 0x1f34), board_ahci_avn }, /* Avoton RAID */
+ { PCI_VDEVICE(INTEL, 0x1f35), board_ahci_avn }, /* Avoton RAID */
+ { PCI_VDEVICE(INTEL, 0x1f36), board_ahci_avn }, /* Avoton RAID */
+ { PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */
+ { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */
+ { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */
{ PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */
{ PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */
{ PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */
return rc;
}
+/*
+ * ahci_avn_hardreset - attempt more aggressive recovery of Avoton ports.
+ *
+ * It has been observed with some SSDs that the timing of events in the
+ * link synchronization phase can leave the port in a state that can not
+ * be recovered by a SATA-hard-reset alone. The failing signature is
+ * SStatus.DET stuck at 1 ("Device presence detected but Phy
+ * communication not established"). It was found that unloading and
+ * reloading the driver when this problem occurs allows the drive
+ * connection to be recovered (DET advanced to 0x3). The critical
+ * component of reloading the driver is that the port state machines are
+ * reset by bouncing "port enable" in the AHCI PCS configuration
+ * register. So, reproduce that effect by bouncing a port whenever we
+ * see DET==1 after a reset.
+ */
+static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
+ unsigned long deadline)
+{
+ const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context);
+ struct ata_port *ap = link->ap;
+ struct ahci_port_priv *pp = ap->private_data;
+ struct ahci_host_priv *hpriv = ap->host->private_data;
+ u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
+ unsigned long tmo = deadline - jiffies;
+ struct ata_taskfile tf;
+ bool online;
+ int rc, i;
+
+ DPRINTK("ENTER\n");
+
+ ahci_stop_engine(ap);
+
+ for (i = 0; i < 2; i++) {
+ u16 val;
+ u32 sstatus;
+ int port = ap->port_no;
+ struct ata_host *host = ap->host;
+ struct pci_dev *pdev = to_pci_dev(host->dev);
+
+ /* clear D2H reception area to properly wait for D2H FIS */
+ ata_tf_init(link->device, &tf);
+ tf.command = ATA_BUSY;
+ ata_tf_to_fis(&tf, 0, 0, d2h_fis);
+
+ rc = sata_link_hardreset(link, timing, deadline, &online,
+ ahci_check_ready);
+
+ if (sata_scr_read(link, SCR_STATUS, &sstatus) != 0 ||
+ (sstatus & 0xf) != 1)
+ break;
+
+ ata_link_printk(link, KERN_INFO, "avn bounce port%d\n",
+ port);
+
+ pci_read_config_word(pdev, 0x92, &val);
+ val &= ~(1 << port);
+ pci_write_config_word(pdev, 0x92, val);
+ ata_msleep(ap, 1000);
+ val |= 1 << port;
+ pci_write_config_word(pdev, 0x92, val);
+ deadline += tmo;
+ }
+
+ hpriv->start_engine(ap);
+
+ if (online)
+ *class = ahci_dev_classify(ap);
+
+ DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
+ return rc;
+}
+
+
#ifdef CONFIG_PM
static int ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
{
writel((cs->mbus_attr << 8) |
(dram->mbus_dram_target_id << 4) | 1,
hpriv->mmio + AHCI_WINDOW_CTRL(i));
- writel(cs->base, hpriv->mmio + AHCI_WINDOW_BASE(i));
+ writel(cs->base >> 16, hpriv->mmio + AHCI_WINDOW_BASE(i));
writel(((cs->size - 1) & 0xffff0000),
hpriv->mmio + AHCI_WINDOW_SIZE(i));
}
struct reset_control *pwr;
struct reset_control *sw_rst;
struct reset_control *pwr_rst;
- struct ahci_host_priv *hpriv;
};
static void st_ahci_configure_oob(void __iomem *mmio)
writel(new_val, mmio + ST_AHCI_OOBR);
}
-static int st_ahci_deassert_resets(struct device *dev)
+static int st_ahci_deassert_resets(struct ahci_host_priv *hpriv,
+ struct device *dev)
{
- struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
+ struct st_ahci_drv_data *drv_data = hpriv->plat_data;
int err;
if (drv_data->pwr) {
static void st_ahci_host_stop(struct ata_host *host)
{
struct ahci_host_priv *hpriv = host->private_data;
+ struct st_ahci_drv_data *drv_data = hpriv->plat_data;
struct device *dev = host->dev;
- struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
int err;
if (drv_data->pwr) {
ahci_platform_disable_resources(hpriv);
}
-static int st_ahci_probe_resets(struct platform_device *pdev)
+static int st_ahci_probe_resets(struct ahci_host_priv *hpriv,
+ struct device *dev)
{
- struct st_ahci_drv_data *drv_data = platform_get_drvdata(pdev);
+ struct st_ahci_drv_data *drv_data = hpriv->plat_data;
- drv_data->pwr = devm_reset_control_get(&pdev->dev, "pwr-dwn");
+ drv_data->pwr = devm_reset_control_get(dev, "pwr-dwn");
if (IS_ERR(drv_data->pwr)) {
- dev_info(&pdev->dev, "power reset control not defined\n");
+ dev_info(dev, "power reset control not defined\n");
drv_data->pwr = NULL;
}
- drv_data->sw_rst = devm_reset_control_get(&pdev->dev, "sw-rst");
+ drv_data->sw_rst = devm_reset_control_get(dev, "sw-rst");
if (IS_ERR(drv_data->sw_rst)) {
- dev_info(&pdev->dev, "soft reset control not defined\n");
+ dev_info(dev, "soft reset control not defined\n");
drv_data->sw_rst = NULL;
}
- drv_data->pwr_rst = devm_reset_control_get(&pdev->dev, "pwr-rst");
+ drv_data->pwr_rst = devm_reset_control_get(dev, "pwr-rst");
if (IS_ERR(drv_data->pwr_rst)) {
- dev_dbg(&pdev->dev, "power soft reset control not defined\n");
+ dev_dbg(dev, "power soft reset control not defined\n");
drv_data->pwr_rst = NULL;
}
- return st_ahci_deassert_resets(&pdev->dev);
+ return st_ahci_deassert_resets(hpriv, dev);
}
static struct ata_port_operations st_ahci_port_ops = {
if (!drv_data)
return -ENOMEM;
- platform_set_drvdata(pdev, drv_data);
-
hpriv = ahci_platform_get_resources(pdev);
if (IS_ERR(hpriv))
return PTR_ERR(hpriv);
+ hpriv->plat_data = drv_data;
- drv_data->hpriv = hpriv;
-
- err = st_ahci_probe_resets(pdev);
+ err = st_ahci_probe_resets(hpriv, &pdev->dev);
if (err)
return err;
if (err)
return err;
- st_ahci_configure_oob(drv_data->hpriv->mmio);
+ st_ahci_configure_oob(hpriv->mmio);
err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info,
&ahci_platform_sht);
#ifdef CONFIG_PM_SLEEP
static int st_ahci_suspend(struct device *dev)
{
- struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
- struct ahci_host_priv *hpriv = drv_data->hpriv;
+ struct ata_host *host = dev_get_drvdata(dev);
+ struct ahci_host_priv *hpriv = host->private_data;
+ struct st_ahci_drv_data *drv_data = hpriv->plat_data;
int err;
err = ahci_platform_suspend_host(dev);
static int st_ahci_resume(struct device *dev)
{
- struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
- struct ahci_host_priv *hpriv = drv_data->hpriv;
+ struct ata_host *host = dev_get_drvdata(dev);
+ struct ahci_host_priv *hpriv = host->private_data;
int err;
err = ahci_platform_enable_resources(hpriv);
if (err)
return err;
- err = st_ahci_deassert_resets(dev);
+ err = st_ahci_deassert_resets(hpriv, dev);
if (err) {
ahci_platform_disable_resources(hpriv);
return err;
}
- st_ahci_configure_oob(drv_data->hpriv->mmio);
+ st_ahci_configure_oob(hpriv->mmio);
return ahci_platform_resume_host(dev);
}
if (unlikely(resetting))
status &= ~PORT_IRQ_BAD_PMP;
- /* if LPM is enabled, PHYRDY doesn't mean anything */
- if (ap->link.lpm_policy > ATA_LPM_MAX_POWER) {
+ if (sata_lpm_ignore_phy_events(&ap->link)) {
status &= ~PORT_IRQ_PHYRDY;
ahci_scr_write(&ap->link, SCR_ERROR, SERR_PHYRDY_CHG);
}
ATA_HORKAGE_ZERO_AFTER_TRIM, },
{ "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM |
ATA_HORKAGE_ZERO_AFTER_TRIM, },
- { "Samsung SSD 850 PRO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM |
+ { "Samsung SSD 8*", NULL, ATA_HORKAGE_NO_NCQ_TRIM |
ATA_HORKAGE_ZERO_AFTER_TRIM, },
/*
return tmp;
}
+/**
+ * sata_lpm_ignore_phy_events - test if PHY event should be ignored
+ * @link: Link receiving the event
+ *
+ * Test whether the received PHY event has to be ignored or not.
+ *
+ * LOCKING:
+ * None:
+ *
+ * RETURNS:
+ * True if the event has to be ignored.
+ */
+bool sata_lpm_ignore_phy_events(struct ata_link *link)
+{
+ unsigned long lpm_timeout = link->last_lpm_change +
+ msecs_to_jiffies(ATA_TMOUT_SPURIOUS_PHY);
+
+ /* if LPM is enabled, PHYRDY doesn't mean anything */
+ if (link->lpm_policy > ATA_LPM_MAX_POWER)
+ return true;
+
+ /* ignore the first PHY event after the LPM policy changed
+ * as it is might be spurious
+ */
+ if ((link->flags & ATA_LFLAG_CHANGED) &&
+ time_before(jiffies, lpm_timeout))
+ return true;
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events);
+
/*
* Dummy port_ops
*/
}
}
+ link->last_lpm_change = jiffies;
+ link->flags |= ATA_LFLAG_CHANGED;
+
return 0;
fail:
},
{},
};
-MODULE_DEVICE_TABLE(of, octeon_i2c_match);
+MODULE_DEVICE_TABLE(of, octeon_cf_match);
static struct platform_driver octeon_cf_driver = {
.probe = octeon_cf_probe,
+++ /dev/null
-/*
- * Support for IDE interfaces on Celleb platform
- *
- * (C) Copyright 2006 TOSHIBA CORPORATION
- *
- * This code is based on drivers/ata/ata_piix.c:
- * Copyright 2003-2005 Red Hat Inc
- * Copyright 2003-2005 Jeff Garzik
- * Copyright (C) 1998-1999 Andrzej Krzysztofowicz, Author and Maintainer
- * Copyright (C) 1998-2000 Andre Hedrick <andre@linux-ide.org>
- * Copyright (C) 2003 Red Hat Inc
- *
- * and drivers/ata/ahci.c:
- * Copyright 2004-2005 Red Hat, Inc.
- *
- * and drivers/ata/libata-core.c:
- * Copyright 2003-2004 Red Hat, Inc. All rights reserved.
- * Copyright 2003-2004 Jeff Garzik
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/blkdev.h>
-#include <linux/delay.h>
-#include <linux/device.h>
-#include <scsi/scsi_host.h>
-#include <linux/libata.h>
-
-#define DRV_NAME "pata_scc"
-#define DRV_VERSION "0.3"
-
-#define PCI_DEVICE_ID_TOSHIBA_SCC_ATA 0x01b4
-
-/* PCI BARs */
-#define SCC_CTRL_BAR 0
-#define SCC_BMID_BAR 1
-
-/* offset of CTRL registers */
-#define SCC_CTL_PIOSHT 0x000
-#define SCC_CTL_PIOCT 0x004
-#define SCC_CTL_MDMACT 0x008
-#define SCC_CTL_MCRCST 0x00C
-#define SCC_CTL_SDMACT 0x010
-#define SCC_CTL_SCRCST 0x014
-#define SCC_CTL_UDENVT 0x018
-#define SCC_CTL_TDVHSEL 0x020
-#define SCC_CTL_MODEREG 0x024
-#define SCC_CTL_ECMODE 0xF00
-#define SCC_CTL_MAEA0 0xF50
-#define SCC_CTL_MAEC0 0xF54
-#define SCC_CTL_CCKCTRL 0xFF0
-
-/* offset of BMID registers */
-#define SCC_DMA_CMD 0x000
-#define SCC_DMA_STATUS 0x004
-#define SCC_DMA_TABLE_OFS 0x008
-#define SCC_DMA_INTMASK 0x010
-#define SCC_DMA_INTST 0x014
-#define SCC_DMA_PTERADD 0x018
-#define SCC_REG_CMD_ADDR 0x020
-#define SCC_REG_DATA 0x000
-#define SCC_REG_ERR 0x004
-#define SCC_REG_FEATURE 0x004
-#define SCC_REG_NSECT 0x008
-#define SCC_REG_LBAL 0x00C
-#define SCC_REG_LBAM 0x010
-#define SCC_REG_LBAH 0x014
-#define SCC_REG_DEVICE 0x018
-#define SCC_REG_STATUS 0x01C
-#define SCC_REG_CMD 0x01C
-#define SCC_REG_ALTSTATUS 0x020
-
-/* register value */
-#define TDVHSEL_MASTER 0x00000001
-#define TDVHSEL_SLAVE 0x00000004
-
-#define MODE_JCUSFEN 0x00000080
-
-#define ECMODE_VALUE 0x01
-
-#define CCKCTRL_ATARESET 0x00040000
-#define CCKCTRL_BUFCNT 0x00020000
-#define CCKCTRL_CRST 0x00010000
-#define CCKCTRL_OCLKEN 0x00000100
-#define CCKCTRL_ATACLKOEN 0x00000002
-#define CCKCTRL_LCLKEN 0x00000001
-
-#define QCHCD_IOS_SS 0x00000001
-
-#define QCHSD_STPDIAG 0x00020000
-
-#define INTMASK_MSK 0xD1000012
-#define INTSTS_SERROR 0x80000000
-#define INTSTS_PRERR 0x40000000
-#define INTSTS_RERR 0x10000000
-#define INTSTS_ICERR 0x01000000
-#define INTSTS_BMSINT 0x00000010
-#define INTSTS_BMHE 0x00000008
-#define INTSTS_IOIRQS 0x00000004
-#define INTSTS_INTRQ 0x00000002
-#define INTSTS_ACTEINT 0x00000001
-
-
-/* PIO transfer mode table */
-/* JCHST */
-static const unsigned long JCHSTtbl[2][7] = {
- {0x0E, 0x05, 0x02, 0x03, 0x02, 0x00, 0x00}, /* 100MHz */
- {0x13, 0x07, 0x04, 0x04, 0x03, 0x00, 0x00} /* 133MHz */
-};
-
-/* JCHHT */
-static const unsigned long JCHHTtbl[2][7] = {
- {0x0E, 0x02, 0x02, 0x02, 0x02, 0x00, 0x00}, /* 100MHz */
- {0x13, 0x03, 0x03, 0x03, 0x03, 0x00, 0x00} /* 133MHz */
-};
-
-/* JCHCT */
-static const unsigned long JCHCTtbl[2][7] = {
- {0x1D, 0x1D, 0x1C, 0x0B, 0x06, 0x00, 0x00}, /* 100MHz */
- {0x27, 0x26, 0x26, 0x0E, 0x09, 0x00, 0x00} /* 133MHz */
-};
-
-/* DMA transfer mode table */
-/* JCHDCTM/JCHDCTS */
-static const unsigned long JCHDCTxtbl[2][7] = {
- {0x0A, 0x06, 0x04, 0x03, 0x01, 0x00, 0x00}, /* 100MHz */
- {0x0E, 0x09, 0x06, 0x04, 0x02, 0x01, 0x00} /* 133MHz */
-};
-
-/* JCSTWTM/JCSTWTS */
-static const unsigned long JCSTWTxtbl[2][7] = {
- {0x06, 0x04, 0x03, 0x02, 0x02, 0x02, 0x00}, /* 100MHz */
- {0x09, 0x06, 0x04, 0x02, 0x02, 0x02, 0x02} /* 133MHz */
-};
-
-/* JCTSS */
-static const unsigned long JCTSStbl[2][7] = {
- {0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x00}, /* 100MHz */
- {0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05} /* 133MHz */
-};
-
-/* JCENVT */
-static const unsigned long JCENVTtbl[2][7] = {
- {0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x00}, /* 100MHz */
- {0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02} /* 133MHz */
-};
-
-/* JCACTSELS/JCACTSELM */
-static const unsigned long JCACTSELtbl[2][7] = {
- {0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x00}, /* 100MHz */
- {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01} /* 133MHz */
-};
-
-static const struct pci_device_id scc_pci_tbl[] = {
- { PCI_VDEVICE(TOSHIBA_2, PCI_DEVICE_ID_TOSHIBA_SCC_ATA), 0},
- { } /* terminate list */
-};
-
-/**
- * scc_set_piomode - Initialize host controller PATA PIO timings
- * @ap: Port whose timings we are configuring
- * @adev: um
- *
- * Set PIO mode for device.
- *
- * LOCKING:
- * None (inherited from caller).
- */
-
-static void scc_set_piomode (struct ata_port *ap, struct ata_device *adev)
-{
- unsigned int pio = adev->pio_mode - XFER_PIO_0;
- void __iomem *ctrl_base = ap->host->iomap[SCC_CTRL_BAR];
- void __iomem *cckctrl_port = ctrl_base + SCC_CTL_CCKCTRL;
- void __iomem *piosht_port = ctrl_base + SCC_CTL_PIOSHT;
- void __iomem *pioct_port = ctrl_base + SCC_CTL_PIOCT;
- unsigned long reg;
- int offset;
-
- reg = in_be32(cckctrl_port);
- if (reg & CCKCTRL_ATACLKOEN)
- offset = 1; /* 133MHz */
- else
- offset = 0; /* 100MHz */
-
- reg = JCHSTtbl[offset][pio] << 16 | JCHHTtbl[offset][pio];
- out_be32(piosht_port, reg);
- reg = JCHCTtbl[offset][pio];
- out_be32(pioct_port, reg);
-}
-
-/**
- * scc_set_dmamode - Initialize host controller PATA DMA timings
- * @ap: Port whose timings we are configuring
- * @adev: um
- *
- * Set UDMA mode for device.
- *
- * LOCKING:
- * None (inherited from caller).
- */
-
-static void scc_set_dmamode (struct ata_port *ap, struct ata_device *adev)
-{
- unsigned int udma = adev->dma_mode;
- unsigned int is_slave = (adev->devno != 0);
- u8 speed = udma;
- void __iomem *ctrl_base = ap->host->iomap[SCC_CTRL_BAR];
- void __iomem *cckctrl_port = ctrl_base + SCC_CTL_CCKCTRL;
- void __iomem *mdmact_port = ctrl_base + SCC_CTL_MDMACT;
- void __iomem *mcrcst_port = ctrl_base + SCC_CTL_MCRCST;
- void __iomem *sdmact_port = ctrl_base + SCC_CTL_SDMACT;
- void __iomem *scrcst_port = ctrl_base + SCC_CTL_SCRCST;
- void __iomem *udenvt_port = ctrl_base + SCC_CTL_UDENVT;
- void __iomem *tdvhsel_port = ctrl_base + SCC_CTL_TDVHSEL;
- int offset, idx;
-
- if (in_be32(cckctrl_port) & CCKCTRL_ATACLKOEN)
- offset = 1; /* 133MHz */
- else
- offset = 0; /* 100MHz */
-
- if (speed >= XFER_UDMA_0)
- idx = speed - XFER_UDMA_0;
- else
- return;
-
- if (is_slave) {
- out_be32(sdmact_port, JCHDCTxtbl[offset][idx]);
- out_be32(scrcst_port, JCSTWTxtbl[offset][idx]);
- out_be32(tdvhsel_port,
- (in_be32(tdvhsel_port) & ~TDVHSEL_SLAVE) | (JCACTSELtbl[offset][idx] << 2));
- } else {
- out_be32(mdmact_port, JCHDCTxtbl[offset][idx]);
- out_be32(mcrcst_port, JCSTWTxtbl[offset][idx]);
- out_be32(tdvhsel_port,
- (in_be32(tdvhsel_port) & ~TDVHSEL_MASTER) | JCACTSELtbl[offset][idx]);
- }
- out_be32(udenvt_port,
- JCTSStbl[offset][idx] << 16 | JCENVTtbl[offset][idx]);
-}
-
-unsigned long scc_mode_filter(struct ata_device *adev, unsigned long mask)
-{
- /* errata A308 workaround: limit ATAPI UDMA mode to UDMA4 */
- if (adev->class == ATA_DEV_ATAPI &&
- (mask & (0xE0 << ATA_SHIFT_UDMA))) {
- printk(KERN_INFO "%s: limit ATAPI UDMA to UDMA4\n", DRV_NAME);
- mask &= ~(0xE0 << ATA_SHIFT_UDMA);
- }
- return mask;
-}
-
-/**
- * scc_tf_load - send taskfile registers to host controller
- * @ap: Port to which output is sent
- * @tf: ATA taskfile register set
- *
- * Note: Original code is ata_sff_tf_load().
- */
-
-static void scc_tf_load (struct ata_port *ap, const struct ata_taskfile *tf)
-{
- struct ata_ioports *ioaddr = &ap->ioaddr;
- unsigned int is_addr = tf->flags & ATA_TFLAG_ISADDR;
-
- if (tf->ctl != ap->last_ctl) {
- out_be32(ioaddr->ctl_addr, tf->ctl);
- ap->last_ctl = tf->ctl;
- ata_wait_idle(ap);
- }
-
- if (is_addr && (tf->flags & ATA_TFLAG_LBA48)) {
- out_be32(ioaddr->feature_addr, tf->hob_feature);
- out_be32(ioaddr->nsect_addr, tf->hob_nsect);
- out_be32(ioaddr->lbal_addr, tf->hob_lbal);
- out_be32(ioaddr->lbam_addr, tf->hob_lbam);
- out_be32(ioaddr->lbah_addr, tf->hob_lbah);
- VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n",
- tf->hob_feature,
- tf->hob_nsect,
- tf->hob_lbal,
- tf->hob_lbam,
- tf->hob_lbah);
- }
-
- if (is_addr) {
- out_be32(ioaddr->feature_addr, tf->feature);
- out_be32(ioaddr->nsect_addr, tf->nsect);
- out_be32(ioaddr->lbal_addr, tf->lbal);
- out_be32(ioaddr->lbam_addr, tf->lbam);
- out_be32(ioaddr->lbah_addr, tf->lbah);
- VPRINTK("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n",
- tf->feature,
- tf->nsect,
- tf->lbal,
- tf->lbam,
- tf->lbah);
- }
-
- if (tf->flags & ATA_TFLAG_DEVICE) {
- out_be32(ioaddr->device_addr, tf->device);
- VPRINTK("device 0x%X\n", tf->device);
- }
-
- ata_wait_idle(ap);
-}
-
-/**
- * scc_check_status - Read device status reg & clear interrupt
- * @ap: port where the device is
- *
- * Note: Original code is ata_check_status().
- */
-
-static u8 scc_check_status (struct ata_port *ap)
-{
- return in_be32(ap->ioaddr.status_addr);
-}
-
-/**
- * scc_tf_read - input device's ATA taskfile shadow registers
- * @ap: Port from which input is read
- * @tf: ATA taskfile register set for storing input
- *
- * Note: Original code is ata_sff_tf_read().
- */
-
-static void scc_tf_read (struct ata_port *ap, struct ata_taskfile *tf)
-{
- struct ata_ioports *ioaddr = &ap->ioaddr;
-
- tf->command = scc_check_status(ap);
- tf->feature = in_be32(ioaddr->error_addr);
- tf->nsect = in_be32(ioaddr->nsect_addr);
- tf->lbal = in_be32(ioaddr->lbal_addr);
- tf->lbam = in_be32(ioaddr->lbam_addr);
- tf->lbah = in_be32(ioaddr->lbah_addr);
- tf->device = in_be32(ioaddr->device_addr);
-
- if (tf->flags & ATA_TFLAG_LBA48) {
- out_be32(ioaddr->ctl_addr, tf->ctl | ATA_HOB);
- tf->hob_feature = in_be32(ioaddr->error_addr);
- tf->hob_nsect = in_be32(ioaddr->nsect_addr);
- tf->hob_lbal = in_be32(ioaddr->lbal_addr);
- tf->hob_lbam = in_be32(ioaddr->lbam_addr);
- tf->hob_lbah = in_be32(ioaddr->lbah_addr);
- out_be32(ioaddr->ctl_addr, tf->ctl);
- ap->last_ctl = tf->ctl;
- }
-}
-
-/**
- * scc_exec_command - issue ATA command to host controller
- * @ap: port to which command is being issued
- * @tf: ATA taskfile register set
- *
- * Note: Original code is ata_sff_exec_command().
- */
-
-static void scc_exec_command (struct ata_port *ap,
- const struct ata_taskfile *tf)
-{
- DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command);
-
- out_be32(ap->ioaddr.command_addr, tf->command);
- ata_sff_pause(ap);
-}
-
-/**
- * scc_check_altstatus - Read device alternate status reg
- * @ap: port where the device is
- */
-
-static u8 scc_check_altstatus (struct ata_port *ap)
-{
- return in_be32(ap->ioaddr.altstatus_addr);
-}
-
-/**
- * scc_dev_select - Select device 0/1 on ATA bus
- * @ap: ATA channel to manipulate
- * @device: ATA device (numbered from zero) to select
- *
- * Note: Original code is ata_sff_dev_select().
- */
-
-static void scc_dev_select (struct ata_port *ap, unsigned int device)
-{
- u8 tmp;
-
- if (device == 0)
- tmp = ATA_DEVICE_OBS;
- else
- tmp = ATA_DEVICE_OBS | ATA_DEV1;
-
- out_be32(ap->ioaddr.device_addr, tmp);
- ata_sff_pause(ap);
-}
-
-/**
- * scc_set_devctl - Write device control reg
- * @ap: port where the device is
- * @ctl: value to write
- */
-
-static void scc_set_devctl(struct ata_port *ap, u8 ctl)
-{
- out_be32(ap->ioaddr.ctl_addr, ctl);
-}
-
-/**
- * scc_bmdma_setup - Set up PCI IDE BMDMA transaction
- * @qc: Info associated with this ATA transaction.
- *
- * Note: Original code is ata_bmdma_setup().
- */
-
-static void scc_bmdma_setup (struct ata_queued_cmd *qc)
-{
- struct ata_port *ap = qc->ap;
- unsigned int rw = (qc->tf.flags & ATA_TFLAG_WRITE);
- u8 dmactl;
- void __iomem *mmio = ap->ioaddr.bmdma_addr;
-
- /* load PRD table addr */
- out_be32(mmio + SCC_DMA_TABLE_OFS, ap->bmdma_prd_dma);
-
- /* specify data direction, triple-check start bit is clear */
- dmactl = in_be32(mmio + SCC_DMA_CMD);
- dmactl &= ~(ATA_DMA_WR | ATA_DMA_START);
- if (!rw)
- dmactl |= ATA_DMA_WR;
- out_be32(mmio + SCC_DMA_CMD, dmactl);
-
- /* issue r/w command */
- ap->ops->sff_exec_command(ap, &qc->tf);
-}
-
-/**
- * scc_bmdma_start - Start a PCI IDE BMDMA transaction
- * @qc: Info associated with this ATA transaction.
- *
- * Note: Original code is ata_bmdma_start().
- */
-
-static void scc_bmdma_start (struct ata_queued_cmd *qc)
-{
- struct ata_port *ap = qc->ap;
- u8 dmactl;
- void __iomem *mmio = ap->ioaddr.bmdma_addr;
-
- /* start host DMA transaction */
- dmactl = in_be32(mmio + SCC_DMA_CMD);
- out_be32(mmio + SCC_DMA_CMD, dmactl | ATA_DMA_START);
-}
-
-/**
- * scc_devchk - PATA device presence detection
- * @ap: ATA channel to examine
- * @device: Device to examine (starting at zero)
- *
- * Note: Original code is ata_devchk().
- */
-
-static unsigned int scc_devchk (struct ata_port *ap,
- unsigned int device)
-{
- struct ata_ioports *ioaddr = &ap->ioaddr;
- u8 nsect, lbal;
-
- ap->ops->sff_dev_select(ap, device);
-
- out_be32(ioaddr->nsect_addr, 0x55);
- out_be32(ioaddr->lbal_addr, 0xaa);
-
- out_be32(ioaddr->nsect_addr, 0xaa);
- out_be32(ioaddr->lbal_addr, 0x55);
-
- out_be32(ioaddr->nsect_addr, 0x55);
- out_be32(ioaddr->lbal_addr, 0xaa);
-
- nsect = in_be32(ioaddr->nsect_addr);
- lbal = in_be32(ioaddr->lbal_addr);
-
- if ((nsect == 0x55) && (lbal == 0xaa))
- return 1; /* we found a device */
-
- return 0; /* nothing found */
-}
-
-/**
- * scc_wait_after_reset - wait for devices to become ready after reset
- *
- * Note: Original code is ata_sff_wait_after_reset
- */
-
-static int scc_wait_after_reset(struct ata_link *link, unsigned int devmask,
- unsigned long deadline)
-{
- struct ata_port *ap = link->ap;
- struct ata_ioports *ioaddr = &ap->ioaddr;
- unsigned int dev0 = devmask & (1 << 0);
- unsigned int dev1 = devmask & (1 << 1);
- int rc, ret = 0;
-
- /* Spec mandates ">= 2ms" before checking status. We wait
- * 150ms, because that was the magic delay used for ATAPI
- * devices in Hale Landis's ATADRVR, for the period of time
- * between when the ATA command register is written, and then
- * status is checked. Because waiting for "a while" before
- * checking status is fine, post SRST, we perform this magic
- * delay here as well.
- *
- * Old drivers/ide uses the 2mS rule and then waits for ready.
- */
- ata_msleep(ap, 150);
-
- /* always check readiness of the master device */
- rc = ata_sff_wait_ready(link, deadline);
- /* -ENODEV means the odd clown forgot the D7 pulldown resistor
- * and TF status is 0xff, bail out on it too.
- */
- if (rc)
- return rc;
-
- /* if device 1 was found in ata_devchk, wait for register
- * access briefly, then wait for BSY to clear.
- */
- if (dev1) {
- int i;
-
- ap->ops->sff_dev_select(ap, 1);
-
- /* Wait for register access. Some ATAPI devices fail
- * to set nsect/lbal after reset, so don't waste too
- * much time on it. We're gonna wait for !BSY anyway.
- */
- for (i = 0; i < 2; i++) {
- u8 nsect, lbal;
-
- nsect = in_be32(ioaddr->nsect_addr);
- lbal = in_be32(ioaddr->lbal_addr);
- if ((nsect == 1) && (lbal == 1))
- break;
- ata_msleep(ap, 50); /* give drive a breather */
- }
-
- rc = ata_sff_wait_ready(link, deadline);
- if (rc) {
- if (rc != -ENODEV)
- return rc;
- ret = rc;
- }
- }
-
- /* is all this really necessary? */
- ap->ops->sff_dev_select(ap, 0);
- if (dev1)
- ap->ops->sff_dev_select(ap, 1);
- if (dev0)
- ap->ops->sff_dev_select(ap, 0);
-
- return ret;
-}
-
-/**
- * scc_bus_softreset - PATA device software reset
- *
- * Note: Original code is ata_bus_softreset().
- */
-
-static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
- unsigned long deadline)
-{
- struct ata_ioports *ioaddr = &ap->ioaddr;
-
- DPRINTK("ata%u: bus reset via SRST\n", ap->print_id);
-
- /* software reset. causes dev0 to be selected */
- out_be32(ioaddr->ctl_addr, ap->ctl);
- udelay(20);
- out_be32(ioaddr->ctl_addr, ap->ctl | ATA_SRST);
- udelay(20);
- out_be32(ioaddr->ctl_addr, ap->ctl);
-
- return scc_wait_after_reset(&ap->link, devmask, deadline);
-}
-
-/**
- * scc_softreset - reset host port via ATA SRST
- * @ap: port to reset
- * @classes: resulting classes of attached devices
- * @deadline: deadline jiffies for the operation
- *
- * Note: Original code is ata_sff_softreset().
- */
-
-static int scc_softreset(struct ata_link *link, unsigned int *classes,
- unsigned long deadline)
-{
- struct ata_port *ap = link->ap;
- unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS;
- unsigned int devmask = 0;
- int rc;
- u8 err;
-
- DPRINTK("ENTER\n");
-
- /* determine if device 0/1 are present */
- if (scc_devchk(ap, 0))
- devmask |= (1 << 0);
- if (slave_possible && scc_devchk(ap, 1))
- devmask |= (1 << 1);
-
- /* select device 0 again */
- ap->ops->sff_dev_select(ap, 0);
-
- /* issue bus reset */
- DPRINTK("about to softreset, devmask=%x\n", devmask);
- rc = scc_bus_softreset(ap, devmask, deadline);
- if (rc) {
- ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc);
- return -EIO;
- }
-
- /* determine by signature whether we have ATA or ATAPI devices */
- classes[0] = ata_sff_dev_classify(&ap->link.device[0],
- devmask & (1 << 0), &err);
- if (slave_possible && err != 0x81)
- classes[1] = ata_sff_dev_classify(&ap->link.device[1],
- devmask & (1 << 1), &err);
-
- DPRINTK("EXIT, classes[0]=%u [1]=%u\n", classes[0], classes[1]);
- return 0;
-}
-
-/**
- * scc_bmdma_stop - Stop PCI IDE BMDMA transfer
- * @qc: Command we are ending DMA for
- */
-
-static void scc_bmdma_stop (struct ata_queued_cmd *qc)
-{
- struct ata_port *ap = qc->ap;
- void __iomem *ctrl_base = ap->host->iomap[SCC_CTRL_BAR];
- void __iomem *bmid_base = ap->host->iomap[SCC_BMID_BAR];
- u32 reg;
-
- while (1) {
- reg = in_be32(bmid_base + SCC_DMA_INTST);
-
- if (reg & INTSTS_SERROR) {
- printk(KERN_WARNING "%s: SERROR\n", DRV_NAME);
- out_be32(bmid_base + SCC_DMA_INTST, INTSTS_SERROR|INTSTS_BMSINT);
- out_be32(bmid_base + SCC_DMA_CMD,
- in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
- continue;
- }
-
- if (reg & INTSTS_PRERR) {
- u32 maea0, maec0;
- maea0 = in_be32(ctrl_base + SCC_CTL_MAEA0);
- maec0 = in_be32(ctrl_base + SCC_CTL_MAEC0);
- printk(KERN_WARNING "%s: PRERR [addr:%x cmd:%x]\n", DRV_NAME, maea0, maec0);
- out_be32(bmid_base + SCC_DMA_INTST, INTSTS_PRERR|INTSTS_BMSINT);
- out_be32(bmid_base + SCC_DMA_CMD,
- in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
- continue;
- }
-
- if (reg & INTSTS_RERR) {
- printk(KERN_WARNING "%s: Response Error\n", DRV_NAME);
- out_be32(bmid_base + SCC_DMA_INTST, INTSTS_RERR|INTSTS_BMSINT);
- out_be32(bmid_base + SCC_DMA_CMD,
- in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
- continue;
- }
-
- if (reg & INTSTS_ICERR) {
- out_be32(bmid_base + SCC_DMA_CMD,
- in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
- printk(KERN_WARNING "%s: Illegal Configuration\n", DRV_NAME);
- out_be32(bmid_base + SCC_DMA_INTST, INTSTS_ICERR|INTSTS_BMSINT);
- continue;
- }
-
- if (reg & INTSTS_BMSINT) {
- unsigned int classes;
- unsigned long deadline = ata_deadline(jiffies, ATA_TMOUT_BOOT);
- printk(KERN_WARNING "%s: Internal Bus Error\n", DRV_NAME);
- out_be32(bmid_base + SCC_DMA_INTST, INTSTS_BMSINT);
- /* TBD: SW reset */
- scc_softreset(&ap->link, &classes, deadline);
- continue;
- }
-
- if (reg & INTSTS_BMHE) {
- out_be32(bmid_base + SCC_DMA_INTST, INTSTS_BMHE);
- continue;
- }
-
- if (reg & INTSTS_ACTEINT) {
- out_be32(bmid_base + SCC_DMA_INTST, INTSTS_ACTEINT);
- continue;
- }
-
- if (reg & INTSTS_IOIRQS) {
- out_be32(bmid_base + SCC_DMA_INTST, INTSTS_IOIRQS);
- continue;
- }
- break;
- }
-
- /* clear start/stop bit */
- out_be32(bmid_base + SCC_DMA_CMD,
- in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
-
- /* one-PIO-cycle guaranteed wait, per spec, for HDMA1:0 transition */
- ata_sff_dma_pause(ap); /* dummy read */
-}
-
-/**
- * scc_bmdma_status - Read PCI IDE BMDMA status
- * @ap: Port associated with this ATA transaction.
- */
-
-static u8 scc_bmdma_status (struct ata_port *ap)
-{
- void __iomem *mmio = ap->ioaddr.bmdma_addr;
- u8 host_stat = in_be32(mmio + SCC_DMA_STATUS);
- u32 int_status = in_be32(mmio + SCC_DMA_INTST);
- struct ata_queued_cmd *qc = ata_qc_from_tag(ap, ap->link.active_tag);
- static int retry = 0;
-
- /* return if IOS_SS is cleared */
- if (!(in_be32(mmio + SCC_DMA_CMD) & ATA_DMA_START))
- return host_stat;
-
- /* errata A252,A308 workaround: Step4 */
- if ((scc_check_altstatus(ap) & ATA_ERR)
- && (int_status & INTSTS_INTRQ))
- return (host_stat | ATA_DMA_INTR);
-
- /* errata A308 workaround Step5 */
- if (int_status & INTSTS_IOIRQS) {
- host_stat |= ATA_DMA_INTR;
-
- /* We don't check ATAPI DMA because it is limited to UDMA4 */
- if ((qc->tf.protocol == ATA_PROT_DMA &&
- qc->dev->xfer_mode > XFER_UDMA_4)) {
- if (!(int_status & INTSTS_ACTEINT)) {
- printk(KERN_WARNING "ata%u: operation failed (transfer data loss)\n",
- ap->print_id);
- host_stat |= ATA_DMA_ERR;
- if (retry++)
- ap->udma_mask &= ~(1 << qc->dev->xfer_mode);
- } else
- retry = 0;
- }
- }
-
- return host_stat;
-}
-
-/**
- * scc_data_xfer - Transfer data by PIO
- * @dev: device for this I/O
- * @buf: data buffer
- * @buflen: buffer length
- * @rw: read/write
- *
- * Note: Original code is ata_sff_data_xfer().
- */
-
-static unsigned int scc_data_xfer (struct ata_device *dev, unsigned char *buf,
- unsigned int buflen, int rw)
-{
- struct ata_port *ap = dev->link->ap;
- unsigned int words = buflen >> 1;
- unsigned int i;
- __le16 *buf16 = (__le16 *) buf;
- void __iomem *mmio = ap->ioaddr.data_addr;
-
- /* Transfer multiple of 2 bytes */
- if (rw == READ)
- for (i = 0; i < words; i++)
- buf16[i] = cpu_to_le16(in_be32(mmio));
- else
- for (i = 0; i < words; i++)
- out_be32(mmio, le16_to_cpu(buf16[i]));
-
- /* Transfer trailing 1 byte, if any. */
- if (unlikely(buflen & 0x01)) {
- __le16 align_buf[1] = { 0 };
- unsigned char *trailing_buf = buf + buflen - 1;
-
- if (rw == READ) {
- align_buf[0] = cpu_to_le16(in_be32(mmio));
- memcpy(trailing_buf, align_buf, 1);
- } else {
- memcpy(align_buf, trailing_buf, 1);
- out_be32(mmio, le16_to_cpu(align_buf[0]));
- }
- words++;
- }
-
- return words << 1;
-}
-
-/**
- * scc_postreset - standard postreset callback
- * @ap: the target ata_port
- * @classes: classes of attached devices
- *
- * Note: Original code is ata_sff_postreset().
- */
-
-static void scc_postreset(struct ata_link *link, unsigned int *classes)
-{
- struct ata_port *ap = link->ap;
-
- DPRINTK("ENTER\n");
-
- /* is double-select really necessary? */
- if (classes[0] != ATA_DEV_NONE)
- ap->ops->sff_dev_select(ap, 1);
- if (classes[1] != ATA_DEV_NONE)
- ap->ops->sff_dev_select(ap, 0);
-
- /* bail out if no device is present */
- if (classes[0] == ATA_DEV_NONE && classes[1] == ATA_DEV_NONE) {
- DPRINTK("EXIT, no device\n");
- return;
- }
-
- /* set up device control */
- out_be32(ap->ioaddr.ctl_addr, ap->ctl);
-
- DPRINTK("EXIT\n");
-}
-
-/**
- * scc_irq_clear - Clear PCI IDE BMDMA interrupt.
- * @ap: Port associated with this ATA transaction.
- *
- * Note: Original code is ata_bmdma_irq_clear().
- */
-
-static void scc_irq_clear (struct ata_port *ap)
-{
- void __iomem *mmio = ap->ioaddr.bmdma_addr;
-
- if (!mmio)
- return;
-
- out_be32(mmio + SCC_DMA_STATUS, in_be32(mmio + SCC_DMA_STATUS));
-}
-
-/**
- * scc_port_start - Set port up for dma.
- * @ap: Port to initialize
- *
- * Allocate space for PRD table using ata_bmdma_port_start().
- * Set PRD table address for PTERADD. (PRD Transfer End Read)
- */
-
-static int scc_port_start (struct ata_port *ap)
-{
- void __iomem *mmio = ap->ioaddr.bmdma_addr;
- int rc;
-
- rc = ata_bmdma_port_start(ap);
- if (rc)
- return rc;
-
- out_be32(mmio + SCC_DMA_PTERADD, ap->bmdma_prd_dma);
- return 0;
-}
-
-/**
- * scc_port_stop - Undo scc_port_start()
- * @ap: Port to shut down
- *
- * Reset PTERADD.
- */
-
-static void scc_port_stop (struct ata_port *ap)
-{
- void __iomem *mmio = ap->ioaddr.bmdma_addr;
-
- out_be32(mmio + SCC_DMA_PTERADD, 0);
-}
-
-static struct scsi_host_template scc_sht = {
- ATA_BMDMA_SHT(DRV_NAME),
-};
-
-static struct ata_port_operations scc_pata_ops = {
- .inherits = &ata_bmdma_port_ops,
-
- .set_piomode = scc_set_piomode,
- .set_dmamode = scc_set_dmamode,
- .mode_filter = scc_mode_filter,
-
- .sff_tf_load = scc_tf_load,
- .sff_tf_read = scc_tf_read,
- .sff_exec_command = scc_exec_command,
- .sff_check_status = scc_check_status,
- .sff_check_altstatus = scc_check_altstatus,
- .sff_dev_select = scc_dev_select,
- .sff_set_devctl = scc_set_devctl,
-
- .bmdma_setup = scc_bmdma_setup,
- .bmdma_start = scc_bmdma_start,
- .bmdma_stop = scc_bmdma_stop,
- .bmdma_status = scc_bmdma_status,
- .sff_data_xfer = scc_data_xfer,
-
- .cable_detect = ata_cable_80wire,
- .softreset = scc_softreset,
- .postreset = scc_postreset,
-
- .sff_irq_clear = scc_irq_clear,
-
- .port_start = scc_port_start,
- .port_stop = scc_port_stop,
-};
-
-static struct ata_port_info scc_port_info[] = {
- {
- .flags = ATA_FLAG_SLAVE_POSS,
- .pio_mask = ATA_PIO4,
- /* No MWDMA */
- .udma_mask = ATA_UDMA6,
- .port_ops = &scc_pata_ops,
- },
-};
-
-/**
- * scc_reset_controller - initialize SCC PATA controller.
- */
-
-static int scc_reset_controller(struct ata_host *host)
-{
- void __iomem *ctrl_base = host->iomap[SCC_CTRL_BAR];
- void __iomem *bmid_base = host->iomap[SCC_BMID_BAR];
- void __iomem *cckctrl_port = ctrl_base + SCC_CTL_CCKCTRL;
- void __iomem *mode_port = ctrl_base + SCC_CTL_MODEREG;
- void __iomem *ecmode_port = ctrl_base + SCC_CTL_ECMODE;
- void __iomem *intmask_port = bmid_base + SCC_DMA_INTMASK;
- void __iomem *dmastatus_port = bmid_base + SCC_DMA_STATUS;
- u32 reg = 0;
-
- out_be32(cckctrl_port, reg);
- reg |= CCKCTRL_ATACLKOEN;
- out_be32(cckctrl_port, reg);
- reg |= CCKCTRL_LCLKEN | CCKCTRL_OCLKEN;
- out_be32(cckctrl_port, reg);
- reg |= CCKCTRL_CRST;
- out_be32(cckctrl_port, reg);
-
- for (;;) {
- reg = in_be32(cckctrl_port);
- if (reg & CCKCTRL_CRST)
- break;
- udelay(5000);
- }
-
- reg |= CCKCTRL_ATARESET;
- out_be32(cckctrl_port, reg);
- out_be32(ecmode_port, ECMODE_VALUE);
- out_be32(mode_port, MODE_JCUSFEN);
- out_be32(intmask_port, INTMASK_MSK);
-
- if (in_be32(dmastatus_port) & QCHSD_STPDIAG) {
- printk(KERN_WARNING "%s: failed to detect 80c cable. (PDIAG# is high)\n", DRV_NAME);
- return -EIO;
- }
-
- return 0;
-}
-
-/**
- * scc_setup_ports - initialize ioaddr with SCC PATA port offsets.
- * @ioaddr: IO address structure to be initialized
- * @base: base address of BMID region
- */
-
-static void scc_setup_ports (struct ata_ioports *ioaddr, void __iomem *base)
-{
- ioaddr->cmd_addr = base + SCC_REG_CMD_ADDR;
- ioaddr->altstatus_addr = ioaddr->cmd_addr + SCC_REG_ALTSTATUS;
- ioaddr->ctl_addr = ioaddr->cmd_addr + SCC_REG_ALTSTATUS;
- ioaddr->bmdma_addr = base;
- ioaddr->data_addr = ioaddr->cmd_addr + SCC_REG_DATA;
- ioaddr->error_addr = ioaddr->cmd_addr + SCC_REG_ERR;
- ioaddr->feature_addr = ioaddr->cmd_addr + SCC_REG_FEATURE;
- ioaddr->nsect_addr = ioaddr->cmd_addr + SCC_REG_NSECT;
- ioaddr->lbal_addr = ioaddr->cmd_addr + SCC_REG_LBAL;
- ioaddr->lbam_addr = ioaddr->cmd_addr + SCC_REG_LBAM;
- ioaddr->lbah_addr = ioaddr->cmd_addr + SCC_REG_LBAH;
- ioaddr->device_addr = ioaddr->cmd_addr + SCC_REG_DEVICE;
- ioaddr->status_addr = ioaddr->cmd_addr + SCC_REG_STATUS;
- ioaddr->command_addr = ioaddr->cmd_addr + SCC_REG_CMD;
-}
-
-static int scc_host_init(struct ata_host *host)
-{
- struct pci_dev *pdev = to_pci_dev(host->dev);
- int rc;
-
- rc = scc_reset_controller(host);
- if (rc)
- return rc;
-
- rc = dma_set_mask(&pdev->dev, ATA_DMA_MASK);
- if (rc)
- return rc;
- rc = dma_set_coherent_mask(&pdev->dev, ATA_DMA_MASK);
- if (rc)
- return rc;
-
- scc_setup_ports(&host->ports[0]->ioaddr, host->iomap[SCC_BMID_BAR]);
-
- pci_set_master(pdev);
-
- return 0;
-}
-
-/**
- * scc_init_one - Register SCC PATA device with kernel services
- * @pdev: PCI device to register
- * @ent: Entry in scc_pci_tbl matching with @pdev
- *
- * LOCKING:
- * Inherited from PCI layer (may sleep).
- *
- * RETURNS:
- * Zero on success, or -ERRNO value.
- */
-
-static int scc_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
-{
- unsigned int board_idx = (unsigned int) ent->driver_data;
- const struct ata_port_info *ppi[] = { &scc_port_info[board_idx], NULL };
- struct ata_host *host;
- int rc;
-
- ata_print_version_once(&pdev->dev, DRV_VERSION);
-
- host = ata_host_alloc_pinfo(&pdev->dev, ppi, 1);
- if (!host)
- return -ENOMEM;
-
- rc = pcim_enable_device(pdev);
- if (rc)
- return rc;
-
- rc = pcim_iomap_regions(pdev, (1 << SCC_CTRL_BAR) | (1 << SCC_BMID_BAR), DRV_NAME);
- if (rc == -EBUSY)
- pcim_pin_device(pdev);
- if (rc)
- return rc;
- host->iomap = pcim_iomap_table(pdev);
-
- ata_port_pbar_desc(host->ports[0], SCC_CTRL_BAR, -1, "ctrl");
- ata_port_pbar_desc(host->ports[0], SCC_BMID_BAR, -1, "bmid");
-
- rc = scc_host_init(host);
- if (rc)
- return rc;
-
- return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt,
- IRQF_SHARED, &scc_sht);
-}
-
-static struct pci_driver scc_pci_driver = {
- .name = DRV_NAME,
- .id_table = scc_pci_tbl,
- .probe = scc_init_one,
- .remove = ata_pci_remove_one,
-#ifdef CONFIG_PM_SLEEP
- .suspend = ata_pci_device_suspend,
- .resume = ata_pci_device_resume,
-#endif
-};
-
-module_pci_driver(scc_pci_driver);
-
-MODULE_AUTHOR("Toshiba corp");
-MODULE_DESCRIPTION("SCSI low-level driver for Toshiba SCC PATA controller");
-MODULE_LICENSE("GPL");
-MODULE_DEVICE_TABLE(pci, scc_pci_tbl);
-MODULE_VERSION(DRV_VERSION);
{
int ret;
- if (init_cache_level(cpu))
+ if (init_cache_level(cpu) || !cache_leaves(cpu))
return -ENOENT;
per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
#include <linux/device.h>
#include <linux/init.h>
#include <linux/memory.h>
+#include <linux/of.h>
#include "base.h"
cpu_dev_init();
memory_dev_init();
container_dev_init();
+ of_core_init();
}
define_id_show_func(core_id);
static DEVICE_ATTR_RO(core_id);
-define_siblings_show_func(thread_siblings, thread_cpumask);
+define_siblings_show_func(thread_siblings, sibling_cpumask);
static DEVICE_ATTR_RO(thread_siblings);
static DEVICE_ATTR_RO(thread_siblings_list);
config BLK_DEV_PMEM
tristate "Persistent memory block device support"
+ depends on HAS_IOMEM
help
Saying Y here will allow you to use a contiguous range of reserved
memory as one or more persistent block devices.
static void loop_remove(struct loop_device *lo)
{
- del_gendisk(lo->lo_disk);
blk_cleanup_queue(lo->lo_queue);
+ del_gendisk(lo->lo_disk);
blk_mq_free_tag_set(&lo->tag_set);
put_disk(lo->lo_disk);
kfree(lo);
struct nvme_iod *iod;
dma_addr_t meta_dma = 0;
void *meta = NULL;
+ void __user *metadata;
if (copy_from_user(&io, uio, sizeof(io)))
return -EFAULT;
meta_len = 0;
}
+ metadata = (void __user *)(unsigned long)io.metadata;
+
write = io.opcode & 1;
switch (io.opcode) {
if (meta_len) {
meta = dma_alloc_coherent(&dev->pci_dev->dev, meta_len,
&meta_dma, GFP_KERNEL);
+
if (!meta) {
status = -ENOMEM;
goto unmap;
}
if (write) {
- if (copy_from_user(meta, (void __user *)io.metadata,
- meta_len)) {
+ if (copy_from_user(meta, metadata, meta_len)) {
status = -EFAULT;
goto unmap;
}
nvme_free_iod(dev, iod);
if (meta) {
if (status == NVME_SC_SUCCESS && !write) {
- if (copy_to_user((void __user *)io.metadata, meta,
- meta_len))
+ if (copy_to_user(metadata, meta, meta_len))
status = -EFAULT;
}
dma_free_coherent(&dev->pci_dev->dev, meta_len, meta, meta_dma);
static int nvme_trans_bdev_limits_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
u8 *inq_response, int alloc_len)
{
- __be32 max_sectors = cpu_to_be32(queue_max_hw_sectors(ns->queue));
+ __be32 max_sectors = cpu_to_be32(
+ nvme_block_nr(ns, queue_max_hw_sectors(ns->queue)));
__be32 max_discard = cpu_to_be32(ns->queue->limits.max_discard_sectors);
__be32 discard_desc_count = cpu_to_be32(0x100);
page_code = GET_INQ_PAGE_CODE(cmd);
alloc_len = GET_INQ_ALLOC_LENGTH(cmd);
- inq_response = kmalloc(alloc_len, GFP_KERNEL);
+ inq_response = kmalloc(max(alloc_len, STANDARD_INQUIRY_LENGTH),
+ GFP_KERNEL);
if (inq_response == NULL) {
res = -ENOMEM;
goto out_mem;
}
/*
- * Map the memory as non-cachable, as we can't write back the contents
+ * Map the memory as write-through, as we can't write back the contents
* of the CPU caches in case of a crash.
*/
err = -ENOMEM;
- pmem->virt_addr = ioremap_nocache(pmem->phys_addr, pmem->size);
+ pmem->virt_addr = ioremap_wt(pmem->phys_addr, pmem->size);
if (!pmem->virt_addr)
goto out_release_region;
memset(&zram->stats, 0, sizeof(zram->stats));
zram->disksize = 0;
zram->max_comp_streams = 1;
+
set_capacity(zram->disk, 0);
+ part_stat_set_all(&zram->disk->part0, 0);
up_write(&zram->init_lock);
/* I/O operation under all of CPU are done so let's free */
{ USB_DEVICE(0x04CA, 0x3007) },
{ USB_DEVICE(0x04CA, 0x3008) },
{ USB_DEVICE(0x04CA, 0x300b) },
+ { USB_DEVICE(0x04CA, 0x300f) },
{ USB_DEVICE(0x04CA, 0x3010) },
{ USB_DEVICE(0x0930, 0x0219) },
{ USB_DEVICE(0x0930, 0x0220) },
{ USB_DEVICE(0x0cf3, 0xe003) },
{ USB_DEVICE(0x0CF3, 0xE004) },
{ USB_DEVICE(0x0CF3, 0xE005) },
+ { USB_DEVICE(0x0CF3, 0xE006) },
{ USB_DEVICE(0x13d3, 0x3362) },
{ USB_DEVICE(0x13d3, 0x3375) },
{ USB_DEVICE(0x13d3, 0x3393) },
{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0CF3, 0x817a), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0xe006), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
iobase = info->p_dev->resource[0]->start;
avail = bt3c_read(iobase, 0x7006);
- //printk("bt3c_cs: receiving %d bytes\n", avail);
bt3c_address(iobase, 0x7480);
while (size < avail) {
bt_cb(info->rx_skb)->pkt_type = inb(iobase + DATA_L);
inb(iobase + DATA_H);
- //printk("bt3c: PACKET_TYPE=%02x\n", bt_cb(info->rx_skb)->pkt_type);
switch (bt_cb(info->rx_skb)->pkt_type) {
if (stat & 0x0001)
bt3c_receive(info);
if (stat & 0x0002) {
- //BT_ERR("Ack (stat=0x%04x)", stat);
clear_bit(XMIT_SENDING, &(info->tx_state));
bt3c_write_wakeup(info);
}
}
EXPORT_SYMBOL_GPL(btbcm_set_bdaddr);
+int btbcm_patchram(struct hci_dev *hdev, const char *firmware)
+{
+ const struct hci_command_hdr *cmd;
+ const struct firmware *fw;
+ const u8 *fw_ptr;
+ size_t fw_size;
+ struct sk_buff *skb;
+ u16 opcode;
+ int err;
+
+ err = request_firmware(&fw, firmware, &hdev->dev);
+ if (err < 0) {
+ BT_INFO("%s: BCM: Patch %s not found", hdev->name, firmware);
+ return err;
+ }
+
+ /* Start Download */
+ skb = __hci_cmd_sync(hdev, 0xfc2e, 0, NULL, HCI_INIT_TIMEOUT);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
+ BT_ERR("%s: BCM: Download Minidrv command failed (%d)",
+ hdev->name, err);
+ goto done;
+ }
+ kfree_skb(skb);
+
+ /* 50 msec delay after Download Minidrv completes */
+ msleep(50);
+
+ fw_ptr = fw->data;
+ fw_size = fw->size;
+
+ while (fw_size >= sizeof(*cmd)) {
+ const u8 *cmd_param;
+
+ cmd = (struct hci_command_hdr *)fw_ptr;
+ fw_ptr += sizeof(*cmd);
+ fw_size -= sizeof(*cmd);
+
+ if (fw_size < cmd->plen) {
+ BT_ERR("%s: BCM: Patch %s is corrupted", hdev->name,
+ firmware);
+ err = -EINVAL;
+ goto done;
+ }
+
+ cmd_param = fw_ptr;
+ fw_ptr += cmd->plen;
+ fw_size -= cmd->plen;
+
+ opcode = le16_to_cpu(cmd->opcode);
+
+ skb = __hci_cmd_sync(hdev, opcode, cmd->plen, cmd_param,
+ HCI_INIT_TIMEOUT);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
+ BT_ERR("%s: BCM: Patch command %04x failed (%d)",
+ hdev->name, opcode, err);
+ goto done;
+ }
+ kfree_skb(skb);
+ }
+
+ /* 250 msec delay after Launch Ram completes */
+ msleep(250);
+
+done:
+ release_firmware(fw);
+ return err;
+}
+EXPORT_SYMBOL(btbcm_patchram);
+
static int btbcm_reset(struct hci_dev *hdev)
{
struct sk_buff *skb;
int btbcm_setup_patchram(struct hci_dev *hdev)
{
- const struct hci_command_hdr *cmd;
- const struct firmware *fw;
- const u8 *fw_ptr;
- size_t fw_size;
char fw_name[64];
- u16 opcode, subver, rev, pid, vid;
+ u16 subver, rev, pid, vid;
const char *hw_name = NULL;
struct sk_buff *skb;
struct hci_rp_read_local_version *ver;
hw_name ? : "BCM", (subver & 0x7000) >> 13,
(subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
- err = request_firmware(&fw, fw_name, &hdev->dev);
- if (err < 0) {
- BT_INFO("%s: BCM: patch %s not found", hdev->name, fw_name);
+ err = btbcm_patchram(hdev, fw_name);
+ if (err == -ENOENT)
return 0;
- }
-
- /* Start Download */
- skb = __hci_cmd_sync(hdev, 0xfc2e, 0, NULL, HCI_INIT_TIMEOUT);
- if (IS_ERR(skb)) {
- err = PTR_ERR(skb);
- BT_ERR("%s: BCM: Download Minidrv command failed (%d)",
- hdev->name, err);
- goto reset;
- }
- kfree_skb(skb);
-
- /* 50 msec delay after Download Minidrv completes */
- msleep(50);
-
- fw_ptr = fw->data;
- fw_size = fw->size;
-
- while (fw_size >= sizeof(*cmd)) {
- const u8 *cmd_param;
-
- cmd = (struct hci_command_hdr *)fw_ptr;
- fw_ptr += sizeof(*cmd);
- fw_size -= sizeof(*cmd);
-
- if (fw_size < cmd->plen) {
- BT_ERR("%s: BCM: patch %s is corrupted", hdev->name,
- fw_name);
- err = -EINVAL;
- goto reset;
- }
- cmd_param = fw_ptr;
- fw_ptr += cmd->plen;
- fw_size -= cmd->plen;
-
- opcode = le16_to_cpu(cmd->opcode);
-
- skb = __hci_cmd_sync(hdev, opcode, cmd->plen, cmd_param,
- HCI_INIT_TIMEOUT);
- if (IS_ERR(skb)) {
- err = PTR_ERR(skb);
- BT_ERR("%s: BCM: patch command %04x failed (%d)",
- hdev->name, opcode, err);
- goto reset;
- }
- kfree_skb(skb);
- }
-
- /* 250 msec delay after Launch Ram completes */
- msleep(250);
-
-reset:
/* Reset */
err = btbcm_reset(hdev);
if (err)
- goto done;
+ return err;
/* Read Local Version Info */
skb = btbcm_read_local_version(hdev);
- if (IS_ERR(skb)) {
- err = PTR_ERR(skb);
- goto done;
- }
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
ver = (struct hci_rp_read_local_version *)skb->data;
rev = le16_to_cpu(ver->hci_rev);
set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
-done:
- release_firmware(fw);
-
- return err;
+ return 0;
}
EXPORT_SYMBOL_GPL(btbcm_setup_patchram);
int btbcm_check_bdaddr(struct hci_dev *hdev);
int btbcm_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr);
+int btbcm_patchram(struct hci_dev *hdev, const char *firmware);
int btbcm_setup_patchram(struct hci_dev *hdev);
int btbcm_setup_apple(struct hci_dev *hdev);
return -EOPNOTSUPP;
}
+static inline int btbcm_patchram(struct hci_dev *hdev, const char *firmware)
+{
+ return -EOPNOTSUPP;
+}
+
static inline int btbcm_setup_patchram(struct hci_dev *hdev)
{
return 0;
#include <linux/module.h>
#include <linux/usb.h>
#include <linux/firmware.h>
+#include <asm/unaligned.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
#define BTUSB_AMP 0x4000
#define BTUSB_QCA_ROME 0x8000
#define BTUSB_BCM_APPLE 0x10000
+#define BTUSB_REALTEK 0x20000
static const struct usb_device_id btusb_table[] = {
/* Generic Bluetooth USB device */
{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0xe006), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 },
/* QCA ROME chipset */
+ { USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x0cf3, 0xe300), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME },
{ USB_VENDOR_AND_INTERFACE_INFO(0x8087, 0xe0, 0x01, 0x01),
.driver_info = BTUSB_IGNORE },
+ /* Realtek Bluetooth devices */
+ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01),
+ .driver_info = BTUSB_REALTEK },
+
+ /* Additional Realtek 8723AE Bluetooth devices */
+ { USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x13d3, 0x3394), .driver_info = BTUSB_REALTEK },
+
+ /* Additional Realtek 8723BE Bluetooth devices */
+ { USB_DEVICE(0x0489, 0xe085), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x0489, 0xe08b), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x13d3, 0x3410), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x13d3, 0x3416), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x13d3, 0x3459), .driver_info = BTUSB_REALTEK },
+
+ /* Additional Realtek 8821AE Bluetooth devices */
+ { USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x13d3, 0x3414), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x13d3, 0x3458), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x13d3, 0x3461), .driver_info = BTUSB_REALTEK },
+ { USB_DEVICE(0x13d3, 0x3462), .driver_info = BTUSB_REALTEK },
+
{ } /* Terminating entry */
};
*/
if (data->setup_on_usb) {
err = data->setup_on_usb(hdev);
- if (err <0)
+ if (err < 0)
return err;
}
return ret;
}
+#define RTL_FRAG_LEN 252
+
+struct rtl_download_cmd {
+ __u8 index;
+ __u8 data[RTL_FRAG_LEN];
+} __packed;
+
+struct rtl_download_response {
+ __u8 status;
+ __u8 index;
+} __packed;
+
+struct rtl_rom_version_evt {
+ __u8 status;
+ __u8 version;
+} __packed;
+
+struct rtl_epatch_header {
+ __u8 signature[8];
+ __le32 fw_version;
+ __le16 num_patches;
+} __packed;
+
+#define RTL_EPATCH_SIGNATURE "Realtech"
+#define RTL_ROM_LMP_3499 0x3499
+#define RTL_ROM_LMP_8723A 0x1200
+#define RTL_ROM_LMP_8723B 0x8723
+#define RTL_ROM_LMP_8821A 0x8821
+#define RTL_ROM_LMP_8761A 0x8761
+
+static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
+{
+ struct rtl_rom_version_evt *rom_version;
+ struct sk_buff *skb;
+ int ret;
+
+ /* Read RTL ROM version command */
+ skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT);
+ if (IS_ERR(skb)) {
+ BT_ERR("%s: Read ROM version failed (%ld)",
+ hdev->name, PTR_ERR(skb));
+ return PTR_ERR(skb);
+ }
+
+ if (skb->len != sizeof(*rom_version)) {
+ BT_ERR("%s: RTL version event length mismatch", hdev->name);
+ kfree_skb(skb);
+ return -EIO;
+ }
+
+ rom_version = (struct rtl_rom_version_evt *)skb->data;
+ BT_INFO("%s: rom_version status=%x version=%x",
+ hdev->name, rom_version->status, rom_version->version);
+
+ ret = rom_version->status;
+ if (ret == 0)
+ *version = rom_version->version;
+
+ kfree_skb(skb);
+ return ret;
+}
+
+static int rtl8723b_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
+ const struct firmware *fw,
+ unsigned char **_buf)
+{
+ const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 };
+ struct rtl_epatch_header *epatch_info;
+ unsigned char *buf;
+ int i, ret, len;
+ size_t min_size;
+ u8 opcode, length, data, rom_version = 0;
+ int project_id = -1;
+ const unsigned char *fwptr, *chip_id_base;
+ const unsigned char *patch_length_base, *patch_offset_base;
+ u32 patch_offset = 0;
+ u16 patch_length, num_patches;
+ const u16 project_id_to_lmp_subver[] = {
+ RTL_ROM_LMP_8723A,
+ RTL_ROM_LMP_8723B,
+ RTL_ROM_LMP_8821A,
+ RTL_ROM_LMP_8761A
+ };
+
+ ret = rtl_read_rom_version(hdev, &rom_version);
+ if (ret)
+ return -bt_to_errno(ret);
+
+ min_size = sizeof(struct rtl_epatch_header) + sizeof(extension_sig) + 3;
+ if (fw->size < min_size)
+ return -EINVAL;
+
+ fwptr = fw->data + fw->size - sizeof(extension_sig);
+ if (memcmp(fwptr, extension_sig, sizeof(extension_sig)) != 0) {
+ BT_ERR("%s: extension section signature mismatch", hdev->name);
+ return -EINVAL;
+ }
+
+ /* Loop from the end of the firmware parsing instructions, until
+ * we find an instruction that identifies the "project ID" for the
+ * hardware supported by this firwmare file.
+ * Once we have that, we double-check that that project_id is suitable
+ * for the hardware we are working with.
+ */
+ while (fwptr >= fw->data + (sizeof(struct rtl_epatch_header) + 3)) {
+ opcode = *--fwptr;
+ length = *--fwptr;
+ data = *--fwptr;
+
+ BT_DBG("check op=%x len=%x data=%x", opcode, length, data);
+
+ if (opcode == 0xff) /* EOF */
+ break;
+
+ if (length == 0) {
+ BT_ERR("%s: found instruction with length 0",
+ hdev->name);
+ return -EINVAL;
+ }
+
+ if (opcode == 0 && length == 1) {
+ project_id = data;
+ break;
+ }
+
+ fwptr -= length;
+ }
+
+ if (project_id < 0) {
+ BT_ERR("%s: failed to find version instruction", hdev->name);
+ return -EINVAL;
+ }
+
+ if (project_id >= ARRAY_SIZE(project_id_to_lmp_subver)) {
+ BT_ERR("%s: unknown project id %d", hdev->name, project_id);
+ return -EINVAL;
+ }
+
+ if (lmp_subver != project_id_to_lmp_subver[project_id]) {
+ BT_ERR("%s: firmware is for %x but this is a %x", hdev->name,
+ project_id_to_lmp_subver[project_id], lmp_subver);
+ return -EINVAL;
+ }
+
+ epatch_info = (struct rtl_epatch_header *)fw->data;
+ if (memcmp(epatch_info->signature, RTL_EPATCH_SIGNATURE, 8) != 0) {
+ BT_ERR("%s: bad EPATCH signature", hdev->name);
+ return -EINVAL;
+ }
+
+ num_patches = le16_to_cpu(epatch_info->num_patches);
+ BT_DBG("fw_version=%x, num_patches=%d",
+ le32_to_cpu(epatch_info->fw_version), num_patches);
+
+ /* After the rtl_epatch_header there is a funky patch metadata section.
+ * Assuming 2 patches, the layout is:
+ * ChipID1 ChipID2 PatchLength1 PatchLength2 PatchOffset1 PatchOffset2
+ *
+ * Find the right patch for this chip.
+ */
+ min_size += 8 * num_patches;
+ if (fw->size < min_size)
+ return -EINVAL;
+
+ chip_id_base = fw->data + sizeof(struct rtl_epatch_header);
+ patch_length_base = chip_id_base + (sizeof(u16) * num_patches);
+ patch_offset_base = patch_length_base + (sizeof(u16) * num_patches);
+ for (i = 0; i < num_patches; i++) {
+ u16 chip_id = get_unaligned_le16(chip_id_base +
+ (i * sizeof(u16)));
+ if (chip_id == rom_version + 1) {
+ patch_length = get_unaligned_le16(patch_length_base +
+ (i * sizeof(u16)));
+ patch_offset = get_unaligned_le32(patch_offset_base +
+ (i * sizeof(u32)));
+ break;
+ }
+ }
+
+ if (!patch_offset) {
+ BT_ERR("%s: didn't find patch for chip id %d",
+ hdev->name, rom_version);
+ return -EINVAL;
+ }
+
+ BT_DBG("length=%x offset=%x index %d", patch_length, patch_offset, i);
+ min_size = patch_offset + patch_length;
+ if (fw->size < min_size)
+ return -EINVAL;
+
+ /* Copy the firmware into a new buffer and write the version at
+ * the end.
+ */
+ len = patch_length;
+ buf = kmemdup(fw->data + patch_offset, patch_length, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ memcpy(buf + patch_length - 4, &epatch_info->fw_version, 4);
+
+ *_buf = buf;
+ return len;
+}
+
+static int rtl_download_firmware(struct hci_dev *hdev,
+ const unsigned char *data, int fw_len)
+{
+ struct rtl_download_cmd *dl_cmd;
+ int frag_num = fw_len / RTL_FRAG_LEN + 1;
+ int frag_len = RTL_FRAG_LEN;
+ int ret = 0;
+ int i;
+
+ dl_cmd = kmalloc(sizeof(struct rtl_download_cmd), GFP_KERNEL);
+ if (!dl_cmd)
+ return -ENOMEM;
+
+ for (i = 0; i < frag_num; i++) {
+ struct rtl_download_response *dl_resp;
+ struct sk_buff *skb;
+
+ BT_DBG("download fw (%d/%d)", i, frag_num);
+
+ dl_cmd->index = i;
+ if (i == (frag_num - 1)) {
+ dl_cmd->index |= 0x80; /* data end */
+ frag_len = fw_len % RTL_FRAG_LEN;
+ }
+ memcpy(dl_cmd->data, data, frag_len);
+
+ /* Send download command */
+ skb = __hci_cmd_sync(hdev, 0xfc20, frag_len + 1, dl_cmd,
+ HCI_INIT_TIMEOUT);
+ if (IS_ERR(skb)) {
+ BT_ERR("%s: download fw command failed (%ld)",
+ hdev->name, PTR_ERR(skb));
+ ret = -PTR_ERR(skb);
+ goto out;
+ }
+
+ if (skb->len != sizeof(*dl_resp)) {
+ BT_ERR("%s: download fw event length mismatch",
+ hdev->name);
+ kfree_skb(skb);
+ ret = -EIO;
+ goto out;
+ }
+
+ dl_resp = (struct rtl_download_response *)skb->data;
+ if (dl_resp->status != 0) {
+ kfree_skb(skb);
+ ret = bt_to_errno(dl_resp->status);
+ goto out;
+ }
+
+ kfree_skb(skb);
+ data += RTL_FRAG_LEN;
+ }
+
+out:
+ kfree(dl_cmd);
+ return ret;
+}
+
+static int btusb_setup_rtl8723a(struct hci_dev *hdev)
+{
+ struct btusb_data *data = dev_get_drvdata(&hdev->dev);
+ struct usb_device *udev = interface_to_usbdev(data->intf);
+ const struct firmware *fw;
+ int ret;
+
+ BT_INFO("%s: rtl: loading rtl_bt/rtl8723a_fw.bin", hdev->name);
+ ret = request_firmware(&fw, "rtl_bt/rtl8723a_fw.bin", &udev->dev);
+ if (ret < 0) {
+ BT_ERR("%s: Failed to load rtl_bt/rtl8723a_fw.bin", hdev->name);
+ return ret;
+ }
+
+ if (fw->size < 8) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* Check that the firmware doesn't have the epatch signature
+ * (which is only for RTL8723B and newer).
+ */
+ if (!memcmp(fw->data, RTL_EPATCH_SIGNATURE, 8)) {
+ BT_ERR("%s: unexpected EPATCH signature!", hdev->name);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = rtl_download_firmware(hdev, fw->data, fw->size);
+
+out:
+ release_firmware(fw);
+ return ret;
+}
+
+static int btusb_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver,
+ const char *fw_name)
+{
+ struct btusb_data *data = dev_get_drvdata(&hdev->dev);
+ struct usb_device *udev = interface_to_usbdev(data->intf);
+ unsigned char *fw_data = NULL;
+ const struct firmware *fw;
+ int ret;
+
+ BT_INFO("%s: rtl: loading %s", hdev->name, fw_name);
+ ret = request_firmware(&fw, fw_name, &udev->dev);
+ if (ret < 0) {
+ BT_ERR("%s: Failed to load %s", hdev->name, fw_name);
+ return ret;
+ }
+
+ ret = rtl8723b_parse_firmware(hdev, lmp_subver, fw, &fw_data);
+ if (ret < 0)
+ goto out;
+
+ ret = rtl_download_firmware(hdev, fw_data, ret);
+ kfree(fw_data);
+ if (ret < 0)
+ goto out;
+
+out:
+ release_firmware(fw);
+ return ret;
+}
+
+static int btusb_setup_realtek(struct hci_dev *hdev)
+{
+ struct sk_buff *skb;
+ struct hci_rp_read_local_version *resp;
+ u16 lmp_subver;
+
+ skb = btusb_read_local_version(hdev);
+ if (IS_ERR(skb))
+ return -PTR_ERR(skb);
+
+ resp = (struct hci_rp_read_local_version *)skb->data;
+ BT_INFO("%s: rtl: examining hci_ver=%02x hci_rev=%04x lmp_ver=%02x "
+ "lmp_subver=%04x", hdev->name, resp->hci_ver, resp->hci_rev,
+ resp->lmp_ver, resp->lmp_subver);
+
+ lmp_subver = le16_to_cpu(resp->lmp_subver);
+ kfree_skb(skb);
+
+ /* Match a set of subver values that correspond to stock firmware,
+ * which is not compatible with standard btusb.
+ * If matched, upload an alternative firmware that does conform to
+ * standard btusb. Once that firmware is uploaded, the subver changes
+ * to a different value.
+ */
+ switch (lmp_subver) {
+ case RTL_ROM_LMP_8723A:
+ case RTL_ROM_LMP_3499:
+ return btusb_setup_rtl8723a(hdev);
+ case RTL_ROM_LMP_8723B:
+ return btusb_setup_rtl8723b(hdev, lmp_subver,
+ "rtl_bt/rtl8723b_fw.bin");
+ case RTL_ROM_LMP_8821A:
+ return btusb_setup_rtl8723b(hdev, lmp_subver,
+ "rtl_bt/rtl8821a_fw.bin");
+ case RTL_ROM_LMP_8761A:
+ return btusb_setup_rtl8723b(hdev, lmp_subver,
+ "rtl_bt/rtl8761a_fw.bin");
+ default:
+ BT_INFO("rtl: assuming no firmware upload needed.");
+ return 0;
+ }
+}
+
static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev,
struct intel_version *ver)
{
int i, err;
err = btusb_qca_send_vendor_req(hdev, QCA_GET_TARGET_VERSION, &ver,
- sizeof(ver));
+ sizeof(ver));
if (err < 0)
return err;
hdev->set_bdaddr = btusb_set_bdaddr_ath3012;
}
+ if (id->driver_info & BTUSB_REALTEK)
+ hdev->setup = btusb_setup_realtek;
+
if (id->driver_info & BTUSB_AMP) {
/* AMP controllers do not support SCO packets */
data->isoc = NULL;
hci_uart_tx_wakeup(hu);
}
-/* Initialize protocol */
static int ath_open(struct hci_uart *hu)
{
struct ath_struct *ath;
return 0;
}
-/* Flush protocol data */
-static int ath_flush(struct hci_uart *hu)
+static int ath_close(struct hci_uart *hu)
{
struct ath_struct *ath = hu->priv;
skb_queue_purge(&ath->txq);
+ kfree_skb(ath->rx_skb);
+
+ cancel_work_sync(&ath->ctxtsw);
+
+ hu->priv = NULL;
+ kfree(ath);
+
return 0;
}
-/* Close protocol */
-static int ath_close(struct hci_uart *hu)
+static int ath_flush(struct hci_uart *hu)
{
struct ath_struct *ath = hu->priv;
skb_queue_purge(&ath->txq);
- kfree_skb(ath->rx_skb);
+ return 0;
+}
- cancel_work_sync(&ath->ctxtsw);
+static int ath_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+ struct sk_buff *skb;
+ u8 buf[10];
+ int err;
+
+ buf[0] = 0x01;
+ buf[1] = 0x01;
+ buf[2] = 0x00;
+ buf[3] = sizeof(bdaddr_t);
+ memcpy(buf + 4, bdaddr, sizeof(bdaddr_t));
+
+ skb = __hci_cmd_sync(hdev, 0xfc0b, sizeof(buf), buf, HCI_INIT_TIMEOUT);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
+ BT_ERR("%s: Change address command failed (%d)",
+ hdev->name, err);
+ return err;
+ }
+ kfree_skb(skb);
- hu->priv = NULL;
- kfree(ath);
+ return 0;
+}
+
+static int ath_setup(struct hci_uart *hu)
+{
+ BT_DBG("hu %p", hu);
+
+ hu->hdev->set_bdaddr = ath_set_bdaddr;
return 0;
}
+static const struct h4_recv_pkt ath_recv_pkts[] = {
+ { H4_RECV_ACL, .recv = hci_recv_frame },
+ { H4_RECV_SCO, .recv = hci_recv_frame },
+ { H4_RECV_EVENT, .recv = hci_recv_frame },
+};
+
+static int ath_recv(struct hci_uart *hu, const void *data, int count)
+{
+ struct ath_struct *ath = hu->priv;
+
+ ath->rx_skb = h4_recv_buf(hu->hdev, ath->rx_skb, data, count,
+ ath_recv_pkts, ARRAY_SIZE(ath_recv_pkts));
+ if (IS_ERR(ath->rx_skb)) {
+ int err = PTR_ERR(ath->rx_skb);
+ BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+ return err;
+ }
+
+ return count;
+}
+
#define HCI_OP_ATH_SLEEP 0xFC04
-/* Enqueue frame for transmittion */
static int ath_enqueue(struct hci_uart *hu, struct sk_buff *skb)
{
struct ath_struct *ath = hu->priv;
return 0;
}
- /*
- * Update power management enable flag with parameters of
+ /* Update power management enable flag with parameters of
* HCI sleep enable vendor specific HCI command.
*/
if (bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
return skb_dequeue(&ath->txq);
}
-static const struct h4_recv_pkt ath_recv_pkts[] = {
- { H4_RECV_ACL, .recv = hci_recv_frame },
- { H4_RECV_SCO, .recv = hci_recv_frame },
- { H4_RECV_EVENT, .recv = hci_recv_frame },
-};
-
-/* Recv data */
-static int ath_recv(struct hci_uart *hu, const void *data, int count)
-{
- struct ath_struct *ath = hu->priv;
-
- ath->rx_skb = h4_recv_buf(hu->hdev, ath->rx_skb, data, count,
- ath_recv_pkts, ARRAY_SIZE(ath_recv_pkts));
- if (IS_ERR(ath->rx_skb)) {
- int err = PTR_ERR(ath->rx_skb);
- BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
- return err;
- }
-
- return count;
-}
-
static const struct hci_uart_proto athp = {
.id = HCI_UART_ATH3K,
.name = "ATH3K",
.open = ath_open,
.close = ath_close,
+ .flush = ath_flush,
+ .setup = ath_setup,
.recv = ath_recv,
.enqueue = ath_enqueue,
.dequeue = ath_dequeue,
- .flush = ath_flush,
};
int __init ath_init(void)
* Initialise the fake PMU. We only need to populate the
* used_mask for the purposes of validation.
*/
- .used_mask = CPU_BITS_NONE,
+ .used_mask = { 0 },
};
if (!validate_event(event->pmu, &fake_pmu, leader))
/* Look for a specific device type */
for (; drb < bus->drbs; drb += size + 1) {
- acsr = readl(cdmm + drb * CDMM_DRB_SIZE);
+ acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE);
type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT;
if (type == dev_type)
return cdmm + drb * CDMM_DRB_SIZE;
bus->discovered = true;
pr_info("cdmm%u discovery (%u blocks)\n", cpu, bus->drbs);
for (; drb < bus->drbs; drb += size + 1) {
- acsr = readl(cdmm + drb * CDMM_DRB_SIZE);
+ acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE);
type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT;
size = (acsr & CDMM_ACSR_DEVSIZE) >> CDMM_ACSR_DEVSIZE_SHIFT;
rev = (acsr & CDMM_ACSR_DEVREV) >> CDMM_ACSR_DEVREV_SHIFT;
#include <linux/debugfs.h>
#include <linux/log2.h>
#include <linux/syscore_ops.h>
-#include <linux/memblock.h>
/*
* DDR target is the same on all platforms.
*/
#define WIN_CTRL_OFF 0x0000
#define WIN_CTRL_ENABLE BIT(0)
+/* Only on HW I/O coherency capable platforms */
#define WIN_CTRL_SYNCBARRIER BIT(1)
#define WIN_CTRL_TGT_MASK 0xf0
#define WIN_CTRL_TGT_SHIFT 4
/* Relative to mbusbridge_base */
#define MBUS_BRIDGE_CTRL_OFF 0x0
-#define MBUS_BRIDGE_SIZE_MASK 0xffff0000
#define MBUS_BRIDGE_BASE_OFF 0x4
-#define MBUS_BRIDGE_BASE_MASK 0xffff0000
/* Maximum number of windows, for all known platforms */
#define MBUS_WINS_MAX 20
ctrl = ((size - 1) & WIN_CTRL_SIZE_MASK) |
(attr << WIN_CTRL_ATTR_SHIFT) |
(target << WIN_CTRL_TGT_SHIFT) |
- WIN_CTRL_SYNCBARRIER |
WIN_CTRL_ENABLE;
+ if (mbus->hw_io_coherency)
+ ctrl |= WIN_CTRL_SYNCBARRIER;
writel(base & WIN_BASE_LOW, addr + WIN_BASE_OFF);
writel(ctrl, addr + WIN_CTRL_OFF);
return MVEBU_MBUS_NO_REMAP;
}
-/*
- * Use the memblock information to find the MBus bridge hole in the
- * physical address space.
- */
-static void __init
-mvebu_mbus_find_bridge_hole(uint64_t *start, uint64_t *end)
-{
- struct memblock_region *r;
- uint64_t s = 0;
-
- for_each_memblock(memory, r) {
- /*
- * This part of the memory is above 4 GB, so we don't
- * care for the MBus bridge hole.
- */
- if (r->base >= 0x100000000)
- continue;
-
- /*
- * The MBus bridge hole is at the end of the RAM under
- * the 4 GB limit.
- */
- if (r->base + r->size > s)
- s = r->base + r->size;
- }
-
- *start = s;
- *end = 0x100000000;
-}
-
static void __init
mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
{
int i;
int cs;
- uint64_t mbus_bridge_base, mbus_bridge_end;
mvebu_mbus_dram_info.mbus_dram_target_id = TARGET_DDR;
- mvebu_mbus_find_bridge_hole(&mbus_bridge_base, &mbus_bridge_end);
-
for (i = 0, cs = 0; i < 4; i++) {
- u64 base = readl(mbus->sdramwins_base + DDR_BASE_CS_OFF(i));
- u64 size = readl(mbus->sdramwins_base + DDR_SIZE_CS_OFF(i));
- u64 end;
- struct mbus_dram_window *w;
-
- /* Ignore entries that are not enabled */
- if (!(size & DDR_SIZE_ENABLED))
- continue;
-
- /*
- * Ignore entries whose base address is above 2^32,
- * since devices cannot DMA to such high addresses
- */
- if (base & DDR_BASE_CS_HIGH_MASK)
- continue;
-
- base = base & DDR_BASE_CS_LOW_MASK;
- size = (size | ~DDR_SIZE_MASK) + 1;
- end = base + size;
-
- /*
- * Adjust base/size of the current CS to make sure it
- * doesn't overlap with the MBus bridge hole. This is
- * particularly important for devices that do DMA from
- * DRAM to a SRAM mapped in a MBus window, such as the
- * CESA cryptographic engine.
- */
+ u32 base = readl(mbus->sdramwins_base + DDR_BASE_CS_OFF(i));
+ u32 size = readl(mbus->sdramwins_base + DDR_SIZE_CS_OFF(i));
/*
- * The CS is fully enclosed inside the MBus bridge
- * area, so ignore it.
+ * We only take care of entries for which the chip
+ * select is enabled, and that don't have high base
+ * address bits set (devices can only access the first
+ * 32 bits of the memory).
*/
- if (base >= mbus_bridge_base && end <= mbus_bridge_end)
- continue;
+ if ((size & DDR_SIZE_ENABLED) &&
+ !(base & DDR_BASE_CS_HIGH_MASK)) {
+ struct mbus_dram_window *w;
- /*
- * Beginning of CS overlaps with end of MBus, raise CS
- * base address, and shrink its size.
- */
- if (base >= mbus_bridge_base && end > mbus_bridge_end) {
- size -= mbus_bridge_end - base;
- base = mbus_bridge_end;
+ w = &mvebu_mbus_dram_info.cs[cs++];
+ w->cs_index = i;
+ w->mbus_attr = 0xf & ~(1 << i);
+ if (mbus->hw_io_coherency)
+ w->mbus_attr |= ATTR_HW_COHERENCY;
+ w->base = base & DDR_BASE_CS_LOW_MASK;
+ w->size = (size | ~DDR_SIZE_MASK) + 1;
}
-
- /*
- * End of CS overlaps with beginning of MBus, shrink
- * CS size.
- */
- if (base < mbus_bridge_base && end > mbus_bridge_base)
- size -= end - mbus_bridge_base;
-
- w = &mvebu_mbus_dram_info.cs[cs++];
- w->cs_index = i;
- w->mbus_attr = 0xf & ~(1 << i);
- if (mbus->hw_io_coherency)
- w->mbus_attr |= ATTR_HW_COHERENCY;
- w->base = base;
- w->size = size;
}
mvebu_mbus_dram_info.num_cs = cs;
}
/*
* OMAP L3 Interconnect error handling driver
*
- * Copyright (C) 2011-2014 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2011-2015 Texas Instruments Incorporated - http://www.ti.com/
* Santosh Shilimkar <santosh.shilimkar@ti.com>
* Sricharan <r.sricharan@ti.com>
*
}
static const struct of_device_id l3_noc_match[] = {
- {.compatible = "ti,omap4-l3-noc", .data = &omap_l3_data},
+ {.compatible = "ti,omap4-l3-noc", .data = &omap4_l3_data},
+ {.compatible = "ti,omap5-l3-noc", .data = &omap5_l3_data},
{.compatible = "ti,dra7-l3-noc", .data = &dra_l3_data},
{.compatible = "ti,am4372-l3-noc", .data = &am4372_l3_data},
{},
/*
* OMAP L3 Interconnect error handling driver header
*
- * Copyright (C) 2011-2014 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2011-2015 Texas Instruments Incorporated - http://www.ti.com/
* Santosh Shilimkar <santosh.shilimkar@ti.com>
* sricharan <r.sricharan@ti.com>
*
};
-static struct l3_target_data omap_l3_target_data_clk3[] = {
- {0x0100, "EMUSS",},
- {0x0300, "DEBUG SOURCE",},
- {0x0, "HOST CLK3",},
+static struct l3_target_data omap4_l3_target_data_clk3[] = {
+ {0x0100, "DEBUGSS",},
};
-static struct l3_flagmux_data omap_l3_flagmux_clk3 = {
+static struct l3_flagmux_data omap4_l3_flagmux_clk3 = {
.offset = 0x0200,
- .l3_targ = omap_l3_target_data_clk3,
- .num_targ_data = ARRAY_SIZE(omap_l3_target_data_clk3),
+ .l3_targ = omap4_l3_target_data_clk3,
+ .num_targ_data = ARRAY_SIZE(omap4_l3_target_data_clk3),
};
static struct l3_masters_data omap_l3_masters[] = {
{ 0x32, "USBHOSTFS"}
};
-static struct l3_flagmux_data *omap_l3_flagmux[] = {
+static struct l3_flagmux_data *omap4_l3_flagmux[] = {
&omap_l3_flagmux_clk1,
&omap_l3_flagmux_clk2,
- &omap_l3_flagmux_clk3,
+ &omap4_l3_flagmux_clk3,
};
-static const struct omap_l3 omap_l3_data = {
- .l3_flagmux = omap_l3_flagmux,
- .num_modules = ARRAY_SIZE(omap_l3_flagmux),
+static const struct omap_l3 omap4_l3_data = {
+ .l3_flagmux = omap4_l3_flagmux,
+ .num_modules = ARRAY_SIZE(omap4_l3_flagmux),
.l3_masters = omap_l3_masters,
.num_masters = ARRAY_SIZE(omap_l3_masters),
/* The 6 MSBs of register field used to distinguish initiator */
.mst_addr_mask = 0xFC,
};
+/* OMAP5 data */
+static struct l3_target_data omap5_l3_target_data_clk3[] = {
+ {0x0100, "L3INSTR",},
+ {0x0300, "DEBUGSS",},
+ {0x0, "HOSTCLK3",},
+};
+
+static struct l3_flagmux_data omap5_l3_flagmux_clk3 = {
+ .offset = 0x0200,
+ .l3_targ = omap5_l3_target_data_clk3,
+ .num_targ_data = ARRAY_SIZE(omap5_l3_target_data_clk3),
+};
+
+static struct l3_flagmux_data *omap5_l3_flagmux[] = {
+ &omap_l3_flagmux_clk1,
+ &omap_l3_flagmux_clk2,
+ &omap5_l3_flagmux_clk3,
+};
+
+static const struct omap_l3 omap5_l3_data = {
+ .l3_flagmux = omap5_l3_flagmux,
+ .num_modules = ARRAY_SIZE(omap5_l3_flagmux),
+ .l3_masters = omap_l3_masters,
+ .num_masters = ARRAY_SIZE(omap_l3_masters),
+ /* The 6 MSBs of register field used to distinguish initiator */
+ .mst_addr_mask = 0x7E0,
+};
+
/* DRA7 data */
static struct l3_target_data dra_l3_target_data_clk1[] = {
{0x2a00, "AES1",},
static struct l3_target_data dra_l3_target_data_clk2[] = {
{0x0, "HOST CLK1",},
- {0x0, "HOST CLK2",},
+ {0x800000, "HOST CLK2",},
{0xdead, L3_TARGET_NOT_SUPPORTED,},
{0x3400, "SHA2_2",},
{0x0900, "BB2D",},
#include <asm/io.h>
#include <asm/msr.h>
#include <asm/cpufeature.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#define PERIPHERAL_RSHIFT_MASK 0x3
#define PERIPHERAL_RSHIFT(val) (((val) >> 16) & PERIPHERAL_RSHIFT_MASK)
-#define PERIPHERAL_MAX_SHIFT 4
+#define PERIPHERAL_MAX_SHIFT 3
struct clk_peripheral {
struct clk_hw hw;
return *parent_rate;
if (periph->range.max) {
- for (; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+ for (; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
cur_rate = *parent_rate >> shift;
if (cur_rate <= periph->range.max)
break;
best_diff = cur_rate - rate;
best_rate = cur_rate;
- for (; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+ for (; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
cur_rate = *parent_rate >> shift;
if (cur_rate < rate)
cur_diff = rate - cur_rate;
if (periph->range.max && rate > periph->range.max)
return -EINVAL;
- for (shift = 0; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+ for (shift = 0; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
if (parent_rate >> shift == rate) {
periph->auto_div = false;
periph->div = shift;
int i = 0;
/* Check if parent_rate is a valid input rate */
- if (parent_rate < characteristics->input.min ||
- parent_rate > characteristics->input.max)
+ if (parent_rate < characteristics->input.min)
return -ERANGE;
/*
if (!mindiv)
mindiv = 1;
+ if (parent_rate > characteristics->input.max) {
+ tmpdiv = DIV_ROUND_UP(parent_rate, characteristics->input.max);
+ if (tmpdiv > PLL_DIV_MAX)
+ return -ERANGE;
+
+ if (tmpdiv > mindiv)
+ mindiv = tmpdiv;
+ }
+
/*
* Calculate the maximum divider which is limited by PLL register
* layout (limited by the MUL or DIV field size).
struct at91_pmc *pmc);
#endif
-#if defined(CONFIG_HAVE_AT91_SMD)
+#if defined(CONFIG_HAVE_AT91_H32MX)
extern void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
struct at91_pmc *pmc);
#endif
if (!pdata)
return -ENOMEM;
- pdata->clk_xtal = of_clk_get(np, 0);
- if (!IS_ERR(pdata->clk_xtal))
- clk_put(pdata->clk_xtal);
- pdata->clk_clkin = of_clk_get(np, 1);
- if (!IS_ERR(pdata->clk_clkin))
- clk_put(pdata->clk_clkin);
-
/*
* property silabs,pll-source : <num src>, [<..>]
* allow to selectively set pll source
i2c_set_clientdata(client, drvdata);
drvdata->client = client;
drvdata->variant = variant;
- drvdata->pxtal = pdata->clk_xtal;
- drvdata->pclkin = pdata->clk_clkin;
+ drvdata->pxtal = devm_clk_get(&client->dev, "xtal");
+ drvdata->pclkin = devm_clk_get(&client->dev, "clkin");
+
+ if (PTR_ERR(drvdata->pxtal) == -EPROBE_DEFER ||
+ PTR_ERR(drvdata->pclkin) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+
+ /*
+ * Check for valid parent clock: VARIANT_A and VARIANT_B need XTAL,
+ * VARIANT_C can have CLKIN instead.
+ */
+ if (IS_ERR(drvdata->pxtal) &&
+ (drvdata->variant != SI5351_VARIANT_C || IS_ERR(drvdata->pclkin))) {
+ dev_err(&client->dev, "missing parent clock\n");
+ return -EINVAL;
+ }
drvdata->regmap = devm_regmap_init_i2c(client, &si5351_regmap_config);
if (IS_ERR(drvdata->regmap)) {
}
}
+ if (!IS_ERR(drvdata->pxtal))
+ clk_prepare_enable(drvdata->pxtal);
+ if (!IS_ERR(drvdata->pclkin))
+ clk_prepare_enable(drvdata->pclkin);
+
/* register xtal input clock gate */
memset(&init, 0, sizeof(init));
init.name = si5351_input_names[0];
clk = devm_clk_register(&client->dev, &drvdata->xtal);
if (IS_ERR(clk)) {
dev_err(&client->dev, "unable to register %s\n", init.name);
- return PTR_ERR(clk);
+ ret = PTR_ERR(clk);
+ goto err_clk;
}
/* register clkin input clock gate */
if (IS_ERR(clk)) {
dev_err(&client->dev, "unable to register %s\n",
init.name);
- return PTR_ERR(clk);
+ ret = PTR_ERR(clk);
+ goto err_clk;
}
}
clk = devm_clk_register(&client->dev, &drvdata->pll[0].hw);
if (IS_ERR(clk)) {
dev_err(&client->dev, "unable to register %s\n", init.name);
- return -EINVAL;
+ ret = PTR_ERR(clk);
+ goto err_clk;
}
/* register PLLB or VXCO (Si5351B) */
clk = devm_clk_register(&client->dev, &drvdata->pll[1].hw);
if (IS_ERR(clk)) {
dev_err(&client->dev, "unable to register %s\n", init.name);
- return -EINVAL;
+ ret = PTR_ERR(clk);
+ goto err_clk;
}
/* register clk multisync and clk out divider */
num_clocks * sizeof(*drvdata->onecell.clks), GFP_KERNEL);
if (WARN_ON(!drvdata->msynth || !drvdata->clkout ||
- !drvdata->onecell.clks))
- return -ENOMEM;
+ !drvdata->onecell.clks)) {
+ ret = -ENOMEM;
+ goto err_clk;
+ }
for (n = 0; n < num_clocks; n++) {
drvdata->msynth[n].num = n;
if (IS_ERR(clk)) {
dev_err(&client->dev, "unable to register %s\n",
init.name);
- return -EINVAL;
+ ret = PTR_ERR(clk);
+ goto err_clk;
}
}
if (IS_ERR(clk)) {
dev_err(&client->dev, "unable to register %s\n",
init.name);
- return -EINVAL;
+ ret = PTR_ERR(clk);
+ goto err_clk;
}
drvdata->onecell.clks[n] = clk;
&drvdata->onecell);
if (ret) {
dev_err(&client->dev, "unable to add clk provider\n");
- return ret;
+ goto err_clk;
}
return 0;
+
+err_clk:
+ if (!IS_ERR(drvdata->pxtal))
+ clk_disable_unprepare(drvdata->pxtal);
+ if (!IS_ERR(drvdata->pclkin))
+ clk_disable_unprepare(drvdata->pclkin);
+ return ret;
}
static const struct i2c_device_id si5351_i2c_ids[] = {
*/
if (clk->prepare_count) {
clk_core_prepare(parent);
+ flags = clk_enable_lock();
clk_core_enable(parent);
clk_core_enable(clk);
+ clk_enable_unlock(flags);
}
/* update the clk tree topology */
struct clk_core *parent,
struct clk_core *old_parent)
{
+ unsigned long flags;
+
/*
* Finish the migration of prepare state and undo the changes done
* for preventing a race with clk_enable().
*/
if (core->prepare_count) {
+ flags = clk_enable_lock();
clk_core_disable(core);
clk_core_disable(old_parent);
+ clk_enable_unlock(flags);
clk_core_unprepare(old_parent);
}
}
clk_enable_unlock(flags);
if (clk->prepare_count) {
+ flags = clk_enable_lock();
clk_core_disable(clk);
clk_core_disable(parent);
+ clk_enable_unlock(flags);
clk_core_unprepare(parent);
}
return ret;
static const struct parent_map gcc_xo_gpll0a_gpll1_gpll2a_map[] = {
{ P_XO, 0 },
{ P_GPLL0_AUX, 3 },
- { P_GPLL2_AUX, 2 },
{ P_GPLL1, 1 },
+ { P_GPLL2_AUX, 2 },
};
static const char *gcc_xo_gpll0a_gpll1_gpll2a[] = {
static const struct freq_tbl ftbl_gcc_venus0_vcodec0_clk[] = {
F(100000000, P_GPLL0, 8, 0, 0),
F(160000000, P_GPLL0, 5, 0, 0),
- F(228570000, P_GPLL0, 5, 0, 0),
+ F(228570000, P_GPLL0, 3.5, 0, 0),
{ }
};
obj-$(CONFIG_SOC_EXYNOS5260) += clk-exynos5260.o
obj-$(CONFIG_SOC_EXYNOS5410) += clk-exynos5410.o
obj-$(CONFIG_SOC_EXYNOS5420) += clk-exynos5420.o
-obj-$(CONFIG_ARCH_EXYNOS5433) += clk-exynos5433.o
+obj-$(CONFIG_ARCH_EXYNOS) += clk-exynos5433.o
obj-$(CONFIG_SOC_EXYNOS5440) += clk-exynos5440.o
obj-$(CONFIG_ARCH_EXYNOS) += clk-exynos-audss.o
obj-$(CONFIG_ARCH_EXYNOS) += clk-exynos-clkout.o
{ .offset = SRC_MASK_PERIC0, .value = 0x11111110, },
{ .offset = SRC_MASK_PERIC1, .value = 0x11111100, },
{ .offset = SRC_MASK_ISP, .value = 0x11111000, },
+ { .offset = GATE_BUS_TOP, .value = 0xffffffff, },
{ .offset = GATE_BUS_DISP1, .value = 0xffffffff, },
{ .offset = GATE_IP_PERIC, .value = 0xffffffff, },
};
PLL_35XX_RATE(825000000U, 275, 4, 1),
PLL_35XX_RATE(800000000U, 400, 6, 1),
PLL_35XX_RATE(733000000U, 733, 12, 1),
- PLL_35XX_RATE(700000000U, 360, 6, 1),
+ PLL_35XX_RATE(700000000U, 175, 3, 1),
PLL_35XX_RATE(667000000U, 222, 4, 1),
PLL_35XX_RATE(633000000U, 211, 4, 1),
PLL_35XX_RATE(600000000U, 500, 5, 2),
PLL_35XX_RATE(444000000U, 370, 5, 2),
PLL_35XX_RATE(420000000U, 350, 5, 2),
PLL_35XX_RATE(400000000U, 400, 6, 2),
- PLL_35XX_RATE(350000000U, 360, 6, 2),
+ PLL_35XX_RATE(350000000U, 350, 6, 2),
PLL_35XX_RATE(333000000U, 222, 4, 2),
PLL_35XX_RATE(300000000U, 500, 5, 3),
PLL_35XX_RATE(266000000U, 532, 6, 3),
PLL_35XX_RATE(200000000U, 400, 6, 3),
PLL_35XX_RATE(166000000U, 332, 6, 3),
PLL_35XX_RATE(160000000U, 320, 6, 3),
- PLL_35XX_RATE(133000000U, 552, 6, 4),
+ PLL_35XX_RATE(133000000U, 532, 6, 4),
PLL_35XX_RATE(100000000U, 400, 6, 4),
{ /* sentinel */ }
};
/* ENABLE_PCLK_MIF_SECURE_MONOTONIC_CNT */
GATE(CLK_PCLK_MONOTONIC_CNT, "pclk_monotonic_cnt", "div_aclk_mif_133",
- ENABLE_PCLK_MIF_SECURE_RTC, 0, 0, 0),
+ ENABLE_PCLK_MIF_SECURE_MONOTONIC_CNT, 0, 0, 0),
/* ENABLE_PCLK_MIF_SECURE_RTC */
GATE(CLK_PCLK_RTC, "pclk_rtc", "div_aclk_mif_133",
ENABLE_SCLK_APOLLO, 3, CLK_IGNORE_UNUSED, 0),
GATE(CLK_SCLK_HPM_APOLLO, "sclk_hpm_apollo", "div_sclk_hpm_apollo",
ENABLE_SCLK_APOLLO, 1, CLK_IGNORE_UNUSED, 0),
- GATE(CLK_SCLK_APOLLO, "sclk_apollo", "div_apollo_pll",
+ GATE(CLK_SCLK_APOLLO, "sclk_apollo", "div_apollo2",
ENABLE_SCLK_APOLLO, 0, CLK_IGNORE_UNUSED, 0),
};
#define ENABLE_PCLK_MSCL 0x0900
#define ENABLE_PCLK_MSCL_SECURE_SMMU_M2MSCALER0 0x0904
#define ENABLE_PCLK_MSCL_SECURE_SMMU_M2MSCALER1 0x0908
-#define ENABLE_PCLK_MSCL_SECURE_SMMU_JPEG 0x000c
+#define ENABLE_PCLK_MSCL_SECURE_SMMU_JPEG 0x090c
#define ENABLE_SCLK_MSCL 0x0a00
#define ENABLE_IP_MSCL0 0x0b00
#define ENABLE_IP_MSCL1 0x0b04
Support to use the timers of EFM32 SoCs as clock source and clock
event device.
+config CLKSRC_LPC32XX
+ bool
+ select CLKSRC_MMIO
+ select CLKSRC_OF
+
+config CLKSRC_STM32
+ bool "Clocksource for STM32 SoCs" if !ARCH_STM32
+ depends on OF && ARM && (ARCH_STM32 || COMPILE_TEST)
+ select CLKSRC_MMIO
+
config ARM_ARCH_TIMER
bool
select CLKSRC_OF if OF
help
Use ARM global timer clock source as sched_clock
+config ARMV7M_SYSTICK
+ bool
+ select CLKSRC_OF if OF
+ select CLKSRC_MMIO
+ help
+ This options enables support for the ARMv7M system timer unit
+
config ATMEL_PIT
select CLKSRC_OF if OF
def_bool SOC_AT91SAM9 || SOC_SAMA5
obj-$(CONFIG_ARCH_BCM_MOBILE) += bcm_kona_timer.o
obj-$(CONFIG_CADENCE_TTC_TIMER) += cadence_ttc_timer.o
obj-$(CONFIG_CLKSRC_EFM32) += time-efm32.o
+obj-$(CONFIG_CLKSRC_STM32) += timer-stm32.o
obj-$(CONFIG_CLKSRC_EXYNOS_MCT) += exynos_mct.o
+obj-$(CONFIG_CLKSRC_LPC32XX) += time-lpc32xx.o
obj-$(CONFIG_CLKSRC_SAMSUNG_PWM) += samsung_pwm_timer.o
obj-$(CONFIG_FSL_FTM_TIMER) += fsl_ftm_timer.o
obj-$(CONFIG_VF_PIT_TIMER) += vf_pit_timer.o
obj-$(CONFIG_ARM_ARCH_TIMER) += arm_arch_timer.o
obj-$(CONFIG_ARM_GLOBAL_TIMER) += arm_global_timer.o
+obj-$(CONFIG_ARMV7M_SYSTICK) += armv7m_systick.o
obj-$(CONFIG_CLKSRC_METAG_GENERIC) += metag_generic.o
obj-$(CONFIG_ARCH_HAS_TICK_BROADCAST) += dummy_timer.o
obj-$(CONFIG_ARCH_KEYSTONE) += timer-keystone.o
--- /dev/null
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author: Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms: GNU General Public License (GPL), version 2
+ */
+
+#include <linux/kernel.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/clk.h>
+#include <linux/bitops.h>
+
+#define SYST_CSR 0x00
+#define SYST_RVR 0x04
+#define SYST_CVR 0x08
+#define SYST_CALIB 0x0c
+
+#define SYST_CSR_ENABLE BIT(0)
+
+#define SYSTICK_LOAD_RELOAD_MASK 0x00FFFFFF
+
+static void __init system_timer_of_register(struct device_node *np)
+{
+ struct clk *clk = NULL;
+ void __iomem *base;
+ u32 rate;
+ int ret;
+
+ base = of_iomap(np, 0);
+ if (!base) {
+ pr_warn("system-timer: invalid base address\n");
+ return;
+ }
+
+ ret = of_property_read_u32(np, "clock-frequency", &rate);
+ if (ret) {
+ clk = of_clk_get(np, 0);
+ if (IS_ERR(clk))
+ goto out_unmap;
+
+ ret = clk_prepare_enable(clk);
+ if (ret)
+ goto out_clk_put;
+
+ rate = clk_get_rate(clk);
+ if (!rate)
+ goto out_clk_disable;
+ }
+
+ writel_relaxed(SYSTICK_LOAD_RELOAD_MASK, base + SYST_RVR);
+ writel_relaxed(SYST_CSR_ENABLE, base + SYST_CSR);
+
+ ret = clocksource_mmio_init(base + SYST_CVR, "arm_system_timer", rate,
+ 200, 24, clocksource_mmio_readl_down);
+ if (ret) {
+ pr_err("failed to init clocksource (%d)\n", ret);
+ if (clk)
+ goto out_clk_disable;
+ else
+ goto out_unmap;
+ }
+
+ pr_info("ARM System timer initialized as clocksource\n");
+
+ return;
+
+out_clk_disable:
+ clk_disable_unprepare(clk);
+out_clk_put:
+ clk_put(clk);
+out_unmap:
+ iounmap(base);
+ pr_warn("ARM System timer register failed (%d)\n", ret);
+}
+
+CLOCKSOURCE_OF_DECLARE(arm_systick, "arm,armv7m-systick",
+ system_timer_of_register);
unsigned long rate;
priv.base = of_io_request_and_map(np, 0, np->name);
- if (!priv.base)
+ if (IS_ERR(priv.base))
panic("%s: unable to map resource", np->name);
clk = of_clk_get(np, 0);
exynos4_mct_frc_start();
}
-struct clocksource mct_frc = {
+static struct clocksource mct_frc = {
.name = "mct-frc",
.rating = 400,
.read = exynos4_frc_read,
}
}
-static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
+static void exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
{
struct clock_event_device *evt = &mevt->evt;
exynos4_mct_tick_stop(mevt);
/* Clear the MCT tick interrupt */
- if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1) {
+ if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1)
exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
- return 1;
- } else {
- return 0;
- }
}
static irqreturn_t exynos4_mct_tick_isr(int irq, void *dev_id)
free_percpu_irq(mct_irqs[MCT_L0_IRQ], &percpu_mct_tick);
}
-void __init mct_init(void __iomem *base, int irq_g0, int irq_l0, int irq_l1)
-{
- mct_irqs[MCT_G0_IRQ] = irq_g0;
- mct_irqs[MCT_L0_IRQ] = irq_l0;
- mct_irqs[MCT_L1_IRQ] = irq_l1;
- mct_int_type = MCT_INT_SPI;
-
- exynos4_timer_resources(NULL, base);
- exynos4_clocksource_init();
- exynos4_clockevent_init();
-}
-
static void __init mct_init_dt(struct device_node *np, unsigned int int_type)
{
u32 nr_irqs, i;
#define GPT_HZ 32768
-#define MSM_DGT_SHIFT 5
-
static void __iomem *event_base;
static void __iomem *sts_base;
register_current_timer_delay(&msm_delay_timer);
}
-#ifdef CONFIG_ARCH_QCOM
static void __init msm_dt_timer_init(struct device_node *np)
{
u32 freq;
}
CLOCKSOURCE_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init);
CLOCKSOURCE_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init);
-#else
-
-static int __init msm_timer_map(phys_addr_t addr, u32 event, u32 source,
- u32 sts)
-{
- void __iomem *base;
-
- base = ioremap(addr, SZ_256);
- if (!base) {
- pr_err("Failed to map timer base\n");
- return -ENOMEM;
- }
- event_base = base + event;
- source_base = base + source;
- if (sts)
- sts_base = base + sts;
-
- return 0;
-}
-
-static notrace cycle_t msm_read_timer_count_shift(struct clocksource *cs)
-{
- /*
- * Shift timer count down by a constant due to unreliable lower bits
- * on some targets.
- */
- return msm_read_timer_count(cs) >> MSM_DGT_SHIFT;
-}
-
-void __init msm7x01_timer_init(void)
-{
- struct clocksource *cs = &msm_clocksource;
-
- if (msm_timer_map(0xc0100000, 0x0, 0x10, 0x0))
- return;
- cs->read = msm_read_timer_count_shift;
- cs->mask = CLOCKSOURCE_MASK((32 - MSM_DGT_SHIFT));
- /* 600 KHz */
- msm_timer_init(19200000 >> MSM_DGT_SHIFT, 32 - MSM_DGT_SHIFT, 7,
- false);
-}
-
-void __init msm7x30_timer_init(void)
-{
- if (msm_timer_map(0xc0100000, 0x4, 0x24, 0x80))
- return;
- msm_timer_init(24576000 / 4, 32, 1, false);
-}
-
-void __init qsd8x50_timer_init(void)
-{
- if (msm_timer_map(0xAC100000, 0x0, 0x10, 0x34))
- return;
- msm_timer_init(19200000 / 4, 32, 7, false);
-}
-#endif
--- /dev/null
+/*
+ * Clocksource driver for NXP LPC32xx/18xx/43xx timer
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * Based on:
+ * time-efm32 Copyright (C) 2013 Pengutronix
+ * mach-lpc32xx/timer.c Copyright (C) 2009 - 2010 NXP Semiconductors
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ */
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+
+#define LPC32XX_TIMER_IR 0x000
+#define LPC32XX_TIMER_IR_MR0INT BIT(0)
+#define LPC32XX_TIMER_TCR 0x004
+#define LPC32XX_TIMER_TCR_CEN BIT(0)
+#define LPC32XX_TIMER_TCR_CRST BIT(1)
+#define LPC32XX_TIMER_TC 0x008
+#define LPC32XX_TIMER_PR 0x00c
+#define LPC32XX_TIMER_MCR 0x014
+#define LPC32XX_TIMER_MCR_MR0I BIT(0)
+#define LPC32XX_TIMER_MCR_MR0R BIT(1)
+#define LPC32XX_TIMER_MCR_MR0S BIT(2)
+#define LPC32XX_TIMER_MR0 0x018
+#define LPC32XX_TIMER_CTCR 0x070
+
+struct lpc32xx_clock_event_ddata {
+ struct clock_event_device evtdev;
+ void __iomem *base;
+};
+
+/* Needed for the sched clock */
+static void __iomem *clocksource_timer_counter;
+
+static u64 notrace lpc32xx_read_sched_clock(void)
+{
+ return readl(clocksource_timer_counter);
+}
+
+static int lpc32xx_clkevt_next_event(unsigned long delta,
+ struct clock_event_device *evtdev)
+{
+ struct lpc32xx_clock_event_ddata *ddata =
+ container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+ /*
+ * Place timer in reset and program the delta in the prescale
+ * register (PR). When the prescale counter matches the value
+ * in PR the counter register is incremented and the compare
+ * match will trigger. After setup the timer is released from
+ * reset and enabled.
+ */
+ writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR);
+ writel_relaxed(delta, ddata->base + LPC32XX_TIMER_PR);
+ writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR);
+
+ return 0;
+}
+
+static int lpc32xx_clkevt_shutdown(struct clock_event_device *evtdev)
+{
+ struct lpc32xx_clock_event_ddata *ddata =
+ container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+ /* Disable the timer */
+ writel_relaxed(0, ddata->base + LPC32XX_TIMER_TCR);
+
+ return 0;
+}
+
+static int lpc32xx_clkevt_oneshot(struct clock_event_device *evtdev)
+{
+ /*
+ * When using oneshot, we must also disable the timer
+ * to wait for the first call to set_next_event().
+ */
+ return lpc32xx_clkevt_shutdown(evtdev);
+}
+
+static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id)
+{
+ struct lpc32xx_clock_event_ddata *ddata = dev_id;
+
+ /* Clear match on channel 0 */
+ writel_relaxed(LPC32XX_TIMER_IR_MR0INT, ddata->base + LPC32XX_TIMER_IR);
+
+ ddata->evtdev.event_handler(&ddata->evtdev);
+
+ return IRQ_HANDLED;
+}
+
+static struct lpc32xx_clock_event_ddata lpc32xx_clk_event_ddata = {
+ .evtdev = {
+ .name = "lpc3220 clockevent",
+ .features = CLOCK_EVT_FEAT_ONESHOT,
+ .rating = 300,
+ .set_next_event = lpc32xx_clkevt_next_event,
+ .set_state_shutdown = lpc32xx_clkevt_shutdown,
+ .set_state_oneshot = lpc32xx_clkevt_oneshot,
+ },
+};
+
+static int __init lpc32xx_clocksource_init(struct device_node *np)
+{
+ void __iomem *base;
+ unsigned long rate;
+ struct clk *clk;
+ int ret;
+
+ clk = of_clk_get_by_name(np, "timerclk");
+ if (IS_ERR(clk)) {
+ pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+ return PTR_ERR(clk);
+ }
+
+ ret = clk_prepare_enable(clk);
+ if (ret) {
+ pr_err("clock enable failed (%d)\n", ret);
+ goto err_clk_enable;
+ }
+
+ base = of_iomap(np, 0);
+ if (!base) {
+ pr_err("unable to map registers\n");
+ ret = -EADDRNOTAVAIL;
+ goto err_iomap;
+ }
+
+ /*
+ * Disable and reset timer then set it to free running timer
+ * mode (CTCR) with no prescaler (PR) or match operations (MCR).
+ * After setup the timer is released from reset and enabled.
+ */
+ writel_relaxed(LPC32XX_TIMER_TCR_CRST, base + LPC32XX_TIMER_TCR);
+ writel_relaxed(0, base + LPC32XX_TIMER_PR);
+ writel_relaxed(0, base + LPC32XX_TIMER_MCR);
+ writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+ writel_relaxed(LPC32XX_TIMER_TCR_CEN, base + LPC32XX_TIMER_TCR);
+
+ rate = clk_get_rate(clk);
+ ret = clocksource_mmio_init(base + LPC32XX_TIMER_TC, "lpc3220 timer",
+ rate, 300, 32, clocksource_mmio_readl_up);
+ if (ret) {
+ pr_err("failed to init clocksource (%d)\n", ret);
+ goto err_clocksource_init;
+ }
+
+ clocksource_timer_counter = base + LPC32XX_TIMER_TC;
+ sched_clock_register(lpc32xx_read_sched_clock, 32, rate);
+
+ return 0;
+
+err_clocksource_init:
+ iounmap(base);
+err_iomap:
+ clk_disable_unprepare(clk);
+err_clk_enable:
+ clk_put(clk);
+ return ret;
+}
+
+static int __init lpc32xx_clockevent_init(struct device_node *np)
+{
+ void __iomem *base;
+ unsigned long rate;
+ struct clk *clk;
+ int ret, irq;
+
+ clk = of_clk_get_by_name(np, "timerclk");
+ if (IS_ERR(clk)) {
+ pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+ return PTR_ERR(clk);
+ }
+
+ ret = clk_prepare_enable(clk);
+ if (ret) {
+ pr_err("clock enable failed (%d)\n", ret);
+ goto err_clk_enable;
+ }
+
+ base = of_iomap(np, 0);
+ if (!base) {
+ pr_err("unable to map registers\n");
+ ret = -EADDRNOTAVAIL;
+ goto err_iomap;
+ }
+
+ irq = irq_of_parse_and_map(np, 0);
+ if (!irq) {
+ pr_err("get irq failed\n");
+ ret = -ENOENT;
+ goto err_irq;
+ }
+
+ /*
+ * Disable timer and clear any pending interrupt (IR) on match
+ * channel 0 (MR0). Configure a compare match value of 1 on MR0
+ * and enable interrupt, reset on match and stop on match (MCR).
+ */
+ writel_relaxed(0, base + LPC32XX_TIMER_TCR);
+ writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+ writel_relaxed(LPC32XX_TIMER_IR_MR0INT, base + LPC32XX_TIMER_IR);
+ writel_relaxed(1, base + LPC32XX_TIMER_MR0);
+ writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R |
+ LPC32XX_TIMER_MCR_MR0S, base + LPC32XX_TIMER_MCR);
+
+ rate = clk_get_rate(clk);
+ lpc32xx_clk_event_ddata.base = base;
+ clockevents_config_and_register(&lpc32xx_clk_event_ddata.evtdev,
+ rate, 1, -1);
+
+ ret = request_irq(irq, lpc32xx_clock_event_handler,
+ IRQF_TIMER | IRQF_IRQPOLL, "lpc3220 clockevent",
+ &lpc32xx_clk_event_ddata);
+ if (ret) {
+ pr_err("request irq failed\n");
+ goto err_irq;
+ }
+
+ return 0;
+
+err_irq:
+ iounmap(base);
+err_iomap:
+ clk_disable_unprepare(clk);
+err_clk_enable:
+ clk_put(clk);
+ return ret;
+}
+
+/*
+ * This function asserts that we have exactly one clocksource and one
+ * clock_event_device in the end.
+ */
+static void __init lpc32xx_timer_init(struct device_node *np)
+{
+ static int has_clocksource, has_clockevent;
+ int ret;
+
+ if (!has_clocksource) {
+ ret = lpc32xx_clocksource_init(np);
+ if (!ret) {
+ has_clocksource = 1;
+ return;
+ }
+ }
+
+ if (!has_clockevent) {
+ ret = lpc32xx_clockevent_init(np);
+ if (!ret) {
+ has_clockevent = 1;
+ return;
+ }
+ }
+}
+CLOCKSOURCE_OF_DECLARE(lpc32xx_timer, "nxp,lpc3220-timer", lpc32xx_timer_init);
struct device_node *sec_node;
base = of_io_request_and_map(node, 0, "integrator-timer");
- if (!base)
+ if (IS_ERR(base))
return;
clk = of_clk_get(node, 0);
--- /dev/null
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author: Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms: GNU General Public License (GPL), version 2
+ *
+ * Inspired by time-efm32.c from Uwe Kleine-Koenig
+ */
+
+#include <linux/kernel.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/clk.h>
+#include <linux/reset.h>
+
+#define TIM_CR1 0x00
+#define TIM_DIER 0x0c
+#define TIM_SR 0x10
+#define TIM_EGR 0x14
+#define TIM_PSC 0x28
+#define TIM_ARR 0x2c
+
+#define TIM_CR1_CEN BIT(0)
+#define TIM_CR1_OPM BIT(3)
+#define TIM_CR1_ARPE BIT(7)
+
+#define TIM_DIER_UIE BIT(0)
+
+#define TIM_SR_UIF BIT(0)
+
+#define TIM_EGR_UG BIT(0)
+
+struct stm32_clock_event_ddata {
+ struct clock_event_device evtdev;
+ unsigned periodic_top;
+ void __iomem *base;
+};
+
+static void stm32_clock_event_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *evtdev)
+{
+ struct stm32_clock_event_ddata *data =
+ container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+ void *base = data->base;
+
+ switch (mode) {
+ case CLOCK_EVT_MODE_PERIODIC:
+ writel_relaxed(data->periodic_top, base + TIM_ARR);
+ writel_relaxed(TIM_CR1_ARPE | TIM_CR1_CEN, base + TIM_CR1);
+ break;
+
+ case CLOCK_EVT_MODE_ONESHOT:
+ default:
+ writel_relaxed(0, base + TIM_CR1);
+ break;
+ }
+}
+
+static int stm32_clock_event_set_next_event(unsigned long evt,
+ struct clock_event_device *evtdev)
+{
+ struct stm32_clock_event_ddata *data =
+ container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+
+ writel_relaxed(evt, data->base + TIM_ARR);
+ writel_relaxed(TIM_CR1_ARPE | TIM_CR1_OPM | TIM_CR1_CEN,
+ data->base + TIM_CR1);
+
+ return 0;
+}
+
+static irqreturn_t stm32_clock_event_handler(int irq, void *dev_id)
+{
+ struct stm32_clock_event_ddata *data = dev_id;
+
+ writel_relaxed(0, data->base + TIM_SR);
+
+ data->evtdev.event_handler(&data->evtdev);
+
+ return IRQ_HANDLED;
+}
+
+static struct stm32_clock_event_ddata clock_event_ddata = {
+ .evtdev = {
+ .name = "stm32 clockevent",
+ .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
+ .set_mode = stm32_clock_event_set_mode,
+ .set_next_event = stm32_clock_event_set_next_event,
+ .rating = 200,
+ },
+};
+
+static void __init stm32_clockevent_init(struct device_node *np)
+{
+ struct stm32_clock_event_ddata *data = &clock_event_ddata;
+ struct clk *clk;
+ struct reset_control *rstc;
+ unsigned long rate, max_delta;
+ int irq, ret, bits, prescaler = 1;
+
+ clk = of_clk_get(np, 0);
+ if (IS_ERR(clk)) {
+ ret = PTR_ERR(clk);
+ pr_err("failed to get clock for clockevent (%d)\n", ret);
+ goto err_clk_get;
+ }
+
+ ret = clk_prepare_enable(clk);
+ if (ret) {
+ pr_err("failed to enable timer clock for clockevent (%d)\n",
+ ret);
+ goto err_clk_enable;
+ }
+
+ rate = clk_get_rate(clk);
+
+ rstc = of_reset_control_get(np, NULL);
+ if (!IS_ERR(rstc)) {
+ reset_control_assert(rstc);
+ reset_control_deassert(rstc);
+ }
+
+ data->base = of_iomap(np, 0);
+ if (!data->base) {
+ pr_err("failed to map registers for clockevent\n");
+ goto err_iomap;
+ }
+
+ irq = irq_of_parse_and_map(np, 0);
+ if (!irq) {
+ pr_err("%s: failed to get irq.\n", np->full_name);
+ goto err_get_irq;
+ }
+
+ /* Detect whether the timer is 16 or 32 bits */
+ writel_relaxed(~0U, data->base + TIM_ARR);
+ max_delta = readl_relaxed(data->base + TIM_ARR);
+ if (max_delta == ~0U) {
+ prescaler = 1;
+ bits = 32;
+ } else {
+ prescaler = 1024;
+ bits = 16;
+ }
+ writel_relaxed(0, data->base + TIM_ARR);
+
+ writel_relaxed(prescaler - 1, data->base + TIM_PSC);
+ writel_relaxed(TIM_EGR_UG, data->base + TIM_EGR);
+ writel_relaxed(TIM_DIER_UIE, data->base + TIM_DIER);
+ writel_relaxed(0, data->base + TIM_SR);
+
+ data->periodic_top = DIV_ROUND_CLOSEST(rate, prescaler * HZ);
+
+ clockevents_config_and_register(&data->evtdev,
+ DIV_ROUND_CLOSEST(rate, prescaler),
+ 0x1, max_delta);
+
+ ret = request_irq(irq, stm32_clock_event_handler, IRQF_TIMER,
+ "stm32 clockevent", data);
+ if (ret) {
+ pr_err("%s: failed to request irq.\n", np->full_name);
+ goto err_get_irq;
+ }
+
+ pr_info("%s: STM32 clockevent driver initialized (%d bits)\n",
+ np->full_name, bits);
+
+ return;
+
+err_get_irq:
+ iounmap(data->base);
+err_iomap:
+ clk_disable_unprepare(clk);
+err_clk_enable:
+ clk_put(clk);
+err_clk_get:
+ return;
+}
+
+CLOCKSOURCE_OF_DECLARE(stm32, "st,stm32-timer", stm32_clockevent_init);
int irq;
timer_base = of_io_request_and_map(node, 0, of_node_full_name(node));
- if (!timer_base)
+ if (IS_ERR(timer_base))
panic("Can't map registers");
irq = irq_of_parse_and_map(node, 0);
dmi_check_system(sw_any_bug_dmi_table);
if (bios_with_sw_any_bug && !policy_is_shared(policy)) {
policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
- cpumask_copy(policy->cpus, cpu_core_mask(cpu));
+ cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
}
if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
cpumask_clear(policy->cpus);
cpumask_set_cpu(cpu, policy->cpus);
- cpumask_copy(data->freqdomain_cpus, cpu_sibling_mask(cpu));
+ cpumask_copy(data->freqdomain_cpus,
+ topology_sibling_cpumask(cpu));
policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
pr_info_once(PFX "overriding BIOS provided _PSD data\n");
}
#include <linux/fs.h>
#include <linux/debugfs.h>
#include <linux/acpi.h>
+#include <linux/vmalloc.h>
#include <trace/events/power.h>
#include <asm/div64.h>
unsigned int i;
#ifdef CONFIG_SMP
- cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+ cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
#endif
/* Errata workaround */
static struct cpufreq_driver cpufreq_amd64_driver;
-#ifndef CONFIG_SMP
-static inline const struct cpumask *cpu_core_mask(int cpu)
-{
- return cpumask_of(0);
-}
-#endif
-
/* Return a frequency in MHz, given an input fid */
static u32 find_freq_from_fid(u32 fid)
{
pr_debug("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
data->powernow_table = powernow_table;
- if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+ if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
print_basics(data);
for (j = 0; j < data->numps; j++)
CPUFREQ_TABLE_END;
data->powernow_table = powernow_table;
- if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+ if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
print_basics(data);
/* notify BIOS that we exist */
if (rc != 0)
goto err_out_exit_acpi;
- cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
+ cpumask_copy(pol->cpus, topology_core_cpumask(pol->cpu));
data->available_cores = pol->cpus;
/* min/max the cpu is capable of */
/* only run on CPU to be set, or on its sibling */
#ifdef CONFIG_SMP
- cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+ cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
#endif
policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
state->current_buf = 0;
state->buf_dma = 0;
+ state->buflen_0 = 0;
+ state->buflen_1 = 0;
return 0;
}
/* Buffer, its dma address and lock */
struct buf_data {
- u8 buf[RN_BUF_SIZE];
+ u8 buf[RN_BUF_SIZE] ____cacheline_aligned;
dma_addr_t addr;
struct completion filled;
u32 hw_desc[DESC_JOB_O_LEN];
#include <asm/cpu_device_id.h>
#include <asm/byteorder.h>
#include <asm/processor.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
/*
* Number of data blocks actually fetched for each xcrypt insn.
#include <linux/kernel.h>
#include <linux/scatterlist.h>
#include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
struct padlock_sha_desc {
struct shash_desc fallback;
int ret;
struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
pagefault_enable();
-
+ preempt_enable();
+
ret += crypto_cipher_setkey(ctx->fallback, key, keylen);
return ret;
}
if (in_interrupt()) {
crypto_cipher_encrypt_one(ctx->fallback, dst, src);
} else {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
aes_p8_encrypt(src, dst, &ctx->enc_key);
pagefault_enable();
+ preempt_enable();
}
}
if (in_interrupt()) {
crypto_cipher_decrypt_one(ctx->fallback, dst, src);
} else {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
aes_p8_decrypt(src, dst, &ctx->dec_key);
pagefault_enable();
+ preempt_enable();
}
}
int ret;
struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
pagefault_enable();
+ preempt_enable();
ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
return ret;
if (in_interrupt()) {
ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes);
} else {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
}
pagefault_enable();
+ preempt_enable();
}
return ret;
if (in_interrupt()) {
ret = crypto_blkcipher_decrypt(&fallback_desc, dst, src, nbytes);
} else {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
}
pagefault_enable();
+ preempt_enable();
}
return ret;
if (keylen != GHASH_KEY_LEN)
return -EINVAL;
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
enable_kernel_fp();
gcm_init_p8(ctx->htable, (const u64 *) key);
pagefault_enable();
+ preempt_enable();
return crypto_shash_setkey(ctx->fallback, key, keylen);
}
}
memcpy(dctx->buffer + dctx->bytes, src,
GHASH_DIGEST_SIZE - dctx->bytes);
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
enable_kernel_fp();
gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer,
GHASH_DIGEST_SIZE);
pagefault_enable();
+ preempt_enable();
src += GHASH_DIGEST_SIZE - dctx->bytes;
srclen -= GHASH_DIGEST_SIZE - dctx->bytes;
dctx->bytes = 0;
}
len = srclen & ~(GHASH_DIGEST_SIZE - 1);
if (len) {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
enable_kernel_fp();
gcm_ghash_p8(dctx->shash, ctx->htable, src, len);
pagefault_enable();
+ preempt_enable();
src += len;
srclen -= len;
}
if (dctx->bytes) {
for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++)
dctx->buffer[i] = 0;
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
enable_kernel_fp();
gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer,
GHASH_DIGEST_SIZE);
pagefault_enable();
+ preempt_enable();
dctx->bytes = 0;
}
memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
#define AT_XDMAC_MBR_UBC_NDV3 (0x3 << 27) /* Next Descriptor View 3 */
#define AT_XDMAC_MAX_CHAN 0x20
+#define AT_XDMAC_MAX_CSIZE 16 /* 16 data */
+#define AT_XDMAC_MAX_DWIDTH 8 /* 64 bits */
#define AT_XDMAC_DMA_BUSWIDTHS\
(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
struct dma_chan chan;
void __iomem *ch_regs;
u32 mask; /* Channel Mask */
- u32 cfg[2]; /* Channel Configuration Register */
- #define AT_XDMAC_DEV_TO_MEM_CFG 0 /* Predifined dev to mem channel conf */
- #define AT_XDMAC_MEM_TO_DEV_CFG 1 /* Predifined mem to dev channel conf */
+ u32 cfg; /* Channel Configuration Register */
u8 perid; /* Peripheral ID */
u8 perif; /* Peripheral Interface */
u8 memif; /* Memory Interface */
- u32 per_src_addr;
- u32 per_dst_addr;
u32 save_cc;
u32 save_cim;
u32 save_cnda;
u32 save_cndc;
unsigned long status;
struct tasklet_struct tasklet;
+ struct dma_slave_config sconfig;
spinlock_t lock;
struct at_xdmac_desc *desc = txd_to_at_desc(tx);
struct at_xdmac_chan *atchan = to_at_xdmac_chan(tx->chan);
dma_cookie_t cookie;
+ unsigned long irqflags;
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, irqflags);
cookie = dma_cookie_assign(tx);
dev_vdbg(chan2dev(tx->chan), "%s: atchan 0x%p, add desc 0x%p to xfers_list\n",
if (list_is_singular(&atchan->xfers_list))
at_xdmac_start_xfer(atchan, desc);
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, irqflags);
return cookie;
}
return chan;
}
+static int at_xdmac_compute_chan_conf(struct dma_chan *chan,
+ enum dma_transfer_direction direction)
+{
+ struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan);
+ int csize, dwidth;
+
+ if (direction == DMA_DEV_TO_MEM) {
+ atchan->cfg =
+ AT91_XDMAC_DT_PERID(atchan->perid)
+ | AT_XDMAC_CC_DAM_INCREMENTED_AM
+ | AT_XDMAC_CC_SAM_FIXED_AM
+ | AT_XDMAC_CC_DIF(atchan->memif)
+ | AT_XDMAC_CC_SIF(atchan->perif)
+ | AT_XDMAC_CC_SWREQ_HWR_CONNECTED
+ | AT_XDMAC_CC_DSYNC_PER2MEM
+ | AT_XDMAC_CC_MBSIZE_SIXTEEN
+ | AT_XDMAC_CC_TYPE_PER_TRAN;
+ csize = ffs(atchan->sconfig.src_maxburst) - 1;
+ if (csize < 0) {
+ dev_err(chan2dev(chan), "invalid src maxburst value\n");
+ return -EINVAL;
+ }
+ atchan->cfg |= AT_XDMAC_CC_CSIZE(csize);
+ dwidth = ffs(atchan->sconfig.src_addr_width) - 1;
+ if (dwidth < 0) {
+ dev_err(chan2dev(chan), "invalid src addr width value\n");
+ return -EINVAL;
+ }
+ atchan->cfg |= AT_XDMAC_CC_DWIDTH(dwidth);
+ } else if (direction == DMA_MEM_TO_DEV) {
+ atchan->cfg =
+ AT91_XDMAC_DT_PERID(atchan->perid)
+ | AT_XDMAC_CC_DAM_FIXED_AM
+ | AT_XDMAC_CC_SAM_INCREMENTED_AM
+ | AT_XDMAC_CC_DIF(atchan->perif)
+ | AT_XDMAC_CC_SIF(atchan->memif)
+ | AT_XDMAC_CC_SWREQ_HWR_CONNECTED
+ | AT_XDMAC_CC_DSYNC_MEM2PER
+ | AT_XDMAC_CC_MBSIZE_SIXTEEN
+ | AT_XDMAC_CC_TYPE_PER_TRAN;
+ csize = ffs(atchan->sconfig.dst_maxburst) - 1;
+ if (csize < 0) {
+ dev_err(chan2dev(chan), "invalid src maxburst value\n");
+ return -EINVAL;
+ }
+ atchan->cfg |= AT_XDMAC_CC_CSIZE(csize);
+ dwidth = ffs(atchan->sconfig.dst_addr_width) - 1;
+ if (dwidth < 0) {
+ dev_err(chan2dev(chan), "invalid dst addr width value\n");
+ return -EINVAL;
+ }
+ atchan->cfg |= AT_XDMAC_CC_DWIDTH(dwidth);
+ }
+
+ dev_dbg(chan2dev(chan), "%s: cfg=0x%08x\n", __func__, atchan->cfg);
+
+ return 0;
+}
+
+/*
+ * Only check that maxburst and addr width values are supported by the
+ * the controller but not that the configuration is good to perform the
+ * transfer since we don't know the direction at this stage.
+ */
+static int at_xdmac_check_slave_config(struct dma_slave_config *sconfig)
+{
+ if ((sconfig->src_maxburst > AT_XDMAC_MAX_CSIZE)
+ || (sconfig->dst_maxburst > AT_XDMAC_MAX_CSIZE))
+ return -EINVAL;
+
+ if ((sconfig->src_addr_width > AT_XDMAC_MAX_DWIDTH)
+ || (sconfig->dst_addr_width > AT_XDMAC_MAX_DWIDTH))
+ return -EINVAL;
+
+ return 0;
+}
+
static int at_xdmac_set_slave_config(struct dma_chan *chan,
struct dma_slave_config *sconfig)
{
struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan);
- u8 dwidth;
- int csize;
- atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] =
- AT91_XDMAC_DT_PERID(atchan->perid)
- | AT_XDMAC_CC_DAM_INCREMENTED_AM
- | AT_XDMAC_CC_SAM_FIXED_AM
- | AT_XDMAC_CC_DIF(atchan->memif)
- | AT_XDMAC_CC_SIF(atchan->perif)
- | AT_XDMAC_CC_SWREQ_HWR_CONNECTED
- | AT_XDMAC_CC_DSYNC_PER2MEM
- | AT_XDMAC_CC_MBSIZE_SIXTEEN
- | AT_XDMAC_CC_TYPE_PER_TRAN;
- csize = at_xdmac_csize(sconfig->src_maxburst);
- if (csize < 0) {
- dev_err(chan2dev(chan), "invalid src maxburst value\n");
+ if (at_xdmac_check_slave_config(sconfig)) {
+ dev_err(chan2dev(chan), "invalid slave configuration\n");
return -EINVAL;
}
- atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] |= AT_XDMAC_CC_CSIZE(csize);
- dwidth = ffs(sconfig->src_addr_width) - 1;
- atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] |= AT_XDMAC_CC_DWIDTH(dwidth);
-
-
- atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] =
- AT91_XDMAC_DT_PERID(atchan->perid)
- | AT_XDMAC_CC_DAM_FIXED_AM
- | AT_XDMAC_CC_SAM_INCREMENTED_AM
- | AT_XDMAC_CC_DIF(atchan->perif)
- | AT_XDMAC_CC_SIF(atchan->memif)
- | AT_XDMAC_CC_SWREQ_HWR_CONNECTED
- | AT_XDMAC_CC_DSYNC_MEM2PER
- | AT_XDMAC_CC_MBSIZE_SIXTEEN
- | AT_XDMAC_CC_TYPE_PER_TRAN;
- csize = at_xdmac_csize(sconfig->dst_maxburst);
- if (csize < 0) {
- dev_err(chan2dev(chan), "invalid src maxburst value\n");
- return -EINVAL;
- }
- atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] |= AT_XDMAC_CC_CSIZE(csize);
- dwidth = ffs(sconfig->dst_addr_width) - 1;
- atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] |= AT_XDMAC_CC_DWIDTH(dwidth);
-
- /* Src and dst addr are needed to configure the link list descriptor. */
- atchan->per_src_addr = sconfig->src_addr;
- atchan->per_dst_addr = sconfig->dst_addr;
- dev_dbg(chan2dev(chan),
- "%s: cfg[dev2mem]=0x%08x, cfg[mem2dev]=0x%08x, per_src_addr=0x%08x, per_dst_addr=0x%08x\n",
- __func__, atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG],
- atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG],
- atchan->per_src_addr, atchan->per_dst_addr);
+ memcpy(&atchan->sconfig, sconfig, sizeof(atchan->sconfig));
return 0;
}
struct scatterlist *sg;
int i;
unsigned int xfer_size = 0;
+ unsigned long irqflags;
+ struct dma_async_tx_descriptor *ret = NULL;
if (!sgl)
return NULL;
flags);
/* Protect dma_sconfig field that can be modified by set_slave_conf. */
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, irqflags);
+
+ if (at_xdmac_compute_chan_conf(chan, direction))
+ goto spin_unlock;
/* Prepare descriptors. */
for_each_sg(sgl, sg, sg_len, i) {
mem = sg_dma_address(sg);
if (unlikely(!len)) {
dev_err(chan2dev(chan), "sg data length is zero\n");
- spin_unlock_bh(&atchan->lock);
- return NULL;
+ goto spin_unlock;
}
dev_dbg(chan2dev(chan), "%s: * sg%d len=%u, mem=0x%08x\n",
__func__, i, len, mem);
dev_err(chan2dev(chan), "can't get descriptor\n");
if (first)
list_splice_init(&first->descs_list, &atchan->free_descs_list);
- spin_unlock_bh(&atchan->lock);
- return NULL;
+ goto spin_unlock;
}
/* Linked list descriptor setup. */
if (direction == DMA_DEV_TO_MEM) {
- desc->lld.mbr_sa = atchan->per_src_addr;
+ desc->lld.mbr_sa = atchan->sconfig.src_addr;
desc->lld.mbr_da = mem;
- desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
} else {
desc->lld.mbr_sa = mem;
- desc->lld.mbr_da = atchan->per_dst_addr;
- desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+ desc->lld.mbr_da = atchan->sconfig.dst_addr;
}
+ desc->lld.mbr_cfg = atchan->cfg;
dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg);
fixed_dwidth = IS_ALIGNED(len, 1 << dwidth)
? at_xdmac_get_dwidth(desc->lld.mbr_cfg)
xfer_size += len;
}
- spin_unlock_bh(&atchan->lock);
first->tx_dma_desc.flags = flags;
first->xfer_size = xfer_size;
first->direction = direction;
+ ret = &first->tx_dma_desc;
- return &first->tx_dma_desc;
+spin_unlock:
+ spin_unlock_irqrestore(&atchan->lock, irqflags);
+ return ret;
}
static struct dma_async_tx_descriptor *
struct at_xdmac_desc *first = NULL, *prev = NULL;
unsigned int periods = buf_len / period_len;
int i;
+ unsigned long irqflags;
dev_dbg(chan2dev(chan), "%s: buf_addr=%pad, buf_len=%zd, period_len=%zd, dir=%s, flags=0x%lx\n",
__func__, &buf_addr, buf_len, period_len,
return NULL;
}
+ if (at_xdmac_compute_chan_conf(chan, direction))
+ return NULL;
+
for (i = 0; i < periods; i++) {
struct at_xdmac_desc *desc = NULL;
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, irqflags);
desc = at_xdmac_get_desc(atchan);
if (!desc) {
dev_err(chan2dev(chan), "can't get descriptor\n");
if (first)
list_splice_init(&first->descs_list, &atchan->free_descs_list);
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, irqflags);
return NULL;
}
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, irqflags);
dev_dbg(chan2dev(chan),
"%s: desc=0x%p, tx_dma_desc.phys=%pad\n",
__func__, desc, &desc->tx_dma_desc.phys);
if (direction == DMA_DEV_TO_MEM) {
- desc->lld.mbr_sa = atchan->per_src_addr;
+ desc->lld.mbr_sa = atchan->sconfig.src_addr;
desc->lld.mbr_da = buf_addr + i * period_len;
- desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
} else {
desc->lld.mbr_sa = buf_addr + i * period_len;
- desc->lld.mbr_da = atchan->per_dst_addr;
- desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+ desc->lld.mbr_da = atchan->sconfig.dst_addr;
}
+ desc->lld.mbr_cfg = atchan->cfg;
desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV1
| AT_XDMAC_MBR_UBC_NDEN
| AT_XDMAC_MBR_UBC_NSEN
| AT_XDMAC_CC_SIF(0)
| AT_XDMAC_CC_MBSIZE_SIXTEEN
| AT_XDMAC_CC_TYPE_MEM_TRAN;
+ unsigned long irqflags;
dev_dbg(chan2dev(chan), "%s: src=%pad, dest=%pad, len=%zd, flags=0x%lx\n",
__func__, &src, &dest, len, flags);
dev_dbg(chan2dev(chan), "%s: remaining_size=%zu\n", __func__, remaining_size);
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, irqflags);
desc = at_xdmac_get_desc(atchan);
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, irqflags);
if (!desc) {
dev_err(chan2dev(chan), "can't get descriptor\n");
if (first)
int residue;
u32 cur_nda, mask, value;
u8 dwidth = 0;
+ unsigned long flags;
ret = dma_cookie_status(chan, cookie, txstate);
if (ret == DMA_COMPLETE)
if (!txstate)
return ret;
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, flags);
desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc, xfer_node);
*/
if (!desc->active_xfer) {
dma_set_residue(txstate, desc->xfer_size);
- spin_unlock_bh(&atchan->lock);
- return ret;
+ goto spin_unlock;
}
residue = desc->xfer_size;
}
residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth;
- spin_unlock_bh(&atchan->lock);
-
dma_set_residue(txstate, residue);
dev_dbg(chan2dev(chan),
"%s: desc=0x%p, tx_dma_desc.phys=%pad, tx_status=%d, cookie=%d, residue=%d\n",
__func__, desc, &desc->tx_dma_desc.phys, ret, cookie, residue);
+spin_unlock:
+ spin_unlock_irqrestore(&atchan->lock, flags);
return ret;
}
static void at_xdmac_advance_work(struct at_xdmac_chan *atchan)
{
struct at_xdmac_desc *desc;
+ unsigned long flags;
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, flags);
/*
* If channel is enabled, do nothing, advance_work will be triggered
at_xdmac_start_xfer(atchan, desc);
}
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, flags);
}
static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan)
{
struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan);
int ret;
+ unsigned long flags;
dev_dbg(chan2dev(chan), "%s\n", __func__);
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, flags);
ret = at_xdmac_set_slave_config(chan, config);
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, flags);
return ret;
}
{
struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan);
struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device);
+ unsigned long flags;
dev_dbg(chan2dev(chan), "%s\n", __func__);
if (test_and_set_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status))
return 0;
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, flags);
at_xdmac_write(atxdmac, AT_XDMAC_GRWS, atchan->mask);
while (at_xdmac_chan_read(atchan, AT_XDMAC_CC)
& (AT_XDMAC_CC_WRIP | AT_XDMAC_CC_RDIP))
cpu_relax();
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, flags);
return 0;
}
{
struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan);
struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device);
+ unsigned long flags;
dev_dbg(chan2dev(chan), "%s\n", __func__);
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, flags);
if (!at_xdmac_chan_is_paused(atchan)) {
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, flags);
return 0;
}
at_xdmac_write(atxdmac, AT_XDMAC_GRWR, atchan->mask);
clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, flags);
return 0;
}
struct at_xdmac_desc *desc, *_desc;
struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan);
struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device);
+ unsigned long flags;
dev_dbg(chan2dev(chan), "%s\n", __func__);
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, flags);
at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask);
while (at_xdmac_read(atxdmac, AT_XDMAC_GS) & atchan->mask)
cpu_relax();
at_xdmac_remove_xfer(atchan, desc);
clear_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status);
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, flags);
return 0;
}
struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan);
struct at_xdmac_desc *desc;
int i;
+ unsigned long flags;
- spin_lock_bh(&atchan->lock);
+ spin_lock_irqsave(&atchan->lock, flags);
if (at_xdmac_chan_is_enabled(atchan)) {
dev_err(chan2dev(chan),
dev_dbg(chan2dev(chan), "%s: allocated %d descriptors\n", __func__, i);
spin_unlock:
- spin_unlock_bh(&atchan->lock);
+ spin_unlock_irqrestore(&atchan->lock, flags);
return i;
}
caps->directions = device->directions;
caps->residue_granularity = device->residue_granularity;
- caps->cmd_pause = !!device->device_pause;
+ /*
+ * Some devices implement only pause (e.g. to get residuum) but no
+ * resume. However cmd_pause is advertised as pause AND resume.
+ */
+ caps->cmd_pause = !!(device->device_pause && device->device_resume);
caps->cmd_terminate = !!device->device_terminate_all;
return 0;
spin_lock_irqsave(&hsuc->vchan.lock, flags);
hsu_dma_stop_channel(hsuc);
- hsuc->desc = NULL;
+ if (hsuc->desc) {
+ hsu_dma_desc_free(&hsuc->desc->vdesc);
+ hsuc->desc = NULL;
+ }
vchan_get_all_descriptors(&hsuc->vchan, &head);
spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
#include <linux/module.h>
#include <linux/io.h>
#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
#include "mic_x100_dma.h"
struct pl330_dmac *pl330 = pch->dmac;
LIST_HEAD(list);
+ pm_runtime_get_sync(pl330->ddma.dev);
spin_lock_irqsave(&pch->lock, flags);
spin_lock(&pl330->lock);
_stop(pch->thread);
list_splice_tail_init(&pch->work_list, &pl330->desc_pool);
list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
spin_unlock_irqrestore(&pch->lock, flags);
+ pm_runtime_mark_last_busy(pl330->ddma.dev);
+ pm_runtime_put_autosuspend(pl330->ddma.dev);
return 0;
}
return PTR_ERR(info->id_gpiod);
}
+ info->edev = devm_extcon_dev_allocate(dev, usb_extcon_cable);
+ if (IS_ERR(info->edev)) {
+ dev_err(dev, "failed to allocate extcon device\n");
+ return -ENOMEM;
+ }
+
+ ret = devm_extcon_dev_register(dev, info->edev);
+ if (ret < 0) {
+ dev_err(dev, "failed to register extcon device\n");
+ return ret;
+ }
+
ret = gpiod_set_debounce(info->id_gpiod,
USB_GPIO_DEBOUNCE_MS * 1000);
if (ret < 0)
return ret;
}
- info->edev = devm_extcon_dev_allocate(dev, usb_extcon_cable);
- if (IS_ERR(info->edev)) {
- dev_err(dev, "failed to allocate extcon device\n");
- return -ENOMEM;
- }
-
- ret = devm_extcon_dev_register(dev, info->edev);
- if (ret < 0) {
- dev_err(dev, "failed to register extcon device\n");
- return ret;
- }
-
platform_set_drvdata(pdev, info);
device_init_wakeup(dev, 1);
buf += 16;
if (memcmp(buf, "_DMI_", 5) == 0 && dmi_checksum(buf, 15)) {
+ if (smbios_ver)
+ dmi_ver = smbios_ver;
+ else
+ dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F);
dmi_num = get_unaligned_le16(buf + 12);
dmi_len = get_unaligned_le16(buf + 6);
dmi_base = get_unaligned_le32(buf + 8);
if (dmi_walk_early(dmi_decode) == 0) {
if (smbios_ver) {
- dmi_ver = smbios_ver;
- pr_info("SMBIOS %d.%d%s present.\n",
- dmi_ver >> 8, dmi_ver & 0xFF,
- (dmi_ver < 0x0300) ? "" : ".x");
+ pr_info("SMBIOS %d.%d present.\n",
+ dmi_ver >> 8, dmi_ver & 0xFF);
} else {
- dmi_ver = (buf[14] & 0xF0) << 4 |
- (buf[14] & 0x0F);
pr_info("Legacy DMI %d.%d present.\n",
dmi_ver >> 8, dmi_ver & 0xFF);
}
Subsequent efibootmgr releases may be found at:
<http://github.com/vathpela/efibootmgr>
+config EFI_ESRT
+ bool
+ depends on EFI && !IA64
+ default y
+
config EFI_VARS_PSTORE
tristate "Register efivars backend for pstore"
depends on EFI_VARS && PSTORE
#
obj-$(CONFIG_EFI) += efi.o vars.o reboot.o
obj-$(CONFIG_EFI_VARS) += efivars.o
+obj-$(CONFIG_EFI_ESRT) += esrt.o
obj-$(CONFIG_EFI_VARS_PSTORE) += efi-pstore.o
obj-$(CONFIG_UEFI_CPER) += cper.o
obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o
.fw_vendor = EFI_INVALID_TABLE_ADDR,
.runtime = EFI_INVALID_TABLE_ADDR,
.config_table = EFI_INVALID_TABLE_ADDR,
+ .esrt = EFI_INVALID_TABLE_ADDR,
};
EXPORT_SYMBOL(efi);
}
early_param("efi", parse_efi_cmdline);
-static struct kobject *efi_kobj;
+struct kobject *efi_kobj;
static struct kobject *efivars_kobj;
/*
str += sprintf(str, "ACPI20=0x%lx\n", efi.acpi20);
if (efi.acpi != EFI_INVALID_TABLE_ADDR)
str += sprintf(str, "ACPI=0x%lx\n", efi.acpi);
- if (efi.smbios != EFI_INVALID_TABLE_ADDR)
- str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios);
+ /*
+ * If both SMBIOS and SMBIOS3 entry points are implemented, the
+ * SMBIOS3 entry point shall be preferred, so we list it first to
+ * let applications stop parsing after the first match.
+ */
if (efi.smbios3 != EFI_INVALID_TABLE_ADDR)
str += sprintf(str, "SMBIOS3=0x%lx\n", efi.smbios3);
+ if (efi.smbios != EFI_INVALID_TABLE_ADDR)
+ str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios);
if (efi.hcdp != EFI_INVALID_TABLE_ADDR)
str += sprintf(str, "HCDP=0x%lx\n", efi.hcdp);
if (efi.boot_info != EFI_INVALID_TABLE_ADDR)
subsys_initcall(efisubsys_init);
+/*
+ * Find the efi memory descriptor for a given physical address. Given a
+ * physicall address, determine if it exists within an EFI Memory Map entry,
+ * and if so, populate the supplied memory descriptor with the appropriate
+ * data.
+ */
+int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
+{
+ struct efi_memory_map *map = efi.memmap;
+ void *p, *e;
+
+ if (!efi_enabled(EFI_MEMMAP)) {
+ pr_err_once("EFI_MEMMAP is not enabled.\n");
+ return -EINVAL;
+ }
+
+ if (!map) {
+ pr_err_once("efi.memmap is not set.\n");
+ return -EINVAL;
+ }
+ if (!out_md) {
+ pr_err_once("out_md is null.\n");
+ return -EINVAL;
+ }
+ if (WARN_ON_ONCE(!map->phys_map))
+ return -EINVAL;
+ if (WARN_ON_ONCE(map->nr_map == 0) || WARN_ON_ONCE(map->desc_size == 0))
+ return -EINVAL;
+
+ e = map->phys_map + map->nr_map * map->desc_size;
+ for (p = map->phys_map; p < e; p += map->desc_size) {
+ efi_memory_desc_t *md;
+ u64 size;
+ u64 end;
+
+ /*
+ * If a driver calls this after efi_free_boot_services,
+ * ->map will be NULL, and the target may also not be mapped.
+ * So just always get our own virtual map on the CPU.
+ *
+ */
+ md = early_memremap((phys_addr_t)p, sizeof (*md));
+ if (!md) {
+ pr_err_once("early_memremap(%p, %zu) failed.\n",
+ p, sizeof (*md));
+ return -ENOMEM;
+ }
+
+ if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+ md->type != EFI_BOOT_SERVICES_DATA &&
+ md->type != EFI_RUNTIME_SERVICES_DATA) {
+ early_memunmap(md, sizeof (*md));
+ continue;
+ }
+
+ size = md->num_pages << EFI_PAGE_SHIFT;
+ end = md->phys_addr + size;
+ if (phys_addr >= md->phys_addr && phys_addr < end) {
+ memcpy(out_md, md, sizeof(*out_md));
+ early_memunmap(md, sizeof (*md));
+ return 0;
+ }
+
+ early_memunmap(md, sizeof (*md));
+ }
+ pr_err_once("requested map not found.\n");
+ return -ENOENT;
+}
+
+/*
+ * Calculate the highest address of an efi memory descriptor.
+ */
+u64 __init efi_mem_desc_end(efi_memory_desc_t *md)
+{
+ u64 size = md->num_pages << EFI_PAGE_SHIFT;
+ u64 end = md->phys_addr + size;
+ return end;
+}
/*
* We can't ioremap data in EFI boot services RAM, because we've already mapped
{SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
{SMBIOS3_TABLE_GUID, "SMBIOS 3.0", &efi.smbios3},
{UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga},
+ {EFI_SYSTEM_RESOURCE_TABLE_GUID, "ESRT", &efi.esrt},
{NULL_GUID, NULL, NULL},
};
* efivar_create_sysfs_entry - create a new entry in sysfs
* @new_var: efivar entry to create
*
- * Returns 1 on failure, 0 on success
+ * Returns 0 on success, negative error code on failure
*/
static int
efivar_create_sysfs_entry(struct efivar_entry *new_var)
char *short_name;
unsigned long variable_name_size;
efi_char16_t *variable_name;
+ int ret;
variable_name = new_var->var.VariableName;
variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t);
short_name = kzalloc(short_name_size, GFP_KERNEL);
if (!short_name)
- return 1;
+ return -ENOMEM;
/* Convert Unicode to normal chars (assume top bits are 0),
ala UTF-8 */
new_var->kobj.kset = efivars_kset;
- i = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
+ ret = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
NULL, "%s", short_name);
kfree(short_name);
- if (i)
- return 1;
+ if (ret)
+ return ret;
kobject_uevent(&new_var->kobj, KOBJ_ADD);
efivar_entry_add(new_var, &efivar_sysfs_list);
--- /dev/null
+/*
+ * esrt.c
+ *
+ * This module exports EFI System Resource Table (ESRT) entries into userspace
+ * through the sysfs file system. The ESRT provides a read-only catalog of
+ * system components for which the system accepts firmware upgrades via UEFI's
+ * "Capsule Update" feature. This module allows userland utilities to evaluate
+ * what firmware updates can be applied to this system, and potentially arrange
+ * for those updates to occur.
+ *
+ * Data is currently found below /sys/firmware/efi/esrt/...
+ */
+#define pr_fmt(fmt) "esrt: " fmt
+
+#include <linux/capability.h>
+#include <linux/device.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/io.h>
+#include <asm/early_ioremap.h>
+
+struct efi_system_resource_entry_v1 {
+ efi_guid_t fw_class;
+ u32 fw_type;
+ u32 fw_version;
+ u32 lowest_supported_fw_version;
+ u32 capsule_flags;
+ u32 last_attempt_version;
+ u32 last_attempt_status;
+};
+
+/*
+ * _count and _version are what they seem like. _max is actually just
+ * accounting info for the firmware when creating the table; it should never
+ * have been exposed to us. To wit, the spec says:
+ * The maximum number of resource array entries that can be within the
+ * table without reallocating the table, must not be zero.
+ * Since there's no guidance about what that means in terms of memory layout,
+ * it means nothing to us.
+ */
+struct efi_system_resource_table {
+ u32 fw_resource_count;
+ u32 fw_resource_count_max;
+ u64 fw_resource_version;
+ u8 entries[];
+};
+
+static phys_addr_t esrt_data;
+static size_t esrt_data_size;
+
+static struct efi_system_resource_table *esrt;
+
+struct esre_entry {
+ union {
+ struct efi_system_resource_entry_v1 *esre1;
+ } esre;
+
+ struct kobject kobj;
+ struct list_head list;
+};
+
+/* global list of esre_entry. */
+static LIST_HEAD(entry_list);
+
+/* entry attribute */
+struct esre_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct esre_entry *entry, char *buf);
+ ssize_t (*store)(struct esre_entry *entry,
+ const char *buf, size_t count);
+};
+
+static struct esre_entry *to_entry(struct kobject *kobj)
+{
+ return container_of(kobj, struct esre_entry, kobj);
+}
+
+static struct esre_attribute *to_attr(struct attribute *attr)
+{
+ return container_of(attr, struct esre_attribute, attr);
+}
+
+static ssize_t esre_attr_show(struct kobject *kobj,
+ struct attribute *_attr, char *buf)
+{
+ struct esre_entry *entry = to_entry(kobj);
+ struct esre_attribute *attr = to_attr(_attr);
+
+ /* Don't tell normal users what firmware versions we've got... */
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ return attr->show(entry, buf);
+}
+
+static const struct sysfs_ops esre_attr_ops = {
+ .show = esre_attr_show,
+};
+
+/* Generic ESRT Entry ("ESRE") support. */
+static ssize_t esre_fw_class_show(struct esre_entry *entry, char *buf)
+{
+ char *str = buf;
+
+ efi_guid_to_str(&entry->esre.esre1->fw_class, str);
+ str += strlen(str);
+ str += sprintf(str, "\n");
+
+ return str - buf;
+}
+
+static struct esre_attribute esre_fw_class = __ATTR(fw_class, 0400,
+ esre_fw_class_show, NULL);
+
+#define esre_attr_decl(name, size, fmt) \
+static ssize_t esre_##name##_show(struct esre_entry *entry, char *buf) \
+{ \
+ return sprintf(buf, fmt "\n", \
+ le##size##_to_cpu(entry->esre.esre1->name)); \
+} \
+\
+static struct esre_attribute esre_##name = __ATTR(name, 0400, \
+ esre_##name##_show, NULL)
+
+esre_attr_decl(fw_type, 32, "%u");
+esre_attr_decl(fw_version, 32, "%u");
+esre_attr_decl(lowest_supported_fw_version, 32, "%u");
+esre_attr_decl(capsule_flags, 32, "0x%x");
+esre_attr_decl(last_attempt_version, 32, "%u");
+esre_attr_decl(last_attempt_status, 32, "%u");
+
+static struct attribute *esre1_attrs[] = {
+ &esre_fw_class.attr,
+ &esre_fw_type.attr,
+ &esre_fw_version.attr,
+ &esre_lowest_supported_fw_version.attr,
+ &esre_capsule_flags.attr,
+ &esre_last_attempt_version.attr,
+ &esre_last_attempt_status.attr,
+ NULL
+};
+static void esre_release(struct kobject *kobj)
+{
+ struct esre_entry *entry = to_entry(kobj);
+
+ list_del(&entry->list);
+ kfree(entry);
+}
+
+static struct kobj_type esre1_ktype = {
+ .release = esre_release,
+ .sysfs_ops = &esre_attr_ops,
+ .default_attrs = esre1_attrs,
+};
+
+
+static struct kobject *esrt_kobj;
+static struct kset *esrt_kset;
+
+static int esre_create_sysfs_entry(void *esre, int entry_num)
+{
+ struct esre_entry *entry;
+ char name[20];
+
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return -ENOMEM;
+
+ sprintf(name, "entry%d", entry_num);
+
+ entry->kobj.kset = esrt_kset;
+
+ if (esrt->fw_resource_version == 1) {
+ int rc = 0;
+
+ entry->esre.esre1 = esre;
+ rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL,
+ "%s", name);
+ if (rc) {
+ kfree(entry);
+ return rc;
+ }
+ }
+
+ list_add_tail(&entry->list, &entry_list);
+ return 0;
+}
+
+/* support for displaying ESRT fields at the top level */
+#define esrt_attr_decl(name, size, fmt) \
+static ssize_t esrt_##name##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, char *buf)\
+{ \
+ return sprintf(buf, fmt "\n", le##size##_to_cpu(esrt->name)); \
+} \
+\
+static struct kobj_attribute esrt_##name = __ATTR(name, 0400, \
+ esrt_##name##_show, NULL)
+
+esrt_attr_decl(fw_resource_count, 32, "%u");
+esrt_attr_decl(fw_resource_count_max, 32, "%u");
+esrt_attr_decl(fw_resource_version, 64, "%llu");
+
+static struct attribute *esrt_attrs[] = {
+ &esrt_fw_resource_count.attr,
+ &esrt_fw_resource_count_max.attr,
+ &esrt_fw_resource_version.attr,
+ NULL,
+};
+
+static inline int esrt_table_exists(void)
+{
+ if (!efi_enabled(EFI_CONFIG_TABLES))
+ return 0;
+ if (efi.esrt == EFI_INVALID_TABLE_ADDR)
+ return 0;
+ return 1;
+}
+
+static umode_t esrt_attr_is_visible(struct kobject *kobj,
+ struct attribute *attr, int n)
+{
+ if (!esrt_table_exists())
+ return 0;
+ return attr->mode;
+}
+
+static struct attribute_group esrt_attr_group = {
+ .attrs = esrt_attrs,
+ .is_visible = esrt_attr_is_visible,
+};
+
+/*
+ * remap the table, copy it to kmalloced pages, and unmap it.
+ */
+void __init efi_esrt_init(void)
+{
+ void *va;
+ struct efi_system_resource_table tmpesrt;
+ struct efi_system_resource_entry_v1 *v1_entries;
+ size_t size, max, entry_size, entries_size;
+ efi_memory_desc_t md;
+ int rc;
+ phys_addr_t end;
+
+ pr_debug("esrt-init: loading.\n");
+ if (!esrt_table_exists())
+ return;
+
+ rc = efi_mem_desc_lookup(efi.esrt, &md);
+ if (rc < 0) {
+ pr_err("ESRT header is not in the memory map.\n");
+ return;
+ }
+
+ max = efi_mem_desc_end(&md);
+ if (max < efi.esrt) {
+ pr_err("EFI memory descriptor is invalid. (esrt: %p max: %p)\n",
+ (void *)efi.esrt, (void *)max);
+ return;
+ }
+
+ size = sizeof(*esrt);
+ max -= efi.esrt;
+
+ if (max < size) {
+ pr_err("ESRT header doen't fit on single memory map entry. (size: %zu max: %zu)\n",
+ size, max);
+ return;
+ }
+
+ va = early_memremap(efi.esrt, size);
+ if (!va) {
+ pr_err("early_memremap(%p, %zu) failed.\n", (void *)efi.esrt,
+ size);
+ return;
+ }
+
+ memcpy(&tmpesrt, va, sizeof(tmpesrt));
+
+ if (tmpesrt.fw_resource_version == 1) {
+ entry_size = sizeof (*v1_entries);
+ } else {
+ pr_err("Unsupported ESRT version %lld.\n",
+ tmpesrt.fw_resource_version);
+ return;
+ }
+
+ if (tmpesrt.fw_resource_count > 0 && max - size < entry_size) {
+ pr_err("ESRT memory map entry can only hold the header. (max: %zu size: %zu)\n",
+ max - size, entry_size);
+ goto err_memunmap;
+ }
+
+ /*
+ * The format doesn't really give us any boundary to test here,
+ * so I'm making up 128 as the max number of individually updatable
+ * components we support.
+ * 128 should be pretty excessive, but there's still some chance
+ * somebody will do that someday and we'll need to raise this.
+ */
+ if (tmpesrt.fw_resource_count > 128) {
+ pr_err("ESRT says fw_resource_count has very large value %d.\n",
+ tmpesrt.fw_resource_count);
+ goto err_memunmap;
+ }
+
+ /*
+ * We know it can't be larger than N * sizeof() here, and N is limited
+ * by the previous test to a small number, so there's no overflow.
+ */
+ entries_size = tmpesrt.fw_resource_count * entry_size;
+ if (max < size + entries_size) {
+ pr_err("ESRT does not fit on single memory map entry (size: %zu max: %zu)\n",
+ size, max);
+ goto err_memunmap;
+ }
+
+ /* remap it with our (plausible) new pages */
+ early_memunmap(va, size);
+ size += entries_size;
+ va = early_memremap(efi.esrt, size);
+ if (!va) {
+ pr_err("early_memremap(%p, %zu) failed.\n", (void *)efi.esrt,
+ size);
+ return;
+ }
+
+ esrt_data = (phys_addr_t)efi.esrt;
+ esrt_data_size = size;
+
+ end = esrt_data + size;
+ pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
+ memblock_reserve(esrt_data, esrt_data_size);
+
+ pr_debug("esrt-init: loaded.\n");
+err_memunmap:
+ early_memunmap(va, size);
+}
+
+static int __init register_entries(void)
+{
+ struct efi_system_resource_entry_v1 *v1_entries = (void *)esrt->entries;
+ int i, rc;
+
+ if (!esrt_table_exists())
+ return 0;
+
+ for (i = 0; i < le32_to_cpu(esrt->fw_resource_count); i++) {
+ void *esre = NULL;
+ if (esrt->fw_resource_version == 1) {
+ esre = &v1_entries[i];
+ } else {
+ pr_err("Unsupported ESRT version %lld.\n",
+ esrt->fw_resource_version);
+ return -EINVAL;
+ }
+
+ rc = esre_create_sysfs_entry(esre, i);
+ if (rc < 0) {
+ pr_err("ESRT entry creation failed with error %d.\n",
+ rc);
+ return rc;
+ }
+ }
+ return 0;
+}
+
+static void cleanup_entry_list(void)
+{
+ struct esre_entry *entry, *next;
+
+ list_for_each_entry_safe(entry, next, &entry_list, list) {
+ kobject_put(&entry->kobj);
+ }
+}
+
+static int __init esrt_sysfs_init(void)
+{
+ int error;
+ struct efi_system_resource_table __iomem *ioesrt;
+
+ pr_debug("esrt-sysfs: loading.\n");
+ if (!esrt_data || !esrt_data_size)
+ return -ENOSYS;
+
+ ioesrt = ioremap(esrt_data, esrt_data_size);
+ if (!ioesrt) {
+ pr_err("ioremap(%pa, %zu) failed.\n", &esrt_data,
+ esrt_data_size);
+ return -ENOMEM;
+ }
+
+ esrt = kmalloc(esrt_data_size, GFP_KERNEL);
+ if (!esrt) {
+ pr_err("kmalloc failed. (wanted %zu bytes)\n", esrt_data_size);
+ iounmap(ioesrt);
+ return -ENOMEM;
+ }
+
+ memcpy_fromio(esrt, ioesrt, esrt_data_size);
+
+ esrt_kobj = kobject_create_and_add("esrt", efi_kobj);
+ if (!esrt_kobj) {
+ pr_err("Firmware table registration failed.\n");
+ error = -ENOMEM;
+ goto err;
+ }
+
+ error = sysfs_create_group(esrt_kobj, &esrt_attr_group);
+ if (error) {
+ pr_err("Sysfs attribute export failed with error %d.\n",
+ error);
+ goto err_remove_esrt;
+ }
+
+ esrt_kset = kset_create_and_add("entries", NULL, esrt_kobj);
+ if (!esrt_kset) {
+ pr_err("kset creation failed.\n");
+ error = -ENOMEM;
+ goto err_remove_group;
+ }
+
+ error = register_entries();
+ if (error)
+ goto err_cleanup_list;
+
+ memblock_remove(esrt_data, esrt_data_size);
+
+ pr_debug("esrt-sysfs: loaded.\n");
+
+ return 0;
+err_cleanup_list:
+ cleanup_entry_list();
+ kset_unregister(esrt_kset);
+err_remove_group:
+ sysfs_remove_group(esrt_kobj, &esrt_attr_group);
+err_remove_esrt:
+ kobject_put(esrt_kobj);
+err:
+ kfree(esrt);
+ esrt = NULL;
+ return error;
+}
+
+static void __exit esrt_sysfs_exit(void)
+{
+ pr_debug("esrt-sysfs: unloading.\n");
+ cleanup_entry_list();
+ kset_unregister(esrt_kset);
+ sysfs_remove_group(esrt_kobj, &esrt_attr_group);
+ kfree(esrt);
+ esrt = NULL;
+ kobject_del(esrt_kobj);
+ kobject_put(esrt_kobj);
+}
+
+module_init(esrt_sysfs_init);
+module_exit(esrt_sysfs_exit);
+
+MODULE_AUTHOR("Peter Jones <pjones@redhat.com>");
+MODULE_DESCRIPTION("EFI System Resource Table support");
+MODULE_LICENSE("GPL");
static struct iscsi_boot_kset *boot_kset;
+/* fully null address */
static const char nulls[16];
+/* IPv4-mapped IPv6 ::ffff:0.0.0.0 */
+static const char mapped_nulls[16] = { 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0xff, 0xff,
+ 0x00, 0x00, 0x00, 0x00 };
+
+static int address_not_null(u8 *ip)
+{
+ return (memcmp(ip, nulls, 16) && memcmp(ip, mapped_nulls, 16));
+}
+
/*
* Helper functions to parse data properly.
*/
rc = S_IRUGO;
break;
case ISCSI_BOOT_ETH_IP_ADDR:
- if (memcmp(nic->ip_addr, nulls, sizeof(nic->ip_addr)))
+ if (address_not_null(nic->ip_addr))
rc = S_IRUGO;
break;
case ISCSI_BOOT_ETH_SUBNET_MASK:
rc = S_IRUGO;
break;
case ISCSI_BOOT_ETH_GATEWAY:
- if (memcmp(nic->gateway, nulls, sizeof(nic->gateway)))
+ if (address_not_null(nic->gateway))
rc = S_IRUGO;
break;
case ISCSI_BOOT_ETH_PRIMARY_DNS:
- if (memcmp(nic->primary_dns, nulls,
- sizeof(nic->primary_dns)))
+ if (address_not_null(nic->primary_dns))
rc = S_IRUGO;
break;
case ISCSI_BOOT_ETH_SECONDARY_DNS:
- if (memcmp(nic->secondary_dns, nulls,
- sizeof(nic->secondary_dns)))
+ if (address_not_null(nic->secondary_dns))
rc = S_IRUGO;
break;
case ISCSI_BOOT_ETH_DHCP:
- if (memcmp(nic->dhcp, nulls, sizeof(nic->dhcp)))
+ if (address_not_null(nic->dhcp))
rc = S_IRUGO;
break;
case ISCSI_BOOT_ETH_VLAN:
rc = S_IRUGO;
break;
case ISCSI_BOOT_INI_ISNS_SERVER:
- if (memcmp(init->isns_server, nulls,
- sizeof(init->isns_server)))
+ if (address_not_null(init->isns_server))
rc = S_IRUGO;
break;
case ISCSI_BOOT_INI_SLP_SERVER:
- if (memcmp(init->slp_server, nulls,
- sizeof(init->slp_server)))
+ if (address_not_null(init->slp_server))
rc = S_IRUGO;
break;
case ISCSI_BOOT_INI_PRI_RADIUS_SERVER:
- if (memcmp(init->pri_radius_server, nulls,
- sizeof(init->pri_radius_server)))
+ if (address_not_null(init->pri_radius_server))
rc = S_IRUGO;
break;
case ISCSI_BOOT_INI_SEC_RADIUS_SERVER:
- if (memcmp(init->sec_radius_server, nulls,
- sizeof(init->sec_radius_server)))
+ if (address_not_null(init->sec_radius_server))
rc = S_IRUGO;
break;
case ISCSI_BOOT_INI_INITIATOR_NAME:
= container_of(chip, struct kempld_gpio_data, chip);
struct kempld_device_data *pld = gpio->pld;
- return kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
+ return !kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
}
static int kempld_gpio_pincount(struct kempld_device_data *pld)
dev_err(bank->dev, "Could not get gpio dbck\n");
}
-static void
-omap_mpuio_alloc_gc(struct gpio_bank *bank, unsigned int irq_start,
- unsigned int num)
-{
- struct irq_chip_generic *gc;
- struct irq_chip_type *ct;
-
- gc = irq_alloc_generic_chip("MPUIO", 1, irq_start, bank->base,
- handle_simple_irq);
- if (!gc) {
- dev_err(bank->dev, "Memory alloc failed for gc\n");
- return;
- }
-
- ct = gc->chip_types;
-
- /* NOTE: No ack required, reading IRQ status clears it. */
- ct->chip.irq_mask = irq_gc_mask_set_bit;
- ct->chip.irq_unmask = irq_gc_mask_clr_bit;
- ct->chip.irq_set_type = omap_gpio_irq_type;
-
- if (bank->regs->wkup_en)
- ct->chip.irq_set_wake = omap_gpio_wake_enable;
-
- ct->regs.mask = OMAP_MPUIO_GPIO_INT / bank->stride;
- irq_setup_generic_chip(gc, IRQ_MSK(num), IRQ_GC_INIT_MASK_CACHE,
- IRQ_NOREQUEST | IRQ_NOPROBE, 0);
-}
-
static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
{
- int j;
static int gpio;
int irq_base = 0;
int ret;
}
#endif
+ /* MPUIO is a bit different, reading IRQ status clears it */
+ if (bank->is_mpuio) {
+ irqc->irq_ack = dummy_irq_chip.irq_ack;
+ irqc->irq_mask = irq_gc_mask_set_bit;
+ irqc->irq_unmask = irq_gc_mask_clr_bit;
+ if (!bank->regs->wkup_en)
+ irqc->irq_set_wake = NULL;
+ }
+
ret = gpiochip_irqchip_add(&bank->chip, irqc,
irq_base, omap_gpio_irq_handler,
IRQ_TYPE_NONE);
gpiochip_set_chained_irqchip(&bank->chip, irqc,
bank->irq, omap_gpio_irq_handler);
- for (j = 0; j < bank->width; j++) {
- int irq = irq_find_mapping(bank->chip.irqdomain, j);
- if (bank->is_mpuio) {
- omap_mpuio_alloc_gc(bank, irq, bank->width);
- irq_set_chip_and_handler(irq, NULL, NULL);
- set_irq_flags(irq, 0);
- }
- }
-
return 0;
}
length = min(agpio->pin_table_length, (u16)(pin_index + bits));
for (i = pin_index; i < length; ++i) {
- unsigned pin = agpio->pin_table[i];
+ int pin = agpio->pin_table[i];
struct acpi_gpio_connection *conn;
struct gpio_desc *desc;
bool found;
*/
int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
{
+ struct gpio_chip *chip;
unsigned long flags;
int status;
const char *ioname = NULL;
return -EINVAL;
}
+ chip = desc->chip;
+
mutex_lock(&sysfs_lock);
+ /* check if chip is being removed */
+ if (!chip || !chip->exported) {
+ status = -ENODEV;
+ goto fail_unlock;
+ }
+
spin_lock_irqsave(&gpio_lock, flags);
if (!test_bit(FLAG_REQUESTED, &desc->flags) ||
test_bit(FLAG_EXPORT, &desc->flags)) {
{
int status;
struct device *dev;
+ struct gpio_desc *desc;
+ unsigned int i;
mutex_lock(&sysfs_lock);
dev = class_find_device(&gpio_class, NULL, chip, match_export);
if (dev) {
put_device(dev);
device_unregister(dev);
+ /* prevent further gpiod exports */
chip->exported = false;
status = 0;
} else
if (status)
chip_dbg(chip, "%s: status %d\n", __func__, status);
+
+ /* unregister gpiod class devices owned by sysfs */
+ for (i = 0; i < chip->ngpio; i++) {
+ desc = &chip->desc[i];
+ if (test_and_clear_bit(FLAG_SYSFS, &desc->flags))
+ gpiod_free(desc);
+ }
}
static int __init gpiolib_sysfs_init(void)
static LIST_HEAD(gpio_lookup_list);
LIST_HEAD(gpio_chips);
+
+static void gpiochip_free_hogs(struct gpio_chip *chip);
+static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
+
+
static inline void desc_set_label(struct gpio_desc *d, const char *label)
{
d->label = label;
err_remove_chip:
acpi_gpiochip_remove(chip);
+ gpiochip_free_hogs(chip);
of_gpiochip_remove(chip);
spin_lock_irqsave(&gpio_lock, flags);
list_del(&chip->list);
}
EXPORT_SYMBOL_GPL(gpiochip_add);
-/* Forward-declaration */
-static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
-static void gpiochip_free_hogs(struct gpio_chip *chip);
-
/**
* gpiochip_remove() - unregister a gpio_chip
* @chip: the chip to unregister
BUG_ON(!dqm || !qpd);
- BUG_ON(!list_empty(&qpd->queues_list));
+ pr_debug("In func %s\n", __func__);
- pr_debug("kfd: In func %s\n", __func__);
+ pr_debug("qpd->queues_list is %s\n",
+ list_empty(&qpd->queues_list) ? "empty" : "not empty");
retval = 0;
mutex_lock(&dqm->lock);
return -ENOMEM;
}
+ init_sdma_vm(dqm, q, qpd);
+
retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
&q->gart_mqd_addr, &q->properties);
if (retval != 0)
dev->node_props.cpu_core_id_base);
sysfs_show_32bit_prop(buffer, "simd_id_base",
dev->node_props.simd_id_base);
- sysfs_show_32bit_prop(buffer, "capability",
- dev->node_props.capability);
sysfs_show_32bit_prop(buffer, "max_waves_per_simd",
dev->node_props.max_waves_per_simd);
sysfs_show_32bit_prop(buffer, "lds_size_in_kb",
sysfs_show_32bit_prop(buffer, "max_engine_clk_fcompute",
dev->gpu->kfd2kgd->get_max_engine_clock_in_mhz(
dev->gpu->kgd));
+
sysfs_show_64bit_prop(buffer, "local_mem_size",
- dev->gpu->kfd2kgd->get_vmem_size(
- dev->gpu->kgd));
+ (unsigned long long int) 0);
sysfs_show_32bit_prop(buffer, "fw_version",
dev->gpu->kfd2kgd->get_fw_version(
dev->gpu->kgd,
KGD_ENGINE_MEC1));
+ sysfs_show_32bit_prop(buffer, "capability",
+ dev->node_props.capability);
}
return sysfs_show_32bit_prop(buffer, "max_engine_clk_ccompute",
#include <linux/pci.h>
#include <linux/export.h>
-#ifdef CONFIG_X86
-#include <asm/mtrr.h>
-#endif
static int drm_version(struct drm_device *dev, void *data,
struct drm_file *file_priv);
map->type = r_list->map->type;
map->flags = r_list->map->flags;
map->handle = (void *)(unsigned long) r_list->user_token;
-
-#ifdef CONFIG_X86
- /*
- * There appears to be exactly one user of the mtrr index: dritest.
- * It's easy enough to keep it working on non-PAT systems.
- */
- map->mtrr = phys_wc_to_mtrr_index(r_list->map->mtrr);
-#else
- map->mtrr = -1;
-#endif
+ map->mtrr = arch_phys_wc_index(r_list->map->mtrr);
mutex_unlock(&dev->struct_mutex);
/* Reinitialize corresponding vblank timestamp if high-precision query
* available. Skip this step if query unsupported or failed. Will
- * reinitialize delayed at next vblank interrupt in that case.
+ * reinitialize delayed at next vblank interrupt in that case and
+ * assign 0 for now, to mark the vblanktimestamp as invalid.
*/
- if (rc) {
- tslot = atomic_read(&vblank->count) + diff;
- vblanktimestamp(dev, crtc, tslot) = t_vblank;
- }
+ tslot = atomic_read(&vblank->count) + diff;
+ vblanktimestamp(dev, crtc, tslot) = rc ? t_vblank : (struct timeval) {0, 0};
smp_mb__before_atomic();
atomic_add(diff, &vblank->count);
if (!crtc[i])
continue;
+ if (crtc[i]->cursor == plane)
+ continue;
+
/* There's no other way to figure out whether the crtc is running. */
ret = drm_crtc_vblank_get(crtc[i]);
if (ret == 0) {
mutex_unlock(&dev->mode_config.mutex);
- return ret;
+ return ret ? ret : count;
}
static ssize_t status_show(struct device *device,
static void decon_clear_channel(struct decon_context *ctx)
{
- int win, ch_enabled = 0;
+ unsigned int win, ch_enabled = 0;
DRM_DEBUG_KMS("%s\n", __FILE__);
}
}
-static struct exynos_drm_crtc_ops decon_crtc_ops = {
+static const struct exynos_drm_crtc_ops decon_crtc_ops = {
.dpms = decon_dpms,
.mode_fixup = decon_mode_fixup,
.commit = decon_commit,
#include <drm/bridge/ptn3460.h>
#include "exynos_dp_core.h"
-#include "exynos_drm_fimd.h"
#define ctx_from_connector(c) container_of(c, struct exynos_dp_device, \
connector)
}
}
- dev_err(dp->dev, "EDID Read success!\n");
+ dev_dbg(dp->dev, "EDID Read success!\n");
return 0;
}
static void exynos_dp_poweron(struct exynos_dp_device *dp)
{
+ struct exynos_drm_crtc *crtc = dp_to_crtc(dp);
+
if (dp->dpms_mode == DRM_MODE_DPMS_ON)
return;
}
}
- fimd_dp_clock_enable(dp_to_crtc(dp), true);
+ if (crtc->ops->clock_enable)
+ crtc->ops->clock_enable(dp_to_crtc(dp), true);
clk_prepare_enable(dp->clock);
exynos_dp_phy_init(dp);
static void exynos_dp_poweroff(struct exynos_dp_device *dp)
{
+ struct exynos_drm_crtc *crtc = dp_to_crtc(dp);
+
if (dp->dpms_mode != DRM_MODE_DPMS_ON)
return;
exynos_dp_phy_exit(dp);
clk_disable_unprepare(dp->clock);
- fimd_dp_clock_enable(dp_to_crtc(dp), false);
+ if (crtc->ops->clock_enable)
+ crtc->ops->clock_enable(dp_to_crtc(dp), false);
if (dp->panel) {
if (drm_panel_unprepare(dp->panel))
};
struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev,
- struct drm_plane *plane,
- int pipe,
- enum exynos_drm_output_type type,
- struct exynos_drm_crtc_ops *ops,
- void *ctx)
+ struct drm_plane *plane,
+ int pipe,
+ enum exynos_drm_output_type type,
+ const struct exynos_drm_crtc_ops *ops,
+ void *ctx)
{
struct exynos_drm_crtc *exynos_crtc;
struct exynos_drm_private *private = drm_dev->dev_private;
#include "exynos_drm_drv.h"
struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev,
- struct drm_plane *plane,
- int pipe,
- enum exynos_drm_output_type type,
- struct exynos_drm_crtc_ops *ops,
- void *context);
+ struct drm_plane *plane,
+ int pipe,
+ enum exynos_drm_output_type type,
+ const struct exynos_drm_crtc_ops *ops,
+ void *context);
int exynos_drm_crtc_enable_vblank(struct drm_device *dev, int pipe);
void exynos_drm_crtc_disable_vblank(struct drm_device *dev, int pipe);
void exynos_drm_crtc_finish_pageflip(struct drm_device *dev, int pipe);
* @dma_addr: array of bus(accessed by dma) address to the memory region
* allocated for a overlay.
* @zpos: order of overlay layer(z position).
- * @index_color: if using color key feature then this value would be used
- * as index color.
- * @default_win: a window to be enabled.
- * @color_key: color key on or off.
- * @local_path: in case of lcd type, local path mode on or off.
- * @transparency: transparency on or off.
- * @activated: activated or not.
* @enabled: enabled or not.
* @resume: to resume or not.
*
uint32_t pixel_format;
dma_addr_t dma_addr[MAX_FB_BUFFER];
unsigned int zpos;
- unsigned int index_color;
- bool default_win:1;
- bool color_key:1;
- bool local_path:1;
- bool transparency:1;
- bool activated:1;
bool enabled:1;
bool resume:1;
};
* @win_disable: disable hardware specific overlay.
* @te_handler: trigger to transfer video image at the tearing effect
* synchronization signal if there is a page flip request.
+ * @clock_enable: optional function enabling/disabling display domain clock,
+ * called from exynos-dp driver before powering up (with
+ * 'enable' argument as true) and after powering down (with
+ * 'enable' as false).
*/
struct exynos_drm_crtc;
struct exynos_drm_crtc_ops {
void (*win_commit)(struct exynos_drm_crtc *crtc, unsigned int zpos);
void (*win_disable)(struct exynos_drm_crtc *crtc, unsigned int zpos);
void (*te_handler)(struct exynos_drm_crtc *crtc);
+ void (*clock_enable)(struct exynos_drm_crtc *crtc, bool enable);
};
/*
unsigned int dpms;
wait_queue_head_t pending_flip_queue;
struct drm_pending_vblank_event *event;
- struct exynos_drm_crtc_ops *ops;
+ const struct exynos_drm_crtc_ops *ops;
void *ctx;
};
return &exynos_fb->fb;
}
-static u32 exynos_drm_format_num_buffers(struct drm_mode_fb_cmd2 *mode_cmd)
-{
- unsigned int cnt = 0;
-
- if (mode_cmd->pixel_format != DRM_FORMAT_NV12)
- return drm_format_num_planes(mode_cmd->pixel_format);
-
- while (cnt != MAX_FB_BUFFER) {
- if (!mode_cmd->handles[cnt])
- break;
- cnt++;
- }
-
- /*
- * check if NV12 or NV12M.
- *
- * NV12
- * handles[0] = base1, offsets[0] = 0
- * handles[1] = base1, offsets[1] = Y_size
- *
- * NV12M
- * handles[0] = base1, offsets[0] = 0
- * handles[1] = base2, offsets[1] = 0
- */
- if (cnt == 2) {
- /*
- * in case of NV12 format, offsets[1] is not 0 and
- * handles[0] is same as handles[1].
- */
- if (mode_cmd->offsets[1] &&
- mode_cmd->handles[0] == mode_cmd->handles[1])
- cnt = 1;
- }
-
- return cnt;
-}
-
static struct drm_framebuffer *
exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
struct drm_mode_fb_cmd2 *mode_cmd)
drm_helper_mode_fill_fb_struct(&exynos_fb->fb, mode_cmd);
exynos_fb->exynos_gem_obj[0] = to_exynos_gem_obj(obj);
- exynos_fb->buf_cnt = exynos_drm_format_num_buffers(mode_cmd);
+ exynos_fb->buf_cnt = drm_format_num_planes(mode_cmd->pixel_format);
DRM_DEBUG_KMS("buf_cnt = %d\n", exynos_fb->buf_cnt);
#include "exynos_drm_crtc.h"
#include "exynos_drm_plane.h"
#include "exynos_drm_iommu.h"
-#include "exynos_drm_fimd.h"
/*
* FIMD stands for Fully Interactive Mobile Display and
DRM_DEBUG_KMS("vblank wait timed out.\n");
}
-static void fimd_enable_video_output(struct fimd_context *ctx, int win,
+static void fimd_enable_video_output(struct fimd_context *ctx, unsigned int win,
bool enable)
{
u32 val = readl(ctx->regs + WINCON(win));
writel(val, ctx->regs + WINCON(win));
}
-static void fimd_enable_shadow_channel_path(struct fimd_context *ctx, int win,
+static void fimd_enable_shadow_channel_path(struct fimd_context *ctx,
+ unsigned int win,
bool enable)
{
u32 val = readl(ctx->regs + SHADOWCON);
static void fimd_clear_channel(struct fimd_context *ctx)
{
- int win, ch_enabled = 0;
+ unsigned int win, ch_enabled = 0;
DRM_DEBUG_KMS("%s\n", __FILE__);
drm_handle_vblank(ctx->drm_dev, ctx->pipe);
}
-static struct exynos_drm_crtc_ops fimd_crtc_ops = {
+static void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable)
+{
+ struct fimd_context *ctx = crtc->ctx;
+ u32 val;
+
+ /*
+ * Only Exynos 5250, 5260, 5410 and 542x requires enabling DP/MIE
+ * clock. On these SoCs the bootloader may enable it but any
+ * power domain off/on will reset it to disable state.
+ */
+ if (ctx->driver_data != &exynos5_fimd_driver_data)
+ return;
+
+ val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE;
+ writel(DP_MIE_CLK_DP_ENABLE, ctx->regs + DP_MIE_CLKCON);
+}
+
+static const struct exynos_drm_crtc_ops fimd_crtc_ops = {
.dpms = fimd_dpms,
.mode_fixup = fimd_mode_fixup,
.commit = fimd_commit,
.win_commit = fimd_win_commit,
.win_disable = fimd_win_disable,
.te_handler = fimd_te_handler,
+ .clock_enable = fimd_dp_clock_enable,
};
static irqreturn_t fimd_irq_handler(int irq, void *dev_id)
if (ctx->display)
exynos_drm_create_enc_conn(drm_dev, ctx->display);
- ret = fimd_iommu_attach_devices(ctx, drm_dev);
- if (ret)
- return ret;
-
- return 0;
-
+ return fimd_iommu_attach_devices(ctx, drm_dev);
}
static void fimd_unbind(struct device *dev, struct device *master,
return 0;
}
-void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable)
-{
- struct fimd_context *ctx = crtc->ctx;
- u32 val;
-
- /*
- * Only Exynos 5250, 5260, 5410 and 542x requires enabling DP/MIE
- * clock. On these SoCs the bootloader may enable it but any
- * power domain off/on will reset it to disable state.
- */
- if (ctx->driver_data != &exynos5_fimd_driver_data)
- return;
-
- val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE;
- writel(DP_MIE_CLK_DP_ENABLE, ctx->regs + DP_MIE_CLKCON);
-}
-EXPORT_SYMBOL_GPL(fimd_dp_clock_enable);
-
struct platform_driver fimd_driver = {
.probe = fimd_probe,
.remove = fimd_remove,
+++ /dev/null
-/*
- * Copyright (c) 2015 Samsung Electronics Co., Ltd.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- */
-
-#ifndef _EXYNOS_DRM_FIMD_H_
-#define _EXYNOS_DRM_FIMD_H_
-
-extern void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable);
-
-#endif /* _EXYNOS_DRM_FIMD_H_ */
return -EFAULT;
}
- exynos_plane->dma_addr[i] = buffer->dma_addr;
+ exynos_plane->dma_addr[i] = buffer->dma_addr + fb->offsets[i];
DRM_DEBUG_KMS("buffer: %d, dma_addr = 0x%lx\n",
i, (unsigned long)exynos_plane->dma_addr[i]);
return 0;
}
-static struct exynos_drm_crtc_ops vidi_crtc_ops = {
+static const struct exynos_drm_crtc_ops vidi_crtc_ops = {
.dpms = vidi_dpms,
.enable_vblank = vidi_enable_vblank,
.disable_vblank = vidi_disable_vblank,
#define MIXER_WIN_NR 3
#define MIXER_DEFAULT_WIN 0
+/* The pixelformats that are natively supported by the mixer. */
+#define MXR_FORMAT_RGB565 4
+#define MXR_FORMAT_ARGB1555 5
+#define MXR_FORMAT_ARGB4444 6
+#define MXR_FORMAT_ARGB8888 7
+
struct mixer_resources {
int irq;
void __iomem *mixer_regs;
mixer_reg_writemask(res, MXR_CFG, val, MXR_CFG_RGB_FMT_MASK);
}
-static void mixer_cfg_layer(struct mixer_context *ctx, int win, bool enable)
+static void mixer_cfg_layer(struct mixer_context *ctx, unsigned int win,
+ bool enable)
{
struct mixer_resources *res = &ctx->mixer_res;
u32 val = enable ? ~0 : 0;
struct mixer_resources *res = &ctx->mixer_res;
mixer_reg_writemask(res, MXR_STATUS, ~0, MXR_STATUS_REG_RUN);
-
- mixer_regs_dump(ctx);
}
static void mixer_stop(struct mixer_context *ctx)
while (!(mixer_reg_read(res, MXR_STATUS) & MXR_STATUS_REG_IDLE) &&
--timeout)
usleep_range(10000, 12000);
-
- mixer_regs_dump(ctx);
}
-static void vp_video_buffer(struct mixer_context *ctx, int win)
+static void vp_video_buffer(struct mixer_context *ctx, unsigned int win)
{
struct mixer_resources *res = &ctx->mixer_res;
unsigned long flags;
struct exynos_drm_plane *plane;
- unsigned int buf_num = 1;
dma_addr_t luma_addr[2], chroma_addr[2];
bool tiled_mode = false;
bool crcb_mode = false;
switch (plane->pixel_format) {
case DRM_FORMAT_NV12:
crcb_mode = false;
- buf_num = 2;
break;
- /* TODO: single buffer format NV12, NV21 */
+ case DRM_FORMAT_NV21:
+ crcb_mode = true;
+ break;
default:
- /* ignore pixel format at disable time */
- if (!plane->dma_addr[0])
- break;
-
DRM_ERROR("pixel format for vp is wrong [%d].\n",
plane->pixel_format);
return;
}
- if (buf_num == 2) {
- luma_addr[0] = plane->dma_addr[0];
- chroma_addr[0] = plane->dma_addr[1];
- } else {
- luma_addr[0] = plane->dma_addr[0];
- chroma_addr[0] = plane->dma_addr[0]
- + (plane->pitch * plane->fb_height);
- }
+ luma_addr[0] = plane->dma_addr[0];
+ chroma_addr[0] = plane->dma_addr[1];
if (plane->scan_flag & DRM_MODE_FLAG_INTERLACE) {
ctx->interlace = true;
mixer_vsync_set_update(ctx, true);
spin_unlock_irqrestore(&res->reg_slock, flags);
+ mixer_regs_dump(ctx);
vp_regs_dump(ctx);
}
return -ENOTSUPP;
}
-static void mixer_graph_buffer(struct mixer_context *ctx, int win)
+static void mixer_graph_buffer(struct mixer_context *ctx, unsigned int win)
{
struct mixer_resources *res = &ctx->mixer_res;
unsigned long flags;
plane = &ctx->planes[win];
- #define RGB565 4
- #define ARGB1555 5
- #define ARGB4444 6
- #define ARGB8888 7
+ switch (plane->pixel_format) {
+ case DRM_FORMAT_XRGB4444:
+ fmt = MXR_FORMAT_ARGB4444;
+ break;
- switch (plane->bpp) {
- case 16:
- fmt = ARGB4444;
+ case DRM_FORMAT_XRGB1555:
+ fmt = MXR_FORMAT_ARGB1555;
break;
- case 32:
- fmt = ARGB8888;
+
+ case DRM_FORMAT_RGB565:
+ fmt = MXR_FORMAT_RGB565;
+ break;
+
+ case DRM_FORMAT_XRGB8888:
+ case DRM_FORMAT_ARGB8888:
+ fmt = MXR_FORMAT_ARGB8888;
break;
+
default:
- fmt = ARGB8888;
+ DRM_DEBUG_KMS("pixelformat unsupported by mixer\n");
+ return;
}
/* check if mixer supports requested scaling setup */
mixer_vsync_set_update(ctx, true);
spin_unlock_irqrestore(&res->reg_slock, flags);
+
+ mixer_regs_dump(ctx);
}
static void vp_win_reset(struct mixer_context *ctx)
mutex_unlock(&ctx->mixer_mutex);
mixer_stop(ctx);
+ mixer_regs_dump(ctx);
mixer_window_suspend(ctx);
ctx->int_en = mixer_reg_read(res, MXR_INT_EN);
return -EINVAL;
}
-static struct exynos_drm_crtc_ops mixer_crtc_ops = {
+static const struct exynos_drm_crtc_ops mixer_crtc_ops = {
.dpms = mixer_dpms,
.enable_vblank = mixer_enable_vblank,
.disable_vblank = mixer_disable_vblank,
.has_sclk = 1,
};
-static struct platform_device_id mixer_driver_types[] = {
+static const struct platform_device_id mixer_driver_types[] = {
{
.name = "s5p-mixer",
.driver_data = (unsigned long)&exynos4210_mxr_drv_data,
if (HAS_PCH_SPLIT(dev))
sr_enabled = I915_READ(WM1_LP_ILK) & WM1_LP_SR_EN;
- else if (IS_CRESTLINE(dev) || IS_I945G(dev) || IS_I945GM(dev))
+ else if (IS_CRESTLINE(dev) || IS_G4X(dev) ||
+ IS_I945G(dev) || IS_I945GM(dev))
sr_enabled = I915_READ(FW_BLC_SELF) & FW_BLC_SELF_EN;
else if (IS_I915GM(dev))
sr_enabled = I915_READ(INSTPM) & INSTPM_SELF_EN;
else if (IS_PINEVIEW(dev))
sr_enabled = I915_READ(DSPFW3) & PINEVIEW_SELF_REFRESH_EN;
+ else if (IS_VALLEYVIEW(dev))
+ sr_enabled = I915_READ(FW_BLC_SELF_VLV) & FW_CSPWRDWNEN;
intel_runtime_pm_put(dev_priv);
intel_init_pch_refclk(dev);
drm_mode_config_reset(dev);
+ /*
+ * Interrupts have to be enabled before any batches are run. If not the
+ * GPU will hang. i915_gem_init_hw() will initiate batches to
+ * update/restore the context.
+ *
+ * Modeset enabling in intel_modeset_init_hw() also needs working
+ * interrupts.
+ */
+ intel_runtime_pm_enable_interrupts(dev_priv);
+
mutex_lock(&dev->struct_mutex);
if (i915_gem_init_hw(dev)) {
DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n");
}
mutex_unlock(&dev->struct_mutex);
- /* We need working interrupts for modeset enabling ... */
- intel_runtime_pm_enable_interrupts(dev_priv);
-
intel_modeset_init_hw(dev);
spin_lock_irq(&dev_priv->irq_lock);
} else if (vma->ggtt_view.pages) {
sg_free_table(vma->ggtt_view.pages);
kfree(vma->ggtt_view.pages);
- vma->ggtt_view.pages = NULL;
}
+ vma->ggtt_view.pages = NULL;
}
drm_mm_remove_node(&vma->node);
#include "i915_trace.h"
#include "intel_drv.h"
#include <linux/dma_remapping.h>
+#include <linux/uaccess.h>
#define __EXEC_OBJECT_HAS_PIN (1<<31)
#define __EXEC_OBJECT_HAS_FENCE (1<<30)
}
/* We can't wait for rendering with pagefaults disabled */
- if (obj->active && in_atomic())
+ if (obj->active && pagefault_disabled())
return -EFAULT;
if (use_cpu_reloc(obj))
};
static struct intel_quirk intel_quirks[] = {
- /* HP Mini needs pipe A force quirk (LP: #322104) */
- { 0x27ae, 0x103c, 0x361a, quirk_pipea_force },
-
/* Toshiba Protege R-205, S-209 needs pipe A force quirk */
{ 0x2592, 0x1179, 0x0001, quirk_pipea_force },
DP_AUX_CH_CTL_RECEIVE_ERROR))
continue;
if (status & DP_AUX_CH_CTL_DONE)
- break;
+ goto done;
}
- if (status & DP_AUX_CH_CTL_DONE)
- break;
}
if ((status & DP_AUX_CH_CTL_DONE) == 0) {
goto out;
}
+done:
/* Check for timeout or receive error.
* Timeouts occur when the sink is not connected
*/
pipe_config->has_dp_encoder = true;
pipe_config->has_drrs = false;
- pipe_config->has_audio = intel_dp->has_audio;
+ pipe_config->has_audio = intel_dp->has_audio && port != PORT_A;
if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) {
intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
int dotclock;
tmp = I915_READ(intel_dp->output_reg);
- if (tmp & DP_AUDIO_OUTPUT_ENABLE)
- pipe_config->has_audio = true;
+
+ pipe_config->has_audio = tmp & DP_AUDIO_OUTPUT_ENABLE && port != PORT_A;
if ((port == PORT_A) || !HAS_PCH_CPT(dev)) {
if (tmp & DP_SYNC_HS_HIGH)
if (val == 0)
break;
- intel_dp->sink_rates[i] = val * 200;
+ /* Value read is in kHz while drm clock is saved in deca-kHz */
+ intel_dp->sink_rates[i] = (val * 200) / 10;
}
intel_dp->num_sink_rates = i;
}
struct intel_gmbus,
adapter);
struct drm_i915_private *dev_priv = bus->dev_priv;
- int i, reg_offset;
+ int i = 0, inc, try = 0, reg_offset;
int ret = 0;
intel_aux_display_runtime_get(dev_priv);
reg_offset = dev_priv->gpio_mmio_base;
+retry:
I915_WRITE(GMBUS0 + reg_offset, bus->reg0);
- for (i = 0; i < num; i++) {
+ for (; i < num; i += inc) {
+ inc = 1;
if (gmbus_is_index_read(msgs, i, num)) {
ret = gmbus_xfer_index_read(dev_priv, &msgs[i]);
- i += 1; /* set i to the index of the read xfer */
+ inc = 2; /* an index read is two msgs */
} else if (msgs[i].flags & I2C_M_RD) {
ret = gmbus_xfer_read(dev_priv, &msgs[i], 0);
} else {
adapter->name, msgs[i].addr,
(msgs[i].flags & I2C_M_RD) ? 'r' : 'w', msgs[i].len);
+ /*
+ * Passive adapters sometimes NAK the first probe. Retry the first
+ * message once on -ENXIO for GMBUS transfers; the bit banging algorithm
+ * has retries internally. See also the retry loop in
+ * drm_do_probe_ddc_edid, which bails out on the first -ENXIO.
+ */
+ if (ret == -ENXIO && i == 0 && try++ == 0) {
+ DRM_DEBUG_KMS("GMBUS [%s] NAK on first message, retry\n",
+ adapter->name);
+ goto retry;
+ }
+
goto out;
timeout:
I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask));
I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff);
+ if (ring->status_page.obj) {
+ I915_WRITE(RING_HWS_PGA(ring->mmio_base),
+ (u32)ring->status_page.gfx_addr);
+ POSTING_READ(RING_HWS_PGA(ring->mmio_base));
+ }
+
I915_WRITE(RING_MODE_GEN7(ring),
_MASKED_BIT_DISABLE(GFX_REPLAY_MODE) |
_MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
static const struct dmi_system_id intel_dual_link_lvds[] = {
{
.callback = intel_dual_link_lvds_callback,
- .ident = "Apple MacBook Pro (Core i5/i7 Series)",
+ .ident = "Apple MacBook Pro 15\" (2010)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro6,2"),
+ },
+ },
+ {
+ .callback = intel_dual_link_lvds_callback,
+ .ident = "Apple MacBook Pro 15\" (2011)",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro8,2"),
},
},
+ {
+ .callback = intel_dual_link_lvds_callback,
+ .ident = "Apple MacBook Pro 15\" (2012)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro9,1"),
+ },
+ },
{ } /* terminating entry */
};
if (i915.lvds_channel_mode > 0)
return i915.lvds_channel_mode == 2;
+ /* single channel LVDS is limited to 112 MHz */
+ if (lvds_encoder->attached_connector->base.panel.fixed_mode->clock
+ > 112999)
+ return true;
+
if (dmi_check_system(intel_dual_link_lvds))
return true;
out:
mutex_unlock(&dev->mode_config.mutex);
+ intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
+
lvds_encoder->is_dual_link = compute_is_dual_link_lvds(lvds_encoder);
DRM_DEBUG_KMS("detected %s-link lvds configuration\n",
lvds_encoder->is_dual_link ? "dual" : "single");
}
drm_connector_register(connector);
- intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
intel_panel_setup_backlight(connector, INVALID_PIPE);
return;
p->pipe_htotal = intel_crtc->config->base.adjusted_mode.crtc_htotal;
p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
- if (crtc->primary->state->fb) {
- p->pri.enabled = true;
+ if (crtc->primary->state->fb)
p->pri.bytes_per_pixel =
crtc->primary->state->fb->bits_per_pixel / 8;
- } else {
- p->pri.enabled = false;
- p->pri.bytes_per_pixel = 0;
- }
+ else
+ p->pri.bytes_per_pixel = 4;
+
+ p->cur.bytes_per_pixel = 4;
+ /*
+ * TODO: for now, assume primary and cursor planes are always enabled.
+ * Setting them to false makes the screen flicker.
+ */
+ p->pri.enabled = true;
+ p->cur.enabled = true;
- if (crtc->cursor->state->fb) {
- p->cur.enabled = true;
- p->cur.bytes_per_pixel = 4;
- } else {
- p->cur.enabled = false;
- p->cur.bytes_per_pixel = 0;
- }
p->pri.horiz_pixels = intel_crtc->config->pipe_src_w;
p->cur.horiz_pixels = intel_crtc->base.cursor->state->crtc_w;
GEN6_WIZ_HASHING_MASK,
GEN6_WIZ_HASHING_16x4);
- if (INTEL_REVID(dev) == SKL_REVID_C0 ||
- INTEL_REVID(dev) == SKL_REVID_D0)
- /* WaBarrierPerformanceFixDisable:skl */
- WA_SET_BIT_MASKED(HDC_CHICKEN0,
- HDC_FENCE_DEST_SLM_DISABLE |
- HDC_BARRIER_PERFORMANCE_DISABLE);
-
return 0;
}
WA_SET_BIT_MASKED(HIZ_CHICKEN,
BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
+ if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+ INTEL_REVID(dev) == SKL_REVID_D0)
+ /* WaBarrierPerformanceFixDisable:skl */
+ WA_SET_BIT_MASKED(HDC_CHICKEN0,
+ HDC_FENCE_DEST_SLM_DISABLE |
+ HDC_BARRIER_PERFORMANCE_DISABLE);
+
return skl_tune_iz_hashing(ring);
}
DRM_DEBUG_KMS("initialising analog device %d\n", device);
- intel_sdvo_connector = kzalloc(sizeof(*intel_sdvo_connector), GFP_KERNEL);
+ intel_sdvo_connector = intel_sdvo_connector_alloc();
if (!intel_sdvo_connector)
return false;
return MODE_BANDWIDTH;
}
+ if ((mode->hdisplay % 8) != 0 || (mode->hsync_start % 8) != 0 ||
+ (mode->hsync_end % 8) != 0 || (mode->htotal % 8) != 0) {
+ return MODE_H_ILLEGAL;
+ }
+
if (mode->crtc_hdisplay > 2048 || mode->crtc_hsync_start > 4096 ||
mode->crtc_hsync_end > 4096 || mode->crtc_htotal > 4096 ||
mode->crtc_vdisplay > 2048 || mode->crtc_vsync_start > 4096 ||
if (gpu->memptrs_bo) {
if (gpu->memptrs_iova)
msm_gem_put_iova(gpu->memptrs_bo, gpu->base.id);
- drm_gem_object_unreference(gpu->memptrs_bo);
+ drm_gem_object_unreference_unlocked(gpu->memptrs_bo);
}
release_firmware(gpu->pm4);
release_firmware(gpu->pfp);
goto fail;
}
+ for (i = 0; i < MSM_DSI_ENCODER_NUM; i++) {
+ encoders[i]->bridge = msm_dsi->bridge;
+ msm_dsi->encoders[i] = encoders[i];
+ }
+
msm_dsi->connector = msm_dsi_manager_connector_init(msm_dsi->id);
if (IS_ERR(msm_dsi->connector)) {
ret = PTR_ERR(msm_dsi->connector);
goto fail;
}
- for (i = 0; i < MSM_DSI_ENCODER_NUM; i++) {
- encoders[i]->bridge = msm_dsi->bridge;
- msm_dsi->encoders[i] = encoders[i];
- }
-
priv->bridges[priv->num_bridges++] = msm_dsi->bridge;
priv->connectors[priv->num_connectors++] = msm_dsi->connector;
*data = buf[1]; /* strip out dcs type */
return 1;
} else {
- pr_err("%s: read data does not match with rx_buf len %d\n",
+ pr_err("%s: read data does not match with rx_buf len %zu\n",
__func__, msg->rx_len);
return -EINVAL;
}
data[1] = buf[2];
return 2;
} else {
- pr_err("%s: read data does not match with rx_buf len %d\n",
+ pr_err("%s: read data does not match with rx_buf len %zu\n",
__func__, msg->rx_len);
return -EINVAL;
}
{
u32 *lp, *temp, data;
int i, j = 0, cnt;
- bool ack_error = false;
u32 read_cnt;
u8 reg[16];
int repeated_bytes = 0;
if (cnt > 4)
cnt = 4; /* 4 x 32 bits registers only */
- /* Calculate real read data count */
- read_cnt = dsi_read(msm_host, 0x1d4) >> 16;
-
- ack_error = (rx_byte == 4) ?
- (read_cnt == 8) : /* short pkt + 4-byte error pkt */
- (read_cnt == (pkt_size + 6 + 4)); /* long pkt+4-byte error pkt*/
-
- if (ack_error)
- read_cnt -= 4; /* Remove 4 byte error pkt */
+ if (rx_byte == 4)
+ read_cnt = 4;
+ else
+ read_cnt = pkt_size + 6;
/*
* In case of multiple reads from the panel, after the first read, there
container_of(work, struct msm_dsi_host, err_work);
u32 status = msm_host->err_work_state;
- pr_err("%s: status=%x\n", __func__, status);
+ pr_err_ratelimited("%s: status=%x\n", __func__, status);
if (status & DSI_ERR_STATE_MDP_FIFO_UNDERFLOW)
dsi_sw_reset_restore(msm_host);
case MIPI_DSI_RX_ACKNOWLEDGE_AND_ERROR_REPORT:
pr_err("%s: rx ACK_ERR_PACLAGE\n", __func__);
ret = 0;
+ break;
case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_1BYTE:
case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_1BYTE:
ret = dsi_short_read1_resp(buf, msg);
struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
struct drm_connector *connector = NULL;
struct dsi_connector *dsi_connector;
- int ret;
+ int ret, i;
dsi_connector = devm_kzalloc(msm_dsi->dev->dev,
sizeof(*dsi_connector), GFP_KERNEL);
if (ret)
goto fail;
+ for (i = 0; i < MSM_DSI_ENCODER_NUM; i++)
+ drm_mode_connector_attach_encoder(connector,
+ msm_dsi->encoders[i]);
+
return connector;
fail:
/* msg sanity check */
if ((native && (msg->size > AUX_CMD_NATIVE_MAX)) ||
(msg->size > AUX_CMD_I2C_MAX)) {
- pr_err("%s: invalid msg: size(%d), request(%x)\n",
+ pr_err("%s: invalid msg: size(%zu), request(%x)\n",
__func__, msg->size, msg->request);
return -EINVAL;
}
*/
edp_write(aux->base + REG_EDP_AUX_TRANS_CTRL, 0);
msm_edp_aux_ctrl(aux, 1);
- pr_err("%s: aux timeout, %d\n", __func__, ret);
+ pr_err("%s: aux timeout, %zd\n", __func__, ret);
goto unlock_exit;
}
DBG("completion");
if (ret)
goto fail;
+ drm_mode_connector_attach_encoder(connector, edp->encoder);
+
return connector;
fail:
ctrl->aux = msm_edp_aux_init(dev, ctrl->base, &ctrl->drm_aux);
if (!ctrl->aux || !ctrl->drm_aux) {
pr_err("%s:failed to init aux\n", __func__);
- return ret;
+ return -ENOMEM;
}
ctrl->phy = msm_edp_phy_init(dev, ctrl->base);
if (!ctrl->phy) {
pr_err("%s:failed to init phy\n", __func__);
+ ret = -ENOMEM;
goto err_destory_aux;
}
.base = { 0x12d00, 0x12e00, 0x12f00 },
},
.intf = {
- .count = 4,
.base = { 0x12500, 0x12700, 0x12900, 0x12b00 },
- },
- .intfs = {
- [0] = INTF_eDP,
- [1] = INTF_DSI,
- [2] = INTF_DSI,
- [3] = INTF_HDMI,
+ .connect = {
+ [0] = INTF_eDP,
+ [1] = INTF_DSI,
+ [2] = INTF_DSI,
+ [3] = INTF_HDMI,
+ },
},
.max_clk = 200000000,
};
.base = { 0x12f00, 0x13000, 0x13100, 0x13200 },
},
.intf = {
- .count = 5,
.base = { 0x12500, 0x12700, 0x12900, 0x12b00, 0x12d00 },
- },
- .intfs = {
- [0] = INTF_eDP,
- [1] = INTF_DSI,
- [2] = INTF_DSI,
- [3] = INTF_HDMI,
+ .connect = {
+ [0] = INTF_eDP,
+ [1] = INTF_DSI,
+ [2] = INTF_DSI,
+ [3] = INTF_HDMI,
+ },
},
.max_clk = 320000000,
};
},
.intf = {
- .count = 1, /* INTF_1 */
- .base = { 0x6B800 },
+ .base = { 0x00000, 0x6b800 },
+ .connect = {
+ [0] = INTF_DISABLED,
+ [1] = INTF_DSI,
+ },
},
- /* TODO enable .intfs[] with [1] = INTF_DSI, once DSI is implemented */
.max_clk = 320000000,
};
#define MDP5_INTF_NUM_MAX 5
+struct mdp5_intf_block {
+ uint32_t base[MAX_BASES];
+ u32 connect[MDP5_INTF_NUM_MAX]; /* array of enum mdp5_intf_type */
+};
+
struct mdp5_cfg_hw {
char *name;
struct mdp5_sub_block dspp;
struct mdp5_sub_block ad;
struct mdp5_sub_block pp;
- struct mdp5_sub_block intf;
-
- u32 intfs[MDP5_INTF_NUM_MAX]; /* array of enum mdp5_intf_type */
+ struct mdp5_intf_block intf;
uint32_t max_clk;
};
static int get_dsi_id_from_intf(const struct mdp5_cfg_hw *hw_cfg, int intf_num)
{
- const int intf_cnt = hw_cfg->intf.count;
- const u32 *intfs = hw_cfg->intfs;
+ const enum mdp5_intf_type *intfs = hw_cfg->intf.connect;
+ const int intf_cnt = ARRAY_SIZE(hw_cfg->intf.connect);
int id = 0, i;
for (i = 0; i < intf_cnt; i++) {
struct msm_drm_private *priv = dev->dev_private;
const struct mdp5_cfg_hw *hw_cfg =
mdp5_cfg_get_hw_config(mdp5_kms->cfg);
- enum mdp5_intf_type intf_type = hw_cfg->intfs[intf_num];
+ enum mdp5_intf_type intf_type = hw_cfg->intf.connect[intf_num];
struct drm_encoder *encoder;
int ret = 0;
/* Construct encoders and modeset initialize connector devices
* for each external display interface.
*/
- for (i = 0; i < ARRAY_SIZE(hw_cfg->intfs); i++) {
+ for (i = 0; i < ARRAY_SIZE(hw_cfg->intf.connect); i++) {
ret = modeset_init_intf(mdp5_kms, i);
if (ret)
goto fail;
*/
mdp5_enable(mdp5_kms);
for (i = 0; i < MDP5_INTF_NUM_MAX; i++) {
- if (!config->hw->intf.base[i] ||
- mdp5_cfg_intf_is_virtual(config->hw->intfs[i]))
+ if (mdp5_cfg_intf_is_virtual(config->hw->intf.connect[i]) ||
+ !config->hw->intf.base[i])
continue;
mdp5_write(mdp5_kms, REG_MDP5_INTF_TIMING_ENGINE_EN(i), 0);
}
mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC2_ADDR(pipe),
msm_framebuffer_iova(fb, mdp5_kms->id, 2));
mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC3_ADDR(pipe),
- msm_framebuffer_iova(fb, mdp5_kms->id, 4));
+ msm_framebuffer_iova(fb, mdp5_kms->id, 3));
plane->fb = fb;
}
static void msm_fb_output_poll_changed(struct drm_device *dev)
{
+#ifdef CONFIG_DRM_MSM_FBDEV
struct msm_drm_private *priv = dev->dev_private;
if (priv->fbdev)
drm_fb_helper_hotplug_event(priv->fbdev);
+#endif
}
static const struct drm_mode_config_funcs mode_config_funcs = {
}
if (reglog)
- printk(KERN_DEBUG "IO:region %s %08x %08lx\n", dbgname, (u32)ptr, size);
+ printk(KERN_DEBUG "IO:region %s %p %08lx\n", dbgname, ptr, size);
return ptr;
}
void msm_writel(u32 data, void __iomem *addr)
{
if (reglog)
- printk(KERN_DEBUG "IO:W %08x %08x\n", (u32)addr, data);
+ printk(KERN_DEBUG "IO:W %p %08x\n", addr, data);
writel(data, addr);
}
{
u32 val = readl(addr);
if (reglog)
- printk(KERN_ERR "IO:R %08x %08x\n", (u32)addr, val);
+ printk(KERN_ERR "IO:R %p %08x\n", addr, val);
return val;
}
if (gpu) {
mutex_lock(&dev->struct_mutex);
gpu->funcs->pm_suspend(gpu);
- gpu->funcs->destroy(gpu);
mutex_unlock(&dev->struct_mutex);
+ gpu->funcs->destroy(gpu);
}
if (priv->vram.paddr) {
const struct of_device_id *match;
match = of_match_node(match_types, dev->of_node);
if (match)
- return (int)match->data;
+ return (int)(unsigned long)match->data;
#endif
return 4;
}
if (ret)
return ret;
size = r.end - r.start;
- DRM_INFO("using VRAM carveout: %lx@%08x\n", size, r.start);
+ DRM_INFO("using VRAM carveout: %lx@%pa\n", size, &r.start);
} else
#endif
drm_mode_config_init(dev);
- ret = msm_init_vram(dev);
- if (ret)
- goto fail;
-
platform_set_drvdata(pdev, dev);
/* Bind all our sub-components: */
if (ret)
return ret;
+ ret = msm_init_vram(dev);
+ if (ret)
+ goto fail;
+
switch (get_mdp_ver(pdev)) {
case 4:
kms = mdp4_kms_init(dev);
static void msm_lastclose(struct drm_device *dev)
{
+#ifdef CONFIG_DRM_MSM_FBDEV
struct msm_drm_private *priv = dev->dev_private;
if (priv->fbdev)
drm_fb_helper_restore_fbdev_mode_unlocked(priv->fbdev);
+#endif
}
static irqreturn_t msm_irq(int irq, void *arg)
{
struct msm_drm_private *priv = dev->dev_private;
struct msm_kms *kms = priv->kms;
- struct msm_framebuffer *msm_fb;
- struct drm_framebuffer *fb = NULL;
+ struct msm_framebuffer *msm_fb = NULL;
+ struct drm_framebuffer *fb;
const struct msm_format *format;
int ret, i, n;
unsigned int hsub, vsub;
return fb;
fail:
- if (fb)
- msm_framebuffer_destroy(fb);
+ kfree(msm_fb);
return ERR_PTR(ret);
}
uint64_t off = drm_vma_node_start(&obj->vma_node);
WARN_ON(!mutex_is_locked(&dev->struct_mutex));
- seq_printf(m, "%08x: %c(r=%u,w=%u) %2d (%2d) %08llx %p %d\n",
+ seq_printf(m, "%08x: %c(r=%u,w=%u) %2d (%2d) %08llx %p %zu\n",
msm_obj->flags, is_active(msm_obj) ? 'A' : 'I',
msm_obj->read_fence, msm_obj->write_fence,
obj->name, obj->refcount.refcount.counter,
u32 pa = sg_phys(sg) - sg->offset;
size_t bytes = sg->length + sg->offset;
- VERB("map[%d]: %08x %08x(%x)", i, iova, pa, bytes);
+ VERB("map[%d]: %08x %08x(%zx)", i, iova, pa, bytes);
ret = iommu_map(domain, da, pa, bytes, prot);
if (ret)
if (unmapped < bytes)
return unmapped;
- VERB("unmap[%d]: %08x(%x)", i, iova, bytes);
+ VERB("unmap[%d]: %08x(%zx)", i, iova, bytes);
BUG_ON(!PAGE_ALIGNED(bytes));
void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
{
if (ring->bo)
- drm_gem_object_unreference(ring->bo);
+ drm_gem_object_unreference_unlocked(ring->bo);
kfree(ring);
}
#define FERMI_TWOD_A 0x0000902d
-#define FERMI_MEMORY_TO_MEMORY_FORMAT_A 0x0000903d
+#define FERMI_MEMORY_TO_MEMORY_FORMAT_A 0x00009039
#define KEPLER_INLINE_TO_MEMORY_A 0x0000a040
#define KEPLER_INLINE_TO_MEMORY_B 0x0000a140
nv_mask(priv, 0x419cc0, 0x00000008, 0x00000008);
for (gpc = 0; gpc < priv->gpc_nr; gpc++) {
- printk(KERN_ERR "ppc %d %d\n", gpc, priv->ppc_nr[gpc]);
for (ppc = 0; ppc < priv->ppc_nr[gpc]; ppc++)
nv_wr32(priv, PPC_UNIT(gpc, ppc, 0x038), 0xc0000000);
nv_wr32(priv, GPC_UNIT(gpc, 0x0420), 0xc0000000);
return disable;
}
-static int
+int
gf100_devinit_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
struct nvkm_oclass *oclass, void *data, u32 size,
struct nvkm_object **pobject)
{
+ struct nvkm_devinit_impl *impl = (void *)oclass;
struct nv50_devinit_priv *priv;
+ u64 disable;
int ret;
ret = nvkm_devinit_create(parent, engine, oclass, &priv);
if (ret)
return ret;
- if (nv_rd32(priv, 0x022500) & 0x00000001)
+ disable = impl->disable(&priv->base);
+ if (disable & (1ULL << NVDEV_ENGINE_DISP))
priv->base.post = true;
return 0;
gm107_devinit_oclass = &(struct nvkm_devinit_impl) {
.base.handle = NV_SUBDEV(DEVINIT, 0x07),
.base.ofuncs = &(struct nvkm_ofuncs) {
- .ctor = nv50_devinit_ctor,
+ .ctor = gf100_devinit_ctor,
.dtor = _nvkm_devinit_dtor,
.init = nv50_devinit_init,
.fini = _nvkm_devinit_fini,
gm204_devinit_oclass = &(struct nvkm_devinit_impl) {
.base.handle = NV_SUBDEV(DEVINIT, 0x07),
.base.ofuncs = &(struct nvkm_ofuncs) {
- .ctor = nv50_devinit_ctor,
+ .ctor = gf100_devinit_ctor,
.dtor = _nvkm_devinit_dtor,
.init = nv50_devinit_init,
.fini = _nvkm_devinit_fini,
int gt215_devinit_pll_set(struct nvkm_devinit *, u32, u32);
+int gf100_devinit_ctor(struct nvkm_object *, struct nvkm_object *,
+ struct nvkm_oclass *, void *, u32,
+ struct nvkm_object **);
int gf100_devinit_pll_set(struct nvkm_devinit *, u32, u32);
u64 gm107_devinit_disable(struct nvkm_devinit *);
else
radeon_crtc->pll_flags |= RADEON_PLL_PREFER_LOW_REF_DIV;
- /* if there is no audio, set MINM_OVER_MAXP */
- if (!drm_detect_monitor_audio(radeon_connector_edid(connector)))
- radeon_crtc->pll_flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
if (rdev->family < CHIP_RV770)
radeon_crtc->pll_flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
/* use frac fb div on APUs */
{
struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv;
u8 msg[DP_DPCD_SIZE];
- int ret;
+ int ret, i;
- ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg,
- DP_DPCD_SIZE);
- if (ret > 0) {
- memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE);
+ for (i = 0; i < 7; i++) {
+ ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg,
+ DP_DPCD_SIZE);
+ if (ret == DP_DPCD_SIZE) {
+ memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE);
- DRM_DEBUG_KMS("DPCD: %*ph\n", (int)sizeof(dig_connector->dpcd),
- dig_connector->dpcd);
+ DRM_DEBUG_KMS("DPCD: %*ph\n", (int)sizeof(dig_connector->dpcd),
+ dig_connector->dpcd);
- radeon_dp_probe_oui(radeon_connector);
+ radeon_dp_probe_oui(radeon_connector);
- return true;
+ return true;
+ }
}
dig_connector->dpcd[0] = 0;
return false;
/* restore context1-15 */
/* set vm size, must be a multiple of 4 */
WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
- WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
+ WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1);
for (i = 1; i < 16; i++) {
if (i < 8)
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
struct drm_device *dev = encoder->dev;
struct radeon_device *rdev = dev->dev_private;
- WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
+ WREG32(DCE3_HDMI0_ACR_PACKET_CONTROL + offset,
HDMI0_ACR_SOURCE | /* select SW CTS value */
HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
if (enable) {
struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
- if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+ if (connector && drm_detect_monitor_audio(radeon_connector_edid(connector))) {
WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset,
HDMI_AVI_INFO_SEND | /* enable AVI info frames */
HDMI_AVI_INFO_CONT | /* required for audio info values to be updated */
if (!dig || !dig->afmt)
return;
- if (enable && drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+ if (enable && connector &&
+ drm_detect_monitor_audio(radeon_connector_edid(connector))) {
struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
struct radeon_connector *radeon_connector = to_radeon_connector(connector);
struct radeon_connector_atom_dig *dig_connector;
*/
for (i = 1; i < 8; i++) {
WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (i << 2), 0);
- WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), rdev->vm_manager.max_pfn);
+ WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2),
+ rdev->vm_manager.max_pfn - 1);
WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
rdev->vm_manager.saved_table_addr[i]);
}
struct radeon_bo *vcpu_bo;
void *cpu_addr;
uint64_t gpu_addr;
- void *saved_bo;
atomic_t handles[RADEON_MAX_UVD_HANDLES];
struct drm_file *filp[RADEON_MAX_UVD_HANDLES];
unsigned img_size[RADEON_MAX_UVD_HANDLES];
static struct radeon_asic_ring rv770_uvd_ring = {
.ib_execute = &uvd_v1_0_ib_execute,
.emit_fence = &uvd_v2_2_fence_emit,
- .emit_semaphore = &uvd_v1_0_semaphore_emit,
+ .emit_semaphore = &uvd_v2_2_semaphore_emit,
.cs_parse = &radeon_uvd_cs_parse,
.ring_test = &uvd_v1_0_ring_test,
.ib_test = &uvd_v1_0_ib_test,
int uvd_v2_2_resume(struct radeon_device *rdev);
void uvd_v2_2_fence_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
+bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev,
+ struct radeon_ring *ring,
+ struct radeon_semaphore *semaphore,
+ bool emit_wait);
/* uvd v3.1 */
bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
if (!connector || !connector->encoder)
return;
- if (!radeon_encoder_is_digital(connector->encoder))
+ rdev = connector->encoder->dev->dev_private;
+
+ if (!radeon_audio_chipset_supported(rdev))
return;
- rdev = connector->encoder->dev->dev_private;
radeon_encoder = to_radeon_encoder(connector->encoder);
dig = radeon_encoder->enc_priv;
- if (!dig->afmt)
- return;
-
if (status == connector_status_connected) {
- struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+ struct radeon_connector *radeon_connector;
+ int sink_type;
+
+ if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+ radeon_encoder->audio = NULL;
+ return;
+ }
+
+ radeon_connector = to_radeon_connector(connector);
+ sink_type = radeon_dp_getsinktype(radeon_connector);
if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort &&
- radeon_dp_getsinktype(radeon_connector) ==
- CONNECTOR_OBJECT_ID_DISPLAYPORT)
+ sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT)
radeon_encoder->audio = rdev->audio.dp_funcs;
else
radeon_encoder->audio = rdev->audio.hdmi_funcs;
dig->afmt->pin = radeon_audio_get_pin(connector->encoder);
- if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
- radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
- } else {
- radeon_audio_enable(rdev, dig->afmt->pin, 0);
- dig->afmt->pin = NULL;
- }
+ radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
} else {
radeon_audio_enable(rdev, dig->afmt->pin, 0);
dig->afmt->pin = NULL;
/* updated in get modes as well since we need to know if it's analog or digital */
radeon_connector_update_scratch_regs(connector, ret);
- if (radeon_audio != 0) {
- radeon_connector_get_edid(connector);
+ if (radeon_audio != 0)
radeon_audio_detect(connector, ret);
- }
exit:
pm_runtime_mark_last_busy(connector->dev->dev);
radeon_connector_update_scratch_regs(connector, ret);
- if (radeon_audio != 0) {
- radeon_connector_get_edid(connector);
+ if (radeon_audio != 0)
radeon_audio_detect(connector, ret);
- }
out:
pm_runtime_mark_last_busy(connector->dev->dev);
if (r)
DRM_ERROR("ib ring test failed (%d).\n", r);
+ /*
+ * Turks/Thames GPU will freeze whole laptop if DPM is not restarted
+ * after the CP ring have chew one packet at least. Hence here we stop
+ * and restart DPM after the radeon_ib_ring_tests().
+ */
+ if (rdev->pm.dpm_enabled &&
+ (rdev->pm.pm_method == PM_METHOD_DPM) &&
+ (rdev->family == CHIP_TURKS) &&
+ (rdev->flags & RADEON_IS_MOBILITY)) {
+ mutex_lock(&rdev->pm.mutex);
+ radeon_dpm_disable(rdev);
+ radeon_dpm_enable(rdev);
+ mutex_unlock(&rdev->pm.mutex);
+ }
+
if ((radeon_testing & 1)) {
if (rdev->accel_working)
radeon_test_moves(rdev);
AUX_SW_RX_HPD_DISCON | \
AUX_SW_RX_PARTIAL_BYTE | \
AUX_SW_NON_AUX_MODE | \
- AUX_SW_RX_MIN_COUNT_VIOL | \
- AUX_SW_RX_INVALID_STOP | \
AUX_SW_RX_SYNC_INVALID_L | \
AUX_SW_RX_SYNC_INVALID_H | \
AUX_SW_RX_INVALID_START | \
radeon_dp_mst_probe(struct radeon_connector *radeon_connector)
{
struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv;
+ struct drm_device *dev = radeon_connector->base.dev;
+ struct radeon_device *rdev = dev->dev_private;
int ret;
u8 msg[1];
+ if (!radeon_mst)
+ return 0;
+
+ if (!ASIC_IS_DCE5(rdev))
+ return 0;
+
if (dig_connector->dpcd[DP_DPCD_REV] < 0x12)
return 0;
if (radeon_get_allowed_info_register(rdev, *value, value))
return -EINVAL;
break;
+ case RADEON_INFO_VA_UNMAP_WORKING:
+ *value = true;
+ break;
default:
DRM_DEBUG_KMS("Invalid request %d\n", info->request);
return -EINVAL;
list_for_each_entry(bo, &node->bos, mn_list) {
+ if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
+ continue;
+
r = radeon_bo_reserve(bo, true);
if (r) {
DRM_ERROR("(%ld) failed to reserve user bo\n", r);
{
struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
struct radeon_ttm_tt *gtt = (void *)ttm;
- struct scatterlist *sg;
- int i;
+ struct sg_page_iter sg_iter;
int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
enum dma_data_direction direction = write ?
/* free the sg table and pages again */
dma_unmap_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
- for_each_sg(ttm->sg->sgl, sg, ttm->sg->nents, i) {
- struct page *page = sg_page(sg);
-
+ for_each_sg_page(ttm->sg->sgl, &sg_iter, ttm->sg->nents, 0) {
+ struct page *page = sg_page_iter_page(&sg_iter);
if (!(gtt->userflags & RADEON_GEM_USERPTR_READONLY))
set_page_dirty(page);
int radeon_uvd_suspend(struct radeon_device *rdev)
{
- unsigned size;
- void *ptr;
- int i;
+ int i, r;
if (rdev->uvd.vcpu_bo == NULL)
return 0;
- for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i)
- if (atomic_read(&rdev->uvd.handles[i]))
- break;
+ for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+ uint32_t handle = atomic_read(&rdev->uvd.handles[i]);
+ if (handle != 0) {
+ struct radeon_fence *fence;
- if (i == RADEON_MAX_UVD_HANDLES)
- return 0;
+ radeon_uvd_note_usage(rdev);
- size = radeon_bo_size(rdev->uvd.vcpu_bo);
- size -= rdev->uvd_fw->size;
+ r = radeon_uvd_get_destroy_msg(rdev,
+ R600_RING_TYPE_UVD_INDEX, handle, &fence);
+ if (r) {
+ DRM_ERROR("Error destroying UVD (%d)!\n", r);
+ continue;
+ }
- ptr = rdev->uvd.cpu_addr;
- ptr += rdev->uvd_fw->size;
+ radeon_fence_wait(fence, false);
+ radeon_fence_unref(&fence);
- rdev->uvd.saved_bo = kmalloc(size, GFP_KERNEL);
- memcpy(rdev->uvd.saved_bo, ptr, size);
+ rdev->uvd.filp[i] = NULL;
+ atomic_set(&rdev->uvd.handles[i], 0);
+ }
+ }
return 0;
}
ptr = rdev->uvd.cpu_addr;
ptr += rdev->uvd_fw->size;
- if (rdev->uvd.saved_bo != NULL) {
- memcpy(ptr, rdev->uvd.saved_bo, size);
- kfree(rdev->uvd.saved_bo);
- rdev->uvd.saved_bo = NULL;
- } else
- memset(ptr, 0, size);
+ memset(ptr, 0, size);
return 0;
}
return 0;
}
+static int radeon_uvd_validate_codec(struct radeon_cs_parser *p,
+ unsigned stream_type)
+{
+ switch (stream_type) {
+ case 0: /* H264 */
+ case 1: /* VC1 */
+ /* always supported */
+ return 0;
+
+ case 3: /* MPEG2 */
+ case 4: /* MPEG4 */
+ /* only since UVD 3 */
+ if (p->rdev->family >= CHIP_PALM)
+ return 0;
+
+ /* fall through */
+ default:
+ DRM_ERROR("UVD codec not supported by hardware %d!\n",
+ stream_type);
+ return -EINVAL;
+ }
+}
+
static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
unsigned offset, unsigned buf_sizes[])
{
return -EINVAL;
}
- if (msg_type == 1) {
- /* it's a decode msg, calc buffer sizes */
- r = radeon_uvd_cs_msg_decode(msg, buf_sizes);
- /* calc image size (width * height) */
- img_size = msg[6] * msg[7];
+ switch (msg_type) {
+ case 0:
+ /* it's a create msg, calc image size (width * height) */
+ img_size = msg[7] * msg[8];
+
+ r = radeon_uvd_validate_codec(p, msg[4]);
radeon_bo_kunmap(bo);
if (r)
return r;
- } else if (msg_type == 2) {
+ /* try to alloc a new handle */
+ for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+ if (atomic_read(&p->rdev->uvd.handles[i]) == handle) {
+ DRM_ERROR("Handle 0x%x already in use!\n", handle);
+ return -EINVAL;
+ }
+
+ if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) {
+ p->rdev->uvd.filp[i] = p->filp;
+ p->rdev->uvd.img_size[i] = img_size;
+ return 0;
+ }
+ }
+
+ DRM_ERROR("No more free UVD handles!\n");
+ return -EINVAL;
+
+ case 1:
+ /* it's a decode msg, validate codec and calc buffer sizes */
+ r = radeon_uvd_validate_codec(p, msg[4]);
+ if (!r)
+ r = radeon_uvd_cs_msg_decode(msg, buf_sizes);
+ radeon_bo_kunmap(bo);
+ if (r)
+ return r;
+
+ /* validate the handle */
+ for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+ if (atomic_read(&p->rdev->uvd.handles[i]) == handle) {
+ if (p->rdev->uvd.filp[i] != p->filp) {
+ DRM_ERROR("UVD handle collision detected!\n");
+ return -EINVAL;
+ }
+ return 0;
+ }
+ }
+
+ DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
+ return -ENOENT;
+
+ case 2:
/* it's a destroy msg, free the handle */
for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i)
atomic_cmpxchg(&p->rdev->uvd.handles[i], handle, 0);
radeon_bo_kunmap(bo);
return 0;
- } else {
- /* it's a create msg, calc image size (width * height) */
- img_size = msg[7] * msg[8];
- radeon_bo_kunmap(bo);
- if (msg_type != 0) {
- DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
- return -EINVAL;
- }
-
- /* it's a create msg, no special handling needed */
- }
-
- /* create or decode, validate the handle */
- for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
- if (atomic_read(&p->rdev->uvd.handles[i]) == handle)
- return 0;
- }
+ default:
- /* handle not found try to alloc a new one */
- for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
- if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) {
- p->rdev->uvd.filp[i] = p->filp;
- p->rdev->uvd.img_size[i] = img_size;
- return 0;
- }
+ DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+ return -EINVAL;
}
- DRM_ERROR("No more free UVD handles!\n");
+ BUG();
return -EINVAL;
}
*
* @p: parser context
* @handle: handle to validate
+ * @allocated: allocated a new handle?
*
* Validates the handle and return the found session index or -EINVAL
* we we don't have another free session index.
*/
-int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle)
+static int radeon_vce_validate_handle(struct radeon_cs_parser *p,
+ uint32_t handle, bool *allocated)
{
unsigned i;
+ *allocated = false;
+
/* validate the handle */
for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
- if (atomic_read(&p->rdev->vce.handles[i]) == handle)
+ if (atomic_read(&p->rdev->vce.handles[i]) == handle) {
+ if (p->rdev->vce.filp[i] != p->filp) {
+ DRM_ERROR("VCE handle collision detected!\n");
+ return -EINVAL;
+ }
return i;
+ }
}
/* handle not found try to alloc a new one */
if (!atomic_cmpxchg(&p->rdev->vce.handles[i], 0, handle)) {
p->rdev->vce.filp[i] = p->filp;
p->rdev->vce.img_size[i] = 0;
+ *allocated = true;
return i;
}
}
int radeon_vce_cs_parse(struct radeon_cs_parser *p)
{
int session_idx = -1;
- bool destroyed = false;
+ bool destroyed = false, created = false, allocated = false;
uint32_t tmp, handle = 0;
uint32_t *size = &tmp;
- int i, r;
+ int i, r = 0;
while (p->idx < p->chunk_ib->length_dw) {
uint32_t len = radeon_get_ib_value(p, p->idx);
if ((len < 8) || (len & 3)) {
DRM_ERROR("invalid VCE command length (%d)!\n", len);
- return -EINVAL;
+ r = -EINVAL;
+ goto out;
}
if (destroyed) {
DRM_ERROR("No other command allowed after destroy!\n");
- return -EINVAL;
+ r = -EINVAL;
+ goto out;
}
switch (cmd) {
case 0x00000001: // session
handle = radeon_get_ib_value(p, p->idx + 2);
- session_idx = radeon_vce_validate_handle(p, handle);
+ session_idx = radeon_vce_validate_handle(p, handle,
+ &allocated);
if (session_idx < 0)
return session_idx;
size = &p->rdev->vce.img_size[session_idx];
break;
case 0x01000001: // create
+ created = true;
+ if (!allocated) {
+ DRM_ERROR("Handle already in use!\n");
+ r = -EINVAL;
+ goto out;
+ }
+
*size = radeon_get_ib_value(p, p->idx + 8) *
radeon_get_ib_value(p, p->idx + 10) *
8 * 3 / 2;
r = radeon_vce_cs_reloc(p, p->idx + 10, p->idx + 9,
*size);
if (r)
- return r;
+ goto out;
r = radeon_vce_cs_reloc(p, p->idx + 12, p->idx + 11,
*size / 3);
if (r)
- return r;
+ goto out;
break;
case 0x02000001: // destroy
r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
*size * 2);
if (r)
- return r;
+ goto out;
break;
case 0x05000004: // video bitstream buffer
r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
tmp);
if (r)
- return r;
+ goto out;
break;
case 0x05000005: // feedback buffer
r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
4096);
if (r)
- return r;
+ goto out;
break;
default:
DRM_ERROR("invalid VCE command (0x%x)!\n", cmd);
- return -EINVAL;
+ r = -EINVAL;
+ goto out;
}
if (session_idx == -1) {
DRM_ERROR("no session command at start of IB\n");
- return -EINVAL;
+ r = -EINVAL;
+ goto out;
}
p->idx += len / 4;
}
- if (destroyed) {
- /* IB contains a destroy msg, free the handle */
+ if (allocated && !created) {
+ DRM_ERROR("New session without create command!\n");
+ r = -ENOENT;
+ }
+
+out:
+ if ((!r && destroyed) || (r && allocated)) {
+ /*
+ * IB contains a destroy msg or we have allocated an
+ * handle and got an error, anyway free the handle
+ */
for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i)
atomic_cmpxchg(&p->rdev->vce.handles[i], handle, 0);
}
- return 0;
+ return r;
}
/**
/* make sure object fit at this offset */
eoffset = soffset + size;
if (soffset >= eoffset) {
- return -EINVAL;
+ r = -EINVAL;
+ goto error_unreserve;
}
last_pfn = eoffset / RADEON_GPU_PAGE_SIZE;
if (last_pfn > rdev->vm_manager.max_pfn) {
dev_err(rdev->dev, "va above limit (0x%08X > 0x%08X)\n",
last_pfn, rdev->vm_manager.max_pfn);
- return -EINVAL;
+ r = -EINVAL;
+ goto error_unreserve;
}
} else {
"(bo %p 0x%010lx 0x%010lx)\n", bo_va->bo,
soffset, tmp->bo, tmp->it.start, tmp->it.last);
mutex_unlock(&vm->mutex);
- return -EINVAL;
+ r = -EINVAL;
+ goto error_unreserve;
}
}
tmp = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
if (!tmp) {
mutex_unlock(&vm->mutex);
- return -ENOMEM;
+ r = -ENOMEM;
+ goto error_unreserve;
}
tmp->it.start = bo_va->it.start;
tmp->it.last = bo_va->it.last;
r = radeon_vm_clear_bo(rdev, pt);
if (r) {
radeon_bo_unref(&pt);
- radeon_bo_reserve(bo_va->bo, false);
return r;
}
mutex_unlock(&vm->mutex);
return 0;
+
+error_unreserve:
+ radeon_bo_unreserve(bo_va->bo);
+ return r;
}
/**
((n) & 0x3FFF) << 16)
/* UVD */
+#define UVD_SEMA_ADDR_LOW 0xef00
+#define UVD_SEMA_ADDR_HIGH 0xef04
+#define UVD_SEMA_CMD 0xef08
#define UVD_GPCOM_VCPU_CMD 0xef0c
#define UVD_GPCOM_VCPU_DATA0 0xef10
#define UVD_GPCOM_VCPU_DATA1 0xef14
/* empty context1-15 */
/* set vm size, must be a multiple of 4 */
WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
- WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
+ WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1);
/* Assign the pt base to something valid for now; the pts used for
* the VMs are determined by the application and setup and assigned
* on the fly in the vm part of radeon_gart.c
struct radeon_semaphore *semaphore,
bool emit_wait)
{
- uint64_t addr = semaphore->gpu_addr;
-
- radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
- radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
-
- radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
- radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
-
- radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
- radeon_ring_write(ring, emit_wait ? 1 : 0);
-
- return true;
+ /* disable semaphores for UVD V1 hardware */
+ return false;
}
/**
radeon_ring_write(ring, 2);
}
+/**
+ * uvd_v2_2_semaphore_emit - emit semaphore command
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ * @semaphore: semaphore to emit commands for
+ * @emit_wait: true if we should emit a wait command
+ *
+ * Emit a semaphore command (either wait or signal) to the UVD ring.
+ */
+bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev,
+ struct radeon_ring *ring,
+ struct radeon_semaphore *semaphore,
+ bool emit_wait)
+{
+ uint64_t addr = semaphore->gpu_addr;
+
+ radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
+ radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
+
+ radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
+ radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
+
+ radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
+ radeon_ring_write(ring, emit_wait ? 1 : 0);
+
+ return true;
+}
+
/**
* uvd_v2_2_resume - memory controller programming
*
drm->irq_enabled = true;
/* syncpoints are used for full 32-bit hardware VBLANK counters */
- drm->vblank_disable_immediate = true;
drm->max_vblank_count = 0xffffffff;
err = drm_vblank_init(drm, drm->mode_config.num_crtc);
ccflags-y := -Iinclude/drm
-vgem-y := vgem_drv.o vgem_dma_buf.o
+vgem-y := vgem_drv.o
obj-$(CONFIG_DRM_VGEM) += vgem.o
+++ /dev/null
-/*
- * Copyright © 2012 Intel Corporation
- * Copyright © 2014 The Chromium OS Authors
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- * Authors:
- * Ben Widawsky <ben@bwidawsk.net>
- *
- */
-
-#include <linux/dma-buf.h>
-#include "vgem_drv.h"
-
-struct sg_table *vgem_gem_prime_get_sg_table(struct drm_gem_object *gobj)
-{
- struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
- BUG_ON(obj->pages == NULL);
-
- return drm_prime_pages_to_sg(obj->pages, obj->base.size / PAGE_SIZE);
-}
-
-int vgem_gem_prime_pin(struct drm_gem_object *gobj)
-{
- struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
- return vgem_gem_get_pages(obj);
-}
-
-void vgem_gem_prime_unpin(struct drm_gem_object *gobj)
-{
- struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
- vgem_gem_put_pages(obj);
-}
-
-void *vgem_gem_prime_vmap(struct drm_gem_object *gobj)
-{
- struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
- BUG_ON(obj->pages == NULL);
-
- return vmap(obj->pages, obj->base.size / PAGE_SIZE, 0, PAGE_KERNEL);
-}
-
-void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
-{
- vunmap(vaddr);
-}
-
-struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev,
- struct dma_buf *dma_buf)
-{
- struct drm_vgem_gem_object *obj = NULL;
- int ret;
-
- obj = kzalloc(sizeof(*obj), GFP_KERNEL);
- if (obj == NULL) {
- ret = -ENOMEM;
- goto fail;
- }
-
- ret = drm_gem_object_init(dev, &obj->base, dma_buf->size);
- if (ret) {
- ret = -ENOMEM;
- goto fail_free;
- }
-
- get_dma_buf(dma_buf);
-
- obj->base.dma_buf = dma_buf;
- obj->use_dma_buf = true;
-
- return &obj->base;
-
-fail_free:
- kfree(obj);
-fail:
- return ERR_PTR(ret);
-}
};
static struct drm_driver vgem_driver = {
- .driver_features = DRIVER_GEM | DRIVER_PRIME,
+ .driver_features = DRIVER_GEM,
.gem_free_object = vgem_gem_free_object,
.gem_vm_ops = &vgem_gem_vm_ops,
.ioctls = vgem_ioctls,
.fops = &vgem_driver_fops,
.dumb_create = vgem_gem_dumb_create,
.dumb_map_offset = vgem_gem_dumb_map,
- .prime_handle_to_fd = drm_gem_prime_handle_to_fd,
- .prime_fd_to_handle = drm_gem_prime_fd_to_handle,
- .gem_prime_export = drm_gem_prime_export,
- .gem_prime_import = vgem_gem_prime_import,
- .gem_prime_pin = vgem_gem_prime_pin,
- .gem_prime_unpin = vgem_gem_prime_unpin,
- .gem_prime_get_sg_table = vgem_gem_prime_get_sg_table,
- .gem_prime_vmap = vgem_gem_prime_vmap,
- .gem_prime_vunmap = vgem_gem_prime_vunmap,
.name = DRIVER_NAME,
.desc = DRIVER_DESC,
.date = DRIVER_DATE,
extern void vgem_gem_put_pages(struct drm_vgem_gem_object *obj);
extern int vgem_gem_get_pages(struct drm_vgem_gem_object *obj);
-/* vgem_dma_buf.c */
-extern struct sg_table *vgem_gem_prime_get_sg_table(
- struct drm_gem_object *gobj);
-extern int vgem_gem_prime_pin(struct drm_gem_object *gobj);
-extern void vgem_gem_prime_unpin(struct drm_gem_object *gobj);
-extern void *vgem_gem_prime_vmap(struct drm_gem_object *gobj);
-extern void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
-extern struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev,
- struct dma_buf *dma_buf);
-
-
#endif
#define USB_DEVICE_ID_ATEN_2PORTKVM 0x2204
#define USB_DEVICE_ID_ATEN_4PORTKVM 0x2205
#define USB_DEVICE_ID_ATEN_4PORTKVMC 0x2208
+#define USB_DEVICE_ID_ATEN_CS682 0x2213
#define USB_VENDOR_ID_ATMEL 0x03eb
#define USB_DEVICE_ID_ATMEL_MULTITOUCH 0x211c
/* bits 1..20 are reserved for classes */
#define HIDPP_QUIRK_DELAYED_INIT BIT(21)
#define HIDPP_QUIRK_WTP_PHYSICAL_BUTTONS BIT(22)
-#define HIDPP_QUIRK_MULTI_INPUT BIT(23)
/*
* There are two hidpp protocols in use, the first version hidpp10 is known
struct hid_field *field, struct hid_usage *usage,
unsigned long **bit, int *max)
{
- struct hidpp_device *hidpp = hid_get_drvdata(hdev);
-
- if ((hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT) &&
- (field->application == HID_GD_KEYBOARD))
- return 0;
-
return -1;
}
{
struct wtp_data *wd = hidpp->private_data;
- if ((hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT) && origin_is_hid_core)
- /* this is the generic hid-input call */
- return;
-
__set_bit(EV_ABS, input_dev->evbit);
__set_bit(EV_KEY, input_dev->evbit);
__clear_bit(EV_REL, input_dev->evbit);
if (hidpp->quirks & HIDPP_QUIRK_DELAYED_INIT)
connect_mask &= ~HID_CONNECT_HIDINPUT;
- /* Re-enable hidinput for multi-input devices */
- if (hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT)
- connect_mask |= HID_CONNECT_HIDINPUT;
-
ret = hid_hw_start(hdev, connect_mask);
if (ret) {
hid_err(hdev, "%s:hid_hw_start returned error\n", __func__);
HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
USB_DEVICE_ID_LOGITECH_T651),
.driver_data = HIDPP_QUIRK_CLASS_WTP },
- { /* Keyboard TK820 */
- HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
- USB_VENDOR_ID_LOGITECH, 0x4102),
- .driver_data = HIDPP_QUIRK_DELAYED_INIT | HIDPP_QUIRK_MULTI_INPUT |
- HIDPP_QUIRK_CLASS_WTP },
{ HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
USB_VENDOR_ID_LOGITECH, HID_ANY_ID)},
if (!report)
return -EINVAL;
- mutex_lock(&hsdev->mutex);
+ mutex_lock(hsdev->mutex_ptr);
if (flag == SENSOR_HUB_SYNC) {
memset(&hsdev->pending, 0, sizeof(hsdev->pending));
init_completion(&hsdev->pending.ready);
kfree(hsdev->pending.raw_data);
hsdev->pending.status = false;
}
- mutex_unlock(&hsdev->mutex);
+ mutex_unlock(hsdev->mutex_ptr);
return ret_val;
}
hsdev->vendor_id = hdev->vendor;
hsdev->product_id = hdev->product;
hsdev->usage = collection->usage;
- mutex_init(&hsdev->mutex);
+ hsdev->mutex_ptr = devm_kzalloc(&hdev->dev,
+ sizeof(struct mutex),
+ GFP_KERNEL);
+ if (!hsdev->mutex_ptr) {
+ ret = -ENOMEM;
+ goto err_stop_hw;
+ }
+ mutex_init(hsdev->mutex_ptr);
hsdev->start_collection_index = i;
if (last_hsdev)
last_hsdev->end_collection_index = i;
union acpi_object *obj;
struct acpi_device *adev;
acpi_handle handle;
+ int ret;
handle = ACPI_HANDLE(&client->dev);
if (!handle || acpi_bus_get_device(handle, &adev))
pdata->hid_descriptor_address = obj->integer.value;
ACPI_FREE(obj);
- return acpi_dev_add_driver_gpios(adev, i2c_hid_acpi_gpios);
+ /* GPIOs are optional */
+ ret = acpi_dev_add_driver_gpios(adev, i2c_hid_acpi_gpios);
+ return ret < 0 && ret != -ENXIO ? ret : 0;
}
static const struct acpi_device_id i2c_hid_acpi_match[] = {
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC, HID_QUIRK_NOGET },
+ { USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS682, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FIGHTERSTICK, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_COMBATSTICK, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_ECLIPSE_YOKE, HID_QUIRK_NOGET },
int count = 0;
int i;
+ if (!touch_max)
+ return 0;
+
/* non-HID_GENERIC single touch input doesn't call this routine */
if ((touch_max == 1) && (wacom->features.type == HID_GENERIC))
return wacom->hid_data.tipswitch &&
#define TO_ATTR_NO(cpu) (TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
#ifdef CONFIG_SMP
-#define for_each_sibling(i, cpu) for_each_cpu(i, cpu_sibling_mask(cpu))
+#define for_each_sibling(i, cpu) \
+ for_each_cpu(i, topology_sibling_cpumask(cpu))
#else
#define for_each_sibling(i, cpu) for (i = 0; false; )
#endif
(*t)->dev_attr.attr.name, tg->base + i);
if ((*t)->s2) {
a2 = &su->u.a2;
+ sysfs_attr_init(&a2->dev_attr.attr);
a2->dev_attr.attr.name = su->name;
a2->nr = (*t)->u.s.nr + i;
a2->index = (*t)->u.s.index;
*attrs = &a2->dev_attr.attr;
} else {
a = &su->u.a1;
+ sysfs_attr_init(&a->dev_attr.attr);
a->dev_attr.attr.name = su->name;
a->index = (*t)->u.index + i;
a->dev_attr.attr.mode =
(*t)->dev_attr.attr.name, tg->base + i);
if ((*t)->s2) {
a2 = &su->u.a2;
+ sysfs_attr_init(&a2->dev_attr.attr);
a2->dev_attr.attr.name = su->name;
a2->nr = (*t)->u.s.nr + i;
a2->index = (*t)->u.s.index;
*attrs = &a2->dev_attr.attr;
} else {
a = &su->u.a1;
+ sysfs_attr_init(&a->dev_attr.attr);
a->dev_attr.attr.name = su->name;
a->index = (*t)->u.index + i;
a->dev_attr.attr.mode =
ntc_thermistor_parse_dt(struct platform_device *pdev)
{
struct iio_channel *chan;
+ enum iio_chan_type type;
struct device_node *np = pdev->dev.of_node;
struct ntc_thermistor_platform_data *pdata;
+ int ret;
if (!np)
return NULL;
if (IS_ERR(chan))
return ERR_CAST(chan);
+ ret = iio_get_channel_type(chan, &type);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
+ if (type != IIO_VOLTAGE)
+ return ERR_PTR(-EINVAL);
+
if (of_property_read_u32(np, "pullup-uv", &pdata->pullup_uv))
return ERR_PTR(-ENODEV);
if (of_property_read_u32(np, "pullup-ohm", &pdata->pullup_ohm))
#include <linux/sysfs.h>
/* Addresses to scan */
-static const unsigned short normal_i2c[] = { 0x37, 0x48, 0x49, 0x4a, 0x4c, 0x4d,
+static const unsigned short normal_i2c[] = { 0x48, 0x49, 0x4a, 0x4c, 0x4d,
0x4e, 0x4f, I2C_CLIENT_END };
enum chips { tmp401, tmp411, tmp431, tmp432, tmp435 };
MODULE_DESCRIPTION("Hix5hd2 I2C Bus driver");
MODULE_AUTHOR("Wei Yan <sledge.yanwei@huawei.com>");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:i2c-hix5hd2");
+MODULE_ALIAS("platform:hix5hd2-i2c");
return -ENOMEM;
i2c->quirks = s3c24xx_get_device_quirks(pdev);
+ i2c->sysreg = ERR_PTR(-ENOENT);
if (pdata)
memcpy(i2c->pdata, pdata, sizeof(*pdata));
else
help
This driver adds support for Toshiba TC86C001 GOKU-S chip.
-config BLK_DEV_CELLEB
- tristate "Toshiba's Cell Reference Set IDE support"
- depends on PPC_CELLEB
- select BLK_DEV_IDEDMA_PCI
- help
- This driver provides support for the on-board IDE controller on
- Toshiba Cell Reference Board.
- If unsure, say Y.
-
endif
# TODO: BLK_DEV_IDEDMA_PCI -> BLK_DEV_IDEDMA_SFF
obj-$(CONFIG_BLK_DEV_ALI15X3) += alim15x3.o
obj-$(CONFIG_BLK_DEV_AMD74XX) += amd74xx.o
obj-$(CONFIG_BLK_DEV_ATIIXP) += atiixp.o
-obj-$(CONFIG_BLK_DEV_CELLEB) += scc_pata.o
obj-$(CONFIG_BLK_DEV_CMD64X) += cmd64x.o
obj-$(CONFIG_BLK_DEV_CS5520) += cs5520.o
obj-$(CONFIG_BLK_DEV_CS5530) += cs5530.o
+++ /dev/null
-/*
- * Support for IDE interfaces on Celleb platform
- *
- * (C) Copyright 2006 TOSHIBA CORPORATION
- *
- * This code is based on drivers/ide/pci/siimage.c:
- * Copyright (C) 2001-2002 Andre Hedrick <andre@linux-ide.org>
- * Copyright (C) 2003 Red Hat
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/ide.h>
-#include <linux/init.h>
-
-#define PCI_DEVICE_ID_TOSHIBA_SCC_ATA 0x01b4
-
-#define SCC_PATA_NAME "scc IDE"
-
-#define TDVHSEL_MASTER 0x00000001
-#define TDVHSEL_SLAVE 0x00000004
-
-#define MODE_JCUSFEN 0x00000080
-
-#define CCKCTRL_ATARESET 0x00040000
-#define CCKCTRL_BUFCNT 0x00020000
-#define CCKCTRL_CRST 0x00010000
-#define CCKCTRL_OCLKEN 0x00000100
-#define CCKCTRL_ATACLKOEN 0x00000002
-#define CCKCTRL_LCLKEN 0x00000001
-
-#define QCHCD_IOS_SS 0x00000001
-
-#define QCHSD_STPDIAG 0x00020000
-
-#define INTMASK_MSK 0xD1000012
-#define INTSTS_SERROR 0x80000000
-#define INTSTS_PRERR 0x40000000
-#define INTSTS_RERR 0x10000000
-#define INTSTS_ICERR 0x01000000
-#define INTSTS_BMSINT 0x00000010
-#define INTSTS_BMHE 0x00000008
-#define INTSTS_IOIRQS 0x00000004
-#define INTSTS_INTRQ 0x00000002
-#define INTSTS_ACTEINT 0x00000001
-
-#define ECMODE_VALUE 0x01
-
-static struct scc_ports {
- unsigned long ctl, dma;
- struct ide_host *host; /* for removing port from system */
-} scc_ports[MAX_HWIFS];
-
-/* PIO transfer mode table */
-/* JCHST */
-static unsigned long JCHSTtbl[2][7] = {
- {0x0E, 0x05, 0x02, 0x03, 0x02, 0x00, 0x00}, /* 100MHz */
- {0x13, 0x07, 0x04, 0x04, 0x03, 0x00, 0x00} /* 133MHz */
-};
-
-/* JCHHT */
-static unsigned long JCHHTtbl[2][7] = {
- {0x0E, 0x02, 0x02, 0x02, 0x02, 0x00, 0x00}, /* 100MHz */
- {0x13, 0x03, 0x03, 0x03, 0x03, 0x00, 0x00} /* 133MHz */
-};
-
-/* JCHCT */
-static unsigned long JCHCTtbl[2][7] = {
- {0x1D, 0x1D, 0x1C, 0x0B, 0x06, 0x00, 0x00}, /* 100MHz */
- {0x27, 0x26, 0x26, 0x0E, 0x09, 0x00, 0x00} /* 133MHz */
-};
-
-
-/* DMA transfer mode table */
-/* JCHDCTM/JCHDCTS */
-static unsigned long JCHDCTxtbl[2][7] = {
- {0x0A, 0x06, 0x04, 0x03, 0x01, 0x00, 0x00}, /* 100MHz */
- {0x0E, 0x09, 0x06, 0x04, 0x02, 0x01, 0x00} /* 133MHz */
-};
-
-/* JCSTWTM/JCSTWTS */
-static unsigned long JCSTWTxtbl[2][7] = {
- {0x06, 0x04, 0x03, 0x02, 0x02, 0x02, 0x00}, /* 100MHz */
- {0x09, 0x06, 0x04, 0x02, 0x02, 0x02, 0x02} /* 133MHz */
-};
-
-/* JCTSS */
-static unsigned long JCTSStbl[2][7] = {
- {0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x00}, /* 100MHz */
- {0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05} /* 133MHz */
-};
-
-/* JCENVT */
-static unsigned long JCENVTtbl[2][7] = {
- {0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x00}, /* 100MHz */
- {0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02} /* 133MHz */
-};
-
-/* JCACTSELS/JCACTSELM */
-static unsigned long JCACTSELtbl[2][7] = {
- {0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x00}, /* 100MHz */
- {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01} /* 133MHz */
-};
-
-
-static u8 scc_ide_inb(unsigned long port)
-{
- u32 data = in_be32((void*)port);
- return (u8)data;
-}
-
-static void scc_exec_command(ide_hwif_t *hwif, u8 cmd)
-{
- out_be32((void *)hwif->io_ports.command_addr, cmd);
- eieio();
- in_be32((void *)(hwif->dma_base + 0x01c));
- eieio();
-}
-
-static u8 scc_read_status(ide_hwif_t *hwif)
-{
- return (u8)in_be32((void *)hwif->io_ports.status_addr);
-}
-
-static u8 scc_read_altstatus(ide_hwif_t *hwif)
-{
- return (u8)in_be32((void *)hwif->io_ports.ctl_addr);
-}
-
-static u8 scc_dma_sff_read_status(ide_hwif_t *hwif)
-{
- return (u8)in_be32((void *)(hwif->dma_base + 4));
-}
-
-static void scc_write_devctl(ide_hwif_t *hwif, u8 ctl)
-{
- out_be32((void *)hwif->io_ports.ctl_addr, ctl);
- eieio();
- in_be32((void *)(hwif->dma_base + 0x01c));
- eieio();
-}
-
-static void scc_ide_insw(unsigned long port, void *addr, u32 count)
-{
- u16 *ptr = (u16 *)addr;
- while (count--) {
- *ptr++ = le16_to_cpu(in_be32((void*)port));
- }
-}
-
-static void scc_ide_insl(unsigned long port, void *addr, u32 count)
-{
- u16 *ptr = (u16 *)addr;
- while (count--) {
- *ptr++ = le16_to_cpu(in_be32((void*)port));
- *ptr++ = le16_to_cpu(in_be32((void*)port));
- }
-}
-
-static void scc_ide_outb(u8 addr, unsigned long port)
-{
- out_be32((void*)port, addr);
-}
-
-static void
-scc_ide_outsw(unsigned long port, void *addr, u32 count)
-{
- u16 *ptr = (u16 *)addr;
- while (count--) {
- out_be32((void*)port, cpu_to_le16(*ptr++));
- }
-}
-
-static void
-scc_ide_outsl(unsigned long port, void *addr, u32 count)
-{
- u16 *ptr = (u16 *)addr;
- while (count--) {
- out_be32((void*)port, cpu_to_le16(*ptr++));
- out_be32((void*)port, cpu_to_le16(*ptr++));
- }
-}
-
-/**
- * scc_set_pio_mode - set host controller for PIO mode
- * @hwif: port
- * @drive: drive
- *
- * Load the timing settings for this device mode into the
- * controller.
- */
-
-static void scc_set_pio_mode(ide_hwif_t *hwif, ide_drive_t *drive)
-{
- struct scc_ports *ports = ide_get_hwifdata(hwif);
- unsigned long ctl_base = ports->ctl;
- unsigned long cckctrl_port = ctl_base + 0xff0;
- unsigned long piosht_port = ctl_base + 0x000;
- unsigned long pioct_port = ctl_base + 0x004;
- unsigned long reg;
- int offset;
- const u8 pio = drive->pio_mode - XFER_PIO_0;
-
- reg = in_be32((void __iomem *)cckctrl_port);
- if (reg & CCKCTRL_ATACLKOEN) {
- offset = 1; /* 133MHz */
- } else {
- offset = 0; /* 100MHz */
- }
- reg = JCHSTtbl[offset][pio] << 16 | JCHHTtbl[offset][pio];
- out_be32((void __iomem *)piosht_port, reg);
- reg = JCHCTtbl[offset][pio];
- out_be32((void __iomem *)pioct_port, reg);
-}
-
-/**
- * scc_set_dma_mode - set host controller for DMA mode
- * @hwif: port
- * @drive: drive
- *
- * Load the timing settings for this device mode into the
- * controller.
- */
-
-static void scc_set_dma_mode(ide_hwif_t *hwif, ide_drive_t *drive)
-{
- struct scc_ports *ports = ide_get_hwifdata(hwif);
- unsigned long ctl_base = ports->ctl;
- unsigned long cckctrl_port = ctl_base + 0xff0;
- unsigned long mdmact_port = ctl_base + 0x008;
- unsigned long mcrcst_port = ctl_base + 0x00c;
- unsigned long sdmact_port = ctl_base + 0x010;
- unsigned long scrcst_port = ctl_base + 0x014;
- unsigned long udenvt_port = ctl_base + 0x018;
- unsigned long tdvhsel_port = ctl_base + 0x020;
- int is_slave = drive->dn & 1;
- int offset, idx;
- unsigned long reg;
- unsigned long jcactsel;
- const u8 speed = drive->dma_mode;
-
- reg = in_be32((void __iomem *)cckctrl_port);
- if (reg & CCKCTRL_ATACLKOEN) {
- offset = 1; /* 133MHz */
- } else {
- offset = 0; /* 100MHz */
- }
-
- idx = speed - XFER_UDMA_0;
-
- jcactsel = JCACTSELtbl[offset][idx];
- if (is_slave) {
- out_be32((void __iomem *)sdmact_port, JCHDCTxtbl[offset][idx]);
- out_be32((void __iomem *)scrcst_port, JCSTWTxtbl[offset][idx]);
- jcactsel = jcactsel << 2;
- out_be32((void __iomem *)tdvhsel_port, (in_be32((void __iomem *)tdvhsel_port) & ~TDVHSEL_SLAVE) | jcactsel);
- } else {
- out_be32((void __iomem *)mdmact_port, JCHDCTxtbl[offset][idx]);
- out_be32((void __iomem *)mcrcst_port, JCSTWTxtbl[offset][idx]);
- out_be32((void __iomem *)tdvhsel_port, (in_be32((void __iomem *)tdvhsel_port) & ~TDVHSEL_MASTER) | jcactsel);
- }
- reg = JCTSStbl[offset][idx] << 16 | JCENVTtbl[offset][idx];
- out_be32((void __iomem *)udenvt_port, reg);
-}
-
-static void scc_dma_host_set(ide_drive_t *drive, int on)
-{
- ide_hwif_t *hwif = drive->hwif;
- u8 unit = drive->dn & 1;
- u8 dma_stat = scc_dma_sff_read_status(hwif);
-
- if (on)
- dma_stat |= (1 << (5 + unit));
- else
- dma_stat &= ~(1 << (5 + unit));
-
- scc_ide_outb(dma_stat, hwif->dma_base + 4);
-}
-
-/**
- * scc_dma_setup - begin a DMA phase
- * @drive: target device
- * @cmd: command
- *
- * Build an IDE DMA PRD (IDE speak for scatter gather table)
- * and then set up the DMA transfer registers.
- *
- * Returns 0 on success. If a PIO fallback is required then 1
- * is returned.
- */
-
-static int scc_dma_setup(ide_drive_t *drive, struct ide_cmd *cmd)
-{
- ide_hwif_t *hwif = drive->hwif;
- u32 rw = (cmd->tf_flags & IDE_TFLAG_WRITE) ? 0 : ATA_DMA_WR;
- u8 dma_stat;
-
- /* fall back to pio! */
- if (ide_build_dmatable(drive, cmd) == 0)
- return 1;
-
- /* PRD table */
- out_be32((void __iomem *)(hwif->dma_base + 8), hwif->dmatable_dma);
-
- /* specify r/w */
- out_be32((void __iomem *)hwif->dma_base, rw);
-
- /* read DMA status for INTR & ERROR flags */
- dma_stat = scc_dma_sff_read_status(hwif);
-
- /* clear INTR & ERROR flags */
- out_be32((void __iomem *)(hwif->dma_base + 4), dma_stat | 6);
-
- return 0;
-}
-
-static void scc_dma_start(ide_drive_t *drive)
-{
- ide_hwif_t *hwif = drive->hwif;
- u8 dma_cmd = scc_ide_inb(hwif->dma_base);
-
- /* start DMA */
- scc_ide_outb(dma_cmd | 1, hwif->dma_base);
-}
-
-static int __scc_dma_end(ide_drive_t *drive)
-{
- ide_hwif_t *hwif = drive->hwif;
- u8 dma_stat, dma_cmd;
-
- /* get DMA command mode */
- dma_cmd = scc_ide_inb(hwif->dma_base);
- /* stop DMA */
- scc_ide_outb(dma_cmd & ~1, hwif->dma_base);
- /* get DMA status */
- dma_stat = scc_dma_sff_read_status(hwif);
- /* clear the INTR & ERROR bits */
- scc_ide_outb(dma_stat | 6, hwif->dma_base + 4);
- /* verify good DMA status */
- return (dma_stat & 7) != 4 ? (0x10 | dma_stat) : 0;
-}
-
-/**
- * scc_dma_end - Stop DMA
- * @drive: IDE drive
- *
- * Check and clear INT Status register.
- * Then call __scc_dma_end().
- */
-
-static int scc_dma_end(ide_drive_t *drive)
-{
- ide_hwif_t *hwif = drive->hwif;
- void __iomem *dma_base = (void __iomem *)hwif->dma_base;
- unsigned long intsts_port = hwif->dma_base + 0x014;
- u32 reg;
- int dma_stat, data_loss = 0;
- static int retry = 0;
-
- /* errata A308 workaround: Step5 (check data loss) */
- /* We don't check non ide_disk because it is limited to UDMA4 */
- if (!(in_be32((void __iomem *)hwif->io_ports.ctl_addr)
- & ATA_ERR) &&
- drive->media == ide_disk && drive->current_speed > XFER_UDMA_4) {
- reg = in_be32((void __iomem *)intsts_port);
- if (!(reg & INTSTS_ACTEINT)) {
- printk(KERN_WARNING "%s: operation failed (transfer data loss)\n",
- drive->name);
- data_loss = 1;
- if (retry++) {
- struct request *rq = hwif->rq;
- ide_drive_t *drive;
- int i;
-
- /* ERROR_RESET and drive->crc_count are needed
- * to reduce DMA transfer mode in retry process.
- */
- if (rq)
- rq->errors |= ERROR_RESET;
-
- ide_port_for_each_dev(i, drive, hwif)
- drive->crc_count++;
- }
- }
- }
-
- while (1) {
- reg = in_be32((void __iomem *)intsts_port);
-
- if (reg & INTSTS_SERROR) {
- printk(KERN_WARNING "%s: SERROR\n", SCC_PATA_NAME);
- out_be32((void __iomem *)intsts_port, INTSTS_SERROR|INTSTS_BMSINT);
-
- out_be32(dma_base, in_be32(dma_base) & ~QCHCD_IOS_SS);
- continue;
- }
-
- if (reg & INTSTS_PRERR) {
- u32 maea0, maec0;
- unsigned long ctl_base = hwif->config_data;
-
- maea0 = in_be32((void __iomem *)(ctl_base + 0xF50));
- maec0 = in_be32((void __iomem *)(ctl_base + 0xF54));
-
- printk(KERN_WARNING "%s: PRERR [addr:%x cmd:%x]\n", SCC_PATA_NAME, maea0, maec0);
-
- out_be32((void __iomem *)intsts_port, INTSTS_PRERR|INTSTS_BMSINT);
-
- out_be32(dma_base, in_be32(dma_base) & ~QCHCD_IOS_SS);
- continue;
- }
-
- if (reg & INTSTS_RERR) {
- printk(KERN_WARNING "%s: Response Error\n", SCC_PATA_NAME);
- out_be32((void __iomem *)intsts_port, INTSTS_RERR|INTSTS_BMSINT);
-
- out_be32(dma_base, in_be32(dma_base) & ~QCHCD_IOS_SS);
- continue;
- }
-
- if (reg & INTSTS_ICERR) {
- out_be32(dma_base, in_be32(dma_base) & ~QCHCD_IOS_SS);
-
- printk(KERN_WARNING "%s: Illegal Configuration\n", SCC_PATA_NAME);
- out_be32((void __iomem *)intsts_port, INTSTS_ICERR|INTSTS_BMSINT);
- continue;
- }
-
- if (reg & INTSTS_BMSINT) {
- printk(KERN_WARNING "%s: Internal Bus Error\n", SCC_PATA_NAME);
- out_be32((void __iomem *)intsts_port, INTSTS_BMSINT);
-
- ide_do_reset(drive);
- continue;
- }
-
- if (reg & INTSTS_BMHE) {
- out_be32((void __iomem *)intsts_port, INTSTS_BMHE);
- continue;
- }
-
- if (reg & INTSTS_ACTEINT) {
- out_be32((void __iomem *)intsts_port, INTSTS_ACTEINT);
- continue;
- }
-
- if (reg & INTSTS_IOIRQS) {
- out_be32((void __iomem *)intsts_port, INTSTS_IOIRQS);
- continue;
- }
- break;
- }
-
- dma_stat = __scc_dma_end(drive);
- if (data_loss)
- dma_stat |= 2; /* emulate DMA error (to retry command) */
- return dma_stat;
-}
-
-/* returns 1 if dma irq issued, 0 otherwise */
-static int scc_dma_test_irq(ide_drive_t *drive)
-{
- ide_hwif_t *hwif = drive->hwif;
- u32 int_stat = in_be32((void __iomem *)hwif->dma_base + 0x014);
-
- /* SCC errata A252,A308 workaround: Step4 */
- if ((in_be32((void __iomem *)hwif->io_ports.ctl_addr)
- & ATA_ERR) &&
- (int_stat & INTSTS_INTRQ))
- return 1;
-
- /* SCC errata A308 workaround: Step5 (polling IOIRQS) */
- if (int_stat & INTSTS_IOIRQS)
- return 1;
-
- return 0;
-}
-
-static u8 scc_udma_filter(ide_drive_t *drive)
-{
- ide_hwif_t *hwif = drive->hwif;
- u8 mask = hwif->ultra_mask;
-
- /* errata A308 workaround: limit non ide_disk drive to UDMA4 */
- if ((drive->media != ide_disk) && (mask & 0xE0)) {
- printk(KERN_INFO "%s: limit %s to UDMA4\n",
- SCC_PATA_NAME, drive->name);
- mask = ATA_UDMA4;
- }
-
- return mask;
-}
-
-/**
- * setup_mmio_scc - map CTRL/BMID region
- * @dev: PCI device we are configuring
- * @name: device name
- *
- */
-
-static int setup_mmio_scc (struct pci_dev *dev, const char *name)
-{
- void __iomem *ctl_addr;
- void __iomem *dma_addr;
- int i, ret;
-
- for (i = 0; i < MAX_HWIFS; i++) {
- if (scc_ports[i].ctl == 0)
- break;
- }
- if (i >= MAX_HWIFS)
- return -ENOMEM;
-
- ret = pci_request_selected_regions(dev, (1 << 2) - 1, name);
- if (ret < 0) {
- printk(KERN_ERR "%s: can't reserve resources\n", name);
- return ret;
- }
-
- ctl_addr = pci_ioremap_bar(dev, 0);
- if (!ctl_addr)
- goto fail_0;
-
- dma_addr = pci_ioremap_bar(dev, 1);
- if (!dma_addr)
- goto fail_1;
-
- pci_set_master(dev);
- scc_ports[i].ctl = (unsigned long)ctl_addr;
- scc_ports[i].dma = (unsigned long)dma_addr;
- pci_set_drvdata(dev, (void *) &scc_ports[i]);
-
- return 1;
-
- fail_1:
- iounmap(ctl_addr);
- fail_0:
- return -ENOMEM;
-}
-
-static int scc_ide_setup_pci_device(struct pci_dev *dev,
- const struct ide_port_info *d)
-{
- struct scc_ports *ports = pci_get_drvdata(dev);
- struct ide_host *host;
- struct ide_hw hw, *hws[] = { &hw };
- int i, rc;
-
- memset(&hw, 0, sizeof(hw));
- for (i = 0; i <= 8; i++)
- hw.io_ports_array[i] = ports->dma + 0x20 + i * 4;
- hw.irq = dev->irq;
- hw.dev = &dev->dev;
-
- rc = ide_host_add(d, hws, 1, &host);
- if (rc)
- return rc;
-
- ports->host = host;
-
- return 0;
-}
-
-/**
- * init_setup_scc - set up an SCC PATA Controller
- * @dev: PCI device
- * @d: IDE port info
- *
- * Perform the initial set up for this device.
- */
-
-static int init_setup_scc(struct pci_dev *dev, const struct ide_port_info *d)
-{
- unsigned long ctl_base;
- unsigned long dma_base;
- unsigned long cckctrl_port;
- unsigned long intmask_port;
- unsigned long mode_port;
- unsigned long ecmode_port;
- u32 reg = 0;
- struct scc_ports *ports;
- int rc;
-
- rc = pci_enable_device(dev);
- if (rc)
- goto end;
-
- rc = setup_mmio_scc(dev, d->name);
- if (rc < 0)
- goto end;
-
- ports = pci_get_drvdata(dev);
- ctl_base = ports->ctl;
- dma_base = ports->dma;
- cckctrl_port = ctl_base + 0xff0;
- intmask_port = dma_base + 0x010;
- mode_port = ctl_base + 0x024;
- ecmode_port = ctl_base + 0xf00;
-
- /* controller initialization */
- reg = 0;
- out_be32((void*)cckctrl_port, reg);
- reg |= CCKCTRL_ATACLKOEN;
- out_be32((void*)cckctrl_port, reg);
- reg |= CCKCTRL_LCLKEN | CCKCTRL_OCLKEN;
- out_be32((void*)cckctrl_port, reg);
- reg |= CCKCTRL_CRST;
- out_be32((void*)cckctrl_port, reg);
-
- for (;;) {
- reg = in_be32((void*)cckctrl_port);
- if (reg & CCKCTRL_CRST)
- break;
- udelay(5000);
- }
-
- reg |= CCKCTRL_ATARESET;
- out_be32((void*)cckctrl_port, reg);
-
- out_be32((void*)ecmode_port, ECMODE_VALUE);
- out_be32((void*)mode_port, MODE_JCUSFEN);
- out_be32((void*)intmask_port, INTMASK_MSK);
-
- rc = scc_ide_setup_pci_device(dev, d);
-
- end:
- return rc;
-}
-
-static void scc_tf_load(ide_drive_t *drive, struct ide_taskfile *tf, u8 valid)
-{
- struct ide_io_ports *io_ports = &drive->hwif->io_ports;
-
- if (valid & IDE_VALID_FEATURE)
- scc_ide_outb(tf->feature, io_ports->feature_addr);
- if (valid & IDE_VALID_NSECT)
- scc_ide_outb(tf->nsect, io_ports->nsect_addr);
- if (valid & IDE_VALID_LBAL)
- scc_ide_outb(tf->lbal, io_ports->lbal_addr);
- if (valid & IDE_VALID_LBAM)
- scc_ide_outb(tf->lbam, io_ports->lbam_addr);
- if (valid & IDE_VALID_LBAH)
- scc_ide_outb(tf->lbah, io_ports->lbah_addr);
- if (valid & IDE_VALID_DEVICE)
- scc_ide_outb(tf->device, io_ports->device_addr);
-}
-
-static void scc_tf_read(ide_drive_t *drive, struct ide_taskfile *tf, u8 valid)
-{
- struct ide_io_ports *io_ports = &drive->hwif->io_ports;
-
- if (valid & IDE_VALID_ERROR)
- tf->error = scc_ide_inb(io_ports->feature_addr);
- if (valid & IDE_VALID_NSECT)
- tf->nsect = scc_ide_inb(io_ports->nsect_addr);
- if (valid & IDE_VALID_LBAL)
- tf->lbal = scc_ide_inb(io_ports->lbal_addr);
- if (valid & IDE_VALID_LBAM)
- tf->lbam = scc_ide_inb(io_ports->lbam_addr);
- if (valid & IDE_VALID_LBAH)
- tf->lbah = scc_ide_inb(io_ports->lbah_addr);
- if (valid & IDE_VALID_DEVICE)
- tf->device = scc_ide_inb(io_ports->device_addr);
-}
-
-static void scc_input_data(ide_drive_t *drive, struct ide_cmd *cmd,
- void *buf, unsigned int len)
-{
- unsigned long data_addr = drive->hwif->io_ports.data_addr;
-
- len++;
-
- if (drive->io_32bit) {
- scc_ide_insl(data_addr, buf, len / 4);
-
- if ((len & 3) >= 2)
- scc_ide_insw(data_addr, (u8 *)buf + (len & ~3), 1);
- } else
- scc_ide_insw(data_addr, buf, len / 2);
-}
-
-static void scc_output_data(ide_drive_t *drive, struct ide_cmd *cmd,
- void *buf, unsigned int len)
-{
- unsigned long data_addr = drive->hwif->io_ports.data_addr;
-
- len++;
-
- if (drive->io_32bit) {
- scc_ide_outsl(data_addr, buf, len / 4);
-
- if ((len & 3) >= 2)
- scc_ide_outsw(data_addr, (u8 *)buf + (len & ~3), 1);
- } else
- scc_ide_outsw(data_addr, buf, len / 2);
-}
-
-/**
- * init_mmio_iops_scc - set up the iops for MMIO
- * @hwif: interface to set up
- *
- */
-
-static void init_mmio_iops_scc(ide_hwif_t *hwif)
-{
- struct pci_dev *dev = to_pci_dev(hwif->dev);
- struct scc_ports *ports = pci_get_drvdata(dev);
- unsigned long dma_base = ports->dma;
-
- ide_set_hwifdata(hwif, ports);
-
- hwif->dma_base = dma_base;
- hwif->config_data = ports->ctl;
-}
-
-/**
- * init_iops_scc - set up iops
- * @hwif: interface to set up
- *
- * Do the basic setup for the SCC hardware interface
- * and then do the MMIO setup.
- */
-
-static void init_iops_scc(ide_hwif_t *hwif)
-{
- struct pci_dev *dev = to_pci_dev(hwif->dev);
-
- hwif->hwif_data = NULL;
- if (pci_get_drvdata(dev) == NULL)
- return;
- init_mmio_iops_scc(hwif);
-}
-
-static int scc_init_dma(ide_hwif_t *hwif, const struct ide_port_info *d)
-{
- return ide_allocate_dma_engine(hwif);
-}
-
-static u8 scc_cable_detect(ide_hwif_t *hwif)
-{
- return ATA_CBL_PATA80;
-}
-
-/**
- * init_hwif_scc - set up hwif
- * @hwif: interface to set up
- *
- * We do the basic set up of the interface structure. The SCC
- * requires several custom handlers so we override the default
- * ide DMA handlers appropriately.
- */
-
-static void init_hwif_scc(ide_hwif_t *hwif)
-{
- /* PTERADD */
- out_be32((void __iomem *)(hwif->dma_base + 0x018), hwif->dmatable_dma);
-
- if (in_be32((void __iomem *)(hwif->config_data + 0xff0)) & CCKCTRL_ATACLKOEN)
- hwif->ultra_mask = ATA_UDMA6; /* 133MHz */
- else
- hwif->ultra_mask = ATA_UDMA5; /* 100MHz */
-}
-
-static const struct ide_tp_ops scc_tp_ops = {
- .exec_command = scc_exec_command,
- .read_status = scc_read_status,
- .read_altstatus = scc_read_altstatus,
- .write_devctl = scc_write_devctl,
-
- .dev_select = ide_dev_select,
- .tf_load = scc_tf_load,
- .tf_read = scc_tf_read,
-
- .input_data = scc_input_data,
- .output_data = scc_output_data,
-};
-
-static const struct ide_port_ops scc_port_ops = {
- .set_pio_mode = scc_set_pio_mode,
- .set_dma_mode = scc_set_dma_mode,
- .udma_filter = scc_udma_filter,
- .cable_detect = scc_cable_detect,
-};
-
-static const struct ide_dma_ops scc_dma_ops = {
- .dma_host_set = scc_dma_host_set,
- .dma_setup = scc_dma_setup,
- .dma_start = scc_dma_start,
- .dma_end = scc_dma_end,
- .dma_test_irq = scc_dma_test_irq,
- .dma_lost_irq = ide_dma_lost_irq,
- .dma_timer_expiry = ide_dma_sff_timer_expiry,
- .dma_sff_read_status = scc_dma_sff_read_status,
-};
-
-static const struct ide_port_info scc_chipset = {
- .name = "sccIDE",
- .init_iops = init_iops_scc,
- .init_dma = scc_init_dma,
- .init_hwif = init_hwif_scc,
- .tp_ops = &scc_tp_ops,
- .port_ops = &scc_port_ops,
- .dma_ops = &scc_dma_ops,
- .host_flags = IDE_HFLAG_SINGLE,
- .irq_flags = IRQF_SHARED,
- .pio_mask = ATA_PIO4,
- .chipset = ide_pci,
-};
-
-/**
- * scc_init_one - pci layer discovery entry
- * @dev: PCI device
- * @id: ident table entry
- *
- * Called by the PCI code when it finds an SCC PATA controller.
- * We then use the IDE PCI generic helper to do most of the work.
- */
-
-static int scc_init_one(struct pci_dev *dev, const struct pci_device_id *id)
-{
- return init_setup_scc(dev, &scc_chipset);
-}
-
-/**
- * scc_remove - pci layer remove entry
- * @dev: PCI device
- *
- * Called by the PCI code when it removes an SCC PATA controller.
- */
-
-static void scc_remove(struct pci_dev *dev)
-{
- struct scc_ports *ports = pci_get_drvdata(dev);
- struct ide_host *host = ports->host;
-
- ide_host_remove(host);
-
- iounmap((void*)ports->dma);
- iounmap((void*)ports->ctl);
- pci_release_selected_regions(dev, (1 << 2) - 1);
- memset(ports, 0, sizeof(*ports));
-}
-
-static const struct pci_device_id scc_pci_tbl[] = {
- { PCI_VDEVICE(TOSHIBA_2, PCI_DEVICE_ID_TOSHIBA_SCC_ATA), 0 },
- { 0, },
-};
-MODULE_DEVICE_TABLE(pci, scc_pci_tbl);
-
-static struct pci_driver scc_pci_driver = {
- .name = "SCC IDE",
- .id_table = scc_pci_tbl,
- .probe = scc_init_one,
- .remove = scc_remove,
-};
-
-static int __init scc_ide_init(void)
-{
- return ide_pci_register_driver(&scc_pci_driver);
-}
-
-static void __exit scc_ide_exit(void)
-{
- pci_unregister_driver(&scc_pci_driver);
-}
-
-module_init(scc_ide_init);
-module_exit(scc_ide_exit);
-
-MODULE_DESCRIPTION("PCI driver module for Toshiba SCC IDE");
-MODULE_LICENSE("GPL");
{
int ret, i;
int len_words = len / sizeof(u16);
- __be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS];
+ __be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS / 2];
+
+ if (len_words > ARRAY_SIZE(be_buf)) {
+ dev_err(&client->dev, "Invalid buffer size %d\n", len);
+ return -EINVAL;
+ }
ret = mma9551_transfer(client, app_id, MMA9551_CMD_READ_CONFIG,
reg, NULL, 0, (u8 *) be_buf, len);
{
int ret, i;
int len_words = len / sizeof(u16);
- __be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS];
+ __be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS / 2];
+
+ if (len_words > ARRAY_SIZE(be_buf)) {
+ dev_err(&client->dev, "Invalid buffer size %d\n", len);
+ return -EINVAL;
+ }
ret = mma9551_transfer(client, app_id, MMA9551_CMD_READ_STATUS,
reg, NULL, 0, (u8 *) be_buf, len);
{
int i;
int len_words = len / sizeof(u16);
- __be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS];
+ __be16 be_buf[(MMA9551_MAX_MAILBOX_DATA_REGS - 1) / 2];
+
+ if (len_words > ARRAY_SIZE(be_buf)) {
+ dev_err(&client->dev, "Invalid buffer size %d\n", len);
+ return -EINVAL;
+ }
for (i = 0; i < len_words; i++)
be_buf[i] = cpu_to_be16(buf[i]);
#define MMA9553_MASK_CONF_STEPCOALESCE GENMASK(7, 0)
#define MMA9553_REG_CONF_ACTTHD 0x0E
+#define MMA9553_MAX_ACTTHD GENMASK(15, 0)
/* Pedometer status registers (R-only) */
#define MMA9553_REG_STATUS 0x00
static int mma9553_read_activity_stepcnt(struct mma9553_data *data,
u8 *activity, u16 *stepcnt)
{
- u32 status_stepcnt;
- u16 status;
+ u16 buf[2];
int ret;
ret = mma9551_read_status_words(data->client, MMA9551_APPID_PEDOMETER,
- MMA9553_REG_STATUS, sizeof(u32),
- (u16 *) &status_stepcnt);
+ MMA9553_REG_STATUS, sizeof(u32), buf);
if (ret < 0) {
dev_err(&data->client->dev,
"error reading status and stepcnt\n");
return ret;
}
- status = status_stepcnt & MMA9553_MASK_CONF_WORD;
- *activity = mma9553_get_bits(status, MMA9553_MASK_STATUS_ACTIVITY);
- *stepcnt = status_stepcnt >> 16;
+ *activity = mma9553_get_bits(buf[0], MMA9553_MASK_STATUS_ACTIVITY);
+ *stepcnt = buf[1];
return 0;
}
case IIO_EV_INFO_PERIOD:
switch (chan->type) {
case IIO_ACTIVITY:
+ if (val < 0 || val > MMA9553_ACTIVITY_THD_TO_SEC(
+ MMA9553_MAX_ACTTHD))
+ return -EINVAL;
mutex_lock(&data->mutex);
ret = mma9553_set_config(data, MMA9553_REG_CONF_ACTTHD,
&data->conf.actthd,
.modified = 1, \
.channel2 = _chan2, \
.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED), \
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_CALIBHEIGHT), \
+ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_CALIBHEIGHT) | \
+ BIT(IIO_CHAN_INFO_ENABLE), \
.event_spec = mma9553_activity_events, \
.num_event_specs = ARRAY_SIZE(mma9553_activity_events), \
.ext_info = mma9553_ext_info, \
indio_dev->modes = INDIO_DIRECT_MODE;
indio_dev->info = &accel_info;
+ mutex_init(&adata->tb.buf_lock);
st_sensors_power_enable(indio_dev);
.channel = 0,
.address = AXP288_TS_ADC_H,
.datasheet_name = "TS_PIN",
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
}, {
.indexed = 1,
.type = IIO_TEMP,
.channel = 1,
.address = AXP288_PMIC_ADC_H,
.datasheet_name = "PMIC_TEMP",
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
}, {
.indexed = 1,
.type = IIO_TEMP,
.channel = 2,
.address = AXP288_GP_ADC_H,
.datasheet_name = "GPADC",
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
}, {
.indexed = 1,
.type = IIO_CURRENT,
.channel = 3,
.address = AXP20X_BATT_CHRG_I_H,
.datasheet_name = "BATT_CHG_I",
- .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
}, {
.indexed = 1,
.type = IIO_CURRENT,
.channel = 4,
.address = AXP20X_BATT_DISCHRG_I_H,
.datasheet_name = "BATT_DISCHRG_I",
- .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
}, {
.indexed = 1,
.type = IIO_VOLTAGE,
.channel = 5,
.address = AXP20X_BATT_V_H,
.datasheet_name = "BATT_V",
- .info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
},
};
chan->address))
dev_err(&indio_dev->dev, "TS pin restore\n");
break;
- case IIO_CHAN_INFO_PROCESSED:
- ret = axp288_adc_read_channel(val, chan->address, info->regmap);
- break;
default:
ret = -EINVAL;
}
#define CC10001_ADC_EOC_SET BIT(0)
#define CC10001_ADC_CHSEL_SAMPLED 0x0c
-#define CC10001_ADC_POWER_UP 0x10
-#define CC10001_ADC_POWER_UP_SET BIT(0)
+#define CC10001_ADC_POWER_DOWN 0x10
+#define CC10001_ADC_POWER_DOWN_SET BIT(0)
+
#define CC10001_ADC_DEBUG 0x14
#define CC10001_ADC_DATA_COUNT 0x20
u16 *buf;
struct mutex lock;
- unsigned long channel_map;
unsigned int start_delay_ns;
unsigned int eoc_delay_ns;
};
return readl(adc_dev->reg_base + reg);
}
+static void cc10001_adc_power_up(struct cc10001_adc_device *adc_dev)
+{
+ cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_DOWN, 0);
+ ndelay(adc_dev->start_delay_ns);
+}
+
+static void cc10001_adc_power_down(struct cc10001_adc_device *adc_dev)
+{
+ cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_DOWN,
+ CC10001_ADC_POWER_DOWN_SET);
+}
+
static void cc10001_adc_start(struct cc10001_adc_device *adc_dev,
unsigned int channel)
{
val = (channel & CC10001_ADC_CH_MASK) | CC10001_ADC_MODE_SINGLE_CONV;
cc10001_adc_write_reg(adc_dev, CC10001_ADC_CONFIG, val);
+ udelay(1);
val = cc10001_adc_read_reg(adc_dev, CC10001_ADC_CONFIG);
val = val | CC10001_ADC_START_CONV;
cc10001_adc_write_reg(adc_dev, CC10001_ADC_CONFIG, val);
struct iio_dev *indio_dev;
unsigned int delay_ns;
unsigned int channel;
+ unsigned int scan_idx;
bool sample_invalid;
u16 *data;
int i;
mutex_lock(&adc_dev->lock);
- cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP,
- CC10001_ADC_POWER_UP_SET);
-
- /* Wait for 8 (6+2) clock cycles before activating START */
- ndelay(adc_dev->start_delay_ns);
+ cc10001_adc_power_up(adc_dev);
/* Calculate delay step for eoc and sampled data */
delay_ns = adc_dev->eoc_delay_ns / CC10001_MAX_POLL_COUNT;
i = 0;
sample_invalid = false;
- for_each_set_bit(channel, indio_dev->active_scan_mask,
+ for_each_set_bit(scan_idx, indio_dev->active_scan_mask,
indio_dev->masklength) {
+ channel = indio_dev->channels[scan_idx].channel;
cc10001_adc_start(adc_dev, channel);
data[i] = cc10001_adc_poll_done(indio_dev, channel, delay_ns);
}
done:
- cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP, 0);
+ cc10001_adc_power_down(adc_dev);
mutex_unlock(&adc_dev->lock);
unsigned int delay_ns;
u16 val;
- cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP,
- CC10001_ADC_POWER_UP_SET);
-
- /* Wait for 8 (6+2) clock cycles before activating START */
- ndelay(adc_dev->start_delay_ns);
+ cc10001_adc_power_up(adc_dev);
/* Calculate delay step for eoc and sampled data */
delay_ns = adc_dev->eoc_delay_ns / CC10001_MAX_POLL_COUNT;
val = cc10001_adc_poll_done(indio_dev, chan->channel, delay_ns);
- cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP, 0);
+ cc10001_adc_power_down(adc_dev);
return val;
}
case IIO_CHAN_INFO_SCALE:
ret = regulator_get_voltage(adc_dev->reg);
- if (ret)
+ if (ret < 0)
return ret;
*val = ret / 1000;
.update_scan_mode = &cc10001_update_scan_mode,
};
-static int cc10001_adc_channel_init(struct iio_dev *indio_dev)
+static int cc10001_adc_channel_init(struct iio_dev *indio_dev,
+ unsigned long channel_map)
{
- struct cc10001_adc_device *adc_dev = iio_priv(indio_dev);
struct iio_chan_spec *chan_array, *timestamp;
unsigned int bit, idx = 0;
- indio_dev->num_channels = bitmap_weight(&adc_dev->channel_map,
- CC10001_ADC_NUM_CHANNELS);
+ indio_dev->num_channels = bitmap_weight(&channel_map,
+ CC10001_ADC_NUM_CHANNELS) + 1;
- chan_array = devm_kcalloc(&indio_dev->dev, indio_dev->num_channels + 1,
+ chan_array = devm_kcalloc(&indio_dev->dev, indio_dev->num_channels,
sizeof(struct iio_chan_spec),
GFP_KERNEL);
if (!chan_array)
return -ENOMEM;
- for_each_set_bit(bit, &adc_dev->channel_map, CC10001_ADC_NUM_CHANNELS) {
+ for_each_set_bit(bit, &channel_map, CC10001_ADC_NUM_CHANNELS) {
struct iio_chan_spec *chan = &chan_array[idx];
chan->type = IIO_VOLTAGE;
unsigned long adc_clk_rate;
struct resource *res;
struct iio_dev *indio_dev;
+ unsigned long channel_map;
int ret;
indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*adc_dev));
adc_dev = iio_priv(indio_dev);
- adc_dev->channel_map = GENMASK(CC10001_ADC_NUM_CHANNELS - 1, 0);
+ channel_map = GENMASK(CC10001_ADC_NUM_CHANNELS - 1, 0);
if (!of_property_read_u32(node, "adc-reserved-channels", &ret))
- adc_dev->channel_map &= ~ret;
+ channel_map &= ~ret;
adc_dev->reg = devm_regulator_get(&pdev->dev, "vref");
if (IS_ERR(adc_dev->reg))
adc_dev->start_delay_ns = adc_dev->eoc_delay_ns * CC10001_WAIT_CYCLES;
/* Setup the ADC channels available on the device */
- ret = cc10001_adc_channel_init(indio_dev);
+ ret = cc10001_adc_channel_init(indio_dev, channel_map);
if (ret < 0)
goto err_disable_clk;
struct spi_message msg;
struct spi_transfer transfer[2];
- u8 tx_buf;
- u8 rx_buf[2];
-
struct regulator *reg;
struct mutex lock;
const struct mcp320x_chip_info *chip_info;
+
+ u8 tx_buf ____cacheline_aligned;
+ u8 rx_buf[2];
};
static int mcp320x_channel_to_tx_data(int device_index,
#include <linux/iio/iio.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
+#include <linux/math64.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/platform_device.h>
const struct vadc_channel_prop *prop, u16 adc_code)
{
const struct vadc_prescale_ratio *prescale;
- s32 voltage;
+ s64 voltage;
voltage = adc_code - vadc->graph[prop->calibration].gnd;
voltage *= vadc->graph[prop->calibration].dx;
- voltage = voltage / vadc->graph[prop->calibration].dy;
+ voltage = div64_s64(voltage, vadc->graph[prop->calibration].dy);
if (prop->calibration == VADC_CALIB_ABSOLUTE)
voltage += vadc->graph[prop->calibration].dx;
voltage = voltage * prescale->den;
- return voltage / prescale->num;
+ return div64_s64(voltage, prescale->num);
}
static int vadc_decimation_from_dt(u32 value)
module_platform_driver(twl6030_gpadc_driver);
-MODULE_ALIAS("platform: " DRIVER_NAME);
+MODULE_ALIAS("platform:" DRIVER_NAME);
MODULE_AUTHOR("Balaji T K <balajitk@ti.com>");
MODULE_AUTHOR("Graeme Gregory <gg@slimlogic.co.uk>");
MODULE_AUTHOR("Oleksandr Kozaruk <oleksandr.kozaruk@ti.com");
switch (chan->address) {
case XADC_REG_VCCINT:
case XADC_REG_VCCAUX:
+ case XADC_REG_VREFP:
case XADC_REG_VCCBRAM:
case XADC_REG_VCCPINT:
case XADC_REG_VCCPAUX:
.num_event_specs = (_alarm) ? ARRAY_SIZE(xadc_voltage_events) : 0, \
.scan_index = (_scan_index), \
.scan_type = { \
- .sign = 'u', \
+ .sign = ((_addr) == XADC_REG_VREFN) ? 's' : 'u', \
.realbits = 12, \
.storagebits = 16, \
.shift = 4, \
static const struct iio_chan_spec xadc_channels[] = {
XADC_CHAN_TEMP(0, 8, XADC_REG_TEMP),
XADC_CHAN_VOLTAGE(0, 9, XADC_REG_VCCINT, "vccint", true),
- XADC_CHAN_VOLTAGE(1, 10, XADC_REG_VCCINT, "vccaux", true),
+ XADC_CHAN_VOLTAGE(1, 10, XADC_REG_VCCAUX, "vccaux", true),
XADC_CHAN_VOLTAGE(2, 14, XADC_REG_VCCBRAM, "vccbram", true),
XADC_CHAN_VOLTAGE(3, 5, XADC_REG_VCCPINT, "vccpint", true),
XADC_CHAN_VOLTAGE(4, 6, XADC_REG_VCCPAUX, "vccpaux", true),
#define XADC_REG_MAX_VCCPINT 0x28
#define XADC_REG_MAX_VCCPAUX 0x29
#define XADC_REG_MAX_VCCO_DDR 0x2a
-#define XADC_REG_MIN_VCCPINT 0x2b
-#define XADC_REG_MIN_VCCPAUX 0x2c
-#define XADC_REG_MIN_VCCO_DDR 0x2d
+#define XADC_REG_MIN_VCCPINT 0x2c
+#define XADC_REG_MIN_VCCPAUX 0x2d
+#define XADC_REG_MIN_VCCO_DDR 0x2e
#define XADC_REG_CONF0 0x40
#define XADC_REG_CONF1 0x41
struct st_sensors_platform_data *of_pdata;
int err = 0;
- mutex_init(&sdata->tb.buf_lock);
-
/* If OF/DT pdata exists, it will take precedence of anything else */
of_pdata = st_sensors_of_probe(indio_dev->dev.parent, pdata);
if (of_pdata)
indio_dev->modes = INDIO_DIRECT_MODE;
indio_dev->info = &gyro_info;
+ mutex_init(&gdata->tb.buf_lock);
st_sensors_power_enable(indio_dev);
#define ADIS16400_NO_BURST BIT(1)
#define ADIS16400_HAS_SLOW_MODE BIT(2)
#define ADIS16400_HAS_SERIAL_NUMBER BIT(3)
+#define ADIS16400_BURST_DIAG_STAT BIT(4)
struct adis16400_state;
int filt_int;
struct adis adis;
+ unsigned long avail_scan_mask[2];
};
/* At the moment triggers are only used for ring buffer
{
struct adis16400_state *st = iio_priv(indio_dev);
struct adis *adis = &st->adis;
- uint16_t *tx;
+ unsigned int burst_length;
+ u8 *tx;
if (st->variant->flags & ADIS16400_NO_BURST)
return adis_update_scan_mode(indio_dev, scan_mask);
kfree(adis->xfer);
kfree(adis->buffer);
+ /* All but the timestamp channel */
+ burst_length = (indio_dev->num_channels - 1) * sizeof(u16);
+ if (st->variant->flags & ADIS16400_BURST_DIAG_STAT)
+ burst_length += sizeof(u16);
+
adis->xfer = kcalloc(2, sizeof(*adis->xfer), GFP_KERNEL);
if (!adis->xfer)
return -ENOMEM;
- adis->buffer = kzalloc(indio_dev->scan_bytes + sizeof(u16),
- GFP_KERNEL);
+ adis->buffer = kzalloc(burst_length + sizeof(u16), GFP_KERNEL);
if (!adis->buffer)
return -ENOMEM;
- tx = adis->buffer + indio_dev->scan_bytes;
-
+ tx = adis->buffer + burst_length;
tx[0] = ADIS_READ_REG(ADIS16400_GLOB_CMD);
tx[1] = 0;
adis->xfer[0].tx_buf = tx;
adis->xfer[0].bits_per_word = 8;
adis->xfer[0].len = 2;
- adis->xfer[1].tx_buf = tx;
+ adis->xfer[1].rx_buf = adis->buffer;
adis->xfer[1].bits_per_word = 8;
- adis->xfer[1].len = indio_dev->scan_bytes;
+ adis->xfer[1].len = burst_length;
spi_message_init(&adis->msg);
spi_message_add_tail(&adis->xfer[0], &adis->msg);
struct adis16400_state *st = iio_priv(indio_dev);
struct adis *adis = &st->adis;
u32 old_speed_hz = st->adis.spi->max_speed_hz;
+ void *buffer;
int ret;
if (!adis->buffer)
spi_setup(st->adis.spi);
}
- iio_push_to_buffers_with_timestamp(indio_dev, adis->buffer,
+ if (st->variant->flags & ADIS16400_BURST_DIAG_STAT)
+ buffer = adis->buffer + sizeof(u16);
+ else
+ buffer = adis->buffer;
+
+ iio_push_to_buffers_with_timestamp(indio_dev, buffer,
pf->timestamp);
iio_trigger_notify_done(indio_dev->trig);
*val = st->variant->temp_scale_nano / 1000000;
*val2 = (st->variant->temp_scale_nano % 1000000);
return IIO_VAL_INT_PLUS_MICRO;
+ case IIO_PRESSURE:
+ /* 20 uBar = 0.002kPascal */
+ *val = 0;
+ *val2 = 2000;
+ return IIO_VAL_INT_PLUS_MICRO;
default:
return -EINVAL;
}
}
}
-#define ADIS16400_VOLTAGE_CHAN(addr, bits, name, si) { \
+#define ADIS16400_VOLTAGE_CHAN(addr, bits, name, si, chn) { \
.type = IIO_VOLTAGE, \
.indexed = 1, \
- .channel = 0, \
+ .channel = chn, \
.extend_name = name, \
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \
BIT(IIO_CHAN_INFO_SCALE), \
}
#define ADIS16400_SUPPLY_CHAN(addr, bits) \
- ADIS16400_VOLTAGE_CHAN(addr, bits, "supply", ADIS16400_SCAN_SUPPLY)
+ ADIS16400_VOLTAGE_CHAN(addr, bits, "supply", ADIS16400_SCAN_SUPPLY, 0)
#define ADIS16400_AUX_ADC_CHAN(addr, bits) \
- ADIS16400_VOLTAGE_CHAN(addr, bits, NULL, ADIS16400_SCAN_ADC)
+ ADIS16400_VOLTAGE_CHAN(addr, bits, NULL, ADIS16400_SCAN_ADC, 1)
#define ADIS16400_GYRO_CHAN(mod, addr, bits) { \
.type = IIO_ANGL_VEL, \
.channels = adis16448_channels,
.num_channels = ARRAY_SIZE(adis16448_channels),
.flags = ADIS16400_HAS_PROD_ID |
- ADIS16400_HAS_SERIAL_NUMBER,
+ ADIS16400_HAS_SERIAL_NUMBER |
+ ADIS16400_BURST_DIAG_STAT,
.gyro_scale_micro = IIO_DEGREE_TO_RAD(10000), /* 0.01 deg/s */
.accel_scale_micro = IIO_G_TO_M_S_2(833), /* 1/1200 g */
.temp_scale_nano = 73860000, /* 0.07386 C */
.debugfs_reg_access = adis_debugfs_reg_access,
};
-static const unsigned long adis16400_burst_scan_mask[] = {
- ~0UL,
- 0,
-};
-
static const char * const adis16400_status_error_msgs[] = {
[ADIS16400_DIAG_STAT_ZACCL_FAIL] = "Z-axis accelerometer self-test failure",
[ADIS16400_DIAG_STAT_YACCL_FAIL] = "Y-axis accelerometer self-test failure",
BIT(ADIS16400_DIAG_STAT_POWER_LOW),
};
+static void adis16400_setup_chan_mask(struct adis16400_state *st)
+{
+ const struct adis16400_chip_info *chip_info = st->variant;
+ unsigned i;
+
+ for (i = 0; i < chip_info->num_channels; i++) {
+ const struct iio_chan_spec *ch = &chip_info->channels[i];
+
+ if (ch->scan_index >= 0 &&
+ ch->scan_index != ADIS16400_SCAN_TIMESTAMP)
+ st->avail_scan_mask[0] |= BIT(ch->scan_index);
+ }
+}
+
static int adis16400_probe(struct spi_device *spi)
{
struct adis16400_state *st;
indio_dev->info = &adis16400_info;
indio_dev->modes = INDIO_DIRECT_MODE;
- if (!(st->variant->flags & ADIS16400_NO_BURST))
- indio_dev->available_scan_masks = adis16400_burst_scan_mask;
+ if (!(st->variant->flags & ADIS16400_NO_BURST)) {
+ adis16400_setup_chan_mask(st);
+ indio_dev->available_scan_masks = st->avail_scan_mask;
+ }
ret = adis_init(&st->adis, indio_dev, spi, &adis16400_data);
if (ret)
kfifo_free(&buf->kf);
ret = __iio_allocate_kfifo(buf, buf->buffer.bytes_per_datum,
buf->buffer.length);
- buf->update_needed = false;
+ if (ret >= 0)
+ buf->update_needed = false;
} else {
kfifo_reset_out(&buf->kf);
}
static const struct iio_chan_spec prox_channels[] = {
{
.type = IIO_PROXIMITY,
- .modified = 1,
- .channel2 = IIO_NO_MOD,
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
BIT(IIO_CHAN_INFO_SCALE) |
struct iio_dev *indio_dev;
struct prox_state *prox_state;
struct hid_sensor_hub_device *hsdev = pdev->dev.platform_data;
- struct iio_chan_spec *channels;
indio_dev = devm_iio_device_alloc(&pdev->dev,
sizeof(struct prox_state));
return ret;
}
- channels = kmemdup(prox_channels, sizeof(prox_channels), GFP_KERNEL);
- if (!channels) {
+ indio_dev->channels = kmemdup(prox_channels, sizeof(prox_channels),
+ GFP_KERNEL);
+ if (!indio_dev->channels) {
dev_err(&pdev->dev, "failed to duplicate channels\n");
return -ENOMEM;
}
- ret = prox_parse_report(pdev, hsdev, channels,
+ ret = prox_parse_report(pdev, hsdev,
+ (struct iio_chan_spec *)indio_dev->channels,
HID_USAGE_SENSOR_PROX, prox_state);
if (ret) {
dev_err(&pdev->dev, "failed to setup attributes\n");
goto error_free_dev_mem;
}
- indio_dev->channels = channels;
indio_dev->num_channels =
ARRAY_SIZE(prox_channels);
indio_dev->dev.parent = &pdev->dev;
indio_dev->modes = INDIO_DIRECT_MODE;
indio_dev->info = &magn_info;
+ mutex_init(&mdata->tb.buf_lock);
st_sensors_power_enable(indio_dev);
var2 = (((((adc_temp >> 4) - ((s32)le16_to_cpu(buf[T1]))) *
((adc_temp >> 4) - ((s32)le16_to_cpu(buf[T1])))) >> 12) *
((s32)(s16)le16_to_cpu(buf[T3]))) >> 14;
+ data->t_fine = var1 + var2;
return (data->t_fine * 5 + 128) >> 8;
}
static const struct iio_chan_spec press_channels[] = {
{
.type = IIO_PRESSURE,
- .modified = 1,
- .channel2 = IIO_NO_MOD,
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
BIT(IIO_CHAN_INFO_SCALE) |
indio_dev->modes = INDIO_DIRECT_MODE;
indio_dev->info = &press_info;
+ mutex_init(&press_data->tb.buf_lock);
st_sensors_power_enable(indio_dev);
} sgid_addr, dgid_addr;
- ret = rdma_gid2ip(&sgid_addr._sockaddr, sgid);
- if (ret)
- return ret;
-
- ret = rdma_gid2ip(&dgid_addr._sockaddr, dgid);
- if (ret)
- return ret;
+ rdma_gid2ip(&sgid_addr._sockaddr, sgid);
+ rdma_gid2ip(&dgid_addr._sockaddr, dgid);
memset(&dev_addr, 0, sizeof(dev_addr));
struct sockaddr_in6 _sockaddr_in6;
} gid_addr;
- ret = rdma_gid2ip(&gid_addr._sockaddr, sgid);
+ rdma_gid2ip(&gid_addr._sockaddr, sgid);
- if (ret)
- return ret;
memset(&dev_addr, 0, sizeof(dev_addr));
ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id);
if (ret)
return cm_id_priv;
}
-static void cm_mask_copy(u8 *dst, u8 *src, u8 *mask)
+static void cm_mask_copy(u32 *dst, const u32 *src, const u32 *mask)
{
int i;
- for (i = 0; i < IB_CM_COMPARE_SIZE / sizeof(unsigned long); i++)
- ((unsigned long *) dst)[i] = ((unsigned long *) src)[i] &
- ((unsigned long *) mask)[i];
+ for (i = 0; i < IB_CM_COMPARE_SIZE; i++)
+ dst[i] = src[i] & mask[i];
}
static int cm_compare_data(struct ib_cm_compare_data *src_data,
struct ib_cm_compare_data *dst_data)
{
- u8 src[IB_CM_COMPARE_SIZE];
- u8 dst[IB_CM_COMPARE_SIZE];
+ u32 src[IB_CM_COMPARE_SIZE];
+ u32 dst[IB_CM_COMPARE_SIZE];
if (!src_data || !dst_data)
return 0;
cm_mask_copy(src, src_data->data, dst_data->mask);
cm_mask_copy(dst, dst_data->data, src_data->mask);
- return memcmp(src, dst, IB_CM_COMPARE_SIZE);
+ return memcmp(src, dst, sizeof(src));
}
-static int cm_compare_private_data(u8 *private_data,
+static int cm_compare_private_data(u32 *private_data,
struct ib_cm_compare_data *dst_data)
{
- u8 src[IB_CM_COMPARE_SIZE];
+ u32 src[IB_CM_COMPARE_SIZE];
if (!dst_data)
return 0;
cm_mask_copy(src, private_data, dst_data->mask);
- return memcmp(src, dst_data->data, IB_CM_COMPARE_SIZE);
+ return memcmp(src, dst_data->data, sizeof(src));
}
/*
static struct cm_id_private * cm_find_listen(struct ib_device *device,
__be64 service_id,
- u8 *private_data)
+ u32 *private_data)
{
struct rb_node *node = cm.listen_service_table.rb_node;
struct cm_id_private *cm_id_priv;
cm_reject_sidr_req(cm_id_priv, IB_SIDR_REJECT);
break;
case IB_CM_REQ_SENT:
+ case IB_CM_MRA_REQ_RCVD:
ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
spin_unlock_irq(&cm_id_priv->lock);
ib_send_cm_rej(cm_id, IB_CM_REJ_TIMEOUT,
NULL, 0, NULL, 0);
}
break;
- case IB_CM_MRA_REQ_RCVD:
case IB_CM_REP_SENT:
case IB_CM_MRA_REP_RCVD:
ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
cm_mask_copy(cm_id_priv->compare_data->data,
compare_data->data, compare_data->mask);
memcpy(cm_id_priv->compare_data->mask, compare_data->mask,
- IB_CM_COMPARE_SIZE);
+ sizeof(compare_data->mask));
}
cm_id->state = IB_CM_LISTEN;
/* local ACK timeout:5, rsvd:3 */
u8 alt_offset139;
- u8 private_data[IB_CM_REQ_PRIVATE_DATA_SIZE];
+ u32 private_data[IB_CM_REQ_PRIVATE_DATA_SIZE / sizeof(u32)];
} __attribute__ ((packed));
__be16 rsvd;
__be64 service_id;
- u8 private_data[IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE];
+ u32 private_data[IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE / sizeof(u32)];
} __attribute__ ((packed));
struct cm_sidr_rep_msg {
listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr;
ib = (struct sockaddr_ib *) &id->route.addr.src_addr;
ib->sib_family = listen_ib->sib_family;
- ib->sib_pkey = path->pkey;
- ib->sib_flowinfo = path->flow_label;
- memcpy(&ib->sib_addr, &path->sgid, 16);
+ if (path) {
+ ib->sib_pkey = path->pkey;
+ ib->sib_flowinfo = path->flow_label;
+ memcpy(&ib->sib_addr, &path->sgid, 16);
+ } else {
+ ib->sib_pkey = listen_ib->sib_pkey;
+ ib->sib_flowinfo = listen_ib->sib_flowinfo;
+ ib->sib_addr = listen_ib->sib_addr;
+ }
ib->sib_sid = listen_ib->sib_sid;
ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL);
ib->sib_scope_id = listen_ib->sib_scope_id;
- ib = (struct sockaddr_ib *) &id->route.addr.dst_addr;
- ib->sib_family = listen_ib->sib_family;
- ib->sib_pkey = path->pkey;
- ib->sib_flowinfo = path->flow_label;
- memcpy(&ib->sib_addr, &path->dgid, 16);
+ if (path) {
+ ib = (struct sockaddr_ib *) &id->route.addr.dst_addr;
+ ib->sib_family = listen_ib->sib_family;
+ ib->sib_pkey = path->pkey;
+ ib->sib_flowinfo = path->flow_label;
+ memcpy(&ib->sib_addr, &path->dgid, 16);
+ }
+}
+
+static __be16 ss_get_port(const struct sockaddr_storage *ss)
+{
+ if (ss->ss_family == AF_INET)
+ return ((struct sockaddr_in *)ss)->sin_port;
+ else if (ss->ss_family == AF_INET6)
+ return ((struct sockaddr_in6 *)ss)->sin6_port;
+ BUG();
}
static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id,
struct cma_hdr *hdr)
{
- struct sockaddr_in *listen4, *ip4;
+ struct sockaddr_in *ip4;
- listen4 = (struct sockaddr_in *) &listen_id->route.addr.src_addr;
ip4 = (struct sockaddr_in *) &id->route.addr.src_addr;
- ip4->sin_family = listen4->sin_family;
+ ip4->sin_family = AF_INET;
ip4->sin_addr.s_addr = hdr->dst_addr.ip4.addr;
- ip4->sin_port = listen4->sin_port;
+ ip4->sin_port = ss_get_port(&listen_id->route.addr.src_addr);
ip4 = (struct sockaddr_in *) &id->route.addr.dst_addr;
- ip4->sin_family = listen4->sin_family;
+ ip4->sin_family = AF_INET;
ip4->sin_addr.s_addr = hdr->src_addr.ip4.addr;
ip4->sin_port = hdr->port;
}
static void cma_save_ip6_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id,
struct cma_hdr *hdr)
{
- struct sockaddr_in6 *listen6, *ip6;
+ struct sockaddr_in6 *ip6;
- listen6 = (struct sockaddr_in6 *) &listen_id->route.addr.src_addr;
ip6 = (struct sockaddr_in6 *) &id->route.addr.src_addr;
- ip6->sin6_family = listen6->sin6_family;
+ ip6->sin6_family = AF_INET6;
ip6->sin6_addr = hdr->dst_addr.ip6;
- ip6->sin6_port = listen6->sin6_port;
+ ip6->sin6_port = ss_get_port(&listen_id->route.addr.src_addr);
ip6 = (struct sockaddr_in6 *) &id->route.addr.dst_addr;
- ip6->sin6_family = listen6->sin6_family;
+ ip6->sin6_family = AF_INET6;
ip6->sin6_addr = hdr->src_addr.ip6;
ip6->sin6_port = hdr->port;
}
{
struct cma_hdr *hdr;
- if ((listen_id->route.addr.src_addr.ss_family == AF_IB) &&
- (ib_event->event == IB_CM_REQ_RECEIVED)) {
- cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path);
+ if (listen_id->route.addr.src_addr.ss_family == AF_IB) {
+ if (ib_event->event == IB_CM_REQ_RECEIVED)
+ cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path);
+ else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED)
+ cma_save_ib_info(id, listen_id, NULL);
return 0;
}
#include "iwpm_util.h"
-static const char iwpm_ulib_name[] = "iWarpPortMapperUser";
+static const char iwpm_ulib_name[IWPM_ULIBNAME_SIZE] = "iWarpPortMapperUser";
static int iwpm_ulib_version = 3;
static int iwpm_user_pid = IWPM_PID_UNDEFINED;
static atomic_t echo_nlmsg_seq;
}
EXPORT_SYMBOL(iwpm_add_mapping_cb);
-/* netlink attribute policy for the response to add and query mapping request */
+/* netlink attribute policy for the response to add and query mapping request
+ * and response with remote address info */
static const struct nla_policy resp_query_policy[IWPM_NLA_RQUERY_MAPPING_MAX] = {
[IWPM_NLA_QUERY_MAPPING_SEQ] = { .type = NLA_U32 },
[IWPM_NLA_QUERY_LOCAL_ADDR] = { .len = sizeof(struct sockaddr_storage) },
}
EXPORT_SYMBOL(iwpm_add_and_query_mapping_cb);
+/*
+ * iwpm_remote_info_cb - Process a port mapper message, containing
+ * the remote connecting peer address info
+ */
+int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct nlattr *nltb[IWPM_NLA_RQUERY_MAPPING_MAX];
+ struct sockaddr_storage *local_sockaddr, *remote_sockaddr;
+ struct sockaddr_storage *mapped_loc_sockaddr, *mapped_rem_sockaddr;
+ struct iwpm_remote_info *rem_info;
+ const char *msg_type;
+ u8 nl_client;
+ int ret = -EINVAL;
+
+ msg_type = "Remote Mapping info";
+ if (iwpm_parse_nlmsg(cb, IWPM_NLA_RQUERY_MAPPING_MAX,
+ resp_query_policy, nltb, msg_type))
+ return ret;
+
+ nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type);
+ if (!iwpm_valid_client(nl_client)) {
+ pr_info("%s: Invalid port mapper client = %d\n",
+ __func__, nl_client);
+ return ret;
+ }
+ atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+
+ local_sockaddr = (struct sockaddr_storage *)
+ nla_data(nltb[IWPM_NLA_QUERY_LOCAL_ADDR]);
+ remote_sockaddr = (struct sockaddr_storage *)
+ nla_data(nltb[IWPM_NLA_QUERY_REMOTE_ADDR]);
+ mapped_loc_sockaddr = (struct sockaddr_storage *)
+ nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]);
+ mapped_rem_sockaddr = (struct sockaddr_storage *)
+ nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_REM_ADDR]);
+
+ if (mapped_loc_sockaddr->ss_family != local_sockaddr->ss_family ||
+ mapped_rem_sockaddr->ss_family != remote_sockaddr->ss_family) {
+ pr_info("%s: Sockaddr family doesn't match the requested one\n",
+ __func__);
+ return ret;
+ }
+ rem_info = kzalloc(sizeof(struct iwpm_remote_info), GFP_ATOMIC);
+ if (!rem_info) {
+ pr_err("%s: Unable to allocate a remote info\n", __func__);
+ ret = -ENOMEM;
+ return ret;
+ }
+ memcpy(&rem_info->mapped_loc_sockaddr, mapped_loc_sockaddr,
+ sizeof(struct sockaddr_storage));
+ memcpy(&rem_info->remote_sockaddr, remote_sockaddr,
+ sizeof(struct sockaddr_storage));
+ memcpy(&rem_info->mapped_rem_sockaddr, mapped_rem_sockaddr,
+ sizeof(struct sockaddr_storage));
+ rem_info->nl_client = nl_client;
+
+ iwpm_add_remote_info(rem_info);
+
+ iwpm_print_sockaddr(local_sockaddr,
+ "remote_info: Local sockaddr:");
+ iwpm_print_sockaddr(mapped_loc_sockaddr,
+ "remote_info: Mapped local sockaddr:");
+ iwpm_print_sockaddr(remote_sockaddr,
+ "remote_info: Remote sockaddr:");
+ iwpm_print_sockaddr(mapped_rem_sockaddr,
+ "remote_info: Mapped remote sockaddr:");
+ return ret;
+}
+EXPORT_SYMBOL(iwpm_remote_info_cb);
+
/* netlink attribute policy for the received request for mapping info */
static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = {
[IWPM_NLA_MAPINFO_ULIB_NAME] = { .type = NLA_STRING,
#include "iwpm_util.h"
-#define IWPM_HASH_BUCKET_SIZE 512
-#define IWPM_HASH_BUCKET_MASK (IWPM_HASH_BUCKET_SIZE - 1)
+#define IWPM_MAPINFO_HASH_SIZE 512
+#define IWPM_MAPINFO_HASH_MASK (IWPM_MAPINFO_HASH_SIZE - 1)
+#define IWPM_REMINFO_HASH_SIZE 64
+#define IWPM_REMINFO_HASH_MASK (IWPM_REMINFO_HASH_SIZE - 1)
static LIST_HEAD(iwpm_nlmsg_req_list);
static DEFINE_SPINLOCK(iwpm_nlmsg_req_lock);
static struct hlist_head *iwpm_hash_bucket;
static DEFINE_SPINLOCK(iwpm_mapinfo_lock);
+static struct hlist_head *iwpm_reminfo_bucket;
+static DEFINE_SPINLOCK(iwpm_reminfo_lock);
+
static DEFINE_MUTEX(iwpm_admin_lock);
static struct iwpm_admin_data iwpm_admin;
int iwpm_init(u8 nl_client)
{
+ int ret = 0;
if (iwpm_valid_client(nl_client))
return -EINVAL;
mutex_lock(&iwpm_admin_lock);
if (atomic_read(&iwpm_admin.refcount) == 0) {
- iwpm_hash_bucket = kzalloc(IWPM_HASH_BUCKET_SIZE *
+ iwpm_hash_bucket = kzalloc(IWPM_MAPINFO_HASH_SIZE *
sizeof(struct hlist_head), GFP_KERNEL);
if (!iwpm_hash_bucket) {
- mutex_unlock(&iwpm_admin_lock);
+ ret = -ENOMEM;
pr_err("%s Unable to create mapinfo hash table\n", __func__);
- return -ENOMEM;
+ goto init_exit;
+ }
+ iwpm_reminfo_bucket = kzalloc(IWPM_REMINFO_HASH_SIZE *
+ sizeof(struct hlist_head), GFP_KERNEL);
+ if (!iwpm_reminfo_bucket) {
+ kfree(iwpm_hash_bucket);
+ ret = -ENOMEM;
+ pr_err("%s Unable to create reminfo hash table\n", __func__);
+ goto init_exit;
}
}
atomic_inc(&iwpm_admin.refcount);
+init_exit:
mutex_unlock(&iwpm_admin_lock);
- iwpm_set_valid(nl_client, 1);
- return 0;
+ if (!ret) {
+ iwpm_set_valid(nl_client, 1);
+ pr_debug("%s: Mapinfo and reminfo tables are created\n",
+ __func__);
+ }
+ return ret;
}
EXPORT_SYMBOL(iwpm_init);
static void free_hash_bucket(void);
+static void free_reminfo_bucket(void);
int iwpm_exit(u8 nl_client)
{
}
if (atomic_dec_and_test(&iwpm_admin.refcount)) {
free_hash_bucket();
- pr_debug("%s: Mapinfo hash table is destroyed\n", __func__);
+ free_reminfo_bucket();
+ pr_debug("%s: Resources are destroyed\n", __func__);
}
mutex_unlock(&iwpm_admin_lock);
iwpm_set_valid(nl_client, 0);
}
EXPORT_SYMBOL(iwpm_exit);
-static struct hlist_head *get_hash_bucket_head(struct sockaddr_storage *,
+static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage *,
struct sockaddr_storage *);
int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
struct hlist_head *hash_bucket_head;
struct iwpm_mapping_info *map_info;
unsigned long flags;
+ int ret = -EINVAL;
if (!iwpm_valid_client(nl_client))
- return -EINVAL;
+ return ret;
map_info = kzalloc(sizeof(struct iwpm_mapping_info), GFP_KERNEL);
if (!map_info) {
pr_err("%s: Unable to allocate a mapping info\n", __func__);
spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
if (iwpm_hash_bucket) {
- hash_bucket_head = get_hash_bucket_head(
+ hash_bucket_head = get_mapinfo_hash_bucket(
&map_info->local_sockaddr,
&map_info->mapped_sockaddr);
- hlist_add_head(&map_info->hlist_node, hash_bucket_head);
+ if (hash_bucket_head) {
+ hlist_add_head(&map_info->hlist_node, hash_bucket_head);
+ ret = 0;
+ }
}
spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
- return 0;
+ return ret;
}
EXPORT_SYMBOL(iwpm_create_mapinfo);
spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
if (iwpm_hash_bucket) {
- hash_bucket_head = get_hash_bucket_head(
+ hash_bucket_head = get_mapinfo_hash_bucket(
local_sockaddr,
mapped_local_addr);
+ if (!hash_bucket_head)
+ goto remove_mapinfo_exit;
+
hlist_for_each_entry_safe(map_info, tmp_hlist_node,
hash_bucket_head, hlist_node) {
}
}
}
+remove_mapinfo_exit:
spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
return ret;
}
/* remove all the mapinfo data from the list */
spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
- for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+ for (i = 0; i < IWPM_MAPINFO_HASH_SIZE; i++) {
hlist_for_each_entry_safe(map_info, tmp_hlist_node,
&iwpm_hash_bucket[i], hlist_node) {
spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
}
+static void free_reminfo_bucket(void)
+{
+ struct hlist_node *tmp_hlist_node;
+ struct iwpm_remote_info *rem_info;
+ unsigned long flags;
+ int i;
+
+ /* remove all the remote info from the list */
+ spin_lock_irqsave(&iwpm_reminfo_lock, flags);
+ for (i = 0; i < IWPM_REMINFO_HASH_SIZE; i++) {
+ hlist_for_each_entry_safe(rem_info, tmp_hlist_node,
+ &iwpm_reminfo_bucket[i], hlist_node) {
+
+ hlist_del_init(&rem_info->hlist_node);
+ kfree(rem_info);
+ }
+ }
+ /* free the hash list */
+ kfree(iwpm_reminfo_bucket);
+ iwpm_reminfo_bucket = NULL;
+ spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
+}
+
+static struct hlist_head *get_reminfo_hash_bucket(struct sockaddr_storage *,
+ struct sockaddr_storage *);
+
+void iwpm_add_remote_info(struct iwpm_remote_info *rem_info)
+{
+ struct hlist_head *hash_bucket_head;
+ unsigned long flags;
+
+ spin_lock_irqsave(&iwpm_reminfo_lock, flags);
+ if (iwpm_reminfo_bucket) {
+ hash_bucket_head = get_reminfo_hash_bucket(
+ &rem_info->mapped_loc_sockaddr,
+ &rem_info->mapped_rem_sockaddr);
+ if (hash_bucket_head)
+ hlist_add_head(&rem_info->hlist_node, hash_bucket_head);
+ }
+ spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
+}
+
+int iwpm_get_remote_info(struct sockaddr_storage *mapped_loc_addr,
+ struct sockaddr_storage *mapped_rem_addr,
+ struct sockaddr_storage *remote_addr,
+ u8 nl_client)
+{
+ struct hlist_node *tmp_hlist_node;
+ struct hlist_head *hash_bucket_head;
+ struct iwpm_remote_info *rem_info = NULL;
+ unsigned long flags;
+ int ret = -EINVAL;
+
+ if (!iwpm_valid_client(nl_client)) {
+ pr_info("%s: Invalid client = %d\n", __func__, nl_client);
+ return ret;
+ }
+ spin_lock_irqsave(&iwpm_reminfo_lock, flags);
+ if (iwpm_reminfo_bucket) {
+ hash_bucket_head = get_reminfo_hash_bucket(
+ mapped_loc_addr,
+ mapped_rem_addr);
+ if (!hash_bucket_head)
+ goto get_remote_info_exit;
+ hlist_for_each_entry_safe(rem_info, tmp_hlist_node,
+ hash_bucket_head, hlist_node) {
+
+ if (!iwpm_compare_sockaddr(&rem_info->mapped_loc_sockaddr,
+ mapped_loc_addr) &&
+ !iwpm_compare_sockaddr(&rem_info->mapped_rem_sockaddr,
+ mapped_rem_addr)) {
+
+ memcpy(remote_addr, &rem_info->remote_sockaddr,
+ sizeof(struct sockaddr_storage));
+ iwpm_print_sockaddr(remote_addr,
+ "get_remote_info: Remote sockaddr:");
+
+ hlist_del_init(&rem_info->hlist_node);
+ kfree(rem_info);
+ ret = 0;
+ break;
+ }
+ }
+ }
+get_remote_info_exit:
+ spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
+ return ret;
+}
+EXPORT_SYMBOL(iwpm_get_remote_info);
+
struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
u8 nl_client, gfp_t gfp)
{
return hash;
}
-static struct hlist_head *get_hash_bucket_head(struct sockaddr_storage
- *local_sockaddr,
- struct sockaddr_storage
- *mapped_sockaddr)
+static int get_hash_bucket(struct sockaddr_storage *a_sockaddr,
+ struct sockaddr_storage *b_sockaddr, u32 *hash)
{
- u32 local_hash, mapped_hash, hash;
+ u32 a_hash, b_hash;
- if (local_sockaddr->ss_family == AF_INET) {
- local_hash = iwpm_ipv4_jhash((struct sockaddr_in *) local_sockaddr);
- mapped_hash = iwpm_ipv4_jhash((struct sockaddr_in *) mapped_sockaddr);
+ if (a_sockaddr->ss_family == AF_INET) {
+ a_hash = iwpm_ipv4_jhash((struct sockaddr_in *) a_sockaddr);
+ b_hash = iwpm_ipv4_jhash((struct sockaddr_in *) b_sockaddr);
- } else if (local_sockaddr->ss_family == AF_INET6) {
- local_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) local_sockaddr);
- mapped_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) mapped_sockaddr);
+ } else if (a_sockaddr->ss_family == AF_INET6) {
+ a_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) a_sockaddr);
+ b_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) b_sockaddr);
} else {
pr_err("%s: Invalid sockaddr family\n", __func__);
- return NULL;
+ return -EINVAL;
}
- if (local_hash == mapped_hash) /* if port mapper isn't available */
- hash = local_hash;
+ if (a_hash == b_hash) /* if port mapper isn't available */
+ *hash = a_hash;
else
- hash = jhash_2words(local_hash, mapped_hash, 0);
+ *hash = jhash_2words(a_hash, b_hash, 0);
+ return 0;
+}
+
+static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage
+ *local_sockaddr, struct sockaddr_storage
+ *mapped_sockaddr)
+{
+ u32 hash;
+ int ret;
- return &iwpm_hash_bucket[hash & IWPM_HASH_BUCKET_MASK];
+ ret = get_hash_bucket(local_sockaddr, mapped_sockaddr, &hash);
+ if (ret)
+ return NULL;
+ return &iwpm_hash_bucket[hash & IWPM_MAPINFO_HASH_MASK];
+}
+
+static struct hlist_head *get_reminfo_hash_bucket(struct sockaddr_storage
+ *mapped_loc_sockaddr, struct sockaddr_storage
+ *mapped_rem_sockaddr)
+{
+ u32 hash;
+ int ret;
+
+ ret = get_hash_bucket(mapped_loc_sockaddr, mapped_rem_sockaddr, &hash);
+ if (ret)
+ return NULL;
+ return &iwpm_reminfo_bucket[hash & IWPM_REMINFO_HASH_MASK];
}
static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
}
skb_num++;
spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
- for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+ for (i = 0; i < IWPM_MAPINFO_HASH_SIZE; i++) {
hlist_for_each_entry(map_info, &iwpm_hash_bucket[i],
hlist_node) {
if (map_info->nl_client != nl_client)
spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
if (iwpm_hash_bucket) {
- for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+ for (i = 0; i < IWPM_MAPINFO_HASH_SIZE; i++) {
if (!hlist_empty(&iwpm_hash_bucket[i])) {
full_bucket = 1;
break;
u8 nl_client;
};
+struct iwpm_remote_info {
+ struct hlist_node hlist_node;
+ struct sockaddr_storage remote_sockaddr;
+ struct sockaddr_storage mapped_loc_sockaddr;
+ struct sockaddr_storage mapped_rem_sockaddr;
+ u8 nl_client;
+};
+
struct iwpm_admin_data {
atomic_t refcount;
atomic_t nlmsg_seq;
*/
int iwpm_get_nlmsg_seq(void);
+/**
+ * iwpm_add_reminfo - Add remote address info of the connecting peer
+ * to the remote info hash table
+ * @reminfo: The remote info to be added
+ */
+void iwpm_add_remote_info(struct iwpm_remote_info *reminfo);
+
/**
* iwpm_valid_client - Check if the port mapper client is valid
* @nl_client: The index of the netlink client
int remove_existing_mapping = 0;
int ret = 0;
- mutex_lock(&umem->odp_data->umem_mutex);
/*
* Note: we avoid writing if seq is different from the initial seq, to
* handle case of a racing notifier. This check also allows us to bail
}
out:
- mutex_unlock(&umem->odp_data->umem_mutex);
-
/* On Demand Paging - avoid pinning the page */
if (umem->context->invalidate_range || !stored_page)
put_page(page);
bcnt -= min_t(size_t, npages << PAGE_SHIFT, bcnt);
user_virt += npages << PAGE_SHIFT;
+ mutex_lock(&umem->odp_data->umem_mutex);
for (j = 0; j < npages; ++j) {
ret = ib_umem_odp_map_dma_single_page(
umem, k, base_virt_addr, local_page_list[j],
break;
k++;
}
+ mutex_unlock(&umem->odp_data->umem_mutex);
if (ret < 0) {
/* Release left over pages when handling errors. */
* faults from completion. We might be racing with other
* invalidations, so we must make sure we free each page only
* once. */
+ mutex_lock(&umem->odp_data->umem_mutex);
for (addr = virt; addr < bound; addr += (u64)umem->page_size) {
idx = (addr - ib_umem_start(umem)) / PAGE_SIZE;
- mutex_lock(&umem->odp_data->umem_mutex);
if (umem->odp_data->page_list[idx]) {
struct page *page = umem->odp_data->page_list[idx];
- struct page *head_page = compound_head(page);
dma_addr_t dma = umem->odp_data->dma_list[idx];
dma_addr_t dma_addr = dma & ODP_DMA_ADDR_MASK;
ib_dma_unmap_page(dev, dma_addr, PAGE_SIZE,
DMA_BIDIRECTIONAL);
- if (dma & ODP_WRITE_ALLOWED_BIT)
+ if (dma & ODP_WRITE_ALLOWED_BIT) {
+ struct page *head_page = compound_head(page);
/*
* set_page_dirty prefers being called with
* the page lock. However, MMU notifiers are
* be removed.
*/
set_page_dirty(head_page);
+ }
/* on demand pinning support */
if (!umem->context->invalidate_range)
put_page(page);
umem->odp_data->page_list[idx] = NULL;
umem->odp_data->dma_list[idx] = 0;
}
- mutex_unlock(&umem->odp_data->umem_mutex);
}
+ mutex_unlock(&umem->odp_data->umem_mutex);
}
EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);
sizeof(ep->com.mapped_remote_addr));
}
+static int get_remote_addr(struct c4iw_ep *parent_ep, struct c4iw_ep *child_ep)
+{
+ int ret;
+
+ print_addr(&parent_ep->com, __func__, "get_remote_addr parent_ep ");
+ print_addr(&child_ep->com, __func__, "get_remote_addr child_ep ");
+
+ ret = iwpm_get_remote_info(&parent_ep->com.mapped_local_addr,
+ &child_ep->com.mapped_remote_addr,
+ &child_ep->com.remote_addr, RDMA_NL_C4IW);
+ if (ret)
+ PDBG("Unable to find remote peer addr info - err %d\n", ret);
+
+ return ret;
+}
+
static void best_mtu(const unsigned short *mtus, unsigned short mtu,
unsigned int *idx, int use_ts, int ipv6)
{
if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
opt2 |= T5_OPT_2_VALID_F;
opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
- opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+ opt2 |= T5_ISS_F;
}
t4_set_arp_err_handler(skb, ep, act_open_req_arp_failure);
status, status2errno(status));
if (is_neg_adv(status)) {
- dev_warn(&dev->rdev.lldi.pdev->dev,
- "Connection problems for atid %u status %u (%s)\n",
- atid, status, neg_adv_str(status));
+ PDBG("%s Connection problems for atid %u status %u (%s)\n",
+ __func__, atid, status, neg_adv_str(status));
+ ep->stats.connect_neg_adv++;
+ mutex_lock(&dev->rdev.stats.lock);
+ dev->rdev.stats.neg_adv++;
+ mutex_unlock(&dev->rdev.stats.lock);
return 0;
}
u32 isn = (prandom_u32() & ~7UL) - 1;
opt2 |= T5_OPT_2_VALID_F;
opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
- opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+ opt2 |= T5_ISS_F;
rpl5 = (void *)rpl;
memset(&rpl5->iss, 0, roundup(sizeof(*rpl5)-sizeof(*rpl), 16));
if (peer2peer)
state_set(&child_ep->com, CONNECTING);
child_ep->com.dev = dev;
child_ep->com.cm_id = NULL;
+
+ /*
+ * The mapped_local and mapped_remote addresses get setup with
+ * the actual 4-tuple. The local address will be based on the
+ * actual local address of the connection, but on the port number
+ * of the parent listening endpoint. The remote address is
+ * setup based on a query to the IWPM since we don't know what it
+ * originally was before mapping. If no mapping was done, then
+ * mapped_remote == remote, and mapped_local == local.
+ */
if (iptype == 4) {
struct sockaddr_in *sin = (struct sockaddr_in *)
- &child_ep->com.local_addr;
+ &child_ep->com.mapped_local_addr;
+
sin->sin_family = PF_INET;
sin->sin_port = local_port;
sin->sin_addr.s_addr = *(__be32 *)local_ip;
- sin = (struct sockaddr_in *)&child_ep->com.remote_addr;
+
+ sin = (struct sockaddr_in *)&child_ep->com.local_addr;
+ sin->sin_family = PF_INET;
+ sin->sin_port = ((struct sockaddr_in *)
+ &parent_ep->com.local_addr)->sin_port;
+ sin->sin_addr.s_addr = *(__be32 *)local_ip;
+
+ sin = (struct sockaddr_in *)&child_ep->com.mapped_remote_addr;
sin->sin_family = PF_INET;
sin->sin_port = peer_port;
sin->sin_addr.s_addr = *(__be32 *)peer_ip;
} else {
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
- &child_ep->com.local_addr;
+ &child_ep->com.mapped_local_addr;
+
sin6->sin6_family = PF_INET6;
sin6->sin6_port = local_port;
memcpy(sin6->sin6_addr.s6_addr, local_ip, 16);
- sin6 = (struct sockaddr_in6 *)&child_ep->com.remote_addr;
+
+ sin6 = (struct sockaddr_in6 *)&child_ep->com.local_addr;
+ sin6->sin6_family = PF_INET6;
+ sin6->sin6_port = ((struct sockaddr_in6 *)
+ &parent_ep->com.local_addr)->sin6_port;
+ memcpy(sin6->sin6_addr.s6_addr, local_ip, 16);
+
+ sin6 = (struct sockaddr_in6 *)&child_ep->com.mapped_remote_addr;
sin6->sin6_family = PF_INET6;
sin6->sin6_port = peer_port;
memcpy(sin6->sin6_addr.s6_addr, peer_ip, 16);
}
+ memcpy(&child_ep->com.remote_addr, &child_ep->com.mapped_remote_addr,
+ sizeof(child_ep->com.remote_addr));
+ get_remote_addr(parent_ep, child_ep);
+
c4iw_get_ep(&parent_ep->com);
child_ep->parent_ep = parent_ep;
child_ep->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid));
ep = lookup_tid(t, tid);
if (is_neg_adv(req->status)) {
- dev_warn(&dev->rdev.lldi.pdev->dev,
- "Negative advice on abort - tid %u status %d (%s)\n",
- ep->hwtid, req->status, neg_adv_str(req->status));
+ PDBG("%s Negative advice on abort- tid %u status %d (%s)\n",
+ __func__, ep->hwtid, req->status,
+ neg_adv_str(req->status));
+ ep->stats.abort_neg_adv++;
+ mutex_lock(&dev->rdev.stats.lock);
+ dev->rdev.stats.neg_adv++;
+ mutex_unlock(&dev->rdev.stats.lock);
return 0;
}
PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid,
* TP will ignore any value > 0 for MSS index.
*/
req->tcb.opt0 = cpu_to_be64(MSS_IDX_V(0xF));
- req->cookie = (unsigned long)skb;
+ req->cookie = (uintptr_t)skb;
set_wr_txq(req_skb, CPL_PRIORITY_CONTROL, port_id);
ret = cxgb4_ofld_send(dev->rdev.lldi.ports[0], req_skb);
return 0;
}
if (is_neg_adv(req->status)) {
- dev_warn(&dev->rdev.lldi.pdev->dev,
- "Negative advice on abort - tid %u status %d (%s)\n",
- ep->hwtid, req->status, neg_adv_str(req->status));
+ PDBG("%s Negative advice on abort- tid %u status %d (%s)\n",
+ __func__, ep->hwtid, req->status,
+ neg_adv_str(req->status));
+ ep->stats.abort_neg_adv++;
+ dev->rdev.stats.neg_adv++;
kfree_skb(skb);
return 0;
}
FW_RI_RES_WR_NRES_V(1) |
FW_WR_COMPL_F);
res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
- res_wr->cookie = (unsigned long) &wr_wait;
+ res_wr->cookie = (uintptr_t)&wr_wait;
res = res_wr->res;
res->u.cq.restype = FW_RI_RES_TYPE_CQ;
res->u.cq.op = FW_RI_RES_OP_RESET;
FW_RI_RES_WR_NRES_V(1) |
FW_WR_COMPL_F);
res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
- res_wr->cookie = (unsigned long) &wr_wait;
+ res_wr->cookie = (uintptr_t)&wr_wait;
res = res_wr->res;
res->u.cq.restype = FW_RI_RES_TYPE_CQ;
res->u.cq.op = FW_RI_RES_OP_WRITE;
goto err4;
cq->gen = 1;
- cq->gts = rdev->lldi.gts_reg;
cq->rdev = rdev;
if (user) {
- cq->ugts = (u64)pci_resource_start(rdev->lldi.pdev, 2) +
- (cq->cqid << rdev->cqshift);
- cq->ugts &= PAGE_MASK;
+ u32 off = (cq->cqid << rdev->cqshift) & PAGE_MASK;
+
+ cq->ugts = (u64)rdev->bar2_pa + off;
+ } else if (is_t4(rdev->lldi.adapter_type)) {
+ cq->gts = rdev->lldi.gts_reg;
+ cq->qid_mask = -1U;
+ } else {
+ u32 off = ((cq->cqid << rdev->cqshift) & PAGE_MASK) + 12;
+
+ cq->gts = rdev->bar2_kva + off;
+ cq->qid_mask = rdev->qpmask;
}
return 0;
err4:
}
PDBG("%s cqid 0x%0x chp %p size %u memsize %zu, dma_addr 0x%0llx\n",
__func__, chp->cq.cqid, chp, chp->cq.size,
- chp->cq.memsize,
- (unsigned long long) chp->cq.dma_addr);
+ chp->cq.memsize, (unsigned long long) chp->cq.dma_addr);
return &chp->ibcq;
err5:
kfree(mm2);
[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
[RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb},
+ [RDMA_NL_IWPM_REMOTE_INFO] = {.dump = iwpm_remote_info_cb},
[RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb},
[RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}
};
int prev_ts_set = 0;
int idx, end;
-#define ts2ns(ts) div64_ul((ts) * dev->rdev.lldi.cclk_ps, 1000)
+#define ts2ns(ts) div64_u64((ts) * dev->rdev.lldi.cclk_ps, 1000)
idx = atomic_read(&dev->rdev.wr_log_idx) &
(dev->rdev.wr_log_size - 1);
dev->rdev.stats.act_ofld_conn_fails);
seq_printf(seq, "PAS_OFLD_CONN_FAILS: %10llu\n",
dev->rdev.stats.pas_ofld_conn_fails);
+ seq_printf(seq, "NEG_ADV_RCVD: %10llu\n", dev->rdev.stats.neg_adv);
seq_printf(seq, "AVAILABLE IRD: %10u\n", dev->avail_ird);
return 0;
}
cc = snprintf(epd->buf + epd->pos, space,
"ep %p cm_id %p qp %p state %d flags 0x%lx "
"history 0x%lx hwtid %d atid %d "
+ "conn_na %u abort_na %u "
"%pI4:%d/%d <-> %pI4:%d/%d\n",
ep, ep->com.cm_id, ep->com.qp,
(int)ep->com.state, ep->com.flags,
ep->com.history, ep->hwtid, ep->atid,
+ ep->stats.connect_neg_adv,
+ ep->stats.abort_neg_adv,
&lsin->sin_addr, ntohs(lsin->sin_port),
ntohs(mapped_lsin->sin_port),
&rsin->sin_addr, ntohs(rsin->sin_port),
cc = snprintf(epd->buf + epd->pos, space,
"ep %p cm_id %p qp %p state %d flags 0x%lx "
"history 0x%lx hwtid %d atid %d "
+ "conn_na %u abort_na %u "
"%pI6:%d/%d <-> %pI6:%d/%d\n",
ep, ep->com.cm_id, ep->com.qp,
(int)ep->com.state, ep->com.flags,
ep->com.history, ep->hwtid, ep->atid,
+ ep->stats.connect_neg_adv,
+ ep->stats.abort_neg_adv,
&lsin6->sin6_addr, ntohs(lsin6->sin6_port),
ntohs(mapped_lsin6->sin6_port),
&rsin6->sin6_addr, ntohs(rsin6->sin6_port),
c4iw_init_dev_ucontext(rdev, &rdev->uctx);
+ /*
+ * This implementation assumes udb_density == ucq_density! Eventually
+ * we might need to support this but for now fail the open. Also the
+ * cqid and qpid range must match for now.
+ */
+ if (rdev->lldi.udb_density != rdev->lldi.ucq_density) {
+ pr_err(MOD "%s: unsupported udb/ucq densities %u/%u\n",
+ pci_name(rdev->lldi.pdev), rdev->lldi.udb_density,
+ rdev->lldi.ucq_density);
+ err = -EINVAL;
+ goto err1;
+ }
+ if (rdev->lldi.vr->qp.start != rdev->lldi.vr->cq.start ||
+ rdev->lldi.vr->qp.size != rdev->lldi.vr->cq.size) {
+ pr_err(MOD "%s: unsupported qp and cq id ranges "
+ "qp start %u size %u cq start %u size %u\n",
+ pci_name(rdev->lldi.pdev), rdev->lldi.vr->qp.start,
+ rdev->lldi.vr->qp.size, rdev->lldi.vr->cq.size,
+ rdev->lldi.vr->cq.size);
+ err = -EINVAL;
+ goto err1;
+ }
+
/*
* qpshift is the number of bits to shift the qpid left in order
* to get the correct address of the doorbell for that qp.
rdev->lldi.vr->qp.size,
rdev->lldi.vr->cq.start,
rdev->lldi.vr->cq.size);
- PDBG("udb len 0x%x udb base %llx db_reg %p gts_reg %p qpshift %lu "
+ PDBG("udb len 0x%x udb base %p db_reg %p gts_reg %p qpshift %lu "
"qpmask 0x%x cqshift %lu cqmask 0x%x\n",
(unsigned)pci_resource_len(rdev->lldi.pdev, 2),
- (u64)pci_resource_start(rdev->lldi.pdev, 2),
+ (void *)pci_resource_start(rdev->lldi.pdev, 2),
rdev->lldi.db_reg,
rdev->lldi.gts_reg,
rdev->qpshift, rdev->qpmask,
t4_sq_host_wq_pidx(&qp->wq),
t4_sq_wq_size(&qp->wq));
if (ret) {
- pr_err(KERN_ERR MOD "%s: Fatal error - "
+ pr_err(MOD "%s: Fatal error - "
"DB overflow recovery failed - "
"error syncing SQ qid %u\n",
pci_name(ctx->lldi.pdev), qp->wq.sq.qid);
t4_rq_wq_size(&qp->wq));
if (ret) {
- pr_err(KERN_ERR MOD "%s: Fatal error - "
+ pr_err(MOD "%s: Fatal error - "
"DB overflow recovery failed - "
"error syncing RQ qid %u\n",
pci_name(ctx->lldi.pdev), qp->wq.rq.qid);
u64 tcam_full;
u64 act_ofld_conn_fails;
u64 pas_ofld_conn_fails;
+ u64 neg_adv;
};
struct c4iw_hw_queue {
int backlog;
};
+struct c4iw_ep_stats {
+ unsigned connect_neg_adv;
+ unsigned abort_neg_adv;
+};
+
struct c4iw_ep {
struct c4iw_ep_common com;
struct c4iw_ep *parent_ep;
unsigned int retry_count;
int snd_win;
int rcv_win;
+ struct c4iw_ep_stats stats;
};
static inline void print_addr(struct c4iw_ep_common *epc, const char *func,
if (i == (num_wqe-1)) {
req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) |
FW_WR_COMPL_F);
- req->wr.wr_lo = (__force __be64)(unsigned long) &wr_wait;
+ req->wr.wr_lo = (__force __be64)&wr_wait;
} else
req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR));
req->wr.wr_mid = cpu_to_be32(
mhp->attr.zbva = 0;
mhp->attr.va_fbo = 0;
mhp->attr.page_size = 0;
- mhp->attr.len = ~0UL;
+ mhp->attr.len = ~0ULL;
mhp->attr.pbl_size = 0;
ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, php->pdid,
FW_RI_STAG_NSMR, mhp->attr.perms,
- mhp->attr.mw_bind_enable, 0, 0, ~0UL, 0, 0, 0);
+ mhp->attr.mw_bind_enable, 0, 0, ~0ULL, 0, 0, 0);
if (ret)
goto err1;
FW_RI_RES_WR_NRES_V(2) |
FW_WR_COMPL_F);
res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
- res_wr->cookie = (unsigned long) &wr_wait;
+ res_wr->cookie = (uintptr_t)&wr_wait;
res = res_wr->res;
res->u.sqrq.restype = FW_RI_RES_TYPE_SQ;
res->u.sqrq.op = FW_RI_RES_OP_WRITE;
wqe->flowid_len16 = cpu_to_be32(
FW_WR_FLOWID_V(ep->hwtid) |
FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*wqe), 16)));
- wqe->cookie = (unsigned long) &ep->com.wr_wait;
+ wqe->cookie = (uintptr_t)&ep->com.wr_wait;
wqe->u.fini.type = FW_RI_TYPE_FINI;
ret = c4iw_ofld_send(&rhp->rdev, skb);
FW_WR_FLOWID_V(qhp->ep->hwtid) |
FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*wqe), 16)));
- wqe->cookie = (unsigned long) &qhp->ep->com.wr_wait;
+ wqe->cookie = (uintptr_t)&qhp->ep->com.wr_wait;
wqe->u.init.type = FW_RI_TYPE_INIT;
wqe->u.init.mpareqbit_p2ptype =
mm2->len = PAGE_ALIGN(qhp->wq.rq.memsize);
insert_mmap(ucontext, mm2);
mm3->key = uresp.sq_db_gts_key;
- mm3->addr = (__force unsigned long) qhp->wq.sq.udb;
+ mm3->addr = (__force unsigned long)qhp->wq.sq.udb;
mm3->len = PAGE_SIZE;
insert_mmap(ucontext, mm3);
mm4->key = uresp.rq_db_gts_key;
- mm4->addr = (__force unsigned long) qhp->wq.rq.udb;
+ mm4->addr = (__force unsigned long)qhp->wq.rq.udb;
mm4->len = PAGE_SIZE;
insert_mmap(ucontext, mm4);
if (mm5) {
size_t memsize;
__be64 bits_type_ts;
u32 cqid;
+ u32 qid_mask;
int vector;
u16 size; /* including status page */
u16 cidx;
set_bit(CQ_ARMED, &cq->flags);
while (cq->cidx_inc > CIDXINC_M) {
val = SEINTARM_V(0) | CIDXINC_V(CIDXINC_M) | TIMERREG_V(7) |
- INGRESSQID_V(cq->cqid);
+ INGRESSQID_V(cq->cqid & cq->qid_mask);
writel(val, cq->gts);
cq->cidx_inc -= CIDXINC_M;
}
val = SEINTARM_V(se) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(6) |
- INGRESSQID_V(cq->cqid);
+ INGRESSQID_V(cq->cqid & cq->qid_mask);
writel(val, cq->gts);
cq->cidx_inc = 0;
return 0;
u32 val;
val = SEINTARM_V(0) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(7) |
- INGRESSQID_V(cq->cqid);
+ INGRESSQID_V(cq->cqid & cq->qid_mask);
writel(val, cq->gts);
cq->cidx_inc = 0;
}
#define CONG_CNTRL_V(x) ((x) << CONG_CNTRL_S)
#define CONG_CNTRL_G(x) (((x) >> CONG_CNTRL_S) & CONG_CNTRL_M)
-#define CONG_CNTRL_VALID (1 << 18)
+#define T5_ISS_S 18
+#define T5_ISS_V(x) ((x) << T5_ISS_S)
+#define T5_ISS_F T5_ISS_V(1U)
#endif /* _T4FW_RI_API_H_ */
return -EINVAL;
}
- memcpy(&my_gid.raw, gid->raw, sizeof(union ib_gid));
+ memcpy(&my_gid, gid->raw, sizeof(union ib_gid));
subnet_prefix = be64_to_cpu(my_gid.global.subnet_prefix);
interface_id = be64_to_cpu(my_gid.global.interface_id);
return -EINVAL;
}
- memcpy(&my_gid.raw, gid->raw, sizeof(union ib_gid));
+ memcpy(&my_gid, gid->raw, sizeof(union ib_gid));
subnet_prefix = be64_to_cpu(my_gid.global.subnet_prefix);
interface_id = be64_to_cpu(my_gid.global.interface_id);
as IP-over-InfiniBand as well as with userspace applications
(in conjunction with InfiniBand userspace access).
For QLogic PCIe QLE based cards, use the QIB driver instead.
+
+ If you have this hardware you will need to boot with PAT disabled
+ on your x86-64 systems, use the nopat kernel parameter.
#include <linux/bitmap.h>
#include <linux/slab.h>
#include <linux/module.h>
+#ifdef CONFIG_X86_64
+#include <asm/pat.h>
+#endif
#include "ipath_kernel.h"
#include "ipath_verbs.h"
unsigned long long addr;
u32 bar0 = 0, bar1 = 0;
+#ifdef CONFIG_X86_64
+ if (WARN(pat_enabled(),
+ "ipath needs PAT disabled, boot with nopat kernel parameter\n")) {
+ ret = -ENODEV;
+ goto bail;
+ }
+#endif
+
dd = ipath_alloc_devdata(pdev);
if (IS_ERR(dd)) {
ret = PTR_ERR(dd);
dd->ipath_kregbase = __ioremap(addr, len,
(_PAGE_NO_CACHE|_PAGE_WRITETHRU));
#else
+ /* XXX: split this properly to enable on PAT */
dd->ipath_kregbase = ioremap_nocache(addr, len);
#endif
ret = ipath_enable_wc(dd);
- if (ret) {
- ipath_dev_err(dd, "Write combining not enabled "
- "(err %d): performance may be poor\n",
- -ret);
+ if (ret)
ret = 0;
- }
ipath_verify_pioperf(dd);
/* offset in HT config space of slave/primary interface block */
u8 ipath_ht_slave_off;
/* for write combining settings */
- unsigned long ipath_wc_cookie;
- unsigned long ipath_wc_base;
- unsigned long ipath_wc_len;
+ int wc_cookie;
/* ref count for each pkey */
atomic_t ipath_pkeyrefs[4];
/* shadow copy of struct page *'s for exp tid pages */
*/
#include <linux/pci.h>
-#include <asm/mtrr.h>
#include <asm/processor.h>
#include "ipath_kernel.h"
}
if (!ret) {
- int cookie;
- ipath_cdbg(VERBOSE, "Setting mtrr for chip to WC "
- "(addr %llx, len=0x%llx)\n",
- (unsigned long long) pioaddr,
- (unsigned long long) piolen);
- cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 0);
- if (cookie < 0) {
- {
- dev_info(&dd->pcidev->dev,
- "mtrr_add() WC for PIO bufs "
- "failed (%d)\n",
- cookie);
- ret = -EINVAL;
- }
- } else {
- ipath_cdbg(VERBOSE, "Set mtrr for chip to WC, "
- "cookie is %d\n", cookie);
- dd->ipath_wc_cookie = cookie;
- dd->ipath_wc_base = (unsigned long) pioaddr;
- dd->ipath_wc_len = (unsigned long) piolen;
- }
+ dd->wc_cookie = arch_phys_wc_add(pioaddr, piolen);
+ if (dd->wc_cookie < 0) {
+ ipath_dev_err(dd, "Seting mtrr failed on PIO buffers\n");
+ ret = -ENODEV;
+ } else if (dd->wc_cookie == 0)
+ ipath_cdbg(VERBOSE, "Set mtrr for chip to WC not needed\n");
+ else
+ ipath_cdbg(VERBOSE, "Set mtrr for chip to WC\n");
}
return ret;
*/
void ipath_disable_wc(struct ipath_devdata *dd)
{
- if (dd->ipath_wc_cookie) {
- int r;
- ipath_cdbg(VERBOSE, "undoing WCCOMB on pio buffers\n");
- r = mtrr_del(dd->ipath_wc_cookie, dd->ipath_wc_base,
- dd->ipath_wc_len);
- if (r < 0)
- dev_info(&dd->pcidev->dev,
- "mtrr_del(%lx, %lx, %lx) failed: %d\n",
- dd->ipath_wc_cookie, dd->ipath_wc_base,
- dd->ipath_wc_len, r);
- dd->ipath_wc_cookie = 0; /* even on failure */
- }
+ arch_phys_wc_del(dd->wc_cookie);
}
MLX4_CMD_TIME_CLASS_B,
MLX4_CMD_WRAPPED);
if (err)
- pr_warn(KERN_WARNING
- "set port %d command failed\n", gw->port);
+ pr_warn("set port %d command failed\n", gw->port);
}
mlx4_free_cmd_mailbox(dev, mailbox);
if (ah->ah_flags & IB_AH_GRH) {
if (ah->grh.sgid_index >= gen->port[port - 1].gid_table_len) {
- pr_err(KERN_ERR "sgid_index (%u) too large. max is %d\n",
+ pr_err("sgid_index (%u) too large. max is %d\n",
ah->grh.sgid_index, gen->port[port - 1].gid_table_len);
return -EINVAL;
}
[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
+ [RDMA_NL_IWPM_REMOTE_INFO] = {.dump = iwpm_remote_info_cb},
[RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb},
[RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb},
[RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}
memcpy(pm_msg->if_name, nesvnic->netdev->name, IWPM_IFNAME_SIZE);
}
+static void record_sockaddr_info(struct sockaddr_storage *addr_info,
+ nes_addr_t *ip_addr, u16 *port_num)
+{
+ struct sockaddr_in *in_addr = (struct sockaddr_in *)addr_info;
+
+ if (in_addr->sin_family == AF_INET) {
+ *ip_addr = ntohl(in_addr->sin_addr.s_addr);
+ *port_num = ntohs(in_addr->sin_port);
+ }
+}
+
/*
* nes_record_pm_msg - Save the received mapping info
*/
static void nes_record_pm_msg(struct nes_cm_info *cm_info,
struct iwpm_sa_data *pm_msg)
{
- struct sockaddr_in *mapped_loc_addr =
- (struct sockaddr_in *)&pm_msg->mapped_loc_addr;
- struct sockaddr_in *mapped_rem_addr =
- (struct sockaddr_in *)&pm_msg->mapped_rem_addr;
-
- if (mapped_loc_addr->sin_family == AF_INET) {
- cm_info->mapped_loc_addr =
- ntohl(mapped_loc_addr->sin_addr.s_addr);
- cm_info->mapped_loc_port = ntohs(mapped_loc_addr->sin_port);
- }
- if (mapped_rem_addr->sin_family == AF_INET) {
- cm_info->mapped_rem_addr =
- ntohl(mapped_rem_addr->sin_addr.s_addr);
- cm_info->mapped_rem_port = ntohs(mapped_rem_addr->sin_port);
- }
+ record_sockaddr_info(&pm_msg->mapped_loc_addr,
+ &cm_info->mapped_loc_addr, &cm_info->mapped_loc_port);
+
+ record_sockaddr_info(&pm_msg->mapped_rem_addr,
+ &cm_info->mapped_rem_addr, &cm_info->mapped_rem_port);
+}
+
+/*
+ * nes_get_reminfo - Get the address info of the remote connecting peer
+ */
+static int nes_get_remote_addr(struct nes_cm_node *cm_node)
+{
+ struct sockaddr_storage mapped_loc_addr, mapped_rem_addr;
+ struct sockaddr_storage remote_addr;
+ int ret;
+
+ nes_create_sockaddr(htonl(cm_node->mapped_loc_addr),
+ htons(cm_node->mapped_loc_port), &mapped_loc_addr);
+ nes_create_sockaddr(htonl(cm_node->mapped_rem_addr),
+ htons(cm_node->mapped_rem_port), &mapped_rem_addr);
+
+ ret = iwpm_get_remote_info(&mapped_loc_addr, &mapped_rem_addr,
+ &remote_addr, RDMA_NL_NES);
+ if (ret)
+ nes_debug(NES_DBG_CM, "Unable to find remote peer address info\n");
+ else
+ record_sockaddr_info(&remote_addr, &cm_node->rem_addr,
+ &cm_node->rem_port);
+ return ret;
}
/**
return NULL;
/* set our node specific transport info */
- cm_node->loc_addr = cm_info->loc_addr;
+ if (listener) {
+ cm_node->loc_addr = listener->loc_addr;
+ cm_node->loc_port = listener->loc_port;
+ } else {
+ cm_node->loc_addr = cm_info->loc_addr;
+ cm_node->loc_port = cm_info->loc_port;
+ }
cm_node->rem_addr = cm_info->rem_addr;
- cm_node->loc_port = cm_info->loc_port;
cm_node->rem_port = cm_info->rem_port;
cm_node->mapped_loc_addr = cm_info->mapped_loc_addr;
cm_node->state = NES_CM_STATE_ESTABLISHED;
if (datasize) {
cm_node->tcp_cntxt.rcv_nxt = inc_sequence + datasize;
+ nes_get_remote_addr(cm_node);
handle_rcv_mpa(cm_node, skb);
} else { /* rcvd ACK only */
dev_kfree_skb_any(skb);
#include <be_roce.h>
#include "ocrdma_sli.h"
-#define OCRDMA_ROCE_DRV_VERSION "10.4.205.0u"
+#define OCRDMA_ROCE_DRV_VERSION "10.6.0.0"
#define OCRDMA_ROCE_DRV_DESC "Emulex OneConnect RoCE Driver"
#define OCRDMA_NODE_DESC "Emulex OneConnect RoCE HCA"
memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
if (rdma_is_multicast_addr(&in6))
rdma_get_mcast_mac(&in6, mac_addr);
+ else if (rdma_link_local_addr(&in6))
+ rdma_get_ll_mac(&in6, mac_addr);
else
memcpy(mac_addr, ah_attr->dmac, ETH_ALEN);
return 0;
vlan_tag = attr->vlan_id;
if (!vlan_tag || (vlan_tag > 0xFFF))
vlan_tag = dev->pvid;
- if (vlan_tag && (vlan_tag < 0x1000)) {
+ if (vlan_tag || dev->pfc_state) {
+ if (!vlan_tag) {
+ pr_err("ocrdma%d:Using VLAN with PFC is recommended\n",
+ dev->id);
+ pr_err("ocrdma%d:Using VLAN 0 for this connection\n",
+ dev->id);
+ }
eth.eth_type = cpu_to_be16(0x8100);
eth.roce_eth_type = cpu_to_be16(OCRDMA_ROCE_ETH_TYPE);
vlan_tag |= (dev->sl & 0x07) << OCRDMA_VID_PCP_SHIFT;
goto av_conf_err;
}
- if (pd->uctx) {
+ if ((pd->uctx) &&
+ (!rdma_is_multicast_addr((struct in6_addr *)attr->grh.dgid.raw)) &&
+ (!rdma_link_local_addr((struct in6_addr *)attr->grh.dgid.raw))) {
status = rdma_addr_find_dmac_by_grh(&sgid, &attr->grh.dgid,
attr->dmac, &attr->vlan_id);
if (status) {
struct ocrdma_eqe eqe;
struct ocrdma_eqe *ptr;
u16 cq_id;
+ u8 mcode;
int budget = eq->cq_cnt;
do {
ptr = ocrdma_get_eqe(eq);
eqe = *ptr;
ocrdma_le32_to_cpu(&eqe, sizeof(eqe));
+ mcode = (eqe.id_valid & OCRDMA_EQE_MAJOR_CODE_MASK)
+ >> OCRDMA_EQE_MAJOR_CODE_SHIFT;
+ if (mcode == OCRDMA_MAJOR_CODE_SENTINAL)
+ pr_err("EQ full on eqid = 0x%x, eqe = 0x%x\n",
+ eq->q.id, eqe.id_valid);
if ((eqe.id_valid & OCRDMA_EQE_VALID_MASK) == 0)
break;
struct ocrdma_alloc_pd_range_rsp *rsp;
/* Pre allocate the DPP PDs */
- cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_ALLOC_PD_RANGE, sizeof(*cmd));
- if (!cmd)
- return -ENOMEM;
- cmd->pd_count = dev->attr.max_dpp_pds;
- cmd->enable_dpp_rsvd |= OCRDMA_ALLOC_PD_ENABLE_DPP;
- status = ocrdma_mbx_cmd(dev, (struct ocrdma_mqe *)cmd);
- if (status)
- goto mbx_err;
- rsp = (struct ocrdma_alloc_pd_range_rsp *)cmd;
-
- if ((rsp->dpp_page_pdid & OCRDMA_ALLOC_PD_RSP_DPP) && rsp->pd_count) {
- dev->pd_mgr->dpp_page_index = rsp->dpp_page_pdid >>
- OCRDMA_ALLOC_PD_RSP_DPP_PAGE_SHIFT;
- dev->pd_mgr->pd_dpp_start = rsp->dpp_page_pdid &
- OCRDMA_ALLOC_PD_RNG_RSP_START_PDID_MASK;
- dev->pd_mgr->max_dpp_pd = rsp->pd_count;
- pd_bitmap_size = BITS_TO_LONGS(rsp->pd_count) * sizeof(long);
- dev->pd_mgr->pd_dpp_bitmap = kzalloc(pd_bitmap_size,
- GFP_KERNEL);
+ if (dev->attr.max_dpp_pds) {
+ cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_ALLOC_PD_RANGE,
+ sizeof(*cmd));
+ if (!cmd)
+ return -ENOMEM;
+ cmd->pd_count = dev->attr.max_dpp_pds;
+ cmd->enable_dpp_rsvd |= OCRDMA_ALLOC_PD_ENABLE_DPP;
+ status = ocrdma_mbx_cmd(dev, (struct ocrdma_mqe *)cmd);
+ rsp = (struct ocrdma_alloc_pd_range_rsp *)cmd;
+
+ if (!status && (rsp->dpp_page_pdid & OCRDMA_ALLOC_PD_RSP_DPP) &&
+ rsp->pd_count) {
+ dev->pd_mgr->dpp_page_index = rsp->dpp_page_pdid >>
+ OCRDMA_ALLOC_PD_RSP_DPP_PAGE_SHIFT;
+ dev->pd_mgr->pd_dpp_start = rsp->dpp_page_pdid &
+ OCRDMA_ALLOC_PD_RNG_RSP_START_PDID_MASK;
+ dev->pd_mgr->max_dpp_pd = rsp->pd_count;
+ pd_bitmap_size =
+ BITS_TO_LONGS(rsp->pd_count) * sizeof(long);
+ dev->pd_mgr->pd_dpp_bitmap = kzalloc(pd_bitmap_size,
+ GFP_KERNEL);
+ }
+ kfree(cmd);
}
- kfree(cmd);
cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_ALLOC_PD_RANGE, sizeof(*cmd));
if (!cmd)
cmd->pd_count = dev->attr.max_pd - dev->attr.max_dpp_pds;
status = ocrdma_mbx_cmd(dev, (struct ocrdma_mqe *)cmd);
- if (status)
- goto mbx_err;
rsp = (struct ocrdma_alloc_pd_range_rsp *)cmd;
- if (rsp->pd_count) {
+ if (!status && rsp->pd_count) {
dev->pd_mgr->pd_norm_start = rsp->dpp_page_pdid &
OCRDMA_ALLOC_PD_RNG_RSP_START_PDID_MASK;
dev->pd_mgr->max_normal_pd = rsp->pd_count;
dev->pd_mgr->pd_norm_bitmap = kzalloc(pd_bitmap_size,
GFP_KERNEL);
}
+ kfree(cmd);
if (dev->pd_mgr->pd_norm_bitmap || dev->pd_mgr->pd_dpp_bitmap) {
/* Enable PD resource manager */
dev->pd_mgr->pd_prealloc_valid = true;
- } else {
- return -ENOMEM;
+ return 0;
}
-mbx_err:
- kfree(cmd);
return status;
}
struct ocrdma_query_qp *cmd;
struct ocrdma_query_qp_rsp *rsp;
- cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_QUERY_QP, sizeof(*cmd));
+ cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_QUERY_QP, sizeof(*rsp));
if (!cmd)
return status;
cmd->qp_id = qp->id;
int status;
struct ib_ah_attr *ah_attr = &attrs->ah_attr;
union ib_gid sgid, zgid;
- u32 vlan_id;
+ u32 vlan_id = 0xFFFF;
u8 mac_addr[6];
struct ocrdma_dev *dev = get_ocrdma_dev(qp->ibqp.device);
cmd->params.vlan_dmac_b4_to_b5 = mac_addr[4] | (mac_addr[5] << 8);
if (attr_mask & IB_QP_VID) {
vlan_id = attrs->vlan_id;
+ } else if (dev->pfc_state) {
+ vlan_id = 0;
+ pr_err("ocrdma%d:Using VLAN with PFC is recommended\n",
+ dev->id);
+ pr_err("ocrdma%d:Using VLAN 0 for this connection\n",
+ dev->id);
+ }
+
+ if (vlan_id < 0x1000) {
cmd->params.vlan_dmac_b4_to_b5 |=
vlan_id << OCRDMA_QP_PARAMS_VLAN_SHIFT;
cmd->flags |= OCRDMA_QP_PARA_VLAN_EN_VALID;
cmd->params.rnt_rc_sl_fl |=
(dev->sl & 0x07) << OCRDMA_QP_PARAMS_SL_SHIFT;
}
+
return 0;
}
cmd->flags |= OCRDMA_QP_PARA_DST_QPN_VALID;
}
if (attr_mask & IB_QP_PATH_MTU) {
- if (attrs->path_mtu < IB_MTU_256 ||
+ if (attrs->path_mtu < IB_MTU_512 ||
attrs->path_mtu > IB_MTU_4096) {
+ pr_err("ocrdma%d: IB MTU %d is not supported\n",
+ dev->id, ib_mtu_enum_to_int(attrs->path_mtu));
status = -EINVAL;
goto pmtu_err;
}
ocrdma_free_pd_pool(dev);
ocrdma_mbx_delete_ah_tbl(dev);
- /* cleanup the eqs */
- ocrdma_destroy_eqs(dev);
-
/* cleanup the control path */
ocrdma_destroy_mq(dev);
+
+ /* cleanup the eqs */
+ ocrdma_destroy_eqs(dev);
}
struct ocrdma_mqe_hdr hdr;
struct ocrdma_mbx_rsp rsp;
struct ocrdma_qp_params params;
+ u32 dpp_credits_cqid;
+ u32 rbq_id;
};
enum {
enum {
OCRDMA_EQE_VALID_SHIFT = 0,
OCRDMA_EQE_VALID_MASK = BIT(0),
+ OCRDMA_EQE_MAJOR_CODE_MASK = 0x0E,
+ OCRDMA_EQE_MAJOR_CODE_SHIFT = 0x01,
OCRDMA_EQE_FOR_CQE_MASK = 0xFFFE,
OCRDMA_EQE_RESOURCE_ID_SHIFT = 16,
OCRDMA_EQE_RESOURCE_ID_MASK = 0xFFFF <<
OCRDMA_EQE_RESOURCE_ID_SHIFT,
};
+enum major_code {
+ OCRDMA_MAJOR_CODE_COMPLETION = 0x00,
+ OCRDMA_MAJOR_CODE_SENTINAL = 0x01
+};
+
struct ocrdma_eqe {
u32 id_valid;
};
if (!pd)
return ERR_PTR(-ENOMEM);
- if (udata && uctx) {
+ if (udata && uctx && dev->attr.max_dpp_pds) {
pd->dpp_enabled =
ocrdma_get_asic_type(dev) == OCRDMA_ASIC_GEN_SKH_R;
pd->num_dpp_qp =
struct ocrdma_qp *qp;
struct ocrdma_dev *dev;
struct ib_qp_attr attrs;
- int attr_mask = IB_QP_STATE;
+ int attr_mask;
unsigned long flags;
qp = get_ocrdma_qp(ibqp);
dev = get_ocrdma_dev(ibqp->device);
- attrs.qp_state = IB_QPS_ERR;
pd = qp->pd;
/* change the QP state to ERROR */
- _ocrdma_modify_qp(ibqp, &attrs, attr_mask);
-
+ if (qp->state != OCRDMA_QPS_RST) {
+ attrs.qp_state = IB_QPS_ERR;
+ attr_mask = IB_QP_STATE;
+ _ocrdma_modify_qp(ibqp, &attrs, attr_mask);
+ }
/* ensure that CQEs for newly created QP (whose id may be same with
* one which just getting destroyed are same), dont get
* discarded until the old CQEs are discarded.
/* PCI Device ID (here for NodeInfo) */
u16 deviceid;
/* for write combining settings */
- unsigned long wc_cookie;
+ int wc_cookie;
unsigned long wc_base;
unsigned long wc_len;
extern u32 qib_cpulist_count;
extern unsigned long *qib_cpulist;
-extern unsigned qib_wc_pat;
extern unsigned qib_cc_table_size;
int qib_init(struct qib_devdata *, int);
int init_chip_wc_pat(struct qib_devdata *dd, u32);
vma->vm_flags &= ~VM_MAYREAD;
vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND;
- if (qib_wc_pat)
+ /* We used PAT if wc_cookie == 0 */
+ if (!dd->wc_cookie)
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
ret = io_remap_pfn_range(vma, vma->vm_start, phys >> PAGE_SHIFT,
qib_6120_config_ctxts(dd);
qib_set_ctxtcnt(dd);
- if (qib_wc_pat) {
- ret = init_chip_wc_pat(dd, 0);
- if (ret)
- goto bail;
- }
+ ret = init_chip_wc_pat(dd, 0);
+ if (ret)
+ goto bail;
set_6120_baseaddrs(dd); /* set chip access pointers now */
ret = 0;
qib_7220_config_ctxts(dd);
qib_set_ctxtcnt(dd); /* needed for PAT setup */
- if (qib_wc_pat) {
- ret = init_chip_wc_pat(dd, 0);
- if (ret)
- goto bail;
- }
+ ret = init_chip_wc_pat(dd, 0);
+ if (ret)
+ goto bail;
set_7220_baseaddrs(dd); /* set chip access pointers now */
ret = 0;
unsigned features, pidx, sbufcnt;
int ret, mtu;
u32 sbufs, updthresh;
+ resource_size_t vl15off;
/* pport structs are contiguous, allocated after devdata */
ppd = (struct qib_pportdata *)(dd + 1);
qib_7322_config_ctxts(dd);
qib_set_ctxtcnt(dd);
- if (qib_wc_pat) {
- resource_size_t vl15off;
- /*
- * We do not set WC on the VL15 buffers to avoid
- * a rare problem with unaligned writes from
- * interrupt-flushed store buffers, so we need
- * to map those separately here. We can't solve
- * this for the rarely used mtrr case.
- */
- ret = init_chip_wc_pat(dd, 0);
- if (ret)
- goto bail;
+ /*
+ * We do not set WC on the VL15 buffers to avoid
+ * a rare problem with unaligned writes from
+ * interrupt-flushed store buffers, so we need
+ * to map those separately here. We can't solve
+ * this for the rarely used mtrr case.
+ */
+ ret = init_chip_wc_pat(dd, 0);
+ if (ret)
+ goto bail;
- /* vl15 buffers start just after the 4k buffers */
- vl15off = dd->physaddr + (dd->piobufbase >> 32) +
- dd->piobcnt4k * dd->align4k;
- dd->piovl15base = ioremap_nocache(vl15off,
- NUM_VL15_BUFS * dd->align4k);
- if (!dd->piovl15base) {
- ret = -ENOMEM;
- goto bail;
- }
+ /* vl15 buffers start just after the 4k buffers */
+ vl15off = dd->physaddr + (dd->piobufbase >> 32) +
+ dd->piobcnt4k * dd->align4k;
+ dd->piovl15base = ioremap_nocache(vl15off,
+ NUM_VL15_BUFS * dd->align4k);
+ if (!dd->piovl15base) {
+ ret = -ENOMEM;
+ goto bail;
}
+
qib_7322_set_baseaddrs(dd); /* set chip access pointers now */
ret = 0;
unsigned qib_cc_table_size;
module_param_named(cc_table_size, qib_cc_table_size, uint, S_IRUGO);
MODULE_PARM_DESC(cc_table_size, "Congestion control table entries 0 (CCA disabled - default), min = 128, max = 1984");
-/*
- * qib_wc_pat parameter:
- * 0 is WC via MTRR
- * 1 is WC via PAT
- * If PAT initialization fails, code reverts back to MTRR
- */
-unsigned qib_wc_pat = 1; /* default (1) is to use PAT, not MTRR */
-module_param_named(wc_pat, qib_wc_pat, uint, S_IRUGO);
-MODULE_PARM_DESC(wc_pat, "enable write-combining via PAT mechanism");
static void verify_interrupt(unsigned long);
spin_unlock(&dd->pport[pidx].cc_shadow_lock);
}
- if (!qib_wc_pat)
- qib_disable_wc(dd);
+ qib_disable_wc(dd);
if (dd->pioavailregs_dma) {
dma_free_coherent(&dd->pcidev->dev, PAGE_SIZE,
goto bail;
}
- if (!qib_wc_pat) {
- ret = qib_enable_wc(dd);
- if (ret) {
- qib_dev_err(dd,
- "Write combining not enabled (err %d): performance may be poor\n",
- -ret);
- ret = 0;
- }
+ ret = qib_enable_wc(dd);
+ if (ret) {
+ qib_dev_err(dd,
+ "Write combining not enabled (err %d): performance may be poor\n",
+ -ret);
+ ret = 0;
}
qib_verify_pioperf(dd);
}
if (!ret) {
- int cookie;
-
- cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 0);
- if (cookie < 0) {
- {
- qib_devinfo(dd->pcidev,
- "mtrr_add() WC for PIO bufs failed (%d)\n",
- cookie);
- ret = -EINVAL;
- }
- } else {
- dd->wc_cookie = cookie;
- dd->wc_base = (unsigned long) pioaddr;
- dd->wc_len = (unsigned long) piolen;
- }
+ dd->wc_cookie = arch_phys_wc_add(pioaddr, piolen);
+ if (dd->wc_cookie < 0)
+ /* use error from routine */
+ ret = dd->wc_cookie;
}
return ret;
*/
void qib_disable_wc(struct qib_devdata *dd)
{
- if (dd->wc_cookie) {
- int r;
-
- r = mtrr_del(dd->wc_cookie, dd->wc_base,
- dd->wc_len);
- if (r < 0)
- qib_devinfo(dd->pcidev,
- "mtrr_del(%lx, %lx, %lx) failed: %d\n",
- dd->wc_cookie, dd->wc_base,
- dd->wc_len, r);
- dd->wc_cookie = 0; /* even on failure */
- }
+ arch_phys_wc_del(dd->wc_cookie);
}
/**
rx->rx_ring[i].mapping,
GFP_KERNEL)) {
ipoib_warn(priv, "failed to allocate receive buffer %d\n", i);
- ret = -ENOMEM;
- goto err_count;
+ ret = -ENOMEM;
+ goto err_count;
}
ret = ipoib_cm_post_receive_nonsrq(dev, rx, &t->wr, t->sge, i);
if (ret) {
isert_rdma_accept(struct isert_conn *isert_conn);
struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
+static void isert_release_work(struct work_struct *work);
+
static inline bool
isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd)
{
return 0;
err_prot_mr:
- ib_dereg_mr(desc->pi_ctx->prot_mr);
+ ib_dereg_mr(pi_ctx->prot_mr);
err_prot_frpl:
- ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl);
+ ib_free_fast_reg_page_list(pi_ctx->prot_frpl);
err_pi_ctx:
- kfree(desc->pi_ctx);
+ kfree(pi_ctx);
return ret;
}
mutex_init(&isert_conn->mutex);
spin_lock_init(&isert_conn->pool_lock);
INIT_LIST_HEAD(&isert_conn->fr_pool);
+ INIT_WORK(&isert_conn->release_work, isert_release_work);
}
static void
{
struct isert_np *isert_np = cma_id->context;
struct isert_conn *isert_conn;
+ bool terminating = false;
if (isert_np->np_cm_id == cma_id)
return isert_np_cma_handler(cma_id->context, event);
isert_conn = cma_id->qp->qp_context;
mutex_lock(&isert_conn->mutex);
+ terminating = (isert_conn->state == ISER_CONN_TERMINATING);
isert_conn_terminate(isert_conn);
mutex_unlock(&isert_conn->mutex);
isert_info("conn %p completing wait\n", isert_conn);
complete(&isert_conn->wait);
+ if (terminating)
+ goto out;
+
+ mutex_lock(&isert_np->np_accept_mutex);
+ if (!list_empty(&isert_conn->accept_node)) {
+ list_del_init(&isert_conn->accept_node);
+ isert_put_conn(isert_conn);
+ queue_work(isert_release_wq, &isert_conn->release_work);
+ }
+ mutex_unlock(&isert_np->np_accept_mutex);
+
+out:
return 0;
}
page_off = offset % PAGE_SIZE;
send_wr->sg_list = ib_sge;
- send_wr->num_sge = sg_nents;
send_wr->wr_id = (uintptr_t)&isert_cmd->tx_desc;
/*
* Perform mapping of TCM scatterlist memory ib_sge dma_addr.
ib_sge->addr, ib_sge->length, ib_sge->lkey);
page_off = 0;
data_left -= ib_sge->length;
+ if (!data_left)
+ break;
ib_sge++;
isert_dbg("Incrementing ib_sge pointer to %p\n", ib_sge);
}
+ send_wr->num_sge = ++i;
isert_dbg("Set outgoing sg_list: %p num_sg: %u from TCM SGLs\n",
send_wr->sg_list, send_wr->num_sge);
- return sg_nents;
+ return send_wr->num_sge;
}
static int
isert_wait4flush(isert_conn);
isert_wait4logout(isert_conn);
- INIT_WORK(&isert_conn->release_work, isert_release_work);
queue_work(isert_release_wq, &isert_conn->release_work);
}
{
struct isert_conn *isert_conn = conn->context;
+ isert_wait4flush(isert_conn);
isert_put_conn(isert_conn);
}
input_close_device(handle);
}
+static bool joydev_dev_is_absolute_mouse(struct input_dev *dev)
+{
+ DECLARE_BITMAP(jd_scratch, KEY_CNT);
+
+ BUILD_BUG_ON(ABS_CNT > KEY_CNT || EV_CNT > KEY_CNT);
+
+ /*
+ * Virtualization (VMware, etc) and remote management (HP
+ * ILO2) solutions use absolute coordinates for their virtual
+ * pointing devices so that there is one-to-one relationship
+ * between pointer position on the host screen and virtual
+ * guest screen, and so their mice use ABS_X, ABS_Y and 3
+ * primary button events. This clashes with what joydev
+ * considers to be joysticks (a device with at minimum ABS_X
+ * axis).
+ *
+ * Here we are trying to separate absolute mice from
+ * joysticks. A device is, for joystick detection purposes,
+ * considered to be an absolute mouse if the following is
+ * true:
+ *
+ * 1) Event types are exactly EV_ABS, EV_KEY and EV_SYN.
+ * 2) Absolute events are exactly ABS_X and ABS_Y.
+ * 3) Keys are exactly BTN_LEFT, BTN_RIGHT and BTN_MIDDLE.
+ * 4) Device is not on "Amiga" bus.
+ */
+
+ bitmap_zero(jd_scratch, EV_CNT);
+ __set_bit(EV_ABS, jd_scratch);
+ __set_bit(EV_KEY, jd_scratch);
+ __set_bit(EV_SYN, jd_scratch);
+ if (!bitmap_equal(jd_scratch, dev->evbit, EV_CNT))
+ return false;
+
+ bitmap_zero(jd_scratch, ABS_CNT);
+ __set_bit(ABS_X, jd_scratch);
+ __set_bit(ABS_Y, jd_scratch);
+ if (!bitmap_equal(dev->absbit, jd_scratch, ABS_CNT))
+ return false;
+
+ bitmap_zero(jd_scratch, KEY_CNT);
+ __set_bit(BTN_LEFT, jd_scratch);
+ __set_bit(BTN_RIGHT, jd_scratch);
+ __set_bit(BTN_MIDDLE, jd_scratch);
+
+ if (!bitmap_equal(dev->keybit, jd_scratch, KEY_CNT))
+ return false;
+
+ /*
+ * Amiga joystick (amijoy) historically uses left/middle/right
+ * button events.
+ */
+ if (dev->id.bustype == BUS_AMIGA)
+ return false;
+
+ return true;
+}
static bool joydev_match(struct input_handler *handler, struct input_dev *dev)
{
if (test_bit(EV_KEY, dev->evbit) && test_bit(BTN_DIGI, dev->keybit))
return false;
+ /* Avoid absolute mice */
+ if (joydev_dev_is_absolute_mouse(dev))
+ return false;
+
return true;
}
Say Y here if you are running under control of VMware hypervisor
(ESXi, Workstation or Fusion). Also make sure that when you enable
this option, you remove the xf86-input-vmmouse user-space driver
- or upgrade it to at least xf86-input-vmmouse 13.0.1, which doesn't
+ or upgrade it to at least xf86-input-vmmouse 13.1.0, which doesn't
load in the presence of an in-kernel vmmouse driver.
If unsure, say N.
case V7_PACKET_ID_TWO:
mt[1].x &= ~0x000F;
mt[1].y |= 0x000F;
+ /* Detect false-postive touches where x & y report max value */
+ if (mt[1].y == 0x7ff && mt[1].x == 0xff0) {
+ mt[1].x = 0;
+ /* y gets set to 0 at the end of this function */
+ }
break;
case V7_PACKET_ID_MULTI:
right = (packet[1] & 0x02) >> 1;
middle = (packet[1] & 0x04) >> 2;
- /* Divide 2 since trackpoint's speed is too fast */
- input_report_rel(dev2, REL_X, (char)x / 2);
- input_report_rel(dev2, REL_Y, -((char)y / 2));
+ input_report_rel(dev2, REL_X, (char)x);
+ input_report_rel(dev2, REL_Y, -((char)y));
input_report_key(dev2, BTN_LEFT, left);
input_report_key(dev2, BTN_RIGHT, right);
unsigned int x2, unsigned int y2)
{
elantech_set_slot(dev, 0, num_fingers != 0, x1, y1);
- elantech_set_slot(dev, 1, num_fingers == 2, x2, y2);
+ elantech_set_slot(dev, 1, num_fingers >= 2, x2, y2);
}
/*
return true;
/*
- * Some models have a revision higher then 20. Meaning param[2] may
- * be 10 or 20, skip the rates check for these.
+ * Some hw_version >= 4 models have a revision higher then 20. Meaning
+ * that param[2] may be 10 or 20, skip the rates check for these.
*/
- if (param[0] == 0x46 && (param[1] & 0xef) == 0x0f && param[2] < 40)
+ if ((param[0] & 0x0f) >= 0x06 && (param[1] & 0xaf) == 0x0f &&
+ param[2] < 40)
return true;
for (i = 0; i < ARRAY_SIZE(rates); i++)
case 9:
case 10:
case 13:
+ case 14:
etd->hw_version = 4;
break;
default:
{ANY_BOARD_ID, 2961},
1024, 5112, 2024, 4832
},
+ {
+ (const char * const []){"LEN2000", NULL},
+ {ANY_BOARD_ID, ANY_BOARD_ID},
+ 1024, 5113, 2021, 4832
+ },
{
(const char * const []){"LEN2001", NULL},
{ANY_BOARD_ID, ANY_BOARD_ID},
"LEN0045",
"LEN0047",
"LEN0049",
- "LEN2000",
+ "LEN2000", /* S540 */
"LEN2001", /* Edge E431 */
"LEN2002", /* Edge E531 */
"LEN2003",
STMPE_TSC_CTRL_TSC_EN, STMPE_TSC_CTRL_TSC_EN);
/* start polling for touch_det to detect release */
- schedule_delayed_work(&ts->work, HZ / 50);
+ schedule_delayed_work(&ts->work, msecs_to_jiffies(50));
return IRQ_HANDLED;
}
return -ENOMEM;
input = devm_input_allocate_device(&client->dev);
- if (!sx8654)
+ if (!input)
return -ENOMEM;
input->name = "SX8654 I2C Touchscreen";
#include <linux/irq.h>
#include <linux/msi.h>
#include <linux/dma-contiguous.h>
+#include <linux/irqdomain.h>
#include <asm/irq_remapping.h>
#include <asm/io_apic.h>
#include <asm/apic.h>
size = PAGE_ALIGN(size);
dma_mask = dev->coherent_dma_mask;
flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+ flag |= __GFP_ZERO;
page = alloc_pages(flag | __GFP_NOWARN, get_order(size));
if (!page) {
} fields;
};
+struct irq_2_irte {
+ u16 devid; /* Device ID for IRTE table */
+ u16 index; /* Index into IRTE table*/
+};
+
+struct amd_ir_data {
+ struct irq_2_irte irq_2_irte;
+ union irte irte_entry;
+ union {
+ struct msi_msg msi_entry;
+ };
+};
+
+static struct irq_chip amd_ir_chip;
+
#define DTE_IRQ_PHYS_ADDR_MASK (((1ULL << 45)-1) << 6)
#define DTE_IRQ_REMAP_INTCTL (2ULL << 60)
#define DTE_IRQ_TABLE_LEN (8ULL << 1)
return table;
}
-static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
+static int alloc_irq_index(u16 devid, int count)
{
struct irq_remap_table *table;
unsigned long flags;
c = 0;
if (c == count) {
- struct irq_2_irte *irte_info;
-
for (; c != 0; --c)
table->table[index - c + 1] = IRTE_ALLOCATED;
index -= count - 1;
-
- cfg->remapped = 1;
- irte_info = &cfg->irq_2_irte;
- irte_info->devid = devid;
- irte_info->index = index;
-
goto out;
}
}
return index;
}
-static int get_irte(u16 devid, int index, union irte *irte)
-{
- struct irq_remap_table *table;
- unsigned long flags;
-
- table = get_irq_table(devid, false);
- if (!table)
- return -ENOMEM;
-
- spin_lock_irqsave(&table->lock, flags);
- irte->val = table->table[index];
- spin_unlock_irqrestore(&table->lock, flags);
-
- return 0;
-}
-
static int modify_irte(u16 devid, int index, union irte irte)
{
struct irq_remap_table *table;
iommu_completion_wait(iommu);
}
-static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
+static int get_devid(struct irq_alloc_info *info)
{
- struct irq_remap_table *table;
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
- union irte irte;
- int ioapic_id;
- int index;
- int devid;
- int ret;
-
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
-
- irte_info = &cfg->irq_2_irte;
- ioapic_id = mpc_ioapic_id(attr->ioapic);
- devid = get_ioapic_devid(ioapic_id);
-
- if (devid < 0)
- return devid;
-
- table = get_irq_table(devid, true);
- if (table == NULL)
- return -ENOMEM;
-
- index = attr->ioapic_pin;
+ int devid = -1;
- /* Setup IRQ remapping info */
- cfg->remapped = 1;
- irte_info->devid = devid;
- irte_info->index = index;
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_IOAPIC:
+ devid = get_ioapic_devid(info->ioapic_id);
+ break;
+ case X86_IRQ_ALLOC_TYPE_HPET:
+ devid = get_hpet_devid(info->hpet_id);
+ break;
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ devid = get_device_id(&info->msi_dev->dev);
+ break;
+ default:
+ BUG_ON(1);
+ break;
+ }
- /* Setup IRTE for IOMMU */
- irte.val = 0;
- irte.fields.vector = vector;
- irte.fields.int_type = apic->irq_delivery_mode;
- irte.fields.destination = destination;
- irte.fields.dm = apic->irq_dest_mode;
- irte.fields.valid = 1;
-
- ret = modify_irte(devid, index, irte);
- if (ret)
- return ret;
+ return devid;
+}
- /* Setup IOAPIC entry */
- memset(entry, 0, sizeof(*entry));
+static struct irq_domain *get_ir_irq_domain(struct irq_alloc_info *info)
+{
+ struct amd_iommu *iommu;
+ int devid;
- entry->vector = index;
- entry->mask = 0;
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
+ if (!info)
+ return NULL;
- /*
- * Mask level triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
+ devid = get_devid(info);
+ if (devid >= 0) {
+ iommu = amd_iommu_rlookup_table[devid];
+ if (iommu)
+ return iommu->ir_domain;
+ }
- return 0;
+ return NULL;
}
-static int set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
+static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
{
- struct irq_2_irte *irte_info;
- unsigned int dest, irq;
- struct irq_cfg *cfg;
- union irte irte;
- int err;
-
- if (!config_enabled(CONFIG_SMP))
- return -1;
-
- cfg = irqd_cfg(data);
- irq = data->irq;
- irte_info = &cfg->irq_2_irte;
+ struct amd_iommu *iommu;
+ int devid;
- if (!cpumask_intersects(mask, cpu_online_mask))
- return -EINVAL;
+ if (!info)
+ return NULL;
- if (get_irte(irte_info->devid, irte_info->index, &irte))
- return -EBUSY;
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ devid = get_device_id(&info->msi_dev->dev);
+ if (devid >= 0) {
+ iommu = amd_iommu_rlookup_table[devid];
+ if (iommu)
+ return iommu->msi_domain;
+ }
+ break;
+ default:
+ break;
+ }
- if (assign_irq_vector(irq, cfg, mask))
- return -EBUSY;
+ return NULL;
+}
- err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
- if (err) {
- if (assign_irq_vector(irq, cfg, data->affinity))
- pr_err("AMD-Vi: Failed to recover vector for irq %d\n", irq);
- return err;
- }
+struct irq_remap_ops amd_iommu_irq_ops = {
+ .prepare = amd_iommu_prepare,
+ .enable = amd_iommu_enable,
+ .disable = amd_iommu_disable,
+ .reenable = amd_iommu_reenable,
+ .enable_faulting = amd_iommu_enable_faulting,
+ .get_ir_irq_domain = get_ir_irq_domain,
+ .get_irq_domain = get_irq_domain,
+};
- irte.fields.vector = cfg->vector;
- irte.fields.destination = dest;
+static void irq_remapping_prepare_irte(struct amd_ir_data *data,
+ struct irq_cfg *irq_cfg,
+ struct irq_alloc_info *info,
+ int devid, int index, int sub_handle)
+{
+ struct irq_2_irte *irte_info = &data->irq_2_irte;
+ struct msi_msg *msg = &data->msi_entry;
+ union irte *irte = &data->irte_entry;
+ struct IO_APIC_route_entry *entry;
- modify_irte(irte_info->devid, irte_info->index, irte);
+ data->irq_2_irte.devid = devid;
+ data->irq_2_irte.index = index + sub_handle;
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
+ /* Setup IRTE for IOMMU */
+ irte->val = 0;
+ irte->fields.vector = irq_cfg->vector;
+ irte->fields.int_type = apic->irq_delivery_mode;
+ irte->fields.destination = irq_cfg->dest_apicid;
+ irte->fields.dm = apic->irq_dest_mode;
+ irte->fields.valid = 1;
+
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_IOAPIC:
+ /* Setup IOAPIC entry */
+ entry = info->ioapic_entry;
+ info->ioapic_entry = NULL;
+ memset(entry, 0, sizeof(*entry));
+ entry->vector = index;
+ entry->mask = 0;
+ entry->trigger = info->ioapic_trigger;
+ entry->polarity = info->ioapic_polarity;
+ /* Mask level triggered irqs. */
+ if (info->ioapic_trigger)
+ entry->mask = 1;
+ break;
- cpumask_copy(data->affinity, mask);
+ case X86_IRQ_ALLOC_TYPE_HPET:
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ msg->address_hi = MSI_ADDR_BASE_HI;
+ msg->address_lo = MSI_ADDR_BASE_LO;
+ msg->data = irte_info->index;
+ break;
- return 0;
+ default:
+ BUG_ON(1);
+ break;
+ }
}
-static int free_irq(int irq)
+static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- struct irq_2_irte *irte_info;
+ struct irq_alloc_info *info = arg;
+ struct irq_data *irq_data;
+ struct amd_ir_data *data;
struct irq_cfg *cfg;
+ int i, ret, devid;
+ int index = -1;
- cfg = irq_cfg(irq);
- if (!cfg)
+ if (!info)
+ return -EINVAL;
+ if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+ info->type != X86_IRQ_ALLOC_TYPE_MSIX)
return -EINVAL;
- irte_info = &cfg->irq_2_irte;
-
- free_irte(irte_info->devid, irte_info->index);
+ /*
+ * With IRQ remapping enabled, don't need contiguous CPU vectors
+ * to support multiple MSI interrupts.
+ */
+ if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+ info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
- return 0;
-}
+ devid = get_devid(info);
+ if (devid < 0)
+ return -EINVAL;
-static void compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
-{
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
- union irte irte;
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+ if (ret < 0)
+ return ret;
- cfg = irq_cfg(irq);
- if (!cfg)
- return;
+ ret = -ENOMEM;
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out_free_parent;
- irte_info = &cfg->irq_2_irte;
+ if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
+ if (get_irq_table(devid, true))
+ index = info->ioapic_pin;
+ else
+ ret = -ENOMEM;
+ } else {
+ index = alloc_irq_index(devid, nr_irqs);
+ }
+ if (index < 0) {
+ pr_warn("Failed to allocate IRTE\n");
+ kfree(data);
+ goto out_free_parent;
+ }
- irte.val = 0;
- irte.fields.vector = cfg->vector;
- irte.fields.int_type = apic->irq_delivery_mode;
- irte.fields.destination = dest;
- irte.fields.dm = apic->irq_dest_mode;
- irte.fields.valid = 1;
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ cfg = irqd_cfg(irq_data);
+ if (!irq_data || !cfg) {
+ ret = -EINVAL;
+ goto out_free_data;
+ }
- modify_irte(irte_info->devid, irte_info->index, irte);
+ if (i > 0) {
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out_free_data;
+ }
+ irq_data->hwirq = (devid << 16) + i;
+ irq_data->chip_data = data;
+ irq_data->chip = &amd_ir_chip;
+ irq_remapping_prepare_irte(data, cfg, info, devid, index, i);
+ irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+ }
+ return 0;
- msg->address_hi = MSI_ADDR_BASE_HI;
- msg->address_lo = MSI_ADDR_BASE_LO;
- msg->data = irte_info->index;
+out_free_data:
+ for (i--; i >= 0; i--) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ if (irq_data)
+ kfree(irq_data->chip_data);
+ }
+ for (i = 0; i < nr_irqs; i++)
+ free_irte(devid, index + i);
+out_free_parent:
+ irq_domain_free_irqs_common(domain, virq, nr_irqs);
+ return ret;
}
-static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec)
+static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs)
{
- struct irq_cfg *cfg;
- int index;
- u16 devid;
-
- if (!pdev)
- return -EINVAL;
+ struct irq_2_irte *irte_info;
+ struct irq_data *irq_data;
+ struct amd_ir_data *data;
+ int i;
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ if (irq_data && irq_data->chip_data) {
+ data = irq_data->chip_data;
+ irte_info = &data->irq_2_irte;
+ free_irte(irte_info->devid, irte_info->index);
+ kfree(data);
+ }
+ }
+ irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
- devid = get_device_id(&pdev->dev);
- index = alloc_irq_index(cfg, devid, nvec);
+static void irq_remapping_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct amd_ir_data *data = irq_data->chip_data;
+ struct irq_2_irte *irte_info = &data->irq_2_irte;
- return index < 0 ? MAX_IRQS_PER_TABLE : index;
+ modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
}
-static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
- int index, int offset)
+static void irq_remapping_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
{
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
- u16 devid;
+ struct amd_ir_data *data = irq_data->chip_data;
+ struct irq_2_irte *irte_info = &data->irq_2_irte;
+ union irte entry;
- if (!pdev)
- return -EINVAL;
+ entry.val = 0;
+ modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+}
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
+static struct irq_domain_ops amd_ir_domain_ops = {
+ .alloc = irq_remapping_alloc,
+ .free = irq_remapping_free,
+ .activate = irq_remapping_activate,
+ .deactivate = irq_remapping_deactivate,
+};
- if (index >= MAX_IRQS_PER_TABLE)
- return 0;
+static int amd_ir_set_affinity(struct irq_data *data,
+ const struct cpumask *mask, bool force)
+{
+ struct amd_ir_data *ir_data = data->chip_data;
+ struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+ struct irq_cfg *cfg = irqd_cfg(data);
+ struct irq_data *parent = data->parent_data;
+ int ret;
- devid = get_device_id(&pdev->dev);
- irte_info = &cfg->irq_2_irte;
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+ return ret;
- cfg->remapped = 1;
- irte_info->devid = devid;
- irte_info->index = index + offset;
+ /*
+ * Atomically updates the IRTE with the new destination, vector
+ * and flushes the interrupt entry cache.
+ */
+ ir_data->irte_entry.fields.vector = cfg->vector;
+ ir_data->irte_entry.fields.destination = cfg->dest_apicid;
+ modify_irte(irte_info->devid, irte_info->index, ir_data->irte_entry);
- return 0;
+ /*
+ * After this point, all the interrupts will start arriving
+ * at the new destination. So, time to cleanup the previous
+ * vector allocation.
+ */
+ send_cleanup_vector(cfg);
+
+ return IRQ_SET_MASK_OK_DONE;
}
-static int alloc_hpet_msi(unsigned int irq, unsigned int id)
+static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
{
- struct irq_2_irte *irte_info;
- struct irq_cfg *cfg;
- int index, devid;
+ struct amd_ir_data *ir_data = irq_data->chip_data;
- cfg = irq_cfg(irq);
- if (!cfg)
- return -EINVAL;
+ *msg = ir_data->msi_entry;
+}
- irte_info = &cfg->irq_2_irte;
- devid = get_hpet_devid(id);
- if (devid < 0)
- return devid;
+static struct irq_chip amd_ir_chip = {
+ .irq_ack = ir_ack_apic_edge,
+ .irq_set_affinity = amd_ir_set_affinity,
+ .irq_compose_msi_msg = ir_compose_msi_msg,
+};
- index = alloc_irq_index(cfg, devid, 1);
- if (index < 0)
- return index;
+int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+ iommu->ir_domain = irq_domain_add_tree(NULL, &amd_ir_domain_ops, iommu);
+ if (!iommu->ir_domain)
+ return -ENOMEM;
- cfg->remapped = 1;
- irte_info->devid = devid;
- irte_info->index = index;
+ iommu->ir_domain->parent = arch_get_ir_parent_domain();
+ iommu->msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
return 0;
}
-
-struct irq_remap_ops amd_iommu_irq_ops = {
- .prepare = amd_iommu_prepare,
- .enable = amd_iommu_enable,
- .disable = amd_iommu_disable,
- .reenable = amd_iommu_reenable,
- .enable_faulting = amd_iommu_enable_faulting,
- .setup_ioapic_entry = setup_ioapic_entry,
- .set_affinity = set_affinity,
- .free_irq = free_irq,
- .compose_msi_msg = compose_msi_msg,
- .msi_alloc_irq = msi_alloc_irq,
- .msi_setup_irq = msi_setup_irq,
- .alloc_hpet_msi = alloc_hpet_msi,
-};
#endif
if (ret)
return ret;
+ ret = amd_iommu_create_irq_domain(iommu);
+ if (ret)
+ return ret;
+
/*
* Make sure IOMMU is not considered to translate itself. The IVRS
* table tells us so, but this is a lie!
extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
u64 *value, bool is_write);
+#ifdef CONFIG_IRQ_REMAP
+extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+#else
+static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+ return 0;
+}
+#endif
+
#define PPR_SUCCESS 0x0
#define PPR_INVALID 0x1
#define PPR_FAILURE 0xf
struct iommu_domain;
+struct irq_domain;
/*
* This structure contains generic data for IOMMU protection domains
/* The maximum PC banks and counters/bank (PCSup=1) */
u8 max_banks;
u8 max_counters;
+#ifdef CONFIG_IRQ_REMAP
+ struct irq_domain *ir_domain;
+ struct irq_domain *msi_domain;
+#endif
};
struct devid_map {
static void put_pasid_state_wait(struct pasid_state *pasid_state)
{
+ atomic_dec(&pasid_state->count);
wait_event(pasid_state->wq, !atomic_read(&pasid_state->count));
free_pasid_state(pasid_state);
}
#define RESUME_TERMINATE (1 << 0)
#define TTBCR2_SEP_SHIFT 15
-#define TTBCR2_SEP_MASK 0x7
-
-#define TTBCR2_ADDR_32 0
-#define TTBCR2_ADDR_36 1
-#define TTBCR2_ADDR_40 2
-#define TTBCR2_ADDR_42 3
-#define TTBCR2_ADDR_44 4
-#define TTBCR2_ADDR_48 5
+#define TTBCR2_SEP_UPSTREAM (0x7 << TTBCR2_SEP_SHIFT)
#define TTBRn_HI_ASID_SHIFT 16
writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
if (smmu->version > ARM_SMMU_V1) {
reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
- switch (smmu->va_size) {
- case 32:
- reg |= (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT);
- break;
- case 36:
- reg |= (TTBCR2_ADDR_36 << TTBCR2_SEP_SHIFT);
- break;
- case 40:
- reg |= (TTBCR2_ADDR_40 << TTBCR2_SEP_SHIFT);
- break;
- case 42:
- reg |= (TTBCR2_ADDR_42 << TTBCR2_SEP_SHIFT);
- break;
- case 44:
- reg |= (TTBCR2_ADDR_44 << TTBCR2_SEP_SHIFT);
- break;
- case 48:
- reg |= (TTBCR2_ADDR_48 << TTBCR2_SEP_SHIFT);
- break;
- }
+ reg |= TTBCR2_SEP_UPSTREAM;
writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2);
}
} else {
if (iommu->irq) {
free_irq(iommu->irq, iommu);
- irq_set_handler_data(iommu->irq, NULL);
dmar_free_hwirq(iommu->irq);
+ iommu->irq = 0;
}
if (iommu->qi) {
if (iommu->irq)
return 0;
- irq = dmar_alloc_hwirq();
- if (irq <= 0) {
+ irq = dmar_alloc_hwirq(iommu->seq_id, iommu->node, iommu);
+ if (irq > 0) {
+ iommu->irq = irq;
+ } else {
pr_err("IOMMU: no free vectors\n");
return -EINVAL;
}
- irq_set_handler_data(irq, iommu);
- iommu->irq = irq;
-
- ret = arch_setup_dmar_msi(irq);
- if (ret) {
- irq_set_handler_data(irq, NULL);
- iommu->irq = 0;
- dmar_free_hwirq(irq);
- return ret;
- }
-
ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
if (ret)
pr_err("IOMMU: can't request irq\n");
static int dmar_forcedac;
static int intel_iommu_strict;
static int intel_iommu_superpage = 1;
+static int intel_iommu_ecs = 1;
+
+/* We only actually use ECS when PASID support (on the new bit 40)
+ * is also advertised. Some early implementations — the ones with
+ * PASID support on bit 28 — have issues even when we *only* use
+ * extended root/context tables. */
+#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
+ ecap_pasid(iommu->ecap))
int intel_iommu_gfx_mapped;
EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
printk(KERN_INFO
"Intel-IOMMU: disable supported super page\n");
intel_iommu_superpage = 0;
+ } else if (!strncmp(str, "ecs_off", 7)) {
+ printk(KERN_INFO
+ "Intel-IOMMU: disable extended context table support\n");
+ intel_iommu_ecs = 0;
}
str += strcspn(str, ",");
struct context_entry *context;
u64 *entry;
- if (ecap_ecs(iommu->ecap)) {
+ if (ecs_enabled(iommu)) {
if (devfn >= 0x80) {
devfn -= 0x80;
entry = &root->hi;
return &context[devfn];
}
+static int iommu_dummy(struct device *dev)
+{
+ return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
+}
+
static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
{
struct dmar_drhd_unit *drhd = NULL;
u16 segment = 0;
int i;
+ if (iommu_dummy(dev))
+ return NULL;
+
if (dev_is_pci(dev)) {
pdev = to_pci_dev(dev);
segment = pci_domain_nr(pdev->bus);
if (context)
free_pgtable_page(context);
- if (!ecap_ecs(iommu->ecap))
+ if (!ecs_enabled(iommu))
continue;
context = iommu_context_addr(iommu, i, 0x80, 0);
unsigned long flag;
addr = virt_to_phys(iommu->root_entry);
- if (ecap_ecs(iommu->ecap))
+ if (ecs_enabled(iommu))
addr |= DMA_RTADDR_RTT;
raw_spin_lock_irqsave(&iommu->register_lock, flag);
return __get_valid_domain_for_dev(dev);
}
-static int iommu_dummy(struct device *dev)
-{
- return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
-}
-
/* Check if the dev needs to go through non-identity map and unmap process.*/
static int iommu_no_mapping(struct device *dev)
{
#include <linux/irq.h>
#include <linux/intel-iommu.h>
#include <linux/acpi.h>
+#include <linux/irqdomain.h>
#include <asm/io_apic.h>
#include <asm/smp.h>
#include <asm/cpu.h>
#include "irq_remapping.h"
+enum irq_mode {
+ IRQ_REMAPPING,
+ IRQ_POSTING,
+};
+
struct ioapic_scope {
struct intel_iommu *iommu;
unsigned int id;
unsigned int devfn;
};
+struct irq_2_iommu {
+ struct intel_iommu *iommu;
+ u16 irte_index;
+ u16 sub_handle;
+ u8 irte_mask;
+ enum irq_mode mode;
+};
+
+struct intel_ir_data {
+ struct irq_2_iommu irq_2_iommu;
+ struct irte irte_entry;
+ union {
+ struct msi_msg msi_entry;
+ };
+};
+
#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
#define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8)
* the dmar_global_lock.
*/
static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
+static struct irq_domain_ops intel_ir_domain_ops;
static int __init parse_ioapics_under_ir(void);
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
- return cfg ? &cfg->irq_2_iommu : NULL;
-}
-
-static int get_irte(int irq, struct irte *entry)
-{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- unsigned long flags;
- int index;
-
- if (!entry || !irq_iommu)
- return -1;
-
- raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
- if (unlikely(!irq_iommu->iommu)) {
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
- return -1;
- }
-
- index = irq_iommu->irte_index + irq_iommu->sub_handle;
- *entry = *(irq_iommu->iommu->ir_table->base + index);
-
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
- return 0;
-}
-
-static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+static int alloc_irte(struct intel_iommu *iommu, int irq,
+ struct irq_2_iommu *irq_iommu, u16 count)
{
struct ir_table *table = iommu->ir_table;
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- struct irq_cfg *cfg = irq_cfg(irq);
unsigned int mask = 0;
unsigned long flags;
int index;
if (index < 0) {
pr_warn("IR%d: can't allocate an IRTE\n", iommu->seq_id);
} else {
- cfg->remapped = 1;
irq_iommu->iommu = iommu;
irq_iommu->irte_index = index;
irq_iommu->sub_handle = 0;
irq_iommu->irte_mask = mask;
+ irq_iommu->mode = IRQ_REMAPPING;
}
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return qi_submit_sync(&desc, iommu);
}
-static int map_irq_to_irte_handle(int irq, u16 *sub_handle)
-{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- unsigned long flags;
- int index;
-
- if (!irq_iommu)
- return -1;
-
- raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
- *sub_handle = irq_iommu->sub_handle;
- index = irq_iommu->irte_index;
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
- return index;
-}
-
-static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
+static int modify_irte(struct irq_2_iommu *irq_iommu,
+ struct irte *irte_modified)
{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- struct irq_cfg *cfg = irq_cfg(irq);
- unsigned long flags;
-
- if (!irq_iommu)
- return -1;
-
- raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
- cfg->remapped = 1;
- irq_iommu->iommu = iommu;
- irq_iommu->irte_index = index;
- irq_iommu->sub_handle = subhandle;
- irq_iommu->irte_mask = 0;
-
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
- return 0;
-}
-
-static int modify_irte(int irq, struct irte *irte_modified)
-{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
struct intel_iommu *iommu;
unsigned long flags;
struct irte *irte;
__iommu_flush_cache(iommu, irte, sizeof(*irte));
rc = qi_flush_iec(iommu, index, 0);
+
+ /* Update iommu mode according to the IRTE mode */
+ irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return rc;
return 0;
iommu = irq_iommu->iommu;
- index = irq_iommu->irte_index + irq_iommu->sub_handle;
+ index = irq_iommu->irte_index;
start = iommu->ir_table->base + index;
end = start + (1 << irq_iommu->irte_mask);
return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
}
-static int free_irte(int irq)
-{
- struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
- unsigned long flags;
- int rc;
-
- if (!irq_iommu)
- return -1;
-
- raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
- rc = clear_entries(irq_iommu);
-
- irq_iommu->iommu = NULL;
- irq_iommu->irte_index = 0;
- irq_iommu->sub_handle = 0;
- irq_iommu->irte_mask = 0;
-
- raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
- return rc;
-}
-
/*
* source validation type
*/
pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO,
INTR_REMAP_PAGE_ORDER);
-
if (!pages) {
pr_err("IR%d: failed to allocate pages of order %d\n",
iommu->seq_id, INTR_REMAP_PAGE_ORDER);
goto out_free_pages;
}
+ iommu->ir_domain = irq_domain_add_hierarchy(arch_get_ir_parent_domain(),
+ 0, INTR_REMAP_TABLE_ENTRIES,
+ NULL, &intel_ir_domain_ops,
+ iommu);
+ if (!iommu->ir_domain) {
+ pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
+ goto out_free_bitmap;
+ }
+ iommu->ir_msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
+
ir_table->base = page_address(pages);
ir_table->bitmap = bitmap;
iommu->ir_table = ir_table;
return 0;
+out_free_bitmap:
+ kfree(bitmap);
out_free_pages:
__free_pages(pages, INTR_REMAP_PAGE_ORDER);
out_free_table:
static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
{
if (iommu && iommu->ir_table) {
+ if (iommu->ir_msi_domain) {
+ irq_domain_remove(iommu->ir_msi_domain);
+ iommu->ir_msi_domain = NULL;
+ }
+ if (iommu->ir_domain) {
+ irq_domain_remove(iommu->ir_domain);
+ iommu->ir_domain = NULL;
+ }
free_pages((unsigned long)iommu->ir_table->base,
INTR_REMAP_PAGE_ORDER);
kfree(iommu->ir_table->bitmap);
return -ENODEV;
}
+/*
+ * Set Posted-Interrupts capability.
+ */
+static inline void set_irq_posting_cap(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+
+ if (!disable_irq_post) {
+ intel_irq_remap_ops.capability |= 1 << IRQ_POSTING_CAP;
+
+ for_each_iommu(iommu, drhd)
+ if (!cap_pi_support(iommu->cap)) {
+ intel_irq_remap_ops.capability &=
+ ~(1 << IRQ_POSTING_CAP);
+ break;
+ }
+ }
+}
+
static int __init intel_enable_irq_remapping(void)
{
struct dmar_drhd_unit *drhd;
irq_remapping_enabled = 1;
- /*
- * VT-d has a different layout for IO-APIC entries when
- * interrupt remapping is enabled. So it needs a special routine
- * to print IO-APIC entries for debugging purposes too.
- */
- x86_io_apic_ops.print_entries = intel_ir_io_apic_print_entries;
+ set_irq_posting_cap();
pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic");
iommu_disable_irq_remapping(iommu);
}
+
+ /*
+ * Clear Posted-Interrupts capability.
+ */
+ if (!disable_irq_post)
+ intel_irq_remap_ops.capability &= ~(1 << IRQ_POSTING_CAP);
}
static int reenable_irq_remapping(int eim)
if (!setup)
goto error;
+ set_irq_posting_cap();
+
return 0;
error:
return -1;
}
-static void prepare_irte(struct irte *irte, int vector,
- unsigned int dest)
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
{
memset(irte, 0, sizeof(*irte));
irte->redir_hint = 1;
}
-static int intel_setup_ioapic_entry(int irq,
- struct IO_APIC_route_entry *route_entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
+static struct irq_domain *intel_get_ir_irq_domain(struct irq_alloc_info *info)
{
- int ioapic_id = mpc_ioapic_id(attr->ioapic);
- struct intel_iommu *iommu;
- struct IR_IO_APIC_route_entry *entry;
- struct irte irte;
- int index;
-
- down_read(&dmar_global_lock);
- iommu = map_ioapic_to_ir(ioapic_id);
- if (!iommu) {
- pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
- index = -ENODEV;
- } else {
- index = alloc_irte(iommu, irq, 1);
- if (index < 0) {
- pr_warn("Failed to allocate IRTE for ioapic %d\n",
- ioapic_id);
- index = -ENOMEM;
- }
- }
- up_read(&dmar_global_lock);
- if (index < 0)
- return index;
-
- prepare_irte(&irte, vector, destination);
+ struct intel_iommu *iommu = NULL;
- /* Set source-id of interrupt request */
- set_ioapic_sid(&irte, ioapic_id);
+ if (!info)
+ return NULL;
- modify_irte(irq, &irte);
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_IOAPIC:
+ iommu = map_ioapic_to_ir(info->ioapic_id);
+ break;
+ case X86_IRQ_ALLOC_TYPE_HPET:
+ iommu = map_hpet_to_ir(info->hpet_id);
+ break;
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ iommu = map_dev_to_ir(info->msi_dev);
+ break;
+ default:
+ BUG_ON(1);
+ break;
+ }
- apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
- "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "
- "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
- "Avail:%X Vector:%02X Dest:%08X "
- "SID:%04X SQ:%X SVT:%X)\n",
- attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
- irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
- irte.avail, irte.vector, irte.dest_id,
- irte.sid, irte.sq, irte.svt);
+ return iommu ? iommu->ir_domain : NULL;
+}
- entry = (struct IR_IO_APIC_route_entry *)route_entry;
- memset(entry, 0, sizeof(*entry));
+static struct irq_domain *intel_get_irq_domain(struct irq_alloc_info *info)
+{
+ struct intel_iommu *iommu;
- entry->index2 = (index >> 15) & 0x1;
- entry->zero = 0;
- entry->format = 1;
- entry->index = (index & 0x7fff);
- /*
- * IO-APIC RTE will be configured with virtual vector.
- * irq handler will do the explicit EOI to the io-apic.
- */
- entry->vector = attr->ioapic_pin;
- entry->mask = 0; /* enable IRQ */
- entry->trigger = attr->trigger;
- entry->polarity = attr->polarity;
+ if (!info)
+ return NULL;
- /* Mask level triggered irqs.
- * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
- */
- if (attr->trigger)
- entry->mask = 1;
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ iommu = map_dev_to_ir(info->msi_dev);
+ if (iommu)
+ return iommu->ir_msi_domain;
+ break;
+ default:
+ break;
+ }
- return 0;
+ return NULL;
}
+struct irq_remap_ops intel_irq_remap_ops = {
+ .prepare = intel_prepare_irq_remapping,
+ .enable = intel_enable_irq_remapping,
+ .disable = disable_irq_remapping,
+ .reenable = reenable_irq_remapping,
+ .enable_faulting = enable_drhd_fault_handling,
+ .get_ir_irq_domain = intel_get_ir_irq_domain,
+ .get_irq_domain = intel_get_irq_domain,
+};
+
/*
* Migrate the IO-APIC irq in the presence of intr-remapping.
*
* is used to migrate MSI irq's in the presence of interrupt-remapping.
*/
static int
-intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
+intel_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
{
+ struct intel_ir_data *ir_data = data->chip_data;
+ struct irte *irte = &ir_data->irte_entry;
struct irq_cfg *cfg = irqd_cfg(data);
- unsigned int dest, irq = data->irq;
- struct irte irte;
- int err;
-
- if (!config_enabled(CONFIG_SMP))
- return -EINVAL;
-
- if (!cpumask_intersects(mask, cpu_online_mask))
- return -EINVAL;
-
- if (get_irte(irq, &irte))
- return -EBUSY;
-
- err = assign_irq_vector(irq, cfg, mask);
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
- if (err) {
- if (assign_irq_vector(irq, cfg, data->affinity))
- pr_err("Failed to recover vector for irq %d\n", irq);
- return err;
- }
+ struct irq_data *parent = data->parent_data;
+ int ret;
- irte.vector = cfg->vector;
- irte.dest_id = IRTE_DEST(dest);
+ ret = parent->chip->irq_set_affinity(parent, mask, force);
+ if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+ return ret;
/*
* Atomically updates the IRTE with the new destination, vector
* and flushes the interrupt entry cache.
*/
- modify_irte(irq, &irte);
+ irte->vector = cfg->vector;
+ irte->dest_id = IRTE_DEST(cfg->dest_apicid);
+
+ /* Update the hardware only if the interrupt is in remapped mode. */
+ if (ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+ modify_irte(&ir_data->irq_2_iommu, irte);
/*
* After this point, all the interrupts will start arriving
* at the new destination. So, time to cleanup the previous
* vector allocation.
*/
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
+ send_cleanup_vector(cfg);
- cpumask_copy(data->affinity, mask);
- return 0;
+ return IRQ_SET_MASK_OK_DONE;
}
-static void intel_compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
+static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
+ struct msi_msg *msg)
{
- struct irq_cfg *cfg;
- struct irte irte;
- u16 sub_handle = 0;
- int ir_index;
+ struct intel_ir_data *ir_data = irq_data->chip_data;
- cfg = irq_cfg(irq);
+ *msg = ir_data->msi_entry;
+}
- ir_index = map_irq_to_irte_handle(irq, &sub_handle);
- BUG_ON(ir_index == -1);
+static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
+{
+ struct intel_ir_data *ir_data = data->chip_data;
+ struct vcpu_data *vcpu_pi_info = info;
- prepare_irte(&irte, cfg->vector, dest);
+ /* stop posting interrupts, back to remapping mode */
+ if (!vcpu_pi_info) {
+ modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+ } else {
+ struct irte irte_pi;
- /* Set source-id of interrupt request */
- if (pdev)
- set_msi_sid(&irte, pdev);
- else
- set_hpet_sid(&irte, hpet_id);
+ /*
+ * We are not caching the posted interrupt entry. We
+ * copy the data from the remapped entry and modify
+ * the fields which are relevant for posted mode. The
+ * cached remapped entry is used for switching back to
+ * remapped mode.
+ */
+ memset(&irte_pi, 0, sizeof(irte_pi));
+ dmar_copy_shared_irte(&irte_pi, &ir_data->irte_entry);
+
+ /* Update the posted mode fields */
+ irte_pi.p_pst = 1;
+ irte_pi.p_urgent = 0;
+ irte_pi.p_vector = vcpu_pi_info->vector;
+ irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >>
+ (32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT);
+ irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
+ ~(-1UL << PDA_HIGH_BIT);
+
+ modify_irte(&ir_data->irq_2_iommu, &irte_pi);
+ }
- modify_irte(irq, &irte);
+ return 0;
+}
+
+static struct irq_chip intel_ir_chip = {
+ .irq_ack = ir_ack_apic_edge,
+ .irq_set_affinity = intel_ir_set_affinity,
+ .irq_compose_msi_msg = intel_ir_compose_msi_msg,
+ .irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity,
+};
- msg->address_hi = MSI_ADDR_BASE_HI;
- msg->data = sub_handle;
- msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
- MSI_ADDR_IR_SHV |
- MSI_ADDR_IR_INDEX1(ir_index) |
- MSI_ADDR_IR_INDEX2(ir_index);
+static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
+ struct irq_cfg *irq_cfg,
+ struct irq_alloc_info *info,
+ int index, int sub_handle)
+{
+ struct IR_IO_APIC_route_entry *entry;
+ struct irte *irte = &data->irte_entry;
+ struct msi_msg *msg = &data->msi_entry;
+
+ prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
+ switch (info->type) {
+ case X86_IRQ_ALLOC_TYPE_IOAPIC:
+ /* Set source-id of interrupt request */
+ set_ioapic_sid(irte, info->ioapic_id);
+ apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set IRTE entry (P:%d FPD:%d Dst_Mode:%d Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X Avail:%X Vector:%02X Dest:%08X SID:%04X SQ:%X SVT:%X)\n",
+ info->ioapic_id, irte->present, irte->fpd,
+ irte->dst_mode, irte->redir_hint,
+ irte->trigger_mode, irte->dlvry_mode,
+ irte->avail, irte->vector, irte->dest_id,
+ irte->sid, irte->sq, irte->svt);
+
+ entry = (struct IR_IO_APIC_route_entry *)info->ioapic_entry;
+ info->ioapic_entry = NULL;
+ memset(entry, 0, sizeof(*entry));
+ entry->index2 = (index >> 15) & 0x1;
+ entry->zero = 0;
+ entry->format = 1;
+ entry->index = (index & 0x7fff);
+ /*
+ * IO-APIC RTE will be configured with virtual vector.
+ * irq handler will do the explicit EOI to the io-apic.
+ */
+ entry->vector = info->ioapic_pin;
+ entry->mask = 0; /* enable IRQ */
+ entry->trigger = info->ioapic_trigger;
+ entry->polarity = info->ioapic_polarity;
+ if (info->ioapic_trigger)
+ entry->mask = 1; /* Mask level triggered irqs. */
+ break;
+
+ case X86_IRQ_ALLOC_TYPE_HPET:
+ case X86_IRQ_ALLOC_TYPE_MSI:
+ case X86_IRQ_ALLOC_TYPE_MSIX:
+ if (info->type == X86_IRQ_ALLOC_TYPE_HPET)
+ set_hpet_sid(irte, info->hpet_id);
+ else
+ set_msi_sid(irte, info->msi_dev);
+
+ msg->address_hi = MSI_ADDR_BASE_HI;
+ msg->data = sub_handle;
+ msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+ MSI_ADDR_IR_SHV |
+ MSI_ADDR_IR_INDEX1(index) |
+ MSI_ADDR_IR_INDEX2(index);
+ break;
+
+ default:
+ BUG_ON(1);
+ break;
+ }
}
-/*
- * Map the PCI dev to the corresponding remapping hardware unit
- * and allocate 'nvec' consecutive interrupt-remapping table entries
- * in it.
- */
-static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec)
+static void intel_free_irq_resources(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs)
{
- struct intel_iommu *iommu;
- int index;
+ struct irq_data *irq_data;
+ struct intel_ir_data *data;
+ struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
+ int i;
- down_read(&dmar_global_lock);
- iommu = map_dev_to_ir(dev);
- if (!iommu) {
- printk(KERN_ERR
- "Unable to map PCI %s to iommu\n", pci_name(dev));
- index = -ENOENT;
- } else {
- index = alloc_irte(iommu, irq, nvec);
- if (index < 0) {
- printk(KERN_ERR
- "Unable to allocate %d IRTE for PCI %s\n",
- nvec, pci_name(dev));
- index = -ENOSPC;
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ if (irq_data && irq_data->chip_data) {
+ data = irq_data->chip_data;
+ irq_iommu = &data->irq_2_iommu;
+ raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+ clear_entries(irq_iommu);
+ raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+ irq_domain_reset_irq_data(irq_data);
+ kfree(data);
}
}
- up_read(&dmar_global_lock);
-
- return index;
}
-static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
- int index, int sub_handle)
+static int intel_irq_remapping_alloc(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs,
+ void *arg)
{
- struct intel_iommu *iommu;
- int ret = -ENOENT;
+ struct intel_iommu *iommu = domain->host_data;
+ struct irq_alloc_info *info = arg;
+ struct intel_ir_data *data, *ird;
+ struct irq_data *irq_data;
+ struct irq_cfg *irq_cfg;
+ int i, ret, index;
+
+ if (!info || !iommu)
+ return -EINVAL;
+ if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+ info->type != X86_IRQ_ALLOC_TYPE_MSIX)
+ return -EINVAL;
+
+ /*
+ * With IRQ remapping enabled, don't need contiguous CPU vectors
+ * to support multiple MSI interrupts.
+ */
+ if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+ info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+ ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+ if (ret < 0)
+ return ret;
+
+ ret = -ENOMEM;
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto out_free_parent;
down_read(&dmar_global_lock);
- iommu = map_dev_to_ir(pdev);
- if (iommu) {
- /*
- * setup the mapping between the irq and the IRTE
- * base index, the sub_handle pointing to the
- * appropriate interrupt remap table entry.
- */
- set_irte_irq(irq, iommu, index, sub_handle);
- ret = 0;
- }
+ index = alloc_irte(iommu, virq, &data->irq_2_iommu, nr_irqs);
up_read(&dmar_global_lock);
+ if (index < 0) {
+ pr_warn("Failed to allocate IRTE\n");
+ kfree(data);
+ goto out_free_parent;
+ }
+ for (i = 0; i < nr_irqs; i++) {
+ irq_data = irq_domain_get_irq_data(domain, virq + i);
+ irq_cfg = irqd_cfg(irq_data);
+ if (!irq_data || !irq_cfg) {
+ ret = -EINVAL;
+ goto out_free_data;
+ }
+
+ if (i > 0) {
+ ird = kzalloc(sizeof(*ird), GFP_KERNEL);
+ if (!ird)
+ goto out_free_data;
+ /* Initialize the common data */
+ ird->irq_2_iommu = data->irq_2_iommu;
+ ird->irq_2_iommu.sub_handle = i;
+ } else {
+ ird = data;
+ }
+
+ irq_data->hwirq = (index << 16) + i;
+ irq_data->chip_data = ird;
+ irq_data->chip = &intel_ir_chip;
+ intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i);
+ irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+ }
+ return 0;
+
+out_free_data:
+ intel_free_irq_resources(domain, virq, i);
+out_free_parent:
+ irq_domain_free_irqs_common(domain, virq, nr_irqs);
return ret;
}
-static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
+static void intel_irq_remapping_free(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs)
{
- int ret = -1;
- struct intel_iommu *iommu;
- int index;
+ intel_free_irq_resources(domain, virq, nr_irqs);
+ irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
- down_read(&dmar_global_lock);
- iommu = map_hpet_to_ir(id);
- if (iommu) {
- index = alloc_irte(iommu, irq, 1);
- if (index >= 0)
- ret = 0;
- }
- up_read(&dmar_global_lock);
+static void intel_irq_remapping_activate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct intel_ir_data *data = irq_data->chip_data;
- return ret;
+ modify_irte(&data->irq_2_iommu, &data->irte_entry);
}
-struct irq_remap_ops intel_irq_remap_ops = {
- .prepare = intel_prepare_irq_remapping,
- .enable = intel_enable_irq_remapping,
- .disable = disable_irq_remapping,
- .reenable = reenable_irq_remapping,
- .enable_faulting = enable_drhd_fault_handling,
- .setup_ioapic_entry = intel_setup_ioapic_entry,
- .set_affinity = intel_ioapic_set_affinity,
- .free_irq = free_irte,
- .compose_msi_msg = intel_compose_msi_msg,
- .msi_alloc_irq = intel_msi_alloc_irq,
- .msi_setup_irq = intel_msi_setup_irq,
- .alloc_hpet_msi = intel_alloc_hpet_msi,
+static void intel_irq_remapping_deactivate(struct irq_domain *domain,
+ struct irq_data *irq_data)
+{
+ struct intel_ir_data *data = irq_data->chip_data;
+ struct irte entry;
+
+ memset(&entry, 0, sizeof(entry));
+ modify_irte(&data->irq_2_iommu, &entry);
+}
+
+static struct irq_domain_ops intel_ir_domain_ops = {
+ .alloc = intel_irq_remapping_alloc,
+ .free = intel_irq_remapping_free,
+ .activate = intel_irq_remapping_activate,
+ .deactivate = intel_irq_remapping_deactivate,
};
/*
return -EINVAL;
if (!ecap_ir_support(iommu->ecap))
return 0;
+ if (irq_remapping_cap(IRQ_POSTING_CAP) &&
+ !cap_pi_support(iommu->cap))
+ return -EBUSY;
if (insert) {
if (!iommu->ir_table)
#include <linux/msi.h>
#include <linux/irq.h>
#include <linux/pci.h>
+#include <linux/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/irq_remapping.h>
int disable_sourceid_checking;
int no_x2apic_optout;
+int disable_irq_post = 1;
+
static int disable_irq_remap;
static struct irq_remap_ops *remap_ops;
-static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec);
-static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
- int index, int sub_handle);
-static int set_remapped_irq_affinity(struct irq_data *data,
- const struct cpumask *mask,
- bool force);
-
-static bool irq_remapped(struct irq_cfg *cfg)
-{
- return (cfg->remapped == 1);
-}
-
static void irq_remapping_disable_io_apic(void)
{
/*
disconnect_bsp_APIC(0);
}
-static int do_setup_msi_irqs(struct pci_dev *dev, int nvec)
-{
- int ret, sub_handle, nvec_pow2, index = 0;
- unsigned int irq;
- struct msi_desc *msidesc;
-
- msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
-
- irq = irq_alloc_hwirqs(nvec, dev_to_node(&dev->dev));
- if (irq == 0)
- return -ENOSPC;
-
- nvec_pow2 = __roundup_pow_of_two(nvec);
- for (sub_handle = 0; sub_handle < nvec; sub_handle++) {
- if (!sub_handle) {
- index = msi_alloc_remapped_irq(dev, irq, nvec_pow2);
- if (index < 0) {
- ret = index;
- goto error;
- }
- } else {
- ret = msi_setup_remapped_irq(dev, irq + sub_handle,
- index, sub_handle);
- if (ret < 0)
- goto error;
- }
- ret = setup_msi_irq(dev, msidesc, irq, sub_handle);
- if (ret < 0)
- goto error;
- }
- return 0;
-
-error:
- irq_free_hwirqs(irq, nvec);
-
- /*
- * Restore altered MSI descriptor fields and prevent just destroyed
- * IRQs from tearing down again in default_teardown_msi_irqs()
- */
- msidesc->irq = 0;
-
- return ret;
-}
-
-static int do_setup_msix_irqs(struct pci_dev *dev, int nvec)
-{
- int node, ret, sub_handle, index = 0;
- struct msi_desc *msidesc;
- unsigned int irq;
-
- node = dev_to_node(&dev->dev);
- sub_handle = 0;
-
- list_for_each_entry(msidesc, &dev->msi_list, list) {
-
- irq = irq_alloc_hwirq(node);
- if (irq == 0)
- return -1;
-
- if (sub_handle == 0)
- ret = index = msi_alloc_remapped_irq(dev, irq, nvec);
- else
- ret = msi_setup_remapped_irq(dev, irq, index, sub_handle);
-
- if (ret < 0)
- goto error;
-
- ret = setup_msi_irq(dev, msidesc, irq, 0);
- if (ret < 0)
- goto error;
-
- sub_handle += 1;
- irq += 1;
- }
-
- return 0;
-
-error:
- irq_free_hwirq(irq);
- return ret;
-}
-
-static int irq_remapping_setup_msi_irqs(struct pci_dev *dev,
- int nvec, int type)
-{
- if (type == PCI_CAP_ID_MSI)
- return do_setup_msi_irqs(dev, nvec);
- else
- return do_setup_msix_irqs(dev, nvec);
-}
-
-static void eoi_ioapic_pin_remapped(int apic, int pin, int vector)
-{
- /*
- * Intr-remapping uses pin number as the virtual vector
- * in the RTE. Actual vector is programmed in
- * intr-remapping table entry. Hence for the io-apic
- * EOI we use the pin number.
- */
- io_apic_eoi(apic, pin);
-}
-
static void __init irq_remapping_modify_x86_ops(void)
{
x86_io_apic_ops.disable = irq_remapping_disable_io_apic;
- x86_io_apic_ops.set_affinity = set_remapped_irq_affinity;
- x86_io_apic_ops.setup_entry = setup_ioapic_remapped_entry;
- x86_io_apic_ops.eoi_ioapic_pin = eoi_ioapic_pin_remapped;
- x86_msi.setup_msi_irqs = irq_remapping_setup_msi_irqs;
- x86_msi.setup_hpet_msi = setup_hpet_msi_remapped;
- x86_msi.compose_msi_msg = compose_remapped_msi_msg;
}
static __init int setup_nointremap(char *str)
irq_remap_broken = 1;
}
+bool irq_remapping_cap(enum irq_remap_cap cap)
+{
+ if (!remap_ops || disable_irq_post)
+ return 0;
+
+ return (remap_ops->capability & (1 << cap));
+}
+EXPORT_SYMBOL_GPL(irq_remapping_cap);
+
int __init irq_remapping_prepare(void)
{
if (disable_irq_remap)
return remap_ops->enable_faulting();
}
-int setup_ioapic_remapped_entry(int irq,
- struct IO_APIC_route_entry *entry,
- unsigned int destination, int vector,
- struct io_apic_irq_attr *attr)
-{
- if (!remap_ops->setup_ioapic_entry)
- return -ENODEV;
-
- return remap_ops->setup_ioapic_entry(irq, entry, destination,
- vector, attr);
-}
-
-static int set_remapped_irq_affinity(struct irq_data *data,
- const struct cpumask *mask, bool force)
-{
- if (!config_enabled(CONFIG_SMP) || !remap_ops->set_affinity)
- return 0;
-
- return remap_ops->set_affinity(data, mask, force);
-}
-
-void free_remapped_irq(int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- if (irq_remapped(cfg) && remap_ops->free_irq)
- remap_ops->free_irq(irq);
-}
-
-void compose_remapped_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- if (!irq_remapped(cfg))
- native_compose_msi_msg(pdev, irq, dest, msg, hpet_id);
- else if (remap_ops->compose_msi_msg)
- remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-}
-
-static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec)
-{
- if (!remap_ops->msi_alloc_irq)
- return -ENODEV;
-
- return remap_ops->msi_alloc_irq(pdev, irq, nvec);
-}
-
-static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
- int index, int sub_handle)
-{
- if (!remap_ops->msi_setup_irq)
- return -ENODEV;
-
- return remap_ops->msi_setup_irq(pdev, irq, index, sub_handle);
-}
-
-int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
- int ret;
-
- if (!remap_ops->alloc_hpet_msi)
- return -ENODEV;
-
- ret = remap_ops->alloc_hpet_msi(irq, id);
- if (ret)
- return -EINVAL;
-
- return default_setup_hpet_msi(irq, id);
-}
-
void panic_if_irq_remap(const char *msg)
{
if (irq_remapping_enabled)
panic(msg);
}
-static void ir_ack_apic_edge(struct irq_data *data)
+void ir_ack_apic_edge(struct irq_data *data)
{
ack_APIC_irq();
}
-static void ir_ack_apic_level(struct irq_data *data)
+/**
+ * irq_remapping_get_ir_irq_domain - Get the irqdomain associated with the IOMMU
+ * device serving request @info
+ * @info: interrupt allocation information, used to identify the IOMMU device
+ *
+ * It's used to get parent irqdomain for HPET and IOAPIC irqdomains.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
{
- ack_APIC_irq();
- eoi_ioapic_irq(data->irq, irqd_cfg(data));
-}
+ if (!remap_ops || !remap_ops->get_ir_irq_domain)
+ return NULL;
-static void ir_print_prefix(struct irq_data *data, struct seq_file *p)
-{
- seq_printf(p, " IR-%s", data->chip->name);
+ return remap_ops->get_ir_irq_domain(info);
}
-void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+/**
+ * irq_remapping_get_irq_domain - Get the irqdomain serving the request @info
+ * @info: interrupt allocation information, used to identify the IOMMU device
+ *
+ * There will be one PCI MSI/MSIX irqdomain associated with each interrupt
+ * remapping device, so this interface is used to retrieve the PCI MSI/MSIX
+ * irqdomain serving request @info.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
{
- chip->irq_print_chip = ir_print_prefix;
- chip->irq_ack = ir_ack_apic_edge;
- chip->irq_eoi = ir_ack_apic_level;
- chip->irq_set_affinity = x86_io_apic_ops.set_affinity;
-}
+ if (!remap_ops || !remap_ops->get_irq_domain)
+ return NULL;
-bool setup_remapped_irq(int irq, struct irq_cfg *cfg, struct irq_chip *chip)
-{
- if (!irq_remapped(cfg))
- return false;
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- irq_remap_modify_chip_defaults(chip);
- return true;
+ return remap_ops->get_irq_domain(info);
}
#ifdef CONFIG_IRQ_REMAP
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
struct irq_data;
-struct cpumask;
-struct pci_dev;
struct msi_msg;
+struct irq_domain;
+struct irq_alloc_info;
extern int irq_remap_broken;
extern int disable_sourceid_checking;
extern int no_x2apic_optout;
extern int irq_remapping_enabled;
+extern int disable_irq_post;
+
struct irq_remap_ops {
+ /* The supported capabilities */
+ int capability;
+
/* Initializes hardware and makes it ready for remapping interrupts */
int (*prepare)(void);
/* Enable fault handling */
int (*enable_faulting)(void);
- /* IO-APIC setup routine */
- int (*setup_ioapic_entry)(int irq, struct IO_APIC_route_entry *,
- unsigned int, int,
- struct io_apic_irq_attr *);
-
- /* Set the CPU affinity of a remapped interrupt */
- int (*set_affinity)(struct irq_data *data, const struct cpumask *mask,
- bool force);
-
- /* Free an IRQ */
- int (*free_irq)(int);
+ /* Get the irqdomain associated the IOMMU device */
+ struct irq_domain *(*get_ir_irq_domain)(struct irq_alloc_info *);
- /* Create MSI msg to use for interrupt remapping */
- void (*compose_msi_msg)(struct pci_dev *,
- unsigned int, unsigned int,
- struct msi_msg *, u8);
-
- /* Allocate remapping resources for MSI */
- int (*msi_alloc_irq)(struct pci_dev *, int, int);
-
- /* Setup the remapped MSI irq */
- int (*msi_setup_irq)(struct pci_dev *, unsigned int, int, int);
-
- /* Setup interrupt remapping for an HPET MSI */
- int (*alloc_hpet_msi)(unsigned int, unsigned int);
+ /* Get the MSI irqdomain associated with the IOMMU device */
+ struct irq_domain *(*get_irq_domain)(struct irq_alloc_info *);
};
extern struct irq_remap_ops intel_irq_remap_ops;
extern struct irq_remap_ops amd_iommu_irq_ops;
+extern void ir_ack_apic_edge(struct irq_data *data);
+
#else /* CONFIG_IRQ_REMAP */
#define irq_remapping_enabled 0
#define irq_remap_broken 0
+#define disable_irq_post 1
#endif /* CONFIG_IRQ_REMAP */
return 0;
}
-#ifdef CONFIG_OF
static const struct of_device_id rk_iommu_dt_ids[] = {
{ .compatible = "rockchip,iommu" },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, rk_iommu_dt_ids);
-#endif
static struct platform_driver rk_iommu_driver = {
.probe = rk_iommu_probe,
.remove = rk_iommu_remove,
.driver = {
.name = "rk_iommu",
- .of_match_table = of_match_ptr(rk_iommu_dt_ids),
+ .of_match_table = rk_iommu_dt_ids,
},
};
u64 typer = readq_relaxed(its->base + GITS_TYPER);
u32 ids = GITS_TYPER_DEVBITS(typer);
- order = get_order((1UL << ids) * entry_size);
+ /*
+ * 'order' was initialized earlier to the default page
+ * granule of the the ITS. We can't have an allocation
+ * smaller than that. If the requested allocation
+ * is smaller, round up to the default page granule.
+ */
+ order = max(get_order((1UL << ids) * entry_size),
+ order);
if (order >= MAX_ORDER) {
order = MAX_ORDER - 1;
pr_warn("%s: Device Table too large, reduce its page order to %u\n",
#define NR_GIC_CPU_IF 8
static u8 gic_cpu_map[NR_GIC_CPU_IF] __read_mostly;
-/*
- * Supported arch specific GIC irq extension.
- * Default make them NULL.
- */
-struct irq_chip gic_arch_extn = {
- .irq_eoi = NULL,
- .irq_mask = NULL,
- .irq_unmask = NULL,
- .irq_retrigger = NULL,
- .irq_set_type = NULL,
- .irq_set_wake = NULL,
-};
-
#ifndef MAX_GIC_NR
#define MAX_GIC_NR 1
#endif
static void gic_mask_irq(struct irq_data *d)
{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&irq_controller_lock, flags);
gic_poke_irq(d, GIC_DIST_ENABLE_CLEAR);
- if (gic_arch_extn.irq_mask)
- gic_arch_extn.irq_mask(d);
- raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
}
static void gic_unmask_irq(struct irq_data *d)
{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&irq_controller_lock, flags);
- if (gic_arch_extn.irq_unmask)
- gic_arch_extn.irq_unmask(d);
gic_poke_irq(d, GIC_DIST_ENABLE_SET);
- raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
}
static void gic_eoi_irq(struct irq_data *d)
{
- if (gic_arch_extn.irq_eoi) {
- raw_spin_lock(&irq_controller_lock);
- gic_arch_extn.irq_eoi(d);
- raw_spin_unlock(&irq_controller_lock);
- }
-
writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI);
}
{
void __iomem *base = gic_dist_base(d);
unsigned int gicirq = gic_irq(d);
- unsigned long flags;
- int ret;
/* Interrupt configuration for SGIs can't be changed */
if (gicirq < 16)
type != IRQ_TYPE_EDGE_RISING)
return -EINVAL;
- raw_spin_lock_irqsave(&irq_controller_lock, flags);
-
- if (gic_arch_extn.irq_set_type)
- gic_arch_extn.irq_set_type(d, type);
-
- ret = gic_configure_irq(gicirq, type, base, NULL);
-
- raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
-
- return ret;
-}
-
-static int gic_retrigger(struct irq_data *d)
-{
- if (gic_arch_extn.irq_retrigger)
- return gic_arch_extn.irq_retrigger(d);
-
- /* the genirq layer expects 0 if we can't retrigger in hardware */
- return 0;
+ return gic_configure_irq(gicirq, type, base, NULL);
}
#ifdef CONFIG_SMP
}
#endif
-#ifdef CONFIG_PM
-static int gic_set_wake(struct irq_data *d, unsigned int on)
-{
- int ret = -ENXIO;
-
- if (gic_arch_extn.irq_set_wake)
- ret = gic_arch_extn.irq_set_wake(d, on);
-
- return ret;
-}
-
-#else
-#define gic_set_wake NULL
-#endif
-
static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
u32 irqstat, irqnr;
.irq_unmask = gic_unmask_irq,
.irq_eoi = gic_eoi_irq,
.irq_set_type = gic_set_type,
- .irq_retrigger = gic_retrigger,
#ifdef CONFIG_SMP
.irq_set_affinity = gic_set_affinity,
#endif
- .irq_set_wake = gic_set_wake,
.irq_get_irqchip_state = gic_irq_get_irqchip_state,
.irq_set_irqchip_state = gic_irq_set_irqchip_state,
};
set_handle_irq(gic_handle_irq);
}
- gic_chip.flags |= gic_arch_extn.flags;
gic_dist_init(gic);
gic_cpu_init(gic);
gic_pm_init(gic);
GIC_LOCAL_TO_HWIRQ(GIC_LOCAL_INT_FDC));
}
-static void gic_handle_shared_int(void)
+static void gic_handle_shared_int(bool chained)
{
unsigned int i, intr, virq;
unsigned long *pcpu_mask;
while (intr != gic_shared_intrs) {
virq = irq_linear_revmap(gic_irq_domain,
GIC_SHARED_TO_HWIRQ(intr));
- do_IRQ(virq);
+ if (chained)
+ generic_handle_irq(virq);
+ else
+ do_IRQ(virq);
/* go to next pending bit */
bitmap_clear(pending, intr, 1);
#endif
};
-static void gic_handle_local_int(void)
+static void gic_handle_local_int(bool chained)
{
unsigned long pending, masked;
unsigned int intr, virq;
while (intr != GIC_NUM_LOCAL_INTRS) {
virq = irq_linear_revmap(gic_irq_domain,
GIC_LOCAL_TO_HWIRQ(intr));
- do_IRQ(virq);
+ if (chained)
+ generic_handle_irq(virq);
+ else
+ do_IRQ(virq);
/* go to next pending bit */
bitmap_clear(&pending, intr, 1);
static void __gic_irq_dispatch(void)
{
- gic_handle_local_int();
- gic_handle_shared_int();
+ gic_handle_local_int(false);
+ gic_handle_shared_int(false);
}
static void gic_irq_dispatch(unsigned int irq, struct irq_desc *desc)
{
- __gic_irq_dispatch();
+ gic_handle_local_int(true);
+ gic_handle_shared_int(true);
}
#ifdef CONFIG_MIPS_GIC_IPI
irqd_set_trigger_type(data, flow_type);
irq_setup_alt_chip(data, flow_type);
- for (i = 0; i <= gc->num_ct; i++, ct++)
+ for (i = 0; i < gc->num_ct; i++, ct++)
if (ct->type & flow_type)
ctrl_off = ct->regs.type;
irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
&tegra_ictlr_chip,
- &info->base[ictlr]);
+ info->base[ictlr]);
}
parent_args = *args;
bool lguest_address_ok(const struct lguest *lg,
unsigned long addr, unsigned long len)
{
- return (addr+len) / PAGE_SIZE < lg->pfn_limit && (addr+len >= addr);
+ return addr+len <= lg->pfn_limit * PAGE_SIZE && (addr+len >= addr);
}
/*
#include "lg.h"
/* Allow Guests to use a non-128 (ie. non-Linux) syscall trap. */
-static unsigned int syscall_vector = SYSCALL_VECTOR;
+static unsigned int syscall_vector = IA32_SYSCALL_VECTOR;
module_param(syscall_vector, uint, 0444);
/* The address of the interrupt handler is split into two bits: */
*/
static bool could_be_syscall(unsigned int num)
{
- /* Normal Linux SYSCALL_VECTOR or reserved vector? */
- return num == SYSCALL_VECTOR || num == syscall_vector;
+ /* Normal Linux IA32_SYSCALL_VECTOR or reserved vector? */
+ return num == IA32_SYSCALL_VECTOR || num == syscall_vector;
}
/* The syscall vector it wants must be unused by Host. */
int init_interrupts(void)
{
/* If they want some strange system call vector, reserve it now */
- if (syscall_vector != SYSCALL_VECTOR) {
+ if (syscall_vector != IA32_SYSCALL_VECTOR) {
if (test_bit(syscall_vector, used_vectors) ||
vector_used_by_percpu_irq(syscall_vector)) {
printk(KERN_ERR "lg: couldn't reserve syscall %u\n",
void free_interrupts(void)
{
- if (syscall_vector != SYSCALL_VECTOR)
+ if (syscall_vector != IA32_SYSCALL_VECTOR)
clear_bit(syscall_vector, used_vectors);
}
#include <asm/setup.h>
#include <asm/lguest.h>
#include <asm/uaccess.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
#include <asm/tlbflush.h>
#include "../lg.h"
* we set it now, so we can trap and pass that trap to the Guest if it
* uses the FPU.
*/
- if (cpu->ts && user_has_fpu())
+ if (cpu->ts && fpregs_active())
stts();
/*
wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
/* Clear the host TS bit if it was set above. */
- if (cpu->ts && user_has_fpu())
+ if (cpu->ts && fpregs_active())
clts();
/*
/*
* Similarly, if we took a trap because the Guest used the FPU,
* we have to restore the FPU it expects to see.
- * math_state_restore() may sleep and we may even move off to
+ * fpu__restore() may sleep and we may even move off to
* a different CPU. So all the critical stuff should be done
* before this.
*/
- else if (cpu->regs->trapnum == 7 && !user_has_fpu())
- math_state_restore();
+ else if (cpu->regs->trapnum == 7 && !fpregs_active())
+ fpu__restore(¤t->thread.fpu);
}
/*H:130
* nr_pending is 0 and In_sync is clear, the entries we return will
* still be in the same position on the list when we re-enter
* list_for_each_entry_continue_rcu.
+ *
+ * Note that if entered with 'rdev == NULL' to start at the
+ * beginning, we temporarily assign 'rdev' to an address which
+ * isn't really an rdev, but which can be used by
+ * list_for_each_entry_continue_rcu() to find the first entry.
*/
rcu_read_lock();
if (rdev == NULL)
/* start at the beginning */
- rdev = list_entry_rcu(&mddev->disks, struct md_rdev, same_set);
+ rdev = list_entry(&mddev->disks, struct md_rdev, same_set);
else {
/* release the previous rdev and start from there. */
rdev_dec_pending(rdev, mddev);
switch (r) {
/* async */
- case -EINPROGRESS:
case -EBUSY:
wait_for_completion(&ctx->restart);
reinit_completion(&ctx->restart);
+ /* fall through*/
+ case -EINPROGRESS:
ctx->req = NULL;
ctx->cc_sector++;
continue;
struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx);
struct crypt_config *cc = io->cc;
- if (error == -EINPROGRESS)
+ if (error == -EINPROGRESS) {
+ complete(&ctx->restart);
return;
+ }
if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post)
error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq);
crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio);
if (!atomic_dec_and_test(&ctx->cc_pending))
- goto done;
+ return;
if (bio_data_dir(io->base_bio) == READ)
kcryptd_crypt_read_done(io);
else
kcryptd_crypt_write_io_submit(io, 1);
-done:
- if (!completion_done(&ctx->restart))
- complete(&ctx->restart);
}
static void kcryptd_crypt(struct work_struct *work)
/* blk-mq request-based interface */
*__clone = blk_get_request(bdev_get_queue(bdev),
rq_data_dir(rq), GFP_ATOMIC);
- if (IS_ERR(*__clone))
+ if (IS_ERR(*__clone)) {
/* ENOMEM, requeue */
+ clear_mapinfo(m, map_context);
return r;
+ }
(*__clone)->bio = (*__clone)->biotail = NULL;
(*__clone)->rq_disk = bdev->bd_disk;
(*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;
}
EXPORT_SYMBOL(dm_consume_args);
+static bool __table_type_request_based(unsigned table_type)
+{
+ return (table_type == DM_TYPE_REQUEST_BASED ||
+ table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
static int dm_table_set_type(struct dm_table *t)
{
unsigned i;
* Determine the type from the live device.
* Default to bio-based if device is new.
*/
- if (live_md_type == DM_TYPE_REQUEST_BASED ||
- live_md_type == DM_TYPE_MQ_REQUEST_BASED)
+ if (__table_type_request_based(live_md_type))
request_based = 1;
else
bio_based = 1;
}
t->type = DM_TYPE_MQ_REQUEST_BASED;
- } else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) {
+ } else if (list_empty(devices) && __table_type_request_based(live_md_type)) {
/* inherit live MD type */
t->type = live_md_type;
bool dm_table_request_based(struct dm_table *t)
{
- unsigned table_type = dm_table_get_type(t);
-
- return (table_type == DM_TYPE_REQUEST_BASED ||
- table_type == DM_TYPE_MQ_REQUEST_BASED);
+ return __table_type_request_based(dm_table_get_type(t));
}
bool dm_table_mq_request_based(struct dm_table *t)
dm_put(md);
}
-static void free_rq_clone(struct request *clone, bool must_be_mapped)
+static void free_rq_clone(struct request *clone)
{
struct dm_rq_target_io *tio = clone->end_io_data;
struct mapped_device *md = tio->md;
- WARN_ON_ONCE(must_be_mapped && !clone->q);
-
blk_rq_unprep_clone(clone);
if (md->type == DM_TYPE_MQ_REQUEST_BASED)
rq->sense_len = clone->sense_len;
}
- free_rq_clone(clone, true);
+ free_rq_clone(clone);
if (!rq->q->mq_ops)
blk_end_request_all(rq, error);
else
}
if (clone)
- free_rq_clone(clone, false);
+ free_rq_clone(clone);
}
/*
spin_lock_irqsave(q->queue_lock, flags);
blk_requeue_request(q, rq);
+ blk_run_queue_async(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
struct mapped_device *md = q->queuedata;
struct dm_table *map = dm_get_live_table_fast(md);
struct dm_target *ti;
- sector_t max_sectors;
- int max_size = 0;
+ sector_t max_sectors, max_size = 0;
if (unlikely(!map))
goto out;
max_sectors = min(max_io_len(bvm->bi_sector, ti),
(sector_t) queue_max_sectors(q));
max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
- if (unlikely(max_size < 0)) /* this shouldn't _ever_ happen */
- max_size = 0;
+
+ /*
+ * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
+ * to the targets' merge function since it holds sectors not bytes).
+ * Just doing this as an interim fix for stable@ because the more
+ * comprehensive cleanup of switching to sector_t will impact every
+ * DM target that implements a ->merge hook.
+ */
+ if (max_size > INT_MAX)
+ max_size = INT_MAX;
/*
* merge_bvec_fn() returns number of bytes
* max is precomputed maximal io size
*/
if (max_size && ti->type->merge)
- max_size = ti->type->merge(ti, bvm, biovec, max_size);
+ max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
/*
* If the target doesn't support merge method and some of the devices
* provided their merge_bvec method (we know this by looking for the
dm_kill_unmapped_request(rq, r);
return r;
}
- if (IS_ERR(clone))
- return DM_MAPIO_REQUEUE;
+ if (r != DM_MAPIO_REMAPPED)
+ return r;
if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
/* -ENOMEM */
ti->type->release_clone_rq(clone);
if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) {
/* clone request is allocated at the end of the pdu */
tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io);
- if (!clone_rq(rq, md, tio, GFP_ATOMIC))
- return BLK_MQ_RQ_QUEUE_BUSY;
+ (void) clone_rq(rq, md, tio, GFP_ATOMIC);
queue_kthread_work(&md->kworker, &tio->work);
} else {
/* Direct call is fine since .queue_rq allows allocations */
- if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
- dm_requeue_unmapped_original_request(md, rq);
+ if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+ /* Undo dm_start_request() before requeuing */
+ rq_completed(md, rq_data_dir(rq), false);
+ return BLK_MQ_RQ_QUEUE_BUSY;
+ }
}
return BLK_MQ_RQ_QUEUE_OK;
err = -EBUSY;
}
spin_unlock(&mddev->lock);
- return err;
+ return err ?: len;
}
err = mddev_lock(mddev);
if (err)
if (!mddev->pers || !mddev->pers->sync_request)
return -EINVAL;
- if (cmd_match(page, "frozen"))
- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- else
- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
- flush_workqueue(md_misc_wq);
- if (mddev->sync_thread) {
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- if (mddev_lock(mddev) == 0) {
+ if (cmd_match(page, "frozen"))
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ else
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
+ mddev_lock(mddev) == 0) {
+ flush_workqueue(md_misc_wq);
+ if (mddev->sync_thread) {
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_reap_sync_thread(mddev);
- mddev_unlock(mddev);
}
+ mddev_unlock(mddev);
}
} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
return -EBUSY;
else if (cmd_match(page, "resync"))
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
else if (cmd_match(page, "recover")) {
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
} else if (cmd_match(page, "reshape")) {
int err;
if (mddev->pers->start_reshape == NULL)
return -EINVAL;
err = mddev_lock(mddev);
if (!err) {
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
err = mddev->pers->start_reshape(mddev);
mddev_unlock(mddev);
}
set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
else if (!cmd_match(page, "repair"))
return -EINVAL;
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
}
if (mddev->sysfs_state)
sysfs_put(mddev->sysfs_state);
+ if (mddev->queue)
+ blk_cleanup_queue(mddev->queue);
if (mddev->gendisk) {
del_gendisk(mddev->gendisk);
put_disk(mddev->gendisk);
}
- if (mddev->queue)
- blk_cleanup_queue(mddev->queue);
kfree(mddev);
}
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+ clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
}
dev[j] = rdev1;
- disk_stack_limits(mddev->gendisk, rdev1->bdev,
- rdev1->data_offset << 9);
+ if (mddev->queue)
+ disk_stack_limits(mddev->gendisk, rdev1->bdev,
+ rdev1->data_offset << 9);
if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
conf->has_merge_bvec = 1;
? (sector & (chunk_sects-1))
: sector_div(sector, chunk_sects));
+ /* Restore due to sector_div */
+ sector = bio->bi_iter.bi_sector;
+
if (sectors < bio_sectors(bio)) {
split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
bio_chain(split, bio);
split = bio;
}
- sector = bio->bi_iter.bi_sector;
zone = find_zone(mddev->private, §or);
tmp_dev = map_sector(mddev, zone, sector, §or);
split->bi_bdev = tmp_dev->bdev;
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
static bool stripe_can_batch(struct stripe_head *sh)
{
return test_bit(STRIPE_BATCH_READY, &sh->state) &&
+ !test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
is_full_stripe_write(sh);
}
< IO_THRESHOLD)
md_wakeup_thread(conf->mddev->thread);
+ if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) {
+ int seq = sh->bm_seq;
+ if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) &&
+ sh->batch_head->bm_seq > seq)
+ seq = sh->batch_head->bm_seq;
+ set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state);
+ sh->batch_head->bm_seq = seq;
+ }
+
atomic_inc(&sh->count);
unlock_out:
unlock_two_stripes(head, sh);
pr_debug("skip op %ld on disc %d for sector %llu\n",
bi->bi_rw, i, (unsigned long long)sh->sector);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
- if (sh->batch_head)
- set_bit(STRIPE_BATCH_ERR,
- &sh->batch_head->state);
set_bit(STRIPE_HANDLE, &sh->state);
}
} else
init_async_submit(&submit, 0, tx, NULL, NULL,
to_addr_conv(sh, percpu, j));
- async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
+ tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
if (!last_stripe) {
j++;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
put_cpu();
}
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+{
+ struct stripe_head *sh;
+
+ sh = kmem_cache_zalloc(sc, gfp);
+ if (sh) {
+ spin_lock_init(&sh->stripe_lock);
+ spin_lock_init(&sh->batch_lock);
+ INIT_LIST_HEAD(&sh->batch_list);
+ INIT_LIST_HEAD(&sh->lru);
+ atomic_set(&sh->count, 1);
+ }
+ return sh;
+}
static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
{
struct stripe_head *sh;
- sh = kmem_cache_zalloc(conf->slab_cache, gfp);
+
+ sh = alloc_stripe(conf->slab_cache, gfp);
if (!sh)
return 0;
sh->raid_conf = conf;
- spin_lock_init(&sh->stripe_lock);
-
if (grow_buffers(sh, gfp)) {
shrink_buffers(sh);
kmem_cache_free(conf->slab_cache, sh);
sh->hash_lock_index =
conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS;
/* we just created an active stripe so... */
- atomic_set(&sh->count, 1);
atomic_inc(&conf->active_stripes);
- INIT_LIST_HEAD(&sh->lru);
- spin_lock_init(&sh->batch_lock);
- INIT_LIST_HEAD(&sh->batch_list);
- sh->batch_head = NULL;
release_stripe(sh);
conf->max_nr_stripes++;
return 1;
return ret;
}
+static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
+{
+ unsigned long cpu;
+ int err = 0;
+
+ mddev_suspend(conf->mddev);
+ get_online_cpus();
+ for_each_present_cpu(cpu) {
+ struct raid5_percpu *percpu;
+ struct flex_array *scribble;
+
+ percpu = per_cpu_ptr(conf->percpu, cpu);
+ scribble = scribble_alloc(new_disks,
+ new_sectors / STRIPE_SECTORS,
+ GFP_NOIO);
+
+ if (scribble) {
+ flex_array_free(percpu->scribble);
+ percpu->scribble = scribble;
+ } else {
+ err = -ENOMEM;
+ break;
+ }
+ }
+ put_online_cpus();
+ mddev_resume(conf->mddev);
+ return err;
+}
+
static int resize_stripes(struct r5conf *conf, int newsize)
{
/* Make all the stripes able to hold 'newsize' devices.
struct stripe_head *osh, *nsh;
LIST_HEAD(newstripes);
struct disk_info *ndisks;
- unsigned long cpu;
int err;
struct kmem_cache *sc;
int i;
return -ENOMEM;
for (i = conf->max_nr_stripes; i; i--) {
- nsh = kmem_cache_zalloc(sc, GFP_KERNEL);
+ nsh = alloc_stripe(sc, GFP_KERNEL);
if (!nsh)
break;
nsh->raid_conf = conf;
- spin_lock_init(&nsh->stripe_lock);
-
list_add(&nsh->lru, &newstripes);
}
if (i) {
lock_device_hash_lock(conf, hash));
osh = get_free_stripe(conf, hash);
unlock_device_hash_lock(conf, hash);
- atomic_set(&nsh->count, 1);
+
for(i=0; i<conf->pool_size; i++) {
nsh->dev[i].page = osh->dev[i].page;
nsh->dev[i].orig_page = osh->dev[i].page;
}
- for( ; i<newsize; i++)
- nsh->dev[i].page = NULL;
nsh->hash_lock_index = hash;
kmem_cache_free(conf->slab_cache, osh);
cnt++;
} else
err = -ENOMEM;
- get_online_cpus();
- for_each_present_cpu(cpu) {
- struct raid5_percpu *percpu;
- struct flex_array *scribble;
-
- percpu = per_cpu_ptr(conf->percpu, cpu);
- scribble = scribble_alloc(newsize, conf->chunk_sectors /
- STRIPE_SECTORS, GFP_NOIO);
-
- if (scribble) {
- flex_array_free(percpu->scribble);
- percpu->scribble = scribble;
- } else {
- err = -ENOMEM;
- break;
- }
- }
- put_online_cpus();
-
/* Step 4, return new stripes to service */
while(!list_empty(&newstripes)) {
nsh = list_entry(newstripes.next, struct stripe_head, lru);
conf->slab_cache = sc;
conf->active_name = 1-conf->active_name;
- conf->pool_size = newsize;
+ if (!err)
+ conf->pool_size = newsize;
return err;
}
}
rdev_dec_pending(rdev, conf->mddev);
- if (sh->batch_head && !uptodate)
+ if (sh->batch_head && !uptodate && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
(unsigned long long)(*bip)->bi_iter.bi_sector,
(unsigned long long)sh->sector, dd_idx);
- spin_unlock_irq(&sh->stripe_lock);
if (conf->mddev->bitmap && firstwrite) {
+ /* Cannot hold spinlock over bitmap_startwrite,
+ * but must ensure this isn't added to a batch until
+ * we have added to the bitmap and set bm_seq.
+ * So set STRIPE_BITMAP_PENDING to prevent
+ * batching.
+ * If multiple add_stripe_bio() calls race here they
+ * much all set STRIPE_BITMAP_PENDING. So only the first one
+ * to complete "bitmap_startwrite" gets to set
+ * STRIPE_BIT_DELAY. This is important as once a stripe
+ * is added to a batch, STRIPE_BIT_DELAY cannot be changed
+ * any more.
+ */
+ set_bit(STRIPE_BITMAP_PENDING, &sh->state);
+ spin_unlock_irq(&sh->stripe_lock);
bitmap_startwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0);
- sh->bm_seq = conf->seq_flush+1;
- set_bit(STRIPE_BIT_DELAY, &sh->state);
+ spin_lock_irq(&sh->stripe_lock);
+ clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
+ if (!sh->batch_head) {
+ sh->bm_seq = conf->seq_flush+1;
+ set_bit(STRIPE_BIT_DELAY, &sh->state);
+ }
}
+ spin_unlock_irq(&sh->stripe_lock);
if (stripe_can_batch(sh))
stripe_add_to_batch_list(conf, sh);
/* reconstruct-write isn't being forced */
return 0;
for (i = 0; i < s->failed; i++) {
- if (!test_bit(R5_UPTODATE, &fdev[i]->flags) &&
+ if (s->failed_num[i] != sh->pd_idx &&
+ s->failed_num[i] != sh->qd_idx &&
+ !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
!test_bit(R5_OVERWRITE, &fdev[i]->flags))
return 1;
}
*/
BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
BUG_ON(test_bit(R5_Wantread, &dev->flags));
+ BUG_ON(sh->batch_head);
if ((s->uptodate == disks - 1) &&
(s->failed && (disk_idx == s->failed_num[0] ||
disk_idx == s->failed_num[1]))) {
{
int i;
- BUG_ON(sh->batch_head);
/* look for blocks to read/compute, skip this if a compute
* is already in flight, or if the stripe contents are in the
* midst of changing due to a write
set_bit(STRIPE_HANDLE, &sh->state);
}
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+ unsigned long handle_flags);
/* handle_stripe_clean_event
* any written block on an uptodate or failed drive can be returned.
* Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
int discard_pending = 0;
struct stripe_head *head_sh = sh;
bool do_endio = false;
- int wakeup_nr = 0;
for (i = disks; i--; )
if (sh->dev[i].written) {
if (atomic_dec_and_test(&conf->pending_full_writes))
md_wakeup_thread(conf->mddev->thread);
- if (!head_sh->batch_head || !do_endio)
- return;
- for (i = 0; i < head_sh->disks; i++) {
- if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
- wakeup_nr++;
- }
- while (!list_empty(&head_sh->batch_list)) {
- int i;
- sh = list_first_entry(&head_sh->batch_list,
- struct stripe_head, batch_list);
- list_del_init(&sh->batch_list);
-
- set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
- head_sh->state & ~((1 << STRIPE_ACTIVE) |
- (1 << STRIPE_PREREAD_ACTIVE) |
- STRIPE_EXPAND_SYNC_FLAG));
- sh->check_state = head_sh->check_state;
- sh->reconstruct_state = head_sh->reconstruct_state;
- for (i = 0; i < sh->disks; i++) {
- if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
- wakeup_nr++;
- sh->dev[i].flags = head_sh->dev[i].flags;
- }
-
- spin_lock_irq(&sh->stripe_lock);
- sh->batch_head = NULL;
- spin_unlock_irq(&sh->stripe_lock);
- if (sh->state & STRIPE_EXPAND_SYNC_FLAG)
- set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
- }
-
- spin_lock_irq(&head_sh->stripe_lock);
- head_sh->batch_head = NULL;
- spin_unlock_irq(&head_sh->stripe_lock);
- wake_up_nr(&conf->wait_for_overlap, wakeup_nr);
- if (head_sh->state & STRIPE_EXPAND_SYNC_FLAG)
- set_bit(STRIPE_HANDLE, &head_sh->state);
+ if (head_sh->batch_head && do_endio)
+ break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
}
static void handle_stripe_dirtying(struct r5conf *conf,
static int clear_batch_ready(struct stripe_head *sh)
{
+ /* Return '1' if this is a member of batch, or
+ * '0' if it is a lone stripe or a head which can now be
+ * handled.
+ */
struct stripe_head *tmp;
if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state))
- return 0;
+ return (sh->batch_head && sh->batch_head != sh);
spin_lock(&sh->stripe_lock);
if (!sh->batch_head) {
spin_unlock(&sh->stripe_lock);
return 0;
}
-static void check_break_stripe_batch_list(struct stripe_head *sh)
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+ unsigned long handle_flags)
{
- struct stripe_head *head_sh, *next;
+ struct stripe_head *sh, *next;
int i;
+ int do_wakeup = 0;
- if (!test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
- return;
+ list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) {
- head_sh = sh;
- do {
- sh = list_first_entry(&sh->batch_list,
- struct stripe_head, batch_list);
- BUG_ON(sh == head_sh);
- } while (!test_bit(STRIPE_DEGRADED, &sh->state));
-
- while (sh != head_sh) {
- next = list_first_entry(&sh->batch_list,
- struct stripe_head, batch_list);
list_del_init(&sh->batch_list);
- set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
- head_sh->state & ~((1 << STRIPE_ACTIVE) |
- (1 << STRIPE_PREREAD_ACTIVE) |
- (1 << STRIPE_DEGRADED) |
- STRIPE_EXPAND_SYNC_FLAG));
+ WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
+ (1 << STRIPE_SYNCING) |
+ (1 << STRIPE_REPLACED) |
+ (1 << STRIPE_PREREAD_ACTIVE) |
+ (1 << STRIPE_DELAYED) |
+ (1 << STRIPE_BIT_DELAY) |
+ (1 << STRIPE_FULL_WRITE) |
+ (1 << STRIPE_BIOFILL_RUN) |
+ (1 << STRIPE_COMPUTE_RUN) |
+ (1 << STRIPE_OPS_REQ_PENDING) |
+ (1 << STRIPE_DISCARD) |
+ (1 << STRIPE_BATCH_READY) |
+ (1 << STRIPE_BATCH_ERR) |
+ (1 << STRIPE_BITMAP_PENDING)));
+ WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
+ (1 << STRIPE_REPLACED)));
+
+ set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+ (1 << STRIPE_DEGRADED)),
+ head_sh->state & (1 << STRIPE_INSYNC));
+
sh->check_state = head_sh->check_state;
sh->reconstruct_state = head_sh->reconstruct_state;
- for (i = 0; i < sh->disks; i++)
+ for (i = 0; i < sh->disks; i++) {
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+ do_wakeup = 1;
sh->dev[i].flags = head_sh->dev[i].flags &
(~((1 << R5_WriteError) | (1 << R5_Overlap)));
-
+ }
spin_lock_irq(&sh->stripe_lock);
sh->batch_head = NULL;
spin_unlock_irq(&sh->stripe_lock);
-
- set_bit(STRIPE_HANDLE, &sh->state);
+ if (handle_flags == 0 ||
+ sh->state & handle_flags)
+ set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
-
- sh = next;
}
+ spin_lock_irq(&head_sh->stripe_lock);
+ head_sh->batch_head = NULL;
+ spin_unlock_irq(&head_sh->stripe_lock);
+ for (i = 0; i < head_sh->disks; i++)
+ if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
+ do_wakeup = 1;
+ if (head_sh->state & handle_flags)
+ set_bit(STRIPE_HANDLE, &head_sh->state);
+
+ if (do_wakeup)
+ wake_up(&head_sh->raid_conf->wait_for_overlap);
}
static void handle_stripe(struct stripe_head *sh)
return;
}
- check_break_stripe_batch_list(sh);
+ if (test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
+ break_stripe_batch_list(sh, 0);
if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
spin_lock(&sh->stripe_lock);
if (s.failed > conf->max_degraded) {
sh->check_state = 0;
sh->reconstruct_state = 0;
+ break_stripe_batch_list(sh, 0);
if (s.to_read+s.to_write+s.written)
handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
if (s.syncing + s.replacing)
percpu->spare_page = alloc_page(GFP_KERNEL);
if (!percpu->scribble)
percpu->scribble = scribble_alloc(max(conf->raid_disks,
- conf->previous_raid_disks), conf->chunk_sectors /
- STRIPE_SECTORS, GFP_KERNEL);
+ conf->previous_raid_disks),
+ max(conf->chunk_sectors,
+ conf->prev_chunk_sectors)
+ / STRIPE_SECTORS,
+ GFP_KERNEL);
if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
free_scratch_buffer(conf, percpu);
if (!check_stripe_cache(mddev))
return -ENOSPC;
+ if (mddev->new_chunk_sectors > mddev->chunk_sectors ||
+ mddev->delta_disks > 0)
+ if (resize_chunks(conf,
+ conf->previous_raid_disks
+ + max(0, mddev->delta_disks),
+ max(mddev->new_chunk_sectors,
+ mddev->chunk_sectors)
+ ) < 0)
+ return -ENOMEM;
return resize_stripes(conf, (conf->previous_raid_disks
+ mddev->delta_disks));
}
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
mddev->sync_thread = md_register_thread(md_do_sync, mddev,
STRIPE_ON_RELEASE_LIST,
STRIPE_BATCH_READY,
STRIPE_BATCH_ERR,
+ STRIPE_BITMAP_PENDING, /* Being added to bitmap, don't add
+ * to batch yet.
+ */
};
-#define STRIPE_EXPAND_SYNC_FLAG \
+#define STRIPE_EXPAND_SYNC_FLAGS \
((1 << STRIPE_EXPAND_SOURCE) |\
(1 << STRIPE_EXPAND_READY) |\
(1 << STRIPE_EXPANDING) |\
config MEDIA_CONTROLLER_DVB
bool "Enable Media controller for DVB"
depends on MEDIA_CONTROLLER
+ depends on BROKEN
---help---
Enable the media controller API support for DVB.
This is used in the Hauppauge PVR-350 card. There is a driver
homepage at <http://www.ivtvdriver.org>.
+ In order to use this module, you will need to boot with PAT disabled
+ on x86 systems, using the nopat kernel parameter.
+
To compile this driver as a module, choose M here: the
module will be called ivtvfb.
#include <linux/ivtvfb.h>
#include <linux/slab.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
+#ifdef CONFIG_X86_64
+#include <asm/pat.h>
#endif
#include "ivtv-driver.h"
/* Buffer size */
u32 video_buffer_size;
-#ifdef CONFIG_MTRR
/* video_base rounded down as required by hardware MTRRs */
unsigned long fb_start_aligned_physaddr;
/* video_base rounded up as required by hardware MTRRs */
unsigned long fb_end_aligned_physaddr;
-#endif
+ int wc_cookie;
/* Store the buffer offset */
int set_osd_coords_x;
static int ivtvfb_init_io(struct ivtv *itv)
{
struct osd_info *oi = itv->osd_info;
+ /* Find the largest power of two that maps the whole buffer */
+ int size_shift = 31;
mutex_lock(&itv->serialize_lock);
if (ivtv_init_on_first_open(itv)) {
oi->video_pbase, oi->video_vbase,
oi->video_buffer_size / 1024);
-#ifdef CONFIG_MTRR
- {
- /* Find the largest power of two that maps the whole buffer */
- int size_shift = 31;
-
- while (!(oi->video_buffer_size & (1 << size_shift))) {
- size_shift--;
- }
- size_shift++;
- oi->fb_start_aligned_physaddr = oi->video_pbase & ~((1 << size_shift) - 1);
- oi->fb_end_aligned_physaddr = oi->video_pbase + oi->video_buffer_size;
- oi->fb_end_aligned_physaddr += (1 << size_shift) - 1;
- oi->fb_end_aligned_physaddr &= ~((1 << size_shift) - 1);
- if (mtrr_add(oi->fb_start_aligned_physaddr,
- oi->fb_end_aligned_physaddr - oi->fb_start_aligned_physaddr,
- MTRR_TYPE_WRCOMB, 1) < 0) {
- IVTVFB_INFO("disabled mttr\n");
- oi->fb_start_aligned_physaddr = 0;
- oi->fb_end_aligned_physaddr = 0;
- }
- }
-#endif
-
+ while (!(oi->video_buffer_size & (1 << size_shift)))
+ size_shift--;
+ size_shift++;
+ oi->fb_start_aligned_physaddr = oi->video_pbase & ~((1 << size_shift) - 1);
+ oi->fb_end_aligned_physaddr = oi->video_pbase + oi->video_buffer_size;
+ oi->fb_end_aligned_physaddr += (1 << size_shift) - 1;
+ oi->fb_end_aligned_physaddr &= ~((1 << size_shift) - 1);
+ oi->wc_cookie = arch_phys_wc_add(oi->fb_start_aligned_physaddr,
+ oi->fb_end_aligned_physaddr -
+ oi->fb_start_aligned_physaddr);
/* Blank the entire osd. */
memset_io(oi->video_vbase, 0, oi->video_buffer_size);
/* Release pseudo palette */
kfree(oi->ivtvfb_info.pseudo_palette);
-
-#ifdef CONFIG_MTRR
- if (oi->fb_end_aligned_physaddr) {
- mtrr_del(-1, oi->fb_start_aligned_physaddr,
- oi->fb_end_aligned_physaddr - oi->fb_start_aligned_physaddr);
- }
-#endif
-
+ arch_phys_wc_del(oi->wc_cookie);
kfree(oi);
itv->osd_info = NULL;
}
int registered = 0;
int err;
+#ifdef CONFIG_X86_64
+ if (WARN(pat_enabled(),
+ "ivtvfb needs PAT disabled, boot with nopat kernel parameter\n")) {
+ return -ENODEV;
+ }
+#endif
+
if (ivtvfb_card_id < -1 || ivtvfb_card_id >= IVTV_MAX_CARDS) {
printk(KERN_ERR "ivtvfb: ivtvfb_card_id parameter is out of range (valid range: -1 - %d)\n",
IVTV_MAX_CARDS - 1);
EXPORT_SYMBOL_GPL(da9052_adc_read_temp);
static const struct mfd_cell da9052_subdev_info[] = {
+ {
+ .name = "da9052-regulator",
+ .id = 0,
+ },
{
.name = "da9052-regulator",
.id = 1,
.name = "da9052-regulator",
.id = 13,
},
- {
- .name = "da9052-regulator",
- .id = 14,
- },
{
.name = "da9052-onkey",
},
md->reset_done &= ~type;
}
+int mmc_access_rpmb(struct mmc_queue *mq)
+{
+ struct mmc_blk_data *md = mq->data;
+ /*
+ * If this is a RPMB partition access, return ture
+ */
+ if (md && md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
+ return true;
+
+ return false;
+}
+
static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
{
struct mmc_blk_data *md = mq->data;
return BLKPREP_KILL;
}
- if (mq && mmc_card_removed(mq->card))
+ if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq)))
return BLKPREP_KILL;
req->cmd_flags |= REQ_DONTPREP;
extern int mmc_packed_init(struct mmc_queue *, struct mmc_card *);
extern void mmc_packed_clean(struct mmc_queue *);
+extern int mmc_access_rpmb(struct mmc_queue *);
+
#endif
switch (mode) {
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
+ case PM_RESTORE_PREPARE:
spin_lock_irqsave(&host->lock, flags);
host->rescan_disable = 1;
spin_unlock_irqrestore(&host->lock, flags);
if (ios->clock) {
unsigned int clock_min = ~0U;
- u32 clkdiv;
+ int clkdiv;
spin_lock_bh(&host->lock);
if (!host->mode_reg) {
/* Calculate clock divider */
if (host->caps.has_odd_clk_div) {
clkdiv = DIV_ROUND_UP(host->bus_hz, clock_min) - 2;
- if (clkdiv > 511) {
+ if (clkdiv < 0) {
+ dev_warn(&mmc->class_dev,
+ "clock %u too fast; using %lu\n",
+ clock_min, host->bus_hz / 2);
+ clkdiv = 0;
+ } else if (clkdiv > 511) {
dev_warn(&mmc->class_dev,
"clock %u too slow; using %lu\n",
clock_min, host->bus_hz / (511 + 2));
host->ring_size = PAGE_SIZE / sizeof(struct idmac_desc);
/* Forward link the descriptor list */
- for (i = 0, p = host->sg_cpu; i < host->ring_size - 1; i++, p++)
+ for (i = 0, p = host->sg_cpu; i < host->ring_size - 1; i++, p++) {
p->des3 = cpu_to_le32(host->sg_dma +
(sizeof(struct idmac_desc) * (i + 1)));
+ p->des1 = 0;
+ }
/* Set the last descriptor as the end-of-ring descriptor */
p->des3 = cpu_to_le32(host->sg_dma);
int gpio_cd = mmc_gpio_get_cd(mmc);
/* Use platform get_cd function, else try onboard card detect */
- if (brd->quirks & DW_MCI_QUIRK_BROKEN_CARD_DETECTION)
+ if ((brd->quirks & DW_MCI_QUIRK_BROKEN_CARD_DETECTION) ||
+ (mmc->caps & MMC_CAP_NONREMOVABLE))
present = 1;
else if (!IS_ERR_VALUE(gpio_cd))
present = gpio_cd;
host = mmc_priv(mmc);
host->mmc = mmc;
host->addr = reg;
- host->timeout = msecs_to_jiffies(1000);
+ host->timeout = msecs_to_jiffies(10000);
host->ccs_enable = !pd || !pd->ccs_unsupported;
host->clk_ctrl2_enable = pd && pd->clk_ctrl2_present;
*/
if (data && data->type)
flash_name = data->type;
- else if (!strcmp(spi->modalias, "nor-jedec"))
+ else if (!strcmp(spi->modalias, "spi-nor"))
flash_name = NULL; /* auto-detect */
else
flash_name = spi->modalias;
* since most of these flash are compatible to some extent, and their
* differences can often be differentiated by the JEDEC read-ID command, we
* encourage new users to add support to the spi-nor library, and simply bind
- * against a generic string here (e.g., "nor-jedec").
+ * against a generic string here (e.g., "jedec,spi-nor").
*
* Many flash names are kept here in this list (as well as in spi-nor.c) to
* keep them available as module aliases for existing platforms.
* Generic support for SPI NOR that can be identified by the JEDEC READ
* ID opcode (0x9F). Use this, if possible.
*/
- {"nor-jedec"},
+ {"spi-nor"},
{ },
};
MODULE_DEVICE_TABLE(spi, m25p_ids);
err = ret;
}
- err = mtdtest_relax();
- if (err)
+ ret = mtdtest_relax();
+ if (ret) {
+ err = ret;
goto out;
+ }
}
if (err)
blk_rq_map_sg(req->q, req, pdu->usgl.sg);
ret = ubiblock_read(pdu);
+ rq_flush_dcache_pages(req);
+
blk_mq_end_request(req, ret);
}
out:
if (ret)
bond_opt_error_interpret(bond, opt, ret, val);
- else
+ else if (bond->dev->reg_state == NETREG_REGISTERED)
call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev);
return ret;
cf->can_id |= CAN_RTR_FLAG;
}
- if (!(id_xcan & XCAN_IDR_SRR_MASK)) {
- data[0] = priv->read_reg(priv, XCAN_RXFIFO_DW1_OFFSET);
- data[1] = priv->read_reg(priv, XCAN_RXFIFO_DW2_OFFSET);
+ /* DW1/DW2 must always be read to remove message from RXFIFO */
+ data[0] = priv->read_reg(priv, XCAN_RXFIFO_DW1_OFFSET);
+ data[1] = priv->read_reg(priv, XCAN_RXFIFO_DW2_OFFSET);
+ if (!(cf->can_id & CAN_RTR_FLAG)) {
/* Change Xilinx CAN data format to socketCAN data format */
if (cf->can_dlc > 0)
*(__be32 *)(cf->data) = cpu_to_be32(data[0]);
#if IS_ENABLED(CONFIG_NET_DSA_MV88E6171)
unregister_switch_driver(&mv88e6171_switch_driver);
#endif
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6352)
+ unregister_switch_driver(&mv88e6352_switch_driver);
+#endif
#if IS_ENABLED(CONFIG_NET_DSA_MV88E6123_61_65)
unregister_switch_driver(&mv88e6123_61_65_switch_driver);
#endif
config AMD_XGBE
tristate "AMD 10GbE Ethernet driver"
depends on (OF_NET || ACPI) && HAS_IOMEM && HAS_DMA
+ depends on ARM64 || COMPILE_TEST
select PHYLIB
select AMD_XGBE_PHY
select BITREVERSE
if (napi_schedule_prep(napi)) {
/* Disable Tx and Rx interrupts */
if (pdata->per_channel_irq)
- disable_irq(channel->dma_irq);
+ disable_irq_nosync(channel->dma_irq);
else
xgbe_disable_rx_tx_ints(pdata);
config NET_XGENE
tristate "APM X-Gene SoC Ethernet Driver"
depends on HAS_DMA
+ depends on ARCH_XGENE || COMPILE_TEST
select PHYLIB
help
This is the Ethernet driver for the on-chip ethernet interface on the
ssb_bus_may_powerdown(sdev->bus);
err_out_free_dev:
+ netif_napi_del(&bp->napi);
free_netdev(dev);
out:
b44_unregister_phy_one(bp);
ssb_device_disable(sdev, 0);
ssb_bus_may_powerdown(sdev->bus);
+ netif_napi_del(&bp->napi);
free_netdev(dev);
ssb_pcihost_set_power_state(sdev, PCI_D3hot);
ssb_set_drvdata(sdev, NULL);
int stats_state;
/* used for synchronization of concurrent threads statistics handling */
- struct mutex stats_lock;
+ struct semaphore stats_lock;
/* used by dmae command loader */
struct dmae_command stats_dmae;
{
struct bnx2x *bp = netdev_priv(dev);
+ if (pci_num_vf(bp->pdev)) {
+ DP(BNX2X_MSG_IOV, "VFs are enabled, can not change MTU\n");
+ return -EPERM;
+ }
+
if (bp->recovery_state != BNX2X_RECOVERY_DONE) {
BNX2X_ERR("Can't perform change MTU during parity recovery\n");
return -EAGAIN;
}
bp = netdev_priv(dev);
- if (pci_num_vf(bp->pdev)) {
- DP(BNX2X_MSG_IOV, "VFs are enabled, can not change MTU\n");
- return -EPERM;
- }
-
if (bp->recovery_state != BNX2X_RECOVERY_DONE) {
BNX2X_ERR("Handling parity error recovery. Try again later\n");
return -EAGAIN;
mutex_init(&bp->port.phy_mutex);
mutex_init(&bp->fw_mb_mutex);
mutex_init(&bp->drv_info_mutex);
- mutex_init(&bp->stats_lock);
+ sema_init(&bp->stats_lock, 1);
bp->drv_info_mng_owner = false;
INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task);
/* Management FW 'remembers' living interfaces. Allow it some time
* to forget previously living interfaces, allowing a proper re-load.
*/
- if (is_kdump_kernel())
- msleep(5000);
+ if (is_kdump_kernel()) {
+ ktime_t now = ktime_get_boottime();
+ ktime_t fw_ready_time = ktime_set(5, 0);
+
+ if (ktime_before(now, fw_ready_time))
+ msleep(ktime_ms_delta(fw_ready_time, now));
+ }
/* An estimated maximum supported CoS number according to the chip
* version.
cancel_delayed_work_sync(&bp->sp_task);
cancel_delayed_work_sync(&bp->period_task);
- mutex_lock(&bp->stats_lock);
- bp->stats_state = STATS_STATE_DISABLED;
- mutex_unlock(&bp->stats_lock);
+ if (!down_timeout(&bp->stats_lock, HZ / 10)) {
+ bp->stats_state = STATS_STATE_DISABLED;
+ up(&bp->stats_lock);
+ }
bnx2x_save_statistics(bp);
* that context in case someone is in the middle of a transition.
* For other events, wait a bit until lock is taken.
*/
- if (!mutex_trylock(&bp->stats_lock)) {
+ if (down_trylock(&bp->stats_lock)) {
if (event == STATS_EVENT_UPDATE)
return;
DP(BNX2X_MSG_STATS,
"Unlikely stats' lock contention [event %d]\n", event);
- mutex_lock(&bp->stats_lock);
+ if (unlikely(down_timeout(&bp->stats_lock, HZ / 10))) {
+ BNX2X_ERR("Failed to take stats lock [event %d]\n",
+ event);
+ return;
+ }
}
bnx2x_stats_stm[state][event].action(bp);
bp->stats_state = bnx2x_stats_stm[state][event].next_state;
- mutex_unlock(&bp->stats_lock);
+ up(&bp->stats_lock);
if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp))
DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n",
/* Wait for statistics to end [while blocking further requests],
* then run supplied function 'safely'.
*/
- mutex_lock(&bp->stats_lock);
+ rc = down_timeout(&bp->stats_lock, HZ / 10);
+ if (unlikely(rc)) {
+ BNX2X_ERR("Failed to take statistics lock for safe execution\n");
+ goto out_no_lock;
+ }
bnx2x_stats_comp(bp);
while (bp->stats_pending && cnt--)
/* No need to restart statistics - if they're enabled, the timer
* will restart the statistics.
*/
- mutex_unlock(&bp->stats_lock);
-
+ up(&bp->stats_lock);
+out_no_lock:
return rc;
}
phy_name = "external RGMII (no delay)";
else
phy_name = "external RGMII (TX delay)";
- reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
- reg |= RGMII_MODE_EN | id_mode_dis;
- bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
bcmgenet_sys_writel(priv,
PORT_MODE_EXT_GPHY, SYS_PORT_CTRL);
break;
return -EINVAL;
}
+ /* This is an external PHY (xMII), so we need to enable the RGMII
+ * block for the interface to work
+ */
+ if (priv->ext_phy) {
+ reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
+ reg |= RGMII_MODE_EN | id_mode_dis;
+ bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
+ }
+
if (init)
dev_info(kdev, "configuring instance for %s\n", phy_name);
if (status == BFA_STATUS_OK)
bfa_ioc_lpu_start(ioc);
else
- bfa_nw_iocpf_timeout(ioc);
+ bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_TIMEOUT);
return status;
}
}
if (ioc->iocpf.poll_time >= BFA_IOC_TOV) {
- bfa_nw_iocpf_timeout(ioc);
+ bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_TIMEOUT);
} else {
ioc->iocpf.poll_time += BFA_IOC_POLL_TOV;
mod_timer(&ioc->iocpf_timer, jiffies +
setup_timer(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout,
((unsigned long)bnad));
- /* Now start the timer before calling IOC */
- mod_timer(&bnad->bna.ioceth.ioc.iocpf_timer,
- jiffies + msecs_to_jiffies(BNA_IOC_TIMER_FREQ));
-
/*
* Start the chip
* If the call back comes with error, we bail out.
u32 *bfi_image_size, char *fw_name)
{
const struct firmware *fw;
+ u32 n;
if (request_firmware(&fw, fw_name, &pdev->dev)) {
pr_alert("Can't locate firmware %s\n", fw_name);
*bfi_image_size = fw->size/sizeof(u32);
bfi_fw = fw;
+ /* Convert loaded firmware to host order as it is stored in file
+ * as sequence of LE32 integers.
+ */
+ for (n = 0; n < *bfi_image_size; n++)
+ le32_to_cpus(*bfi_image + n);
+
return *bfi_image;
error:
return NULL;
else
phydev->supported &= PHY_BASIC_FEATURES;
+ if (bp->caps & MACB_CAPS_NO_GIGABIT_HALF)
+ phydev->supported &= ~SUPPORTED_1000baseT_Half;
+
phydev->advertising = phydev->supported;
bp->link = 0;
struct macb_queue *queue = dev_id;
struct macb *bp = queue->bp;
struct net_device *dev = bp->dev;
- u32 status;
+ u32 status, ctrl;
status = queue_readl(queue, ISR);
* add that if/when we get our hands on a full-blown MII PHY.
*/
+ /* There is a hardware issue under heavy load where DMA can
+ * stop, this causes endless "used buffer descriptor read"
+ * interrupts but it can be cleared by re-enabling RX. See
+ * the at91 manual, section 41.3.1 or the Zynq manual
+ * section 16.7.4 for details.
+ */
+ if (status & MACB_BIT(RXUBR)) {
+ ctrl = macb_readl(bp, NCR);
+ macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE));
+ macb_writel(bp, NCR, ctrl | MACB_BIT(RE));
+
+ if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
+ macb_writel(bp, ISR, MACB_BIT(RXUBR));
+ }
+
if (status & MACB_BIT(ISR_ROVR)) {
/* We missed at least one packet */
if (macb_is_gem(bp))
.init = at91ether_init,
};
+static const struct macb_config zynq_config = {
+ .caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE |
+ MACB_CAPS_NO_GIGABIT_HALF,
+ .dma_burst_length = 16,
+ .clk_init = macb_clk_init,
+ .init = macb_init,
+};
+
static const struct of_device_id macb_dt_ids[] = {
{ .compatible = "cdns,at32ap7000-macb" },
{ .compatible = "cdns,at91sam9260-macb", .data = &at91sam9260_config },
{ .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config },
{ .compatible = "cdns,at91rm9200-emac", .data = &emac_config },
{ .compatible = "cdns,emac", .data = &emac_config },
+ { .compatible = "cdns,zynq-gem", .data = &zynq_config },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, macb_dt_ids);
#define MACB_CAPS_ISR_CLEAR_ON_WRITE 0x00000001
#define MACB_CAPS_USRIO_HAS_CLKEN 0x00000002
#define MACB_CAPS_USRIO_DEFAULT_IS_MII 0x00000004
+#define MACB_CAPS_NO_GIGABIT_HALF 0x00000008
#define MACB_CAPS_FIFO_MODE 0x10000000
#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
#define MACB_CAPS_SG_DISABLED 0x40000000
{
struct enic *enic = netdev_priv(netdev);
struct vnic_devcmd_fw_info *fw_info;
+ int err;
- enic_dev_fw_info(enic, &fw_info);
+ err = enic_dev_fw_info(enic, &fw_info);
+ /* return only when pci_zalloc_consistent fails in vnic_dev_fw_info
+ * For other failures, like devcmd failure, we return previously
+ * recorded info.
+ */
+ if (err == -ENOMEM)
+ return;
strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
struct enic *enic = netdev_priv(netdev);
struct vnic_stats *vstats;
unsigned int i;
-
- enic_dev_stats_dump(enic, &vstats);
+ int err;
+
+ err = enic_dev_stats_dump(enic, &vstats);
+ /* return only when pci_zalloc_consistent fails in vnic_dev_stats_dump
+ * For other failures, like devcmd failure, we return previously
+ * recorded stats.
+ */
+ if (err == -ENOMEM)
+ return;
for (i = 0; i < enic_n_tx_stats; i++)
*(data++) = ((u64 *)&vstats->tx)[enic_tx_stats[i].index];
{
struct enic *enic = netdev_priv(netdev);
struct vnic_stats *stats;
+ int err;
- enic_dev_stats_dump(enic, &stats);
+ err = enic_dev_stats_dump(enic, &stats);
+ /* return only when pci_zalloc_consistent fails in vnic_dev_stats_dump
+ * For other failures, like devcmd failure, we return previously
+ * recorded stats.
+ */
+ if (err == -ENOMEM)
+ return net_stats;
net_stats->tx_packets = stats->tx.tx_frames_ok;
net_stats->tx_bytes = stats->tx.tx_bytes_ok;
*/
enic_calc_int_moderation(enic, &enic->rq[rq]);
+ enic_poll_unlock_napi(&enic->rq[rq]);
if (work_done < work_to_do) {
/* Some work done, but not enough to stay in polling,
enic_set_int_moderation(enic, &enic->rq[rq]);
vnic_intr_unmask(&enic->intr[intr]);
}
- enic_poll_unlock_napi(&enic->rq[rq]);
return work_done;
}
struct vnic_rq_buf *buf;
u32 fetch_index;
unsigned int count = rq->ring.desc_count;
+ int i;
buf = rq->to_clean;
- while (vnic_rq_desc_used(rq) > 0) {
-
+ for (i = 0; i < rq->ring.desc_count; i++) {
(*buf_clean)(rq, buf);
-
- buf = rq->to_clean = buf->next;
- rq->ring.desc_avail++;
+ buf = buf->next;
}
+ rq->ring.desc_avail = rq->ring.desc_count - 1;
/* Use current fetch_index as the ring starting point */
fetch_index = ioread32(&rq->ctrl->fetch_index);
total_size = buf_len;
get_fat_cmd.size = sizeof(struct be_cmd_req_get_fat) + 60*1024;
- get_fat_cmd.va = pci_alloc_consistent(adapter->pdev,
- get_fat_cmd.size,
- &get_fat_cmd.dma);
+ get_fat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+ get_fat_cmd.size,
+ &get_fat_cmd.dma, GFP_ATOMIC);
if (!get_fat_cmd.va) {
dev_err(&adapter->pdev->dev,
"Memory allocation failure while reading FAT data\n");
log_offset += buf_size;
}
err:
- pci_free_consistent(adapter->pdev, get_fat_cmd.size,
- get_fat_cmd.va, get_fat_cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
+ get_fat_cmd.va, get_fat_cmd.dma);
spin_unlock_bh(&adapter->mcc_lock);
return status;
}
return -EINVAL;
cmd.size = sizeof(struct be_cmd_resp_port_type);
- cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+ cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+ GFP_ATOMIC);
if (!cmd.va) {
dev_err(&adapter->pdev->dev, "Memory allocation failed\n");
return -ENOMEM;
}
- memset(cmd.va, 0, cmd.size);
spin_lock_bh(&adapter->mcc_lock);
}
err:
spin_unlock_bh(&adapter->mcc_lock);
- pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
return status;
}
goto err;
}
cmd.size = sizeof(struct be_cmd_req_get_phy_info);
- cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+ cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+ GFP_ATOMIC);
if (!cmd.va) {
dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
status = -ENOMEM;
BE_SUPPORTED_SPEED_1GBPS;
}
}
- pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
err:
spin_unlock_bh(&adapter->mcc_lock);
return status;
memset(&attribs_cmd, 0, sizeof(struct be_dma_mem));
attribs_cmd.size = sizeof(struct be_cmd_resp_cntl_attribs);
- attribs_cmd.va = pci_alloc_consistent(adapter->pdev, attribs_cmd.size,
- &attribs_cmd.dma);
+ attribs_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+ attribs_cmd.size,
+ &attribs_cmd.dma, GFP_ATOMIC);
if (!attribs_cmd.va) {
dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
status = -ENOMEM;
err:
mutex_unlock(&adapter->mbox_lock);
if (attribs_cmd.va)
- pci_free_consistent(adapter->pdev, attribs_cmd.size,
- attribs_cmd.va, attribs_cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, attribs_cmd.size,
+ attribs_cmd.va, attribs_cmd.dma);
return status;
}
memset(&get_mac_list_cmd, 0, sizeof(struct be_dma_mem));
get_mac_list_cmd.size = sizeof(struct be_cmd_resp_get_mac_list);
- get_mac_list_cmd.va = pci_alloc_consistent(adapter->pdev,
- get_mac_list_cmd.size,
- &get_mac_list_cmd.dma);
+ get_mac_list_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+ get_mac_list_cmd.size,
+ &get_mac_list_cmd.dma,
+ GFP_ATOMIC);
if (!get_mac_list_cmd.va) {
dev_err(&adapter->pdev->dev,
out:
spin_unlock_bh(&adapter->mcc_lock);
- pci_free_consistent(adapter->pdev, get_mac_list_cmd.size,
- get_mac_list_cmd.va, get_mac_list_cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
+ get_mac_list_cmd.va, get_mac_list_cmd.dma);
return status;
}
memset(&cmd, 0, sizeof(struct be_dma_mem));
cmd.size = sizeof(struct be_cmd_req_set_mac_list);
- cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
- &cmd.dma, GFP_KERNEL);
+ cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+ GFP_KERNEL);
if (!cmd.va)
return -ENOMEM;
memset(&cmd, 0, sizeof(struct be_dma_mem));
cmd.size = sizeof(struct be_cmd_resp_acpi_wol_magic_config_v1);
- cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+ cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+ GFP_ATOMIC);
if (!cmd.va) {
dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
status = -ENOMEM;
err:
mutex_unlock(&adapter->mbox_lock);
if (cmd.va)
- pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+ cmd.dma);
return status;
}
memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
- extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
- &extfat_cmd.dma);
+ extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+ extfat_cmd.size, &extfat_cmd.dma,
+ GFP_ATOMIC);
if (!extfat_cmd.va)
return -ENOMEM;
status = be_cmd_set_ext_fat_capabilites(adapter, &extfat_cmd, cfgs);
err:
- pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
- extfat_cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+ extfat_cmd.dma);
return status;
}
memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
- extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
- &extfat_cmd.dma);
+ extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+ extfat_cmd.size, &extfat_cmd.dma,
+ GFP_ATOMIC);
if (!extfat_cmd.va) {
dev_err(&adapter->pdev->dev, "%s: Memory allocation failure\n",
level = cfgs->module[0].trace_lvl[j].dbg_lvl;
}
}
- pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
- extfat_cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+ extfat_cmd.dma);
err:
return level;
}
memset(&cmd, 0, sizeof(struct be_dma_mem));
cmd.size = sizeof(struct be_cmd_resp_get_func_config);
- cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+ cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+ GFP_ATOMIC);
if (!cmd.va) {
dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
status = -ENOMEM;
err:
mutex_unlock(&adapter->mbox_lock);
if (cmd.va)
- pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+ cmd.dma);
return status;
}
memset(&cmd, 0, sizeof(struct be_dma_mem));
cmd.size = sizeof(struct be_cmd_resp_get_profile_config);
- cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+ cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+ GFP_ATOMIC);
if (!cmd.va)
return -ENOMEM;
res->vf_if_cap_flags = vf_res->cap_flags;
err:
if (cmd.va)
- pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+ cmd.dma);
return status;
}
memset(&cmd, 0, sizeof(struct be_dma_mem));
cmd.size = sizeof(struct be_cmd_req_set_profile_config);
- cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+ cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+ GFP_ATOMIC);
if (!cmd.va)
return -ENOMEM;
status = be_cmd_notify_wait(adapter, &wrb);
if (cmd.va)
- pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+ cmd.dma);
return status;
}
int status = 0;
read_cmd.size = LANCER_READ_FILE_CHUNK;
- read_cmd.va = pci_alloc_consistent(adapter->pdev, read_cmd.size,
- &read_cmd.dma);
+ read_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, read_cmd.size,
+ &read_cmd.dma, GFP_ATOMIC);
if (!read_cmd.va) {
dev_err(&adapter->pdev->dev,
break;
}
}
- pci_free_consistent(adapter->pdev, read_cmd.size, read_cmd.va,
- read_cmd.dma);
+ dma_free_coherent(&adapter->pdev->dev, read_cmd.size, read_cmd.va,
+ read_cmd.dma);
return status;
}
};
ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test);
- ddrdma_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, ddrdma_cmd.size,
- &ddrdma_cmd.dma, GFP_KERNEL);
+ ddrdma_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+ ddrdma_cmd.size, &ddrdma_cmd.dma,
+ GFP_KERNEL);
if (!ddrdma_cmd.va)
return -ENOMEM;
memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem));
eeprom_cmd.size = sizeof(struct be_cmd_req_seeprom_read);
- eeprom_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, eeprom_cmd.size,
- &eeprom_cmd.dma, GFP_KERNEL);
+ eeprom_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+ eeprom_cmd.size, &eeprom_cmd.dma,
+ GFP_KERNEL);
if (!eeprom_cmd.va)
return -ENOMEM;
adapter->cfg_num_qs);
for_all_evt_queues(adapter, eqo, i) {
+ int numa_node = dev_to_node(&adapter->pdev->dev);
if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL))
return -ENOMEM;
- cpumask_set_cpu_local_first(i, dev_to_node(&adapter->pdev->dev),
- eqo->affinity_mask);
-
+ cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+ eqo->affinity_mask);
netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
BE_NAPI_WEIGHT);
napi_hash_add(&eqo->napi);
flash_cmd.size = sizeof(struct lancer_cmd_req_write_object)
+ LANCER_FW_DOWNLOAD_CHUNK;
- flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size,
- &flash_cmd.dma, GFP_KERNEL);
+ flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size,
+ &flash_cmd.dma, GFP_KERNEL);
if (!flash_cmd.va)
return -ENOMEM;
}
flash_cmd.size = sizeof(struct be_cmd_write_flashrom);
- flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
- GFP_KERNEL);
+ flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
+ GFP_KERNEL);
if (!flash_cmd.va)
return -ENOMEM;
int status = 0;
mbox_mem_alloc->size = sizeof(struct be_mcc_mailbox) + 16;
- mbox_mem_alloc->va = dma_alloc_coherent(dev, mbox_mem_alloc->size,
- &mbox_mem_alloc->dma,
- GFP_KERNEL);
+ mbox_mem_alloc->va = dma_zalloc_coherent(dev, mbox_mem_alloc->size,
+ &mbox_mem_alloc->dma,
+ GFP_KERNEL);
if (!mbox_mem_alloc->va)
return -ENOMEM;
mbox_mem_align->size = sizeof(struct be_mcc_mailbox);
mbox_mem_align->va = PTR_ALIGN(mbox_mem_alloc->va, 16);
mbox_mem_align->dma = PTR_ALIGN(mbox_mem_alloc->dma, 16);
- memset(mbox_mem_align->va, 0, sizeof(struct be_mcc_mailbox));
rx_filter->size = sizeof(struct be_cmd_req_rx_filter);
rx_filter->va = dma_zalloc_coherent(dev, rx_filter->size,
static int emac_get_regs_len(struct emac_instance *dev)
{
- if (emac_has_feature(dev, EMAC_FTR_EMAC4))
- return sizeof(struct emac_ethtool_regs_subhdr) +
- EMAC4_ETHTOOL_REGS_SIZE(dev);
- else
return sizeof(struct emac_ethtool_regs_subhdr) +
- EMAC_ETHTOOL_REGS_SIZE(dev);
+ sizeof(struct emac_regs);
}
static int emac_ethtool_get_regs_len(struct net_device *ndev)
struct emac_ethtool_regs_subhdr *hdr = buf;
hdr->index = dev->cell_index;
- if (emac_has_feature(dev, EMAC_FTR_EMAC4)) {
+ if (emac_has_feature(dev, EMAC_FTR_EMAC4SYNC)) {
+ hdr->version = EMAC4SYNC_ETHTOOL_REGS_VER;
+ } else if (emac_has_feature(dev, EMAC_FTR_EMAC4)) {
hdr->version = EMAC4_ETHTOOL_REGS_VER;
- memcpy_fromio(hdr + 1, dev->emacp, EMAC4_ETHTOOL_REGS_SIZE(dev));
- return (void *)(hdr + 1) + EMAC4_ETHTOOL_REGS_SIZE(dev);
} else {
hdr->version = EMAC_ETHTOOL_REGS_VER;
- memcpy_fromio(hdr + 1, dev->emacp, EMAC_ETHTOOL_REGS_SIZE(dev));
- return (void *)(hdr + 1) + EMAC_ETHTOOL_REGS_SIZE(dev);
}
+ memcpy_fromio(hdr + 1, dev->emacp, sizeof(struct emac_regs));
+ return (void *)(hdr + 1) + sizeof(struct emac_regs);
}
static void emac_ethtool_get_regs(struct net_device *ndev,
};
#define EMAC_ETHTOOL_REGS_VER 0
-#define EMAC_ETHTOOL_REGS_SIZE(dev) ((dev)->rsrc_regs.end - \
- (dev)->rsrc_regs.start + 1)
-#define EMAC4_ETHTOOL_REGS_VER 1
-#define EMAC4_ETHTOOL_REGS_SIZE(dev) ((dev)->rsrc_regs.end - \
- (dev)->rsrc_regs.start + 1)
+#define EMAC4_ETHTOOL_REGS_VER 1
+#define EMAC4SYNC_ETHTOOL_REGS_VER 2
#endif /* __IBM_NEWEMAC_CORE_H */
#include <linux/ptp_classify.h>
#include <linux/mii.h>
#include <linux/mdio.h>
+#include <linux/pm_qos.h>
#include "hw.h"
struct e1000_info;
unsigned int total_bytes = 0, total_packets = 0;
u16 cleaned_count = fm10k_desc_unused(rx_ring);
- do {
+ while (likely(total_packets < budget)) {
union fm10k_rx_desc *rx_desc;
/* return some buffers to hardware, one at a time is too slow */
/* update budget accounting */
total_packets++;
- } while (likely(total_packets < budget));
+ }
/* place incomplete frames back on ring for completion */
rx_ring->skb = skb;
#endif
#define I40E_FLAG_PORT_ID_VALID (u64)(1 << 28)
#define I40E_FLAG_DCB_CAPABLE (u64)(1 << 29)
+#define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40)
/* tracks features that get auto disabled by errors */
u64 auto_disable_flags;
goto command_write_done;
}
+ /* By default we are in VEPA mode, if this is the first VF/VMDq
+ * VSI to be added switch to VEB mode.
+ */
+ if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+ pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+ i40e_do_reset_safe(pf,
+ BIT_ULL(__I40E_PF_RESET_REQUESTED));
+ }
+
vsi = i40e_vsi_setup(pf, I40E_VSI_VMDQ2, vsi_seid, 0);
if (vsi)
dev_info(&pf->pdev->dev, "added VSI %d to relay %d\n",
if (ret)
goto end_reconstitute;
+ if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
+ veb->bridge_mode = BRIDGE_MODE_VEB;
+ else
+ veb->bridge_mode = BRIDGE_MODE_VEPA;
i40e_config_bridge_mode(veb);
/* create the remaining VSIs attached to this VEB */
} else if (mode != veb->bridge_mode) {
/* Existing HW bridge but different mode needs reset */
veb->bridge_mode = mode;
- i40e_do_reset(pf, (1 << __I40E_PF_RESET_REQUESTED));
+ /* TODO: If no VFs or VMDq VSIs, disallow VEB mode */
+ if (mode == BRIDGE_MODE_VEB)
+ pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+ else
+ pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+ i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
break;
}
}
ctxt.uplink_seid = vsi->uplink_seid;
ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL;
ctxt.flags = I40E_AQ_VSI_TYPE_PF;
- if (i40e_is_vsi_uplink_mode_veb(vsi)) {
+ if ((pf->flags & I40E_FLAG_VEB_MODE_ENABLED) &&
+ (i40e_is_vsi_uplink_mode_veb(vsi))) {
ctxt.info.valid_sections |=
- cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
+ cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
ctxt.info.switch_id =
- cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
+ cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
}
i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
break;
__func__);
return NULL;
}
+ /* We come up by default in VEPA mode if SRIOV is not
+ * already enabled, in which case we can't force VEPA
+ * mode.
+ */
+ if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+ veb->bridge_mode = BRIDGE_MODE_VEPA;
+ pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+ }
i40e_config_bridge_mode(veb);
}
for (i = 0; i < I40E_MAX_VEB && !veb; i++) {
goto err_switch_setup;
}
+#ifdef CONFIG_PCI_IOV
+ /* prep for VF support */
+ if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
+ (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
+ !test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+ if (pci_num_vf(pdev))
+ pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+ }
+#endif
err = i40e_setup_pf_switch(pf, false);
if (err) {
dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err);
* i40e_chk_linearize - Check if there are more than 8 fragments per packet
* @skb: send buffer
* @tx_flags: collected send information
- * @hdr_len: size of the packet header
*
* Note: Our HW can't scatter-gather more than 8 fragments to build
* a packet on the wire and so we need to figure out the cases where we
* need to linearize the skb.
**/
-static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
- const u8 hdr_len)
+static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags)
{
struct skb_frag_struct *frag;
bool linearize = false;
gso_segs = skb_shinfo(skb)->gso_segs;
if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) {
- u16 j = 1;
+ u16 j = 0;
if (num_frags < (I40E_MAX_BUFFER_TXD))
goto linearize_chk_done;
goto linearize_chk_done;
}
frag = &skb_shinfo(skb)->frags[0];
- size = hdr_len;
/* we might still have more fragments per segment */
do {
size += skb_frag_size(frag);
frag++; j++;
+ if ((size >= skb_shinfo(skb)->gso_size) &&
+ (j < I40E_MAX_BUFFER_TXD)) {
+ size = (size % skb_shinfo(skb)->gso_size);
+ j = (size) ? 1 : 0;
+ }
if (j == I40E_MAX_BUFFER_TXD) {
- if (size < skb_shinfo(skb)->gso_size) {
- linearize = true;
- break;
- }
- j = 1;
- size -= skb_shinfo(skb)->gso_size;
- if (size)
- j++;
- size += hdr_len;
+ linearize = true;
+ break;
}
num_frags--;
} while (num_frags);
if (tsyn)
tx_flags |= I40E_TX_FLAGS_TSYN;
- if (i40e_chk_linearize(skb, tx_flags, hdr_len))
+ if (i40e_chk_linearize(skb, tx_flags))
if (skb_linearize(skb))
goto out_drop;
{
struct i40e_pf *pf = pci_get_drvdata(pdev);
- if (num_vfs)
+ if (num_vfs) {
+ if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+ pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+ i40e_do_reset_safe(pf,
+ BIT_ULL(__I40E_PF_RESET_REQUESTED));
+ }
return i40e_pci_sriov_enable(pdev, num_vfs);
+ }
if (!pci_vfs_assigned(pf->pdev)) {
i40e_free_vfs(pf);
+ pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+ i40e_do_reset_safe(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
} else {
dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
return -EINVAL;
* i40e_chk_linearize - Check if there are more than 8 fragments per packet
* @skb: send buffer
* @tx_flags: collected send information
- * @hdr_len: size of the packet header
*
* Note: Our HW can't scatter-gather more than 8 fragments to build
* a packet on the wire and so we need to figure out the cases where we
* need to linearize the skb.
**/
-static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
- const u8 hdr_len)
+static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags)
{
struct skb_frag_struct *frag;
bool linearize = false;
gso_segs = skb_shinfo(skb)->gso_segs;
if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) {
- u16 j = 1;
+ u16 j = 0;
if (num_frags < (I40E_MAX_BUFFER_TXD))
goto linearize_chk_done;
goto linearize_chk_done;
}
frag = &skb_shinfo(skb)->frags[0];
- size = hdr_len;
/* we might still have more fragments per segment */
do {
size += skb_frag_size(frag);
frag++; j++;
+ if ((size >= skb_shinfo(skb)->gso_size) &&
+ (j < I40E_MAX_BUFFER_TXD)) {
+ size = (size % skb_shinfo(skb)->gso_size);
+ j = (size) ? 1 : 0;
+ }
if (j == I40E_MAX_BUFFER_TXD) {
- if (size < skb_shinfo(skb)->gso_size) {
- linearize = true;
- break;
- }
- j = 1;
- size -= skb_shinfo(skb)->gso_size;
- if (size)
- j++;
- size += hdr_len;
+ linearize = true;
+ break;
}
num_frags--;
} while (num_frags);
else if (tso)
tx_flags |= I40E_TX_FLAGS_TSO;
- if (i40e_chk_linearize(skb, tx_flags, hdr_len))
+ if (i40e_chk_linearize(skb, tx_flags))
if (skb_linearize(skb))
goto out_drop;
adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL;
if (q_vector->rx.ring)
- adapter->tx_ring[q_vector->rx.ring->queue_index] = NULL;
+ adapter->rx_ring[q_vector->rx.ring->queue_index] = NULL;
netif_napi_del(&q_vector->napi);
q_vector = adapter->q_vector[v_idx];
if (!q_vector)
q_vector = kzalloc(size, GFP_KERNEL);
+ else
+ memset(q_vector, 0, size);
if (!q_vector)
return -ENOMEM;
igb->perout[i].start.tv_nsec = rq->perout.start.nsec;
igb->perout[i].period.tv_sec = ts.tv_sec;
igb->perout[i].period.tv_nsec = ts.tv_nsec;
- wr32(trgttiml, rq->perout.start.sec);
- wr32(trgttimh, rq->perout.start.nsec);
+ wr32(trgttimh, rq->perout.start.sec);
+ wr32(trgttiml, rq->perout.start.nsec);
tsauxc |= tsauxc_mask;
tsim |= tsim_mask;
} else {
u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL);
if (!dst_mac || is_link_local_ether_addr(dst_mac)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
msecs_to_jiffies(timeout))) {
mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
op);
- err = -EIO;
- goto out_reset;
+ if (op == MLX4_CMD_NOP) {
+ err = -EBUSY;
+ goto out;
+ } else {
+ err = -EIO;
+ goto out_reset;
+ }
}
err = context->result;
{
struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
int numa_node = priv->mdev->dev->numa_node;
- int ret = 0;
if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL))
return -ENOMEM;
- ret = cpumask_set_cpu_local_first(ring_idx, numa_node,
- ring->affinity_mask);
- if (ret)
- free_cpumask_var(ring->affinity_mask);
-
- return ret;
+ cpumask_set_cpu(cpumask_local_spread(ring_idx, numa_node),
+ ring->affinity_mask);
+ return 0;
}
static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
int i;
int offset = next - start;
- for (i = 0; i <= num; i++) {
+ for (i = 0; i < num; i++) {
ret += be64_to_cpu(*curr);
curr += offset;
}
ring->queue_index = queue_index;
if (queue_index < priv->num_tx_rings_p_up)
- cpumask_set_cpu_local_first(queue_index,
- priv->mdev->dev->numa_node,
- &ring->affinity_mask);
+ cpumask_set_cpu(cpumask_local_spread(queue_index,
+ priv->mdev->dev->numa_node),
+ &ring->affinity_mask);
*pring = ring;
return 0;
{
int err;
int eqn = vhcr->in_modifier;
- int res_id = (slave << 8) | eqn;
+ int res_id = (slave << 10) | eqn;
struct mlx4_eq_context *eqc = inbox->buf;
int mtt_base = eq_get_mtt_addr(eqc) / dev->caps.mtt_entry_sz;
int mtt_size = eq_get_mtt_size(eqc);
struct mlx4_cmd_info *cmd)
{
int eqn = vhcr->in_modifier;
- int res_id = eqn | (slave << 8);
+ int res_id = eqn | (slave << 10);
struct res_eq *eq;
int err;
return 0;
mutex_lock(&priv->mfunc.master.gen_eqe_mutex[slave]);
- res_id = (slave << 8) | event_eq->eqn;
+ res_id = (slave << 10) | event_eq->eqn;
err = get_res(dev, slave, res_id, RES_EQ, &req);
if (err)
goto unlock;
memcpy(mailbox->buf, (u8 *) eqe, 28);
- in_modifier = (slave & 0xff) | ((event_eq->eqn & 0xff) << 16);
+ in_modifier = (slave & 0xff) | ((event_eq->eqn & 0x3ff) << 16);
err = mlx4_cmd(dev, mailbox->dma, in_modifier, 0,
MLX4_CMD_GEN_EQE, MLX4_CMD_TIME_CLASS_B,
struct mlx4_cmd_info *cmd)
{
int eqn = vhcr->in_modifier;
- int res_id = eqn | (slave << 8);
+ int res_id = eqn | (slave << 10);
struct res_eq *eq;
int err;
int cqn = vhcr->in_modifier;
struct mlx4_cq_context *cqc = inbox->buf;
int mtt_base = cq_get_mtt_addr(cqc) / dev->caps.mtt_entry_sz;
- struct res_cq *cq;
+ struct res_cq *cq = NULL;
struct res_mtt *mtt;
err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_HW, &cq);
{
int err;
int cqn = vhcr->in_modifier;
- struct res_cq *cq;
+ struct res_cq *cq = NULL;
err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_ALLOCATED, &cq);
if (err)
int err;
int srqn = vhcr->in_modifier;
struct res_mtt *mtt;
- struct res_srq *srq;
+ struct res_srq *srq = NULL;
struct mlx4_srq_context *srqc = inbox->buf;
int mtt_base = srq_get_mtt_addr(srqc) / dev->caps.mtt_entry_sz;
{
int err;
int srqn = vhcr->in_modifier;
- struct res_srq *srq;
+ struct res_srq *srq = NULL;
err = srq_res_start_move_to(dev, slave, srqn, RES_SRQ_ALLOCATED, &srq);
if (err)
break;
case RES_EQ_HW:
- err = mlx4_cmd(dev, slave, eqn & 0xff,
+ err = mlx4_cmd(dev, slave, eqn & 0x3ff,
1, MLX4_CMD_HW2SW_EQ,
MLX4_CMD_TIME_CLASS_A,
MLX4_CMD_NATIVE);
if (err)
mlx4_dbg(dev, "rem_slave_eqs: failed to move slave %d eqs %d to SW ownership\n",
- slave, eqn);
+ slave, eqn & 0x3ff);
atomic_dec(&eq->mtt->ref_count);
state = RES_EQ_RESERVED;
break;
int done = 0;
struct nx_host_tx_ring *tx_ring = adapter->tx_ring;
- if (!spin_trylock(&adapter->tx_clean_lock))
+ if (!spin_trylock_bh(&adapter->tx_clean_lock))
return 1;
sw_consumer = tx_ring->sw_consumer;
*/
hw_consumer = le32_to_cpu(*(tx_ring->hw_consumer));
done = (sw_consumer == hw_consumer);
- spin_unlock(&adapter->tx_clean_lock);
+ spin_unlock_bh(&adapter->tx_clean_lock);
return done;
}
u8 dw, rows, cols, banks, ranks;
u32 val;
- if (size != sizeof(struct netxen_dimm_cfg)) {
+ if (size < attr->size) {
netdev_err(netdev, "Invalid size\n");
- return -1;
+ return -EINVAL;
}
memset(&dimm, 0, sizeof(struct netxen_dimm_cfg));
static struct bin_attribute bin_attr_dimm = {
.attr = { .name = "dimm", .mode = (S_IRUGO | S_IWUSR) },
- .size = 0,
+ .size = sizeof(struct netxen_dimm_cfg),
.read = netxen_sysfs_read_dimm,
};
qca->spi_dev = spi_device;
qca->legacy_mode = legacy_mode;
+ spi_set_drvdata(spi_device, qcaspi_devs);
+
mac = of_get_mac_address(spi_device->dev.of_node);
if (mac)
return -EFAULT;
}
- spi_set_drvdata(spi_device, qcaspi_devs);
-
qcaspi_init_device_debugfs(qca);
return 0;
rtl8169_start_xmit(nskb, tp->dev);
} while (segs);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
if (skb_checksum_help(skb) < 0)
goto drop;
drop:
stats = &tp->dev->stats;
stats->tx_dropped++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
}
}
struct neighbour *n = __ipv4_neigh_lookup(dev, (__force u32)ip_addr);
int err = 0;
- if (!n)
+ if (!n) {
n = neigh_create(&arp_tbl, &ip_addr, dev);
- if (!n)
- return -ENOMEM;
+ if (IS_ERR(n))
+ return IS_ERR(n);
+ }
/* If the neigh is already resolved, then go ahead and
* install the entry, otherwise start the ARP process to
else
neigh_event_send(n, NULL);
+ neigh_release(n);
return err;
}
if (!cpumask_test_cpu(cpu, thread_mask)) {
++count;
cpumask_or(thread_mask, thread_mask,
- topology_thread_cpumask(cpu));
+ topology_sibling_cpumask(cpu));
}
}
}
}
-static void efx_free_rx_buffer(struct efx_rx_buffer *rx_buf)
+static void efx_free_rx_buffers(struct efx_rx_queue *rx_queue,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int num_bufs)
{
- if (rx_buf->page) {
- put_page(rx_buf->page);
- rx_buf->page = NULL;
- }
+ do {
+ if (rx_buf->page) {
+ put_page(rx_buf->page);
+ rx_buf->page = NULL;
+ }
+ rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+ } while (--num_bufs);
}
/* Attempt to recycle the page if there is an RX recycle ring; the page can
/* If this is the last buffer in a page, unmap and free it. */
if (rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE) {
efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
- efx_free_rx_buffer(rx_buf);
+ efx_free_rx_buffers(rx_queue, rx_buf, 1);
}
rx_buf->page = NULL;
}
efx_recycle_rx_pages(channel, rx_buf, n_frags);
- do {
- efx_free_rx_buffer(rx_buf);
- rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
- } while (--n_frags);
+ efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
}
/**
skb = napi_get_frags(napi);
if (unlikely(!skb)) {
- while (n_frags--) {
- put_page(rx_buf->page);
- rx_buf->page = NULL;
- rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf);
- }
+ struct efx_rx_queue *rx_queue;
+
+ rx_queue = efx_channel_get_rx_queue(channel);
+ efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
return;
}
skb = efx_rx_mk_skb(channel, rx_buf, n_frags, eh, hdr_len);
if (unlikely(skb == NULL)) {
- efx_free_rx_buffer(rx_buf);
+ struct efx_rx_queue *rx_queue;
+
+ rx_queue = efx_channel_get_rx_queue(channel);
+ efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
return;
}
skb_record_rx_queue(skb, channel->rx_queue.core_index);
* loopback layer, and free the rx_buf here
*/
if (unlikely(efx->loopback_selftest)) {
+ struct efx_rx_queue *rx_queue;
+
efx_loopback_rx_packet(efx, eh, rx_buf->len);
- efx_free_rx_buffer(rx_buf);
+ rx_queue = efx_channel_get_rx_queue(channel);
+ efx_free_rx_buffers(rx_queue, rx_buf,
+ channel->rx_pkt_n_frags);
goto out;
}
const struct of_device_id *match = NULL;
struct smc_local *lp;
struct net_device *ndev;
- struct resource *res, *ires;
+ struct resource *res;
unsigned int __iomem *addr;
unsigned long irq_flags = SMC_IRQ_FLAGS;
+ unsigned long irq_resflags;
int ret;
ndev = alloc_etherdev(sizeof(struct smc_local));
goto out_free_netdev;
}
- ires = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
- if (!ires) {
+ ndev->irq = platform_get_irq(pdev, 0);
+ if (ndev->irq <= 0) {
ret = -ENODEV;
goto out_release_io;
}
-
- ndev->irq = ires->start;
-
- if (irq_flags == -1 || ires->flags & IRQF_TRIGGER_MASK)
- irq_flags = ires->flags & IRQF_TRIGGER_MASK;
+ /*
+ * If this platform does not specify any special irqflags, or if
+ * the resource supplies a trigger, override the irqflags with
+ * the trigger flags from the resource.
+ */
+ irq_resflags = irqd_get_trigger_type(irq_get_irq_data(ndev->irq));
+ if (irq_flags == -1 || irq_resflags & IRQF_TRIGGER_MASK)
+ irq_flags = irq_resflags & IRQF_TRIGGER_MASK;
ret = smc_request_attrib(pdev, ndev);
if (ret)
struct net_device *dev;
struct smsc911x_data *pdata;
struct smsc911x_platform_config *config = dev_get_platdata(&pdev->dev);
- struct resource *res, *irq_res;
+ struct resource *res;
unsigned int intcfg = 0;
- int res_size, irq_flags;
+ int res_size, irq, irq_flags;
int retval;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
}
res_size = resource_size(res);
- irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
- if (!irq_res) {
+ irq = platform_get_irq(pdev, 0);
+ if (irq <= 0) {
pr_warn("Could not allocate irq resource\n");
retval = -ENODEV;
goto out_0;
SET_NETDEV_DEV(dev, &pdev->dev);
pdata = netdev_priv(dev);
- dev->irq = irq_res->start;
- irq_flags = irq_res->flags & IRQF_TRIGGER_MASK;
+ dev->irq = irq;
+ irq_flags = irq_get_trigger_type(irq);
pdata->ioaddr = ioremap_nocache(res->start, res_size);
pdata->dev = dev;
int use_riwt;
int irq_wake;
spinlock_t ptp_lock;
+
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *dbgfs_dir;
+ struct dentry *dbgfs_rings_status;
+ struct dentry *dbgfs_dma_cap;
+#endif
};
int stmmac_mdio_unregister(struct net_device *ndev);
#ifdef CONFIG_DEBUG_FS
static int stmmac_init_fs(struct net_device *dev);
-static void stmmac_exit_fs(void);
+static void stmmac_exit_fs(struct net_device *dev);
#endif
#define STMMAC_COAL_TIMER(x) (jiffies + usecs_to_jiffies(x))
netif_carrier_off(dev);
#ifdef CONFIG_DEBUG_FS
- stmmac_exit_fs();
+ stmmac_exit_fs(dev);
#endif
stmmac_release_ptp(priv);
#ifdef CONFIG_DEBUG_FS
static struct dentry *stmmac_fs_dir;
-static struct dentry *stmmac_rings_status;
-static struct dentry *stmmac_dma_cap;
static void sysfs_display_ring(void *head, int size, int extend_desc,
struct seq_file *seq)
static int stmmac_init_fs(struct net_device *dev)
{
- /* Create debugfs entries */
- stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL);
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ /* Create per netdev entries */
+ priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir);
- if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) {
- pr_err("ERROR %s, debugfs create directory failed\n",
- STMMAC_RESOURCE_NAME);
+ if (!priv->dbgfs_dir || IS_ERR(priv->dbgfs_dir)) {
+ pr_err("ERROR %s/%s, debugfs create directory failed\n",
+ STMMAC_RESOURCE_NAME, dev->name);
return -ENOMEM;
}
/* Entry to report DMA RX/TX rings */
- stmmac_rings_status = debugfs_create_file("descriptors_status",
- S_IRUGO, stmmac_fs_dir, dev,
- &stmmac_rings_status_fops);
+ priv->dbgfs_rings_status =
+ debugfs_create_file("descriptors_status", S_IRUGO,
+ priv->dbgfs_dir, dev,
+ &stmmac_rings_status_fops);
- if (!stmmac_rings_status || IS_ERR(stmmac_rings_status)) {
+ if (!priv->dbgfs_rings_status || IS_ERR(priv->dbgfs_rings_status)) {
pr_info("ERROR creating stmmac ring debugfs file\n");
- debugfs_remove(stmmac_fs_dir);
+ debugfs_remove_recursive(priv->dbgfs_dir);
return -ENOMEM;
}
/* Entry to report the DMA HW features */
- stmmac_dma_cap = debugfs_create_file("dma_cap", S_IRUGO, stmmac_fs_dir,
- dev, &stmmac_dma_cap_fops);
+ priv->dbgfs_dma_cap = debugfs_create_file("dma_cap", S_IRUGO,
+ priv->dbgfs_dir,
+ dev, &stmmac_dma_cap_fops);
- if (!stmmac_dma_cap || IS_ERR(stmmac_dma_cap)) {
+ if (!priv->dbgfs_dma_cap || IS_ERR(priv->dbgfs_dma_cap)) {
pr_info("ERROR creating stmmac MMC debugfs file\n");
- debugfs_remove(stmmac_rings_status);
- debugfs_remove(stmmac_fs_dir);
+ debugfs_remove_recursive(priv->dbgfs_dir);
return -ENOMEM;
}
return 0;
}
-static void stmmac_exit_fs(void)
+static void stmmac_exit_fs(struct net_device *dev)
{
- debugfs_remove(stmmac_rings_status);
- debugfs_remove(stmmac_dma_cap);
- debugfs_remove(stmmac_fs_dir);
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ debugfs_remove_recursive(priv->dbgfs_dir);
}
#endif /* CONFIG_DEBUG_FS */
__setup("stmmaceth=", stmmac_cmdline_opt);
#endif /* MODULE */
+static int __init stmmac_init(void)
+{
+#ifdef CONFIG_DEBUG_FS
+ /* Create debugfs main directory if it doesn't exist yet */
+ if (!stmmac_fs_dir) {
+ stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL);
+
+ if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) {
+ pr_err("ERROR %s, debugfs create directory failed\n",
+ STMMAC_RESOURCE_NAME);
+
+ return -ENOMEM;
+ }
+ }
+#endif
+
+ return 0;
+}
+
+static void __exit stmmac_exit(void)
+{
+#ifdef CONFIG_DEBUG_FS
+ debugfs_remove_recursive(stmmac_fs_dir);
+#endif
+}
+
+module_init(stmmac_init)
+module_exit(stmmac_exit)
+
MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet device driver");
MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
MODULE_LICENSE("GPL");
*******************************************************************************/
#include <linux/platform_device.h>
+#include <linux/module.h>
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_net.h>
cur_p->app0 |= STS_CTRL_APP0_SOP;
cur_p->len = skb_headlen(skb);
- cur_p->phys = dma_map_single(ndev->dev.parent, skb->data, skb->len,
- DMA_TO_DEVICE);
+ cur_p->phys = dma_map_single(ndev->dev.parent, skb->data,
+ skb_headlen(skb), DMA_TO_DEVICE);
cur_p->app4 = (unsigned long)skb;
for (ii = 0; ii < num_frag; ii++) {
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/if_ether.h>
+#include <linux/vmalloc.h>
#include <asm/sync_bitops.h>
#include "hyperv_net.h"
u16 q_idx = packet->q_idx;
u32 pktlen = packet->total_data_buflen, msd_len = 0;
unsigned int section_index = NETVSC_INVALID_INDEX;
- struct sk_buff *skb = NULL;
unsigned long flag;
struct multi_send_data *msdp;
struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL;
if (cur_send)
ret = netvsc_send_pkt(cur_send, net_device);
- if (ret != 0) {
- if (section_index != NETVSC_INVALID_INDEX)
- netvsc_free_send_slot(net_device, section_index);
- } else if (skb) {
- dev_kfree_skb_any(skb);
- }
+ if (ret != 0 && section_index != NETVSC_INVALID_INDEX)
+ netvsc_free_send_slot(net_device, section_index);
return ret;
}
#include <linux/netdevice.h>
#include <linux/if_vlan.h>
#include <linux/nls.h>
+#include <linux/vmalloc.h>
#include "hyperv_net.h"
struct ieee802154_hw *hw;
struct at86rf2xx_chip_data *data;
struct regmap *regmap;
+ int slp_tr;
struct completion state_complete;
struct at86rf230_state_change state;
unsigned long cal_timeout;
s8 max_frame_retries;
bool is_tx;
+ bool is_tx_from_off;
u8 tx_retry;
struct sk_buff *tx_skb;
struct at86rf230_state_change tx;
};
-#define RG_TRX_STATUS (0x01)
-#define SR_TRX_STATUS 0x01, 0x1f, 0
-#define SR_RESERVED_01_3 0x01, 0x20, 5
-#define SR_CCA_STATUS 0x01, 0x40, 6
-#define SR_CCA_DONE 0x01, 0x80, 7
-#define RG_TRX_STATE (0x02)
-#define SR_TRX_CMD 0x02, 0x1f, 0
-#define SR_TRAC_STATUS 0x02, 0xe0, 5
-#define RG_TRX_CTRL_0 (0x03)
-#define SR_CLKM_CTRL 0x03, 0x07, 0
-#define SR_CLKM_SHA_SEL 0x03, 0x08, 3
-#define SR_PAD_IO_CLKM 0x03, 0x30, 4
-#define SR_PAD_IO 0x03, 0xc0, 6
-#define RG_TRX_CTRL_1 (0x04)
-#define SR_IRQ_POLARITY 0x04, 0x01, 0
-#define SR_IRQ_MASK_MODE 0x04, 0x02, 1
-#define SR_SPI_CMD_MODE 0x04, 0x0c, 2
-#define SR_RX_BL_CTRL 0x04, 0x10, 4
-#define SR_TX_AUTO_CRC_ON 0x04, 0x20, 5
-#define SR_IRQ_2_EXT_EN 0x04, 0x40, 6
-#define SR_PA_EXT_EN 0x04, 0x80, 7
-#define RG_PHY_TX_PWR (0x05)
-#define SR_TX_PWR 0x05, 0x0f, 0
-#define SR_PA_LT 0x05, 0x30, 4
-#define SR_PA_BUF_LT 0x05, 0xc0, 6
-#define RG_PHY_RSSI (0x06)
-#define SR_RSSI 0x06, 0x1f, 0
-#define SR_RND_VALUE 0x06, 0x60, 5
-#define SR_RX_CRC_VALID 0x06, 0x80, 7
-#define RG_PHY_ED_LEVEL (0x07)
-#define SR_ED_LEVEL 0x07, 0xff, 0
-#define RG_PHY_CC_CCA (0x08)
-#define SR_CHANNEL 0x08, 0x1f, 0
-#define SR_CCA_MODE 0x08, 0x60, 5
-#define SR_CCA_REQUEST 0x08, 0x80, 7
-#define RG_CCA_THRES (0x09)
-#define SR_CCA_ED_THRES 0x09, 0x0f, 0
-#define SR_RESERVED_09_1 0x09, 0xf0, 4
-#define RG_RX_CTRL (0x0a)
-#define SR_PDT_THRES 0x0a, 0x0f, 0
-#define SR_RESERVED_0a_1 0x0a, 0xf0, 4
-#define RG_SFD_VALUE (0x0b)
-#define SR_SFD_VALUE 0x0b, 0xff, 0
-#define RG_TRX_CTRL_2 (0x0c)
-#define SR_OQPSK_DATA_RATE 0x0c, 0x03, 0
-#define SR_SUB_MODE 0x0c, 0x04, 2
-#define SR_BPSK_QPSK 0x0c, 0x08, 3
-#define SR_OQPSK_SUB1_RC_EN 0x0c, 0x10, 4
-#define SR_RESERVED_0c_5 0x0c, 0x60, 5
-#define SR_RX_SAFE_MODE 0x0c, 0x80, 7
-#define RG_ANT_DIV (0x0d)
-#define SR_ANT_CTRL 0x0d, 0x03, 0
-#define SR_ANT_EXT_SW_EN 0x0d, 0x04, 2
-#define SR_ANT_DIV_EN 0x0d, 0x08, 3
-#define SR_RESERVED_0d_2 0x0d, 0x70, 4
-#define SR_ANT_SEL 0x0d, 0x80, 7
-#define RG_IRQ_MASK (0x0e)
-#define SR_IRQ_MASK 0x0e, 0xff, 0
-#define RG_IRQ_STATUS (0x0f)
-#define SR_IRQ_0_PLL_LOCK 0x0f, 0x01, 0
-#define SR_IRQ_1_PLL_UNLOCK 0x0f, 0x02, 1
-#define SR_IRQ_2_RX_START 0x0f, 0x04, 2
-#define SR_IRQ_3_TRX_END 0x0f, 0x08, 3
-#define SR_IRQ_4_CCA_ED_DONE 0x0f, 0x10, 4
-#define SR_IRQ_5_AMI 0x0f, 0x20, 5
-#define SR_IRQ_6_TRX_UR 0x0f, 0x40, 6
-#define SR_IRQ_7_BAT_LOW 0x0f, 0x80, 7
-#define RG_VREG_CTRL (0x10)
-#define SR_RESERVED_10_6 0x10, 0x03, 0
-#define SR_DVDD_OK 0x10, 0x04, 2
-#define SR_DVREG_EXT 0x10, 0x08, 3
-#define SR_RESERVED_10_3 0x10, 0x30, 4
-#define SR_AVDD_OK 0x10, 0x40, 6
-#define SR_AVREG_EXT 0x10, 0x80, 7
-#define RG_BATMON (0x11)
-#define SR_BATMON_VTH 0x11, 0x0f, 0
-#define SR_BATMON_HR 0x11, 0x10, 4
-#define SR_BATMON_OK 0x11, 0x20, 5
-#define SR_RESERVED_11_1 0x11, 0xc0, 6
-#define RG_XOSC_CTRL (0x12)
-#define SR_XTAL_TRIM 0x12, 0x0f, 0
-#define SR_XTAL_MODE 0x12, 0xf0, 4
-#define RG_RX_SYN (0x15)
-#define SR_RX_PDT_LEVEL 0x15, 0x0f, 0
-#define SR_RESERVED_15_2 0x15, 0x70, 4
-#define SR_RX_PDT_DIS 0x15, 0x80, 7
-#define RG_XAH_CTRL_1 (0x17)
-#define SR_RESERVED_17_8 0x17, 0x01, 0
-#define SR_AACK_PROM_MODE 0x17, 0x02, 1
-#define SR_AACK_ACK_TIME 0x17, 0x04, 2
-#define SR_RESERVED_17_5 0x17, 0x08, 3
-#define SR_AACK_UPLD_RES_FT 0x17, 0x10, 4
-#define SR_AACK_FLTR_RES_FT 0x17, 0x20, 5
-#define SR_CSMA_LBT_MODE 0x17, 0x40, 6
-#define SR_RESERVED_17_1 0x17, 0x80, 7
-#define RG_FTN_CTRL (0x18)
-#define SR_RESERVED_18_2 0x18, 0x7f, 0
-#define SR_FTN_START 0x18, 0x80, 7
-#define RG_PLL_CF (0x1a)
-#define SR_RESERVED_1a_2 0x1a, 0x7f, 0
-#define SR_PLL_CF_START 0x1a, 0x80, 7
-#define RG_PLL_DCU (0x1b)
-#define SR_RESERVED_1b_3 0x1b, 0x3f, 0
-#define SR_RESERVED_1b_2 0x1b, 0x40, 6
-#define SR_PLL_DCU_START 0x1b, 0x80, 7
-#define RG_PART_NUM (0x1c)
-#define SR_PART_NUM 0x1c, 0xff, 0
-#define RG_VERSION_NUM (0x1d)
-#define SR_VERSION_NUM 0x1d, 0xff, 0
-#define RG_MAN_ID_0 (0x1e)
-#define SR_MAN_ID_0 0x1e, 0xff, 0
-#define RG_MAN_ID_1 (0x1f)
-#define SR_MAN_ID_1 0x1f, 0xff, 0
-#define RG_SHORT_ADDR_0 (0x20)
-#define SR_SHORT_ADDR_0 0x20, 0xff, 0
-#define RG_SHORT_ADDR_1 (0x21)
-#define SR_SHORT_ADDR_1 0x21, 0xff, 0
-#define RG_PAN_ID_0 (0x22)
-#define SR_PAN_ID_0 0x22, 0xff, 0
-#define RG_PAN_ID_1 (0x23)
-#define SR_PAN_ID_1 0x23, 0xff, 0
-#define RG_IEEE_ADDR_0 (0x24)
-#define SR_IEEE_ADDR_0 0x24, 0xff, 0
-#define RG_IEEE_ADDR_1 (0x25)
-#define SR_IEEE_ADDR_1 0x25, 0xff, 0
-#define RG_IEEE_ADDR_2 (0x26)
-#define SR_IEEE_ADDR_2 0x26, 0xff, 0
-#define RG_IEEE_ADDR_3 (0x27)
-#define SR_IEEE_ADDR_3 0x27, 0xff, 0
-#define RG_IEEE_ADDR_4 (0x28)
-#define SR_IEEE_ADDR_4 0x28, 0xff, 0
-#define RG_IEEE_ADDR_5 (0x29)
-#define SR_IEEE_ADDR_5 0x29, 0xff, 0
-#define RG_IEEE_ADDR_6 (0x2a)
-#define SR_IEEE_ADDR_6 0x2a, 0xff, 0
-#define RG_IEEE_ADDR_7 (0x2b)
-#define SR_IEEE_ADDR_7 0x2b, 0xff, 0
-#define RG_XAH_CTRL_0 (0x2c)
-#define SR_SLOTTED_OPERATION 0x2c, 0x01, 0
-#define SR_MAX_CSMA_RETRIES 0x2c, 0x0e, 1
-#define SR_MAX_FRAME_RETRIES 0x2c, 0xf0, 4
-#define RG_CSMA_SEED_0 (0x2d)
-#define SR_CSMA_SEED_0 0x2d, 0xff, 0
-#define RG_CSMA_SEED_1 (0x2e)
-#define SR_CSMA_SEED_1 0x2e, 0x07, 0
-#define SR_AACK_I_AM_COORD 0x2e, 0x08, 3
-#define SR_AACK_DIS_ACK 0x2e, 0x10, 4
-#define SR_AACK_SET_PD 0x2e, 0x20, 5
-#define SR_AACK_FVN_MODE 0x2e, 0xc0, 6
-#define RG_CSMA_BE (0x2f)
-#define SR_MIN_BE 0x2f, 0x0f, 0
-#define SR_MAX_BE 0x2f, 0xf0, 4
+#define RG_TRX_STATUS (0x01)
+#define SR_TRX_STATUS 0x01, 0x1f, 0
+#define SR_RESERVED_01_3 0x01, 0x20, 5
+#define SR_CCA_STATUS 0x01, 0x40, 6
+#define SR_CCA_DONE 0x01, 0x80, 7
+#define RG_TRX_STATE (0x02)
+#define SR_TRX_CMD 0x02, 0x1f, 0
+#define SR_TRAC_STATUS 0x02, 0xe0, 5
+#define RG_TRX_CTRL_0 (0x03)
+#define SR_CLKM_CTRL 0x03, 0x07, 0
+#define SR_CLKM_SHA_SEL 0x03, 0x08, 3
+#define SR_PAD_IO_CLKM 0x03, 0x30, 4
+#define SR_PAD_IO 0x03, 0xc0, 6
+#define RG_TRX_CTRL_1 (0x04)
+#define SR_IRQ_POLARITY 0x04, 0x01, 0
+#define SR_IRQ_MASK_MODE 0x04, 0x02, 1
+#define SR_SPI_CMD_MODE 0x04, 0x0c, 2
+#define SR_RX_BL_CTRL 0x04, 0x10, 4
+#define SR_TX_AUTO_CRC_ON 0x04, 0x20, 5
+#define SR_IRQ_2_EXT_EN 0x04, 0x40, 6
+#define SR_PA_EXT_EN 0x04, 0x80, 7
+#define RG_PHY_TX_PWR (0x05)
+#define SR_TX_PWR 0x05, 0x0f, 0
+#define SR_PA_LT 0x05, 0x30, 4
+#define SR_PA_BUF_LT 0x05, 0xc0, 6
+#define RG_PHY_RSSI (0x06)
+#define SR_RSSI 0x06, 0x1f, 0
+#define SR_RND_VALUE 0x06, 0x60, 5
+#define SR_RX_CRC_VALID 0x06, 0x80, 7
+#define RG_PHY_ED_LEVEL (0x07)
+#define SR_ED_LEVEL 0x07, 0xff, 0
+#define RG_PHY_CC_CCA (0x08)
+#define SR_CHANNEL 0x08, 0x1f, 0
+#define SR_CCA_MODE 0x08, 0x60, 5
+#define SR_CCA_REQUEST 0x08, 0x80, 7
+#define RG_CCA_THRES (0x09)
+#define SR_CCA_ED_THRES 0x09, 0x0f, 0
+#define SR_RESERVED_09_1 0x09, 0xf0, 4
+#define RG_RX_CTRL (0x0a)
+#define SR_PDT_THRES 0x0a, 0x0f, 0
+#define SR_RESERVED_0a_1 0x0a, 0xf0, 4
+#define RG_SFD_VALUE (0x0b)
+#define SR_SFD_VALUE 0x0b, 0xff, 0
+#define RG_TRX_CTRL_2 (0x0c)
+#define SR_OQPSK_DATA_RATE 0x0c, 0x03, 0
+#define SR_SUB_MODE 0x0c, 0x04, 2
+#define SR_BPSK_QPSK 0x0c, 0x08, 3
+#define SR_OQPSK_SUB1_RC_EN 0x0c, 0x10, 4
+#define SR_RESERVED_0c_5 0x0c, 0x60, 5
+#define SR_RX_SAFE_MODE 0x0c, 0x80, 7
+#define RG_ANT_DIV (0x0d)
+#define SR_ANT_CTRL 0x0d, 0x03, 0
+#define SR_ANT_EXT_SW_EN 0x0d, 0x04, 2
+#define SR_ANT_DIV_EN 0x0d, 0x08, 3
+#define SR_RESERVED_0d_2 0x0d, 0x70, 4
+#define SR_ANT_SEL 0x0d, 0x80, 7
+#define RG_IRQ_MASK (0x0e)
+#define SR_IRQ_MASK 0x0e, 0xff, 0
+#define RG_IRQ_STATUS (0x0f)
+#define SR_IRQ_0_PLL_LOCK 0x0f, 0x01, 0
+#define SR_IRQ_1_PLL_UNLOCK 0x0f, 0x02, 1
+#define SR_IRQ_2_RX_START 0x0f, 0x04, 2
+#define SR_IRQ_3_TRX_END 0x0f, 0x08, 3
+#define SR_IRQ_4_CCA_ED_DONE 0x0f, 0x10, 4
+#define SR_IRQ_5_AMI 0x0f, 0x20, 5
+#define SR_IRQ_6_TRX_UR 0x0f, 0x40, 6
+#define SR_IRQ_7_BAT_LOW 0x0f, 0x80, 7
+#define RG_VREG_CTRL (0x10)
+#define SR_RESERVED_10_6 0x10, 0x03, 0
+#define SR_DVDD_OK 0x10, 0x04, 2
+#define SR_DVREG_EXT 0x10, 0x08, 3
+#define SR_RESERVED_10_3 0x10, 0x30, 4
+#define SR_AVDD_OK 0x10, 0x40, 6
+#define SR_AVREG_EXT 0x10, 0x80, 7
+#define RG_BATMON (0x11)
+#define SR_BATMON_VTH 0x11, 0x0f, 0
+#define SR_BATMON_HR 0x11, 0x10, 4
+#define SR_BATMON_OK 0x11, 0x20, 5
+#define SR_RESERVED_11_1 0x11, 0xc0, 6
+#define RG_XOSC_CTRL (0x12)
+#define SR_XTAL_TRIM 0x12, 0x0f, 0
+#define SR_XTAL_MODE 0x12, 0xf0, 4
+#define RG_RX_SYN (0x15)
+#define SR_RX_PDT_LEVEL 0x15, 0x0f, 0
+#define SR_RESERVED_15_2 0x15, 0x70, 4
+#define SR_RX_PDT_DIS 0x15, 0x80, 7
+#define RG_XAH_CTRL_1 (0x17)
+#define SR_RESERVED_17_8 0x17, 0x01, 0
+#define SR_AACK_PROM_MODE 0x17, 0x02, 1
+#define SR_AACK_ACK_TIME 0x17, 0x04, 2
+#define SR_RESERVED_17_5 0x17, 0x08, 3
+#define SR_AACK_UPLD_RES_FT 0x17, 0x10, 4
+#define SR_AACK_FLTR_RES_FT 0x17, 0x20, 5
+#define SR_CSMA_LBT_MODE 0x17, 0x40, 6
+#define SR_RESERVED_17_1 0x17, 0x80, 7
+#define RG_FTN_CTRL (0x18)
+#define SR_RESERVED_18_2 0x18, 0x7f, 0
+#define SR_FTN_START 0x18, 0x80, 7
+#define RG_PLL_CF (0x1a)
+#define SR_RESERVED_1a_2 0x1a, 0x7f, 0
+#define SR_PLL_CF_START 0x1a, 0x80, 7
+#define RG_PLL_DCU (0x1b)
+#define SR_RESERVED_1b_3 0x1b, 0x3f, 0
+#define SR_RESERVED_1b_2 0x1b, 0x40, 6
+#define SR_PLL_DCU_START 0x1b, 0x80, 7
+#define RG_PART_NUM (0x1c)
+#define SR_PART_NUM 0x1c, 0xff, 0
+#define RG_VERSION_NUM (0x1d)
+#define SR_VERSION_NUM 0x1d, 0xff, 0
+#define RG_MAN_ID_0 (0x1e)
+#define SR_MAN_ID_0 0x1e, 0xff, 0
+#define RG_MAN_ID_1 (0x1f)
+#define SR_MAN_ID_1 0x1f, 0xff, 0
+#define RG_SHORT_ADDR_0 (0x20)
+#define SR_SHORT_ADDR_0 0x20, 0xff, 0
+#define RG_SHORT_ADDR_1 (0x21)
+#define SR_SHORT_ADDR_1 0x21, 0xff, 0
+#define RG_PAN_ID_0 (0x22)
+#define SR_PAN_ID_0 0x22, 0xff, 0
+#define RG_PAN_ID_1 (0x23)
+#define SR_PAN_ID_1 0x23, 0xff, 0
+#define RG_IEEE_ADDR_0 (0x24)
+#define SR_IEEE_ADDR_0 0x24, 0xff, 0
+#define RG_IEEE_ADDR_1 (0x25)
+#define SR_IEEE_ADDR_1 0x25, 0xff, 0
+#define RG_IEEE_ADDR_2 (0x26)
+#define SR_IEEE_ADDR_2 0x26, 0xff, 0
+#define RG_IEEE_ADDR_3 (0x27)
+#define SR_IEEE_ADDR_3 0x27, 0xff, 0
+#define RG_IEEE_ADDR_4 (0x28)
+#define SR_IEEE_ADDR_4 0x28, 0xff, 0
+#define RG_IEEE_ADDR_5 (0x29)
+#define SR_IEEE_ADDR_5 0x29, 0xff, 0
+#define RG_IEEE_ADDR_6 (0x2a)
+#define SR_IEEE_ADDR_6 0x2a, 0xff, 0
+#define RG_IEEE_ADDR_7 (0x2b)
+#define SR_IEEE_ADDR_7 0x2b, 0xff, 0
+#define RG_XAH_CTRL_0 (0x2c)
+#define SR_SLOTTED_OPERATION 0x2c, 0x01, 0
+#define SR_MAX_CSMA_RETRIES 0x2c, 0x0e, 1
+#define SR_MAX_FRAME_RETRIES 0x2c, 0xf0, 4
+#define RG_CSMA_SEED_0 (0x2d)
+#define SR_CSMA_SEED_0 0x2d, 0xff, 0
+#define RG_CSMA_SEED_1 (0x2e)
+#define SR_CSMA_SEED_1 0x2e, 0x07, 0
+#define SR_AACK_I_AM_COORD 0x2e, 0x08, 3
+#define SR_AACK_DIS_ACK 0x2e, 0x10, 4
+#define SR_AACK_SET_PD 0x2e, 0x20, 5
+#define SR_AACK_FVN_MODE 0x2e, 0xc0, 6
+#define RG_CSMA_BE (0x2f)
+#define SR_MIN_BE 0x2f, 0x0f, 0
+#define SR_MAX_BE 0x2f, 0xf0, 4
#define CMD_REG 0x80
#define CMD_REG_MASK 0x3f
#define STATE_BUSY_RX_AACK_NOCLK 0x1E
#define STATE_TRANSITION_IN_PROGRESS 0x1F
+#define TRX_STATE_MASK (0x1F)
+
#define AT86RF2XX_NUMREGS 0x3F
static void
return regmap_update_bits(lp->regmap, addr, mask, data << shift);
}
+static inline void
+at86rf230_slp_tr_rising_edge(struct at86rf230_local *lp)
+{
+ gpio_set_value(lp->slp_tr, 1);
+ udelay(1);
+ gpio_set_value(lp->slp_tr, 0);
+}
+
static bool
at86rf230_reg_writeable(struct device *dev, unsigned int reg)
{
struct at86rf230_state_change *ctx = context;
struct at86rf230_local *lp = ctx->lp;
const u8 *buf = ctx->buf;
- const u8 trx_state = buf[1] & 0x1f;
+ const u8 trx_state = buf[1] & TRX_STATE_MASK;
/* Assert state change */
if (trx_state != ctx->to_state) {
switch (ctx->to_state) {
case STATE_RX_AACK_ON:
tim = ktime_set(0, c->t_off_to_aack * NSEC_PER_USEC);
+ /* state change from TRX_OFF to RX_AACK_ON to do a
+ * calibration, we need to reset the timeout for the
+ * next one.
+ */
+ lp->cal_timeout = jiffies + AT86RF2XX_CAL_LOOP_TIMEOUT;
goto change;
+ case STATE_TX_ARET_ON:
case STATE_TX_ON:
tim = ktime_set(0, c->t_off_to_tx_on * NSEC_PER_USEC);
- /* state change from TRX_OFF to TX_ON to do a
- * calibration, we need to reset the timeout for the
+ /* state change from TRX_OFF to TX_ON or ARET_ON to do
+ * a calibration, we need to reset the timeout for the
* next one.
*/
lp->cal_timeout = jiffies + AT86RF2XX_CAL_LOOP_TIMEOUT;
struct at86rf230_state_change *ctx = context;
struct at86rf230_local *lp = ctx->lp;
u8 *buf = ctx->buf;
- const u8 trx_state = buf[1] & 0x1f;
+ const u8 trx_state = buf[1] & TRX_STATE_MASK;
int rc;
/* Check for "possible" STATE_TRANSITION_IN_PROGRESS */
at86rf230_tx_complete, true);
}
-static void
-at86rf230_tx_trac_error(void *context)
-{
- struct at86rf230_state_change *ctx = context;
- struct at86rf230_local *lp = ctx->lp;
-
- at86rf230_async_state_change(lp, ctx, STATE_TX_ON,
- at86rf230_tx_on, true);
-}
-
static void
at86rf230_tx_trac_check(void *context)
{
const u8 trac = (buf[1] & 0xe0) >> 5;
/* If trac status is different than zero we need to do a state change
- * to STATE_FORCE_TRX_OFF then STATE_TX_ON to recover the transceiver
- * state to TX_ON.
+ * to STATE_FORCE_TRX_OFF then STATE_RX_AACK_ON to recover the
+ * transceiver.
*/
if (trac)
at86rf230_async_state_change(lp, ctx, STATE_FORCE_TRX_OFF,
- at86rf230_tx_trac_error, true);
+ at86rf230_tx_on, true);
else
at86rf230_tx_on(context);
}
u8 *buf = ctx->buf;
int rc;
- buf[0] = (RG_TRX_STATE & CMD_REG_MASK) | CMD_REG | CMD_WRITE;
- buf[1] = STATE_BUSY_TX;
ctx->trx.len = 2;
- ctx->msg.complete = NULL;
- rc = spi_async(lp->spi, &ctx->msg);
- if (rc)
- at86rf230_async_error(lp, ctx, rc);
+
+ if (gpio_is_valid(lp->slp_tr)) {
+ at86rf230_slp_tr_rising_edge(lp);
+ } else {
+ buf[0] = (RG_TRX_STATE & CMD_REG_MASK) | CMD_REG | CMD_WRITE;
+ buf[1] = STATE_BUSY_TX;
+ ctx->msg.complete = NULL;
+ rc = spi_async(lp->spi, &ctx->msg);
+ if (rc)
+ at86rf230_async_error(lp, ctx, rc);
+ }
}
static void
* are in STATE_TX_ON. The pfad differs here, so we change
* the complete handler.
*/
- if (lp->tx_aret)
- at86rf230_async_state_change(lp, ctx, STATE_TX_ON,
- at86rf230_xmit_tx_on, false);
- else
+ if (lp->tx_aret) {
+ if (lp->is_tx_from_off) {
+ lp->is_tx_from_off = false;
+ at86rf230_async_state_change(lp, ctx, STATE_TX_ARET_ON,
+ at86rf230_xmit_tx_on,
+ false);
+ } else {
+ at86rf230_async_state_change(lp, ctx, STATE_TX_ON,
+ at86rf230_xmit_tx_on,
+ false);
+ }
+ } else {
at86rf230_async_state_change(lp, ctx, STATE_TX_ON,
at86rf230_write_frame, false);
+ }
}
static int
* to TX_ON, the lp->cal_timeout should be reinit by state_delay
* function then to start in the next 5 minutes.
*/
- if (time_is_before_jiffies(lp->cal_timeout))
+ if (time_is_before_jiffies(lp->cal_timeout)) {
+ lp->is_tx_from_off = true;
at86rf230_async_state_change(lp, ctx, STATE_TRX_OFF,
at86rf230_xmit_start, false);
- else
+ } else {
at86rf230_xmit_start(ctx);
+ }
return 0;
}
static int
at86rf230_start(struct ieee802154_hw *hw)
{
- struct at86rf230_local *lp = hw->priv;
-
- lp->cal_timeout = jiffies + AT86RF2XX_CAL_LOOP_TIMEOUT;
return at86rf230_sync_state_change(hw->priv, STATE_RX_AACK_ON);
}
lp = hw->priv;
lp->hw = hw;
lp->spi = spi;
+ lp->slp_tr = slp_tr;
hw->parent = &spi->dev;
hw->vif_data_size = sizeof(*lp);
ieee802154_random_extended_addr(&hw->phy->perm_extended_addr);
goto del_unicast;
}
+ if (dev->flags & IFF_PROMISC) {
+ err = dev_set_promiscuity(lowerdev, 1);
+ if (err < 0)
+ goto clear_multi;
+ }
+
hash_add:
macvlan_hash_add(vlan);
return 0;
+clear_multi:
+ dev_set_allmulti(lowerdev, -1);
del_unicast:
dev_uc_del(lowerdev, dev->dev_addr);
out:
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, -1);
+ if (dev->flags & IFF_PROMISC)
+ dev_set_promiscuity(lowerdev, -1);
+
dev_uc_del(lowerdev, dev->dev_addr);
hash_del:
if (dev->flags & IFF_UP) {
if (change & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+ if (change & IFF_PROMISC)
+ dev_set_promiscuity(lowerdev,
+ dev->flags & IFF_PROMISC ? 1 : -1);
+
}
}
config AMD_XGBE_PHY
tristate "Driver for the AMD 10GbE (amd-xgbe) PHYs"
depends on (OF || ACPI) && HAS_IOMEM
+ depends on ARM64 || COMPILE_TEST
---help---
Currently supports the AMD 10GbE PHY
return ret;
}
+static bool amd_xgbe_phy_use_xgmii_mode(struct phy_device *phydev)
+{
+ if (phydev->autoneg == AUTONEG_ENABLE) {
+ if (phydev->advertising & ADVERTISED_10000baseKR_Full)
+ return true;
+ } else {
+ if (phydev->speed == SPEED_10000)
+ return true;
+ }
+
+ return false;
+}
+
+static bool amd_xgbe_phy_use_gmii_2500_mode(struct phy_device *phydev)
+{
+ if (phydev->autoneg == AUTONEG_ENABLE) {
+ if (phydev->advertising & ADVERTISED_2500baseX_Full)
+ return true;
+ } else {
+ if (phydev->speed == SPEED_2500)
+ return true;
+ }
+
+ return false;
+}
+
+static bool amd_xgbe_phy_use_gmii_mode(struct phy_device *phydev)
+{
+ if (phydev->autoneg == AUTONEG_ENABLE) {
+ if (phydev->advertising & ADVERTISED_1000baseKX_Full)
+ return true;
+ } else {
+ if (phydev->speed == SPEED_1000)
+ return true;
+ }
+
+ return false;
+}
+
static int amd_xgbe_phy_set_an(struct phy_device *phydev, bool enable,
bool restart)
{
/* Set initial mode - call the mode setting routines
* directly to insure we are properly configured
*/
- if (phydev->advertising & SUPPORTED_10000baseKR_Full)
+ if (amd_xgbe_phy_use_xgmii_mode(phydev))
ret = amd_xgbe_phy_xgmii_mode(phydev);
- else if (phydev->advertising & SUPPORTED_1000baseKX_Full)
+ else if (amd_xgbe_phy_use_gmii_mode(phydev))
ret = amd_xgbe_phy_gmii_mode(phydev);
- else if (phydev->advertising & SUPPORTED_2500baseX_Full)
+ else if (amd_xgbe_phy_use_gmii_2500_mode(phydev))
ret = amd_xgbe_phy_gmii_2500_mode(phydev);
else
ret = -EINVAL;
.name = "Broadcom BCM7425",
.features = PHY_GBIT_FEATURES |
SUPPORTED_Pause | SUPPORTED_Asym_Pause,
- .flags = 0,
+ .flags = PHY_IS_INTERNAL,
.config_init = bcm7xxx_config_init,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
#define PSF_TX 0x1000
#define EXT_EVENT 1
#define CAL_EVENT 7
-#define CAL_TRIGGER 7
+#define CAL_TRIGGER 1
#define DP83640_N_PINS 12
#define MII_DP83640_MICR 0x11
else
evnt |= EVNT_RISE;
}
+ mutex_lock(&clock->extreg_lock);
ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
+ mutex_unlock(&clock->extreg_lock);
return 0;
case PTP_CLK_REQ_PEROUT:
static void enable_status_frames(struct phy_device *phydev, bool on)
{
+ struct dp83640_private *dp83640 = phydev->priv;
+ struct dp83640_clock *clock = dp83640->clock;
u16 cfg0 = 0, ver;
if (on)
ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT;
+ mutex_lock(&clock->extreg_lock);
+
ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0);
ext_write(0, phydev, PAGE6, PSF_CFG1, ver);
+ mutex_unlock(&clock->extreg_lock);
+
if (!phydev->attached_dev) {
pr_warn("expected to find an attached netdevice\n");
return;
list_del_init(&rxts->list);
phy2rxts(phy_rxts, rxts);
- spin_lock_irqsave(&dp83640->rx_queue.lock, flags);
+ spin_lock(&dp83640->rx_queue.lock);
skb_queue_walk(&dp83640->rx_queue, skb) {
struct dp83640_skb_info *skb_info;
break;
}
}
- spin_unlock_irqrestore(&dp83640->rx_queue.lock, flags);
+ spin_unlock(&dp83640->rx_queue.lock);
if (!shhwtstamps)
list_add_tail(&rxts->list, &dp83640->rxts);
if (clock->chosen && !list_empty(&clock->phylist))
recalibrate(clock);
- else
+ else {
+ mutex_lock(&clock->extreg_lock);
enable_broadcast(phydev, clock->page, 1);
+ mutex_unlock(&clock->extreg_lock);
+ }
enable_status_frames(phydev, true);
+
+ mutex_lock(&clock->extreg_lock);
ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+ mutex_unlock(&clock->extreg_lock);
+
return 0;
}
if (!new_bus->irq[i])
new_bus->irq[i] = PHY_POLL;
- snprintf(new_bus->id, MII_BUS_ID_SIZE, "gpio-%x", bus_id);
+ if (bus_id != -1)
+ snprintf(new_bus->id, MII_BUS_ID_SIZE, "gpio-%x", bus_id);
+ else
+ strncpy(new_bus->id, "gpio", MII_BUS_ID_SIZE);
if (devm_gpio_request(dev, bitbang->mdc, "mdc"))
goto out_free_bus;
}
clk = devm_clk_get(&phydev->dev, "rmii-ref");
- if (!IS_ERR(clk)) {
+ /* NOTE: clk may be NULL if building without CONFIG_HAVE_CLK */
+ if (!IS_ERR_OR_NULL(clk)) {
unsigned long rate = clk_get_rate(clk);
bool rmii_ref_clk_sel_25_mhz;
*/
void phy_start(struct phy_device *phydev)
{
+ bool do_resume = false;
+ int err = 0;
+
mutex_lock(&phydev->lock);
switch (phydev->state) {
phydev->state = PHY_UP;
break;
case PHY_HALTED:
+ /* make sure interrupts are re-enabled for the PHY */
+ err = phy_enable_interrupts(phydev);
+ if (err < 0)
+ break;
+
phydev->state = PHY_RESUMING;
+ do_resume = true;
+ break;
default:
break;
}
mutex_unlock(&phydev->lock);
+
+ /* if phy was suspended, bring the physical link up again */
+ if (do_resume)
+ phy_resume(phydev);
}
EXPORT_SYMBOL(phy_start);
struct delayed_work *dwork = to_delayed_work(work);
struct phy_device *phydev =
container_of(dwork, struct phy_device, state_queue);
- bool needs_aneg = false, do_suspend = false, do_resume = false;
+ bool needs_aneg = false, do_suspend = false;
int err = 0;
mutex_lock(&phydev->lock);
}
break;
case PHY_RESUMING:
- err = phy_clear_interrupt(phydev);
- if (err)
- break;
-
- err = phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED);
- if (err)
- break;
-
if (AUTONEG_ENABLE == phydev->autoneg) {
err = phy_aneg_done(phydev);
if (err < 0)
}
phydev->adjust_link(phydev->attached_dev);
}
- do_resume = true;
break;
}
err = phy_start_aneg(phydev);
else if (do_suspend)
phy_suspend(phydev);
- else if (do_resume)
- phy_resume(phydev);
if (err < 0)
phy_error(phydev);
{
/* According to 802.3az,the EEE is supported only in full duplex-mode.
* Also EEE feature is active when core is operating with MII, GMII
- * or RGMII. Internal PHYs are also allowed to proceed and should
- * return an error if they do not support EEE.
+ * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
+ * should return an error if they do not support EEE.
*/
if ((phydev->duplex == DUPLEX_FULL) &&
((phydev->interface == PHY_INTERFACE_MODE_MII) ||
(phydev->interface == PHY_INTERFACE_MODE_GMII) ||
- (phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
+ (phydev->interface >= PHY_INTERFACE_MODE_RGMII &&
+ phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID) ||
phy_is_internal(phydev))) {
int eee_lp, eee_cap, eee_adv;
u32 lp, cap, adv;
struct sock *sk = sk_pppox(po);
lock_sock(sk);
+ if (po->pppoe_dev) {
+ dev_put(po->pppoe_dev);
+ po->pppoe_dev = NULL;
+ }
pppox_unbind_sock(sk);
release_sock(sk);
sock_put(sk);
* payload data instead.
*/
usbnet_set_skb_tx_stats(skb_out, n,
- ctx->tx_curr_frame_payload - skb_out->len);
+ (long)ctx->tx_curr_frame_payload - skb_out->len);
return skb_out;
{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7205)},
+ {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f)},
{}
};
struct net_device *net)
{
struct usbnet *dev = netdev_priv(net);
- int length;
+ unsigned int length;
struct urb *urb = NULL;
struct skb_data *entry;
struct driver_info *info = dev->driver_info;
}
} else
netif_dbg(dev, tx_queued, dev->net,
- "> tx, len %d, type 0x%x\n", length, skb->protocol);
+ "> tx, len %u, type 0x%x\n", length, skb->protocol);
#ifdef CONFIG_PM
deferred:
#endif
* to the list by the previous loop.
*/
if (!net_eq(dev_net(vxlan->dev), net))
- unregister_netdevice_queue(dev, &list);
+ unregister_netdevice_queue(vxlan->dev, &list);
}
unregister_netdevice_many(&list);
struct sk_buff *skb;
struct ath_frame_info *fi;
struct ieee80211_tx_info *info;
- struct ieee80211_vif *vif;
struct ath_hw *ah = sc->sc_ah;
if (sc->tx99_state || !ah->tpc_enabled)
return MAX_RATE_POWER;
skb = bf->bf_mpdu;
- info = IEEE80211_SKB_CB(skb);
- vif = info->control.vif;
-
- if (!vif) {
- max_power = sc->cur_chan->cur_txpower;
- goto out;
- }
-
- if (vif->bss_conf.txpower_type != NL80211_TX_POWER_LIMITED) {
- max_power = min_t(u8, sc->cur_chan->cur_txpower,
- 2 * vif->bss_conf.txpower);
- goto out;
- }
-
fi = get_frame_info(skb);
+ info = IEEE80211_SKB_CB(skb);
if (!AR_SREV_9300_20_OR_LATER(ah)) {
int txpower = fi->tx_power;
txpower -= 2;
txpower = max(txpower, 0);
- max_power = min_t(u8, ah->tx_power[rateidx],
- 2 * vif->bss_conf.txpower);
- max_power = min_t(u8, max_power, txpower);
+ max_power = min_t(u8, ah->tx_power[rateidx], txpower);
+
+ /* XXX: clamp minimum TX power at 1 for AR9160 since if
+ * max_power is set to 0, frames are transmitted at max
+ * TX power
+ */
+ if (!max_power && !AR_SREV_9280_20_OR_LATER(ah))
+ max_power = 1;
} else if (!bf->bf_state.bfs_paprd) {
if (rateidx < 8 && (info->flags & IEEE80211_TX_CTL_STBC))
max_power = min_t(u8, ah->tx_power_stbc[rateidx],
- 2 * vif->bss_conf.txpower);
+ fi->tx_power);
else
max_power = min_t(u8, ah->tx_power[rateidx],
- 2 * vif->bss_conf.txpower);
- max_power = min(max_power, fi->tx_power);
+ fi->tx_power);
} else {
max_power = ah->paprd_training_power;
}
-out:
- /* XXX: clamp minimum TX power at 1 for AR9160 since if max_power
- * is set to 0, frames are transmitted at max TX power
- */
- return (!max_power && !AR_SREV_9280_20_OR_LATER(ah)) ? 1 : max_power;
+
+ return max_power;
}
static void ath_buf_set_rate(struct ath_softc *sc, struct ath_buf *bf,
struct ath_node *an = NULL;
enum ath9k_key_type keytype;
bool short_preamble = false;
+ u8 txpower;
/*
* We check if Short Preamble is needed for the CTS rate by
if (sta)
an = (struct ath_node *) sta->drv_priv;
+ if (tx_info->control.vif) {
+ struct ieee80211_vif *vif = tx_info->control.vif;
+
+ txpower = 2 * vif->bss_conf.txpower;
+ } else {
+ struct ath_softc *sc = hw->priv;
+
+ txpower = sc->cur_chan->cur_txpower;
+ }
+
memset(fi, 0, sizeof(*fi));
fi->txq = -1;
if (hw_key)
fi->keyix = ATH9K_TXKEYIX_INVALID;
fi->keytype = keytype;
fi->framelen = framelen;
- fi->tx_power = MAX_RATE_POWER;
+ fi->tx_power = txpower;
if (!rate)
return;
msgbuf->rx_pktids,
msgbuf->ioctl_resp_pktid);
if (msgbuf->ioctl_resp_ret_len != 0) {
- if (!skb) {
- brcmf_err("Invalid packet id idx recv'd %d\n",
- msgbuf->ioctl_resp_pktid);
+ if (!skb)
return -EBADF;
- }
+
memcpy(buf, skb->data, (len < msgbuf->ioctl_resp_ret_len) ?
len : msgbuf->ioctl_resp_ret_len);
}
flowid -= BRCMF_NROF_H2D_COMMON_MSGRINGS;
skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev,
msgbuf->tx_pktids, idx);
- if (!skb) {
- brcmf_err("Invalid packet id idx recv'd %d\n", idx);
+ if (!skb)
return;
- }
set_bit(flowid, msgbuf->txstatus_done_map);
commonring = msgbuf->flowrings[flowid];
skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev,
msgbuf->rx_pktids, idx);
+ if (!skb)
+ return;
if (data_offset)
skb_pull(skb, data_offset);
Intel 7260 Wi-Fi Adapter
Intel 3160 Wi-Fi Adapter
Intel 7265 Wi-Fi Adapter
+ Intel 3165 Wi-Fi Adapter
This driver uses the kernel's mac80211 subsystem.
/* Highest firmware API version supported */
#define IWL7260_UCODE_API_MAX 13
-#define IWL3160_UCODE_API_MAX 13
/* Oldest version we won't warn about */
#define IWL7260_UCODE_API_OK 12
-#define IWL3160_UCODE_API_OK 12
+#define IWL3165_UCODE_API_OK 13
/* Lowest firmware API version supported */
#define IWL7260_UCODE_API_MIN 10
-#define IWL3160_UCODE_API_MIN 10
+#define IWL3165_UCODE_API_MIN 13
/* NVM versions */
#define IWL7260_NVM_VERSION 0x0a1d
#define IWL3160_FW_PRE "iwlwifi-3160-"
#define IWL3160_MODULE_FIRMWARE(api) IWL3160_FW_PRE __stringify(api) ".ucode"
-#define IWL3165_FW_PRE "iwlwifi-3165-"
-#define IWL3165_MODULE_FIRMWARE(api) IWL3165_FW_PRE __stringify(api) ".ucode"
-
#define IWL7265_FW_PRE "iwlwifi-7265-"
#define IWL7265_MODULE_FIRMWARE(api) IWL7265_FW_PRE __stringify(api) ".ucode"
const struct iwl_cfg iwl3165_2ac_cfg = {
.name = "Intel(R) Dual Band Wireless AC 3165",
- .fw_name_pre = IWL3165_FW_PRE,
+ .fw_name_pre = IWL7265D_FW_PRE,
IWL_DEVICE_7000,
+ /* sparse doens't like the re-assignment but it is safe */
+#ifndef __CHECKER__
+ .ucode_api_ok = IWL3165_UCODE_API_OK,
+ .ucode_api_min = IWL3165_UCODE_API_MIN,
+#endif
.ht_params = &iwl7000_ht_params,
.nvm_ver = IWL3165_NVM_VERSION,
.nvm_calib_ver = IWL3165_TX_POWER_VERSION,
MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL3160_UCODE_API_OK));
-MODULE_FIRMWARE(IWL3165_MODULE_FIRMWARE(IWL3160_UCODE_API_OK));
MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
* GPL LICENSE SUMMARY
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* BSD LICENSE
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
return;
}
+ if (data->sku_cap_mimo_disabled)
+ rx_chains = 1;
+
ht_info->ht_supported = true;
ht_info->cap = IEEE80211_HT_CAP_DSSSCCK40;
* GPL LICENSE SUMMARY
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* BSD LICENSE
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
bool sku_cap_11ac_enable;
bool sku_cap_amt_enable;
bool sku_cap_ipan_enable;
+ bool sku_cap_mimo_disabled;
u16 radio_cfg_type;
u8 radio_cfg_step;
* longer than the passive one, which is essential for fragmented scan.
* @IWL_UCODE_TLV_API_WIFI_MCC_UPDATE: ucode supports MCC updates with source.
* IWL_UCODE_TLV_API_HDC_PHASE_0: ucode supports finer configuration of LTR
+ * @IWL_UCODE_TLV_API_TX_POWER_DEV: new API for tx power.
* @IWL_UCODE_TLV_API_BASIC_DWELL: use only basic dwell time in scan command,
* regardless of the band or the number of the probes. FW will calculate
* the actual dwell time.
IWL_UCODE_TLV_API_FRAGMENTED_SCAN = BIT(8),
IWL_UCODE_TLV_API_WIFI_MCC_UPDATE = BIT(9),
IWL_UCODE_TLV_API_HDC_PHASE_0 = BIT(10),
+ IWL_UCODE_TLV_API_TX_POWER_DEV = BIT(11),
IWL_UCODE_TLV_API_BASIC_DWELL = BIT(13),
IWL_UCODE_TLV_API_SCD_CFG = BIT(15),
IWL_UCODE_TLV_API_SINGLE_SCAN_EBS = BIT(16),
* GPL LICENSE SUMMARY
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* BSD LICENSE
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/* SKU Capabilities (actual values from NVM definition) */
enum nvm_sku_bits {
- NVM_SKU_CAP_BAND_24GHZ = BIT(0),
- NVM_SKU_CAP_BAND_52GHZ = BIT(1),
- NVM_SKU_CAP_11N_ENABLE = BIT(2),
- NVM_SKU_CAP_11AC_ENABLE = BIT(3),
+ NVM_SKU_CAP_BAND_24GHZ = BIT(0),
+ NVM_SKU_CAP_BAND_52GHZ = BIT(1),
+ NVM_SKU_CAP_11N_ENABLE = BIT(2),
+ NVM_SKU_CAP_11AC_ENABLE = BIT(3),
+ NVM_SKU_CAP_MIMO_DISABLE = BIT(5),
};
/*
if (cfg->ht_params->ldpc)
vht_cap->cap |= IEEE80211_VHT_CAP_RXLDPC;
+ if (data->sku_cap_mimo_disabled) {
+ num_rx_ants = 1;
+ num_tx_ants = 1;
+ }
+
if (num_tx_ants > 1)
vht_cap->cap |= IEEE80211_VHT_CAP_TXSTBC;
else
if (cfg->device_family != IWL_DEVICE_FAMILY_8000)
return le16_to_cpup(nvm_sw + RADIO_CFG);
- return le32_to_cpup((__le32 *)(nvm_sw + RADIO_CFG_FAMILY_8000));
+ return le32_to_cpup((__le32 *)(phy_sku + RADIO_CFG_FAMILY_8000));
}
const u8 *hw_addr;
if (mac_override) {
+ static const u8 reserved_mac[] = {
+ 0x02, 0xcc, 0xaa, 0xff, 0xee, 0x00
+ };
+
hw_addr = (const u8 *)(mac_override +
MAC_ADDRESS_OVERRIDE_FAMILY_8000);
data->hw_addr[4] = hw_addr[5];
data->hw_addr[5] = hw_addr[4];
- if (is_valid_ether_addr(data->hw_addr))
+ /*
+ * Force the use of the OTP MAC address in case of reserved MAC
+ * address in the NVM, or if address is given but invalid.
+ */
+ if (is_valid_ether_addr(data->hw_addr) &&
+ memcmp(reserved_mac, hw_addr, ETH_ALEN) != 0)
return;
IWL_ERR_DEV(dev,
data->sku_cap_11n_enable = false;
data->sku_cap_11ac_enable = data->sku_cap_11n_enable &&
(sku & NVM_SKU_CAP_11AC_ENABLE);
+ data->sku_cap_mimo_disabled = sku & NVM_SKU_CAP_MIMO_DISABLE;
data->n_hw_addrs = iwl_get_n_hw_addrs(cfg, nvm_sw);
* GPL LICENSE SUMMARY
*
* Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* BSD LICENSE
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*
* All the handlers MUST be implemented
*
- * @start_hw: starts the HW- from that point on, the HW can send interrupts
- * May sleep
+ * @start_hw: starts the HW. If low_power is true, the NIC needs to be taken
+ * out of a low power state. From that point on, the HW can send
+ * interrupts. May sleep.
* @op_mode_leave: Turn off the HW RF kill indication if on
* May sleep
* @start_fw: allocates and inits all the resources for the transport
* the SCD base address in SRAM, then provide it here, or 0 otherwise.
* May sleep
* @stop_device: stops the whole device (embedded CPU put to reset) and stops
- * the HW. From that point on, the HW will be in low power but will still
- * issue interrupt if the HW RF kill is triggered. This callback must do
- * the right thing and not crash even if start_hw() was called but not
- * start_fw(). May sleep
+ * the HW. If low_power is true, the NIC will be put in low power state.
+ * From that point on, the HW will be stopped but will still issue an
+ * interrupt if the HW RF kill switch is triggered.
+ * This callback must do the right thing and not crash even if %start_hw()
+ * was called but not &start_fw(). May sleep.
* @d3_suspend: put the device into the correct mode for WoWLAN during
* suspend. This is optional, if not implemented WoWLAN will not be
* supported. This callback may sleep.
*/
struct iwl_trans_ops {
- int (*start_hw)(struct iwl_trans *iwl_trans);
+ int (*start_hw)(struct iwl_trans *iwl_trans, bool low_power);
void (*op_mode_leave)(struct iwl_trans *iwl_trans);
int (*start_fw)(struct iwl_trans *trans, const struct fw_img *fw,
bool run_in_rfkill);
int (*update_sf)(struct iwl_trans *trans,
struct iwl_sf_region *st_fwrd_space);
void (*fw_alive)(struct iwl_trans *trans, u32 scd_addr);
- void (*stop_device)(struct iwl_trans *trans);
+ void (*stop_device)(struct iwl_trans *trans, bool low_power);
void (*d3_suspend)(struct iwl_trans *trans, bool test);
int (*d3_resume)(struct iwl_trans *trans, enum iwl_d3_status *status,
trans->ops->configure(trans, trans_cfg);
}
-static inline int iwl_trans_start_hw(struct iwl_trans *trans)
+static inline int _iwl_trans_start_hw(struct iwl_trans *trans, bool low_power)
{
might_sleep();
- return trans->ops->start_hw(trans);
+ return trans->ops->start_hw(trans, low_power);
+}
+
+static inline int iwl_trans_start_hw(struct iwl_trans *trans)
+{
+ return trans->ops->start_hw(trans, true);
}
static inline void iwl_trans_op_mode_leave(struct iwl_trans *trans)
return 0;
}
-static inline void iwl_trans_stop_device(struct iwl_trans *trans)
+static inline void _iwl_trans_stop_device(struct iwl_trans *trans,
+ bool low_power)
{
might_sleep();
- trans->ops->stop_device(trans);
+ trans->ops->stop_device(trans, low_power);
trans->state = IWL_TRANS_NO_FW;
}
+static inline void iwl_trans_stop_device(struct iwl_trans *trans)
+{
+ _iwl_trans_stop_device(trans, true);
+}
+
static inline void iwl_trans_d3_suspend(struct iwl_trans *trans, bool test)
{
might_sleep();
struct iwl_host_cmd cmd = {
.id = BT_CONFIG,
.len = { sizeof(*bt_cmd), },
- .dataflags = { IWL_HCMD_DFL_NOCOPY, },
+ .dataflags = { IWL_HCMD_DFL_DUP, },
.flags = CMD_ASYNC,
};
struct iwl_mvm_sta *mvmsta;
results->matched_profiles = le32_to_cpu(query->matched_profiles);
memcpy(results->matches, query->matches, sizeof(results->matches));
-#ifdef CPTCFG_IWLWIFI_DEBUGFS
+#ifdef CONFIG_IWLWIFI_DEBUGFS
mvm->last_netdetect_scans = le32_to_cpu(query->n_scans_done);
#endif
int i, j, n_matches, ret;
fw_status = iwl_mvm_get_wakeup_status(mvm, vif);
- if (!IS_ERR_OR_NULL(fw_status))
+ if (!IS_ERR_OR_NULL(fw_status)) {
reasons = le32_to_cpu(fw_status->wakeup_reasons);
+ kfree(fw_status);
+ }
if (reasons & IWL_WOWLAN_WAKEUP_BY_RFKILL_DEASSERTED)
wakeup.rfkill_release = true;
/* get the BSS vif pointer again */
vif = iwl_mvm_get_bss_vif(mvm);
if (IS_ERR_OR_NULL(vif))
- goto out_unlock;
+ goto err;
ret = iwl_trans_d3_resume(mvm->trans, &d3_status, test);
if (ret)
- goto out_unlock;
+ goto err;
if (d3_status != IWL_D3_STATUS_ALIVE) {
IWL_INFO(mvm, "Device was reset during suspend\n");
- goto out_unlock;
+ goto err;
}
/* query SRAM first in case we want event logging */
goto out_iterate;
}
- out_unlock:
+err:
+ iwl_mvm_free_nd(mvm);
mutex_unlock(&mvm->mutex);
out_iterate:
/* return 1 to reconfigure the device */
set_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
set_bit(IWL_MVM_STATUS_D3_RECONFIG, &mvm->status);
+
+ /* We always return 1, which causes mac80211 to do a reconfig
+ * with IEEE80211_RECONFIG_TYPE_RESTART. This type of
+ * reconfig calls iwl_mvm_restart_complete(), where we unref
+ * the IWL_MVM_REF_UCODE_DOWN, so we need to take the
+ * reference here.
+ */
+ iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
return 1;
}
__iwl_mvm_resume(mvm, true);
rtnl_unlock();
iwl_abort_notification_waits(&mvm->notif_wait);
- iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
ieee80211_restart_hw(mvm->hw);
/* wait for restart and disconnect all interfaces */
u8 reserved[3];
} __packed;
+/**
+ * struct iwl_reduce_tx_power_cmd - TX power reduction command
+ * REDUCE_TX_POWER_CMD = 0x9f
+ * @flags: (reserved for future implementation)
+ * @mac_context_id: id of the mac ctx for which we are reducing TX power.
+ * @pwr_restriction: TX power restriction in dBms.
+ */
+struct iwl_reduce_tx_power_cmd {
+ u8 flags;
+ u8 mac_context_id;
+ __le16 pwr_restriction;
+} __packed; /* TX_REDUCED_POWER_API_S_VER_1 */
+
+/**
+ * struct iwl_dev_tx_power_cmd - TX power reduction command
+ * REDUCE_TX_POWER_CMD = 0x9f
+ * @set_mode: 0 - MAC tx power, 1 - device tx power
+ * @mac_context_id: id of the mac ctx for which we are reducing TX power.
+ * @pwr_restriction: TX power restriction in 1/8 dBms.
+ * @dev_24: device TX power restriction in 1/8 dBms
+ * @dev_52_low: device TX power restriction upper band - low
+ * @dev_52_high: device TX power restriction upper band - high
+ */
+struct iwl_dev_tx_power_cmd {
+ __le32 set_mode;
+ __le32 mac_context_id;
+ __le16 pwr_restriction;
+ __le16 dev_24;
+ __le16 dev_52_low;
+ __le16 dev_52_high;
+} __packed; /* TX_REDUCED_POWER_API_S_VER_2 */
+
+#define IWL_DEV_MAX_TX_POWER 0x7FFF
+
/**
* struct iwl_beacon_filter_cmd
* REPLY_BEACON_FILTERING_CMD = 0xd2 (command)
SCAN_COMP_STATUS_ERR_ALLOC_TE = 0x0C,
};
-/**
- * struct iwl_scan_results_notif - scan results for one channel
- * ( SCAN_RESULTS_NOTIFICATION = 0x83 )
- * @channel: which channel the results are from
- * @band: 0 for 5.2 GHz, 1 for 2.4 GHz
- * @probe_status: SCAN_PROBE_STATUS_*, indicates success of probe request
- * @num_probe_not_sent: # of request that weren't sent due to not enough time
- * @duration: duration spent in channel, in usecs
- * @statistics: statistics gathered for this channel
- */
-struct iwl_scan_results_notif {
- u8 channel;
- u8 band;
- u8 probe_status;
- u8 num_probe_not_sent;
- __le32 duration;
- __le32 statistics[SCAN_RESULTS_STATISTICS];
-} __packed; /* SCAN_RESULT_NTF_API_S_VER_2 */
-
-/**
- * struct iwl_scan_complete_notif - notifies end of scanning (all channels)
- * ( SCAN_COMPLETE_NOTIFICATION = 0x84 )
- * @scanned_channels: number of channels scanned (and number of valid results)
- * @status: one of SCAN_COMP_STATUS_*
- * @bt_status: BT on/off status
- * @last_channel: last channel that was scanned
- * @tsf_low: TSF timer (lower half) in usecs
- * @tsf_high: TSF timer (higher half) in usecs
- * @results: array of scan results, only "scanned_channels" of them are valid
- */
-struct iwl_scan_complete_notif {
- u8 scanned_channels;
- u8 status;
- u8 bt_status;
- u8 last_channel;
- __le32 tsf_low;
- __le32 tsf_high;
- struct iwl_scan_results_notif results[];
-} __packed; /* SCAN_COMPLETE_NTF_API_S_VER_2 */
-
/* scan offload */
#define IWL_SCAN_MAX_BLACKLIST_LEN 64
#define IWL_SCAN_SHORT_BLACKLIST_LEN 16
} __packed;
/**
- * struct iwl_lmac_scan_results_notif - scan results for one channel -
+ * struct iwl_scan_results_notif - scan results for one channel -
* SCAN_RESULT_NTF_API_S_VER_3
* @channel: which channel the results are from
* @band: 0 for 5.2 GHz, 1 for 2.4 GHz
* @num_probe_not_sent: # of request that weren't sent due to not enough time
* @duration: duration spent in channel, in usecs
*/
-struct iwl_lmac_scan_results_notif {
+struct iwl_scan_results_notif {
u8 channel;
u8 band;
u8 probe_status;
__le32 valid;
} __packed;
-/**
- * struct iwl_reduce_tx_power_cmd - TX power reduction command
- * REDUCE_TX_POWER_CMD = 0x9f
- * @flags: (reserved for future implementation)
- * @mac_context_id: id of the mac ctx for which we are reducing TX power.
- * @pwr_restriction: TX power restriction in dBms.
- */
-struct iwl_reduce_tx_power_cmd {
- u8 flags;
- u8 mac_context_id;
- __le16 pwr_restriction;
-} __packed; /* TX_REDUCED_POWER_API_S_VER_1 */
-
/*
* Calibration control struct.
* Sent as part of the phy configuration command.
* GPL LICENSE SUMMARY
*
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* BSD LICENSE
*
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
lockdep_assert_held(&mvm->mutex);
- if (WARN_ON_ONCE(mvm->init_ucode_complete || mvm->calibrating))
+ if (WARN_ON_ONCE(mvm->calibrating))
return 0;
iwl_init_notification_wait(&mvm->notif_wait,
*/
ret = iwl_wait_notification(&mvm->notif_wait, &calib_wait,
MVM_UCODE_CALIB_TIMEOUT);
- if (!ret)
- mvm->init_ucode_complete = true;
if (ret && iwl_mvm_is_radio_killed(mvm)) {
IWL_DEBUG_RF_KILL(mvm, "RFKILL while calibrating.\n");
mvm->fw_dump_desc = desc;
- /* stop recording */
- if (mvm->cfg->device_family == IWL_DEVICE_FAMILY_7000) {
- iwl_set_bits_prph(mvm->trans, MON_BUFF_SAMPLE_CTL, 0x100);
- } else {
- iwl_write_prph(mvm->trans, DBGC_IN_SAMPLE, 0);
- /* wait before we collect the data till the DBGC stop */
- udelay(100);
- }
-
queue_delayed_work(system_wq, &mvm->fw_dump_wk, delay);
return 0;
* module loading, load init ucode now
* (for example, if we were in RFKILL)
*/
- if (!mvm->init_ucode_complete) {
- ret = iwl_run_init_mvm_ucode(mvm, false);
- if (ret && !iwlmvm_mod_params.init_dbg) {
- IWL_ERR(mvm, "Failed to run INIT ucode: %d\n", ret);
- /* this can't happen */
- if (WARN_ON(ret > 0))
- ret = -ERFKILL;
- goto error;
- }
- if (!iwlmvm_mod_params.init_dbg) {
- /*
- * should stop and start HW since that INIT
- * image just loaded
- */
- iwl_trans_stop_device(mvm->trans);
- ret = iwl_trans_start_hw(mvm->trans);
- if (ret)
- return ret;
- }
+ ret = iwl_run_init_mvm_ucode(mvm, false);
+ if (ret && !iwlmvm_mod_params.init_dbg) {
+ IWL_ERR(mvm, "Failed to run INIT ucode: %d\n", ret);
+ /* this can't happen */
+ if (WARN_ON(ret > 0))
+ ret = -ERFKILL;
+ goto error;
+ }
+ if (!iwlmvm_mod_params.init_dbg) {
+ /*
+ * Stop and start the transport without entering low power
+ * mode. This will save the state of other components on the
+ * device that are triggered by the INIT firwmare (MFUART).
+ */
+ _iwl_trans_stop_device(mvm->trans, false);
+ _iwl_trans_start_hw(mvm->trans, false);
+ if (ret)
+ return ret;
}
if (iwlmvm_mod_params.init_dbg)
clear_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
iwl_mvm_d0i3_enable_tx(mvm, NULL);
- ret = iwl_mvm_update_quotas(mvm, false, NULL);
+ ret = iwl_mvm_update_quotas(mvm, true, NULL);
if (ret)
IWL_ERR(mvm, "Failed to update quotas after restart (%d)\n",
ret);
return NULL;
}
-static int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
- s8 tx_power)
+static int iwl_mvm_set_tx_power_old(struct iwl_mvm *mvm,
+ struct ieee80211_vif *vif, s8 tx_power)
{
/* FW is in charge of regulatory enforcement */
struct iwl_reduce_tx_power_cmd reduce_txpwr_cmd = {
&reduce_txpwr_cmd);
}
+static int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+ s16 tx_power)
+{
+ struct iwl_dev_tx_power_cmd cmd = {
+ .set_mode = 0,
+ .mac_context_id =
+ cpu_to_le32(iwl_mvm_vif_from_mac80211(vif)->id),
+ .pwr_restriction = cpu_to_le16(8 * tx_power),
+ };
+
+ if (!(mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_TX_POWER_DEV))
+ return iwl_mvm_set_tx_power_old(mvm, vif, tx_power);
+
+ if (tx_power == IWL_DEFAULT_MAX_TX_POWER)
+ cmd.pwr_restriction = cpu_to_le16(IWL_DEV_MAX_TX_POWER);
+
+ return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0,
+ sizeof(cmd), &cmd);
+}
+
static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
struct ieee80211_vif *vif)
{
if (!iwl_fw_dbg_trigger_enabled(mvm->fw, FW_DBG_TRIGGER_MLME))
return;
- if (event->u.mlme.status == MLME_SUCCESS)
- return;
-
trig = iwl_fw_dbg_get_trigger(mvm->fw, FW_DBG_TRIGGER_MLME);
trig_mlme = (void *)trig->data;
if (!iwl_fw_dbg_trigger_check_stop(mvm, vif, trig))
enum iwl_ucode_type cur_ucode;
bool ucode_loaded;
- bool init_ucode_complete;
bool calibrating;
u32 error_event_table;
u32 log_event_table;
return;
mutex_lock(&mvm->mutex);
+
+ /* stop recording */
+ if (mvm->cfg->device_family == IWL_DEVICE_FAMILY_7000) {
+ iwl_set_bits_prph(mvm->trans, MON_BUFF_SAMPLE_CTL, 0x100);
+ } else {
+ iwl_write_prph(mvm->trans, DBGC_IN_SAMPLE, 0);
+ /* wait before we collect the data till the DBGC stop */
+ udelay(100);
+ }
+
iwl_mvm_fw_error_dump(mvm);
/* start recording again if the firmware is not crashed */
ieee80211_iterate_active_interfaces(
mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
iwl_mvm_d0i3_disconnect_iter, mvm);
-
- iwl_free_resp(&get_status_cmd);
out:
iwl_mvm_d0i3_enable_tx(mvm, qos_seq);
+ /* qos_seq might point inside resp_pkt, so free it only now */
+ if (get_status_cmd.resp_pkt)
+ iwl_free_resp(&get_status_cmd);
+
/* the FW might have updated the regdomain */
iwl_mvm_update_changed_regdom(mvm);
if (iwl_mvm_vif_low_latency(mvmvif) && mvmsta->vif->p2p)
return false;
+ if (mvm->nvm_data->sku_cap_mimo_disabled)
+ return false;
+
return true;
}
if (vif->type != NL80211_IFTYPE_STATION)
return;
+ if (sig == 0) {
+ IWL_DEBUG_RX(mvm, "RSSI is 0 - skip signal based decision\n");
+ return;
+ }
+
mvmvif->bf_data.ave_beacon_signal = sig;
/* BT Coex */
struct iwl_device_cmd *cmd)
{
struct iwl_rx_packet *pkt = rxb_addr(rxb);
- struct iwl_scan_complete_notif *notif = (void *)pkt->data;
+ struct iwl_lmac_scan_complete_notif *notif = (void *)pkt->data;
IWL_DEBUG_SCAN(mvm,
"Scan offload iteration complete: status=0x%x scanned channels=%d\n",
/******************************************************************************
*
- * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2003 - 2015 Intel Corporation. All rights reserved.
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
*
* Portions of this file are derived from the ipw3945 project, as well
* as portions of the ieee80211 subsystem header files.
/*protect hw register */
spinlock_t reg_lock;
- bool cmd_in_flight;
+ bool cmd_hold_nic_awake;
bool ref_cmd_in_flight;
/* protect ref counter */
*
* GPL LICENSE SUMMARY
*
- * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2007 - 2015 Intel Corporation. All rights reserved.
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
*
* BSD LICENSE
*
- * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2005 - 2015 Intel Corporation. All rights reserved.
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
static void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
- struct page *page;
+ struct page *page = NULL;
dma_addr_t phys;
u32 size;
u8 power;
DMA_FROM_DEVICE);
if (dma_mapping_error(trans->dev, phys)) {
__free_pages(page, order);
+ page = NULL;
continue;
}
IWL_INFO(trans,
iwl_pcie_tx_start(trans, scd_addr);
}
-static void iwl_trans_pcie_stop_device(struct iwl_trans *trans)
+static void iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
bool hw_rfkill, was_hw_rfkill;
iwl_pcie_rx_stop(trans);
/* Power-down device's busmaster DMA clocks */
- iwl_write_prph(trans, APMG_CLK_DIS_REG,
- APMG_CLK_VAL_DMA_CLK_RQT);
- udelay(5);
+ if (trans->cfg->device_family != IWL_DEVICE_FAMILY_8000) {
+ iwl_write_prph(trans, APMG_CLK_DIS_REG,
+ APMG_CLK_VAL_DMA_CLK_RQT);
+ udelay(5);
+ }
}
/* Make sure (redundant) we've released our request to stay awake */
void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state)
{
if (iwl_op_mode_hw_rf_kill(trans->op_mode, state))
- iwl_trans_pcie_stop_device(trans);
+ iwl_trans_pcie_stop_device(trans, true);
}
static void iwl_trans_pcie_d3_suspend(struct iwl_trans *trans, bool test)
return 0;
}
-static int iwl_trans_pcie_start_hw(struct iwl_trans *trans)
+static int iwl_trans_pcie_start_hw(struct iwl_trans *trans, bool low_power)
{
bool hw_rfkill;
int err;
spin_lock_irqsave(&trans_pcie->reg_lock, *flags);
- if (trans_pcie->cmd_in_flight)
+ if (trans_pcie->cmd_hold_nic_awake)
goto out;
/* this bit wakes up the NIC */
*/
__acquire(&trans_pcie->reg_lock);
- if (trans_pcie->cmd_in_flight)
+ if (trans_pcie->cmd_hold_nic_awake)
goto out;
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
iwl_trans_pcie_ref(trans);
}
- if (trans_pcie->cmd_in_flight)
- return 0;
-
- trans_pcie->cmd_in_flight = true;
-
/*
* wake up the NIC to make sure that the firmware will see the host
* command - we will let the NIC sleep once all the host commands
* returned. This needs to be done only on NICs that have
* apmg_wake_up_wa set.
*/
- if (trans->cfg->base_params->apmg_wake_up_wa) {
+ if (trans->cfg->base_params->apmg_wake_up_wa &&
+ !trans_pcie->cmd_hold_nic_awake) {
__iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL,
CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
if (ret < 0) {
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
- trans_pcie->cmd_in_flight = false;
IWL_ERR(trans, "Failed to wake NIC for hcmd\n");
return -EIO;
}
+ trans_pcie->cmd_hold_nic_awake = true;
}
return 0;
iwl_trans_pcie_unref(trans);
}
- if (WARN_ON(!trans_pcie->cmd_in_flight))
- return 0;
-
- trans_pcie->cmd_in_flight = false;
+ if (trans->cfg->base_params->apmg_wake_up_wa) {
+ if (WARN_ON(!trans_pcie->cmd_hold_nic_awake))
+ return 0;
- if (trans->cfg->base_params->apmg_wake_up_wa)
+ trans_pcie->cmd_hold_nic_awake = false;
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
-
+ CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ }
return 0;
}
do {
status = usb_control_msg(udev, pipe, request, reqtype, value,
- index, pdata, len, 0); /*max. timeout*/
+ index, pdata, len, 1000);
if (status < 0) {
/* firmware download is checksumed, don't retry */
if ((value >= FW_8192C_START_ADDRESS &&
netdev_err(queue->vif->dev,
"txreq.offset: %x, size: %u, end: %lu\n",
txreq.offset, txreq.size,
- (txreq.offset&~PAGE_MASK) + txreq.size);
+ (unsigned long)(txreq.offset&~PAGE_MASK) + txreq.size);
xenvif_fatal_tx_err(queue->vif);
break;
}
enum xenbus_state frontend_state;
struct xenbus_watch hotplug_status_watch;
u8 have_hotplug_status_watch:1;
+
+ const char *hotplug_script;
};
static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
xenvif_free(be->vif);
be->vif = NULL;
}
+ kfree(be->hotplug_script);
kfree(be);
dev_set_drvdata(&dev->dev, NULL);
return 0;
struct xenbus_transaction xbt;
int err;
int sg;
+ const char *script;
struct backend_info *be = kzalloc(sizeof(struct backend_info),
GFP_KERNEL);
if (!be) {
if (err)
pr_debug("Error writing multi-queue-max-queues\n");
+ script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL);
+ if (IS_ERR(script)) {
+ err = PTR_ERR(script);
+ xenbus_dev_fatal(dev, err, "reading script");
+ goto fail;
+ }
+
+ be->hotplug_script = script;
+
err = xenbus_switch_state(dev, XenbusStateInitWait);
if (err)
goto fail;
struct kobj_uevent_env *env)
{
struct backend_info *be = dev_get_drvdata(&xdev->dev);
- char *val;
- val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
- if (IS_ERR(val)) {
- int err = PTR_ERR(val);
- xenbus_dev_fatal(xdev, err, "reading script");
- return err;
- } else {
- if (add_uevent_var(env, "script=%s", val)) {
- kfree(val);
- return -ENOMEM;
- }
- kfree(val);
- }
+ if (!be)
+ return 0;
- if (!be || !be->vif)
+ if (add_uevent_var(env, "script=%s", be->hotplug_script))
+ return -ENOMEM;
+
+ if (!be->vif)
return 0;
return add_uevent_var(env, "vif=%s", be->vif->dev->name);
goto err;
}
+ queue->credit_bytes = credit_bytes;
queue->remaining_credit = credit_bytes;
queue->credit_usec = credit_usec;
if (netif_running(info->netdev))
napi_disable(&queue->napi);
+ del_timer_sync(&queue->rx_refill_timer);
netif_napi_del(&queue->napi);
}
static int xennet_remove(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
- unsigned int num_queues = info->netdev->real_num_tx_queues;
- struct netfront_queue *queue = NULL;
- unsigned int i = 0;
dev_dbg(&dev->dev, "%s\n", dev->nodename);
unregister_netdev(info->netdev);
- for (i = 0; i < num_queues; ++i) {
- queue = &info->queues[i];
- del_timer_sync(&queue->rx_refill_timer);
- }
-
- if (num_queues) {
- kfree(info->queues);
- info->queues = NULL;
- }
-
+ xennet_destroy_queues(info);
xennet_free_netdev(info->netdev);
return 0;
u32 ppd;
ndev->hw_type = BWD_HW;
+ ndev->limits.max_mw = BWD_MAX_MW;
rc = pci_read_config_dword(ndev->pdev, NTB_PPD_OFFSET, &ppd);
if (rc)
dev_warn(&pdev->dev, "Cannot remap BAR %d\n",
MW_TO_BAR(i));
rc = -EIO;
- goto err3;
+ goto err4;
}
}
return 0;
}
-static int __init of_init(void)
+void __init of_core_init(void)
{
struct device_node *np;
of_kset = kset_create_and_add("devicetree", NULL, firmware_kobj);
if (!of_kset) {
mutex_unlock(&of_mutex);
- return -ENOMEM;
+ pr_err("devicetree: failed to register existing nodes\n");
+ return;
}
for_each_of_allnodes(np)
__of_attach_node_sysfs(np);
/* Symlink in /proc as required by userspace ABI */
if (of_root)
proc_symlink("device-tree", NULL, "/sys/firmware/devicetree/base");
-
- return 0;
}
-core_initcall(of_init);
static struct property *__of_find_property(const struct device_node *np,
const char *name, int *lenp)
phandle = __of_get_property(np, "phandle", &sz);
if (!phandle)
phandle = __of_get_property(np, "linux,phandle", &sz);
- if (IS_ENABLED(PPC_PSERIES) && !phandle)
+ if (IS_ENABLED(CONFIG_PPC_PSERIES) && !phandle)
phandle = __of_get_property(np, "ibm,phandle", &sz);
np->phandle = (phandle && (sz >= 4)) ? be32_to_cpup(phandle) : 0;
BUG();
return -1;
}
- printk("superio_fixup_irq(%s) ven 0x%x dev 0x%x from %pf\n",
+ printk(KERN_DEBUG "superio_fixup_irq(%s) ven 0x%x dev 0x%x from %ps\n",
pci_name(pcidev),
pcidev->vendor, pcidev->device,
__builtin_return_address(0));
*/
static DEFINE_SPINLOCK(ht_irq_lock);
-struct ht_irq_cfg {
- struct pci_dev *dev;
- /* Update callback used to cope with buggy hardware */
- ht_irq_update_t *update;
- unsigned pos;
- unsigned idx;
- struct ht_irq_msg msg;
-};
-
-
void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
{
struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
unsigned long flags;
+
spin_lock_irqsave(&ht_irq_lock, flags);
if (cfg->msg.address_lo != msg->address_lo) {
pci_write_config_byte(cfg->dev, cfg->pos + 2, cfg->idx);
void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
{
struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
+
*msg = cfg->msg;
}
*/
int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
{
- struct ht_irq_cfg *cfg;
int max_irq, pos, irq;
unsigned long flags;
u32 data;
if (idx > max_irq)
return -EINVAL;
- cfg = kmalloc(sizeof(*cfg), GFP_KERNEL);
- if (!cfg)
- return -ENOMEM;
-
- cfg->dev = dev;
- cfg->update = update;
- cfg->pos = pos;
- cfg->idx = 0x10 + (idx * 2);
- /* Initialize msg to a value that will never match the first write. */
- cfg->msg.address_lo = 0xffffffff;
- cfg->msg.address_hi = 0xffffffff;
-
- irq = irq_alloc_hwirq(dev_to_node(&dev->dev));
- if (!irq) {
- kfree(cfg);
- return -EBUSY;
- }
- irq_set_handler_data(irq, cfg);
-
- if (arch_setup_ht_irq(irq, dev) < 0) {
- ht_destroy_irq(irq);
- return -EBUSY;
- }
+ irq = arch_setup_ht_irq(idx, pos, dev, update);
+ if (irq > 0)
+ dev_dbg(&dev->dev, "irq %d for HT\n", irq);
return irq;
}
*/
void ht_destroy_irq(unsigned int irq)
{
- struct ht_irq_cfg *cfg;
-
- cfg = irq_get_handler_data(irq);
- irq_set_chip(irq, NULL);
- irq_set_handler_data(irq, NULL);
- irq_free_hwirq(irq);
-
- kfree(cfg);
+ arch_teardown_ht_irq(irq);
}
EXPORT_SYMBOL(ht_destroy_irq);
}
}
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_VIPER_7410, quirk_amd_ioapic);
-
-static void quirk_ioapic_rmw(struct pci_dev *dev)
-{
- if (dev->devfn == 0 && dev->bus->number == 0)
- sis_apic_bug = 1;
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI, PCI_ANY_ID, quirk_ioapic_rmw);
#endif /* CONFIG_X86_IO_APIC */
/*
* consistent.
*/
if (add_align > dev_res->res->start) {
+ resource_size_t r_size = resource_size(dev_res->res);
+
dev_res->res->start = add_align;
- dev_res->res->end = add_align +
- resource_size(dev_res->res);
+ dev_res->res->end = add_align + r_size - 1;
list_for_each_entry(dev_res2, head, list) {
align = pci_resource_alignment(dev_res2->dev,
dev_res2->res);
- if (add_align > align)
+ if (add_align > align) {
list_move_tail(&dev_res->list,
&dev_res2->list);
+ break;
+ }
}
}
config PHY_DM816X_USB
tristate "TI dm816x USB PHY driver"
depends on ARCH_OMAP2PLUS
+ depends on USB_SUPPORT
select GENERIC_PHY
+ select USB_PHY
help
Enable this for dm816x USB to work.
config OMAP_USB2
tristate "OMAP USB2 PHY Driver"
depends on ARCH_OMAP2PLUS
- depends on USB_PHY
+ depends on USB_SUPPORT
select GENERIC_PHY
+ select USB_PHY
select OMAP_CONTROL_PHY
depends on OMAP_OCP2SCP
help
config TWL4030_USB
tristate "TWL4030 USB Transceiver Driver"
depends on TWL4030_CORE && REGULATOR_TWL4030 && USB_MUSB_OMAP2PLUS
- depends on USB_PHY
+ depends on USB_SUPPORT
select GENERIC_PHY
+ select USB_PHY
help
Enable this to support the USB OTG transceiver on TWL4030
family chips (including the TWL5030 and TPS659x0 devices).
config PHY_QCOM_UFS
tristate "Qualcomm UFS PHY driver"
- depends on OF && ARCH_MSM
+ depends on OF && ARCH_QCOM
select GENERIC_PHY
help
Support for UFS PHY on QCOM chipsets.
{
struct phy *phy = phy_get(dev, string);
- if (PTR_ERR(phy) == -ENODEV)
+ if (IS_ERR(phy) && (PTR_ERR(phy) == -ENODEV))
phy = NULL;
return phy;
{
struct phy *phy = devm_phy_get(dev, string);
- if (PTR_ERR(phy) == -ENODEV)
+ if (IS_ERR(phy) && (PTR_ERR(phy) == -ENODEV))
phy = NULL;
return phy;
phy->wkupclk = devm_clk_get(phy->dev, "usb_phy_cm_clk32k");
if (IS_ERR(phy->wkupclk)) {
dev_err(&pdev->dev, "unable to get usb_phy_cm_clk32k\n");
+ pm_runtime_disable(phy->dev);
return PTR_ERR(phy->wkupclk);
} else {
dev_warn(&pdev->dev,
#define USBHS_LPSTS 0x02
#define USBHS_UGCTRL 0x80
#define USBHS_UGCTRL2 0x84
-#define USBHS_UGSTS 0x88 /* The manuals have 0x90 */
+#define USBHS_UGSTS 0x88 /* From technical update */
/* Low Power Status register (LPSTS) */
#define USBHS_LPSTS_SUSPM 0x4000
#define USBHS_UGCTRL2_USB0SEL_HS_USB 0x00000030
/* USB General status register (UGSTS) */
-#define USBHS_UGSTS_LOCK 0x00000300 /* The manuals have 0x3 */
+#define USBHS_UGSTS_LOCK 0x00000100 /* From technical update */
#define PHYS_PER_CHANNEL 2
CYGNUS_PINRANGE(87, 104, 12),
CYGNUS_PINRANGE(99, 102, 2),
CYGNUS_PINRANGE(101, 90, 4),
- CYGNUS_PINRANGE(105, 116, 10),
+ CYGNUS_PINRANGE(105, 116, 6),
+ CYGNUS_PINRANGE(111, 100, 2),
+ CYGNUS_PINRANGE(113, 122, 4),
CYGNUS_PINRANGE(123, 11, 1),
CYGNUS_PINRANGE(124, 38, 4),
CYGNUS_PINRANGE(128, 43, 1),
EXPORT_SYMBOL_GPL(devm_pinctrl_put);
int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps,
- bool dup, bool locked)
+ bool dup)
{
int i, ret;
struct pinctrl_maps *maps_node;
maps_node->maps = maps;
}
- if (!locked)
- mutex_lock(&pinctrl_maps_mutex);
+ mutex_lock(&pinctrl_maps_mutex);
list_add_tail(&maps_node->node, &pinctrl_maps);
- if (!locked)
- mutex_unlock(&pinctrl_maps_mutex);
+ mutex_unlock(&pinctrl_maps_mutex);
return 0;
}
int pinctrl_register_mappings(struct pinctrl_map const *maps,
unsigned num_maps)
{
- return pinctrl_register_map(maps, num_maps, true, false);
+ return pinctrl_register_map(maps, num_maps, true);
}
void pinctrl_unregister_map(struct pinctrl_map const *map)
}
int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps,
- bool dup, bool locked);
+ bool dup);
void pinctrl_unregister_map(struct pinctrl_map const *map);
extern int pinctrl_force_sleep(struct pinctrl_dev *pctldev);
dt_map->num_maps = num_maps;
list_add_tail(&dt_map->node, &p->dt_maps);
- return pinctrl_register_map(map, num_maps, false, true);
+ return pinctrl_register_map(map, num_maps, false);
}
struct pinctrl_dev *of_pinctrl_get(struct device_node *np)
chv_gpio_irq_mask_unmask(d, false);
}
+static unsigned chv_gpio_irq_startup(struct irq_data *d)
+{
+ /*
+ * Check if the interrupt has been requested with 0 as triggering
+ * type. In that case it is assumed that the current values
+ * programmed to the hardware are used (e.g BIOS configured
+ * defaults).
+ *
+ * In that case ->irq_set_type() will never be called so we need to
+ * read back the values from hardware now, set correct flow handler
+ * and update mappings before the interrupt is being used.
+ */
+ if (irqd_get_trigger_type(d) == IRQ_TYPE_NONE) {
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct chv_pinctrl *pctrl = gpiochip_to_pinctrl(gc);
+ unsigned offset = irqd_to_hwirq(d);
+ int pin = chv_gpio_offset_to_pin(pctrl, offset);
+ irq_flow_handler_t handler;
+ unsigned long flags;
+ u32 intsel, value;
+
+ intsel = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0));
+ intsel &= CHV_PADCTRL0_INTSEL_MASK;
+ intsel >>= CHV_PADCTRL0_INTSEL_SHIFT;
+
+ value = readl(chv_padreg(pctrl, pin, CHV_PADCTRL1));
+ if (value & CHV_PADCTRL1_INTWAKECFG_LEVEL)
+ handler = handle_level_irq;
+ else
+ handler = handle_edge_irq;
+
+ spin_lock_irqsave(&pctrl->lock, flags);
+ if (!pctrl->intr_lines[intsel]) {
+ __irq_set_handler_locked(d->irq, handler);
+ pctrl->intr_lines[intsel] = offset;
+ }
+ spin_unlock_irqrestore(&pctrl->lock, flags);
+ }
+
+ chv_gpio_irq_unmask(d);
+ return 0;
+}
+
static int chv_gpio_irq_type(struct irq_data *d, unsigned type)
{
struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
static struct irq_chip chv_gpio_irqchip = {
.name = "chv-gpio",
+ .irq_startup = chv_gpio_irq_startup,
.irq_ack = chv_gpio_irq_ack,
.irq_mask = chv_gpio_irq_mask,
.irq_unmask = chv_gpio_irq_unmask,
if (!mtk_eint_get_mask(pctl, eint_num)) {
mtk_eint_mask(d);
unmask = 1;
+ } else {
+ unmask = 0;
}
clr_bit = 0xff << eint_offset;
domain->chip.direction_output = meson_gpio_direction_output;
domain->chip.get = meson_gpio_get;
domain->chip.set = meson_gpio_set;
- domain->chip.base = -1;
+ domain->chip.base = domain->data->pin_base;
domain->chip.ngpio = domain->data->num_pins;
domain->chip.can_sleep = false;
domain->chip.of_node = domain->of_node;
.banks = meson8b_banks,
.num_banks = ARRAY_SIZE(meson8b_banks),
.pin_base = 0,
- .num_pins = 83,
+ .num_pins = 130,
},
{
.name = "ao-bank",
.banks = meson8b_ao_banks,
.num_banks = ARRAY_SIZE(meson8b_ao_banks),
- .pin_base = 83,
+ .pin_base = 130,
.num_pins = 16,
},
};
MPP_FUNCTION(0x5, "audio", "mclk"),
MPP_FUNCTION(0x6, "uart0", "cts")),
MPP_MODE(63,
- MPP_FUNCTION(0x0, "gpo", NULL),
+ MPP_FUNCTION(0x0, "gpio", NULL),
MPP_FUNCTION(0x1, "spi0", "sck"),
MPP_FUNCTION(0x2, "tclk", NULL)),
MPP_MODE(64,
val = 1;
}
+ val = val << PMIC_GPIO_REG_MODE_DIR_SHIFT;
val |= pad->function << PMIC_GPIO_REG_MODE_FUNCTION_SHIFT;
val |= pad->out_value & PMIC_GPIO_REG_MODE_VALUE_SHIFT;
return ret;
val = pad->buffer_type << PMIC_GPIO_REG_OUT_TYPE_SHIFT;
- val = pad->strength << PMIC_GPIO_REG_OUT_STRENGTH_SHIFT;
+ val |= pad->strength << PMIC_GPIO_REG_OUT_STRENGTH_SHIFT;
ret = pmic_gpio_write(state, pad, PMIC_GPIO_REG_DIG_OUT_CTL, val);
if (ret < 0)
seq_puts(s, " ---");
} else {
- if (!pad->input_enabled) {
+ if (pad->input_enabled) {
ret = pmic_gpio_read(state, pad, PMIC_MPP_REG_RT_STS);
- if (!ret) {
- ret &= PMIC_MPP_REG_RT_STS_VAL_MASK;
- pad->out_value = ret;
- }
+ if (ret < 0)
+ return;
+
+ ret &= PMIC_MPP_REG_RT_STS_VAL_MASK;
+ pad->out_value = ret;
}
seq_printf(s, " %-4s", pad->output_enabled ? "out" : "in");
}
}
+ val = val << PMIC_MPP_REG_MODE_DIR_SHIFT;
val |= pad->function << PMIC_MPP_REG_MODE_FUNCTION_SHIFT;
val |= pad->out_value & PMIC_MPP_REG_MODE_VALUE_MASK;
if (pad->input_enabled) {
ret = pmic_mpp_read(state, pad, PMIC_MPP_REG_RT_STS);
- if (!ret) {
- ret &= PMIC_MPP_REG_RT_STS_VAL_MASK;
- pad->out_value = ret;
- }
+ if (ret < 0)
+ return;
+
+ ret &= PMIC_MPP_REG_RT_STS_VAL_MASK;
+ pad->out_value = ret;
}
seq_printf(s, " %-4s", pad->output_enabled ? "out" : "in");
return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_wakeup_reason);
}
-static DEVICE_ATTR_RO(hotkey_wakeup_reason);
+static DEVICE_ATTR(wakeup_reason, S_IRUGO, hotkey_wakeup_reason_show, NULL);
static void hotkey_wakeup_reason_notify_change(void)
{
return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_autosleep_ack);
}
-static DEVICE_ATTR_RO(hotkey_wakeup_hotunplug_complete);
+static DEVICE_ATTR(wakeup_hotunplug_complete, S_IRUGO,
+ hotkey_wakeup_hotunplug_complete_show, NULL);
static void hotkey_wakeup_hotunplug_complete_notify_change(void)
{
&dev_attr_hotkey_enable.attr,
&dev_attr_hotkey_bios_enabled.attr,
&dev_attr_hotkey_bios_mask.attr,
- &dev_attr_hotkey_wakeup_reason.attr,
- &dev_attr_hotkey_wakeup_hotunplug_complete.attr,
+ &dev_attr_wakeup_reason.attr,
+ &dev_attr_wakeup_hotunplug_complete.attr,
&dev_attr_hotkey_mask.attr,
&dev_attr_hotkey_all_mask.attr,
&dev_attr_hotkey_recommended_mask.attr,
attr, buf, count);
}
-static DEVICE_ATTR_RW(wan_enable);
+static DEVICE_ATTR(wwan_enable, S_IWUSR | S_IRUGO,
+ wan_enable_show, wan_enable_store);
/* --------------------------------------------------------------------- */
static struct attribute *wan_attributes[] = {
- &dev_attr_wan_enable.attr,
+ &dev_attr_wwan_enable.attr,
NULL
};
return count;
}
-static DEVICE_ATTR_RW(fan_pwm1_enable);
+static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO,
+ fan_pwm1_enable_show, fan_pwm1_enable_store);
/* sysfs fan pwm1 ------------------------------------------------------ */
static ssize_t fan_pwm1_show(struct device *dev,
return (rc) ? rc : count;
}
-static DEVICE_ATTR_RW(fan_pwm1);
+static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, fan_pwm1_show, fan_pwm1_store);
/* sysfs fan fan1_input ------------------------------------------------ */
static ssize_t fan_fan1_input_show(struct device *dev,
return snprintf(buf, PAGE_SIZE, "%u\n", speed);
}
-static DEVICE_ATTR_RO(fan_fan1_input);
+static DEVICE_ATTR(fan1_input, S_IRUGO, fan_fan1_input_show, NULL);
/* sysfs fan fan2_input ------------------------------------------------ */
static ssize_t fan_fan2_input_show(struct device *dev,
return snprintf(buf, PAGE_SIZE, "%u\n", speed);
}
-static DEVICE_ATTR_RO(fan_fan2_input);
+static DEVICE_ATTR(fan2_input, S_IRUGO, fan_fan2_input_show, NULL);
/* sysfs fan fan_watchdog (hwmon driver) ------------------------------- */
static ssize_t fan_fan_watchdog_show(struct device_driver *drv,
/* --------------------------------------------------------------------- */
static struct attribute *fan_attributes[] = {
- &dev_attr_fan_pwm1_enable.attr, &dev_attr_fan_pwm1.attr,
- &dev_attr_fan_fan1_input.attr,
+ &dev_attr_pwm1_enable.attr, &dev_attr_pwm1.attr,
+ &dev_attr_fan1_input.attr,
NULL, /* for fan2_input */
NULL
};
if (tp_features.second_fan) {
/* attach second fan tachometer */
fan_attributes[ARRAY_SIZE(fan_attributes)-2] =
- &dev_attr_fan_fan2_input.attr;
+ &dev_attr_fan2_input.attr;
}
rc = sysfs_create_group(&tpacpi_sensors_pdev->dev.kobj,
&fan_attr_group);
return snprintf(buf, PAGE_SIZE, "%s\n", TPACPI_NAME);
}
-static DEVICE_ATTR_RO(thinkpad_acpi_pdev_name);
+static DEVICE_ATTR(name, S_IRUGO, thinkpad_acpi_pdev_name_show, NULL);
/* --------------------------------------------------------------------- */
hwmon_device_unregister(tpacpi_hwmon);
if (tp_features.sensors_pdev_attrs_registered)
- device_remove_file(&tpacpi_sensors_pdev->dev,
- &dev_attr_thinkpad_acpi_pdev_name);
+ device_remove_file(&tpacpi_sensors_pdev->dev, &dev_attr_name);
if (tpacpi_sensors_pdev)
platform_device_unregister(tpacpi_sensors_pdev);
if (tpacpi_pdev)
thinkpad_acpi_module_exit();
return ret;
}
- ret = device_create_file(&tpacpi_sensors_pdev->dev,
- &dev_attr_thinkpad_acpi_pdev_name);
+ ret = device_create_file(&tpacpi_sensors_pdev->dev, &dev_attr_name);
if (ret) {
pr_err("unable to create sysfs hwmon device attributes\n");
thinkpad_acpi_module_exit();
module_platform_driver(axp288_fuel_gauge_driver);
+MODULE_AUTHOR("Ramakrishna Pallala <ramakrishna.pallala@intel.com>");
MODULE_AUTHOR("Todd Brandt <todd.e.brandt@linux.intel.com>");
MODULE_DESCRIPTION("Xpower AXP288 Fuel Gauge Driver");
MODULE_LICENSE("GPL");
}
module_exit(bq27x00_battery_exit);
+#ifdef CONFIG_BATTERY_BQ27X00_PLATFORM
+MODULE_ALIAS("platform:bq27000-battery");
+#endif
+
+#ifdef CONFIG_BATTERY_BQ27X00_I2C
+MODULE_ALIAS("i2c:bq27000-battery");
+#endif
+
MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
MODULE_DESCRIPTION("BQ27x00 battery monitor driver");
MODULE_LICENSE("GPL");
goto err_psy_reg_main;
}
- psy_main_cfg.drv_data = &collie_bat_bu;
+ psy_bu_cfg.drv_data = &collie_bat_bu;
collie_bat_bu.psy = power_supply_register(&dev->ucb->dev,
&collie_bat_bu_desc,
&psy_bu_cfg);
config POWER_RESET_BRCMSTB
bool "Broadcom STB reset driver"
depends on ARM || MIPS || COMPILE_TEST
+ depends on MFD_SYSCON
default ARCH_BRCMSTB
help
This driver provides restart support for Broadcom STB boards.
res = platform_get_resource(pdev, IORESOURCE_MEM, idx + 1 );
at91_ramc_base[idx] = devm_ioremap(&pdev->dev, res->start,
resource_size(res));
- if (IS_ERR(at91_ramc_base[idx])) {
+ if (!at91_ramc_base[idx]) {
dev_err(&pdev->dev, "Could not map ram controller address\n");
- return PTR_ERR(at91_ramc_base[idx]);
+ return -ENOMEM;
}
}
static void ltc2952_poweroff_start_wde(struct ltc2952_poweroff *data)
{
- if (hrtimer_start(&data->timer_wde, data->wde_interval,
- HRTIMER_MODE_REL)) {
- /*
- * The device will not toggle the watchdog reset,
- * thus shut down is only safe if the PowerPath controller
- * has a long enough time-off before triggering a hardware
- * power-off.
- *
- * Only sending a warning as the system will power-off anyway
- */
- dev_err(data->dev, "unable to start the timer\n");
- }
+ hrtimer_start(&data->timer_wde, data->wde_interval, HRTIMER_MODE_REL);
}
static enum hrtimer_restart
}
if (gpiod_get_value(data->gpio_trigger)) {
- if (hrtimer_start(&data->timer_trigger, data->trigger_delay,
- HRTIMER_MODE_REL))
- dev_err(data->dev, "unable to start the wait timer\n");
+ hrtimer_start(&data->timer_trigger, data->trigger_delay,
+ HRTIMER_MODE_REL);
} else {
hrtimer_cancel(&data->timer_trigger);
- /* omitting return value check, timer should have been valid */
}
return IRQ_HANDLED;
}
#include <linux/mfd/syscon.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/pwm.h>
#include <linux/regmap.h>
#define PERIP_PWM_PDM_CONTROL_CH_MASK 0x1
#define PERIP_PWM_PDM_CONTROL_CH_SHIFT(ch) ((ch) * 4)
-#define MAX_TMBASE_STEPS 65536
+/*
+ * PWM period is specified with a timebase register,
+ * in number of step periods. The PWM duty cycle is also
+ * specified in step periods, in the [0, $timebase] range.
+ * In other words, the timebase imposes the duty cycle
+ * resolution. Therefore, let's constraint the timebase to
+ * a minimum value to allow a sane range of duty cycle values.
+ * Imposing a minimum timebase, will impose a maximum PWM frequency.
+ *
+ * The value chosen is completely arbitrary.
+ */
+#define MIN_TMBASE_STEPS 16
+
+struct img_pwm_soc_data {
+ u32 max_timebase;
+};
struct img_pwm_chip {
struct device *dev;
struct clk *sys_clk;
void __iomem *base;
struct regmap *periph_regs;
+ int max_period_ns;
+ int min_period_ns;
+ const struct img_pwm_soc_data *data;
};
static inline struct img_pwm_chip *to_img_pwm_chip(struct pwm_chip *chip)
u32 val, div, duty, timebase;
unsigned long mul, output_clk_hz, input_clk_hz;
struct img_pwm_chip *pwm_chip = to_img_pwm_chip(chip);
+ unsigned int max_timebase = pwm_chip->data->max_timebase;
+
+ if (period_ns < pwm_chip->min_period_ns ||
+ period_ns > pwm_chip->max_period_ns) {
+ dev_err(chip->dev, "configured period not in range\n");
+ return -ERANGE;
+ }
input_clk_hz = clk_get_rate(pwm_chip->pwm_clk);
output_clk_hz = DIV_ROUND_UP(NSEC_PER_SEC, period_ns);
mul = DIV_ROUND_UP(input_clk_hz, output_clk_hz);
- if (mul <= MAX_TMBASE_STEPS) {
+ if (mul <= max_timebase) {
div = PWM_CTRL_CFG_NO_SUB_DIV;
timebase = DIV_ROUND_UP(mul, 1);
- } else if (mul <= MAX_TMBASE_STEPS * 8) {
+ } else if (mul <= max_timebase * 8) {
div = PWM_CTRL_CFG_SUB_DIV0;
timebase = DIV_ROUND_UP(mul, 8);
- } else if (mul <= MAX_TMBASE_STEPS * 64) {
+ } else if (mul <= max_timebase * 64) {
div = PWM_CTRL_CFG_SUB_DIV1;
timebase = DIV_ROUND_UP(mul, 64);
- } else if (mul <= MAX_TMBASE_STEPS * 512) {
+ } else if (mul <= max_timebase * 512) {
div = PWM_CTRL_CFG_SUB_DIV0_DIV1;
timebase = DIV_ROUND_UP(mul, 512);
- } else if (mul > MAX_TMBASE_STEPS * 512) {
+ } else if (mul > max_timebase * 512) {
dev_err(chip->dev,
"failed to configure timebase steps/divider value\n");
return -EINVAL;
.owner = THIS_MODULE,
};
+static const struct img_pwm_soc_data pistachio_pwm = {
+ .max_timebase = 255,
+};
+
+static const struct of_device_id img_pwm_of_match[] = {
+ {
+ .compatible = "img,pistachio-pwm",
+ .data = &pistachio_pwm,
+ },
+ { }
+};
+MODULE_DEVICE_TABLE(of, img_pwm_of_match);
+
static int img_pwm_probe(struct platform_device *pdev)
{
int ret;
+ u64 val;
+ unsigned long clk_rate;
struct resource *res;
struct img_pwm_chip *pwm;
+ const struct of_device_id *of_dev_id;
pwm = devm_kzalloc(&pdev->dev, sizeof(*pwm), GFP_KERNEL);
if (!pwm)
if (IS_ERR(pwm->base))
return PTR_ERR(pwm->base);
+ of_dev_id = of_match_device(img_pwm_of_match, &pdev->dev);
+ if (!of_dev_id)
+ return -ENODEV;
+ pwm->data = of_dev_id->data;
+
pwm->periph_regs = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
"img,cr-periph");
if (IS_ERR(pwm->periph_regs))
goto disable_sysclk;
}
+ clk_rate = clk_get_rate(pwm->pwm_clk);
+
+ /* The maximum input clock divider is 512 */
+ val = (u64)NSEC_PER_SEC * 512 * pwm->data->max_timebase;
+ do_div(val, clk_rate);
+ pwm->max_period_ns = val;
+
+ val = (u64)NSEC_PER_SEC * MIN_TMBASE_STEPS;
+ do_div(val, clk_rate);
+ pwm->min_period_ns = val;
+
pwm->chip.dev = &pdev->dev;
pwm->chip.ops = &img_pwm_ops;
pwm->chip.base = -1;
return pwmchip_remove(&pwm_chip->chip);
}
-static const struct of_device_id img_pwm_of_match[] = {
- { .compatible = "img,pistachio-pwm", },
- { }
-};
-MODULE_DEVICE_TABLE(of, img_pwm_of_match);
-
static struct platform_driver img_pwm_driver = {
.driver = {
.name = "img-pwm",
static int da9052_regulator_probe(struct platform_device *pdev)
{
+ const struct mfd_cell *cell = mfd_get_cell(pdev);
struct regulator_config config = { };
struct da9052_regulator *regulator;
struct da9052 *da9052;
regulator->da9052 = da9052;
regulator->info = find_regulator_info(regulator->da9052->chip_id,
- pdev->id);
+ cell->id);
if (regulator->info == NULL) {
dev_err(&pdev->dev, "invalid regulator ID specified\n");
return -EINVAL;
config.driver_data = regulator;
config.regmap = da9052->regmap;
if (pdata && pdata->regulators) {
- config.init_data = pdata->regulators[pdev->id];
+ config.init_data = pdata->regulators[cell->id];
} else {
#ifdef CONFIG_OF
struct device_node *nproot = da9052->dev->of_node;
static int armada38x_rtc_read_time(struct device *dev, struct rtc_time *tm)
{
struct armada38x_rtc *rtc = dev_get_drvdata(dev);
- unsigned long time, time_check, flags;
+ unsigned long time, time_check;
mutex_lock(&rtc->mutex_time);
time = readl(rtc->regs + RTC_TIME);
poll_timeout = time;
hr_time = ktime_set(0, poll_timeout);
- if (!hrtimer_is_queued(&ap_poll_timer) ||
- !hrtimer_forward(&ap_poll_timer, hrtimer_get_expires(&ap_poll_timer), hr_time)) {
- hrtimer_set_expires(&ap_poll_timer, hr_time);
- hrtimer_start_expires(&ap_poll_timer, HRTIMER_MODE_ABS);
- }
+ spin_lock_bh(&ap_poll_timer_lock);
+ hrtimer_cancel(&ap_poll_timer);
+ hrtimer_set_expires(&ap_poll_timer, hr_time);
+ hrtimer_start_expires(&ap_poll_timer, HRTIMER_MODE_ABS);
+ spin_unlock_bh(&ap_poll_timer_lock);
+
return count;
}
ktime_t hr_time;
spin_lock_bh(&ap_poll_timer_lock);
- if (hrtimer_is_queued(&ap_poll_timer) || ap_suspend_flag)
- goto out;
- if (ktime_to_ns(hrtimer_expires_remaining(&ap_poll_timer)) <= 0) {
+ if (!hrtimer_is_queued(&ap_poll_timer) && !ap_suspend_flag) {
hr_time = ktime_set(0, poll_timeout);
hrtimer_forward_now(&ap_poll_timer, hr_time);
hrtimer_restart(&ap_poll_timer);
}
-out:
spin_unlock_bh(&ap_poll_timer_lock);
}
{
int i;
- if (ap_domain_index != -1)
+ if ((ap_domain_index != -1) && (ap_test_config_domain(ap_domain_index)))
for (i = 0; i < AP_DEVICES; i++)
ap_reset_queue(AP_MKQID(i, ap_domain_index));
}
hrtimer_cancel(&ap_poll_timer);
destroy_workqueue(ap_work_queue);
tasklet_kill(&ap_tasklet);
- root_device_unregister(ap_root_device);
while ((dev = bus_find_device(&ap_bus_type, NULL, NULL,
__ap_match_all)))
{
}
for (i = 0; ap_bus_attrs[i]; i++)
bus_remove_file(&ap_bus_type, ap_bus_attrs[i]);
+ root_device_unregister(ap_root_device);
bus_unregister(&ap_bus_type);
unregister_reset_call(&ap_reset_call);
if (ap_using_interrupts())
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* Public License is included in this distribution in the file called COPYING.
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* Public License is included in this distribution in the file called COPYING.
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* Public License is included in this distribution in the file called COPYING.
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* as published by the Free Software Foundation. The full GNU General
* Public License is included in this distribution in the file called COPYING.
*
- * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com)
+ * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com)
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* as published by the Free Software Foundation. The full GNU General
* Public License is included in this distribution in the file called COPYING.
*
- * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com)
+ * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com)
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* as published by the Free Software Foundation. The full GNU General
* Public License is included in this distribution in the file called COPYING.
*
- * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com)
+ * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com)
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
MODULE_DESCRIPTION(DRV_DESC " " BUILD_STR);
MODULE_VERSION(BUILD_STR);
-MODULE_AUTHOR("Emulex Corporation");
+MODULE_AUTHOR("Avago Technologies");
MODULE_LICENSE("GPL");
module_param(be_iopoll_budget, int, 0);
module_param(enable_msix, int, 0);
static struct scsi_host_template beiscsi_sht = {
.module = THIS_MODULE,
- .name = "Emulex 10Gbe open-iscsi Initiator Driver",
+ .name = "Avago Technologies 10Gbe open-iscsi Initiator Driver",
.proc_name = DRV_NAME,
.queuecommand = iscsi_queuecommand,
.change_queue_depth = scsi_change_queue_depth,
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* as published by the Free Software Foundation. The full GNU General
* Public License is included in this distribution in the file called COPYING.
*
- * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com)
+ * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com)
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
#define DRV_NAME "be2iscsi"
#define BUILD_STR "10.4.114.0"
-#define BE_NAME "Emulex OneConnect" \
+#define BE_NAME "Avago Technologies OneConnect" \
"Open-iSCSI Driver version" BUILD_STR
#define DRV_DESC BE_NAME " " "Driver"
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* as published by the Free Software Foundation. The full GNU General
* Public License is included in this distribution in the file called COPYING.
*
- * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com)
+ * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com)
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
/**
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Avago Technologies
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
* as published by the Free Software Foundation. The full GNU General
* Public License is included in this distribution in the file called COPYING.
*
- * Written by: Jayamohan Kallickal (jayamohan.kallickal@emulex.com)
+ * Written by: Jayamohan Kallickal (jayamohan.kallickal@avagotech.com)
*
* Contact Information:
- * linux-drivers@emulex.com
+ * linux-drivers@avagotech.com
*
- * Emulex
+ * Avago Technologies
* 3333 Susan Street
* Costa Mesa, CA 92626
*/
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/debugfs.h>
+#include <linux/vmalloc.h>
#include "fnic.h"
static struct dentry *fnic_trace_debugfs_root;
#include <linux/spinlock.h>
#include <linux/kallsyms.h>
#include <linux/time.h>
+#include <linux/vmalloc.h>
#include "fnic_io.h"
#include "fnic.h"
phba->lpfc_release_scsi_buf(phba, psb);
}
-/**
- * lpfc_fcpcmd_to_iocb - copy the fcp_cmd data into the IOCB
- * @data: A pointer to the immediate command data portion of the IOCB.
- * @fcp_cmnd: The FCP Command that is provided by the SCSI layer.
- *
- * The routine copies the entire FCP command from @fcp_cmnd to @data while
- * byte swapping the data to big endian format for transmission on the wire.
- **/
-static void
-lpfc_fcpcmd_to_iocb(uint8_t *data, struct fcp_cmnd *fcp_cmnd)
-{
- int i, j;
-
- for (i = 0, j = 0; i < sizeof(struct fcp_cmnd);
- i += sizeof(uint32_t), j++) {
- ((uint32_t *)data)[j] = cpu_to_be32(((uint32_t *)fcp_cmnd)[j]);
- }
-}
-
/**
* lpfc_scsi_prep_dma_buf_s3 - DMA mapping for scsi buffer to SLI3 IF spec
* @phba: The Hba for which this call is being executed.
* we need to set word 4 of IOCB here
*/
iocb_cmd->un.fcpi.fcpi_parm = scsi_bufflen(scsi_cmnd);
- lpfc_fcpcmd_to_iocb(iocb_cmd->unsli3.fcp_ext.icd, fcp_cmnd);
return 0;
}
lpfc_release_scsi_buf(phba, lpfc_cmd);
}
+/**
+ * lpfc_fcpcmd_to_iocb - copy the fcp_cmd data into the IOCB
+ * @data: A pointer to the immediate command data portion of the IOCB.
+ * @fcp_cmnd: The FCP Command that is provided by the SCSI layer.
+ *
+ * The routine copies the entire FCP command from @fcp_cmnd to @data while
+ * byte swapping the data to big endian format for transmission on the wire.
+ **/
+static void
+lpfc_fcpcmd_to_iocb(uint8_t *data, struct fcp_cmnd *fcp_cmnd)
+{
+ int i, j;
+ for (i = 0, j = 0; i < sizeof(struct fcp_cmnd);
+ i += sizeof(uint32_t), j++) {
+ ((uint32_t *)data)[j] = cpu_to_be32(((uint32_t *)fcp_cmnd)[j]);
+ }
+}
+
/**
* lpfc_scsi_prep_cmnd - Wrapper func for convert scsi cmnd to FCP info unit
* @vport: The virtual port for which this call is being executed.
fcp_cmnd->fcpCntl3 = 0;
phba->fc4ControlRequests++;
}
+ if (phba->sli_rev == 3 &&
+ !(phba->sli3_options & LPFC_SLI3_BG_ENABLED))
+ lpfc_fcpcmd_to_iocb(iocb_cmd->unsli3.fcp_ext.icd, fcp_cmnd);
/*
* Finish initializing those IOCB fields that are independent
* of the scsi_cmnd request_buffer
struct se_portal_group *se_tpg = &base_tpg->se_tpg;
struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
- if (!configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
- &se_tpg->tpg_group.cg_item)) {
+ if (!target_depend_item(&se_tpg->tpg_group.cg_item)) {
atomic_set(&base_tpg->lport_tpg_enabled, 1);
qlt_enable_vha(base_vha);
}
if (!qlt_stop_phase1(base_vha->vha_tgt.qla_tgt)) {
atomic_set(&base_tpg->lport_tpg_enabled, 0);
- configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
- &se_tpg->tpg_group.cg_item);
+ target_undepend_item(&se_tpg->tpg_group.cg_item);
}
complete(&base_tpg->tpg_base_comp);
}
{
u64 start_lba = blk_rq_pos(scmd->request);
u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512);
+ u64 factor = scmd->device->sector_size / 512;
u64 bad_lba;
int info_valid;
/*
if (scsi_bufflen(scmd) <= scmd->device->sector_size)
return 0;
- if (scmd->device->sector_size < 512) {
- /* only legitimate sector_size here is 256 */
- start_lba <<= 1;
- end_lba <<= 1;
- } else {
- /* be careful ... don't want any overflows */
- unsigned int factor = scmd->device->sector_size / 512;
- do_div(start_lba, factor);
- do_div(end_lba, factor);
- }
+ /* be careful ... don't want any overflows */
+ do_div(start_lba, factor);
+ do_div(end_lba, factor);
/* The bad lba was reported incorrectly, we have no idea where
* the error is.
if (sector_size != 512 &&
sector_size != 1024 &&
sector_size != 2048 &&
- sector_size != 4096 &&
- sector_size != 256) {
+ sector_size != 4096) {
sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n",
sector_size);
/*
sdkp->capacity <<= 2;
else if (sector_size == 1024)
sdkp->capacity <<= 1;
- else if (sector_size == 256)
- sdkp->capacity >>= 1;
blk_queue_physical_block_size(sdp->request_queue,
sdkp->physical_block_size);
break;
default:
vm_srb->data_in = UNKNOWN_TYPE;
- vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_DATA_IN |
- SRB_FLAGS_DATA_OUT);
+ vm_srb->win8_extension.srb_flags |= SRB_FLAGS_NO_DATA_TRANSFER;
break;
}
config MTK_PMIC_WRAP
tristate "MediaTek PMIC Wrapper Support"
depends on ARCH_MEDIATEK
+ depends on RESET_CONTROLLER
select REGMAP
help
Say yes here to add support for MediaTek PMIC Wrapper found
static int pwrap_write(struct pmic_wrapper *wrp, u32 adr, u32 wdata)
{
int ret;
- u32 val;
-
- val = pwrap_readl(wrp, PWRAP_WACS2_RDATA);
- if (PWRAP_GET_WACS_FSM(val) == PWRAP_WACS_FSM_WFVLDCLR)
- pwrap_writel(wrp, 1, PWRAP_WACS2_VLDCLR);
ret = pwrap_wait_for_state(wrp, pwrap_is_fsm_idle);
if (ret)
static int pwrap_read(struct pmic_wrapper *wrp, u32 adr, u32 *rdata)
{
int ret;
- u32 val;
-
- val = pwrap_readl(wrp, PWRAP_WACS2_RDATA);
- if (PWRAP_GET_WACS_FSM(val) == PWRAP_WACS_FSM_WFVLDCLR)
- pwrap_writel(wrp, 1, PWRAP_WACS2_VLDCLR);
ret = pwrap_wait_for_state(wrp, pwrap_is_fsm_idle);
if (ret)
*rdata = PWRAP_GET_WACS_RDATA(pwrap_readl(wrp, PWRAP_WACS2_RDATA));
+ pwrap_writel(wrp, 1, PWRAP_WACS2_VLDCLR);
+
return 0;
}
static int pwrap_init_reg_clock(struct pmic_wrapper *wrp)
{
- unsigned long rate_spi;
- int ck_mhz;
-
- rate_spi = clk_get_rate(wrp->clk_spi);
-
- if (rate_spi > 26000000)
- ck_mhz = 26;
- else if (rate_spi > 18000000)
- ck_mhz = 18;
- else
- ck_mhz = 0;
-
- switch (ck_mhz) {
- case 18:
- if (pwrap_is_mt8135(wrp))
- pwrap_writel(wrp, 0xc, PWRAP_CSHEXT);
- pwrap_writel(wrp, 0x4, PWRAP_CSHEXT_WRITE);
- pwrap_writel(wrp, 0xc, PWRAP_CSHEXT_READ);
- pwrap_writel(wrp, 0x0, PWRAP_CSLEXT_START);
- pwrap_writel(wrp, 0x0, PWRAP_CSLEXT_END);
- break;
- case 26:
- if (pwrap_is_mt8135(wrp))
- pwrap_writel(wrp, 0x4, PWRAP_CSHEXT);
+ if (pwrap_is_mt8135(wrp)) {
+ pwrap_writel(wrp, 0x4, PWRAP_CSHEXT);
pwrap_writel(wrp, 0x0, PWRAP_CSHEXT_WRITE);
pwrap_writel(wrp, 0x4, PWRAP_CSHEXT_READ);
pwrap_writel(wrp, 0x0, PWRAP_CSLEXT_START);
pwrap_writel(wrp, 0x0, PWRAP_CSLEXT_END);
- break;
- case 0:
- if (pwrap_is_mt8135(wrp))
- pwrap_writel(wrp, 0xf, PWRAP_CSHEXT);
- pwrap_writel(wrp, 0xf, PWRAP_CSHEXT_WRITE);
- pwrap_writel(wrp, 0xf, PWRAP_CSHEXT_READ);
- pwrap_writel(wrp, 0xf, PWRAP_CSLEXT_START);
- pwrap_writel(wrp, 0xf, PWRAP_CSLEXT_END);
- break;
- default:
- return -EINVAL;
+ } else {
+ pwrap_writel(wrp, 0x0, PWRAP_CSHEXT_WRITE);
+ pwrap_writel(wrp, 0x4, PWRAP_CSHEXT_READ);
+ pwrap_writel(wrp, 0x2, PWRAP_CSLEXT_START);
+ pwrap_writel(wrp, 0x2, PWRAP_CSLEXT_END);
}
return 0;
config SPI_BCM2835
tristate "BCM2835 SPI controller"
depends on ARCH_BCM2835 || COMPILE_TEST
+ depends on GPIOLIB
help
This selects a driver for the Broadcom BCM2835 SPI master.
config SPI_FSL_DSPI
tristate "Freescale DSPI controller"
select REGMAP_MMIO
- depends on SOC_VF610 || COMPILE_TEST
+ depends on SOC_VF610 || SOC_LS1021A || COMPILE_TEST
help
This enables support for the Freescale DSPI controller in master
mode. VF610 platform uses the controller.
unsigned long xfer_time_us)
{
struct bcm2835_spi *bs = spi_master_get_devdata(master);
- unsigned long timeout = jiffies +
- max(4 * xfer_time_us * HZ / 1000000, 2uL);
+ /* set timeout to 1 second of maximum polling */
+ unsigned long timeout = jiffies + HZ;
/* enable HW block without interrupts */
bcm2835_wr(bs, BCM2835_SPI_CS, cs | BCM2835_SPI_CS_TA);
- /* set timeout to 4x the expected time, or 2 jiffies */
/* loop until finished the transfer */
while (bs->rx_len) {
/* read from fifo as much as possible */
{
struct spi_bitbang_cs *cs = spi->controller_state;
struct spi_bitbang *bitbang;
- int retval;
unsigned long flags;
bitbang = spi_master_get_devdata(spi->master);
if (!cs->txrx_word)
return -EINVAL;
- retval = bitbang->setup_transfer(spi, NULL);
- if (retval < 0)
- return retval;
+ if (bitbang->setup_transfer) {
+ int retval = bitbang->setup_transfer(spi, NULL);
+ if (retval < 0)
+ return retval;
+ }
dev_dbg(&spi->dev, "%s, %u nsec/bit\n", __func__, 2 * cs->nsecs);
/* init (-1) or override (1) transfer params */
if (do_setup != 0) {
- status = bitbang->setup_transfer(spi, t);
- if (status < 0)
- break;
+ if (bitbang->setup_transfer) {
+ status = bitbang->setup_transfer(spi, t);
+ if (status < 0)
+ break;
+ }
if (do_setup == -1)
do_setup = 0;
}
#include <linux/of_address.h>
#include <linux/spi/spi.h>
#include <linux/types.h>
+#include <linux/platform_device.h>
#include "spi-fsl-cpm.h"
#include "spi-fsl-lib.h"
if (mspi->flags & SPI_CPM2) {
pram_ofs = cpm_muram_alloc(SPI_PRAM_SIZE, 64);
out_be16(spi_base, pram_ofs);
- } else {
- struct spi_pram __iomem *pram = spi_base;
- u16 rpbase = in_be16(&pram->rpbase);
-
- /* Microcode relocation patch applied? */
- if (rpbase) {
- pram_ofs = rpbase;
- } else {
- pram_ofs = cpm_muram_alloc(SPI_PRAM_SIZE, 64);
- out_be16(spi_base, pram_ofs);
- }
}
iounmap(spi_base);
struct device_node *np = dev->of_node;
const u32 *iprop;
int size;
- unsigned long pram_ofs;
unsigned long bds_ofs;
if (!(mspi->flags & SPI_CPM_MODE))
}
}
- pram_ofs = fsl_spi_cpm_get_pram(mspi);
- if (IS_ERR_VALUE(pram_ofs)) {
+ if (mspi->flags & SPI_CPM1) {
+ struct resource *res;
+ void *pram;
+
+ res = platform_get_resource(to_platform_device(dev),
+ IORESOURCE_MEM, 1);
+ pram = devm_ioremap_resource(dev, res);
+ if (IS_ERR(pram))
+ mspi->pram = NULL;
+ else
+ mspi->pram = pram;
+ } else {
+ unsigned long pram_ofs = fsl_spi_cpm_get_pram(mspi);
+
+ if (IS_ERR_VALUE(pram_ofs))
+ mspi->pram = NULL;
+ else
+ mspi->pram = cpm_muram_addr(pram_ofs);
+ }
+ if (mspi->pram == NULL) {
dev_err(dev, "can't allocate spi parameter ram\n");
goto err_pram;
}
goto err_dummy_rx;
}
- mspi->pram = cpm_muram_addr(pram_ofs);
-
mspi->tx_bd = cpm_muram_addr(bds_ofs);
mspi->rx_bd = cpm_muram_addr(bds_ofs + sizeof(*mspi->tx_bd));
err_dummy_tx:
cpm_muram_free(bds_ofs);
err_bds:
- cpm_muram_free(pram_ofs);
+ if (!(mspi->flags & SPI_CPM1))
+ cpm_muram_free(cpm_muram_offset(mspi->pram));
err_pram:
fsl_spi_free_dummy_rx();
return -ENOMEM;
struct fsl_espi_transfer *trans, u8 *rx_buff)
{
struct fsl_espi_transfer *espi_trans = trans;
- unsigned int n_tx = espi_trans->n_tx;
- unsigned int n_rx = espi_trans->n_rx;
+ unsigned int total_len = espi_trans->len;
struct spi_transfer *t;
u8 *local_buf;
u8 *rx_buf = rx_buff;
unsigned int trans_len;
unsigned int addr;
- int i, pos, loop;
+ unsigned int tx_only;
+ unsigned int rx_pos = 0;
+ unsigned int pos;
+ int i, loop;
local_buf = kzalloc(SPCOM_TRANLEN_MAX, GFP_KERNEL);
if (!local_buf) {
return;
}
- for (pos = 0, loop = 0; pos < n_rx; pos += trans_len, loop++) {
- trans_len = n_rx - pos;
- if (trans_len > SPCOM_TRANLEN_MAX - n_tx)
- trans_len = SPCOM_TRANLEN_MAX - n_tx;
+ for (pos = 0, loop = 0; pos < total_len; pos += trans_len, loop++) {
+ trans_len = total_len - pos;
i = 0;
+ tx_only = 0;
list_for_each_entry(t, &m->transfers, transfer_list) {
if (t->tx_buf) {
memcpy(local_buf + i, t->tx_buf, t->len);
i += t->len;
+ if (!t->rx_buf)
+ tx_only += t->len;
}
}
+ /* Add additional TX bytes to compensate SPCOM_TRANLEN_MAX */
+ if (loop > 0)
+ trans_len += tx_only;
+
+ if (trans_len > SPCOM_TRANLEN_MAX)
+ trans_len = SPCOM_TRANLEN_MAX;
+
+ /* Update device offset */
if (pos > 0) {
addr = fsl_espi_cmd2addr(local_buf);
- addr += pos;
+ addr += rx_pos;
fsl_espi_addr2cmd(addr, local_buf);
}
- espi_trans->n_tx = n_tx;
- espi_trans->n_rx = trans_len;
- espi_trans->len = trans_len + n_tx;
+ espi_trans->len = trans_len;
espi_trans->tx_buf = local_buf;
espi_trans->rx_buf = local_buf;
fsl_espi_do_trans(m, espi_trans);
- memcpy(rx_buf + pos, espi_trans->rx_buf + n_tx, trans_len);
+ /* If there is at least one RX byte then copy it to rx_buf */
+ if (tx_only < SPCOM_TRANLEN_MAX)
+ memcpy(rx_buf + rx_pos, espi_trans->rx_buf + tx_only,
+ trans_len - tx_only);
+
+ rx_pos += trans_len - tx_only;
if (loop > 0)
- espi_trans->actual_length += espi_trans->len - n_tx;
+ espi_trans->actual_length += espi_trans->len - tx_only;
else
espi_trans->actual_length += espi_trans->len;
}
u8 *rx_buf = NULL;
unsigned int n_tx = 0;
unsigned int n_rx = 0;
+ unsigned int xfer_len = 0;
struct fsl_espi_transfer espi_trans;
list_for_each_entry(t, &m->transfers, transfer_list) {
n_rx += t->len;
rx_buf = t->rx_buf;
}
+ if ((t->tx_buf) || (t->rx_buf))
+ xfer_len += t->len;
}
espi_trans.n_tx = n_tx;
espi_trans.n_rx = n_rx;
- espi_trans.len = n_tx + n_rx;
+ espi_trans.len = xfer_len;
espi_trans.actual_length = 0;
espi_trans.status = 0;
struct omap2_mcspi *mcspi;
struct omap2_mcspi_dma *mcspi_dma;
struct spi_transfer *t;
+ int status;
spi = m->spi;
mcspi = spi_master_get_devdata(master);
tx_buf ? "tx" : "",
rx_buf ? "rx" : "",
t->bits_per_word);
- return -EINVAL;
+ status = -EINVAL;
+ goto out;
}
if (m->is_dma_mapped || len < DMA_MIN_BYTES)
if (dma_mapping_error(mcspi->dev, t->tx_dma)) {
dev_dbg(mcspi->dev, "dma %cX %d bytes error\n",
'T', len);
- return -EINVAL;
+ status = -EINVAL;
+ goto out;
}
}
if (mcspi_dma->dma_rx && rx_buf != NULL) {
if (tx_buf != NULL)
dma_unmap_single(mcspi->dev, t->tx_dma,
len, DMA_TO_DEVICE);
- return -EINVAL;
+ status = -EINVAL;
+ goto out;
}
}
}
omap2_mcspi_work(mcspi, m);
+ /* spi_finalize_current_message() changes the status inside the
+ * spi_message, save the status here. */
+ status = m->status;
+out:
spi_finalize_current_message(master);
- return 0;
+ return status;
}
static int omap2_mcspi_master_setup(struct omap2_mcspi *mcspi)
rx_dev = master->dma_rx->device->dev;
list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+ /*
+ * Restore the original value of tx_buf or rx_buf if they are
+ * NULL.
+ */
+ if (xfer->tx_buf == master->dummy_tx)
+ xfer->tx_buf = NULL;
+ if (xfer->rx_buf == master->dummy_rx)
+ xfer->rx_buf = NULL;
+
if (!master->can_dma(master, msg->spi, xfer))
continue;
u32 crystalfreq;
const struct pmu0_plltab_entry *e = NULL;
- crystalfreq = chipco_read32(cc, SSB_CHIPCO_PMU_CTL) &
- SSB_CHIPCO_PMU_CTL_XTALFREQ >> SSB_CHIPCO_PMU_CTL_XTALFREQ_SHIFT;
+ crystalfreq = (chipco_read32(cc, SSB_CHIPCO_PMU_CTL) &
+ SSB_CHIPCO_PMU_CTL_XTALFREQ) >> SSB_CHIPCO_PMU_CTL_XTALFREQ_SHIFT;
e = pmu0_plltab_find_entry(crystalfreq);
BUG_ON(!e);
return e->freq * 1000;
switch (bus->chip_id) {
case 0x5354:
- ssb_pmu_get_alp_clock_clk0(cc);
+ return ssb_pmu_get_alp_clock_clk0(cc);
default:
ssb_err("ERROR: PMU alp clock unknown for device %04X\n",
bus->chip_id);
/*
* Accessing PCI config without a proper delay after devices reset (not
- * GPIO reset) was causing reboots on WRT300N v1.0.
+ * GPIO reset) was causing reboots on WRT300N v1.0 (BCM4704).
* Tested delay 850 us lowered reboot chance to 50-80%, 1000 us fixed it
* completely. Flushing all writes was also tested but with no luck.
+ * The same problem was reported for WRT350N v1 (BCM4705), so we just
+ * sleep here unconditionally.
*/
- if (pc->dev->bus->chip_id == 0x4704)
- usleep_range(1000, 2000);
+ usleep_range(1000, 2000);
/* Enable PCI bridge BAR0 prefetch and burst */
val = PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY;
unsigned int start_flag;
unsigned int payload_size;
unsigned short packet_type;
- int dummy_cnt;
+ int total_len;
u32 packet_size_sum = r->offset;
int index;
int ret = TO_HOST_INVALID_PACKET;
break;
}
- dummy_cnt = ALIGN(MUX_HEADER_SIZE + payload_size, 4);
+ total_len = ALIGN(MUX_HEADER_SIZE + payload_size, 4);
if (len - packet_size_sum <
- MUX_HEADER_SIZE + payload_size + dummy_cnt) {
+ total_len) {
pr_err("invalid payload : %d %d %04x\n",
payload_size, len, packet_type);
break;
break;
}
- packet_size_sum += MUX_HEADER_SIZE + payload_size + dummy_cnt;
+ packet_size_sum += total_len;
if (len - packet_size_sum <= MUX_HEADER_SIZE + 2) {
ret = r->callback(NULL,
0,
struct mux_pkt_header *mux_header;
struct mux_tx *t = NULL;
static u32 seq_num = 1;
- int dummy_cnt;
int total_len;
int ret;
unsigned long flags;
spin_lock_irqsave(&mux_dev->write_lock, flags);
- dummy_cnt = ALIGN(MUX_HEADER_SIZE + len, 4);
-
- total_len = len + MUX_HEADER_SIZE + dummy_cnt;
+ total_len = ALIGN(MUX_HEADER_SIZE + len, 4);
t = alloc_mux_tx(total_len);
if (!t) {
mux_header->packet_type = __cpu_to_le16(packet_type[tty_index]);
memcpy(t->buf+MUX_HEADER_SIZE, data, len);
- memset(t->buf+MUX_HEADER_SIZE+len, 0, dummy_cnt);
+ memset(t->buf+MUX_HEADER_SIZE+len, 0, total_len - MUX_HEADER_SIZE -
+ len);
t->len = total_len;
t->callback = cb;
#endif
-
-/*
- * After 3.1, kernel's nameidata.intent.open.flags is different
- * with lustre's lookup_intent.it_flags, as lustre's it_flags'
- * lower bits equal to FMODE_xxx while kernel doesn't transliterate
- * lower bits of nameidata.intent.open.flags to FMODE_xxx.
- * */
#include <linux/version.h>
-static inline int ll_namei_to_lookup_intent_flag(int flag)
-{
-#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 1, 0)
- flag = (flag & ~O_ACCMODE) | OPEN_FMODE(flag);
-#endif
- return flag;
-}
-
#include <linux/fs.h>
# define ll_umode_t umode_t
/* return cpumask of HTs in the same core */
static void cfs_cpu_ht_siblings(int cpu, cpumask_t *mask)
{
- cpumask_copy(mask, topology_thread_cpumask(cpu));
+ cpumask_copy(mask, topology_sibling_cpumask(cpu));
}
static void cfs_node_to_cpumask(int node, cpumask_t *mask)
#define VM_FAULT_RETRY 0
#endif
-/* Kernel 3.1 kills LOOKUP_CONTINUE, LOOKUP_PARENT is equivalent to it.
- * seem kernel commit 49084c3bb2055c401f3493c13edae14d49128ca0 */
-#ifndef LOOKUP_CONTINUE
-#define LOOKUP_CONTINUE LOOKUP_PARENT
-#endif
-
/** Only used on client-side for indicating the tail of dir hash/offset. */
#define LL_DIR_END_OFF 0x7fffffffffffffffULL
#define LL_DIR_END_OFF_32BIT 0x7fffffffUL
return rc;
}
-static void *ll_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *ll_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
struct ptlrpc_request *request = NULL;
char *symname = NULL;
CDEBUG(D_VFSTRACE, "VFS Op\n");
- /* Limit the recursive symlink depth to 5 instead of default
- * 8 links when kernel has 4k stack to prevent stack overflow.
- * For 8k stacks we need to limit it to 7 for local servers. */
- if (THREAD_SIZE < 8192 && current->link_count >= 6) {
- rc = -ELOOP;
- } else if (THREAD_SIZE == 8192 && current->link_count >= 8) {
- rc = -ELOOP;
- } else {
- ll_inode_size_lock(inode);
- rc = ll_readlink_internal(inode, &request, &symname);
- ll_inode_size_unlock(inode);
- }
+ ll_inode_size_lock(inode);
+ rc = ll_readlink_internal(inode, &request, &symname);
+ ll_inode_size_unlock(inode);
if (rc) {
ptlrpc_req_finished(request);
- request = NULL;
- symname = ERR_PTR(rc);
+ return ERR_PTR(rc);
}
- nd_set_link(nd, symname);
/* symname may contain a pointer to the request message buffer,
* we delay request releasing until ll_put_link then.
*/
- return request;
+ *cookie = request;
+ return symname;
}
-static void ll_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+static void ll_put_link(struct inode *unused, void *cookie)
{
ptlrpc_req_finished(cookie);
}
* there are.
*/
/* weight is # of HTs */
- if (cpumask_weight(topology_thread_cpumask(0)) > 1) {
+ if (cpumask_weight(topology_sibling_cpumask(0)) > 1) {
/* depress thread factor for hyper-thread */
factor = factor - (factor >> 1) + (factor >> 3);
}
init_waitqueue_head(&ptlrpc_hr.hr_waitq);
- weight = cpumask_weight(topology_thread_cpumask(0));
+ weight = cpumask_weight(topology_sibling_cpumask(0));
cfs_percpt_for_each(hrp, i, ptlrpc_hr.hr_partitions) {
hrp->hrp_cpt = i;
/*
* Context: softirq
*/
-void oz_hcd_get_desc_cnf(void *hport, u8 req_id, int status, const u8 *desc,
- int length, int offset, int total_size)
+void oz_hcd_get_desc_cnf(void *hport, u8 req_id, u8 status, const u8 *desc,
+ u8 length, u16 offset, u16 total_size)
{
struct oz_port *port = hport;
struct urb *urb;
if (!urb)
return;
if (status == 0) {
- int copy_len;
- int required_size = urb->transfer_buffer_length;
+ unsigned int copy_len;
+ unsigned int required_size = urb->transfer_buffer_length;
if (required_size > total_size)
required_size = total_size;
/* Confirmation functions.
*/
-void oz_hcd_get_desc_cnf(void *hport, u8 req_id, int status,
- const u8 *desc, int length, int offset, int total_size);
+void oz_hcd_get_desc_cnf(void *hport, u8 req_id, u8 status,
+ const u8 *desc, u8 length, u16 offset, u16 total_size);
void oz_hcd_control_cnf(void *hport, u8 req_id, u8 rcode,
const u8 *data, int data_len);
struct oz_multiple_fixed *body =
(struct oz_multiple_fixed *)data_hdr;
u8 *data = body->data;
- int n = (len - sizeof(struct oz_multiple_fixed)+1)
+ unsigned int n;
+ if (!body->unit_size ||
+ len < sizeof(struct oz_multiple_fixed) - 1)
+ break;
+ n = (len - (sizeof(struct oz_multiple_fixed) - 1))
/ body->unit_size;
while (n--) {
oz_hcd_data_ind(usb_ctx->hport, body->endpoint,
case OZ_GET_DESC_RSP: {
struct oz_get_desc_rsp *body =
(struct oz_get_desc_rsp *)usb_hdr;
- int data_len = elt->length -
- sizeof(struct oz_get_desc_rsp) + 1;
- u16 offs = le16_to_cpu(get_unaligned(&body->offset));
- u16 total_size =
+ u16 offs, total_size;
+ u8 data_len;
+
+ if (elt->length < sizeof(struct oz_get_desc_rsp) - 1)
+ break;
+ data_len = elt->length -
+ (sizeof(struct oz_get_desc_rsp) - 1);
+ offs = le16_to_cpu(get_unaligned(&body->offset));
+ total_size =
le16_to_cpu(get_unaligned(&body->total_size));
oz_dbg(ON, "USB_REQ_GET_DESCRIPTOR - cnf\n");
oz_hcd_get_desc_cnf(usb_ctx->hport, body->req_id,
IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedNoLinkBlinkInProgress = true;
IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedLinkBlinkInProgress = true;
if (IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedScanBlinkInProgress = true;
IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedLinkBlinkInProgress = false;
}
pLed->bLedBlinkInProgress = true;
case LED_CTL_START_WPS_BOTTON:
if (pLed->bLedWPSBlinkInProgress == false) {
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
pLed->bLedWPSBlinkInProgress = true;
break;
case LED_CTL_STOP_WPS:
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
if (pLed->bLedWPSBlinkInProgress)
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
else
pLed->bLedWPSBlinkInProgress = true;
pLed->CurrLedState = LED_BLINK_WPS_STOP;
break;
case LED_CTL_STOP_WPS_FAIL:
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
pLed->bLedNoLinkBlinkInProgress = true;
pLed->CurrLedState = LED_OFF;
pLed->BlinkingLedState = LED_OFF;
if (pLed->bLedNoLinkBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedLinkBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
mod_timer(&pLed->BlinkTimer,
return;
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedScanBlinkInProgress = true;
pLed->CurrLedState = LED_ON;
pLed->BlinkingLedState = LED_ON;
if (pLed->bLedBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
case LED_CTL_START_WPS_BOTTON:
if (pLed->bLedWPSBlinkInProgress == false) {
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
pLed->bLedWPSBlinkInProgress = true;
pLed->CurrLedState = LED_OFF;
pLed->BlinkingLedState = LED_OFF;
if (pLed->bLedBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
mod_timer(&pLed->BlinkTimer,
if (IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedScanBlinkInProgress = true;
pLed->CurrLedState = LED_ON;
pLed->BlinkingLedState = LED_ON;
if (pLed->bLedBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
mod_timer(&pLed->BlinkTimer,
case LED_CTL_START_WPS_BOTTON:
if (pLed->bLedWPSBlinkInProgress == false) {
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
pLed->bLedWPSBlinkInProgress = true;
break;
case LED_CTL_STOP_WPS:
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&(pLed->BlinkTimer));
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
} else
pLed->bLedWPSBlinkInProgress = true;
break;
case LED_CTL_STOP_WPS_FAIL:
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
pLed->CurrLedState = LED_OFF;
pLed->CurrLedState = LED_OFF;
pLed->BlinkingLedState = LED_OFF;
if (pLed->bLedBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
mod_timer(&pLed->BlinkTimer,
case LED_CTL_START_TO_LINK:
if (pLed1->bLedWPSBlinkInProgress) {
pLed1->bLedWPSBlinkInProgress = false;
- del_timer_sync(&pLed1->BlinkTimer);
+ del_timer(&pLed1->BlinkTimer);
pLed1->BlinkingLedState = LED_OFF;
pLed1->CurrLedState = LED_OFF;
if (pLed1->bLedOn)
IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
pLed->bLedStartToLinkBlinkInProgress = true;
if (LedAction == LED_CTL_LINK) {
if (pLed1->bLedWPSBlinkInProgress) {
pLed1->bLedWPSBlinkInProgress = false;
- del_timer_sync(&pLed1->BlinkTimer);
+ del_timer(&pLed1->BlinkTimer);
pLed1->BlinkingLedState = LED_OFF;
pLed1->CurrLedState = LED_OFF;
if (pLed1->bLedOn)
IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedNoLinkBlinkInProgress = true;
if (IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedScanBlinkInProgress = true;
IS_LED_WPS_BLINKING(pLed))
return;
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
pLed->bLedBlinkInProgress = true;
case LED_CTL_START_WPS_BOTTON:
if (pLed1->bLedWPSBlinkInProgress) {
pLed1->bLedWPSBlinkInProgress = false;
- del_timer_sync(&(pLed1->BlinkTimer));
+ del_timer(&pLed1->BlinkTimer);
pLed1->BlinkingLedState = LED_OFF;
pLed1->CurrLedState = LED_OFF;
if (pLed1->bLedOn)
}
if (pLed->bLedWPSBlinkInProgress == false) {
if (pLed->bLedNoLinkBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
pLed->bLedWPSBlinkInProgress = true;
break;
case LED_CTL_STOP_WPS: /*WPS connect success*/
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
pLed->bLedNoLinkBlinkInProgress = true;
break;
case LED_CTL_STOP_WPS_FAIL: /*WPS authentication fail*/
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
pLed->bLedNoLinkBlinkInProgress = true;
msecs_to_jiffies(LED_BLINK_NO_LINK_INTERVAL_ALPHA));
/*LED1 settings*/
if (pLed1->bLedWPSBlinkInProgress)
- del_timer_sync(&pLed1->BlinkTimer);
+ del_timer(&pLed1->BlinkTimer);
else
pLed1->bLedWPSBlinkInProgress = true;
pLed1->CurrLedState = LED_BLINK_WPS_STOP;
break;
case LED_CTL_STOP_WPS_FAIL_OVERLAP: /*WPS session overlap*/
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
pLed->bLedNoLinkBlinkInProgress = true;
msecs_to_jiffies(LED_BLINK_NO_LINK_INTERVAL_ALPHA));
/*LED1 settings*/
if (pLed1->bLedWPSBlinkInProgress)
- del_timer_sync(&pLed1->BlinkTimer);
+ del_timer(&pLed1->BlinkTimer);
else
pLed1->bLedWPSBlinkInProgress = true;
pLed1->CurrLedState = LED_BLINK_WPS_STOP_OVERLAP;
pLed->CurrLedState = LED_OFF;
pLed->BlinkingLedState = LED_OFF;
if (pLed->bLedNoLinkBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedNoLinkBlinkInProgress = false;
}
if (pLed->bLedLinkBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedLinkBlinkInProgress = false;
}
if (pLed->bLedBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
if (pLed->bLedScanBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedScanBlinkInProgress = false;
}
if (pLed->bLedStartToLinkBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedStartToLinkBlinkInProgress = false;
}
if (pLed1->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed1->BlinkTimer);
+ del_timer(&pLed1->BlinkTimer);
pLed1->bLedWPSBlinkInProgress = false;
}
pLed1->BlinkingLedState = LED_UNKNOWN;
; /* dummy branch */
else if (pLed->bLedScanBlinkInProgress == false) {
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedScanBlinkInProgress = true;
pLed->CurrLedState = LED_OFF;
pLed->BlinkingLedState = LED_OFF;
if (pLed->bLedBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
SwLedOff(padapter, pLed);
case LED_CTL_START_WPS_BOTTON:
if (pLed->bLedWPSBlinkInProgress == false) {
if (pLed->bLedBlinkInProgress == true) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
pLed->bLedWPSBlinkInProgress = true;
case LED_CTL_STOP_WPS_FAIL:
case LED_CTL_STOP_WPS:
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
pLed->CurrLedState = LED_ON;
pLed->CurrLedState = LED_OFF;
pLed->BlinkingLedState = LED_OFF;
if (pLed->bLedBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedBlinkInProgress = false;
}
if (pLed->bLedWPSBlinkInProgress) {
- del_timer_sync(&pLed->BlinkTimer);
+ del_timer(&pLed->BlinkTimer);
pLed->bLedWPSBlinkInProgress = false;
}
SwLedOff(padapter, pLed);
if (pcmd->res != H2C_SUCCESS)
mod_timer(&pmlmepriv->assoc_timer,
jiffies + msecs_to_jiffies(1));
- del_timer_sync(&pmlmepriv->assoc_timer);
+ del_timer(&pmlmepriv->assoc_timer);
#ifdef __BIG_ENDIAN
/* endian_convert */
pnetwork->Length = le32_to_cpu(pnetwork->Length);
struct mp_ioctl_handler *phandler;
struct mp_ioctl_param *poidparam;
unsigned long BytesRead, BytesWritten, BytesNeeded;
- u8 *pparmbuf = NULL, bset;
+ u8 *pparmbuf, bset;
u16 len;
uint status;
int ret = 0;
- if ((!p->length) || (!p->pointer)) {
- ret = -EINVAL;
- goto _r871x_mp_ioctl_hdl_exit;
- }
+ if ((!p->length) || (!p->pointer))
+ return -EINVAL;
+
bset = (u8)(p->flags & 0xFFFF);
len = p->length;
- pparmbuf = NULL;
pparmbuf = memdup_user(p->pointer, len);
- if (IS_ERR(pparmbuf)) {
- ret = PTR_ERR(pparmbuf);
- goto _r871x_mp_ioctl_hdl_exit;
- }
+ if (IS_ERR(pparmbuf))
+ return PTR_ERR(pparmbuf);
+
poidparam = (struct mp_ioctl_param *)pparmbuf;
if (poidparam->subcode >= MAX_MP_IOCTL_SUBCODE) {
ret = -EINVAL;
spin_lock_irqsave(&pmlmepriv->lock, irqL);
if (check_fwstate(pmlmepriv, _FW_UNDER_SURVEY) == true) {
- del_timer_sync(&pmlmepriv->scan_to_timer);
+ del_timer(&pmlmepriv->scan_to_timer);
_clr_fwstate_(pmlmepriv, _FW_UNDER_SURVEY);
}
}
if (padapter->pwrctrlpriv.pwr_mode !=
padapter->registrypriv.power_mgnt) {
- del_timer_sync(&pmlmepriv->dhcp_timer);
+ del_timer(&pmlmepriv->dhcp_timer);
r8712_set_ps_mode(padapter, padapter->registrypriv.power_mgnt,
padapter->registrypriv.smart_ps);
}
if (check_fwstate(pmlmepriv, WIFI_STATION_STATE)
== true)
r8712_indicate_connect(adapter);
- del_timer_sync(&pmlmepriv->assoc_timer);
+ del_timer(&pmlmepriv->assoc_timer);
} else
goto ignore_joinbss_callback;
} else {
if (pwrpriv->cpwm_tog == ((preportpwrstate->state) & 0x80))
return;
- del_timer_sync(&padapter->pwrctrlpriv.rpwm_check_timer);
+ del_timer(&padapter->pwrctrlpriv.rpwm_check_timer);
_enter_pwrlock(&pwrpriv->lock);
pwrpriv->cpwm = (preportpwrstate->state) & 0xf;
if (pwrpriv->cpwm >= PS_STATE_S2) {
* cancel reordering_ctrl_timer */
for (i = 0; i < 16; i++) {
preorder_ctrl = &psta->recvreorder_ctrl[i];
- del_timer_sync(&preorder_ctrl->reordering_ctrl_timer);
+ del_timer(&preorder_ctrl->reordering_ctrl_timer);
}
spin_lock(&(pfree_sta_queue->lock));
/* insert into free_sta_queue; 20061114 */
return -ENODEV;
}
-static void __exit lynxfb_pci_remove(struct pci_dev *pdev)
+static void lynxfb_pci_remove(struct pci_dev *pdev)
{
struct fb_info *info;
struct lynx_share *share;
* Return Value: none
*/
bool CARDbUpdateTSF(struct vnt_private *pDevice, unsigned char byRxRate,
- u64 qwBSSTimestamp, u64 qwLocalTSF)
+ u64 qwBSSTimestamp)
{
+ u64 local_tsf;
u64 qwTSFOffset = 0;
- if (qwBSSTimestamp != qwLocalTSF) {
- qwTSFOffset = CARDqGetTSFOffset(byRxRate, qwBSSTimestamp, qwLocalTSF);
+ CARDbGetCurrentTSF(pDevice, &local_tsf);
+
+ if (qwBSSTimestamp != local_tsf) {
+ qwTSFOffset = CARDqGetTSFOffset(byRxRate, qwBSSTimestamp,
+ local_tsf);
/* adjust TSF, HW's TSF add TSF Offset reg */
VNSvOutPortD(pDevice->PortOffset + MAC_REG_TSFOFST, (u32)qwTSFOffset);
VNSvOutPortD(pDevice->PortOffset + MAC_REG_TSFOFST + 4, (u32)(qwTSFOffset >> 32));
bool CARDbRadioPowerOn(struct vnt_private *);
bool CARDbSetPhyParameter(struct vnt_private *, u8);
bool CARDbUpdateTSF(struct vnt_private *, unsigned char byRxRate,
- u64 qwBSSTimestamp, u64 qwLocalTSF);
+ u64 qwBSSTimestamp);
bool CARDbSetBeaconPeriod(struct vnt_private *, unsigned short wBeaconInterval);
#endif /* __CARD_H__ */
if (!(tsr1 & TSR1_TERR)) {
info->status.rates[0].idx = idx;
- info->flags |= IEEE80211_TX_STAT_ACK;
+
+ if (info->flags & IEEE80211_TX_CTL_NO_ACK)
+ info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED;
+ else
+ info->flags |= IEEE80211_TX_STAT_ACK;
}
return 0;
/* Only the status of first TD in the chain is correct */
if (pTD->m_td1TD1.byTCR & TCR_STP) {
if ((pTD->pTDInfo->byFlags & TD_FLAGS_NETIF_SKB) != 0) {
-
- vnt_int_report_rate(pDevice, pTD->pTDInfo, byTsr0, byTsr1);
-
if (!(byTsr1 & TSR1_TERR)) {
if (byTsr0 != 0) {
pr_debug(" Tx[%d] OK but has error. tsr1[%02X] tsr0[%02X]\n",
(int)uIdx, byTsr1, byTsr0);
}
}
+
+ vnt_int_report_rate(pDevice, pTD->pTDInfo, byTsr0, byTsr1);
+
device_free_tx_buf(pDevice, pTD);
pDevice->iTDUsed[uIdx]--;
}
skb->len, DMA_TO_DEVICE);
}
- if (pTDInfo->byFlags & TD_FLAGS_NETIF_SKB)
+ if (skb)
ieee80211_tx_status_irqsafe(pDevice->hw, skb);
- else
- dev_kfree_skb_irq(skb);
pTDInfo->skb_dma = 0;
pTDInfo->skb = NULL;
if (dma_idx == TYPE_AC0DMA)
head_td->pTDInfo->byFlags = TD_FLAGS_NETIF_SKB;
- priv->iTDUsed[dma_idx]++;
-
- /* Take ownership */
- wmb();
- head_td->m_td0TD0.f1Owner = OWNED_BY_NIC;
-
- /* get Next */
- wmb();
priv->apCurrTD[dma_idx] = head_td->next;
spin_unlock_irqrestore(&priv->lock, flags);
head_td->buff_addr = cpu_to_le32(head_td->pTDInfo->skb_dma);
+ /* Poll Transmit the adapter */
+ wmb();
+ head_td->m_td0TD0.f1Owner = OWNED_BY_NIC;
+ wmb(); /* second memory barrier */
+
if (head_td->pTDInfo->byFlags & TD_FLAGS_NETIF_SKB)
MACvTransmitAC0(priv->PortOffset);
else
MACvTransmit0(priv->PortOffset);
+ priv->iTDUsed[dma_idx]++;
+
spin_unlock_irqrestore(&priv->lock, flags);
return 0;
priv->current_aid = conf->aid;
- if (changed & BSS_CHANGED_BSSID)
+ if (changed & BSS_CHANGED_BSSID) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&priv->lock, flags);
+
MACvWriteBSSIDAddress(priv->PortOffset, (u8 *)conf->bssid);
+ spin_unlock_irqrestore(&priv->lock, flags);
+ }
+
if (changed & BSS_CHANGED_BASIC_RATES) {
priv->basic_rates = conf->basic_rates;
if (changed & BSS_CHANGED_ASSOC && priv->op_mode != NL80211_IFTYPE_AP) {
if (conf->assoc) {
CARDbUpdateTSF(priv, conf->beacon_rate->hw_value,
- conf->sync_device_ts, conf->sync_tsf);
+ conf->sync_tsf);
CARDbSetBeaconPeriod(priv, conf->beacon_int);
vnt_schedule_command(priv, WLAN_CMD_SETPOWER);
}
- if (current_rate > RATE_11M)
- pkt_type = priv->packet_type;
- else
+ if (current_rate > RATE_11M) {
+ if (info->band == IEEE80211_BAND_5GHZ) {
+ pkt_type = PK_TYPE_11A;
+ } else {
+ if (tx_rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT)
+ pkt_type = PK_TYPE_11GB;
+ else
+ pkt_type = PK_TYPE_11GA;
+ }
+ } else {
pkt_type = PK_TYPE_11B;
+ }
spin_lock_irqsave(&priv->lock, flags);
* Here we serialize access across the TIQN+TPG Tuple.
*/
ret = down_interruptible(&tpg->np_login_sem);
- if ((ret != 0) || signal_pending(current))
+ if (ret != 0)
return -1;
spin_lock_bh(&tpg->tpg_state_lock);
if (IS_ERR(sess->se_sess)) {
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ kfree(sess->sess_ops);
kfree(sess);
return -ENOMEM;
}
int iscsit_get_tpg(
struct iscsi_portal_group *tpg)
{
- int ret;
-
- ret = mutex_lock_interruptible(&tpg->tpg_access_lock);
- return ((ret != 0) || signal_pending(current)) ? -1 : 0;
+ return mutex_lock_interruptible(&tpg->tpg_access_lock);
}
void iscsit_put_tpg(struct iscsi_portal_group *tpg)
if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
return 0;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
if (!port)
int core_setup_alua(struct se_device *dev)
{
- if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV &&
+ if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
struct t10_alua_lu_gp_member *lu_gp_mem;
pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:"
" %s\n", tf->tf_group.cg_item.ci_name);
- /*
- * Setup tf_ops.tf_subsys pointer for usage with configfs_depend_item()
- */
- tf->tf_ops.tf_subsys = tf->tf_subsys;
tf->tf_fabric = &tf->tf_group.cg_item;
pr_debug("Target_Core_ConfigFS: REGISTER -> Set tf->tf_fabric"
" for %s\n", name);
},
};
-struct configfs_subsystem *target_core_subsystem[] = {
- &target_core_fabrics,
- NULL,
-};
+int target_depend_item(struct config_item *item)
+{
+ return configfs_depend_item(&target_core_fabrics, item);
+}
+EXPORT_SYMBOL(target_depend_item);
+
+void target_undepend_item(struct config_item *item)
+{
+ return configfs_undepend_item(&target_core_fabrics, item);
+}
+EXPORT_SYMBOL(target_undepend_item);
/*##############################################################################
// Start functions called by external Target Fabrics Modules
* struct target_fabric_configfs->tf_cit_tmpl
*/
tf->tf_module = fo->module;
- tf->tf_subsys = target_core_subsystem[0];
snprintf(tf->tf_name, TARGET_FABRIC_NAME_SIZE, "%s", fo->name);
tf->tf_ops = *fo;
{
int ret;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return sprintf(page, "Passthrough\n");
spin_lock(&dev->dev_reservation_lock);
static ssize_t target_core_dev_pr_show_attr_res_type(
struct se_device *dev, char *page)
{
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return sprintf(page, "SPC_PASSTHROUGH\n");
else if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
return sprintf(page, "SPC2_RESERVATIONS\n");
static ssize_t target_core_dev_pr_show_attr_res_aptpl_active(
struct se_device *dev, char *page)
{
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
return sprintf(page, "APTPL Bit Status: %s\n",
static ssize_t target_core_dev_pr_show_attr_res_aptpl_metadata(
struct se_device *dev, char *page)
{
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
return sprintf(page, "Ready to process PR APTPL metadata..\n");
u16 port_rpti = 0, tpgt = 0;
u8 type = 0, scope;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
return 0;
{
struct config_group *target_cg, *hba_cg = NULL, *alua_cg = NULL;
struct config_group *lu_gp_cg = NULL;
- struct configfs_subsystem *subsys;
+ struct configfs_subsystem *subsys = &target_core_fabrics;
struct t10_alua_lu_gp *lu_gp;
int ret;
" Engine: %s on %s/%s on "UTS_RELEASE"\n",
TARGET_CORE_VERSION, utsname()->sysname, utsname()->machine);
- subsys = target_core_subsystem[0];
config_group_init(&subsys->su_group);
mutex_init(&subsys->su_mutex);
static void __exit target_core_exit_configfs(void)
{
- struct configfs_subsystem *subsys;
struct config_group *hba_cg, *alua_cg, *lu_gp_cg;
struct config_item *item;
int i;
- subsys = target_core_subsystem[0];
-
lu_gp_cg = &alua_lu_gps_group;
for (i = 0; lu_gp_cg->default_groups[i]; i++) {
item = &lu_gp_cg->default_groups[i]->cg_item;
* We expect subsys->su_group.default_groups to be released
* by configfs subsystem provider logic..
*/
- configfs_unregister_subsystem(subsys);
- kfree(subsys->su_group.default_groups);
+ configfs_unregister_subsystem(&target_core_fabrics);
+ kfree(target_core_fabrics.su_group.default_groups);
core_alua_free_lu_gp(default_lu_gp);
default_lu_gp = NULL;
#include <linux/kthread.h>
#include <linux/in.h>
#include <linux/export.h>
+#include <asm/unaligned.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <scsi/scsi.h>
list_add_tail(&port->sep_list, &dev->dev_sep_list);
spin_unlock(&dev->se_port_lock);
- if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV &&
+ if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
tg_pt_gp_mem = core_alua_allocate_tg_pt_gp_mem(port);
if (IS_ERR(tg_pt_gp_mem) || !tg_pt_gp_mem) {
* anything virtual (IBLOCK, FILEIO, RAMDISK), but not for TCM/pSCSI
* passthrough because this is being provided by the backend LLD.
*/
- if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV) {
+ if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)) {
strncpy(&dev->t10_wwn.vendor[0], "LIO-ORG", 8);
strncpy(&dev->t10_wwn.model[0],
dev->transport->inquiry_prod, 16);
target_free_device(g_lun0_dev);
core_delete_hba(hba);
}
+
+/*
+ * Common CDB parsing for kernel and user passthrough.
+ */
+sense_reason_t
+passthrough_parse_cdb(struct se_cmd *cmd,
+ sense_reason_t (*exec_cmd)(struct se_cmd *cmd))
+{
+ unsigned char *cdb = cmd->t_task_cdb;
+
+ /*
+ * Clear a lun set in the cdb if the initiator talking to use spoke
+ * and old standards version, as we can't assume the underlying device
+ * won't choke up on it.
+ */
+ switch (cdb[0]) {
+ case READ_10: /* SBC - RDProtect */
+ case READ_12: /* SBC - RDProtect */
+ case READ_16: /* SBC - RDProtect */
+ case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */
+ case VERIFY: /* SBC - VRProtect */
+ case VERIFY_16: /* SBC - VRProtect */
+ case WRITE_VERIFY: /* SBC - VRProtect */
+ case WRITE_VERIFY_12: /* SBC - VRProtect */
+ case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */
+ break;
+ default:
+ cdb[1] &= 0x1f; /* clear logical unit number */
+ break;
+ }
+
+ /*
+ * For REPORT LUNS we always need to emulate the response, for everything
+ * else, pass it up.
+ */
+ if (cdb[0] == REPORT_LUNS) {
+ cmd->execute_cmd = spc_emulate_report_luns;
+ return TCM_NO_SENSE;
+ }
+
+ /* Set DATA_CDB flag for ops that should have it */
+ switch (cdb[0]) {
+ case READ_6:
+ case READ_10:
+ case READ_12:
+ case READ_16:
+ case WRITE_6:
+ case WRITE_10:
+ case WRITE_12:
+ case WRITE_16:
+ case WRITE_VERIFY:
+ case WRITE_VERIFY_12:
+ case 0x8e: /* WRITE_VERIFY_16 */
+ case COMPARE_AND_WRITE:
+ case XDWRITEREAD_10:
+ cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
+ break;
+ case VARIABLE_LENGTH_CMD:
+ switch (get_unaligned_be16(&cdb[8])) {
+ case READ_32:
+ case WRITE_32:
+ case 0x0c: /* WRITE_VERIFY_32 */
+ case XDWRITEREAD_32:
+ cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
+ break;
+ }
+ }
+
+ cmd->execute_cmd = exec_cmd;
+
+ return TCM_NO_SENSE;
+}
+EXPORT_SYMBOL(passthrough_parse_cdb);
.inquiry_prod = "FILEIO",
.inquiry_rev = FD_VERSION,
.owner = THIS_MODULE,
- .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV,
.attach_hba = fd_attach_hba,
.detach_hba = fd_detach_hba,
.alloc_device = fd_alloc_device,
.inquiry_prod = "IBLOCK",
.inquiry_rev = IBLOCK_VERSION,
.owner = THIS_MODULE,
- .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV,
.attach_hba = iblock_attach_hba,
.detach_hba = iblock_detach_hba,
.alloc_device = iblock_alloc_device,
/* target_core_alua.c */
extern struct t10_alua_lu_gp *default_lu_gp;
-/* target_core_configfs.c */
-extern struct configfs_subsystem *target_core_subsystem[];
-
/* target_core_device.c */
extern struct mutex g_device_mutex;
extern struct list_head g_device_list;
static int core_scsi3_tpg_depend_item(struct se_portal_group *tpg)
{
- return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
- &tpg->tpg_group.cg_item);
+ return target_depend_item(&tpg->tpg_group.cg_item);
}
static void core_scsi3_tpg_undepend_item(struct se_portal_group *tpg)
{
- configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
- &tpg->tpg_group.cg_item);
-
+ target_undepend_item(&tpg->tpg_group.cg_item);
atomic_dec_mb(&tpg->tpg_pr_ref_count);
}
static int core_scsi3_nodeacl_depend_item(struct se_node_acl *nacl)
{
- struct se_portal_group *tpg = nacl->se_tpg;
-
if (nacl->dynamic_node_acl)
return 0;
-
- return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
- &nacl->acl_group.cg_item);
+ return target_depend_item(&nacl->acl_group.cg_item);
}
static void core_scsi3_nodeacl_undepend_item(struct se_node_acl *nacl)
{
- struct se_portal_group *tpg = nacl->se_tpg;
-
- if (nacl->dynamic_node_acl) {
- atomic_dec_mb(&nacl->acl_pr_ref_count);
- return;
- }
-
- configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
- &nacl->acl_group.cg_item);
-
+ if (!nacl->dynamic_node_acl)
+ target_undepend_item(&nacl->acl_group.cg_item);
atomic_dec_mb(&nacl->acl_pr_ref_count);
}
nacl = lun_acl->se_lun_nacl;
tpg = nacl->se_tpg;
- return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
- &lun_acl->se_lun_group.cg_item);
+ return target_depend_item(&lun_acl->se_lun_group.cg_item);
}
static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve)
nacl = lun_acl->se_lun_nacl;
tpg = nacl->se_tpg;
- configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
- &lun_acl->se_lun_group.cg_item);
-
+ target_undepend_item(&lun_acl->se_lun_group.cg_item);
atomic_dec_mb(&se_deve->pr_ref_count);
}
return 0;
if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
return 0;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
spin_lock(&dev->dev_reservation_lock);
" pdv_host_id: %d\n", pdv->pdv_host_id);
return -EINVAL;
}
+ pdv->pdv_lld_host = sh;
}
} else {
if (phv->phv_mode == PHV_VIRTUAL_HOST_ID) {
if ((phv->phv_mode == PHV_LLD_SCSI_HOST_NO) &&
(phv->phv_lld_host != NULL))
scsi_host_put(phv->phv_lld_host);
+ else if (pdv->pdv_lld_host)
+ scsi_host_put(pdv->pdv_lld_host);
if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM))
scsi_device_put(sd);
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
-/*
- * Clear a lun set in the cdb if the initiator talking to use spoke
- * and old standards version, as we can't assume the underlying device
- * won't choke up on it.
- */
-static inline void pscsi_clear_cdb_lun(unsigned char *cdb)
-{
- switch (cdb[0]) {
- case READ_10: /* SBC - RDProtect */
- case READ_12: /* SBC - RDProtect */
- case READ_16: /* SBC - RDProtect */
- case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */
- case VERIFY: /* SBC - VRProtect */
- case VERIFY_16: /* SBC - VRProtect */
- case WRITE_VERIFY: /* SBC - VRProtect */
- case WRITE_VERIFY_12: /* SBC - VRProtect */
- case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */
- break;
- default:
- cdb[1] &= 0x1f; /* clear logical unit number */
- break;
- }
-}
-
static sense_reason_t
pscsi_parse_cdb(struct se_cmd *cmd)
{
- unsigned char *cdb = cmd->t_task_cdb;
-
if (cmd->se_cmd_flags & SCF_BIDI)
return TCM_UNSUPPORTED_SCSI_OPCODE;
- pscsi_clear_cdb_lun(cdb);
-
- /*
- * For REPORT LUNS we always need to emulate the response, for everything
- * else the default for pSCSI is to pass the command to the underlying
- * LLD / physical hardware.
- */
- switch (cdb[0]) {
- case REPORT_LUNS:
- cmd->execute_cmd = spc_emulate_report_luns;
- return 0;
- case READ_6:
- case READ_10:
- case READ_12:
- case READ_16:
- case WRITE_6:
- case WRITE_10:
- case WRITE_12:
- case WRITE_16:
- case WRITE_VERIFY:
- cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- /* FALLTHROUGH*/
- default:
- cmd->execute_cmd = pscsi_execute_cmd;
- return 0;
- }
+ return passthrough_parse_cdb(cmd, pscsi_execute_cmd);
}
static sense_reason_t
static struct se_subsystem_api pscsi_template = {
.name = "pscsi",
.owner = THIS_MODULE,
- .transport_type = TRANSPORT_PLUGIN_PHBA_PDEV,
+ .transport_flags = TRANSPORT_FLAG_PASSTHROUGH,
.attach_hba = pscsi_attach_hba,
.detach_hba = pscsi_detach_hba,
.pmode_enable_hba = pscsi_pmode_enable_hba,
int pdv_lun_id;
struct block_device *pdv_bd;
struct scsi_device *pdv_sd;
+ struct Scsi_Host *pdv_lld_host;
} ____cacheline_aligned;
typedef enum phv_modes {
.name = "rd_mcp",
.inquiry_prod = "RAMDISK-MCP",
.inquiry_rev = RD_MCP_VERSION,
- .transport_type = TRANSPORT_PLUGIN_VHBA_VDEV,
.attach_hba = rd_attach_hba,
.detach_hba = rd_detach_hba,
.alloc_device = rd_alloc_device,
* comparision using SGLs at cmd->t_bidi_data_sg..
*/
rc = down_interruptible(&dev->caw_sem);
- if ((rc != 0) || signal_pending(current)) {
+ if (rc != 0) {
cmd->transport_complete_callback = NULL;
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
* Check if SAM Task Attribute emulation is enabled for this
* struct se_device storage object
*/
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return 0;
if (cmd->sam_task_attr == TCM_ACA_TAG) {
sectors, 0, NULL, 0);
if (unlikely(cmd->pi_err)) {
spin_lock_irq(&cmd->t_state_lock);
- cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT;
+ cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
spin_unlock_irq(&cmd->t_state_lock);
transport_generic_request_failure(cmd, cmd->pi_err);
return -1;
{
struct se_device *dev = cmd->se_dev;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return false;
/*
if (target_handle_task_attr(cmd)) {
spin_lock_irq(&cmd->t_state_lock);
- cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT;
+ cmd->transport_state &= ~(CMD_T_BUSY | CMD_T_SENT);
spin_unlock_irq(&cmd->t_state_lock);
return;
}
{
struct se_device *dev = cmd->se_dev;
- if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
return;
if (cmd->sam_task_attr == TCM_SIMPLE_TAG) {
case DMA_TO_DEVICE:
if (cmd->se_cmd_flags & SCF_BIDI) {
ret = cmd->se_tfo->queue_data_in(cmd);
- if (ret < 0)
- break;
+ break;
}
/* Fall through for DMA_TO_DEVICE */
case DMA_NONE:
u32 host_id;
};
-/* User wants all cmds or just some */
-enum passthru_level {
- TCMU_PASS_ALL = 0,
- TCMU_PASS_IO,
- TCMU_PASS_INVALID,
-};
-
#define TCMU_CONFIG_LEN 256
struct tcmu_dev {
#define TCMU_DEV_BIT_OPEN 0
#define TCMU_DEV_BIT_BROKEN 1
unsigned long flags;
- enum passthru_level pass_level;
struct uio_info uio_info;
setup_timer(&udev->timeout, tcmu_device_timedout,
(unsigned long)udev);
- udev->pass_level = TCMU_PASS_ALL;
-
return &udev->se_dev;
}
}
enum {
- Opt_dev_config, Opt_dev_size, Opt_err, Opt_pass_level,
+ Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_err,
};
static match_table_t tokens = {
{Opt_dev_config, "dev_config=%s"},
{Opt_dev_size, "dev_size=%u"},
- {Opt_pass_level, "pass_level=%u"},
+ {Opt_hw_block_size, "hw_block_size=%u"},
{Opt_err, NULL}
};
char *orig, *ptr, *opts, *arg_p;
substring_t args[MAX_OPT_ARGS];
int ret = 0, token;
- int arg;
+ unsigned long tmp_ul;
opts = kstrdup(page, GFP_KERNEL);
if (!opts)
if (ret < 0)
pr_err("kstrtoul() failed for dev_size=\n");
break;
- case Opt_pass_level:
- match_int(args, &arg);
- if (arg >= TCMU_PASS_INVALID) {
- pr_warn("TCMU: Invalid pass_level: %d\n", arg);
+ case Opt_hw_block_size:
+ arg_p = match_strdup(&args[0]);
+ if (!arg_p) {
+ ret = -ENOMEM;
break;
}
-
- pr_debug("TCMU: Setting pass_level to %d\n", arg);
- udev->pass_level = arg;
+ ret = kstrtoul(arg_p, 0, &tmp_ul);
+ kfree(arg_p);
+ if (ret < 0) {
+ pr_err("kstrtoul() failed for hw_block_size=\n");
+ break;
+ }
+ if (!tmp_ul) {
+ pr_err("hw_block_size must be nonzero\n");
+ break;
+ }
+ dev->dev_attrib.hw_block_size = tmp_ul;
break;
default:
break;
bl = sprintf(b + bl, "Config: %s ",
udev->dev_config[0] ? udev->dev_config : "NULL");
- bl += sprintf(b + bl, "Size: %zu PassLevel: %u\n",
- udev->dev_size, udev->pass_level);
+ bl += sprintf(b + bl, "Size: %zu\n", udev->dev_size);
return bl;
}
dev->dev_attrib.block_size);
}
-static sense_reason_t
-tcmu_execute_rw(struct se_cmd *se_cmd, struct scatterlist *sgl, u32 sgl_nents,
- enum dma_data_direction data_direction)
-{
- int ret;
-
- ret = tcmu_queue_cmd(se_cmd);
-
- if (ret != 0)
- return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
- else
- return TCM_NO_SENSE;
-}
-
static sense_reason_t
tcmu_pass_op(struct se_cmd *se_cmd)
{
return TCM_NO_SENSE;
}
-static struct sbc_ops tcmu_sbc_ops = {
- .execute_rw = tcmu_execute_rw,
- .execute_sync_cache = tcmu_pass_op,
- .execute_write_same = tcmu_pass_op,
- .execute_write_same_unmap = tcmu_pass_op,
- .execute_unmap = tcmu_pass_op,
-};
-
static sense_reason_t
tcmu_parse_cdb(struct se_cmd *cmd)
{
- unsigned char *cdb = cmd->t_task_cdb;
- struct tcmu_dev *udev = TCMU_DEV(cmd->se_dev);
- sense_reason_t ret;
-
- switch (udev->pass_level) {
- case TCMU_PASS_ALL:
- /* We're just like pscsi, then */
- /*
- * For REPORT LUNS we always need to emulate the response, for everything
- * else, pass it up.
- */
- switch (cdb[0]) {
- case REPORT_LUNS:
- cmd->execute_cmd = spc_emulate_report_luns;
- break;
- case READ_6:
- case READ_10:
- case READ_12:
- case READ_16:
- case WRITE_6:
- case WRITE_10:
- case WRITE_12:
- case WRITE_16:
- case WRITE_VERIFY:
- cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
- /* FALLTHROUGH */
- default:
- cmd->execute_cmd = tcmu_pass_op;
- }
- ret = TCM_NO_SENSE;
- break;
- case TCMU_PASS_IO:
- ret = sbc_parse_cdb(cmd, &tcmu_sbc_ops);
- break;
- default:
- pr_err("Unknown tcm-user pass level %d\n", udev->pass_level);
- ret = TCM_CHECK_CONDITION_ABORT_CMD;
- }
-
- return ret;
+ return passthrough_parse_cdb(cmd, tcmu_pass_op);
}
-DEF_TB_DEFAULT_ATTRIBS(tcmu);
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_pi_prot_type);
+TB_DEV_ATTR_RO(tcmu, hw_pi_prot_type);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_block_size);
+TB_DEV_ATTR_RO(tcmu, hw_block_size);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_max_sectors);
+TB_DEV_ATTR_RO(tcmu, hw_max_sectors);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_queue_depth);
+TB_DEV_ATTR_RO(tcmu, hw_queue_depth);
static struct configfs_attribute *tcmu_backend_dev_attrs[] = {
- &tcmu_dev_attrib_emulate_model_alias.attr,
- &tcmu_dev_attrib_emulate_dpo.attr,
- &tcmu_dev_attrib_emulate_fua_write.attr,
- &tcmu_dev_attrib_emulate_fua_read.attr,
- &tcmu_dev_attrib_emulate_write_cache.attr,
- &tcmu_dev_attrib_emulate_ua_intlck_ctrl.attr,
- &tcmu_dev_attrib_emulate_tas.attr,
- &tcmu_dev_attrib_emulate_tpu.attr,
- &tcmu_dev_attrib_emulate_tpws.attr,
- &tcmu_dev_attrib_emulate_caw.attr,
- &tcmu_dev_attrib_emulate_3pc.attr,
- &tcmu_dev_attrib_pi_prot_type.attr,
&tcmu_dev_attrib_hw_pi_prot_type.attr,
- &tcmu_dev_attrib_pi_prot_format.attr,
- &tcmu_dev_attrib_enforce_pr_isids.attr,
- &tcmu_dev_attrib_is_nonrot.attr,
- &tcmu_dev_attrib_emulate_rest_reord.attr,
- &tcmu_dev_attrib_force_pr_aptpl.attr,
&tcmu_dev_attrib_hw_block_size.attr,
- &tcmu_dev_attrib_block_size.attr,
&tcmu_dev_attrib_hw_max_sectors.attr,
- &tcmu_dev_attrib_optimal_sectors.attr,
&tcmu_dev_attrib_hw_queue_depth.attr,
- &tcmu_dev_attrib_queue_depth.attr,
- &tcmu_dev_attrib_max_unmap_lba_count.attr,
- &tcmu_dev_attrib_max_unmap_block_desc_count.attr,
- &tcmu_dev_attrib_unmap_granularity.attr,
- &tcmu_dev_attrib_unmap_granularity_alignment.attr,
- &tcmu_dev_attrib_max_write_same_len.attr,
NULL,
};
.inquiry_prod = "USER",
.inquiry_rev = TCMU_VERSION,
.owner = THIS_MODULE,
- .transport_type = TRANSPORT_PLUGIN_VHBA_PDEV,
+ .transport_flags = TRANSPORT_FLAG_PASSTHROUGH,
.attach_hba = tcmu_attach_hba,
.detach_hba = tcmu_detach_hba,
.alloc_device = tcmu_alloc_device,
bool src)
{
struct se_device *se_dev;
- struct configfs_subsystem *subsys = target_core_subsystem[0];
unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN], *dev_wwn;
int rc;
" se_dev\n", xop->src_dev);
}
- rc = configfs_depend_item(subsys,
- &se_dev->dev_group.cg_item);
+ rc = target_depend_item(&se_dev->dev_group.cg_item);
if (rc != 0) {
pr_err("configfs_depend_item attempt failed:"
" %d for se_dev: %p\n", rc, se_dev);
return rc;
}
- pr_debug("Called configfs_depend_item for subsys: %p se_dev: %p"
- " se_dev->se_dev_group: %p\n", subsys, se_dev,
+ pr_debug("Called configfs_depend_item for se_dev: %p"
+ " se_dev->se_dev_group: %p\n", se_dev,
&se_dev->dev_group);
mutex_unlock(&g_device_mutex);
static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop)
{
- struct configfs_subsystem *subsys = target_core_subsystem[0];
struct se_device *remote_dev;
if (xop->op_origin == XCOL_SOURCE_RECV_OP)
else
remote_dev = xop->src_dev;
- pr_debug("Calling configfs_undepend_item for subsys: %p"
+ pr_debug("Calling configfs_undepend_item for"
" remote_dev: %p remote_dev->dev_group: %p\n",
- subsys, remote_dev, &remote_dev->dev_group.cg_item);
+ remote_dev, &remote_dev->dev_group.cg_item);
- configfs_undepend_item(subsys, &remote_dev->dev_group.cg_item);
+ target_undepend_item(&remote_dev->dev_group.cg_item);
}
static void xcopy_pt_release_cmd(struct se_cmd *se_cmd)
.is_valid_shift = 10,
.temp_shift = 0,
.temp_mask = 0x3ff,
- .coef_b = 1169498786UL,
- .coef_m = 2000000UL,
- .coef_div = 4289,
+ .coef_b = 2931108200UL,
+ .coef_m = 5000000UL,
+ .coef_div = 10502,
.inverted = true,
};
}
+struct pkg_cstate_info {
+ bool skip;
+ int msr_index;
+ int cstate_id;
+};
+
+#define PKG_CSTATE_INIT(id) { \
+ .msr_index = MSR_PKG_C##id##_RESIDENCY, \
+ .cstate_id = id \
+ }
+
+static struct pkg_cstate_info pkg_cstates[] = {
+ PKG_CSTATE_INIT(2),
+ PKG_CSTATE_INIT(3),
+ PKG_CSTATE_INIT(6),
+ PKG_CSTATE_INIT(7),
+ PKG_CSTATE_INIT(8),
+ PKG_CSTATE_INIT(9),
+ PKG_CSTATE_INIT(10),
+ {NULL},
+};
+
static bool has_pkg_state_counter(void)
{
- u64 tmp;
- return !rdmsrl_safe(MSR_PKG_C2_RESIDENCY, &tmp) ||
- !rdmsrl_safe(MSR_PKG_C3_RESIDENCY, &tmp) ||
- !rdmsrl_safe(MSR_PKG_C6_RESIDENCY, &tmp) ||
- !rdmsrl_safe(MSR_PKG_C7_RESIDENCY, &tmp);
+ u64 val;
+ struct pkg_cstate_info *info = pkg_cstates;
+
+ /* check if any one of the counter msrs exists */
+ while (info->msr_index) {
+ if (!rdmsrl_safe(info->msr_index, &val))
+ return true;
+ info++;
+ }
+
+ return false;
}
static u64 pkg_state_counter(void)
{
u64 val;
u64 count = 0;
-
- static bool skip_c2;
- static bool skip_c3;
- static bool skip_c6;
- static bool skip_c7;
-
- if (!skip_c2) {
- if (!rdmsrl_safe(MSR_PKG_C2_RESIDENCY, &val))
- count += val;
- else
- skip_c2 = true;
- }
-
- if (!skip_c3) {
- if (!rdmsrl_safe(MSR_PKG_C3_RESIDENCY, &val))
- count += val;
- else
- skip_c3 = true;
- }
-
- if (!skip_c6) {
- if (!rdmsrl_safe(MSR_PKG_C6_RESIDENCY, &val))
- count += val;
- else
- skip_c6 = true;
- }
-
- if (!skip_c7) {
- if (!rdmsrl_safe(MSR_PKG_C7_RESIDENCY, &val))
- count += val;
- else
- skip_c7 = true;
+ struct pkg_cstate_info *info = pkg_cstates;
+
+ while (info->msr_index) {
+ if (!info->skip) {
+ if (!rdmsrl_safe(info->msr_index, &val))
+ count += val;
+ else
+ info->skip = true;
+ }
+ info++;
}
return count;
};
/* runs on Nehalem and later */
-static const struct x86_cpu_id intel_powerclamp_ids[] = {
+static const struct x86_cpu_id intel_powerclamp_ids[] __initconst = {
{ X86_VENDOR_INTEL, 6, 0x1a},
{ X86_VENDOR_INTEL, 6, 0x1c},
{ X86_VENDOR_INTEL, 6, 0x1e},
{ X86_VENDOR_INTEL, 6, 0x46},
{ X86_VENDOR_INTEL, 6, 0x4c},
{ X86_VENDOR_INTEL, 6, 0x4d},
+ { X86_VENDOR_INTEL, 6, 0x4f},
{ X86_VENDOR_INTEL, 6, 0x56},
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids);
-static int powerclamp_probe(void)
+static int __init powerclamp_probe(void)
{
if (!x86_match_cpu(intel_powerclamp_ids)) {
pr_err("Intel powerclamp does not run on family %d model %d\n",
debugfs_remove_recursive(debug_dir);
}
-static int powerclamp_init(void)
+static int __init powerclamp_init(void)
{
int retval;
int bitmap_size;
}
module_init(powerclamp_init);
-static void powerclamp_exit(void)
+static void __exit powerclamp_exit(void)
{
unregister_hotcpu_notifier(&powerclamp_cpu_notifier);
end_power_clamp();
thermal->pclk = devm_clk_get(&pdev->dev, "apb_pclk");
if (IS_ERR(thermal->pclk)) {
- error = PTR_ERR(thermal->clk);
+ error = PTR_ERR(thermal->pclk);
dev_err(&pdev->dev, "failed to get apb_pclk clock: %d\n",
error);
return error;
static inline bool of_thermal_is_trip_valid(struct thermal_zone_device *tz,
int trip)
{
- return 0;
+ return false;
}
static inline const struct thermal_trip *
of_thermal_get_trip_points(struct thermal_zone_device *tz)
TI_BANDGAP_FEATURE_FREEZE_BIT |
TI_BANDGAP_FEATURE_TALERT |
TI_BANDGAP_FEATURE_COUNTER_DELAY |
- TI_BANDGAP_FEATURE_HISTORY_BUFFER,
+ TI_BANDGAP_FEATURE_HISTORY_BUFFER |
+ TI_BANDGAP_FEATURE_ERRATA_814,
.fclock_name = "l3instr_ts_gclk_div",
.div_ck_name = "l3instr_ts_gclk_div",
.conv_table = dra752_adc_to_temp,
TI_BANDGAP_FEATURE_FREEZE_BIT |
TI_BANDGAP_FEATURE_TALERT |
TI_BANDGAP_FEATURE_COUNTER_DELAY |
- TI_BANDGAP_FEATURE_HISTORY_BUFFER,
+ TI_BANDGAP_FEATURE_HISTORY_BUFFER |
+ TI_BANDGAP_FEATURE_ERRATA_813,
.fclock_name = "l3instr_ts_gclk_div",
.div_ck_name = "l3instr_ts_gclk_div",
.conv_table = omap5430_adc_to_temp,
return ret;
}
+/**
+ * ti_errata814_bandgap_read_temp() - helper function to read dra7 sensor temperature
+ * @bgp: pointer to ti_bandgap structure
+ * @reg: desired register (offset) to be read
+ *
+ * Function to read dra7 bandgap sensor temperature. This is done separately
+ * so as to workaround the errata "Bandgap Temperature read Dtemp can be
+ * corrupted" - Errata ID: i814".
+ * Read accesses to registers listed below can be corrupted due to incorrect
+ * resynchronization between clock domains.
+ * Read access to registers below can be corrupted :
+ * CTRL_CORE_DTEMP_MPU/GPU/CORE/DSPEVE/IVA_n (n = 0 to 4)
+ * CTRL_CORE_TEMP_SENSOR_MPU/GPU/CORE/DSPEVE/IVA_n
+ *
+ * Return: the register value.
+ */
+static u32 ti_errata814_bandgap_read_temp(struct ti_bandgap *bgp, u32 reg)
+{
+ u32 val1, val2;
+
+ val1 = ti_bandgap_readl(bgp, reg);
+ val2 = ti_bandgap_readl(bgp, reg);
+
+ /* If both times we read the same value then that is right */
+ if (val1 == val2)
+ return val1;
+
+ /* if val1 and val2 are different read it third time */
+ return ti_bandgap_readl(bgp, reg);
+}
+
/**
* ti_bandgap_read_temp() - helper function to read sensor temperature
* @bgp: pointer to ti_bandgap structure
}
/* read temperature */
- temp = ti_bandgap_readl(bgp, reg);
+ if (TI_BANDGAP_HAS(bgp, ERRATA_814))
+ temp = ti_errata814_bandgap_read_temp(bgp, reg);
+ else
+ temp = ti_bandgap_readl(bgp, reg);
+
temp &= tsr->bgap_dtemp_mask;
if (TI_BANDGAP_HAS(bgp, FREEZE_BIT))
{
struct temp_sensor_data *ts_data = bgp->conf->sensors[id].ts_data;
struct temp_sensor_registers *tsr;
- u32 thresh_val, reg_val, t_hot, t_cold;
+ u32 thresh_val, reg_val, t_hot, t_cold, ctrl;
int err = 0;
tsr = bgp->conf->sensors[id].registers;
~(tsr->threshold_thot_mask | tsr->threshold_tcold_mask);
reg_val |= (t_hot << __ffs(tsr->threshold_thot_mask)) |
(t_cold << __ffs(tsr->threshold_tcold_mask));
+
+ /**
+ * Errata i813:
+ * Spurious Thermal Alert: Talert can happen randomly while the device
+ * remains under the temperature limit defined for this event to trig.
+ * This spurious event is caused by a incorrect re-synchronization
+ * between clock domains. The comparison between configured threshold
+ * and current temperature value can happen while the value is
+ * transitioning (metastable), thus causing inappropriate event
+ * generation. No spurious event occurs as long as the threshold value
+ * stays unchanged. Spurious event can be generated while a thermal
+ * alert threshold is modified in
+ * CONTROL_BANDGAP_THRESHOLD_MPU/GPU/CORE/DSPEVE/IVA_n.
+ */
+
+ if (TI_BANDGAP_HAS(bgp, ERRATA_813)) {
+ /* Mask t_hot and t_cold events at the IP Level */
+ ctrl = ti_bandgap_readl(bgp, tsr->bgap_mask_ctrl);
+
+ if (hot)
+ ctrl &= ~tsr->mask_hot_mask;
+ else
+ ctrl &= ~tsr->mask_cold_mask;
+
+ ti_bandgap_writel(bgp, ctrl, tsr->bgap_mask_ctrl);
+ }
+
+ /* Write the threshold value */
ti_bandgap_writel(bgp, reg_val, tsr->bgap_threshold);
+ if (TI_BANDGAP_HAS(bgp, ERRATA_813)) {
+ /* Unmask t_hot and t_cold events at the IP Level */
+ ctrl = ti_bandgap_readl(bgp, tsr->bgap_mask_ctrl);
+ if (hot)
+ ctrl |= tsr->mask_hot_mask;
+ else
+ ctrl |= tsr->mask_cold_mask;
+
+ ti_bandgap_writel(bgp, ctrl, tsr->bgap_mask_ctrl);
+ }
+
if (err) {
dev_err(bgp->dev, "failed to reprogram thot threshold\n");
err = -EIO;
* TI_BANDGAP_FEATURE_HISTORY_BUFFER - used when the bandgap device features
* a history buffer of temperatures.
*
+ * TI_BANDGAP_FEATURE_ERRATA_814 - used to workaorund when the bandgap device
+ * has Errata 814
+ * TI_BANDGAP_FEATURE_ERRATA_813 - used to workaorund when the bandgap device
+ * has Errata 813
* TI_BANDGAP_HAS(b, f) - macro to check if a bandgap device is capable of a
* specific feature (above) or not. Return non-zero, if yes.
*/
#define TI_BANDGAP_FEATURE_FREEZE_BIT BIT(7)
#define TI_BANDGAP_FEATURE_COUNTER_DELAY BIT(8)
#define TI_BANDGAP_FEATURE_HISTORY_BUFFER BIT(9)
+#define TI_BANDGAP_FEATURE_ERRATA_814 BIT(10)
+#define TI_BANDGAP_FEATURE_ERRATA_813 BIT(11)
#define TI_BANDGAP_HAS(b, f) \
((b)->conf->features & TI_BANDGAP_FEATURE_ ## f)
return -ENOMEM;
}
- info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0);
+ info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false);
info->vtermno = HVC_COOKIE;
spin_lock(&xencons_lock);
static inline void mips_ejtag_fdc_write(struct mips_ejtag_fdc_tty *priv,
unsigned int offs, unsigned int data)
{
- iowrite32(data, priv->reg + offs);
+ __raw_writel(data, priv->reg + offs);
}
static inline unsigned int mips_ejtag_fdc_read(struct mips_ejtag_fdc_tty *priv,
unsigned int offs)
{
- return ioread32(priv->reg + offs);
+ return __raw_readl(priv->reg + offs);
}
/* Encoding of byte stream in FDC words */
s += inc[word.bytes - 1];
/* Busy wait until there's space in fifo */
- while (ioread32(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
+ while (__raw_readl(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
;
- iowrite32(word.word, regs + REG_FDTX(c->index));
+ __raw_writel(word.word, regs + REG_FDTX(c->index));
}
out:
local_irq_restore(flags);
/* Read next word from KGDB channel */
do {
- stat = ioread32(regs + REG_FDSTAT);
+ stat = __raw_readl(regs + REG_FDSTAT);
/* No data waiting? */
if (stat & REG_FDSTAT_RXE)
/* Read next word */
channel = (stat & REG_FDSTAT_RXCHAN) >>
REG_FDSTAT_RXCHAN_SHIFT;
- data = ioread32(regs + REG_FDRX);
+ data = __raw_readl(regs + REG_FDRX);
} while (channel != CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN);
/* Decode into rbuf */
return;
/* Busy wait until there's space in fifo */
- while (ioread32(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
+ while (__raw_readl(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
;
- iowrite32(word.word, regs + REG_FDTX(CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN));
+ __raw_writel(word.word,
+ regs + REG_FDTX(CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN));
}
/* flush the whole write buffer to the TX FIFO */
return gsmtty_modem_update(dlci, encode);
}
-static void gsmtty_remove(struct tty_driver *driver, struct tty_struct *tty)
+static void gsmtty_cleanup(struct tty_struct *tty)
{
struct gsm_dlci *dlci = tty->driver_data;
struct gsm_mux *gsm = dlci->gsm;
dlci_put(dlci);
dlci_put(gsm->dlci[0]);
mux_put(gsm);
- driver->ttys[tty->index] = NULL;
}
/* Virtual ttys for the demux */
.tiocmget = gsmtty_tiocmget,
.tiocmset = gsmtty_tiocmset,
.break_ctl = gsmtty_break_ctl,
- .remove = gsmtty_remove,
+ .cleanup = gsmtty_cleanup,
};
add_wait_queue(&tty->read_wait, &wait);
for (;;) {
- if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) {
+ if (test_bit(TTY_OTHER_DONE, &tty->flags)) {
ret = -EIO;
break;
}
/* set bits for operations that won't block */
if (n_hdlc->rx_buf_list.head)
mask |= POLLIN | POLLRDNORM; /* readable */
- if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
+ if (test_bit(TTY_OTHER_DONE, &tty->flags))
mask |= POLLHUP;
if (tty_hung_up_p(filp))
mask |= POLLHUP;
return put_user(x, ptr);
}
+static inline int tty_copy_to_user(struct tty_struct *tty,
+ void __user *to,
+ const void *from,
+ unsigned long n)
+{
+ struct n_tty_data *ldata = tty->disc_data;
+
+ tty_audit_add_data(tty, to, n, ldata->icanon);
+ return copy_to_user(to, from, n);
+}
+
/**
* n_tty_kick_worker - start input worker (if required)
* @tty: terminal
return ldata->commit_head - ldata->read_tail >= amt;
}
+static inline int check_other_done(struct tty_struct *tty)
+{
+ int done = test_bit(TTY_OTHER_DONE, &tty->flags);
+ if (done) {
+ /* paired with cmpxchg() in check_other_closed(); ensures
+ * read buffer head index is not stale
+ */
+ smp_mb__after_atomic();
+ }
+ return done;
+}
+
/**
* copy_from_read_buf - copy read data directly
* @tty: terminal device
size = N_TTY_BUF_SIZE - tail;
n = eol - tail;
- if (n > 4096)
- n += 4096;
+ if (n > N_TTY_BUF_SIZE)
+ n += N_TTY_BUF_SIZE;
n += found;
c = n;
__func__, eol, found, n, c, size, more);
if (n > size) {
- ret = copy_to_user(*b, read_buf_addr(ldata, tail), size);
+ ret = tty_copy_to_user(tty, *b, read_buf_addr(ldata, tail), size);
if (ret)
return -EFAULT;
- ret = copy_to_user(*b + size, ldata->read_buf, n - size);
+ ret = tty_copy_to_user(tty, *b + size, ldata->read_buf, n - size);
} else
- ret = copy_to_user(*b, read_buf_addr(ldata, tail), n);
+ ret = tty_copy_to_user(tty, *b, read_buf_addr(ldata, tail), n);
if (ret)
return -EFAULT;
struct n_tty_data *ldata = tty->disc_data;
unsigned char __user *b = buf;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
- int c;
+ int c, done;
int minimum, time;
ssize_t retval = 0;
long timeout;
((minimum - (b - buf)) >= 1))
ldata->minimum_to_wake = (minimum - (b - buf));
+ done = check_other_done(tty);
+
if (!input_available_p(tty, 0)) {
- if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) {
+ if (done) {
retval = -EIO;
break;
}
poll_wait(file, &tty->read_wait, wait);
poll_wait(file, &tty->write_wait, wait);
+ if (check_other_done(tty))
+ mask |= POLLHUP;
if (input_available_p(tty, 1))
mask |= POLLIN | POLLRDNORM;
if (tty->packet && tty->link->ctrl_status)
mask |= POLLPRI | POLLIN | POLLRDNORM;
- if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
- mask |= POLLHUP;
if (tty_hung_up_p(file))
mask |= POLLHUP;
if (!(mask & (POLLHUP | POLLIN | POLLRDNORM))) {
/* Review - krefs on tty_link ?? */
if (!tty->link)
return;
- tty_flush_to_ldisc(tty->link);
set_bit(TTY_OTHER_CLOSED, &tty->link->flags);
- wake_up_interruptible(&tty->link->read_wait);
+ tty_flip_buffer_push(tty->link->port);
wake_up_interruptible(&tty->link->write_wait);
if (tty->driver->subtype == PTY_TYPE_MASTER) {
set_bit(TTY_OTHER_CLOSED, &tty->flags);
goto out;
clear_bit(TTY_IO_ERROR, &tty->flags);
+ /* TTY_OTHER_CLOSED must be cleared before TTY_OTHER_DONE */
clear_bit(TTY_OTHER_CLOSED, &tty->link->flags);
+ clear_bit(TTY_OTHER_DONE, &tty->link->flags);
set_bit(TTY_THROTTLED, &tty->flags);
return 0;
return IRQ_NONE;
}
+#ifdef CONFIG_SERIAL_8250_DMA
+static int omap_8250_dma_handle_irq(struct uart_port *port);
+#endif
+
+static irqreturn_t omap8250_irq(int irq, void *dev_id)
+{
+ struct uart_port *port = dev_id;
+ struct uart_8250_port *up = up_to_u8250p(port);
+ unsigned int iir;
+ int ret;
+
+#ifdef CONFIG_SERIAL_8250_DMA
+ if (up->dma) {
+ ret = omap_8250_dma_handle_irq(port);
+ return IRQ_RETVAL(ret);
+ }
+#endif
+
+ serial8250_rpm_get(up);
+ iir = serial_port_in(port, UART_IIR);
+ ret = serial8250_handle_irq(port, iir);
+ serial8250_rpm_put(up);
+
+ return IRQ_RETVAL(ret);
+}
+
static int omap_8250_startup(struct uart_port *port)
{
- struct uart_8250_port *up =
- container_of(port, struct uart_8250_port, port);
+ struct uart_8250_port *up = up_to_u8250p(port);
struct omap8250_priv *priv = port->private_data;
-
int ret;
if (priv->wakeirq) {
pm_runtime_get_sync(port->dev);
- ret = serial8250_do_startup(port);
- if (ret)
+ up->mcr = 0;
+ serial_out(up, UART_FCR, UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT);
+
+ serial_out(up, UART_LCR, UART_LCR_WLEN8);
+
+ up->lsr_saved_flags = 0;
+ up->msr_saved_flags = 0;
+
+ if (up->dma) {
+ ret = serial8250_request_dma(up);
+ if (ret) {
+ dev_warn_ratelimited(port->dev,
+ "failed to request DMA\n");
+ up->dma = NULL;
+ }
+ }
+
+ ret = request_irq(port->irq, omap8250_irq, IRQF_SHARED,
+ dev_name(port->dev), port);
+ if (ret < 0)
goto err;
+ up->ier = UART_IER_RLSI | UART_IER_RDI;
+ serial_out(up, UART_IER, up->ier);
+
#ifdef CONFIG_PM
up->capabilities |= UART_CAP_RPM;
#endif
static void omap_8250_shutdown(struct uart_port *port)
{
- struct uart_8250_port *up =
- container_of(port, struct uart_8250_port, port);
+ struct uart_8250_port *up = up_to_u8250p(port);
struct omap8250_priv *priv = port->private_data;
flush_work(&priv->qos_work);
pm_runtime_get_sync(port->dev);
serial_out(up, UART_OMAP_WER, 0);
- serial8250_do_shutdown(port);
+
+ up->ier = 0;
+ serial_out(up, UART_IER, 0);
+
+ if (up->dma)
+ serial8250_release_dma(up);
+
+ /*
+ * Disable break condition and FIFOs
+ */
+ if (up->lcr & UART_LCR_SBC)
+ serial_out(up, UART_LCR, up->lcr & ~UART_LCR_SBC);
+ serial_out(up, UART_FCR, UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT);
pm_runtime_mark_last_busy(port->dev);
pm_runtime_put_autosuspend(port->dev);
+ free_irq(port->irq, port);
if (priv->wakeirq)
free_irq(priv->wakeirq, port);
}
}
#endif
+static int omap8250_no_handle_irq(struct uart_port *port)
+{
+ /* IRQ has not been requested but handling irq? */
+ WARN_ONCE(1, "Unexpected irq handling before port startup\n");
+ return 0;
+}
+
static int omap8250_probe(struct platform_device *pdev)
{
struct resource *regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
pm_runtime_get_sync(&pdev->dev);
omap_serial_fill_features_erratas(&up, priv);
+ up.port.handle_irq = omap8250_no_handle_irq;
#ifdef CONFIG_SERIAL_8250_DMA
if (pdev->dev.of_node) {
/*
ret = of_property_count_strings(pdev->dev.of_node, "dma-names");
if (ret == 2) {
up.dma = &priv->omap8250_dma;
- up.port.handle_irq = omap_8250_dma_handle_irq;
priv->omap8250_dma.fn = the_no_dma_filter_fn;
priv->omap8250_dma.tx_dma = omap_8250_tx_dma;
priv->omap8250_dma.rx_dma = omap_8250_rx_dma;
/*
* Transmit a character
- * There must be at least one free entry in the TX FIFO to accept the char.
*
- * Returns true if the FIFO might have space in it afterwards;
- * returns false if the FIFO definitely became full.
+ * Returns true if the character was successfully queued to the FIFO.
+ * Returns false otherwise.
*/
static bool pl011_tx_char(struct uart_amba_port *uap, unsigned char c)
{
+ if (readw(uap->port.membase + UART01x_FR) & UART01x_FR_TXFF)
+ return false; /* unable to transmit character */
+
writew(c, uap->port.membase + UART01x_DR);
uap->port.icount.tx++;
- if (likely(uap->tx_irq_seen > 1))
- return true;
-
- return !(readw(uap->port.membase + UART01x_FR) & UART01x_FR_TXFF);
+ return true;
}
static bool pl011_tx_chars(struct uart_amba_port *uap)
return false;
if (uap->port.x_char) {
- pl011_tx_char(uap, uap->port.x_char);
+ if (!pl011_tx_char(uap, uap->port.x_char))
+ goto done;
uap->port.x_char = 0;
--count;
}
writew(uap->vendor->ifls, uap->port.membase + UART011_IFLS);
+ /* Assume that TX IRQ doesn't work until we see one: */
+ uap->tx_irq_seen = 0;
+
spin_lock_irq(&uap->port.lock);
/* restore RTS and DTR */
spin_lock_irq(&uap->port.lock);
uap->im = 0;
writew(uap->im, uap->port.membase + UART011_IMSC);
- writew(0xffff & ~UART011_TXIS, uap->port.membase + UART011_ICR);
+ writew(0xffff, uap->port.membase + UART011_ICR);
spin_unlock_irq(&uap->port.lock);
pl011_dma_shutdown(uap);
return 0;
err = setup_earlycon(buf);
- if (err == -ENOENT) {
- pr_warn("no match for %s\n", buf);
- err = 0;
- } else if (err == -EALREADY) {
- pr_warn("already registered\n");
- err = 0;
- }
+ if (err == -ENOENT || err == -EALREADY)
+ return 0;
return err;
}
early_param("earlycon", param_setup_earlycon);
status = dmaengine_tx_status(chan, (dma_cookie_t)0, &state);
count = RX_BUF_SIZE - state.residue;
+
+ if (readl(sport->port.membase + USR2) & USR2_IDLE) {
+ /* In condition [3] the SDMA counted up too early */
+ count--;
+
+ writel(USR2_IDLE, sport->port.membase + USR2);
+ }
+
dev_dbg(sport->port.dev, "We get %d bytes.\n", count);
if (count) {
err_add_port:
pm_runtime_put(&pdev->dev);
pm_runtime_disable(&pdev->dev);
+ pm_qos_remove_request(&up->pm_qos_request);
+ device_init_wakeup(up->dev, false);
err_rs485:
err_port_line:
return ret;
#define TTY_BUFFER_PAGE (((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~0xFF)
+/*
+ * If all tty flip buffers have been processed by flush_to_ldisc() or
+ * dropped by tty_buffer_flush(), check if the linked pty has been closed.
+ * If so, wake the reader/poll to process
+ */
+static inline void check_other_closed(struct tty_struct *tty)
+{
+ unsigned long flags, old;
+
+ /* transition from TTY_OTHER_CLOSED => TTY_OTHER_DONE must be atomic */
+ for (flags = ACCESS_ONCE(tty->flags);
+ test_bit(TTY_OTHER_CLOSED, &flags);
+ ) {
+ old = flags;
+ __set_bit(TTY_OTHER_DONE, &flags);
+ flags = cmpxchg(&tty->flags, old, flags);
+ if (old == flags) {
+ wake_up_interruptible(&tty->read_wait);
+ break;
+ }
+ }
+}
/**
* tty_buffer_lock_exclusive - gain exclusive access to buffer
if (ld && ld->ops->flush_buffer)
ld->ops->flush_buffer(tty);
+ check_other_closed(tty);
+
atomic_dec(&buf->priority);
mutex_unlock(&buf->lock);
}
smp_rmb();
count = head->commit - head->read;
if (!count) {
- if (next == NULL)
+ if (next == NULL) {
+ check_other_closed(tty);
break;
+ }
buf->head = next;
tty_buffer_free(port, head);
continue;
tty_ldisc_deref(disc);
}
-/**
- * tty_flush_to_ldisc
- * @tty: tty to push
- *
- * Push the terminal flip buffers to the line discipline.
- *
- * Must not be called from IRQ context.
- */
-void tty_flush_to_ldisc(struct tty_struct *tty)
-{
- flush_work(&tty->port->buf.work);
-}
-
/**
* tty_flip_buffer_push - terminal
* @port: tty port to push
char buf[32];
int ret;
- if (copy_from_user(buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
+ count = min_t(size_t, sizeof(buf) - 1, count);
+ if (copy_from_user(buf, ubuf, count))
return -EFAULT;
+ /* sscanf requires a zero terminated string */
+ buf[count] = '\0';
+
if (sscanf(buf, "%u", &mode) != 1)
return -EINVAL;
{ USB_DEVICE(0x04f3, 0x010c), .driver_info =
USB_QUIRK_DEVICE_QUALIFIER },
+ { USB_DEVICE(0x04f3, 0x0125), .driver_info =
+ USB_QUIRK_DEVICE_QUALIFIER },
+
{ USB_DEVICE(0x04f3, 0x016f), .driver_info =
USB_QUIRK_DEVICE_QUALIFIER },
#define DWC3_DGCMD_SET_ENDPOINT_NRDY 0x0c
#define DWC3_DGCMD_RUN_SOC_BUS_LOOPBACK 0x10
-#define DWC3_DGCMD_STATUS(n) (((n) >> 15) & 1)
+#define DWC3_DGCMD_STATUS(n) (((n) >> 12) & 0x0F)
#define DWC3_DGCMD_CMDACT (1 << 10)
#define DWC3_DGCMD_CMDIOC (1 << 8)
#define DWC3_DEPCMD_PARAM_SHIFT 16
#define DWC3_DEPCMD_PARAM(x) ((x) << DWC3_DEPCMD_PARAM_SHIFT)
#define DWC3_DEPCMD_GET_RSC_IDX(x) (((x) >> DWC3_DEPCMD_PARAM_SHIFT) & 0x7f)
-#define DWC3_DEPCMD_STATUS(x) (((x) >> 15) & 1)
+#define DWC3_DEPCMD_STATUS(x) (((x) >> 12) & 0x0F)
#define DWC3_DEPCMD_HIPRI_FORCERM (1 << 11)
#define DWC3_DEPCMD_CMDACT (1 << 10)
#define DWC3_DEPCMD_CMDIOC (1 << 8)
#define USBOTGSS_IRQENABLE_SET_MISC 0x003c
#define USBOTGSS_IRQENABLE_CLR_MISC 0x0040
#define USBOTGSS_IRQMISC_OFFSET 0x03fc
-#define USBOTGSS_UTMI_OTG_CTRL 0x0080
-#define USBOTGSS_UTMI_OTG_STATUS 0x0084
+#define USBOTGSS_UTMI_OTG_STATUS 0x0080
+#define USBOTGSS_UTMI_OTG_CTRL 0x0084
#define USBOTGSS_UTMI_OTG_OFFSET 0x0480
#define USBOTGSS_TXFIFO_DEPTH 0x0508
#define USBOTGSS_RXFIFO_DEPTH 0x050c
#define USBOTGSS_IRQMISC_DISCHRGVBUS_FALL (1 << 3)
#define USBOTGSS_IRQMISC_IDPULLUP_FALL (1 << 0)
-/* UTMI_OTG_CTRL REGISTER */
-#define USBOTGSS_UTMI_OTG_CTRL_DRVVBUS (1 << 5)
-#define USBOTGSS_UTMI_OTG_CTRL_CHRGVBUS (1 << 4)
-#define USBOTGSS_UTMI_OTG_CTRL_DISCHRGVBUS (1 << 3)
-#define USBOTGSS_UTMI_OTG_CTRL_IDPULLUP (1 << 0)
-
/* UTMI_OTG_STATUS REGISTER */
-#define USBOTGSS_UTMI_OTG_STATUS_SW_MODE (1 << 31)
-#define USBOTGSS_UTMI_OTG_STATUS_POWERPRESENT (1 << 9)
-#define USBOTGSS_UTMI_OTG_STATUS_TXBITSTUFFENABLE (1 << 8)
-#define USBOTGSS_UTMI_OTG_STATUS_IDDIG (1 << 4)
-#define USBOTGSS_UTMI_OTG_STATUS_SESSEND (1 << 3)
-#define USBOTGSS_UTMI_OTG_STATUS_SESSVALID (1 << 2)
-#define USBOTGSS_UTMI_OTG_STATUS_VBUSVALID (1 << 1)
+#define USBOTGSS_UTMI_OTG_STATUS_DRVVBUS (1 << 5)
+#define USBOTGSS_UTMI_OTG_STATUS_CHRGVBUS (1 << 4)
+#define USBOTGSS_UTMI_OTG_STATUS_DISCHRGVBUS (1 << 3)
+#define USBOTGSS_UTMI_OTG_STATUS_IDPULLUP (1 << 0)
+
+/* UTMI_OTG_CTRL REGISTER */
+#define USBOTGSS_UTMI_OTG_CTRL_SW_MODE (1 << 31)
+#define USBOTGSS_UTMI_OTG_CTRL_POWERPRESENT (1 << 9)
+#define USBOTGSS_UTMI_OTG_CTRL_TXBITSTUFFENABLE (1 << 8)
+#define USBOTGSS_UTMI_OTG_CTRL_IDDIG (1 << 4)
+#define USBOTGSS_UTMI_OTG_CTRL_SESSEND (1 << 3)
+#define USBOTGSS_UTMI_OTG_CTRL_SESSVALID (1 << 2)
+#define USBOTGSS_UTMI_OTG_CTRL_VBUSVALID (1 << 1)
struct dwc3_omap {
struct device *dev;
int irq;
void __iomem *base;
- u32 utmi_otg_status;
+ u32 utmi_otg_ctrl;
u32 utmi_otg_offset;
u32 irqmisc_offset;
u32 irq_eoi_offset;
writel(value, base + offset);
}
-static u32 dwc3_omap_read_utmi_status(struct dwc3_omap *omap)
+static u32 dwc3_omap_read_utmi_ctrl(struct dwc3_omap *omap)
{
- return dwc3_omap_readl(omap->base, USBOTGSS_UTMI_OTG_STATUS +
+ return dwc3_omap_readl(omap->base, USBOTGSS_UTMI_OTG_CTRL +
omap->utmi_otg_offset);
}
-static void dwc3_omap_write_utmi_status(struct dwc3_omap *omap, u32 value)
+static void dwc3_omap_write_utmi_ctrl(struct dwc3_omap *omap, u32 value)
{
- dwc3_omap_writel(omap->base, USBOTGSS_UTMI_OTG_STATUS +
+ dwc3_omap_writel(omap->base, USBOTGSS_UTMI_OTG_CTRL +
omap->utmi_otg_offset, value);
}
}
}
- val = dwc3_omap_read_utmi_status(omap);
- val &= ~(USBOTGSS_UTMI_OTG_STATUS_IDDIG
- | USBOTGSS_UTMI_OTG_STATUS_VBUSVALID
- | USBOTGSS_UTMI_OTG_STATUS_SESSEND);
- val |= USBOTGSS_UTMI_OTG_STATUS_SESSVALID
- | USBOTGSS_UTMI_OTG_STATUS_POWERPRESENT;
- dwc3_omap_write_utmi_status(omap, val);
+ val = dwc3_omap_read_utmi_ctrl(omap);
+ val &= ~(USBOTGSS_UTMI_OTG_CTRL_IDDIG
+ | USBOTGSS_UTMI_OTG_CTRL_VBUSVALID
+ | USBOTGSS_UTMI_OTG_CTRL_SESSEND);
+ val |= USBOTGSS_UTMI_OTG_CTRL_SESSVALID
+ | USBOTGSS_UTMI_OTG_CTRL_POWERPRESENT;
+ dwc3_omap_write_utmi_ctrl(omap, val);
break;
case OMAP_DWC3_VBUS_VALID:
dev_dbg(omap->dev, "VBUS Connect\n");
- val = dwc3_omap_read_utmi_status(omap);
- val &= ~USBOTGSS_UTMI_OTG_STATUS_SESSEND;
- val |= USBOTGSS_UTMI_OTG_STATUS_IDDIG
- | USBOTGSS_UTMI_OTG_STATUS_VBUSVALID
- | USBOTGSS_UTMI_OTG_STATUS_SESSVALID
- | USBOTGSS_UTMI_OTG_STATUS_POWERPRESENT;
- dwc3_omap_write_utmi_status(omap, val);
+ val = dwc3_omap_read_utmi_ctrl(omap);
+ val &= ~USBOTGSS_UTMI_OTG_CTRL_SESSEND;
+ val |= USBOTGSS_UTMI_OTG_CTRL_IDDIG
+ | USBOTGSS_UTMI_OTG_CTRL_VBUSVALID
+ | USBOTGSS_UTMI_OTG_CTRL_SESSVALID
+ | USBOTGSS_UTMI_OTG_CTRL_POWERPRESENT;
+ dwc3_omap_write_utmi_ctrl(omap, val);
break;
case OMAP_DWC3_ID_FLOAT:
case OMAP_DWC3_VBUS_OFF:
dev_dbg(omap->dev, "VBUS Disconnect\n");
- val = dwc3_omap_read_utmi_status(omap);
- val &= ~(USBOTGSS_UTMI_OTG_STATUS_SESSVALID
- | USBOTGSS_UTMI_OTG_STATUS_VBUSVALID
- | USBOTGSS_UTMI_OTG_STATUS_POWERPRESENT);
- val |= USBOTGSS_UTMI_OTG_STATUS_SESSEND
- | USBOTGSS_UTMI_OTG_STATUS_IDDIG;
- dwc3_omap_write_utmi_status(omap, val);
+ val = dwc3_omap_read_utmi_ctrl(omap);
+ val &= ~(USBOTGSS_UTMI_OTG_CTRL_SESSVALID
+ | USBOTGSS_UTMI_OTG_CTRL_VBUSVALID
+ | USBOTGSS_UTMI_OTG_CTRL_POWERPRESENT);
+ val |= USBOTGSS_UTMI_OTG_CTRL_SESSEND
+ | USBOTGSS_UTMI_OTG_CTRL_IDDIG;
+ dwc3_omap_write_utmi_ctrl(omap, val);
break;
default:
struct device_node *node = omap->dev->of_node;
int utmi_mode = 0;
- reg = dwc3_omap_read_utmi_status(omap);
+ reg = dwc3_omap_read_utmi_ctrl(omap);
of_property_read_u32(node, "utmi-mode", &utmi_mode);
switch (utmi_mode) {
case DWC3_OMAP_UTMI_MODE_SW:
- reg |= USBOTGSS_UTMI_OTG_STATUS_SW_MODE;
+ reg |= USBOTGSS_UTMI_OTG_CTRL_SW_MODE;
break;
case DWC3_OMAP_UTMI_MODE_HW:
- reg &= ~USBOTGSS_UTMI_OTG_STATUS_SW_MODE;
+ reg &= ~USBOTGSS_UTMI_OTG_CTRL_SW_MODE;
break;
default:
dev_dbg(omap->dev, "UNKNOWN utmi mode %d\n", utmi_mode);
}
- dwc3_omap_write_utmi_status(omap, reg);
+ dwc3_omap_write_utmi_ctrl(omap, reg);
}
static int dwc3_omap_extcon_register(struct dwc3_omap *omap)
{
struct dwc3_omap *omap = dev_get_drvdata(dev);
- omap->utmi_otg_status = dwc3_omap_read_utmi_status(omap);
+ omap->utmi_otg_ctrl = dwc3_omap_read_utmi_ctrl(omap);
dwc3_omap_disable_irqs(omap);
return 0;
{
struct dwc3_omap *omap = dev_get_drvdata(dev);
- dwc3_omap_write_utmi_status(omap, omap->utmi_otg_status);
+ dwc3_omap_write_utmi_ctrl(omap, omap->utmi_otg_ctrl);
dwc3_omap_enable_irqs(omap);
pm_runtime_disable(dev);
}
}
c->next_interface_id = 0;
+ memset(c->interface, 0, sizeof(c->interface));
c->superspeed = 0;
c->highspeed = 0;
c->fullspeed = 0;
return ret;
}
- set_bit(FFS_FL_CALL_CLOSED_CALLBACK, &ffs->flags);
return len;
}
break;
ret = ep->status;
if (io_data->read && ret > 0) {
ret = copy_to_iter(data, ret, &io_data->data);
- if (unlikely(iov_iter_count(&io_data->data)))
+ if (!ret)
ret = -EFAULT;
}
}
{
ENTER();
- if (test_and_clear_bit(FFS_FL_CALL_CLOSED_CALLBACK, &ffs->flags))
- ffs_closed(ffs);
+ ffs_closed(ffs);
BUG_ON(ffs->gadget);
ffs_obj->desc_ready = true;
ffs_obj->ffs_data = ffs;
- if (ffs_obj->ffs_ready_callback)
+ if (ffs_obj->ffs_ready_callback) {
ret = ffs_obj->ffs_ready_callback(ffs);
+ if (ret)
+ goto done;
+ }
+ set_bit(FFS_FL_CALL_CLOSED_CALLBACK, &ffs->flags);
done:
ffs_dev_unlock();
return ret;
ffs_obj->desc_ready = false;
- if (ffs_obj->ffs_closed_callback)
+ if (test_and_clear_bit(FFS_FL_CALL_CLOSED_CALLBACK, &ffs->flags) &&
+ ffs_obj->ffs_closed_callback)
ffs_obj->ffs_closed_callback(ffs);
if (!ffs_obj->opts || ffs_obj->opts->no_configfs
| USB_REQ_GET_DESCRIPTOR):
switch (value >> 8) {
case HID_DT_HID:
+ {
+ struct hid_descriptor hidg_desc_copy = hidg_desc;
+
VDBG(cdev, "USB_REQ_GET_DESCRIPTOR: HID\n");
+ hidg_desc_copy.desc[0].bDescriptorType = HID_DT_REPORT;
+ hidg_desc_copy.desc[0].wDescriptorLength =
+ cpu_to_le16(hidg->report_desc_length);
+
length = min_t(unsigned short, length,
- hidg_desc.bLength);
- memcpy(req->buf, &hidg_desc, length);
+ hidg_desc_copy.bLength);
+ memcpy(req->buf, &hidg_desc_copy, length);
goto respond;
break;
+ }
case HID_DT_REPORT:
VDBG(cdev, "USB_REQ_GET_DESCRIPTOR: REPORT\n");
length = min_t(unsigned short, length,
hidg_fs_in_ep_desc.wMaxPacketSize = cpu_to_le16(hidg->report_length);
hidg_hs_out_ep_desc.wMaxPacketSize = cpu_to_le16(hidg->report_length);
hidg_fs_out_ep_desc.wMaxPacketSize = cpu_to_le16(hidg->report_length);
+ /*
+ * We can use hidg_desc struct here but we should not relay
+ * that its content won't change after returning from this function.
+ */
hidg_desc.desc[0].bDescriptorType = HID_DT_REPORT;
hidg_desc.desc[0].wDescriptorLength =
cpu_to_le16(hidg->report_desc_length);
int result;
mutex_lock(&opts->lock);
- result = strlcpy(page, opts->id, PAGE_SIZE);
+ if (opts->id) {
+ result = strlcpy(page, opts->id, PAGE_SIZE);
+ } else {
+ page[0] = 0;
+ result = 0;
+ }
+
mutex_unlock(&opts->lock);
return result;
if (intf == 1) {
if (alt == 1) {
- config_ep_by_speed(cdev->gadget, f, out_ep);
+ err = config_ep_by_speed(cdev->gadget, f, out_ep);
+ if (err)
+ return err;
+
usb_ep_enable(out_ep);
out_ep->driver_data = audio;
audio->copy_buf = f_audio_buffer_alloc(audio_buf_size);
int write_allocated;
struct gs_buf port_write_buf;
wait_queue_head_t drain_wait; /* wait while writes drain */
+ bool write_busy;
/* REVISIT this state ... */
struct usb_cdc_line_coding port_line_coding; /* 8-N-1 etc */
int status = 0;
bool do_tty_wake = false;
- while (!list_empty(pool)) {
+ while (!port->write_busy && !list_empty(pool)) {
struct usb_request *req;
int len;
* NOTE that we may keep sending data for a while after
* the TTY closed (dev->ioport->port_tty is NULL).
*/
+ port->write_busy = true;
spin_unlock(&port->port_lock);
status = usb_ep_queue(in, req, GFP_ATOMIC);
spin_lock(&port->port_lock);
+ port->write_busy = false;
if (status) {
pr_debug("%s: %s %s err %d\n",
/*
* We _always_ have both ACM and mass storage functions.
*/
-static int __init acm_ms_do_config(struct usb_configuration *c)
+static int acm_ms_do_config(struct usb_configuration *c)
{
struct fsg_opts *opts;
int status;
/*-------------------------------------------------------------------------*/
-static int __init acm_ms_bind(struct usb_composite_dev *cdev)
+static int acm_ms_bind(struct usb_composite_dev *cdev)
{
struct usb_gadget *gadget = cdev->gadget;
struct fsg_opts *opts;
return status;
}
-static int __exit acm_ms_unbind(struct usb_composite_dev *cdev)
+static int acm_ms_unbind(struct usb_composite_dev *cdev)
{
usb_put_function(f_msg);
usb_put_function_instance(fi_msg);
return 0;
}
-static __refdata struct usb_composite_driver acm_ms_driver = {
+static struct usb_composite_driver acm_ms_driver = {
.name = "g_acm_ms",
.dev = &device_desc,
.max_speed = USB_SPEED_SUPER,
.strings = dev_strings,
.bind = acm_ms_bind,
- .unbind = __exit_p(acm_ms_unbind),
+ .unbind = acm_ms_unbind,
};
module_usb_composite_driver(acm_ms_driver);
/*-------------------------------------------------------------------------*/
-static int __init audio_do_config(struct usb_configuration *c)
+static int audio_do_config(struct usb_configuration *c)
{
int status;
/*-------------------------------------------------------------------------*/
-static int __init audio_bind(struct usb_composite_dev *cdev)
+static int audio_bind(struct usb_composite_dev *cdev)
{
#ifndef CONFIG_GADGET_UAC1
struct f_uac2_opts *uac2_opts;
return status;
}
-static int __exit audio_unbind(struct usb_composite_dev *cdev)
+static int audio_unbind(struct usb_composite_dev *cdev)
{
#ifdef CONFIG_GADGET_UAC1
if (!IS_ERR_OR_NULL(f_uac1))
return 0;
}
-static __refdata struct usb_composite_driver audio_driver = {
+static struct usb_composite_driver audio_driver = {
.name = "g_audio",
.dev = &device_desc,
.strings = audio_strings,
.max_speed = USB_SPEED_HIGH,
.bind = audio_bind,
- .unbind = __exit_p(audio_unbind),
+ .unbind = audio_unbind,
};
module_usb_composite_driver(audio_driver);
/*
* We _always_ have both CDC ECM and CDC ACM functions.
*/
-static int __init cdc_do_config(struct usb_configuration *c)
+static int cdc_do_config(struct usb_configuration *c)
{
int status;
/*-------------------------------------------------------------------------*/
-static int __init cdc_bind(struct usb_composite_dev *cdev)
+static int cdc_bind(struct usb_composite_dev *cdev)
{
struct usb_gadget *gadget = cdev->gadget;
struct f_ecm_opts *ecm_opts;
return status;
}
-static int __exit cdc_unbind(struct usb_composite_dev *cdev)
+static int cdc_unbind(struct usb_composite_dev *cdev)
{
usb_put_function(f_acm);
usb_put_function_instance(fi_serial);
return 0;
}
-static __refdata struct usb_composite_driver cdc_driver = {
+static struct usb_composite_driver cdc_driver = {
.name = "g_cdc",
.dev = &device_desc,
.strings = dev_strings,
.max_speed = USB_SPEED_HIGH,
.bind = cdc_bind,
- .unbind = __exit_p(cdc_unbind),
+ .unbind = cdc_unbind,
};
module_usb_composite_driver(cdc_driver);
return -ENODEV;
}
-static int __init dbgp_bind(struct usb_gadget *gadget,
+static int dbgp_bind(struct usb_gadget *gadget,
struct usb_gadget_driver *driver)
{
int err, stp;
return err;
}
-static __refdata struct usb_gadget_driver dbgp_driver = {
+static struct usb_gadget_driver dbgp_driver = {
.function = "dbgp",
.max_speed = USB_SPEED_HIGH,
.bind = dbgp_bind,
* the first one present. That's to make Microsoft's drivers happy,
* and to follow DOCSIS 1.0 (cable modem standard).
*/
-static int __init rndis_do_config(struct usb_configuration *c)
+static int rndis_do_config(struct usb_configuration *c)
{
int status;
/*
* We _always_ have an ECM, CDC Subset, or EEM configuration.
*/
-static int __init eth_do_config(struct usb_configuration *c)
+static int eth_do_config(struct usb_configuration *c)
{
int status = 0;
/*-------------------------------------------------------------------------*/
-static int __init eth_bind(struct usb_composite_dev *cdev)
+static int eth_bind(struct usb_composite_dev *cdev)
{
struct usb_gadget *gadget = cdev->gadget;
struct f_eem_opts *eem_opts = NULL;
return status;
}
-static int __exit eth_unbind(struct usb_composite_dev *cdev)
+static int eth_unbind(struct usb_composite_dev *cdev)
{
if (has_rndis()) {
usb_put_function(f_rndis);
return 0;
}
-static __refdata struct usb_composite_driver eth_driver = {
+static struct usb_composite_driver eth_driver = {
.name = "g_ether",
.dev = &device_desc,
.strings = dev_strings,
.max_speed = USB_SPEED_SUPER,
.bind = eth_bind,
- .unbind = __exit_p(eth_unbind),
+ .unbind = eth_unbind,
};
module_usb_composite_driver(eth_driver);
static int gfs_do_config(struct usb_configuration *c);
-static __refdata struct usb_composite_driver gfs_driver = {
+static struct usb_composite_driver gfs_driver = {
.name = DRIVER_NAME,
.dev = &gfs_dev_desc,
.strings = gfs_dev_strings,
gfs_registered = true;
ret = usb_composite_probe(&gfs_driver);
- if (unlikely(ret < 0))
+ if (unlikely(ret < 0)) {
+ ++missing_funcs;
gfs_registered = false;
+ }
return ret;
}
static struct usb_function_instance *fi_midi;
static struct usb_function *f_midi;
-static int __exit midi_unbind(struct usb_composite_dev *dev)
+static int midi_unbind(struct usb_composite_dev *dev)
{
usb_put_function(f_midi);
usb_put_function_instance(fi_midi);
.MaxPower = CONFIG_USB_GADGET_VBUS_DRAW,
};
-static int __init midi_bind_config(struct usb_configuration *c)
+static int midi_bind_config(struct usb_configuration *c)
{
int status;
return 0;
}
-static int __init midi_bind(struct usb_composite_dev *cdev)
+static int midi_bind(struct usb_composite_dev *cdev)
{
struct f_midi_opts *midi_opts;
int status;
return status;
}
-static __refdata struct usb_composite_driver midi_driver = {
+static struct usb_composite_driver midi_driver = {
.name = (char *) longname,
.dev = &device_desc,
.strings = dev_strings,
.max_speed = USB_SPEED_HIGH,
.bind = midi_bind,
- .unbind = __exit_p(midi_unbind),
+ .unbind = midi_unbind,
};
module_usb_composite_driver(midi_driver);
/****************************** Configurations ******************************/
-static int __init do_config(struct usb_configuration *c)
+static int do_config(struct usb_configuration *c)
{
struct hidg_func_node *e, *n;
int status = 0;
/****************************** Gadget Bind ******************************/
-static int __init hid_bind(struct usb_composite_dev *cdev)
+static int hid_bind(struct usb_composite_dev *cdev)
{
struct usb_gadget *gadget = cdev->gadget;
struct list_head *tmp;
return status;
}
-static int __exit hid_unbind(struct usb_composite_dev *cdev)
+static int hid_unbind(struct usb_composite_dev *cdev)
{
struct hidg_func_node *n;
return 0;
}
-static int __init hidg_plat_driver_probe(struct platform_device *pdev)
+static int hidg_plat_driver_probe(struct platform_device *pdev)
{
struct hidg_func_descriptor *func = dev_get_platdata(&pdev->dev);
struct hidg_func_node *entry;
/****************************** Some noise ******************************/
-static __refdata struct usb_composite_driver hidg_driver = {
+static struct usb_composite_driver hidg_driver = {
.name = "g_hid",
.dev = &device_desc,
.strings = dev_strings,
.max_speed = USB_SPEED_HIGH,
.bind = hid_bind,
- .unbind = __exit_p(hid_unbind),
+ .unbind = hid_unbind,
};
static struct platform_driver hidg_plat_driver = {
return 0;
}
-static int __init msg_do_config(struct usb_configuration *c)
+static int msg_do_config(struct usb_configuration *c)
{
struct fsg_opts *opts;
int ret;
/****************************** Gadget Bind ******************************/
-static int __init msg_bind(struct usb_composite_dev *cdev)
+static int msg_bind(struct usb_composite_dev *cdev)
{
static const struct fsg_operations ops = {
.thread_exits = msg_thread_exits,
/****************************** Some noise ******************************/
-static __refdata struct usb_composite_driver msg_driver = {
+static struct usb_composite_driver msg_driver = {
.name = "g_mass_storage",
.dev = &msg_device_desc,
.max_speed = USB_SPEED_SUPER,
static struct usb_function *f_rndis;
static struct usb_function *f_msg_rndis;
-static __init int rndis_do_config(struct usb_configuration *c)
+static int rndis_do_config(struct usb_configuration *c)
{
struct fsg_opts *fsg_opts;
int ret;
static struct usb_function *f_ecm;
static struct usb_function *f_msg_multi;
-static __init int cdc_do_config(struct usb_configuration *c)
+static int cdc_do_config(struct usb_configuration *c)
{
struct fsg_opts *fsg_opts;
int ret;
return status;
}
-static int __exit multi_unbind(struct usb_composite_dev *cdev)
+static int multi_unbind(struct usb_composite_dev *cdev)
{
#ifdef CONFIG_USB_G_MULTI_CDC
usb_put_function(f_msg_multi);
/****************************** Some noise ******************************/
-static __refdata struct usb_composite_driver multi_driver = {
+static struct usb_composite_driver multi_driver = {
.name = "g_multi",
.dev = &device_desc,
.strings = dev_strings,
.max_speed = USB_SPEED_HIGH,
.bind = multi_bind,
- .unbind = __exit_p(multi_unbind),
+ .unbind = multi_unbind,
.needs_serial = 1,
};
/*-------------------------------------------------------------------------*/
-static int __init ncm_do_config(struct usb_configuration *c)
+static int ncm_do_config(struct usb_configuration *c)
{
int status;
/*-------------------------------------------------------------------------*/
-static int __init gncm_bind(struct usb_composite_dev *cdev)
+static int gncm_bind(struct usb_composite_dev *cdev)
{
struct usb_gadget *gadget = cdev->gadget;
struct f_ncm_opts *ncm_opts;
return status;
}
-static int __exit gncm_unbind(struct usb_composite_dev *cdev)
+static int gncm_unbind(struct usb_composite_dev *cdev)
{
if (!IS_ERR_OR_NULL(f_ncm))
usb_put_function(f_ncm);
return 0;
}
-static __refdata struct usb_composite_driver ncm_driver = {
+static struct usb_composite_driver ncm_driver = {
.name = "g_ncm",
.dev = &device_desc,
.strings = dev_strings,
.max_speed = USB_SPEED_HIGH,
.bind = gncm_bind,
- .unbind = __exit_p(gncm_unbind),
+ .unbind = gncm_unbind,
};
module_usb_composite_driver(ncm_driver);
static struct usb_function_instance *fi_obex2;
static struct usb_function_instance *fi_phonet;
-static int __init nokia_bind_config(struct usb_configuration *c)
+static int nokia_bind_config(struct usb_configuration *c)
{
struct usb_function *f_acm;
struct usb_function *f_phonet = NULL;
return status;
}
-static int __init nokia_bind(struct usb_composite_dev *cdev)
+static int nokia_bind(struct usb_composite_dev *cdev)
{
struct usb_gadget *gadget = cdev->gadget;
int status;
return status;
}
-static int __exit nokia_unbind(struct usb_composite_dev *cdev)
+static int nokia_unbind(struct usb_composite_dev *cdev)
{
if (!IS_ERR_OR_NULL(f_obex1_cfg2))
usb_put_function(f_obex1_cfg2);
return 0;
}
-static __refdata struct usb_composite_driver nokia_driver = {
+static struct usb_composite_driver nokia_driver = {
.name = "g_nokia",
.dev = &device_desc,
.strings = dev_strings,
.max_speed = USB_SPEED_HIGH,
.bind = nokia_bind,
- .unbind = __exit_p(nokia_unbind),
+ .unbind = nokia_unbind,
};
module_usb_composite_driver(nokia_driver);
.bmAttributes = USB_CONFIG_ATT_ONE | USB_CONFIG_ATT_SELFPOWER,
};
-static int __init printer_do_config(struct usb_configuration *c)
+static int printer_do_config(struct usb_configuration *c)
{
struct usb_gadget *gadget = c->cdev->gadget;
int status = 0;
return status;
}
-static int __init printer_bind(struct usb_composite_dev *cdev)
+static int printer_bind(struct usb_composite_dev *cdev)
{
struct f_printer_opts *opts;
int ret, len;
return ret;
}
-static int __exit printer_unbind(struct usb_composite_dev *cdev)
+static int printer_unbind(struct usb_composite_dev *cdev)
{
usb_put_function(f_printer);
usb_put_function_instance(fi_printer);
return 0;
}
-static __refdata struct usb_composite_driver printer_driver = {
+static struct usb_composite_driver printer_driver = {
.name = shortname,
.dev = &device_desc,
.strings = dev_strings,
return ret;
}
-static int __init gs_bind(struct usb_composite_dev *cdev)
+static int gs_bind(struct usb_composite_dev *cdev)
{
int status;
return 0;
}
-static __refdata struct usb_composite_driver gserial_driver = {
+static struct usb_composite_driver gserial_driver = {
.name = "g_serial",
.dev = &device_desc,
.strings = dev_strings,
return 0;
}
-static __refdata struct usb_composite_driver usbg_driver = {
+static struct usb_composite_driver usbg_driver = {
.name = "g_target",
.dev = &usbg_device_desc,
.strings = usbg_strings,
* USB configuration
*/
-static int __init
+static int
webcam_config_bind(struct usb_configuration *c)
{
int status = 0;
.MaxPower = CONFIG_USB_GADGET_VBUS_DRAW,
};
-static int /* __init_or_exit */
+static int
webcam_unbind(struct usb_composite_dev *cdev)
{
if (!IS_ERR_OR_NULL(f_uvc))
return 0;
}
-static int __init
+static int
webcam_bind(struct usb_composite_dev *cdev)
{
struct f_uvc_opts *uvc_opts;
* Driver
*/
-static __refdata struct usb_composite_driver webcam_driver = {
+static struct usb_composite_driver webcam_driver = {
.name = "g_webcam",
.dev = &webcam_device_descriptor,
.strings = webcam_device_strings,
module_param_named(qlen, gzero_options.qlen, uint, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(qlen, "depth of loopback queue");
-static int __init zero_bind(struct usb_composite_dev *cdev)
+static int zero_bind(struct usb_composite_dev *cdev)
{
struct f_ss_opts *ss_opts;
struct f_lb_opts *lb_opts;
return 0;
}
-static __refdata struct usb_composite_driver zero_driver = {
+static struct usb_composite_driver zero_driver = {
.name = "zero",
.dev = &device_desc,
.strings = dev_strings,
return retval;
}
-static int __exit at91udc_remove(struct platform_device *pdev)
+static int at91udc_remove(struct platform_device *pdev)
{
struct at91_udc *udc = platform_get_drvdata(pdev);
unsigned long flags;
#endif
static struct platform_driver at91_udc_driver = {
- .remove = __exit_p(at91udc_remove),
+ .remove = at91udc_remove,
.shutdown = at91udc_shutdown,
.suspend = at91udc_suspend,
.resume = at91udc_resume,
return 0;
}
-static int __exit usba_udc_remove(struct platform_device *pdev)
+static int usba_udc_remove(struct platform_device *pdev)
{
struct usba_udc *udc;
int i;
static SIMPLE_DEV_PM_OPS(usba_udc_pm_ops, usba_udc_suspend, usba_udc_resume);
static struct platform_driver udc_driver = {
- .remove = __exit_p(usba_udc_remove),
+ .remove = usba_udc_remove,
.driver = {
.name = "atmel_usba_udc",
.pm = &usba_udc_pm_ops,
/* Driver removal function
* Free resources and finish pending transactions
*/
-static int __exit fsl_udc_remove(struct platform_device *pdev)
+static int fsl_udc_remove(struct platform_device *pdev)
{
struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev);
};
MODULE_DEVICE_TABLE(platform, fsl_udc_devtype);
static struct platform_driver udc_driver = {
- .remove = __exit_p(fsl_udc_remove),
+ .remove = fsl_udc_remove,
/* Just for FSL i.mx SoC currently */
.id_table = fsl_udc_devtype,
/* these suspend and resume are not usb suspend and resume */
.udc_stop = fusb300_udc_stop,
};
-static int __exit fusb300_remove(struct platform_device *pdev)
+static int fusb300_remove(struct platform_device *pdev)
{
struct fusb300 *fusb300 = platform_get_drvdata(pdev);
}
static struct platform_driver fusb300_driver = {
- .remove = __exit_p(fusb300_remove),
+ .remove = fusb300_remove,
.driver = {
.name = (char *) udc_name,
},
.pullup = m66592_pullup,
};
-static int __exit m66592_remove(struct platform_device *pdev)
+static int m66592_remove(struct platform_device *pdev)
{
struct m66592 *m66592 = platform_get_drvdata(pdev);
/*-------------------------------------------------------------------------*/
static struct platform_driver m66592_driver = {
- .remove = __exit_p(m66592_remove),
+ .remove = m66592_remove,
.driver = {
.name = (char *) udc_name,
},
.set_selfpowered = r8a66597_set_selfpowered,
};
-static int __exit r8a66597_remove(struct platform_device *pdev)
+static int r8a66597_remove(struct platform_device *pdev)
{
struct r8a66597 *r8a66597 = platform_get_drvdata(pdev);
/*-------------------------------------------------------------------------*/
static struct platform_driver r8a66597_driver = {
- .remove = __exit_p(r8a66597_remove),
+ .remove = r8a66597_remove,
.driver = {
.name = (char *) udc_name,
},
dprintk(DEBUG_NORMAL, "%s()\n", __func__);
- s3c2410_udc_set_pullup(udc, is_on ? 0 : 1);
+ s3c2410_udc_set_pullup(udc, is_on);
return 0;
}
/* Map the registers */
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
udc->addr = devm_ioremap_resource(&pdev->dev, res);
- if (!udc->addr)
- return -ENOMEM;
+ if (IS_ERR(udc->addr))
+ return PTR_ERR(udc->addr);
irq = platform_get_irq(pdev, 0);
if (irq < 0) {
break;
case COMP_DEV_ERR:
case COMP_STALL:
+ frame->status = -EPROTO;
+ skip_td = true;
+ break;
case COMP_TX_ERR:
frame->status = -EPROTO;
+ if (event_trb != td->last_trb)
+ return 0;
skip_td = true;
break;
case COMP_STOP:
xhci_halt(xhci);
hw_died:
spin_unlock(&xhci->lock);
- return -ESHUTDOWN;
+ return IRQ_HANDLED;
}
/*
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
unsigned long flags;
- int ret;
+ int ret, slot_id;
struct xhci_command *command;
command = xhci_alloc_command(xhci, false, false, GFP_KERNEL);
if (!command)
return 0;
+ /* xhci->slot_id and xhci->addr_dev are not thread-safe */
+ mutex_lock(&xhci->mutex);
spin_lock_irqsave(&xhci->lock, flags);
command->completion = &xhci->addr_dev;
ret = xhci_queue_slot_control(xhci, command, TRB_ENABLE_SLOT, 0);
if (ret) {
spin_unlock_irqrestore(&xhci->lock, flags);
+ mutex_unlock(&xhci->mutex);
xhci_dbg(xhci, "FIXME: allocate a command ring segment\n");
kfree(command);
return 0;
spin_unlock_irqrestore(&xhci->lock, flags);
wait_for_completion(command->completion);
+ slot_id = xhci->slot_id;
+ mutex_unlock(&xhci->mutex);
- if (!xhci->slot_id || command->status != COMP_SUCCESS) {
+ if (!slot_id || command->status != COMP_SUCCESS) {
xhci_err(xhci, "Error while assigning device slot ID\n");
xhci_err(xhci, "Max number of devices this xHCI host supports is %u.\n",
HCS_MAX_SLOTS(
* xhci_discover_or_reset_device(), which may be called as part of
* mass storage driver error handling.
*/
- if (!xhci_alloc_virt_device(xhci, xhci->slot_id, udev, GFP_NOIO)) {
+ if (!xhci_alloc_virt_device(xhci, slot_id, udev, GFP_NOIO)) {
xhci_warn(xhci, "Could not allocate xHCI USB device data structures\n");
goto disable_slot;
}
- udev->slot_id = xhci->slot_id;
+ udev->slot_id = slot_id;
#ifndef CONFIG_USB_DEFAULT_PERSIST
/*
struct xhci_slot_ctx *slot_ctx;
struct xhci_input_control_ctx *ctrl_ctx;
u64 temp_64;
- struct xhci_command *command;
+ struct xhci_command *command = NULL;
+
+ mutex_lock(&xhci->mutex);
if (!udev->slot_id) {
xhci_dbg_trace(xhci, trace_xhci_dbg_address,
"Bad Slot ID %d", udev->slot_id);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
virt_dev = xhci->devs[udev->slot_id];
*/
xhci_warn(xhci, "Virt dev invalid for slot_id 0x%x!\n",
udev->slot_id);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
if (setup == SETUP_CONTEXT_ONLY) {
if (GET_SLOT_STATE(le32_to_cpu(slot_ctx->dev_state)) ==
SLOT_STATE_DEFAULT) {
xhci_dbg(xhci, "Slot already in default state\n");
- return 0;
+ goto out;
}
}
command = xhci_alloc_command(xhci, false, false, GFP_KERNEL);
- if (!command)
- return -ENOMEM;
+ if (!command) {
+ ret = -ENOMEM;
+ goto out;
+ }
command->in_ctx = virt_dev->in_ctx;
command->completion = &xhci->addr_dev;
if (!ctrl_ctx) {
xhci_warn(xhci, "%s: Could not get input context, bad type.\n",
__func__);
- kfree(command);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
/*
* If this is the first Set Address since device plug-in or
spin_unlock_irqrestore(&xhci->lock, flags);
xhci_dbg_trace(xhci, trace_xhci_dbg_address,
"FIXME: allocate a command ring segment");
- kfree(command);
- return ret;
+ goto out;
}
xhci_ring_cmd_db(xhci);
spin_unlock_irqrestore(&xhci->lock, flags);
ret = -EINVAL;
break;
}
- if (ret) {
- kfree(command);
- return ret;
- }
+ if (ret)
+ goto out;
temp_64 = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr);
xhci_dbg_trace(xhci, trace_xhci_dbg_address,
"Op regs DCBAA ptr = %#016llx", temp_64);
xhci_dbg_trace(xhci, trace_xhci_dbg_address,
"Internal device address = %d",
le32_to_cpu(slot_ctx->dev_state) & DEV_ADDR_MASK);
+out:
+ mutex_unlock(&xhci->mutex);
kfree(command);
- return 0;
+ return ret;
}
int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
return 0;
}
+ mutex_init(&xhci->mutex);
xhci->cap_regs = hcd->regs;
xhci->op_regs = hcd->regs +
HC_LENGTH(readl(&xhci->cap_regs->hc_capbase));
BUILD_BUG_ON(sizeof(struct xhci_run_regs) != (8+8*128)*32/8);
return 0;
}
+
+/*
+ * If an init function is provided, an exit function must also be provided
+ * to allow module unload.
+ */
+static void __exit xhci_hcd_fini(void) { }
+
module_init(xhci_hcd_init);
+module_exit(xhci_hcd_fini);
* since the command ring is 64-byte aligned.
* It must also be greater than 16.
*/
-#define TRBS_PER_SEGMENT 64
+#define TRBS_PER_SEGMENT 256
/* Allow two commands + a link TRB, along with any reserved command TRBs */
#define MAX_RSVD_CMD_TRBS (TRBS_PER_SEGMENT - 3)
#define TRB_SEGMENT_SIZE (TRBS_PER_SEGMENT*16)
struct list_head lpm_failed_devs;
/* slot enabling and address device helpers */
+ /* these are not thread safe so use mutex */
+ struct mutex mutex;
struct completion addr_dev;
int slot_id;
/* For USB 3.0 LPM enable/disable. */
if (musb->ops->quirks)
musb->io.quirks = musb->ops->quirks;
- /* At least tusb6010 has it's own offsets.. */
- if (musb->ops->ep_offset)
- musb->io.ep_offset = musb->ops->ep_offset;
- if (musb->ops->ep_select)
- musb->io.ep_select = musb->ops->ep_select;
-
- /* ..and some devices use indexed offset or flat offset */
+ /* Most devices use indexed offset or flat offset */
if (musb->io.quirks & MUSB_INDEXED_EP) {
musb->io.ep_offset = musb_indexed_ep_offset;
musb->io.ep_select = musb_indexed_ep_select;
musb->io.ep_select = musb_flat_ep_select;
}
+ /* At least tusb6010 has its own offsets */
+ if (musb->ops->ep_offset)
+ musb->io.ep_offset = musb->ops->ep_offset;
+ if (musb->ops->ep_select)
+ musb->io.ep_select = musb->ops->ep_select;
+
if (musb->ops->fifo_mode)
fifo_mode = musb->ops->fifo_mode;
else
}
err = devm_request_threaded_irq(&pdev->dev, irq, NULL,
ab8500_usb_link_status_irq,
- IRQF_NO_SUSPEND | IRQF_SHARED,
+ IRQF_NO_SUSPEND | IRQF_SHARED | IRQF_ONESHOT,
"usb-link-status", ab);
if (err < 0) {
dev_err(ab->dev, "request_irq failed for link status irq\n");
}
err = devm_request_threaded_irq(&pdev->dev, irq, NULL,
ab8500_usb_disconnect_irq,
- IRQF_NO_SUSPEND | IRQF_SHARED,
+ IRQF_NO_SUSPEND | IRQF_SHARED | IRQF_ONESHOT,
"usb-id-fall", ab);
if (err < 0) {
dev_err(ab->dev, "request_irq failed for ID fall irq\n");
}
err = devm_request_threaded_irq(&pdev->dev, irq, NULL,
ab8500_usb_disconnect_irq,
- IRQF_NO_SUSPEND | IRQF_SHARED,
+ IRQF_NO_SUSPEND | IRQF_SHARED | IRQF_ONESHOT,
"usb-vbus-fall", ab);
if (err < 0) {
dev_err(ab->dev, "request_irq failed for Vbus fall irq\n");
#if defined(CONFIG_MACH_OMAP_H2) || defined(CONFIG_MACH_OMAP_H3)
-#if defined(CONFIG_TPS65010) || defined(CONFIG_TPS65010_MODULE)
+#if defined(CONFIG_TPS65010) || (defined(CONFIG_TPS65010_MODULE) && defined(MODULE))
#include <linux/i2c/tps65010.h>
dev_set_drvdata(&pdev->dev, tu);
tu->irq = platform_get_irq(pdev, 0);
- ret = request_threaded_irq(tu->irq, NULL, tahvo_usb_vbus_interrupt, 0,
+ ret = request_threaded_irq(tu->irq, NULL, tahvo_usb_vbus_interrupt,
+ IRQF_ONESHOT,
"tahvo-vbus", tu);
if (ret) {
dev_err(&pdev->dev, "could not register tahvo-vbus irq: %d\n",
static int usbhsf_prepare_pop(struct usbhs_pkt *pkt, int *is_done)
{
struct usbhs_pipe *pipe = pkt->pipe;
+ struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe);
+ struct usbhs_fifo *fifo = usbhsf_get_cfifo(priv);
if (usbhs_pipe_is_busy(pipe))
return 0;
usbhs_pipe_data_sequence(pipe, pkt->sequence);
pkt->sequence = -1; /* -1 sequence will be ignored */
+ if (usbhs_pipe_is_dcp(pipe))
+ usbhsf_fifo_clear(pipe, fifo);
+
usbhs_pipe_set_trans_count_if_bulk(pipe, pkt->length);
usbhs_pipe_enable(pipe);
usbhs_pipe_running(pipe, 1);
*is_done = 1;
usbhsf_rx_irq_ctrl(pipe, 0);
usbhs_pipe_running(pipe, 0);
- usbhs_pipe_disable(pipe); /* disable pipe first */
+ /*
+ * If function mode, since this controller is possible to enter
+ * Control Write status stage at this timing, this driver
+ * should not disable the pipe. If such a case happens, this
+ * controller is not able to complete the status stage.
+ */
+ if (!usbhs_mod_is_host(priv) && !usbhs_pipe_is_dcp(pipe))
+ usbhs_pipe_disable(pipe); /* disable pipe first */
}
/*
{
char name[16];
- snprintf(name, sizeof(name), "tx%d", channel);
- fifo->tx_chan = dma_request_slave_channel_reason(dev, name);
- if (IS_ERR(fifo->tx_chan))
- fifo->tx_chan = NULL;
-
- snprintf(name, sizeof(name), "rx%d", channel);
- fifo->rx_chan = dma_request_slave_channel_reason(dev, name);
- if (IS_ERR(fifo->rx_chan))
- fifo->rx_chan = NULL;
+ /*
+ * To avoid complex handing for DnFIFOs, the driver uses each
+ * DnFIFO as TX or RX direction (not bi-direction).
+ * So, the driver uses odd channels for TX, even channels for RX.
+ */
+ snprintf(name, sizeof(name), "ch%d", channel);
+ if (channel & 1) {
+ fifo->tx_chan = dma_request_slave_channel_reason(dev, name);
+ if (IS_ERR(fifo->tx_chan))
+ fifo->tx_chan = NULL;
+ } else {
+ fifo->rx_chan = dma_request_slave_channel_reason(dev, name);
+ if (IS_ERR(fifo->rx_chan))
+ fifo->rx_chan = NULL;
+ }
}
static void usbhsf_dma_init(struct usbhs_priv *priv, struct usbhs_fifo *fifo,
{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
{ USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */
+ { USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
+ { USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_DONGLE_PID) },
{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) },
{ USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
+ { USB_DEVICE(XSENS_VID, XSENS_MTDEVBOARD_PID) },
{ USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
#define XSENS_AWINDA_STATION_PID 0x0101
#define XSENS_AWINDA_DONGLE_PID 0x0102
#define XSENS_MTW_PID 0x0200 /* Xsens MTw */
+#define XSENS_MTDEVBOARD_PID 0x0300 /* Motion Tracker Development Board */
#define XSENS_CONVERTER_PID 0xD00D /* Xsens USB-serial converter */
/* Xsens devices using FTDI VID */
{ USB_DEVICE(DCU10_VENDOR_ID, DCU10_PRODUCT_ID) },
{ USB_DEVICE(SITECOM_VENDOR_ID, SITECOM_PRODUCT_ID) },
{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_ID) },
- { USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_ID) },
{ USB_DEVICE(SIEMENS_VENDOR_ID, SIEMENS_PRODUCT_ID_SX1),
.driver_info = PL2303_QUIRK_UART_STATE_IDX0 },
{ USB_DEVICE(SIEMENS_VENDOR_ID, SIEMENS_PRODUCT_ID_X65),
#define ALCATEL_VENDOR_ID 0x11f7
#define ALCATEL_PRODUCT_ID 0x02df
-/* Samsung I330 phone cradle */
-#define SAMSUNG_VENDOR_ID 0x04e8
-#define SAMSUNG_PRODUCT_ID 0x8001
-
#define SIEMENS_VENDOR_ID 0x11f5
#define SIEMENS_PRODUCT_ID_SX1 0x0001
#define SIEMENS_PRODUCT_ID_X65 0x0003
.driver_info = (kernel_ulong_t)&palm_os_4_probe },
{ USB_DEVICE(ACER_VENDOR_ID, ACER_S10_ID),
.driver_info = (kernel_ulong_t)&palm_os_4_probe },
- { USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_SCH_I330_ID),
+ { USB_DEVICE_INTERFACE_CLASS(SAMSUNG_VENDOR_ID, SAMSUNG_SCH_I330_ID, 0xff),
.driver_info = (kernel_ulong_t)&palm_os_4_probe },
{ USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_SPH_I500_ID),
.driver_info = (kernel_ulong_t)&palm_os_4_probe },
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_GO_SLOW ),
+/* Reported by Christian Schaller <cschalle@redhat.com> */
+UNUSUAL_DEV( 0x059f, 0x0651, 0x0000, 0x0000,
+ "LaCie",
+ "External HDD",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_NO_WP_DETECT ),
+
/* Submitted by Joel Bourquard <numlock@freesurf.ch>
* Some versions of this device need the SubClass and Protocol overrides
* while others don't.
mutex_lock(&vdev->igate);
if (vdev->req_trigger) {
- dev_dbg(&vdev->pdev->dev, "Requesting device from user\n");
+ if (!(count % 10))
+ dev_notice_ratelimited(&vdev->pdev->dev,
+ "Relaying device request to user (#%u)\n",
+ count);
eventfd_signal(vdev->req_trigger, 1);
+ } else if (count == 0) {
+ dev_warn(&vdev->pdev->dev,
+ "No device request channel registered, blocked until released by user\n");
}
mutex_unlock(&vdev->igate);
void *device_data = device->device_data;
struct vfio_unbound_dev *unbound;
unsigned int i = 0;
+ long ret;
+ bool interrupted = false;
/*
* The group exists so long as we have a device reference. Get
vfio_device_put(device);
- } while (wait_event_interruptible_timeout(vfio.release_q,
- !vfio_dev_present(group, dev),
- HZ * 10) <= 0);
+ if (interrupted) {
+ ret = wait_event_timeout(vfio.release_q,
+ !vfio_dev_present(group, dev), HZ * 10);
+ } else {
+ ret = wait_event_interruptible_timeout(vfio.release_q,
+ !vfio_dev_present(group, dev), HZ * 10);
+ if (ret == -ERESTARTSYS) {
+ interrupted = true;
+ dev_warn(dev,
+ "Device is currently in use, task"
+ " \"%s\" (%d) "
+ "blocked until device is released",
+ current->comm, task_pid_nr(current));
+ }
+ }
+ } while (ret <= 0);
vfio_group_put(group);
* dependency now.
*/
se_tpg = &tpg->se_tpg;
- ret = configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
- &se_tpg->tpg_group.cg_item);
+ ret = target_depend_item(&se_tpg->tpg_group.cg_item);
if (ret) {
pr_warn("configfs_depend_item() failed: %d\n", ret);
kfree(vs_tpg);
* to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur.
*/
se_tpg = &tpg->se_tpg;
- configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
- &se_tpg->tpg_group.cg_item);
+ target_undepend_item(&se_tpg->tpg_group.cg_item);
}
if (match) {
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
pb->pwm = devm_pwm_get(&pdev->dev, NULL);
if (IS_ERR(pb->pwm)) {
+ ret = PTR_ERR(pb->pwm);
+ if (ret == -EPROBE_DEFER)
+ goto err_alloc;
+
dev_err(&pdev->dev, "unable to request PWM, trying legacy API\n");
pb->legacy = true;
pb->pwm = pwm_request(data->pwm_id, "pwm-backlight");
* access the videomem with writethrough cache
*/
info->fix.smem_start = (u_long)ZTWO_PADDR(videomemory);
- videomemory = (u_long)ioremap_writethrough(info->fix.smem_start,
- info->fix.smem_len);
+ videomemory = (u_long)ioremap_wt(info->fix.smem_start,
+ info->fix.smem_len);
if (!videomemory) {
dev_warn(&pdev->dev,
"Unable to map videomem cached writethrough\n");
/* Map the video memory (physical address given) to somewhere
* in the kernel address space.
*/
- external_screen_base = ioremap_writethrough(external_addr,
- external_len);
+ external_screen_base = ioremap_wt(external_addr, external_len);
if (external_vgaiobase)
external_vgaiobase =
(unsigned long)ioremap(external_vgaiobase, 0x10000);
fb_info.fix.line_length = fb_width;
fb_height = (in_8(fb_regs + HPFB_FBHMSB) << 8) | in_8(fb_regs + HPFB_FBHLSB);
fb_info.fix.smem_len = fb_width * fb_height;
- fb_start = (unsigned long)ioremap_writethrough(fb_info.fix.smem_start,
- fb_info.fix.smem_len);
+ fb_start = (unsigned long)ioremap_wt(fb_info.fix.smem_start,
+ fb_info.fix.smem_len);
hpfb_defined.xres = (in_8(fb_regs + HPFB_DWMSB) << 8) | in_8(fb_regs + HPFB_DWLSB);
hpfb_defined.yres = (in_8(fb_regs + HPFB_DHMSB) << 8) | in_8(fb_regs + HPFB_DHLSB);
hpfb_defined.xres_virtual = hpfb_defined.xres;
if (cpu == -1)
irq_set_affinity_hint(irq, NULL);
else {
+ cpumask_clear(mask);
cpumask_set_cpu(cpu, mask);
irq_set_affinity_hint(irq, mask);
}
}
EXPORT_SYMBOL_GPL(xen_evtchn_nr_channels);
-int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
+int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
{
struct evtchn_bind_virq bind_virq;
int evtchn, irq, ret;
if (irq < 0)
goto out;
- irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
- handle_percpu_irq, "virq");
+ if (percpu)
+ irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
+ handle_percpu_irq, "virq");
+ else
+ irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+ handle_edge_irq, "virq");
bind_virq.virq = virq;
bind_virq.vcpu = cpu;
{
int irq, retval;
- irq = bind_virq_to_irq(virq, cpu);
+ irq = bind_virq_to_irq(virq, cpu, irqflags & IRQF_PERCPU);
if (irq < 0)
return irq;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry);
-extern void v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd,
- void *p);
extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
struct p9_fid *fid,
struct super_block *sb, int new);
}
/**
- * v9fs_readlink - read a symlink's location (internal version)
+ * v9fs_vfs_follow_link - follow a symlink path
* @dentry: dentry for symlink
- * @buffer: buffer to load symlink location into
- * @buflen: length of buffer
- *
+ * @cookie: place to pass the data to put_link()
*/
-static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
+static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie)
{
- int retval;
-
- struct v9fs_session_info *v9ses;
- struct p9_fid *fid;
+ struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry);
+ struct p9_fid *fid = v9fs_fid_lookup(dentry);
struct p9_wstat *st;
+ char *res;
+
+ p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
- p9_debug(P9_DEBUG_VFS, " %pd\n", dentry);
- retval = -EPERM;
- v9ses = v9fs_dentry2v9ses(dentry);
- fid = v9fs_fid_lookup(dentry);
if (IS_ERR(fid))
- return PTR_ERR(fid);
+ return ERR_CAST(fid);
if (!v9fs_proto_dotu(v9ses))
- return -EBADF;
+ return ERR_PTR(-EBADF);
st = p9_client_stat(fid);
if (IS_ERR(st))
- return PTR_ERR(st);
+ return ERR_CAST(st);
if (!(st->mode & P9_DMSYMLINK)) {
- retval = -EINVAL;
- goto done;
+ p9stat_free(st);
+ kfree(st);
+ return ERR_PTR(-EINVAL);
}
+ res = st->extension;
+ st->extension = NULL;
+ if (strlen(res) >= PATH_MAX)
+ res[PATH_MAX - 1] = '\0';
- /* copy extension buffer into buffer */
- retval = min(strlen(st->extension)+1, (size_t)buflen);
- memcpy(buffer, st->extension, retval);
-
- p9_debug(P9_DEBUG_VFS, "%pd -> %s (%.*s)\n",
- dentry, st->extension, buflen, buffer);
-
-done:
p9stat_free(st);
kfree(st);
- return retval;
-}
-
-/**
- * v9fs_vfs_follow_link - follow a symlink path
- * @dentry: dentry for symlink
- * @nd: nameidata
- *
- */
-
-static void *v9fs_vfs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- int len = 0;
- char *link = __getname();
-
- p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
-
- if (!link)
- link = ERR_PTR(-ENOMEM);
- else {
- len = v9fs_readlink(dentry, link, PATH_MAX);
-
- if (len < 0) {
- __putname(link);
- link = ERR_PTR(len);
- } else
- link[min(len, PATH_MAX-1)] = 0;
- }
- nd_set_link(nd, link);
-
- return NULL;
-}
-
-/**
- * v9fs_vfs_put_link - release a symlink path
- * @dentry: dentry for symlink
- * @nd: nameidata
- * @p: unused
- *
- */
-
-void
-v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
-{
- char *s = nd_get_link(nd);
-
- p9_debug(P9_DEBUG_VFS, " %pd %s\n",
- dentry, IS_ERR(s) ? "<error>" : s);
- if (!IS_ERR(s))
- __putname(s);
+ return *cookie = res;
}
/**
return v9fs_vfs_mkspecial(dir, dentry, P9_DMSYMLINK, symname);
}
+#define U32_MAX_DIGITS 10
+
/**
* v9fs_vfs_link - create a hardlink
* @old_dentry: dentry for file to link to
struct dentry *dentry)
{
int retval;
- char *name;
+ char name[1 + U32_MAX_DIGITS + 2]; /* sign + number + \n + \0 */
struct p9_fid *oldfid;
p9_debug(P9_DEBUG_VFS, " %lu,%pd,%pd\n",
if (IS_ERR(oldfid))
return PTR_ERR(oldfid);
- name = __getname();
- if (unlikely(!name)) {
- retval = -ENOMEM;
- goto clunk_fid;
- }
-
sprintf(name, "%d\n", oldfid->fid);
retval = v9fs_vfs_mkspecial(dir, dentry, P9_DMLINK, name);
- __putname(name);
if (!retval) {
v9fs_refresh_inode(oldfid, d_inode(old_dentry));
v9fs_invalidate_inode_attr(dir);
}
-clunk_fid:
p9_client_clunk(oldfid);
return retval;
}
{
struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
int retval;
- char *name;
+ char name[2 + U32_MAX_DIGITS + 1 + U32_MAX_DIGITS + 1];
u32 perm;
p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
if (!new_valid_dev(rdev))
return -EINVAL;
- name = __getname();
- if (!name)
- return -ENOMEM;
/* build extension */
if (S_ISBLK(mode))
sprintf(name, "b %u %u", MAJOR(rdev), MINOR(rdev));
else if (S_ISCHR(mode))
sprintf(name, "c %u %u", MAJOR(rdev), MINOR(rdev));
- else if (S_ISFIFO(mode))
- *name = 0;
- else if (S_ISSOCK(mode))
+ else
*name = 0;
- else {
- __putname(name);
- return -EINVAL;
- }
perm = unixmode2p9mode(v9ses, mode);
retval = v9fs_vfs_mkspecial(dir, dentry, perm, name);
- __putname(name);
return retval;
}
static const struct inode_operations v9fs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = v9fs_vfs_follow_link,
- .put_link = v9fs_vfs_put_link,
+ .put_link = kfree_put_link,
.getattr = v9fs_vfs_getattr,
.setattr = v9fs_vfs_setattr,
};
/**
* v9fs_vfs_follow_link_dotl - follow a symlink path
* @dentry: dentry for symlink
- * @nd: nameidata
- *
+ * @cookie: place to pass the data to put_link()
*/
-static void *
-v9fs_vfs_follow_link_dotl(struct dentry *dentry, struct nameidata *nd)
+static const char *
+v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie)
{
- int retval;
- struct p9_fid *fid;
- char *link = __getname();
+ struct p9_fid *fid = v9fs_fid_lookup(dentry);
char *target;
+ int retval;
p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
- if (!link) {
- link = ERR_PTR(-ENOMEM);
- goto ndset;
- }
- fid = v9fs_fid_lookup(dentry);
- if (IS_ERR(fid)) {
- __putname(link);
- link = ERR_CAST(fid);
- goto ndset;
- }
+ if (IS_ERR(fid))
+ return ERR_CAST(fid);
retval = p9_client_readlink(fid, &target);
- if (!retval) {
- strcpy(link, target);
- kfree(target);
- goto ndset;
- }
- __putname(link);
- link = ERR_PTR(retval);
-ndset:
- nd_set_link(nd, link);
- return NULL;
+ if (retval)
+ return ERR_PTR(retval);
+ return *cookie = target;
}
int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
const struct inode_operations v9fs_symlink_inode_operations_dotl = {
.readlink = generic_readlink,
.follow_link = v9fs_vfs_follow_link_dotl,
- .put_link = v9fs_vfs_put_link,
+ .put_link = kfree_put_link,
.getattr = v9fs_vfs_getattr_dotl,
.setattr = v9fs_vfs_setattr_dotl,
.setxattr = generic_setxattr,
#include "autofs_i.h"
-static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *autofs4_follow_link(struct dentry *dentry, void **cookie)
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
if (ino && !autofs4_oz_mode(sbi))
ino->last_used = jiffies;
- nd_set_link(nd, d_inode(dentry)->i_private);
- return NULL;
+ return d_inode(dentry)->i_private;
}
const struct inode_operations autofs4_symlink_inode_operations = {
static struct inode *befs_alloc_inode(struct super_block *sb);
static void befs_destroy_inode(struct inode *inode);
static void befs_destroy_inodecache(void);
-static void *befs_follow_link(struct dentry *, struct nameidata *);
-static void *befs_fast_follow_link(struct dentry *, struct nameidata *);
+static const char *befs_follow_link(struct dentry *, void **);
static int befs_utf2nls(struct super_block *sb, const char *in, int in_len,
char **out, int *out_len);
static int befs_nls2utf(struct super_block *sb, const char *in, int in_len,
.bmap = befs_bmap,
};
-static const struct inode_operations befs_fast_symlink_inode_operations = {
- .readlink = generic_readlink,
- .follow_link = befs_fast_follow_link,
-};
-
static const struct inode_operations befs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = befs_follow_link,
inode->i_op = &befs_dir_inode_operations;
inode->i_fop = &befs_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
- if (befs_ino->i_flags & BEFS_LONG_SYMLINK)
+ if (befs_ino->i_flags & BEFS_LONG_SYMLINK) {
inode->i_op = &befs_symlink_inode_operations;
- else
- inode->i_op = &befs_fast_symlink_inode_operations;
+ } else {
+ inode->i_link = befs_ino->i_data.symlink;
+ inode->i_op = &simple_symlink_inode_operations;
+ }
} else {
befs_error(sb, "Inode %lu is not a regular file, "
"directory or symlink. THAT IS WRONG! BeFS has no "
* The data stream become link name. Unless the LONG_SYMLINK
* flag is set.
*/
-static void *
-befs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *
+befs_follow_link(struct dentry *dentry, void **cookie)
{
struct super_block *sb = dentry->d_sb;
struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry));
if (len == 0) {
befs_error(sb, "Long symlink with illegal length");
- link = ERR_PTR(-EIO);
- } else {
- befs_debug(sb, "Follow long symlink");
-
- link = kmalloc(len, GFP_NOFS);
- if (!link) {
- link = ERR_PTR(-ENOMEM);
- } else if (befs_read_lsymlink(sb, data, link, len) != len) {
- kfree(link);
- befs_error(sb, "Failed to read entire long symlink");
- link = ERR_PTR(-EIO);
- } else {
- link[len - 1] = '\0';
- }
+ return ERR_PTR(-EIO);
}
- nd_set_link(nd, link);
- return NULL;
-}
-
-
-static void *
-befs_fast_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry));
+ befs_debug(sb, "Follow long symlink");
- nd_set_link(nd, befs_ino->i_data.symlink);
- return NULL;
+ link = kmalloc(len, GFP_NOFS);
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ if (befs_read_lsymlink(sb, data, link, len) != len) {
+ kfree(link);
+ befs_error(sb, "Failed to read entire long symlink");
+ return ERR_PTR(-EIO);
+ }
+ link[len - 1] = '\0';
+ return *cookie = link;
}
/*
total_size = total_mapping_size(elf_phdata,
loc->elf_ex.e_phnum);
if (!total_size) {
- error = -EINVAL;
+ retval = -EINVAL;
goto out_free_dentry;
}
}
* indirect refs to their parent bytenr.
* When roots are found, they're added to the roots list
*
+ * NOTE: This can return values > 0
+ *
* FIXME some caching might speed things up
*/
static int find_parent_nodes(struct btrfs_trans_handle *trans,
return ret;
}
+/**
+ * btrfs_check_shared - tell us whether an extent is shared
+ *
+ * @trans: optional trans handle
+ *
+ * btrfs_check_shared uses the backref walking code but will short
+ * circuit as soon as it finds a root or inode that doesn't match the
+ * one passed in. This provides a significant performance benefit for
+ * callers (such as fiemap) which want to know whether the extent is
+ * shared but do not need a ref count.
+ *
+ * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error.
+ */
int btrfs_check_shared(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 root_objectid,
u64 inum, u64 bytenr)
ret = find_parent_nodes(trans, fs_info, bytenr, elem.seq, tmp,
roots, NULL, root_objectid, inum);
if (ret == BACKREF_FOUND_SHARED) {
+ /* this is the only condition under which we return 1 */
ret = 1;
break;
}
if (ret < 0 && ret != -ENOENT)
break;
+ ret = 0;
node = ulist_next(tmp, &uiter);
if (!node)
break;
btrfs_mark_buffer_dirty(leaf);
fail:
btrfs_release_path(path);
- if (ret)
- btrfs_abort_transaction(trans, root, ret);
return ret;
}
ret = 0;
}
}
- if (!ret)
+ if (!ret) {
ret = write_one_cache_group(trans, root, path, cache);
+ /*
+ * Our block group might still be attached to the list
+ * of new block groups in the transaction handle of some
+ * other task (struct btrfs_trans_handle->new_bgs). This
+ * means its block group item isn't yet in the extent
+ * tree. If this happens ignore the error, as we will
+ * try again later in the critical section of the
+ * transaction commit.
+ */
+ if (ret == -ENOENT) {
+ ret = 0;
+ spin_lock(&cur_trans->dirty_bgs_lock);
+ if (list_empty(&cache->dirty_list)) {
+ list_add_tail(&cache->dirty_list,
+ &cur_trans->dirty_bgs);
+ btrfs_get_block_group(cache);
+ }
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+ } else if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ }
+ }
/* if its not on the io list, we need to put the block group */
if (should_put)
ret = 0;
}
}
- if (!ret)
+ if (!ret) {
ret = write_one_cache_group(trans, root, path, cache);
+ if (ret)
+ btrfs_abort_transaction(trans, root, ret);
+ }
/* if its not on the io list, we need to put the block group */
if (should_put)
goto again;
}
+ /*
+ * if we are changing raid levels, try to allocate a corresponding
+ * block group with the new raid level.
+ */
+ alloc_flags = update_block_group_flags(root, cache->flags);
+ if (alloc_flags != cache->flags) {
+ ret = do_chunk_alloc(trans, root, alloc_flags,
+ CHUNK_ALLOC_FORCE);
+ /*
+ * ENOSPC is allowed here, we may have enough space
+ * already allocated at the new raid level to
+ * carry on
+ */
+ if (ret == -ENOSPC)
+ ret = 0;
+ if (ret < 0)
+ goto out;
+ }
ret = set_block_group_ro(cache, 0);
if (!ret)
out:
if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
alloc_flags = update_block_group_flags(root, cache->flags);
+ lock_chunks(root->fs_info->chunk_root);
check_system_chunk(trans, root, alloc_flags);
+ unlock_chunks(root->fs_info->chunk_root);
}
mutex_unlock(&root->fs_info->ro_block_group_mutex);
start >> PAGE_CACHE_SHIFT);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
+ /*
+ * Lock our eb's refs_lock to avoid races with
+ * free_extent_buffer. When we get our eb it might be flagged
+ * with EXTENT_BUFFER_STALE and another task running
+ * free_extent_buffer might have seen that flag set,
+ * eb->refs == 2, that the buffer isn't under IO (dirty and
+ * writeback flags not set) and it's still in the tree (flag
+ * EXTENT_BUFFER_TREE_REF set), therefore being in the process
+ * of decrementing the extent buffer's reference count twice.
+ * So here we could race and increment the eb's reference count,
+ * clear its stale flag, mark it as dirty and drop our reference
+ * before the other task finishes executing free_extent_buffer,
+ * which would later result in an attempt to free an extent
+ * buffer that is dirty.
+ */
+ if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) {
+ spin_lock(&eb->refs_lock);
+ spin_unlock(&eb->refs_lock);
+ }
mark_extent_buffer_accessed(eb, NULL);
return eb;
}
mapping_set_gfp_mask(inode->i_mapping,
mapping_gfp_mask(inode->i_mapping) &
- ~(GFP_NOFS & ~__GFP_HIGHMEM));
+ ~(__GFP_FS | __GFP_HIGHMEM));
return inode;
}
struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
int ret;
struct btrfs_io_ctl io_ctl;
+ bool release_metadata = true;
if (!btrfs_test_opt(root, INODE_MAP_CACHE))
return 0;
memset(&io_ctl, 0, sizeof(io_ctl));
ret = __btrfs_write_out_cache(root, inode, ctl, NULL, &io_ctl,
trans, path, 0);
- if (!ret)
+ if (!ret) {
+ /*
+ * At this point writepages() didn't error out, so our metadata
+ * reservation is released when the writeback finishes, at
+ * inode.c:btrfs_finish_ordered_io(), regardless of it finishing
+ * with or without an error.
+ */
+ release_metadata = false;
ret = btrfs_wait_cache_io(root, trans, NULL, &io_ctl, path, 0);
+ }
if (ret) {
- btrfs_delalloc_release_metadata(inode, inode->i_size);
+ if (release_metadata)
+ btrfs_delalloc_release_metadata(inode, inode->i_size);
#ifdef DEBUG
btrfs_err(root->fs_info,
"failed to write free ino cache for root %llu",
int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
{
int ret = 0;
+ int ret_wb = 0;
u64 end;
u64 orig_end;
struct btrfs_ordered_extent *ordered;
if (ret)
return ret;
- ret = filemap_fdatawait_range(inode->i_mapping, start, orig_end);
- if (ret)
- return ret;
+ /*
+ * If we have a writeback error don't return immediately. Wait first
+ * for any ordered extents that haven't completed yet. This is to make
+ * sure no one can dirty the same page ranges and call writepages()
+ * before the ordered extents complete - to avoid failures (-EEXIST)
+ * when adding the new ordered extents to the ordered tree.
+ */
+ ret_wb = filemap_fdatawait_range(inode->i_mapping, start, orig_end);
end = orig_end;
while (1) {
break;
end--;
}
- return ret;
+ return ret_wb ? ret_wb : ret;
}
/*
{
u64 chunk_offset;
+ ASSERT(mutex_is_locked(&extent_root->fs_info->chunk_mutex));
chunk_offset = find_next_chunk(extent_root->fs_info);
return __btrfs_alloc_chunk(trans, extent_root, chunk_offset, type);
}
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
-#include <linux/namei.h>
#include <linux/writeback.h>
#include <linux/vmalloc.h>
#include <linux/posix_acl.h>
else
kfree(sym); /* lost a race */
}
+ inode->i_link = ci->i_symlink;
break;
case S_IFDIR:
inode->i_op = &ceph_dir_iops;
/*
* symlinks
*/
-static void *ceph_sym_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct ceph_inode_info *ci = ceph_inode(d_inode(dentry));
- nd_set_link(nd, ci->i_symlink);
- return NULL;
-}
-
static const struct inode_operations ceph_symlink_iops = {
.readlink = generic_readlink,
- .follow_link = ceph_sym_follow_link,
+ .follow_link = simple_follow_link,
.setattr = ceph_setattr,
.getattr = ceph_getattr,
.setxattr = ceph_setxattr,
#include "cifsfs.h"
#include "dns_resolve.h"
#include "cifs_debug.h"
+#include "cifs_unicode.h"
static LIST_HEAD(cifs_dfs_automount_list);
xid = get_xid();
rc = get_dfs_path(xid, ses, full_path + 1, cifs_sb->local_nls,
&num_referrals, &referrals,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_remap(cifs_sb));
free_xid(xid);
cifs_put_tlink(tlink);
#include "cifsglob.h"
#include "cifs_debug.h"
-/*
- * cifs_utf16_bytes - how long will a string be after conversion?
- * @utf16 - pointer to input string
- * @maxbytes - don't go past this many bytes of input string
- * @codepage - destination codepage
- *
- * Walk a utf16le string and return the number of bytes that the string will
- * be after being converted to the given charset, not including any null
- * termination required. Don't walk past maxbytes in the source buffer.
- */
-int
-cifs_utf16_bytes(const __le16 *from, int maxbytes,
- const struct nls_table *codepage)
-{
- int i;
- int charlen, outlen = 0;
- int maxwords = maxbytes / 2;
- char tmp[NLS_MAX_CHARSET_SIZE];
- __u16 ftmp;
-
- for (i = 0; i < maxwords; i++) {
- ftmp = get_unaligned_le16(&from[i]);
- if (ftmp == 0)
- break;
-
- charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE);
- if (charlen > 0)
- outlen += charlen;
- else
- outlen++;
- }
-
- return outlen;
-}
-
int cifs_remap(struct cifs_sb_info *cifs_sb)
{
int map_type;
* enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
*/
static int
-cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
+cifs_mapchar(char *target, const __u16 *from, const struct nls_table *cp,
int maptype)
{
int len = 1;
+ __u16 src_char;
+
+ src_char = *from;
if ((maptype == SFM_MAP_UNI_RSVD) && convert_sfm_char(src_char, target))
return len;
/* if character not one of seven in special remap set */
len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);
- if (len <= 0) {
- *target = '?';
- len = 1;
- }
+ if (len <= 0)
+ goto surrogate_pair;
+
+ return len;
+
+surrogate_pair:
+ /* convert SURROGATE_PAIR and IVS */
+ if (strcmp(cp->charset, "utf8"))
+ goto unknown;
+ len = utf16s_to_utf8s(from, 3, UTF16_LITTLE_ENDIAN, target, 6);
+ if (len <= 0)
+ goto unknown;
+ return len;
+
+unknown:
+ *target = '?';
+ len = 1;
return len;
}
int nullsize = nls_nullsize(codepage);
int fromwords = fromlen / 2;
char tmp[NLS_MAX_CHARSET_SIZE];
- __u16 ftmp;
+ __u16 ftmp[3]; /* ftmp[3] = 3array x 2bytes = 6bytes UTF-16 */
/*
* because the chars can be of varying widths, we need to take care
safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);
for (i = 0; i < fromwords; i++) {
- ftmp = get_unaligned_le16(&from[i]);
- if (ftmp == 0)
+ ftmp[0] = get_unaligned_le16(&from[i]);
+ if (ftmp[0] == 0)
break;
+ if (i + 1 < fromwords)
+ ftmp[1] = get_unaligned_le16(&from[i + 1]);
+ else
+ ftmp[1] = 0;
+ if (i + 2 < fromwords)
+ ftmp[2] = get_unaligned_le16(&from[i + 2]);
+ else
+ ftmp[2] = 0;
/*
* check to see if converting this character might make the
/* put converted char into 'to' buffer */
charlen = cifs_mapchar(&to[outlen], ftmp, codepage, map_type);
outlen += charlen;
+
+ /* charlen (=bytes of UTF-8 for 1 character)
+ * 4bytes UTF-8(surrogate pair) is charlen=4
+ * (4bytes UTF-16 code)
+ * 7-8bytes UTF-8(IVS) is charlen=3+4 or 4+4
+ * (2 UTF-8 pairs divided to 2 UTF-16 pairs) */
+ if (charlen == 4)
+ i++;
+ else if (charlen >= 5)
+ /* 5-6bytes UTF-8 */
+ i += 2;
}
/* properly null-terminate string */
return i;
}
+/*
+ * cifs_utf16_bytes - how long will a string be after conversion?
+ * @utf16 - pointer to input string
+ * @maxbytes - don't go past this many bytes of input string
+ * @codepage - destination codepage
+ *
+ * Walk a utf16le string and return the number of bytes that the string will
+ * be after being converted to the given charset, not including any null
+ * termination required. Don't walk past maxbytes in the source buffer.
+ */
+int
+cifs_utf16_bytes(const __le16 *from, int maxbytes,
+ const struct nls_table *codepage)
+{
+ int i;
+ int charlen, outlen = 0;
+ int maxwords = maxbytes / 2;
+ char tmp[NLS_MAX_CHARSET_SIZE];
+ __u16 ftmp[3];
+
+ for (i = 0; i < maxwords; i++) {
+ ftmp[0] = get_unaligned_le16(&from[i]);
+ if (ftmp[0] == 0)
+ break;
+ if (i + 1 < maxwords)
+ ftmp[1] = get_unaligned_le16(&from[i + 1]);
+ else
+ ftmp[1] = 0;
+ if (i + 2 < maxwords)
+ ftmp[2] = get_unaligned_le16(&from[i + 2]);
+ else
+ ftmp[2] = 0;
+
+ charlen = cifs_mapchar(tmp, ftmp, codepage, NO_MAP_UNI_RSVD);
+ outlen += charlen;
+ }
+
+ return outlen;
+}
+
/*
* cifs_strndup_from_utf16 - copy a string from wire format to the local
* codepage
char src_char;
__le16 dst_char;
wchar_t tmp;
+ wchar_t *wchar_to; /* UTF-16 */
+ int ret;
+ unicode_t u;
if (map_chars == NO_MAP_UNI_RSVD)
return cifs_strtoUTF16(target, source, PATH_MAX, cp);
+ wchar_to = kzalloc(6, GFP_KERNEL);
+
for (i = 0; i < srclen; j++) {
src_char = source[i];
charlen = 1;
* if no match, use question mark, which at least in
* some cases serves as wild card
*/
- if (charlen < 1) {
- dst_char = cpu_to_le16(0x003f);
- charlen = 1;
+ if (charlen > 0)
+ goto ctoUTF16;
+
+ /* convert SURROGATE_PAIR */
+ if (strcmp(cp->charset, "utf8") || !wchar_to)
+ goto unknown;
+ if (*(source + i) & 0x80) {
+ charlen = utf8_to_utf32(source + i, 6, &u);
+ if (charlen < 0)
+ goto unknown;
+ } else
+ goto unknown;
+ ret = utf8s_to_utf16s(source + i, charlen,
+ UTF16_LITTLE_ENDIAN,
+ wchar_to, 6);
+ if (ret < 0)
+ goto unknown;
+
+ i += charlen;
+ dst_char = cpu_to_le16(*wchar_to);
+ if (charlen <= 3)
+ /* 1-3bytes UTF-8 to 2bytes UTF-16 */
+ put_unaligned(dst_char, &target[j]);
+ else if (charlen == 4) {
+ /* 4bytes UTF-8(surrogate pair) to 4bytes UTF-16
+ * 7-8bytes UTF-8(IVS) divided to 2 UTF-16
+ * (charlen=3+4 or 4+4) */
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 1));
+ j++;
+ put_unaligned(dst_char, &target[j]);
+ } else if (charlen >= 5) {
+ /* 5-6bytes UTF-8 to 6bytes UTF-16 */
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 1));
+ j++;
+ put_unaligned(dst_char, &target[j]);
+ dst_char = cpu_to_le16(*(wchar_to + 2));
+ j++;
+ put_unaligned(dst_char, &target[j]);
}
+ continue;
+
+unknown:
+ dst_char = cpu_to_le16(0x003f);
+ charlen = 1;
}
+
+ctoUTF16:
/*
* character may take more than one byte in the source string,
* but will take exactly two bytes in the target string
ctoUTF16_out:
put_unaligned(0, &target[j]); /* Null terminate target unicode string */
+ kfree(wchar_to);
return j;
}
seq_puts(s, ",nouser_xattr");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
seq_puts(s, ",mapchars");
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
+ seq_puts(s, ",mapposix");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
seq_puts(s, ",sfu");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
#endif
/* Functions related to symlinks */
-extern void *cifs_follow_link(struct dentry *direntry, struct nameidata *nd);
+extern const char *cifs_follow_link(struct dentry *direntry, void **cookie);
extern int cifs_readlink(struct dentry *direntry, char __user *buffer,
int buflen);
extern int cifs_symlink(struct inode *inode, struct dentry *direntry,
extern int CIFSUnixCreateSymLink(const unsigned int xid,
struct cifs_tcon *tcon,
const char *fromName, const char *toName,
- const struct nls_table *nls_codepage);
+ const struct nls_table *nls_codepage, int remap);
extern int CIFSSMBUnixQuerySymLink(const unsigned int xid,
struct cifs_tcon *tcon,
const unsigned char *searchName, char **syminfo,
- const struct nls_table *nls_codepage);
+ const struct nls_table *nls_codepage, int remap);
extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
__u16 fid, char **symlinkinfo,
const struct nls_table *nls_codepage);
int
CIFSUnixCreateSymLink(const unsigned int xid, struct cifs_tcon *tcon,
const char *fromName, const char *toName,
- const struct nls_table *nls_codepage)
+ const struct nls_table *nls_codepage, int remap)
{
TRANSACTION2_SPI_REQ *pSMB = NULL;
TRANSACTION2_SPI_RSP *pSMBr = NULL;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifs_strtoUTF16((__le16 *) pSMB->FileName, fromName,
- /* find define for this maxpathcomponent */
- PATH_MAX, nls_codepage);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName, fromName,
+ /* find define for this maxpathcomponent */
+ PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len_target =
- cifs_strtoUTF16((__le16 *) data_offset, toName, PATH_MAX
- /* find define for this maxpathcomponent */
- , nls_codepage);
+ cifsConvertToUTF16((__le16 *) data_offset, toName,
+ /* find define for this maxpathcomponent */
+ PATH_MAX, nls_codepage, remap);
name_len_target++; /* trailing null */
name_len_target *= 2;
} else { /* BB improve the check for buffer overruns BB */
int
CIFSSMBUnixQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
const unsigned char *searchName, char **symlinkinfo,
- const struct nls_table *nls_codepage)
+ const struct nls_table *nls_codepage, int remap)
{
/* SMB_QUERY_FILE_UNIX_LINK */
TRANSACTION2_QPI_REQ *pSMB = NULL;
if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
name_len =
- cifs_strtoUTF16((__le16 *) pSMB->FileName, searchName,
- PATH_MAX, nls_codepage);
+ cifsConvertToUTF16((__le16 *) pSMB->FileName,
+ searchName, PATH_MAX, nls_codepage,
+ remap);
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
strncpy(pSMB->RequestFileName, search_name, name_len);
}
- if (ses->server && ses->server->sign)
+ if (ses->server->sign)
pSMB->hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
pSMB->hdr.Uid = ses->Suid;
rc = generic_ip_connect(server);
if (rc) {
cifs_dbg(FYI, "reconnect error %d\n", rc);
+ mutex_unlock(&server->srv_mutex);
msleep(3000);
} else {
atomic_inc(&tcpSesReconnectCount);
if (server->tcpStatus != CifsExiting)
server->tcpStatus = CifsNeedNegotiate;
spin_unlock(&GlobalMid_Lock);
+ mutex_unlock(&server->srv_mutex);
}
- mutex_unlock(&server->srv_mutex);
} while (server->tcpStatus == CifsNeedReconnect);
return rc;
}
rc = CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_remap(cifs_sb));
if (rc)
goto mknod_out;
posix_flags = cifs_posix_convert_flags(f_flags);
rc = CIFSPOSIXCreate(xid, tcon, posix_flags, mode, pnetfid, presp_data,
poplock, full_path, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
if (rc)
rc = server->ops->mand_unlock_range(cfile, flock, xid);
out:
- if (flock->fl_flags & FL_POSIX)
- posix_lock_file_wait(file, flock);
+ if (flock->fl_flags & FL_POSIX && !rc)
+ rc = posix_lock_file_wait(file, flock);
return rc;
}
/* could have done a find first instead but this returns more info */
rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data,
- cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_sb->local_nls, cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
if (!rc) {
rc = -ENOMEM;
} else {
/* we already have inode, update it */
+
+ /* if uniqueid is different, return error */
+ if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM &&
+ CIFS_I(*pinode)->uniqueid != fattr.cf_uniqueid)) {
+ rc = -ESTALE;
+ goto cgiiu_exit;
+ }
+
+ /* if filetype is different, return error */
+ if (unlikely(((*pinode)->i_mode & S_IFMT) !=
+ (fattr.cf_mode & S_IFMT))) {
+ rc = -ESTALE;
+ goto cgiiu_exit;
+ }
+
cifs_fattr_to_inode(*pinode, &fattr);
}
+cgiiu_exit:
return rc;
}
if (!*inode)
rc = -ENOMEM;
} else {
+ /* we already have inode, update it */
+
+ /* if filetype is different, return error */
+ if (unlikely(((*inode)->i_mode & S_IFMT) !=
+ (fattr.cf_mode & S_IFMT))) {
+ rc = -ESTALE;
+ goto cgii_exit;
+ }
+
cifs_fattr_to_inode(*inode, &fattr);
}
pTcon = tlink_tcon(tlink);
rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, args,
cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
}
return rc;
}
-void *
-cifs_follow_link(struct dentry *direntry, struct nameidata *nd)
+const char *
+cifs_follow_link(struct dentry *direntry, void **cookie)
{
struct inode *inode = d_inode(direntry);
int rc = -ENOMEM;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
- rc = PTR_ERR(tlink);
- tlink = NULL;
- goto out;
+ free_xid(xid);
+ return ERR_CAST(tlink);
}
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
full_path = build_path_from_dentry(direntry);
- if (!full_path)
- goto out;
+ if (!full_path) {
+ free_xid(xid);
+ cifs_put_tlink(tlink);
+ return ERR_PTR(-ENOMEM);
+ }
cifs_dbg(FYI, "Full path: %s inode = 0x%p\n", full_path, inode);
&target_path, cifs_sb);
kfree(full_path);
-out:
+ free_xid(xid);
+ cifs_put_tlink(tlink);
if (rc != 0) {
kfree(target_path);
- target_path = ERR_PTR(rc);
+ return ERR_PTR(rc);
}
-
- free_xid(xid);
- if (tlink)
- cifs_put_tlink(tlink);
- nd_set_link(nd, target_path);
- return NULL;
+ return *cookie = target_path;
}
int
rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname);
else if (pTcon->unix_ext)
rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname,
- cifs_sb->local_nls);
+ cifs_sb->local_nls,
+ cifs_remap(cifs_sb));
/* else
rc = CIFSCreateReparseSymLink(xid, pTcon, fromName, toName,
cifs_sb_target->local_nls); */
if (dentry) {
inode = d_inode(dentry);
if (inode) {
+ if (d_mountpoint(dentry))
+ goto out;
/*
* If we're generating inode numbers, then we don't
* want to clobber the existing one with the one that
/* Check for unix extensions */
if (cap_unix(tcon->ses)) {
rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path,
- cifs_sb->local_nls);
+ cifs_sb->local_nls,
+ cifs_remap(cifs_sb));
if (rc == -EREMOTE)
rc = cifs_unix_dfs_readlink(xid, tcon, full_path,
target_path,
/* GLOBAL_CAP_LARGE_MTU will only be set if dialect > SMB2.02 */
/* See sections 2.2.4 and 3.2.4.1.5 of MS-SMB2 */
- if ((tcon->ses) &&
+ if ((tcon->ses) && (tcon->ses->server) &&
(tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
hdr->CreditCharge = cpu_to_le16(1);
/* else CreditCharge MBZ */
}
-static void *configfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *configfs_follow_link(struct dentry *dentry, void **cookie)
{
- int error = -ENOMEM;
unsigned long page = get_zeroed_page(GFP_KERNEL);
+ int error;
- if (page) {
- error = configfs_getlink(dentry, (char *)page);
- if (!error) {
- nd_set_link(nd, (char *)page);
- return (void *)page;
- }
- }
-
- nd_set_link(nd, ERR_PTR(error));
- return NULL;
-}
+ if (!page)
+ return ERR_PTR(-ENOMEM);
-static void configfs_put_link(struct dentry *dentry, struct nameidata *nd,
- void *cookie)
-{
- if (cookie) {
- unsigned long page = (unsigned long)cookie;
- free_page(page);
+ error = configfs_getlink(dentry, (char *)page);
+ if (!error) {
+ return *cookie = (void *)page;
}
+
+ free_page(page);
+ return ERR_PTR(error);
}
const struct inode_operations configfs_symlink_inode_operations = {
.follow_link = configfs_follow_link,
.readlink = generic_readlink,
- .put_link = configfs_put_link,
+ .put_link = free_page_put_link,
.setattr = configfs_setattr,
};
}
/**
- * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
+ * dentry_rcuwalk_invalidate - invalidate in-progress rcu-walk lookups
* @dentry: the target dentry
* After this call, in-progress rcu-walk path lookup will fail. This
* should be called after unhashing, and after changing d_inode (if
* the dentry has not already been unhashed).
*/
-static inline void dentry_rcuwalk_barrier(struct dentry *dentry)
+static inline void dentry_rcuwalk_invalidate(struct dentry *dentry)
{
- assert_spin_locked(&dentry->d_lock);
- /* Go through a barrier */
- write_seqcount_barrier(&dentry->d_seq);
+ lockdep_assert_held(&dentry->d_lock);
+ /* Go through am invalidation barrier */
+ write_seqcount_invalidate(&dentry->d_seq);
}
/*
struct inode *inode = dentry->d_inode;
__d_clear_type_and_inode(dentry);
hlist_del_init(&dentry->d_u.d_alias);
- dentry_rcuwalk_barrier(dentry);
+ dentry_rcuwalk_invalidate(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
__hlist_bl_del(&dentry->d_hash);
dentry->d_hash.pprev = NULL;
hlist_bl_unlock(b);
- dentry_rcuwalk_barrier(dentry);
+ dentry_rcuwalk_invalidate(dentry);
}
}
EXPORT_SYMBOL(__d_drop);
/* might go back up the wrong parent if we have had a rename. */
if (need_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_child.next;
- while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+ /* go into the first sibling still alive */
+ do {
+ next = child->d_child.next;
if (next == &this_parent->d_subdirs)
goto ascend;
child = list_entry(next, struct dentry, d_child);
- next = next->next;
- }
+ } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
rcu_read_unlock();
goto resume;
}
if (inode)
hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
__d_set_inode_and_type(dentry, inode, add_flags);
- dentry_rcuwalk_barrier(dentry);
+ dentry_rcuwalk_invalidate(dentry);
spin_unlock(&dentry->d_lock);
fsnotify_d_instantiate(dentry, inode);
}
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/pagemap.h>
-#include <linux/namei.h>
#include <linux/debugfs.h>
#include <linux/io.h>
#include <linux/slab.h>
.llseek = noop_llseek,
};
-static void *debugfs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- nd_set_link(nd, d_inode(dentry)->i_private);
- return NULL;
-}
-
-const struct inode_operations debugfs_link_operations = {
- .readlink = generic_readlink,
- .follow_link = debugfs_follow_link,
-};
-
static int debugfs_u8_set(void *data, u64 val)
{
*(u8 *)data = val;
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (S_ISLNK(inode->i_mode))
- kfree(inode->i_private);
+ kfree(inode->i_link);
}
static const struct super_operations debugfs_super_operations = {
return failed_creating(dentry);
}
inode->i_mode = S_IFLNK | S_IRWXUGO;
- inode->i_op = &debugfs_link_operations;
- inode->i_private = link;
+ inode->i_op = &simple_symlink_inode_operations;
+ inode->i_link = link;
d_instantiate(dentry, inode);
return end_creating(dentry);
}
* @directory_inode: inode of the new file's dentry's parent in ecryptfs
* @ecryptfs_dentry: New file's dentry in ecryptfs
* @mode: The mode of the new file
- * @nd: nameidata of ecryptfs' parent's dentry & vfsmount
*
* Creates the underlying file and the eCryptfs inode which will link to
* it. It will also update the eCryptfs directory inode to mimic the
* ecryptfs_lookup
* @ecryptfs_dir_inode: The eCryptfs directory inode
* @ecryptfs_dentry: The eCryptfs dentry that we are looking up
- * @ecryptfs_nd: nameidata; may be NULL
+ * @flags: lookup flags
*
* Find a file on disk. If the file does not exist, then we'll add it to the
* dentry cache and continue on to read it from the disk.
return rc ? ERR_PTR(rc) : buf;
}
-static void *ecryptfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *ecryptfs_follow_link(struct dentry *dentry, void **cookie)
{
size_t len;
char *buf = ecryptfs_readlink_lower(dentry, &len);
if (IS_ERR(buf))
- goto out;
+ return buf;
fsstack_copy_attr_atime(d_inode(dentry),
d_inode(ecryptfs_dentry_to_lower(dentry)));
buf[len] = '\0';
-out:
- nd_set_link(nd, buf);
- return NULL;
+ return *cookie = buf;
}
/**
if (stack_base > STACK_SIZE_MAX)
stack_base = STACK_SIZE_MAX;
+ /* Add space for stack randomization. */
+ stack_base += (STACK_RND_MASK << PAGE_SHIFT);
+
/* Make sure we didn't let the argument array grow too large. */
if (vma->vm_end - vma->vm_start > stack_base)
return -ENOMEM;
libore-y := ore.o ore_raid.o
obj-$(CONFIG_ORE) += libore.o
-exofs-y := inode.o file.o symlink.o namei.o dir.o super.o sys.o
+exofs-y := inode.o file.o namei.o dir.o super.o sys.o
obj-$(CONFIG_EXOFS_FS) += exofs.o
extern const struct inode_operations exofs_dir_inode_operations;
extern const struct inode_operations exofs_special_inode_operations;
-/* symlink.c */
-extern const struct inode_operations exofs_symlink_inode_operations;
-extern const struct inode_operations exofs_fast_symlink_inode_operations;
-
/* exofs_init_comps will initialize an ore_components device array
* pointing to a single ore_comp struct, and a round-robin view
* of the device table.
inode->i_fop = &exofs_dir_operations;
inode->i_mapping->a_ops = &exofs_aops;
} else if (S_ISLNK(inode->i_mode)) {
- if (exofs_inode_is_fast_symlink(inode))
- inode->i_op = &exofs_fast_symlink_inode_operations;
- else {
- inode->i_op = &exofs_symlink_inode_operations;
+ if (exofs_inode_is_fast_symlink(inode)) {
+ inode->i_op = &simple_symlink_inode_operations;
+ inode->i_link = (char *)oi->i_data;
+ } else {
+ inode->i_op = &page_symlink_inode_operations;
inode->i_mapping->a_ops = &exofs_aops;
}
} else {
oi = exofs_i(inode);
if (l > sizeof(oi->i_data)) {
/* slow symlink */
- inode->i_op = &exofs_symlink_inode_operations;
+ inode->i_op = &page_symlink_inode_operations;
inode->i_mapping->a_ops = &exofs_aops;
memset(oi->i_data, 0, sizeof(oi->i_data));
goto out_fail;
} else {
/* fast symlink */
- inode->i_op = &exofs_fast_symlink_inode_operations;
+ inode->i_op = &simple_symlink_inode_operations;
+ inode->i_link = (char *)oi->i_data;
memcpy(oi->i_data, symname, l);
inode->i_size = l-1;
}
+++ /dev/null
-/*
- * Copyright (C) 2005, 2006
- * Avishay Traeger (avishay@gmail.com)
- * Copyright (C) 2008, 2009
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * Copyrights for code taken from ext2:
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- * from
- * linux/fs/minix/inode.c
- * Copyright (C) 1991, 1992 Linus Torvalds
- *
- * This file is part of exofs.
- *
- * exofs is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation. Since it is based on ext2, and the only
- * valid version of GPL for the Linux kernel is version 2, the only valid
- * version of GPL for exofs is version 2.
- *
- * exofs is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with exofs; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-#include <linux/namei.h>
-
-#include "exofs.h"
-
-static void *exofs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct exofs_i_info *oi = exofs_i(d_inode(dentry));
-
- nd_set_link(nd, (char *)oi->i_data);
- return NULL;
-}
-
-const struct inode_operations exofs_symlink_inode_operations = {
- .readlink = generic_readlink,
- .follow_link = page_follow_link_light,
- .put_link = page_put_link,
-};
-
-const struct inode_operations exofs_fast_symlink_inode_operations = {
- .readlink = generic_readlink,
- .follow_link = exofs_follow_link,
-};
inode->i_mapping->a_ops = &ext2_aops;
} else if (S_ISLNK(inode->i_mode)) {
if (ext2_inode_is_fast_symlink(inode)) {
+ inode->i_link = (char *)ei->i_data;
inode->i_op = &ext2_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) - 1);
} else {
/* fast symlink */
inode->i_op = &ext2_fast_symlink_inode_operations;
- memcpy((char*)(EXT2_I(inode)->i_data),symname,l);
+ inode->i_link = (char*)EXT2_I(inode)->i_data;
+ memcpy(inode->i_link, symname, l);
inode->i_size = l-1;
}
mark_inode_dirty(inode);
#include "ext2.h"
#include "xattr.h"
-#include <linux/namei.h>
-
-static void *ext2_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct ext2_inode_info *ei = EXT2_I(d_inode(dentry));
- nd_set_link(nd, (char *)ei->i_data);
- return NULL;
-}
const struct inode_operations ext2_symlink_inode_operations = {
.readlink = generic_readlink,
const struct inode_operations ext2_fast_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = ext2_follow_link,
+ .follow_link = simple_follow_link,
.setattr = ext2_setattr,
#ifdef CONFIG_EXT2_FS_XATTR
.setxattr = generic_setxattr,
inode->i_op = &ext3_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) - 1);
+ inode->i_link = (char *)ei->i_data;
} else {
inode->i_op = &ext3_symlink_inode_operations;
ext3_set_aops(inode);
}
} else {
inode->i_op = &ext3_fast_symlink_inode_operations;
- memcpy((char*)&EXT3_I(inode)->i_data,symname,l);
+ inode->i_link = (char*)&EXT3_I(inode)->i_data;
+ memcpy(inode->i_link, symname, l);
inode->i_size = l-1;
}
EXT3_I(inode)->i_disksize = inode->i_size;
* ext3 symlink handling code
*/
-#include <linux/namei.h>
#include "ext3.h"
#include "xattr.h"
-static void * ext3_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct ext3_inode_info *ei = EXT3_I(d_inode(dentry));
- nd_set_link(nd, (char*)ei->i_data);
- return NULL;
-}
-
const struct inode_operations ext3_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
const struct inode_operations ext3_fast_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = ext3_follow_link,
+ .follow_link = simple_follow_link,
.setattr = ext3_setattr,
#ifdef CONFIG_EXT3_FS_XATTR
.setxattr = generic_setxattr,
unsigned nr_pages);
/* symlink.c */
+extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
struct ext4_map_blocks *map, int flags);
extern int ext4_ext_calc_metadata_amount(struct inode *inode,
ext4_lblk_t lblocks);
-extern int ext4_extent_tree_init(handle_t *, struct inode *);
extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
int num,
struct ext4_ext_path *path);
ext4_put_nojournal(handle);
return 0;
}
+
+ if (!handle->h_transaction) {
+ err = jbd2_journal_stop(handle);
+ return handle->h_err ? handle->h_err : err;
+ }
+
sb = handle->h_transaction->t_journal->j_private;
err = handle->h_err;
rc = jbd2_journal_stop(handle);
ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
ext4_lblk_t last = lblock + len - 1;
- if (lblock > last)
+ if (len == 0 || lblock > last)
return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
loff_t new_size, ioffset;
int ret;
+ /*
+ * We need to test this early because xfstests assumes that a
+ * collapse range of (0, 1) will return EOPNOTSUPP if the file
+ * system does not support collapse range.
+ */
+ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ return -EOPNOTSUPP;
+
/* Collapse range works only on fs block size aligned offsets. */
if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
len & (EXT4_CLUSTER_SIZE(sb) - 1))
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
- if (ext4_inode_is_fast_symlink(inode) &&
- !ext4_encrypted_inode(inode)) {
+ if (ext4_encrypted_inode(inode)) {
+ inode->i_op = &ext4_encrypted_symlink_inode_operations;
+ ext4_set_aops(inode);
+ } else if (ext4_inode_is_fast_symlink(inode)) {
+ inode->i_link = (char *)ei->i_data;
inode->i_op = &ext4_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) - 1);
int inode_size = EXT4_INODE_SIZE(sb);
oi.orig_ino = orig_ino;
- ino = orig_ino & ~(inodes_per_block - 1);
+ ino = (orig_ino & ~(inodes_per_block - 1)) + 1;
for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
if (ino == orig_ino)
continue;
goto err_drop_inode;
sd->len = cpu_to_le16(ostr.len);
disk_link.name = (char *) sd;
+ inode->i_op = &ext4_encrypted_symlink_inode_operations;
}
if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
- inode->i_op = &ext4_symlink_inode_operations;
+ if (!encryption_required)
+ inode->i_op = &ext4_symlink_inode_operations;
ext4_set_aops(inode);
/*
* We cannot call page_symlink() with transaction started
} else {
/* clear the extent format for fast symlink */
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
- inode->i_op = encryption_required ?
- &ext4_symlink_inode_operations :
- &ext4_fast_symlink_inode_operations;
+ if (!encryption_required) {
+ inode->i_op = &ext4_fast_symlink_inode_operations;
+ inode->i_link = (char *)&EXT4_I(inode)->i_data;
+ }
memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name,
disk_link.len);
inode->i_size = disk_link.len - 1;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ if (bdev_read_only(sb->s_bdev))
+ return;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
es->s_last_error_time = cpu_to_le32(get_seconds());
strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
#include "xattr.h"
#ifdef CONFIG_EXT4_FS_ENCRYPTION
-static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *ext4_follow_link(struct dentry *dentry, void **cookie)
{
struct page *cpage = NULL;
char *caddr, *paddr = NULL;
int res;
u32 plen, max_size = inode->i_sb->s_blocksize;
- if (!ext4_encrypted_inode(inode))
- return page_follow_link_light(dentry, nd);
-
ctx = ext4_get_fname_crypto_ctx(inode, inode->i_sb->s_blocksize);
if (IS_ERR(ctx))
- return ctx;
+ return ERR_CAST(ctx);
if (ext4_inode_is_fast_symlink(inode)) {
caddr = (char *) EXT4_I(inode)->i_data;
cpage = read_mapping_page(inode->i_mapping, 0, NULL);
if (IS_ERR(cpage)) {
ext4_put_fname_crypto_ctx(&ctx);
- return cpage;
+ return ERR_CAST(cpage);
}
caddr = kmap(cpage);
caddr[size] = 0;
/* Null-terminate the name */
if (res <= plen)
paddr[res] = '\0';
- nd_set_link(nd, paddr);
ext4_put_fname_crypto_ctx(&ctx);
if (cpage) {
kunmap(cpage);
page_cache_release(cpage);
}
- return NULL;
+ return *cookie = paddr;
errout:
ext4_put_fname_crypto_ctx(&ctx);
if (cpage) {
return ERR_PTR(res);
}
-static void ext4_put_link(struct dentry *dentry, struct nameidata *nd,
- void *cookie)
-{
- struct page *page = cookie;
-
- if (!page) {
- kfree(nd_get_link(nd));
- } else {
- kunmap(page);
- page_cache_release(page);
- }
-}
+const struct inode_operations ext4_encrypted_symlink_inode_operations = {
+ .readlink = generic_readlink,
+ .follow_link = ext4_follow_link,
+ .put_link = kfree_put_link,
+ .setattr = ext4_setattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = ext4_listxattr,
+ .removexattr = generic_removexattr,
+};
#endif
-static void *ext4_follow_fast_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct ext4_inode_info *ei = EXT4_I(d_inode(dentry));
- nd_set_link(nd, (char *) ei->i_data);
- return NULL;
-}
-
const struct inode_operations ext4_symlink_inode_operations = {
.readlink = generic_readlink,
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- .follow_link = ext4_follow_link,
- .put_link = ext4_put_link,
-#else
.follow_link = page_follow_link_light,
.put_link = page_put_link,
-#endif
.setattr = ext4_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
const struct inode_operations ext4_fast_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = ext4_follow_fast_link,
+ .follow_link = simple_follow_link,
.setattr = ext4_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ bool locked = false;
int ret;
long diff;
diff = nr_pages_to_write(sbi, DATA, wbc);
+ if (!S_ISDIR(inode->i_mode)) {
+ mutex_lock(&sbi->writepages);
+ locked = true;
+ }
ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
+ if (locked)
+ mutex_unlock(&sbi->writepages);
f2fs_submit_merged_bio(sbi, DATA, WRITE);
struct mutex cp_mutex; /* checkpoint procedure lock */
struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
+ struct mutex writepages; /* mutex for writepages() */
wait_queue_head_t cp_wait;
struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
return err;
}
-static void *f2fs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *f2fs_follow_link(struct dentry *dentry, void **cookie)
{
- struct page *page;
-
- page = page_follow_link_light(dentry, nd);
- if (IS_ERR(page))
- return page;
-
- /* this is broken symlink case */
- if (*nd_get_link(nd) == 0) {
- kunmap(page);
- page_cache_release(page);
- return ERR_PTR(-ENOENT);
+ const char *link = page_follow_link_light(dentry, cookie);
+ if (!IS_ERR(link) && !*link) {
+ /* this is broken symlink case */
+ page_put_link(NULL, *cookie);
+ link = ERR_PTR(-ENOENT);
}
- return page;
+ return link;
}
static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
sbi->raw_super = raw_super;
sbi->raw_super_buf = raw_super_buf;
mutex_init(&sbi->gc_mutex);
+ mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
clear_sbi_flag(sbi, SBI_POR_DOING);
goto out_err;
}
/* copy the full handle */
- if (copy_from_user(handle, ufh,
- sizeof(struct file_handle) +
+ *handle = f_handle;
+ if (copy_from_user(&handle->f_handle,
+ &ufh->f_handle,
f_handle.handle_bytes)) {
retval = -EFAULT;
goto out_handle;
/* vxfs_fshead.c */
extern int vxfs_read_fshead(struct super_block *);
-/* vxfs_immed.c */
-extern const struct inode_operations vxfs_immed_symlink_iops;
-
/* vxfs_inode.c */
extern const struct address_space_operations vxfs_immed_aops;
extern struct kmem_cache *vxfs_inode_cachep;
*/
#include <linux/fs.h>
#include <linux/pagemap.h>
-#include <linux/namei.h>
#include "vxfs.h"
#include "vxfs_extern.h"
#include "vxfs_inode.h"
-static void * vxfs_immed_follow_link(struct dentry *, struct nameidata *);
-
static int vxfs_immed_readpage(struct file *, struct page *);
-/*
- * Inode operations for immed symlinks.
- *
- * Unliked all other operations we do not go through the pagecache,
- * but do all work directly on the inode.
- */
-const struct inode_operations vxfs_immed_symlink_iops = {
- .readlink = generic_readlink,
- .follow_link = vxfs_immed_follow_link,
-};
-
/*
* Address space operations for immed files and directories.
*/
.readpage = vxfs_immed_readpage,
};
-/**
- * vxfs_immed_follow_link - follow immed symlink
- * @dp: dentry for the link
- * @np: pathname lookup data for the current path walk
- *
- * Description:
- * vxfs_immed_follow_link restarts the pathname lookup with
- * the data obtained from @dp.
- *
- * Returns:
- * Zero on success, else a negative error code.
- */
-static void *
-vxfs_immed_follow_link(struct dentry *dp, struct nameidata *np)
-{
- struct vxfs_inode_info *vip = VXFS_INO(d_inode(dp));
- nd_set_link(np, vip->vii_immed.vi_immed);
- return NULL;
-}
-
/**
* vxfs_immed_readpage - read part of an immed inode into pagecache
* @file: file context (unused)
#include <linux/pagemap.h>
#include <linux/kernel.h>
#include <linux/slab.h>
+#include <linux/namei.h>
#include "vxfs.h"
#include "vxfs_inode.h"
ip->i_op = &page_symlink_inode_operations;
ip->i_mapping->a_ops = &vxfs_aops;
} else {
- ip->i_op = &vxfs_immed_symlink_iops;
- vip->vii_immed.vi_immed[ip->i_size] = '\0';
+ ip->i_op = &simple_symlink_inode_operations;
+ ip->i_link = vip->vii_immed.vi_immed;
+ nd_terminate_link(ip->i_link, ip->i_size,
+ sizeof(vip->vii_immed.vi_immed) - 1);
}
} else
init_special_inode(ip, ip->i_mode, old_decode_dev(vip->vii_rdev));
return err;
}
-static char *read_link(struct dentry *dentry)
+static const char *fuse_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
struct fuse_conn *fc = get_fuse_conn(inode);
link = ERR_PTR(ret);
} else {
link[ret] = '\0';
+ *cookie = link;
}
fuse_invalidate_atime(inode);
return link;
}
-static void free_link(char *link)
-{
- if (!IS_ERR(link))
- free_page((unsigned long) link);
-}
-
-static void *fuse_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- nd_set_link(nd, read_link(dentry));
- return NULL;
-}
-
-static void fuse_put_link(struct dentry *dentry, struct nameidata *nd, void *c)
-{
- free_link(nd_get_link(nd));
-}
-
static int fuse_dir_open(struct inode *inode, struct file *file)
{
return fuse_open_common(inode, file, true);
static const struct inode_operations fuse_symlink_inode_operations = {
.setattr = fuse_setattr,
.follow_link = fuse_follow_link,
- .put_link = fuse_put_link,
+ .put_link = free_page_put_link,
.readlink = generic_readlink,
.getattr = fuse_getattr,
.setxattr = fuse_setxattr,
* Returns: 0 on success or error code
*/
-static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *gfs2_follow_link(struct dentry *dentry, void **cookie)
{
struct gfs2_inode *ip = GFS2_I(d_inode(dentry));
struct gfs2_holder i_gh;
error = gfs2_glock_nq(&i_gh);
if (error) {
gfs2_holder_uninit(&i_gh);
- nd_set_link(nd, ERR_PTR(error));
- return NULL;
+ return ERR_PTR(error);
}
size = (unsigned int)i_size_read(&ip->i_inode);
brelse(dibh);
out:
gfs2_glock_dq_uninit(&i_gh);
- nd_set_link(nd, buf);
- return NULL;
+ if (!IS_ERR(buf))
+ *cookie = buf;
+ return buf;
}
/**
if (name == NULL)
goto out_put;
- fd = file_create(name, mode & S_IFMT);
+ fd = file_create(name, mode & 0777);
if (fd < 0)
error = fd;
else
.setattr = hostfs_setattr,
};
-static void *hostfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *hostfs_follow_link(struct dentry *dentry, void **cookie)
{
char *link = __getname();
if (link) {
}
if (err < 0) {
__putname(link);
- link = ERR_PTR(err);
+ return ERR_PTR(err);
}
} else {
- link = ERR_PTR(-ENOMEM);
+ return ERR_PTR(-ENOMEM);
}
- nd_set_link(nd, link);
- return NULL;
+ return *cookie = link;
}
-static void hostfs_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+static void hostfs_put_link(struct inode *unused, void *cookie)
{
- char *s = nd_get_link(nd);
- if (!IS_ERR(s))
- __putname(s);
+ __putname(cookie);
}
static const struct inode_operations hostfs_link_iops = {
buflen);
}
-static void *hppfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *hppfs_follow_link(struct dentry *dentry, void **cookie)
{
struct dentry *proc_dentry = HPPFS_I(d_inode(dentry))->proc_dentry;
- return d_inode(proc_dentry)->i_op->follow_link(proc_dentry, nd);
+ return d_inode(proc_dentry)->i_op->follow_link(proc_dentry, cookie);
}
-static void hppfs_put_link(struct dentry *dentry, struct nameidata *nd,
- void *cookie)
+static void hppfs_put_link(struct inode *inode, void *cookie)
{
- struct dentry *proc_dentry = HPPFS_I(d_inode(dentry))->proc_dentry;
+ struct inode *proc_inode = d_inode(HPPFS_I(inode)->proc_dentry);
- if (d_inode(proc_dentry)->i_op->put_link)
- d_inode(proc_dentry)->i_op->put_link(proc_dentry, nd, cookie);
+ if (proc_inode->i_op->put_link)
+ proc_inode->i_op->put_link(proc_inode, cookie);
}
static const struct inode_operations hppfs_dir_iops = {
inode->i_pipe = NULL;
inode->i_bdev = NULL;
inode->i_cdev = NULL;
+ inode->i_link = NULL;
inode->i_rdev = 0;
inode->dirtied_when = 0;
* This function automatically handles read only file systems and media,
* as well as the "noatime" flag and inode specific "noatime" markers.
*/
-void touch_atime(const struct path *path)
+bool atime_needs_update(const struct path *path, struct inode *inode)
{
struct vfsmount *mnt = path->mnt;
- struct inode *inode = d_inode(path->dentry);
struct timespec now;
if (inode->i_flags & S_NOATIME)
- return;
+ return false;
if (IS_NOATIME(inode))
- return;
+ return false;
if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
- return;
+ return false;
if (mnt->mnt_flags & MNT_NOATIME)
- return;
+ return false;
if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
- return;
+ return false;
now = current_fs_time(inode->i_sb);
if (!relatime_need_update(mnt, inode, now))
- return;
+ return false;
if (timespec_equal(&inode->i_atime, &now))
+ return false;
+
+ return true;
+}
+
+void touch_atime(const struct path *path)
+{
+ struct vfsmount *mnt = path->mnt;
+ struct inode *inode = d_inode(path->dentry);
+ struct timespec now;
+
+ if (!atime_needs_update(path, inode))
return;
if (!sb_start_write_trylock(inode->i_sb))
return;
- if (__mnt_want_write(mnt))
+ if (__mnt_want_write(mnt) != 0)
goto skip_update;
/*
* File systems can error out when updating inodes if they need to
* We may also fail on filesystems that have the ability to make parts
* of the fs read only, e.g. subvolumes in Btrfs.
*/
+ now = current_fs_time(inode->i_sb);
update_time(inode, &now, S_ATIME);
__mnt_drop_write(mnt);
skip_update:
{
jbd2_journal_revoke_header_t *header;
int offset, max;
+ int csum_size = 0;
+ __u32 rcount;
int record_len = 4;
header = (jbd2_journal_revoke_header_t *) bh->b_data;
offset = sizeof(jbd2_journal_revoke_header_t);
- max = be32_to_cpu(header->r_count);
+ rcount = be32_to_cpu(header->r_count);
if (!jbd2_revoke_block_csum_verify(journal, header))
return -EINVAL;
+ if (jbd2_journal_has_csum_v2or3(journal))
+ csum_size = sizeof(struct jbd2_journal_revoke_tail);
+ if (rcount > journal->j_blocksize - csum_size)
+ return -EINVAL;
+ max = rcount;
+
if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
record_len = 8;
{
int csum_size = 0;
struct buffer_head *descriptor;
- int offset;
+ int sz, offset;
journal_header_t *header;
/* If we are already aborting, this all becomes a noop. We
if (jbd2_journal_has_csum_v2or3(journal))
csum_size = sizeof(struct jbd2_journal_revoke_tail);
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
+ sz = 8;
+ else
+ sz = 4;
+
/* Make sure we have a descriptor with space left for the record */
if (descriptor) {
- if (offset >= journal->j_blocksize - csum_size) {
+ if (offset + sz > journal->j_blocksize - csum_size) {
flush_descriptor(journal, descriptor, offset, write_op);
descriptor = NULL;
}
*descriptorp = descriptor;
}
- if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) {
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
* ((__be64 *)(&descriptor->b_data[offset])) =
cpu_to_be64(record->blocknr);
- offset += 8;
-
- } else {
+ else
* ((__be32 *)(&descriptor->b_data[offset])) =
cpu_to_be32(record->blocknr);
- offset += 4;
- }
+ offset += sz;
*offsetp = offset;
}
int result;
int wanted;
- WARN_ON(!transaction);
if (is_handle_aborted(handle))
return -EROFS;
journal = transaction->t_journal;
tid_t tid;
int need_to_start, ret;
- WARN_ON(!transaction);
/* If we've had an abort of any type, don't even think about
* actually doing the restart! */
if (is_handle_aborted(handle))
int need_copy = 0;
unsigned long start_lock, time_lock;
- WARN_ON(!transaction);
if (is_handle_aborted(handle))
return -EROFS;
journal = transaction->t_journal;
int err;
jbd_debug(5, "journal_head %p\n", jh);
- WARN_ON(!transaction);
err = -EROFS;
if (is_handle_aborted(handle))
goto out;
struct journal_head *jh;
int ret = 0;
- WARN_ON(!transaction);
if (is_handle_aborted(handle))
return -EROFS;
journal = transaction->t_journal;
int err = 0;
int was_modified = 0;
- WARN_ON(!transaction);
if (is_handle_aborted(handle))
return -EROFS;
journal = transaction->t_journal;
tid_t tid;
pid_t pid;
- if (!transaction)
- goto free_and_exit;
+ if (!transaction) {
+ /*
+ * Handle is already detached from the transaction so
+ * there is nothing to do other than decrease a refcount,
+ * or free the handle if refcount drops to zero
+ */
+ if (--handle->h_ref > 0) {
+ jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
+ handle->h_ref);
+ return err;
+ } else {
+ if (handle->h_rsv_handle)
+ jbd2_free_handle(handle->h_rsv_handle);
+ goto free_and_exit;
+ }
+ }
journal = transaction->t_journal;
J_ASSERT(journal_current_handle() == handle);
transaction_t *transaction = handle->h_transaction;
journal_t *journal;
- WARN_ON(!transaction);
if (is_handle_aborted(handle))
return -EROFS;
journal = transaction->t_journal;
ret = -ENOMEM;
goto fail;
}
+ inode->i_link = f->target;
jffs2_dbg(1, "%s(): symlink's target '%s' cached\n",
__func__, (char *)f->target);
case S_IFLNK:
inode->i_op = &jffs2_symlink_inode_operations;
+ inode->i_link = f->target;
break;
case S_IFDIR:
*
*/
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/namei.h>
#include "nodelist.h"
-static void *jffs2_follow_link(struct dentry *dentry, struct nameidata *nd);
-
const struct inode_operations jffs2_symlink_inode_operations =
{
.readlink = generic_readlink,
- .follow_link = jffs2_follow_link,
+ .follow_link = simple_follow_link,
.setattr = jffs2_setattr,
.setxattr = jffs2_setxattr,
.getxattr = jffs2_getxattr,
.listxattr = jffs2_listxattr,
.removexattr = jffs2_removexattr
};
-
-static void *jffs2_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct jffs2_inode_info *f = JFFS2_INODE_INFO(d_inode(dentry));
- char *p = (char *)f->target;
-
- /*
- * We don't acquire the f->sem mutex here since the only data we
- * use is f->target.
- *
- * 1. If we are here the inode has already built and f->target has
- * to point to the target path.
- * 2. Nobody uses f->target (if the inode is symlink's inode). The
- * exception is inode freeing function which frees f->target. But
- * it can't be called while we are here and before VFS has
- * stopped using our f->target string which we provide by means of
- * nd_set_link() call.
- */
-
- if (!p) {
- pr_err("%s(): can't find symlink target\n", __func__);
- p = ERR_PTR(-EIO);
- }
- jffs2_dbg(1, "%s(): target path is '%s'\n",
- __func__, (char *)f->target);
-
- nd_set_link(nd, p);
-
- /*
- * We will unlock the f->sem mutex but VFS will use the f->target string. This is safe
- * since the only way that may cause f->target to be changed is iput() operation.
- * But VFS will not use f->target after iput() has been called.
- */
- return NULL;
-}
-
inode->i_mapping->a_ops = &jfs_aops;
} else {
inode->i_op = &jfs_fast_symlink_inode_operations;
+ inode->i_link = JFS_IP(inode)->i_inline;
/*
* The inline data should be null-terminated, but
* don't let on-disk corruption crash the kernel
*/
- JFS_IP(inode)->i_inline[inode->i_size] = '\0';
+ inode->i_link[inode->i_size] = '\0';
}
} else {
inode->i_op = &jfs_file_inode_operations;
int ssize; /* source pathname size */
struct btstack btstack;
struct inode *ip = d_inode(dentry);
- unchar *i_fastsymlink;
s64 xlen = 0;
int bmask = 0, xsize;
s64 xaddr;
if (ssize <= IDATASIZE) {
ip->i_op = &jfs_fast_symlink_inode_operations;
- i_fastsymlink = JFS_IP(ip)->i_inline;
- memcpy(i_fastsymlink, name, ssize);
+ ip->i_link = JFS_IP(ip)->i_inline;
+ memcpy(ip->i_link, name, ssize);
ip->i_size = ssize - 1;
/*
*/
#include <linux/fs.h>
-#include <linux/namei.h>
#include "jfs_incore.h"
#include "jfs_inode.h"
#include "jfs_xattr.h"
-static void *jfs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- char *s = JFS_IP(d_inode(dentry))->i_inline;
- nd_set_link(nd, s);
- return NULL;
-}
-
const struct inode_operations jfs_fast_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = jfs_follow_link,
+ .follow_link = simple_follow_link,
.setattr = jfs_setattr,
.setxattr = jfs_setxattr,
.getxattr = jfs_getxattr,
if (!kn)
goto err_out1;
- ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL);
+ /*
+ * If the ino of the sysfs entry created for a kmem cache gets
+ * allocated from an ida layer, which is accounted to the memcg that
+ * owns the cache, the memcg will get pinned forever. So do not account
+ * ino ida allocations.
+ */
+ ret = ida_simple_get(&root->ino_ida, 1, 0,
+ GFP_KERNEL | __GFP_NOACCOUNT);
if (ret < 0)
goto err_out2;
kn->ino = ret;
return error;
}
-static void *kernfs_iop_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *kernfs_iop_follow_link(struct dentry *dentry, void **cookie)
{
int error = -ENOMEM;
unsigned long page = get_zeroed_page(GFP_KERNEL);
- if (page) {
- error = kernfs_getlink(dentry, (char *) page);
- if (error < 0)
- free_page((unsigned long)page);
- }
- nd_set_link(nd, error ? ERR_PTR(error) : (char *)page);
- return NULL;
-}
-
-static void kernfs_iop_put_link(struct dentry *dentry, struct nameidata *nd,
- void *cookie)
-{
- char *page = nd_get_link(nd);
- if (!IS_ERR(page))
+ if (!page)
+ return ERR_PTR(-ENOMEM);
+ error = kernfs_getlink(dentry, (char *)page);
+ if (unlikely(error < 0)) {
free_page((unsigned long)page);
+ return ERR_PTR(error);
+ }
+ return *cookie = (char *)page;
}
const struct inode_operations kernfs_symlink_iops = {
.listxattr = kernfs_iop_listxattr,
.readlink = generic_readlink,
.follow_link = kernfs_iop_follow_link,
- .put_link = kernfs_iop_put_link,
+ .put_link = free_page_put_link,
.setattr = kernfs_iop_setattr,
.getattr = kernfs_iop_getattr,
.permission = kernfs_iop_permission,
}
EXPORT_SYMBOL(noop_fsync);
-void kfree_put_link(struct dentry *dentry, struct nameidata *nd,
- void *cookie)
+void kfree_put_link(struct inode *unused, void *cookie)
{
- char *s = nd_get_link(nd);
- if (!IS_ERR(s))
- kfree(s);
+ kfree(cookie);
}
EXPORT_SYMBOL(kfree_put_link);
+void free_page_put_link(struct inode *unused, void *cookie)
+{
+ free_page((unsigned long) cookie);
+}
+EXPORT_SYMBOL(free_page_put_link);
+
/*
* nop .set_page_dirty method so that people can use .page_mkwrite on
* anon inodes.
return -EINVAL;
}
EXPORT_SYMBOL(simple_nosetlease);
+
+const char *simple_follow_link(struct dentry *dentry, void **cookie)
+{
+ return d_inode(dentry)->i_link;
+}
+EXPORT_SYMBOL(simple_follow_link);
+
+const struct inode_operations simple_symlink_inode_operations = {
+ .follow_link = simple_follow_link,
+ .readlink = generic_readlink
+};
+EXPORT_SYMBOL(simple_symlink_inode_operations);
const struct inode_operations logfs_symlink_iops = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
+ .put_link = page_put_link,
};
const struct inode_operations logfs_dir_iops = {
extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
+extern int __legitimize_mnt(struct vfsmount *, unsigned);
extern bool legitimize_mnt(struct vfsmount *, unsigned);
extern void __detach_mounts(struct dentry *dentry);
}
EXPORT_SYMBOL(path_put);
+#define EMBEDDED_LEVELS 2
struct nameidata {
struct path path;
struct qstr last;
unsigned seq, m_seq;
int last_type;
unsigned depth;
- struct file *base;
- char *saved_names[MAX_NESTED_LINKS + 1];
+ int total_link_count;
+ struct saved {
+ struct path link;
+ void *cookie;
+ const char *name;
+ struct inode *inode;
+ unsigned seq;
+ } *stack, internal[EMBEDDED_LEVELS];
+ struct filename *name;
+ struct nameidata *saved;
+ unsigned root_seq;
+ int dfd;
};
+static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
+{
+ struct nameidata *old = current->nameidata;
+ p->stack = p->internal;
+ p->dfd = dfd;
+ p->name = name;
+ p->total_link_count = old ? old->total_link_count : 0;
+ p->saved = old;
+ current->nameidata = p;
+}
+
+static void restore_nameidata(void)
+{
+ struct nameidata *now = current->nameidata, *old = now->saved;
+
+ current->nameidata = old;
+ if (old)
+ old->total_link_count = now->total_link_count;
+ if (now->stack != now->internal) {
+ kfree(now->stack);
+ now->stack = now->internal;
+ }
+}
+
+static int __nd_alloc_stack(struct nameidata *nd)
+{
+ struct saved *p;
+
+ if (nd->flags & LOOKUP_RCU) {
+ p= kmalloc(MAXSYMLINKS * sizeof(struct saved),
+ GFP_ATOMIC);
+ if (unlikely(!p))
+ return -ECHILD;
+ } else {
+ p= kmalloc(MAXSYMLINKS * sizeof(struct saved),
+ GFP_KERNEL);
+ if (unlikely(!p))
+ return -ENOMEM;
+ }
+ memcpy(p, nd->internal, sizeof(nd->internal));
+ nd->stack = p;
+ return 0;
+}
+
+static inline int nd_alloc_stack(struct nameidata *nd)
+{
+ if (likely(nd->depth != EMBEDDED_LEVELS))
+ return 0;
+ if (likely(nd->stack != nd->internal))
+ return 0;
+ return __nd_alloc_stack(nd);
+}
+
+static void drop_links(struct nameidata *nd)
+{
+ int i = nd->depth;
+ while (i--) {
+ struct saved *last = nd->stack + i;
+ struct inode *inode = last->inode;
+ if (last->cookie && inode->i_op->put_link) {
+ inode->i_op->put_link(inode, last->cookie);
+ last->cookie = NULL;
+ }
+ }
+}
+
+static void terminate_walk(struct nameidata *nd)
+{
+ drop_links(nd);
+ if (!(nd->flags & LOOKUP_RCU)) {
+ int i;
+ path_put(&nd->path);
+ for (i = 0; i < nd->depth; i++)
+ path_put(&nd->stack[i].link);
+ if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+ path_put(&nd->root);
+ nd->root.mnt = NULL;
+ }
+ } else {
+ nd->flags &= ~LOOKUP_RCU;
+ if (!(nd->flags & LOOKUP_ROOT))
+ nd->root.mnt = NULL;
+ rcu_read_unlock();
+ }
+ nd->depth = 0;
+}
+
+/* path_put is needed afterwards regardless of success or failure */
+static bool legitimize_path(struct nameidata *nd,
+ struct path *path, unsigned seq)
+{
+ int res = __legitimize_mnt(path->mnt, nd->m_seq);
+ if (unlikely(res)) {
+ if (res > 0)
+ path->mnt = NULL;
+ path->dentry = NULL;
+ return false;
+ }
+ if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) {
+ path->dentry = NULL;
+ return false;
+ }
+ return !read_seqcount_retry(&path->dentry->d_seq, seq);
+}
+
+static bool legitimize_links(struct nameidata *nd)
+{
+ int i;
+ for (i = 0; i < nd->depth; i++) {
+ struct saved *last = nd->stack + i;
+ if (unlikely(!legitimize_path(nd, &last->link, last->seq))) {
+ drop_links(nd);
+ nd->depth = i + 1;
+ return false;
+ }
+ }
+ return true;
+}
+
/*
* Path walking has 2 modes, rcu-walk and ref-walk (see
* Documentation/filesystems/path-lookup.txt). In situations when we can't
* unlazy_walk - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
* @dentry: child of nd->path.dentry or NULL
+ * @seq: seq number to check dentry against
* Returns: 0 on success, -ECHILD on failure
*
* unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
* for ref-walk mode. @dentry must be a path found by a do_lookup call on
* @nd or NULL. Must be called from rcu-walk context.
+ * Nothing should touch nameidata between unlazy_walk() failure and
+ * terminate_walk().
*/
-static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
+static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq)
{
- struct fs_struct *fs = current->fs;
struct dentry *parent = nd->path.dentry;
BUG_ON(!(nd->flags & LOOKUP_RCU));
- /*
- * After legitimizing the bastards, terminate_walk()
- * will do the right thing for non-RCU mode, and all our
- * subsequent exit cases should rcu_read_unlock()
- * before returning. Do vfsmount first; if dentry
- * can't be legitimized, just set nd->path.dentry to NULL
- * and rely on dput(NULL) being a no-op.
- */
- if (!legitimize_mnt(nd->path.mnt, nd->m_seq))
- return -ECHILD;
nd->flags &= ~LOOKUP_RCU;
-
- if (!lockref_get_not_dead(&parent->d_lockref)) {
- nd->path.dentry = NULL;
- goto out;
- }
+ if (unlikely(!legitimize_links(nd)))
+ goto out2;
+ if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
+ goto out2;
+ if (unlikely(!lockref_get_not_dead(&parent->d_lockref)))
+ goto out1;
/*
* For a negative lookup, the lookup sequence point is the parents
} else {
if (!lockref_get_not_dead(&dentry->d_lockref))
goto out;
- if (read_seqcount_retry(&dentry->d_seq, nd->seq))
+ if (read_seqcount_retry(&dentry->d_seq, seq))
goto drop_dentry;
}
* still valid and get it if required.
*/
if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
- spin_lock(&fs->lock);
- if (nd->root.mnt != fs->root.mnt || nd->root.dentry != fs->root.dentry)
- goto unlock_and_drop_dentry;
- path_get(&nd->root);
- spin_unlock(&fs->lock);
+ if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq))) {
+ rcu_read_unlock();
+ dput(dentry);
+ return -ECHILD;
+ }
}
rcu_read_unlock();
return 0;
-unlock_and_drop_dentry:
- spin_unlock(&fs->lock);
drop_dentry:
rcu_read_unlock();
dput(dentry);
goto drop_root_mnt;
+out2:
+ nd->path.mnt = NULL;
+out1:
+ nd->path.dentry = NULL;
out:
rcu_read_unlock();
drop_root_mnt:
return -ECHILD;
}
+static int unlazy_link(struct nameidata *nd, struct path *link, unsigned seq)
+{
+ if (unlikely(!legitimize_path(nd, link, seq))) {
+ drop_links(nd);
+ nd->depth = 0;
+ nd->flags &= ~LOOKUP_RCU;
+ nd->path.mnt = NULL;
+ nd->path.dentry = NULL;
+ if (!(nd->flags & LOOKUP_ROOT))
+ nd->root.mnt = NULL;
+ rcu_read_unlock();
+ } else if (likely(unlazy_walk(nd, NULL, 0)) == 0) {
+ return 0;
+ }
+ path_put(link);
+ return -ECHILD;
+}
+
static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
{
return dentry->d_op->d_revalidate(dentry, flags);
int status;
if (nd->flags & LOOKUP_RCU) {
- nd->flags &= ~LOOKUP_RCU;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
-
- if (!legitimize_mnt(nd->path.mnt, nd->m_seq)) {
- rcu_read_unlock();
+ if (unlikely(unlazy_walk(nd, NULL, 0)))
return -ECHILD;
- }
- if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) {
- rcu_read_unlock();
- mntput(nd->path.mnt);
- return -ECHILD;
- }
- if (read_seqcount_retry(&dentry->d_seq, nd->seq)) {
- rcu_read_unlock();
- dput(dentry);
- mntput(nd->path.mnt);
- return -ECHILD;
- }
- rcu_read_unlock();
}
if (likely(!(nd->flags & LOOKUP_JUMPED)))
if (!status)
status = -ESTALE;
- path_put(&nd->path);
return status;
}
-static __always_inline void set_root(struct nameidata *nd)
+static void set_root(struct nameidata *nd)
{
get_fs_root(current->fs, &nd->root);
}
-static int link_path_walk(const char *, struct nameidata *);
-
-static __always_inline unsigned set_root_rcu(struct nameidata *nd)
+static unsigned set_root_rcu(struct nameidata *nd)
{
struct fs_struct *fs = current->fs;
- unsigned seq, res;
+ unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
nd->root = fs->root;
- res = __read_seqcount_begin(&nd->root.dentry->d_seq);
+ nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
} while (read_seqcount_retry(&fs->seq, seq));
- return res;
+ return nd->root_seq;
}
static void path_put_conditional(struct path *path, struct nameidata *nd)
* Helper to directly jump to a known parsed path from ->follow_link,
* caller must have taken a reference to path beforehand.
*/
-void nd_jump_link(struct nameidata *nd, struct path *path)
+void nd_jump_link(struct path *path)
{
+ struct nameidata *nd = current->nameidata;
path_put(&nd->path);
nd->path = *path;
nd->flags |= LOOKUP_JUMPED;
}
-void nd_set_link(struct nameidata *nd, char *path)
+static inline void put_link(struct nameidata *nd)
{
- nd->saved_names[nd->depth] = path;
-}
-EXPORT_SYMBOL(nd_set_link);
-
-char *nd_get_link(struct nameidata *nd)
-{
- return nd->saved_names[nd->depth];
-}
-EXPORT_SYMBOL(nd_get_link);
-
-static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
-{
- struct inode *inode = link->dentry->d_inode;
- if (inode->i_op->put_link)
- inode->i_op->put_link(link->dentry, nd, cookie);
- path_put(link);
+ struct saved *last = nd->stack + --nd->depth;
+ struct inode *inode = last->inode;
+ if (last->cookie && inode->i_op->put_link)
+ inode->i_op->put_link(inode, last->cookie);
+ if (!(nd->flags & LOOKUP_RCU))
+ path_put(&last->link);
}
int sysctl_protected_symlinks __read_mostly = 0;
/**
* may_follow_link - Check symlink following for unsafe situations
- * @link: The path of the symlink
* @nd: nameidata pathwalk data
*
* In the case of the sysctl_protected_symlinks sysctl being enabled,
*
* Returns 0 if following the symlink is allowed, -ve on error.
*/
-static inline int may_follow_link(struct path *link, struct nameidata *nd)
+static inline int may_follow_link(struct nameidata *nd)
{
const struct inode *inode;
const struct inode *parent;
return 0;
/* Allowed if owner and follower match. */
- inode = link->dentry->d_inode;
+ inode = nd->stack[0].inode;
if (uid_eq(current_cred()->fsuid, inode->i_uid))
return 0;
if (uid_eq(parent->i_uid, inode->i_uid))
return 0;
- audit_log_link_denied("follow_link", link);
- path_put_conditional(link, nd);
- path_put(&nd->path);
+ if (nd->flags & LOOKUP_RCU)
+ return -ECHILD;
+
+ audit_log_link_denied("follow_link", &nd->stack[0].link);
return -EACCES;
}
return -EPERM;
}
-static __always_inline int
-follow_link(struct path *link, struct nameidata *nd, void **p)
+static __always_inline
+const char *get_link(struct nameidata *nd)
{
- struct dentry *dentry = link->dentry;
+ struct saved *last = nd->stack + nd->depth - 1;
+ struct dentry *dentry = last->link.dentry;
+ struct inode *inode = last->inode;
int error;
- char *s;
-
- BUG_ON(nd->flags & LOOKUP_RCU);
-
- if (link->mnt == nd->path.mnt)
- mntget(link->mnt);
+ const char *res;
- error = -ELOOP;
- if (unlikely(current->total_link_count >= 40))
- goto out_put_nd_path;
-
- cond_resched();
- current->total_link_count++;
-
- touch_atime(link);
- nd_set_link(nd, NULL);
+ if (!(nd->flags & LOOKUP_RCU)) {
+ touch_atime(&last->link);
+ cond_resched();
+ } else if (atime_needs_update(&last->link, inode)) {
+ if (unlikely(unlazy_walk(nd, NULL, 0)))
+ return ERR_PTR(-ECHILD);
+ touch_atime(&last->link);
+ }
- error = security_inode_follow_link(link->dentry, nd);
- if (error)
- goto out_put_nd_path;
+ error = security_inode_follow_link(dentry, inode,
+ nd->flags & LOOKUP_RCU);
+ if (unlikely(error))
+ return ERR_PTR(error);
nd->last_type = LAST_BIND;
- *p = dentry->d_inode->i_op->follow_link(dentry, nd);
- error = PTR_ERR(*p);
- if (IS_ERR(*p))
- goto out_put_nd_path;
-
- error = 0;
- s = nd_get_link(nd);
- if (s) {
- if (unlikely(IS_ERR(s))) {
- path_put(&nd->path);
- put_link(nd, link, *p);
- return PTR_ERR(s);
+ res = inode->i_link;
+ if (!res) {
+ if (nd->flags & LOOKUP_RCU) {
+ if (unlikely(unlazy_walk(nd, NULL, 0)))
+ return ERR_PTR(-ECHILD);
}
- if (*s == '/') {
+ res = inode->i_op->follow_link(dentry, &last->cookie);
+ if (IS_ERR_OR_NULL(res)) {
+ last->cookie = NULL;
+ return res;
+ }
+ }
+ if (*res == '/') {
+ if (nd->flags & LOOKUP_RCU) {
+ struct dentry *d;
+ if (!nd->root.mnt)
+ set_root_rcu(nd);
+ nd->path = nd->root;
+ d = nd->path.dentry;
+ nd->inode = d->d_inode;
+ nd->seq = nd->root_seq;
+ if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
+ return ERR_PTR(-ECHILD);
+ } else {
if (!nd->root.mnt)
set_root(nd);
path_put(&nd->path);
nd->path = nd->root;
path_get(&nd->root);
- nd->flags |= LOOKUP_JUMPED;
+ nd->inode = nd->path.dentry->d_inode;
}
- nd->inode = nd->path.dentry->d_inode;
- error = link_path_walk(s, nd);
- if (unlikely(error))
- put_link(nd, link, *p);
+ nd->flags |= LOOKUP_JUMPED;
+ while (unlikely(*++res == '/'))
+ ;
}
-
- return error;
-
-out_put_nd_path:
- *p = NULL;
- path_put(&nd->path);
- path_put(link);
- return error;
-}
-
-static int follow_up_rcu(struct path *path)
-{
- struct mount *mnt = real_mount(path->mnt);
- struct mount *parent;
- struct dentry *mountpoint;
-
- parent = mnt->mnt_parent;
- if (&parent->mnt == path->mnt)
- return 0;
- mountpoint = mnt->mnt_mountpoint;
- path->dentry = mountpoint;
- path->mnt = &parent->mnt;
- return 1;
+ if (!*res)
+ res = NULL;
+ return res;
}
/*
* - return -EISDIR to tell follow_managed() to stop and return the path we
* were called with.
*/
-static int follow_automount(struct path *path, unsigned flags,
+static int follow_automount(struct path *path, struct nameidata *nd,
bool *need_mntput)
{
struct vfsmount *mnt;
* as being automount points. These will need the attentions
* of the daemon to instantiate them before they can be used.
*/
- if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
- LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+ if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
+ LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
path->dentry->d_inode)
return -EISDIR;
- current->total_link_count++;
- if (current->total_link_count >= 40)
+ nd->total_link_count++;
+ if (nd->total_link_count >= 40)
return -ELOOP;
mnt = path->dentry->d_op->d_automount(path);
* the path being looked up; if it wasn't then the remainder of
* the path is inaccessible and we should say so.
*/
- if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_PARENT))
+ if (PTR_ERR(mnt) == -EISDIR && (nd->flags & LOOKUP_PARENT))
return -EREMOTE;
return PTR_ERR(mnt);
}
*
* Serialization is taken care of in namespace.c
*/
-static int follow_managed(struct path *path, unsigned flags)
+static int follow_managed(struct path *path, struct nameidata *nd)
{
struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
unsigned managed;
/* Handle an automount point */
if (managed & DCACHE_NEED_AUTOMOUNT) {
- ret = follow_automount(path, flags, &need_mntput);
+ ret = follow_automount(path, nd, &need_mntput);
if (ret < 0)
break;
continue;
mntput(path->mnt);
if (ret == -EISDIR)
ret = 0;
- return ret < 0 ? ret : need_mntput;
+ if (need_mntput)
+ nd->flags |= LOOKUP_JUMPED;
+ if (unlikely(ret < 0))
+ path_put_conditional(path, nd);
+ return ret;
}
int follow_down_one(struct path *path)
* we meet a managed dentry that would need blocking.
*/
static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
- struct inode **inode)
+ struct inode **inode, unsigned *seqp)
{
for (;;) {
struct mount *mounted;
path->mnt = &mounted->mnt;
path->dentry = mounted->mnt.mnt_root;
nd->flags |= LOOKUP_JUMPED;
- nd->seq = read_seqcount_begin(&path->dentry->d_seq);
+ *seqp = read_seqcount_begin(&path->dentry->d_seq);
/*
* Update the inode too. We don't need to re-check the
* dentry sequence number here after this d_inode read,
set_root_rcu(nd);
while (1) {
- if (nd->path.dentry == nd->root.dentry &&
- nd->path.mnt == nd->root.mnt) {
+ if (path_equal(&nd->path, &nd->root))
break;
- }
if (nd->path.dentry != nd->path.mnt->mnt_root) {
struct dentry *old = nd->path.dentry;
struct dentry *parent = old->d_parent;
inode = parent->d_inode;
seq = read_seqcount_begin(&parent->d_seq);
- if (read_seqcount_retry(&old->d_seq, nd->seq))
- goto failed;
+ if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq)))
+ return -ECHILD;
nd->path.dentry = parent;
nd->seq = seq;
break;
+ } else {
+ struct mount *mnt = real_mount(nd->path.mnt);
+ struct mount *mparent = mnt->mnt_parent;
+ struct dentry *mountpoint = mnt->mnt_mountpoint;
+ struct inode *inode2 = mountpoint->d_inode;
+ unsigned seq = read_seqcount_begin(&mountpoint->d_seq);
+ if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+ return -ECHILD;
+ if (&mparent->mnt == nd->path.mnt)
+ break;
+ /* we know that mountpoint was pinned */
+ nd->path.dentry = mountpoint;
+ nd->path.mnt = &mparent->mnt;
+ inode = inode2;
+ nd->seq = seq;
}
- if (!follow_up_rcu(&nd->path))
- break;
- inode = nd->path.dentry->d_inode;
- nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
}
- while (d_mountpoint(nd->path.dentry)) {
+ while (unlikely(d_mountpoint(nd->path.dentry))) {
struct mount *mounted;
mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
+ if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+ return -ECHILD;
if (!mounted)
break;
nd->path.mnt = &mounted->mnt;
nd->path.dentry = mounted->mnt.mnt_root;
inode = nd->path.dentry->d_inode;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
- if (read_seqretry(&mount_lock, nd->m_seq))
- goto failed;
}
nd->inode = inode;
return 0;
-
-failed:
- nd->flags &= ~LOOKUP_RCU;
- if (!(nd->flags & LOOKUP_ROOT))
- nd->root.mnt = NULL;
- rcu_read_unlock();
- return -ECHILD;
}
/*
* It _is_ time-critical.
*/
static int lookup_fast(struct nameidata *nd,
- struct path *path, struct inode **inode)
+ struct path *path, struct inode **inode,
+ unsigned *seqp)
{
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent = nd->path.dentry;
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
+ bool negative;
dentry = __d_lookup_rcu(parent, &nd->last, &seq);
if (!dentry)
goto unlazy;
* This sequence count validates that the inode matches
* the dentry name information from lookup.
*/
- *inode = dentry->d_inode;
+ *inode = d_backing_inode(dentry);
+ negative = d_is_negative(dentry);
if (read_seqcount_retry(&dentry->d_seq, seq))
return -ECHILD;
+ if (negative)
+ return -ENOENT;
/*
* This sequence count validates that the parent had no
*/
if (__read_seqcount_retry(&parent->d_seq, nd->seq))
return -ECHILD;
- nd->seq = seq;
+ *seqp = seq;
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
status = d_revalidate(dentry, nd->flags);
if (unlikely(status <= 0)) {
}
path->mnt = mnt;
path->dentry = dentry;
- if (likely(__follow_mount_rcu(nd, path, inode)))
+ if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
return 0;
unlazy:
- if (unlazy_walk(nd, dentry))
+ if (unlazy_walk(nd, dentry, seq))
return -ECHILD;
} else {
dentry = __d_lookup(parent, &nd->last);
goto need_lookup;
}
+ if (unlikely(d_is_negative(dentry))) {
+ dput(dentry);
+ return -ENOENT;
+ }
path->mnt = mnt;
path->dentry = dentry;
- err = follow_managed(path, nd->flags);
- if (unlikely(err < 0)) {
- path_put_conditional(path, nd);
- return err;
- }
- if (err)
- nd->flags |= LOOKUP_JUMPED;
- *inode = path->dentry->d_inode;
- return 0;
+ err = follow_managed(path, nd);
+ if (likely(!err))
+ *inode = d_backing_inode(path->dentry);
+ return err;
need_lookup:
return 1;
static int lookup_slow(struct nameidata *nd, struct path *path)
{
struct dentry *dentry, *parent;
- int err;
parent = nd->path.dentry;
BUG_ON(nd->inode != parent->d_inode);
return PTR_ERR(dentry);
path->mnt = nd->path.mnt;
path->dentry = dentry;
- err = follow_managed(path, nd->flags);
- if (unlikely(err < 0)) {
- path_put_conditional(path, nd);
- return err;
- }
- if (err)
- nd->flags |= LOOKUP_JUMPED;
- return 0;
+ return follow_managed(path, nd);
}
static inline int may_lookup(struct nameidata *nd)
int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
if (err != -ECHILD)
return err;
- if (unlazy_walk(nd, NULL))
+ if (unlazy_walk(nd, NULL, 0))
return -ECHILD;
}
return inode_permission(nd->inode, MAY_EXEC);
{
if (type == LAST_DOTDOT) {
if (nd->flags & LOOKUP_RCU) {
- if (follow_dotdot_rcu(nd))
- return -ECHILD;
+ return follow_dotdot_rcu(nd);
} else
follow_dotdot(nd);
}
return 0;
}
-static void terminate_walk(struct nameidata *nd)
+static int pick_link(struct nameidata *nd, struct path *link,
+ struct inode *inode, unsigned seq)
{
+ int error;
+ struct saved *last;
+ if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) {
+ path_to_nameidata(link, nd);
+ return -ELOOP;
+ }
if (!(nd->flags & LOOKUP_RCU)) {
- path_put(&nd->path);
- } else {
- nd->flags &= ~LOOKUP_RCU;
- if (!(nd->flags & LOOKUP_ROOT))
- nd->root.mnt = NULL;
- rcu_read_unlock();
+ if (link->mnt == nd->path.mnt)
+ mntget(link->mnt);
+ }
+ error = nd_alloc_stack(nd);
+ if (unlikely(error)) {
+ if (error == -ECHILD) {
+ if (unlikely(unlazy_link(nd, link, seq)))
+ return -ECHILD;
+ error = nd_alloc_stack(nd);
+ }
+ if (error) {
+ path_put(link);
+ return error;
+ }
}
+
+ last = nd->stack + nd->depth++;
+ last->link = *link;
+ last->cookie = NULL;
+ last->inode = inode;
+ last->seq = seq;
+ return 1;
}
/*
* so we keep a cache of "no, this doesn't need follow_link"
* for the common case.
*/
-static inline int should_follow_link(struct dentry *dentry, int follow)
+static inline int should_follow_link(struct nameidata *nd, struct path *link,
+ int follow,
+ struct inode *inode, unsigned seq)
{
- return unlikely(d_is_symlink(dentry)) ? follow : 0;
+ if (likely(!d_is_symlink(link->dentry)))
+ return 0;
+ if (!follow)
+ return 0;
+ return pick_link(nd, link, inode, seq);
}
-static inline int walk_component(struct nameidata *nd, struct path *path,
- int follow)
+enum {WALK_GET = 1, WALK_PUT = 2};
+
+static int walk_component(struct nameidata *nd, int flags)
{
+ struct path path;
struct inode *inode;
+ unsigned seq;
int err;
/*
* "." and ".." are special - ".." especially so because it has
* to be able to know about the current root directory and
* parent relationships.
*/
- if (unlikely(nd->last_type != LAST_NORM))
- return handle_dots(nd, nd->last_type);
- err = lookup_fast(nd, path, &inode);
+ if (unlikely(nd->last_type != LAST_NORM)) {
+ err = handle_dots(nd, nd->last_type);
+ if (flags & WALK_PUT)
+ put_link(nd);
+ return err;
+ }
+ err = lookup_fast(nd, &path, &inode, &seq);
if (unlikely(err)) {
if (err < 0)
- goto out_err;
+ return err;
- err = lookup_slow(nd, path);
+ err = lookup_slow(nd, &path);
if (err < 0)
- goto out_err;
+ return err;
- inode = path->dentry->d_inode;
+ inode = d_backing_inode(path.dentry);
+ seq = 0; /* we are already out of RCU mode */
+ err = -ENOENT;
+ if (d_is_negative(path.dentry))
+ goto out_path_put;
}
- err = -ENOENT;
- if (d_is_negative(path->dentry))
- goto out_path_put;
- if (should_follow_link(path->dentry, follow)) {
- if (nd->flags & LOOKUP_RCU) {
- if (unlikely(nd->path.mnt != path->mnt ||
- unlazy_walk(nd, path->dentry))) {
- err = -ECHILD;
- goto out_err;
- }
- }
- BUG_ON(inode != path->dentry->d_inode);
- return 1;
- }
- path_to_nameidata(path, nd);
+ if (flags & WALK_PUT)
+ put_link(nd);
+ err = should_follow_link(nd, &path, flags & WALK_GET, inode, seq);
+ if (unlikely(err))
+ return err;
+ path_to_nameidata(&path, nd);
nd->inode = inode;
+ nd->seq = seq;
return 0;
out_path_put:
- path_to_nameidata(path, nd);
-out_err:
- terminate_walk(nd);
+ path_to_nameidata(&path, nd);
return err;
}
-/*
- * This limits recursive symlink follows to 8, while
- * limiting consecutive symlinks to 40.
- *
- * Without that kind of total limit, nasty chains of consecutive
- * symlinks can cause almost arbitrarily long lookups.
- */
-static inline int nested_symlink(struct path *path, struct nameidata *nd)
-{
- int res;
-
- if (unlikely(current->link_count >= MAX_NESTED_LINKS)) {
- path_put_conditional(path, nd);
- path_put(&nd->path);
- return -ELOOP;
- }
- BUG_ON(nd->depth >= MAX_NESTED_LINKS);
-
- nd->depth++;
- current->link_count++;
-
- do {
- struct path link = *path;
- void *cookie;
-
- res = follow_link(&link, nd, &cookie);
- if (res)
- break;
- res = walk_component(nd, path, LOOKUP_FOLLOW);
- put_link(nd, &link, cookie);
- } while (res > 0);
-
- current->link_count--;
- nd->depth--;
- return res;
-}
-
/*
* We can do the critical dentry name comparison and hashing
* operations one word at a time, but we are limited to:
*/
static int link_path_walk(const char *name, struct nameidata *nd)
{
- struct path next;
int err;
-
+
while (*name=='/')
name++;
if (!*name)
err = may_lookup(nd);
if (err)
- break;
+ return err;
hash_len = hash_name(name);
struct qstr this = { { .hash_len = hash_len }, .name = name };
err = parent->d_op->d_hash(parent, &this);
if (err < 0)
- break;
+ return err;
hash_len = this.hash_len;
name = this.name;
}
name += hashlen_len(hash_len);
if (!*name)
- return 0;
+ goto OK;
/*
* If it wasn't NUL, we know it was '/'. Skip that
* slash, and continue until no more slashes.
do {
name++;
} while (unlikely(*name == '/'));
- if (!*name)
- return 0;
-
- err = walk_component(nd, &next, LOOKUP_FOLLOW);
+ if (unlikely(!*name)) {
+OK:
+ /* pathname body, done */
+ if (!nd->depth)
+ return 0;
+ name = nd->stack[nd->depth - 1].name;
+ /* trailing symlink, done */
+ if (!name)
+ return 0;
+ /* last component of nested symlink */
+ err = walk_component(nd, WALK_GET | WALK_PUT);
+ } else {
+ err = walk_component(nd, WALK_GET);
+ }
if (err < 0)
return err;
if (err) {
- err = nested_symlink(&next, nd);
- if (err)
- return err;
- }
- if (!d_can_lookup(nd->path.dentry)) {
- err = -ENOTDIR;
- break;
+ const char *s = get_link(nd);
+
+ if (unlikely(IS_ERR(s)))
+ return PTR_ERR(s);
+ err = 0;
+ if (unlikely(!s)) {
+ /* jumped */
+ put_link(nd);
+ } else {
+ nd->stack[nd->depth - 1].name = name;
+ name = s;
+ continue;
+ }
}
+ if (unlikely(!d_can_lookup(nd->path.dentry)))
+ return -ENOTDIR;
}
- terminate_walk(nd);
- return err;
}
-static int path_init(int dfd, const struct filename *name, unsigned int flags,
- struct nameidata *nd)
+static const char *path_init(struct nameidata *nd, unsigned flags)
{
int retval = 0;
- const char *s = name->name;
+ const char *s = nd->name->name;
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
nd->depth = 0;
- nd->base = NULL;
+ nd->total_link_count = 0;
if (flags & LOOKUP_ROOT) {
struct dentry *root = nd->root.dentry;
struct inode *inode = root->d_inode;
if (*s) {
if (!d_can_lookup(root))
- return -ENOTDIR;
+ return ERR_PTR(-ENOTDIR);
retval = inode_permission(inode, MAY_EXEC);
if (retval)
- return retval;
+ return ERR_PTR(retval);
}
nd->path = nd->root;
nd->inode = inode;
if (flags & LOOKUP_RCU) {
rcu_read_lock();
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+ nd->root_seq = nd->seq;
nd->m_seq = read_seqbegin(&mount_lock);
} else {
path_get(&nd->path);
}
- goto done;
+ return s;
}
nd->root.mnt = NULL;
path_get(&nd->root);
}
nd->path = nd->root;
- } else if (dfd == AT_FDCWD) {
+ } else if (nd->dfd == AT_FDCWD) {
if (flags & LOOKUP_RCU) {
struct fs_struct *fs = current->fs;
unsigned seq;
}
} else {
/* Caller must check execute permissions on the starting path component */
- struct fd f = fdget_raw(dfd);
+ struct fd f = fdget_raw(nd->dfd);
struct dentry *dentry;
if (!f.file)
- return -EBADF;
+ return ERR_PTR(-EBADF);
dentry = f.file->f_path.dentry;
if (*s) {
if (!d_can_lookup(dentry)) {
fdput(f);
- return -ENOTDIR;
+ return ERR_PTR(-ENOTDIR);
}
}
nd->path = f.file->f_path;
if (flags & LOOKUP_RCU) {
- if (f.flags & FDPUT_FPUT)
- nd->base = f.file;
- nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
rcu_read_lock();
+ nd->inode = nd->path.dentry->d_inode;
+ nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
} else {
path_get(&nd->path);
- fdput(f);
+ nd->inode = nd->path.dentry->d_inode;
}
+ fdput(f);
+ return s;
}
nd->inode = nd->path.dentry->d_inode;
if (!(flags & LOOKUP_RCU))
- goto done;
+ return s;
if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq)))
- goto done;
+ return s;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
rcu_read_unlock();
- return -ECHILD;
-done:
- current->total_link_count = 0;
- return link_path_walk(s, nd);
+ return ERR_PTR(-ECHILD);
}
-static void path_cleanup(struct nameidata *nd)
+static const char *trailing_symlink(struct nameidata *nd)
{
- if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
- path_put(&nd->root);
- nd->root.mnt = NULL;
- }
- if (unlikely(nd->base))
- fput(nd->base);
+ const char *s;
+ int error = may_follow_link(nd);
+ if (unlikely(error))
+ return ERR_PTR(error);
+ nd->flags |= LOOKUP_PARENT;
+ nd->stack[0].name = NULL;
+ s = get_link(nd);
+ return s ? s : "";
}
-static inline int lookup_last(struct nameidata *nd, struct path *path)
+static inline int lookup_last(struct nameidata *nd)
{
if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
nd->flags &= ~LOOKUP_PARENT;
- return walk_component(nd, path, nd->flags & LOOKUP_FOLLOW);
+ return walk_component(nd,
+ nd->flags & LOOKUP_FOLLOW
+ ? nd->depth
+ ? WALK_PUT | WALK_GET
+ : WALK_GET
+ : 0);
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
-static int path_lookupat(int dfd, const struct filename *name,
- unsigned int flags, struct nameidata *nd)
+static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
{
- struct path path;
+ const char *s = path_init(nd, flags);
int err;
- /*
- * Path walking is largely split up into 2 different synchronisation
- * schemes, rcu-walk and ref-walk (explained in
- * Documentation/filesystems/path-lookup.txt). These share much of the
- * path walk code, but some things particularly setup, cleanup, and
- * following mounts are sufficiently divergent that functions are
- * duplicated. Typically there is a function foo(), and its RCU
- * analogue, foo_rcu().
- *
- * -ECHILD is the error number of choice (just to avoid clashes) that
- * is returned if some aspect of an rcu-walk fails. Such an error must
- * be handled by restarting a traditional ref-walk (which will always
- * be able to complete).
- */
- err = path_init(dfd, name, flags, nd);
- if (!err && !(flags & LOOKUP_PARENT)) {
- err = lookup_last(nd, &path);
- while (err > 0) {
- void *cookie;
- struct path link = path;
- err = may_follow_link(&link, nd);
- if (unlikely(err))
- break;
- nd->flags |= LOOKUP_PARENT;
- err = follow_link(&link, nd, &cookie);
- if (err)
- break;
- err = lookup_last(nd, &path);
- put_link(nd, &link, cookie);
+ if (IS_ERR(s))
+ return PTR_ERR(s);
+ while (!(err = link_path_walk(s, nd))
+ && ((err = lookup_last(nd)) > 0)) {
+ s = trailing_symlink(nd);
+ if (IS_ERR(s)) {
+ err = PTR_ERR(s);
+ break;
}
}
-
if (!err)
err = complete_walk(nd);
- if (!err && nd->flags & LOOKUP_DIRECTORY) {
- if (!d_can_lookup(nd->path.dentry)) {
- path_put(&nd->path);
+ if (!err && nd->flags & LOOKUP_DIRECTORY)
+ if (!d_can_lookup(nd->path.dentry))
err = -ENOTDIR;
- }
+ if (!err) {
+ *path = nd->path;
+ nd->path.mnt = NULL;
+ nd->path.dentry = NULL;
}
-
- path_cleanup(nd);
+ terminate_walk(nd);
return err;
}
-static int filename_lookup(int dfd, struct filename *name,
- unsigned int flags, struct nameidata *nd)
+static int filename_lookup(int dfd, struct filename *name, unsigned flags,
+ struct path *path, struct path *root)
{
- int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
+ int retval;
+ struct nameidata nd;
+ if (IS_ERR(name))
+ return PTR_ERR(name);
+ if (unlikely(root)) {
+ nd.root = *root;
+ flags |= LOOKUP_ROOT;
+ }
+ set_nameidata(&nd, dfd, name);
+ retval = path_lookupat(&nd, flags | LOOKUP_RCU, path);
if (unlikely(retval == -ECHILD))
- retval = path_lookupat(dfd, name, flags, nd);
+ retval = path_lookupat(&nd, flags, path);
if (unlikely(retval == -ESTALE))
- retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);
+ retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path);
if (likely(!retval))
- audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT);
+ audit_inode(name, path->dentry, flags & LOOKUP_PARENT);
+ restore_nameidata();
+ putname(name);
return retval;
}
+/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+static int path_parentat(struct nameidata *nd, unsigned flags,
+ struct path *parent)
+{
+ const char *s = path_init(nd, flags);
+ int err;
+ if (IS_ERR(s))
+ return PTR_ERR(s);
+ err = link_path_walk(s, nd);
+ if (!err)
+ err = complete_walk(nd);
+ if (!err) {
+ *parent = nd->path;
+ nd->path.mnt = NULL;
+ nd->path.dentry = NULL;
+ }
+ terminate_walk(nd);
+ return err;
+}
+
+static struct filename *filename_parentat(int dfd, struct filename *name,
+ unsigned int flags, struct path *parent,
+ struct qstr *last, int *type)
+{
+ int retval;
+ struct nameidata nd;
+
+ if (IS_ERR(name))
+ return name;
+ set_nameidata(&nd, dfd, name);
+ retval = path_parentat(&nd, flags | LOOKUP_RCU, parent);
+ if (unlikely(retval == -ECHILD))
+ retval = path_parentat(&nd, flags, parent);
+ if (unlikely(retval == -ESTALE))
+ retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent);
+ if (likely(!retval)) {
+ *last = nd.last;
+ *type = nd.last_type;
+ audit_inode(name, parent->dentry, LOOKUP_PARENT);
+ } else {
+ putname(name);
+ name = ERR_PTR(retval);
+ }
+ restore_nameidata();
+ return name;
+}
+
/* does lookup, returns the object with parent locked */
struct dentry *kern_path_locked(const char *name, struct path *path)
{
- struct filename *filename = getname_kernel(name);
- struct nameidata nd;
+ struct filename *filename;
struct dentry *d;
- int err;
+ struct qstr last;
+ int type;
+ filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path,
+ &last, &type);
if (IS_ERR(filename))
return ERR_CAST(filename);
-
- err = filename_lookup(AT_FDCWD, filename, LOOKUP_PARENT, &nd);
- if (err) {
- d = ERR_PTR(err);
- goto out;
- }
- if (nd.last_type != LAST_NORM) {
- path_put(&nd.path);
- d = ERR_PTR(-EINVAL);
- goto out;
+ if (unlikely(type != LAST_NORM)) {
+ path_put(path);
+ putname(filename);
+ return ERR_PTR(-EINVAL);
}
- mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
- d = __lookup_hash(&nd.last, nd.path.dentry, 0);
+ mutex_lock_nested(&path->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ d = __lookup_hash(&last, path->dentry, 0);
if (IS_ERR(d)) {
- mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
- path_put(&nd.path);
- goto out;
+ mutex_unlock(&path->dentry->d_inode->i_mutex);
+ path_put(path);
}
- *path = nd.path;
-out:
putname(filename);
return d;
}
int kern_path(const char *name, unsigned int flags, struct path *path)
{
- struct nameidata nd;
- struct filename *filename = getname_kernel(name);
- int res = PTR_ERR(filename);
-
- if (!IS_ERR(filename)) {
- res = filename_lookup(AT_FDCWD, filename, flags, &nd);
- putname(filename);
- if (!res)
- *path = nd.path;
- }
- return res;
+ return filename_lookup(AT_FDCWD, getname_kernel(name),
+ flags, path, NULL);
}
EXPORT_SYMBOL(kern_path);
const char *name, unsigned int flags,
struct path *path)
{
- struct filename *filename = getname_kernel(name);
- int err = PTR_ERR(filename);
-
- BUG_ON(flags & LOOKUP_PARENT);
-
- /* the first argument of filename_lookup() is ignored with LOOKUP_ROOT */
- if (!IS_ERR(filename)) {
- struct nameidata nd;
- nd.root.dentry = dentry;
- nd.root.mnt = mnt;
- err = filename_lookup(AT_FDCWD, filename,
- flags | LOOKUP_ROOT, &nd);
- if (!err)
- *path = nd.path;
- putname(filename);
- }
- return err;
+ struct path root = {.mnt = mnt, .dentry = dentry};
+ /* the first argument of filename_lookup() is ignored with root */
+ return filename_lookup(AT_FDCWD, getname_kernel(name),
+ flags , path, &root);
}
EXPORT_SYMBOL(vfs_path_lookup);
-/*
- * Restricted form of lookup. Doesn't follow links, single-component only,
- * needs parent already locked. Doesn't follow mounts.
- * SMP-safe.
- */
-static struct dentry *lookup_hash(struct nameidata *nd)
-{
- return __lookup_hash(&nd->last, nd->path.dentry, nd->flags);
-}
-
/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
struct path *path, int *empty)
{
- struct nameidata nd;
- struct filename *tmp = getname_flags(name, flags, empty);
- int err = PTR_ERR(tmp);
- if (!IS_ERR(tmp)) {
-
- BUG_ON(flags & LOOKUP_PARENT);
-
- err = filename_lookup(dfd, tmp, flags, &nd);
- putname(tmp);
- if (!err)
- *path = nd.path;
- }
- return err;
-}
-
-int user_path_at(int dfd, const char __user *name, unsigned flags,
- struct path *path)
-{
- return user_path_at_empty(dfd, name, flags, path, NULL);
+ return filename_lookup(dfd, getname_flags(name, flags, empty),
+ flags, path, NULL);
}
-EXPORT_SYMBOL(user_path_at);
+EXPORT_SYMBOL(user_path_at_empty);
/*
* NB: most callers don't do anything directly with the reference to the
* allocated by getname. So we must hold the reference to it until all
* path-walking is complete.
*/
-static struct filename *
-user_path_parent(int dfd, const char __user *path, struct nameidata *nd,
+static inline struct filename *
+user_path_parent(int dfd, const char __user *path,
+ struct path *parent,
+ struct qstr *last,
+ int *type,
unsigned int flags)
{
- struct filename *s = getname(path);
- int error;
-
/* only LOOKUP_REVAL is allowed in extra flags */
- flags &= LOOKUP_REVAL;
-
- if (IS_ERR(s))
- return s;
-
- error = filename_lookup(dfd, s, flags | LOOKUP_PARENT, nd);
- if (error) {
- putname(s);
- return ERR_PTR(error);
- }
-
- return s;
+ return filename_parentat(dfd, getname(path), flags & LOOKUP_REVAL,
+ parent, last, type);
}
/**
/* If we're in rcuwalk, drop out of it to handle last component */
if (nd->flags & LOOKUP_RCU) {
- if (unlazy_walk(nd, NULL)) {
- error = -ECHILD;
- goto out;
- }
+ if (unlazy_walk(nd, NULL, 0))
+ return -ECHILD;
}
nd->flags &= ~LOOKUP_PARENT;
if (unlikely(nd->last_type != LAST_NORM)) {
error = handle_dots(nd, nd->last_type);
if (error)
- goto out;
+ return error;
dentry = dget(nd->path.dentry);
goto done;
}
*/
dentry = d_alloc(dir, &nd->last);
if (!dentry) {
- error = -ENOMEM;
mutex_unlock(&dir->d_inode->i_mutex);
- goto out;
+ return -ENOMEM;
}
dentry = lookup_real(dir->d_inode, dentry, nd->flags);
- error = PTR_ERR(dentry);
if (IS_ERR(dentry)) {
mutex_unlock(&dir->d_inode->i_mutex);
- goto out;
+ return PTR_ERR(dentry);
}
}
mutex_unlock(&dir->d_inode->i_mutex);
done:
if (d_is_negative(dentry)) {
- error = -ENOENT;
dput(dentry);
- goto out;
+ return -ENOENT;
}
+ if (nd->depth)
+ put_link(nd);
path->dentry = dentry;
path->mnt = nd->path.mnt;
- if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW))
- return 1;
+ error = should_follow_link(nd, path, nd->flags & LOOKUP_FOLLOW,
+ d_backing_inode(dentry), 0);
+ if (unlikely(error))
+ return error;
mntget(path->mnt);
follow_mount(path);
- error = 0;
-out:
- terminate_walk(nd);
- return error;
+ return 0;
}
/**
* path_mountpoint - look up a path to be umounted
- * @dfd: directory file descriptor to start walk from
- * @name: full pathname to walk
- * @path: pointer to container for result
+ * @nameidata: lookup context
* @flags: lookup flags
+ * @path: pointer to container for result
*
* Look up the given name, but don't attempt to revalidate the last component.
* Returns 0 and "path" will be valid on success; Returns error otherwise.
*/
static int
-path_mountpoint(int dfd, const struct filename *name, struct path *path,
- unsigned int flags)
+path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
{
- struct nameidata nd;
+ const char *s = path_init(nd, flags);
int err;
-
- err = path_init(dfd, name, flags, &nd);
- if (unlikely(err))
- goto out;
-
- err = mountpoint_last(&nd, path);
- while (err > 0) {
- void *cookie;
- struct path link = *path;
- err = may_follow_link(&link, &nd);
- if (unlikely(err))
- break;
- nd.flags |= LOOKUP_PARENT;
- err = follow_link(&link, &nd, &cookie);
- if (err)
+ if (IS_ERR(s))
+ return PTR_ERR(s);
+ while (!(err = link_path_walk(s, nd)) &&
+ (err = mountpoint_last(nd, path)) > 0) {
+ s = trailing_symlink(nd);
+ if (IS_ERR(s)) {
+ err = PTR_ERR(s);
break;
- err = mountpoint_last(&nd, path);
- put_link(&nd, &link, cookie);
+ }
}
-out:
- path_cleanup(&nd);
+ terminate_walk(nd);
return err;
}
filename_mountpoint(int dfd, struct filename *name, struct path *path,
unsigned int flags)
{
+ struct nameidata nd;
int error;
if (IS_ERR(name))
return PTR_ERR(name);
- error = path_mountpoint(dfd, name, path, flags | LOOKUP_RCU);
+ set_nameidata(&nd, dfd, name);
+ error = path_mountpoint(&nd, flags | LOOKUP_RCU, path);
if (unlikely(error == -ECHILD))
- error = path_mountpoint(dfd, name, path, flags);
+ error = path_mountpoint(&nd, flags, path);
if (unlikely(error == -ESTALE))
- error = path_mountpoint(dfd, name, path, flags | LOOKUP_REVAL);
+ error = path_mountpoint(&nd, flags | LOOKUP_REVAL, path);
if (likely(!error))
audit_inode(name, path->dentry, 0);
+ restore_nameidata();
putname(name);
return error;
}
*/
static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
{
- struct inode *inode = victim->d_inode;
+ struct inode *inode = d_backing_inode(victim);
int error;
if (d_is_negative(victim))
/*
* Handle the last step of open()
*/
-static int do_last(struct nameidata *nd, struct path *path,
+static int do_last(struct nameidata *nd,
struct file *file, const struct open_flags *op,
- int *opened, struct filename *name)
+ int *opened)
{
struct dentry *dir = nd->path.dentry;
int open_flag = op->open_flag;
bool will_truncate = (open_flag & O_TRUNC) != 0;
bool got_write = false;
int acc_mode = op->acc_mode;
+ unsigned seq;
struct inode *inode;
- bool symlink_ok = false;
struct path save_parent = { .dentry = NULL, .mnt = NULL };
+ struct path path;
bool retried = false;
int error;
if (nd->last_type != LAST_NORM) {
error = handle_dots(nd, nd->last_type);
- if (error)
+ if (unlikely(error))
return error;
goto finish_open;
}
if (!(open_flag & O_CREAT)) {
if (nd->last.name[nd->last.len])
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
- if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
- symlink_ok = true;
/* we _can_ be in RCU mode here */
- error = lookup_fast(nd, path, &inode);
+ error = lookup_fast(nd, &path, &inode, &seq);
if (likely(!error))
goto finish_lookup;
if (error < 0)
- goto out;
+ return error;
BUG_ON(nd->inode != dir->d_inode);
} else {
if (error)
return error;
- audit_inode(name, dir, LOOKUP_PARENT);
- error = -EISDIR;
+ audit_inode(nd->name, dir, LOOKUP_PARENT);
/* trailing slashes? */
- if (nd->last.name[nd->last.len])
- goto out;
+ if (unlikely(nd->last.name[nd->last.len]))
+ return -EISDIR;
}
retry_lookup:
*/
}
mutex_lock(&dir->d_inode->i_mutex);
- error = lookup_open(nd, path, file, op, got_write, opened);
+ error = lookup_open(nd, &path, file, op, got_write, opened);
mutex_unlock(&dir->d_inode->i_mutex);
if (error <= 0) {
!S_ISREG(file_inode(file)->i_mode))
will_truncate = false;
- audit_inode(name, file->f_path.dentry, 0);
+ audit_inode(nd->name, file->f_path.dentry, 0);
goto opened;
}
open_flag &= ~O_TRUNC;
will_truncate = false;
acc_mode = MAY_OPEN;
- path_to_nameidata(path, nd);
+ path_to_nameidata(&path, nd);
goto finish_open_created;
}
/*
* create/update audit record if it already exists.
*/
- if (d_is_positive(path->dentry))
- audit_inode(name, path->dentry, 0);
+ if (d_is_positive(path.dentry))
+ audit_inode(nd->name, path.dentry, 0);
/*
* If atomic_open() acquired write access it is dropped now due to
got_write = false;
}
- error = -EEXIST;
- if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))
- goto exit_dput;
-
- error = follow_managed(path, nd->flags);
- if (error < 0)
- goto exit_dput;
+ if (unlikely((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))) {
+ path_to_nameidata(&path, nd);
+ return -EEXIST;
+ }
- if (error)
- nd->flags |= LOOKUP_JUMPED;
+ error = follow_managed(&path, nd);
+ if (unlikely(error < 0))
+ return error;
BUG_ON(nd->flags & LOOKUP_RCU);
- inode = path->dentry->d_inode;
-finish_lookup:
- /* we _can_ be in RCU mode here */
- error = -ENOENT;
- if (d_is_negative(path->dentry)) {
- path_to_nameidata(path, nd);
- goto out;
+ inode = d_backing_inode(path.dentry);
+ seq = 0; /* out of RCU mode, so the value doesn't matter */
+ if (unlikely(d_is_negative(path.dentry))) {
+ path_to_nameidata(&path, nd);
+ return -ENOENT;
}
+finish_lookup:
+ if (nd->depth)
+ put_link(nd);
+ error = should_follow_link(nd, &path, nd->flags & LOOKUP_FOLLOW,
+ inode, seq);
+ if (unlikely(error))
+ return error;
- if (should_follow_link(path->dentry, !symlink_ok)) {
- if (nd->flags & LOOKUP_RCU) {
- if (unlikely(nd->path.mnt != path->mnt ||
- unlazy_walk(nd, path->dentry))) {
- error = -ECHILD;
- goto out;
- }
- }
- BUG_ON(inode != path->dentry->d_inode);
- return 1;
+ if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) {
+ path_to_nameidata(&path, nd);
+ return -ELOOP;
}
- if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) {
- path_to_nameidata(path, nd);
+ if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
+ path_to_nameidata(&path, nd);
} else {
save_parent.dentry = nd->path.dentry;
- save_parent.mnt = mntget(path->mnt);
- nd->path.dentry = path->dentry;
+ save_parent.mnt = mntget(path.mnt);
+ nd->path.dentry = path.dentry;
}
nd->inode = inode;
+ nd->seq = seq;
/* Why this, you ask? _Now_ we might have grown LOOKUP_JUMPED... */
finish_open:
error = complete_walk(nd);
path_put(&save_parent);
return error;
}
- audit_inode(name, nd->path.dentry, 0);
+ audit_inode(nd->name, nd->path.dentry, 0);
error = -EISDIR;
if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
goto out;
if (got_write)
mnt_drop_write(nd->path.mnt);
path_put(&save_parent);
- terminate_walk(nd);
return error;
-exit_dput:
- path_put_conditional(path, nd);
- goto out;
exit_fput:
fput(file);
goto out;
goto retry_lookup;
}
-static int do_tmpfile(int dfd, struct filename *pathname,
- struct nameidata *nd, int flags,
+static int do_tmpfile(struct nameidata *nd, unsigned flags,
const struct open_flags *op,
struct file *file, int *opened)
{
static const struct qstr name = QSTR_INIT("/", 1);
- struct dentry *dentry, *child;
+ struct dentry *child;
struct inode *dir;
- int error = path_lookupat(dfd, pathname,
- flags | LOOKUP_DIRECTORY, nd);
+ struct path path;
+ int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
if (unlikely(error))
return error;
- error = mnt_want_write(nd->path.mnt);
+ error = mnt_want_write(path.mnt);
if (unlikely(error))
goto out;
+ dir = path.dentry->d_inode;
/* we want directory to be writable */
- error = inode_permission(nd->inode, MAY_WRITE | MAY_EXEC);
+ error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out2;
- dentry = nd->path.dentry;
- dir = dentry->d_inode;
if (!dir->i_op->tmpfile) {
error = -EOPNOTSUPP;
goto out2;
}
- child = d_alloc(dentry, &name);
+ child = d_alloc(path.dentry, &name);
if (unlikely(!child)) {
error = -ENOMEM;
goto out2;
}
- nd->flags &= ~LOOKUP_DIRECTORY;
- nd->flags |= op->intent;
- dput(nd->path.dentry);
- nd->path.dentry = child;
- error = dir->i_op->tmpfile(dir, nd->path.dentry, op->mode);
+ dput(path.dentry);
+ path.dentry = child;
+ error = dir->i_op->tmpfile(dir, child, op->mode);
if (error)
goto out2;
- audit_inode(pathname, nd->path.dentry, 0);
+ audit_inode(nd->name, child, 0);
/* Don't check for other permissions, the inode was just created */
- error = may_open(&nd->path, MAY_OPEN, op->open_flag);
+ error = may_open(&path, MAY_OPEN, op->open_flag);
if (error)
goto out2;
- file->f_path.mnt = nd->path.mnt;
- error = finish_open(file, nd->path.dentry, NULL, opened);
+ file->f_path.mnt = path.mnt;
+ error = finish_open(file, child, NULL, opened);
if (error)
goto out2;
error = open_check_o_direct(file);
spin_unlock(&inode->i_lock);
}
out2:
- mnt_drop_write(nd->path.mnt);
+ mnt_drop_write(path.mnt);
out:
- path_put(&nd->path);
+ path_put(&path);
return error;
}
-static struct file *path_openat(int dfd, struct filename *pathname,
- struct nameidata *nd, const struct open_flags *op, int flags)
+static struct file *path_openat(struct nameidata *nd,
+ const struct open_flags *op, unsigned flags)
{
+ const char *s;
struct file *file;
- struct path path;
int opened = 0;
int error;
file->f_flags = op->open_flag;
if (unlikely(file->f_flags & __O_TMPFILE)) {
- error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened);
- goto out;
+ error = do_tmpfile(nd, flags, op, file, &opened);
+ goto out2;
}
- error = path_init(dfd, pathname, flags, nd);
- if (unlikely(error))
- goto out;
-
- error = do_last(nd, &path, file, op, &opened, pathname);
- while (unlikely(error > 0)) { /* trailing symlink */
- struct path link = path;
- void *cookie;
- if (!(nd->flags & LOOKUP_FOLLOW)) {
- path_put_conditional(&path, nd);
- path_put(&nd->path);
- error = -ELOOP;
- break;
- }
- error = may_follow_link(&link, nd);
- if (unlikely(error))
- break;
- nd->flags |= LOOKUP_PARENT;
+ s = path_init(nd, flags);
+ if (IS_ERR(s)) {
+ put_filp(file);
+ return ERR_CAST(s);
+ }
+ while (!(error = link_path_walk(s, nd)) &&
+ (error = do_last(nd, file, op, &opened)) > 0) {
nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
- error = follow_link(&link, nd, &cookie);
- if (unlikely(error))
+ s = trailing_symlink(nd);
+ if (IS_ERR(s)) {
+ error = PTR_ERR(s);
break;
- error = do_last(nd, &path, file, op, &opened, pathname);
- put_link(nd, &link, cookie);
+ }
}
-out:
- path_cleanup(nd);
+ terminate_walk(nd);
+out2:
if (!(opened & FILE_OPENED)) {
BUG_ON(!error);
put_filp(file);
int flags = op->lookup_flags;
struct file *filp;
- filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_RCU);
+ set_nameidata(&nd, dfd, pathname);
+ filp = path_openat(&nd, op, flags | LOOKUP_RCU);
if (unlikely(filp == ERR_PTR(-ECHILD)))
- filp = path_openat(dfd, pathname, &nd, op, flags);
+ filp = path_openat(&nd, op, flags);
if (unlikely(filp == ERR_PTR(-ESTALE)))
- filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_REVAL);
+ filp = path_openat(&nd, op, flags | LOOKUP_REVAL);
+ restore_nameidata();
return filp;
}
if (unlikely(IS_ERR(filename)))
return ERR_CAST(filename);
- file = path_openat(-1, filename, &nd, op, flags | LOOKUP_RCU);
+ set_nameidata(&nd, -1, filename);
+ file = path_openat(&nd, op, flags | LOOKUP_RCU);
if (unlikely(file == ERR_PTR(-ECHILD)))
- file = path_openat(-1, filename, &nd, op, flags);
+ file = path_openat(&nd, op, flags);
if (unlikely(file == ERR_PTR(-ESTALE)))
- file = path_openat(-1, filename, &nd, op, flags | LOOKUP_REVAL);
+ file = path_openat(&nd, op, flags | LOOKUP_REVAL);
+ restore_nameidata();
putname(filename);
return file;
}
struct path *path, unsigned int lookup_flags)
{
struct dentry *dentry = ERR_PTR(-EEXIST);
- struct nameidata nd;
+ struct qstr last;
+ int type;
int err2;
int error;
bool is_dir = (lookup_flags & LOOKUP_DIRECTORY);
*/
lookup_flags &= LOOKUP_REVAL;
- error = filename_lookup(dfd, name, LOOKUP_PARENT|lookup_flags, &nd);
- if (error)
- return ERR_PTR(error);
+ name = filename_parentat(dfd, name, lookup_flags, path, &last, &type);
+ if (IS_ERR(name))
+ return ERR_CAST(name);
/*
* Yucky last component or no last component at all?
* (foo/., foo/.., /////)
*/
- if (nd.last_type != LAST_NORM)
+ if (unlikely(type != LAST_NORM))
goto out;
- nd.flags &= ~LOOKUP_PARENT;
- nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL;
/* don't fail immediately if it's r/o, at least try to report other errors */
- err2 = mnt_want_write(nd.path.mnt);
+ err2 = mnt_want_write(path->mnt);
/*
* Do the final lookup.
*/
- mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
- dentry = lookup_hash(&nd);
+ lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL;
+ mutex_lock_nested(&path->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ dentry = __lookup_hash(&last, path->dentry, lookup_flags);
if (IS_ERR(dentry))
goto unlock;
* all is fine. Let's be bastards - you had / on the end, you've
* been asking for (non-existent) directory. -ENOENT for you.
*/
- if (unlikely(!is_dir && nd.last.name[nd.last.len])) {
+ if (unlikely(!is_dir && last.name[last.len])) {
error = -ENOENT;
goto fail;
}
error = err2;
goto fail;
}
- *path = nd.path;
+ putname(name);
return dentry;
fail:
dput(dentry);
dentry = ERR_PTR(error);
unlock:
- mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ mutex_unlock(&path->dentry->d_inode->i_mutex);
if (!err2)
- mnt_drop_write(nd.path.mnt);
+ mnt_drop_write(path->mnt);
out:
- path_put(&nd.path);
+ path_put(path);
+ putname(name);
return dentry;
}
struct dentry *kern_path_create(int dfd, const char *pathname,
struct path *path, unsigned int lookup_flags)
{
- struct filename *filename = getname_kernel(pathname);
- struct dentry *res;
-
- if (IS_ERR(filename))
- return ERR_CAST(filename);
- res = filename_create(dfd, filename, path, lookup_flags);
- putname(filename);
- return res;
+ return filename_create(dfd, getname_kernel(pathname),
+ path, lookup_flags);
}
EXPORT_SYMBOL(kern_path_create);
}
EXPORT_SYMBOL(done_path_create);
-struct dentry *user_path_create(int dfd, const char __user *pathname,
+inline struct dentry *user_path_create(int dfd, const char __user *pathname,
struct path *path, unsigned int lookup_flags)
{
- struct filename *tmp = getname(pathname);
- struct dentry *res;
- if (IS_ERR(tmp))
- return ERR_CAST(tmp);
- res = filename_create(dfd, tmp, path, lookup_flags);
- putname(tmp);
- return res;
+ return filename_create(dfd, getname(pathname), path, lookup_flags);
}
EXPORT_SYMBOL(user_path_create);
int error = 0;
struct filename *name;
struct dentry *dentry;
- struct nameidata nd;
+ struct path path;
+ struct qstr last;
+ int type;
unsigned int lookup_flags = 0;
retry:
- name = user_path_parent(dfd, pathname, &nd, lookup_flags);
+ name = user_path_parent(dfd, pathname,
+ &path, &last, &type, lookup_flags);
if (IS_ERR(name))
return PTR_ERR(name);
- switch(nd.last_type) {
+ switch (type) {
case LAST_DOTDOT:
error = -ENOTEMPTY;
goto exit1;
goto exit1;
}
- nd.flags &= ~LOOKUP_PARENT;
- error = mnt_want_write(nd.path.mnt);
+ error = mnt_want_write(path.mnt);
if (error)
goto exit1;
- mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
- dentry = lookup_hash(&nd);
+ mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ dentry = __lookup_hash(&last, path.dentry, lookup_flags);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto exit2;
error = -ENOENT;
goto exit3;
}
- error = security_path_rmdir(&nd.path, dentry);
+ error = security_path_rmdir(&path, dentry);
if (error)
goto exit3;
- error = vfs_rmdir(nd.path.dentry->d_inode, dentry);
+ error = vfs_rmdir(path.dentry->d_inode, dentry);
exit3:
dput(dentry);
exit2:
- mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
- mnt_drop_write(nd.path.mnt);
+ mutex_unlock(&path.dentry->d_inode->i_mutex);
+ mnt_drop_write(path.mnt);
exit1:
- path_put(&nd.path);
+ path_put(&path);
putname(name);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
int error;
struct filename *name;
struct dentry *dentry;
- struct nameidata nd;
+ struct path path;
+ struct qstr last;
+ int type;
struct inode *inode = NULL;
struct inode *delegated_inode = NULL;
unsigned int lookup_flags = 0;
retry:
- name = user_path_parent(dfd, pathname, &nd, lookup_flags);
+ name = user_path_parent(dfd, pathname,
+ &path, &last, &type, lookup_flags);
if (IS_ERR(name))
return PTR_ERR(name);
error = -EISDIR;
- if (nd.last_type != LAST_NORM)
+ if (type != LAST_NORM)
goto exit1;
- nd.flags &= ~LOOKUP_PARENT;
- error = mnt_want_write(nd.path.mnt);
+ error = mnt_want_write(path.mnt);
if (error)
goto exit1;
retry_deleg:
- mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
- dentry = lookup_hash(&nd);
+ mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ dentry = __lookup_hash(&last, path.dentry, lookup_flags);
error = PTR_ERR(dentry);
if (!IS_ERR(dentry)) {
/* Why not before? Because we want correct error value */
- if (nd.last.name[nd.last.len])
+ if (last.name[last.len])
goto slashes;
inode = dentry->d_inode;
if (d_is_negative(dentry))
goto slashes;
ihold(inode);
- error = security_path_unlink(&nd.path, dentry);
+ error = security_path_unlink(&path, dentry);
if (error)
goto exit2;
- error = vfs_unlink(nd.path.dentry->d_inode, dentry, &delegated_inode);
+ error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode);
exit2:
dput(dentry);
}
- mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ mutex_unlock(&path.dentry->d_inode->i_mutex);
if (inode)
iput(inode); /* truncate the inode here */
inode = NULL;
if (!error)
goto retry_deleg;
}
- mnt_drop_write(nd.path.mnt);
+ mnt_drop_write(path.mnt);
exit1:
- path_put(&nd.path);
+ path_put(&path);
putname(name);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
int, newdfd, const char __user *, newname, unsigned int, flags)
{
- struct dentry *old_dir, *new_dir;
struct dentry *old_dentry, *new_dentry;
struct dentry *trap;
- struct nameidata oldnd, newnd;
+ struct path old_path, new_path;
+ struct qstr old_last, new_last;
+ int old_type, new_type;
struct inode *delegated_inode = NULL;
struct filename *from;
struct filename *to;
- unsigned int lookup_flags = 0;
+ unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET;
bool should_retry = false;
int error;
if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD))
return -EPERM;
+ if (flags & RENAME_EXCHANGE)
+ target_flags = 0;
+
retry:
- from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
+ from = user_path_parent(olddfd, oldname,
+ &old_path, &old_last, &old_type, lookup_flags);
if (IS_ERR(from)) {
error = PTR_ERR(from);
goto exit;
}
- to = user_path_parent(newdfd, newname, &newnd, lookup_flags);
+ to = user_path_parent(newdfd, newname,
+ &new_path, &new_last, &new_type, lookup_flags);
if (IS_ERR(to)) {
error = PTR_ERR(to);
goto exit1;
}
error = -EXDEV;
- if (oldnd.path.mnt != newnd.path.mnt)
+ if (old_path.mnt != new_path.mnt)
goto exit2;
- old_dir = oldnd.path.dentry;
error = -EBUSY;
- if (oldnd.last_type != LAST_NORM)
+ if (old_type != LAST_NORM)
goto exit2;
- new_dir = newnd.path.dentry;
if (flags & RENAME_NOREPLACE)
error = -EEXIST;
- if (newnd.last_type != LAST_NORM)
+ if (new_type != LAST_NORM)
goto exit2;
- error = mnt_want_write(oldnd.path.mnt);
+ error = mnt_want_write(old_path.mnt);
if (error)
goto exit2;
- oldnd.flags &= ~LOOKUP_PARENT;
- newnd.flags &= ~LOOKUP_PARENT;
- if (!(flags & RENAME_EXCHANGE))
- newnd.flags |= LOOKUP_RENAME_TARGET;
-
retry_deleg:
- trap = lock_rename(new_dir, old_dir);
+ trap = lock_rename(new_path.dentry, old_path.dentry);
- old_dentry = lookup_hash(&oldnd);
+ old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags);
error = PTR_ERR(old_dentry);
if (IS_ERR(old_dentry))
goto exit3;
error = -ENOENT;
if (d_is_negative(old_dentry))
goto exit4;
- new_dentry = lookup_hash(&newnd);
+ new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags);
error = PTR_ERR(new_dentry);
if (IS_ERR(new_dentry))
goto exit4;
if (!d_is_dir(new_dentry)) {
error = -ENOTDIR;
- if (newnd.last.name[newnd.last.len])
+ if (new_last.name[new_last.len])
goto exit5;
}
}
/* unless the source is a directory trailing slashes give -ENOTDIR */
if (!d_is_dir(old_dentry)) {
error = -ENOTDIR;
- if (oldnd.last.name[oldnd.last.len])
+ if (old_last.name[old_last.len])
goto exit5;
- if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len])
+ if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len])
goto exit5;
}
/* source should not be ancestor of target */
if (new_dentry == trap)
goto exit5;
- error = security_path_rename(&oldnd.path, old_dentry,
- &newnd.path, new_dentry, flags);
+ error = security_path_rename(&old_path, old_dentry,
+ &new_path, new_dentry, flags);
if (error)
goto exit5;
- error = vfs_rename(old_dir->d_inode, old_dentry,
- new_dir->d_inode, new_dentry,
+ error = vfs_rename(old_path.dentry->d_inode, old_dentry,
+ new_path.dentry->d_inode, new_dentry,
&delegated_inode, flags);
exit5:
dput(new_dentry);
exit4:
dput(old_dentry);
exit3:
- unlock_rename(new_dir, old_dir);
+ unlock_rename(new_path.dentry, old_path.dentry);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
- mnt_drop_write(oldnd.path.mnt);
+ mnt_drop_write(old_path.mnt);
exit2:
if (retry_estale(error, lookup_flags))
should_retry = true;
- path_put(&newnd.path);
+ path_put(&new_path);
putname(to);
exit1:
- path_put(&oldnd.path);
+ path_put(&old_path);
putname(from);
if (should_retry) {
should_retry = false;
*/
int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
- struct nameidata nd;
void *cookie;
+ struct inode *inode = d_inode(dentry);
+ const char *link = inode->i_link;
int res;
- nd.depth = 0;
- cookie = dentry->d_inode->i_op->follow_link(dentry, &nd);
- if (IS_ERR(cookie))
- return PTR_ERR(cookie);
-
- res = readlink_copy(buffer, buflen, nd_get_link(&nd));
- if (dentry->d_inode->i_op->put_link)
- dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
+ if (!link) {
+ link = inode->i_op->follow_link(dentry, &cookie);
+ if (IS_ERR(link))
+ return PTR_ERR(link);
+ }
+ res = readlink_copy(buffer, buflen, link);
+ if (inode->i_op->put_link)
+ inode->i_op->put_link(inode, cookie);
return res;
}
EXPORT_SYMBOL(generic_readlink);
}
EXPORT_SYMBOL(page_readlink);
-void *page_follow_link_light(struct dentry *dentry, struct nameidata *nd)
+const char *page_follow_link_light(struct dentry *dentry, void **cookie)
{
struct page *page = NULL;
- nd_set_link(nd, page_getlink(dentry, &page));
- return page;
+ char *res = page_getlink(dentry, &page);
+ if (!IS_ERR(res))
+ *cookie = page;
+ return res;
}
EXPORT_SYMBOL(page_follow_link_light);
-void page_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+void page_put_link(struct inode *unused, void *cookie)
{
struct page *page = cookie;
-
- if (page) {
- kunmap(page);
- page_cache_release(page);
- }
+ kunmap(page);
+ page_cache_release(page);
}
EXPORT_SYMBOL(page_put_link);
}
/* call under rcu_read_lock */
-bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
+int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
{
struct mount *mnt;
if (read_seqretry(&mount_lock, seq))
- return false;
+ return 1;
if (bastard == NULL)
- return true;
+ return 0;
mnt = real_mount(bastard);
mnt_add_count(mnt, 1);
if (likely(!read_seqretry(&mount_lock, seq)))
- return true;
+ return 0;
if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
mnt_add_count(mnt, -1);
- return false;
+ return 1;
+ }
+ return -1;
+}
+
+/* call under rcu_read_lock */
+bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
+{
+ int res = __legitimize_mnt(bastard, seq);
+ if (likely(!res))
+ return true;
+ if (unlikely(res < 0)) {
+ rcu_read_unlock();
+ mntput(bastard);
+ rcu_read_lock();
}
- rcu_read_unlock();
- mntput(bastard);
- rcu_read_lock();
return false;
}
if (mnt->mnt.mnt_sb->s_type != type)
continue;
+ /* This mount is not fully visible if it's root directory
+ * is not the root directory of the filesystem.
+ */
+ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
+ continue;
+
/* This mount is not fully visible if there are any child mounts
* that cover anything except for empty directories.
*/
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/errno.h>
+#include <linux/file.h>
#include <linux/string.h>
#include <linux/ratelimit.h>
#include <linux/printk.h>
p->server = server;
atomic_inc(&lsp->ls_count);
p->ctx = get_nfs_open_context(ctx);
+ get_file(fl->fl_file);
memcpy(&p->fl, fl, sizeof(p->fl));
return p;
out_free_seqid:
nfs_free_seqid(data->arg.lock_seqid);
nfs4_put_lock_state(data->lsp);
put_nfs_open_context(data->ctx);
+ fput(data->fl.fl_file);
kfree(data);
dprintk("%s: done!\n", __func__);
}
#include <linux/stat.h>
#include <linux/mm.h>
#include <linux/string.h>
-#include <linux/namei.h>
/* Symlink caching in the page cache is even more simplistic
* and straight-forward than readdir caching.
return -EIO;
}
-static void *nfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *nfs_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
struct page *page;
err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
if (err)
- goto read_failed;
+ return err;
page = read_cache_page(&inode->i_data, 0,
(filler_t *)nfs_symlink_filler, inode);
- if (IS_ERR(page)) {
- err = page;
- goto read_failed;
- }
- nd_set_link(nd, kmap(page));
- return page;
-
-read_failed:
- nd_set_link(nd, err);
- return NULL;
+ if (IS_ERR(page))
+ return ERR_CAST(page);
+ *cookie = page;
+ return kmap(page);
}
/*
trace_nfs_writeback_inode_enter(inode);
ret = filemap_write_and_wait(inode->i_mapping);
- if (!ret) {
- ret = nfs_commit_inode(inode, FLUSH_SYNC);
- if (!ret)
- pnfs_sync_inode(inode, true);
- }
+ if (ret)
+ goto out;
+ ret = nfs_commit_inode(inode, FLUSH_SYNC);
+ if (ret < 0)
+ goto out;
+ pnfs_sync_inode(inode, true);
+ ret = 0;
+out:
trace_nfs_writeback_inode_exit(inode, ret);
return ret;
}
}
const struct nfsd4_layout_ops bl_layout_ops = {
+ /*
+ * Pretend that we send notification to the client. This is a blatant
+ * lie to force recent Linux clients to cache our device IDs.
+ * We rarely ever change the device ID, so the harm of leaking deviceids
+ * for a while isn't too bad. Unfortunately RFC5661 is a complete mess
+ * in this regard, but I filed errata 4119 for this a while ago, and
+ * hopefully the Linux client will eventually start caching deviceids
+ * without this again.
+ */
+ .notify_types =
+ NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
.proc_getdeviceinfo = nfsd4_block_proc_getdeviceinfo,
.encode_getdeviceinfo = nfsd4_block_encode_getdeviceinfo,
.proc_layoutget = nfsd4_block_proc_layoutget,
}
static int decode_cb_op_status(struct xdr_stream *xdr, enum nfs_opnum4 expected,
- enum nfsstat4 *status)
+ int *status)
{
__be32 *p;
u32 op;
op = be32_to_cpup(p++);
if (unlikely(op != expected))
goto out_unexpected;
- *status = be32_to_cpup(p);
+ *status = nfs_cb_stat_to_errno(be32_to_cpup(p));
return 0;
out_overflow:
print_overflow_msg(__func__, xdr);
static int decode_cb_sequence4res(struct xdr_stream *xdr,
struct nfsd4_callback *cb)
{
- enum nfsstat4 nfserr;
int status;
if (cb->cb_minorversion == 0)
return 0;
- status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &nfserr);
- if (unlikely(status))
- goto out;
- if (unlikely(nfserr != NFS4_OK))
- goto out_default;
- status = decode_cb_sequence4resok(xdr, cb);
-out:
- return status;
-out_default:
- return nfs_cb_stat_to_errno(nfserr);
+ status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &cb->cb_status);
+ if (unlikely(status || cb->cb_status))
+ return status;
+
+ return decode_cb_sequence4resok(xdr, cb);
}
/*
struct nfsd4_callback *cb)
{
struct nfs4_cb_compound_hdr hdr;
- enum nfsstat4 nfserr;
int status;
status = decode_cb_compound4res(xdr, &hdr);
if (unlikely(status))
- goto out;
+ return status;
if (cb != NULL) {
status = decode_cb_sequence4res(xdr, cb);
- if (unlikely(status))
- goto out;
+ if (unlikely(status || cb->cb_status))
+ return status;
}
- status = decode_cb_op_status(xdr, OP_CB_RECALL, &nfserr);
- if (unlikely(status))
- goto out;
- if (unlikely(nfserr != NFS4_OK))
- status = nfs_cb_stat_to_errno(nfserr);
-out:
- return status;
+ return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status);
}
#ifdef CONFIG_NFSD_PNFS
struct nfsd4_callback *cb)
{
struct nfs4_cb_compound_hdr hdr;
- enum nfsstat4 nfserr;
int status;
status = decode_cb_compound4res(xdr, &hdr);
if (unlikely(status))
- goto out;
+ return status;
+
if (cb) {
status = decode_cb_sequence4res(xdr, cb);
- if (unlikely(status))
- goto out;
+ if (unlikely(status || cb->cb_status))
+ return status;
}
- status = decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &nfserr);
- if (unlikely(status))
- goto out;
- if (unlikely(nfserr != NFS4_OK))
- status = nfs_cb_stat_to_errno(nfserr);
-out:
- return status;
+ return decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &cb->cb_status);
}
#endif /* CONFIG_NFSD_PNFS */
if (!nfsd41_cb_get_slot(clp, task))
return;
}
- spin_lock(&clp->cl_lock);
- if (list_empty(&cb->cb_per_client)) {
- /* This is the first call, not a restart */
- cb->cb_done = false;
- list_add(&cb->cb_per_client, &clp->cl_callbacks);
- }
- spin_unlock(&clp->cl_lock);
rpc_call_start(task);
}
if (clp->cl_minorversion) {
/* No need for lock, access serialized in nfsd4_cb_prepare */
- ++clp->cl_cb_session->se_cb_seq_nr;
+ if (!task->tk_status)
+ ++clp->cl_cb_session->se_cb_seq_nr;
clear_bit(0, &clp->cl_cb_slot_busy);
rpc_wake_up_next(&clp->cl_cb_waitq);
dprintk("%s: freed slot, new seqid=%d\n", __func__,
clp->cl_cb_session->se_cb_seq_nr);
}
- if (clp->cl_cb_client != task->tk_client) {
- /* We're shutting down or changing cl_cb_client; leave
- * it to nfsd4_process_cb_update to restart the call if
- * necessary. */
+ /*
+ * If the backchannel connection was shut down while this
+ * task was queued, we need to resubmit it after setting up
+ * a new backchannel connection.
+ *
+ * Note that if we lost our callback connection permanently
+ * the submission code will error out, so we don't need to
+ * handle that case here.
+ */
+ if (task->tk_flags & RPC_TASK_KILLED) {
+ task->tk_status = 0;
+ cb->cb_need_restart = true;
return;
}
- if (cb->cb_done)
- return;
+ if (cb->cb_status) {
+ WARN_ON_ONCE(task->tk_status);
+ task->tk_status = cb->cb_status;
+ }
switch (cb->cb_ops->done(cb, task)) {
case 0:
default:
BUG();
}
- cb->cb_done = true;
}
static void nfsd4_cb_release(void *calldata)
{
struct nfsd4_callback *cb = calldata;
- struct nfs4_client *clp = cb->cb_clp;
-
- if (cb->cb_done) {
- spin_lock(&clp->cl_lock);
- list_del(&cb->cb_per_client);
- spin_unlock(&clp->cl_lock);
+ if (cb->cb_need_restart)
+ nfsd4_run_cb(cb);
+ else
cb->cb_ops->release(cb);
- }
+
}
static const struct rpc_call_ops nfsd4_cb_ops = {
nfsd4_mark_cb_down(clp, err);
return;
}
- /* Yay, the callback channel's back! Restart any callbacks: */
- list_for_each_entry(cb, &clp->cl_callbacks, cb_per_client)
- queue_work(callback_wq, &cb->cb_work);
}
static void
struct nfs4_client *clp = cb->cb_clp;
struct rpc_clnt *clnt;
- if (cb->cb_ops && cb->cb_ops->prepare)
- cb->cb_ops->prepare(cb);
+ if (cb->cb_need_restart) {
+ cb->cb_need_restart = false;
+ } else {
+ if (cb->cb_ops && cb->cb_ops->prepare)
+ cb->cb_ops->prepare(cb);
+ }
if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)
nfsd4_process_cb_update(cb);
cb->cb_ops->release(cb);
return;
}
+
+ /*
+ * Don't send probe messages for 4.1 or later.
+ */
+ if (!cb->cb_ops && clp->cl_minorversion) {
+ clp->cl_cb_state = NFSD4_CB_UP;
+ return;
+ }
+
cb->cb_msg.rpc_cred = clp->cl_cb_cred;
rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb);
cb->cb_msg.rpc_resp = cb;
cb->cb_ops = ops;
INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
- INIT_LIST_HEAD(&cb->cb_per_client);
- cb->cb_done = true;
+ cb->cb_status = 0;
+ cb->cb_need_restart = false;
}
void nfsd4_run_cb(struct nfsd4_callback *cb)
static struct kmem_cache *file_slab;
static struct kmem_cache *stateid_slab;
static struct kmem_cache *deleg_slab;
+static struct kmem_cache *odstate_slab;
static void free_session(struct nfsd4_session *);
if (atomic_dec_and_lock(&fi->fi_ref, &state_lock)) {
hlist_del_rcu(&fi->fi_hash);
spin_unlock(&state_lock);
+ WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate));
WARN_ON_ONCE(!list_empty(&fi->fi_delegations));
call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu);
}
__nfs4_file_put_access(fp, O_RDONLY);
}
+/*
+ * Allocate a new open/delegation state counter. This is needed for
+ * pNFS for proper return on close semantics.
+ *
+ * Note that we only allocate it for pNFS-enabled exports, otherwise
+ * all pointers to struct nfs4_clnt_odstate are always NULL.
+ */
+static struct nfs4_clnt_odstate *
+alloc_clnt_odstate(struct nfs4_client *clp)
+{
+ struct nfs4_clnt_odstate *co;
+
+ co = kmem_cache_zalloc(odstate_slab, GFP_KERNEL);
+ if (co) {
+ co->co_client = clp;
+ atomic_set(&co->co_odcount, 1);
+ }
+ return co;
+}
+
+static void
+hash_clnt_odstate_locked(struct nfs4_clnt_odstate *co)
+{
+ struct nfs4_file *fp = co->co_file;
+
+ lockdep_assert_held(&fp->fi_lock);
+ list_add(&co->co_perfile, &fp->fi_clnt_odstate);
+}
+
+static inline void
+get_clnt_odstate(struct nfs4_clnt_odstate *co)
+{
+ if (co)
+ atomic_inc(&co->co_odcount);
+}
+
+static void
+put_clnt_odstate(struct nfs4_clnt_odstate *co)
+{
+ struct nfs4_file *fp;
+
+ if (!co)
+ return;
+
+ fp = co->co_file;
+ if (atomic_dec_and_lock(&co->co_odcount, &fp->fi_lock)) {
+ list_del(&co->co_perfile);
+ spin_unlock(&fp->fi_lock);
+
+ nfsd4_return_all_file_layouts(co->co_client, fp);
+ kmem_cache_free(odstate_slab, co);
+ }
+}
+
+static struct nfs4_clnt_odstate *
+find_or_hash_clnt_odstate(struct nfs4_file *fp, struct nfs4_clnt_odstate *new)
+{
+ struct nfs4_clnt_odstate *co;
+ struct nfs4_client *cl;
+
+ if (!new)
+ return NULL;
+
+ cl = new->co_client;
+
+ spin_lock(&fp->fi_lock);
+ list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
+ if (co->co_client == cl) {
+ get_clnt_odstate(co);
+ goto out;
+ }
+ }
+ co = new;
+ co->co_file = fp;
+ hash_clnt_odstate_locked(new);
+out:
+ spin_unlock(&fp->fi_lock);
+ return co;
+}
+
struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
struct kmem_cache *slab)
{
}
static struct nfs4_delegation *
-alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh)
+alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh,
+ struct nfs4_clnt_odstate *odstate)
{
struct nfs4_delegation *dp;
long n;
INIT_LIST_HEAD(&dp->dl_perfile);
INIT_LIST_HEAD(&dp->dl_perclnt);
INIT_LIST_HEAD(&dp->dl_recall_lru);
+ dp->dl_clnt_odstate = odstate;
+ get_clnt_odstate(odstate);
dp->dl_type = NFS4_OPEN_DELEGATE_READ;
dp->dl_retries = 1;
nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
spin_lock(&state_lock);
unhash_delegation_locked(dp);
spin_unlock(&state_lock);
+ put_clnt_odstate(dp->dl_clnt_odstate);
nfs4_put_deleg_lease(dp->dl_stid.sc_file);
nfs4_put_stid(&dp->dl_stid);
}
WARN_ON(!list_empty(&dp->dl_recall_lru));
+ put_clnt_odstate(dp->dl_clnt_odstate);
nfs4_put_deleg_lease(dp->dl_stid.sc_file);
if (clp->cl_minorversion == 0)
{
struct nfs4_ol_stateid *stp = openlockstateid(stid);
+ put_clnt_odstate(stp->st_clnt_odstate);
release_all_access(stp);
if (stp->st_stateowner)
nfs4_put_stateowner(stp->st_stateowner);
INIT_LIST_HEAD(&clp->cl_openowners);
INIT_LIST_HEAD(&clp->cl_delegations);
INIT_LIST_HEAD(&clp->cl_lru);
- INIT_LIST_HEAD(&clp->cl_callbacks);
INIT_LIST_HEAD(&clp->cl_revoked);
#ifdef CONFIG_NFSD_PNFS
INIT_LIST_HEAD(&clp->cl_lo_states);
while (!list_empty(&reaplist)) {
dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
list_del_init(&dp->dl_recall_lru);
+ put_clnt_odstate(dp->dl_clnt_odstate);
nfs4_put_deleg_lease(dp->dl_stid.sc_file);
nfs4_put_stid(&dp->dl_stid);
}
spin_lock_init(&fp->fi_lock);
INIT_LIST_HEAD(&fp->fi_stateids);
INIT_LIST_HEAD(&fp->fi_delegations);
+ INIT_LIST_HEAD(&fp->fi_clnt_odstate);
fh_copy_shallow(&fp->fi_fhandle, fh);
fp->fi_deleg_file = NULL;
fp->fi_had_conflict = false;
void
nfsd4_free_slabs(void)
{
+ kmem_cache_destroy(odstate_slab);
kmem_cache_destroy(openowner_slab);
kmem_cache_destroy(lockowner_slab);
kmem_cache_destroy(file_slab);
sizeof(struct nfs4_delegation), 0, 0, NULL);
if (deleg_slab == NULL)
goto out_free_stateid_slab;
+ odstate_slab = kmem_cache_create("nfsd4_odstate",
+ sizeof(struct nfs4_clnt_odstate), 0, 0, NULL);
+ if (odstate_slab == NULL)
+ goto out_free_deleg_slab;
return 0;
+out_free_deleg_slab:
+ kmem_cache_destroy(deleg_slab);
out_free_stateid_slab:
kmem_cache_destroy(stateid_slab);
out_free_file_slab:
open->op_stp = nfs4_alloc_open_stateid(clp);
if (!open->op_stp)
return nfserr_jukebox;
+
+ if (nfsd4_has_session(cstate) &&
+ (cstate->current_fh.fh_export->ex_flags & NFSEXP_PNFS)) {
+ open->op_odstate = alloc_clnt_odstate(clp);
+ if (!open->op_odstate)
+ return nfserr_jukebox;
+ }
+
return nfs_ok;
}
static struct nfs4_delegation *
nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
- struct nfs4_file *fp)
+ struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
{
int status;
struct nfs4_delegation *dp;
if (fp->fi_had_conflict)
return ERR_PTR(-EAGAIN);
- dp = alloc_init_deleg(clp, fh);
+ dp = alloc_init_deleg(clp, fh, odstate);
if (!dp)
return ERR_PTR(-ENOMEM);
spin_unlock(&state_lock);
out:
if (status) {
+ put_clnt_odstate(dp->dl_clnt_odstate);
nfs4_put_stid(&dp->dl_stid);
return ERR_PTR(status);
}
default:
goto out_no_deleg;
}
- dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file);
+ dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file, stp->st_clnt_odstate);
if (IS_ERR(dp))
goto out_no_deleg;
release_open_stateid(stp);
goto out;
}
+
+ stp->st_clnt_odstate = find_or_hash_clnt_odstate(fp,
+ open->op_odstate);
+ if (stp->st_clnt_odstate == open->op_odstate)
+ open->op_odstate = NULL;
}
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
kmem_cache_free(file_slab, open->op_file);
if (open->op_stp)
nfs4_put_stid(&open->op_stp->st_stid);
+ if (open->op_odstate)
+ kmem_cache_free(odstate_slab, open->op_odstate);
}
__be32
return nfserr_old_stateid;
}
+static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols)
+{
+ if (ols->st_stateowner->so_is_open_owner &&
+ !(openowner(ols->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED))
+ return nfserr_bad_stateid;
+ return nfs_ok;
+}
+
static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
{
struct nfs4_stid *s;
- struct nfs4_ol_stateid *ols;
__be32 status = nfserr_bad_stateid;
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
break;
case NFS4_OPEN_STID:
case NFS4_LOCK_STID:
- ols = openlockstateid(s);
- if (ols->st_stateowner->so_is_open_owner
- && !(openowner(ols->st_stateowner)->oo_flags
- & NFS4_OO_CONFIRMED))
- status = nfserr_bad_stateid;
- else
- status = nfs_ok;
+ status = nfsd4_check_openowner_confirmed(openlockstateid(s));
break;
default:
printk("unknown stateid type %x\n", s->sc_type);
status = nfs4_check_fh(current_fh, stp);
if (status)
goto out;
- if (stp->st_stateowner->so_is_open_owner
- && !(openowner(stp->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED))
+ status = nfsd4_check_openowner_confirmed(stp);
+ if (status)
goto out;
status = nfs4_check_openmode(stp, flags);
if (status)
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
- nfsd4_return_all_file_layouts(stp->st_stateowner->so_client,
- stp->st_stid.sc_file);
-
nfsd4_close_open_stateid(stp);
/* put reference from nfs4_preprocess_seqid_op */
list_for_each_safe(pos, next, &reaplist) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
list_del_init(&dp->dl_recall_lru);
+ put_clnt_odstate(dp->dl_clnt_odstate);
nfs4_put_deleg_lease(dp->dl_stid.sc_file);
nfs4_put_stid(&dp->dl_stid);
}
struct nfsd4_callback {
struct nfs4_client *cb_clp;
- struct list_head cb_per_client;
u32 cb_minorversion;
struct rpc_message cb_msg;
struct nfsd4_callback_ops *cb_ops;
struct work_struct cb_work;
- bool cb_done;
+ int cb_status;
+ bool cb_need_restart;
};
struct nfsd4_callback_ops {
struct list_head dl_perfile;
struct list_head dl_perclnt;
struct list_head dl_recall_lru; /* delegation recalled */
+ struct nfs4_clnt_odstate *dl_clnt_odstate;
u32 dl_type;
time_t dl_time;
/* For recall: */
int cl_cb_state;
struct nfsd4_callback cl_cb_null;
struct nfsd4_session *cl_cb_session;
- struct list_head cl_callbacks; /* list of in-progress callbacks */
/* for all client information that callback code might need: */
spinlock_t cl_lock;
return container_of(so, struct nfs4_lockowner, lo_owner);
}
+/*
+ * Per-client state indicating no. of opens and outstanding delegations
+ * on a file from a particular client.'od' stands for 'open & delegation'
+ */
+struct nfs4_clnt_odstate {
+ struct nfs4_client *co_client;
+ struct nfs4_file *co_file;
+ struct list_head co_perfile;
+ atomic_t co_odcount;
+};
+
/*
* nfs4_file: a file opened by some number of (open) nfs4_stateowners.
*
struct list_head fi_delegations;
struct rcu_head fi_rcu;
};
+ struct list_head fi_clnt_odstate;
/* One each for O_RDONLY, O_WRONLY, O_RDWR: */
struct file * fi_fds[3];
/*
struct list_head st_perstateowner;
struct list_head st_locks;
struct nfs4_stateowner * st_stateowner;
+ struct nfs4_clnt_odstate * st_clnt_odstate;
unsigned char st_access_bmap;
unsigned char st_deny_bmap;
struct nfs4_ol_stateid * st_openstp;
struct nfs4_openowner *op_openowner; /* used during processing */
struct nfs4_file *op_file; /* used during processing */
struct nfs4_ol_stateid *op_stp; /* used during processing */
+ struct nfs4_clnt_odstate *op_odstate; /* used during processing */
struct nfs4_acl *op_acl;
struct xdr_netobj op_label;
};
* ntfs_lookup - find the inode represented by a dentry in a directory inode
* @dir_ino: directory inode in which to look for the inode
* @dent: dentry representing the inode to look for
- * @nd: lookup nameidata
+ * @flags: lookup flags
*
* In short, ntfs_lookup() looks for the inode represented by the dentry @dent
* in the directory inode @dir_ino and if found attaches the inode to the
goto out;
found:
- *return_block = i * bits_per_entry + bit;
+ *return_block = (u64) i * bits_per_entry + bit;
*return_size = run;
ret = set_run(sb, i, bits_per_entry, bit, run, 1);
*/
static int omfs_get_imap(struct super_block *sb)
{
- unsigned int bitmap_size, count, array_size;
+ unsigned int bitmap_size, array_size;
+ int count;
struct omfs_sb_info *sbi = OMFS_SB(sb);
struct buffer_head *bh;
unsigned long **ptr;
}
enum {
- Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask
+ Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_err
};
static const match_table_t tokens = {
{Opt_umask, "umask=%o"},
{Opt_dmask, "dmask=%o"},
{Opt_fmask, "fmask=%o"},
+ {Opt_err, NULL},
};
static int parse_options(char *options, struct omfs_sb_info *sbi)
}
sb->s_root = d_make_root(root);
- if (!sb->s_root)
+ if (!sb->s_root) {
+ ret = -ENOMEM;
goto out_brelse_bh2;
+ }
printk(KERN_DEBUG "omfs: Mounted volume %s\n", omfs_rb->r_name);
ret = 0;
if (res)
goto out;
- inode = path.dentry->d_inode;
+ inode = d_backing_inode(path.dentry);
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
/*
struct cred *override_cred;
char *link = NULL;
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
ovl_path_upper(parent, &parentpath);
upperdir = parentpath.dentry;
struct kstat stat;
int err;
+ if (WARN_ON(!workdir))
+ return ERR_PTR(-EROFS);
+
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
struct dentry *newdentry;
int err;
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
struct dentry *opaquedir = NULL;
int err;
- if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) {
- opaquedir = ovl_check_empty_and_clear(dentry);
- err = PTR_ERR(opaquedir);
- if (IS_ERR(opaquedir))
- goto out;
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
+ if (is_dir) {
+ if (OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) {
+ opaquedir = ovl_check_empty_and_clear(dentry);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir))
+ goto out;
+ } else {
+ LIST_HEAD(list);
+
+ /*
+ * When removing an empty opaque directory, then it
+ * makes no sense to replace it with an exact replica of
+ * itself. But emptiness still needs to be checked.
+ */
+ err = ovl_check_empty_dir(dentry, &list);
+ ovl_cache_free(&list);
+ if (err)
+ goto out;
+ }
}
err = ovl_lock_rename_workdir(workdir, upperdir);
void *cookie;
};
-static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *ovl_follow_link(struct dentry *dentry, void **cookie)
{
- void *ret;
struct dentry *realdentry;
struct inode *realinode;
+ struct ovl_link_data *data = NULL;
+ const char *ret;
realdentry = ovl_dentry_real(dentry);
realinode = realdentry->d_inode;
if (WARN_ON(!realinode->i_op->follow_link))
return ERR_PTR(-EPERM);
- ret = realinode->i_op->follow_link(realdentry, nd);
- if (IS_ERR(ret))
- return ret;
-
if (realinode->i_op->put_link) {
- struct ovl_link_data *data;
-
data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL);
- if (!data) {
- realinode->i_op->put_link(realdentry, nd, ret);
+ if (!data)
return ERR_PTR(-ENOMEM);
- }
data->realdentry = realdentry;
- data->cookie = ret;
+ }
- return data;
- } else {
- return NULL;
+ ret = realinode->i_op->follow_link(realdentry, cookie);
+ if (IS_ERR_OR_NULL(ret)) {
+ kfree(data);
+ return ret;
}
+
+ if (data)
+ data->cookie = *cookie;
+
+ *cookie = data;
+
+ return ret;
}
-static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c)
+static void ovl_put_link(struct inode *unused, void *c)
{
struct inode *realinode;
struct ovl_link_data *data = c;
return;
realinode = data->realdentry->d_inode;
- realinode->i_op->put_link(data->realdentry, nd, data->cookie);
+ realinode->i_op->put_link(realinode, data->cookie);
kfree(data);
}
{
struct ovl_fs *ufs = sb->s_fs_info;
- if (!(*flags & MS_RDONLY) && !ufs->upper_mnt)
+ if (!(*flags & MS_RDONLY) && (!ufs->upper_mnt || !ufs->workdir))
return -EROFS;
return 0;
ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
err = PTR_ERR(ufs->workdir);
if (IS_ERR(ufs->workdir)) {
- pr_err("overlayfs: failed to create directory %s/%s\n",
- ufs->config.workdir, OVL_WORKDIR_NAME);
- goto out_put_upper_mnt;
+ pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
+ ufs->config.workdir, OVL_WORKDIR_NAME, -err);
+ sb->s_flags |= MS_RDONLY;
+ ufs->workdir = NULL;
}
}
kfree(ufs->lower_mnt);
out_put_workdir:
dput(ufs->workdir);
-out_put_upper_mnt:
mntput(ufs->upper_mnt);
out_put_lowerpath:
for (i = 0; i < numlower; i++)
return -ENOENT;
}
-static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
struct path path;
if (error)
goto out;
- nd_jump_link(nd, &path);
+ nd_jump_link(&path);
return NULL;
out:
return ERR_PTR(error);
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/magic.h>
-#include <linux/namei.h>
#include <asm/uaccess.h>
};
#endif
-static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_follow_link(struct dentry *dentry, void **cookie)
{
struct proc_dir_entry *pde = PDE(d_inode(dentry));
if (unlikely(!use_pde(pde)))
return ERR_PTR(-EINVAL);
- nd_set_link(nd, pde->data);
- return pde;
+ *cookie = pde;
+ return pde->data;
}
-static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+static void proc_put_link(struct inode *unused, void *p)
{
unuse_pde(p);
}
&mntns_operations,
};
-static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
if (ptrace_may_access(task, PTRACE_MODE_READ)) {
error = ns_get_path(&ns_path, task, ns_ops);
if (!error)
- nd_jump_link(nd, &ns_path);
+ nd_jump_link(&ns_path);
}
put_task_struct(task);
return error;
#include <linux/sched.h>
-#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/pid_namespace.h>
#include "internal.h"
return readlink_copy(buffer, buflen, tmp);
}
-static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_self_follow_link(struct dentry *dentry, void **cookie)
{
struct pid_namespace *ns = dentry->d_sb->s_fs_info;
pid_t tgid = task_tgid_nr_ns(current, ns);
- char *name = ERR_PTR(-ENOENT);
- if (tgid) {
- /* 11 for max length of signed int in decimal + NULL term */
- name = kmalloc(12, GFP_KERNEL);
- if (!name)
- name = ERR_PTR(-ENOMEM);
- else
- sprintf(name, "%d", tgid);
- }
- nd_set_link(nd, name);
- return NULL;
+ char *name;
+
+ if (!tgid)
+ return ERR_PTR(-ENOENT);
+ /* 11 for max length of signed int in decimal + NULL term */
+ name = kmalloc(12, GFP_KERNEL);
+ if (!name)
+ return ERR_PTR(-ENOMEM);
+ sprintf(name, "%d", tgid);
+ return *cookie = name;
}
static const struct inode_operations proc_self_inode_operations = {
#include <linux/sched.h>
-#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/pid_namespace.h>
#include "internal.h"
return readlink_copy(buffer, buflen, tmp);
}
-static void *proc_thread_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie)
{
struct pid_namespace *ns = dentry->d_sb->s_fs_info;
pid_t tgid = task_tgid_nr_ns(current, ns);
pid_t pid = task_pid_nr_ns(current, ns);
- char *name = ERR_PTR(-ENOENT);
- if (pid) {
- name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
- if (!name)
- name = ERR_PTR(-ENOMEM);
- else
- sprintf(name, "%d/task/%d", tgid, pid);
- }
- nd_set_link(nd, name);
- return NULL;
+ char *name;
+
+ if (!pid)
+ return ERR_PTR(-ENOENT);
+ name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
+ if (!name)
+ return ERR_PTR(-ENOMEM);
+ sprintf(name, "%d/task/%d", tgid, pid);
+ return *cookie = name;
}
static const struct inode_operations proc_thread_self_inode_operations = {
* doesn't imply write barrier and the users expect write
* barrier semantics on wakeup functions. The following
* smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
- * and is paired with set_mb() in poll_schedule_timeout.
+ * and is paired with smp_store_mb() in poll_schedule_timeout.
*/
smp_wmb();
pwq->triggered = 1;
/*
* Prepare for the next iteration.
*
- * The following set_mb() serves two purposes. First, it's
+ * The following smp_store_mb() serves two purposes. First, it's
* the counterpart rmb of the wmb in pollwake() such that data
* written before wake up is always visible after wake up.
* Second, the full barrier guarantees that triggered clearing
* this problem doesn't exist for the first iteration as
* add_wait_queue() has full barrier semantics.
*/
- set_mb(pwq->triggered, 0);
+ smp_store_mb(pwq->triggered, 0);
return rc;
}
long ret, bytes;
umode_t i_mode;
size_t len;
- int i, flags;
+ int i, flags, more;
/*
* We require the input being a regular file, as we don't want to
* Don't block on output, we have to drain the direct pipe.
*/
sd->flags &= ~SPLICE_F_NONBLOCK;
+ more = sd->flags & SPLICE_F_MORE;
while (len) {
size_t read_len;
read_len = ret;
sd->total_len = read_len;
+ /*
+ * If more data is pending, set SPLICE_F_MORE
+ * If this is the last data and SPLICE_F_MORE was not set
+ * initially, clears it.
+ */
+ if (read_len < len)
+ sd->flags |= SPLICE_F_MORE;
+ else if (!more)
+ sd->flags &= ~SPLICE_F_MORE;
/*
* NOTE: nonblocking mode only applies to the input. We
* must not do the output in nonblocking mode as then we
obj-$(CONFIG_SYSV_FS) += sysv.o
sysv-objs := ialloc.o balloc.o inode.o itree.o file.o dir.o \
- namei.o super.o symlink.o
+ namei.o super.o
inode->i_op = &sysv_symlink_inode_operations;
inode->i_mapping->a_ops = &sysv_aops;
} else {
- inode->i_op = &sysv_fast_symlink_inode_operations;
- nd_terminate_link(SYSV_I(inode)->i_data, inode->i_size,
+ inode->i_op = &simple_symlink_inode_operations;
+ inode->i_link = (char *)SYSV_I(inode)->i_data;
+ nd_terminate_link(inode->i_link, inode->i_size,
sizeof(SYSV_I(inode)->i_data) - 1);
}
} else
+++ /dev/null
-/*
- * linux/fs/sysv/symlink.c
- *
- * Handling of System V filesystem fast symlinks extensions.
- * Aug 2001, Christoph Hellwig (hch@infradead.org)
- */
-
-#include "sysv.h"
-#include <linux/namei.h>
-
-static void *sysv_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- nd_set_link(nd, (char *)SYSV_I(d_inode(dentry))->i_data);
- return NULL;
-}
-
-const struct inode_operations sysv_fast_symlink_inode_operations = {
- .readlink = generic_readlink,
- .follow_link = sysv_follow_link,
-};
extern const struct inode_operations sysv_file_inode_operations;
extern const struct inode_operations sysv_dir_inode_operations;
-extern const struct inode_operations sysv_fast_symlink_inode_operations;
extern const struct file_operations sysv_file_operations;
extern const struct file_operations sysv_dir_operations;
extern const struct address_space_operations sysv_aops;
memcpy(ui->data, symname, len);
((char *)ui->data)[len] = '\0';
+ inode->i_link = ui->data;
/*
* The terminating zero byte is not written to the flash media and it
* is put just to make later in-memory string processing simpler. Thus,
#include "ubifs.h"
#include <linux/mount.h>
-#include <linux/namei.h>
#include <linux/slab.h>
static int read_block(struct inode *inode, void *addr, unsigned int block,
ClearPageChecked(page);
}
-static void *ubifs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct ubifs_inode *ui = ubifs_inode(d_inode(dentry));
-
- nd_set_link(nd, ui->data);
- return NULL;
-}
-
int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
const struct inode_operations ubifs_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = ubifs_follow_link,
+ .follow_link = simple_follow_link,
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
.setxattr = ubifs_setxattr,
}
memcpy(ui->data, ino->data, ui->data_len);
((char *)ui->data)[ui->data_len] = '\0';
+ inode->i_link = ui->data;
break;
case S_IFBLK:
case S_IFCHR:
inode->i_fop = &ufs_dir_operations;
inode->i_mapping->a_ops = &ufs_aops;
} else if (S_ISLNK(inode->i_mode)) {
- if (!inode->i_blocks)
+ if (!inode->i_blocks) {
inode->i_op = &ufs_fast_symlink_inode_operations;
- else {
+ inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink;
+ } else {
inode->i_op = &ufs_symlink_inode_operations;
inode->i_mapping->a_ops = &ufs_aops;
}
} else {
/* fast symlink */
inode->i_op = &ufs_fast_symlink_inode_operations;
- memcpy(UFS_I(inode)->i_u1.i_symlink, symname, l);
+ inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink;
+ memcpy(inode->i_link, symname, l);
inode->i_size = l-1;
}
mark_inode_dirty(inode);
* ext2 symlink handling code
*/
-#include <linux/fs.h>
-#include <linux/namei.h>
-
#include "ufs_fs.h"
#include "ufs.h"
-
-static void *ufs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct ufs_inode_info *p = UFS_I(d_inode(dentry));
- nd_set_link(nd, (char*)p->i_u1.i_symlink);
- return NULL;
-}
-
const struct inode_operations ufs_fast_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = ufs_follow_link,
+ .follow_link = simple_follow_link,
.setattr = ufs_setattr,
};
* After the last attribute is removed revert to original inode format,
* making all literal area available to the data fork once more.
*/
-STATIC void
-xfs_attr_fork_reset(
+void
+xfs_attr_fork_remove(
struct xfs_inode *ip,
struct xfs_trans *tp)
{
(mp->m_flags & XFS_MOUNT_ATTR2) &&
(dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
!(args->op_flags & XFS_DA_OP_ADDNAME)) {
- xfs_attr_fork_reset(dp, args->trans);
+ xfs_attr_fork_remove(dp, args->trans);
} else {
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
if (forkoff == -1) {
ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2);
ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE);
- xfs_attr_fork_reset(dp, args->trans);
+ xfs_attr_fork_remove(dp, args->trans);
goto out;
}
int xfs_attr_shortform_list(struct xfs_attr_list_context *context);
int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
int xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
-
+void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
/*
* Internal routines when attribute fork size == XFS_LBSIZE(mp).
align_alen += temp;
align_off -= temp;
}
+
+ /* Same adjustment for the end of the requested area. */
+ temp = (align_alen % extsz);
+ if (temp)
+ align_alen += extsz - temp;
+
/*
- * Same adjustment for the end of the requested area.
+ * For large extent hint sizes, the aligned extent might be larger than
+ * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls
+ * the length back under MAXEXTLEN. The outer allocation loops handle
+ * short allocation just fine, so it is safe to do this. We only want to
+ * do it when we are forced to, though, because it means more allocation
+ * operations are required.
*/
- if ((temp = (align_alen % extsz))) {
- align_alen += extsz - temp;
- }
+ while (align_alen > MAXEXTLEN)
+ align_alen -= extsz;
+ ASSERT(align_alen <= MAXEXTLEN);
+
/*
* If the previous block overlaps with this proposed allocation
* then move the start forward without adjusting the length.
return -EINVAL;
} else {
ASSERT(orig_off >= align_off);
- ASSERT(orig_end <= align_off + align_alen);
+ /* see MAXEXTLEN handling above */
+ ASSERT(orig_end <= align_off + align_alen ||
+ align_alen + extsz > MAXEXTLEN);
}
#ifdef DEBUG
/* Figure out the extent size, adjust alen */
extsz = xfs_get_extsz_hint(ip);
if (extsz) {
- /*
- * Make sure we don't exceed a single extent length when we
- * align the extent by reducing length we are going to
- * allocate by the maximum amount extent size aligment may
- * require.
- */
- alen = XFS_FILBLKS_MIN(len, MAXEXTLEN - (2 * extsz - 1));
error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof,
1, 0, &aoff, &alen);
ASSERT(!error);
*/
newlen = args.mp->m_ialloc_inos;
if (args.mp->m_maxicount &&
- percpu_counter_read(&args.mp->m_icount) + newlen >
+ percpu_counter_read_positive(&args.mp->m_icount) + newlen >
args.mp->m_maxicount)
return -ENOSPC;
args.minlen = args.maxlen = args.mp->m_ialloc_blks;
* If we have already hit the ceiling of inode blocks then clear
* okalloc so we scan all available agi structures for a free
* inode.
+ *
+ * Read rough value of mp->m_icount by percpu_counter_read_positive,
+ * which will sacrifice the preciseness but improve the performance.
*/
if (mp->m_maxicount &&
- percpu_counter_read(&mp->m_icount) + mp->m_ialloc_inos >
- mp->m_maxicount) {
+ percpu_counter_read_positive(&mp->m_icount) + mp->m_ialloc_inos
+ > mp->m_maxicount) {
noroom = 1;
okalloc = 0;
}
return error;
}
+/*
+ * xfs_attr_inactive kills all traces of an attribute fork on an inode. It
+ * removes both the on-disk and in-memory inode fork. Note that this also has to
+ * handle the condition of inodes without attributes but with an attribute fork
+ * configured, so we can't use xfs_inode_hasattr() here.
+ *
+ * The in-memory attribute fork is removed even on error.
+ */
int
-xfs_attr_inactive(xfs_inode_t *dp)
+xfs_attr_inactive(
+ struct xfs_inode *dp)
{
- xfs_trans_t *trans;
- xfs_mount_t *mp;
- int error;
+ struct xfs_trans *trans;
+ struct xfs_mount *mp;
+ int cancel_flags = 0;
+ int lock_mode = XFS_ILOCK_SHARED;
+ int error = 0;
mp = dp->i_mount;
ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
- xfs_ilock(dp, XFS_ILOCK_SHARED);
- if (!xfs_inode_hasattr(dp) ||
- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
- return 0;
- }
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
+ xfs_ilock(dp, lock_mode);
+ if (!XFS_IFORK_Q(dp))
+ goto out_destroy_fork;
+ xfs_iunlock(dp, lock_mode);
/*
* Start our first transaction of the day.
* the inode in every transaction to let it float upward through
* the log.
*/
+ lock_mode = 0;
trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
- if (error) {
- xfs_trans_cancel(trans, 0);
- return error;
- }
- xfs_ilock(dp, XFS_ILOCK_EXCL);
+ if (error)
+ goto out_cancel;
+
+ lock_mode = XFS_ILOCK_EXCL;
+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT;
+ xfs_ilock(dp, lock_mode);
+
+ if (!XFS_IFORK_Q(dp))
+ goto out_cancel;
/*
* No need to make quota reservations here. We expect to release some
*/
xfs_trans_ijoin(trans, dp, 0);
- /*
- * Decide on what work routines to call based on the inode size.
- */
- if (!xfs_inode_hasattr(dp) ||
- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- error = 0;
- goto out;
+ /* invalidate and truncate the attribute fork extents */
+ if (dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) {
+ error = xfs_attr3_root_inactive(&trans, dp);
+ if (error)
+ goto out_cancel;
+
+ error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
+ if (error)
+ goto out_cancel;
}
- error = xfs_attr3_root_inactive(&trans, dp);
- if (error)
- goto out;
- error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
- if (error)
- goto out;
+ /* Reset the attribute fork - this also destroys the in-core fork */
+ xfs_attr_fork_remove(dp, trans);
error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
+ xfs_iunlock(dp, lock_mode);
return error;
-out:
- xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
+out_cancel:
+ xfs_trans_cancel(trans, cancel_flags);
+out_destroy_fork:
+ /* kill the in-core attr fork before we drop the inode lock */
+ if (dp->i_afp)
+ xfs_idestroy_fork(dp, XFS_ATTR_FORK);
+ if (lock_mode)
+ xfs_iunlock(dp, lock_mode);
return error;
}
status = 0;
} while (count);
- return (-status);
+ return status;
}
int
/*
* If there are attributes associated with the file then blow them away
* now. The code calls a routine that recursively deconstructs the
- * attribute fork. We need to just commit the current transaction
- * because we can't use it for xfs_attr_inactive().
+ * attribute fork. If also blows away the in-core attribute fork.
*/
- if (ip->i_d.di_anextents > 0) {
- ASSERT(ip->i_d.di_forkoff != 0);
-
+ if (XFS_IFORK_Q(ip)) {
error = xfs_attr_inactive(ip);
if (error)
return;
}
- if (ip->i_afp)
- xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
+ ASSERT(!ip->i_afp);
ASSERT(ip->i_d.di_anextents == 0);
+ ASSERT(ip->i_d.di_forkoff == 0);
/*
* Free the inode.
if (error)
return error;
- /* Satisfy xfs_bumplink that this is a real tmpfile */
+ /*
+ * Prepare the tmpfile inode as if it were created through the VFS.
+ * Otherwise, the link increment paths will complain about nlink 0->1.
+ * Drop the link count as done by d_tmpfile(), complete the inode setup
+ * and flag it as linkable.
+ */
+ drop_nlink(VFS_I(tmpfile));
xfs_finish_inode_setup(tmpfile);
VFS_I(tmpfile)->i_state |= I_LINKABLE;
* intermediate state on disk.
*/
if (wip) {
- ASSERT(wip->i_d.di_nlink == 0);
+ ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0);
error = xfs_bumplink(tp, wip);
if (error)
goto out_trans_abort;
#include <linux/capability.h>
#include <linux/xattr.h>
-#include <linux/namei.h>
#include <linux/posix_acl.h>
#include <linux/security.h>
#include <linux/fiemap.h>
* we need to be very careful about how much stack we use.
* uio is kmalloced for this reason...
*/
-STATIC void *
+STATIC const char *
xfs_vn_follow_link(
struct dentry *dentry,
- struct nameidata *nd)
+ void **cookie)
{
char *link;
int error = -ENOMEM;
if (unlikely(error))
goto out_kfree;
- nd_set_link(nd, link);
- return NULL;
+ return *cookie = link;
out_kfree:
kfree(link);
out_err:
- nd_set_link(nd, ERR_PTR(error));
- return NULL;
+ return ERR_PTR(error);
}
STATIC int
return xfs_sync_sb(mp, true);
}
+/*
+ * Deltas for the inode count are +/-64, hence we use a large batch size
+ * of 128 so we don't need to take the counter lock on every update.
+ */
+#define XFS_ICOUNT_BATCH 128
int
xfs_mod_icount(
struct xfs_mount *mp,
int64_t delta)
{
- /* deltas are +/-64, hence the large batch size of 128. */
- __percpu_counter_add(&mp->m_icount, delta, 128);
- if (percpu_counter_compare(&mp->m_icount, 0) < 0) {
+ __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
+ if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
ASSERT(0);
percpu_counter_add(&mp->m_icount, -delta);
return -EINVAL;
return 0;
}
+/*
+ * Deltas for the block count can vary from 1 to very large, but lock contention
+ * only occurs on frequent small block count updates such as in the delayed
+ * allocation path for buffered writes (page a time updates). Hence we set
+ * a large batch count (1024) to minimise global counter updates except when
+ * we get near to ENOSPC and we have to be very accurate with our updates.
+ */
+#define XFS_FDBLOCKS_BATCH 1024
int
xfs_mod_fdblocks(
struct xfs_mount *mp,
* Taking blocks away, need to be more accurate the closer we
* are to zero.
*
- * batch size is set to a maximum of 1024 blocks - if we are
- * allocating of freeing extents larger than this then we aren't
- * going to be hammering the counter lock so a lock per update
- * is not a problem.
- *
* If the counter has a value of less than 2 * max batch size,
* then make everything serialise as we are real close to
* ENOSPC.
*/
-#define __BATCH 1024
- if (percpu_counter_compare(&mp->m_fdblocks, 2 * __BATCH) < 0)
+ if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH,
+ XFS_FDBLOCKS_BATCH) < 0)
batch = 1;
else
- batch = __BATCH;
-#undef __BATCH
+ batch = XFS_FDBLOCKS_BATCH;
__percpu_counter_add(&mp->m_fdblocks, delta, batch);
- if (percpu_counter_compare(&mp->m_fdblocks,
- XFS_ALLOC_SET_ASIDE(mp)) >= 0) {
+ if (__percpu_counter_compare(&mp->m_fdblocks, XFS_ALLOC_SET_ASIDE(mp),
+ XFS_FDBLOCKS_BATCH) >= 0) {
/* we had space! */
return 0;
}
#define smp_read_barrier_depends() do { } while (0)
#endif
-#ifndef set_mb
-#define set_mb(var, value) do { (var) = (value); mb(); } while (0)
+#ifndef smp_store_mb
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0)
#endif
#ifndef smp_mb__before_atomic
/*
* Atomic compare and exchange.
- *
- * Do not define __HAVE_ARCH_CMPXCHG because we want to use it to check whether
- * a cmpxchg primitive faster than repeated local irq save/restore exists.
*/
#include <asm-generic/cmpxchg-local.h>
#ifndef CONFIG_SMP
/*
* The following implementation only for uniprocessor machines.
- * For UP, it's relies on the fact that pagefault_disable() also disables
- * preemption to ensure mutual exclusion.
+ * It relies on preempt_disable() ensuring mutual exclusion.
*
*/
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
+ preempt_disable();
pagefault_disable();
ret = -EFAULT;
out_pagefault_enable:
pagefault_enable();
+ preempt_enable();
if (ret == 0) {
switch (cmp) {
{
u32 val;
+ preempt_disable();
if (unlikely(get_user(val, uaddr) != 0))
return -EFAULT;
return -EFAULT;
*uval = val;
+ preempt_enable();
return 0;
}
}
#endif
+#ifndef ioremap_uc
+#define ioremap_uc ioremap_uc
+static inline void __iomem *ioremap_uc(phys_addr_t offset, size_t size)
+{
+ return ioremap_nocache(offset, size);
+}
+#endif
+
#ifndef ioremap_wc
#define ioremap_wc ioremap_wc
static inline void __iomem *ioremap_wc(phys_addr_t offset, size_t size)
}
#endif
+#ifndef ioremap_wt
+#define ioremap_wt ioremap_wt
+static inline void __iomem *ioremap_wt(phys_addr_t offset, size_t size)
+{
+ return ioremap_nocache(offset, size);
+}
+#endif
+
#ifndef iounmap
#define iounmap iounmap
+
static inline void iounmap(void __iomem *addr)
{
}
#define ioremap_wc ioremap_nocache
#endif
+#ifndef ARCH_HAS_IOREMAP_WT
+#define ioremap_wt ioremap_nocache
+#endif
+
#ifdef CONFIG_PCI
/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */
struct pci_dev;
#define pgprot_writecombine pgprot_noncached
#endif
+#ifndef pgprot_writethrough
+#define pgprot_writethrough pgprot_noncached
+#endif
+
#ifndef pgprot_device
#define pgprot_device pgprot_noncached
#endif
#ifdef CONFIG_PREEMPT
extern asmlinkage void preempt_schedule(void);
#define __preempt_schedule() preempt_schedule()
-
-#ifdef CONFIG_CONTEXT_TRACKING
-extern asmlinkage void preempt_schedule_context(void);
-#define __preempt_schedule_context() preempt_schedule_context()
-#endif
+extern asmlinkage void preempt_schedule_notrace(void);
+#define __preempt_schedule_notrace() preempt_schedule_notrace()
#endif /* CONFIG_PREEMPT */
#endif /* __ASM_PREEMPT_H */
--- /dev/null
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_H
+#define __ASM_GENERIC_QSPINLOCK_H
+
+#include <asm-generic/qspinlock_types.h>
+
+/**
+ * queued_spin_is_locked - is the spinlock locked?
+ * @lock: Pointer to queued spinlock structure
+ * Return: 1 if it is locked, 0 otherwise
+ */
+static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
+{
+ return atomic_read(&lock->val);
+}
+
+/**
+ * queued_spin_value_unlocked - is the spinlock structure unlocked?
+ * @lock: queued spinlock structure
+ * Return: 1 if it is unlocked, 0 otherwise
+ *
+ * N.B. Whenever there are tasks waiting for the lock, it is considered
+ * locked wrt the lockref code to avoid lock stealing by the lockref
+ * code and change things underneath the lock. This also allows some
+ * optimizations to be applied without conflict with lockref.
+ */
+static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
+{
+ return !atomic_read(&lock.val);
+}
+
+/**
+ * queued_spin_is_contended - check if the lock is contended
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock contended, 0 otherwise
+ */
+static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
+{
+ return atomic_read(&lock->val) & ~_Q_LOCKED_MASK;
+}
+/**
+ * queued_spin_trylock - try to acquire the queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static __always_inline int queued_spin_trylock(struct qspinlock *lock)
+{
+ if (!atomic_read(&lock->val) &&
+ (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0))
+ return 1;
+ return 0;
+}
+
+extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+
+/**
+ * queued_spin_lock - acquire a queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_lock(struct qspinlock *lock)
+{
+ u32 val;
+
+ val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL);
+ if (likely(val == 0))
+ return;
+ queued_spin_lock_slowpath(lock, val);
+}
+
+#ifndef queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ /*
+ * smp_mb__before_atomic() in order to guarantee release semantics
+ */
+ smp_mb__before_atomic_dec();
+ atomic_sub(_Q_LOCKED_VAL, &lock->val);
+}
+#endif
+
+/**
+ * queued_spin_unlock_wait - wait until current lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+static inline void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+ while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+ cpu_relax();
+}
+
+#ifndef virt_queued_spin_lock
+static __always_inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+ return false;
+}
+#endif
+
+/*
+ * Initializier
+ */
+#define __ARCH_SPIN_LOCK_UNLOCKED { ATOMIC_INIT(0) }
+
+/*
+ * Remapping spinlock architecture specific functions to the corresponding
+ * queued spinlock functions.
+ */
+#define arch_spin_is_locked(l) queued_spin_is_locked(l)
+#define arch_spin_is_contended(l) queued_spin_is_contended(l)
+#define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l)
+#define arch_spin_lock(l) queued_spin_lock(l)
+#define arch_spin_trylock(l) queued_spin_trylock(l)
+#define arch_spin_unlock(l) queued_spin_unlock(l)
+#define arch_spin_lock_flags(l, f) queued_spin_lock(l)
+#define arch_spin_unlock_wait(l) queued_spin_unlock_wait(l)
+
+#endif /* __ASM_GENERIC_QSPINLOCK_H */
--- /dev/null
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_TYPES_H
+#define __ASM_GENERIC_QSPINLOCK_TYPES_H
+
+/*
+ * Including atomic.h with PARAVIRT on will cause compilation errors because
+ * of recursive header file incluson via paravirt_types.h. So don't include
+ * it if PARAVIRT is on.
+ */
+#ifndef CONFIG_PARAVIRT
+#include <linux/types.h>
+#include <linux/atomic.h>
+#endif
+
+typedef struct qspinlock {
+ atomic_t val;
+} arch_spinlock_t;
+
+/*
+ * Bitfields in the atomic value:
+ *
+ * When NR_CPUS < 16K
+ * 0- 7: locked byte
+ * 8: pending
+ * 9-15: not used
+ * 16-17: tail index
+ * 18-31: tail cpu (+1)
+ *
+ * When NR_CPUS >= 16K
+ * 0- 7: locked byte
+ * 8: pending
+ * 9-10: tail index
+ * 11-31: tail cpu (+1)
+ */
+#define _Q_SET_MASK(type) (((1U << _Q_ ## type ## _BITS) - 1)\
+ << _Q_ ## type ## _OFFSET)
+#define _Q_LOCKED_OFFSET 0
+#define _Q_LOCKED_BITS 8
+#define _Q_LOCKED_MASK _Q_SET_MASK(LOCKED)
+
+#define _Q_PENDING_OFFSET (_Q_LOCKED_OFFSET + _Q_LOCKED_BITS)
+#if CONFIG_NR_CPUS < (1U << 14)
+#define _Q_PENDING_BITS 8
+#else
+#define _Q_PENDING_BITS 1
+#endif
+#define _Q_PENDING_MASK _Q_SET_MASK(PENDING)
+
+#define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS)
+#define _Q_TAIL_IDX_BITS 2
+#define _Q_TAIL_IDX_MASK _Q_SET_MASK(TAIL_IDX)
+
+#define _Q_TAIL_CPU_OFFSET (_Q_TAIL_IDX_OFFSET + _Q_TAIL_IDX_BITS)
+#define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET)
+#define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU)
+
+#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET
+#define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
+
+#define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET)
+#define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET)
+
+#endif /* __ASM_GENERIC_QSPINLOCK_TYPES_H */
{0x1002, 0x6658, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x665c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x665d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x665f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6660, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6663, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6664, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
enum alarmtimer_restart (*function)(struct alarm *, ktime_t));
-int alarm_start(struct alarm *alarm, ktime_t start);
-int alarm_start_relative(struct alarm *alarm, ktime_t start);
+void alarm_start(struct alarm *alarm, ktime_t start);
+void alarm_start_relative(struct alarm *alarm, ktime_t start);
void alarm_restart(struct alarm *alarm);
int alarm_try_to_cancel(struct alarm *alarm);
int alarm_cancel(struct alarm *alarm);
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
-void bdi_unregister(struct backing_dev_info *bdi);
int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
enum wb_reason reason);
/* This mask is used for both bio and request merge checking */
#define REQ_NOMERGE_FLAGS \
- (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA)
+ (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_FLUSH_SEQ)
#define REQ_RAHEAD (1ULL << __REQ_RAHEAD)
#define REQ_THROTTLED (1ULL << __REQ_THROTTLED)
extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
struct scsi_ioctl_command __user *);
-extern void blk_queue_bio(struct request_queue *q, struct bio *bio);
-
/*
* A queue has just exitted congestion. Note this in the global counter of
* congested queues, and wake up anyone who was waiting for requests to be
#define _LINUX_BH_H
#include <linux/preempt.h>
-#include <linux/preempt_mask.h>
#ifdef CONFIG_TRACE_IRQFLAGS
extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
#define PHY_ID_BCM7250 0xae025280
#define PHY_ID_BCM7364 0xae025260
#define PHY_ID_BCM7366 0x600d8490
-#define PHY_ID_BCM7425 0x03625e60
+#define PHY_ID_BCM7425 0x600d86b0
#define PHY_ID_BCM7429 0x600d8730
#define PHY_ID_BCM7439 0x600d8480
#define PHY_ID_BCM7439_2 0xae025080
* reached from DETACHED or SHUTDOWN.
* ONESHOT: Device is programmed to generate event only once. Can be reached
* from DETACHED or SHUTDOWN.
+ * ONESHOT_STOPPED: Device was programmed in ONESHOT mode and is temporarily
+ * stopped.
*/
enum clock_event_state {
CLOCK_EVT_STATE_DETACHED,
CLOCK_EVT_STATE_SHUTDOWN,
CLOCK_EVT_STATE_PERIODIC,
CLOCK_EVT_STATE_ONESHOT,
+ CLOCK_EVT_STATE_ONESHOT_STOPPED,
};
/*
* @mult: nanosecond to cycles multiplier
* @shift: nanoseconds to cycles divisor (power of two)
* @mode: operating mode, relevant only to ->set_mode(), OBSOLETE
- * @state: current state of the device, assigned by the core code
+ * @state_use_accessors:current state of the device, assigned by the core code
* @features: features
* @retries: number of forced programming retries
* @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME.
* @set_state_periodic: switch state to periodic, if !set_mode
* @set_state_oneshot: switch state to oneshot, if !set_mode
+ * @set_state_oneshot_stopped: switch state to oneshot_stopped, if !set_mode
* @set_state_shutdown: switch state to shutdown, if !set_mode
* @tick_resume: resume clkevt device, if !set_mode
* @broadcast: function to broadcast events
u32 mult;
u32 shift;
enum clock_event_mode mode;
- enum clock_event_state state;
+ enum clock_event_state state_use_accessors;
unsigned int features;
unsigned long retries;
* State transition callback(s): Only one of the two groups should be
* defined:
* - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME.
- * - set_state_{shutdown|periodic|oneshot}(), tick_resume().
+ * - set_state_{shutdown|periodic|oneshot|oneshot_stopped}(), tick_resume().
*/
void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *);
int (*set_state_periodic)(struct clock_event_device *);
int (*set_state_oneshot)(struct clock_event_device *);
+ int (*set_state_oneshot_stopped)(struct clock_event_device *);
int (*set_state_shutdown)(struct clock_event_device *);
int (*tick_resume)(struct clock_event_device *);
struct module *owner;
} ____cacheline_aligned;
+/* Helpers to verify state of a clockevent device */
+static inline bool clockevent_state_detached(struct clock_event_device *dev)
+{
+ return dev->state_use_accessors == CLOCK_EVT_STATE_DETACHED;
+}
+
+static inline bool clockevent_state_shutdown(struct clock_event_device *dev)
+{
+ return dev->state_use_accessors == CLOCK_EVT_STATE_SHUTDOWN;
+}
+
+static inline bool clockevent_state_periodic(struct clock_event_device *dev)
+{
+ return dev->state_use_accessors == CLOCK_EVT_STATE_PERIODIC;
+}
+
+static inline bool clockevent_state_oneshot(struct clock_event_device *dev)
+{
+ return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT;
+}
+
+static inline bool clockevent_state_oneshot_stopped(struct clock_event_device *dev)
+{
+ return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT_STOPPED;
+}
+
/*
* Calculate a multiplication factor for scaled math, which is used to convert
* nanoseconds based values to clock ticks:
extern int clocksource_unregister(struct clocksource*);
extern void clocksource_touch_watchdog(void);
-extern struct clocksource* clocksource_get_next(void);
extern void clocksource_change_rating(struct clocksource *cs, int rating);
extern void clocksource_suspend(void);
extern void clocksource_resume(void);
({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
#define WRITE_ONCE(x, val) \
- ({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; })
+ ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+/**
+ * READ_ONCE_CTRL - Read a value heading a control dependency
+ * @x: The value to be read, heading the control dependency
+ *
+ * Control dependencies are tricky. See Documentation/memory-barriers.txt
+ * for important information on how to use them. Note that in many cases,
+ * use of smp_load_acquire() will be much simpler. Control dependencies
+ * should be avoided except on the hottest of hotpaths.
+ */
+#define READ_ONCE_CTRL(x) \
+({ \
+ typeof(x) __val = READ_ONCE(x); \
+ smp_read_barrier_depends(); /* Enforce control dependency. */ \
+ __val; \
+})
#endif /* __KERNEL__ */
* with an explicit memory barrier or atomic instruction that provides the
* required ordering.
*
- * If possible use READ_ONCE/ASSIGN_ONCE instead.
+ * If possible use READ_ONCE()/WRITE_ONCE() instead.
*/
#define __ACCESS_ONCE(x) ({ \
__maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
return 1;
}
-static inline int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+static inline unsigned int cpumask_local_spread(unsigned int i, int node)
{
- set_bit(0, cpumask_bits(dstp));
-
return 0;
}
int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
-int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp);
+unsigned int cpumask_local_spread(unsigned int i, int node);
/**
* for_each_cpu - iterate over every cpu in a mask
/* declared over in file.c */
extern const struct file_operations debugfs_file_operations;
-extern const struct inode_operations debugfs_link_operations;
struct dentry *debugfs_create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
struct irte {
union {
+ /* Shared between remapped and posted mode*/
struct {
- __u64 present : 1,
- fpd : 1,
- dst_mode : 1,
- redir_hint : 1,
- trigger_mode : 1,
- dlvry_mode : 3,
- avail : 4,
- __reserved_1 : 4,
- vector : 8,
- __reserved_2 : 8,
- dest_id : 32;
+ __u64 present : 1, /* 0 */
+ fpd : 1, /* 1 */
+ __res0 : 6, /* 2 - 6 */
+ avail : 4, /* 8 - 11 */
+ __res1 : 3, /* 12 - 14 */
+ pst : 1, /* 15 */
+ vector : 8, /* 16 - 23 */
+ __res2 : 40; /* 24 - 63 */
+ };
+
+ /* Remapped mode */
+ struct {
+ __u64 r_present : 1, /* 0 */
+ r_fpd : 1, /* 1 */
+ dst_mode : 1, /* 2 */
+ redir_hint : 1, /* 3 */
+ trigger_mode : 1, /* 4 */
+ dlvry_mode : 3, /* 5 - 7 */
+ r_avail : 4, /* 8 - 11 */
+ r_res0 : 4, /* 12 - 15 */
+ r_vector : 8, /* 16 - 23 */
+ r_res1 : 8, /* 24 - 31 */
+ dest_id : 32; /* 32 - 63 */
+ };
+
+ /* Posted mode */
+ struct {
+ __u64 p_present : 1, /* 0 */
+ p_fpd : 1, /* 1 */
+ p_res0 : 6, /* 2 - 7 */
+ p_avail : 4, /* 8 - 11 */
+ p_res1 : 2, /* 12 - 13 */
+ p_urgent : 1, /* 14 */
+ p_pst : 1, /* 15 */
+ p_vector : 8, /* 16 - 23 */
+ p_res2 : 14, /* 24 - 37 */
+ pda_l : 26; /* 38 - 63 */
};
__u64 low;
};
union {
+ /* Shared between remapped and posted mode*/
struct {
- __u64 sid : 16,
- sq : 2,
- svt : 2,
- __reserved_3 : 44;
+ __u64 sid : 16, /* 64 - 79 */
+ sq : 2, /* 80 - 81 */
+ svt : 2, /* 82 - 83 */
+ __res3 : 44; /* 84 - 127 */
+ };
+
+ /* Posted mode*/
+ struct {
+ __u64 p_sid : 16, /* 64 - 79 */
+ p_sq : 2, /* 80 - 81 */
+ p_svt : 2, /* 82 - 83 */
+ p_res3 : 12, /* 84 - 95 */
+ pda_h : 32; /* 96 - 127 */
};
__u64 high;
};
};
+static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src)
+{
+ dst->present = src->present;
+ dst->fpd = src->fpd;
+ dst->avail = src->avail;
+ dst->pst = src->pst;
+ dst->vector = src->vector;
+ dst->sid = src->sid;
+ dst->sq = src->sq;
+ dst->svt = src->svt;
+}
+
+#define PDA_LOW_BIT 26
+#define PDA_HIGH_BIT 32
+
enum {
IRQ_REMAP_XAPIC_MODE,
IRQ_REMAP_X2APIC_MODE,
extern void dmar_msi_write(int irq, struct msi_msg *msg);
extern int dmar_set_interrupt(struct intel_iommu *iommu);
extern irqreturn_t dmar_fault(int irq, void *dev_id);
-extern int arch_setup_dmar_msi(unsigned int irq);
+extern int dmar_alloc_hwirq(int id, int node, void *arg);
+extern void dmar_free_hwirq(int irq);
#endif /* __DMAR_H__ */
#define EFI_FILE_INFO_ID \
EFI_GUID( 0x9576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
+#define EFI_SYSTEM_RESOURCE_TABLE_GUID \
+ EFI_GUID( 0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80 )
+
#define EFI_FILE_SYSTEM_GUID \
EFI_GUID( 0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
unsigned long fw_vendor; /* fw_vendor */
unsigned long runtime; /* runtime table */
unsigned long config_table; /* config tables */
+ unsigned long esrt; /* ESRT table */
efi_get_time_t *get_time;
efi_set_time_t *set_time;
efi_get_wakeup_time_t *get_wakeup_time;
#endif
extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
extern int efi_config_init(efi_config_table_type_t *arch_tables);
+#ifdef CONFIG_EFI_ESRT
+extern void __init efi_esrt_init(void);
+#else
+static inline void efi_esrt_init(void) { }
+#endif
extern int efi_config_parse_tables(void *config_tables, int count, int sz,
efi_config_table_type_t *arch_tables);
extern u64 efi_get_iobase (void);
extern u64 efi_mem_attributes (unsigned long phys_addr);
extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
extern int __init efi_uart_console_only (void);
+extern u64 efi_mem_desc_end(efi_memory_desc_t *md);
+extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md);
extern void efi_initialize_iomem_resources(struct resource *code_resource,
struct resource *data_resource, struct resource *bss_resource);
extern void efi_get_time(struct timespec *now);
extern void efi_reserve_boot_services(void);
extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose);
extern struct efi_memory_map memmap;
+extern struct kobject *efi_kobj;
extern int efi_reboot_quirk_mode;
extern bool efi_poweroff_required(void);
struct export_operations;
struct hd_geometry;
struct iovec;
-struct nameidata;
struct kiocb;
struct kobject;
struct pipe_inode_info;
struct pipe_inode_info *i_pipe;
struct block_device *i_bdev;
struct cdev *i_cdev;
+ char *i_link;
};
__u32 i_generation;
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
- void * (*follow_link) (struct dentry *, struct nameidata *);
+ const char * (*follow_link) (struct dentry *, void **);
int (*permission) (struct inode *, int);
struct posix_acl * (*get_acl)(struct inode *, int);
int (*readlink) (struct dentry *, char __user *,int);
- void (*put_link) (struct dentry *, struct nameidata *, void *);
+ void (*put_link) (struct inode *, void *);
int (*create) (struct inode *,struct dentry *, umode_t, bool);
int (*link) (struct dentry *,struct inode *,struct dentry *);
S_VERSION = 8,
};
+extern bool atime_needs_update(const struct path *, struct inode *);
extern void touch_atime(const struct path *);
static inline void file_accessed(struct file *file)
{
extern int readlink_copy(char __user *, int, const char *);
extern int page_readlink(struct dentry *, char __user *, int);
-extern void *page_follow_link_light(struct dentry *, struct nameidata *);
-extern void page_put_link(struct dentry *, struct nameidata *, void *);
+extern const char *page_follow_link_light(struct dentry *, void **);
+extern void page_put_link(struct inode *, void *);
extern int __page_symlink(struct inode *inode, const char *symname, int len,
int nofs);
extern int page_symlink(struct inode *inode, const char *symname, int len);
extern const struct inode_operations page_symlink_inode_operations;
-extern void kfree_put_link(struct dentry *, struct nameidata *, void *);
+extern void kfree_put_link(struct inode *, void *);
+extern void free_page_put_link(struct inode *, void *);
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
int vfs_getattr_nosec(struct path *path, struct kstat *stat);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);
+const char *simple_follow_link(struct dentry *, void **);
+extern const struct inode_operations simple_symlink_inode_operations;
extern int iterate_dir(struct file *, struct dir_context *);
const unsigned char *buf, int len);
const char *ftrace_print_array_seq(struct trace_seq *p,
- const void *buf, int buf_len,
+ const void *buf, int count,
size_t el_size);
struct trace_iterator;
#define ___GFP_HARDWALL 0x20000u
#define ___GFP_THISNODE 0x40000u
#define ___GFP_RECLAIMABLE 0x80000u
+#define ___GFP_NOACCOUNT 0x100000u
#define ___GFP_NOTRACK 0x200000u
#define ___GFP_NO_KSWAPD 0x400000u
#define ___GFP_OTHER_NODE 0x800000u
#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */
#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */
#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
+#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */
#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */
#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD)
#ifndef LINUX_HARDIRQ_H
#define LINUX_HARDIRQ_H
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
#include <linux/lockdep.h>
#include <linux/ftrace_irq.h>
#include <linux/vtime.h>
* @usage: Usage id for this hub device instance.
* @start_collection_index: Starting index for a phy type collection
* @end_collection_index: Last index for a phy type collection
- * @mutex: synchronizing mutex.
+ * @mutex_ptr: synchronizing mutex pointer.
* @pending: Holds information of pending sync read request.
*/
struct hid_sensor_hub_device {
u32 usage;
int start_collection_index;
int end_collection_index;
- struct mutex mutex;
+ struct mutex *mutex_ptr;
struct sensor_hub_pending pending;
};
static inline void *kmap_atomic(struct page *page)
{
+ preempt_disable();
pagefault_disable();
return page_address(page);
}
static inline void __kunmap_atomic(void *addr)
{
pagefault_enable();
+ preempt_enable();
}
#define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn))
*
* 0x00 inactive
* 0x01 enqueued into rbtree
- * 0x02 callback function running
- * 0x04 timer is migrated to another cpu
*
- * Special cases:
- * 0x03 callback function running and enqueued
- * (was requeued on another CPU)
- * 0x05 timer was migrated on CPU hotunplug
+ * The callback state is not part of the timer->state because clearing it would
+ * mean touching the timer after the callback, this makes it impossible to free
+ * the timer from the callback function.
*
- * The "callback function running and enqueued" status is only possible on
- * SMP. It happens for example when a posix timer expired and the callback
+ * Therefore we track the callback state in:
+ *
+ * timer->base->cpu_base->running == timer
+ *
+ * On SMP it is possible to have a "callback function running and enqueued"
+ * status. It happens for example when a posix timer expired and the callback
* queued a signal. Between dropping the lock which protects the posix timer
* and reacquiring the base lock of the hrtimer, another CPU can deliver the
- * signal and rearm the timer. We have to preserve the callback running state,
- * as otherwise the timer could be removed before the softirq code finishes the
- * the handling of the timer.
- *
- * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state
- * to preserve the HRTIMER_STATE_CALLBACK in the above scenario. This
- * also affects HRTIMER_STATE_MIGRATE where the preservation is not
- * necessary. HRTIMER_STATE_MIGRATE is cleared after the timer is
- * enqueued on the new cpu.
+ * signal and rearm the timer.
*
* All state transitions are protected by cpu_base->lock.
*/
#define HRTIMER_STATE_INACTIVE 0x00
#define HRTIMER_STATE_ENQUEUED 0x01
-#define HRTIMER_STATE_CALLBACK 0x02
-#define HRTIMER_STATE_MIGRATE 0x04
/**
* struct hrtimer - the basic hrtimer structure
struct task_struct *task;
};
+#ifdef CONFIG_64BIT
+# define HRTIMER_CLOCK_BASE_ALIGN 64
+#else
+# define HRTIMER_CLOCK_BASE_ALIGN 32
+#endif
+
/**
* struct hrtimer_clock_base - the timer base for a specific clock
* @cpu_base: per cpu clock base
* timer to a base on another cpu.
* @clockid: clock id for per_cpu support
* @active: red black tree root node for the active timers
- * @resolution: the resolution of the clock, in nanoseconds
* @get_time: function to retrieve the current time of the clock
- * @softirq_time: the time when running the hrtimer queue in the softirq
* @offset: offset of this clock to the monotonic base
*/
struct hrtimer_clock_base {
int index;
clockid_t clockid;
struct timerqueue_head active;
- ktime_t resolution;
ktime_t (*get_time)(void);
- ktime_t softirq_time;
ktime_t offset;
-};
+} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
enum hrtimer_base_type {
HRTIMER_BASE_MONOTONIC,
* struct hrtimer_cpu_base - the per cpu clock bases
* @lock: lock protecting the base and associated clock bases
* and timers
+ * @seq: seqcount around __run_hrtimer
+ * @running: pointer to the currently running hrtimer
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
- * @clock_was_set: Indicates that clock was set from irq context.
+ * @clock_was_set_seq: Sequence counter of clock was set events
+ * @migration_enabled: The migration of hrtimers to other cpus is enabled
+ * @nohz_active: The nohz functionality is enabled
* @expires_next: absolute time of the next event which was scheduled
* via clock_set_next_event()
+ * @next_timer: Pointer to the first expiring timer
* @in_hrtirq: hrtimer_interrupt() is currently executing
* @hres_active: State of high resolution mode
* @hang_detected: The last hrtimer interrupt detected a hang
* @nr_hangs: Total number of hrtimer interrupt hangs
* @max_hang_time: Maximum time spent in hrtimer_interrupt
* @clock_base: array of clock bases for this cpu
+ *
+ * Note: next_timer is just an optimization for __remove_hrtimer().
+ * Do not dereference the pointer because it is not reliable on
+ * cross cpu removals.
*/
struct hrtimer_cpu_base {
raw_spinlock_t lock;
+ seqcount_t seq;
+ struct hrtimer *running;
unsigned int cpu;
unsigned int active_bases;
- unsigned int clock_was_set;
+ unsigned int clock_was_set_seq;
+ bool migration_enabled;
+ bool nohz_active;
#ifdef CONFIG_HIGH_RES_TIMERS
+ unsigned int in_hrtirq : 1,
+ hres_active : 1,
+ hang_detected : 1;
ktime_t expires_next;
- int in_hrtirq;
- int hres_active;
- int hang_detected;
- unsigned long nr_events;
- unsigned long nr_retries;
- unsigned long nr_hangs;
- ktime_t max_hang_time;
+ struct hrtimer *next_timer;
+ unsigned int nr_events;
+ unsigned int nr_retries;
+ unsigned int nr_hangs;
+ unsigned int max_hang_time;
#endif
struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES];
-};
+} ____cacheline_aligned;
static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
{
+ BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN);
+
timer->node.expires = time;
timer->_softexpires = time;
}
return ktime_sub(timer->node.expires, timer->base->get_time());
}
-#ifdef CONFIG_HIGH_RES_TIMERS
-struct clock_event_device;
-
-extern void hrtimer_interrupt(struct clock_event_device *dev);
-
-/*
- * In high resolution mode the time reference must be read accurate
- */
static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
{
return timer->base->get_time();
}
+#ifdef CONFIG_HIGH_RES_TIMERS
+struct clock_event_device;
+
+extern void hrtimer_interrupt(struct clock_event_device *dev);
+
static inline int hrtimer_is_hres_active(struct hrtimer *timer)
{
return timer->base->cpu_base->hres_active;
extern void clock_was_set_delayed(void);
+extern unsigned int hrtimer_resolution;
+
#else
# define MONOTONIC_RES_NSEC LOW_RES_NSEC
# define KTIME_MONOTONIC_RES KTIME_LOW_RES
-static inline void hrtimer_peek_ahead_timers(void) { }
+#define hrtimer_resolution (unsigned int)LOW_RES_NSEC
-/*
- * In non high resolution mode the time reference is taken from
- * the base softirq time variable.
- */
-static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
-{
- return timer->base->softirq_time;
-}
+static inline void hrtimer_peek_ahead_timers(void) { }
static inline int hrtimer_is_hres_active(struct hrtimer *timer)
{
#endif
/* Basic timer operations: */
-extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
- const enum hrtimer_mode mode);
-extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
unsigned long range_ns, const enum hrtimer_mode mode);
-extern int
-__hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- unsigned long delta_ns,
- const enum hrtimer_mode mode, int wakeup);
+
+/**
+ * hrtimer_start - (re)start an hrtimer on the current CPU
+ * @timer: the timer to be added
+ * @tim: expiry time
+ * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL)
+ */
+static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
+ const enum hrtimer_mode mode)
+{
+ hrtimer_start_range_ns(timer, tim, 0, mode);
+}
extern int hrtimer_cancel(struct hrtimer *timer);
extern int hrtimer_try_to_cancel(struct hrtimer *timer);
-static inline int hrtimer_start_expires(struct hrtimer *timer,
- enum hrtimer_mode mode)
+static inline void hrtimer_start_expires(struct hrtimer *timer,
+ enum hrtimer_mode mode)
{
unsigned long delta;
ktime_t soft, hard;
soft = hrtimer_get_softexpires(timer);
hard = hrtimer_get_expires(timer);
delta = ktime_to_ns(ktime_sub(hard, soft));
- return hrtimer_start_range_ns(timer, soft, delta, mode);
+ hrtimer_start_range_ns(timer, soft, delta, mode);
}
-static inline int hrtimer_restart(struct hrtimer *timer)
+static inline void hrtimer_restart(struct hrtimer *timer)
{
- return hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}
/* Query timers: */
extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
-extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
-extern ktime_t hrtimer_get_next_event(void);
+extern u64 hrtimer_get_next_event(void);
-/*
- * A timer is active, when it is enqueued into the rbtree or the
- * callback function is running or it's in the state of being migrated
- * to another cpu.
- */
-static inline int hrtimer_active(const struct hrtimer *timer)
-{
- return timer->state != HRTIMER_STATE_INACTIVE;
-}
+extern bool hrtimer_active(const struct hrtimer *timer);
/*
* Helper function to check, whether the timer is on one of the queues
*/
static inline int hrtimer_callback_running(struct hrtimer *timer)
{
- return timer->state & HRTIMER_STATE_CALLBACK;
+ return timer->base->cpu_base->running == timer;
}
/* Forward a hrtimer so it expires after now: */
extern u64
hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval);
-/* Forward a hrtimer so it expires after the hrtimer's current now */
+/**
+ * hrtimer_forward_now - forward the timer expiry so it expires after now
+ * @timer: hrtimer to forward
+ * @interval: the interval to forward
+ *
+ * Forward the timer expiry so it will expire after the current time
+ * of the hrtimer clock base. Returns the number of overruns.
+ *
+ * Can be safely called from the callback function of @timer. If
+ * called from other contexts @timer must neither be enqueued nor
+ * running the callback and the caller needs to take care of
+ * serialization.
+ *
+ * Note: This only updates the timer expiry value and does not requeue
+ * the timer.
+ */
static inline u64 hrtimer_forward_now(struct hrtimer *timer,
ktime_t interval)
{
/* Soft interrupt function to run the hrtimer queues: */
extern void hrtimer_run_queues(void);
-extern void hrtimer_run_pending(void);
/* Bootup initialization: */
extern void __init hrtimers_init(void);
#ifndef LINUX_HTIRQ_H
#define LINUX_HTIRQ_H
+struct pci_dev;
+struct irq_data;
+
struct ht_irq_msg {
u32 address_lo; /* low 32 bits of the ht irq message */
u32 address_hi; /* high 32 bits of the it irq message */
};
+typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
+ struct ht_irq_msg *msg);
+
+struct ht_irq_cfg {
+ struct pci_dev *dev;
+ /* Update callback used to cope with buggy hardware */
+ ht_irq_update_t *update;
+ unsigned pos;
+ unsigned idx;
+ struct ht_irq_msg msg;
+};
+
/* Helper functions.. */
void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-struct irq_data;
void mask_ht_irq(struct irq_data *data);
void unmask_ht_irq(struct irq_data *data);
/* The arch hook for getting things started */
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev);
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+ ht_irq_update_t *update);
+void arch_teardown_ht_irq(unsigned int irq);
/* For drivers of buggy hardware */
-typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
- struct ht_irq_msg *msg);
int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update);
#endif /* LINUX_HTIRQ_H */
.cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \
.rlim = INIT_RLIMITS, \
.cputimer = { \
- .cputime = INIT_CPUTIME, \
- .running = 0, \
- .lock = __RAW_SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \
+ .cputime_atomic = INIT_CPUTIME_ATOMIC, \
+ .running = 0, \
}, \
.cred_guard_mutex = \
__MUTEX_INITIALIZER(sig.cred_guard_mutex), \
/*
* Decoding Capability Register
*/
+#define cap_pi_support(c) (((c) >> 59) & 1)
#define cap_read_drain(c) (((c) >> 55) & 1)
#define cap_write_drain(c) (((c) >> 54) & 1)
#define cap_max_amask_val(c) (((c) >> 48) & 0x3f)
* Extended Capability Register
*/
+#define ecap_pasid(e) ((e >> 40) & 0x1)
#define ecap_pss(e) ((e >> 35) & 0x1f)
#define ecap_eafs(e) ((e >> 34) & 0x1)
#define ecap_nwfs(e) ((e >> 33) & 0x1)
#define ecap_srs(e) ((e >> 31) & 0x1)
#define ecap_ers(e) ((e >> 30) & 0x1)
#define ecap_prs(e) ((e >> 29) & 0x1)
-#define ecap_pasid(e) ((e >> 28) & 0x1)
+/* PASID support used to be on bit 28 */
#define ecap_dis(e) ((e >> 27) & 0x1)
#define ecap_nest(e) ((e >> 26) & 0x1)
#define ecap_mts(e) ((e >> 25) & 0x1)
#define INTR_REMAP_TABLE_ENTRIES 65536
+struct irq_domain;
+
struct ir_table {
struct irte *base;
unsigned long *bitmap;
#ifdef CONFIG_IRQ_REMAP
struct ir_table *ir_table; /* Interrupt remapping info */
+ struct irq_domain *ir_domain;
+ struct irq_domain *ir_msi_domain;
#endif
struct device *iommu_dev; /* IOMMU-sysfs device */
int node;
BLOCK_IOPOLL_SOFTIRQ,
TASKLET_SOFTIRQ,
SCHED_SOFTIRQ,
- HRTIMER_SOFTIRQ,
+ HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the
+ numbering. Sigh! */
RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */
NR_SOFTIRQS
clockid_t which_clock, enum hrtimer_mode mode);
static inline
-int tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
- const enum hrtimer_mode mode)
+void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
+ const enum hrtimer_mode mode)
{
- return hrtimer_start(&ttimer->timer, time, mode);
+ hrtimer_start(&ttimer->timer, time, mode);
}
static inline
io_mapping_map_atomic_wc(struct io_mapping *mapping,
unsigned long offset)
{
+ preempt_disable();
pagefault_disable();
return ((char __force __iomem *) mapping) + offset;
}
io_mapping_unmap_atomic(void __iomem *vaddr)
{
pagefault_enable();
+ preempt_enable();
}
/* Non-atomic map/unmap */
#define _LINUX_IO_H
#include <linux/types.h>
+#include <linux/init.h>
#include <asm/io.h>
#include <asm/page.h>
}
#define arch_phys_wc_add arch_phys_wc_add
+#ifndef arch_phys_wc_index
+static inline int arch_phys_wc_index(int handle)
+{
+ return -1;
+}
+#define arch_phys_wc_index arch_phys_wc_index
+#endif
#endif
#endif /* _LINUX_IO_H */
* @irq_write_msi_msg: optional to write message content for MSI
* @irq_get_irqchip_state: return the internal state of an interrupt
* @irq_set_irqchip_state: set the internal state of a interrupt
+ * @irq_set_vcpu_affinity: optional to target a vCPU in a virtual machine
* @flags: chip specific flags
*/
struct irq_chip {
int (*irq_get_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool *state);
int (*irq_set_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool state);
+ int (*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info);
+
unsigned long flags;
};
extern void irq_cpu_offline(void);
extern int irq_set_affinity_locked(struct irq_data *data,
const struct cpumask *cpumask, bool force);
+extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info);
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
void irq_move_irq(struct irq_data *data);
const struct cpumask *dest,
bool force);
extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on);
+extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data,
+ void *vcpu_info);
#endif
/* Handling of unhandled and spurious interrupts: */
struct device_node;
-extern struct irq_chip gic_arch_extn;
-
void gic_set_irqchip_flags(unsigned long flags);
void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *,
u32 offset, struct device_node *);
extern struct irq_desc irq_desc[NR_IRQS];
#endif
+static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
+{
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+ return irq_to_desc(data->irq);
+#else
+ return container_of(data, struct irq_desc, irq_data);
+#endif
+}
+
static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
{
return &desc->irq_data;
#include <linux/time.h>
#include <linux/timex.h>
#include <asm/param.h> /* for HZ */
+#include <generated/timeconst.h>
/*
* The following defines establish the engineering parameters of the PLL
return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC;
}
-extern unsigned long msecs_to_jiffies(const unsigned int m);
-extern unsigned long usecs_to_jiffies(const unsigned int u);
+extern unsigned long __msecs_to_jiffies(const unsigned int m);
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+/*
+ * HZ is equal to or smaller than 1000, and 1000 is a nice round
+ * multiple of HZ, divide with the factor between them, but round
+ * upwards:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+ return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
+}
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+/*
+ * HZ is larger than 1000, and HZ is a nice round multiple of 1000 -
+ * simply multiply with the factor between them.
+ *
+ * But first make sure the multiplication result cannot overflow:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+ if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+ return MAX_JIFFY_OFFSET;
+ return m * (HZ / MSEC_PER_SEC);
+}
+#else
+/*
+ * Generic case - multiply, round and divide. But first check that if
+ * we are doing a net multiplication, that we wouldn't overflow:
+ */
+static inline unsigned long _msecs_to_jiffies(const unsigned int m)
+{
+ if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+ return MAX_JIFFY_OFFSET;
+
+ return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) >> MSEC_TO_HZ_SHR32;
+}
+#endif
+/**
+ * msecs_to_jiffies: - convert milliseconds to jiffies
+ * @m: time in milliseconds
+ *
+ * conversion is done as follows:
+ *
+ * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
+ *
+ * - 'too large' values [that would result in larger than
+ * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ * the input value by a factor or dividing it with a factor and
+ * handling any 32-bit overflows.
+ * for the details see __msecs_to_jiffies()
+ *
+ * msecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __msecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the HZ range specific helpers _msecs_to_jiffies() are called both
+ * directly here and from __msecs_to_jiffies() in the case where
+ * constant folding is not possible.
+ */
+static inline unsigned long msecs_to_jiffies(const unsigned int m)
+{
+ if (__builtin_constant_p(m)) {
+ if ((int)m < 0)
+ return MAX_JIFFY_OFFSET;
+ return _msecs_to_jiffies(m);
+ } else {
+ return __msecs_to_jiffies(m);
+ }
+}
+
+extern unsigned long __usecs_to_jiffies(const unsigned int u);
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+ return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
+}
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+ return u * (HZ / USEC_PER_SEC);
+}
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+#else
+static inline unsigned long _usecs_to_jiffies(const unsigned int u)
+{
+ return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
+ >> USEC_TO_HZ_SHR32;
+}
+#endif
+
+/**
+ * usecs_to_jiffies: - convert microseconds to jiffies
+ * @u: time in microseconds
+ *
+ * conversion is done as follows:
+ *
+ * - 'too large' values [that would result in larger than
+ * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ * the input value by a factor or dividing it with a factor and
+ * handling any 32-bit overflows as for msecs_to_jiffies.
+ *
+ * usecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __usecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the HZ range specific helpers _usecs_to_jiffies() are called both
+ * directly here and from __msecs_to_jiffies() in the case where
+ * constant folding is not possible.
+ */
+static inline unsigned long usecs_to_jiffies(const unsigned int u)
+{
+ if (__builtin_constant_p(u)) {
+ if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
+ return MAX_JIFFY_OFFSET;
+ return _usecs_to_jiffies(u);
+ } else {
+ return __usecs_to_jiffies(u);
+ }
+}
+
extern unsigned long timespec_to_jiffies(const struct timespec *value);
extern void jiffies_to_timespec(const unsigned long jiffies,
struct timespec *value);
#if defined(CONFIG_MMU) && \
(defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP))
-void might_fault(void);
+#define might_fault() __might_fault(__FILE__, __LINE__)
+void __might_fault(const char *file, int line);
#else
static inline void might_fault(void) { }
#endif
}
#if BITS_PER_LONG < 64
-extern u64 __ktime_divns(const ktime_t kt, s64 div);
-static inline u64 ktime_divns(const ktime_t kt, s64 div)
+extern s64 __ktime_divns(const ktime_t kt, s64 div);
+static inline s64 ktime_divns(const ktime_t kt, s64 div)
{
+ /*
+ * Negative divisors could cause an inf loop,
+ * so bug out here.
+ */
+ BUG_ON(div < 0);
if (__builtin_constant_p(div) && !(div >> 32)) {
- u64 ns = kt.tv64;
- do_div(ns, div);
- return ns;
+ s64 ns = kt.tv64;
+ u64 tmp = ns < 0 ? -ns : ns;
+
+ do_div(tmp, div);
+ return ns < 0 ? -tmp : tmp;
} else {
return __ktime_divns(kt, div);
}
}
#else /* BITS_PER_LONG < 64 */
-# define ktime_divns(kt, div) (u64)((kt).tv64 / (div))
+static inline s64 ktime_divns(const ktime_t kt, s64 div)
+{
+ /*
+ * 32-bit implementation cannot handle negative divisors,
+ * so catch them on 64bit as well.
+ */
+ WARN_ON(div < 0);
+ return kt.tv64 / div;
+}
#endif
static inline s64 ktime_to_us(const ktime_t kt)
static struct lglock name = { .lock = &name ## _lock }
void lg_lock_init(struct lglock *lg, char *name);
+
void lg_local_lock(struct lglock *lg);
void lg_local_unlock(struct lglock *lg);
void lg_local_lock_cpu(struct lglock *lg, int cpu);
void lg_local_unlock_cpu(struct lglock *lg, int cpu);
+
+void lg_double_lock(struct lglock *lg, int cpu1, int cpu2);
+void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2);
+
void lg_global_lock(struct lglock *lg);
void lg_global_unlock(struct lglock *lg);
ATA_LFLAG_SW_ACTIVITY = (1 << 7), /* keep activity stats */
ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */
ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */
+ ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */
/* struct ata_port flags */
ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */
*/
ATA_TMOUT_PMP_SRST_WAIT = 5000,
+ /* When the LPM policy is set to ATA_LPM_MAX_POWER, there might
+ * be a spurious PHY event, so ignore the first PHY event that
+ * occurs within 10s after the policy change.
+ */
+ ATA_TMOUT_SPURIOUS_PHY = 10000,
+
/* ATA bus states */
BUS_UNKNOWN = 0,
BUS_DMA = 1,
struct ata_eh_context eh_context;
struct ata_device device[ATA_MAX_DEVICES];
+
+ unsigned long last_lpm_change; /* when last LPM change happened */
};
#define ATA_LINK_CLEAR_BEGIN offsetof(struct ata_link, active_tag)
#define ATA_LINK_CLEAR_END offsetof(struct ata_link, device[0])
extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap);
extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q);
+extern bool sata_lpm_ignore_phy_events(struct ata_link *link);
extern int ata_cable_40wire(struct ata_port *ap);
extern int ata_cable_80wire(struct ata_port *ap);
};
struct lock_class_stats {
- unsigned long contention_point[4];
- unsigned long contending_point[4];
+ unsigned long contention_point[LOCKSTAT_POINTS];
+ unsigned long contending_point[LOCKSTAT_POINTS];
struct lock_time read_waittime;
struct lock_time write_waittime;
struct lock_time read_holdtime;
if (!memcg_kmem_enabled())
return true;
+ if (gfp & __GFP_NOACCOUNT)
+ return true;
/*
* __GFP_NOFAIL allocations will move on even if charging is not
* possible. Therefore we don't even try, and have this allocation
{
if (!memcg_kmem_enabled())
return cachep;
+ if (gfp & __GFP_NOACCOUNT)
+ return cachep;
if (gfp & __GFP_NOFAIL)
return cachep;
if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
#ifndef _LINUX_NAMEI_H
#define _LINUX_NAMEI_H
-#include <linux/dcache.h>
-#include <linux/errno.h>
-#include <linux/linkage.h>
+#include <linux/kernel.h>
#include <linux/path.h>
-
-struct vfsmount;
-struct nameidata;
+#include <linux/fcntl.h>
+#include <linux/errno.h>
enum { MAX_NESTED_LINKS = 8 };
+#define MAXSYMLINKS 40
+
/*
* Type of the last component on LOOKUP_PARENT
*/
#define LOOKUP_ROOT 0x2000
#define LOOKUP_EMPTY 0x4000
-extern int user_path_at(int, const char __user *, unsigned, struct path *);
extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
-#define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
-#define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path)
-#define user_path_dir(name, path) \
- user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path)
+static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
+ struct path *path)
+{
+ return user_path_at_empty(dfd, name, flags, path, NULL);
+}
+
+static inline int user_path(const char __user *name, struct path *path)
+{
+ return user_path_at_empty(AT_FDCWD, name, LOOKUP_FOLLOW, path, NULL);
+}
+
+static inline int user_lpath(const char __user *name, struct path *path)
+{
+ return user_path_at_empty(AT_FDCWD, name, 0, path, NULL);
+}
+
+static inline int user_path_dir(const char __user *name, struct path *path)
+{
+ return user_path_at_empty(AT_FDCWD, name,
+ LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path, NULL);
+}
extern int kern_path(const char *, unsigned, struct path *);
extern struct dentry *lock_rename(struct dentry *, struct dentry *);
extern void unlock_rename(struct dentry *, struct dentry *);
-extern void nd_jump_link(struct nameidata *nd, struct path *path);
-extern void nd_set_link(struct nameidata *nd, char *path);
-extern char *nd_get_link(struct nameidata *nd);
+extern void nd_jump_link(struct path *path);
static inline void nd_terminate_link(void *name, size_t len, size_t maxlen)
{
#ifndef _LINUX_NETDEVICE_H
#define _LINUX_NETDEVICE_H
-#include <linux/pm_qos.h>
#include <linux/timer.h>
#include <linux/bug.h>
#include <linux/delay.h>
*
* @qdisc_tx_busylock: XXX: need comments on this one
*
- * @pm_qos_req: Power Management QoS object
- *
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
extern raw_spinlock_t devtree_lock;
#ifdef CONFIG_OF
+void of_core_init(void);
+
static inline bool is_of_node(struct fwnode_handle *fwnode)
{
return fwnode && fwnode->type == FWNODE_OF;
#else /* CONFIG_OF */
+static inline void of_core_init(void)
+{
+}
+
static inline bool is_of_node(struct fwnode_handle *fwnode)
{
return false;
extern bool osq_lock(struct optimistic_spin_queue *lock);
extern void osq_unlock(struct optimistic_spin_queue *lock);
+static inline bool osq_is_locked(struct optimistic_spin_queue *lock)
+{
+ return atomic_read(&lock->tail) != OSQ_UNLOCKED_VAL;
+}
+
#endif
void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
s64 __percpu_counter_sum(struct percpu_counter *fbc);
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs);
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
+
+static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+{
+ return __percpu_counter_compare(fbc, rhs, percpu_counter_batch);
+}
static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
{
return 0;
}
+static inline int
+__percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
+{
+ return percpu_counter_compare(fbc, rhs);
+}
+
static inline void
percpu_counter_add(struct percpu_counter *fbc, s64 amount)
{
int idx; /* index in shared_regs->regs[] */
};
-struct event_constraint;
-
/**
* struct hw_perf_event - performance event hardware details:
*/
struct hw_perf_event_extra extra_reg;
struct hw_perf_event_extra branch_reg;
-
- struct event_constraint *constraint;
};
struct { /* software */
struct hrtimer hrtimer;
};
struct { /* intel_cqm */
int cqm_state;
- int cqm_rmid;
+ u32 cqm_rmid;
struct list_head cqm_events_entry;
struct list_head cqm_groups_entry;
struct list_head cqm_group_entry;
struct perf_event_context *task_ctx;
int active_oncpu;
int exclusive;
+
+ raw_spinlock_t hrtimer_lock;
struct hrtimer hrtimer;
ktime_t hrtimer_interval;
+ unsigned int hrtimer_active;
+
struct pmu *unique_pmu;
struct perf_cgroup *cgrp;
};
struct perf_sample_data *data,
struct pt_regs *regs);
+extern void perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs);
+
+extern void
+perf_event_header__init_id(struct perf_event_header *header,
+ struct perf_sample_data *data,
+ struct perf_event *event);
+extern void
+perf_event__output_id_sample(struct perf_event *event,
+ struct perf_output_handle *handle,
+ struct perf_sample_data *sample);
+
+extern void
+perf_log_lost_samples(struct perf_event *event, u64 lost);
+
static inline bool is_sampling_event(struct perf_event *event)
{
return event->attr.sample_period != 0;
extern struct static_key_deferred perf_sched_events;
+static __always_inline bool
+perf_sw_migrate_enabled(void)
+{
+ if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS]))
+ return true;
+ return false;
+}
+
+static inline void perf_event_task_migrate(struct task_struct *task)
+{
+ if (perf_sw_migrate_enabled())
+ task->sched_migrated = 1;
+}
+
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
if (static_key_false(&perf_sched_events.key))
__perf_event_task_sched_in(prev, task);
+
+ if (perf_sw_migrate_enabled() && task->sched_migrated) {
+ struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+ perf_fetch_caller_regs(regs);
+ ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0);
+ task->sched_migrated = 0;
+ }
}
static inline void perf_event_task_sched_out(struct task_struct *prev,
static inline void *
perf_get_aux(struct perf_output_handle *handle) { return NULL; }
static inline void
+perf_event_task_migrate(struct task_struct *task) { }
+static inline void
perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task) { }
static inline void
#ifndef __LINUX_PLATFORM_DATA_SI5351_H__
#define __LINUX_PLATFORM_DATA_SI5351_H__
-struct clk;
-
/**
* enum si5351_pll_src - Si5351 pll clock source
* @SI5351_PLL_SRC_DEFAULT: default, do not change eeprom config
* @clkout: array of clkout configuration
*/
struct si5351_platform_data {
- struct clk *clk_xtal;
- struct clk *clk_clkin;
enum si5351_pll_src pll_src[2];
struct si5351_clkout_config clkout[8];
};
#include <linux/list.h>
/*
- * We use the MSB mostly because its available; see <linux/preempt_mask.h> for
- * the other bits -- can't include that header due to inclusion hell.
+ * We put the hardirq and softirq counter into the preemption
+ * counter. The bitmask has the following meaning:
+ *
+ * - bits 0-7 are the preemption count (max preemption depth: 256)
+ * - bits 8-15 are the softirq count (max # of softirqs: 256)
+ *
+ * The hardirq count could in theory be the same as the number of
+ * interrupts in the system, but we run all interrupt handlers with
+ * interrupts disabled, so we cannot have nesting interrupts. Though
+ * there are a few palaeontologic drivers which reenable interrupts in
+ * the handler, so we need more than one bit here.
+ *
+ * PREEMPT_MASK: 0x000000ff
+ * SOFTIRQ_MASK: 0x0000ff00
+ * HARDIRQ_MASK: 0x000f0000
+ * NMI_MASK: 0x00100000
+ * PREEMPT_ACTIVE: 0x00200000
+ * PREEMPT_NEED_RESCHED: 0x80000000
*/
+#define PREEMPT_BITS 8
+#define SOFTIRQ_BITS 8
+#define HARDIRQ_BITS 4
+#define NMI_BITS 1
+
+#define PREEMPT_SHIFT 0
+#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS)
+#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS)
+
+#define __IRQ_MASK(x) ((1UL << (x))-1)
+
+#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
+#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
+#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT)
+
+#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT)
+#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT)
+#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
+#define NMI_OFFSET (1UL << NMI_SHIFT)
+
+#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
+
+#define PREEMPT_ACTIVE_BITS 1
+#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS)
+#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
+
+/* We use the MSB mostly because its available */
#define PREEMPT_NEED_RESCHED 0x80000000
+/* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
#include <asm/preempt.h>
+#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
+#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
+#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
+ | NMI_MASK))
+
+/*
+ * Are we doing bottom half or hardware interrupt processing?
+ * Are we in a softirq context? Interrupt context?
+ * in_softirq - Are we currently processing softirq or have bh disabled?
+ * in_serving_softirq - Are we currently processing softirq?
+ */
+#define in_irq() (hardirq_count())
+#define in_softirq() (softirq_count())
+#define in_interrupt() (irq_count())
+#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
+
+/*
+ * Are we in NMI context?
+ */
+#define in_nmi() (preempt_count() & NMI_MASK)
+
+#if defined(CONFIG_PREEMPT_COUNT)
+# define PREEMPT_DISABLE_OFFSET 1
+#else
+# define PREEMPT_DISABLE_OFFSET 0
+#endif
+
+/*
+ * The preempt_count offset needed for things like:
+ *
+ * spin_lock_bh()
+ *
+ * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
+ * softirqs, such that unlock sequences of:
+ *
+ * spin_unlock();
+ * local_bh_enable();
+ *
+ * Work as expected.
+ */
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_DISABLE_OFFSET)
+
+/*
+ * Are we running in atomic context? WARNING: this macro cannot
+ * always detect atomic context; in particular, it cannot know about
+ * held spinlocks in non-preemptible kernels. Thus it should not be
+ * used in the general case to determine whether sleeping is possible.
+ * Do not use in_atomic() in driver code.
+ */
+#define in_atomic() (preempt_count() != 0)
+
+/*
+ * Check whether we were atomic before we did preempt_disable():
+ * (used by the scheduler)
+ */
+#define in_atomic_preempt_off() \
+ ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_DISABLE_OFFSET)
+
#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
extern void preempt_count_add(int val);
extern void preempt_count_sub(int val);
#define preempt_count_inc() preempt_count_add(1)
#define preempt_count_dec() preempt_count_sub(1)
+#define preempt_active_enter() \
+do { \
+ preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
+ barrier(); \
+} while (0)
+
+#define preempt_active_exit() \
+do { \
+ barrier(); \
+ preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
+} while (0)
+
#ifdef CONFIG_PREEMPT_COUNT
#define preempt_disable() \
#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
+#define preemptible() (preempt_count() == 0 && !irqs_disabled())
+
#ifdef CONFIG_PREEMPT
#define preempt_enable() \
do { \
__preempt_schedule(); \
} while (0)
+#define preempt_enable_notrace() \
+do { \
+ barrier(); \
+ if (unlikely(__preempt_count_dec_and_test())) \
+ __preempt_schedule_notrace(); \
+} while (0)
+
#define preempt_check_resched() \
do { \
if (should_resched()) \
__preempt_schedule(); \
} while (0)
-#else
+#else /* !CONFIG_PREEMPT */
#define preempt_enable() \
do { \
barrier(); \
preempt_count_dec(); \
} while (0)
-#define preempt_check_resched() do { } while (0)
-#endif
-
-#define preempt_disable_notrace() \
-do { \
- __preempt_count_inc(); \
- barrier(); \
-} while (0)
-#define preempt_enable_no_resched_notrace() \
+#define preempt_enable_notrace() \
do { \
barrier(); \
__preempt_count_dec(); \
} while (0)
-#ifdef CONFIG_PREEMPT
-
-#ifndef CONFIG_CONTEXT_TRACKING
-#define __preempt_schedule_context() __preempt_schedule()
-#endif
+#define preempt_check_resched() do { } while (0)
+#endif /* CONFIG_PREEMPT */
-#define preempt_enable_notrace() \
+#define preempt_disable_notrace() \
do { \
+ __preempt_count_inc(); \
barrier(); \
- if (unlikely(__preempt_count_dec_and_test())) \
- __preempt_schedule_context(); \
} while (0)
-#else
-#define preempt_enable_notrace() \
+
+#define preempt_enable_no_resched_notrace() \
do { \
barrier(); \
__preempt_count_dec(); \
} while (0)
-#endif
#else /* !CONFIG_PREEMPT_COUNT */
#define preempt_disable_notrace() barrier()
#define preempt_enable_no_resched_notrace() barrier()
#define preempt_enable_notrace() barrier()
+#define preemptible() 0
#endif /* CONFIG_PREEMPT_COUNT */
+++ /dev/null
-#ifndef LINUX_PREEMPT_MASK_H
-#define LINUX_PREEMPT_MASK_H
-
-#include <linux/preempt.h>
-
-/*
- * We put the hardirq and softirq counter into the preemption
- * counter. The bitmask has the following meaning:
- *
- * - bits 0-7 are the preemption count (max preemption depth: 256)
- * - bits 8-15 are the softirq count (max # of softirqs: 256)
- *
- * The hardirq count could in theory be the same as the number of
- * interrupts in the system, but we run all interrupt handlers with
- * interrupts disabled, so we cannot have nesting interrupts. Though
- * there are a few palaeontologic drivers which reenable interrupts in
- * the handler, so we need more than one bit here.
- *
- * PREEMPT_MASK: 0x000000ff
- * SOFTIRQ_MASK: 0x0000ff00
- * HARDIRQ_MASK: 0x000f0000
- * NMI_MASK: 0x00100000
- * PREEMPT_ACTIVE: 0x00200000
- */
-#define PREEMPT_BITS 8
-#define SOFTIRQ_BITS 8
-#define HARDIRQ_BITS 4
-#define NMI_BITS 1
-
-#define PREEMPT_SHIFT 0
-#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS)
-#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS)
-#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS)
-
-#define __IRQ_MASK(x) ((1UL << (x))-1)
-
-#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
-#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
-#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
-#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT)
-
-#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT)
-#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT)
-#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
-#define NMI_OFFSET (1UL << NMI_SHIFT)
-
-#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
-
-#define PREEMPT_ACTIVE_BITS 1
-#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS)
-#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
-
-#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
-#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
-#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
- | NMI_MASK))
-
-/*
- * Are we doing bottom half or hardware interrupt processing?
- * Are we in a softirq context? Interrupt context?
- * in_softirq - Are we currently processing softirq or have bh disabled?
- * in_serving_softirq - Are we currently processing softirq?
- */
-#define in_irq() (hardirq_count())
-#define in_softirq() (softirq_count())
-#define in_interrupt() (irq_count())
-#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
-
-/*
- * Are we in NMI context?
- */
-#define in_nmi() (preempt_count() & NMI_MASK)
-
-#if defined(CONFIG_PREEMPT_COUNT)
-# define PREEMPT_CHECK_OFFSET 1
-#else
-# define PREEMPT_CHECK_OFFSET 0
-#endif
-
-/*
- * The preempt_count offset needed for things like:
- *
- * spin_lock_bh()
- *
- * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
- * softirqs, such that unlock sequences of:
- *
- * spin_unlock();
- * local_bh_enable();
- *
- * Work as expected.
- */
-#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_CHECK_OFFSET)
-
-/*
- * Are we running in atomic context? WARNING: this macro cannot
- * always detect atomic context; in particular, it cannot know about
- * held spinlocks in non-preemptible kernels. Thus it should not be
- * used in the general case to determine whether sleeping is possible.
- * Do not use in_atomic() in driver code.
- */
-#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0)
-
-/*
- * Check whether we were atomic before we did preempt_disable():
- * (used by the scheduler, *after* releasing the kernel lock)
- */
-#define in_atomic_preempt_off() \
- ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET)
-
-#ifdef CONFIG_PREEMPT_COUNT
-# define preemptible() (preempt_count() == 0 && !irqs_disabled())
-#else
-# define preemptible() 0
-#endif
-
-#endif /* LINUX_PREEMPT_MASK_H */
*/
static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
{
- ACCESS_ONCE(list->next) = list;
- ACCESS_ONCE(list->prev) = list;
+ WRITE_ONCE(list->next, list);
+ WRITE_ONCE(list->prev, list);
}
/*
#define list_first_or_null_rcu(ptr, type, member) \
({ \
struct list_head *__ptr = (ptr); \
- struct list_head *__next = ACCESS_ONCE(__ptr->next); \
+ struct list_head *__next = READ_ONCE(__ptr->next); \
likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \
})
*/
#define hlist_for_each_entry_from_rcu(pos, member) \
for (; pos; \
- pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
- typeof(*(pos)), member))
+ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \
+ &(pos)->member)), typeof(*(pos)), member))
#endif /* __KERNEL__ */
#endif
#include <linux/debugobjects.h>
#include <linux/bug.h>
#include <linux/compiler.h>
+#include <linux/ktime.h>
+
#include <asm/barrier.h>
extern int rcu_expedited; /* for sysctl */
void rcu_bh_qs(void);
void rcu_check_callbacks(int user);
struct notifier_block;
-void rcu_idle_enter(void);
-void rcu_idle_exit(void);
-void rcu_irq_enter(void);
-void rcu_irq_exit(void);
int rcu_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu);
#define rcu_note_voluntary_context_switch(t) \
do { \
rcu_all_qs(); \
- if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
- ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
+ if (READ_ONCE((t)->rcu_tasks_holdout)) \
+ WRITE_ONCE((t)->rcu_tasks_holdout, false); \
} while (0)
#else /* #ifdef CONFIG_TASKS_RCU */
#define TASKS_RCU(x) do { } while (0)
#define __rcu_access_pointer(p, space) \
({ \
- typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \
rcu_dereference_sparse(p, space); \
((typeof(*p) __force __kernel *)(_________p1)); \
})
((typeof(*p) __force __kernel *)(p)); \
})
-#define __rcu_access_index(p, space) \
-({ \
- typeof(p) _________p1 = ACCESS_ONCE(p); \
- rcu_dereference_sparse(p, space); \
- (_________p1); \
-})
-#define __rcu_dereference_index_check(p, c) \
-({ \
- /* Dependency order vs. p above. */ \
- typeof(p) _________p1 = lockless_dereference(p); \
- rcu_lockdep_assert(c, \
- "suspicious rcu_dereference_index_check() usage"); \
- (_________p1); \
-})
-
/**
* RCU_INITIALIZER() - statically initialize an RCU-protected global variable
* @v: The value to statically initialize with.
*/
#define lockless_dereference(p) \
({ \
- typeof(p) _________p1 = ACCESS_ONCE(p); \
+ typeof(p) _________p1 = READ_ONCE(p); \
smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
(_________p1); \
})
* @p: The pointer to read
*
* Return the value of the specified RCU-protected pointer, but omit the
- * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful
+ * smp_read_barrier_depends() and keep the READ_ONCE(). This is useful
* when the value of this pointer is accessed, but the pointer is not
* dereferenced, for example, when testing an RCU-protected pointer against
* NULL. Although rcu_access_pointer() may also be used in cases where
*/
#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)
-/**
- * rcu_access_index() - fetch RCU index with no dereferencing
- * @p: The index to read
- *
- * Return the value of the specified RCU-protected index, but omit the
- * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful
- * when the value of this index is accessed, but the index is not
- * dereferenced, for example, when testing an RCU-protected index against
- * -1. Although rcu_access_index() may also be used in cases where
- * update-side locks prevent the value of the index from changing, you
- * should instead use rcu_dereference_index_protected() for this use case.
- */
-#define rcu_access_index(p) __rcu_access_index((p), __rcu)
-
-/**
- * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
- * @p: The pointer to read, prior to dereferencing
- * @c: The conditions under which the dereference will take place
- *
- * Similar to rcu_dereference_check(), but omits the sparse checking.
- * This allows rcu_dereference_index_check() to be used on integers,
- * which can then be used as array indices. Attempting to use
- * rcu_dereference_check() on an integer will give compiler warnings
- * because the sparse address-space mechanism relies on dereferencing
- * the RCU-protected pointer. Dereferencing integers is not something
- * that even gcc will put up with.
- *
- * Note that this function does not implicitly check for RCU read-side
- * critical sections. If this function gains lots of uses, it might
- * make sense to provide versions for each flavor of RCU, but it does
- * not make sense as of early 2010.
- */
-#define rcu_dereference_index_check(p, c) \
- __rcu_dereference_index_check((p), (c))
-
/**
* rcu_dereference_protected() - fetch RCU pointer when updates prevented
* @p: The pointer to read, prior to dereferencing
* @c: The conditions under which the dereference will take place
*
* Return the value of the specified RCU-protected pointer, but omit
- * both the smp_read_barrier_depends() and the ACCESS_ONCE(). This
+ * both the smp_read_barrier_depends() and the READ_ONCE(). This
* is useful in cases where update-side locks prevent the value of the
* pointer from changing. Please note that this primitive does -not-
* prevent the compiler from repeating this reference or combining it
#define kfree_rcu(ptr, rcu_head) \
__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
-#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
-static inline int rcu_needs_cpu(unsigned long *delta_jiffies)
+#ifdef CONFIG_TINY_RCU
+static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
{
- *delta_jiffies = ULONG_MAX;
+ *nextevt = KTIME_MAX;
return 0;
}
-#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */
+#endif /* #ifdef CONFIG_TINY_RCU */
#if defined(CONFIG_RCU_NOCB_CPU_ALL)
static inline bool rcu_is_nocb_cpu(int cpu) { return true; }
{
}
+static inline void rcu_idle_enter(void)
+{
+}
+
+static inline void rcu_idle_exit(void)
+{
+}
+
+static inline void rcu_irq_enter(void)
+{
+}
+
+static inline void rcu_irq_exit(void)
+{
+}
+
static inline void exit_rcu(void)
{
}
#define __LINUX_RCUTREE_H
void rcu_note_context_switch(void);
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *delta_jiffies);
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
+int rcu_needs_cpu(u64 basem, u64 *nextevt);
void rcu_cpu_stall_reset(void);
/*
void rcu_bh_force_quiescent_state(void);
void rcu_sched_force_quiescent_state(void);
+void rcu_idle_enter(void);
+void rcu_idle_exit(void);
+void rcu_irq_enter(void);
+void rcu_irq_exit(void);
+
void exit_rcu(void);
void rcu_scheduler_starting(void);
#ifndef _LINUX_RHASHTABLE_H
#define _LINUX_RHASHTABLE_H
+#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/errno.h>
#include <linux/jhash.h>
* @key_len: Length of key
* @key_offset: Offset of key in struct to be hashed
* @head_offset: Offset of rhash_head in struct to be hashed
+ * @insecure_max_entries: Maximum number of entries (may be exceeded)
* @max_size: Maximum size while expanding
* @min_size: Minimum size while shrinking
* @nulls_base: Base value to generate nulls marker
size_t key_len;
size_t key_offset;
size_t head_offset;
+ unsigned int insecure_max_entries;
unsigned int max_size;
unsigned int min_size;
u32 nulls_base;
(!ht->p.max_size || tbl->size < ht->p.max_size);
}
+/**
+ * rht_grow_above_max - returns true if table is above maximum
+ * @ht: hash table
+ * @tbl: current table
+ */
+static inline bool rht_grow_above_max(const struct rhashtable *ht,
+ const struct bucket_table *tbl)
+{
+ return ht->p.insecure_max_entries &&
+ atomic_read(&ht->nelems) >= ht->p.insecure_max_entries;
+}
+
/* The bucket lock is selected based on the hash and protects mutations
* on a group of hash buckets.
*
goto out;
}
+ err = -E2BIG;
+ if (unlikely(rht_grow_above_max(ht, tbl)))
+ goto out;
+
if (unlikely(rht_grow_above_100(ht, tbl))) {
slow_path:
spin_unlock_bh(lock);
#include <linux/errno.h>
#include <linux/nodemask.h>
#include <linux/mm_types.h>
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
#include <asm/page.h>
#include <asm/ptrace.h>
struct perf_event_context;
struct blk_plug;
struct filename;
+struct nameidata;
#define VMACACHE_BITS 2
#define VMACACHE_SIZE (1U << VMACACHE_BITS)
extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
extern void calc_global_load(unsigned long ticks);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void update_cpu_load_nohz(void);
+#else
+static inline void update_cpu_load_nohz(void) { }
+#endif
extern unsigned long get_parent_ip(unsigned long addr);
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
#define TASK_PARKED 512
-#define TASK_STATE_MAX 1024
+#define TASK_NOLOAD 1024
+#define TASK_STATE_MAX 2048
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN"
extern char ___assert_task_state[1 - 2*!!(
sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
#define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED)
+#define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
+
/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
- (task->flags & PF_FROZEN) == 0)
+ (task->flags & PF_FROZEN) == 0 && \
+ (task->state & TASK_NOLOAD) == 0)
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
#define set_task_state(tsk, state_value) \
do { \
(tsk)->task_state_change = _THIS_IP_; \
- set_mb((tsk)->state, (state_value)); \
+ smp_store_mb((tsk)->state, (state_value)); \
} while (0)
/*
#define set_current_state(state_value) \
do { \
current->task_state_change = _THIS_IP_; \
- set_mb(current->state, (state_value)); \
+ smp_store_mb(current->state, (state_value)); \
} while (0)
#else
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value) \
- set_mb((tsk)->state, (state_value))
+ smp_store_mb((tsk)->state, (state_value))
/*
* set_current_state() includes a barrier so that the write of current->state
#define __set_current_state(state_value) \
do { current->state = (state_value); } while (0)
#define set_current_state(state_value) \
- set_mb(current->state, (state_value))
+ smp_store_mb(current->state, (state_value))
#endif
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void nohz_balance_enter_idle(int cpu);
extern void set_cpu_sd_state_idle(void);
-extern int get_nohz_timer_target(int pinned);
+extern int get_nohz_timer_target(void);
#else
static inline void nohz_balance_enter_idle(int cpu) { }
static inline void set_cpu_sd_state_idle(void) { }
-static inline int get_nohz_timer_target(int pinned)
-{
- return smp_processor_id();
-}
#endif
/*
.sum_exec_runtime = 0, \
}
+/*
+ * This is the atomic variant of task_cputime, which can be used for
+ * storing and updating task_cputime statistics without locking.
+ */
+struct task_cputime_atomic {
+ atomic64_t utime;
+ atomic64_t stime;
+ atomic64_t sum_exec_runtime;
+};
+
+#define INIT_CPUTIME_ATOMIC \
+ (struct task_cputime_atomic) { \
+ .utime = ATOMIC64_INIT(0), \
+ .stime = ATOMIC64_INIT(0), \
+ .sum_exec_runtime = ATOMIC64_INIT(0), \
+ }
+
#ifdef CONFIG_PREEMPT_COUNT
#define PREEMPT_DISABLED (1 + PREEMPT_ENABLED)
#else
/**
* struct thread_group_cputimer - thread group interval timer counts
- * @cputime: thread group interval timers.
+ * @cputime_atomic: atomic thread group interval timers.
* @running: non-zero when there are timers running and
* @cputime receives updates.
- * @lock: lock for fields in this struct.
*
* This structure contains the version of task_cputime, above, that is
* used for thread group CPU timer calculations.
*/
struct thread_group_cputimer {
- struct task_cputime cputime;
+ struct task_cputime_atomic cputime_atomic;
int running;
- raw_spinlock_t lock;
};
#include <linux/rwsem.h>
#define SCHED_CAPACITY_SHIFT 10
#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT)
+/*
+ * Wake-queues are lists of tasks with a pending wakeup, whose
+ * callers have already marked the task as woken internally,
+ * and can thus carry on. A common use case is being able to
+ * do the wakeups once the corresponding user lock as been
+ * released.
+ *
+ * We hold reference to each task in the list across the wakeup,
+ * thus guaranteeing that the memory is still valid by the time
+ * the actual wakeups are performed in wake_up_q().
+ *
+ * One per task suffices, because there's never a need for a task to be
+ * in two wake queues simultaneously; it is forbidden to abandon a task
+ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
+ * already in a wake queue, the wakeup will happen soon and the second
+ * waker can just skip it.
+ *
+ * The WAKE_Q macro declares and initializes the list head.
+ * wake_up_q() does NOT reinitialize the list; it's expected to be
+ * called near the end of a function, where the fact that the queue is
+ * not used again will be easy to see by inspection.
+ *
+ * Note that this can cause spurious wakeups. schedule() callers
+ * must ensure the call is done inside a loop, confirming that the
+ * wakeup condition has in fact occurred.
+ */
+struct wake_q_node {
+ struct wake_q_node *next;
+};
+
+struct wake_q_head {
+ struct wake_q_node *first;
+ struct wake_q_node **lastp;
+};
+
+#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
+
+#define WAKE_Q(name) \
+ struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+
+extern void wake_q_add(struct wake_q_head *head,
+ struct task_struct *task);
+extern void wake_up_q(struct wake_q_head *head);
+
/*
* sched-domains (multiprocessor balancing) declarations:
*/
int rcu_read_lock_nesting;
union rcu_special rcu_read_unlock_special;
struct list_head rcu_node_entry;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_PREEMPT_RCU
struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TASKS_RCU
#endif
struct mm_struct *mm, *active_mm;
-#ifdef CONFIG_COMPAT_BRK
- unsigned brk_randomized:1;
-#endif
/* per-thread vma caching */
u32 vmacache_seqnum;
struct vm_area_struct *vmacache[VMACACHE_SIZE];
int exit_state;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
- unsigned int jobctl; /* JOBCTL_*, siglock protected */
+ unsigned long jobctl; /* JOBCTL_*, siglock protected */
/* Used for emulating ABI behavior of previous Linux versions */
unsigned int personality;
/* Revert to default priority/policy when forking */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
+ unsigned sched_migrated:1;
#ifdef CONFIG_MEMCG_KMEM
unsigned memcg_kmem_skip_account:1;
#endif
+#ifdef CONFIG_COMPAT_BRK
+ unsigned brk_randomized:1;
+#endif
unsigned long atomic_flags; /* Flags needing atomic access. */
it with task_lock())
- initialized normally by setup_new_exec */
/* file system info */
- int link_count, total_link_count;
+ struct nameidata *nameidata;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
struct sysv_sem sysvsem;
/* Protection of the PI data structures: */
raw_spinlock_t pi_lock;
+ struct wake_q_node wake_q;
+
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task */
struct rb_root pi_waiters;
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
unsigned long task_state_change;
#endif
+ int pagefault_disabled;
};
/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */
#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */
-#define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT)
-#define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT)
-#define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT)
-#define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT)
-#define JOBCTL_TRAP_NOTIFY (1 << JOBCTL_TRAP_NOTIFY_BIT)
-#define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT)
-#define JOBCTL_LISTENING (1 << JOBCTL_LISTENING_BIT)
+#define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP (1UL << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY (1UL << JOBCTL_TRAP_NOTIFY_BIT)
+#define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT)
#define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
extern bool task_set_jobctl_pending(struct task_struct *task,
- unsigned int mask);
+ unsigned long mask);
extern void task_clear_jobctl_trapping(struct task_struct *task);
extern void task_clear_jobctl_pending(struct task_struct *task,
- unsigned int mask);
+ unsigned long mask);
static inline void rcu_copy_process(struct task_struct *p)
{
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
-static inline void thread_group_cputime_init(struct signal_struct *sig)
-{
- raw_spin_lock_init(&sig->cputimer.lock);
-}
-
/*
* Reevaluate whether the task has signals pending delivery.
* Wake the task if so.
static inline unsigned long task_rlimit(const struct task_struct *tsk,
unsigned int limit)
{
- return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
+ return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
}
static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
unsigned int limit)
{
- return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
+ return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
}
static inline unsigned long rlimit(unsigned int limit)
#ifdef CONFIG_RT_MUTEXES
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern int rt_mutex_check_prio(struct task_struct *task, int newprio);
+extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio);
extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
extern void rt_mutex_adjust_pi(struct task_struct *p);
static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
return p->normal_prio;
}
-static inline int rt_mutex_check_prio(struct task_struct *task, int newprio)
+static inline int rt_mutex_get_effective_prio(struct task_struct *task,
+ int newprio)
{
- return 0;
+ return newprio;
}
static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;
extern unsigned int sysctl_sched_time_avg;
-extern unsigned int sysctl_timer_migration;
extern unsigned int sysctl_sched_shares_window;
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
loff_t *ppos);
#endif
-#ifdef CONFIG_SCHED_DEBUG
-static inline unsigned int get_sysctl_timer_migration(void)
-{
- return sysctl_timer_migration;
-}
-#else
-static inline unsigned int get_sysctl_timer_migration(void)
-{
- return 1;
-}
-#endif
/*
* control realtime throttling:
struct vfsmount;
struct path;
struct qstr;
-struct nameidata;
struct iattr;
struct fown_struct;
struct file_operations;
* @inode_follow_link:
* Check permission to follow a symbolic link when looking up a pathname.
* @dentry contains the dentry structure for the link.
- * @nd contains the nameidata structure for the parent directory.
+ * @inode contains the inode, which itself is not stable in RCU-walk
+ * @rcu indicates whether we are in RCU-walk mode.
* Return 0 if permission is granted.
* @inode_permission:
* Check permission before accessing an inode. This hook is called by the
int (*inode_rename) (struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry);
int (*inode_readlink) (struct dentry *dentry);
- int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd);
+ int (*inode_follow_link) (struct dentry *dentry, struct inode *inode,
+ bool rcu);
int (*inode_permission) (struct inode *inode, int mask);
int (*inode_setattr) (struct dentry *dentry, struct iattr *attr);
int (*inode_getattr) (const struct path *path);
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags);
int security_inode_readlink(struct dentry *dentry);
-int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd);
+int security_inode_follow_link(struct dentry *dentry, struct inode *inode,
+ bool rcu);
int security_inode_permission(struct inode *inode, int mask);
int security_inode_setattr(struct dentry *dentry, struct iattr *attr);
int security_inode_getattr(const struct path *path);
}
static inline int security_inode_follow_link(struct dentry *dentry,
- struct nameidata *nd)
+ struct inode *inode,
+ bool rcu)
{
return 0;
}
s->sequence++;
}
+/**
+ * raw_write_seqcount_barrier - do a seq write barrier
+ * @s: pointer to seqcount_t
+ *
+ * This can be used to provide an ordering guarantee instead of the
+ * usual consistency guarantee. It is one wmb cheaper, because we can
+ * collapse the two back-to-back wmb()s.
+ *
+ * seqcount_t seq;
+ * bool X = true, Y = false;
+ *
+ * void read(void)
+ * {
+ * bool x, y;
+ *
+ * do {
+ * int s = read_seqcount_begin(&seq);
+ *
+ * x = X; y = Y;
+ *
+ * } while (read_seqcount_retry(&seq, s));
+ *
+ * BUG_ON(!x && !y);
+ * }
+ *
+ * void write(void)
+ * {
+ * Y = true;
+ *
+ * raw_write_seqcount_barrier(seq);
+ *
+ * X = false;
+ * }
+ */
+static inline void raw_write_seqcount_barrier(seqcount_t *s)
+{
+ s->sequence++;
+ smp_wmb();
+ s->sequence++;
+}
+
/*
* raw_write_seqcount_latch - redirect readers to even/odd copy
* @s: pointer to seqcount_t
}
/**
- * write_seqcount_barrier - invalidate in-progress read-side seq operations
+ * write_seqcount_invalidate - invalidate in-progress read-side seq operations
* @s: pointer to seqcount_t
*
- * After write_seqcount_barrier, no read-side seq operations will complete
+ * After write_seqcount_invalidate, no read-side seq operations will complete
* successfully and see data older than this.
*/
-static inline void write_seqcount_barrier(seqcount_t *s)
+static inline void write_seqcount_invalidate(seqcount_t *s)
{
smp_wmb();
s->sequence+=2;
struct net_device *physindev;
struct net_device *physoutdev;
char neigh_header[8];
+ __be32 ipv4_daddr;
};
#endif
/*
* Despite its name it doesn't necessarily has to be a full barrier.
* It should only guarantee that a STORE before the critical section
- * can not be reordered with a LOAD inside this section.
+ * can not be reordered with LOADs and STOREs inside this section.
* spin_lock() is the one-way barrier, this LOAD can not escape out
* of the region. So the default implementation simply ensures that
* a STORE can not move into the critical section, smp_wmb() should
* read the code and the spec side by side (and laugh ...)
* See RFC793 and RFC1122. The RFC writes these in capitals.
*/
+ u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived
+ * sum(delta(rcv_nxt)), or how many bytes
+ * were acked.
+ */
u32 rcv_nxt; /* What we want to receive next */
u32 copied_seq; /* Head of yet unread data */
u32 rcv_wup; /* rcv_nxt on last window update sent */
u32 snd_nxt; /* Next sequence we send */
+ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
+ * sum(delta(snd_una)), or how many bytes
+ * were acked.
+ */
+ struct u64_stats_sync syncp; /* protects 64bit vars (cf tcp_get_info()) */
+
u32 snd_una; /* First byte we want an ack for */
u32 snd_sml; /* Last byte of the most recently transmitted small packet */
u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */
#define _LINUX_TIME64_H
#include <uapi/linux/time.h>
+#include <linux/math64.h>
typedef __s64 time64_t;
#define FSEC_PER_SEC 1000000000000000LL
/* Located here for timespec[64]_valid_strict */
+#define TIME64_MAX ((s64)~((u64)1 << 63))
#define KTIME_MAX ((s64)~((u64)1 << 63))
#define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC)
* @offs_boot: Offset clock monotonic -> clock boottime
* @offs_tai: Offset clock monotonic -> clock tai
* @tai_offset: The current UTC to TAI offset in seconds
+ * @clock_was_set_seq: The sequence number of clock was set events
+ * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second
* @raw_time: Monotonic raw base time in timespec64 format
* @cycle_interval: Number of clock cycles in one NTP interval
* @xtime_interval: Number of clock shifted nano seconds in one NTP
* shifted nano seconds.
* @ntp_error_shift: Shift conversion between clock shifted nano seconds and
* ntp shifted nano seconds.
+ * @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING)
+ * @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING)
+ * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING)
*
* Note: For timespec(64) based interfaces wall_to_monotonic is what
* we need to add to xtime (or xtime corrected for sub jiffie times)
ktime_t offs_boot;
ktime_t offs_tai;
s32 tai_offset;
+ unsigned int clock_was_set_seq;
+ ktime_t next_leap_ktime;
struct timespec64 raw_time;
/* The following members are for timekeeping internal use */
s64 ntp_error;
u32 ntp_error_shift;
u32 ntp_err_mult;
+#ifdef CONFIG_DEBUG_TIMEKEEPING
+ long last_warning;
+ /*
+ * These simple flag variables are managed
+ * without locks, which is racy, but they are
+ * ok since we don't really care about being
+ * super precise about how many events were
+ * seen, just that a problem was observed.
+ */
+ int underflow_seen;
+ int overflow_seen;
+#endif
};
#ifdef CONFIG_GENERIC_TIME_VSYSCALL
extern ktime_t ktime_get_with_offset(enum tk_offsets offs);
extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs);
extern ktime_t ktime_get_raw(void);
+extern u32 ktime_get_resolution_ns(void);
/**
* ktime_get_real - get the real (wall-) time in ktime_t format
extern void read_persistent_clock(struct timespec *ts);
extern void read_persistent_clock64(struct timespec64 *ts);
-extern void read_boot_clock(struct timespec *ts);
extern void read_boot_clock64(struct timespec64 *ts);
extern int update_persistent_clock(struct timespec now);
extern int update_persistent_clock64(struct timespec64 now);
* All fields that change during normal runtime grouped to the
* same cacheline
*/
- struct list_head entry;
- unsigned long expires;
- struct tvec_base *base;
-
- void (*function)(unsigned long);
- unsigned long data;
-
- int slack;
+ struct hlist_node entry;
+ unsigned long expires;
+ void (*function)(unsigned long);
+ unsigned long data;
+ u32 flags;
+ int slack;
#ifdef CONFIG_TIMER_STATS
- int start_pid;
- void *start_site;
- char start_comm[16];
+ int start_pid;
+ void *start_site;
+ char start_comm[16];
#endif
#ifdef CONFIG_LOCKDEP
- struct lockdep_map lockdep_map;
+ struct lockdep_map lockdep_map;
#endif
};
-extern struct tvec_base boot_tvec_bases;
-
#ifdef CONFIG_LOCKDEP
/*
* NB: because we have to copy the lockdep_map, setting the lockdep_map key
#endif
/*
- * Note that all tvec_bases are at least 4 byte aligned and lower two bits
- * of base in timer_list is guaranteed to be zero. Use them for flags.
- *
* A deferrable timer will work normally when the system is busy, but
* will not cause a CPU to come out of idle just to service it; instead,
* the timer will be serviced when the CPU eventually wakes up with a
* workqueue locking issues. It's not meant for executing random crap
* with interrupts disabled. Abuse is monitored!
*/
-#define TIMER_DEFERRABLE 0x1LU
-#define TIMER_IRQSAFE 0x2LU
-
-#define TIMER_FLAG_MASK 0x3LU
+#define TIMER_CPUMASK 0x0007FFFF
+#define TIMER_MIGRATING 0x00080000
+#define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING)
+#define TIMER_DEFERRABLE 0x00100000
+#define TIMER_IRQSAFE 0x00200000
#define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \
- .entry = { .prev = TIMER_ENTRY_STATIC }, \
+ .entry = { .next = TIMER_ENTRY_STATIC }, \
.function = (_function), \
.expires = (_expires), \
.data = (_data), \
- .base = (void *)((unsigned long)&boot_tvec_bases + (_flags)), \
+ .flags = (_flags), \
.slack = -1, \
__TIMER_LOCKDEP_MAP_INITIALIZER( \
__FILE__ ":" __stringify(__LINE__)) \
*/
static inline int timer_pending(const struct timer_list * timer)
{
- return timer->entry.next != NULL;
+ return timer->entry.pprev != NULL;
}
extern void add_timer_on(struct timer_list *timer, int cpu);
*/
#define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1)
-/*
- * Return when the next timer-wheel timeout occurs (in absolute jiffies),
- * locks the timer base and does the comparison against the given
- * jiffie.
- */
-extern unsigned long get_next_timer_interrupt(unsigned long now);
-
/*
* Timer-statistics info:
*/
extern int timer_stats_active;
-#define TIMER_STATS_FLAG_DEFERRABLE 0x1
-
extern void init_timer_stats(void);
extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
- void *timerf, char *comm,
- unsigned int timer_flag);
+ void *timerf, char *comm, u32 flags);
extern void __timer_stats_timer_set_start_info(struct timer_list *timer,
void *addr);
struct hrtimer;
extern enum hrtimer_restart it_real_fn(struct hrtimer *);
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#include <linux/sysctl.h>
+
+extern unsigned int sysctl_timer_migration;
+int timer_migration_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
+#endif
+
unsigned long __round_jiffies(unsigned long j, int cpu);
unsigned long __round_jiffies_relative(unsigned long j, int cpu);
unsigned long round_jiffies(unsigned long j);
};
-extern void timerqueue_add(struct timerqueue_head *head,
- struct timerqueue_node *node);
-extern void timerqueue_del(struct timerqueue_head *head,
- struct timerqueue_node *node);
+extern bool timerqueue_add(struct timerqueue_head *head,
+ struct timerqueue_node *node);
+extern bool timerqueue_del(struct timerqueue_head *head,
+ struct timerqueue_node *node);
extern struct timerqueue_node *timerqueue_iterate_next(
struct timerqueue_node *node);
#ifndef topology_core_id
#define topology_core_id(cpu) ((void)(cpu), 0)
#endif
-#ifndef topology_thread_cpumask
-#define topology_thread_cpumask(cpu) cpumask_of(cpu)
+#ifndef topology_sibling_cpumask
+#define topology_sibling_cpumask(cpu) cpumask_of(cpu)
#endif
#ifndef topology_core_cpumask
#define topology_core_cpumask(cpu) cpumask_of(cpu)
#ifdef CONFIG_SCHED_SMT
static inline const struct cpumask *cpu_smt_mask(int cpu)
{
- return topology_thread_cpumask(cpu);
+ return topology_sibling_cpumask(cpu);
}
#endif
#define TTY_EXCLUSIVE 3 /* Exclusive open mode */
#define TTY_DEBUG 4 /* Debugging */
#define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */
+#define TTY_OTHER_DONE 6 /* Closed pty has completed input processing */
#define TTY_LDISC_OPEN 11 /* Line discipline is open */
#define TTY_PTY_LOCK 16 /* pty private */
#define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */
extern void do_SAK(struct tty_struct *tty);
extern void __do_SAK(struct tty_struct *tty);
extern void no_tty(void);
-extern void tty_flush_to_ldisc(struct tty_struct *tty);
extern void tty_buffer_free_all(struct tty_port *port);
extern void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld);
extern void tty_buffer_init(struct tty_port *port);
#ifndef __LINUX_UACCESS_H__
#define __LINUX_UACCESS_H__
-#include <linux/preempt.h>
+#include <linux/sched.h>
#include <asm/uaccess.h>
+static __always_inline void pagefault_disabled_inc(void)
+{
+ current->pagefault_disabled++;
+}
+
+static __always_inline void pagefault_disabled_dec(void)
+{
+ current->pagefault_disabled--;
+ WARN_ON(current->pagefault_disabled < 0);
+}
+
/*
- * These routines enable/disable the pagefault handler in that
- * it will not take any locks and go straight to the fixup table.
+ * These routines enable/disable the pagefault handler. If disabled, it will
+ * not take any locks and go straight to the fixup table.
*
- * They have great resemblance to the preempt_disable/enable calls
- * and in fact they are identical; this is because currently there is
- * no other way to make the pagefault handlers do this. So we do
- * disable preemption but we don't necessarily care about that.
+ * User access methods will not sleep when called from a pagefault_disabled()
+ * environment.
*/
static inline void pagefault_disable(void)
{
- preempt_count_inc();
+ pagefault_disabled_inc();
/*
* make sure to have issued the store before a pagefault
* can hit.
static inline void pagefault_enable(void)
{
-#ifndef CONFIG_PREEMPT
/*
* make sure to issue those last loads/stores before enabling
* the pagefault handler again.
*/
barrier();
- preempt_count_dec();
-#else
- preempt_enable();
-#endif
+ pagefault_disabled_dec();
}
+/*
+ * Is the pagefault handler disabled? If so, user access methods will not sleep.
+ */
+#define pagefault_disabled() (current->pagefault_disabled != 0)
+
+/*
+ * The pagefault handler is in general disabled by pagefault_disable() or
+ * when in irq context (via in_atomic()).
+ *
+ * This function should only be used by the fault handlers. Other users should
+ * stick to pagefault_disabled().
+ * Please NEVER use preempt_disable() to disable the fault handler. With
+ * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled.
+ * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT.
+ */
+#define faulthandler_disabled() (pagefault_disabled() || in_atomic())
+
#ifndef ARCH_HAS_NOCACHE_UACCESS
static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
static inline bool uid_valid(kuid_t uid)
{
- return !uid_eq(uid, INVALID_UID);
+ return __kuid_val(uid) != (uid_t) -1;
}
static inline bool gid_valid(kgid_t gid)
{
- return !gid_eq(gid, INVALID_GID);
+ return __kgid_val(gid) != (gid_t) -1;
}
#ifdef CONFIG_USER_NS
* on that signal.
*/
static inline int
-wait_on_bit(void *word, int bit, unsigned mode)
+wait_on_bit(unsigned long *word, int bit, unsigned mode)
{
might_sleep();
if (!test_bit(bit, word))
* on that signal.
*/
static inline int
-wait_on_bit_io(void *word, int bit, unsigned mode)
+wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
{
might_sleep();
if (!test_bit(bit, word))
* received a signal and the mode permitted wakeup on that signal.
*/
static inline int
-wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout)
+wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
+ unsigned long timeout)
{
might_sleep();
if (!test_bit(bit, word))
* on that signal.
*/
static inline int
-wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
+wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
+ unsigned mode)
{
might_sleep();
if (!test_bit(bit, word))
* the @mode allows that signal to wake the process.
*/
static inline int
-wait_on_bit_lock(void *word, int bit, unsigned mode)
+wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
{
might_sleep();
if (!test_and_set_bit(bit, word))
* the @mode allows that signal to wake the process.
*/
static inline int
-wait_on_bit_lock_io(void *word, int bit, unsigned mode)
+wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode)
{
might_sleep();
if (!test_and_set_bit(bit, word))
* the @mode allows that signal to wake the process.
*/
static inline int
-wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
+wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
+ unsigned mode)
{
might_sleep();
if (!test_and_set_bit(bit, word))
struct cfg802154_ops {
struct net_device * (*add_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
const char *name,
+ unsigned char name_assign_type,
int type);
void (*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
struct net_device *dev);
int (*add_virtual_intf)(struct wpan_phy *wpan_phy,
const char *name,
+ unsigned char name_assign_type,
enum nl802154_iftype type,
__le64 extended_addr);
int (*del_virtual_intf)(struct wpan_phy *wpan_phy,
* struct codel_params - contains codel parameters
* @target: target queue size (in time units)
* @interval: width of moving time window
+ * @mtu: device mtu, or minimal queue backlog in bytes.
* @ecn: is Explicit Congestion Notification enabled
*/
struct codel_params {
codel_time_t target;
codel_time_t interval;
+ u32 mtu;
bool ecn;
};
u32 ecn_mark;
};
-static void codel_params_init(struct codel_params *params)
+static void codel_params_init(struct codel_params *params,
+ const struct Qdisc *sch)
{
params->interval = MS2TIME(100);
params->target = MS2TIME(5);
+ params->mtu = psched_mtu(qdisc_dev(sch));
params->ecn = false;
}
static void codel_stats_init(struct codel_stats *stats)
{
- stats->maxpacket = 256;
+ stats->maxpacket = 0;
}
/*
stats->maxpacket = qdisc_pkt_len(skb);
if (codel_time_before(vars->ldelay, params->target) ||
- sch->qstats.backlog <= stats->maxpacket) {
+ sch->qstats.backlog <= params->mtu) {
/* went below - stay below for at least interval */
vars->first_above_time = 0;
return false;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
- __u8 icsk_ca_state:7,
+ __u8 icsk_ca_state:6,
+ icsk_ca_setsockopt:1,
icsk_ca_dst_locked:1;
__u8 icsk_retransmits;
__u8 icsk_pending;
u32 probe_timestamp;
} icsk_mtup;
- u32 icsk_ca_priv[16];
u32 icsk_user_timeout;
-#define ICSK_CA_PRIV_SIZE (16 * sizeof(u32))
+
+ u64 icsk_ca_priv[64 / sizeof(u64)];
+#define ICSK_CA_PRIV_SIZE (8 * sizeof(u64))
};
#define ICSK_TIME_RETRANS 1 /* Retransmit timer */
};
/**
- * enum ieee80211_rssi_event - data attached to an %RSSI_EVENT
+ * struct ieee80211_rssi_event - data attached to an %RSSI_EVENT
* @data: See &enum ieee80211_rssi_event_data
*/
struct ieee80211_rssi_event {
};
/**
- * enum ieee80211_mlme_event - data attached to an %MLME_EVENT
+ * struct ieee80211_mlme_event - data attached to an %MLME_EVENT
* @data: See &enum ieee80211_mlme_event_data
* @status: See &enum ieee80211_mlme_event_status
* @reason: the reason code if applicable
/**
* struct ieee80211_event - event to be sent to the driver
- * @type The event itself. See &enum ieee80211_event_type.
+ * @type: The event itself. See &enum ieee80211_event_type.
* @rssi: relevant if &type is %RSSI_EVENT
* @mlme: relevant if &type is %AUTH_EVENT
+ * @u: union holding the above two fields
*/
struct ieee80211_event {
enum ieee80211_event_type type;
* @sta: station table entry, %NULL for per-vif queue
* @tid: the TID for this queue (unused for per-vif queue)
* @ac: the AC for this queue
+ * @drv_priv: data area for driver use, will always be aligned to
+ * sizeof(void *).
*
* The driver can obtain packets from this queue by calling
* ieee80211_tx_dequeue().
__put_unaligned_memmove64(swab64p(le64_src), be64_dst);
}
-/* Basic interface to register ieee802154 device */
+/**
+ * ieee802154_alloc_hw - Allocate a new hardware device
+ *
+ * This must be called once for each hardware device. The returned pointer
+ * must be used to refer to this device when calling other functions.
+ * mac802154 allocates a private data area for the driver pointed to by
+ * @priv in &struct ieee802154_hw, the size of this area is given as
+ * @priv_data_len.
+ *
+ * @priv_data_len: length of private data
+ * @ops: callbacks for this device
+ *
+ * Return: A pointer to the new hardware device, or %NULL on error.
+ */
struct ieee802154_hw *
ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops);
+
+/**
+ * ieee802154_free_hw - free hardware descriptor
+ *
+ * This function frees everything that was allocated, including the
+ * private data for the driver. You must call ieee802154_unregister_hw()
+ * before calling this function.
+ *
+ * @hw: the hardware to free
+ */
void ieee802154_free_hw(struct ieee802154_hw *hw);
+
+/**
+ * ieee802154_register_hw - Register hardware device
+ *
+ * You must call this function before any other functions in
+ * mac802154. Note that before a hardware can be registered, you
+ * need to fill the contained wpan_phy's information.
+ *
+ * @hw: the device to register as returned by ieee802154_alloc_hw()
+ *
+ * Return: 0 on success. An error code otherwise.
+ */
int ieee802154_register_hw(struct ieee802154_hw *hw);
+
+/**
+ * ieee802154_unregister_hw - Unregister a hardware device
+ *
+ * This function instructs mac802154 to free allocated resources
+ * and unregister netdevices from the networking subsystem.
+ *
+ * @hw: the hardware to unregister
+ */
void ieee802154_unregister_hw(struct ieee802154_hw *hw);
+/**
+ * ieee802154_rx - receive frame
+ *
+ * Use this function to hand received frames to mac802154. The receive
+ * buffer in @skb must start with an IEEE 802.15.4 header. In case of a
+ * paged @skb is used, the driver is recommended to put the ieee802154
+ * header of the frame on the linear part of the @skb to avoid memory
+ * allocation and/or memcpy by the stack.
+ *
+ * This function may not be called in IRQ context. Calls to this function
+ * for a single hardware must be synchronized against each other.
+ *
+ * @hw: the hardware this frame came in on
+ * @skb: the buffer to receive, owned by mac802154 after this call
+ */
void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb);
+
+/**
+ * ieee802154_rx_irqsafe - receive frame
+ *
+ * Like ieee802154_rx() but can be called in IRQ context
+ * (internally defers to a tasklet.)
+ *
+ * @hw: the hardware this frame came in on
+ * @skb: the buffer to receive, owned by mac802154 after this call
+ * @lqi: link quality indicator
+ */
void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb,
u8 lqi);
-
+/**
+ * ieee802154_wake_queue - wake ieee802154 queue
+ * @hw: pointer as obtained from ieee802154_alloc_hw().
+ *
+ * Drivers should use this function instead of netif_wake_queue.
+ */
void ieee802154_wake_queue(struct ieee802154_hw *hw);
+
+/**
+ * ieee802154_stop_queue - stop ieee802154 queue
+ * @hw: pointer as obtained from ieee802154_alloc_hw().
+ *
+ * Drivers should use this function instead of netif_stop_queue.
+ */
void ieee802154_stop_queue(struct ieee802154_hw *hw);
+
+/**
+ * ieee802154_xmit_complete - frame transmission complete
+ *
+ * @hw: pointer as obtained from ieee802154_alloc_hw().
+ * @skb: buffer for transmission
+ * @ifs_handling: indicate interframe space handling
+ */
void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb,
bool ifs_handling);
/* Map v4 address to v4-mapped v6 address */
static inline void sctp_v4_map_v6(union sctp_addr *addr)
{
+ __be16 port;
+
+ port = addr->v4.sin_port;
+ addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
+ addr->v6.sin6_port = port;
addr->v6.sin6_family = AF_INET6;
addr->v6.sin6_flowinfo = 0;
addr->v6.sin6_scope_id = 0;
- addr->v6.sin6_port = addr->v4.sin_port;
- addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
addr->v6.sin6_addr.s6_addr32[0] = 0;
addr->v6.sin6_addr.s6_addr32[1] = 0;
addr->v6.sin6_addr.s6_addr32[2] = htonl(0x0000ffff);
}
/* tcp.c */
-void tcp_get_info(const struct sock *, struct tcp_info *);
+void tcp_get_info(struct sock *, struct tcp_info *);
/* Read 'sendfile()'-style from a TCP socket */
typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
/* Requires ECN/ECT set on all packets */
#define TCP_CONG_NEEDS_ECN 0x2
+union tcp_cc_info;
+
struct tcp_congestion_ops {
struct list_head list;
u32 key;
/* hook for packet ack accounting (optional) */
void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us);
/* get info for inet_diag (optional) */
- int (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);
+ size_t (*get_info)(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info);
char name[TCP_CA_NAME_MAX];
struct module *owner;
}
/* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */
-static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
+static inline void rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
{
if (ipv6_addr_v4mapped((struct in6_addr *)gid)) {
struct sockaddr_in *out_in = (struct sockaddr_in *)out;
out_in->sin6_family = AF_INET6;
memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16);
}
- return 0;
}
static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE = 216,
IB_CM_SIDR_REP_PRIVATE_DATA_SIZE = 136,
IB_CM_SIDR_REP_INFO_LENGTH = 72,
- IB_CM_COMPARE_SIZE = 64
+ /* compare done u32 at a time */
+ IB_CM_COMPARE_SIZE = (64 / sizeof(u32))
};
struct ib_cm_id;
#define IB_SDP_SERVICE_ID_MASK cpu_to_be64(0xFFFFFFFFFFFF0000ULL)
struct ib_cm_compare_data {
- u8 data[IB_CM_COMPARE_SIZE];
- u8 mask[IB_CM_COMPARE_SIZE];
+ u32 data[IB_CM_COMPARE_SIZE];
+ u32 mask[IB_CM_COMPARE_SIZE];
};
/**
*/
int iwpm_add_and_query_mapping_cb(struct sk_buff *, struct netlink_callback *);
+/**
+ * iwpm_remote_info_cb - Process remote connecting peer address info, which
+ * the port mapper has received from the connecting peer
+ *
+ * @cb: Contains the received message (payload and netlink header)
+ *
+ * Stores the IPv4/IPv6 address info in a hash table
+ */
+int iwpm_remote_info_cb(struct sk_buff *, struct netlink_callback *);
+
/**
* iwpm_mapping_error_cb - Process port mapper notification for error
*
*/
int iwpm_ack_mapping_info_cb(struct sk_buff *, struct netlink_callback *);
+/**
+ * iwpm_get_remote_info - Get the remote connecting peer address info
+ *
+ * @mapped_loc_addr: Mapped local address of the listening peer
+ * @mapped_rem_addr: Mapped remote address of the connecting peer
+ * @remote_addr: To store the remote address of the connecting peer
+ * @nl_client: The index of the netlink client
+ *
+ * The remote address info is retrieved and provided to the client in
+ * the remote_addr. After that it is removed from the hash table
+ */
+int iwpm_get_remote_info(struct sockaddr_storage *mapped_loc_addr,
+ struct sockaddr_storage *mapped_rem_addr,
+ struct sockaddr_storage *remote_addr, u8 nl_client);
+
/**
* iwpm_create_mapinfo - Store local and mapped IPv4/IPv6 address
* info in a hash table
#include <sound/core.h>
#include <sound/hdaudio.h>
+#define AC_AMP_FAKE_MUTE 0x10 /* fake mute bit set to amp verbs */
+
int snd_hdac_regmap_init(struct hdac_device *codec);
void snd_hdac_regmap_exit(struct hdac_device *codec);
int snd_hdac_regmap_add_vendor_verb(struct hdac_device *codec,
#ifndef TARGET_CORE_BACKEND_H
#define TARGET_CORE_BACKEND_H
-#define TRANSPORT_PLUGIN_PHBA_PDEV 1
-#define TRANSPORT_PLUGIN_VHBA_PDEV 2
-#define TRANSPORT_PLUGIN_VHBA_VDEV 3
+#define TRANSPORT_FLAG_PASSTHROUGH 1
struct target_backend_cits {
struct config_item_type tb_dev_cit;
char inquiry_rev[4];
struct module *owner;
- u8 transport_type;
+ u8 transport_flags;
int (*attach_hba)(struct se_hba *, u32);
void (*detach_hba)(struct se_hba *);
int se_dev_set_max_sectors(struct se_device *, u32);
int se_dev_set_optimal_sectors(struct se_device *, u32);
int se_dev_set_block_size(struct se_device *, u32);
+sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
+ sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
#endif /* TARGET_CORE_BACKEND_H */
struct config_item *tf_fabric;
/* Passed from fabric modules */
struct config_item_type *tf_fabric_cit;
- /* Pointer to target core subsystem */
- struct configfs_subsystem *tf_subsys;
/* Pointer to fabric's struct module */
struct module *tf_module;
struct target_core_fabric_ops tf_ops;
struct target_core_fabric_ops {
struct module *module;
const char *name;
- struct configfs_subsystem *tf_subsys;
char *(*get_fabric_name)(void);
u8 (*get_fabric_proto_ident)(struct se_portal_group *);
char *(*tpg_get_wwn)(struct se_portal_group *);
int target_register_template(const struct target_core_fabric_ops *fo);
void target_unregister_template(const struct target_core_fabric_ops *fo);
+int target_depend_item(struct config_item *item);
+void target_undepend_item(struct config_item *item);
+
struct se_session *transport_init_session(enum target_prot_op);
int transport_alloc_session_tags(struct se_session *, unsigned int,
unsigned int);
TP_ARGS(call_site, ptr)
);
-DEFINE_EVENT(kmem_free, kmem_cache_free,
+DEFINE_EVENT_CONDITION(kmem_free, kmem_cache_free,
TP_PROTO(unsigned long call_site, const void *ptr),
- TP_ARGS(call_site, ptr)
+ TP_ARGS(call_site, ptr),
+
+ /*
+ * This trace can be potentially called from an offlined cpu.
+ * Since trace points use RCU and RCU should not be used from
+ * offline cpus, filter such calls out.
+ * While this trace can be called from a preemptable section,
+ * it has no impact on the condition since tasks can migrate
+ * only from online cpus to other online cpus. Thus its safe
+ * to use raw_smp_processor_id.
+ */
+ TP_CONDITION(cpu_online(raw_smp_processor_id()))
);
-TRACE_EVENT(mm_page_free,
+TRACE_EVENT_CONDITION(mm_page_free,
TP_PROTO(struct page *page, unsigned int order),
TP_ARGS(page, order),
+
+ /*
+ * This trace can be potentially called from an offlined cpu.
+ * Since trace points use RCU and RCU should not be used from
+ * offline cpus, filter such calls out.
+ * While this trace can be called from a preemptable section,
+ * it has no impact on the condition since tasks can migrate
+ * only from online cpus to other online cpus. Thus its safe
+ * to use raw_smp_processor_id.
+ */
+ TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
TP_STRUCT__entry(
__field( unsigned long, pfn )
__field( unsigned int, order )
TP_ARGS(page, order, migratetype)
);
-DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
+TRACE_EVENT_CONDITION(mm_page_pcpu_drain,
TP_PROTO(struct page *page, unsigned int order, int migratetype),
TP_ARGS(page, order, migratetype),
+ /*
+ * This trace can be potentially called from an offlined cpu.
+ * Since trace points use RCU and RCU should not be used from
+ * offline cpus, filter such calls out.
+ * While this trace can be called from a preemptable section,
+ * it has no impact on the condition since tasks can migrate
+ * only from online cpus to other online cpus. Thus its safe
+ * to use raw_smp_processor_id.
+ */
+ TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, pfn )
+ __field( unsigned int, order )
+ __field( int, migratetype )
+ ),
+
+ TP_fast_assign(
+ __entry->pfn = page ? page_to_pfn(page) : -1UL;
+ __entry->order = order;
+ __entry->migratetype = migratetype;
+ ),
+
TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
pfn_to_page(__entry->pfn), __entry->pfn,
__entry->order, __entry->migratetype)
__print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
{ 16, "Z" }, { 32, "X" }, { 64, "x" },
- { 128, "K" }, { 256, "W" }, { 512, "P" }) : "R",
+ { 128, "K" }, { 256, "W" }, { 512, "P" },
+ { 1024, "N" }) : "R",
__entry->prev_state & TASK_STATE_MAX ? "+" : "",
__entry->next_comm, __entry->next_pid, __entry->next_prio)
);
*/
TRACE_EVENT(timer_start,
- TP_PROTO(struct timer_list *timer, unsigned long expires),
+ TP_PROTO(struct timer_list *timer,
+ unsigned long expires,
+ unsigned int flags),
- TP_ARGS(timer, expires),
+ TP_ARGS(timer, expires, flags),
TP_STRUCT__entry(
__field( void *, timer )
__field( void *, function )
__field( unsigned long, expires )
__field( unsigned long, now )
+ __field( unsigned int, flags )
),
TP_fast_assign(
__entry->function = timer->function;
__entry->expires = expires;
__entry->now = jiffies;
+ __entry->flags = flags;
),
- TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld]",
+ TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] flags=0x%08x",
__entry->timer, __entry->function, __entry->expires,
- (long)__entry->expires - __entry->now)
+ (long)__entry->expires - __entry->now, __entry->flags)
);
/**
DEFINE_WRITEBACK_EVENT(writeback_nowork);
DEFINE_WRITEBACK_EVENT(writeback_wake_background);
DEFINE_WRITEBACK_EVENT(writeback_bdi_register);
-DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister);
DECLARE_EVENT_CLASS(wbc_class,
TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi),
#define RADEON_INFO_CURRENT_GPU_SCLK 0x22
#define RADEON_INFO_CURRENT_GPU_MCLK 0x23
#define RADEON_INFO_READ_REG 0x24
+#define RADEON_INFO_VA_UNMAP_WORKING 0x25
struct drm_radeon_info {
uint32_t request;
__u32 dctcp_ab_tot;
};
+union tcp_cc_info {
+ struct tcpvegas_info vegas;
+ struct tcp_dctcp_info dctcp;
+};
#endif /* _UAPI_INET_DIAG_H_ */
#define MPLS_LS_TTL_MASK 0x000000FF
#define MPLS_LS_TTL_SHIFT 0
+/* Reserved labels */
+#define MPLS_LABEL_IPV4NULL 0 /* RFC3032 */
+#define MPLS_LABEL_RTALERT 1 /* RFC3032 */
+#define MPLS_LABEL_IPV6NULL 2 /* RFC3032 */
+#define MPLS_LABEL_IMPLNULL 3 /* RFC3032 */
+#define MPLS_LABEL_ENTROPY 7 /* RFC6790 */
+#define MPLS_LABEL_GAL 13 /* RFC5586 */
+#define MPLS_LABEL_OAMALERT 14 /* RFC3429 */
+#define MPLS_LABEL_EXTENSION 15 /* RFC7274 */
+
#endif /* _UAPI_MPLS_H */
/* The field td_maxack has been set */
#define IP_CT_TCP_FLAG_MAXACK_SET 0x20
+/* Marks possibility for expected RFC5961 challenge ACK */
+#define IP_CT_EXP_CHALLENGE_ACK 0x40
+
struct nf_ct_tcp_flags {
__u8 flags;
__u8 mask;
PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */
PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */
+ PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */
PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */
};
PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT,
PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
+ PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
};
#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0)
#define PERF_RECORD_MISC_GUEST_USER (5 << 0)
+/*
+ * Indicates that /proc/PID/maps parsing are truncated by time out.
+ */
+#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12)
/*
* PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
* different events so can reuse the same bit position.
*/
PERF_RECORD_ITRACE_START = 12,
+ /*
+ * Records the dropped/lost sample number.
+ *
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u64 lost;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_LOST_SAMPLES = 13,
+
PERF_RECORD_MAX, /* non-ABI */
};
#define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */
#define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */
#define RTNH_F_ONLINK 4 /* Gateway is forced on link */
-#define RTNH_F_EXTERNAL 8 /* Route installed externally */
+#define RTNH_F_OFFLOAD 8 /* offloaded route */
/* Macros to handle hexthops */
#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */
#define TCP_TIMESTAMP 24
#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */
+#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */
struct tcp_repair_opt {
__u32 opt_code;
__u64 tcpi_pacing_rate;
__u64 tcpi_max_pacing_rate;
+ __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
+ __u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
};
/* for TCP_MD5SIG socket option */
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE. */
#include <linux/types.h>
+#include <linux/virtio_types.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
RDMA_NL_IWPM_ADD_MAPPING,
RDMA_NL_IWPM_QUERY_MAPPING,
RDMA_NL_IWPM_REMOVE_MAPPING,
+ RDMA_NL_IWPM_REMOTE_INFO,
RDMA_NL_IWPM_HANDLE_ERR,
RDMA_NL_IWPM_MAPINFO,
RDMA_NL_IWPM_MAPINFO_NUM,
irq_handler_t handler,
unsigned long irqflags, const char *devname,
void *dev_id);
-int bind_virq_to_irq(unsigned int virq, unsigned int cpu);
+int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu);
int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
irq_handler_t handler,
unsigned long irqflags, const char *devname,
menu "RCU Subsystem"
-choice
- prompt "RCU Implementation"
- default TREE_RCU
-
config TREE_RCU
- bool "Tree-based hierarchical RCU"
- depends on !PREEMPT && SMP
+ bool
+ default y if !PREEMPT && SMP
help
This option selects the RCU implementation that is
designed for very large SMP system with hundreds or
smaller systems.
config PREEMPT_RCU
- bool "Preemptible tree-based hierarchical RCU"
- depends on PREEMPT
+ bool
+ default y if PREEMPT
help
This option selects the RCU implementation that is
designed for very large SMP systems with hundreds or
Select this option if you are unsure.
config TINY_RCU
- bool "UP-only small-memory-footprint RCU"
- depends on !PREEMPT && !SMP
+ bool
+ default y if !PREEMPT && !SMP
help
This option selects the RCU implementation that is
designed for UP systems from which real-time response
is not required. This option greatly reduces the
memory footprint of RCU.
-endchoice
+config RCU_EXPERT
+ bool "Make expert-level adjustments to RCU configuration"
+ default n
+ help
+ This option needs to be enabled if you wish to make
+ expert-level adjustments to RCU configuration. By default,
+ no such adjustments can be made, which has the often-beneficial
+ side-effect of preventing "make oldconfig" from asking you all
+ sorts of detailed questions about how you would like numerous
+ obscure RCU options to be set up.
+
+ Say Y if you need to make expert-level adjustments to RCU.
+
+ Say N if you are unsure.
config SRCU
bool
sections.
config TASKS_RCU
- bool "Task_based RCU implementation using voluntary context switch"
+ bool
default n
select SRCU
help
only voluntary context switch (not preemption!), idle, and
user-mode execution as quiescent states.
- If unsure, say N.
-
config RCU_STALL_COMMON
def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
help
bool
config RCU_USER_QS
- bool "Consider userspace as in RCU extended quiescent state"
- depends on HAVE_CONTEXT_TRACKING && SMP
- select CONTEXT_TRACKING
+ bool
help
This option sets hooks on kernel / userspace boundaries and
puts RCU in extended quiescent state when the CPU runs in
excluded from the global RCU state machine and thus doesn't
try to keep the timer tick on for RCU.
- Unless you want to hack and help the development of the full
- dynticks mode, you shouldn't enable this option. It also
- adds unnecessary overhead.
-
- If unsure say N
-
config CONTEXT_TRACKING_FORCE
bool "Force context tracking"
depends on CONTEXT_TRACKING
int "Tree-based hierarchical RCU fanout value"
range 2 64 if 64BIT
range 2 32 if !64BIT
- depends on TREE_RCU || PREEMPT_RCU
+ depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
default 64 if 64BIT
default 32 if !64BIT
help
config RCU_FANOUT_LEAF
int "Tree-based hierarchical RCU leaf-level fanout value"
- range 2 RCU_FANOUT if 64BIT
- range 2 RCU_FANOUT if !64BIT
- depends on TREE_RCU || PREEMPT_RCU
+ range 2 64 if 64BIT
+ range 2 32 if !64BIT
+ depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
default 16
help
This option controls the leaf-level fanout of hierarchical
Take the default if unsure.
-config RCU_FANOUT_EXACT
- bool "Disable tree-based hierarchical RCU auto-balancing"
- depends on TREE_RCU || PREEMPT_RCU
- default n
- help
- This option forces use of the exact RCU_FANOUT value specified,
- regardless of imbalances in the hierarchy. This is useful for
- testing RCU itself, and might one day be useful on systems with
- strong NUMA behavior.
-
- Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
-
- Say N if unsure.
-
config RCU_FAST_NO_HZ
bool "Accelerate last non-dyntick-idle CPU's grace periods"
- depends on NO_HZ_COMMON && SMP
+ depends on NO_HZ_COMMON && SMP && RCU_EXPERT
default n
help
This option permits CPUs to enter dynticks-idle state even if
config RCU_BOOST
bool "Enable RCU priority boosting"
- depends on RT_MUTEXES && PREEMPT_RCU
+ depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
default n
help
This option boosts the priority of preempted RCU readers that
range 0 99 if !RCU_BOOST
default 1 if RCU_BOOST
default 0 if !RCU_BOOST
+ depends on RCU_EXPERT
help
This option specifies the SCHED_FIFO priority value that will be
assigned to the rcuc/n and rcub/n threads and is also the value
config DEBUG_PERF_USE_VMALLOC
default n
bool "Debug: use vmalloc to back perf mmap() buffers"
- depends on PERF_EVENTS && DEBUG_KERNEL
+ depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
select PERF_USE_VMALLOC
help
Use vmalloc memory to back perf mmap() buffers.
#endif
if (strncmp(name, "/dev/", 5) != 0) {
- unsigned maj, min;
+ unsigned maj, min, offset;
char dummy;
- if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2) {
+ if ((sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2) ||
+ (sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3)) {
res = MKDEV(maj, min);
if (maj != MAJOR(res) || min != MINOR(res))
goto fail;
#define RECV 1
#define STATE_NONE 0
-#define STATE_PENDING 1
-#define STATE_READY 2
+#define STATE_READY 1
struct posix_msg_tree_node {
struct rb_node rb_node;
wq_add(info, sr, ewp);
for (;;) {
- set_current_state(TASK_INTERRUPTIBLE);
+ __set_current_state(TASK_INTERRUPTIBLE);
spin_unlock(&info->lock);
time = schedule_hrtimeout_range_clock(timeout, 0,
HRTIMER_MODE_ABS, CLOCK_REALTIME);
- while (ewp->state == STATE_PENDING)
- cpu_relax();
-
if (ewp->state == STATE_READY) {
retval = 0;
goto out;
* list of waiting receivers. A sender checks that list before adding the new
* message into the message array. If there is a waiting receiver, then it
* bypasses the message array and directly hands the message over to the
- * receiver.
- * The receiver accepts the message and returns without grabbing the queue
- * spinlock. Therefore an intermediate STATE_PENDING state and memory barriers
- * are necessary. The same algorithm is used for sysv semaphores, see
- * ipc/sem.c for more details.
+ * receiver. The receiver accepts the message and returns without grabbing the
+ * queue spinlock:
+ *
+ * - Set pointer to message.
+ * - Queue the receiver task for later wakeup (without the info->lock).
+ * - Update its state to STATE_READY. Now the receiver can continue.
+ * - Wake up the process after the lock is dropped. Should the process wake up
+ * before this wakeup (due to a timeout or a signal) it will either see
+ * STATE_READY and continue or acquire the lock to check the state again.
*
* The same algorithm is used for senders.
*/
/* pipelined_send() - send a message directly to the task waiting in
* sys_mq_timedreceive() (without inserting message into a queue).
*/
-static inline void pipelined_send(struct mqueue_inode_info *info,
+static inline void pipelined_send(struct wake_q_head *wake_q,
+ struct mqueue_inode_info *info,
struct msg_msg *message,
struct ext_wait_queue *receiver)
{
receiver->msg = message;
list_del(&receiver->list);
- receiver->state = STATE_PENDING;
- wake_up_process(receiver->task);
- smp_wmb();
+ wake_q_add(wake_q, receiver->task);
+ /*
+ * Rely on the implicit cmpxchg barrier from wake_q_add such
+ * that we can ensure that updating receiver->state is the last
+ * write operation: As once set, the receiver can continue,
+ * and if we don't have the reference count from the wake_q,
+ * yet, at that point we can later have a use-after-free
+ * condition and bogus wakeup.
+ */
receiver->state = STATE_READY;
}
/* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
* gets its message and put to the queue (we have one free place for sure). */
-static inline void pipelined_receive(struct mqueue_inode_info *info)
+static inline void pipelined_receive(struct wake_q_head *wake_q,
+ struct mqueue_inode_info *info)
{
struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND);
}
if (msg_insert(sender->msg, info))
return;
+
list_del(&sender->list);
- sender->state = STATE_PENDING;
- wake_up_process(sender->task);
- smp_wmb();
+ wake_q_add(wake_q, sender->task);
sender->state = STATE_READY;
}
struct timespec ts;
struct posix_msg_tree_node *new_leaf = NULL;
int ret = 0;
+ WAKE_Q(wake_q);
if (u_abs_timeout) {
int res = prepare_timeout(u_abs_timeout, &expires, &ts);
} else {
receiver = wq_get_first_waiter(info, RECV);
if (receiver) {
- pipelined_send(info, msg_ptr, receiver);
+ pipelined_send(&wake_q, info, msg_ptr, receiver);
} else {
/* adds message to the queue */
ret = msg_insert(msg_ptr, info);
}
out_unlock:
spin_unlock(&info->lock);
+ wake_up_q(&wake_q);
out_free:
if (ret)
free_msg(msg_ptr);
msg_ptr = wait.msg;
}
} else {
+ WAKE_Q(wake_q);
+
msg_ptr = msg_get(info);
inode->i_atime = inode->i_mtime = inode->i_ctime =
CURRENT_TIME;
/* There is now free space in queue. */
- pipelined_receive(info);
+ pipelined_receive(&wake_q, info);
spin_unlock(&info->lock);
+ wake_up_q(&wake_q);
ret = 0;
}
if (ret == 0) {
def_bool y
depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER
-config ARCH_USE_QUEUE_RWLOCK
+config ARCH_USE_QUEUED_SPINLOCKS
bool
-config QUEUE_RWLOCK
- def_bool y if ARCH_USE_QUEUE_RWLOCK
+config QUEUED_SPINLOCKS
+ def_bool y if ARCH_USE_QUEUED_SPINLOCKS
+ depends on SMP
+
+config ARCH_USE_QUEUED_RWLOCKS
+ bool
+
+config QUEUED_RWLOCKS
+ def_bool y if ARCH_USE_QUEUED_RWLOCKS
depends on SMP
* bitmap. We must however ensure the end of the
* kernel bitmap is zeroed.
*/
- if (nr_compat_longs-- > 0) {
+ if (nr_compat_longs) {
+ nr_compat_longs--;
if (__get_user(um, umask))
return -EFAULT;
} else {
* We dont want to write past the end of the userspace
* bitmap.
*/
- if (nr_compat_longs-- > 0) {
+ if (nr_compat_longs) {
+ nr_compat_longs--;
if (__put_user(um, umask))
return -EFAULT;
}
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
if (err) {
/* CPU didn't die: tell everyone. Can't complain. */
- smpboot_unpark_threads(cpu);
cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
goto out_release;
}
switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DOWN_FAILED:
case CPU_ONLINE:
smpboot_unpark_threads(cpu);
break;
.priority = CPU_PRI_SMPBOOT,
};
-void __cpuinit smpboot_thread_init(void)
+void smpboot_thread_init(void)
{
register_cpu_notifier(&smpboot_thread_notifier);
}
static struct workqueue_struct *perf_wq;
+typedef int (*remote_function_f)(void *);
+
struct remote_function_call {
struct task_struct *p;
- int (*func)(void *info);
+ remote_function_f func;
void *info;
int ret;
};
* -EAGAIN - when the process moved away
*/
static int
-task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+task_function_call(struct task_struct *p, remote_function_f func, void *info)
{
struct remote_function_call data = {
.p = p,
*
* returns: @func return value or -ENXIO when the cpu is offline
*/
-static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+static int cpu_function_call(int cpu, remote_function_f func, void *info)
{
struct remote_function_call data = {
.p = NULL,
/*
* function must be called with interrupts disbled
*/
-static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr)
+static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
{
struct perf_cpu_context *cpuctx;
- enum hrtimer_restart ret = HRTIMER_NORESTART;
int rotations = 0;
WARN_ON(!irqs_disabled());
cpuctx = container_of(hr, struct perf_cpu_context, hrtimer);
-
rotations = perf_rotate_context(cpuctx);
- /*
- * arm timer if needed
- */
- if (rotations) {
+ raw_spin_lock(&cpuctx->hrtimer_lock);
+ if (rotations)
hrtimer_forward_now(hr, cpuctx->hrtimer_interval);
- ret = HRTIMER_RESTART;
- }
-
- return ret;
-}
-
-/* CPU is going down */
-void perf_cpu_hrtimer_cancel(int cpu)
-{
- struct perf_cpu_context *cpuctx;
- struct pmu *pmu;
- unsigned long flags;
-
- if (WARN_ON(cpu != smp_processor_id()))
- return;
-
- local_irq_save(flags);
-
- rcu_read_lock();
-
- list_for_each_entry_rcu(pmu, &pmus, entry) {
- cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
- if (pmu->task_ctx_nr == perf_sw_context)
- continue;
-
- hrtimer_cancel(&cpuctx->hrtimer);
- }
-
- rcu_read_unlock();
+ else
+ cpuctx->hrtimer_active = 0;
+ raw_spin_unlock(&cpuctx->hrtimer_lock);
- local_irq_restore(flags);
+ return rotations ? HRTIMER_RESTART : HRTIMER_NORESTART;
}
-static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
+static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
{
- struct hrtimer *hr = &cpuctx->hrtimer;
+ struct hrtimer *timer = &cpuctx->hrtimer;
struct pmu *pmu = cpuctx->ctx.pmu;
- int timer;
+ u64 interval;
/* no multiplexing needed for SW PMU */
if (pmu->task_ctx_nr == perf_sw_context)
* check default is sane, if not set then force to
* default interval (1/tick)
*/
- timer = pmu->hrtimer_interval_ms;
- if (timer < 1)
- timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
+ interval = pmu->hrtimer_interval_ms;
+ if (interval < 1)
+ interval = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
- cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
+ cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
- hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
- hr->function = perf_cpu_hrtimer_handler;
+ raw_spin_lock_init(&cpuctx->hrtimer_lock);
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+ timer->function = perf_mux_hrtimer_handler;
}
-static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx)
+static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
{
- struct hrtimer *hr = &cpuctx->hrtimer;
+ struct hrtimer *timer = &cpuctx->hrtimer;
struct pmu *pmu = cpuctx->ctx.pmu;
+ unsigned long flags;
/* not for SW PMU */
if (pmu->task_ctx_nr == perf_sw_context)
- return;
+ return 0;
- if (hrtimer_active(hr))
- return;
+ raw_spin_lock_irqsave(&cpuctx->hrtimer_lock, flags);
+ if (!cpuctx->hrtimer_active) {
+ cpuctx->hrtimer_active = 1;
+ hrtimer_forward_now(timer, cpuctx->hrtimer_interval);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+ }
+ raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags);
- if (!hrtimer_callback_running(hr))
- __hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval,
- 0, HRTIMER_MODE_REL_PINNED, 0);
+ return 0;
}
void perf_pmu_disable(struct pmu *pmu)
* Those places that change perf_event::ctx will hold both
* perf_event_ctx::mutex of the 'old' and 'new' ctx value.
*
- * Lock ordering is by mutex address. There is one other site where
- * perf_event_context::mutex nests and that is put_event(). But remember that
- * that is a parent<->child context relation, and migration does not affect
- * children, therefore these two orderings should not interact.
+ * Lock ordering is by mutex address. There are two other sites where
+ * perf_event_context::mutex nests and those are:
+ *
+ * - perf_event_exit_task_context() [ child , 0 ]
+ * __perf_event_exit_task()
+ * sync_child_event()
+ * put_event() [ parent, 1 ]
+ *
+ * - perf_event_init_context() [ parent, 0 ]
+ * inherit_task_group()
+ * inherit_group()
+ * inherit_event()
+ * perf_event_alloc()
+ * perf_init_event()
+ * perf_try_init_event() [ child , 1 ]
+ *
+ * While it appears there is an obvious deadlock here -- the parent and child
+ * nesting levels are inverted between the two. This is in fact safe because
+ * life-time rules separate them. That is an exiting task cannot fork, and a
+ * spawning task cannot (yet) exit.
+ *
+ * But remember that that these are parent<->child context relations, and
+ * migration does not affect children, therefore these two orderings should not
+ * interact.
*
* The change in perf_event::ctx does not affect children (as claimed above)
* because the sys_perf_event_open() case will install a new event and break
if (event_sched_in(group_event, cpuctx, ctx)) {
pmu->cancel_txn(pmu);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
return -EAGAIN;
}
pmu->cancel_txn(pmu);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
return -EAGAIN;
}
*/
if (leader != event) {
group_sched_out(leader, cpuctx, ctx);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
}
if (leader->attr.pinned) {
update_group_times(leader);
if (event->ns)
put_pid_ns(event->ns);
perf_event_free_filter(event);
- perf_event_free_bpf_prog(event);
kfree(event);
}
put_callchain_buffers();
}
+ perf_event_free_bpf_prog(event);
+
if (event->destroy)
event->destroy(event);
}
}
-/*
- * Called when the last reference to the file is gone.
- */
static void put_event(struct perf_event *event)
{
struct perf_event_context *ctx;
}
EXPORT_SYMBOL_GPL(perf_event_release_kernel);
+/*
+ * Called when the last reference to the file is gone.
+ */
static int perf_release(struct inode *inode, struct file *file)
{
put_event(file->private_data);
WARN_ON_ONCE(event->rcu_pending);
old_rb = event->rb;
- event->rcu_batches = get_state_synchronize_rcu();
- event->rcu_pending = 1;
-
spin_lock_irqsave(&old_rb->event_lock, flags);
list_del_rcu(&event->rb_entry);
spin_unlock_irqrestore(&old_rb->event_lock, flags);
- }
- if (event->rcu_pending && rb) {
- cond_synchronize_rcu(event->rcu_batches);
- event->rcu_pending = 0;
+ event->rcu_batches = get_state_synchronize_rcu();
+ event->rcu_pending = 1;
}
if (rb) {
+ if (event->rcu_pending) {
+ cond_synchronize_rcu(event->rcu_batches);
+ event->rcu_pending = 0;
+ }
+
spin_lock_irqsave(&rb->event_lock, flags);
list_add_rcu(&event->rb_entry, &rb->event_list);
spin_unlock_irqrestore(&rb->event_lock, flags);
}
}
-static void perf_event_output(struct perf_event *event,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
struct perf_output_handle handle;
struct perf_event_header header;
perf_output_end(&handle);
}
+/*
+ * Lost/dropped samples logging
+ */
+void perf_log_lost_samples(struct perf_event *event, u64 lost)
+{
+ struct perf_output_handle handle;
+ struct perf_sample_data sample;
+ int ret;
+
+ struct {
+ struct perf_event_header header;
+ u64 lost;
+ } lost_samples_event = {
+ .header = {
+ .type = PERF_RECORD_LOST_SAMPLES,
+ .misc = 0,
+ .size = sizeof(lost_samples_event),
+ },
+ .lost = lost,
+ };
+
+ perf_event_header__init_id(&lost_samples_event.header, &sample, event);
+
+ ret = perf_output_begin(&handle, event,
+ lost_samples_event.header.size);
+ if (ret)
+ return;
+
+ perf_output_put(&handle, lost_samples_event);
+ perf_event__output_id_sample(event, &handle, &sample);
+ perf_output_end(&handle);
+}
+
/*
* IRQ throttle logging
*/
} else {
period = max_t(u64, 10000, hwc->sample_period);
}
- __hrtimer_start_range_ns(&hwc->hrtimer,
- ns_to_ktime(period), 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&hwc->hrtimer, ns_to_ktime(period),
+ HRTIMER_MODE_REL_PINNED);
}
static void perf_swevent_cancel_hrtimer(struct perf_event *event)
return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
}
+static DEFINE_MUTEX(mux_interval_mutex);
+
static ssize_t
perf_event_mux_interval_ms_store(struct device *dev,
struct device_attribute *attr,
if (timer == pmu->hrtimer_interval_ms)
return count;
+ mutex_lock(&mux_interval_mutex);
pmu->hrtimer_interval_ms = timer;
/* update all cpuctx for this PMU */
- for_each_possible_cpu(cpu) {
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
struct perf_cpu_context *cpuctx;
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
- if (hrtimer_active(&cpuctx->hrtimer))
- hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval);
+ cpu_function_call(cpu,
+ (remote_function_f)perf_mux_hrtimer_restart, cpuctx);
}
+ put_online_cpus();
+ mutex_unlock(&mux_interval_mutex);
return count;
}
lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
cpuctx->ctx.pmu = pmu;
- __perf_cpu_hrtimer_init(cpuctx, cpu);
+ __perf_mux_hrtimer_init(cpuctx, cpu);
cpuctx->unique_pmu = pmu;
}
return -ENODEV;
if (event->group_leader != event) {
- ctx = perf_event_ctx_lock(event->group_leader);
+ /*
+ * This ctx->mutex can nest when we're called through
+ * inheritance. See the perf_event_ctx_lock_nested() comment.
+ */
+ ctx = perf_event_ctx_lock_nested(event->group_leader,
+ SINGLE_DEPTH_NESTING);
BUG_ON(!ctx);
}
void perf_event_aux_event(struct perf_event *event, unsigned long head,
unsigned long size, u64 flags);
-extern void
-perf_event_header__init_id(struct perf_event_header *header,
- struct perf_sample_data *data,
- struct perf_event *event);
-extern void
-perf_event__output_id_sample(struct perf_event *event,
- struct perf_output_handle *handle,
- struct perf_sample_data *sample);
-
extern struct page *
perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff);
perf_output_get_handle(handle);
do {
- tail = ACCESS_ONCE(rb->user_page->data_tail);
+ tail = READ_ONCE_CTRL(rb->user_page->data_tail);
offset = head = local_read(&rb->head);
if (!rb->overwrite &&
unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
rb->aux_pages[rb->aux_nr_pages] = page_address(page++);
}
+ /*
+ * In overwrite mode, PMUs that don't support SG may not handle more
+ * than one contiguous allocation, since they rely on PMI to do double
+ * buffering. In this case, the entire buffer has to be one contiguous
+ * chunk.
+ */
+ if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) &&
+ overwrite) {
+ struct page *page = virt_to_page(rb->aux_pages[0]);
+
+ if (page_private(page) != max_order)
+ goto out;
+ }
+
rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages,
overwrite);
if (!rb->aux_priv)
{
unsigned long cpu_limit;
- /* Thread group counters. */
- thread_group_cputime_init(sig);
-
- cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+ cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
if (cpu_limit != RLIM_INFINITY) {
sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
sig->cputimer.running = 1;
p->hardirq_context = 0;
p->softirq_context = 0;
#endif
+
+ p->pagefault_disabled = 0;
+
#ifdef CONFIG_LOCKDEP
p->lockdep_depth = 0; /* no locks held yet */
p->curr_chain_key = 0;
/*
* The hash bucket lock must be held when this is called.
- * Afterwards, the futex_q must not be accessed.
+ * Afterwards, the futex_q must not be accessed. Callers
+ * must ensure to later call wake_up_q() for the actual
+ * wakeups to occur.
*/
-static void wake_futex(struct futex_q *q)
+static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
{
struct task_struct *p = q->task;
return;
/*
- * We set q->lock_ptr = NULL _before_ we wake up the task. If
- * a non-futex wake up happens on another CPU then the task
- * might exit and p would dereference a non-existing task
- * struct. Prevent this by holding a reference on p across the
- * wake up.
+ * Queue the task for later wakeup for after we've released
+ * the hb->lock. wake_q_add() grabs reference to p.
*/
- get_task_struct(p);
-
+ wake_q_add(wake_q, p);
__unqueue_futex(q);
/*
* The waiting task can free the futex_q as soon as
*/
smp_wmb();
q->lock_ptr = NULL;
-
- wake_up_state(p, TASK_NORMAL);
- put_task_struct(p);
}
static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
struct futex_q *this, *next;
union futex_key key = FUTEX_KEY_INIT;
int ret;
+ WAKE_Q(wake_q);
if (!bitset)
return -EINVAL;
if (!(this->bitset & bitset))
continue;
- wake_futex(this);
+ mark_wake_futex(&wake_q, this);
if (++ret >= nr_wake)
break;
}
}
spin_unlock(&hb->lock);
+ wake_up_q(&wake_q);
out_put_key:
put_futex_key(&key);
out:
struct futex_hash_bucket *hb1, *hb2;
struct futex_q *this, *next;
int ret, op_ret;
+ WAKE_Q(wake_q);
retry:
ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
ret = -EINVAL;
goto out_unlock;
}
- wake_futex(this);
+ mark_wake_futex(&wake_q, this);
if (++ret >= nr_wake)
break;
}
ret = -EINVAL;
goto out_unlock;
}
- wake_futex(this);
+ mark_wake_futex(&wake_q, this);
if (++op_ret >= nr_wake2)
break;
}
out_unlock:
double_unlock_hb(hb1, hb2);
+ wake_up_q(&wake_q);
out_put_keys:
put_futex_key(&key2);
out_put_key1:
struct futex_pi_state *pi_state = NULL;
struct futex_hash_bucket *hb1, *hb2;
struct futex_q *this, *next;
+ WAKE_Q(wake_q);
if (requeue_pi) {
/*
* woken by futex_unlock_pi().
*/
if (++task_count <= nr_wake && !requeue_pi) {
- wake_futex(this);
+ mark_wake_futex(&wake_q, this);
continue;
}
out_unlock:
free_pi_state(pi_state);
double_unlock_hb(hb1, hb2);
+ wake_up_q(&wake_q);
hb_waiters_dec(hb2);
/*
{
/*
* The task state is guaranteed to be set before another task can
- * wake it. set_current_state() is implemented using set_mb() and
+ * wake it. set_current_state() is implemented using smp_store_mb() and
* queue_me() calls spin_unlock() upon completion, both serializing
* access to the hash list and forcing another memory barrier.
*/
queue_me(q, hb);
/* Arm the timer */
- if (timeout) {
+ if (timeout)
hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
- if (!hrtimer_active(&timeout->timer))
- timeout->task = NULL;
- }
/*
* If we have been removed from the hash list, then another task
return -ENOSYS;
}
+/**
+ * irq_chip_set_vcpu_affinity_parent - Set vcpu affinity on the parent interrupt
+ * @data: Pointer to interrupt specific data
+ * @dest: The vcpu affinity information
+ */
+int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
+{
+ data = data->parent_data;
+ if (data->chip->irq_set_vcpu_affinity)
+ return data->chip->irq_set_vcpu_affinity(data, vcpu_info);
+
+ return -ENOSYS;
+}
+
/**
* irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt
* @data: Pointer to interrupt specific data
.irq_ack = noop,
.irq_mask = noop,
.irq_unmask = noop,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
};
EXPORT_SYMBOL_GPL(dummy_irq_chip);
#include "debug.h"
#include "settings.h"
-#define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data)
-
extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
unsigned long flags);
extern void __disable_irq(struct irq_desc *desc, unsigned int irq);
}
EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+/**
+ * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
+ * @irq: interrupt number to set affinity
+ * @vcpu_info: vCPU specific data
+ *
+ * This function uses the vCPU specific data to set the vCPU
+ * affinity for an irq. The vCPU specific data is passed from
+ * outside, such as KVM. One example code path is as below:
+ * KVM -> IOMMU -> irq_set_vcpu_affinity().
+ */
+int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
+{
+ unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
+ struct irq_data *data;
+ struct irq_chip *chip;
+ int ret = -ENOSYS;
+
+ if (!desc)
+ return -EINVAL;
+
+ data = irq_desc_get_irq_data(desc);
+ chip = irq_data_get_irq_chip(data);
+ if (chip && chip->irq_set_vcpu_affinity)
+ ret = chip->irq_set_vcpu_affinity(data, vcpu_info);
+ irq_put_desc_unlock(desc, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);
+
static void irq_affinity_notify(struct work_struct *work)
{
struct irq_affinity_notify *notify =
void irq_move_masked_irq(struct irq_data *idata)
{
struct irq_desc *desc = irq_data_to_desc(idata);
- struct irq_chip *chip = idata->chip;
+ struct irq_chip *chip = desc->irq_data.chip;
if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
return;
{
bool masked;
+ /*
+ * Get top level irq_data when CONFIG_IRQ_DOMAIN_HIERARCHY is enabled,
+ * and it should be optimized away when CONFIG_IRQ_DOMAIN_HIERARCHY is
+ * disabled. So we avoid an "#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY" here.
+ */
+ idata = irq_desc_get_irq_data(irq_data_to_desc(idata));
+
if (likely(!irqd_is_setaffinity_pending(idata)))
return;
obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
obj-$(CONFIG_SMP) += lglock.o
obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
+obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o
obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
-obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o
+obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
}
EXPORT_SYMBOL(lg_local_unlock_cpu);
+void lg_double_lock(struct lglock *lg, int cpu1, int cpu2)
+{
+ BUG_ON(cpu1 == cpu2);
+
+ /* lock in cpu order, just like lg_global_lock */
+ if (cpu2 < cpu1)
+ swap(cpu1, cpu2);
+
+ preempt_disable();
+ lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
+ arch_spin_lock(per_cpu_ptr(lg->lock, cpu1));
+ arch_spin_lock(per_cpu_ptr(lg->lock, cpu2));
+}
+
+void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2)
+{
+ lock_release(&lg->lock_dep_map, 1, _RET_IP_);
+ arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1));
+ arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2));
+ preempt_enable();
+}
+
void lg_global_lock(struct lglock *lg)
{
int i;
list_del_rcu(&class->hash_entry);
list_del_rcu(&class->lock_entry);
- class->key = NULL;
+ RCU_INIT_POINTER(class->key, NULL);
+ RCU_INIT_POINTER(class->name, NULL);
}
static inline int within(const void *addr, void *start, unsigned long size)
#ifdef CONFIG_DEBUG_LOCKDEP
if (lockdep_init_error) {
- printk("WARNING: lockdep init error! lock-%s was acquired"
- "before lockdep_init\n", lock_init_error);
+ printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error);
printk("Call stack leading to lockdep invocation was:\n");
print_stack_trace(&lockdep_init_trace, 0);
}
static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
{
- char name[39];
- struct lock_class *class;
+ struct lockdep_subclass_key *ckey;
struct lock_class_stats *stats;
+ struct lock_class *class;
+ const char *cname;
int i, namelen;
+ char name[39];
class = data->class;
stats = &data->stats;
if (class->subclass)
namelen -= 2;
- if (!class->name) {
+ rcu_read_lock_sched();
+ cname = rcu_dereference_sched(class->name);
+ ckey = rcu_dereference_sched(class->key);
+
+ if (!cname && !ckey) {
+ rcu_read_unlock_sched();
+ return;
+
+ } else if (!cname) {
char str[KSYM_NAME_LEN];
const char *key_name;
- key_name = __get_key_name(class->key, str);
+ key_name = __get_key_name(ckey, str);
snprintf(name, namelen, "%s", key_name);
} else {
- snprintf(name, namelen, "%s", class->name);
+ snprintf(name, namelen, "%s", cname);
}
+ rcu_read_unlock_sched();
+
namelen = strlen(name);
if (class->name_version > 1) {
snprintf(name+namelen, 3, "#%d", class->name_version);
static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_us = 100;
+ const unsigned long longdelay_ms = 100;
/* We want a long delay occasionally to force massive contention. */
if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_us)))
- mdelay(longdelay_us);
+ (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+ mdelay(longdelay_ms);
#ifdef CONFIG_PREEMPT
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
preempt_schedule(); /* Allow test to be preempted. */
static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
- const unsigned long longdelay_us = 100;
+ const unsigned long longdelay_ms = 100;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_us)))
- mdelay(longdelay_us);
+ (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+ mdelay(longdelay_ms);
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 2 * shortdelay_us)))
udelay(shortdelay_us);
static void torture_rwlock_read_unlock_irq(void)
__releases(torture_rwlock)
{
- write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
+ read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
}
static struct lock_torture_ops rw_lock_irq_ops = {
struct mcs_spinlock {
struct mcs_spinlock *next;
int locked; /* 1 if lock acquired */
+ int count; /* nesting count, see qspinlock.c */
};
#ifndef arch_mcs_spin_lock_contended
/*
- * Queue read/write lock
+ * Queued read/write locks
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
#include <linux/hardirq.h>
#include <asm/qrwlock.h>
+/*
+ * This internal data structure is used for optimizing access to some of
+ * the subfields within the atomic_t cnts.
+ */
+struct __qrwlock {
+ union {
+ atomic_t cnts;
+ struct {
+#ifdef __LITTLE_ENDIAN
+ u8 wmode; /* Writer mode */
+ u8 rcnts[3]; /* Reader counts */
+#else
+ u8 rcnts[3]; /* Reader counts */
+ u8 wmode; /* Writer mode */
+#endif
+ };
+ };
+ arch_spinlock_t lock;
+};
+
/**
* rspin_until_writer_unlock - inc reader count & spin until writer is gone
* @lock : Pointer to queue rwlock structure
* or wait for a previous writer to go away.
*/
for (;;) {
- cnts = atomic_read(&lock->cnts);
- if (!(cnts & _QW_WMASK) &&
- (atomic_cmpxchg(&lock->cnts, cnts,
- cnts | _QW_WAITING) == cnts))
+ struct __qrwlock *l = (struct __qrwlock *)lock;
+
+ if (!READ_ONCE(l->wmode) &&
+ (cmpxchg(&l->wmode, 0, _QW_WAITING) == 0))
break;
cpu_relax_lowlatency();
--- /dev/null
+/*
+ * Queued spinlock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ * (C) Copyright 2013-2014 Red Hat, Inc.
+ * (C) Copyright 2015 Intel Corp.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ * Peter Zijlstra <peterz@infradead.org>
+ */
+
+#ifndef _GEN_PV_LOCK_SLOWPATH
+
+#include <linux/smp.h>
+#include <linux/bug.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/mutex.h>
+#include <asm/byteorder.h>
+#include <asm/qspinlock.h>
+
+/*
+ * The basic principle of a queue-based spinlock can best be understood
+ * by studying a classic queue-based spinlock implementation called the
+ * MCS lock. The paper below provides a good description for this kind
+ * of lock.
+ *
+ * http://www.cise.ufl.edu/tr/DOC/REP-1992-71.pdf
+ *
+ * This queued spinlock implementation is based on the MCS lock, however to make
+ * it fit the 4 bytes we assume spinlock_t to be, and preserve its existing
+ * API, we must modify it somehow.
+ *
+ * In particular; where the traditional MCS lock consists of a tail pointer
+ * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to
+ * unlock the next pending (next->locked), we compress both these: {tail,
+ * next->locked} into a single u32 value.
+ *
+ * Since a spinlock disables recursion of its own context and there is a limit
+ * to the contexts that can nest; namely: task, softirq, hardirq, nmi. As there
+ * are at most 4 nesting levels, it can be encoded by a 2-bit number. Now
+ * we can encode the tail by combining the 2-bit nesting level with the cpu
+ * number. With one byte for the lock value and 3 bytes for the tail, only a
+ * 32-bit word is now needed. Even though we only need 1 bit for the lock,
+ * we extend it to a full byte to achieve better performance for architectures
+ * that support atomic byte write.
+ *
+ * We also change the first spinner to spin on the lock bit instead of its
+ * node; whereby avoiding the need to carry a node from lock to unlock, and
+ * preserving existing lock API. This also makes the unlock code simpler and
+ * faster.
+ *
+ * N.B. The current implementation only supports architectures that allow
+ * atomic operations on smaller 8-bit and 16-bit data types.
+ *
+ */
+
+#include "mcs_spinlock.h"
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define MAX_NODES 8
+#else
+#define MAX_NODES 4
+#endif
+
+/*
+ * Per-CPU queue node structures; we can never have more than 4 nested
+ * contexts: task, softirq, hardirq, nmi.
+ *
+ * Exactly fits one 64-byte cacheline on a 64-bit architecture.
+ *
+ * PV doubles the storage and uses the second cacheline for PV state.
+ */
+static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]);
+
+/*
+ * We must be able to distinguish between no-tail and the tail at 0:0,
+ * therefore increment the cpu number by one.
+ */
+
+static inline u32 encode_tail(int cpu, int idx)
+{
+ u32 tail;
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+ BUG_ON(idx > 3);
+#endif
+ tail = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
+ tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
+
+ return tail;
+}
+
+static inline struct mcs_spinlock *decode_tail(u32 tail)
+{
+ int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
+ int idx = (tail & _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
+
+ return per_cpu_ptr(&mcs_nodes[idx], cpu);
+}
+
+#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
+
+/*
+ * By using the whole 2nd least significant byte for the pending bit, we
+ * can allow better optimization of the lock acquisition for the pending
+ * bit holder.
+ *
+ * This internal structure is also used by the set_locked function which
+ * is not restricted to _Q_PENDING_BITS == 8.
+ */
+struct __qspinlock {
+ union {
+ atomic_t val;
+#ifdef __LITTLE_ENDIAN
+ struct {
+ u8 locked;
+ u8 pending;
+ };
+ struct {
+ u16 locked_pending;
+ u16 tail;
+ };
+#else
+ struct {
+ u16 tail;
+ u16 locked_pending;
+ };
+ struct {
+ u8 reserved[2];
+ u8 pending;
+ u8 locked;
+ };
+#endif
+ };
+};
+
+#if _Q_PENDING_BITS == 8
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ *
+ * Lock stealing is not allowed if this function is used.
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL);
+}
+
+/*
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
+}
+
+#else /* _Q_PENDING_BITS == 8 */
+
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ */
+static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
+{
+ atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val);
+}
+
+/**
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+ u32 old, new, val = atomic_read(&lock->val);
+
+ for (;;) {
+ new = (val & _Q_LOCKED_PENDING_MASK) | tail;
+ old = atomic_cmpxchg(&lock->val, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+ return old;
+}
+#endif /* _Q_PENDING_BITS == 8 */
+
+/**
+ * set_locked - Set the lock bit and own the lock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,*,0 -> *,0,1
+ */
+static __always_inline void set_locked(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+}
+
+
+/*
+ * Generate the native code for queued_spin_unlock_slowpath(); provide NOPs for
+ * all the PV callbacks.
+ */
+
+static __always_inline void __pv_init_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_wait_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_kick_node(struct mcs_spinlock *node) { }
+
+static __always_inline void __pv_wait_head(struct qspinlock *lock,
+ struct mcs_spinlock *node) { }
+
+#define pv_enabled() false
+
+#define pv_init_node __pv_init_node
+#define pv_wait_node __pv_wait_node
+#define pv_kick_node __pv_kick_node
+#define pv_wait_head __pv_wait_head
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
+#endif
+
+#endif /* _GEN_PV_LOCK_SLOWPATH */
+
+/**
+ * queued_spin_lock_slowpath - acquire the queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ * @val: Current value of the queued spinlock 32-bit word
+ *
+ * (queue tail, pending bit, lock value)
+ *
+ * fast : slow : unlock
+ * : :
+ * uncontended (0,0,0) -:--> (0,0,1) ------------------------------:--> (*,*,0)
+ * : | ^--------.------. / :
+ * : v \ \ | :
+ * pending : (0,1,1) +--> (0,1,0) \ | :
+ * : | ^--' | | :
+ * : v | | :
+ * uncontended : (n,x,y) +--> (n,0,0) --' | :
+ * queue : | ^--' | :
+ * : v | :
+ * contended : (*,x,y) +--> (*,0,0) ---> (*,0,1) -' :
+ * queue : ^--' :
+ */
+void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+ struct mcs_spinlock *prev, *next, *node;
+ u32 new, old, tail;
+ int idx;
+
+ BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
+
+ if (pv_enabled())
+ goto queue;
+
+ if (virt_queued_spin_lock(lock))
+ return;
+
+ /*
+ * wait for in-progress pending->locked hand-overs
+ *
+ * 0,1,0 -> 0,0,1
+ */
+ if (val == _Q_PENDING_VAL) {
+ while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL)
+ cpu_relax();
+ }
+
+ /*
+ * trylock || pending
+ *
+ * 0,0,0 -> 0,0,1 ; trylock
+ * 0,0,1 -> 0,1,1 ; pending
+ */
+ for (;;) {
+ /*
+ * If we observe any contention; queue.
+ */
+ if (val & ~_Q_LOCKED_MASK)
+ goto queue;
+
+ new = _Q_LOCKED_VAL;
+ if (val == new)
+ new |= _Q_PENDING_VAL;
+
+ old = atomic_cmpxchg(&lock->val, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+
+ /*
+ * we won the trylock
+ */
+ if (new == _Q_LOCKED_VAL)
+ return;
+
+ /*
+ * we're pending, wait for the owner to go away.
+ *
+ * *,1,1 -> *,1,0
+ *
+ * this wait loop must be a load-acquire such that we match the
+ * store-release that clears the locked bit and create lock
+ * sequentiality; this is because not all clear_pending_set_locked()
+ * implementations imply full barriers.
+ */
+ while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK)
+ cpu_relax();
+
+ /*
+ * take ownership and clear the pending bit.
+ *
+ * *,1,0 -> *,0,1
+ */
+ clear_pending_set_locked(lock);
+ return;
+
+ /*
+ * End of pending bit optimistic spinning and beginning of MCS
+ * queuing.
+ */
+queue:
+ node = this_cpu_ptr(&mcs_nodes[0]);
+ idx = node->count++;
+ tail = encode_tail(smp_processor_id(), idx);
+
+ node += idx;
+ node->locked = 0;
+ node->next = NULL;
+ pv_init_node(node);
+
+ /*
+ * We touched a (possibly) cold cacheline in the per-cpu queue node;
+ * attempt the trylock once more in the hope someone let go while we
+ * weren't watching.
+ */
+ if (queued_spin_trylock(lock))
+ goto release;
+
+ /*
+ * We have already touched the queueing cacheline; don't bother with
+ * pending stuff.
+ *
+ * p,*,* -> n,*,*
+ */
+ old = xchg_tail(lock, tail);
+
+ /*
+ * if there was a previous node; link it and wait until reaching the
+ * head of the waitqueue.
+ */
+ if (old & _Q_TAIL_MASK) {
+ prev = decode_tail(old);
+ WRITE_ONCE(prev->next, node);
+
+ pv_wait_node(node);
+ arch_mcs_spin_lock_contended(&node->locked);
+ }
+
+ /*
+ * we're at the head of the waitqueue, wait for the owner & pending to
+ * go away.
+ *
+ * *,x,y -> *,0,0
+ *
+ * this wait loop must use a load-acquire such that we match the
+ * store-release that clears the locked bit and create lock
+ * sequentiality; this is because the set_locked() function below
+ * does not imply a full barrier.
+ *
+ */
+ pv_wait_head(lock, node);
+ while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK)
+ cpu_relax();
+
+ /*
+ * claim the lock:
+ *
+ * n,0,0 -> 0,0,1 : lock, uncontended
+ * *,0,0 -> *,0,1 : lock, contended
+ *
+ * If the queue head is the only one in the queue (lock value == tail),
+ * clear the tail code and grab the lock. Otherwise, we only need
+ * to grab the lock.
+ */
+ for (;;) {
+ if (val != tail) {
+ set_locked(lock);
+ break;
+ }
+ old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL);
+ if (old == val)
+ goto release; /* No contention */
+
+ val = old;
+ }
+
+ /*
+ * contended path; wait for next, release.
+ */
+ while (!(next = READ_ONCE(node->next)))
+ cpu_relax();
+
+ arch_mcs_spin_unlock_contended(&next->locked);
+ pv_kick_node(next);
+
+release:
+ /*
+ * release the node
+ */
+ this_cpu_dec(mcs_nodes[0].count);
+}
+EXPORT_SYMBOL(queued_spin_lock_slowpath);
+
+/*
+ * Generate the paravirt code for queued_spin_unlock_slowpath().
+ */
+#if !defined(_GEN_PV_LOCK_SLOWPATH) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#define _GEN_PV_LOCK_SLOWPATH
+
+#undef pv_enabled
+#define pv_enabled() true
+
+#undef pv_init_node
+#undef pv_wait_node
+#undef pv_kick_node
+#undef pv_wait_head
+
+#undef queued_spin_lock_slowpath
+#define queued_spin_lock_slowpath __pv_queued_spin_lock_slowpath
+
+#include "qspinlock_paravirt.h"
+#include "qspinlock.c"
+
+#endif
--- /dev/null
+#ifndef _GEN_PV_LOCK_SLOWPATH
+#error "do not include this file"
+#endif
+
+#include <linux/hash.h>
+#include <linux/bootmem.h>
+
+/*
+ * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
+ * of spinning them.
+ *
+ * This relies on the architecture to provide two paravirt hypercalls:
+ *
+ * pv_wait(u8 *ptr, u8 val) -- suspends the vcpu if *ptr == val
+ * pv_kick(cpu) -- wakes a suspended vcpu
+ *
+ * Using these we implement __pv_queued_spin_lock_slowpath() and
+ * __pv_queued_spin_unlock() to replace native_queued_spin_lock_slowpath() and
+ * native_queued_spin_unlock().
+ */
+
+#define _Q_SLOW_VAL (3U << _Q_LOCKED_OFFSET)
+
+enum vcpu_state {
+ vcpu_running = 0,
+ vcpu_halted,
+};
+
+struct pv_node {
+ struct mcs_spinlock mcs;
+ struct mcs_spinlock __res[3];
+
+ int cpu;
+ u8 state;
+};
+
+/*
+ * Lock and MCS node addresses hash table for fast lookup
+ *
+ * Hashing is done on a per-cacheline basis to minimize the need to access
+ * more than one cacheline.
+ *
+ * Dynamically allocate a hash table big enough to hold at least 4X the
+ * number of possible cpus in the system. Allocation is done on page
+ * granularity. So the minimum number of hash buckets should be at least
+ * 256 (64-bit) or 512 (32-bit) to fully utilize a 4k page.
+ *
+ * Since we should not be holding locks from NMI context (very rare indeed) the
+ * max load factor is 0.75, which is around the point where open addressing
+ * breaks down.
+ *
+ */
+struct pv_hash_entry {
+ struct qspinlock *lock;
+ struct pv_node *node;
+};
+
+#define PV_HE_PER_LINE (SMP_CACHE_BYTES / sizeof(struct pv_hash_entry))
+#define PV_HE_MIN (PAGE_SIZE / sizeof(struct pv_hash_entry))
+
+static struct pv_hash_entry *pv_lock_hash;
+static unsigned int pv_lock_hash_bits __read_mostly;
+
+/*
+ * Allocate memory for the PV qspinlock hash buckets
+ *
+ * This function should be called from the paravirt spinlock initialization
+ * routine.
+ */
+void __init __pv_init_lock_hash(void)
+{
+ int pv_hash_size = ALIGN(4 * num_possible_cpus(), PV_HE_PER_LINE);
+
+ if (pv_hash_size < PV_HE_MIN)
+ pv_hash_size = PV_HE_MIN;
+
+ /*
+ * Allocate space from bootmem which should be page-size aligned
+ * and hence cacheline aligned.
+ */
+ pv_lock_hash = alloc_large_system_hash("PV qspinlock",
+ sizeof(struct pv_hash_entry),
+ pv_hash_size, 0, HASH_EARLY,
+ &pv_lock_hash_bits, NULL,
+ pv_hash_size, pv_hash_size);
+}
+
+#define for_each_hash_entry(he, offset, hash) \
+ for (hash &= ~(PV_HE_PER_LINE - 1), he = &pv_lock_hash[hash], offset = 0; \
+ offset < (1 << pv_lock_hash_bits); \
+ offset++, he = &pv_lock_hash[(hash + offset) & ((1 << pv_lock_hash_bits) - 1)])
+
+static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
+{
+ unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
+ struct pv_hash_entry *he;
+
+ for_each_hash_entry(he, offset, hash) {
+ if (!cmpxchg(&he->lock, NULL, lock)) {
+ WRITE_ONCE(he->node, node);
+ return &he->lock;
+ }
+ }
+ /*
+ * Hard assume there is a free entry for us.
+ *
+ * This is guaranteed by ensuring every blocked lock only ever consumes
+ * a single entry, and since we only have 4 nesting levels per CPU
+ * and allocated 4*nr_possible_cpus(), this must be so.
+ *
+ * The single entry is guaranteed by having the lock owner unhash
+ * before it releases.
+ */
+ BUG();
+}
+
+static struct pv_node *pv_unhash(struct qspinlock *lock)
+{
+ unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits);
+ struct pv_hash_entry *he;
+ struct pv_node *node;
+
+ for_each_hash_entry(he, offset, hash) {
+ if (READ_ONCE(he->lock) == lock) {
+ node = READ_ONCE(he->node);
+ WRITE_ONCE(he->lock, NULL);
+ return node;
+ }
+ }
+ /*
+ * Hard assume we'll find an entry.
+ *
+ * This guarantees a limited lookup time and is itself guaranteed by
+ * having the lock owner do the unhash -- IFF the unlock sees the
+ * SLOW flag, there MUST be a hash entry.
+ */
+ BUG();
+}
+
+/*
+ * Initialize the PV part of the mcs_spinlock node.
+ */
+static void pv_init_node(struct mcs_spinlock *node)
+{
+ struct pv_node *pn = (struct pv_node *)node;
+
+ BUILD_BUG_ON(sizeof(struct pv_node) > 5*sizeof(struct mcs_spinlock));
+
+ pn->cpu = smp_processor_id();
+ pn->state = vcpu_running;
+}
+
+/*
+ * Wait for node->locked to become true, halt the vcpu after a short spin.
+ * pv_kick_node() is used to wake the vcpu again.
+ */
+static void pv_wait_node(struct mcs_spinlock *node)
+{
+ struct pv_node *pn = (struct pv_node *)node;
+ int loop;
+
+ for (;;) {
+ for (loop = SPIN_THRESHOLD; loop; loop--) {
+ if (READ_ONCE(node->locked))
+ return;
+ cpu_relax();
+ }
+
+ /*
+ * Order pn->state vs pn->locked thusly:
+ *
+ * [S] pn->state = vcpu_halted [S] next->locked = 1
+ * MB MB
+ * [L] pn->locked [RmW] pn->state = vcpu_running
+ *
+ * Matches the xchg() from pv_kick_node().
+ */
+ smp_store_mb(pn->state, vcpu_halted);
+
+ if (!READ_ONCE(node->locked))
+ pv_wait(&pn->state, vcpu_halted);
+
+ /*
+ * Reset the vCPU state to avoid unncessary CPU kicking
+ */
+ WRITE_ONCE(pn->state, vcpu_running);
+
+ /*
+ * If the locked flag is still not set after wakeup, it is a
+ * spurious wakeup and the vCPU should wait again. However,
+ * there is a pretty high overhead for CPU halting and kicking.
+ * So it is better to spin for a while in the hope that the
+ * MCS lock will be released soon.
+ */
+ }
+ /*
+ * By now our node->locked should be 1 and our caller will not actually
+ * spin-wait for it. We do however rely on our caller to do a
+ * load-acquire for us.
+ */
+}
+
+/*
+ * Called after setting next->locked = 1, used to wake those stuck in
+ * pv_wait_node().
+ */
+static void pv_kick_node(struct mcs_spinlock *node)
+{
+ struct pv_node *pn = (struct pv_node *)node;
+
+ /*
+ * Note that because node->locked is already set, this actual
+ * mcs_spinlock entry could be re-used already.
+ *
+ * This should be fine however, kicking people for no reason is
+ * harmless.
+ *
+ * See the comment in pv_wait_node().
+ */
+ if (xchg(&pn->state, vcpu_running) == vcpu_halted)
+ pv_kick(pn->cpu);
+}
+
+/*
+ * Wait for l->locked to become clear; halt the vcpu after a short spin.
+ * __pv_queued_spin_unlock() will wake us.
+ */
+static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
+{
+ struct pv_node *pn = (struct pv_node *)node;
+ struct __qspinlock *l = (void *)lock;
+ struct qspinlock **lp = NULL;
+ int loop;
+
+ for (;;) {
+ for (loop = SPIN_THRESHOLD; loop; loop--) {
+ if (!READ_ONCE(l->locked))
+ return;
+ cpu_relax();
+ }
+
+ WRITE_ONCE(pn->state, vcpu_halted);
+ if (!lp) { /* ONCE */
+ lp = pv_hash(lock, pn);
+ /*
+ * lp must be set before setting _Q_SLOW_VAL
+ *
+ * [S] lp = lock [RmW] l = l->locked = 0
+ * MB MB
+ * [S] l->locked = _Q_SLOW_VAL [L] lp
+ *
+ * Matches the cmpxchg() in __pv_queued_spin_unlock().
+ */
+ if (!cmpxchg(&l->locked, _Q_LOCKED_VAL, _Q_SLOW_VAL)) {
+ /*
+ * The lock is free and _Q_SLOW_VAL has never
+ * been set. Therefore we need to unhash before
+ * getting the lock.
+ */
+ WRITE_ONCE(*lp, NULL);
+ return;
+ }
+ }
+ pv_wait(&l->locked, _Q_SLOW_VAL);
+
+ /*
+ * The unlocker should have freed the lock before kicking the
+ * CPU. So if the lock is still not free, it is a spurious
+ * wakeup and so the vCPU should wait again after spinning for
+ * a while.
+ */
+ }
+
+ /*
+ * Lock is unlocked now; the caller will acquire it without waiting.
+ * As with pv_wait_node() we rely on the caller to do a load-acquire
+ * for us.
+ */
+}
+
+/*
+ * PV version of the unlock function to be used in stead of
+ * queued_spin_unlock().
+ */
+__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+ struct pv_node *node;
+
+ /*
+ * We must not unlock if SLOW, because in that case we must first
+ * unhash. Otherwise it would be possible to have multiple @lock
+ * entries, which would be BAD.
+ */
+ if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL))
+ return;
+
+ /*
+ * Since the above failed to release, this must be the SLOW path.
+ * Therefore start by looking up the blocked node and unhashing it.
+ */
+ node = pv_unhash(lock);
+
+ /*
+ * Now that we have a reference to the (likely) blocked pv_node,
+ * release the lock.
+ */
+ smp_store_release(&l->locked, 0);
+
+ /*
+ * At this point the memory pointed at by lock can be freed/reused,
+ * however we can still use the pv_node to kick the CPU.
+ */
+ if (READ_ONCE(node->state) == vcpu_halted)
+ pv_kick(node->cpu);
+}
+/*
+ * Include the architecture specific callee-save thunk of the
+ * __pv_queued_spin_unlock(). This thunk is put together with
+ * __pv_queued_spin_unlock() near the top of the file to make sure
+ * that the callee-save thunk and the real unlock function are close
+ * to each other sharing consecutive instruction cachelines.
+ */
+#include <asm/qspinlock_paravirt.h>
+
}
/*
- * We can speed up the acquire/release, if the architecture
- * supports cmpxchg and if there's no debugging state to be set up
+ * We can speed up the acquire/release, if there's no debugging state to be
+ * set up.
*/
-#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
+#ifndef CONFIG_DEBUG_RT_MUTEXES
# define rt_mutex_cmpxchg(l,c,n) (cmpxchg(&l->owner, c, n) == c)
static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
{
}
/*
- * Called by sched_setscheduler() to check whether the priority change
- * is overruled by a possible priority boosting.
+ * Called by sched_setscheduler() to get the priority which will be
+ * effective after the change.
*/
-int rt_mutex_check_prio(struct task_struct *task, int newprio)
+int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
{
if (!task_has_pi_waiters(task))
- return 0;
+ return newprio;
- return task_top_pi_waiter(task)->task->prio <= newprio;
+ if (task_top_pi_waiter(task)->task->prio <= newprio)
+ return task_top_pi_waiter(task)->task->prio;
+ return newprio;
}
/*
set_current_state(state);
/* Setup the timer, when timeout != NULL */
- if (unlikely(timeout)) {
+ if (unlikely(timeout))
hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
- if (!hrtimer_active(&timeout->timer))
- timeout->task = NULL;
- }
ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
*
* @lock: the rt_mutex to be locked
*
+ * This function can only be called in thread context. It's safe to
+ * call it from atomic regions, but not from hard interrupt or soft
+ * interrupt context.
+ *
* Returns 1 on success and 0 on contention
*/
int __sched rt_mutex_trylock(struct rt_mutex *lock)
{
+ if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq()))
+ return 0;
+
return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
}
EXPORT_SYMBOL_GPL(rt_mutex_trylock);
return taken;
}
+/*
+ * Return true if the rwsem has active spinner
+ */
+static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
+{
+ return osq_is_locked(&sem->osq);
+}
+
#else
static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
{
return false;
}
+
+static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
+{
+ return false;
+}
#endif
/*
{
unsigned long flags;
+ /*
+ * If a spinner is present, it is not necessary to do the wakeup.
+ * Try to do wakeup only if the trylock succeeds to minimize
+ * spinlock contention which may introduce too much delay in the
+ * unlock operation.
+ *
+ * spinning writer up_write/up_read caller
+ * --------------- -----------------------
+ * [S] osq_unlock() [L] osq
+ * MB RMB
+ * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock)
+ *
+ * Here, it is important to make sure that there won't be a missed
+ * wakeup while the rwsem is free and the only spinning writer goes
+ * to sleep without taking the rwsem. Even when the spinning writer
+ * is just going to break out of the waiting loop, it will still do
+ * a trylock in rwsem_down_write_failed() before sleeping. IOW, if
+ * rwsem_has_spinner() is true, it will guarantee at least one
+ * trylock attempt on the rwsem later on.
+ */
+ if (rwsem_has_spinner(sem)) {
+ /*
+ * The smp_rmb() here is to make sure that the spinner
+ * state is consulted before reading the wait_lock.
+ */
+ smp_rmb();
+ if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags))
+ return sem;
+ goto locked;
+ }
raw_spin_lock_irqsave(&sem->wait_lock, flags);
+locked:
/* do nothing if list empty */
if (!list_empty(&sem->wait_list))
module_bug_cleanup(mod);
mutex_unlock(&module_mutex);
+ blocking_notifier_call_chain(&module_notify_list,
+ MODULE_STATE_GOING, mod);
+
/* we can't deallocate the module until we clear memory protection */
unset_module_init_ro_nx(mod);
unset_module_core_ro_nx(mod);
struct rcu_torture_ops {
int ttype;
void (*init)(void);
+ void (*cleanup)(void);
int (*readlock)(void);
void (*read_delay)(struct torture_random_state *rrsp);
void (*readunlock)(int idx);
*/
DEFINE_STATIC_SRCU(srcu_ctl);
+static struct srcu_struct srcu_ctld;
+static struct srcu_struct *srcu_ctlp = &srcu_ctl;
-static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
+static int srcu_torture_read_lock(void) __acquires(srcu_ctlp)
{
- return srcu_read_lock(&srcu_ctl);
+ return srcu_read_lock(srcu_ctlp);
}
static void srcu_read_delay(struct torture_random_state *rrsp)
rcu_read_delay(rrsp);
}
-static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
+static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp)
{
- srcu_read_unlock(&srcu_ctl, idx);
+ srcu_read_unlock(srcu_ctlp, idx);
}
static unsigned long srcu_torture_completed(void)
{
- return srcu_batches_completed(&srcu_ctl);
+ return srcu_batches_completed(srcu_ctlp);
}
static void srcu_torture_deferred_free(struct rcu_torture *rp)
{
- call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
+ call_srcu(srcu_ctlp, &rp->rtort_rcu, rcu_torture_cb);
}
static void srcu_torture_synchronize(void)
{
- synchronize_srcu(&srcu_ctl);
+ synchronize_srcu(srcu_ctlp);
}
static void srcu_torture_call(struct rcu_head *head,
void (*func)(struct rcu_head *head))
{
- call_srcu(&srcu_ctl, head, func);
+ call_srcu(srcu_ctlp, head, func);
}
static void srcu_torture_barrier(void)
{
- srcu_barrier(&srcu_ctl);
+ srcu_barrier(srcu_ctlp);
}
static void srcu_torture_stats(void)
{
int cpu;
- int idx = srcu_ctl.completed & 0x1;
+ int idx = srcu_ctlp->completed & 0x1;
pr_alert("%s%s per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
long c0, c1;
- c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
- c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
+ c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx];
+ c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx];
pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
}
pr_cont("\n");
static void srcu_torture_synchronize_expedited(void)
{
- synchronize_srcu_expedited(&srcu_ctl);
+ synchronize_srcu_expedited(srcu_ctlp);
}
static struct rcu_torture_ops srcu_ops = {
.name = "srcu"
};
+static void srcu_torture_init(void)
+{
+ rcu_sync_torture_init();
+ WARN_ON(init_srcu_struct(&srcu_ctld));
+ srcu_ctlp = &srcu_ctld;
+}
+
+static void srcu_torture_cleanup(void)
+{
+ cleanup_srcu_struct(&srcu_ctld);
+ srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
+}
+
+/* As above, but dynamically allocated. */
+static struct rcu_torture_ops srcud_ops = {
+ .ttype = SRCU_FLAVOR,
+ .init = srcu_torture_init,
+ .cleanup = srcu_torture_cleanup,
+ .readlock = srcu_torture_read_lock,
+ .read_delay = srcu_read_delay,
+ .readunlock = srcu_torture_read_unlock,
+ .started = NULL,
+ .completed = srcu_torture_completed,
+ .deferred_free = srcu_torture_deferred_free,
+ .sync = srcu_torture_synchronize,
+ .exp_sync = srcu_torture_synchronize_expedited,
+ .call = srcu_torture_call,
+ .cb_barrier = srcu_torture_barrier,
+ .stats = srcu_torture_stats,
+ .name = "srcud"
+};
+
/*
* Definitions for sched torture testing.
*/
struct rcu_boost_inflight *rbip =
container_of(head, struct rcu_boost_inflight, rcu);
- smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
- rbip->inflight = 0;
+ /* Ensure RCU-core accesses precede clearing ->inflight */
+ smp_store_release(&rbip->inflight, 0);
}
static int rcu_torture_boost(void *arg)
call_rcu_time = jiffies;
while (ULONG_CMP_LT(jiffies, endtime)) {
/* If we don't have a callback in flight, post one. */
- if (!rbi.inflight) {
- smp_mb(); /* RCU core before ->inflight = 1. */
- rbi.inflight = 1;
+ if (!smp_load_acquire(&rbi.inflight)) {
+ /* RCU core before ->inflight = 1. */
+ smp_store_release(&rbi.inflight, 1);
call_rcu(&rbi.rcu, rcu_torture_boost_cb);
if (jiffies - call_rcu_time >
test_boost_duration * HZ - HZ / 2) {
} while (!torture_must_stop());
/* Clean up and exit. */
- while (!kthread_should_stop() || rbi.inflight) {
+ while (!kthread_should_stop() || smp_load_acquire(&rbi.inflight)) {
torture_shutdown_absorb("rcu_torture_boost");
schedule_timeout_uninterruptible(1);
}
- smp_mb(); /* order accesses to ->inflight before stack-frame death. */
destroy_rcu_head_on_stack(&rbi.rcu);
torture_kthread_stopping("rcu_torture_boost");
return 0;
p = rcu_dereference_check(rcu_torture_current,
rcu_read_lock_bh_held() ||
rcu_read_lock_sched_held() ||
- srcu_read_lock_held(&srcu_ctl));
+ srcu_read_lock_held(srcu_ctlp));
if (p == NULL) {
/* Leave because rcu_torture_writer is not yet underway */
cur_ops->readunlock(idx);
p = rcu_dereference_check(rcu_torture_current,
rcu_read_lock_bh_held() ||
rcu_read_lock_sched_held() ||
- srcu_read_lock_held(&srcu_ctl));
+ srcu_read_lock_held(srcu_ctlp));
if (p == NULL) {
/* Wait for rcu_torture_writer to get underway */
cur_ops->readunlock(idx);
do {
wait_event(barrier_cbs_wq[myid],
(newphase =
- ACCESS_ONCE(barrier_phase)) != lastphase ||
+ smp_load_acquire(&barrier_phase)) != lastphase ||
torture_must_stop());
lastphase = newphase;
- smp_mb(); /* ensure barrier_phase load before ->call(). */
if (torture_must_stop())
break;
+ /*
+ * The above smp_load_acquire() ensures barrier_phase load
+ * is ordered before the folloiwng ->call().
+ */
cur_ops->call(&rcu, rcu_torture_barrier_cbf);
if (atomic_dec_and_test(&barrier_cbs_count))
wake_up(&barrier_wq);
do {
atomic_set(&barrier_cbs_invoked, 0);
atomic_set(&barrier_cbs_count, n_barrier_cbs);
- smp_mb(); /* Ensure barrier_phase after prior assignments. */
- barrier_phase = !barrier_phase;
+ /* Ensure barrier_phase ordered after prior assignments. */
+ smp_store_release(&barrier_phase, !barrier_phase);
for (i = 0; i < n_barrier_cbs; i++)
wake_up(&barrier_cbs_wq[i]);
wait_event(barrier_wq,
rcutorture_booster_cleanup(i);
}
- /* Wait for all RCU callbacks to fire. */
-
+ /*
+ * Wait for all RCU callbacks to fire, then do flavor-specific
+ * cleanup operations.
+ */
if (cur_ops->cb_barrier != NULL)
cur_ops->cb_barrier();
+ if (cur_ops->cleanup != NULL)
+ cur_ops->cleanup();
rcu_torture_stats_print(); /* -After- the stats thread is stopped! */
int cpu;
int firsterr = 0;
static struct rcu_torture_ops *torture_ops[] = {
- &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
- RCUTORTURE_TASKS_OPS
+ &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
+ &sched_ops, RCUTORTURE_TASKS_OPS
};
if (!torture_init_begin(torture_type, verbose, &torture_runnable))
if (nreaders >= 0) {
nrealreaders = nreaders;
} else {
- nrealreaders = num_online_cpus() - 1;
+ nrealreaders = num_online_cpus() - 2 - nreaders;
if (nrealreaders <= 0)
nrealreaders = 1;
}
unsigned long t;
for_each_possible_cpu(cpu) {
- t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
+ t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
sum += t;
}
return sum;
unsigned long t;
for_each_possible_cpu(cpu) {
- t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
+ t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
sum += t;
}
return sum;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
- sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
- sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+ sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
+ sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
}
return sum;
}
{
int idx;
- idx = ACCESS_ONCE(sp->completed) & 0x1;
+ idx = READ_ONCE(sp->completed) & 0x1;
preempt_disable();
__this_cpu_inc(sp->per_cpu_ref->c[idx]);
smp_mb(); /* B */ /* Avoid leaking the critical section. */
#include "tiny_plugin.h"
-/*
- * Enter idle, which is an extended quiescent state if we have fully
- * entered that mode.
- */
-void rcu_idle_enter(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_idle_enter);
-
-/*
- * Exit an interrupt handler towards idle.
- */
-void rcu_irq_exit(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_irq_exit);
-
-/*
- * Exit idle, so that we are no longer in an extended quiescent state.
- */
-void rcu_idle_exit(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_idle_exit);
-
-/*
- * Enter an interrupt handler, moving away from idle.
- */
-void rcu_irq_enter(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_irq_enter);
-
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
/*
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
+ if (rcp->donetail == &rcp->rcucblist) {
+ /* No callbacks ready, so just leave. */
+ local_irq_restore(flags);
+ return;
+ }
RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
list = rcp->rcucblist;
rcp->rcucblist = *rcp->donetail;
return;
rcp->ticks_this_gp++;
j = jiffies;
- js = ACCESS_ONCE(rcp->jiffies_stall);
+ js = READ_ONCE(rcp->jiffies_stall);
if (rcp->rcucblist && ULONG_CMP_GE(j, js)) {
pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE,
jiffies - rcp->gp_start, rcp->qlen);
dump_stack();
- ACCESS_ONCE(rcp->jiffies_stall) = jiffies +
- 3 * rcu_jiffies_till_stall_check() + 3;
+ WRITE_ONCE(rcp->jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
} else if (ULONG_CMP_GE(j, js)) {
- ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+ WRITE_ONCE(rcp->jiffies_stall,
+ jiffies + rcu_jiffies_till_stall_check());
}
}
{
rcp->ticks_this_gp = 0;
rcp->gp_start = jiffies;
- ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+ WRITE_ONCE(rcp->jiffies_stall,
+ jiffies + rcu_jiffies_till_stall_check());
}
static void check_cpu_stalls(void)
#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
DEFINE_RCU_TPS(sname) \
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
struct rcu_state sname##_state = { \
.level = { &sname##_state.node[0] }, \
.rda = &sname##_data, \
RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
-static struct rcu_state *rcu_state_p;
+static struct rcu_state *const rcu_state_p;
+static struct rcu_data __percpu *const rcu_data_p;
LIST_HEAD(rcu_struct_flavors);
-/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
-static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF;
+/* Dump rcu_node combining tree at boot to verify correct setup. */
+static bool dump_tree;
+module_param(dump_tree, bool, 0444);
+/* Control rcu_node-tree auto-balancing at boot time. */
+static bool rcu_fanout_exact;
+module_param(rcu_fanout_exact, bool, 0444);
+/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */
+static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
module_param(rcu_fanout_leaf, int, 0444);
int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
/* rcuc/rcub kthread realtime priority */
+#ifdef CONFIG_RCU_KTHREAD_PRIO
static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
+#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */
+static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
+#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */
module_param(kthread_prio, int, 0644);
/* Delay in jiffies for grace-period initialization delays, debug only. */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT
+static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY;
+module_param(gp_preinit_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
+static const int gp_preinit_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
+
#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
module_param(gp_init_delay, int, 0644);
#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
static const int gp_init_delay;
#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
-#define PER_RCU_NODE_PERIOD 10 /* Number of grace periods between delays. */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP
+static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY;
+module_param(gp_cleanup_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
+static const int gp_cleanup_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
+
+/*
+ * Number of grace periods between delays, normalized by the duration of
+ * the delay. The longer the the delay, the more the grace periods between
+ * each delay. The reason for this normalization is that it means that,
+ * for non-zero delays, the overall slowdown of grace periods is constant
+ * regardless of the duration of the delay. This arrangement balances
+ * the need for long delays to increase some race probabilities with the
+ * need for fast grace periods to increase other race probabilities.
+ */
+#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */
/*
* Track the rcutorture test sequence number and the update version
*/
unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
- return ACCESS_ONCE(rnp->qsmaskinitnext);
+ return READ_ONCE(rnp->qsmaskinitnext);
}
/*
- * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s
+ * Return true if an RCU grace period is in progress. The READ_ONCE()s
* permit this function to be invoked without holding the root rcu_node
* structure's ->lock, but of course results can be subject to change.
*/
static int rcu_gp_in_progress(struct rcu_state *rsp)
{
- return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
+ return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
}
/*
if (!(resched_mask & rsp->flavor_mask))
continue;
smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
- if (ACCESS_ONCE(rdp->mynode->completed) !=
- ACCESS_ONCE(rdp->cond_resched_completed))
+ if (READ_ONCE(rdp->mynode->completed) !=
+ READ_ONCE(rdp->cond_resched_completed))
continue;
/*
break;
}
if (rsp != NULL) {
- *flags = ACCESS_ONCE(rsp->gp_flags);
- *gpnum = ACCESS_ONCE(rsp->gpnum);
- *completed = ACCESS_ONCE(rsp->completed);
+ *flags = READ_ONCE(rsp->gp_flags);
+ *gpnum = READ_ONCE(rsp->gpnum);
+ *completed = READ_ONCE(rsp->completed);
return;
}
*flags = 0;
static int rcu_future_needs_gp(struct rcu_state *rsp)
{
struct rcu_node *rnp = rcu_get_root(rsp);
- int idx = (ACCESS_ONCE(rnp->completed) + 1) & 0x1;
+ int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
int *fp = &rnp->need_future_gp[idx];
- return ACCESS_ONCE(*fp);
+ return READ_ONCE(*fp);
}
/*
return 1; /* Yes, this CPU has newly registered callbacks. */
for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
- ULONG_CMP_LT(ACCESS_ONCE(rsp->completed),
+ ULONG_CMP_LT(READ_ONCE(rsp->completed),
rdp->nxtcompleted[i]))
return 1; /* Yes, CBs for future grace period. */
return 0; /* No grace period needed. */
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
- if (!user && !is_idle_task(current)) {
+ if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ !user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
idle_task(smp_processor_id());
smp_mb__before_atomic(); /* See above. */
atomic_inc(&rdtp->dynticks);
smp_mb__after_atomic(); /* Force ordering with next sojourn. */
- WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ atomic_read(&rdtp->dynticks) & 0x1);
rcu_dynticks_task_enter();
/*
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
- WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ (oldval & DYNTICK_TASK_NEST_MASK) == 0);
if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
rdtp->dynticks_nesting = 0;
rcu_eqs_enter_common(oldval, user);
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting--;
- WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ rdtp->dynticks_nesting < 0);
if (rdtp->dynticks_nesting)
trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
else
atomic_inc(&rdtp->dynticks);
/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
smp_mb__after_atomic(); /* See above. */
- WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ !(atomic_read(&rdtp->dynticks) & 0x1));
rcu_cleanup_after_idle();
trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
- if (!user && !is_idle_task(current)) {
+ if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ !user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
idle_task(smp_processor_id());
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
- WARN_ON_ONCE(oldval < 0);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
if (oldval & DYNTICK_TASK_NEST_MASK) {
rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
} else {
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting++;
- WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ rdtp->dynticks_nesting == 0);
if (oldval)
trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
else
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
return 1;
} else {
- if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4,
+ if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
rdp->mynode->gpnum))
- ACCESS_ONCE(rdp->gpwrap) = true;
+ WRITE_ONCE(rdp->gpwrap, true);
return 0;
}
}
if (ULONG_CMP_GE(jiffies,
rdp->rsp->gp_start + jiffies_till_sched_qs) ||
ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
- if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
- ACCESS_ONCE(rdp->cond_resched_completed) =
- ACCESS_ONCE(rdp->mynode->completed);
+ if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
+ WRITE_ONCE(rdp->cond_resched_completed,
+ READ_ONCE(rdp->mynode->completed));
smp_mb(); /* ->cond_resched_completed before *rcrmp. */
- ACCESS_ONCE(*rcrmp) =
- ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask;
+ WRITE_ONCE(*rcrmp,
+ READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask);
resched_cpu(rdp->cpu); /* Force CPU into scheduler. */
rdp->rsp->jiffies_resched += 5; /* Enable beating. */
} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
rsp->gp_start = j;
smp_wmb(); /* Record start time before stall time. */
j1 = rcu_jiffies_till_stall_check();
- ACCESS_ONCE(rsp->jiffies_stall) = j + j1;
+ WRITE_ONCE(rsp->jiffies_stall, j + j1);
rsp->jiffies_resched = j + j1 / 2;
- rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs);
+ rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
}
/*
unsigned long j;
j = jiffies;
- gpa = ACCESS_ONCE(rsp->gp_activity);
+ gpa = READ_ONCE(rsp->gp_activity);
if (j - gpa > 2 * HZ)
- pr_err("%s kthread starved for %ld jiffies!\n",
- rsp->name, j - gpa);
+ pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n",
+ rsp->name, j - gpa,
+ rsp->gpnum, rsp->completed, rsp->gp_flags);
}
/*
/* Only let one CPU complain about others per time interval. */
raw_spin_lock_irqsave(&rnp->lock, flags);
- delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall);
+ delta = jiffies - READ_ONCE(rsp->jiffies_stall);
if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
- ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+ WRITE_ONCE(rsp->jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
/*
if (ndetected) {
rcu_dump_cpu_stacks(rsp);
} else {
- if (ACCESS_ONCE(rsp->gpnum) != gpnum ||
- ACCESS_ONCE(rsp->completed) == gpnum) {
+ if (READ_ONCE(rsp->gpnum) != gpnum ||
+ READ_ONCE(rsp->completed) == gpnum) {
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
- gpa = ACCESS_ONCE(rsp->gp_activity);
+ gpa = READ_ONCE(rsp->gp_activity);
pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
rsp->name, j - gpa, j, gpa,
jiffies_till_next_fqs,
rcu_dump_cpu_stacks(rsp);
raw_spin_lock_irqsave(&rnp->lock, flags);
- if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall)))
- ACCESS_ONCE(rsp->jiffies_stall) = jiffies +
- 3 * rcu_jiffies_till_stall_check() + 3;
+ if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+ WRITE_ONCE(rsp->jiffies_stall,
+ jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
/*
* Given this check, comparisons of jiffies, rsp->jiffies_stall,
* and rsp->gp_start suffice to forestall false positives.
*/
- gpnum = ACCESS_ONCE(rsp->gpnum);
+ gpnum = READ_ONCE(rsp->gpnum);
smp_rmb(); /* Pick up ->gpnum first... */
- js = ACCESS_ONCE(rsp->jiffies_stall);
+ js = READ_ONCE(rsp->jiffies_stall);
smp_rmb(); /* ...then ->jiffies_stall before the rest... */
- gps = ACCESS_ONCE(rsp->gp_start);
+ gps = READ_ONCE(rsp->gp_start);
smp_rmb(); /* ...and finally ->gp_start before ->completed. */
- completed = ACCESS_ONCE(rsp->completed);
+ completed = READ_ONCE(rsp->completed);
if (ULONG_CMP_GE(completed, gpnum) ||
ULONG_CMP_LT(j, js) ||
ULONG_CMP_GE(gps, js))
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
if (rcu_gp_in_progress(rsp) &&
- (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask)) {
+ (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
struct rcu_state *rsp;
for_each_rcu_flavor(rsp)
- ACCESS_ONCE(rsp->jiffies_stall) = jiffies + ULONG_MAX / 2;
+ WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
}
/*
* doing some extra useless work.
*/
if (rnp->gpnum != rnp->completed ||
- ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) {
+ READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) {
rnp->need_future_gp[c & 0x1]++;
trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
goto out;
static void rcu_gp_kthread_wake(struct rcu_state *rsp)
{
if (current == rsp->gp_kthread ||
- !ACCESS_ONCE(rsp->gp_flags) ||
+ !READ_ONCE(rsp->gp_flags) ||
!rsp->gp_kthread)
return;
wake_up(&rsp->gp_wq);
/* Handle the ends of any preceding grace periods first. */
if (rdp->completed == rnp->completed &&
- !unlikely(ACCESS_ONCE(rdp->gpwrap))) {
+ !unlikely(READ_ONCE(rdp->gpwrap))) {
/* No grace period end, so just accelerate recent callbacks. */
ret = rcu_accelerate_cbs(rsp, rnp, rdp);
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
}
- if (rdp->gpnum != rnp->gpnum || unlikely(ACCESS_ONCE(rdp->gpwrap))) {
+ if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
/*
* If the current grace period is waiting for this CPU,
* set up to detect a quiescent state, otherwise don't
rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
zero_cpu_stall_ticks(rdp);
- ACCESS_ONCE(rdp->gpwrap) = false;
+ WRITE_ONCE(rdp->gpwrap, false);
}
return ret;
}
local_irq_save(flags);
rnp = rdp->mynode;
- if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) &&
- rdp->completed == ACCESS_ONCE(rnp->completed) &&
- !unlikely(ACCESS_ONCE(rdp->gpwrap))) || /* w/out lock. */
+ if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
+ rdp->completed == READ_ONCE(rnp->completed) &&
+ !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
!raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
local_irq_restore(flags);
return;
rcu_gp_kthread_wake(rsp);
}
+static void rcu_gp_slow(struct rcu_state *rsp, int delay)
+{
+ if (delay > 0 &&
+ !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+ schedule_timeout_uninterruptible(delay);
+}
+
/*
* Initialize a new grace period. Return 0 if no grace period required.
*/
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
- if (!ACCESS_ONCE(rsp->gp_flags)) {
+ if (!READ_ONCE(rsp->gp_flags)) {
/* Spurious wakeup, tell caller to go back to sleep. */
raw_spin_unlock_irq(&rnp->lock);
return 0;
}
- ACCESS_ONCE(rsp->gp_flags) = 0; /* Clear all flags: New grace period. */
+ WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) {
/*
* will handle subsequent offline CPUs.
*/
rcu_for_each_leaf_node(rsp, rnp) {
+ rcu_gp_slow(rsp, gp_preinit_delay);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
* process finishes, because this kthread handles both.
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
+ rcu_gp_slow(rsp, gp_init_delay);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
rdp = this_cpu_ptr(rsp->rda);
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
- ACCESS_ONCE(rnp->gpnum) = rsp->gpnum;
+ WRITE_ONCE(rnp->gpnum, rsp->gpnum);
if (WARN_ON_ONCE(rnp->completed != rsp->completed))
- ACCESS_ONCE(rnp->completed) = rsp->completed;
+ WRITE_ONCE(rnp->completed, rsp->completed);
if (rnp == rdp->mynode)
(void)__note_gp_changes(rsp, rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
rnp->grphi, rnp->qsmask);
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
- if (gp_init_delay > 0 &&
- !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD)))
- schedule_timeout_uninterruptible(gp_init_delay);
+ WRITE_ONCE(rsp->gp_activity, jiffies);
}
return 1;
unsigned long maxj;
struct rcu_node *rnp = rcu_get_root(rsp);
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
rsp->n_force_qs++;
if (fqs_state == RCU_SAVE_DYNTICK) {
/* Collect dyntick-idle snapshots. */
force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
}
/* Clear flag to prevent immediate re-entry. */
- if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+ if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
- ACCESS_ONCE(rsp->gp_flags) =
- ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS;
+ WRITE_ONCE(rsp->gp_flags,
+ READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
raw_spin_unlock_irq(&rnp->lock);
}
return fqs_state;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
gp_duration = jiffies - rsp->gp_start;
smp_mb__after_unlock_lock();
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
WARN_ON_ONCE(rnp->qsmask);
- ACCESS_ONCE(rnp->completed) = rsp->gpnum;
+ WRITE_ONCE(rnp->completed, rsp->gpnum);
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
+ rcu_gp_slow(rsp, gp_cleanup_delay);
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
rcu_nocb_gp_set(rnp, nocb);
/* Declare grace period done. */
- ACCESS_ONCE(rsp->completed) = rsp->gpnum;
+ WRITE_ONCE(rsp->completed, rsp->gpnum);
trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
rsp->fqs_state = RCU_GP_IDLE;
rdp = this_cpu_ptr(rsp->rda);
/* Advance CBs to reduce false positives below. */
needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
if (needgp || cpu_needs_another_gp(rsp, rdp)) {
- ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
+ WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("newreq"));
}
raw_spin_unlock_irq(&rnp->lock);
/* Handle grace-period start. */
for (;;) {
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("reqwait"));
rsp->gp_state = RCU_GP_WAIT_GPS;
wait_event_interruptible(rsp->gp_wq,
- ACCESS_ONCE(rsp->gp_flags) &
+ READ_ONCE(rsp->gp_flags) &
RCU_GP_FLAG_INIT);
/* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("reqwaitsig"));
}
if (!ret)
rsp->jiffies_force_qs = jiffies + j;
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("fqswait"));
rsp->gp_state = RCU_GP_WAIT_FQS;
ret = wait_event_interruptible_timeout(rsp->gp_wq,
- ((gf = ACCESS_ONCE(rsp->gp_flags)) &
+ ((gf = READ_ONCE(rsp->gp_flags)) &
RCU_GP_FLAG_FQS) ||
- (!ACCESS_ONCE(rnp->qsmask) &&
+ (!READ_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp)),
j);
/* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
- if (!ACCESS_ONCE(rnp->qsmask) &&
+ if (!READ_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
break;
/* If time for quiescent-state forcing, do it. */
if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
(gf & RCU_GP_FLAG_FQS)) {
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("fqsstart"));
fqs_state = rcu_gp_fqs(rsp, fqs_state);
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("fqsend"));
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
} else {
/* Deal with stray signal. */
cond_resched_rcu_qs();
- ACCESS_ONCE(rsp->gp_activity) = jiffies;
+ WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
- ACCESS_ONCE(rsp->gpnum),
+ READ_ONCE(rsp->gpnum),
TPS("fqswaitsig"));
}
j = jiffies_till_next_fqs;
*/
return false;
}
- ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
- trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum),
+ WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
TPS("newreq"));
/*
__releases(rcu_get_root(rsp)->lock)
{
WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+ WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
rcu_gp_kthread_wake(rsp);
}
rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
}
-#ifdef CONFIG_HOTPLUG_CPU
-
/*
* Send the specified CPU's RCU callbacks to the orphanage. The
* specified CPU must be offline, and the caller must hold the
struct rcu_node *rnp, struct rcu_data *rdp)
{
/* No-CBs CPUs do not have orphanable callbacks. */
- if (rcu_is_nocb_cpu(rdp->cpu))
+ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
return;
/*
rsp->qlen += rdp->qlen;
rdp->n_cbs_orphaned += rdp->qlen;
rdp->qlen_lazy = 0;
- ACCESS_ONCE(rdp->qlen) = 0;
+ WRITE_ONCE(rdp->qlen, 0);
}
/*
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
/* No-CBs CPUs are handled specially. */
- if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
+ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+ rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
return;
/* Do the accounting first. */
RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
+ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+ return;
+
RCU_TRACE(mask = rdp->grpmask);
trace_rcu_grace_period(rsp->name,
rnp->gpnum + 1 - !!(rnp->qsmask & mask),
long mask;
struct rcu_node *rnp = rnp_leaf;
- if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+ rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
return;
for (;;) {
mask = rnp->grpmask;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
+ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+ return;
+
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
raw_spin_lock_irqsave(&rnp->lock, flags);
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
+ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+ return;
+
/* Adjust any no-longer-needed kthreads. */
rcu_boost_kthread_setaffinity(rnp, -1);
cpu, rdp->qlen, rdp->nxtlist);
}
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
-{
-}
-
-static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
-{
-}
-
-static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
/*
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Thottle as specified by rdp->blimit.
/* If no callbacks are ready, just return. */
if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
- trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
+ trace_rcu_batch_end(rsp->name, 0, !!READ_ONCE(rdp->nxtlist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
return;
}
smp_mb(); /* List handling before counting for rcu_barrier(). */
rdp->qlen_lazy -= count_lazy;
- ACCESS_ONCE(rdp->qlen) = rdp->qlen - count;
+ WRITE_ONCE(rdp->qlen, rdp->qlen - count);
rdp->n_cbs_invoked += count;
/* Reinstate batch limit if we have worked down the excess. */
mask = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
- if (!rcu_gp_in_progress(rsp)) {
- raw_spin_unlock_irqrestore(&rnp->lock, flags);
- return;
- }
if (rnp->qsmask == 0) {
if (rcu_state_p == &rcu_sched_state ||
rsp != rcu_state_p ||
bit = 1;
for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
if ((rnp->qsmask & bit) != 0) {
- if ((rnp->qsmaskinit & bit) == 0)
- *isidle = false; /* Pending hotplug. */
if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
mask |= bit;
}
/* Funnel through hierarchy to reduce memory contention. */
rnp = __this_cpu_read(rsp->rda->mynode);
for (; rnp != NULL; rnp = rnp->parent) {
- ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
+ ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
!raw_spin_trylock(&rnp->fqslock);
if (rnp_old != NULL)
raw_spin_unlock(&rnp_old->fqslock);
raw_spin_lock_irqsave(&rnp_old->lock, flags);
smp_mb__after_unlock_lock();
raw_spin_unlock(&rnp_old->fqslock);
- if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+ if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
rsp->n_force_qs_lh++;
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
return; /* Someone beat us to it. */
}
- ACCESS_ONCE(rsp->gp_flags) =
- ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS;
+ WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
rcu_gp_kthread_wake(rsp);
}
*/
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
{
- if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active)))
+ if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
return;
if (likely(!rsp->boost)) {
rcu_do_batch(rsp, rdp);
WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */
if (debug_rcu_head_queue(head)) {
/* Probable double call_rcu(), so leak the callback. */
- ACCESS_ONCE(head->func) = rcu_leak_callback;
+ WRITE_ONCE(head->func, rcu_leak_callback);
WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n");
return;
}
if (!likely(rdp->nxtlist))
init_default_callback_list(rdp);
}
- ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1;
+ WRITE_ONCE(rdp->qlen, rdp->qlen + 1);
if (lazy)
rdp->qlen_lazy++;
else
if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start),
(ulong)atomic_long_read(&rsp->expedited_done) +
ULONG_MAX / 8)) {
- synchronize_sched();
+ wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_wrap);
return;
}
}
/* Has another RCU grace period completed? */
- if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
+ if (READ_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
rdp->n_rp_gp_completed++;
return 1;
}
/* Has a new RCU grace period started? */
- if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum ||
- unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* outside lock */
+ if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+ unlikely(READ_ONCE(rdp->gpwrap))) { /* outside lock */
rdp->n_rp_gp_started++;
return 1;
}
* non-NULL, store an indication of whether all callbacks are lazy.
* (If there are no callbacks, all of them are deemed to be lazy.)
*/
-static int __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
+static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
{
bool al = true;
bool hc = false;
{
int cpu;
struct rcu_data *rdp;
- unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done);
+ unsigned long snap = READ_ONCE(rsp->n_barrier_done);
unsigned long snap_done;
_rcu_barrier_trace(rsp, "Begin", -1, snap);
/*
* Increment ->n_barrier_done to avoid duplicate work. Use
- * ACCESS_ONCE() to prevent the compiler from speculating
+ * WRITE_ONCE() to prevent the compiler from speculating
* the increment to precede the early-exit check.
*/
- ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
+ WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
_rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */
__call_rcu(&rdp->barrier_head,
rcu_barrier_callback, rsp, cpu, 0);
}
- } else if (ACCESS_ONCE(rdp->qlen)) {
+ } else if (READ_ONCE(rdp->qlen)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu,
rsp->n_barrier_done);
smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
/* Increment ->n_barrier_done to prevent duplicate work. */
smp_mb(); /* Keep increment after above mechanism. */
- ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
+ WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
_rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
smp_mb(); /* Keep increment before caller's subsequent code. */
rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
rdp->completed = rnp->completed;
rdp->passed_quiesce = false;
- rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+ rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
rdp->qs_pending = false;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
raw_spin_unlock_irqrestore(&rnp->lock, flags);
/*
* Compute the per-level fanout, either using the exact fanout specified
- * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
+ * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
*/
static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
- if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) {
+ if (rcu_fanout_exact) {
rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
for (i = rcu_num_lvls - 2; i >= 0; i--)
- rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+ rsp->levelspread[i] = RCU_FANOUT;
} else {
int ccur;
int cprv;
BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */
- /* Silence gcc 4.8 warning about array index out of range. */
- if (rcu_num_lvls > RCU_NUM_LVLS)
- panic("rcu_init_one: rcu_num_lvls overflow");
+ /* Silence gcc 4.8 false positive about array index out of range. */
+ if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
+ panic("rcu_init_one: rcu_num_lvls out of range");
/* Initialize the level-tracking arrays. */
jiffies_till_next_fqs = d;
/* If the compile-time values are accurate, just leave. */
- if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
+ if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
rcu_capacity[0] = 1;
rcu_capacity[1] = rcu_fanout_leaf;
for (i = 2; i <= MAX_RCU_LVLS; i++)
- rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT;
+ rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
/*
* The boot-time rcu_fanout_leaf parameter is only permitted
* the configured number of CPUs. Complain and fall back to the
* compile-time values if these limits are exceeded.
*/
- if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF ||
+ if (rcu_fanout_leaf < RCU_FANOUT_LEAF ||
rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
n > rcu_capacity[MAX_RCU_LVLS]) {
WARN_ON(1);
rcu_num_nodes -= n;
}
+/*
+ * Dump out the structure of the rcu_node combining tree associated
+ * with the rcu_state structure referenced by rsp.
+ */
+static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
+{
+ int level = 0;
+ struct rcu_node *rnp;
+
+ pr_info("rcu_node tree layout dump\n");
+ pr_info(" ");
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ if (rnp->level != level) {
+ pr_cont("\n");
+ pr_info(" ");
+ level = rnp->level;
+ }
+ pr_cont("%d:%d ^%d ", rnp->grplo, rnp->grphi, rnp->grpnum);
+ }
+ pr_cont("\n");
+}
+
void __init rcu_init(void)
{
int cpu;
rcu_init_geometry();
rcu_init_one(&rcu_bh_state, &rcu_bh_data);
rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+ if (dump_tree)
+ rcu_dump_rcu_node_tree(&rcu_sched_state);
__rcu_init_preempt();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
* In practice, this did work well going from three levels to four.
* Of course, your mileage may vary.
*/
+
#define MAX_RCU_LVLS 4
-#define RCU_FANOUT_1 (CONFIG_RCU_FANOUT_LEAF)
-#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
+
+#ifdef CONFIG_RCU_FANOUT
+#define RCU_FANOUT CONFIG_RCU_FANOUT
+#else /* #ifdef CONFIG_RCU_FANOUT */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT 64
+# else
+# define RCU_FANOUT 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT */
+
+#ifdef CONFIG_RCU_FANOUT_LEAF
+#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
+#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT_LEAF 64
+# else
+# define RCU_FANOUT_LEAF 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
+
+#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
+#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
+#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
#if NR_CPUS <= RCU_FANOUT_1
# define RCU_NUM_LVLS 1
/* if there is no such task. If there */
/* is no current expedited grace period, */
/* then there can cannot be any such task. */
-#ifdef CONFIG_RCU_BOOST
struct list_head *boost_tasks;
/* Pointer to first task that needs to be */
/* priority boosted, or NULL if no priority */
unsigned long n_balk_nos;
/* Refused to boost: not sure why, though. */
/* This can happen due to race conditions. */
-#endif /* #ifdef CONFIG_RCU_BOOST */
#ifdef CONFIG_RCU_NOCB_CPU
wait_queue_head_t nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
* RCU implementation internal declarations:
*/
extern struct rcu_state rcu_sched_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
extern struct rcu_state rcu_bh_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
#ifdef CONFIG_PREEMPT_RCU
extern struct rcu_state rcu_preempt_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DEFINE_PER_CPU(char, rcu_cpu_has_work);
-#endif /* #ifdef CONFIG_RCU_BOOST */
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
+ * all uses are in dead code. Provide a definition to keep the compiler
+ * happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
+ * This probably needs to be excluded from -rt builds.
+ */
+#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
+
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
#ifdef CONFIG_RCU_NOCB_CPU
static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
{
if (IS_ENABLED(CONFIG_RCU_TRACE))
pr_info("\tRCU debugfs-based tracing is enabled.\n");
- if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) ||
- (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32))
+ if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
+ (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
- CONFIG_RCU_FANOUT);
- if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT))
+ RCU_FANOUT);
+ if (rcu_fanout_exact)
pr_info("\tHierarchical RCU autobalancing is disabled.\n");
if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
pr_info("\tAdditional per-CPU info printed with stalls.\n");
if (NUM_RCU_LVL_4 != 0)
pr_info("\tFour-level hierarchy is enabled.\n");
- if (CONFIG_RCU_FANOUT_LEAF != 16)
+ if (RCU_FANOUT_LEAF != 16)
pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
- CONFIG_RCU_FANOUT_LEAF);
- if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
+ RCU_FANOUT_LEAF);
+ if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
if (nr_cpu_ids != NR_CPUS)
pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
#ifdef CONFIG_PREEMPT_RCU
RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
-static struct rcu_state *rcu_state_p = &rcu_preempt_state;
+static struct rcu_state *const rcu_state_p = &rcu_preempt_state;
+static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
static int rcu_preempted_readers_exp(struct rcu_node *rnp);
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
*/
static void rcu_preempt_qs(void)
{
- if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) {
+ if (!__this_cpu_read(rcu_data_p->passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_preempt"),
- __this_cpu_read(rcu_preempt_data.gpnum),
+ __this_cpu_read(rcu_data_p->gpnum),
TPS("cpuqs"));
- __this_cpu_write(rcu_preempt_data.passed_quiesce, 1);
+ __this_cpu_write(rcu_data_p->passed_quiesce, 1);
barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
current->rcu_read_unlock_special.b.need_qs = false;
}
!t->rcu_read_unlock_special.b.blocked) {
/* Possibly blocking in an RCU read-side critical section. */
- rdp = this_cpu_ptr(rcu_preempt_state.rda);
+ rdp = this_cpu_ptr(rcu_state_p->rda);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
rnp->gp_tasks = &t->rcu_node_entry;
-#ifdef CONFIG_RCU_BOOST
- if (rnp->boost_tasks != NULL)
+ if (IS_ENABLED(CONFIG_RCU_BOOST) &&
+ rnp->boost_tasks != NULL)
rnp->boost_tasks = rnp->gp_tasks;
-#endif /* #ifdef CONFIG_RCU_BOOST */
} else {
list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
if (rnp->qsmask & rdp->grpmask)
bool empty_exp_now;
unsigned long flags;
struct list_head *np;
-#ifdef CONFIG_RCU_BOOST
bool drop_boost_mutex = false;
-#endif /* #ifdef CONFIG_RCU_BOOST */
struct rcu_node *rnp;
union rcu_special special;
t->rcu_read_unlock_special.b.blocked = false;
/*
- * Remove this task from the list it blocked on. The
- * task can migrate while we acquire the lock, but at
- * most one time. So at most two passes through loop.
+ * Remove this task from the list it blocked on. The task
+ * now remains queued on the rcu_node corresponding to
+ * the CPU it first blocked on, so the first attempt to
+ * acquire the task's rcu_node's ->lock will succeed.
+ * Keep the loop and add a WARN_ON() out of sheer paranoia.
*/
for (;;) {
rnp = t->rcu_blocked_node;
smp_mb__after_unlock_lock();
if (rnp == t->rcu_blocked_node)
break;
+ WARN_ON_ONCE(1);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
rnp->gp_tasks = np;
if (&t->rcu_node_entry == rnp->exp_tasks)
rnp->exp_tasks = np;
-#ifdef CONFIG_RCU_BOOST
- if (&t->rcu_node_entry == rnp->boost_tasks)
- rnp->boost_tasks = np;
- /* Snapshot ->boost_mtx ownership with rcu_node lock held. */
- drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
-#endif /* #ifdef CONFIG_RCU_BOOST */
+ if (IS_ENABLED(CONFIG_RCU_BOOST)) {
+ if (&t->rcu_node_entry == rnp->boost_tasks)
+ rnp->boost_tasks = np;
+ /* Snapshot ->boost_mtx ownership w/rnp->lock held. */
+ drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
+ }
/*
* If this was the last task on the current list, and if
rnp->grplo,
rnp->grphi,
!!rnp->gp_tasks);
- rcu_report_unblock_qs_rnp(&rcu_preempt_state,
- rnp, flags);
+ rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags);
} else {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
-#ifdef CONFIG_RCU_BOOST
/* Unboost if we were boosted. */
- if (drop_boost_mutex)
+ if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
rt_mutex_unlock(&rnp->boost_mtx);
-#endif /* #ifdef CONFIG_RCU_BOOST */
/*
* If this was the last task on the expedited lists,
* then we need to report up the rcu_node hierarchy.
*/
if (!empty_exp && empty_exp_now)
- rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
+ rcu_report_exp_rnp(rcu_state_p, rnp, true);
} else {
local_irq_restore(flags);
}
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
- t = list_entry(rnp->gp_tasks,
+ t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
sched_show_task(t);
if (!rcu_preempt_blocked_readers_cgp(rnp))
return 0;
rcu_print_task_stall_begin(rnp);
- t = list_entry(rnp->gp_tasks,
+ t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
return;
}
if (t->rcu_read_lock_nesting > 0 &&
- __this_cpu_read(rcu_preempt_data.qs_pending) &&
- !__this_cpu_read(rcu_preempt_data.passed_quiesce))
+ __this_cpu_read(rcu_data_p->qs_pending) &&
+ !__this_cpu_read(rcu_data_p->passed_quiesce))
t->rcu_read_unlock_special.b.need_qs = true;
}
static void rcu_preempt_do_callbacks(void)
{
- rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
+ rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
}
#endif /* #ifdef CONFIG_RCU_BOOST */
*/
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
- __call_rcu(head, func, &rcu_preempt_state, -1, 0);
+ __call_rcu(head, func, rcu_state_p, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu);
static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
return !rcu_preempted_readers_exp(rnp) &&
- ACCESS_ONCE(rnp->expmask) == 0;
+ READ_ONCE(rnp->expmask) == 0;
}
/*
void synchronize_rcu_expedited(void)
{
struct rcu_node *rnp;
- struct rcu_state *rsp = &rcu_preempt_state;
+ struct rcu_state *rsp = rcu_state_p;
unsigned long snap;
int trycount = 0;
smp_mb(); /* Caller's modifications seen first by other CPUs. */
- snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
+ snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1;
smp_mb(); /* Above access cannot bleed into critical section. */
/*
*/
while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
if (ULONG_CMP_LT(snap,
- ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+ READ_ONCE(sync_rcu_preempt_exp_count))) {
put_online_cpus();
goto mb_ret; /* Others did our work for us. */
}
return;
}
}
- if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+ if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) {
put_online_cpus();
goto unlock_mb_ret; /* Others did our work for us. */
}
/* Clean up and exit. */
smp_mb(); /* ensure expedited GP seen before counter increment. */
- ACCESS_ONCE(sync_rcu_preempt_exp_count) =
- sync_rcu_preempt_exp_count + 1;
+ WRITE_ONCE(sync_rcu_preempt_exp_count, sync_rcu_preempt_exp_count + 1);
unlock_mb_ret:
mutex_unlock(&sync_rcu_preempt_exp_mutex);
mb_ret:
*/
void rcu_barrier(void)
{
- _rcu_barrier(&rcu_preempt_state);
+ _rcu_barrier(rcu_state_p);
}
EXPORT_SYMBOL_GPL(rcu_barrier);
*/
static void __init __rcu_init_preempt(void)
{
- rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
+ rcu_init_one(rcu_state_p, rcu_data_p);
}
/*
#else /* #ifdef CONFIG_PREEMPT_RCU */
-static struct rcu_state *rcu_state_p = &rcu_sched_state;
+static struct rcu_state *const rcu_state_p = &rcu_sched_state;
+static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data;
/*
* Tell them what RCU they are running.
struct task_struct *t;
struct list_head *tb;
- if (ACCESS_ONCE(rnp->exp_tasks) == NULL &&
- ACCESS_ONCE(rnp->boost_tasks) == NULL)
+ if (READ_ONCE(rnp->exp_tasks) == NULL &&
+ READ_ONCE(rnp->boost_tasks) == NULL)
return 0; /* Nothing left to boost. */
raw_spin_lock_irqsave(&rnp->lock, flags);
rt_mutex_lock(&rnp->boost_mtx);
rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */
- return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
- ACCESS_ONCE(rnp->boost_tasks) != NULL;
+ return READ_ONCE(rnp->exp_tasks) != NULL ||
+ READ_ONCE(rnp->boost_tasks) != NULL;
}
/*
struct sched_param sp;
struct task_struct *t;
- if (&rcu_preempt_state != rsp)
+ if (rcu_state_p != rsp)
return 0;
if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0)
* Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
* any flavor of RCU.
*/
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *delta_jiffies)
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
{
- *delta_jiffies = ULONG_MAX;
- return rcu_cpu_has_callbacks(NULL);
+ *nextevt = KTIME_MAX;
+ return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)
+ ? 0 : rcu_cpu_has_callbacks(NULL);
}
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
module_param(rcu_idle_lazy_gp_delay, int, 0644);
-extern int tick_nohz_active;
-
/*
* Try to advance callbacks for all flavors of RCU on the current CPU, but
* only if it has been awhile since the last time we did so. Afterwards,
* callbacks not yet ready to invoke.
*/
if ((rdp->completed != rnp->completed ||
- unlikely(ACCESS_ONCE(rdp->gpwrap))) &&
+ unlikely(READ_ONCE(rdp->gpwrap))) &&
rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
note_gp_changes(rsp, rdp);
*
* The caller must have disabled interrupts.
*/
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
-int rcu_needs_cpu(unsigned long *dj)
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ unsigned long dj;
+
+ if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) {
+ *nextevt = KTIME_MAX;
+ return 0;
+ }
/* Snapshot to detect later posting of non-lazy callback. */
rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
/* If no callbacks, RCU doesn't need the CPU. */
if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) {
- *dj = ULONG_MAX;
+ *nextevt = KTIME_MAX;
return 0;
}
/* Request timer delay depending on laziness, and round. */
if (!rdtp->all_lazy) {
- *dj = round_up(rcu_idle_gp_delay + jiffies,
+ dj = round_up(rcu_idle_gp_delay + jiffies,
rcu_idle_gp_delay) - jiffies;
} else {
- *dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
+ dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
}
+ *nextevt = basemono + dj * TICK_NSEC;
return 0;
}
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Prepare a CPU for idle from an RCU perspective. The first major task
*/
static void rcu_prepare_for_idle(void)
{
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
bool needwake;
struct rcu_data *rdp;
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
struct rcu_state *rsp;
int tne;
+ if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL))
+ return;
+
/* Handle nohz enablement switches conservatively. */
- tne = ACCESS_ONCE(tick_nohz_active);
+ tne = READ_ONCE(tick_nohz_active);
if (tne != rdtp->tick_nohz_enabled_snap) {
if (rcu_cpu_has_callbacks(NULL))
invoke_rcu_core(); /* force nohz to see update. */
if (needwake)
rcu_gp_kthread_wake(rsp);
}
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
}
/*
*/
static void rcu_cleanup_after_idle(void)
{
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
- if (rcu_is_nocb_cpu(smp_processor_id()))
+ if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
+ rcu_is_nocb_cpu(smp_processor_id()))
return;
if (rcu_try_advance_all_cbs())
invoke_rcu_core();
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
}
/*
atomic_read(&rdtp->dynticks) & 0xfff,
rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
- ACCESS_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
+ READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
fast_no_hz);
}
{
struct rcu_data *rdp_leader = rdp->nocb_leader;
- if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
+ if (!READ_ONCE(rdp_leader->nocb_kthread))
return;
- if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
+ if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
/* Prior smp_mb__after_atomic() orders against prior enqueue. */
- ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
+ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
wake_up(&rdp_leader->nocb_wq);
}
}
ret = atomic_long_read(&rdp->nocb_q_count);
#ifdef CONFIG_PROVE_RCU
- rhp = ACCESS_ONCE(rdp->nocb_head);
+ rhp = READ_ONCE(rdp->nocb_head);
if (!rhp)
- rhp = ACCESS_ONCE(rdp->nocb_gp_head);
+ rhp = READ_ONCE(rdp->nocb_gp_head);
if (!rhp)
- rhp = ACCESS_ONCE(rdp->nocb_follower_head);
+ rhp = READ_ONCE(rdp->nocb_follower_head);
/* Having no rcuo kthread but CBs after scheduler starts is bad! */
- if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp &&
+ if (!READ_ONCE(rdp->nocb_kthread) && rhp &&
rcu_scheduler_fully_active) {
/* RCU callback enqueued before CPU first came online??? */
pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
atomic_long_add(rhcount, &rdp->nocb_q_count);
/* rcu_barrier() relies on ->nocb_q_count add before xchg. */
old_rhpp = xchg(&rdp->nocb_tail, rhtp);
- ACCESS_ONCE(*old_rhpp) = rhp;
+ WRITE_ONCE(*old_rhpp, rhp);
atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */
/* If we are not being polled and there is a kthread, awaken it ... */
- t = ACCESS_ONCE(rdp->nocb_kthread);
+ t = READ_ONCE(rdp->nocb_kthread);
if (rcu_nocb_poll || !t) {
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeNotPoll"));
for (;;) {
wait_event_interruptible(
rnp->nocb_gp_wq[c & 0x1],
- (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c)));
+ (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
if (likely(d))
break;
WARN_ON(signal_pending(current));
if (!rcu_nocb_poll) {
trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
wait_event_interruptible(my_rdp->nocb_wq,
- !ACCESS_ONCE(my_rdp->nocb_leader_sleep));
+ !READ_ONCE(my_rdp->nocb_leader_sleep));
/* Memory barrier handled by smp_mb() calls below and repoll. */
} else if (firsttime) {
firsttime = false; /* Don't drown trace log with "Poll"! */
*/
gotcbs = false;
for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
- rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head);
+ rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head);
if (!rdp->nocb_gp_head)
continue; /* No CBs here, try next follower. */
/* Move callbacks to wait-for-GP list, which is empty. */
- ACCESS_ONCE(rdp->nocb_head) = NULL;
+ WRITE_ONCE(rdp->nocb_head, NULL);
rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
gotcbs = true;
}
my_rdp->nocb_leader_sleep = true;
smp_mb(); /* Ensure _sleep true before scan. */
for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
- if (ACCESS_ONCE(rdp->nocb_head)) {
+ if (READ_ONCE(rdp->nocb_head)) {
/* Found CB, so short-circuit next wait. */
my_rdp->nocb_leader_sleep = false;
break;
/* Each pass through the following loop wakes a follower, if needed. */
for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
- if (ACCESS_ONCE(rdp->nocb_head))
+ if (READ_ONCE(rdp->nocb_head))
my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/
if (!rdp->nocb_gp_head)
continue; /* No CBs, so no need to wake follower. */
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
"FollowerSleep");
wait_event_interruptible(rdp->nocb_wq,
- ACCESS_ONCE(rdp->nocb_follower_head));
+ READ_ONCE(rdp->nocb_follower_head));
} else if (firsttime) {
/* Don't drown trace log with "Poll"! */
firsttime = false;
nocb_follower_wait(rdp);
/* Pull the ready-to-invoke callbacks onto local list. */
- list = ACCESS_ONCE(rdp->nocb_follower_head);
+ list = READ_ONCE(rdp->nocb_follower_head);
BUG_ON(!list);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty");
- ACCESS_ONCE(rdp->nocb_follower_head) = NULL;
+ WRITE_ONCE(rdp->nocb_follower_head, NULL);
tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head);
/* Each pass through the following loop invokes a callback. */
/* Is a deferred wakeup of rcu_nocb_kthread() required? */
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
{
- return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+ return READ_ONCE(rdp->nocb_defer_wakeup);
}
/* Do a deferred wakeup of rcu_nocb_kthread(). */
if (!rcu_nocb_need_deferred_wakeup(rdp))
return;
- ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup);
- ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT;
+ ndw = READ_ONCE(rdp->nocb_defer_wakeup);
+ WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_NOT);
wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake"));
}
t = kthread_run(rcu_nocb_kthread, rdp_spawn,
"rcuo%c/%d", rsp->abbr, cpu);
BUG_ON(IS_ERR(t));
- ACCESS_ONCE(rdp_spawn->nocb_kthread) = t;
+ WRITE_ONCE(rdp_spawn->nocb_kthread, t);
}
/*
/* Record start of fully idle period. */
j = jiffies;
- ACCESS_ONCE(rdtp->dynticks_idle_jiffies) = j;
+ WRITE_ONCE(rdtp->dynticks_idle_jiffies, j);
smp_mb__before_atomic();
atomic_inc(&rdtp->dynticks_idle);
smp_mb__after_atomic();
*/
void rcu_sysidle_force_exit(void)
{
- int oldstate = ACCESS_ONCE(full_sysidle_state);
+ int oldstate = READ_ONCE(full_sysidle_state);
int newoldstate;
/*
smp_mb(); /* Read counters before timestamps. */
/* Pick up timestamps. */
- j = ACCESS_ONCE(rdtp->dynticks_idle_jiffies);
+ j = READ_ONCE(rdtp->dynticks_idle_jiffies);
/* If this CPU entered idle more recently, update maxj timestamp. */
if (ULONG_CMP_LT(*maxj, j))
*maxj = j;
static void rcu_sysidle(unsigned long j)
{
/* Check the current state. */
- switch (ACCESS_ONCE(full_sysidle_state)) {
+ switch (READ_ONCE(full_sysidle_state)) {
case RCU_SYSIDLE_NOT:
/* First time all are idle, so note a short idle period. */
- ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_SHORT;
+ WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_SHORT);
break;
case RCU_SYSIDLE_SHORT:
{
smp_mb();
if (full_sysidle_state > RCU_SYSIDLE_SHORT)
- ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT;
+ WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_NOT);
}
/*
smp_mb(); /* grace period precedes setting inuse. */
rshp = container_of(rhp, struct rcu_sysidle_head, rh);
- ACCESS_ONCE(rshp->inuse) = 0;
+ WRITE_ONCE(rshp->inuse, 0);
}
/*
bool rcu_sys_is_idle(void)
{
static struct rcu_sysidle_head rsh;
- int rss = ACCESS_ONCE(full_sysidle_state);
+ int rss = READ_ONCE(full_sysidle_state);
if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu))
return false;
}
rcu_sysidle_report(rcu_state_p, isidle, maxj, false);
oldrss = rss;
- rss = ACCESS_ONCE(full_sysidle_state);
+ rss = READ_ONCE(full_sysidle_state);
}
}
#ifdef CONFIG_NO_HZ_FULL
if (tick_nohz_full_cpu(smp_processor_id()) &&
(!rcu_gp_in_progress(rsp) ||
- ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
- return 1;
+ ULONG_CMP_LT(jiffies, READ_ONCE(rsp->gp_start) + HZ)))
+ return true;
#endif /* #ifdef CONFIG_NO_HZ_FULL */
- return 0;
+ return false;
}
/*
static void rcu_dynticks_task_enter(void)
{
#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
- ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id();
+ WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
}
static void rcu_dynticks_task_exit(void)
{
#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
- ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1;
+ WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
}
seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
- ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
+ READ_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
struct rcu_node *rnp = &rsp->node[0];
raw_spin_lock_irqsave(&rnp->lock, flags);
- completed = ACCESS_ONCE(rsp->completed);
- gpnum = ACCESS_ONCE(rsp->gpnum);
+ completed = READ_ONCE(rsp->completed);
+ gpnum = READ_ONCE(rsp->gpnum);
if (completed == gpnum)
gpage = 0;
else
barrier(); /* critical section before exit code. */
t->rcu_read_lock_nesting = INT_MIN;
barrier(); /* assign before ->rcu_read_unlock_special load */
- if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s)))
+ if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
rcu_read_unlock_special(t);
barrier(); /* ->rcu_read_unlock_special load before assign */
t->rcu_read_lock_nesting = 0;
}
#ifdef CONFIG_PROVE_LOCKING
{
- int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
+ int rrln = READ_ONCE(t->rcu_read_lock_nesting);
WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
}
int rcu_jiffies_till_stall_check(void)
{
- int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);
+ int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
/*
* Limit check must be consistent with the Kconfig limits
* for CONFIG_RCU_CPU_STALL_TIMEOUT.
*/
if (till_stall_check < 3) {
- ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
+ WRITE_ONCE(rcu_cpu_stall_timeout, 3);
till_stall_check = 3;
} else if (till_stall_check > 300) {
- ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
+ WRITE_ONCE(rcu_cpu_stall_timeout, 300);
till_stall_check = 300;
}
return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
{
int cpu;
- if (!ACCESS_ONCE(t->rcu_tasks_holdout) ||
- t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) ||
- !ACCESS_ONCE(t->on_rq) ||
+ if (!READ_ONCE(t->rcu_tasks_holdout) ||
+ t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
+ !READ_ONCE(t->on_rq) ||
(IS_ENABLED(CONFIG_NO_HZ_FULL) &&
!is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
- ACCESS_ONCE(t->rcu_tasks_holdout) = false;
+ WRITE_ONCE(t->rcu_tasks_holdout, false);
list_del_init(&t->rcu_tasks_holdout_list);
put_task_struct(t);
return;
*/
rcu_read_lock();
for_each_process_thread(g, t) {
- if (t != current && ACCESS_ONCE(t->on_rq) &&
+ if (t != current && READ_ONCE(t->on_rq) &&
!is_idle_task(t)) {
get_task_struct(t);
- t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw);
- ACCESS_ONCE(t->rcu_tasks_holdout) = true;
+ t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
+ WRITE_ONCE(t->rcu_tasks_holdout, true);
list_add(&t->rcu_tasks_holdout_list,
&rcu_tasks_holdouts);
}
struct task_struct *t1;
schedule_timeout_interruptible(HZ);
- rtst = ACCESS_ONCE(rcu_task_stall_timeout);
+ rtst = READ_ONCE(rcu_task_stall_timeout);
needreport = rtst > 0 &&
time_after(jiffies, lastreport + rtst);
if (needreport)
static struct task_struct *rcu_tasks_kthread_ptr;
struct task_struct *t;
- if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) {
+ if (READ_ONCE(rcu_tasks_kthread_ptr)) {
smp_mb(); /* Ensure caller sees full kthread. */
return;
}
t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
BUG_ON(IS_ERR(t));
smp_mb(); /* Ensure others see full kthread. */
- ACCESS_ONCE(rcu_tasks_kthread_ptr) = t;
+ WRITE_ONCE(rcu_tasks_kthread_ptr, t);
mutex_unlock(&rcu_tasks_kthread_mutex);
}
CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
endif
-obj-y += core.o proc.o clock.o cputime.o
+obj-y += core.o loadavg.o clock.o cputime.o
obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
obj-y += wait.o completion.o idle.o
obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
-#ifdef CONFIG_SCHED_AUTOGROUP
-
#include "sched.h"
#include <linux/proc_fs.h>
p->signal->autogroup = autogroup_kref_get(ag);
- if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+ if (!READ_ONCE(sysctl_sched_autogroup_enabled))
goto out;
for_each_thread(p, t)
return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
}
#endif /* CONFIG_SCHED_DEBUG */
-
-#endif /* CONFIG_SCHED_AUTOGROUP */
static inline struct task_group *
autogroup_task_group(struct task_struct *p, struct task_group *tg)
{
- int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+ int enabled = READ_ONCE(sysctl_sched_autogroup_enabled);
if (enabled && task_wants_autogroup(p, tg))
return p->signal->autogroup->tg;
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
-void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
-{
- unsigned long delta;
- ktime_t soft, hard, now;
-
- for (;;) {
- if (hrtimer_active(period_timer))
- break;
-
- now = hrtimer_cb_get_time(period_timer);
- hrtimer_forward(period_timer, now, period);
-
- soft = hrtimer_get_softexpires(period_timer);
- hard = hrtimer_get_expires(period_timer);
- delta = ktime_to_ns(ktime_sub(hard, soft));
- __hrtimer_start_range_ns(period_timer, soft, delta,
- HRTIMER_MODE_ABS_PINNED, 0);
- }
-}
-
DEFINE_MUTEX(sched_domains_mutex);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#ifdef CONFIG_SMP
-static int __hrtick_restart(struct rq *rq)
+static void __hrtick_restart(struct rq *rq)
{
struct hrtimer *timer = &rq->hrtick_timer;
- ktime_t time = hrtimer_get_softexpires(timer);
- return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
}
/*
* doesn't make sense. Rely on vruntime for fairness.
*/
delay = max_t(u64, delay, 10000LL);
- __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
+ HRTIMER_MODE_REL_PINNED);
}
static inline void init_hrtick(void)
static bool set_nr_if_polling(struct task_struct *p)
{
struct thread_info *ti = task_thread_info(p);
- typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags);
+ typeof(ti->flags) old, val = READ_ONCE(ti->flags);
for (;;) {
if (!(val & _TIF_POLLING_NRFLAG))
#endif
#endif
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+ struct wake_q_node *node = &task->wake_q;
+
+ /*
+ * Atomically grab the task, if ->wake_q is !nil already it means
+ * its already queued (either by us or someone else) and will get the
+ * wakeup due to that.
+ *
+ * This cmpxchg() implies a full barrier, which pairs with the write
+ * barrier implied by the wakeup in wake_up_list().
+ */
+ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+ return;
+
+ get_task_struct(task);
+
+ /*
+ * The head is context local, there can be no concurrency.
+ */
+ *head->lastp = node;
+ head->lastp = &node->next;
+}
+
+void wake_up_q(struct wake_q_head *head)
+{
+ struct wake_q_node *node = head->first;
+
+ while (node != WAKE_Q_TAIL) {
+ struct task_struct *task;
+
+ task = container_of(node, struct task_struct, wake_q);
+ BUG_ON(!task);
+ /* task can safely be re-inserted now */
+ node = node->next;
+ task->wake_q.next = NULL;
+
+ /*
+ * wake_up_process() implies a wmb() to pair with the queueing
+ * in wake_q_add() so as not to miss wakeups.
+ */
+ wake_up_process(task);
+ put_task_struct(task);
+ }
+}
+
/*
* resched_curr - mark rq's current task 'to be rescheduled now'.
*
* selecting an idle cpu will add more delays to the timers than intended
* (as that cpu's timer base may not be uptodate wrt jiffies etc).
*/
-int get_nohz_timer_target(int pinned)
+int get_nohz_timer_target(void)
{
- int cpu = smp_processor_id();
- int i;
+ int i, cpu = smp_processor_id();
struct sched_domain *sd;
- if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu))
+ if (!idle_cpu(cpu))
return cpu;
rcu_read_lock();
if (p->sched_class->migrate_task_rq)
p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
- perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+ perf_event_task_migrate(p);
}
__set_task_cpu(p, new_cpu);
#ifdef CONFIG_PREEMPT_NOTIFIERS
+static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;
+
/**
* preempt_notifier_register - tell me when current is being preempted & rescheduled
* @notifier: notifier struct to register
*/
void preempt_notifier_register(struct preempt_notifier *notifier)
{
+ static_key_slow_inc(&preempt_notifier_key);
hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
}
EXPORT_SYMBOL_GPL(preempt_notifier_register);
* preempt_notifier_unregister - no longer interested in preemption notifications
* @notifier: notifier struct to unregister
*
- * This is safe to call from within a preemption notifier.
+ * This is *not* safe to call from within a preemption notifier.
*/
void preempt_notifier_unregister(struct preempt_notifier *notifier)
{
hlist_del(¬ifier->link);
+ static_key_slow_dec(&preempt_notifier_key);
}
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
struct preempt_notifier *notifier;
notifier->ops->sched_in(notifier, raw_smp_processor_id());
}
+static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+ if (static_key_false(&preempt_notifier_key))
+ __fire_sched_in_preempt_notifiers(curr);
+}
+
static void
-fire_sched_out_preempt_notifiers(struct task_struct *curr,
- struct task_struct *next)
+__fire_sched_out_preempt_notifiers(struct task_struct *curr,
+ struct task_struct *next)
{
struct preempt_notifier *notifier;
notifier->ops->sched_out(notifier, next);
}
+static __always_inline void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+ struct task_struct *next)
+{
+ if (static_key_false(&preempt_notifier_key))
+ __fire_sched_out_preempt_notifiers(curr, next);
+}
+
#else /* !CONFIG_PREEMPT_NOTIFIERS */
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
}
-static void
+static inline void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
struct task_struct *next)
{
void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
- struct rq *this = this_rq();
- *nr_waiters = atomic_read(&this->nr_iowait);
- *load = this->cpu_load[0];
+ struct rq *rq = this_rq();
+ *nr_waiters = atomic_read(&rq->nr_iowait);
+ *load = rq->load.weight;
}
#ifdef CONFIG_SMP
update_rq_clock(rq);
curr->sched_class->task_tick(rq, curr, 0);
update_cpu_load_active(rq);
+ calc_global_load_tick(rq);
raw_spin_unlock(&rq->lock);
perf_event_task_tick();
u64 scheduler_tick_max_deferment(void)
{
struct rq *rq = this_rq();
- unsigned long next, now = ACCESS_ONCE(jiffies);
+ unsigned long next, now = READ_ONCE(jiffies);
next = rq->last_sched_tick + HZ;
* - return from syscall or exception to user-space
* - return from interrupt-handler to user-space
*
- * WARNING: all callers must re-check need_resched() afterward and reschedule
- * accordingly in case an event triggered the need for rescheduling (such as
- * an interrupt waking up a task) while preemption was disabled in __schedule().
+ * WARNING: must be called with preemption disabled!
*/
static void __sched __schedule(void)
{
struct rq *rq;
int cpu;
- preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
rcu_note_context_switch();
raw_spin_unlock_irq(&rq->lock);
post_schedule(rq);
-
- sched_preempt_enable_no_resched();
}
static inline void sched_submit_work(struct task_struct *tsk)
sched_submit_work(tsk);
do {
+ preempt_disable();
__schedule();
+ sched_preempt_enable_no_resched();
} while (need_resched());
}
EXPORT_SYMBOL(schedule);
static void __sched notrace preempt_schedule_common(void)
{
do {
- __preempt_count_add(PREEMPT_ACTIVE);
+ preempt_active_enter();
__schedule();
- __preempt_count_sub(PREEMPT_ACTIVE);
+ preempt_active_exit();
/*
* Check again in case we missed a preemption opportunity
* between schedule and now.
*/
- barrier();
} while (need_resched());
}
NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
/**
- * preempt_schedule_context - preempt_schedule called by tracing
+ * preempt_schedule_notrace - preempt_schedule called by tracing
*
* The tracing infrastructure uses preempt_enable_notrace to prevent
* recursion and tracing preempt enabling caused by the tracing
* instead of preempt_schedule() to exit user context if needed before
* calling the scheduler.
*/
-asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
{
enum ctx_state prev_ctx;
return;
do {
- __preempt_count_add(PREEMPT_ACTIVE);
+ /*
+ * Use raw __prempt_count() ops that don't call function.
+ * We can't call functions before disabling preemption which
+ * disarm preemption tracing recursions.
+ */
+ __preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
+ barrier();
/*
* Needs preempt disabled in case user_exit() is traced
* and the tracer calls preempt_enable_notrace() causing
__schedule();
exception_exit(prev_ctx);
- __preempt_count_sub(PREEMPT_ACTIVE);
barrier();
+ __preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
} while (need_resched());
}
-EXPORT_SYMBOL_GPL(preempt_schedule_context);
-#endif /* CONFIG_CONTEXT_TRACKING */
+EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
#endif /* CONFIG_PREEMPT */
prev_state = exception_enter();
do {
- __preempt_count_add(PREEMPT_ACTIVE);
+ preempt_active_enter();
local_irq_enable();
__schedule();
local_irq_disable();
- __preempt_count_sub(PREEMPT_ACTIVE);
-
- /*
- * Check again in case we missed a preemption opportunity
- * between schedule and now.
- */
- barrier();
+ preempt_active_exit();
} while (need_resched());
exception_exit(prev_state);
if (!dl_prio(p->normal_prio) ||
(pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
p->dl.dl_boosted = 1;
- p->dl.dl_throttled = 0;
enqueue_flag = ENQUEUE_REPLENISH;
} else
p->dl.dl_boosted = 0;
/* Actually do priority change: must hold pi & rq lock. */
static void __setscheduler(struct rq *rq, struct task_struct *p,
- const struct sched_attr *attr)
+ const struct sched_attr *attr, bool keep_boost)
{
__setscheduler_params(p, attr);
/*
- * If we get here, there was no pi waiters boosting the
- * task. It is safe to use the normal prio.
+ * Keep a potential priority boosting if called from
+ * sched_setscheduler().
*/
- p->prio = normal_prio(p);
+ if (keep_boost)
+ p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
+ else
+ p->prio = normal_prio(p);
if (dl_prio(p->prio))
p->sched_class = &dl_sched_class;
int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
MAX_RT_PRIO - 1 - attr->sched_priority;
int retval, oldprio, oldpolicy = -1, queued, running;
- int policy = attr->sched_policy;
+ int new_effective_prio, policy = attr->sched_policy;
unsigned long flags;
const struct sched_class *prev_class;
struct rq *rq;
oldprio = p->prio;
/*
- * Special case for priority boosted tasks.
- *
- * If the new priority is lower or equal (user space view)
- * than the current (boosted) priority, we just store the new
+ * Take priority boosted tasks into account. If the new
+ * effective priority is unchanged, we just store the new
* normal parameters and do not touch the scheduler class and
* the runqueue. This will be done when the task deboost
* itself.
*/
- if (rt_mutex_check_prio(p, newprio)) {
+ new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
+ if (new_effective_prio == oldprio) {
__setscheduler_params(p, attr);
task_rq_unlock(rq, p, &flags);
return 0;
put_prev_task(rq, p);
prev_class = p->sched_class;
- __setscheduler(rq, p, attr);
+ __setscheduler(rq, p, attr, true);
if (running)
p->sched_class->set_curr_task(rq);
long ret;
current->in_iowait = 1;
- if (old_iowait)
- blk_schedule_flush_plug(current);
- else
- blk_flush_plug(current);
+ blk_schedule_flush_plug(current);
delayacct_blkio_start();
rq = raw_rq();
.priority = CPU_PRI_MIGRATION,
};
-static void __cpuinit set_cpu_rq_start_time(void)
+static void set_cpu_rq_start_time(void)
{
int cpu = smp_processor_id();
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
long cpu = (long)hcpu;
struct dl_bw *dl_b;
+ bool overflow;
+ int cpus;
- switch (action & ~CPU_TASKS_FROZEN) {
+ switch (action) {
case CPU_DOWN_PREPARE:
- /* explicitly allow suspend */
- if (!(action & CPU_TASKS_FROZEN)) {
- bool overflow;
- int cpus;
-
- rcu_read_lock_sched();
- dl_b = dl_bw_of(cpu);
+ rcu_read_lock_sched();
+ dl_b = dl_bw_of(cpu);
- raw_spin_lock_irqsave(&dl_b->lock, flags);
- cpus = dl_bw_cpus(cpu);
- overflow = __dl_overflow(dl_b, cpus, 0, 0);
- raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+ cpus = dl_bw_cpus(cpu);
+ overflow = __dl_overflow(dl_b, cpus, 0, 0);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
- rcu_read_unlock_sched();
+ rcu_read_unlock_sched();
- if (overflow)
- return notifier_from_errno(-EBUSY);
- }
+ if (overflow)
+ return notifier_from_errno(-EBUSY);
cpuset_update_active_cpus(false);
break;
case CPU_DOWN_PREPARE_FROZEN:
}
#endif /* CONFIG_SMP */
-const_debug unsigned int sysctl_timer_migration = 1;
-
int in_sched_functions(unsigned long addr)
{
return in_lock_functions(addr) ||
queued = task_on_rq_queued(p);
if (queued)
dequeue_task(rq, p, 0);
- __setscheduler(rq, p, &attr);
+ __setscheduler(rq, p, &attr, false);
if (queued) {
enqueue_task(rq, p, 0);
resched_curr(rq);
return rt_runtime_us;
}
-static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
+static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
{
u64 rt_runtime, rt_period;
- rt_period = (u64)rt_period_us * NSEC_PER_USEC;
+ rt_period = rt_period_us * NSEC_PER_USEC;
rt_runtime = tg->rt_bandwidth.rt_runtime;
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
__refill_cfs_bandwidth_runtime(cfs_b);
/* restart the period timer (if active) to handle new period expiry */
- if (runtime_enabled && cfs_b->timer_active) {
- /* force a reprogram */
- __start_cfs_bandwidth(cfs_b, true);
- }
+ if (runtime_enabled)
+ start_cfs_bandwidth(cfs_b);
raw_spin_unlock_irq(&cfs_b->lock);
for_each_online_cpu(i) {
{
cputime_t old;
- while (new > (old = ACCESS_ONCE(*counter)))
+ while (new > (old = READ_ONCE(*counter)))
cmpxchg_cputime(counter, old, new);
}
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
ktime_t now, act;
- ktime_t soft, hard;
- unsigned long range;
s64 delta;
if (boosted)
if (ktime_us_delta(act, now) < 0)
return 0;
- hrtimer_set_expires(&dl_se->dl_timer, act);
+ hrtimer_start(&dl_se->dl_timer, act, HRTIMER_MODE_ABS);
- soft = hrtimer_get_softexpires(&dl_se->dl_timer);
- hard = hrtimer_get_expires(&dl_se->dl_timer);
- range = ktime_to_ns(ktime_sub(hard, soft));
- __hrtimer_start_range_ns(&dl_se->dl_timer, soft,
- range, HRTIMER_MODE_ABS, 0);
-
- return hrtimer_active(&dl_se->dl_timer);
+ return 1;
}
/*
}
static
-int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
+int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
{
return (dl_se->runtime <= 0);
}
sched_rt_avg_update(rq, delta_exec);
dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
- if (dl_runtime_exceeded(rq, dl_se)) {
+ if (dl_runtime_exceeded(dl_se)) {
dl_se->dl_throttled = 1;
__dequeue_task_dl(rq, curr, 0);
if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted)))
rq = cpu_rq(cpu);
rcu_read_lock();
- curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+ curr = READ_ONCE(rq->curr); /* unlocked access */
/*
* If we are dealing with a -deadline task, we must
(p->nr_cpus_allowed > 1)) {
int target = find_later_rq(p);
- if (target != -1)
+ if (target != -1 &&
+ dl_time_before(p->dl.deadline,
+ cpu_rq(target)->dl.earliest_dl.curr))
cpu = target;
}
rcu_read_unlock();
return NULL;
}
+/*
+ * Return the earliest pushable rq's task, which is suitable to be executed
+ * on the CPU, NULL otherwise:
+ */
+static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu)
+{
+ struct rb_node *next_node = rq->dl.pushable_dl_tasks_leftmost;
+ struct task_struct *p = NULL;
+
+ if (!has_pushable_dl_tasks(rq))
+ return NULL;
+
+next_node:
+ if (next_node) {
+ p = rb_entry(next_node, struct task_struct, pushable_dl_tasks);
+
+ if (pick_dl_task(rq, p, cpu))
+ return p;
+
+ next_node = rb_next(next_node);
+ goto next_node;
+ }
+
+ return NULL;
+}
+
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
static int find_later_rq(struct task_struct *task)
later_rq = cpu_rq(cpu);
+ if (!dl_time_before(task->dl.deadline,
+ later_rq->dl.earliest_dl.curr)) {
+ /*
+ * Target rq has tasks of equal or earlier deadline,
+ * retrying does not release any lock and is unlikely
+ * to yield a different result.
+ */
+ later_rq = NULL;
+ break;
+ }
+
/* Retry if something changed. */
if (double_lock_balance(rq, later_rq)) {
if (unlikely(task_rq(task) != rq ||
if (src_rq->dl.dl_nr_running <= 1)
goto skip;
- p = pick_next_earliest_dl_task(src_rq, this_cpu);
+ p = pick_earliest_pushable_dl_task(src_rq, this_cpu);
/*
* We found a task to be pulled if:
cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
}
-void init_sched_dl_class(void)
+void __init init_sched_dl_class(void)
{
unsigned int i;
p->prio);
#ifdef CONFIG_SCHEDSTATS
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
- SPLIT_NS(p->se.vruntime),
+ SPLIT_NS(p->se.statistics.wait_sum),
SPLIT_NS(p->se.sum_exec_runtime),
SPLIT_NS(p->se.statistics.sum_sleep_runtime));
#else
- SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
- 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
+ SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
+ 0LL, 0L,
+ SPLIT_NS(p->se.sum_exec_runtime),
+ 0LL, 0L);
#endif
#ifdef CONFIG_NUMA_BALANCING
SEQ_printf(m, " %d", task_node(p));
SEQ_printf(m,
"\nrunnable tasks:\n"
" task PID tree-key switches prio"
- " exec-runtime sum-exec sum-sleep\n"
+ " wait-time sum-exec sum-sleep\n"
"------------------------------------------------------"
"----------------------------------------------------\n");
#endif
#endif
#ifdef CONFIG_CFS_BANDWIDTH
- SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
- cfs_rq->tg->cfs_bandwidth.timer_active);
SEQ_printf(m, " .%-30s: %d\n", "throttled",
cfs_rq->throttled);
SEQ_printf(m, " .%-30s: %d\n", "throttle_count",
nr_switches = p->nvcsw + p->nivcsw;
#ifdef CONFIG_SCHEDSTATS
+ PN(se.statistics.sum_sleep_runtime);
PN(se.statistics.wait_start);
PN(se.statistics.sleep_start);
PN(se.statistics.block_start);
*
* This idea comes from the SD scheduler of Con Kolivas:
*/
-static int get_update_sysctl_factor(void)
+static unsigned int get_update_sysctl_factor(void)
{
- unsigned int cpus = min_t(int, num_online_cpus(), 8);
+ unsigned int cpus = min_t(unsigned int, num_online_cpus(), 8);
unsigned int factor;
switch (sysctl_sched_tunable_scaling) {
loff_t *ppos)
{
int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
- int factor = get_update_sysctl_factor();
+ unsigned int factor = get_update_sysctl_factor();
if (ret || !write)
return ret;
static unsigned int task_scan_min(struct task_struct *p)
{
- unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size);
+ unsigned int scan_size = READ_ONCE(sysctl_numa_balancing_scan_size);
unsigned int scan, floor;
unsigned int windows = 1;
static bool load_too_imbalanced(long src_load, long dst_load,
struct task_numa_env *env)
{
+ long imb, old_imb;
+ long orig_src_load, orig_dst_load;
long src_capacity, dst_capacity;
- long orig_src_load;
- long load_a, load_b;
- long moved_load;
- long imb;
/*
* The load is corrected for the CPU capacity available on each node.
dst_capacity = env->dst_stats.compute_capacity;
/* We care about the slope of the imbalance, not the direction. */
- load_a = dst_load;
- load_b = src_load;
- if (load_a < load_b)
- swap(load_a, load_b);
+ if (dst_load < src_load)
+ swap(dst_load, src_load);
/* Is the difference below the threshold? */
- imb = load_a * src_capacity * 100 -
- load_b * dst_capacity * env->imbalance_pct;
+ imb = dst_load * src_capacity * 100 -
+ src_load * dst_capacity * env->imbalance_pct;
if (imb <= 0)
return false;
/*
* The imbalance is above the allowed threshold.
- * Allow a move that brings us closer to a balanced situation,
- * without moving things past the point of balance.
+ * Compare it with the old imbalance.
*/
orig_src_load = env->src_stats.load;
+ orig_dst_load = env->dst_stats.load;
- /*
- * In a task swap, there will be one load moving from src to dst,
- * and another moving back. This is the net sum of both moves.
- * A simple task move will always have a positive value.
- * Allow the move if it brings the system closer to a balanced
- * situation, without crossing over the balance point.
- */
- moved_load = orig_src_load - src_load;
+ if (orig_dst_load < orig_src_load)
+ swap(orig_dst_load, orig_src_load);
- if (moved_load > 0)
- /* Moving src -> dst. Did we overshoot balance? */
- return src_load * dst_capacity < dst_load * src_capacity;
- else
- /* Moving dst -> src. Did we overshoot balance? */
- return dst_load * src_capacity < src_load * dst_capacity;
+ old_imb = orig_dst_load * src_capacity * 100 -
+ orig_src_load * dst_capacity * env->imbalance_pct;
+
+ /* Would this change make things worse? */
+ return (imb > old_imb);
}
/*
}
}
+/* Only move tasks to a NUMA node less busy than the current node. */
+static bool numa_has_capacity(struct task_numa_env *env)
+{
+ struct numa_stats *src = &env->src_stats;
+ struct numa_stats *dst = &env->dst_stats;
+
+ if (src->has_free_capacity && !dst->has_free_capacity)
+ return false;
+
+ /*
+ * Only consider a task move if the source has a higher load
+ * than the destination, corrected for CPU capacity on each node.
+ *
+ * src->load dst->load
+ * --------------------- vs ---------------------
+ * src->compute_capacity dst->compute_capacity
+ */
+ if (src->load * dst->compute_capacity >
+ dst->load * src->compute_capacity)
+ return true;
+
+ return false;
+}
+
static int task_numa_migrate(struct task_struct *p)
{
struct task_numa_env env = {
update_numa_stats(&env.dst_stats, env.dst_nid);
/* Try to find a spot on the preferred nid. */
- task_numa_find_cpu(&env, taskimp, groupimp);
+ if (numa_has_capacity(&env))
+ task_numa_find_cpu(&env, taskimp, groupimp);
/*
* Look at other nodes in these cases:
env.dist = dist;
env.dst_nid = nid;
update_numa_stats(&env.dst_stats, env.dst_nid);
- task_numa_find_cpu(&env, taskimp, groupimp);
+ if (numa_has_capacity(&env))
+ task_numa_find_cpu(&env, taskimp, groupimp);
}
}
u64 runtime, period;
spinlock_t *group_lock = NULL;
- seq = ACCESS_ONCE(p->mm->numa_scan_seq);
+ /*
+ * The p->mm->numa_scan_seq field gets updated without
+ * exclusive access. Use READ_ONCE() here to ensure
+ * that the field is read in a single access:
+ */
+ seq = READ_ONCE(p->mm->numa_scan_seq);
if (p->numa_scan_seq == seq)
return;
p->numa_scan_seq = seq;
}
rcu_read_lock();
- tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);
+ tsk = READ_ONCE(cpu_rq(cpu)->curr);
if (!cpupid_match_pid(tsk, cpupid))
goto no_join;
static void reset_ptenuma_scan(struct task_struct *p)
{
- ACCESS_ONCE(p->mm->numa_scan_seq)++;
+ /*
+ * We only did a read acquisition of the mmap sem, so
+ * p->mm->numa_scan_seq is written to without exclusive access
+ * and the update is not guaranteed to be atomic. That's not
+ * much of an issue though, since this is just used for
+ * statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not
+ * expensive, to avoid any form of compiler optimizations:
+ */
+ WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1);
p->mm->numa_scan_offset = 0;
}
}
for (; vma; vma = vma->vm_next) {
if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
- is_vm_hugetlb_page(vma)) {
+ is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
continue;
}
if (cfs_b->quota == RUNTIME_INF)
amount = min_amount;
else {
- /*
- * If the bandwidth pool has become inactive, then at least one
- * period must have elapsed since the last consumption.
- * Refresh the global state and ensure bandwidth timer becomes
- * active.
- */
- if (!cfs_b->timer_active) {
- __refill_cfs_bandwidth_runtime(cfs_b);
- __start_cfs_bandwidth(cfs_b, false);
- }
+ start_cfs_bandwidth(cfs_b);
if (cfs_b->runtime > 0) {
amount = min(cfs_b->runtime, min_amount);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
long task_delta, dequeue = 1;
+ bool empty;
se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
cfs_rq->throttled = 1;
cfs_rq->throttled_clock = rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
+ empty = list_empty(&cfs_rq->throttled_list);
+
/*
* Add to the _head_ of the list, so that an already-started
* distribute_cfs_runtime will not see us
*/
list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
- if (!cfs_b->timer_active)
- __start_cfs_bandwidth(cfs_b, false);
+
+ /*
+ * If we're the first throttled task, make sure the bandwidth
+ * timer is running.
+ */
+ if (empty)
+ start_cfs_bandwidth(cfs_b);
+
raw_spin_unlock(&cfs_b->lock);
}
if (cfs_b->idle && !throttled)
goto out_deactivate;
- /*
- * if we have relooped after returning idle once, we need to update our
- * status as actually running, so that other cpus doing
- * __start_cfs_bandwidth will stop trying to cancel us.
- */
- cfs_b->timer_active = 1;
-
__refill_cfs_bandwidth_runtime(cfs_b);
if (!throttled) {
return 0;
out_deactivate:
- cfs_b->timer_active = 0;
return 1;
}
* Are we near the end of the current quota period?
*
* Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
- * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * hrtimer base being cleared by hrtimer_start. In the case of
* migrate_hrtimers, base is never cleared, so we are fine.
*/
static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
if (runtime_refresh_within(cfs_b, min_left))
return;
- start_bandwidth_timer(&cfs_b->slack_timer,
- ns_to_ktime(cfs_bandwidth_slack_period));
+ hrtimer_start(&cfs_b->slack_timer,
+ ns_to_ktime(cfs_bandwidth_slack_period),
+ HRTIMER_MODE_REL);
}
/* we know any runtime found here is valid as update_curr() precedes return */
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, slack_timer);
+
do_sched_cfs_slack_timer(cfs_b);
return HRTIMER_NORESTART;
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, period_timer);
- ktime_t now;
int overrun;
int idle = 0;
raw_spin_lock(&cfs_b->lock);
for (;;) {
- now = hrtimer_cb_get_time(timer);
- overrun = hrtimer_forward(timer, now, cfs_b->period);
-
+ overrun = hrtimer_forward_now(timer, cfs_b->period);
if (!overrun)
break;
idle = do_sched_cfs_period_timer(cfs_b, overrun);
}
+ if (idle)
+ cfs_b->period_active = 0;
raw_spin_unlock(&cfs_b->lock);
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
cfs_b->period = ns_to_ktime(default_cfs_period());
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
- hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
cfs_b->period_timer.function = sched_cfs_period_timer;
hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->slack_timer.function = sched_cfs_slack_timer;
INIT_LIST_HEAD(&cfs_rq->throttled_list);
}
-/* requires cfs_b->lock, may release to reprogram timer */
-void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
+void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
- /*
- * The timer may be active because we're trying to set a new bandwidth
- * period or because we're racing with the tear-down path
- * (timer_active==0 becomes visible before the hrtimer call-back
- * terminates). In either case we ensure that it's re-programmed
- */
- while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
- hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
- /* bounce the lock to allow do_sched_cfs_period_timer to run */
- raw_spin_unlock(&cfs_b->lock);
- cpu_relax();
- raw_spin_lock(&cfs_b->lock);
- /* if someone else restarted the timer then we're done */
- if (!force && cfs_b->timer_active)
- return;
- }
+ lockdep_assert_held(&cfs_b->lock);
- cfs_b->timer_active = 1;
- start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
+ if (!cfs_b->period_active) {
+ cfs_b->period_active = 1;
+ hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+ hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
+ }
}
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
}
#ifdef CONFIG_SMP
+
+/*
+ * per rq 'load' arrray crap; XXX kill this.
+ */
+
+/*
+ * The exact cpuload at various idx values, calculated at every tick would be
+ * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ *
+ * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
+ * on nth tick when cpu may be busy, then we have:
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *
+ * decay_load_missed() below does efficient calculation of
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ * The calculation is approximated on a 128 point scale.
+ * degrade_zero_ticks is the number of ticks after which load at any
+ * particular idx is approximated to be zero.
+ * degrade_factor is a precomputed table, a row for each load idx.
+ * Each column corresponds to degradation factor for a power of two ticks,
+ * based on 128 point scale.
+ * Example:
+ * row 2, col 3 (=12) says that the degradation at load idx 2 after
+ * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
+ *
+ * With this power of 2 load factors, we can degrade the load n times
+ * by looking at 1 bits in n and doing as many mult/shift instead of
+ * n mult/shifts needed by the exact degradation.
+ */
+#define DEGRADE_SHIFT 7
+static const unsigned char
+ degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const unsigned char
+ degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+ {0, 0, 0, 0, 0, 0, 0, 0},
+ {64, 32, 8, 0, 0, 0, 0, 0},
+ {96, 72, 40, 12, 1, 0, 0},
+ {112, 98, 75, 43, 15, 1, 0},
+ {120, 112, 98, 76, 45, 16, 2} };
+
+/*
+ * Update cpu_load for any missed ticks, due to tickless idle. The backlog
+ * would be when CPU is idle and so we just decay the old load without
+ * adding any new load.
+ */
+static unsigned long
+decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
+{
+ int j = 0;
+
+ if (!missed_updates)
+ return load;
+
+ if (missed_updates >= degrade_zero_ticks[idx])
+ return 0;
+
+ if (idx == 1)
+ return load >> missed_updates;
+
+ while (missed_updates) {
+ if (missed_updates % 2)
+ load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
+
+ missed_updates >>= 1;
+ j++;
+ }
+ return load;
+}
+
+/*
+ * Update rq->cpu_load[] statistics. This function is usually called every
+ * scheduler tick (TICK_NSEC). With tickless idle this will not be called
+ * every tick. We fix it up based on jiffies.
+ */
+static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+ unsigned long pending_updates)
+{
+ int i, scale;
+
+ this_rq->nr_load_updates++;
+
+ /* Update our load: */
+ this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
+ for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
+ unsigned long old_load, new_load;
+
+ /* scale is effectively 1 << i now, and >> i divides by scale */
+
+ old_load = this_rq->cpu_load[i];
+ old_load = decay_load_missed(old_load, pending_updates - 1, i);
+ new_load = this_load;
+ /*
+ * Round up the averaging division if load is increasing. This
+ * prevents us from getting stuck on 9 if the load is 10, for
+ * example.
+ */
+ if (new_load > old_load)
+ new_load += scale - 1;
+
+ this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
+ }
+
+ sched_avg_update(this_rq);
+}
+
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
+/*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+static void update_idle_cpu_load(struct rq *this_rq)
+{
+ unsigned long curr_jiffies = READ_ONCE(jiffies);
+ unsigned long load = this_rq->cfs.runnable_load_avg;
+ unsigned long pending_updates;
+
+ /*
+ * bail if there's load or we're actually up-to-date.
+ */
+ if (load || curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ this_rq->last_load_update_tick = curr_jiffies;
+
+ __update_cpu_load(this_rq, load, pending_updates);
+}
+
+/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+ struct rq *this_rq = this_rq();
+ unsigned long curr_jiffies = READ_ONCE(jiffies);
+ unsigned long pending_updates;
+
+ if (curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&this_rq->lock);
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ if (pending_updates) {
+ this_rq->last_load_update_tick = curr_jiffies;
+ /*
+ * We were idle, this means load 0, the current load might be
+ * !0 due to remote wakeups and the sort.
+ */
+ __update_cpu_load(this_rq, 0, pending_updates);
+ }
+ raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
+ * Called from scheduler_tick()
+ */
+void update_cpu_load_active(struct rq *this_rq)
+{
+ unsigned long load = this_rq->cfs.runnable_load_avg;
+ /*
+ * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
+ */
+ this_rq->last_load_update_tick = jiffies;
+ __update_cpu_load(this_rq, load, 1);
+}
+
/* Used instead of source_load when we know the type == 0 */
static unsigned long weighted_cpuload(const int cpu)
{
static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running);
+ unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
unsigned long load_avg = rq->cfs.runnable_load_avg;
if (nr_running)
* entity, update_curr() will update its vruntime, otherwise
* forget we've ever seen it.
*/
- if (curr && curr->on_rq)
- update_curr(cfs_rq);
- else
- curr = NULL;
+ if (curr) {
+ if (curr->on_rq)
+ update_curr(cfs_rq);
+ else
+ curr = NULL;
- /*
- * This call to check_cfs_rq_runtime() will do the throttle and
- * dequeue its entity in the parent(s). Therefore the 'simple'
- * nr_running test will indeed be correct.
- */
- if (unlikely(check_cfs_rq_runtime(cfs_rq)))
- goto simple;
+ /*
+ * This call to check_cfs_rq_runtime() will do the
+ * throttle and dequeue its entity in the parent(s).
+ * Therefore the 'simple' nr_running test will indeed
+ * be correct.
+ */
+ if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+ goto simple;
+ }
se = pick_next_entity(cfs_rq, curr);
cfs_rq = group_cfs_rq(se);
}
#ifdef CONFIG_NUMA_BALANCING
-/* Returns true if the destination node has incurred more faults */
+/*
+ * Returns true if the destination node is the preferred node.
+ * Needs to match fbq_classify_rq(): if there is a runnable task
+ * that is not on its preferred node, we should identify it.
+ */
static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
+ unsigned long src_faults, dst_faults;
int src_nid, dst_nid;
if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
if (src_nid == dst_nid)
return false;
- if (numa_group) {
- /* Task is already in the group's interleave set. */
- if (node_isset(src_nid, numa_group->active_nodes))
- return false;
-
- /* Task is moving into the group's interleave set. */
- if (node_isset(dst_nid, numa_group->active_nodes))
- return true;
-
- return group_faults(p, dst_nid) > group_faults(p, src_nid);
- }
-
/* Encourage migration to the preferred node. */
if (dst_nid == p->numa_preferred_nid)
return true;
- return task_faults(p, dst_nid) > task_faults(p, src_nid);
+ /* Migrating away from the preferred node is bad. */
+ if (src_nid == p->numa_preferred_nid)
+ return false;
+
+ if (numa_group) {
+ src_faults = group_faults(p, src_nid);
+ dst_faults = group_faults(p, dst_nid);
+ } else {
+ src_faults = task_faults(p, src_nid);
+ dst_faults = task_faults(p, dst_nid);
+ }
+
+ return dst_faults > src_faults;
}
static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
+ unsigned long src_faults, dst_faults;
int src_nid, dst_nid;
if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
if (src_nid == dst_nid)
return false;
- if (numa_group) {
- /* Task is moving within/into the group's interleave set. */
- if (node_isset(dst_nid, numa_group->active_nodes))
- return false;
+ /* Migrating away from the preferred node is bad. */
+ if (src_nid == p->numa_preferred_nid)
+ return true;
- /* Task is moving out of the group's interleave set. */
- if (node_isset(src_nid, numa_group->active_nodes))
- return true;
+ /* Encourage migration to the preferred node. */
+ if (dst_nid == p->numa_preferred_nid)
+ return false;
- return group_faults(p, dst_nid) < group_faults(p, src_nid);
+ if (numa_group) {
+ src_faults = group_faults(p, src_nid);
+ dst_faults = group_faults(p, dst_nid);
+ } else {
+ src_faults = task_faults(p, src_nid);
+ dst_faults = task_faults(p, dst_nid);
}
- /* Migrating away from the preferred node is always bad. */
- if (src_nid == p->numa_preferred_nid)
- return true;
-
- return task_faults(p, dst_nid) < task_faults(p, src_nid);
+ return dst_faults < src_faults;
}
#else
* Since we're reading these variables without serialization make sure
* we read them once before doing sanity checks on them.
*/
- age_stamp = ACCESS_ONCE(rq->age_stamp);
- avg = ACCESS_ONCE(rq->rt_avg);
+ age_stamp = READ_ONCE(rq->age_stamp);
+ avg = READ_ONCE(rq->rt_avg);
delta = __rq_clock_broken(rq) - age_stamp;
if (unlikely(delta < 0))
--- /dev/null
+/*
+ * kernel/sched/loadavg.c
+ *
+ * This file contains the magic bits required to compute the global loadavg
+ * figure. Its a silly number but people think its important. We go through
+ * great pains to make it work on big machines and tickless kernels.
+ */
+
+#include <linux/export.h>
+
+#include "sched.h"
+
+/*
+ * Global load-average calculations
+ *
+ * We take a distributed and async approach to calculating the global load-avg
+ * in order to minimize overhead.
+ *
+ * The global load average is an exponentially decaying average of nr_running +
+ * nr_uninterruptible.
+ *
+ * Once every LOAD_FREQ:
+ *
+ * nr_active = 0;
+ * for_each_possible_cpu(cpu)
+ * nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible;
+ *
+ * avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n)
+ *
+ * Due to a number of reasons the above turns in the mess below:
+ *
+ * - for_each_possible_cpu() is prohibitively expensive on machines with
+ * serious number of cpus, therefore we need to take a distributed approach
+ * to calculating nr_active.
+ *
+ * \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0
+ * = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) }
+ *
+ * So assuming nr_active := 0 when we start out -- true per definition, we
+ * can simply take per-cpu deltas and fold those into a global accumulate
+ * to obtain the same result. See calc_load_fold_active().
+ *
+ * Furthermore, in order to avoid synchronizing all per-cpu delta folding
+ * across the machine, we assume 10 ticks is sufficient time for every
+ * cpu to have completed this task.
+ *
+ * This places an upper-bound on the IRQ-off latency of the machine. Then
+ * again, being late doesn't loose the delta, just wrecks the sample.
+ *
+ * - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because
+ * this would add another cross-cpu cacheline miss and atomic operation
+ * to the wakeup path. Instead we increment on whatever cpu the task ran
+ * when it went into uninterruptible state and decrement on whatever cpu
+ * did the wakeup. This means that only the sum of nr_uninterruptible over
+ * all cpus yields the correct result.
+ *
+ * This covers the NO_HZ=n code, for extra head-aches, see the comment below.
+ */
+
+/* Variables and functions for calc_load */
+atomic_long_t calc_load_tasks;
+unsigned long calc_load_update;
+unsigned long avenrun[3];
+EXPORT_SYMBOL(avenrun); /* should be removed */
+
+/**
+ * get_avenrun - get the load average array
+ * @loads: pointer to dest load array
+ * @offset: offset to add
+ * @shift: shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
+{
+ loads[0] = (avenrun[0] + offset) << shift;
+ loads[1] = (avenrun[1] + offset) << shift;
+ loads[2] = (avenrun[2] + offset) << shift;
+}
+
+long calc_load_fold_active(struct rq *this_rq)
+{
+ long nr_active, delta = 0;
+
+ nr_active = this_rq->nr_running;
+ nr_active += (long)this_rq->nr_uninterruptible;
+
+ if (nr_active != this_rq->calc_load_active) {
+ delta = nr_active - this_rq->calc_load_active;
+ this_rq->calc_load_active = nr_active;
+ }
+
+ return delta;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ */
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+ load *= exp;
+ load += active * (FIXED_1 - exp);
+ load += 1UL << (FSHIFT - 1);
+ return load >> FSHIFT;
+}
+
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * Handle NO_HZ for the global load-average.
+ *
+ * Since the above described distributed algorithm to compute the global
+ * load-average relies on per-cpu sampling from the tick, it is affected by
+ * NO_HZ.
+ *
+ * The basic idea is to fold the nr_active delta into a global idle-delta upon
+ * entering NO_HZ state such that we can include this as an 'extra' cpu delta
+ * when we read the global state.
+ *
+ * Obviously reality has to ruin such a delightfully simple scheme:
+ *
+ * - When we go NO_HZ idle during the window, we can negate our sample
+ * contribution, causing under-accounting.
+ *
+ * We avoid this by keeping two idle-delta counters and flipping them
+ * when the window starts, thus separating old and new NO_HZ load.
+ *
+ * The only trick is the slight shift in index flip for read vs write.
+ *
+ * 0s 5s 10s 15s
+ * +10 +10 +10 +10
+ * |-|-----------|-|-----------|-|-----------|-|
+ * r:0 0 1 1 0 0 1 1 0
+ * w:0 1 1 0 0 1 1 0 0
+ *
+ * This ensures we'll fold the old idle contribution in this window while
+ * accumlating the new one.
+ *
+ * - When we wake up from NO_HZ idle during the window, we push up our
+ * contribution, since we effectively move our sample point to a known
+ * busy state.
+ *
+ * This is solved by pushing the window forward, and thus skipping the
+ * sample, for this cpu (effectively using the idle-delta for this cpu which
+ * was in effect at the time the window opened). This also solves the issue
+ * of having to deal with a cpu having been in NOHZ idle for multiple
+ * LOAD_FREQ intervals.
+ *
+ * When making the ILB scale, we should try to pull this in as well.
+ */
+static atomic_long_t calc_load_idle[2];
+static int calc_load_idx;
+
+static inline int calc_load_write_idx(void)
+{
+ int idx = calc_load_idx;
+
+ /*
+ * See calc_global_nohz(), if we observe the new index, we also
+ * need to observe the new update time.
+ */
+ smp_rmb();
+
+ /*
+ * If the folding window started, make sure we start writing in the
+ * next idle-delta.
+ */
+ if (!time_before(jiffies, calc_load_update))
+ idx++;
+
+ return idx & 1;
+}
+
+static inline int calc_load_read_idx(void)
+{
+ return calc_load_idx & 1;
+}
+
+void calc_load_enter_idle(void)
+{
+ struct rq *this_rq = this_rq();
+ long delta;
+
+ /*
+ * We're going into NOHZ mode, if there's any pending delta, fold it
+ * into the pending idle delta.
+ */
+ delta = calc_load_fold_active(this_rq);
+ if (delta) {
+ int idx = calc_load_write_idx();
+
+ atomic_long_add(delta, &calc_load_idle[idx]);
+ }
+}
+
+void calc_load_exit_idle(void)
+{
+ struct rq *this_rq = this_rq();
+
+ /*
+ * If we're still before the sample window, we're done.
+ */
+ if (time_before(jiffies, this_rq->calc_load_update))
+ return;
+
+ /*
+ * We woke inside or after the sample window, this means we're already
+ * accounted through the nohz accounting, so skip the entire deal and
+ * sync up for the next window.
+ */
+ this_rq->calc_load_update = calc_load_update;
+ if (time_before(jiffies, this_rq->calc_load_update + 10))
+ this_rq->calc_load_update += LOAD_FREQ;
+}
+
+static long calc_load_fold_idle(void)
+{
+ int idx = calc_load_read_idx();
+ long delta = 0;
+
+ if (atomic_long_read(&calc_load_idle[idx]))
+ delta = atomic_long_xchg(&calc_load_idle[idx], 0);
+
+ return delta;
+}
+
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x: base of the power
+ * @frac_bits: fractional bits of @x
+ * @n: power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
+ */
+static unsigned long
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
+{
+ unsigned long result = 1UL << frac_bits;
+
+ if (n) {
+ for (;;) {
+ if (n & 1) {
+ result *= x;
+ result += 1UL << (frac_bits - 1);
+ result >>= frac_bits;
+ }
+ n >>= 1;
+ if (!n)
+ break;
+ x *= x;
+ x += 1UL << (frac_bits - 1);
+ x >>= frac_bits;
+ }
+ }
+
+ return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ * = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ * ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ * = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ * n 1 - x^(n+1)
+ * S_n := \Sum x^i = -------------
+ * i=0 1 - x
+ */
+static unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+ unsigned long active, unsigned int n)
+{
+ return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
+}
+
+/*
+ * NO_HZ can leave us missing all per-cpu ticks calling
+ * calc_load_account_active(), but since an idle CPU folds its delta into
+ * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
+ * in the pending idle delta if our idle period crossed a load cycle boundary.
+ *
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+static void calc_global_nohz(void)
+{
+ long delta, active, n;
+
+ if (!time_before(jiffies, calc_load_update + 10)) {
+ /*
+ * Catch-up, fold however many we are behind still
+ */
+ delta = jiffies - calc_load_update - 10;
+ n = 1 + (delta / LOAD_FREQ);
+
+ active = atomic_long_read(&calc_load_tasks);
+ active = active > 0 ? active * FIXED_1 : 0;
+
+ avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+ avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+ avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+ calc_load_update += n * LOAD_FREQ;
+ }
+
+ /*
+ * Flip the idle index...
+ *
+ * Make sure we first write the new time then flip the index, so that
+ * calc_load_write_idx() will see the new time when it reads the new
+ * index, this avoids a double flip messing things up.
+ */
+ smp_wmb();
+ calc_load_idx++;
+}
+#else /* !CONFIG_NO_HZ_COMMON */
+
+static inline long calc_load_fold_idle(void) { return 0; }
+static inline void calc_global_nohz(void) { }
+
+#endif /* CONFIG_NO_HZ_COMMON */
+
+/*
+ * calc_load - update the avenrun load estimates 10 ticks after the
+ * CPUs have updated calc_load_tasks.
+ *
+ * Called from the global timer code.
+ */
+void calc_global_load(unsigned long ticks)
+{
+ long active, delta;
+
+ if (time_before(jiffies, calc_load_update + 10))
+ return;
+
+ /*
+ * Fold the 'old' idle-delta to include all NO_HZ cpus.
+ */
+ delta = calc_load_fold_idle();
+ if (delta)
+ atomic_long_add(delta, &calc_load_tasks);
+
+ active = atomic_long_read(&calc_load_tasks);
+ active = active > 0 ? active * FIXED_1 : 0;
+
+ avenrun[0] = calc_load(avenrun[0], EXP_1, active);
+ avenrun[1] = calc_load(avenrun[1], EXP_5, active);
+ avenrun[2] = calc_load(avenrun[2], EXP_15, active);
+
+ calc_load_update += LOAD_FREQ;
+
+ /*
+ * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
+ */
+ calc_global_nohz();
+}
+
+/*
+ * Called from scheduler_tick() to periodically update this CPU's
+ * active count.
+ */
+void calc_global_load_tick(struct rq *this_rq)
+{
+ long delta;
+
+ if (time_before(jiffies, this_rq->calc_load_update))
+ return;
+
+ delta = calc_load_fold_active(this_rq);
+ if (delta)
+ atomic_long_add(delta, &calc_load_tasks);
+
+ this_rq->calc_load_update += LOAD_FREQ;
+}
+++ /dev/null
-/*
- * kernel/sched/proc.c
- *
- * Kernel load calculations, forked from sched/core.c
- */
-
-#include <linux/export.h>
-
-#include "sched.h"
-
-/*
- * Global load-average calculations
- *
- * We take a distributed and async approach to calculating the global load-avg
- * in order to minimize overhead.
- *
- * The global load average is an exponentially decaying average of nr_running +
- * nr_uninterruptible.
- *
- * Once every LOAD_FREQ:
- *
- * nr_active = 0;
- * for_each_possible_cpu(cpu)
- * nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible;
- *
- * avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n)
- *
- * Due to a number of reasons the above turns in the mess below:
- *
- * - for_each_possible_cpu() is prohibitively expensive on machines with
- * serious number of cpus, therefore we need to take a distributed approach
- * to calculating nr_active.
- *
- * \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0
- * = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) }
- *
- * So assuming nr_active := 0 when we start out -- true per definition, we
- * can simply take per-cpu deltas and fold those into a global accumulate
- * to obtain the same result. See calc_load_fold_active().
- *
- * Furthermore, in order to avoid synchronizing all per-cpu delta folding
- * across the machine, we assume 10 ticks is sufficient time for every
- * cpu to have completed this task.
- *
- * This places an upper-bound on the IRQ-off latency of the machine. Then
- * again, being late doesn't loose the delta, just wrecks the sample.
- *
- * - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because
- * this would add another cross-cpu cacheline miss and atomic operation
- * to the wakeup path. Instead we increment on whatever cpu the task ran
- * when it went into uninterruptible state and decrement on whatever cpu
- * did the wakeup. This means that only the sum of nr_uninterruptible over
- * all cpus yields the correct result.
- *
- * This covers the NO_HZ=n code, for extra head-aches, see the comment below.
- */
-
-/* Variables and functions for calc_load */
-atomic_long_t calc_load_tasks;
-unsigned long calc_load_update;
-unsigned long avenrun[3];
-EXPORT_SYMBOL(avenrun); /* should be removed */
-
-/**
- * get_avenrun - get the load average array
- * @loads: pointer to dest load array
- * @offset: offset to add
- * @shift: shift count to shift the result left
- *
- * These values are estimates at best, so no need for locking.
- */
-void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
-{
- loads[0] = (avenrun[0] + offset) << shift;
- loads[1] = (avenrun[1] + offset) << shift;
- loads[2] = (avenrun[2] + offset) << shift;
-}
-
-long calc_load_fold_active(struct rq *this_rq)
-{
- long nr_active, delta = 0;
-
- nr_active = this_rq->nr_running;
- nr_active += (long) this_rq->nr_uninterruptible;
-
- if (nr_active != this_rq->calc_load_active) {
- delta = nr_active - this_rq->calc_load_active;
- this_rq->calc_load_active = nr_active;
- }
-
- return delta;
-}
-
-/*
- * a1 = a0 * e + a * (1 - e)
- */
-static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
-{
- load *= exp;
- load += active * (FIXED_1 - exp);
- load += 1UL << (FSHIFT - 1);
- return load >> FSHIFT;
-}
-
-#ifdef CONFIG_NO_HZ_COMMON
-/*
- * Handle NO_HZ for the global load-average.
- *
- * Since the above described distributed algorithm to compute the global
- * load-average relies on per-cpu sampling from the tick, it is affected by
- * NO_HZ.
- *
- * The basic idea is to fold the nr_active delta into a global idle-delta upon
- * entering NO_HZ state such that we can include this as an 'extra' cpu delta
- * when we read the global state.
- *
- * Obviously reality has to ruin such a delightfully simple scheme:
- *
- * - When we go NO_HZ idle during the window, we can negate our sample
- * contribution, causing under-accounting.
- *
- * We avoid this by keeping two idle-delta counters and flipping them
- * when the window starts, thus separating old and new NO_HZ load.
- *
- * The only trick is the slight shift in index flip for read vs write.
- *
- * 0s 5s 10s 15s
- * +10 +10 +10 +10
- * |-|-----------|-|-----------|-|-----------|-|
- * r:0 0 1 1 0 0 1 1 0
- * w:0 1 1 0 0 1 1 0 0
- *
- * This ensures we'll fold the old idle contribution in this window while
- * accumlating the new one.
- *
- * - When we wake up from NO_HZ idle during the window, we push up our
- * contribution, since we effectively move our sample point to a known
- * busy state.
- *
- * This is solved by pushing the window forward, and thus skipping the
- * sample, for this cpu (effectively using the idle-delta for this cpu which
- * was in effect at the time the window opened). This also solves the issue
- * of having to deal with a cpu having been in NOHZ idle for multiple
- * LOAD_FREQ intervals.
- *
- * When making the ILB scale, we should try to pull this in as well.
- */
-static atomic_long_t calc_load_idle[2];
-static int calc_load_idx;
-
-static inline int calc_load_write_idx(void)
-{
- int idx = calc_load_idx;
-
- /*
- * See calc_global_nohz(), if we observe the new index, we also
- * need to observe the new update time.
- */
- smp_rmb();
-
- /*
- * If the folding window started, make sure we start writing in the
- * next idle-delta.
- */
- if (!time_before(jiffies, calc_load_update))
- idx++;
-
- return idx & 1;
-}
-
-static inline int calc_load_read_idx(void)
-{
- return calc_load_idx & 1;
-}
-
-void calc_load_enter_idle(void)
-{
- struct rq *this_rq = this_rq();
- long delta;
-
- /*
- * We're going into NOHZ mode, if there's any pending delta, fold it
- * into the pending idle delta.
- */
- delta = calc_load_fold_active(this_rq);
- if (delta) {
- int idx = calc_load_write_idx();
- atomic_long_add(delta, &calc_load_idle[idx]);
- }
-}
-
-void calc_load_exit_idle(void)
-{
- struct rq *this_rq = this_rq();
-
- /*
- * If we're still before the sample window, we're done.
- */
- if (time_before(jiffies, this_rq->calc_load_update))
- return;
-
- /*
- * We woke inside or after the sample window, this means we're already
- * accounted through the nohz accounting, so skip the entire deal and
- * sync up for the next window.
- */
- this_rq->calc_load_update = calc_load_update;
- if (time_before(jiffies, this_rq->calc_load_update + 10))
- this_rq->calc_load_update += LOAD_FREQ;
-}
-
-static long calc_load_fold_idle(void)
-{
- int idx = calc_load_read_idx();
- long delta = 0;
-
- if (atomic_long_read(&calc_load_idle[idx]))
- delta = atomic_long_xchg(&calc_load_idle[idx], 0);
-
- return delta;
-}
-
-/**
- * fixed_power_int - compute: x^n, in O(log n) time
- *
- * @x: base of the power
- * @frac_bits: fractional bits of @x
- * @n: power to raise @x to.
- *
- * By exploiting the relation between the definition of the natural power
- * function: x^n := x*x*...*x (x multiplied by itself for n times), and
- * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
- * (where: n_i \elem {0, 1}, the binary vector representing n),
- * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
- * of course trivially computable in O(log_2 n), the length of our binary
- * vector.
- */
-static unsigned long
-fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
-{
- unsigned long result = 1UL << frac_bits;
-
- if (n) for (;;) {
- if (n & 1) {
- result *= x;
- result += 1UL << (frac_bits - 1);
- result >>= frac_bits;
- }
- n >>= 1;
- if (!n)
- break;
- x *= x;
- x += 1UL << (frac_bits - 1);
- x >>= frac_bits;
- }
-
- return result;
-}
-
-/*
- * a1 = a0 * e + a * (1 - e)
- *
- * a2 = a1 * e + a * (1 - e)
- * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
- * = a0 * e^2 + a * (1 - e) * (1 + e)
- *
- * a3 = a2 * e + a * (1 - e)
- * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
- * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
- *
- * ...
- *
- * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
- * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
- * = a0 * e^n + a * (1 - e^n)
- *
- * [1] application of the geometric series:
- *
- * n 1 - x^(n+1)
- * S_n := \Sum x^i = -------------
- * i=0 1 - x
- */
-static unsigned long
-calc_load_n(unsigned long load, unsigned long exp,
- unsigned long active, unsigned int n)
-{
-
- return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
-}
-
-/*
- * NO_HZ can leave us missing all per-cpu ticks calling
- * calc_load_account_active(), but since an idle CPU folds its delta into
- * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
- * in the pending idle delta if our idle period crossed a load cycle boundary.
- *
- * Once we've updated the global active value, we need to apply the exponential
- * weights adjusted to the number of cycles missed.
- */
-static void calc_global_nohz(void)
-{
- long delta, active, n;
-
- if (!time_before(jiffies, calc_load_update + 10)) {
- /*
- * Catch-up, fold however many we are behind still
- */
- delta = jiffies - calc_load_update - 10;
- n = 1 + (delta / LOAD_FREQ);
-
- active = atomic_long_read(&calc_load_tasks);
- active = active > 0 ? active * FIXED_1 : 0;
-
- avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
- avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
- avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
-
- calc_load_update += n * LOAD_FREQ;
- }
-
- /*
- * Flip the idle index...
- *
- * Make sure we first write the new time then flip the index, so that
- * calc_load_write_idx() will see the new time when it reads the new
- * index, this avoids a double flip messing things up.
- */
- smp_wmb();
- calc_load_idx++;
-}
-#else /* !CONFIG_NO_HZ_COMMON */
-
-static inline long calc_load_fold_idle(void) { return 0; }
-static inline void calc_global_nohz(void) { }
-
-#endif /* CONFIG_NO_HZ_COMMON */
-
-/*
- * calc_load - update the avenrun load estimates 10 ticks after the
- * CPUs have updated calc_load_tasks.
- */
-void calc_global_load(unsigned long ticks)
-{
- long active, delta;
-
- if (time_before(jiffies, calc_load_update + 10))
- return;
-
- /*
- * Fold the 'old' idle-delta to include all NO_HZ cpus.
- */
- delta = calc_load_fold_idle();
- if (delta)
- atomic_long_add(delta, &calc_load_tasks);
-
- active = atomic_long_read(&calc_load_tasks);
- active = active > 0 ? active * FIXED_1 : 0;
-
- avenrun[0] = calc_load(avenrun[0], EXP_1, active);
- avenrun[1] = calc_load(avenrun[1], EXP_5, active);
- avenrun[2] = calc_load(avenrun[2], EXP_15, active);
-
- calc_load_update += LOAD_FREQ;
-
- /*
- * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
- */
- calc_global_nohz();
-}
-
-/*
- * Called from update_cpu_load() to periodically update this CPU's
- * active count.
- */
-static void calc_load_account_active(struct rq *this_rq)
-{
- long delta;
-
- if (time_before(jiffies, this_rq->calc_load_update))
- return;
-
- delta = calc_load_fold_active(this_rq);
- if (delta)
- atomic_long_add(delta, &calc_load_tasks);
-
- this_rq->calc_load_update += LOAD_FREQ;
-}
-
-/*
- * End of global load-average stuff
- */
-
-/*
- * The exact cpuload at various idx values, calculated at every tick would be
- * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
- *
- * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
- * on nth tick when cpu may be busy, then we have:
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
- *
- * decay_load_missed() below does efficient calculation of
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
- *
- * The calculation is approximated on a 128 point scale.
- * degrade_zero_ticks is the number of ticks after which load at any
- * particular idx is approximated to be zero.
- * degrade_factor is a precomputed table, a row for each load idx.
- * Each column corresponds to degradation factor for a power of two ticks,
- * based on 128 point scale.
- * Example:
- * row 2, col 3 (=12) says that the degradation at load idx 2 after
- * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
- *
- * With this power of 2 load factors, we can degrade the load n times
- * by looking at 1 bits in n and doing as many mult/shift instead of
- * n mult/shifts needed by the exact degradation.
- */
-#define DEGRADE_SHIFT 7
-static const unsigned char
- degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
-static const unsigned char
- degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
- {0, 0, 0, 0, 0, 0, 0, 0},
- {64, 32, 8, 0, 0, 0, 0, 0},
- {96, 72, 40, 12, 1, 0, 0},
- {112, 98, 75, 43, 15, 1, 0},
- {120, 112, 98, 76, 45, 16, 2} };
-
-/*
- * Update cpu_load for any missed ticks, due to tickless idle. The backlog
- * would be when CPU is idle and so we just decay the old load without
- * adding any new load.
- */
-static unsigned long
-decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
-{
- int j = 0;
-
- if (!missed_updates)
- return load;
-
- if (missed_updates >= degrade_zero_ticks[idx])
- return 0;
-
- if (idx == 1)
- return load >> missed_updates;
-
- while (missed_updates) {
- if (missed_updates % 2)
- load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
-
- missed_updates >>= 1;
- j++;
- }
- return load;
-}
-
-/*
- * Update rq->cpu_load[] statistics. This function is usually called every
- * scheduler tick (TICK_NSEC). With tickless idle this will not be called
- * every tick. We fix it up based on jiffies.
- */
-static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
- unsigned long pending_updates)
-{
- int i, scale;
-
- this_rq->nr_load_updates++;
-
- /* Update our load: */
- this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
- for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
- unsigned long old_load, new_load;
-
- /* scale is effectively 1 << i now, and >> i divides by scale */
-
- old_load = this_rq->cpu_load[i];
- old_load = decay_load_missed(old_load, pending_updates - 1, i);
- new_load = this_load;
- /*
- * Round up the averaging division if load is increasing. This
- * prevents us from getting stuck on 9 if the load is 10, for
- * example.
- */
- if (new_load > old_load)
- new_load += scale - 1;
-
- this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
- }
-
- sched_avg_update(this_rq);
-}
-
-#ifdef CONFIG_SMP
-static inline unsigned long get_rq_runnable_load(struct rq *rq)
-{
- return rq->cfs.runnable_load_avg;
-}
-#else
-static inline unsigned long get_rq_runnable_load(struct rq *rq)
-{
- return rq->load.weight;
-}
-#endif
-
-#ifdef CONFIG_NO_HZ_COMMON
-/*
- * There is no sane way to deal with nohz on smp when using jiffies because the
- * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
- * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
- *
- * Therefore we cannot use the delta approach from the regular tick since that
- * would seriously skew the load calculation. However we'll make do for those
- * updates happening while idle (nohz_idle_balance) or coming out of idle
- * (tick_nohz_idle_exit).
- *
- * This means we might still be one tick off for nohz periods.
- */
-
-/*
- * Called from nohz_idle_balance() to update the load ratings before doing the
- * idle balance.
- */
-void update_idle_cpu_load(struct rq *this_rq)
-{
- unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
- unsigned long load = get_rq_runnable_load(this_rq);
- unsigned long pending_updates;
-
- /*
- * bail if there's load or we're actually up-to-date.
- */
- if (load || curr_jiffies == this_rq->last_load_update_tick)
- return;
-
- pending_updates = curr_jiffies - this_rq->last_load_update_tick;
- this_rq->last_load_update_tick = curr_jiffies;
-
- __update_cpu_load(this_rq, load, pending_updates);
-}
-
-/*
- * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
- */
-void update_cpu_load_nohz(void)
-{
- struct rq *this_rq = this_rq();
- unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
- unsigned long pending_updates;
-
- if (curr_jiffies == this_rq->last_load_update_tick)
- return;
-
- raw_spin_lock(&this_rq->lock);
- pending_updates = curr_jiffies - this_rq->last_load_update_tick;
- if (pending_updates) {
- this_rq->last_load_update_tick = curr_jiffies;
- /*
- * We were idle, this means load 0, the current load might be
- * !0 due to remote wakeups and the sort.
- */
- __update_cpu_load(this_rq, 0, pending_updates);
- }
- raw_spin_unlock(&this_rq->lock);
-}
-#endif /* CONFIG_NO_HZ */
-
-/*
- * Called from scheduler_tick()
- */
-void update_cpu_load_active(struct rq *this_rq)
-{
- unsigned long load = get_rq_runnable_load(this_rq);
- /*
- * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
- */
- this_rq->last_load_update_tick = jiffies;
- __update_cpu_load(this_rq, load, 1);
-
- calc_load_account_active(this_rq);
-}
{
struct rt_bandwidth *rt_b =
container_of(timer, struct rt_bandwidth, rt_period_timer);
- ktime_t now;
- int overrun;
int idle = 0;
+ int overrun;
+ raw_spin_lock(&rt_b->rt_runtime_lock);
for (;;) {
- now = hrtimer_cb_get_time(timer);
- overrun = hrtimer_forward(timer, now, rt_b->rt_period);
-
+ overrun = hrtimer_forward_now(timer, rt_b->rt_period);
if (!overrun)
break;
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
idle = do_sched_rt_period_timer(rt_b, overrun);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
}
+ if (idle)
+ rt_b->rt_period_active = 0;
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}
if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
return;
- if (hrtimer_active(&rt_b->rt_period_timer))
- return;
-
raw_spin_lock(&rt_b->rt_runtime_lock);
- start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period);
+ if (!rt_b->rt_period_active) {
+ rt_b->rt_period_active = 1;
+ hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period);
+ hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
+ }
raw_spin_unlock(&rt_b->rt_runtime_lock);
}
rq = cpu_rq(cpu);
rcu_read_lock();
- curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+ curr = READ_ONCE(rq->curr); /* unlocked access */
/*
* If the current task on @p's runqueue is an RT task, then
extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;
+extern void calc_global_load_tick(struct rq *this_rq);
extern long calc_load_fold_active(struct rq *this_rq);
+
+#ifdef CONFIG_SMP
extern void update_cpu_load_active(struct rq *this_rq);
+#else
+static inline void update_cpu_load_active(struct rq *this_rq) { }
+#endif
/*
* Helpers for converting nanosecond timing to jiffy resolution
ktime_t rt_period;
u64 rt_runtime;
struct hrtimer rt_period_timer;
+ unsigned int rt_period_active;
};
void __dl_clear_params(struct task_struct *p);
s64 hierarchical_quota;
u64 runtime_expires;
- int idle, timer_active;
+ int idle, period_active;
struct hrtimer period_timer, slack_timer;
struct list_head throttled_cfs_rq;
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
-extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force);
+extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
extern void free_rt_sched_group(struct task_group *tg);
static inline u64 __rq_clock_broken(struct rq *rq)
{
- return ACCESS_ONCE(rq->clock);
+ return READ_ONCE(rq->clock);
}
static inline u64 rq_clock(struct rq *rq)
extern void init_sched_dl_class(void);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
-extern void init_sched_dl_class(void);
extern void resched_curr(struct rq *rq);
extern void resched_cpu(int cpu);
unsigned long to_ratio(u64 period, u64 runtime);
-extern void update_idle_cpu_load(struct rq *this_rq);
-
extern void init_task_runnable_average(struct task_struct *p);
static inline void add_nr_running(struct rq *rq, unsigned count)
static inline void sched_avg_update(struct rq *rq) { }
#endif
-extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);
-
/*
* __task_rq_lock - lock the rq @p resides on.
*/
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
- if (!cputimer->running)
+ /* Check if cputimer isn't running. This is accessed without locking. */
+ if (!READ_ONCE(cputimer->running))
return false;
/*
if (!cputimer_running(tsk))
return;
- raw_spin_lock(&cputimer->lock);
- cputimer->cputime.utime += cputime;
- raw_spin_unlock(&cputimer->lock);
+ atomic64_add(cputime, &cputimer->cputime_atomic.utime);
}
/**
if (!cputimer_running(tsk))
return;
- raw_spin_lock(&cputimer->lock);
- cputimer->cputime.stime += cputime;
- raw_spin_unlock(&cputimer->lock);
+ atomic64_add(cputime, &cputimer->cputime_atomic.stime);
}
/**
if (!cputimer_running(tsk))
return;
- raw_spin_lock(&cputimer->lock);
- cputimer->cputime.sum_exec_runtime += ns;
- raw_spin_unlock(&cputimer->lock);
+ atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime);
}
* condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
* an event.
*/
- set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+ smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
return timeout;
}
* doesn't imply write barrier and the users expects write
* barrier semantics on wakeup functions. The following
* smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
- * and is paired with set_mb() in wait_woken().
+ * and is paired with smp_store_mb() in wait_woken().
*/
smp_wmb(); /* C */
wait->flags |= WQ_FLAG_WOKEN;
__sched int bit_wait_timeout(struct wait_bit_key *word)
{
- unsigned long now = ACCESS_ONCE(jiffies);
+ unsigned long now = READ_ONCE(jiffies);
if (signal_pending_state(current->state, current))
return 1;
if (time_after_eq(now, word->timeout))
__sched int bit_wait_io_timeout(struct wait_bit_key *word)
{
- unsigned long now = ACCESS_ONCE(jiffies);
+ unsigned long now = READ_ONCE(jiffies);
if (signal_pending_state(current->state, current))
return 1;
if (time_after_eq(now, word->timeout))
* RETURNS:
* %true if @mask is set, %false if made noop because @task was dying.
*/
-bool task_set_jobctl_pending(struct task_struct *task, unsigned int mask)
+bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask)
{
BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME |
JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
* CONTEXT:
* Must be called with @task->sighand->siglock held.
*/
-void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask)
+void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask)
{
BUG_ON(mask & ~JOBCTL_PENDING_MASK);
struct signal_struct *sig = current->signal;
if (!(current->jobctl & JOBCTL_STOP_PENDING)) {
- unsigned int gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
+ unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
struct task_struct *t;
/* signr will be recorded in task->jobctl for retries */
return err;
}
-struct irq_cpu_stop_queue_work_info {
- int cpu1;
- int cpu2;
- struct cpu_stop_work *work1;
- struct cpu_stop_work *work2;
-};
-
-/*
- * This function is always run with irqs and preemption disabled.
- * This guarantees that both work1 and work2 get queued, before
- * our local migrate thread gets the chance to preempt us.
- */
-static void irq_cpu_stop_queue_work(void *arg)
-{
- struct irq_cpu_stop_queue_work_info *info = arg;
- cpu_stop_queue_work(info->cpu1, info->work1);
- cpu_stop_queue_work(info->cpu2, info->work2);
-}
-
/**
* stop_two_cpus - stops two cpus
* @cpu1: the cpu to stop
{
struct cpu_stop_done done;
struct cpu_stop_work work1, work2;
- struct irq_cpu_stop_queue_work_info call_args;
struct multi_stop_data msdata;
preempt_disable();
.done = &done
};
- call_args = (struct irq_cpu_stop_queue_work_info){
- .cpu1 = cpu1,
- .cpu2 = cpu2,
- .work1 = &work1,
- .work2 = &work2,
- };
-
cpu_stop_init_done(&done, 2);
set_state(&msdata, MULTI_STOP_PREPARE);
return -ENOENT;
}
- lg_local_lock(&stop_cpus_lock);
- /*
- * Queuing needs to be done by the lowest numbered CPU, to ensure
- * that works are always queued in the same order on every CPU.
- * This prevents deadlocks.
- */
- smp_call_function_single(min(cpu1, cpu2),
- &irq_cpu_stop_queue_work,
- &call_args, 1);
- lg_local_unlock(&stop_cpus_lock);
+ lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
+ cpu_stop_queue_work(cpu1, &work1);
+ cpu_stop_queue_work(cpu2, &work2);
+ lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
+
preempt_enable();
wait_for_completion(&done.completion);
# define SET_TSC_CTL(a) (-EINVAL)
#endif
#ifndef MPX_ENABLE_MANAGEMENT
-# define MPX_ENABLE_MANAGEMENT(a) (-EINVAL)
+# define MPX_ENABLE_MANAGEMENT() (-EINVAL)
#endif
#ifndef MPX_DISABLE_MANAGEMENT
-# define MPX_DISABLE_MANAGEMENT(a) (-EINVAL)
+# define MPX_DISABLE_MANAGEMENT() (-EINVAL)
#endif
#ifndef GET_FP_MODE
# define GET_FP_MODE(a) (-EINVAL)
case PR_MPX_ENABLE_MANAGEMENT:
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
- error = MPX_ENABLE_MANAGEMENT(me);
+ error = MPX_ENABLE_MANAGEMENT();
break;
case PR_MPX_DISABLE_MANAGEMENT:
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
- error = MPX_DISABLE_MANAGEMENT(me);
+ error = MPX_DISABLE_MANAGEMENT();
break;
case PR_SET_FP_MODE:
error = SET_FP_MODE(me, arg2);
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "timer_migration",
- .data = &sysctl_timer_migration,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &one,
- },
#endif /* CONFIG_SMP */
#ifdef CONFIG_NUMA_BALANCING
{
.extra1 = &zero,
.extra2 = &one,
},
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+ {
+ .procname = "timer_migration",
+ .data = &sysctl_timer_migration,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = timer_migration_handler,
+ },
+#endif
{ }
};
obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o
obj-$(CONFIG_TEST_UDELAY) += test_udelay.o
-$(obj)/time.o: $(obj)/timeconst.h
-
-quiet_cmd_hzfile = HZFILE $@
- cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@
-
-targets += hz.bc
-$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE
- $(call if_changed,hzfile)
-
-quiet_cmd_bc = BC $@
- cmd_bc = bc -q $(filter-out FORCE,$^) > $@
-
-targets += timeconst.h
-$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
- $(call if_changed,bc)
-
+$(obj)/time.o: $(objtree)/include/config/
* @alarm: ptr to alarm to set
* @start: time to run the alarm
*/
-int alarm_start(struct alarm *alarm, ktime_t start)
+void alarm_start(struct alarm *alarm, ktime_t start)
{
struct alarm_base *base = &alarm_bases[alarm->type];
unsigned long flags;
- int ret;
spin_lock_irqsave(&base->lock, flags);
alarm->node.expires = start;
alarmtimer_enqueue(base, alarm);
- ret = hrtimer_start(&alarm->timer, alarm->node.expires,
- HRTIMER_MODE_ABS);
+ hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
spin_unlock_irqrestore(&base->lock, flags);
- return ret;
}
EXPORT_SYMBOL_GPL(alarm_start);
* @alarm: ptr to alarm to set
* @start: time relative to now to run the alarm
*/
-int alarm_start_relative(struct alarm *alarm, ktime_t start)
+void alarm_start_relative(struct alarm *alarm, ktime_t start)
{
struct alarm_base *base = &alarm_bases[alarm->type];
start = ktime_add(start, base->gettime());
- return alarm_start(alarm, start);
+ alarm_start(alarm, start);
}
EXPORT_SYMBOL_GPL(alarm_start_relative);
*/
static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
{
- clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
-
if (!alarmtimer_get_rtcdev())
return -EINVAL;
- return hrtimer_get_res(baseid, tp);
+ tp->tv_sec = 0;
+ tp->tv_nsec = hrtimer_resolution;
+ return 0;
}
/**
}
EXPORT_SYMBOL_GPL(clockevent_delta2ns);
-static int __clockevents_set_state(struct clock_event_device *dev,
- enum clock_event_state state)
+static int __clockevents_switch_state(struct clock_event_device *dev,
+ enum clock_event_state state)
{
/* Transition with legacy set_mode() callback */
if (dev->set_mode) {
/* Transition with new state-specific callbacks */
switch (state) {
case CLOCK_EVT_STATE_DETACHED:
- /*
- * This is an internal state, which is guaranteed to go from
- * SHUTDOWN to DETACHED. No driver interaction required.
- */
- return 0;
+ /* The clockevent device is getting replaced. Shut it down. */
case CLOCK_EVT_STATE_SHUTDOWN:
return dev->set_state_shutdown(dev);
return -ENOSYS;
return dev->set_state_oneshot(dev);
+ case CLOCK_EVT_STATE_ONESHOT_STOPPED:
+ /* Core internal bug */
+ if (WARN_ONCE(!clockevent_state_oneshot(dev),
+ "Current state: %d\n",
+ clockevent_get_state(dev)))
+ return -EINVAL;
+
+ if (dev->set_state_oneshot_stopped)
+ return dev->set_state_oneshot_stopped(dev);
+ else
+ return -ENOSYS;
+
default:
return -ENOSYS;
}
}
/**
- * clockevents_set_state - set the operating state of a clock event device
+ * clockevents_switch_state - set the operating state of a clock event device
* @dev: device to modify
* @state: new state
*
* Must be called with interrupts disabled !
*/
-void clockevents_set_state(struct clock_event_device *dev,
- enum clock_event_state state)
+void clockevents_switch_state(struct clock_event_device *dev,
+ enum clock_event_state state)
{
- if (dev->state != state) {
- if (__clockevents_set_state(dev, state))
+ if (clockevent_get_state(dev) != state) {
+ if (__clockevents_switch_state(dev, state))
return;
- dev->state = state;
+ clockevent_set_state(dev, state);
/*
* A nsec2cyc multiplicator of 0 is invalid and we'd crash
* on it, so fix it up and emit a warning:
*/
- if (state == CLOCK_EVT_STATE_ONESHOT) {
+ if (clockevent_state_oneshot(dev)) {
if (unlikely(!dev->mult)) {
dev->mult = 1;
WARN_ON(1);
*/
void clockevents_shutdown(struct clock_event_device *dev)
{
- clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
dev->next_event.tv64 = KTIME_MAX;
}
delta = dev->min_delta_ns;
dev->next_event = ktime_add_ns(ktime_get(), delta);
- if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+ if (clockevent_state_shutdown(dev))
return 0;
dev->retries++;
delta = dev->min_delta_ns;
dev->next_event = ktime_add_ns(ktime_get(), delta);
- if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+ if (clockevent_state_shutdown(dev))
return 0;
dev->retries++;
dev->next_event = expires;
- if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
+ if (clockevent_state_shutdown(dev))
return 0;
+ /* We must be in ONESHOT state here */
+ WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n",
+ clockevent_get_state(dev));
+
/* Shortcut for clockevent devices that can deal with ktime. */
if (dev->features & CLOCK_EVT_FEAT_KTIME)
return dev->set_next_ktime(expires, dev);
struct clock_event_device *dev, *newdev = NULL;
list_for_each_entry(dev, &clockevent_devices, list) {
- if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED)
+ if (dev == ced || !clockevent_state_detached(dev))
continue;
if (!tick_check_replacement(newdev, dev))
static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
{
/* Fast track. Device is unused */
- if (ced->state == CLOCK_EVT_STATE_DETACHED) {
+ if (clockevent_state_detached(ced)) {
list_del_init(&ced->list);
return 0;
}
if (dev->set_mode) {
/* We shouldn't be supporting new modes now */
WARN_ON(dev->set_state_periodic || dev->set_state_oneshot ||
- dev->set_state_shutdown || dev->tick_resume);
+ dev->set_state_shutdown || dev->tick_resume ||
+ dev->set_state_oneshot_stopped);
BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
return 0;
BUG_ON(clockevents_sanity_check(dev));
/* Initialize state to DETACHED */
- dev->state = CLOCK_EVT_STATE_DETACHED;
+ clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
if (!dev->cpumask) {
WARN_ON(num_possible_cpus() > 1);
{
clockevents_config(dev, freq);
- if (dev->state == CLOCK_EVT_STATE_ONESHOT)
+ if (clockevent_state_oneshot(dev))
return clockevents_program_event(dev, dev->next_event, false);
- if (dev->state == CLOCK_EVT_STATE_PERIODIC)
- return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
+ if (clockevent_state_periodic(dev))
+ return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
return 0;
}
*/
if (old) {
module_put(old->owner);
- clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED);
+ clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED);
list_del(&old->list);
list_add(&old->list, &clockevents_released);
}
if (new) {
- BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED);
+ BUG_ON(!clockevent_state_detached(new));
clockevents_shutdown(new);
}
}
struct clock_event_device *dev;
list_for_each_entry_reverse(dev, &clockevent_devices, list)
- if (dev->suspend)
+ if (dev->suspend && !clockevent_state_detached(dev))
dev->suspend(dev);
}
struct clock_event_device *dev;
list_for_each_entry(dev, &clockevent_devices, list)
- if (dev->resume)
+ if (dev->resume && !clockevent_state_detached(dev))
dev->resume(dev);
}
if (cpumask_test_cpu(cpu, dev->cpumask) &&
cpumask_weight(dev->cpumask) == 1 &&
!tick_is_broadcast_device(dev)) {
- BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED);
+ BUG_ON(!clockevent_state_detached(dev));
list_del(&dev->list);
}
}
* o Allow clocksource drivers to be unregistered
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/device.h>
#include <linux/clocksource.h>
#include <linux/init.h>
/* Check the deviation from the watchdog clocksource. */
if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
- pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name);
- pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
+ pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
+ cs->name);
+ pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
watchdog->name, wdnow, wdlast, watchdog->mask);
- pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
+ pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
cs->name, csnow, cslast, cs->mask);
__clocksource_unstable(cs);
continue;
*/
if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
/* Override clocksource cannot be used. */
- printk(KERN_WARNING "Override clocksource %s is not "
- "HRT compatible. Cannot switch while in "
- "HRT/NOHZ mode\n", cs->name);
+ pr_warn("Override clocksource %s is not HRT compatible - cannot switch while in HRT/NOHZ mode\n",
+ cs->name);
override_name[0] = 0;
} else
/* Override clocksource can be used. */
clocksource_update_max_deferment(cs);
- pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
- cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
+ pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
+ cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
}
EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
static int __init boot_override_clock(char* str)
{
if (!strcmp(str, "pmtmr")) {
- printk("Warning: clock=pmtmr is deprecated. "
- "Use clocksource=acpi_pm.\n");
+ pr_warn("clock=pmtmr is deprecated - use clocksource=acpi_pm\n");
return boot_override_clocksource("acpi_pm");
}
- printk("Warning! clock= boot option is deprecated. "
- "Use clocksource=xyz\n");
+ pr_warn("clock= boot option is deprecated - use clocksource=xyz\n");
return boot_override_clocksource(str);
}
*/
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
-
.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
+ .seq = SEQCNT_ZERO(hrtimer_bases.seq),
.clock_base =
{
{
.index = HRTIMER_BASE_MONOTONIC,
.clockid = CLOCK_MONOTONIC,
.get_time = &ktime_get,
- .resolution = KTIME_LOW_RES,
},
{
.index = HRTIMER_BASE_REALTIME,
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
- .resolution = KTIME_LOW_RES,
},
{
.index = HRTIMER_BASE_BOOTTIME,
.clockid = CLOCK_BOOTTIME,
.get_time = &ktime_get_boottime,
- .resolution = KTIME_LOW_RES,
},
{
.index = HRTIMER_BASE_TAI,
.clockid = CLOCK_TAI,
.get_time = &ktime_get_clocktai,
- .resolution = KTIME_LOW_RES,
},
}
};
return hrtimer_clock_to_base_table[clock_id];
}
-
-/*
- * Get the coarse grained time at the softirq based on xtime and
- * wall_to_monotonic.
- */
-static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
-{
- ktime_t xtim, mono, boot, tai;
- ktime_t off_real, off_boot, off_tai;
-
- mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
- boot = ktime_add(mono, off_boot);
- xtim = ktime_add(mono, off_real);
- tai = ktime_add(mono, off_tai);
-
- base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
- base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
- base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
- base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai;
-}
-
/*
* Functions and macros which are different for UP/SMP systems are kept in a
* single place
*/
#ifdef CONFIG_SMP
+/*
+ * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base()
+ * such that hrtimer_callback_running() can unconditionally dereference
+ * timer->base->cpu_base
+ */
+static struct hrtimer_cpu_base migration_cpu_base = {
+ .seq = SEQCNT_ZERO(migration_cpu_base),
+ .clock_base = { { .cpu_base = &migration_cpu_base, }, },
+};
+
+#define migration_base migration_cpu_base.clock_base[0]
+
/*
* We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
* means that all timers which are tied to this base via timer->base are
* be found on the lists/queues.
*
* When the timer's base is locked, and the timer removed from list, it is
- * possible to set timer->base = NULL and drop the lock: the timer remains
- * locked.
+ * possible to set timer->base = &migration_base and drop the lock: the timer
+ * remains locked.
*/
static
struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
for (;;) {
base = timer->base;
- if (likely(base != NULL)) {
+ if (likely(base != &migration_base)) {
raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
if (likely(base == timer->base))
return base;
#endif
}
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+static inline
+struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
+ int pinned)
+{
+ if (pinned || !base->migration_enabled)
+ return this_cpu_ptr(&hrtimer_bases);
+ return &per_cpu(hrtimer_bases, get_nohz_timer_target());
+}
+#else
+static inline
+struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
+ int pinned)
+{
+ return this_cpu_ptr(&hrtimer_bases);
+}
+#endif
+
/*
* Switch the timer base to the current CPU when possible.
*/
switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
int pinned)
{
+ struct hrtimer_cpu_base *new_cpu_base, *this_base;
struct hrtimer_clock_base *new_base;
- struct hrtimer_cpu_base *new_cpu_base;
- int this_cpu = smp_processor_id();
- int cpu = get_nohz_timer_target(pinned);
int basenum = base->index;
+ this_base = this_cpu_ptr(&hrtimer_bases);
+ new_cpu_base = get_target_base(this_base, pinned);
again:
- new_cpu_base = &per_cpu(hrtimer_bases, cpu);
new_base = &new_cpu_base->clock_base[basenum];
if (base != new_base) {
if (unlikely(hrtimer_callback_running(timer)))
return base;
- /* See the comment in lock_timer_base() */
- timer->base = NULL;
+ /* See the comment in lock_hrtimer_base() */
+ timer->base = &migration_base;
raw_spin_unlock(&base->cpu_base->lock);
raw_spin_lock(&new_base->cpu_base->lock);
- if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
- cpu = this_cpu;
+ if (new_cpu_base != this_base &&
+ hrtimer_check_target(timer, new_base)) {
raw_spin_unlock(&new_base->cpu_base->lock);
raw_spin_lock(&base->cpu_base->lock);
+ new_cpu_base = this_base;
timer->base = base;
goto again;
}
timer->base = new_base;
} else {
- if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
- cpu = this_cpu;
+ if (new_cpu_base != this_base &&
+ hrtimer_check_target(timer, new_base)) {
+ new_cpu_base = this_base;
goto again;
}
}
/*
* Divide a ktime value by a nanosecond value
*/
-u64 __ktime_divns(const ktime_t kt, s64 div)
+s64 __ktime_divns(const ktime_t kt, s64 div)
{
- u64 dclc;
int sft = 0;
+ s64 dclc;
+ u64 tmp;
dclc = ktime_to_ns(kt);
+ tmp = dclc < 0 ? -dclc : dclc;
+
/* Make sure the divisor is less than 2^32: */
while (div >> 32) {
sft++;
div >>= 1;
}
- dclc >>= sft;
- do_div(dclc, (unsigned long) div);
-
- return dclc;
+ tmp >>= sft;
+ do_div(tmp, (unsigned long) div);
+ return dclc < 0 ? -tmp : tmp;
}
EXPORT_SYMBOL_GPL(__ktime_divns);
#endif /* BITS_PER_LONG >= 64 */
}
#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
+ struct hrtimer *timer)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+ cpu_base->next_timer = timer;
+#endif
+}
+
static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
{
struct hrtimer_clock_base *base = cpu_base->clock_base;
ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
- int i;
+ unsigned int active = cpu_base->active_bases;
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+ hrtimer_update_next_timer(cpu_base, NULL);
+ for (; active; base++, active >>= 1) {
struct timerqueue_node *next;
struct hrtimer *timer;
- next = timerqueue_getnext(&base->active);
- if (!next)
+ if (!(active & 0x01))
continue;
+ next = timerqueue_getnext(&base->active);
timer = container_of(next, struct hrtimer, node);
expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
- if (expires.tv64 < expires_next.tv64)
+ if (expires.tv64 < expires_next.tv64) {
expires_next = expires;
+ hrtimer_update_next_timer(cpu_base, timer);
+ }
}
/*
* clock_was_set() might have changed base->offset of any of
}
#endif
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+ ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+ ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+ ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
+
+ return ktime_get_update_offsets_now(&base->clock_was_set_seq,
+ offs_real, offs_boot, offs_tai);
+}
+
/* High resolution timer related functions */
#ifdef CONFIG_HIGH_RES_TIMERS
* High resolution timer enabled ?
*/
static int hrtimer_hres_enabled __read_mostly = 1;
+unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
+EXPORT_SYMBOL_GPL(hrtimer_resolution);
/*
* Enable / Disable high resolution mode
/*
* Is the high resolution mode active ?
*/
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
+{
+ return cpu_base->hres_active;
+}
+
static inline int hrtimer_hres_active(void)
{
- return __this_cpu_read(hrtimer_bases.hres_active);
+ return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases));
}
/*
static void
hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
{
- ktime_t expires_next = __hrtimer_get_next_event(cpu_base);
+ ktime_t expires_next;
+
+ if (!cpu_base->hres_active)
+ return;
+
+ expires_next = __hrtimer_get_next_event(cpu_base);
if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
return;
if (cpu_base->hang_detected)
return;
- if (cpu_base->expires_next.tv64 != KTIME_MAX)
- tick_program_event(cpu_base->expires_next, 1);
+ tick_program_event(cpu_base->expires_next, 1);
}
/*
- * Shared reprogramming for clock_realtime and clock_monotonic
- *
* When a timer is enqueued and expires earlier than the already enqueued
* timers, we have to check, whether it expires earlier than the timer for
* which the clock event device was armed.
*
- * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming
- * and no expiry check happens. The timer gets enqueued into the rbtree. The
- * reprogramming and expiry check is done in the hrtimer_interrupt or in the
- * softirq.
- *
* Called with interrupts disabled and base->cpu_base.lock held
*/
-static int hrtimer_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+static void hrtimer_reprogram(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
- int res;
WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
/*
- * When the callback is running, we do not reprogram the clock event
- * device. The timer callback is either running on a different CPU or
- * the callback is executed in the hrtimer_interrupt context. The
- * reprogramming is handled either by the softirq, which called the
- * callback or at the end of the hrtimer_interrupt.
+ * If the timer is not on the current cpu, we cannot reprogram
+ * the other cpus clock event device.
*/
- if (hrtimer_callback_running(timer))
- return 0;
+ if (base->cpu_base != cpu_base)
+ return;
+
+ /*
+ * If the hrtimer interrupt is running, then it will
+ * reevaluate the clock bases and reprogram the clock event
+ * device. The callbacks are always executed in hard interrupt
+ * context so we don't need an extra check for a running
+ * callback.
+ */
+ if (cpu_base->in_hrtirq)
+ return;
/*
* CLOCK_REALTIME timer might be requested with an absolute
- * expiry time which is less than base->offset. Nothing wrong
- * about that, just avoid to call into the tick code, which
- * has now objections against negative expiry values.
+ * expiry time which is less than base->offset. Set it to 0.
*/
if (expires.tv64 < 0)
- return -ETIME;
+ expires.tv64 = 0;
if (expires.tv64 >= cpu_base->expires_next.tv64)
- return 0;
+ return;
- /*
- * When the target cpu of the timer is currently executing
- * hrtimer_interrupt(), then we do not touch the clock event
- * device. hrtimer_interrupt() will reevaluate all clock bases
- * before reprogramming the device.
- */
- if (cpu_base->in_hrtirq)
- return 0;
+ /* Update the pointer to the next expiring timer */
+ cpu_base->next_timer = timer;
/*
* If a hang was detected in the last timer interrupt then we
* to make progress.
*/
if (cpu_base->hang_detected)
- return 0;
+ return;
/*
- * Clockevents returns -ETIME, when the event was in the past.
+ * Program the timer hardware. We enforce the expiry for
+ * events which are already in the past.
*/
- res = tick_program_event(expires, 0);
- if (!IS_ERR_VALUE(res))
- cpu_base->expires_next = expires;
- return res;
+ cpu_base->expires_next = expires;
+ tick_program_event(expires, 1);
}
/*
base->hres_active = 0;
}
-static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
-{
- ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
- ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
- ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
-
- return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai);
-}
-
/*
* Retrigger next event is called after clock was set
*
{
struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
- if (!hrtimer_hres_active())
+ if (!base->hres_active)
return;
raw_spin_lock(&base->lock);
*/
static int hrtimer_switch_to_hres(void)
{
- int i, cpu = smp_processor_id();
- struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
- unsigned long flags;
-
- if (base->hres_active)
- return 1;
-
- local_irq_save(flags);
+ struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
if (tick_init_highres()) {
- local_irq_restore(flags);
printk(KERN_WARNING "Could not switch to high resolution "
- "mode on CPU %d\n", cpu);
+ "mode on CPU %d\n", base->cpu);
return 0;
}
base->hres_active = 1;
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
- base->clock_base[i].resolution = KTIME_HIGH_RES;
+ hrtimer_resolution = HIGH_RES_NSEC;
tick_setup_sched_timer();
/* "Retrigger" the interrupt to get things going */
retrigger_next_event(NULL);
- local_irq_restore(flags);
return 1;
}
#else
+static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline int hrtimer_switch_to_hres(void) { return 0; }
*
* Forward the timer expiry so it will expire in the future.
* Returns the number of overruns.
+ *
+ * Can be safely called from the callback function of @timer. If
+ * called from other contexts @timer must neither be enqueued nor
+ * running the callback and the caller needs to take care of
+ * serialization.
+ *
+ * Note: This only updates the timer expiry value and does not requeue
+ * the timer.
*/
u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
{
if (delta.tv64 < 0)
return 0;
- if (interval.tv64 < timer->base->resolution.tv64)
- interval.tv64 = timer->base->resolution.tv64;
+ if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED))
+ return 0;
+
+ if (interval.tv64 < hrtimer_resolution)
+ interval.tv64 = hrtimer_resolution;
if (unlikely(delta.tv64 >= interval.tv64)) {
s64 incr = ktime_to_ns(interval);
{
debug_activate(timer);
- timerqueue_add(&base->active, &timer->node);
base->cpu_base->active_bases |= 1 << base->index;
- /*
- * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
- * state of a possibly running callback.
- */
- timer->state |= HRTIMER_STATE_ENQUEUED;
+ timer->state = HRTIMER_STATE_ENQUEUED;
- return (&timer->node == base->active.next);
+ return timerqueue_add(&base->active, &timer->node);
}
/*
struct hrtimer_clock_base *base,
unsigned long newstate, int reprogram)
{
- struct timerqueue_node *next_timer;
- if (!(timer->state & HRTIMER_STATE_ENQUEUED))
- goto out;
+ struct hrtimer_cpu_base *cpu_base = base->cpu_base;
+ unsigned int state = timer->state;
+
+ timer->state = newstate;
+ if (!(state & HRTIMER_STATE_ENQUEUED))
+ return;
+
+ if (!timerqueue_del(&base->active, &timer->node))
+ cpu_base->active_bases &= ~(1 << base->index);
- next_timer = timerqueue_getnext(&base->active);
- timerqueue_del(&base->active, &timer->node);
- if (&timer->node == next_timer) {
#ifdef CONFIG_HIGH_RES_TIMERS
- /* Reprogram the clock event device. if enabled */
- if (reprogram && hrtimer_hres_active()) {
- ktime_t expires;
-
- expires = ktime_sub(hrtimer_get_expires(timer),
- base->offset);
- if (base->cpu_base->expires_next.tv64 == expires.tv64)
- hrtimer_force_reprogram(base->cpu_base, 1);
- }
+ /*
+ * Note: If reprogram is false we do not update
+ * cpu_base->next_timer. This happens when we remove the first
+ * timer on a remote cpu. No harm as we never dereference
+ * cpu_base->next_timer. So the worst thing what can happen is
+ * an superflous call to hrtimer_force_reprogram() on the
+ * remote cpu later on if the same timer gets enqueued again.
+ */
+ if (reprogram && timer == cpu_base->next_timer)
+ hrtimer_force_reprogram(cpu_base, 1);
#endif
- }
- if (!timerqueue_getnext(&base->active))
- base->cpu_base->active_bases &= ~(1 << base->index);
-out:
- timer->state = newstate;
}
/*
* remove hrtimer, called with base lock held
*/
static inline int
-remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
+remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
{
if (hrtimer_is_queued(timer)) {
- unsigned long state;
+ unsigned long state = timer->state;
int reprogram;
/*
debug_deactivate(timer);
timer_stats_hrtimer_clear_start_info(timer);
reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
- /*
- * We must preserve the CALLBACK state flag here,
- * otherwise we could move the timer base in
- * switch_hrtimer_base.
- */
- state = timer->state & HRTIMER_STATE_CALLBACK;
+
+ if (!restart)
+ state = HRTIMER_STATE_INACTIVE;
+
__remove_hrtimer(timer, base, state, reprogram);
return 1;
}
return 0;
}
-int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- unsigned long delta_ns, const enum hrtimer_mode mode,
- int wakeup)
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer: the timer to be added
+ * @tim: expiry time
+ * @delta_ns: "slack" range for the timer
+ * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL)
+ */
+void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns, const enum hrtimer_mode mode)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
- int ret, leftmost;
+ int leftmost;
base = lock_hrtimer_base(timer, &flags);
/* Remove an active timer from the queue: */
- ret = remove_hrtimer(timer, base);
+ remove_hrtimer(timer, base, true);
if (mode & HRTIMER_MODE_REL) {
tim = ktime_add_safe(tim, base->get_time());
* timeouts. This will go away with the GTOD framework.
*/
#ifdef CONFIG_TIME_LOW_RES
- tim = ktime_add_safe(tim, base->resolution);
+ tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
#endif
}
timer_stats_hrtimer_set_start_info(timer);
leftmost = enqueue_hrtimer(timer, new_base);
-
- if (!leftmost) {
- unlock_hrtimer_base(timer, &flags);
- return ret;
- }
+ if (!leftmost)
+ goto unlock;
if (!hrtimer_is_hres_active(timer)) {
/*
* Kick to reschedule the next tick to handle the new timer
* on dynticks target.
*/
- wake_up_nohz_cpu(new_base->cpu_base->cpu);
- } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) &&
- hrtimer_reprogram(timer, new_base)) {
- /*
- * Only allow reprogramming if the new base is on this CPU.
- * (it might still be on another CPU if the timer was pending)
- *
- * XXX send_remote_softirq() ?
- */
- if (wakeup) {
- /*
- * We need to drop cpu_base->lock to avoid a
- * lock ordering issue vs. rq->lock.
- */
- raw_spin_unlock(&new_base->cpu_base->lock);
- raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- local_irq_restore(flags);
- return ret;
- } else {
- __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- }
+ if (new_base->cpu_base->nohz_active)
+ wake_up_nohz_cpu(new_base->cpu_base->cpu);
+ } else {
+ hrtimer_reprogram(timer, new_base);
}
-
+unlock:
unlock_hrtimer_base(timer, &flags);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns);
-
-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer: the timer to be added
- * @tim: expiry time
- * @delta_ns: "slack" range for the timer
- * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
- * relative (HRTIMER_MODE_REL)
- *
- * Returns:
- * 0 on success
- * 1 when the timer was active
- */
-int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- unsigned long delta_ns, const enum hrtimer_mode mode)
-{
- return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
}
EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
-/**
- * hrtimer_start - (re)start an hrtimer on the current CPU
- * @timer: the timer to be added
- * @tim: expiry time
- * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
- * relative (HRTIMER_MODE_REL)
- *
- * Returns:
- * 0 on success
- * 1 when the timer was active
- */
-int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
-{
- return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
-}
-EXPORT_SYMBOL_GPL(hrtimer_start);
-
-
/**
* hrtimer_try_to_cancel - try to deactivate a timer
* @timer: hrtimer to stop
unsigned long flags;
int ret = -1;
+ /*
+ * Check lockless first. If the timer is not active (neither
+ * enqueued nor running the callback, nothing to do here. The
+ * base lock does not serialize against a concurrent enqueue,
+ * so we can avoid taking it.
+ */
+ if (!hrtimer_active(timer))
+ return 0;
+
base = lock_hrtimer_base(timer, &flags);
if (!hrtimer_callback_running(timer))
- ret = remove_hrtimer(timer, base);
+ ret = remove_hrtimer(timer, base, false);
unlock_hrtimer_base(timer, &flags);
/**
* hrtimer_get_next_event - get the time until next expiry event
*
- * Returns the delta to the next expiry event or KTIME_MAX if no timer
- * is pending.
+ * Returns the next expiry time or KTIME_MAX if no timer is pending.
*/
-ktime_t hrtimer_get_next_event(void)
+u64 hrtimer_get_next_event(void)
{
struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
- ktime_t mindelta = { .tv64 = KTIME_MAX };
+ u64 expires = KTIME_MAX;
unsigned long flags;
raw_spin_lock_irqsave(&cpu_base->lock, flags);
- if (!hrtimer_hres_active())
- mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base),
- ktime_get());
+ if (!__hrtimer_hres_active(cpu_base))
+ expires = __hrtimer_get_next_event(cpu_base).tv64;
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
- if (mindelta.tv64 < 0)
- mindelta.tv64 = 0;
- return mindelta;
+ return expires;
}
#endif
}
EXPORT_SYMBOL_GPL(hrtimer_init);
-/**
- * hrtimer_get_res - get the timer resolution for a clock
- * @which_clock: which clock to query
- * @tp: pointer to timespec variable to store the resolution
+/*
+ * A timer is active, when it is enqueued into the rbtree or the
+ * callback function is running or it's in the state of being migrated
+ * to another cpu.
*
- * Store the resolution of the clock selected by @which_clock in the
- * variable pointed to by @tp.
+ * It is important for this function to not return a false negative.
*/
-int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
+bool hrtimer_active(const struct hrtimer *timer)
{
struct hrtimer_cpu_base *cpu_base;
- int base = hrtimer_clockid_to_base(which_clock);
+ unsigned int seq;
- cpu_base = raw_cpu_ptr(&hrtimer_bases);
- *tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
+ do {
+ cpu_base = READ_ONCE(timer->base->cpu_base);
+ seq = raw_read_seqcount_begin(&cpu_base->seq);
- return 0;
+ if (timer->state != HRTIMER_STATE_INACTIVE ||
+ cpu_base->running == timer)
+ return true;
+
+ } while (read_seqcount_retry(&cpu_base->seq, seq) ||
+ cpu_base != READ_ONCE(timer->base->cpu_base));
+
+ return false;
}
-EXPORT_SYMBOL_GPL(hrtimer_get_res);
+EXPORT_SYMBOL_GPL(hrtimer_active);
-static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
+/*
+ * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3
+ * distinct sections:
+ *
+ * - queued: the timer is queued
+ * - callback: the timer is being ran
+ * - post: the timer is inactive or (re)queued
+ *
+ * On the read side we ensure we observe timer->state and cpu_base->running
+ * from the same section, if anything changed while we looked at it, we retry.
+ * This includes timer->base changing because sequence numbers alone are
+ * insufficient for that.
+ *
+ * The sequence numbers are required because otherwise we could still observe
+ * a false negative if the read side got smeared over multiple consequtive
+ * __run_hrtimer() invocations.
+ */
+
+static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
+ struct hrtimer_clock_base *base,
+ struct hrtimer *timer, ktime_t *now)
{
- struct hrtimer_clock_base *base = timer->base;
- struct hrtimer_cpu_base *cpu_base = base->cpu_base;
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
- WARN_ON(!irqs_disabled());
+ lockdep_assert_held(&cpu_base->lock);
debug_deactivate(timer);
- __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+ cpu_base->running = timer;
+
+ /*
+ * Separate the ->running assignment from the ->state assignment.
+ *
+ * As with a regular write barrier, this ensures the read side in
+ * hrtimer_active() cannot observe cpu_base->running == NULL &&
+ * timer->state == INACTIVE.
+ */
+ raw_write_seqcount_barrier(&cpu_base->seq);
+
+ __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
timer_stats_account_hrtimer(timer);
fn = timer->function;
raw_spin_lock(&cpu_base->lock);
/*
- * Note: We clear the CALLBACK bit after enqueue_hrtimer and
+ * Note: We clear the running state after enqueue_hrtimer and
* we do not reprogramm the event hardware. Happens either in
* hrtimer_start_range_ns() or in hrtimer_interrupt()
+ *
+ * Note: Because we dropped the cpu_base->lock above,
+ * hrtimer_start_range_ns() can have popped in and enqueued the timer
+ * for us already.
*/
- if (restart != HRTIMER_NORESTART) {
- BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
+ if (restart != HRTIMER_NORESTART &&
+ !(timer->state & HRTIMER_STATE_ENQUEUED))
enqueue_hrtimer(timer, base);
- }
- WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+ /*
+ * Separate the ->running assignment from the ->state assignment.
+ *
+ * As with a regular write barrier, this ensures the read side in
+ * hrtimer_active() cannot observe cpu_base->running == NULL &&
+ * timer->state == INACTIVE.
+ */
+ raw_write_seqcount_barrier(&cpu_base->seq);
- timer->state &= ~HRTIMER_STATE_CALLBACK;
+ WARN_ON_ONCE(cpu_base->running != timer);
+ cpu_base->running = NULL;
}
-#ifdef CONFIG_HIGH_RES_TIMERS
-
-/*
- * High resolution timer interrupt
- * Called with interrupts disabled
- */
-void hrtimer_interrupt(struct clock_event_device *dev)
+static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
{
- struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
- ktime_t expires_next, now, entry_time, delta;
- int i, retries = 0;
-
- BUG_ON(!cpu_base->hres_active);
- cpu_base->nr_events++;
- dev->next_event.tv64 = KTIME_MAX;
-
- raw_spin_lock(&cpu_base->lock);
- entry_time = now = hrtimer_update_base(cpu_base);
-retry:
- cpu_base->in_hrtirq = 1;
- /*
- * We set expires_next to KTIME_MAX here with cpu_base->lock
- * held to prevent that a timer is enqueued in our queue via
- * the migration code. This does not affect enqueueing of
- * timers which run their callback and need to be requeued on
- * this CPU.
- */
- cpu_base->expires_next.tv64 = KTIME_MAX;
+ struct hrtimer_clock_base *base = cpu_base->clock_base;
+ unsigned int active = cpu_base->active_bases;
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
- struct hrtimer_clock_base *base;
+ for (; active; base++, active >>= 1) {
struct timerqueue_node *node;
ktime_t basenow;
- if (!(cpu_base->active_bases & (1 << i)))
+ if (!(active & 0x01))
continue;
- base = cpu_base->clock_base + i;
basenow = ktime_add(now, base->offset);
while ((node = timerqueue_getnext(&base->active))) {
if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
break;
- __run_hrtimer(timer, &basenow);
+ __run_hrtimer(cpu_base, base, timer, &basenow);
}
}
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer interrupt
+ * Called with interrupts disabled
+ */
+void hrtimer_interrupt(struct clock_event_device *dev)
+{
+ struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+ ktime_t expires_next, now, entry_time, delta;
+ int retries = 0;
+
+ BUG_ON(!cpu_base->hres_active);
+ cpu_base->nr_events++;
+ dev->next_event.tv64 = KTIME_MAX;
+
+ raw_spin_lock(&cpu_base->lock);
+ entry_time = now = hrtimer_update_base(cpu_base);
+retry:
+ cpu_base->in_hrtirq = 1;
+ /*
+ * We set expires_next to KTIME_MAX here with cpu_base->lock
+ * held to prevent that a timer is enqueued in our queue via
+ * the migration code. This does not affect enqueueing of
+ * timers which run their callback and need to be requeued on
+ * this CPU.
+ */
+ cpu_base->expires_next.tv64 = KTIME_MAX;
+
+ __hrtimer_run_queues(cpu_base, now);
+
/* Reevaluate the clock bases for the next expiry */
expires_next = __hrtimer_get_next_event(cpu_base);
/*
raw_spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
- if (expires_next.tv64 == KTIME_MAX ||
- !tick_program_event(expires_next, 0)) {
+ if (!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
return;
}
cpu_base->hang_detected = 1;
raw_spin_unlock(&cpu_base->lock);
delta = ktime_sub(now, entry_time);
- if (delta.tv64 > cpu_base->max_hang_time.tv64)
- cpu_base->max_hang_time = delta;
+ if ((unsigned int)delta.tv64 > cpu_base->max_hang_time)
+ cpu_base->max_hang_time = (unsigned int) delta.tv64;
/*
* Limit it to a sensible value as we enforce a longer
* delay. Give the CPU at least 100ms to catch up.
* local version of hrtimer_peek_ahead_timers() called with interrupts
* disabled.
*/
-static void __hrtimer_peek_ahead_timers(void)
+static inline void __hrtimer_peek_ahead_timers(void)
{
struct tick_device *td;
hrtimer_interrupt(td->evtdev);
}
-/**
- * hrtimer_peek_ahead_timers -- run soft-expired timers now
- *
- * hrtimer_peek_ahead_timers will peek at the timer queue of
- * the current cpu and check if there are any timers for which
- * the soft expires time has passed. If any such timers exist,
- * they are run immediately and then removed from the timer queue.
- *
- */
-void hrtimer_peek_ahead_timers(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __hrtimer_peek_ahead_timers();
- local_irq_restore(flags);
-}
-
-static void run_hrtimer_softirq(struct softirq_action *h)
-{
- hrtimer_peek_ahead_timers();
-}
-
#else /* CONFIG_HIGH_RES_TIMERS */
static inline void __hrtimer_peek_ahead_timers(void) { }
#endif /* !CONFIG_HIGH_RES_TIMERS */
/*
- * Called from timer softirq every jiffy, expire hrtimers:
- *
- * For HRT its the fall back code to run the softirq in the timer
- * softirq context in case the hrtimer initialization failed or has
- * not been done yet.
+ * Called from run_local_timers in hardirq context every jiffy
*/
-void hrtimer_run_pending(void)
+void hrtimer_run_queues(void)
{
- if (hrtimer_hres_active())
+ struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+ ktime_t now;
+
+ if (__hrtimer_hres_active(cpu_base))
return;
/*
- * This _is_ ugly: We have to check in the softirq context,
- * whether we can switch to highres and / or nohz mode. The
- * clocksource switch happens in the timer interrupt with
- * xtime_lock held. Notification from there only sets the
- * check bit in the tick_oneshot code, otherwise we might
- * deadlock vs. xtime_lock.
+ * This _is_ ugly: We have to check periodically, whether we
+ * can switch to highres and / or nohz mode. The clocksource
+ * switch happens with xtime_lock held. Notification from
+ * there only sets the check bit in the tick_oneshot code,
+ * otherwise we might deadlock vs. xtime_lock.
*/
- if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) {
hrtimer_switch_to_hres();
-}
-
-/*
- * Called from hardirq context every jiffy
- */
-void hrtimer_run_queues(void)
-{
- struct timerqueue_node *node;
- struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
- struct hrtimer_clock_base *base;
- int index, gettime = 1;
-
- if (hrtimer_hres_active())
return;
-
- for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
- base = &cpu_base->clock_base[index];
- if (!timerqueue_getnext(&base->active))
- continue;
-
- if (gettime) {
- hrtimer_get_softirq_time(cpu_base);
- gettime = 0;
- }
-
- raw_spin_lock(&cpu_base->lock);
-
- while ((node = timerqueue_getnext(&base->active))) {
- struct hrtimer *timer;
-
- timer = container_of(node, struct hrtimer, node);
- if (base->softirq_time.tv64 <=
- hrtimer_get_expires_tv64(timer))
- break;
-
- __run_hrtimer(timer, &base->softirq_time);
- }
- raw_spin_unlock(&cpu_base->lock);
}
+
+ raw_spin_lock(&cpu_base->lock);
+ now = hrtimer_update_base(cpu_base);
+ __hrtimer_run_queues(cpu_base, now);
+ raw_spin_unlock(&cpu_base->lock);
}
/*
do {
set_current_state(TASK_INTERRUPTIBLE);
hrtimer_start_expires(&t->timer, mode);
- if (!hrtimer_active(&t->timer))
- t->task = NULL;
if (likely(t->task))
freezable_schedule();
debug_deactivate(timer);
/*
- * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+ * Mark it as ENQUEUED not INACTIVE otherwise the
* timer could be seen as !active and just vanish away
* under us on another CPU
*/
- __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
+ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0);
timer->base = new_base;
/*
* Enqueue the timers on the new cpu. This does not
* event device.
*/
enqueue_hrtimer(timer, new_base);
-
- /* Clear the migration state bit */
- timer->state &= ~HRTIMER_STATE_MIGRATE;
}
}
hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
-#ifdef CONFIG_HIGH_RES_TIMERS
- open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
}
/**
hrtimer_init_sleeper(&t, current);
hrtimer_start_expires(&t.timer, mode);
- if (!hrtimer_active(&t.timer))
- t.task = NULL;
if (likely(t.task))
schedule();
static u64 tick_length;
static u64 tick_length_base;
+#define SECS_PER_DAY 86400
#define MAX_TICKADJ 500LL /* usecs */
#define MAX_TICKADJ_SCALED \
(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
/* constant (boot-param configurable) NTP tick adjustment (upscaled) */
static s64 ntp_tick_adj;
+/* second value of the next pending leapsecond, or TIME64_MAX if no leap */
+static time64_t ntp_next_leap_sec = TIME64_MAX;
+
#ifdef CONFIG_NTP_PPS
/*
tick_length = tick_length_base;
time_offset = 0;
+ ntp_next_leap_sec = TIME64_MAX;
/* Clear PPS state variables */
pps_clear();
}
return tick_length;
}
+/**
+ * ntp_get_next_leap - Returns the next leapsecond in CLOCK_REALTIME ktime_t
+ *
+ * Provides the time of the next leapsecond against CLOCK_REALTIME in
+ * a ktime_t format. Returns KTIME_MAX if no leapsecond is pending.
+ */
+ktime_t ntp_get_next_leap(void)
+{
+ ktime_t ret;
+
+ if ((time_state == TIME_INS) && (time_status & STA_INS))
+ return ktime_set(ntp_next_leap_sec, 0);
+ ret.tv64 = KTIME_MAX;
+ return ret;
+}
/*
* this routine handles the overflow of the microsecond field
*/
switch (time_state) {
case TIME_OK:
- if (time_status & STA_INS)
+ if (time_status & STA_INS) {
time_state = TIME_INS;
- else if (time_status & STA_DEL)
+ ntp_next_leap_sec = secs + SECS_PER_DAY -
+ (secs % SECS_PER_DAY);
+ } else if (time_status & STA_DEL) {
time_state = TIME_DEL;
+ ntp_next_leap_sec = secs + SECS_PER_DAY -
+ ((secs+1) % SECS_PER_DAY);
+ }
break;
case TIME_INS:
- if (!(time_status & STA_INS))
+ if (!(time_status & STA_INS)) {
+ ntp_next_leap_sec = TIME64_MAX;
time_state = TIME_OK;
- else if (secs % 86400 == 0) {
+ } else if (secs % SECS_PER_DAY == 0) {
leap = -1;
time_state = TIME_OOP;
printk(KERN_NOTICE
}
break;
case TIME_DEL:
- if (!(time_status & STA_DEL))
+ if (!(time_status & STA_DEL)) {
+ ntp_next_leap_sec = TIME64_MAX;
time_state = TIME_OK;
- else if ((secs + 1) % 86400 == 0) {
+ } else if ((secs + 1) % SECS_PER_DAY == 0) {
leap = 1;
+ ntp_next_leap_sec = TIME64_MAX;
time_state = TIME_WAIT;
printk(KERN_NOTICE
"Clock: deleting leap second 23:59:59 UTC\n");
}
break;
case TIME_OOP:
+ ntp_next_leap_sec = TIME64_MAX;
time_state = TIME_WAIT;
break;
-
case TIME_WAIT:
if (!(time_status & (STA_INS | STA_DEL)))
time_state = TIME_OK;
if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
time_state = TIME_OK;
time_status = STA_UNSYNC;
+ ntp_next_leap_sec = TIME64_MAX;
/* restart PPS frequency calibration */
pps_reset_freq_interval();
}
if (!(time_status & STA_NANO))
txc->time.tv_usec /= NSEC_PER_USEC;
+ /* Handle leapsec adjustments */
+ if (unlikely(ts->tv_sec >= ntp_next_leap_sec)) {
+ if ((time_state == TIME_INS) && (time_status & STA_INS)) {
+ result = TIME_OOP;
+ txc->tai++;
+ txc->time.tv_sec--;
+ }
+ if ((time_state == TIME_DEL) && (time_status & STA_DEL)) {
+ result = TIME_WAIT;
+ txc->tai--;
+ txc->time.tv_sec++;
+ }
+ if ((time_state == TIME_OOP) &&
+ (ts->tv_sec == ntp_next_leap_sec)) {
+ result = TIME_WAIT;
+ }
+ }
+
return result;
}
extern void ntp_clear(void);
/* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
extern u64 ntp_tick_length(void);
+extern ktime_t ntp_get_next_leap(void);
extern int second_overflow(unsigned long secs);
extern int ntp_validate_timex(struct timex *);
extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
return 0;
}
-static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+/*
+ * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg
+ * to avoid race conditions with concurrent updates to cputime.
+ */
+static inline void __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime)
{
- if (b->utime > a->utime)
- a->utime = b->utime;
+ u64 curr_cputime;
+retry:
+ curr_cputime = atomic64_read(cputime);
+ if (sum_cputime > curr_cputime) {
+ if (atomic64_cmpxchg(cputime, curr_cputime, sum_cputime) != curr_cputime)
+ goto retry;
+ }
+}
- if (b->stime > a->stime)
- a->stime = b->stime;
+static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, struct task_cputime *sum)
+{
+ __update_gt_cputime(&cputime_atomic->utime, sum->utime);
+ __update_gt_cputime(&cputime_atomic->stime, sum->stime);
+ __update_gt_cputime(&cputime_atomic->sum_exec_runtime, sum->sum_exec_runtime);
+}
- if (b->sum_exec_runtime > a->sum_exec_runtime)
- a->sum_exec_runtime = b->sum_exec_runtime;
+/* Sample task_cputime_atomic values in "atomic_timers", store results in "times". */
+static inline void sample_cputime_atomic(struct task_cputime *times,
+ struct task_cputime_atomic *atomic_times)
+{
+ times->utime = atomic64_read(&atomic_times->utime);
+ times->stime = atomic64_read(&atomic_times->stime);
+ times->sum_exec_runtime = atomic64_read(&atomic_times->sum_exec_runtime);
}
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
struct task_cputime sum;
- unsigned long flags;
- if (!cputimer->running) {
+ /* Check if cputimer isn't running. This is accessed without locking. */
+ if (!READ_ONCE(cputimer->running)) {
/*
* The POSIX timer interface allows for absolute time expiry
* values through the TIMER_ABSTIME flag, therefore we have
- * to synchronize the timer to the clock every time we start
- * it.
+ * to synchronize the timer to the clock every time we start it.
*/
thread_group_cputime(tsk, &sum);
- raw_spin_lock_irqsave(&cputimer->lock, flags);
- cputimer->running = 1;
- update_gt_cputime(&cputimer->cputime, &sum);
- } else
- raw_spin_lock_irqsave(&cputimer->lock, flags);
- *times = cputimer->cputime;
- raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+ update_gt_cputime(&cputimer->cputime_atomic, &sum);
+
+ /*
+ * We're setting cputimer->running without a lock. Ensure
+ * this only gets written to in one operation. We set
+ * running after update_gt_cputime() as a small optimization,
+ * but barriers are not required because update_gt_cputime()
+ * can handle concurrent updates.
+ */
+ WRITE_ONCE(cputimer->running, 1);
+ }
+ sample_cputime_atomic(times, &cputimer->cputime_atomic);
}
/*
if (!task_cputime_zero(&tsk->cputime_expires))
return false;
- if (tsk->signal->cputimer.running)
+ /* Check if cputimer is running. This is accessed without locking. */
+ if (READ_ONCE(tsk->signal->cputimer.running))
return false;
return true;
/*
* Check for the special case thread timers.
*/
- soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
+ soft = READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
if (soft != RLIM_INFINITY) {
unsigned long hard =
- ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
+ READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
if (hard != RLIM_INFINITY &&
tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
}
}
-static void stop_process_timers(struct signal_struct *sig)
+static inline void stop_process_timers(struct signal_struct *sig)
{
struct thread_group_cputimer *cputimer = &sig->cputimer;
- unsigned long flags;
- raw_spin_lock_irqsave(&cputimer->lock, flags);
- cputimer->running = 0;
- raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+ /* Turn off cputimer->running. This is done without locking. */
+ WRITE_ONCE(cputimer->running, 0);
}
static u32 onecputick;
SIGPROF);
check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
SIGVTALRM);
- soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+ soft = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
if (soft != RLIM_INFINITY) {
unsigned long psecs = cputime_to_secs(ptime);
unsigned long hard =
- ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
+ READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
cputime_t x;
if (psecs >= hard) {
/*
}
sig = tsk->signal;
- if (sig->cputimer.running) {
+ /* Check if cputimer is running. This is accessed without locking. */
+ if (READ_ONCE(sig->cputimer.running)) {
struct task_cputime group_sample;
- raw_spin_lock(&sig->cputimer.lock);
- group_sample = sig->cputimer.cputime;
- raw_spin_unlock(&sig->cputimer.lock);
+ sample_cputime_atomic(&group_sample, &sig->cputimer.cputime_atomic);
if (task_cputime_expired(&group_sample, &sig->cputime_expires))
return 1;
* If there are any active process wide timers (POSIX 1.b, itimers,
* RLIMIT_CPU) cputimer must be running.
*/
- if (tsk->signal->cputimer.running)
+ if (READ_ONCE(tsk->signal->cputimer.running))
check_process_timers(tsk, &firing);
/*
return 0;
}
+static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec *tp)
+{
+ tp->tv_sec = 0;
+ tp->tv_nsec = hrtimer_resolution;
+ return 0;
+}
+
/*
* Initialize everything, well, just everything in Posix clocks/timers ;)
*/
static __init int init_posix_timers(void)
{
struct k_clock clock_realtime = {
- .clock_getres = hrtimer_get_res,
+ .clock_getres = posix_get_hrtimer_res,
.clock_get = posix_clock_realtime_get,
.clock_set = posix_clock_realtime_set,
.clock_adj = posix_clock_realtime_adj,
.timer_del = common_timer_del,
};
struct k_clock clock_monotonic = {
- .clock_getres = hrtimer_get_res,
+ .clock_getres = posix_get_hrtimer_res,
.clock_get = posix_ktime_get_ts,
.nsleep = common_nsleep,
.nsleep_restart = hrtimer_nanosleep_restart,
.timer_del = common_timer_del,
};
struct k_clock clock_monotonic_raw = {
- .clock_getres = hrtimer_get_res,
+ .clock_getres = posix_get_hrtimer_res,
.clock_get = posix_get_monotonic_raw,
};
struct k_clock clock_realtime_coarse = {
.clock_get = posix_get_monotonic_coarse,
};
struct k_clock clock_tai = {
- .clock_getres = hrtimer_get_res,
+ .clock_getres = posix_get_hrtimer_res,
.clock_get = posix_get_tai,
.nsleep = common_nsleep,
.nsleep_restart = hrtimer_nanosleep_restart,
.timer_del = common_timer_del,
};
struct k_clock clock_boottime = {
- .clock_getres = hrtimer_get_res,
+ .clock_getres = posix_get_hrtimer_res,
.clock_get = posix_get_boottime,
.nsleep = common_nsleep,
.nsleep_restart = hrtimer_nanosleep_restart,
struct clock_event_device *bc)
{
switch (mode) {
+ case CLOCK_EVT_MODE_UNUSED:
case CLOCK_EVT_MODE_SHUTDOWN:
/*
* Note, we cannot cancel the timer here as we might
* hrtimer_{start/cancel} functions call into tracing,
* calls to these functions must be bound within RCU_NONIDLE.
*/
- RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
- !hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
- 0);
+ RCU_NONIDLE({
+ bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
+ if (bc_moved)
+ hrtimer_start(&bctimer, expires,
+ HRTIMER_MODE_ABS_PINNED);});
if (bc_moved) {
/* Bind the "device" to the cpu */
bc->bound_on = smp_processor_id();
{
ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
- if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+ switch (ce_broadcast_hrtimer.mode) {
+ case CLOCK_EVT_MODE_ONESHOT:
+ if (ce_broadcast_hrtimer.next_event.tv64 != KTIME_MAX)
+ return HRTIMER_RESTART;
+ default:
return HRTIMER_NORESTART;
-
- return HRTIMER_RESTART;
+ }
}
void tick_setup_hrtimer_broadcast(void)
/*
* Broadcast the event to the cpus, which are set in the mask (mangled).
*/
-static void tick_do_broadcast(struct cpumask *mask)
+static bool tick_do_broadcast(struct cpumask *mask)
{
int cpu = smp_processor_id();
struct tick_device *td;
+ bool local = false;
/*
* Check, if the current cpu is in the mask
*/
if (cpumask_test_cpu(cpu, mask)) {
cpumask_clear_cpu(cpu, mask);
- td = &per_cpu(tick_cpu_device, cpu);
- td->evtdev->event_handler(td->evtdev);
+ local = true;
}
if (!cpumask_empty(mask)) {
td = &per_cpu(tick_cpu_device, cpumask_first(mask));
td->evtdev->broadcast(mask);
}
+ return local;
}
/*
* Periodic broadcast:
* - invoke the broadcast handlers
*/
-static void tick_do_periodic_broadcast(void)
+static bool tick_do_periodic_broadcast(void)
{
cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
- tick_do_broadcast(tmpmask);
+ return tick_do_broadcast(tmpmask);
}
/*
*/
static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
{
- ktime_t next;
+ struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+ bool bc_local;
raw_spin_lock(&tick_broadcast_lock);
+ bc_local = tick_do_periodic_broadcast();
- tick_do_periodic_broadcast();
+ if (clockevent_state_oneshot(dev)) {
+ ktime_t next = ktime_add(dev->next_event, tick_period);
- /*
- * The device is in periodic mode. No reprogramming necessary:
- */
- if (dev->state == CLOCK_EVT_STATE_PERIODIC)
- goto unlock;
+ clockevents_program_event(dev, next, true);
+ }
+ raw_spin_unlock(&tick_broadcast_lock);
/*
- * Setup the next period for devices, which do not have
- * periodic mode. We read dev->next_event first and add to it
- * when the event already expired. clockevents_program_event()
- * sets dev->next_event only when the event is really
- * programmed to the device.
+ * We run the handler of the local cpu after dropping
+ * tick_broadcast_lock because the handler might deadlock when
+ * trying to switch to oneshot mode.
*/
- for (next = dev->next_event; ;) {
- next = ktime_add(next, tick_period);
-
- if (!clockevents_program_event(dev, next, false))
- goto unlock;
- tick_do_periodic_broadcast();
- }
-unlock:
- raw_spin_unlock(&tick_broadcast_lock);
+ if (bc_local)
+ td->evtdev->event_handler(td->evtdev);
}
/**
irq_set_affinity(bc->irq, bc->cpumask);
}
-static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
- ktime_t expires, int force)
+static void tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
+ ktime_t expires)
{
- int ret;
-
- if (bc->state != CLOCK_EVT_STATE_ONESHOT)
- clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+ if (!clockevent_state_oneshot(bc))
+ clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
- ret = clockevents_program_event(bc, expires, force);
- if (!ret)
- tick_broadcast_set_affinity(bc, cpumask_of(cpu));
- return ret;
+ clockevents_program_event(bc, expires, 1);
+ tick_broadcast_set_affinity(bc, cpumask_of(cpu));
}
static void tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
- clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+ clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
}
/*
* switched over, leave the device alone.
*/
if (td->mode == TICKDEV_MODE_ONESHOT) {
- clockevents_set_state(td->evtdev,
+ clockevents_switch_state(td->evtdev,
CLOCK_EVT_STATE_ONESHOT);
}
}
struct tick_device *td;
ktime_t now, next_event;
int cpu, next_cpu = 0;
+ bool bc_local;
raw_spin_lock(&tick_broadcast_lock);
-again:
dev->next_event.tv64 = KTIME_MAX;
next_event.tv64 = KTIME_MAX;
cpumask_clear(tmpmask);
/*
* Wakeup the cpus which have an expired event.
*/
- tick_do_broadcast(tmpmask);
+ bc_local = tick_do_broadcast(tmpmask);
/*
* Two reasons for reprogram:
* - There are pending events on sleeping CPUs which were not
* in the event mask
*/
- if (next_event.tv64 != KTIME_MAX) {
- /*
- * Rearm the broadcast device. If event expired,
- * repeat the above
- */
- if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
- goto again;
- }
+ if (next_event.tv64 != KTIME_MAX)
+ tick_broadcast_set_event(dev, next_cpu, next_event);
+
raw_spin_unlock(&tick_broadcast_lock);
+
+ if (bc_local) {
+ td = this_cpu_ptr(&tick_cpu_device);
+ td->evtdev->event_handler(td->evtdev);
+ }
}
static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
if (dev->next_event.tv64 < bc->next_event.tv64)
return;
}
- clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
}
/**
*/
if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
dev->next_event.tv64 < bc->next_event.tv64)
- tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
+ tick_broadcast_set_event(bc, cpu, dev->next_event);
}
/*
* If the current CPU owns the hrtimer broadcast
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
- clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
/*
* The cpu which was handling the broadcast
* timer marked this cpu in the broadcast
/* Set it up only once ! */
if (bc->event_handler != tick_handle_oneshot_broadcast) {
- int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC;
+ int was_periodic = clockevent_state_periodic(bc);
bc->event_handler = tick_handle_oneshot_broadcast;
tick_broadcast_oneshot_mask, tmpmask);
if (was_periodic && !cpumask_empty(tmpmask)) {
- clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
+ clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT);
tick_broadcast_init_next_event(tmpmask,
tick_next_period);
- tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
+ tick_broadcast_set_event(bc, cpu, tick_next_period);
} else
bc->next_event.tv64 = KTIME_MAX;
} else {
tick_periodic(cpu);
- if (dev->state != CLOCK_EVT_STATE_ONESHOT)
+#if defined(CONFIG_HIGH_RES_TIMERS) || defined(CONFIG_NO_HZ_COMMON)
+ /*
+ * The cpu might have transitioned to HIGHRES or NOHZ mode via
+ * update_process_times() -> run_local_timers() ->
+ * hrtimer_run_queues().
+ */
+ if (dev->event_handler != tick_handle_periodic)
+ return;
+#endif
+
+ if (!clockevent_state_oneshot(dev))
return;
for (;;) {
/*
if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
!tick_broadcast_oneshot_active()) {
- clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
} else {
unsigned long seq;
ktime_t next;
next = tick_next_period;
} while (read_seqretry(&jiffies_lock, seq));
- clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
for (;;) {
if (!clockevents_program_event(dev, next, false))
* Prevent that the clock events layer tries to call
* the set mode function!
*/
- dev->state = CLOCK_EVT_STATE_DETACHED;
+ clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
dev->mode = CLOCK_EVT_MODE_UNUSED;
clockevents_exchange_device(dev, NULL);
dev->event_handler = clockevents_handle_noop;
return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
}
+static inline enum clock_event_state clockevent_get_state(struct clock_event_device *dev)
+{
+ return dev->state_use_accessors;
+}
+
+static inline void clockevent_set_state(struct clock_event_device *dev,
+ enum clock_event_state state)
+{
+ dev->state_use_accessors = state;
+}
+
extern void clockevents_shutdown(struct clock_event_device *dev);
extern void clockevents_exchange_device(struct clock_event_device *old,
struct clock_event_device *new);
-extern void clockevents_set_state(struct clock_event_device *dev,
- enum clock_event_state state);
+extern void clockevents_switch_state(struct clock_event_device *dev,
+ enum clock_event_state state);
extern int clockevents_program_event(struct clock_event_device *dev,
ktime_t expires, bool force);
extern void clockevents_handle_noop(struct clock_event_device *dev);
# else
static inline void tick_nohz_init(void) { }
#endif
+
+#ifdef CONFIG_NO_HZ_COMMON
+extern unsigned long tick_nohz_active;
+#else
+#define tick_nohz_active (0)
+#endif
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void timers_update_migration(bool update_nohz);
+#else
+static inline void timers_update_migration(bool update_nohz) { }
+#endif
+
+DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
+
+extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem);
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
+ if (unlikely(expires.tv64 == KTIME_MAX)) {
+ /*
+ * We don't need the clock event device any more, stop it.
+ */
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED);
+ return 0;
+ }
+
+ if (unlikely(clockevent_state_oneshot_stopped(dev))) {
+ /*
+ * We need the clock event again, configure it in ONESHOT mode
+ * before using it.
+ */
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
+ }
+
return clockevents_program_event(dev, expires, force);
}
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
- clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
clockevents_program_event(dev, ktime_get(), true);
}
ktime_t next_event)
{
newdev->event_handler = handler;
- clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT);
+ clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT);
clockevents_program_event(newdev, next_event, true);
}
td->mode = TICKDEV_MODE_ONESHOT;
dev->event_handler = handler;
- clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
+ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
tick_broadcast_switch_to_oneshot();
return 0;
}
* NO HZ enabled ?
*/
static int tick_nohz_enabled __read_mostly = 1;
-int tick_nohz_active __read_mostly;
+unsigned long tick_nohz_active __read_mostly;
/*
* Enable / Disable tickless mode
*/
}
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
+{
+ hrtimer_cancel(&ts->sched_timer);
+ hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
+
+ /* Forward the time to expire in the future */
+ hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+ if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+ hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
+ else
+ tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+}
+
static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
ktime_t now, int cpu)
{
- unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
- ktime_t last_update, expires, ret = { .tv64 = 0 };
- unsigned long rcu_delta_jiffies;
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
- u64 time_delta;
-
- time_delta = timekeeping_max_deferment();
+ u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
+ unsigned long seq, basejiff;
+ ktime_t tick;
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqbegin(&jiffies_lock);
- last_update = last_jiffies_update;
- last_jiffies = jiffies;
+ basemono = last_jiffies_update.tv64;
+ basejiff = jiffies;
} while (read_seqretry(&jiffies_lock, seq));
+ ts->last_jiffies = basejiff;
- if (rcu_needs_cpu(&rcu_delta_jiffies) ||
+ if (rcu_needs_cpu(basemono, &next_rcu) ||
arch_needs_cpu() || irq_work_needs_cpu()) {
- next_jiffies = last_jiffies + 1;
- delta_jiffies = 1;
+ next_tick = basemono + TICK_NSEC;
} else {
- /* Get the next timer wheel timer */
- next_jiffies = get_next_timer_interrupt(last_jiffies);
- delta_jiffies = next_jiffies - last_jiffies;
- if (rcu_delta_jiffies < delta_jiffies) {
- next_jiffies = last_jiffies + rcu_delta_jiffies;
- delta_jiffies = rcu_delta_jiffies;
- }
+ /*
+ * Get the next pending timer. If high resolution
+ * timers are enabled this only takes the timer wheel
+ * timers into account. If high resolution timers are
+ * disabled this also looks at the next expiring
+ * hrtimer.
+ */
+ next_tmr = get_next_timer_interrupt(basejiff, basemono);
+ ts->next_timer = next_tmr;
+ /* Take the next rcu event into account */
+ next_tick = next_rcu < next_tmr ? next_rcu : next_tmr;
}
/*
- * Do not stop the tick, if we are only one off (or less)
- * or if the cpu is required for RCU:
+ * If the tick is due in the next period, keep it ticking or
+ * restart it proper.
*/
- if (!ts->tick_stopped && delta_jiffies <= 1)
- goto out;
-
- /* Schedule the tick, if we are at least one jiffie off */
- if ((long)delta_jiffies >= 1) {
-
- /*
- * If this cpu is the one which updates jiffies, then
- * give up the assignment and let it be taken by the
- * cpu which runs the tick timer next, which might be
- * this cpu as well. If we don't drop this here the
- * jiffies might be stale and do_timer() never
- * invoked. Keep track of the fact that it was the one
- * which had the do_timer() duty last. If this cpu is
- * the one which had the do_timer() duty last, we
- * limit the sleep time to the timekeeping
- * max_deferement value which we retrieved
- * above. Otherwise we can sleep as long as we want.
- */
- if (cpu == tick_do_timer_cpu) {
- tick_do_timer_cpu = TICK_DO_TIMER_NONE;
- ts->do_timer_last = 1;
- } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
- time_delta = KTIME_MAX;
- ts->do_timer_last = 0;
- } else if (!ts->do_timer_last) {
- time_delta = KTIME_MAX;
+ delta = next_tick - basemono;
+ if (delta <= (u64)TICK_NSEC) {
+ tick.tv64 = 0;
+ if (!ts->tick_stopped)
+ goto out;
+ if (delta == 0) {
+ /* Tick is stopped, but required now. Enforce it */
+ tick_nohz_restart(ts, now);
+ goto out;
}
+ }
+
+ /*
+ * If this cpu is the one which updates jiffies, then give up
+ * the assignment and let it be taken by the cpu which runs
+ * the tick timer next, which might be this cpu as well. If we
+ * don't drop this here the jiffies might be stale and
+ * do_timer() never invoked. Keep track of the fact that it
+ * was the one which had the do_timer() duty last. If this cpu
+ * is the one which had the do_timer() duty last, we limit the
+ * sleep time to the timekeeping max_deferement value.
+ * Otherwise we can sleep as long as we want.
+ */
+ delta = timekeeping_max_deferment();
+ if (cpu == tick_do_timer_cpu) {
+ tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+ ts->do_timer_last = 1;
+ } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+ delta = KTIME_MAX;
+ ts->do_timer_last = 0;
+ } else if (!ts->do_timer_last) {
+ delta = KTIME_MAX;
+ }
#ifdef CONFIG_NO_HZ_FULL
- if (!ts->inidle) {
- time_delta = min(time_delta,
- scheduler_tick_max_deferment());
- }
+ /* Limit the tick delta to the maximum scheduler deferment */
+ if (!ts->inidle)
+ delta = min(delta, scheduler_tick_max_deferment());
#endif
- /*
- * calculate the expiry time for the next timer wheel
- * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
- * that there is no timer pending or at least extremely
- * far into the future (12 days for HZ=1000). In this
- * case we set the expiry to the end of time.
- */
- if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
- /*
- * Calculate the time delta for the next timer event.
- * If the time delta exceeds the maximum time delta
- * permitted by the current clocksource then adjust
- * the time delta accordingly to ensure the
- * clocksource does not wrap.
- */
- time_delta = min_t(u64, time_delta,
- tick_period.tv64 * delta_jiffies);
- }
-
- if (time_delta < KTIME_MAX)
- expires = ktime_add_ns(last_update, time_delta);
- else
- expires.tv64 = KTIME_MAX;
-
- /* Skip reprogram of event if its not changed */
- if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
- goto out;
+ /* Calculate the next expiry time */
+ if (delta < (KTIME_MAX - basemono))
+ expires = basemono + delta;
+ else
+ expires = KTIME_MAX;
- ret = expires;
+ expires = min_t(u64, expires, next_tick);
+ tick.tv64 = expires;
- /*
- * nohz_stop_sched_tick can be called several times before
- * the nohz_restart_sched_tick is called. This happens when
- * interrupts arrive which do not cause a reschedule. In the
- * first call we save the current tick time, so we can restart
- * the scheduler tick in nohz_restart_sched_tick.
- */
- if (!ts->tick_stopped) {
- nohz_balance_enter_idle(cpu);
- calc_load_enter_idle();
+ /* Skip reprogram of event if its not changed */
+ if (ts->tick_stopped && (expires == dev->next_event.tv64))
+ goto out;
- ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
- ts->tick_stopped = 1;
- trace_tick_stop(1, " ");
- }
+ /*
+ * nohz_stop_sched_tick can be called several times before
+ * the nohz_restart_sched_tick is called. This happens when
+ * interrupts arrive which do not cause a reschedule. In the
+ * first call we save the current tick time, so we can restart
+ * the scheduler tick in nohz_restart_sched_tick.
+ */
+ if (!ts->tick_stopped) {
+ nohz_balance_enter_idle(cpu);
+ calc_load_enter_idle();
- /*
- * If the expiration time == KTIME_MAX, then
- * in this case we simply stop the tick timer.
- */
- if (unlikely(expires.tv64 == KTIME_MAX)) {
- if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
- hrtimer_cancel(&ts->sched_timer);
- goto out;
- }
+ ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
+ ts->tick_stopped = 1;
+ trace_tick_stop(1, " ");
+ }
- if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
- hrtimer_start(&ts->sched_timer, expires,
- HRTIMER_MODE_ABS_PINNED);
- /* Check, if the timer was already in the past */
- if (hrtimer_active(&ts->sched_timer))
- goto out;
- } else if (!tick_program_event(expires, 0))
- goto out;
- /*
- * We are past the event already. So we crossed a
- * jiffie boundary. Update jiffies and raise the
- * softirq.
- */
- tick_do_update_jiffies64(ktime_get());
+ /*
+ * If the expiration time == KTIME_MAX, then we simply stop
+ * the tick timer.
+ */
+ if (unlikely(expires == KTIME_MAX)) {
+ if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+ hrtimer_cancel(&ts->sched_timer);
+ goto out;
}
- raise_softirq_irqoff(TIMER_SOFTIRQ);
+
+ if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
+ hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+ else
+ tick_program_event(tick, 1);
out:
- ts->next_jiffies = next_jiffies;
- ts->last_jiffies = last_jiffies;
+ /* Update the estimated sleep length */
ts->sleep_length = ktime_sub(dev->next_event, now);
-
- return ret;
+ return tick;
}
static void tick_nohz_full_stop_tick(struct tick_sched *ts)
return ts->sleep_length;
}
-static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
-{
- hrtimer_cancel(&ts->sched_timer);
- hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
-
- while (1) {
- /* Forward the time to expire in the future */
- hrtimer_forward(&ts->sched_timer, now, tick_period);
-
- if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
- hrtimer_start_expires(&ts->sched_timer,
- HRTIMER_MODE_ABS_PINNED);
- /* Check, if the timer was already in the past */
- if (hrtimer_active(&ts->sched_timer))
- break;
- } else {
- if (!tick_program_event(
- hrtimer_get_expires(&ts->sched_timer), 0))
- break;
- }
- /* Reread time and update jiffies */
- now = ktime_get();
- tick_do_update_jiffies64(now);
- }
-}
-
static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
{
/* Update jiffies first */
local_irq_enable();
}
-static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
-{
- hrtimer_forward(&ts->sched_timer, now, tick_period);
- return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0);
-}
-
/*
* The nohz low res interrupt handler
*/
if (unlikely(ts->tick_stopped))
return;
- while (tick_nohz_reprogram(ts, now)) {
- now = ktime_get();
- tick_do_update_jiffies64(now);
- }
+ hrtimer_forward(&ts->sched_timer, now, tick_period);
+ tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+}
+
+static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
+{
+ if (!tick_nohz_enabled)
+ return;
+ ts->nohz_mode = mode;
+ /* One update is enough */
+ if (!test_and_set_bit(0, &tick_nohz_active))
+ timers_update_migration(true);
}
/**
if (!tick_nohz_enabled)
return;
- local_irq_disable();
- if (tick_switch_to_oneshot(tick_nohz_handler)) {
- local_irq_enable();
+ if (tick_switch_to_oneshot(tick_nohz_handler))
return;
- }
- tick_nohz_active = 1;
- ts->nohz_mode = NOHZ_MODE_LOWRES;
/*
* Recycle the hrtimer in ts, so we can share the
/* Get the next period */
next = tick_init_jiffy_update();
- for (;;) {
- hrtimer_set_expires(&ts->sched_timer, next);
- if (!tick_program_event(next, 0))
- break;
- next = ktime_add(next, tick_period);
- }
- local_irq_enable();
+ hrtimer_forward_now(&ts->sched_timer, tick_period);
+ hrtimer_set_expires(&ts->sched_timer, next);
+ tick_program_event(next, 1);
+ tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
}
/*
static inline void tick_nohz_switch_to_nohz(void) { }
static inline void tick_nohz_irq_enter(void) { }
+static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { }
#endif /* CONFIG_NO_HZ_COMMON */
hrtimer_add_expires_ns(&ts->sched_timer, offset);
}
- for (;;) {
- hrtimer_forward(&ts->sched_timer, now, tick_period);
- hrtimer_start_expires(&ts->sched_timer,
- HRTIMER_MODE_ABS_PINNED);
- /* Check, if the timer was already in the past */
- if (hrtimer_active(&ts->sched_timer))
- break;
- now = ktime_get();
- }
-
-#ifdef CONFIG_NO_HZ_COMMON
- if (tick_nohz_enabled) {
- ts->nohz_mode = NOHZ_MODE_HIGHRES;
- tick_nohz_active = 1;
- }
-#endif
+ hrtimer_forward(&ts->sched_timer, now, tick_period);
+ hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
+ tick_nohz_activate(ts, NOHZ_MODE_HIGHRES);
}
#endif /* HIGH_RES_TIMERS */
* Called cyclic from the hrtimer softirq (driven by the timer
* softirq) allow_nohz signals, that we can switch into low-res nohz
* mode, because high resolution timers are disabled (either compile
- * or runtime).
+ * or runtime). Called with interrupts disabled.
*/
int tick_check_oneshot_change(int allow_nohz)
{
ktime_t iowait_sleeptime;
ktime_t sleep_length;
unsigned long last_jiffies;
- unsigned long next_jiffies;
+ u64 next_timer;
ktime_t idle_expires;
int do_timer_last;
};
#include <asm/uaccess.h>
#include <asm/unistd.h>
-#include "timeconst.h"
+#include <generated/timeconst.h>
#include "timekeeping.h"
/*
return error;
if (tz) {
+ /* Verify we're witin the +-15 hrs range */
+ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60)
+ return -EINVAL;
+
sys_tz = *tz;
update_vsyscall_tz();
if (firsttime) {
}
EXPORT_SYMBOL(ns_to_timespec64);
#endif
-/*
- * When we convert to jiffies then we interpret incoming values
- * the following way:
+/**
+ * msecs_to_jiffies: - convert milliseconds to jiffies
+ * @m: time in milliseconds
+ *
+ * conversion is done as follows:
*
* - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
*
* MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
*
* - all other values are converted to jiffies by either multiplying
- * the input value by a factor or dividing it with a factor
- *
- * We must also be careful about 32-bit overflows.
+ * the input value by a factor or dividing it with a factor and
+ * handling any 32-bit overflows.
+ * for the details see __msecs_to_jiffies()
+ *
+ * msecs_to_jiffies() checks for the passed in value being a constant
+ * via __builtin_constant_p() allowing gcc to eliminate most of the
+ * code, __msecs_to_jiffies() is called if the value passed does not
+ * allow constant folding and the actual conversion must be done at
+ * runtime.
+ * the _msecs_to_jiffies helpers are the HZ dependent conversion
+ * routines found in include/linux/jiffies.h
*/
-unsigned long msecs_to_jiffies(const unsigned int m)
+unsigned long __msecs_to_jiffies(const unsigned int m)
{
/*
* Negative value, means infinite timeout:
*/
if ((int)m < 0)
return MAX_JIFFY_OFFSET;
-
-#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
- /*
- * HZ is equal to or smaller than 1000, and 1000 is a nice
- * round multiple of HZ, divide with the factor between them,
- * but round upwards:
- */
- return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
-#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
- /*
- * HZ is larger than 1000, and HZ is a nice round multiple of
- * 1000 - simply multiply with the factor between them.
- *
- * But first make sure the multiplication result cannot
- * overflow:
- */
- if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
- return MAX_JIFFY_OFFSET;
-
- return m * (HZ / MSEC_PER_SEC);
-#else
- /*
- * Generic case - multiply, round and divide. But first
- * check that if we are doing a net multiplication, that
- * we wouldn't overflow:
- */
- if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
- return MAX_JIFFY_OFFSET;
-
- return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32)
- >> MSEC_TO_HZ_SHR32;
-#endif
+ return _msecs_to_jiffies(m);
}
-EXPORT_SYMBOL(msecs_to_jiffies);
+EXPORT_SYMBOL(__msecs_to_jiffies);
-unsigned long usecs_to_jiffies(const unsigned int u)
+unsigned long __usecs_to_jiffies(const unsigned int u)
{
if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
return MAX_JIFFY_OFFSET;
-#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
- return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
-#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
- return u * (HZ / USEC_PER_SEC);
-#else
- return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
- >> USEC_TO_HZ_SHR32;
-#endif
+ return _usecs_to_jiffies(u);
}
-EXPORT_SYMBOL(usecs_to_jiffies);
+EXPORT_SYMBOL(__usecs_to_jiffies);
/*
* The TICK_NSEC - 1 rounds up the value to the next resolution. Note
print "#include <linux/types.h>\n\n"
print "#if HZ != ", hz, "\n"
- print "#error \qkernel/timeconst.h has the wrong HZ value!\q\n"
+ print "#error \qinclude/generated/timeconst.h has the wrong HZ value!\q\n"
print "#endif\n\n"
if (hz < 2) {
halt
}
+hz = read();
timeconst(hz)
#ifdef CONFIG_DEBUG_TIMEKEEPING
#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
-/*
- * These simple flag variables are managed
- * without locks, which is racy, but ok since
- * we don't really care about being super
- * precise about how many events were seen,
- * just that a problem was observed.
- */
-static int timekeeping_underflow_seen;
-static int timekeeping_overflow_seen;
-
-/* last_warning is only modified under the timekeeping lock */
-static long timekeeping_last_warning;
static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
{
}
}
- if (timekeeping_underflow_seen) {
- if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+ if (tk->underflow_seen) {
+ if (jiffies - tk->last_warning > WARNING_FREQ) {
printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name);
printk_deferred(" Please report this, consider using a different clocksource, if possible.\n");
printk_deferred(" Your kernel is probably still fine.\n");
- timekeeping_last_warning = jiffies;
+ tk->last_warning = jiffies;
}
- timekeeping_underflow_seen = 0;
+ tk->underflow_seen = 0;
}
- if (timekeeping_overflow_seen) {
- if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+ if (tk->overflow_seen) {
+ if (jiffies - tk->last_warning > WARNING_FREQ) {
printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name);
printk_deferred(" Please report this, consider using a different clocksource, if possible.\n");
printk_deferred(" Your kernel is probably still fine.\n");
- timekeeping_last_warning = jiffies;
+ tk->last_warning = jiffies;
}
- timekeeping_overflow_seen = 0;
+ tk->overflow_seen = 0;
}
}
static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
{
+ struct timekeeper *tk = &tk_core.timekeeper;
cycle_t now, last, mask, max, delta;
unsigned int seq;
* mask-relative negative values.
*/
if (unlikely((~delta & mask) < (mask >> 3))) {
- timekeeping_underflow_seen = 1;
+ tk->underflow_seen = 1;
delta = 0;
}
/* Cap delta value to the max_cycles values to avoid mult overflows */
if (unlikely(delta > max)) {
- timekeeping_overflow_seen = 1;
+ tk->overflow_seen = 1;
delta = tkr->clock->max_cycles;
}
}
EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
+/*
+ * tk_update_leap_state - helper to update the next_leap_ktime
+ */
+static inline void tk_update_leap_state(struct timekeeper *tk)
+{
+ tk->next_leap_ktime = ntp_get_next_leap();
+ if (tk->next_leap_ktime.tv64 != KTIME_MAX)
+ /* Convert to monotonic time */
+ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real);
+}
+
/*
* Update the ktime_t based scalar nsec members of the timekeeper
*/
ntp_clear();
}
+ tk_update_leap_state(tk);
tk_update_ktime_data(tk);
update_vsyscall(tk);
update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
+ update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
+ update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw);
+
+ if (action & TK_CLOCK_WAS_SET)
+ tk->clock_was_set_seq++;
+ /*
+ * The mirroring of the data to the shadow-timekeeper needs
+ * to happen last here to ensure we don't over-write the
+ * timekeeper structure on the next update with stale data
+ */
if (action & TK_MIRROR)
memcpy(&shadow_timekeeper, &tk_core.timekeeper,
sizeof(tk_core.timekeeper));
-
- update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
- update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw);
}
/**
}
EXPORT_SYMBOL_GPL(ktime_get);
+u32 ktime_get_resolution_ns(void)
+{
+ struct timekeeper *tk = &tk_core.timekeeper;
+ unsigned int seq;
+ u32 nsecs;
+
+ WARN_ON(timekeeping_suspended);
+
+ do {
+ seq = read_seqcount_begin(&tk_core.seq);
+ nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift;
+ } while (read_seqcount_retry(&tk_core.seq, seq));
+
+ return nsecs;
+}
+EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);
+
static ktime_t *offsets[TK_OFFS_MAX] = {
[TK_OFFS_REAL] = &tk_core.timekeeper.offs_real,
[TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot,
}
/**
- * read_boot_clock - Return time of the system start.
+ * read_boot_clock64 - Return time of the system start.
*
* Weak dummy function for arches that do not yet support it.
* Function to read the exact time the system has been started.
- * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
+ * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
*
* XXX - Do be sure to remove it once all arches implement it.
*/
-void __weak read_boot_clock(struct timespec *ts)
+void __weak read_boot_clock64(struct timespec64 *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
}
-void __weak read_boot_clock64(struct timespec64 *ts64)
-{
- struct timespec ts;
-
- read_boot_clock(&ts);
- *ts64 = timespec_to_timespec64(ts);
-}
-
/* Flag for if timekeeping_resume() has injected sleeptime */
static bool sleeptime_injected;
* memcpy under the tk_core.seq against one before we start
* updating.
*/
+ timekeeping_update(tk, clock_set);
memcpy(real_tk, tk, sizeof(*tk));
- timekeeping_update(real_tk, clock_set);
+ /* The memcpy must come last. Do not put anything here! */
write_seqcount_end(&tk_core.seq);
out:
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
calc_global_load(ticks);
}
-/**
- * ktime_get_update_offsets_tick - hrtimer helper
- * @offs_real: pointer to storage for monotonic -> realtime offset
- * @offs_boot: pointer to storage for monotonic -> boottime offset
- * @offs_tai: pointer to storage for monotonic -> clock tai offset
- *
- * Returns monotonic time at last tick and various offsets
- */
-ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot,
- ktime_t *offs_tai)
-{
- struct timekeeper *tk = &tk_core.timekeeper;
- unsigned int seq;
- ktime_t base;
- u64 nsecs;
-
- do {
- seq = read_seqcount_begin(&tk_core.seq);
-
- base = tk->tkr_mono.base;
- nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
-
- *offs_real = tk->offs_real;
- *offs_boot = tk->offs_boot;
- *offs_tai = tk->offs_tai;
- } while (read_seqcount_retry(&tk_core.seq, seq));
-
- return ktime_add_ns(base, nsecs);
-}
-
-#ifdef CONFIG_HIGH_RES_TIMERS
/**
* ktime_get_update_offsets_now - hrtimer helper
+ * @cwsseq: pointer to check and store the clock was set sequence number
* @offs_real: pointer to storage for monotonic -> realtime offset
* @offs_boot: pointer to storage for monotonic -> boottime offset
* @offs_tai: pointer to storage for monotonic -> clock tai offset
*
- * Returns current monotonic time and updates the offsets
+ * Returns current monotonic time and updates the offsets if the
+ * sequence number in @cwsseq and timekeeper.clock_was_set_seq are
+ * different.
+ *
* Called from hrtimer_interrupt() or retrigger_next_event()
*/
-ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
- ktime_t *offs_tai)
+ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
+ ktime_t *offs_boot, ktime_t *offs_tai)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
base = tk->tkr_mono.base;
nsecs = timekeeping_get_ns(&tk->tkr_mono);
+ base = ktime_add_ns(base, nsecs);
+
+ if (*cwsseq != tk->clock_was_set_seq) {
+ *cwsseq = tk->clock_was_set_seq;
+ *offs_real = tk->offs_real;
+ *offs_boot = tk->offs_boot;
+ *offs_tai = tk->offs_tai;
+ }
+
+ /* Handle leapsecond insertion adjustments */
+ if (unlikely(base.tv64 >= tk->next_leap_ktime.tv64))
+ *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0));
- *offs_real = tk->offs_real;
- *offs_boot = tk->offs_boot;
- *offs_tai = tk->offs_tai;
} while (read_seqcount_retry(&tk_core.seq, seq));
- return ktime_add_ns(base, nsecs);
+ return base;
}
-#endif
/**
* do_adjtimex() - Accessor function to NTP __do_adjtimex function
__timekeeping_set_tai_offset(tk, tai);
timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
}
+ tk_update_leap_state(tk);
+
write_seqcount_end(&tk_core.seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
/*
* Internal interfaces for kernel/time/
*/
-extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real,
- ktime_t *offs_boot,
- ktime_t *offs_tai);
-extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real,
- ktime_t *offs_boot,
- ktime_t *offs_tai);
+extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
+ ktime_t *offs_real,
+ ktime_t *offs_boot,
+ ktime_t *offs_tai);
extern int timekeeping_valid_for_hres(void);
extern u64 timekeeping_max_deferment(void);
extern int timekeeping_inject_offset(struct timespec *ts);
extern s32 timekeeping_get_tai_offset(void);
extern void timekeeping_set_tai_offset(s32 tai_offset);
-extern void timekeeping_clocktai(struct timespec *ts);
extern int timekeeping_suspend(void);
extern void timekeeping_resume(void);
#include <asm/timex.h>
#include <asm/io.h>
+#include "tick-internal.h"
+
#define CREATE_TRACE_POINTS
#include <trace/events/timer.h>
#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1))
struct tvec {
- struct list_head vec[TVN_SIZE];
+ struct hlist_head vec[TVN_SIZE];
};
struct tvec_root {
- struct list_head vec[TVR_SIZE];
+ struct hlist_head vec[TVR_SIZE];
};
struct tvec_base {
unsigned long active_timers;
unsigned long all_timers;
int cpu;
+ bool migration_enabled;
+ bool nohz_active;
struct tvec_root tv1;
struct tvec tv2;
struct tvec tv3;
struct tvec tv5;
} ____cacheline_aligned;
-/*
- * __TIMER_INITIALIZER() needs to set ->base to a valid pointer (because we've
- * made NULL special, hint: lock_timer_base()) and we cannot get a compile time
- * pointer to per-cpu entries because we don't know where we'll map the section,
- * even for the boot cpu.
- *
- * And so we use boot_tvec_bases for boot CPU and per-cpu __tvec_bases for the
- * rest of them.
- */
-struct tvec_base boot_tvec_bases;
-EXPORT_SYMBOL(boot_tvec_bases);
-static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
+static DEFINE_PER_CPU(struct tvec_base, tvec_bases);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+unsigned int sysctl_timer_migration = 1;
-/* Functions below help us manage 'deferrable' flag */
-static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
+void timers_update_migration(bool update_nohz)
{
- return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE);
+ bool on = sysctl_timer_migration && tick_nohz_active;
+ unsigned int cpu;
+
+ /* Avoid the loop, if nothing to update */
+ if (this_cpu_read(tvec_bases.migration_enabled) == on)
+ return;
+
+ for_each_possible_cpu(cpu) {
+ per_cpu(tvec_bases.migration_enabled, cpu) = on;
+ per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
+ if (!update_nohz)
+ continue;
+ per_cpu(tvec_bases.nohz_active, cpu) = true;
+ per_cpu(hrtimer_bases.nohz_active, cpu) = true;
+ }
}
-static inline unsigned int tbase_get_irqsafe(struct tvec_base *base)
+int timer_migration_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
{
- return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE);
+ static DEFINE_MUTEX(mutex);
+ int ret;
+
+ mutex_lock(&mutex);
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ if (!ret && write)
+ timers_update_migration(false);
+ mutex_unlock(&mutex);
+ return ret;
}
-static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
+static inline struct tvec_base *get_target_base(struct tvec_base *base,
+ int pinned)
{
- return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK));
+ if (pinned || !base->migration_enabled)
+ return this_cpu_ptr(&tvec_bases);
+ return per_cpu_ptr(&tvec_bases, get_nohz_timer_target());
}
-
-static inline void
-timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
+#else
+static inline struct tvec_base *get_target_base(struct tvec_base *base,
+ int pinned)
{
- unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK;
-
- timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags);
+ return this_cpu_ptr(&tvec_bases);
}
+#endif
static unsigned long round_jiffies_common(unsigned long j, int cpu,
bool force_up)
}
EXPORT_SYMBOL_GPL(set_timer_slack);
-/*
- * If the list is empty, catch up ->timer_jiffies to the current time.
- * The caller must hold the tvec_base lock. Returns true if the list
- * was empty and therefore ->timer_jiffies was updated.
- */
-static bool catchup_timer_jiffies(struct tvec_base *base)
-{
- if (!base->all_timers) {
- base->timer_jiffies = jiffies;
- return true;
- }
- return false;
-}
-
static void
__internal_add_timer(struct tvec_base *base, struct timer_list *timer)
{
unsigned long expires = timer->expires;
unsigned long idx = expires - base->timer_jiffies;
- struct list_head *vec;
+ struct hlist_head *vec;
if (idx < TVR_SIZE) {
int i = expires & TVR_MASK;
i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
vec = base->tv5.vec + i;
}
- /*
- * Timers are FIFO:
- */
- list_add_tail(&timer->entry, vec);
+
+ hlist_add_head(&timer->entry, vec);
}
static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
{
- (void)catchup_timer_jiffies(base);
+ /* Advance base->jiffies, if the base is empty */
+ if (!base->all_timers++)
+ base->timer_jiffies = jiffies;
+
__internal_add_timer(base, timer);
/*
* Update base->active_timers and base->next_timer
*/
- if (!tbase_get_deferrable(timer->base)) {
+ if (!(timer->flags & TIMER_DEFERRABLE)) {
if (!base->active_timers++ ||
time_before(timer->expires, base->next_timer))
base->next_timer = timer->expires;
}
- base->all_timers++;
/*
* Check whether the other CPU is in dynticks mode and needs
* require special care against races with idle_cpu(), lets deal
* with that later.
*/
- if (!tbase_get_deferrable(base) || tick_nohz_full_cpu(base->cpu))
- wake_up_nohz_cpu(base->cpu);
+ if (base->nohz_active) {
+ if (!(timer->flags & TIMER_DEFERRABLE) ||
+ tick_nohz_full_cpu(base->cpu))
+ wake_up_nohz_cpu(base->cpu);
+ }
}
#ifdef CONFIG_TIMER_STATS
static void timer_stats_account_timer(struct timer_list *timer)
{
- unsigned int flag = 0;
-
if (likely(!timer->start_site))
return;
- if (unlikely(tbase_get_deferrable(timer->base)))
- flag |= TIMER_STATS_FLAG_DEFERRABLE;
timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
- timer->function, timer->start_comm, flag);
+ timer->function, timer->start_comm,
+ timer->flags);
}
#else
* statically initialized. We just make sure that it
* is tracked in the object tracker.
*/
- if (timer->entry.next == NULL &&
- timer->entry.prev == TIMER_ENTRY_STATIC) {
+ if (timer->entry.pprev == NULL &&
+ timer->entry.next == TIMER_ENTRY_STATIC) {
debug_object_init(timer, &timer_debug_descr);
debug_object_activate(timer, &timer_debug_descr);
return 0;
switch (state) {
case ODEBUG_STATE_NOTAVAILABLE:
- if (timer->entry.prev == TIMER_ENTRY_STATIC) {
+ if (timer->entry.next == TIMER_ENTRY_STATIC) {
/*
* This is not really a fixup. The timer was
* statically initialized. We just make sure that it
debug_activate(struct timer_list *timer, unsigned long expires)
{
debug_timer_activate(timer);
- trace_timer_start(timer, expires);
+ trace_timer_start(timer, expires, timer->flags);
}
static inline void debug_deactivate(struct timer_list *timer)
static void do_init_timer(struct timer_list *timer, unsigned int flags,
const char *name, struct lock_class_key *key)
{
- struct tvec_base *base = raw_cpu_read(tvec_bases);
-
- timer->entry.next = NULL;
- timer->base = (void *)((unsigned long)base | flags);
+ timer->entry.pprev = NULL;
+ timer->flags = flags | raw_smp_processor_id();
timer->slack = -1;
#ifdef CONFIG_TIMER_STATS
timer->start_site = NULL;
static inline void detach_timer(struct timer_list *timer, bool clear_pending)
{
- struct list_head *entry = &timer->entry;
+ struct hlist_node *entry = &timer->entry;
debug_deactivate(timer);
- __list_del(entry->prev, entry->next);
+ __hlist_del(entry);
if (clear_pending)
- entry->next = NULL;
- entry->prev = LIST_POISON2;
+ entry->pprev = NULL;
+ entry->next = LIST_POISON2;
}
static inline void
detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
{
detach_timer(timer, true);
- if (!tbase_get_deferrable(timer->base))
+ if (!(timer->flags & TIMER_DEFERRABLE))
base->active_timers--;
base->all_timers--;
- (void)catchup_timer_jiffies(base);
}
static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
return 0;
detach_timer(timer, clear_pending);
- if (!tbase_get_deferrable(timer->base)) {
+ if (!(timer->flags & TIMER_DEFERRABLE)) {
base->active_timers--;
if (timer->expires == base->next_timer)
base->next_timer = base->timer_jiffies;
}
- base->all_timers--;
- (void)catchup_timer_jiffies(base);
+ /* If this was the last timer, advance base->jiffies */
+ if (!--base->all_timers)
+ base->timer_jiffies = jiffies;
return 1;
}
* So __run_timers/migrate_timers can safely modify all timers which could
* be found on ->tvX lists.
*
- * When the timer's base is locked, and the timer removed from list, it is
- * possible to set timer->base = NULL and drop the lock: the timer remains
- * locked.
+ * When the timer's base is locked and removed from the list, the
+ * TIMER_MIGRATING flag is set, FIXME
*/
static struct tvec_base *lock_timer_base(struct timer_list *timer,
unsigned long *flags)
__acquires(timer->base->lock)
{
- struct tvec_base *base;
-
for (;;) {
- struct tvec_base *prelock_base = timer->base;
- base = tbase_get_base(prelock_base);
- if (likely(base != NULL)) {
+ u32 tf = timer->flags;
+ struct tvec_base *base;
+
+ if (!(tf & TIMER_MIGRATING)) {
+ base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK);
spin_lock_irqsave(&base->lock, *flags);
- if (likely(prelock_base == timer->base))
+ if (timer->flags == tf)
return base;
- /* The timer has migrated to another CPU */
spin_unlock_irqrestore(&base->lock, *flags);
}
cpu_relax();
static inline int
__mod_timer(struct timer_list *timer, unsigned long expires,
- bool pending_only, int pinned)
+ bool pending_only, int pinned)
{
struct tvec_base *base, *new_base;
unsigned long flags;
- int ret = 0 , cpu;
+ int ret = 0;
timer_stats_timer_set_start_info(timer);
BUG_ON(!timer->function);
debug_activate(timer, expires);
- cpu = get_nohz_timer_target(pinned);
- new_base = per_cpu(tvec_bases, cpu);
+ new_base = get_target_base(base, pinned);
if (base != new_base) {
/*
*/
if (likely(base->running_timer != timer)) {
/* See the comment in lock_timer_base() */
- timer_set_base(timer, NULL);
+ timer->flags |= TIMER_MIGRATING;
+
spin_unlock(&base->lock);
base = new_base;
spin_lock(&base->lock);
- timer_set_base(timer, base);
+ timer->flags &= ~TIMER_BASEMASK;
+ timer->flags |= base->cpu;
}
}
*/
void add_timer_on(struct timer_list *timer, int cpu)
{
- struct tvec_base *base = per_cpu(tvec_bases, cpu);
+ struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu);
unsigned long flags;
timer_stats_timer_set_start_info(timer);
BUG_ON(timer_pending(timer) || !timer->function);
spin_lock_irqsave(&base->lock, flags);
- timer_set_base(timer, base);
+ timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu;
debug_activate(timer, timer->expires);
internal_add_timer(base, timer);
spin_unlock_irqrestore(&base->lock, flags);
EXPORT_SYMBOL(try_to_del_timer_sync);
#ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct tvec_base, __tvec_bases);
-
/**
* del_timer_sync - deactivate a timer and wait for the handler to finish.
* @timer: the timer to be deactivated
* don't use it in hardirq context, because it
* could lead to deadlock.
*/
- WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base));
+ WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE));
for (;;) {
int ret = try_to_del_timer_sync(timer);
if (ret >= 0)
static int cascade(struct tvec_base *base, struct tvec *tv, int index)
{
/* cascade all the timers from tv up one level */
- struct timer_list *timer, *tmp;
- struct list_head tv_list;
+ struct timer_list *timer;
+ struct hlist_node *tmp;
+ struct hlist_head tv_list;
- list_replace_init(tv->vec + index, &tv_list);
+ hlist_move_list(tv->vec + index, &tv_list);
/*
* We are removing _all_ timers from the list, so we
* don't have to detach them individually.
*/
- list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
- BUG_ON(tbase_get_base(timer->base) != base);
+ hlist_for_each_entry_safe(timer, tmp, &tv_list, entry) {
/* No accounting, while moving them */
__internal_add_timer(base, timer);
}
struct timer_list *timer;
spin_lock_irq(&base->lock);
- if (catchup_timer_jiffies(base)) {
- spin_unlock_irq(&base->lock);
- return;
- }
+
while (time_after_eq(jiffies, base->timer_jiffies)) {
- struct list_head work_list;
- struct list_head *head = &work_list;
- int index = base->timer_jiffies & TVR_MASK;
+ struct hlist_head work_list;
+ struct hlist_head *head = &work_list;
+ int index;
+
+ if (!base->all_timers) {
+ base->timer_jiffies = jiffies;
+ break;
+ }
+
+ index = base->timer_jiffies & TVR_MASK;
/*
* Cascade timers:
!cascade(base, &base->tv4, INDEX(2)))
cascade(base, &base->tv5, INDEX(3));
++base->timer_jiffies;
- list_replace_init(base->tv1.vec + index, head);
- while (!list_empty(head)) {
+ hlist_move_list(base->tv1.vec + index, head);
+ while (!hlist_empty(head)) {
void (*fn)(unsigned long);
unsigned long data;
bool irqsafe;
- timer = list_first_entry(head, struct timer_list,entry);
+ timer = hlist_entry(head->first, struct timer_list, entry);
fn = timer->function;
data = timer->data;
- irqsafe = tbase_get_irqsafe(timer->base);
+ irqsafe = timer->flags & TIMER_IRQSAFE;
timer_stats_account_timer(timer);
/* Look for timer events in tv1. */
index = slot = timer_jiffies & TVR_MASK;
do {
- list_for_each_entry(nte, base->tv1.vec + slot, entry) {
- if (tbase_get_deferrable(nte->base))
+ hlist_for_each_entry(nte, base->tv1.vec + slot, entry) {
+ if (nte->flags & TIMER_DEFERRABLE)
continue;
found = 1;
index = slot = timer_jiffies & TVN_MASK;
do {
- list_for_each_entry(nte, varp->vec + slot, entry) {
- if (tbase_get_deferrable(nte->base))
+ hlist_for_each_entry(nte, varp->vec + slot, entry) {
+ if (nte->flags & TIMER_DEFERRABLE)
continue;
found = 1;
* Check, if the next hrtimer event is before the next timer wheel
* event:
*/
-static unsigned long cmp_next_hrtimer_event(unsigned long now,
- unsigned long expires)
+static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
{
- ktime_t hr_delta = hrtimer_get_next_event();
- struct timespec tsdelta;
- unsigned long delta;
-
- if (hr_delta.tv64 == KTIME_MAX)
- return expires;
+ u64 nextevt = hrtimer_get_next_event();
/*
- * Expired timer available, let it expire in the next tick
+ * If high resolution timers are enabled
+ * hrtimer_get_next_event() returns KTIME_MAX.
*/
- if (hr_delta.tv64 <= 0)
- return now + 1;
-
- tsdelta = ktime_to_timespec(hr_delta);
- delta = timespec_to_jiffies(&tsdelta);
+ if (expires <= nextevt)
+ return expires;
/*
- * Limit the delta to the max value, which is checked in
- * tick_nohz_stop_sched_tick():
+ * If the next timer is already expired, return the tick base
+ * time so the tick is fired immediately.
*/
- if (delta > NEXT_TIMER_MAX_DELTA)
- delta = NEXT_TIMER_MAX_DELTA;
+ if (nextevt <= basem)
+ return basem;
/*
- * Take rounding errors in to account and make sure, that it
- * expires in the next tick. Otherwise we go into an endless
- * ping pong due to tick_nohz_stop_sched_tick() retriggering
- * the timer softirq
+ * Round up to the next jiffie. High resolution timers are
+ * off, so the hrtimers are expired in the tick and we need to
+ * make sure that this tick really expires the timer to avoid
+ * a ping pong of the nohz stop code.
+ *
+ * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3
*/
- if (delta < 1)
- delta = 1;
- now += delta;
- if (time_before(now, expires))
- return now;
- return expires;
+ return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC;
}
/**
- * get_next_timer_interrupt - return the jiffy of the next pending timer
- * @now: current time (in jiffies)
+ * get_next_timer_interrupt - return the time (clock mono) of the next timer
+ * @basej: base time jiffies
+ * @basem: base time clock monotonic
+ *
+ * Returns the tick aligned clock monotonic time of the next pending
+ * timer or KTIME_MAX if no timer is pending.
*/
-unsigned long get_next_timer_interrupt(unsigned long now)
+u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
{
- struct tvec_base *base = __this_cpu_read(tvec_bases);
- unsigned long expires = now + NEXT_TIMER_MAX_DELTA;
+ struct tvec_base *base = this_cpu_ptr(&tvec_bases);
+ u64 expires = KTIME_MAX;
+ unsigned long nextevt;
/*
* Pretend that there is no timer pending if the cpu is offline.
if (base->active_timers) {
if (time_before_eq(base->next_timer, base->timer_jiffies))
base->next_timer = __next_timer_interrupt(base);
- expires = base->next_timer;
+ nextevt = base->next_timer;
+ if (time_before_eq(nextevt, basej))
+ expires = basem;
+ else
+ expires = basem + (nextevt - basej) * TICK_NSEC;
}
spin_unlock(&base->lock);
- if (time_before_eq(expires, now))
- return now;
-
- return cmp_next_hrtimer_event(now, expires);
+ return cmp_next_hrtimer_event(basem, expires);
}
#endif
*/
static void run_timer_softirq(struct softirq_action *h)
{
- struct tvec_base *base = __this_cpu_read(tvec_bases);
-
- hrtimer_run_pending();
+ struct tvec_base *base = this_cpu_ptr(&tvec_bases);
if (time_after_eq(jiffies, base->timer_jiffies))
__run_timers(base);
EXPORT_SYMBOL(schedule_timeout_uninterruptible);
#ifdef CONFIG_HOTPLUG_CPU
-static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head)
+static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *head)
{
struct timer_list *timer;
+ int cpu = new_base->cpu;
- while (!list_empty(head)) {
- timer = list_first_entry(head, struct timer_list, entry);
+ while (!hlist_empty(head)) {
+ timer = hlist_entry(head->first, struct timer_list, entry);
/* We ignore the accounting on the dying cpu */
detach_timer(timer, false);
- timer_set_base(timer, new_base);
+ timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu;
internal_add_timer(new_base, timer);
}
}
int i;
BUG_ON(cpu_online(cpu));
- old_base = per_cpu(tvec_bases, cpu);
- new_base = get_cpu_var(tvec_bases);
+ old_base = per_cpu_ptr(&tvec_bases, cpu);
+ new_base = this_cpu_ptr(&tvec_bases);
/*
* The caller is globally serialized and nobody else
* takes two locks at once, deadlock is not possible.
spin_unlock(&old_base->lock);
spin_unlock_irq(&new_base->lock);
- put_cpu_var(tvec_bases);
}
static int timer_cpu_notify(struct notifier_block *self,
static inline void timer_register_cpu_notifier(void) { }
#endif /* CONFIG_HOTPLUG_CPU */
-static void __init init_timer_cpu(struct tvec_base *base, int cpu)
+static void __init init_timer_cpu(int cpu)
{
- int j;
-
- BUG_ON(base != tbase_get_base(base));
+ struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu);
base->cpu = cpu;
- per_cpu(tvec_bases, cpu) = base;
spin_lock_init(&base->lock);
- for (j = 0; j < TVN_SIZE; j++) {
- INIT_LIST_HEAD(base->tv5.vec + j);
- INIT_LIST_HEAD(base->tv4.vec + j);
- INIT_LIST_HEAD(base->tv3.vec + j);
- INIT_LIST_HEAD(base->tv2.vec + j);
- }
- for (j = 0; j < TVR_SIZE; j++)
- INIT_LIST_HEAD(base->tv1.vec + j);
-
base->timer_jiffies = jiffies;
base->next_timer = base->timer_jiffies;
}
static void __init init_timer_cpus(void)
{
- struct tvec_base *base;
- int local_cpu = smp_processor_id();
int cpu;
- for_each_possible_cpu(cpu) {
- if (cpu == local_cpu)
- base = &boot_tvec_bases;
-#ifdef CONFIG_SMP
- else
- base = per_cpu_ptr(&__tvec_bases, cpu);
-#endif
-
- init_timer_cpu(base, cpu);
- }
+ for_each_possible_cpu(cpu)
+ init_timer_cpu(cpu);
}
void __init init_timers(void)
{
- /* ensure there are enough low bits for flags in timer->base pointer */
- BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK);
-
init_timer_cpus();
init_timer_stats();
timer_register_cpu_notifier();
EXPORT_SYMBOL(msleep_interruptible);
-static int __sched do_usleep_range(unsigned long min, unsigned long max)
+static void __sched do_usleep_range(unsigned long min, unsigned long max)
{
ktime_t kmin;
unsigned long delta;
kmin = ktime_set(0, min * NSEC_PER_USEC);
delta = (max - min) * NSEC_PER_USEC;
- return schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
+ schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
}
/**
* @min: Minimum time in usecs to sleep
* @max: Maximum time in usecs to sleep
*/
-void usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range(unsigned long min, unsigned long max)
{
__set_current_state(TASK_UNINTERRUPTIBLE);
do_usleep_range(min, max);
typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes);
-DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
-
/*
* This allows printing both to /proc/timer_list and
* to the console (on SysRq-Q):
*/
-#define SEQ_printf(m, x...) \
- do { \
- if (m) \
- seq_printf(m, x); \
- else \
- printk(x); \
- } while (0)
+__printf(2, 3)
+static void SEQ_printf(struct seq_file *m, const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+
+ if (m)
+ seq_vprintf(m, fmt, args);
+ else
+ vprintk(fmt, args);
+
+ va_end(args);
+}
static void print_name_offset(struct seq_file *m, void *sym)
{
print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
{
SEQ_printf(m, " .base: %pK\n", base);
- SEQ_printf(m, " .index: %d\n",
- base->index);
- SEQ_printf(m, " .resolution: %Lu nsecs\n",
- (unsigned long long)ktime_to_ns(base->resolution));
+ SEQ_printf(m, " .index: %d\n", base->index);
+
+ SEQ_printf(m, " .resolution: %u nsecs\n", (unsigned) hrtimer_resolution);
+
SEQ_printf(m, " .get_time: ");
print_name_offset(m, base->get_time);
SEQ_printf(m, "\n");
P(nr_events);
P(nr_retries);
P(nr_hangs);
- P_ns(max_hang_time);
+ P(max_hang_time);
#endif
#undef P
#undef P_ns
P_ns(idle_sleeptime);
P_ns(iowait_sleeptime);
P(last_jiffies);
- P(next_jiffies);
+ P(next_timer);
P_ns(idle_expires);
SEQ_printf(m, "jiffies: %Lu\n",
(unsigned long long)jiffies);
SEQ_printf(m, "\n");
}
+ if (dev->set_state_oneshot_stopped) {
+ SEQ_printf(m, " oneshot stopped: ");
+ print_name_offset(m, dev->set_state_oneshot_stopped);
+ SEQ_printf(m, "\n");
+ }
+
if (dev->tick_resume) {
SEQ_printf(m, " resume: ");
print_name_offset(m, dev->tick_resume);
{
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
print_tickdevice(m, tick_get_broadcast_device(), -1);
- SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
- cpumask_bits(tick_get_broadcast_mask())[0]);
+ SEQ_printf(m, "tick_broadcast_mask: %*pb\n",
+ cpumask_pr_args(tick_get_broadcast_mask()));
#ifdef CONFIG_TICK_ONESHOT
- SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n",
- cpumask_bits(tick_get_broadcast_oneshot_mask())[0]);
+ SEQ_printf(m, "tick_broadcast_oneshot_mask: %*pb\n",
+ cpumask_pr_args(tick_get_broadcast_oneshot_mask()));
#endif
SEQ_printf(m, "\n");
#endif
static inline void timer_list_header(struct seq_file *m, u64 now)
{
- SEQ_printf(m, "Timer List Version: v0.7\n");
+ SEQ_printf(m, "Timer List Version: v0.8\n");
SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
SEQ_printf(m, "\n");
* Number of timeout events:
*/
unsigned long count;
- unsigned int timer_flag;
+ u32 flags;
/*
* We save the command-line string to preserve
* @startf: pointer to the function which did the timer setup
* @timerf: pointer to the timer callback function of the timer
* @comm: name of the process which set up the timer
+ * @tflags: The flags field of the timer
*
* When the timer is already registered, then the event counter is
* incremented. Otherwise the timer is registered in a free slot.
*/
void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
- void *timerf, char *comm,
- unsigned int timer_flag)
+ void *timerf, char *comm, u32 tflags)
{
/*
* It doesn't matter which lock we take:
input.start_func = startf;
input.expire_func = timerf;
input.pid = pid;
- input.timer_flag = timer_flag;
+ input.flags = tflags;
raw_spin_lock_irqsave(lock, flags);
if (!timer_stats_active)
for (i = 0; i < nr_entries; i++) {
entry = entries + i;
- if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) {
+ if (entry->flags & TIMER_DEFERRABLE) {
seq_printf(m, "%4luD, %5d %-16s ",
entry->count, entry->pid, entry->comm);
} else {
*/
void torture_shutdown_absorb(const char *title)
{
- while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+ while (READ_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
pr_notice("torture thread %s parking due to system shutdown\n",
title);
schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
unsigned long unused2, void *unused3)
{
mutex_lock(&fullstop_mutex);
- if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
+ if (READ_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected");
- ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN;
+ WRITE_ONCE(fullstop, FULLSTOP_SHUTDOWN);
} else {
pr_warn("Concurrent rmmod and shutdown illegal!\n");
}
*/
void stutter_wait(const char *title)
{
- while (ACCESS_ONCE(stutter_pause_test) ||
- (torture_runnable && !ACCESS_ONCE(*torture_runnable))) {
+ while (READ_ONCE(stutter_pause_test) ||
+ (torture_runnable && !READ_ONCE(*torture_runnable))) {
if (stutter_pause_test)
- if (ACCESS_ONCE(stutter_pause_test) == 1)
+ if (READ_ONCE(stutter_pause_test) == 1)
schedule_timeout_interruptible(1);
else
- while (ACCESS_ONCE(stutter_pause_test))
+ while (READ_ONCE(stutter_pause_test))
cond_resched();
else
schedule_timeout_interruptible(round_jiffies_relative(HZ));
if (!torture_must_stop()) {
if (stutter > 1) {
schedule_timeout_interruptible(stutter - 1);
- ACCESS_ONCE(stutter_pause_test) = 2;
+ WRITE_ONCE(stutter_pause_test, 2);
}
schedule_timeout_interruptible(1);
- ACCESS_ONCE(stutter_pause_test) = 1;
+ WRITE_ONCE(stutter_pause_test, 1);
}
if (!torture_must_stop())
schedule_timeout_interruptible(stutter);
- ACCESS_ONCE(stutter_pause_test) = 0;
+ WRITE_ONCE(stutter_pause_test, 0);
torture_shutdown_absorb("torture_stutter");
} while (!torture_must_stop());
torture_kthread_stopping("torture_stutter");
bool torture_cleanup_begin(void)
{
mutex_lock(&fullstop_mutex);
- if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+ if (READ_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
pr_warn("Concurrent rmmod and shutdown illegal!\n");
mutex_unlock(&fullstop_mutex);
schedule_timeout_uninterruptible(10);
return true;
}
- ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD;
+ WRITE_ONCE(fullstop, FULLSTOP_RMMOD);
mutex_unlock(&fullstop_mutex);
torture_shutdown_cleanup();
torture_shuffle_cleanup();
*/
bool torture_must_stop_irq(void)
{
- return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP;
+ return READ_ONCE(fullstop) != FULLSTOP_DONTSTOP;
}
EXPORT_SYMBOL_GPL(torture_must_stop_irq);
if (producer_fifo >= 0) {
struct sched_param param = {
- .sched_priority = consumer_fifo
+ .sched_priority = producer_fifo
};
sched_setscheduler(producer, SCHED_FIFO, ¶m);
} else
{
int n_normal_preds = 0, n_logical_preds = 0;
struct postfix_elt *elt;
+ int cnt = 0;
list_for_each_entry(elt, &ps->postfix, list) {
- if (elt->op == OP_NONE)
+ if (elt->op == OP_NONE) {
+ cnt++;
continue;
+ }
if (elt->op == OP_AND || elt->op == OP_OR) {
n_logical_preds++;
+ cnt--;
continue;
}
+ if (elt->op != OP_NOT)
+ cnt--;
n_normal_preds++;
+ WARN_ON_ONCE(cnt < 0);
}
- if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+ if (cnt != 1 || !n_normal_preds || n_logical_preds >= n_normal_preds) {
parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
return -EINVAL;
}
EXPORT_SYMBOL(ftrace_print_hex_seq);
const char *
-ftrace_print_array_seq(struct trace_seq *p, const void *buf, int buf_len,
+ftrace_print_array_seq(struct trace_seq *p, const void *buf, int count,
size_t el_size)
{
const char *ret = trace_seq_buffer_ptr(p);
const char *prefix = "";
void *ptr = (void *)buf;
+ size_t buf_len = count * el_size;
trace_seq_putc(p, '{');
#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT)
#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT)
+static DEFINE_MUTEX(watchdog_proc_mutex);
+
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
#else
{
int cpu;
- if (!watchdog_user_enabled)
- return;
+ mutex_lock(&watchdog_proc_mutex);
+
+ if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+ goto unlock;
get_online_cpus();
for_each_online_cpu(cpu)
watchdog_nmi_enable(cpu);
put_online_cpus();
+
+unlock:
+ mutex_unlock(&watchdog_proc_mutex);
}
void watchdog_nmi_disable_all(void)
{
int cpu;
+ mutex_lock(&watchdog_proc_mutex);
+
if (!watchdog_running)
- return;
+ goto unlock;
get_online_cpus();
for_each_online_cpu(cpu)
watchdog_nmi_disable(cpu);
put_online_cpus();
+
+unlock:
+ mutex_unlock(&watchdog_proc_mutex);
}
#else
static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
}
-static DEFINE_MUTEX(watchdog_proc_mutex);
-
/*
* common function for watchdog, nmi_watchdog and soft_watchdog parameter
*
depends on DEBUG_KERNEL
select TORTURE_TEST
select SRCU
+ select TASKS_RCU
default n
help
This option provides a kernel module that runs torture tests
Say N here if you want the RCU torture tests to start only
after being manually enabled via /proc.
+config RCU_TORTURE_TEST_SLOW_PREINIT
+ bool "Slow down RCU grace-period pre-initialization to expose races"
+ depends on RCU_TORTURE_TEST
+ help
+ This option delays grace-period pre-initialization (the
+ propagation of CPU-hotplug changes up the rcu_node combining
+ tree) for a few jiffies between initializing each pair of
+ consecutive rcu_node structures. This helps to expose races
+ involving grace-period pre-initialization, in other words, it
+ makes your kernel less stable. It can also greatly increase
+ grace-period latency, especially on systems with large numbers
+ of CPUs. This is useful when torture-testing RCU, but in
+ almost no other circumstance.
+
+ Say Y here if you want your system to crash and hang more often.
+ Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_PREINIT_DELAY
+ int "How much to slow down RCU grace-period pre-initialization"
+ range 0 5
+ default 3
+ depends on RCU_TORTURE_TEST_SLOW_PREINIT
+ help
+ This option specifies the number of jiffies to wait between
+ each rcu_node structure pre-initialization step.
+
config RCU_TORTURE_TEST_SLOW_INIT
bool "Slow down RCU grace-period initialization to expose races"
depends on RCU_TORTURE_TEST
help
- This option makes grace-period initialization block for a
- few jiffies between initializing each pair of consecutive
+ This option delays grace-period initialization for a few
+ jiffies between initializing each pair of consecutive
rcu_node structures. This helps to expose races involving
grace-period initialization, in other words, it makes your
kernel less stable. It can also greatly increase grace-period
This option specifies the number of jiffies to wait between
each rcu_node structure initialization.
+config RCU_TORTURE_TEST_SLOW_CLEANUP
+ bool "Slow down RCU grace-period cleanup to expose races"
+ depends on RCU_TORTURE_TEST
+ help
+ This option delays grace-period cleanup for a few jiffies
+ between cleaning up each pair of consecutive rcu_node
+ structures. This helps to expose races involving grace-period
+ cleanup, in other words, it makes your kernel less stable.
+ It can also greatly increase grace-period latency, especially
+ on systems with large numbers of CPUs. This is useful when
+ torture-testing RCU, but in almost no other circumstance.
+
+ Say Y here if you want your system to crash and hang more often.
+ Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY
+ int "How much to slow down RCU grace-period cleanup"
+ range 0 5
+ default 3
+ depends on RCU_TORTURE_TEST_SLOW_CLEANUP
+ help
+ This option specifies the number of jiffies to wait between
+ each rcu_node structure cleanup operation.
+
config RCU_CPU_STALL_TIMEOUT
int "RCU CPU stall timeout in seconds"
depends on RCU_STALL_COMMON
Say Y here if you want to enable RCU tracing
Say N if you are unsure.
+config RCU_EQS_DEBUG
+ bool "Use this when adding any sort of NO_HZ support to your arch"
+ depends on DEBUG_KERNEL
+ help
+ This option provides consistency checks in RCU's handling of
+ NO_HZ. These checks have proven quite helpful in detecting
+ bugs in arch-specific NO_HZ code.
+
+ Say N here if you need ultimate kernel/user switch latencies
+ Say Y if you are unsure
+
endmenu # "RCU Debugging"
config DEBUG_BLOCK_EXT_DEVT
/* Update distances based on topology */
for_each_cpu(cpu, update_mask) {
if (cpu_rmap_copy_neigh(rmap, cpu,
- topology_thread_cpumask(cpu), 1))
+ topology_sibling_cpumask(cpu), 1))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_core_cpumask(cpu), 2))
int cpumask_next_and(int n, const struct cpumask *src1p,
const struct cpumask *src2p)
{
- struct cpumask tmp;
-
- if (cpumask_and(&tmp, src1p, src2p))
- return cpumask_next(n, &tmp);
- return nr_cpu_ids;
+ while ((n = cpumask_next(n, src1p)) < nr_cpu_ids)
+ if (cpumask_test_cpu(n, src2p))
+ break;
+ return n;
}
EXPORT_SYMBOL(cpumask_next_and);
#endif
/**
- * cpumask_set_cpu_local_first - set i'th cpu with local numa cpu's first
- *
+ * cpumask_local_spread - select the i'th cpu with local numa cpu's first
* @i: index number
- * @numa_node: local numa_node
- * @dstp: cpumask with the relevant cpu bit set according to the policy
+ * @node: local numa_node
*
- * This function sets the cpumask according to a numa aware policy.
- * cpumask could be used as an affinity hint for the IRQ related to a
- * queue. When the policy is to spread queues across cores - local cores
- * first.
+ * This function selects an online CPU according to a numa aware policy;
+ * local cpus are returned first, followed by non-local ones, then it
+ * wraps around.
*
- * Returns 0 on success, -ENOMEM for no memory, and -EAGAIN when failed to set
- * the cpu bit and need to re-call the function.
+ * It's not very efficient, but useful for setup.
*/
-int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+unsigned int cpumask_local_spread(unsigned int i, int node)
{
- cpumask_var_t mask;
int cpu;
- int ret = 0;
-
- if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
- return -ENOMEM;
+ /* Wrap: we always want a cpu. */
i %= num_online_cpus();
- if (numa_node == -1 || !cpumask_of_node(numa_node)) {
- /* Use all online cpu's for non numa aware system */
- cpumask_copy(mask, cpu_online_mask);
+ if (node == -1) {
+ for_each_cpu(cpu, cpu_online_mask)
+ if (i-- == 0)
+ return cpu;
} else {
- int n;
-
- cpumask_and(mask,
- cpumask_of_node(numa_node), cpu_online_mask);
-
- n = cpumask_weight(mask);
- if (i >= n) {
- i -= n;
-
- /* If index > number of local cpu's, mask out local
- * cpu's
- */
- cpumask_andnot(mask, cpu_online_mask, mask);
+ /* NUMA first. */
+ for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
+ if (i-- == 0)
+ return cpu;
+
+ for_each_cpu(cpu, cpu_online_mask) {
+ /* Skip NUMA nodes, done above. */
+ if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
+ continue;
+
+ if (i-- == 0)
+ return cpu;
}
}
-
- for_each_cpu(cpu, mask) {
- if (--i < 0)
- goto out;
- }
-
- ret = -EAGAIN;
-
-out:
- free_cpumask_var(mask);
-
- if (!ret)
- cpumask_set_cpu(cpu, dstp);
-
- return ret;
+ BUG();
}
-EXPORT_SYMBOL(cpumask_set_cpu_local_first);
+EXPORT_SYMBOL(cpumask_local_spread);
************** MIPS *****************
***************************************/
#if defined(__mips__) && W_TYPE_SIZE == 32
-#if __GNUC__ >= 4 && __GNUC_MINOR__ >= 4
+#if (__GNUC__ >= 5) || (__GNUC__ >= 4 && __GNUC_MINOR__ >= 4)
#define umul_ppmm(w1, w0, u, v) \
do { \
UDItype __ll = (UDItype)(u) * (v); \
************** MIPS/64 **************
***************************************/
#if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64
-#if __GNUC__ >= 4 && __GNUC_MINOR__ >= 4
+#if (__GNUC__ >= 5) || (__GNUC__ >= 4 && __GNUC_MINOR__ >= 4)
#define umul_ppmm(w1, w0, u, v) \
do { \
typedef unsigned int __ll_UTItype __attribute__((mode(TI))); \
* Compare counter against given value.
* Return 1 if greater, 0 if equal and -1 if less
*/
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
{
s64 count;
count = percpu_counter_read(fbc);
/* Check to see if rough count will be sufficient for comparison */
- if (abs(count - rhs) > (percpu_counter_batch*num_online_cpus())) {
+ if (abs(count - rhs) > (batch * num_online_cpus())) {
if (count > rhs)
return 1;
else
else
return 0;
}
-EXPORT_SYMBOL(percpu_counter_compare);
+EXPORT_SYMBOL(__percpu_counter_compare);
static int __init percpu_counter_startup(void)
{
#include <linux/string.h>
#include <linux/bitops.h>
#include <linux/rcupdate.h>
-#include <linux/preempt_mask.h> /* in_interrupt() */
+#include <linux/preempt.h> /* in_interrupt() */
/*
#ifdef __KERNEL__ /* Real code */
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
#else /* Dummy code for user space testing */
* published by the Free Software Foundation.
*/
+#include <linux/atomic.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/log2.h>
#include <linux/random.h>
#include <linux/rhashtable.h>
#include <linux/err.h>
+#include <linux/export.h>
#define HASH_DEFAULT_SIZE 64UL
#define HASH_MIN_SIZE 4U
if (key && rhashtable_lookup_fast(ht, key, ht->p))
goto exit;
+ err = -E2BIG;
+ if (unlikely(rht_grow_above_max(ht, tbl)))
+ goto exit;
+
err = -EAGAIN;
if (rhashtable_check_elasticity(ht, tbl, hash) ||
rht_grow_above_100(ht, tbl))
if (params->max_size)
ht->p.max_size = rounddown_pow_of_two(params->max_size);
+ if (params->insecure_max_entries)
+ ht->p.insecure_max_entries =
+ rounddown_pow_of_two(params->insecure_max_entries);
+ else
+ ht->p.insecure_max_entries = ht->p.max_size * 2;
+
ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE);
/* The maximum (not average) chain length grows with the
return res + find_zero(data) + 1 - align;
}
res += sizeof(unsigned long);
- if (unlikely(max < sizeof(unsigned long)))
+ /* We already handled 'unsigned long' bytes. Did we do it all ? */
+ if (unlikely(max <= sizeof(unsigned long)))
break;
max -= sizeof(unsigned long);
if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
* @str: The string to measure.
* @count: Maximum count (including NUL character)
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
* Returns the size of the string INCLUDING the terminating NUL.
- * If the string is too long, returns 'count+1'.
+ * If the string is too long, returns a number larger than @count. User
+ * has to check the return value against "> count".
* On exception (or invalid count), returns 0.
+ *
+ * NOTE! You should basically never use this function. There is
+ * almost never any valid case for using the length of a user space
+ * string, since the string can be changed at any time by other
+ * threads. Use "strncpy_from_user()" instead to get a stable copy
+ * of the string.
*/
long strnlen_user(const char __user *str, long count)
{
* strlen_user: - Get the size of a user string INCLUDING final NUL.
* @str: The string to measure.
*
- * Context: User context only. This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ * enabled.
*
* Get the size of a NUL-terminated string in user space.
*
* Allocates bounce buffer and returns its kernel virtual address.
*/
-phys_addr_t map_single(struct device *hwdev, phys_addr_t phys, size_t size,
- enum dma_data_direction dir)
+static phys_addr_t
+map_single(struct device *hwdev, phys_addr_t phys, size_t size,
+ enum dma_data_direction dir)
{
dma_addr_t start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
*/
phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
if (paddr == SWIOTLB_MAP_ERROR)
- return NULL;
+ goto err_warn;
ret = phys_to_virt(paddr);
dev_addr = phys_to_dma(hwdev, paddr);
/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
swiotlb_tbl_unmap_single(hwdev, paddr,
size, DMA_TO_DEVICE);
- return NULL;
+ goto err_warn;
}
}
memset(ret, 0, size);
return ret;
+
+err_warn:
+ pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
+ dev_name(hwdev), size);
+ dump_stack();
+
+ return NULL;
}
EXPORT_SYMBOL(swiotlb_alloc_coherent);
* Adds the timer node to the timerqueue, sorted by the
* node's expires value.
*/
-void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
+bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
{
struct rb_node **p = &head->head.rb_node;
struct rb_node *parent = NULL;
rb_link_node(&node->node, parent, p);
rb_insert_color(&node->node, &head->head);
- if (!head->next || node->expires.tv64 < head->next->expires.tv64)
+ if (!head->next || node->expires.tv64 < head->next->expires.tv64) {
head->next = node;
+ return true;
+ }
+ return false;
}
EXPORT_SYMBOL_GPL(timerqueue_add);
*
* Removes the timer node from the timerqueue.
*/
-void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
+bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
{
WARN_ON_ONCE(RB_EMPTY_NODE(&node->node));
}
rb_erase(&node->node, &head->head);
RB_CLEAR_NODE(&node->node);
+ return head->next != NULL;
}
EXPORT_SYMBOL_GPL(timerqueue_del);
flush_delayed_work(&bdi->wb.dwork);
}
-/*
- * Called when the device behind @bdi has been removed or ejected.
- *
- * We can't really do much here except for reducing the dirty ratio at
- * the moment. In the future we should be able to set a flag so that
- * the filesystem can handle errors at mark_inode_dirty time instead
- * of only at writeback time.
- */
-void bdi_unregister(struct backing_dev_info *bdi)
-{
- if (WARN_ON_ONCE(!bdi->dev))
- return;
-
- bdi_set_min_ratio(bdi, 0);
-}
-EXPORT_SYMBOL(bdi_unregister);
-
static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
{
memset(wb, 0, sizeof(*wb));
int i;
bdi_wb_shutdown(bdi);
+ bdi_set_min_ratio(bdi, 0);
WARN_ON(!list_empty(&bdi->work_list));
WARN_ON(delayed_work_pending(&bdi->wb.dwork));
#define BYTES_PER_POINTER sizeof(void *)
/* GFP bitmask for kmemleak internal allocations */
-#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \
+#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC | \
+ __GFP_NOACCOUNT)) | \
__GFP_NORETRY | __GFP_NOMEMALLOC | \
__GFP_NOWARN)
css_get_many(&memcg->css, batch);
if (batch > nr_pages)
refill_stock(memcg, batch - nr_pages);
+ if (!(gfp_mask & __GFP_WAIT))
+ goto done;
/*
* If the hierarchy is above the normal consumption range,
* make the charging task trim their excess contribution.
if (!mem_cgroup_is_root(memcg))
page_counter_uncharge(&memcg->memory, 1);
- /* XXX: caller holds IRQ-safe mapping->tree_lock */
- VM_BUG_ON(!irqs_disabled());
-
+ /* Caller disabled preemption with mapping->tree_lock */
mem_cgroup_charge_statistics(memcg, page, -1);
memcg_check_events(memcg, page);
}
}
#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
-void might_fault(void)
+void __might_fault(const char *file, int line)
{
/*
* Some code (nfs/sunrpc) uses socket ops on kernel memory while
*/
if (segment_eq(get_fs(), KERNEL_DS))
return;
-
- /*
- * it would be nicer only to annotate paths which are not under
- * pagefault_disable, however that requires a larger audit and
- * providing helpers like get_user_atomic.
- */
- if (in_atomic())
+ if (pagefault_disabled())
return;
-
- __might_sleep(__FILE__, __LINE__, 0);
-
+ __might_sleep(file, line, 0);
+#if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
if (current->mm)
might_lock_read(¤t->mm->mmap_sem);
+#endif
}
-EXPORT_SYMBOL(might_fault);
+EXPORT_SYMBOL(__might_fault);
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
* wait_table may be allocated from boot memory,
* here only free if it's allocated by vmalloc.
*/
- if (is_vmalloc_addr(zone->wait_table))
+ if (is_vmalloc_addr(zone->wait_table)) {
vfree(zone->wait_table);
+ zone->wait_table = NULL;
+ }
}
}
EXPORT_SYMBOL(try_offline_node);
if (numabalancing_override)
set_numabalancing_state(numabalancing_override == 1);
- if (nr_node_ids > 1 && !numabalancing_override) {
+ if (num_online_nodes() > 1 && !numabalancing_override) {
pr_info("%s automatic NUMA balancing. "
"Configure with numa_balancing= or the "
"kernel.numa_balancing sysctl",
long x;
x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
- limit - setpoint + 1);
+ (limit - setpoint) | 1);
pos_ratio = x;
pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
* scale global setpoint to bdi's:
* bdi_setpoint = setpoint * bdi_thresh / thresh
*/
- x = div_u64((u64)bdi_thresh << 16, thresh + 1);
+ x = div_u64((u64)bdi_thresh << 16, thresh | 1);
bdi_setpoint = setpoint * (u64)x >> 16;
/*
* Use span=(8*write_bw) in single bdi case as indicated by
if (bdi_dirty < x_intercept - span / 4) {
pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
- x_intercept - bdi_setpoint + 1);
+ (x_intercept - bdi_setpoint) | 1);
} else
pos_ratio /= 4;
buddy_idx = __find_buddy_index(page_idx, order);
buddy = page + (buddy_idx - page_idx);
- if (!is_migrate_isolate_page(buddy)) {
+ if (pfn_valid_within(page_to_pfn(buddy)) &&
+ !is_migrate_isolate_page(buddy)) {
__isolate_free_page(page, order);
kernel_map_pages(page, (1 << order), 1);
set_page_refcounted(page);
return -ENOMEM;
}
inode->i_op = &shmem_short_symlink_operations;
+ inode->i_link = info->symlink;
} else {
error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL);
if (error) {
return 0;
}
-static void *shmem_follow_short_symlink(struct dentry *dentry, struct nameidata *nd)
-{
- nd_set_link(nd, SHMEM_I(d_inode(dentry))->symlink);
- return NULL;
-}
-
-static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *shmem_follow_link(struct dentry *dentry, void **cookie)
{
struct page *page = NULL;
int error = shmem_getpage(d_inode(dentry), 0, &page, SGP_READ, NULL);
- nd_set_link(nd, error ? ERR_PTR(error) : kmap(page));
- if (page)
- unlock_page(page);
- return page;
+ if (error)
+ return ERR_PTR(error);
+ unlock_page(page);
+ *cookie = page;
+ return kmap(page);
}
-static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+static void shmem_put_link(struct inode *unused, void *cookie)
{
- if (!IS_ERR(nd_get_link(nd))) {
- struct page *page = cookie;
- kunmap(page);
- mark_page_accessed(page);
- page_cache_release(page);
- }
+ struct page *page = cookie;
+ kunmap(page);
+ mark_page_accessed(page);
+ page_cache_release(page);
}
#ifdef CONFIG_TMPFS_XATTR
static const struct inode_operations shmem_short_symlink_operations = {
.readlink = generic_readlink,
- .follow_link = shmem_follow_short_symlink,
+ .follow_link = simple_follow_link,
#ifdef CONFIG_TMPFS_XATTR
.setxattr = shmem_setxattr,
.getxattr = shmem_getxattr,
struct file *file;
loff_t size = vma->vm_end - vma->vm_start;
- file = shmem_file_setup("dev/zero", size, vma->vm_flags);
+ /*
+ * Cloning a new file under mmap_sem leads to a lock ordering conflict
+ * between XFS directory reading and selinux: since this file is only
+ * accessible to the user through its mapping, use S_PRIVATE flag to
+ * bypass file security, in the same way as shmem_kernel_file_setup().
+ */
+ file = __shmem_file_setup("dev/zero", size, vma->vm_flags, S_PRIVATE);
if (IS_ERR(file))
return PTR_ERR(file);
static void destroy_handle_cache(struct zs_pool *pool)
{
- kmem_cache_destroy(pool->handle_cachep);
+ if (pool->handle_cachep)
+ kmem_cache_destroy(pool->handle_cachep);
}
static unsigned long alloc_handle(struct zs_pool *pool)
case NETDEV_UP:
/* Put all VLANs for this dev in the up state too. */
vlan_group_for_each_dev(grp, i, vlandev) {
- flgs = vlandev->flags;
+ flgs = dev_get_flags(vlandev);
if (flgs & IFF_UP)
continue;
{
BT_DBG("%s %p", hdev->name, hdev);
- if (!hci_dev_test_flag(hdev, HCI_UNREGISTER)) {
+ if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) &&
+ test_bit(HCI_UP, &hdev->flags)) {
/* Execute vendor specific shutdown routine */
if (hdev->shutdown)
hdev->shutdown(hdev);
* state. If we were running both LE and BR/EDR inquiry
* simultaneously, and BR/EDR inquiry is already
* finished, stop discovery, otherwise BR/EDR inquiry
- * will stop discovery when finished.
+ * will stop discovery when finished. If we will resolve
+ * remote device name, do not change discovery state.
*/
- if (!test_bit(HCI_INQUIRY, &hdev->flags))
+ if (!test_bit(HCI_INQUIRY, &hdev->flags) &&
+ hdev->discovery.state != DISCOVERY_RESOLVING)
hci_discovery_set_state(hdev,
DISCOVERY_STOPPED);
} else {
int err = 0;
if (ndm->ndm_flags & NTF_USE) {
+ local_bh_disable();
rcu_read_lock();
br_fdb_update(p->br, p, addr, vid, true);
rcu_read_unlock();
+ local_bh_enable();
} else {
spin_lock_bh(&p->br->hash_lock);
err = fdb_add_entry(p, addr, ndm->ndm_state,
err = br_ip6_multicast_add_group(br, port, &grec->grec_mca,
vid);
- if (!err)
+ if (err)
break;
}
struct net_bridge_port *p;
struct hlist_node *slot = NULL;
+ if (!hlist_unhashed(&port->rlist))
+ return;
+
hlist_for_each_entry(p, &br->router_list, rlist) {
if ((unsigned long) port >= (unsigned long) p)
break;
if (port->multicast_router != 1)
return;
- if (!hlist_unhashed(&port->rlist))
- goto timer;
-
br_multicast_add_router(br, port);
-timer:
mod_timer(&port->multicast_router_timer,
now + br->multicast_querier_interval);
}
if (query->startup_sent < br->multicast_startup_query_count)
query->startup_sent++;
- RCU_INIT_POINTER(querier, NULL);
+ RCU_INIT_POINTER(querier->port, NULL);
br_multicast_send_query(br, NULL, query);
spin_unlock(&br->multicast_lock);
}
#include <net/route.h>
#include <net/netfilter/br_netfilter.h>
-#if IS_ENABLED(CONFIG_NF_CONNTRACK)
-#include <net/netfilter/nf_conntrack.h>
-#endif
-
#include <asm/uaccess.h>
#include "br_private.h"
#ifdef CONFIG_SYSCTL
return 0;
}
-static bool dnat_took_place(const struct sk_buff *skb)
+static bool daddr_was_changed(const struct sk_buff *skb,
+ const struct nf_bridge_info *nf_bridge)
{
-#if IS_ENABLED(CONFIG_NF_CONNTRACK)
- enum ip_conntrack_info ctinfo;
- struct nf_conn *ct;
-
- ct = nf_ct_get(skb, &ctinfo);
- if (!ct || nf_ct_is_untracked(ct))
- return false;
-
- return test_bit(IPS_DST_NAT_BIT, &ct->status);
-#else
- return false;
-#endif
+ return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr;
}
/* This requires some explaining. If DNAT has taken place,
* we will need to fix up the destination Ethernet address.
+ * This is also true when SNAT takes place (for the reply direction).
*
* There are two cases to consider:
* 1. The packet was DNAT'ed to a device in the same bridge
nf_bridge->pkt_otherhost = false;
}
nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
- if (dnat_took_place(skb)) {
+ if (daddr_was_changed(skb, nf_bridge)) {
if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct sk_buff *skb,
const struct nf_hook_state *state)
{
+ struct nf_bridge_info *nf_bridge;
struct net_bridge_port *p;
struct net_bridge *br;
__u32 len = nf_bridge_encap_header_len(skb);
if (!setup_pre_routing(skb))
return NF_DROP;
+ nf_bridge = nf_bridge_info_get(skb);
+ nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr;
+
skb->protocol = htons(ETH_P_IP);
NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb,
netif_carrier_on(br->dev);
}
br_log_state(p);
+ rcu_read_lock();
br_ifinfo_notify(RTM_NEWLINK, p);
+ rcu_read_unlock();
spin_unlock(&br->lock);
}
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
+
+ if (sock_flag(sk, SOCK_DEAD))
+ break;
+
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
}
struct sk_buff *skb;
lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD)) {
+ err = -ECONNRESET;
+ goto unlock;
+ }
skb = skb_dequeue(&sk->sk_receive_queue);
caif_check_flow_release(sk);
if (list_empty(&req->r_osd_item))
req->r_osd = NULL;
}
-
- list_del_init(&req->r_req_lru_item); /* can be on notarget */
ceph_osdc_put_request(req);
}
err = __map_request(osdc, req,
force_resend || force_resend_writes);
dout("__map_request returned %d\n", err);
- if (err == 0)
- continue; /* no change and no osd was specified */
if (err < 0)
continue; /* hrm! */
- if (req->r_osd == NULL) {
- dout("tid %llu maps to no valid osd\n", req->r_tid);
- needmap++; /* request a newer map */
- continue;
- }
+ if (req->r_osd == NULL || err > 0) {
+ if (req->r_osd == NULL) {
+ dout("lingering %p tid %llu maps to no osd\n",
+ req, req->r_tid);
+ /*
+ * A homeless lingering request makes
+ * no sense, as it's job is to keep
+ * a particular OSD connection open.
+ * Request a newer map and kick the
+ * request, knowing that it won't be
+ * resent until we actually get a map
+ * that can tell us where to send it.
+ */
+ needmap++;
+ }
- dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid,
- req->r_osd ? req->r_osd->o_osd : -1);
- __register_request(osdc, req);
- __unregister_linger_request(osdc, req);
+ dout("kicking lingering %p tid %llu osd%d\n", req,
+ req->r_tid, req->r_osd ? req->r_osd->o_osd : -1);
+ __register_request(osdc, req);
+ __unregister_linger_request(osdc, req);
+ }
}
reset_changed_osds(osdc);
mutex_unlock(&osdc->request_mutex);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
- if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
- if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
- atomic_long_inc(&dev->rx_dropped);
- kfree_skb(skb);
- return NET_RX_DROP;
- }
- }
-
- if (unlikely(!is_skb_forwardable(dev, skb))) {
+ if (skb_orphan_frags(skb, GFP_ATOMIC) ||
+ unlikely(!is_skb_forwardable(dev, skb))) {
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
return -EBUSY;
- if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
+ if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper))
return -EEXIST;
if (master && netdev_master_upper_dev_get(dev))
}
err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
- RTM_GETNSID, net, peer, -1);
+ RTM_NEWNSID, net, peer, -1);
if (err < 0)
goto err_out;
do {
set_current_state(TASK_INTERRUPTIBLE);
hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
- if (!hrtimer_active(&t.timer))
- t.task = NULL;
if (likely(t.task))
schedule();
{
struct sk_buff *skb;
+ if (dev->reg_state != NETREG_REGISTERED)
+ return;
+
skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
if (skb)
rtmsg_ifinfo_send(skb, dev, flags);
while (order) {
if (npages >= 1 << order) {
- page = alloc_pages(gfp_mask |
+ page = alloc_pages((gfp_mask & ~__GFP_WAIT) |
__GFP_COMP |
__GFP_NOWARN |
__GFP_NORETRY,
/*
* SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
- * progress of swapping. However, if SOCK_MEMALLOC is cleared while
- * it has rmem allocations there is a risk that the user of the
- * socket cannot make forward progress due to exceeding the rmem
- * limits. By rights, sk_clear_memalloc() should only be called
- * on sockets being torn down but warn and reset the accounting if
- * that assumption breaks.
+ * progress of swapping. SOCK_MEMALLOC may be cleared while
+ * it has rmem allocations due to the last swapfile being deactivated
+ * but there is a risk that the socket is unusable due to exceeding
+ * the rmem limits. Reclaim the reserves and obey rmem limits again.
*/
- if (WARN_ON(sk->sk_forward_alloc))
- sk_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);
return;
sock_hold(sk);
- sock_net_set(sk, get_net(&init_net));
sock_release(sk->sk_socket);
+ sock_net_set(sk, get_net(&init_net));
sock_put(sk);
}
EXPORT_SYMBOL(sk_release_kernel);
pfrag->offset = 0;
if (SKB_FRAG_PAGE_ORDER) {
- pfrag->page = alloc_pages(gfp | __GFP_COMP |
+ pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP |
__GFP_NOWARN | __GFP_NORETRY,
SKB_FRAG_PAGE_ORDER);
if (likely(pfrag->page)) {
*/
ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL);
if (ds == NULL)
- return NULL;
+ return ERR_PTR(-ENOMEM);
ds->dst = dst;
ds->index = index;
ret = dsa_switch_setup_one(ds, parent);
if (ret)
- return NULL;
+ return ERR_PTR(ret);
return ds;
}
obj-y += 6lowpan/
ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o core.o \
- header_ops.o sysfs.o nl802154.o
+ header_ops.o sysfs.o nl802154.o trace.o
ieee802154_socket-y := socket.o
+CFLAGS_trace.o := -I$(src)
+
ccflags-y += -D__CHECK_ENDIAN__
int rc = -ENOBUFS;
struct net_device *dev;
int type = __IEEE802154_DEV_INVALID;
+ unsigned char name_assign_type;
pr_debug("%s\n", __func__);
if (devname[nla_len(info->attrs[IEEE802154_ATTR_DEV_NAME]) - 1]
!= '\0')
return -EINVAL; /* phy name should be null-terminated */
+ name_assign_type = NET_NAME_USER;
} else {
devname = "wpan%d";
+ name_assign_type = NET_NAME_ENUM;
}
if (strlen(devname) >= IFNAMSIZ)
}
dev = rdev_add_virtual_intf_deprecated(wpan_phy_to_rdev(phy), devname,
- type);
+ name_assign_type, type);
if (IS_ERR(dev)) {
rc = PTR_ERR(dev);
goto nla_put_failure;
return rdev_add_virtual_intf(rdev,
nla_data(info->attrs[NL802154_ATTR_IFNAME]),
- type, extended_addr);
+ NET_NAME_USER, type, extended_addr);
}
static int nl802154_del_interface(struct sk_buff *skb, struct genl_info *info)
#include <net/cfg802154.h>
#include "core.h"
+#include "trace.h"
static inline struct net_device *
rdev_add_virtual_intf_deprecated(struct cfg802154_registered_device *rdev,
- const char *name, int type)
+ const char *name,
+ unsigned char name_assign_type,
+ int type)
{
return rdev->ops->add_virtual_intf_deprecated(&rdev->wpan_phy, name,
- type);
+ name_assign_type, type);
}
static inline void
static inline int
rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name,
+ unsigned char name_assign_type,
enum nl802154_iftype type, __le64 extended_addr)
{
- return rdev->ops->add_virtual_intf(&rdev->wpan_phy, name, type,
+ int ret;
+
+ trace_802154_rdev_add_virtual_intf(&rdev->wpan_phy, name, type,
extended_addr);
+ ret = rdev->ops->add_virtual_intf(&rdev->wpan_phy, name,
+ name_assign_type, type,
+ extended_addr);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_del_virtual_intf(struct cfg802154_registered_device *rdev,
struct wpan_dev *wpan_dev)
{
- return rdev->ops->del_virtual_intf(&rdev->wpan_phy, wpan_dev);
+ int ret;
+
+ trace_802154_rdev_del_virtual_intf(&rdev->wpan_phy, wpan_dev);
+ ret = rdev->ops->del_virtual_intf(&rdev->wpan_phy, wpan_dev);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_set_channel(struct cfg802154_registered_device *rdev, u8 page, u8 channel)
{
- return rdev->ops->set_channel(&rdev->wpan_phy, page, channel);
+ int ret;
+
+ trace_802154_rdev_set_channel(&rdev->wpan_phy, page, channel);
+ ret = rdev->ops->set_channel(&rdev->wpan_phy, page, channel);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_set_cca_mode(struct cfg802154_registered_device *rdev,
const struct wpan_phy_cca *cca)
{
- return rdev->ops->set_cca_mode(&rdev->wpan_phy, cca);
+ int ret;
+
+ trace_802154_rdev_set_cca_mode(&rdev->wpan_phy, cca);
+ ret = rdev->ops->set_cca_mode(&rdev->wpan_phy, cca);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_set_pan_id(struct cfg802154_registered_device *rdev,
struct wpan_dev *wpan_dev, __le16 pan_id)
{
- return rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id);
+ int ret;
+
+ trace_802154_rdev_set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id);
+ ret = rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_set_short_addr(struct cfg802154_registered_device *rdev,
struct wpan_dev *wpan_dev, __le16 short_addr)
{
- return rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr);
+ int ret;
+
+ trace_802154_rdev_set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr);
+ ret = rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_set_backoff_exponent(struct cfg802154_registered_device *rdev,
struct wpan_dev *wpan_dev, u8 min_be, u8 max_be)
{
- return rdev->ops->set_backoff_exponent(&rdev->wpan_phy, wpan_dev,
+ int ret;
+
+ trace_802154_rdev_set_backoff_exponent(&rdev->wpan_phy, wpan_dev,
min_be, max_be);
+ ret = rdev->ops->set_backoff_exponent(&rdev->wpan_phy, wpan_dev,
+ min_be, max_be);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_set_max_csma_backoffs(struct cfg802154_registered_device *rdev,
struct wpan_dev *wpan_dev, u8 max_csma_backoffs)
{
- return rdev->ops->set_max_csma_backoffs(&rdev->wpan_phy, wpan_dev,
- max_csma_backoffs);
+ int ret;
+
+ trace_802154_rdev_set_csma_backoffs(&rdev->wpan_phy, wpan_dev,
+ max_csma_backoffs);
+ ret = rdev->ops->set_max_csma_backoffs(&rdev->wpan_phy, wpan_dev,
+ max_csma_backoffs);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_set_max_frame_retries(struct cfg802154_registered_device *rdev,
struct wpan_dev *wpan_dev, s8 max_frame_retries)
{
- return rdev->ops->set_max_frame_retries(&rdev->wpan_phy, wpan_dev,
+ int ret;
+
+ trace_802154_rdev_set_max_frame_retries(&rdev->wpan_phy, wpan_dev,
max_frame_retries);
+ ret = rdev->ops->set_max_frame_retries(&rdev->wpan_phy, wpan_dev,
+ max_frame_retries);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
static inline int
rdev_set_lbt_mode(struct cfg802154_registered_device *rdev,
struct wpan_dev *wpan_dev, bool mode)
{
- return rdev->ops->set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode);
+ int ret;
+
+ trace_802154_rdev_set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode);
+ ret = rdev->ops->set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode);
+ trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+ return ret;
}
#endif /* __CFG802154_RDEV_OPS */
--- /dev/null
+#include <linux/module.h>
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+#endif
--- /dev/null
+/* Based on net/wireless/tracing.h */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cfg802154
+
+#if !defined(__RDEV_CFG802154_OPS_TRACE) || defined(TRACE_HEADER_MULTI_READ)
+#define __RDEV_CFG802154_OPS_TRACE
+
+#include <linux/tracepoint.h>
+
+#include <net/cfg802154.h>
+
+#define MAXNAME 32
+#define WPAN_PHY_ENTRY __array(char, wpan_phy_name, MAXNAME)
+#define WPAN_PHY_ASSIGN strlcpy(__entry->wpan_phy_name, \
+ wpan_phy_name(wpan_phy), \
+ MAXNAME)
+#define WPAN_PHY_PR_FMT "%s"
+#define WPAN_PHY_PR_ARG __entry->wpan_phy_name
+
+#define WPAN_DEV_ENTRY __field(u32, identifier)
+#define WPAN_DEV_ASSIGN (__entry->identifier) = (!IS_ERR_OR_NULL(wpan_dev) \
+ ? wpan_dev->identifier : 0)
+#define WPAN_DEV_PR_FMT "wpan_dev(%u)"
+#define WPAN_DEV_PR_ARG (__entry->identifier)
+
+#define WPAN_CCA_ENTRY __field(enum nl802154_cca_modes, cca_mode) \
+ __field(enum nl802154_cca_opts, cca_opt)
+#define WPAN_CCA_ASSIGN \
+ do { \
+ (__entry->cca_mode) = cca->mode; \
+ (__entry->cca_opt) = cca->opt; \
+ } while (0)
+#define WPAN_CCA_PR_FMT "cca_mode: %d, cca_opt: %d"
+#define WPAN_CCA_PR_ARG __entry->cca_mode, __entry->cca_opt
+
+#define BOOL_TO_STR(bo) (bo) ? "true" : "false"
+
+/*************************************************************
+ * rdev->ops traces *
+ *************************************************************/
+
+TRACE_EVENT(802154_rdev_add_virtual_intf,
+ TP_PROTO(struct wpan_phy *wpan_phy, char *name,
+ enum nl802154_iftype type, __le64 extended_addr),
+ TP_ARGS(wpan_phy, name, type, extended_addr),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ __string(vir_intf_name, name ? name : "<noname>")
+ __field(enum nl802154_iftype, type)
+ __field(__le64, extended_addr)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ __assign_str(vir_intf_name, name ? name : "<noname>");
+ __entry->type = type;
+ __entry->extended_addr = extended_addr;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", virtual intf name: %s, type: %d, ea %llx",
+ WPAN_PHY_PR_ARG, __get_str(vir_intf_name), __entry->type,
+ __le64_to_cpu(__entry->extended_addr))
+);
+
+TRACE_EVENT(802154_rdev_del_virtual_intf,
+ TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev),
+ TP_ARGS(wpan_phy, wpan_dev),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ WPAN_DEV_ENTRY
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ WPAN_DEV_ASSIGN;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT, WPAN_PHY_PR_ARG,
+ WPAN_DEV_PR_ARG)
+);
+
+TRACE_EVENT(802154_rdev_set_channel,
+ TP_PROTO(struct wpan_phy *wpan_phy, u8 page, u8 channel),
+ TP_ARGS(wpan_phy, page, channel),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ __field(u8, page)
+ __field(u8, channel)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ __entry->page = page;
+ __entry->channel = channel;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", page: %d, channel: %d", WPAN_PHY_PR_ARG,
+ __entry->page, __entry->channel)
+);
+
+TRACE_EVENT(802154_rdev_set_cca_mode,
+ TP_PROTO(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca),
+ TP_ARGS(wpan_phy, cca),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ WPAN_CCA_ENTRY
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ WPAN_CCA_ASSIGN;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", " WPAN_CCA_PR_FMT, WPAN_PHY_PR_ARG,
+ WPAN_CCA_PR_ARG)
+);
+
+DECLARE_EVENT_CLASS(802154_le16_template,
+ TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ __le16 le16arg),
+ TP_ARGS(wpan_phy, wpan_dev, le16arg),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ WPAN_DEV_ENTRY
+ __field(__le16, le16arg)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ WPAN_DEV_ASSIGN;
+ __entry->le16arg = le16arg;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", pan id: 0x%04x",
+ WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG,
+ __le16_to_cpu(__entry->le16arg))
+);
+
+DEFINE_EVENT(802154_le16_template, 802154_rdev_set_pan_id,
+ TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ __le16 le16arg),
+ TP_ARGS(wpan_phy, wpan_dev, le16arg)
+);
+
+DEFINE_EVENT_PRINT(802154_le16_template, 802154_rdev_set_short_addr,
+ TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ __le16 le16arg),
+ TP_ARGS(wpan_phy, wpan_dev, le16arg),
+ TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", sa: 0x%04x",
+ WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG,
+ __le16_to_cpu(__entry->le16arg))
+);
+
+TRACE_EVENT(802154_rdev_set_backoff_exponent,
+ TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ u8 min_be, u8 max_be),
+ TP_ARGS(wpan_phy, wpan_dev, min_be, max_be),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ WPAN_DEV_ENTRY
+ __field(u8, min_be)
+ __field(u8, max_be)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ WPAN_DEV_ASSIGN;
+ __entry->min_be = min_be;
+ __entry->max_be = max_be;
+ ),
+
+ TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT
+ ", min be: %d, max_be: %d", WPAN_PHY_PR_ARG,
+ WPAN_DEV_PR_ARG, __entry->min_be, __entry->max_be)
+);
+
+TRACE_EVENT(802154_rdev_set_csma_backoffs,
+ TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ u8 max_csma_backoffs),
+ TP_ARGS(wpan_phy, wpan_dev, max_csma_backoffs),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ WPAN_DEV_ENTRY
+ __field(u8, max_csma_backoffs)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ WPAN_DEV_ASSIGN;
+ __entry->max_csma_backoffs = max_csma_backoffs;
+ ),
+
+ TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT
+ ", max csma backoffs: %d", WPAN_PHY_PR_ARG,
+ WPAN_DEV_PR_ARG, __entry->max_csma_backoffs)
+);
+
+TRACE_EVENT(802154_rdev_set_max_frame_retries,
+ TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ s8 max_frame_retries),
+ TP_ARGS(wpan_phy, wpan_dev, max_frame_retries),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ WPAN_DEV_ENTRY
+ __field(s8, max_frame_retries)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ WPAN_DEV_ASSIGN;
+ __entry->max_frame_retries = max_frame_retries;
+ ),
+
+ TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT
+ ", max frame retries: %d", WPAN_PHY_PR_ARG,
+ WPAN_DEV_PR_ARG, __entry->max_frame_retries)
+);
+
+TRACE_EVENT(802154_rdev_set_lbt_mode,
+ TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ bool mode),
+ TP_ARGS(wpan_phy, wpan_dev, mode),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ WPAN_DEV_ENTRY
+ __field(bool, mode)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ WPAN_DEV_ASSIGN;
+ __entry->mode = mode;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT
+ ", lbt mode: %s", WPAN_PHY_PR_ARG,
+ WPAN_DEV_PR_ARG, BOOL_TO_STR(__entry->mode))
+);
+
+TRACE_EVENT(802154_rdev_return_int,
+ TP_PROTO(struct wpan_phy *wpan_phy, int ret),
+ TP_ARGS(wpan_phy, ret),
+ TP_STRUCT__entry(
+ WPAN_PHY_ENTRY
+ __field(int, ret)
+ ),
+ TP_fast_assign(
+ WPAN_PHY_ASSIGN;
+ __entry->ret = ret;
+ ),
+ TP_printk(WPAN_PHY_PR_FMT ", returned: %d", WPAN_PHY_PR_ARG,
+ __entry->ret)
+);
+
+#endif /* !__RDEV_CFG802154_OPS_TRACE || TRACE_HEADER_MULTI_READ */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
aead_givcrypt_set_assoc(req, asg, assoclen);
aead_givcrypt_set_giv(req, esph->enc_data,
- XFRM_SKB_CB(skb)->seq.output.low);
+ XFRM_SKB_CB(skb)->seq.output.low +
+ ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
ESP_SKB_CB(skb)->tmp = tmp;
err = crypto_aead_givencrypt(req);
state = fa->fa_state;
new_fa->fa_state = state & ~FA_S_ACCESSED;
new_fa->fa_slen = fa->fa_slen;
+ new_fa->tb_id = tb->tb_id;
err = netdev_switch_fib_ipv4_add(key, plen, fi,
new_fa->fa_tos,
/* record local slen */
slen = fa->fa_slen;
- if (!fi || !(fi->fib_flags & RTNH_F_EXTERNAL))
+ if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD))
continue;
netdev_switch_fib_ipv4_del(n->key,
handler->idiag_get_info(sk, r, info);
if (sk->sk_state < TCP_TIME_WAIT) {
- int err = 0;
+ union tcp_cc_info info;
+ size_t sz = 0;
+ int attr;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops && ca_ops->get_info)
- err = ca_ops->get_info(sk, ext, skb);
+ sz = ca_ops->get_info(sk, ext, &attr, &info);
rcu_read_unlock();
- if (err < 0)
+ if (sz && nla_put(skb, attr, sz, &info) < 0)
goto errout;
}
goto drop;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
- skb->mark = be32_to_cpu(tunnel->parms.i_key);
return xfrm_input(skb, nexthdr, spi, encap_type);
}
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
+ u32 orig_mark = skb->mark;
+ int ret;
if (!tunnel)
return 1;
x = xfrm_input_state(skb);
family = x->inner_mode->afinfo->family;
- if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ skb->mark = be32_to_cpu(tunnel->parms.i_key);
+ ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+ skb->mark = orig_mark;
+
+ if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
memset(&fl, 0, sizeof(fl));
- skb->mark = be32_to_cpu(tunnel->parms.o_key);
-
switch (skb->protocol) {
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
return NETDEV_TX_OK;
}
+ /* override mark with tunnel output key */
+ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
+
return vti_xmit(skb, dev, &fl);
}
/* overflow check */
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
/* overflow check */
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
bool send;
int code;
+ /* IP on this device is disabled. */
+ if (!in_dev)
+ goto out;
+
net = dev_net(rt->dst.dev);
if (!IN_DEV_FORWARD(in_dev)) {
switch (rt->dst.error) {
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
+#include <linux/inet_diag.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/skbuff.h>
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
+ u64_stats_init(&tp->syncp);
tp->reordering = sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
#endif
/* Return information about state of tcp endpoint in API format. */
-void tcp_get_info(const struct sock *sk, struct tcp_info *info)
+void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
+ unsigned int start;
u32 rate;
memset(info, 0, sizeof(*info));
rate = READ_ONCE(sk->sk_max_pacing_rate);
info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&tp->syncp);
+ info->tcpi_bytes_acked = tp->bytes_acked;
+ info->tcpi_bytes_received = tp->bytes_received;
+ } while (u64_stats_fetch_retry_irq(&tp->syncp, start));
}
EXPORT_SYMBOL_GPL(tcp_get_info);
return -EFAULT;
return 0;
}
+ case TCP_CC_INFO: {
+ const struct tcp_congestion_ops *ca_ops;
+ union tcp_cc_info info;
+ size_t sz = 0;
+ int attr;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ ca_ops = icsk->icsk_ca_ops;
+ if (ca_ops && ca_ops->get_info)
+ sz = ca_ops->get_info(sk, ~0U, &attr, &info);
+
+ len = min_t(unsigned int, len, sz);
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &info, len))
+ return -EFAULT;
+ return 0;
+ }
case TCP_QUICKACK:
val = !icsk->icsk_ack.pingpong;
break;
tcp_cleanup_congestion_control(sk);
icsk->icsk_ca_ops = ca;
+ icsk->icsk_ca_setsockopt = 1;
if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
rcu_read_lock();
ca = __tcp_ca_find_autoload(name);
/* No change asking for existing value */
- if (ca == icsk->icsk_ca_ops)
+ if (ca == icsk->icsk_ca_ops) {
+ icsk->icsk_ca_setsockopt = 1;
goto out;
+ }
if (!ca)
err = -ENOENT;
else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
}
}
-static int dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info)
{
const struct dctcp *ca = inet_csk_ca(sk);
*/
if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) ||
ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcp_dctcp_info info;
-
- memset(&info, 0, sizeof(info));
+ memset(info, 0, sizeof(struct tcp_dctcp_info));
if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) {
- info.dctcp_enabled = 1;
- info.dctcp_ce_state = (u16) ca->ce_state;
- info.dctcp_alpha = ca->dctcp_alpha;
- info.dctcp_ab_ecn = ca->acked_bytes_ecn;
- info.dctcp_ab_tot = ca->acked_bytes_total;
+ info->dctcp.dctcp_enabled = 1;
+ info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
+ info->dctcp.dctcp_alpha = ca->dctcp_alpha;
+ info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
+ info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
}
- return nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info);
+ *attr = INET_DIAG_DCTCPINFO;
+ return sizeof(*info);
}
return 0;
}
skb_set_owner_r(skb2, child);
__skb_queue_tail(&child->sk_receive_queue, skb2);
tp->syn_data_acked = 1;
+
+ /* u64_stats_update_begin(&tp->syncp) not needed here,
+ * as we certainly are not changing upper 32bit value (0)
+ */
+ tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
} else {
end_seq = TCP_SKB_CB(skb)->seq + 1;
}
}
/* Extract info for Tcp socket info provided via netlink. */
-static int tcp_illinois_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info)
{
const struct illinois *ca = inet_csk_ca(sk);
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcpvegas_info info = {
- .tcpv_enabled = 1,
- .tcpv_rttcnt = ca->cnt_rtt,
- .tcpv_minrtt = ca->base_rtt,
- };
+ info->vegas.tcpv_enabled = 1;
+ info->vegas.tcpv_rttcnt = ca->cnt_rtt;
+ info->vegas.tcpv_minrtt = ca->base_rtt;
+ info->vegas.tcpv_rtt = 0;
- if (info.tcpv_rttcnt > 0) {
+ if (info->vegas.tcpv_rttcnt > 0) {
u64 t = ca->sum_rtt;
- do_div(t, info.tcpv_rttcnt);
- info.tcpv_rtt = t;
+ do_div(t, info->vegas.tcpv_rttcnt);
+ info->vegas.tcpv_rtt = t;
}
- return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+ *attr = INET_DIAG_VEGASINFO;
+ return sizeof(struct tcpvegas_info);
}
return 0;
}
for (j = 0; j < used_sacks; j++)
tp->recv_sack_cache[i++] = sp[j];
- tcp_mark_lost_retrans(sk);
-
- tcp_verify_left_out(tp);
-
if ((state.reord < tp->fackets_out) &&
((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))
tcp_update_reordering(sk, tp->fackets_out - state.reord, 0);
+ tcp_mark_lost_retrans(sk);
+ tcp_verify_left_out(tp);
out:
#if FASTRETRANS_DEBUG > 0
struct tcp_sock *tp = tcp_sk(sk);
bool recovered = !before(tp->snd_una, tp->high_seq);
+ if ((flag & FLAG_SND_UNA_ADVANCED) &&
+ tcp_try_undo_loss(sk, false))
+ return;
+
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
/* Step 3.b. A timeout is spurious if not all data are
* lost, i.e., never-retransmitted data are (s)acked.
*/
- if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
+ if ((flag & FLAG_ORIG_SACK_ACKED) &&
+ tcp_try_undo_loss(sk, true))
return;
- if (after(tp->snd_nxt, tp->high_seq) &&
- (flag & FLAG_DATA_SACKED || is_dupack)) {
- tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
+ if (after(tp->snd_nxt, tp->high_seq)) {
+ if (flag & FLAG_DATA_SACKED || is_dupack)
+ tp->frto = 0; /* Step 3.a. loss was real */
} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
tp->high_seq = tp->snd_nxt;
__tcp_push_pending_frames(sk, tcp_current_mss(sk),
else if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
}
- if (tcp_try_undo_loss(sk, false))
- return;
tcp_xmit_retransmit_queue(sk);
}
(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
}
+/* If we update tp->snd_una, also update tp->bytes_acked */
+static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
+{
+ u32 delta = ack - tp->snd_una;
+
+ u64_stats_update_begin(&tp->syncp);
+ tp->bytes_acked += delta;
+ u64_stats_update_end(&tp->syncp);
+ tp->snd_una = ack;
+}
+
+/* If we update tp->rcv_nxt, also update tp->bytes_received */
+static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
+{
+ u32 delta = seq - tp->rcv_nxt;
+
+ u64_stats_update_begin(&tp->syncp);
+ tp->bytes_received += delta;
+ u64_stats_update_end(&tp->syncp);
+ tp->rcv_nxt = seq;
+}
+
/* Update our send window.
*
* Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
}
}
- tp->snd_una = ack;
+ tcp_snd_una_update(tp, ack);
return flag;
}
* Note, we use the fact that SND.UNA>=SND.WL2.
*/
tcp_update_wl(tp, ack_seq);
- tp->snd_una = ack;
+ tcp_snd_una_update(tp, ack);
flag |= FLAG_WIN_UPDATE;
tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
tail = skb_peek_tail(&sk->sk_receive_queue);
eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
- tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
if (!eaten)
__skb_queue_tail(&sk->sk_receive_queue, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
__skb_pull(skb, hdrlen);
eaten = (tail &&
tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0;
- tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
if (!eaten) {
__skb_queue_tail(&sk->sk_receive_queue, skb);
skb_set_owner_r(skb, sk);
eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
}
- tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
if (skb->len)
tcp_event_data_recv(sk, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
tcp_rcv_rtt_measure_ts(sk, skb);
__skb_pull(skb, tcp_header_len);
- tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER);
eaten = 1;
}
tw->tw_v6_daddr = sk->sk_v6_daddr;
tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
tw->tw_tclass = np->tclass;
- tw->tw_flowlabel = np->flow_label >> 12;
+ tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
tw->tw_ipv6only = sk->sk_ipv6only;
}
#endif
rcu_read_unlock();
}
- if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner))
+ /* If no valid choice made yet, assign current system default ca. */
+ if (!ca_got_dst &&
+ (!icsk->icsk_ca_setsockopt ||
+ !try_module_get(icsk->icsk_ca_ops->owner)))
tcp_assign_congestion_control(sk);
tcp_set_ca_state(sk, TCP_CA_Open);
}
/* Extract info for Tcp socket info provided via netlink. */
-int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info)
{
const struct vegas *ca = inet_csk_ca(sk);
+
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcpvegas_info info = {
- .tcpv_enabled = ca->doing_vegas_now,
- .tcpv_rttcnt = ca->cntRTT,
- .tcpv_rtt = ca->baseRTT,
- .tcpv_minrtt = ca->minRTT,
- };
-
- return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+ info->vegas.tcpv_enabled = ca->doing_vegas_now,
+ info->vegas.tcpv_rttcnt = ca->cntRTT,
+ info->vegas.tcpv_rtt = ca->baseRTT,
+ info->vegas.tcpv_minrtt = ca->minRTT,
+
+ *attr = INET_DIAG_VEGASINFO;
+ return sizeof(struct tcpvegas_info);
}
return 0;
}
void tcp_vegas_state(struct sock *sk, u8 ca_state);
void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us);
void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event);
-int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb);
+size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info);
#endif /* __TCP_VEGAS_H */
}
/* Extract info for Tcp socket info provided via netlink. */
-static int tcp_westwood_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr,
+ union tcp_cc_info *info)
{
const struct westwood *ca = inet_csk_ca(sk);
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcpvegas_info info = {
- .tcpv_enabled = 1,
- .tcpv_rtt = jiffies_to_usecs(ca->rtt),
- .tcpv_minrtt = jiffies_to_usecs(ca->rtt_min),
- };
+ info->vegas.tcpv_enabled = 1;
+ info->vegas.tcpv_rttcnt = 0;
+ info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt),
+ info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min),
- return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+ *attr = INET_DIAG_VEGASINFO;
+ return sizeof(struct tcpvegas_info);
}
return 0;
}
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/igmp.h>
+#include <linux/inetdevice.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
}
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
struct sock *sk;
struct dst_entry *dst;
int dif = skb->dev->ifindex;
+ int ours;
/* validate the packet */
if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
uh = udp_hdr(skb);
if (skb->pkt_type == PACKET_BROADCAST ||
- skb->pkt_type == PACKET_MULTICAST)
+ skb->pkt_type == PACKET_MULTICAST) {
+ struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+
+ if (!in_dev)
+ return;
+
+ ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+ iph->protocol);
+ if (!ours)
+ return;
sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif);
- else if (skb->pkt_type == PACKET_HOST)
+ } else if (skb->pkt_type == PACKET_HOST) {
sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif);
- else
+ } else {
return;
+ }
if (!sk)
return;
free_percpu(idev->stats.ipv6);
}
+static void in6_dev_finish_destroy_rcu(struct rcu_head *head)
+{
+ struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu);
+
+ snmp6_free_dev(idev);
+ kfree(idev);
+}
+
/* Nobody refers to this device, we may destroy it. */
void in6_dev_finish_destroy(struct inet6_dev *idev)
pr_warn("Freeing alive inet6 device %p\n", idev);
return;
}
- snmp6_free_dev(idev);
- kfree_rcu(idev, rcu);
+ call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu);
}
EXPORT_SYMBOL(in6_dev_finish_destroy);
aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
aead_givcrypt_set_assoc(req, asg, assoclen);
aead_givcrypt_set_giv(req, esph->enc_data,
- XFRM_SKB_CB(skb)->seq.output.low);
+ XFRM_SKB_CB(skb)->seq.output.low +
+ ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
ESP_SKB_CB(skb)->tmp = tmp;
err = crypto_aead_givencrypt(req);
{
struct rt6_info *iter = NULL;
struct rt6_info **ins;
+ struct rt6_info **fallback_ins = NULL;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
int add = (!info->nlh ||
(info->nlh->nlmsg_flags & NLM_F_EXCL))
return -EEXIST;
if (replace) {
- found++;
- break;
+ if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
+ found++;
+ break;
+ }
+ if (rt_can_ecmp)
+ fallback_ins = fallback_ins ?: ins;
+ goto next_iter;
}
if (iter->dst.dev == rt->dst.dev &&
if (iter->rt6i_metric > rt->rt6i_metric)
break;
+next_iter:
ins = &iter->dst.rt6_next;
}
+ if (fallback_ins && !found) {
+ /* No ECMP-able route found, replace first non-ECMP one */
+ ins = fallback_ins;
+ iter = *ins;
+ found++;
+ }
+
/* Reset round-robin state, if necessary */
if (ins == &fn->leaf)
fn->rr_ptr = NULL;
}
} else {
+ int nsiblings;
+
if (!found) {
if (add)
goto add;
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
+ nsiblings = iter->rt6i_nsiblings;
fib6_purge_rt(iter, fn, info->nl_net);
rt6_release(iter);
+
+ if (nsiblings) {
+ /* Replacing an ECMP route, remove all siblings */
+ ins = &rt->dst.rt6_next;
+ iter = *ins;
+ while (iter) {
+ if (rt6_qualify_for_ecmp(iter)) {
+ *ins = iter->dst.rt6_next;
+ fib6_purge_rt(iter, fn, info->nl_net);
+ rt6_release(iter);
+ nsiblings--;
+ } else {
+ ins = &iter->dst.rt6_next;
+ }
+ iter = *ins;
+ }
+ WARN_ON(nsiblings != 0);
+ }
}
return 0;
#endif
int err;
- if (!*dst)
- *dst = ip6_route_output(net, sk, fl6);
-
- err = (*dst)->error;
- if (err)
- goto out_err_release;
+ /* The correct way to handle this would be to do
+ * ip6_route_get_saddr, and then ip6_route_output; however,
+ * the route-specific preferred source forces the
+ * ip6_route_output call _before_ ip6_route_get_saddr.
+ *
+ * In source specific routing (no src=any default route),
+ * ip6_route_output will fail given src=any saddr, though, so
+ * that's why we try it again later.
+ */
+ if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) {
+ struct rt6_info *rt;
+ bool had_dst = *dst != NULL;
- if (ipv6_addr_any(&fl6->saddr)) {
- struct rt6_info *rt = (struct rt6_info *) *dst;
+ if (!had_dst)
+ *dst = ip6_route_output(net, sk, fl6);
+ rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
err = ip6_route_get_saddr(net, rt, &fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)
goto out_err_release;
+
+ /* If we had an erroneous initial result, pretend it
+ * never existed and let the SA-enabled version take
+ * over.
+ */
+ if (!had_dst && (*dst)->error) {
+ dst_release(*dst);
+ *dst = NULL;
+ }
}
+ if (!*dst)
+ *dst = ip6_route_output(net, sk, fl6);
+
+ err = (*dst)->error;
+ if (err)
+ goto out_err_release;
+
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
/* If this is the first and only packet and device
* supports checksum offloading, let's use it.
+ * Use transhdrlen, same as IPv4, because partial
+ * sums only work when transhdrlen is set.
*/
- if (!skb && sk->sk_protocol == IPPROTO_UDP &&
+ if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
length + fragheaderlen < mtu &&
rt->dst.dev->features & NETIF_F_V6_CSUM &&
!exthdrlen)
}
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
- skb->mark = be32_to_cpu(t->parms.i_key);
rcu_read_unlock();
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
+ u32 orig_mark = skb->mark;
+ int ret;
if (!t)
return 1;
x = xfrm_input_state(skb);
family = x->inner_mode->afinfo->family;
- if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ skb->mark = be32_to_cpu(t->parms.i_key);
+ ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+ skb->mark = orig_mark;
+
+ if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
struct net_device *tdev;
struct xfrm_state *x;
int err = -1;
+ int mtu;
if (!dst)
goto tx_err_link_failure;
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
+ mtu = dst_mtu(dst);
+ if (!skb->ignore_df && skb->len > mtu) {
+ skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
+
+ if (skb->protocol == htons(ETH_P_IPV6))
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ else
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
+
+ return -EMSGSIZE;
+ }
+
err = dst_output(skb);
if (net_xmit_eval(err) == 0) {
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
int ret;
memset(&fl, 0, sizeof(fl));
- skb->mark = be32_to_cpu(t->parms.o_key);
switch (skb->protocol) {
case htons(ETH_P_IPV6):
goto tx_err;
}
+ /* override mark with tunnel output key */
+ fl.flowi_mark = be32_to_cpu(t->parms.o_key);
+
ret = vti6_xmit(skb, dev, &fl);
if (ret < 0)
goto tx_err;
/* overflow check */
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
unsigned int prefs,
struct in6_addr *saddr)
{
- struct inet6_dev *idev = ip6_dst_idev((struct dst_entry *)rt);
+ struct inet6_dev *idev =
+ rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
int err = 0;
- if (rt->rt6i_prefsrc.plen)
+ if (rt && rt->rt6i_prefsrc.plen)
*saddr = rt->rt6i_prefsrc.addr;
else
err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
int attrlen;
int err = 0, last_err = 0;
+ remaining = cfg->fc_mp_len;
beginning:
rtnh = (struct rtnexthop *)cfg->fc_mp;
- remaining = cfg->fc_mp_len;
/* Parse a Multipath Entry */
while (rtnh_ok(rtnh, remaining)) {
* next hops that have been already added.
*/
add = 0;
+ remaining = cfg->fc_mp_len - remaining;
goto beginning;
}
}
/* Because each route is added like a single route we remove
- * this flag after the first nexthop (if there is a collision,
- * we have already fail to add the first nexthop:
- * fib6_add_rt2node() has reject it).
+ * these flags after the first nexthop: if there is a collision,
+ * we have already failed to add the first nexthop:
+ * fib6_add_rt2node() has rejected it; when replacing, old
+ * nexthops have been replaced by first new, the rest should
+ * be added to it.
*/
- cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL;
+ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
+ NLM_F_REPLACE);
rtnh = rtnh_next(rtnh, &remaining);
}
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp + tcptw->tw_ts_offset,
tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
- tw->tw_tclass, (tw->tw_flowlabel << 12));
+ tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
inet_twsk_put(tw);
}
}
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
(inet->inet_dport && inet->inet_dport != rmt_port) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+ (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+ (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+ !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
if (!inet6_mc_check(sk, loc_addr, rmt_addr))
return false;
struct ieee80211_roc_work *new_roc,
struct ieee80211_roc_work *cur_roc)
{
- unsigned long j = jiffies;
- unsigned long cur_roc_end = cur_roc->hw_start_time +
- msecs_to_jiffies(cur_roc->duration);
- struct ieee80211_roc_work *next_roc;
- int new_dur;
+ unsigned long now = jiffies;
+ unsigned long remaining = cur_roc->hw_start_time +
+ msecs_to_jiffies(cur_roc->duration) -
+ now;
if (WARN_ON(!cur_roc->started || !cur_roc->hw_begun))
return false;
- if (time_after(j + IEEE80211_ROC_MIN_LEFT, cur_roc_end))
+ /* if it doesn't fit entirely, schedule a new one */
+ if (new_roc->duration > jiffies_to_msecs(remaining))
return false;
ieee80211_handle_roc_started(new_roc);
- new_dur = new_roc->duration - jiffies_to_msecs(cur_roc_end - j);
-
- /* cur_roc is long enough - add new_roc to the dependents list. */
- if (new_dur <= 0) {
- list_add_tail(&new_roc->list, &cur_roc->dependents);
- return true;
- }
-
- new_roc->duration = new_dur;
-
- /*
- * if cur_roc was already coalesced before, we might
- * want to extend the next roc instead of adding
- * a new one.
- */
- next_roc = list_entry(cur_roc->list.next,
- struct ieee80211_roc_work, list);
- if (&next_roc->list != &local->roc_list &&
- next_roc->chan == new_roc->chan &&
- next_roc->sdata == new_roc->sdata &&
- !WARN_ON(next_roc->started)) {
- list_add_tail(&new_roc->list, &next_roc->dependents);
- next_roc->duration = max(next_roc->duration,
- new_roc->duration);
- next_roc->type = max(next_roc->type, new_roc->type);
- return true;
- }
-
- /* add right after cur_roc */
- list_add(&new_roc->list, &cur_roc->list);
-
+ /* add to dependents so we send the expired event properly */
+ list_add_tail(&new_roc->list, &cur_roc->dependents);
return true;
}
* In the offloaded ROC case, if it hasn't begun, add
* this new one to the dependent list to be handled
* when the master one begins. If it has begun,
- * check that there's still a minimum time left and
- * if so, start this one, transmitting the frame, but
- * add it to the list directly after this one with
- * a reduced time so we'll ask the driver to execute
- * it right after finishing the previous one, in the
- * hope that it'll also be executed right afterwards,
- * effectively extending the old one.
- * If there's no minimum time left, just add it to the
- * normal list.
- * TODO: the ROC type is ignored here, assuming that it
- * is better to immediately use the current ROC.
+ * check if it fits entirely within the existing one,
+ * in which case it will just be dependent as well.
+ * Otherwise, schedule it by itself.
*/
if (!tmp->hw_begun) {
list_add_tail(&roc->list, &tmp->dependents);
* @IEEE80211_RX_CMNTR: received on cooked monitor already
* @IEEE80211_RX_BEACON_REPORTED: This frame was already reported
* to cfg80211_report_obss_beacon().
+ * @IEEE80211_RX_REORDER_TIMER: this frame is released by the
+ * reorder buffer timeout timer, not the normal RX path
*
* These flags are used across handling multiple interfaces
* for a single frame.
enum ieee80211_rx_flags {
IEEE80211_RX_CMNTR = BIT(0),
IEEE80211_RX_BEACON_REPORTED = BIT(1),
+ IEEE80211_RX_REORDER_TIMER = BIT(2),
};
struct ieee80211_rx_data {
u8 flags;
};
-#if HZ/100 == 0
-#define IEEE80211_ROC_MIN_LEFT 1
-#else
-#define IEEE80211_ROC_MIN_LEFT (HZ/100)
-#endif
-
struct ieee80211_roc_work {
struct list_head list;
struct list_head dependents;
memcpy(sdata->vif.hw_queue, master->vif.hw_queue,
sizeof(sdata->vif.hw_queue));
sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef;
+
+ mutex_lock(&local->key_mtx);
+ sdata->crypto_tx_tailroom_needed_cnt +=
+ master->crypto_tx_tailroom_needed_cnt;
+ mutex_unlock(&local->key_mtx);
+
break;
}
case NL80211_IFTYPE_AP:
* (because if we remove a STA after ops->remove_interface()
* the driver will have removed the vif info already!)
*
- * This is relevant only in WDS mode, in all other modes we've
- * already removed all stations when disconnecting or similar,
- * so warn otherwise.
+ * In WDS mode a station must exist here and be flushed, for
+ * AP_VLANs stations may exist since there's nothing else that
+ * would have removed them, but in other modes there shouldn't
+ * be any stations.
*/
flushed = sta_info_flush(sdata);
- WARN_ON_ONCE((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
- (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1));
+ WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
+ ((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
+ (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)));
/* don't count this interface for promisc/allmulti while it is down */
if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
lockdep_assert_held(&local->key_mtx);
}
+static void
+update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta)
+{
+ struct ieee80211_sub_if_data *vlan;
+
+ if (sdata->vif.type != NL80211_IFTYPE_AP)
+ return;
+
+ mutex_lock(&sdata->local->mtx);
+
+ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+ vlan->crypto_tx_tailroom_needed_cnt += delta;
+
+ mutex_unlock(&sdata->local->mtx);
+}
+
static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
{
/*
* http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net
*/
+ update_vlan_tailroom_need_count(sdata, 1);
+
if (!sdata->crypto_tx_tailroom_needed_cnt++) {
/*
* Flush all XMIT packets currently using HW encryption or no
}
}
+static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata,
+ int delta)
+{
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta);
+
+ update_vlan_tailroom_need_count(sdata, -delta);
+ sdata->crypto_tx_tailroom_needed_cnt -= delta;
+}
+
static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
{
struct ieee80211_sub_if_data *sdata;
if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
(key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM)))
- sdata->crypto_tx_tailroom_needed_cnt--;
+ decrease_tailroom_need_count(sdata, 1);
WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV));
schedule_delayed_work(&sdata->dec_tailroom_needed_wk,
HZ/2);
} else {
- sdata->crypto_tx_tailroom_needed_cnt--;
+ decrease_tailroom_need_count(sdata, 1);
}
}
void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_key *key;
+ struct ieee80211_sub_if_data *vlan;
ASSERT_RTNL();
mutex_lock(&sdata->local->key_mtx);
- sdata->crypto_tx_tailroom_needed_cnt = 0;
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
+ sdata->crypto_tx_tailroom_pending_dec);
+
+ if (sdata->vif.type == NL80211_IFTYPE_AP) {
+ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+ WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt ||
+ vlan->crypto_tx_tailroom_pending_dec);
+ }
list_for_each_entry(key, &sdata->key_list, list) {
increment_tailroom_need_count(sdata);
mutex_unlock(&sdata->local->key_mtx);
}
+void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata)
+{
+ struct ieee80211_sub_if_data *vlan;
+
+ mutex_lock(&sdata->local->key_mtx);
+
+ sdata->crypto_tx_tailroom_needed_cnt = 0;
+
+ if (sdata->vif.type == NL80211_IFTYPE_AP) {
+ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+ vlan->crypto_tx_tailroom_needed_cnt = 0;
+ }
+
+ mutex_unlock(&sdata->local->key_mtx);
+}
+
void ieee80211_iter_keys(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
void (*iter)(struct ieee80211_hw *hw,
{
struct ieee80211_key *key, *tmp;
- sdata->crypto_tx_tailroom_needed_cnt -=
- sdata->crypto_tx_tailroom_pending_dec;
+ decrease_tailroom_need_count(sdata,
+ sdata->crypto_tx_tailroom_pending_dec);
sdata->crypto_tx_tailroom_pending_dec = 0;
ieee80211_debugfs_key_remove_mgmt_default(sdata);
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_sub_if_data *vlan;
+ struct ieee80211_sub_if_data *master;
struct ieee80211_key *key, *tmp;
LIST_HEAD(keys);
list_for_each_entry_safe(key, tmp, &keys, list)
__ieee80211_key_destroy(key, false);
- WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
- sdata->crypto_tx_tailroom_pending_dec);
+ if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+ if (sdata->bss) {
+ master = container_of(sdata->bss,
+ struct ieee80211_sub_if_data,
+ u.ap);
+
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt !=
+ master->crypto_tx_tailroom_needed_cnt);
+ }
+ } else {
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
+ sdata->crypto_tx_tailroom_pending_dec);
+ }
+
if (sdata->vif.type == NL80211_IFTYPE_AP) {
list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt ||
*/
mutex_lock(&sdata->local->key_mtx);
- sdata->crypto_tx_tailroom_needed_cnt -=
- sdata->crypto_tx_tailroom_pending_dec;
+ decrease_tailroom_need_count(sdata,
+ sdata->crypto_tx_tailroom_pending_dec);
sdata->crypto_tx_tailroom_pending_dec = 0;
mutex_unlock(&sdata->local->key_mtx);
}
void ieee80211_free_sta_keys(struct ieee80211_local *local,
struct sta_info *sta);
void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata);
+void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata);
#define key_mtx_dereference(local, ref) \
rcu_dereference_protected(ref, lockdep_is_held(&((local)->key_mtx)))
/* deliver to local stack */
skb->protocol = eth_type_trans(skb, dev);
memset(skb->cb, 0, sizeof(skb->cb));
- if (rx->local->napi)
+ if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) &&
+ rx->local->napi)
napi_gro_receive(rx->local->napi, skb);
else
netif_receive_skb(skb);
/* This is OK -- must be QoS data frame */
.security_idx = tid,
.seqno_idx = tid,
- .flags = 0,
+ .flags = IEEE80211_RX_REORDER_TIMER,
};
struct tid_ampdu_rx *tid_agg_rx;
static const struct rhashtable_params sta_rht_params = {
.nelem_hint = 3, /* start small */
+ .automatic_shrinking = true,
.head_offset = offsetof(struct sta_info, hash_node),
.key_offset = offsetof(struct sta_info, sta.addr),
.key_len = ETH_ALEN,
const u8 *addr)
{
struct ieee80211_local *local = sdata->local;
+ struct sta_info *sta;
+ struct rhash_head *tmp;
+ const struct bucket_table *tbl;
+
+ rcu_read_lock();
+ tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
- return rhashtable_lookup_fast(&local->sta_hash, addr, sta_rht_params);
+ for_each_sta_info(local, tbl, addr, sta, tmp) {
+ if (sta->sdata == sdata) {
+ rcu_read_unlock();
+ /* this is safe as the caller must already hold
+ * another rcu read section or the mutex
+ */
+ return sta;
+ }
+ }
+ rcu_read_unlock();
+ return NULL;
}
/*
mutex_unlock(&local->sta_mtx);
/* add back keys */
+ list_for_each_entry(sdata, &local->interfaces, list)
+ ieee80211_reset_crypto_tx_tailroom(sdata);
+
list_for_each_entry(sdata, &local->interfaces, list)
if (ieee80211_sdata_running(sdata))
ieee80211_enable_keys(sdata);
hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED);
- if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN ||
- skb_headroom(skb) < IEEE80211_WEP_IV_LEN))
+ if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN))
return NULL;
hdrlen = ieee80211_hdrlen(hdr->frame_control);
size_t len;
u8 rc4key[3 + WLAN_KEY_LEN_WEP104];
+ if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN))
+ return -1;
+
iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx);
if (!iv)
return -1;
static struct net_device *
ieee802154_add_iface_deprecated(struct wpan_phy *wpan_phy,
- const char *name, int type)
+ const char *name,
+ unsigned char name_assign_type, int type)
{
struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
struct net_device *dev;
rtnl_lock();
- dev = ieee802154_if_add(local, name, type,
+ dev = ieee802154_if_add(local, name, name_assign_type, type,
cpu_to_le64(0x0000000000000000ULL));
rtnl_unlock();
static int
ieee802154_add_iface(struct wpan_phy *phy, const char *name,
+ unsigned char name_assign_type,
enum nl802154_iftype type, __le64 extended_addr)
{
struct ieee802154_local *local = wpan_phy_priv(phy);
struct net_device *err;
- err = ieee802154_if_add(local, name, type, extended_addr);
+ err = ieee802154_if_add(local, name, name_assign_type, type,
+ extended_addr);
return PTR_ERR_OR_ZERO(err);
}
void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata);
struct net_device *
ieee802154_if_add(struct ieee802154_local *local, const char *name,
- enum nl802154_iftype type, __le64 extended_addr);
+ unsigned char name_assign_type, enum nl802154_iftype type,
+ __le64 extended_addr);
void ieee802154_remove_interfaces(struct ieee802154_local *local);
#endif /* __IEEE802154_I_H */
struct net_device *
ieee802154_if_add(struct ieee802154_local *local, const char *name,
- enum nl802154_iftype type, __le64 extended_addr)
+ unsigned char name_assign_type, enum nl802154_iftype type,
+ __le64 extended_addr)
{
struct net_device *ndev = NULL;
struct ieee802154_sub_if_data *sdata = NULL;
ASSERT_RTNL();
ndev = alloc_netdev(sizeof(*sdata) + local->hw.vif_data_size, name,
- NET_NAME_UNKNOWN, ieee802154_if_setup);
+ name_assign_type, ieee802154_if_setup);
if (!ndev)
return ERR_PTR(-ENOMEM);
for (i = 0; i < ARRAY_SIZE(key->tfm); i++) {
key->tfm[i] = crypto_alloc_aead("ccm(aes)", 0,
CRYPTO_ALG_ASYNC);
- if (!key->tfm[i])
+ if (IS_ERR(key->tfm[i]))
goto err_tfm;
if (crypto_aead_setkey(key->tfm[i], template->key,
IEEE802154_LLSEC_KEY_SIZE))
}
key->tfm0 = crypto_alloc_blkcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
- if (!key->tfm0)
+ if (IS_ERR(key->tfm0))
goto err_tfm;
if (crypto_blkcipher_setkey(key->tfm0, template->key,
rtnl_lock();
- dev = ieee802154_if_add(local, "wpan%d", NL802154_IFTYPE_NODE,
+ dev = ieee802154_if_add(local, "wpan%d", NET_NAME_ENUM,
+ NL802154_IFTYPE_NODE,
cpu_to_le64(0x0000000000000000ULL));
if (IS_ERR(dev)) {
rtnl_unlock();
rc = PTR_ERR(dev);
- goto out_wq;
+ goto out_phy;
}
rtnl_unlock();
return 0;
+out_phy:
+ wpan_phy_unregister(local->phy);
out_wq:
destroy_workqueue(local->workqueue);
out:
RCU_INIT_POINTER(dev->mpls_ptr, NULL);
- kfree(mdev);
+ kfree_rcu(mdev, rcu);
}
static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
case NETDEV_UNREGISTER:
mpls_ifdown(dev);
break;
+ case NETDEV_CHANGENAME:
+ mdev = mpls_dev_get(dev);
+ if (mdev) {
+ int err;
+
+ mpls_dev_sysctl_unregister(mdev);
+ err = mpls_dev_sysctl_register(dev, mdev);
+ if (err)
+ return notifier_from_errno(err);
+ }
+ break;
}
return NOTIFY_OK;
}
return -EINVAL;
switch (dec.label) {
- case LABEL_IMPLICIT_NULL:
+ case MPLS_LABEL_IMPLNULL:
/* RFC3032: This is a label that an LSR may
* assign and distribute, but which never
* actually appears in the encapsulation.
}
/* In case the predefined labels need to be populated */
- if (limit > LABEL_IPV4_EXPLICIT_NULL) {
+ if (limit > MPLS_LABEL_IPV4NULL) {
struct net_device *lo = net->loopback_dev;
rt0 = mpls_rt_alloc(lo->addr_len);
if (!rt0)
rt0->rt_via_table = NEIGH_LINK_TABLE;
memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len);
}
- if (limit > LABEL_IPV6_EXPLICIT_NULL) {
+ if (limit > MPLS_LABEL_IPV6NULL) {
struct net_device *lo = net->loopback_dev;
rt2 = mpls_rt_alloc(lo->addr_len);
if (!rt2)
memcpy(labels, old, cp_size);
/* If needed set the predefined labels */
- if ((old_limit <= LABEL_IPV6_EXPLICIT_NULL) &&
- (limit > LABEL_IPV6_EXPLICIT_NULL)) {
- RCU_INIT_POINTER(labels[LABEL_IPV6_EXPLICIT_NULL], rt2);
+ if ((old_limit <= MPLS_LABEL_IPV6NULL) &&
+ (limit > MPLS_LABEL_IPV6NULL)) {
+ RCU_INIT_POINTER(labels[MPLS_LABEL_IPV6NULL], rt2);
rt2 = NULL;
}
- if ((old_limit <= LABEL_IPV4_EXPLICIT_NULL) &&
- (limit > LABEL_IPV4_EXPLICIT_NULL)) {
- RCU_INIT_POINTER(labels[LABEL_IPV4_EXPLICIT_NULL], rt0);
+ if ((old_limit <= MPLS_LABEL_IPV4NULL) &&
+ (limit > MPLS_LABEL_IPV4NULL)) {
+ RCU_INIT_POINTER(labels[MPLS_LABEL_IPV4NULL], rt0);
rt0 = NULL;
}
#ifndef MPLS_INTERNAL_H
#define MPLS_INTERNAL_H
-#define LABEL_IPV4_EXPLICIT_NULL 0 /* RFC3032 */
-#define LABEL_ROUTER_ALERT_LABEL 1 /* RFC3032 */
-#define LABEL_IPV6_EXPLICIT_NULL 2 /* RFC3032 */
-#define LABEL_IMPLICIT_NULL 3 /* RFC3032 */
-#define LABEL_ENTROPY_INDICATOR 7 /* RFC6790 */
-#define LABEL_GAL 13 /* RFC5586 */
-#define LABEL_OAM_ALERT 14 /* RFC3429 */
-#define LABEL_EXTENSION 15 /* RFC7274 */
-
-
struct mpls_shim_hdr {
__be32 label_stack_entry;
};
int input_enabled;
struct ctl_table_header *sysctl;
+ struct rcu_head rcu;
};
struct sk_buff;
depends on NETFILTER_XTABLES
depends on NETFILTER_ADVANCED
depends on (IPV6 || IPV6=n)
+ depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n)
depends on IP_NF_MANGLE
select NF_DEFRAG_IPV4
select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
depends on NETFILTER_ADVANCED
depends on !NF_CONNTRACK || NF_CONNTRACK
depends on (IPV6 || IPV6=n)
+ depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n)
select NF_DEFRAG_IPV4
select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
help
cancel_work_sync(&ipvs->defense_work.work);
unregister_net_sysctl_table(ipvs->sysctl_hdr);
ip_vs_stop_estimator(net, &ipvs->tot_stats);
+
+ if (!net_eq(net, &init_net))
+ kfree(ipvs->sysctl_tbl);
}
#else
* sES -> sES :-)
* sFW -> sCW Normal close request answered by ACK.
* sCW -> sCW
- * sLA -> sTW Last ACK detected.
+ * sLA -> sTW Last ACK detected (RFC5961 challenged)
* sTW -> sTW Retransmitted last ACK. Remain in the same state.
* sCL -> sCL
*/
* sES -> sES :-)
* sFW -> sCW Normal close request answered by ACK.
* sCW -> sCW
- * sLA -> sTW Last ACK detected.
+ * sLA -> sTW Last ACK detected (RFC5961 challenged)
* sTW -> sTW Retransmitted last ACK.
* sCL -> sCL
*/
1 : ct->proto.tcp.last_win;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale =
ct->proto.tcp.last_wscale;
+ ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
ct->proto.tcp.last_flags;
memset(&ct->proto.tcp.seen[dir], 0,
* may be in sync but we are not. In that case, we annotate
* the TCP options and let the packet go through. If it is a
* valid SYN packet, the server will reply with a SYN/ACK, and
- * then we'll get in sync. Otherwise, the server ignores it. */
+ * then we'll get in sync. Otherwise, the server potentially
+ * responds with a challenge ACK if implementing RFC5961.
+ */
if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) {
struct ip_ct_tcp_state seen = {};
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_SACK_PERM;
}
+ /* Mark the potential for RFC5961 challenge ACK,
+ * this pose a special problem for LAST_ACK state
+ * as ACK is intrepretated as ACKing last FIN.
+ */
+ if (old_state == TCP_CONNTRACK_LAST_ACK)
+ ct->proto.tcp.last_flags |=
+ IP_CT_EXP_CHALLENGE_ACK;
}
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid state ");
return -NF_ACCEPT;
+ case TCP_CONNTRACK_TIME_WAIT:
+ /* RFC5961 compliance cause stack to send "challenge-ACK"
+ * e.g. in response to spurious SYNs. Conntrack MUST
+ * not believe this ACK is acking last FIN.
+ */
+ if (old_state == TCP_CONNTRACK_LAST_ACK &&
+ index == TCP_ACK_SET &&
+ ct->proto.tcp.last_dir != dir &&
+ ct->proto.tcp.last_index == TCP_SYN_SET &&
+ (ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) {
+ /* Detected RFC5961 challenge ACK */
+ ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
+ spin_unlock_bh(&ct->lock);
+ if (LOG_INVALID(net, IPPROTO_TCP))
+ nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
+ "nf_ct_tcp: challenge-ACK ignored ");
+ return NF_ACCEPT; /* Don't change state */
+ }
+ break;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
*/
void nft_data_uninit(const struct nft_data *data, enum nft_data_types type)
{
- switch (type) {
- case NFT_DATA_VALUE:
+ if (type < NFT_DATA_VERDICT)
return;
+ switch (type) {
case NFT_DATA_VERDICT:
return nft_verdict_uninit(data);
default:
static int __init nfnetlink_log_init(void)
{
- int status = -ENOMEM;
+ int status;
+
+ status = register_pernet_subsys(&nfnl_log_net_ops);
+ if (status < 0) {
+ pr_err("failed to register pernet ops\n");
+ goto out;
+ }
netlink_register_notifier(&nfulnl_rtnl_notifier);
status = nfnetlink_subsys_register(&nfulnl_subsys);
goto cleanup_subsys;
}
- status = register_pernet_subsys(&nfnl_log_net_ops);
- if (status < 0) {
- pr_err("failed to register pernet ops\n");
- goto cleanup_logger;
- }
return status;
-cleanup_logger:
- nf_log_unregister(&nfulnl_logger);
cleanup_subsys:
nfnetlink_subsys_unregister(&nfulnl_subsys);
cleanup_netlink_notifier:
netlink_unregister_notifier(&nfulnl_rtnl_notifier);
+ unregister_pernet_subsys(&nfnl_log_net_ops);
+out:
return status;
}
static void __exit nfnetlink_log_fini(void)
{
- unregister_pernet_subsys(&nfnl_log_net_ops);
nf_log_unregister(&nfulnl_logger);
nfnetlink_subsys_unregister(&nfulnl_subsys);
netlink_unregister_notifier(&nfulnl_rtnl_notifier);
+ unregister_pernet_subsys(&nfnl_log_net_ops);
}
MODULE_DESCRIPTION("netfilter userspace logging");
static int __init nfnetlink_queue_init(void)
{
- int status = -ENOMEM;
+ int status;
+
+ status = register_pernet_subsys(&nfnl_queue_net_ops);
+ if (status < 0) {
+ pr_err("nf_queue: failed to register pernet ops\n");
+ goto out;
+ }
netlink_register_notifier(&nfqnl_rtnl_notifier);
status = nfnetlink_subsys_register(&nfqnl_subsys);
goto cleanup_netlink_notifier;
}
- status = register_pernet_subsys(&nfnl_queue_net_ops);
- if (status < 0) {
- pr_err("nf_queue: failed to register pernet ops\n");
- goto cleanup_subsys;
- }
register_netdevice_notifier(&nfqnl_dev_notifier);
nf_register_queue_handler(&nfqh);
return status;
-cleanup_subsys:
- nfnetlink_subsys_unregister(&nfqnl_subsys);
cleanup_netlink_notifier:
netlink_unregister_notifier(&nfqnl_rtnl_notifier);
+out:
return status;
}
{
nf_unregister_queue_handler();
unregister_netdevice_notifier(&nfqnl_dev_notifier);
- unregister_pernet_subsys(&nfnl_queue_net_ops);
nfnetlink_subsys_unregister(&nfqnl_subsys);
netlink_unregister_notifier(&nfqnl_rtnl_notifier);
+ unregister_pernet_subsys(&nfnl_queue_net_ops);
rcu_barrier(); /* Wait for completion of call_rcu()'s */
}
return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
}
-struct netlink_table *nl_table;
+struct netlink_table *nl_table __read_mostly;
EXPORT_SYMBOL_GPL(nl_table);
static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
if (err) {
if (err == -EEXIST)
err = -EADDRINUSE;
+ nlk_sk(sk)->portid = 0;
sock_put(sk);
}
.key_len = netlink_compare_arg_len,
.obj_hashfn = netlink_hash,
.obj_cmpfn = netlink_compare,
- .max_size = 65536,
.automatic_shrinking = true,
};
if (err)
goto error_master_upper_dev_unlink;
+ dev_disable_lro(netdev_vport->dev);
dev_set_promiscuity(netdev_vport->dev, 1);
netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH;
rtnl_unlock();
tlen = dev->needed_tailroom;
skb = sock_alloc_send_skb(&po->sk,
hlen + tlen + sizeof(struct sockaddr_ll),
- 0, &err);
+ !need_wait, &err);
- if (unlikely(skb == NULL))
+ if (unlikely(skb == NULL)) {
+ /* we assume the socket was initially writeable ... */
+ if (likely(len_sum > 0))
+ err = len_sum;
goto out_status;
-
+ }
tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
addr, hlen);
if (tp_len > dev->mtu + dev->hard_header_len) {
struct rds_transport *loop_trans;
unsigned long flags;
int ret;
+ struct rds_transport *otrans = trans;
+ if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP)
+ goto new_conn;
rcu_read_lock();
conn = rds_conn_lookup(head, laddr, faddr, trans);
if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport &&
if (conn)
goto out;
+new_conn:
conn = kmem_cache_zalloc(rds_conn_slab, gfp);
if (!conn) {
conn = ERR_PTR(-ENOMEM);
/* Creating normal conn */
struct rds_connection *found;
- found = rds_conn_lookup(head, laddr, faddr, trans);
+ if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP)
+ found = NULL;
+ else
+ found = rds_conn_lookup(head, laddr, faddr, trans);
if (found) {
trans->conn_free(conn->c_transport_data);
kmem_cache_free(rds_conn_slab, conn);
conn = found;
} else {
- hlist_add_head_rcu(&conn->c_hash_node, head);
+ if ((is_outgoing && otrans->t_type == RDS_TRANS_TCP) ||
+ (otrans->t_type != RDS_TRANS_TCP)) {
+ /* Only the active side should be added to
+ * reconnect list for TCP.
+ */
+ hlist_add_head_rcu(&conn->c_hash_node, head);
+ }
rds_cong_add_conn(conn);
rds_conn_count++;
}
/* If the peer gave us the last packet it saw, process this as if
* we had received a regular ACK. */
- if (dp && dp->dp_ack_seq)
- rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL);
+ if (dp) {
+ /* dp structure start is not guaranteed to be 8 bytes aligned.
+ * Since dp_ack_seq is 64-bit extended load operations can be
+ * used so go through get_unaligned to avoid unaligned errors.
+ */
+ __be64 dp_ack_seq = get_unaligned(&dp->dp_ack_seq);
+
+ if (dp_ack_seq)
+ rds_send_drop_acked(conn, be64_to_cpu(dp_ack_seq),
+ NULL);
+ }
rds_connect_complete(conn);
}
case TCP_ESTABLISHED:
rds_connect_complete(conn);
break;
+ case TCP_CLOSE_WAIT:
case TCP_CLOSE:
rds_conn_drop(conn);
default:
static DECLARE_WORK(rds_tcp_listen_work, rds_tcp_accept_worker);
static struct socket *rds_tcp_listen_sock;
+static int rds_tcp_keepalive(struct socket *sock)
+{
+ /* values below based on xs_udp_default_timeout */
+ int keepidle = 5; /* send a probe 'keepidle' secs after last data */
+ int keepcnt = 5; /* number of unack'ed probes before declaring dead */
+ int keepalive = 1;
+ int ret = 0;
+
+ ret = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
+ (char *)&keepalive, sizeof(keepalive));
+ if (ret < 0)
+ goto bail;
+
+ ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPCNT,
+ (char *)&keepcnt, sizeof(keepcnt));
+ if (ret < 0)
+ goto bail;
+
+ ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPIDLE,
+ (char *)&keepidle, sizeof(keepidle));
+ if (ret < 0)
+ goto bail;
+
+ /* KEEPINTVL is the interval between successive probes. We follow
+ * the model in xs_tcp_finish_connecting() and re-use keepidle.
+ */
+ ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPINTVL,
+ (char *)&keepidle, sizeof(keepidle));
+bail:
+ return ret;
+}
+
static int rds_tcp_accept_one(struct socket *sock)
{
struct socket *new_sock = NULL;
struct rds_connection *conn;
int ret;
struct inet_sock *inet;
+ struct rds_tcp_connection *rs_tcp;
ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type,
sock->sk->sk_protocol, &new_sock);
if (ret < 0)
goto out;
+ ret = rds_tcp_keepalive(new_sock);
+ if (ret < 0)
+ goto out;
+
rds_tcp_tune(new_sock);
inet = inet_sk(new_sock->sk);
ret = PTR_ERR(conn);
goto out;
}
+ /* An incoming SYN request came in, and TCP just accepted it.
+ * We always create a new conn for listen side of TCP, and do not
+ * add it to the c_hash_list.
+ *
+ * If the client reboots, this conn will need to be cleaned up.
+ * rds_tcp_state_change() will do that cleanup
+ */
+ rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data;
+ WARN_ON(!rs_tcp || rs_tcp->t_sock);
/*
* see the comment above rds_queue_delayed_reconnect()
struct tcf_proto_ops *t;
int rc = -ENOENT;
+ /* Wait for outstanding call_rcu()s, if any, from a
+ * tcf_proto_ops's destroy() handler.
+ */
+ rcu_barrier();
+
write_lock(&cls_mod_lock);
list_for_each_entry(t, &tcf_proto_base, head) {
if (t == ops) {
case RTM_DELTFILTER:
err = tp->ops->delete(tp, fh);
if (err == 0) {
- tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
- if (tcf_destroy(tp, false)) {
- struct tcf_proto *next = rtnl_dereference(tp->next);
+ struct tcf_proto *next = rtnl_dereference(tp->next);
+ tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
+ if (tcf_destroy(tp, false))
RCU_INIT_POINTER(*back, next);
- }
}
goto errout;
case RTM_GETTFILTER:
if (dev->flags & IFF_UP)
dev_deactivate(dev);
- if (new && new->ops->attach) {
- new->ops->attach(new);
- num_q = 0;
- }
+ if (new && new->ops->attach)
+ goto skip;
for (i = 0; i < num_q; i++) {
struct netdev_queue *dev_queue = dev_ingress_queue(dev);
qdisc_destroy(old);
}
+skip:
if (!ingress) {
notify_and_destroy(net, skb, n, classid,
dev->qdisc, new);
if (new && !new->ops->attach)
atomic_inc(&new->refcnt);
dev->qdisc = new ? : &noop_qdisc;
+
+ if (new && new->ops->attach)
+ new->ops->attach(new);
} else {
notify_and_destroy(net, skb, n, classid, old, new);
}
#ifdef CONFIG_PROC_FS
static int psched_show(struct seq_file *seq, void *v)
{
- struct timespec ts;
-
- hrtimer_get_res(CLOCK_MONOTONIC, &ts);
seq_printf(seq, "%08x %08x %08x %08x\n",
(u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1),
1000000,
- (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts)));
+ (u32)NSEC_PER_SEC / hrtimer_resolution);
return 0;
}
sch->limit = DEFAULT_CODEL_LIMIT;
- codel_params_init(&q->params);
+ codel_params_init(&q->params, sch);
codel_vars_init(&q->vars);
codel_stats_init(&q->stats);
q->perturbation = prandom_u32();
INIT_LIST_HEAD(&q->new_flows);
INIT_LIST_HEAD(&q->old_flows);
- codel_params_init(&q->cparams);
+ codel_params_init(&q->cparams, sch);
codel_stats_init(&q->cstats);
q->cparams.ecn = true;
break;
}
- if (q->backlog + qdisc_pkt_len(skb) <= q->limit) {
+ if (gred_backlog(t, q, sch) + qdisc_pkt_len(skb) <= q->limit) {
q->backlog += qdisc_pkt_len(skb);
return qdisc_enqueue_tail(skb, sch);
}
opt.limit = q->limit;
opt.DP = q->DP;
- opt.backlog = q->backlog;
+ opt.backlog = gred_backlog(table, q, sch);
opt.prio = q->prio;
opt.qth_min = q->parms.qth_min >> q->parms.Wlog;
opt.qth_max = q->parms.qth_max >> q->parms.Wlog;
}
-/* Public interface to creat the association shared key.
+/* Public interface to create the association shared key.
* See code above for the algorithm.
*/
int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
{
struct sctp_auth_bytes *secret;
struct sctp_shared_key *ep_key;
+ struct sctp_chunk *chunk;
/* If we don't support AUTH, or peer is not capable
* we don't need to do anything.
sctp_auth_key_put(asoc->asoc_shared_key);
asoc->asoc_shared_key = secret;
+ /* Update send queue in case any chunk already in there now
+ * needs authenticating
+ */
+ list_for_each_entry(chunk, &asoc->outqueue.out_chunk_list, list) {
+ if (sctp_auth_send_cid(chunk->chunk_hdr->type, asoc))
+ chunk->auth = 1;
+ }
+
return 0;
}
{
u32 value_follows;
int err;
+ struct page *scratch;
+
+ scratch = alloc_page(GFP_KERNEL);
+ if (!scratch)
+ return -ENOMEM;
+ xdr_set_scratch_buffer(xdr, page_address(scratch), PAGE_SIZE);
/* res->status */
err = gssx_dec_status(xdr, &res->status);
if (err)
- return err;
+ goto out_free;
/* res->context_handle */
err = gssx_dec_bool(xdr, &value_follows);
if (err)
- return err;
+ goto out_free;
if (value_follows) {
err = gssx_dec_ctx(xdr, res->context_handle);
if (err)
- return err;
+ goto out_free;
} else {
res->context_handle = NULL;
}
/* res->output_token */
err = gssx_dec_bool(xdr, &value_follows);
if (err)
- return err;
+ goto out_free;
if (value_follows) {
err = gssx_dec_buffer(xdr, res->output_token);
if (err)
- return err;
+ goto out_free;
} else {
res->output_token = NULL;
}
/* res->delegated_cred_handle */
err = gssx_dec_bool(xdr, &value_follows);
if (err)
- return err;
+ goto out_free;
if (value_follows) {
/* we do not support upcall servers sending this data. */
- return -EINVAL;
+ err = -EINVAL;
+ goto out_free;
}
/* res->options */
err = gssx_dec_option_array(xdr, &res->options);
+out_free:
+ __free_page(scratch);
return err;
}
fi, tos, type, nlflags,
tb_id);
if (!err)
- fi->fib_flags |= RTNH_F_EXTERNAL;
+ fi->fib_flags |= RTNH_F_OFFLOAD;
}
return err;
const struct swdev_ops *ops;
int err = 0;
- if (!(fi->fib_flags & RTNH_F_EXTERNAL))
+ if (!(fi->fib_flags & RTNH_F_OFFLOAD))
return 0;
dev = netdev_switch_get_dev_by_nhs(fi);
err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len,
fi, tos, type, tb_id);
if (!err)
- fi->fib_flags &= ~RTNH_F_EXTERNAL;
+ fi->fib_flags &= ~RTNH_F_OFFLOAD;
}
return err;
peer_node = tsk_peer_node(tsk);
if (tsk->probing_state == TIPC_CONN_PROBING) {
- /* Previous probe not answered -> self abort */
- skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
- TIPC_CONN_MSG, SHORT_H_SIZE, 0,
- own_node, peer_node, tsk->portid,
- peer_port, TIPC_ERR_NO_PORT);
+ if (!sock_owned_by_user(sk)) {
+ sk->sk_socket->state = SS_DISCONNECTING;
+ tsk->connected = 0;
+ tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
+ tsk_peer_port(tsk));
+ sk->sk_state_change(sk);
+ } else {
+ /* Try again later */
+ sk_reset_timer(sk, &sk->sk_timer, (HZ / 20));
+ }
+
} else {
skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE,
INT_H_SIZE, 0, peer_node, own_node,
unix_state_unlock(sk);
timeo = freezable_schedule_timeout(timeo);
unix_state_lock(sk);
+
+ if (sock_flag(sk, SOCK_DEAD))
+ break;
+
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
}
struct sk_buff *skb, *last;
unix_state_lock(sk);
+ if (sock_flag(sk, SOCK_DEAD)) {
+ err = -ECONNRESET;
+ goto unlock;
+ }
last = skb = skb_peek(&sk->sk_receive_queue);
again:
if (skb == NULL) {
memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN);
wdev_unlock(wdev);
+ memset(&sinfo, 0, sizeof(sinfo));
+
if (rdev_get_station(rdev, dev, bssid, &sinfo))
return NULL;
#include <net/dst.h>
#include <net/ip.h>
#include <net/xfrm.h>
+#include <net/ip_tunnels.h>
+#include <net/ip6_tunnel.h>
static struct kmem_cache *secpath_cachep __read_mostly;
struct xfrm_state *x = NULL;
xfrm_address_t *daddr;
struct xfrm_mode *inner_mode;
+ u32 mark = skb->mark;
unsigned int family;
int decaps = 0;
int async = 0;
XFRM_SPI_SKB_CB(skb)->daddroff);
family = XFRM_SPI_SKB_CB(skb)->family;
+ /* if tunnel is present override skb->mark value with tunnel i_key */
+ if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) {
+ switch (family) {
+ case AF_INET:
+ mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key);
+ break;
+ case AF_INET6:
+ mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key);
+ break;
+ }
+ }
+
/* Allocate new secpath or COW existing one. */
if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
struct sec_path *sp;
goto drop;
}
- x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family);
+ x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family);
if (x == NULL) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
xfrm_audit_state_notfound(skb, family, spi, seq);
if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq;
+ XFRM_SKB_CB(skb)->seq.output.hi = 0;
if (unlikely(x->replay.oseq == 0)) {
x->replay.oseq--;
xfrm_audit_state_replay_overflow(x, skb);
if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq;
+ XFRM_SKB_CB(skb)->seq.output.hi = 0;
if (unlikely(replay_esn->oseq == 0)) {
replay_esn->oseq--;
xfrm_audit_state_replay_overflow(x, skb);
x->id.spi != spi)
continue;
- spin_unlock_bh(&net->xfrm.xfrm_state_lock);
xfrm_state_hold(x);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
}
# check for global initialisers.
- if ($line =~ /^\+(\s*$Type\s*$Ident\s*(?:\s+$Modifier))*\s*=\s*(0|NULL|false)\s*;/) {
+ if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*(?:0|NULL|false)\s*;/) {
if (ERROR("GLOBAL_INITIALISERS",
"do not initialise globals to 0 or NULL\n" .
$herecurr) &&
$fix) {
- $fixed[$fixlinenr] =~ s/($Type\s*$Ident\s*(?:\s+$Modifier))*\s*=\s*(0|NULL|false)\s*;/$1;/;
+ $fixed[$fixlinenr] =~ s/(^.$Type\s*$Ident(?:\s+$Modifier)*)\s*=\s*(0|NULL|false)\s*;/$1;/;
}
}
# check for static initialisers.
)
}
-(ignore_list && syscall_list $(dirname $0)/../arch/x86/syscalls/syscall_32.tbl) | \
+(ignore_list && syscall_list $(dirname $0)/../arch/x86/entry/syscalls/syscall_32.tbl) | \
$* -E -x c - > /dev/null
" " if utils.get_long_type().sizeof == 8 else ""))
for module in module_list():
- ref = 0
- module_refptr = module['refptr']
- for cpu in cpus.cpu_list("cpu_possible_mask"):
- refptr = cpus.per_cpu(module_refptr, cpu)
- ref += refptr['incs']
- ref -= refptr['decs']
-
gdb.write("{address} {name:<19} {size:>8} {ref}".format(
address=str(module['module_core']).split()[0],
name=module['name'].string(),
size=str(module['core_size']),
- ref=str(ref)))
+ ref=str(module['refcnt']['counter'])))
source_list = module['source_list']
t = self._module_use_type.get_type().pointer()
return 0;
}
-static int cap_inode_follow_link(struct dentry *dentry,
- struct nameidata *nameidata)
+static int cap_inode_follow_link(struct dentry *dentry, struct inode *inode,
+ bool rcu)
{
return 0;
}
return security_ops->inode_readlink(dentry);
}
-int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd)
+int security_inode_follow_link(struct dentry *dentry, struct inode *inode,
+ bool rcu)
{
- if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+ if (unlikely(IS_PRIVATE(inode)))
return 0;
- return security_ops->inode_follow_link(dentry, nd);
+ return security_ops->inode_follow_link(dentry, inode, rcu);
}
int security_inode_permission(struct inode *inode, int mask)
rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd);
- rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata);
+ rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata, 0);
+ if (rc2)
+ return rc2;
+ return rc;
+}
+
+int avc_has_perm_flags(u32 ssid, u32 tsid, u16 tclass,
+ u32 requested, struct common_audit_data *auditdata,
+ int flags)
+{
+ struct av_decision avd;
+ int rc, rc2;
+
+ rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd);
+
+ rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc,
+ auditdata, flags);
if (rc2)
return rc2;
return rc;
rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd);
if (audit == SECURITY_CAP_AUDIT) {
- int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad);
+ int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad, 0);
if (rc2)
return rc2;
}
return dentry_has_perm(cred, dentry, FILE__READ);
}
-static int selinux_inode_follow_link(struct dentry *dentry, struct nameidata *nameidata)
+static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode,
+ bool rcu)
{
const struct cred *cred = current_cred();
+ struct common_audit_data ad;
+ struct inode_security_struct *isec;
+ u32 sid;
- return dentry_has_perm(cred, dentry, FILE__READ);
+ validate_creds(cred);
+
+ ad.type = LSM_AUDIT_DATA_DENTRY;
+ ad.u.dentry = dentry;
+ sid = cred_sid(cred);
+ isec = inode->i_security;
+
+ return avc_has_perm_flags(sid, isec->sid, isec->sclass, FILE__READ, &ad,
+ rcu ? MAY_NOT_BLOCK : 0);
}
static noinline int audit_inode_permission(struct inode *inode,
u16 tclass, u32 requested,
struct av_decision *avd,
int result,
- struct common_audit_data *a)
+ struct common_audit_data *a,
+ int flags)
{
u32 audited, denied;
audited = avc_audit_required(requested, avd, result, 0, &denied);
return 0;
return slow_avc_audit(ssid, tsid, tclass,
requested, audited, denied, result,
- a, 0);
+ a, flags);
}
#define AVC_STRICT 1 /* Ignore permissive mode. */
int avc_has_perm(u32 ssid, u32 tsid,
u16 tclass, u32 requested,
struct common_audit_data *auditdata);
+int avc_has_perm_flags(u32 ssid, u32 tsid,
+ u16 tclass, u32 requested,
+ struct common_audit_data *auditdata,
+ int flags);
u32 avc_policy_seqno(void);
{
struct ac97c_platform_data *pdata;
struct device_node *node = dev->of_node;
- const struct of_device_id *match;
if (!node) {
dev_err(dev, "Device does not have associated DT data\n");
static int __init snd_hrtimer_init(void)
{
struct snd_timer *timer;
- struct timespec tp;
int err;
- hrtimer_get_res(CLOCK_MONOTONIC, &tp);
- if (tp.tv_sec > 0 || !tp.tv_nsec) {
- pr_err("snd-hrtimer: Invalid resolution %u.%09u",
- (unsigned)tp.tv_sec, (unsigned)tp.tv_nsec);
- return -EINVAL;
- }
- resolution = tp.tv_nsec;
+ resolution = hrtimer_resolution;
/* Create a new timer and set up the fields */
err = snd_timer_global_new("hrtimer", SNDRV_TIMER_GLOBAL_HRTIMER,
if (delta > new_hw_ptr) {
/* check for double acknowledged interrupts */
hdelta = curr_jiffies - runtime->hw_ptr_jiffies;
- if (hdelta > runtime->hw_ptr_buffer_jiffies/2) {
+ if (hdelta > runtime->hw_ptr_buffer_jiffies/2 + 1) {
hw_base += runtime->buffer_size;
if (hw_base >= runtime->boundary) {
hw_base = 0;
static int snd_pcsp_create(struct snd_card *card)
{
static struct snd_device_ops ops = { };
- struct timespec tp;
- int err;
- int div, min_div, order;
-
- hrtimer_get_res(CLOCK_MONOTONIC, &tp);
+ unsigned int resolution = hrtimer_resolution;
+ int err, div, min_div, order;
if (!nopcm) {
- if (tp.tv_sec || tp.tv_nsec > PCSP_MAX_PERIOD_NS) {
+ if (resolution > PCSP_MAX_PERIOD_NS) {
printk(KERN_ERR "PCSP: Timer resolution is not sufficient "
- "(%linS)\n", tp.tv_nsec);
+ "(%unS)\n", resolution);
printk(KERN_ERR "PCSP: Make sure you have HPET and ACPI "
"enabled.\n");
printk(KERN_ERR "PCSP: Turned into nopcm mode.\n");
}
}
- if (loops_per_jiffy >= PCSP_MIN_LPJ && tp.tv_nsec <= PCSP_MIN_PERIOD_NS)
+ if (loops_per_jiffy >= PCSP_MIN_LPJ && resolution <= PCSP_MIN_PERIOD_NS)
min_div = MIN_DIV;
else
min_div = MAX_DIV;
#if PCSP_DEBUG
- printk(KERN_DEBUG "PCSP: lpj=%li, min_div=%i, res=%li\n",
- loops_per_jiffy, min_div, tp.tv_nsec);
+ printk(KERN_DEBUG "PCSP: lpj=%li, min_div=%i, res=%u\n",
+ loops_per_jiffy, min_div, resolution);
#endif
div = MAX_DIV / min_div;
return hda_reg_read_stereo_amp(codec, reg, val);
if (verb == AC_VERB_GET_PROC_COEF)
return hda_reg_read_coef(codec, reg, val);
+ if ((verb & 0x700) == AC_VERB_SET_AMP_GAIN_MUTE)
+ reg &= ~AC_AMP_FAKE_MUTE;
+
err = snd_hdac_exec_verb(codec, reg, 0, val);
if (err < 0)
return err;
unsigned int verb;
int i, bytes, err;
+ if (codec->caps_overwriting)
+ return 0;
+
reg &= ~0x00080000U; /* drop GET bit */
reg |= (codec->addr << 28);
verb = get_verb(reg);
switch (verb & 0xf00) {
case AC_VERB_SET_AMP_GAIN_MUTE:
+ if ((reg & AC_AMP_FAKE_MUTE) && (val & AC_AMP_MUTE))
+ val = 0;
verb = AC_VERB_SET_AMP_GAIN_MUTE;
if (reg & AC_AMP_GET_LEFT)
verb |= AC_AMP_SET_LEFT >> 8;
config SND_SGI_O2
tristate "SGI O2 Audio"
depends on SGI_IP32
+ select SND_PCM
help
Sound support for the SGI O2 Workstation.
config SND_SGI_HAL2
tristate "SGI HAL2 Audio"
depends on SGI_HAS_HAL2
+ select SND_PCM
help
Sound support for the SGI Indy and Indigo2 Workstation.
#include <linux/pci.h>
#include <linux/stringify.h>
#include <linux/module.h>
+#include <linux/vmalloc.h>
#ifdef MODULE_FIRMWARE
MODULE_FIRMWARE("asihpi/dsp5000.bin");
get_wcaps_type(wcaps) != AC_WID_PIN)
return 0;
- parm = snd_hda_param_read(codec, nid, AC_PAR_DEVLIST_LEN);
+ parm = snd_hdac_read_parm_uncached(&codec->core, nid, AC_PAR_DEVLIST_LEN);
if (parm == -1 && codec->bus->rirb_error)
parm = 0;
return parm & AC_DEV_LIST_LEN_MASK;
}
EXPORT_SYMBOL_GPL(snd_hda_override_amp_caps);
+/**
+ * snd_hda_codec_amp_update - update the AMP mono value
+ * @codec: HD-audio codec
+ * @nid: NID to read the AMP value
+ * @ch: channel to update (0 or 1)
+ * @dir: #HDA_INPUT or #HDA_OUTPUT
+ * @idx: the index value (only for input direction)
+ * @mask: bit mask to set
+ * @val: the bits value to set
+ *
+ * Update the AMP values for the given channel, direction and index.
+ */
+int snd_hda_codec_amp_update(struct hda_codec *codec, hda_nid_t nid,
+ int ch, int dir, int idx, int mask, int val)
+{
+ unsigned int cmd = snd_hdac_regmap_encode_amp(nid, ch, dir, idx);
+
+ /* enable fake mute if no h/w mute but min=mute */
+ if ((query_amp_caps(codec, nid, dir) &
+ (AC_AMPCAP_MUTE | AC_AMPCAP_MIN_MUTE)) == AC_AMPCAP_MIN_MUTE)
+ cmd |= AC_AMP_FAKE_MUTE;
+ return snd_hdac_regmap_update_raw(&codec->core, cmd, mask, val);
+}
+EXPORT_SYMBOL_GPL(snd_hda_codec_amp_update);
+
/**
* snd_hda_codec_amp_stereo - update the AMP stereo values
* @codec: HD-audio codec
snd_hda_codec_write(codec, nid, 0,
AC_VERB_SET_POWER_STATE, state);
changed = nid;
+ /* all known codecs seem to be capable to handl
+ * widgets state even in D3, so far.
+ * if any new codecs need to restore the widget
+ * states after D0 transition, call the function
+ * below.
+ */
+#if 0 /* disabled */
if (state == AC_PWRST_D0)
snd_hdac_regmap_sync_node(&codec->core, nid);
+#endif
}
}
return changed;
dig_only:
parse_digital(codec);
- if (spec->power_down_unused || codec->power_save_node)
+ if (spec->power_down_unused || codec->power_save_node) {
if (!codec->power_filter)
codec->power_filter = snd_hda_gen_path_power_filter;
+ if (!codec->patch_ops.stream_pm)
+ codec->patch_ops.stream_pm = snd_hda_gen_stream_pm;
+ }
if (!spec->no_analog && spec->beep_nid) {
err = snd_hda_attach_beep_device(codec, spec->beep_nid);
#define use_vga_switcheroo(chip) 0
#endif
+#define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \
+ ((pci)->device == 0x0c0c) || \
+ ((pci)->device == 0x0d0c) || \
+ ((pci)->device == 0x160c))
+
static char *driver_short_names[] = {
[AZX_DRIVER_ICH] = "HDA Intel",
[AZX_DRIVER_PCH] = "HDA Intel PCH",
if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
#ifdef CONFIG_SND_HDA_I915
err = hda_i915_init(hda);
- if (err < 0)
- goto out_free;
+ if (err < 0) {
+ /* if the controller is bound only with HDMI/DP
+ * (for HSW and BDW), we need to abort the probe;
+ * for other chips, still continue probing as other
+ * codecs can be on the same link.
+ */
+ if (CONTROLLER_IN_GPU(pci))
+ goto out_free;
+ else
+ goto skip_i915;
+ }
err = hda_display_power(hda, true);
if (err < 0) {
dev_err(chip->card->dev,
#endif
}
+#ifdef CONFIG_SND_HDA_I915
+ skip_i915:
+#endif
err = azx_first_init(chip);
if (err < 0)
goto out_free;
.driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
{ PCI_DEVICE(0x1002, 0xaab0),
.driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+ { PCI_DEVICE(0x1002, 0xaac8),
+ .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
/* VIA VT8251/VT8237A */
{ PCI_DEVICE(0x1106, 0x3288),
.driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA },
/* lowlevel accessor with caching; use carefully */
#define snd_hda_codec_amp_read(codec, nid, ch, dir, idx) \
snd_hdac_regmap_get_amp(&(codec)->core, nid, ch, dir, idx)
-#define snd_hda_codec_amp_update(codec, nid, ch, dir, idx, mask, val) \
- snd_hdac_regmap_update_amp(&(codec)->core, nid, ch, dir, idx, mask, val)
+int snd_hda_codec_amp_update(struct hda_codec *codec, hda_nid_t nid,
+ int ch, int dir, int idx, int mask, int val);
int snd_hda_codec_amp_stereo(struct hda_codec *codec, hda_nid_t nid,
int dir, int idx, int mask, int val);
int snd_hda_codec_amp_init(struct hda_codec *codec, hda_nid_t nid, int ch,
.patch = patch_conexant_auto },
{ .id = 0x14f150b9, .name = "CX20665",
.patch = patch_conexant_auto },
+ { .id = 0x14f150f1, .name = "CX20721",
+ .patch = patch_conexant_auto },
+ { .id = 0x14f150f2, .name = "CX20722",
+ .patch = patch_conexant_auto },
+ { .id = 0x14f150f3, .name = "CX20723",
+ .patch = patch_conexant_auto },
+ { .id = 0x14f150f4, .name = "CX20724",
+ .patch = patch_conexant_auto },
{ .id = 0x14f1510f, .name = "CX20751/2",
.patch = patch_conexant_auto },
{ .id = 0x14f15110, .name = "CX20751/2",
MODULE_ALIAS("snd-hda-codec-id:14f150ac");
MODULE_ALIAS("snd-hda-codec-id:14f150b8");
MODULE_ALIAS("snd-hda-codec-id:14f150b9");
+MODULE_ALIAS("snd-hda-codec-id:14f150f1");
+MODULE_ALIAS("snd-hda-codec-id:14f150f2");
+MODULE_ALIAS("snd-hda-codec-id:14f150f3");
+MODULE_ALIAS("snd-hda-codec-id:14f150f4");
MODULE_ALIAS("snd-hda-codec-id:14f1510f");
MODULE_ALIAS("snd-hda-codec-id:14f15110");
MODULE_ALIAS("snd-hda-codec-id:14f15111");
{ 0x10ec0668, 0x1028, 0, "ALC3661" },
{ 0x10ec0275, 0x1028, 0, "ALC3260" },
{ 0x10ec0899, 0x1028, 0, "ALC3861" },
+ { 0x10ec0298, 0x1028, 0, "ALC3266" },
+ { 0x10ec0256, 0x1028, 0, "ALC3246" },
{ 0x10ec0670, 0x1025, 0, "ALC669X" },
{ 0x10ec0676, 0x1025, 0, "ALC679X" },
{ 0x10ec0282, 0x1043, 0, "ALC3229" },
static const struct snd_pci_quirk alc882_fixup_tbl[] = {
SND_PCI_QUIRK(0x1025, 0x006c, "Acer Aspire 9810", ALC883_FIXUP_ACER_EAPD),
SND_PCI_QUIRK(0x1025, 0x0090, "Acer Aspire", ALC883_FIXUP_ACER_EAPD),
+ SND_PCI_QUIRK(0x1025, 0x0107, "Acer Aspire", ALC883_FIXUP_ACER_EAPD),
SND_PCI_QUIRK(0x1025, 0x010a, "Acer Ferrari 5000", ALC883_FIXUP_ACER_EAPD),
SND_PCI_QUIRK(0x1025, 0x0110, "Acer Aspire", ALC883_FIXUP_ACER_EAPD),
SND_PCI_QUIRK(0x1025, 0x0112, "Acer Aspire 9303", ALC883_FIXUP_ACER_EAPD),
alc_process_coef_fw(codec, coef0293);
snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
break;
+ case 0x10ec0662:
+ snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
+ snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
+ break;
case 0x10ec0668:
alc_write_coef_idx(codec, 0x11, 0x0001);
snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
case 0x10ec0288:
alc_process_coef_fw(codec, coef0288);
break;
- break;
case 0x10ec0292:
alc_process_coef_fw(codec, coef0292);
break;
if (new_headset_mode != ALC_HEADSET_MODE_MIC) {
snd_hda_set_pin_ctl_cache(codec, hp_pin,
AC_PINCTL_OUT_EN | AC_PINCTL_HP_EN);
- if (spec->headphone_mic_pin)
+ if (spec->headphone_mic_pin && spec->headphone_mic_pin != hp_pin)
snd_hda_set_pin_ctl_cache(codec, spec->headphone_mic_pin,
PIN_VREFHIZ);
}
}
}
+static void alc_fixup_headset_mode_alc662(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct alc_spec *spec = codec->spec;
+
+ if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ spec->parse_flags |= HDA_PINCFG_HEADSET_MIC;
+ spec->gen.hp_mic = 1; /* Mic-in is same pin as headphone */
+
+ /* Disable boost for mic-in permanently. (This code is only called
+ from quirks that guarantee that the headphone is at NID 0x1b.) */
+ snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_AMP_GAIN_MUTE, 0x7000);
+ snd_hda_override_wcaps(codec, 0x1b, get_wcaps(codec, 0x1b) & ~AC_WCAP_IN_AMP);
+ } else
+ alc_fixup_headset_mode(codec, fix, action);
+}
+
static void alc_fixup_headset_mode_alc668(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
ALC288_FIXUP_DELL_HEADSET_MODE,
ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC288_FIXUP_DELL_XPS_13_GPIO6,
+ ALC292_FIXUP_DELL_E7X,
+ ALC292_FIXUP_DISABLE_AAMIX,
};
static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE
},
+ [ALC292_FIXUP_DISABLE_AAMIX] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_disable_aamix,
+ },
+ [ALC292_FIXUP_DELL_E7X] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_dell_xps13,
+ .chained = true,
+ .chain_id = ALC292_FIXUP_DISABLE_AAMIX
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
+ SND_PCI_QUIRK(0x1028, 0x05ca, "Dell Latitude E7240", ALC292_FIXUP_DELL_E7X),
+ SND_PCI_QUIRK(0x1028, 0x05cb, "Dell Latitude E7440", ALC292_FIXUP_DELL_E7X),
SND_PCI_QUIRK(0x1028, 0x05da, "Dell Vostro 5460", ALC290_FIXUP_SUBWOOFER),
SND_PCI_QUIRK(0x1028, 0x05f4, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x05f5, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK),
SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0665, "Dell XPS 13", ALC292_FIXUP_DELL_E7X),
SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX),
SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN),
+ SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN),
SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC),
SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK),
SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK),
+ SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK),
SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
{0x17, 0x40000000},
{0x1d, 0x40700001},
{0x21, 0x02211050}),
+ SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell Inspiron 5548", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ ALC255_STANDARD_PINS,
+ {0x12, 0x90a60180},
+ {0x14, 0x90170130},
+ {0x17, 0x40000000},
+ {0x1d, 0x40700001},
+ {0x21, 0x02211040}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ ALC255_STANDARD_PINS,
+ {0x12, 0x90a60160},
+ {0x14, 0x90170120},
+ {0x17, 0x40000000},
+ {0x1d, 0x40700001},
+ {0x21, 0x02211030}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC256_STANDARD_PINS,
{0x13, 0x40000000}),
ALC662_FIXUP_NO_JACK_DETECT,
ALC662_FIXUP_ZOTAC_Z68,
ALC662_FIXUP_INV_DMIC,
+ ALC662_FIXUP_DELL_MIC_NO_PRESENCE,
ALC668_FIXUP_DELL_MIC_NO_PRESENCE,
+ ALC662_FIXUP_HEADSET_MODE,
ALC668_FIXUP_HEADSET_MODE,
ALC662_FIXUP_BASS_MODE4_CHMAP,
ALC662_FIXUP_BASS_16,
.chained = true,
.chain_id = ALC668_FIXUP_DELL_MIC_NO_PRESENCE
},
+ [ALC662_FIXUP_DELL_MIC_NO_PRESENCE] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x19, 0x03a1113c }, /* use as headset mic, without its own jack detect */
+ /* headphone mic by setting pin control of 0x1b (headphone out) to in + vref_50 */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC662_FIXUP_HEADSET_MODE
+ },
+ [ALC662_FIXUP_HEADSET_MODE] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_headset_mode_alc662,
+ },
[ALC668_FIXUP_DELL_MIC_NO_PRESENCE] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
};
static const struct snd_hda_pin_quirk alc662_pin_fixup_tbl[] = {
+ SND_HDA_PIN_QUIRK(0x10ec0662, 0x1028, "Dell", ALC662_FIXUP_DELL_MIC_NO_PRESENCE,
+ {0x12, 0x4004c000},
+ {0x14, 0x01014010},
+ {0x15, 0x411111f0},
+ {0x16, 0x411111f0},
+ {0x18, 0x01a19020},
+ {0x19, 0x411111f0},
+ {0x1a, 0x0181302f},
+ {0x1b, 0x0221401f},
+ {0x1c, 0x411111f0},
+ {0x1d, 0x4054c601},
+ {0x1e, 0x411111f0}),
SND_HDA_PIN_QUIRK(0x10ec0668, 0x1028, "Dell", ALC668_FIXUP_AUTO_MUTE,
{0x12, 0x99a30130},
{0x14, 0x90170110},
STAC_HP_ENVY_BASS,
STAC_HP_BNB13_EQ,
STAC_HP_ENVY_TS_BASS,
+ STAC_HP_ENVY_TS_DAC_BIND,
STAC_92HD83XXX_GPIO10_EAPD,
STAC_92HD83XXX_MODELS
};
spec->eapd_switch = 0;
}
+static void hp_envy_ts_fixup_dac_bind(struct hda_codec *codec,
+ const struct hda_fixup *fix,
+ int action)
+{
+ struct sigmatel_spec *spec = codec->spec;
+ static hda_nid_t preferred_pairs[] = {
+ 0xd, 0x13,
+ 0
+ };
+
+ if (action != HDA_FIXUP_ACT_PRE_PROBE)
+ return;
+
+ spec->gen.preferred_dacs = preferred_pairs;
+}
+
static const struct hda_verb hp_bnb13_eq_verbs[] = {
/* 44.1KHz base */
{ 0x22, 0x7A6, 0x3E },
{}
},
},
+ [STAC_HP_ENVY_TS_DAC_BIND] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = hp_envy_ts_fixup_dac_bind,
+ .chained = true,
+ .chain_id = STAC_HP_ENVY_TS_BASS,
+ },
[STAC_92HD83XXX_GPIO10_EAPD] = {
.type = HDA_FIXUP_FUNC,
.v.func = stac92hd83xxx_fixup_gpio10_eapd,
"HP bNB13", STAC_HP_BNB13_EQ),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x190e,
"HP ENVY TS", STAC_HP_ENVY_TS_BASS),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1967,
+ "HP ENVY TS", STAC_HP_ENVY_TS_DAC_BIND),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1940,
"HP bNB13", STAC_HP_BNB13_EQ),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1941,
#ifdef CONFIG_PM
.suspend = stac_suspend,
#endif
- .stream_pm = snd_hda_gen_stream_pm,
.reboot_notify = stac_shutup,
};
return err;
spec = codec->spec;
- codec->power_save_node = 1;
+ /* disabled power_save_node since it causes noises on a Dell machine */
+ /* codec->power_save_node = 1; */
spec->linear_tone_beep = 0;
spec->gen.own_eapd_ctl = 1;
spec->gen.power_down_unused = 1;
return 0;
}
+
+static int via_resume(struct hda_codec *codec)
+{
+ /* some delay here to make jack detection working (bko#98921) */
+ msleep(10);
+ codec->patch_ops.init(codec);
+ regcache_sync(codec->core.regmap);
+ return 0;
+}
#endif
#ifdef CONFIG_PM
.stream_pm = snd_hda_gen_stream_pm,
#ifdef CONFIG_PM
.suspend = via_suspend,
+ .resume = via_resume,
.check_power_status = via_check_power_status,
#endif
};
if (led_set_func(TPACPI_LED_MUTE, false) >= 0) {
old_vmaster_hook = spec->vmaster_mute.hook;
spec->vmaster_mute.hook = update_tpacpi_mute_led;
- spec->vmaster_mute_enum = 1;
removefunc = false;
}
if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) {
AUDIO_SSI_SEL, 0);
else
mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_CODEC,
- 0, AUDIO_SSI_SEL);
+ AUDIO_SSI_SEL, AUDIO_SSI_SEL);
if (priv->dac_ssi_port == MC13783_SSI1_PORT)
mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_DAC,
AUDIO_SSI_SEL, 0);
else
mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_DAC,
- 0, AUDIO_SSI_SEL);
+ AUDIO_SSI_SEL, AUDIO_SSI_SEL);
return 0;
}
if ((fmt & SND_SOC_DAIFMT_MASTER_MASK) != SND_SOC_DAIFMT_CBS_CFS)
return -EINVAL;
- uda1380_write(codec, UDA1380_IFACE, iface);
+ uda1380_write_reg_cache(codec, UDA1380_IFACE, iface);
return 0;
}
{ "Right Input Mixer", "Boost Switch", "Right Boost Mixer", },
{ "Right Input Mixer", NULL, "RINPUT1", }, /* Really Boost Switch */
{ "Right Input Mixer", NULL, "RINPUT2" },
- { "Right Input Mixer", NULL, "LINPUT3" },
+ { "Right Input Mixer", NULL, "RINPUT3" },
{ "Left ADC", NULL, "Left Input Mixer" },
{ "Right ADC", NULL, "Right Input Mixer" },
};
static int fs_ratios[] = {
- 64, 128, 192, 256, 348, 512, 768, 1024, 1408, 1536
+ 64, 128, 192, 256, 384, 512, 768, 1024, 1408, 1536
};
static int bclk_divs[] = {
u32 reg;
int i;
- context->pm_state = pm_runtime_enabled(mcasp->dev);
+ context->pm_state = pm_runtime_active(mcasp->dev);
if (!context->pm_state)
pm_runtime_get_sync(mcasp->dev);
}
prefix = soc_dapm_prefix(dapm);
- if (prefix)
+ if (prefix) {
w->name = kasprintf(GFP_KERNEL, "%s %s", prefix, widget->name);
- else
+ if (widget->sname)
+ w->sname = kasprintf(GFP_KERNEL, "%s %s", prefix,
+ widget->sname);
+ } else {
w->name = kasprintf(GFP_KERNEL, "%s", widget->name);
-
+ if (widget->sname)
+ w->sname = kasprintf(GFP_KERNEL, "%s", widget->sname);
+ }
if (w->name == NULL) {
kfree(w);
return NULL;
case USB_ID(0x046d, 0x081d): /* HD Webcam c510 */
case USB_ID(0x046d, 0x0825): /* HD Webcam c270 */
case USB_ID(0x046d, 0x0826): /* HD Webcam c525 */
+ case USB_ID(0x046d, 0x08ca): /* Logitech Quickcam Fusion */
case USB_ID(0x046d, 0x0991):
/* Most audio usb devices lie about volume resolution.
* Most Logitech webcams have res = 384.
unitid);
return -EINVAL;
}
- /* no bmControls field (e.g. Maya44) -> ignore */
- if (desc->bLength <= 10 + input_pins) {
- usb_audio_dbg(state->chip, "MU %d has no bmControls field\n",
- unitid);
- return 0;
- }
num_ins = 0;
ich = 0;
err = parse_audio_unit(state, desc->baSourceID[pin]);
if (err < 0)
continue;
+ /* no bmControls field (e.g. Maya44) -> ignore */
+ if (desc->bLength <= 10 + input_pins)
+ continue;
err = check_input_term(state, desc->baSourceID[pin], &iterm);
if (err < 0)
return err;
.id = USB_ID(0x200c, 0x1018),
.map = ebox44_map,
},
+ {
+ /* MAYA44 USB+ */
+ .id = USB_ID(0x2573, 0x0008),
+ .map = maya44_map,
+ },
{
/* KEF X300A */
.id = USB_ID(0x27ac, 0x1000),
switch (chip->usb_id) {
case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */
case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */
+ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */
+ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */
case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
+ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */
return true;
}
return false;
if (fp->altsetting == 2)
return SNDRV_PCM_FMTBIT_DSD_U32_BE;
break;
- /* DIYINHK DSD DXD 384kHz USB to I2S/DSD */
- case USB_ID(0x20b1, 0x2009):
+
+ case USB_ID(0x20b1, 0x2009): /* DIYINHK DSD DXD 384kHz USB to I2S/DSD */
+ case USB_ID(0x20b1, 0x2023): /* JLsounds I2SoverUSB */
if (fp->altsetting == 3)
return SNDRV_PCM_FMTBIT_DSD_U32_BE;
break;
+# Some of the tools (perf) use same make variables
+# as in kernel build.
+export srctree=
+export objtree=
+
include scripts/Makefile.include
help:
liblockdep: FORCE
$(call descend,lib/lockdep)
-libapikfs: FORCE
+libapi: FORCE
$(call descend,lib/api)
-perf: libapikfs FORCE
- $(call descend,$@)
+# The perf build does not follow the descend function setup,
+# invoking it via it's own make rule.
+PERF_O = $(if $(O),$(O)/tools/perf,)
+
+perf: FORCE
+ $(Q)mkdir -p $(PERF_O) .
+ $(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir=
selftests: FORCE
$(call descend,testing/$@)
liblockdep_clean:
$(call descend,lib/lockdep,clean)
-libapikfs_clean:
+libapi_clean:
$(call descend,lib/api,clean)
-perf_clean: libapikfs_clean
+perf_clean:
$(call descend,$(@:_clean=),clean)
selftests_clean:
--- /dev/null
+#ifndef __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
+#define __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
+
+#define mb() __asm__ __volatile__("mb": : :"memory")
+#define rmb() __asm__ __volatile__("mb": : :"memory")
+#define wmb() __asm__ __volatile__("wmb": : :"memory")
+
+#endif /* __TOOLS_LINUX_ASM_ALPHA_BARRIER_H */
--- /dev/null
+#ifndef _TOOLS_LINUX_ASM_ARM_BARRIER_H
+#define _TOOLS_LINUX_ASM_ARM_BARRIER_H
+
+/*
+ * Use the __kuser_memory_barrier helper in the CPU helper page. See
+ * arch/arm/kernel/entry-armv.S in the kernel source for details.
+ */
+#define mb() ((void(*)(void))0xffff0fa0)()
+#define wmb() ((void(*)(void))0xffff0fa0)()
+#define rmb() ((void(*)(void))0xffff0fa0)()
+
+#endif /* _TOOLS_LINUX_ASM_ARM_BARRIER_H */
--- /dev/null
+#ifndef _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
+#define _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
+
+/*
+ * From tools/perf/perf-sys.h, last modified in:
+ * f428ebd184c82a7914b2aa7e9f868918aaf7ea78 perf tools: Fix AAAAARGH64 memory barriers
+ *
+ * XXX: arch/arm64/include/asm/barrier.h in the kernel sources use dsb, is this
+ * a case like for arm32 where we do things differently in userspace?
+ */
+
+#define mb() asm volatile("dmb ish" ::: "memory")
+#define wmb() asm volatile("dmb ishst" ::: "memory")
+#define rmb() asm volatile("dmb ishld" ::: "memory")
+
+#endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */
--- /dev/null
+/*
+ * Copied from the kernel sources to tools/:
+ *
+ * Memory barrier definitions. This is based on information published
+ * in the Processor Abstraction Layer and the System Abstraction Layer
+ * manual.
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ * David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ */
+#ifndef _TOOLS_LINUX_ASM_IA64_BARRIER_H
+#define _TOOLS_LINUX_ASM_IA64_BARRIER_H
+
+#include <linux/compiler.h>
+
+/*
+ * Macros to force memory ordering. In these descriptions, "previous"
+ * and "subsequent" refer to program order; "visible" means that all
+ * architecturally visible effects of a memory access have occurred
+ * (at a minimum, this means the memory has been read or written).
+ *
+ * wmb(): Guarantees that all preceding stores to memory-
+ * like regions are visible before any subsequent
+ * stores and that all following stores will be
+ * visible only after all previous stores.
+ * rmb(): Like wmb(), but for reads.
+ * mb(): wmb()/rmb() combo, i.e., all previous memory
+ * accesses are visible before all subsequent
+ * accesses and vice versa. This is also known as
+ * a "fence."
+ *
+ * Note: "mb()" and its variants cannot be used as a fence to order
+ * accesses to memory mapped I/O registers. For that, mf.a needs to
+ * be used. However, we don't want to always use mf.a because (a)
+ * it's (presumably) much slower than mf and (b) mf.a is supported for
+ * sequential memory pages only.
+ */
+
+/* XXX From arch/ia64/include/uapi/asm/gcc_intrin.h */
+#define ia64_mf() asm volatile ("mf" ::: "memory")
+
+#define mb() ia64_mf()
+#define rmb() mb()
+#define wmb() mb()
+
+#endif /* _TOOLS_LINUX_ASM_IA64_BARRIER_H */
--- /dev/null
+#ifndef _TOOLS_LINUX_ASM_MIPS_BARRIER_H
+#define _TOOLS_LINUX_ASM_MIPS_BARRIER_H
+/*
+ * FIXME: This came from tools/perf/perf-sys.h, where it was first introduced
+ * in c1e028ef40b8d6943b767028ba17d4f2ba020edb, more work needed to make it
+ * more closely follow the Linux kernel arch/mips/include/asm/barrier.h file.
+ * Probably when we continue work on tools/ Kconfig support to have all the
+ * CONFIG_ needed for properly doing that.
+ */
+#define mb() asm volatile( \
+ ".set mips2\n\t" \
+ "sync\n\t" \
+ ".set mips0" \
+ : /* no output */ \
+ : /* no input */ \
+ : "memory")
+#define wmb() mb()
+#define rmb() mb()
+
+#endif /* _TOOLS_LINUX_ASM_MIPS_BARRIER_H */
--- /dev/null
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _TOOLS_LINUX_ASM_POWERPC_BARRIER_H
+#define _TOOLS_LINUX_ASM_POWERPC_BARRIER_H
+
+/*
+ * Memory barrier.
+ * The sync instruction guarantees that all memory accesses initiated
+ * by this processor have been performed (with respect to all other
+ * mechanisms that access memory). The eieio instruction is a barrier
+ * providing an ordering (separately) for (a) cacheable stores and (b)
+ * loads and stores to non-cacheable memory (e.g. I/O devices).
+ *
+ * mb() prevents loads and stores being reordered across this point.
+ * rmb() prevents loads being reordered across this point.
+ * wmb() prevents stores being reordered across this point.
+ *
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
+ */
+#define mb() __asm__ __volatile__ ("sync" : : : "memory")
+#define rmb() __asm__ __volatile__ ("sync" : : : "memory")
+#define wmb() __asm__ __volatile__ ("sync" : : : "memory")
+
+#endif /* _TOOLS_LINUX_ASM_POWERPC_BARRIER_H */
--- /dev/null
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __TOOLS_LINUX_ASM_BARRIER_H
+#define __TOOLS_LINUX_ASM_BARRIER_H
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+/* Fast-BCR without checkpoint synchronization */
+#define __ASM_BARRIER "bcr 14,0\n"
+#else
+#define __ASM_BARRIER "bcr 15,0\n"
+#endif
+
+#define mb() do { asm volatile(__ASM_BARRIER : : : "memory"); } while (0)
+
+#define rmb() mb()
+#define wmb() mb()
+
+#endif /* __TOOLS_LIB_ASM_BARRIER_H */
--- /dev/null
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright (C) 1999, 2000 Niibe Yutaka & Kaz Kojima
+ * Copyright (C) 2002 Paul Mundt
+ */
+#ifndef __TOOLS_LINUX_ASM_SH_BARRIER_H
+#define __TOOLS_LINUX_ASM_SH_BARRIER_H
+
+/*
+ * A brief note on ctrl_barrier(), the control register write barrier.
+ *
+ * Legacy SH cores typically require a sequence of 8 nops after
+ * modification of a control register in order for the changes to take
+ * effect. On newer cores (like the sh4a and sh5) this is accomplished
+ * with icbi.
+ *
+ * Also note that on sh4a in the icbi case we can forego a synco for the
+ * write barrier, as it's not necessary for control registers.
+ *
+ * Historically we have only done this type of barrier for the MMUCR, but
+ * it's also necessary for the CCR, so we make it generic here instead.
+ */
+#if defined(__SH4A__) || defined(__SH5__)
+#define mb() __asm__ __volatile__ ("synco": : :"memory")
+#define rmb() mb()
+#define wmb() mb()
+#endif
+
+#include <asm-generic/barrier.h>
+
+#endif /* __TOOLS_LINUX_ASM_SH_BARRIER_H */
--- /dev/null
+#ifndef ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
+#define ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
+#if defined(__sparc__) && defined(__arch64__)
+#include "barrier_64.h"
+#else
+#include "barrier_32.h"
+#endif
+#endif
--- /dev/null
+#ifndef __TOOLS_PERF_SPARC_BARRIER_H
+#define __TOOLS_PERF_SPARC_BARRIER_H
+
+#include <asm-generic/barrier.h>
+
+#endif /* !(__TOOLS_PERF_SPARC_BARRIER_H) */
--- /dev/null
+#ifndef __TOOLS_LINUX_SPARC64_BARRIER_H
+#define __TOOLS_LINUX_SPARC64_BARRIER_H
+
+/* Copied from the kernel sources to tools/:
+ *
+ * These are here in an effort to more fully work around Spitfire Errata
+ * #51. Essentially, if a memory barrier occurs soon after a mispredicted
+ * branch, the chip can stop executing instructions until a trap occurs.
+ * Therefore, if interrupts are disabled, the chip can hang forever.
+ *
+ * It used to be believed that the memory barrier had to be right in the
+ * delay slot, but a case has been traced recently wherein the memory barrier
+ * was one instruction after the branch delay slot and the chip still hung.
+ * The offending sequence was the following in sym_wakeup_done() of the
+ * sym53c8xx_2 driver:
+ *
+ * call sym_ccb_from_dsa, 0
+ * movge %icc, 0, %l0
+ * brz,pn %o0, .LL1303
+ * mov %o0, %l2
+ * membar #LoadLoad
+ *
+ * The branch has to be mispredicted for the bug to occur. Therefore, we put
+ * the memory barrier explicitly into a "branch always, predicted taken"
+ * delay slot to avoid the problem case.
+ */
+#define membar_safe(type) \
+do { __asm__ __volatile__("ba,pt %%xcc, 1f\n\t" \
+ " membar " type "\n" \
+ "1:\n" \
+ : : : "memory"); \
+} while (0)
+
+/* The kernel always executes in TSO memory model these days,
+ * and furthermore most sparc64 chips implement more stringent
+ * memory ordering than required by the specifications.
+ */
+#define mb() membar_safe("#StoreLoad")
+#define rmb() __asm__ __volatile__("":::"memory")
+#define wmb() __asm__ __volatile__("":::"memory")
+
+#endif /* !(__TOOLS_LINUX_SPARC64_BARRIER_H) */
--- /dev/null
+#ifndef _TOOLS_LINUX_ASM_TILE_BARRIER_H
+#define _TOOLS_LINUX_ASM_TILE_BARRIER_H
+/*
+ * FIXME: This came from tools/perf/perf-sys.h, where it was first introduced
+ * in 620830b6954913647b7c7f68920cf48eddf6ad92, more work needed to make it
+ * more closely follow the Linux kernel arch/tile/include/asm/barrier.h file.
+ * Probably when we continue work on tools/ Kconfig support to have all the
+ * CONFIG_ needed for properly doing that.
+ */
+
+#define mb() asm volatile ("mf" ::: "memory")
+#define wmb() mb()
+#define rmb() mb()
+
+#endif /* _TOOLS_LINUX_ASM_TILE_BARRIER_H */
--- /dev/null
+#ifndef _TOOLS_LINUX_ASM_X86_ATOMIC_H
+#define _TOOLS_LINUX_ASM_X86_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "rmwcc.h"
+
+#define LOCK_PREFIX "\n\tlock; "
+
+/*
+ * Atomic operations that C can't guarantee us. Useful for
+ * resource counting etc..
+ */
+
+#define ATOMIC_INIT(i) { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+ return ACCESS_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+ v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+ asm volatile(LOCK_PREFIX "incl %0"
+ : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+ GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
+}
+
+#endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */
--- /dev/null
+#ifndef _TOOLS_LINUX_ASM_X86_BARRIER_H
+#define _TOOLS_LINUX_ASM_X86_BARRIER_H
+
+/*
+ * Copied from the Linux kernel sources, and also moving code
+ * out from tools/perf/perf-sys.h so as to make it be located
+ * in a place similar as in the kernel sources.
+ *
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#if defined(__i386__)
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#elif defined(__x86_64__)
+#define mb() asm volatile("mfence":::"memory")
+#define rmb() asm volatile("lfence":::"memory")
+#define wmb() asm volatile("sfence" ::: "memory")
+#endif
+
+#endif /* _TOOLS_LINUX_ASM_X86_BARRIER_H */
--- /dev/null
+#ifndef _TOOLS_LINUX_ASM_X86_RMWcc
+#define _TOOLS_LINUX_ASM_X86_RMWcc
+
+#ifdef CC_HAVE_ASM_GOTO
+
+#define __GEN_RMWcc(fullop, var, cc, ...) \
+do { \
+ asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \
+ : : "m" (var), ## __VA_ARGS__ \
+ : "memory" : cc_label); \
+ return 0; \
+cc_label: \
+ return 1; \
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
+ __GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \
+ __GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
+
+#else /* !CC_HAVE_ASM_GOTO */
+
+#define __GEN_RMWcc(fullop, var, cc, ...) \
+do { \
+ char c; \
+ asm volatile (fullop "; set" cc " %1" \
+ : "+m" (var), "=qm" (c) \
+ : __VA_ARGS__ : "memory"); \
+ return c != 0; \
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
+ __GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \
+ __GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
+
+#endif /* CC_HAVE_ASM_GOTO */
+
+#endif /* _TOOLS_LINUX_ASM_X86_RMWcc */
--- /dev/null
+/*
+ * Copied from the kernel sources to tools/:
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2012 Tensilica Inc.
+ */
+
+#ifndef _TOOLS_LINUX_XTENSA_SYSTEM_H
+#define _TOOLS_LINUX_XTENSA_SYSTEM_H
+
+#define mb() ({ __asm__ __volatile__("memw" : : : "memory"); })
+#define rmb() barrier()
+#define wmb() mb()
+
+#endif /* _TOOLS_LINUX_XTENSA_SYSTEM_H */
# Build definitions
build-file := $(dir)/Build
-include $(build-file)
+-include $(build-file)
quiet_cmd_flex = FLEX $@
quiet_cmd_bison = BISON $@
subdir-obj-y := $(filter %/$(obj)-in.o, $(obj-y))
# '$(OUTPUT)/dir' prefix to all objects
-prefix := $(subst ./,,$(OUTPUT)$(dir)/)
-obj-y := $(addprefix $(prefix),$(obj-y))
-subdir-obj-y := $(addprefix $(prefix),$(subdir-obj-y))
+objprefix := $(subst ./,,$(OUTPUT)$(dir)/)
+obj-y := $(addprefix $(objprefix),$(obj-y))
+subdir-obj-y := $(addprefix $(objprefix),$(subdir-obj-y))
# Final '$(obj)-in.o' object
-in-target := $(prefix)$(obj)-in.o
+in-target := $(objprefix)$(obj)-in.o
PHONY += $(subdir-y)
# the rule that uses them - an example for that is the 'bionic'
# feature check. ]
#
-FEATURE_TESTS = \
+FEATURE_TESTS ?= \
backtrace \
dwarf \
fortify-source \
zlib \
lzma
-FEATURE_DISPLAY = \
+FEATURE_DISPLAY ?= \
dwarf \
glibc \
gtk2 \
ex-y += a.o
ex-y += b.o
ex-y += empty/
+ex-y += empty2/
libex-y += c.o
libex-y += d.o
--- /dev/null
+This directory is left intentionally without Build file
+to test proper nesting into Build-less directories.
--- /dev/null
+#ifndef __TOOLS_ASM_GENERIC_ATOMIC_H
+#define __TOOLS_ASM_GENERIC_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+/*
+ * Atomic operations that C can't guarantee us. Useful for
+ * resource counting etc..
+ *
+ * Excerpts obtained from the Linux kernel sources.
+ */
+
+#define ATOMIC_INIT(i) { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+ return ACCESS_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+ v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+ __sync_add_and_fetch(&v->counter, 1);
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+ return __sync_sub_and_fetch(&v->counter, 1) == 0;
+}
+
+#endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
--- /dev/null
+/*
+ * Copied from the kernel sources to tools/perf/:
+ *
+ * Generic barrier definitions, originally based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+#define __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+
+/*
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
+ *
+ * Fall back to compiler barriers if nothing better is provided.
+ */
+
+#ifndef mb
+#define mb() barrier()
+#endif
+
+#ifndef rmb
+#define rmb() mb()
+#endif
+
+#ifndef wmb
+#define wmb() mb()
+#endif
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __TOOLS_LINUX_ASM_GENERIC_BARRIER_H */
--- /dev/null
+#ifndef __TOOLS_LINUX_ASM_ATOMIC_H
+#define __TOOLS_LINUX_ASM_ATOMIC_H
+
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/atomic.h"
+#else
+#include <asm-generic/atomic-gcc.h>
+#endif
+
+#endif /* __TOOLS_LINUX_ASM_ATOMIC_H */
--- /dev/null
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/barrier.h"
+#elif defined(__arm__)
+#include "../../arch/arm/include/asm/barrier.h"
+#elif defined(__aarch64__)
+#include "../../arch/arm64/include/asm/barrier.h"
+#elif defined(__powerpc__)
+#include "../../arch/powerpc/include/asm/barrier.h"
+#elif defined(__s390__)
+#include "../../arch/s390/include/asm/barrier.h"
+#elif defined(__sh__)
+#include "../../arch/sh/include/asm/barrier.h"
+#elif defined(__sparc__)
+#include "../../arch/sparc/include/asm/barrier.h"
+#elif defined(__tile__)
+#include "../../arch/tile/include/asm/barrier.h"
+#elif defined(__alpha__)
+#include "../../arch/alpha/include/asm/barrier.h"
+#elif defined(__mips__)
+#include "../../arch/mips/include/asm/barrier.h"
+#elif defined(__ia64__)
+#include "../../arch/ia64/include/asm/barrier.h"
+#elif defined(__xtensa__)
+#include "../../arch/xtensa/include/asm/barrier.h"
+#else
+#include <asm-generic/barrier.h>
+#endif
--- /dev/null
+#ifndef __TOOLS_LINUX_ATOMIC_H
+#define __TOOLS_LINUX_ATOMIC_H
+
+#include <asm/atomic.h>
+
+#endif /* __TOOLS_LINUX_ATOMIC_H */
#ifndef _TOOLS_LINUX_COMPILER_H_
#define _TOOLS_LINUX_COMPILER_H_
+/* Optimization barrier */
+/* The "volatile" is due to gcc bugs */
+#define barrier() __asm__ __volatile__("": : :"memory")
+
#ifndef __always_inline
# define __always_inline inline __attribute__((always_inline))
#endif
--- /dev/null
+#ifndef __TOOLS_LINUX_KERNEL_H
+#define __TOOLS_LINUX_KERNEL_H
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+
+#define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
+#define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask))
+
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+#endif
+
+#ifndef container_of
+/**
+ * container_of - cast a member of a structure out to the containing structure
+ * @ptr: the pointer to the member.
+ * @type: the type of the container struct this is embedded in.
+ * @member: the name of the member within the struct.
+ *
+ */
+#define container_of(ptr, type, member) ({ \
+ const typeof(((type *)0)->member) * __mptr = (ptr); \
+ (type *)((char *)__mptr - offsetof(type, member)); })
+#endif
+
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+
+#ifndef max
+#define max(x, y) ({ \
+ typeof(x) _max1 = (x); \
+ typeof(y) _max2 = (y); \
+ (void) (&_max1 == &_max2); \
+ _max1 > _max2 ? _max1 : _max2; })
+#endif
+
+#ifndef min
+#define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+#endif
+
+#ifndef roundup
+#define roundup(x, y) ( \
+{ \
+ const typeof(y) __y = y; \
+ (((x) + (__y - 1)) / __y) * __y; \
+} \
+)
+#endif
+
+#ifndef BUG_ON
+#ifdef NDEBUG
+#define BUG_ON(cond) do { if (cond) {} } while (0)
+#else
+#define BUG_ON(cond) assert(!(cond))
+#endif
+#endif
+
+/*
+ * Both need more care to handle endianness
+ * (Don't use bitmap_copy_le() for now)
+ */
+#define cpu_to_le64(x) (x)
+#define cpu_to_le32(x) (x)
+
+static inline int
+vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
+{
+ int i;
+ ssize_t ssize = size;
+
+ i = vsnprintf(buf, size, fmt, args);
+
+ return (i >= ssize) ? (ssize - 1) : i;
+}
+
+static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
+{
+ va_list args;
+ ssize_t ssize = size;
+ int i;
+
+ va_start(args, fmt);
+ i = vsnprintf(buf, size, fmt, args);
+ va_end(args);
+
+ return (i >= ssize) ? (ssize - 1) : i;
+}
+
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
+#endif
--- /dev/null
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "../../../include/linux/list.h"
+
+#ifndef TOOLS_LIST_H
+#define TOOLS_LIST_H
+/**
+ * list_del_range - deletes range of entries from list.
+ * @begin: first element in the range to delete from the list.
+ * @end: last element in the range to delete from the list.
+ * Note: list_empty on the range of entries does not return true after this,
+ * the entries is in an undefined state.
+ */
+static inline void list_del_range(struct list_head *begin,
+ struct list_head *end)
+{
+ begin->prev->next = end->next;
+ end->next->prev = begin->prev;
+}
+
+/**
+ * list_for_each_from - iterate over a list from one of its nodes
+ * @pos: the &struct list_head to use as a loop cursor, from where to start
+ * @head: the head for your list.
+ */
+#define list_for_each_from(pos, head) \
+ for (; pos != (head); pos = pos->next)
+#endif
--- /dev/null
+#include "../../../include/linux/poison.h"
typedef __u64 __bitwise __le64;
typedef __u64 __bitwise __be64;
+typedef struct {
+ int counter;
+} atomic_t;
+
+#ifndef __aligned_u64
+# define __aligned_u64 __u64 __attribute__((aligned(8)))
+#endif
+
struct list_head {
struct list_head *next, *prev;
};
$(eval $(1) = $(2)))
endef
-# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
$(call allow-override,CC,$(CROSS_COMPILE)gcc)
$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
INSTALL = install
#define __init
#define noinline
#define list_add_tail_rcu list_add_tail
+#define list_for_each_entry_rcu list_for_each_entry
+#define barrier()
+#define synchronize_sched()
#ifndef CALLER_ADDR0
#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
TRACEEVENT-CFLAGS
+libtraceevent-dynamic-list
# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
$(call allow-override,CC,$(CROSS_COMPILE)gcc)
$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,NM,$(CROSS_COMPILE)nm)
EXT = -std=gnu99
INSTALL = install
DESTDIR ?=
DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+ libdir_relative = lib64
+else
+ libdir_relative = lib
+endif
+
prefix ?= /usr/local
-bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+libdir = $(prefix)/$(libdir_relative)
man_dir = $(prefix)/share/man
man_dir_SQ = '$(subst ','\'',$(man_dir))'
override plugin_dir = $(HOME)/.traceevent/plugins
set_plugin_dir := 0
else
-override plugin_dir = $(prefix)/lib/traceevent/plugins
+override plugin_dir = $(libdir)/traceevent/plugins
endif
endif
#$(info Determined 'srctree' to be $(srctree))
endif
-export prefix bindir src obj
+export prefix libdir src obj
# Shell quotes
-bindir_SQ = $(subst ','\'',$(bindir))
-bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
LIB_FILE = libtraceevent.a libtraceevent.so
TE_IN := $(OUTPUT)libtraceevent-in.o
LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
-CMD_TARGETS = $(LIB_FILE) $(PLUGINS)
+CMD_TARGETS = $(LIB_FILE) $(PLUGINS) $(DYNAMIC_LIST_FILE)
TARGETS = $(CMD_TARGETS)
$(OUTPUT)libtraceevent.a: $(TE_IN)
$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
+$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS)
+ $(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@)
+
plugins: $(PLUGINS)
__plugin_obj = $(notdir $@)
done
endef
+define do_generate_dynamic_list_file
+ (echo '{'; \
+ $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u; \
+ echo '};'; \
+ ) > $2
+endef
+
install_lib: all_cmd install_plugins
$(call QUIET_INSTALL, $(LIB_FILE)) \
- $(call do_install,$(LIB_FILE),$(bindir_SQ))
+ $(call do_install,$(LIB_FILE),$(libdir_SQ))
install_plugins: $(PLUGINS)
$(call QUIET_INSTALL, trace_plugins) \
do_warning_event(event, "%s: no type found", __func__);
goto fail;
}
- field->name = last_token;
+ field->name = field->alias = last_token;
if (test_type(type, EVENT_OP))
goto fail;
size_dynamic = type_size(field->name);
free_token(field->name);
strcat(field->type, brackets);
- field->name = token;
+ field->name = field->alias = token;
type = read_token(&token);
} else {
char *new_type;
void pevent_free_format_field(struct format_field *field)
{
free(field->type);
+ if (field->alias != field->name)
+ free(field->alias);
free(field->name);
free(field);
}
struct event_format *event;
char *type;
char *name;
+ char *alias;
int offset;
int size;
unsigned int arraylen;
#include <endian.h>
#include "event-parse.h"
+/*
+ * From glibc endian.h, for older systems where it is not present, e.g.: RHEL5,
+ * Fedora6.
+ */
+#ifndef le16toh
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+# define le16toh(x) (x)
+# else
+# define le16toh(x) __bswap_16 (x)
+# endif
+#endif
+
+
static unsigned long long
process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
{
assert(ret == 0);
ptr = haystack;
+ memset(pmatch, 0, sizeof(pmatch));
+
while (1) {
ret = regexec(®ex, ptr, 1, pmatch, 0);
if (ret == 0) {
*-flex.*
*.pyc
*.pyo
+.config-detected
--- /dev/null
+Overhead calculation
+--------------------
+The overhead can be shown in two columns as 'Children' and 'Self' when
+perf collects callchains. The 'self' overhead is simply calculated by
+adding all period values of the entry - usually a function (symbol).
+This is the value that perf shows traditionally and sum of all the
+'self' overhead values should be 100%.
+
+The 'children' overhead is calculated by adding all period values of
+the child functions so that it can show the total overhead of the
+higher level functions even if they don't directly execute much.
+'Children' here means functions that are called from another (parent)
+function.
+
+It might be confusing that the sum of all the 'children' overhead
+values exceeds 100% since each of them is already an accumulation of
+'self' overhead of its child functions. But with this enabled, users
+can find which function has the most overhead even if samples are
+spread over the children.
+
+Consider the following example; there are three functions like below.
+
+-----------------------
+void foo(void) {
+ /* do something */
+}
+
+void bar(void) {
+ /* do something */
+ foo();
+}
+
+int main(void) {
+ bar()
+ return 0;
+}
+-----------------------
+
+In this case 'foo' is a child of 'bar', and 'bar' is an immediate
+child of 'main' so 'foo' also is a child of 'main'. In other words,
+'main' is a parent of 'foo' and 'bar', and 'bar' is a parent of 'foo'.
+
+Suppose all samples are recorded in 'foo' and 'bar' only. When it's
+recorded with callchains the output will show something like below
+in the usual (self-overhead-only) output of perf report:
+
+----------------------------------
+Overhead Symbol
+........ .....................
+ 60.00% foo
+ |
+ --- foo
+ bar
+ main
+ __libc_start_main
+
+ 40.00% bar
+ |
+ --- bar
+ main
+ __libc_start_main
+----------------------------------
+
+When the --children option is enabled, the 'self' overhead values of
+child functions (i.e. 'foo' and 'bar') are added to the parents to
+calculate the 'children' overhead. In this case the report could be
+displayed as:
+
+-------------------------------------------
+Children Self Symbol
+........ ........ ....................
+ 100.00% 0.00% __libc_start_main
+ |
+ --- __libc_start_main
+
+ 100.00% 0.00% main
+ |
+ --- main
+ __libc_start_main
+
+ 100.00% 40.00% bar
+ |
+ --- bar
+ main
+ __libc_start_main
+
+ 60.00% 60.00% foo
+ |
+ --- foo
+ bar
+ main
+ __libc_start_main
+-------------------------------------------
+
+In the above output, the 'self' overhead of 'foo' (60%) was add to the
+'children' overhead of 'bar', 'main' and '\_\_libc_start_main'.
+Likewise, the 'self' overhead of 'bar' (40%) was added to the
+'children' overhead of 'main' and '\_\_libc_start_main'.
+
+So '\_\_libc_start_main' and 'main' are shown first since they have
+same (100%) 'children' overhead (even though they have zero 'self'
+overhead) and they are the parents of 'foo' and 'bar'.
+
+Since v3.16 the 'children' overhead is shown by default and the output
+is sorted by its values. The 'children' overhead is disabled by
+specifying --no-children option on the command line or by adding
+'report.children = false' or 'top.children = false' in the perf config
+file.
*wake*::
Suite for evaluating wake calls.
+*wake-parallel*::
+Suite for evaluating parallel wake calls.
+
*requeue*::
Suite for evaluating requeue calls.
--kallsyms=<file>::
kallsyms pathname
+--itrace::
+ Decode Instruction Tracing data, replacing it with synthesized events.
+ Options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ x synthesize transactions events
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+
+ The default is all events i.e. the same as --itrace=ibxe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions or
+ transactions events can be specified.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
-s <key[,key2...]>::
--sort=<key[,key2...]>::
- Sort the output (default: frag,hit,bytes)
+ Sort the output (default: 'frag,hit,bytes' for slab and 'bytes,hit'
+ for page). Available sort keys are 'ptr, callsite, bytes, hit,
+ pingpong, frag' for slab and 'page, callsite, bytes, hit, order,
+ migtype, gfp' for page. This option should be preceded by one of the
+ mode selection options - i.e. --slab, --page, --alloc and/or --caller.
-l <num>::
--line=<num>::
--page::
Analyze page allocator events
+--live::
+ Show live page stat. The perf kmem shows total allocation stat by
+ default, but this option shows live (currently allocated) pages
+ instead. (This option works with --page option only)
+
SEE ALSO
--------
linkperf:perf-record[1]
Show events other than HLT (x86 only) or Wait state (s390 only)
that take longer than duration usecs.
+--proc-map-timeout::
+ When processing pre-existing threads /proc/XXX/mmap, it may take
+ a long time, because the file may be huge. A time out is needed
+ in such cases.
+ This option sets the time out limit. The default value is 500 ms.
+
SEE ALSO
--------
linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],
or
'perf probe' [options] --del='[GROUP:]EVENT' [...]
or
-'perf probe' --list
+'perf probe' --list[=[GROUP:]EVENT]
or
'perf probe' [options] --line='LINE'
or
'perf probe' [options] --vars='PROBEPOINT'
+or
+'perf probe' [options] --funcs
DESCRIPTION
-----------
classes(e.g. [a-z], [!A-Z]).
-l::
---list::
- List up current probe events.
+--list[=[GROUP:]EVENT]::
+ List up current probe events. This can also accept filtering patterns of event names.
-L::
--line=::
(Only for --vars) Show external defined variables in addition to local
variables.
+--no-inlines::
+ (Only for --add) Search only for non-inlined functions. The functions
+ which do not have instances are ignored.
+
-F::
---funcs::
+--funcs[=FILTER]::
Show available functions in given module or kernel. With -x/--exec,
can also list functions in a user space executable / shared library.
+ This also can accept a FILTER rule argument.
--filter=FILTER::
(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
[NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
-'$vars' special argument is also available for NAME, it is expanded to the local variables which can access at given probe point.
+'$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
Number of mmap data pages (must be a power of two) or size
specification with appended unit character - B/K/M/G. The
size is rounded up to have nearest pages power of two value.
+ Also, by adding a comma, the number of mmap pages for AUX
+ area tracing can be specified.
--group::
Put all events in a single event group. This precedes the --event
-s::
--stat::
- Per thread counts.
+ Record per-thread event counts. Use it with 'perf report -T' to see
+ the values.
-d::
--data::
- Sample addresses.
+ Record the sample addresses.
-T::
--timestamp::
- Sample timestamps. Use it with 'perf report -D' to see the timestamps,
- for instance.
+ Record the sample timestamps. Use it with 'perf report -D' to see the
+ timestamps, for instance.
+
+-P::
+--period::
+ Record the sample period.
-n::
--no-samples::
CLOCK_MONOTONIC_RAW are supported, some events might also allow
CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI.
+-S::
+--snapshot::
+Select AUX area tracing Snapshot Mode. This option is valid only with an
+AUX area tracing event. Optionally the number of bytes to capture per
+snapshot can be specified. In Snapshot Mode, trace data is captured only when
+signal SIGUSR2 is received.
+
+--proc-map-timeout::
+When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
+because the file may be huge. A time out is needed in such cases.
+This option sets the time out limit. The default value is 500 ms.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]
-T::
--threads::
- Show per-thread event counters
+ Show per-thread event counters. The input data file should be recorded
+ with -s option.
-c::
--comms=::
Only consider symbols in these comms. CSV that understands
Accumulate callchain of children to parent entry so that then can
show up in the output. The output will have a new "Children" column
and will be sorted on the data. It requires callchains are recorded.
+ See the `overhead calculation' section for more details.
--max-stack::
Set the stack depth limit when parsing the callchain, anything
--header-only::
Show only perf.data header (forces --stdio).
+--itrace::
+ Options for decoding instruction tracing data. The options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ x synthesize transactions events
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+
+ The default is all events i.e. the same as --itrace=ibxe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions or
+ transactions events can be specified.
+
+ To disable decoding entirely, use --no-itrace.
+
+
+include::callchain-overhead-calculation.txt[]
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-annotate[1]
-f::
--fields::
Comma separated list of fields to print. Options are:
- comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period.
+ comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
+ srcline, period, flags.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace
At this point usage is displayed, and perf-script exits.
+ The flags field is synthesized and may have a value when Instruction
+ Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
+ call, return, conditional, system, asynchronous, interrupt,
+ transaction abort, trace begin, trace end, and in transaction,
+ respectively.
+
Finally, a user may not set fields to none for all event types.
i.e., -f "" is not allowed.
--header-only
Show only perf.data header.
+--itrace::
+ Options for decoding instruction tracing data. The options are:
+
+ i synthesize instructions events
+ b synthesize branches events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ x synthesize transactions events
+ e synthesize error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+
+ The default is all events i.e. the same as --itrace=ibxe
+
+ In addition, the period (default 100000) for instructions events
+ can be specified in units of:
+
+ i instructions
+ t ticks
+ ms milliseconds
+ us microseconds
+ ns nanoseconds (default)
+
+ Also the call chain size (default 16, max. 1024) for instructions or
+ transactions events can be specified.
+
+ To disable decoding entirely, use --no-itrace.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
Accumulate callchain of children to parent entry so that then can
show up in the output. The output will have a new "Children" column
and will be sorted on the data. It requires -g/--call-graph option
- enabled.
+ enabled. See the `overhead calculation' section for more details.
--max-stack::
Set the stack depth limit when parsing the callchain, anything
Force each column width to the provided list, for large terminal
readability. 0 means no limit (default behavior).
+--proc-map-timeout::
+ When processing pre-existing threads /proc/XXX/mmap, it may take
+ a long time, because the file may be huge. A time out is needed
+ in such cases.
+ This option sets the time out limit. The default value is 500 ms.
+
INTERACTIVE PROMPTING KEYS
--------------------------
Pressing any unmapped key displays a menu, and prompts for input.
+include::callchain-overhead-calculation.txt[]
SEE ALSO
--------
-e::
--expr::
- List of events to show, currently only syscall names.
+ List of syscalls to show, currently only syscall names.
Prefixing with ! shows all syscalls but the ones specified. You may
need to escape it.
--event::
Trace other events, see 'perf list' for a complete list.
+--proc-map-timeout::
+ When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
+ because the file may be huge. A time out is needed in such cases.
+ This option sets the time out limit. The default value is 500 ms.
+
PAGEFAULTS
----------
tools/perf
+tools/arch/alpha/include/asm/barrier.h
+tools/arch/arm/include/asm/barrier.h
+tools/arch/ia64/include/asm/barrier.h
+tools/arch/mips/include/asm/barrier.h
+tools/arch/powerpc/include/asm/barrier.h
+tools/arch/s390/include/asm/barrier.h
+tools/arch/sh/include/asm/barrier.h
+tools/arch/sparc/include/asm/barrier.h
+tools/arch/sparc/include/asm/barrier_32.h
+tools/arch/sparc/include/asm/barrier_64.h
+tools/arch/tile/include/asm/barrier.h
+tools/arch/x86/include/asm/barrier.h
+tools/arch/xtensa/include/asm/barrier.h
tools/scripts
tools/build
+tools/arch/x86/include/asm/atomic.h
+tools/arch/x86/include/asm/rmwcc.h
tools/lib/traceevent
tools/lib/api
tools/lib/symbol/kallsyms.c
tools/lib/symbol/kallsyms.h
tools/lib/util/find_next_bit.c
+tools/include/asm/atomic.h
+tools/include/asm/barrier.h
tools/include/asm/bug.h
+tools/include/asm-generic/barrier.h
tools/include/asm-generic/bitops/arch_hweight.h
tools/include/asm-generic/bitops/atomic.h
tools/include/asm-generic/bitops/const_hweight.h
tools/include/asm-generic/bitops/fls.h
tools/include/asm-generic/bitops/hweight.h
tools/include/asm-generic/bitops.h
+tools/include/linux/atomic.h
tools/include/linux/bitops.h
tools/include/linux/compiler.h
tools/include/linux/export.h
tools/include/linux/hash.h
+tools/include/linux/kernel.h
+tools/include/linux/list.h
tools/include/linux/log2.h
+tools/include/linux/poison.h
tools/include/linux/types.h
include/asm-generic/bitops/arch_hweight.h
include/asm-generic/bitops/const_hweight.h
include/asm-generic/bitops/fls64.h
include/asm-generic/bitops/__fls.h
include/asm-generic/bitops/fls.h
-include/linux/const.h
include/linux/perf_event.h
include/linux/rbtree.h
include/linux/list.h
include/linux/hash.h
include/linux/stringify.h
-lib/find_next_bit.c
lib/hweight.c
lib/rbtree.c
include/linux/swab.h
arch/*/include/asm/unistd*.h
-arch/*/include/asm/perf_regs.h
arch/*/include/uapi/asm/unistd*.h
arch/*/include/uapi/asm/perf_regs.h
arch/*/lib/memcpy*.S
arch/*/lib/memset*.S
include/linux/poison.h
-include/linux/magic.h
include/linux/hw_breakpoint.h
include/linux/rbtree_augmented.h
include/uapi/linux/perf_event.h
# (To override it, run 'make JOBS=1' and similar.)
#
ifeq ($(JOBS),)
- JOBS := $(shell egrep -c '^processor|^CPU' /proc/cpuinfo 2>/dev/null)
+ JOBS := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null)
ifeq ($(JOBS),0)
JOBS := 1
endif
# for CTF data format.
#
# Define NO_LZMA if you do not want to support compressed (xz) kernel modules
+#
+# Define NO_AUXTRACE if you do not want AUX area tracing support
ifeq ($(srctree),)
srctree := $(patsubst %/,%,$(dir $(shell pwd)))
LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
export LIBTRACEEVENT
+LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
+LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+
LIBAPI = $(LIB_PATH)libapi.a
export LIBAPI
PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI)
-$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
- $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
+ $(QUIET_GEN)CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
+ $(PYTHON_WORD) util/setup.py \
--quiet build_ext; \
mkdir -p $(OUTPUT)python && \
cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
$(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE
$(Q)$(MAKE) $(build)=perf
-$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN)
- $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(PERF_IN) $(LIBS) -o $@
+$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
+ $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS) \
+ $(PERF_IN) $(LIBS) -o $@
$(GTK_IN): FORCE
$(Q)$(MAKE) $(build)=gtk
LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
$(LIBTRACEEVENT): FORCE
- $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a plugins
+ $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a
+
+libtraceevent_plugins: FORCE
+ $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) plugins
+
+$(LIBTRACEEVENT_DYNAMIC_LIST): libtraceevent_plugins
+ $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent-dynamic-list
$(LIBTRACEEVENT)-clean:
$(call QUIET_CLEAN, libtraceevent)
install-gtk:
-install-bin: all install-gtk
+install-tools: all install-gtk
$(call QUIET_INSTALL, binaries) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
$(call QUIET_INSTALL, perf_completion-script) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+
+install-tests: all install-gtk
$(call QUIET_INSTALL, tests) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
+install-bin: install-tools install-tests
+
install: install-bin try-install-man install-traceevent-plugins
install-python_ext:
.PHONY: all install clean config-clean strip install-gtk
.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE single_dep
+.PHONY: libtraceevent_plugins
libperf-y += util/
+libperf-$(CONFIG_DWARF_UNWIND) += tests/
#include <linux/types.h>
#include <asm/perf_regs.h>
+void perf_regs_load(u64 *regs);
+
#define PERF_REGS_MASK ((1ULL << PERF_REG_ARM64_MAX) - 1)
#define PERF_REGS_MAX PERF_REG_ARM64_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
#define PERF_REG_IP PERF_REG_ARM64_PC
#define PERF_REG_SP PERF_REG_ARM64_SP
--- /dev/null
+libperf-y += regs_load.o
+libperf-y += dwarf-unwind.o
--- /dev/null
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+ struct thread *thread, u64 *regs)
+{
+ struct stack_dump *stack = &sample->user_stack;
+ struct map *map;
+ unsigned long sp;
+ u64 stack_size, *buf;
+
+ buf = malloc(STACK_SIZE);
+ if (!buf) {
+ pr_debug("failed to allocate sample uregs data\n");
+ return -1;
+ }
+
+ sp = (unsigned long) regs[PERF_REG_ARM64_SP];
+
+ map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+ if (!map) {
+ pr_debug("failed to get stack map\n");
+ free(buf);
+ return -1;
+ }
+
+ stack_size = map->end - sp;
+ stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+ memcpy(buf, (void *) sp, stack_size);
+ stack->data = (char *) buf;
+ stack->size = stack_size;
+ return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+ struct thread *thread)
+{
+ struct regs_dump *regs = &sample->user_regs;
+ u64 *buf;
+
+ buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+ if (!buf) {
+ pr_debug("failed to allocate sample uregs data\n");
+ return -1;
+ }
+
+ perf_regs_load(buf);
+ regs->abi = PERF_SAMPLE_REGS_ABI;
+ regs->regs = buf;
+ regs->mask = PERF_REGS_MASK;
+
+ return sample_ustack(sample, thread, buf);
+}
--- /dev/null
+#include <linux/linkage.h>
+
+.text
+.type perf_regs_load,%function
+#define STR_REG(r) str x##r, [x0, 8 * r]
+#define LDR_REG(r) ldr x##r, [x0, 8 * r]
+#define SP (8 * 31)
+#define PC (8 * 32)
+ENTRY(perf_regs_load)
+ STR_REG(0)
+ STR_REG(1)
+ STR_REG(2)
+ STR_REG(3)
+ STR_REG(4)
+ STR_REG(5)
+ STR_REG(6)
+ STR_REG(7)
+ STR_REG(8)
+ STR_REG(9)
+ STR_REG(10)
+ STR_REG(11)
+ STR_REG(12)
+ STR_REG(13)
+ STR_REG(14)
+ STR_REG(15)
+ STR_REG(16)
+ STR_REG(17)
+ STR_REG(18)
+ STR_REG(19)
+ STR_REG(20)
+ STR_REG(21)
+ STR_REG(22)
+ STR_REG(23)
+ STR_REG(24)
+ STR_REG(25)
+ STR_REG(26)
+ STR_REG(27)
+ STR_REG(28)
+ STR_REG(29)
+ STR_REG(30)
+ mov x1, sp
+ str x1, [x0, #SP]
+ str x30, [x0, #PC]
+ LDR_REG(1)
+ ret
+ENDPROC(perf_regs_load)
static bool lookup_path(char *name)
{
bool found = false;
- char *path, *tmp;
+ char *path, *tmp = NULL;
char buf[PATH_MAX];
char *env = getenv("PATH");
libperf-y += header.o
+libperf-y += sym-handling.o
libperf-$(CONFIG_DWARF) += dwarf-regs.o
libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
--- /dev/null
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include "debug.h"
+#include "symbol.h"
+#include "map.h"
+#include "probe-event.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+ return ehdr.e_type == ET_EXEC ||
+ ehdr.e_type == ET_REL ||
+ ehdr.e_type == ET_DYN;
+}
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+void arch__elf_sym_adjust(GElf_Sym *sym)
+{
+ sym->st_value += PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#endif
+#endif
+
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+int arch__choose_best_symbol(struct symbol *syma,
+ struct symbol *symb __maybe_unused)
+{
+ char *sym = syma->name;
+
+ /* Skip over any initial dot */
+ if (*sym == '.')
+ sym++;
+
+ /* Avoid "SyS" kernel syscall aliases */
+ if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
+ return SYMBOL_B;
+ if (strlen(sym) >= 10 && !strncmp(sym, "compat_SyS", 10))
+ return SYMBOL_B;
+
+ return SYMBOL_A;
+}
+
+/* Allow matching against dot variants */
+int arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+ /* Skip over initial dot */
+ if (*namea == '.')
+ namea++;
+ if (*nameb == '.')
+ nameb++;
+
+ return strcmp(namea, nameb);
+}
+#endif
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+bool arch__prefers_symtab(void)
+{
+ return true;
+}
+
+#define PPC64LE_LEP_OFFSET 8
+
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+ struct probe_trace_event *tev, struct map *map)
+{
+ /*
+ * ppc64 ABIv2 local entry point is currently always 2 instructions
+ * (8 bytes) after the global entry point.
+ */
+ if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
+ tev->point.address += PPC64LE_LEP_OFFSET;
+ tev->point.offset += PPC64LE_LEP_OFFSET;
+ }
+}
+#endif
perf-y += mem-memcpy.o
perf-y += futex-hash.o
perf-y += futex-wake.o
+perf-y += futex-wake-parallel.o
perf-y += futex-requeue.o
perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
+extern int bench_futex_wake_parallel(int argc, const char **argv,
+ const char *prefix);
extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
#define BENCH_FORMAT_DEFAULT_STR "default"
--- /dev/null
+/*
+ * Copyright (C) 2015 Davidlohr Bueso.
+ *
+ * Block a bunch of threads and let parallel waker threads wakeup an
+ * equal amount of them. The program output reflects the avg latency
+ * for each individual thread to service its share of work. Ultimately
+ * it can be used to measure futex_wake() changes.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+struct thread_data {
+ pthread_t worker;
+ unsigned int nwoken;
+ struct timeval runtime;
+};
+
+static unsigned int nwakes = 1;
+
+/* all threads will block on the same futex -- hash bucket chaos ;) */
+static u_int32_t futex = 0;
+
+static pthread_t *blocked_worker;
+static bool done = false, silent = false, fshared = false;
+static unsigned int nblocked_threads = 0, nwaking_threads = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats waketime_stats, wakeup_stats;
+static unsigned int ncpus, threads_starting;
+static int futex_flag = 0;
+
+static const struct option options[] = {
+ OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"),
+ OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking threads"),
+ OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
+ OPT_END()
+};
+
+static const char * const bench_futex_wake_parallel_usage[] = {
+ "perf bench futex wake-parallel <options>",
+ NULL
+};
+
+static void *waking_workerfn(void *arg)
+{
+ struct thread_data *waker = (struct thread_data *) arg;
+ struct timeval start, end;
+
+ gettimeofday(&start, NULL);
+
+ waker->nwoken = futex_wake(&futex, nwakes, futex_flag);
+ if (waker->nwoken != nwakes)
+ warnx("couldn't wakeup all tasks (%d/%d)",
+ waker->nwoken, nwakes);
+
+ gettimeofday(&end, NULL);
+ timersub(&end, &start, &waker->runtime);
+
+ pthread_exit(NULL);
+ return NULL;
+}
+
+static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
+{
+ unsigned int i;
+
+ pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
+
+ /* create and block all threads */
+ for (i = 0; i < nwaking_threads; i++) {
+ /*
+ * Thread creation order will impact per-thread latency
+ * as it will affect the order to acquire the hb spinlock.
+ * For now let the scheduler decide.
+ */
+ if (pthread_create(&td[i].worker, &thread_attr,
+ waking_workerfn, (void *)&td[i]))
+ err(EXIT_FAILURE, "pthread_create");
+ }
+
+ for (i = 0; i < nwaking_threads; i++)
+ if (pthread_join(td[i].worker, NULL))
+ err(EXIT_FAILURE, "pthread_join");
+}
+
+static void *blocked_workerfn(void *arg __maybe_unused)
+{
+ pthread_mutex_lock(&thread_lock);
+ threads_starting--;
+ if (!threads_starting)
+ pthread_cond_signal(&thread_parent);
+ pthread_cond_wait(&thread_worker, &thread_lock);
+ pthread_mutex_unlock(&thread_lock);
+
+ while (1) { /* handle spurious wakeups */
+ if (futex_wait(&futex, 0, NULL, futex_flag) != EINTR)
+ break;
+ }
+
+ pthread_exit(NULL);
+ return NULL;
+}
+
+static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
+{
+ cpu_set_t cpu;
+ unsigned int i;
+
+ threads_starting = nblocked_threads;
+
+ /* create and block all threads */
+ for (i = 0; i < nblocked_threads; i++) {
+ CPU_ZERO(&cpu);
+ CPU_SET(i % ncpus, &cpu);
+
+ if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+ err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+ if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
+ err(EXIT_FAILURE, "pthread_create");
+ }
+}
+
+static void print_run(struct thread_data *waking_worker, unsigned int run_num)
+{
+ unsigned int i, wakeup_avg;
+ double waketime_avg, waketime_stddev;
+ struct stats __waketime_stats, __wakeup_stats;
+
+ init_stats(&__wakeup_stats);
+ init_stats(&__waketime_stats);
+
+ for (i = 0; i < nwaking_threads; i++) {
+ update_stats(&__waketime_stats, waking_worker[i].runtime.tv_usec);
+ update_stats(&__wakeup_stats, waking_worker[i].nwoken);
+ }
+
+ waketime_avg = avg_stats(&__waketime_stats);
+ waketime_stddev = stddev_stats(&__waketime_stats);
+ wakeup_avg = avg_stats(&__wakeup_stats);
+
+ printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) "
+ "in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg,
+ nblocked_threads, waketime_avg/1e3,
+ rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+static void print_summary(void)
+{
+ unsigned int wakeup_avg;
+ double waketime_avg, waketime_stddev;
+
+ waketime_avg = avg_stats(&waketime_stats);
+ waketime_stddev = stddev_stats(&waketime_stats);
+ wakeup_avg = avg_stats(&wakeup_stats);
+
+ printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n",
+ wakeup_avg,
+ nblocked_threads,
+ waketime_avg/1e3,
+ rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+
+static void do_run_stats(struct thread_data *waking_worker)
+{
+ unsigned int i;
+
+ for (i = 0; i < nwaking_threads; i++) {
+ update_stats(&waketime_stats, waking_worker[i].runtime.tv_usec);
+ update_stats(&wakeup_stats, waking_worker[i].nwoken);
+ }
+
+}
+
+static void toggle_done(int sig __maybe_unused,
+ siginfo_t *info __maybe_unused,
+ void *uc __maybe_unused)
+{
+ done = true;
+}
+
+int bench_futex_wake_parallel(int argc, const char **argv,
+ const char *prefix __maybe_unused)
+{
+ int ret = 0;
+ unsigned int i, j;
+ struct sigaction act;
+ pthread_attr_t thread_attr;
+ struct thread_data *waking_worker;
+
+ argc = parse_options(argc, argv, options,
+ bench_futex_wake_parallel_usage, 0);
+ if (argc) {
+ usage_with_options(bench_futex_wake_parallel_usage, options);
+ exit(EXIT_FAILURE);
+ }
+
+ sigfillset(&act.sa_mask);
+ act.sa_sigaction = toggle_done;
+ sigaction(SIGINT, &act, NULL);
+
+ ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+ if (!nblocked_threads)
+ nblocked_threads = ncpus;
+
+ /* some sanity checks */
+ if (nwaking_threads > nblocked_threads || !nwaking_threads)
+ nwaking_threads = nblocked_threads;
+
+ if (nblocked_threads % nwaking_threads)
+ errx(EXIT_FAILURE, "Must be perfectly divisible");
+ /*
+ * Each thread will wakeup nwakes tasks in
+ * a single futex_wait call.
+ */
+ nwakes = nblocked_threads/nwaking_threads;
+
+ blocked_worker = calloc(nblocked_threads, sizeof(*blocked_worker));
+ if (!blocked_worker)
+ err(EXIT_FAILURE, "calloc");
+
+ if (!fshared)
+ futex_flag = FUTEX_PRIVATE_FLAG;
+
+ printf("Run summary [PID %d]: blocking on %d threads (at [%s] "
+ "futex %p), %d threads waking up %d at a time.\n\n",
+ getpid(), nblocked_threads, fshared ? "shared":"private",
+ &futex, nwaking_threads, nwakes);
+
+ init_stats(&wakeup_stats);
+ init_stats(&waketime_stats);
+
+ pthread_attr_init(&thread_attr);
+ pthread_mutex_init(&thread_lock, NULL);
+ pthread_cond_init(&thread_parent, NULL);
+ pthread_cond_init(&thread_worker, NULL);
+
+ for (j = 0; j < bench_repeat && !done; j++) {
+ waking_worker = calloc(nwaking_threads, sizeof(*waking_worker));
+ if (!waking_worker)
+ err(EXIT_FAILURE, "calloc");
+
+ /* create, launch & block all threads */
+ block_threads(blocked_worker, thread_attr);
+
+ /* make sure all threads are already blocked */
+ pthread_mutex_lock(&thread_lock);
+ while (threads_starting)
+ pthread_cond_wait(&thread_parent, &thread_lock);
+ pthread_cond_broadcast(&thread_worker);
+ pthread_mutex_unlock(&thread_lock);
+
+ usleep(100000);
+
+ /* Ok, all threads are patiently blocked, start waking folks up */
+ wakeup_threads(waking_worker, thread_attr);
+
+ for (i = 0; i < nblocked_threads; i++) {
+ ret = pthread_join(blocked_worker[i], NULL);
+ if (ret)
+ err(EXIT_FAILURE, "pthread_join");
+ }
+
+ do_run_stats(waking_worker);
+ if (!silent)
+ print_run(waking_worker, j);
+
+ free(waking_worker);
+ }
+
+ /* cleanup & report results */
+ pthread_cond_destroy(&thread_parent);
+ pthread_cond_destroy(&thread_worker);
+ pthread_mutex_destroy(&thread_lock);
+ pthread_attr_destroy(&thread_attr);
+
+ print_summary();
+
+ free(blocked_worker);
+ return ret;
+}
pthread_cond_wait(&thread_worker, &thread_lock);
pthread_mutex_unlock(&thread_lock);
- futex_wait(&futex1, 0, NULL, futex_flag);
+ while (1) {
+ if (futex_wait(&futex1, 0, NULL, futex_flag) != EINTR)
+ break;
+ }
+
+ pthread_exit(NULL);
return NULL;
}
#include "../builtin.h"
#include "../util/util.h"
#include "../util/parse-options.h"
+#include "../util/cloexec.h"
#include "bench.h"
#include <pthread.h>
#include <sys/mman.h>
#include <sys/time.h>
+#include <sys/resource.h>
#include <sys/wait.h>
#include <sys/prctl.h>
#include <sys/types.h>
unsigned int loops_done;
u64 val;
u64 runtime_ns;
+ u64 system_time_ns;
+ u64 user_time_ns;
+ double speed_gbs;
pthread_mutex_t *process_lock;
};
u64 bytes_done;
long work_done;
u32 l;
+ struct rusage rusage;
bind_to_cpumask(td->bind_cpumask);
bind_to_memnode(td->bind_node);
timersub(&stop, &start0, &diff);
td->runtime_ns = diff.tv_sec * 1000000000ULL;
td->runtime_ns += diff.tv_usec * 1000ULL;
+ td->speed_gbs = bytes_done / (td->runtime_ns / 1e9) / 1e9;
+
+ getrusage(RUSAGE_THREAD, &rusage);
+ td->system_time_ns = rusage.ru_stime.tv_sec * 1000000000ULL;
+ td->system_time_ns += rusage.ru_stime.tv_usec * 1000ULL;
+ td->user_time_ns = rusage.ru_utime.tv_sec * 1000000000ULL;
+ td->user_time_ns += rusage.ru_utime.tv_usec * 1000ULL;
free_data(thread_data, g->p.bytes_thread);
double runtime_sec_min;
int wait_stat;
double bytes;
- int i, t;
+ int i, t, p;
if (init())
return -1;
print_res(name, bytes / runtime_sec_max / 1e9,
"GB/sec,", "total-speed", "GB/sec total speed");
+ if (g->p.show_details >= 2) {
+ char tname[32];
+ struct thread_data *td;
+ for (p = 0; p < g->p.nr_proc; p++) {
+ for (t = 0; t < g->p.nr_threads; t++) {
+ memset(tname, 0, 32);
+ td = g->threads + p*g->p.nr_threads + t;
+ snprintf(tname, 32, "process%d:thread%d", p, t);
+ print_res(tname, td->speed_gbs,
+ "GB/sec", "thread-speed", "GB/sec/thread speed");
+ print_res(tname, td->system_time_ns / 1e9,
+ "secs", "thread-system-time", "system CPU time/thread");
+ print_res(tname, td->user_time_ns / 1e9,
+ "secs", "thread-user-time", "user CPU time/thread");
+ }
+ }
+ }
+
free(pids);
deinit();
(al->sym == NULL ||
strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
/* We're only interested in a symbol named sym_hist_filter */
+ /*
+ * FIXME: why isn't this done in the symbol_filter when loading
+ * the DSO?
+ */
if (al->sym != NULL) {
rb_erase(&al->sym->rb_node,
&al->map->dso->symbols[al->map->type]);
{
struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
struct addr_location al;
+ int ret = 0;
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
}
if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
- return 0;
+ goto out_put;
if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
pr_warning("problem incrementing symbol count, "
"skipping event\n");
- return -1;
+ ret = -1;
}
-
- return 0;
+out_put:
+ addr_location__put(&al);
+ return ret;
}
static int hist_entry__tty_annotate(struct hist_entry *he,
},
};
struct perf_data_file file = {
- .path = input_name,
.mode = PERF_DATA_MODE_READ,
};
const struct option options[] = {
"objdump binary to use for disassembly and annotations"),
OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
"Show event group information together"),
+ OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
+ "Show a column with the sum of periods"),
OPT_END()
};
int ret = hists__init();
else if (annotate.use_gtk)
use_browser = 2;
+ file.path = input_name;
+
setup_browser(true);
annotate.session = perf_session__new(&file, false, &annotate.tool);
static struct bench futex_benchmarks[] = {
{ "hash", "Benchmark for futex hash table", bench_futex_hash },
{ "wake", "Benchmark for futex wake calls", bench_futex_wake },
+ { "wake-parallel", "Benchmark for parallel futex wake calls", bench_futex_wake_parallel },
{ "requeue", "Benchmark for futex requeue calls", bench_futex_requeue },
{ "all", "Test all futex benchmarks", NULL },
{ NULL, NULL, NULL }
session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
if (session == NULL)
return -1;
+
+ /*
+ * We take all buildids when the file contains AUX area tracing data
+ * because we do not decode the trace because it would take too long.
+ */
+ if (!perf_data_file__is_pipe(&file) &&
+ perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+ with_hits = false;
+
/*
* in pipe-mode, the only way to get the buildids is to parse
* the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
{
struct addr_location al;
struct hists *hists = evsel__hists(evsel);
+ int ret = -1;
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
if (hists__add_entry(hists, &al, sample->period,
sample->weight, sample->transaction)) {
pr_warning("problem incrementing symbol period, skipping event\n");
- return -1;
+ goto out_put;
}
/*
hists->stats.total_period += sample->period;
if (!al.filtered)
hists->stats.total_non_filtered_period += sample->period;
-
- return 0;
+ ret = 0;
+out_put:
+ addr_location__put(&al);
+ return ret;
}
static struct perf_tool tool = {
#include "util/debug.h"
#include "util/build-id.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include "util/parse-options.h"
struct perf_session *session;
bool build_ids;
bool sched_stat;
+ bool have_auxtrace;
const char *input_name;
struct perf_data_file output;
u64 bytes_written;
struct list_head samples;
+ struct itrace_synth_opts itrace_synth_opts;
};
struct event_entry {
union perf_event event[0];
};
-static int perf_event__repipe_synth(struct perf_tool *tool,
- union perf_event *event)
+static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
{
- struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
ssize_t size;
- size = perf_data_file__write(&inject->output, event,
- event->header.size);
+ size = perf_data_file__write(&inject->output, buf, sz);
if (size < 0)
return -errno;
return 0;
}
+static int perf_event__repipe_synth(struct perf_tool *tool,
+ union perf_event *event)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+
+ return output_bytes(inject, event, event->header.size);
+}
+
static int perf_event__repipe_oe_synth(struct perf_tool *tool,
union perf_event *event,
struct ordered_events *oe __maybe_unused)
return perf_event__repipe_synth(tool, event);
}
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+ char buf[4096];
+ ssize_t ssz;
+ int ret;
+
+ while (size > 0) {
+ ssz = read(fd, buf, min(size, (off_t)sizeof(buf)));
+ if (ssz < 0)
+ return -errno;
+ ret = output_bytes(inject, buf, ssz);
+ if (ret)
+ return ret;
+ size -= ssz;
+ }
+
+ return 0;
+}
+
+static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ struct perf_inject *inject = container_of(tool, struct perf_inject,
+ tool);
+ int ret;
+
+ inject->have_auxtrace = true;
+
+ if (!inject->output.is_pipe) {
+ off_t offset;
+
+ offset = lseek(inject->output.fd, 0, SEEK_CUR);
+ if (offset == -1)
+ return -errno;
+ ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
+ event, offset);
+ if (ret < 0)
+ return ret;
+ }
+
+ if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+ ret = output_bytes(inject, event, event->header.size);
+ if (ret < 0)
+ return ret;
+ ret = copy_bytes(inject, perf_data_file__fd(session->file),
+ event->auxtrace.size);
+ } else {
+ ret = output_bytes(inject, event,
+ event->header.size + event->auxtrace.size);
+ }
+ if (ret < 0)
+ return ret;
+
+ return event->auxtrace.size;
+}
+
+#else
+
+static s64
+perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+#endif
+
static int perf_event__repipe(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
return err;
}
+static int perf_event__repipe_comm(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_comm(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
+static int perf_event__repipe_exit(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_exit(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
static int perf_event__repipe_tracing_data(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session)
return err;
}
+static int perf_event__repipe_id_index(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ int err;
+
+ perf_event__repipe_synth(tool, event);
+ err = perf_event__process_id_index(tool, event, session);
+
+ return err;
+}
+
static int dso__read_build_id(struct dso *dso)
{
if (dso->has_build_id)
}
}
+ thread__put(thread);
repipe:
perf_event__repipe(tool, event, sample, machine);
return 0;
struct perf_session *session = inject->session;
struct perf_data_file *file_out = &inject->output;
int fd = perf_data_file__fd(file_out);
+ u64 output_data_offset;
signal(SIGINT, sig_handler);
- if (inject->build_ids || inject->sched_stat) {
+ if (inject->build_ids || inject->sched_stat ||
+ inject->itrace_synth_opts.set) {
inject->tool.mmap = perf_event__repipe_mmap;
inject->tool.mmap2 = perf_event__repipe_mmap2;
inject->tool.fork = perf_event__repipe_fork;
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
+ output_data_offset = session->header.data_offset;
+
if (inject->build_ids) {
inject->tool.sample = perf_event__inject_buildid;
} else if (inject->sched_stat) {
else if (!strncmp(name, "sched:sched_stat_", 17))
evsel->handler = perf_inject__sched_stat;
}
+ } else if (inject->itrace_synth_opts.set) {
+ session->itrace_synth_opts = &inject->itrace_synth_opts;
+ inject->itrace_synth_opts.inject = true;
+ inject->tool.comm = perf_event__repipe_comm;
+ inject->tool.exit = perf_event__repipe_exit;
+ inject->tool.id_index = perf_event__repipe_id_index;
+ inject->tool.auxtrace_info = perf_event__process_auxtrace_info;
+ inject->tool.auxtrace = perf_event__process_auxtrace;
+ inject->tool.ordered_events = true;
+ inject->tool.ordering_requires_timestamps = true;
+ /* Allow space in the header for new attributes */
+ output_data_offset = 4096;
}
+ if (!inject->itrace_synth_opts.set)
+ auxtrace_index__free(&session->auxtrace_index);
+
if (!file_out->is_pipe)
- lseek(fd, session->header.data_offset, SEEK_SET);
+ lseek(fd, output_data_offset, SEEK_SET);
ret = perf_session__process_events(session);
if (!file_out->is_pipe) {
- if (inject->build_ids)
+ if (inject->build_ids) {
perf_header__set_feat(&session->header,
HEADER_BUILD_ID);
+ if (inject->have_auxtrace)
+ dsos__hit_all(session);
+ }
+ /*
+ * The AUX areas have been removed and replaced with
+ * synthesized hardware events, so clear the feature flag.
+ */
+ if (inject->itrace_synth_opts.set)
+ perf_header__clear_feat(&session->header,
+ HEADER_AUXTRACE);
+ session->header.data_offset = output_data_offset;
session->header.data_size = inject->bytes_written;
perf_session__write_header(session, session->evlist, fd, true);
}
.fork = perf_event__repipe,
.exit = perf_event__repipe,
.lost = perf_event__repipe,
+ .aux = perf_event__repipe,
+ .itrace_start = perf_event__repipe,
.read = perf_event__repipe_sample,
.throttle = perf_event__repipe,
.unthrottle = perf_event__repipe,
.attr = perf_event__repipe_attr,
.tracing_data = perf_event__repipe_op2_synth,
+ .auxtrace_info = perf_event__repipe_op2_synth,
+ .auxtrace = perf_event__repipe_auxtrace,
+ .auxtrace_error = perf_event__repipe_op2_synth,
.finished_round = perf_event__repipe_oe_synth,
.build_id = perf_event__repipe_op2_synth,
.id_index = perf_event__repipe_op2_synth,
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
"kallsyms pathname"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
+ NULL, "opts", "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
const char * const inject_usage[] = {
#include "util/header.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/callchain.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
#include <linux/rbtree.h>
#include <linux/string.h>
#include <locale.h>
+#include <regex.h>
static int kmem_slab;
static int kmem_page;
static long kmem_page_size;
+static enum {
+ KMEM_SLAB,
+ KMEM_PAGE,
+} kmem_default = KMEM_SLAB; /* for backward compatibility */
struct alloc_stat;
-typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
+typedef int (*sort_fn_t)(void *, void *);
static int alloc_flag;
static int caller_flag;
return ret;
}
-static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
-static int callsite_cmp(struct alloc_stat *, struct alloc_stat *);
+static int ptr_cmp(void *, void *);
+static int slab_callsite_cmp(void *, void *);
static struct alloc_stat *search_alloc_stat(unsigned long ptr,
unsigned long call_site,
s_alloc->pingpong++;
s_caller = search_alloc_stat(0, s_alloc->call_site,
- &root_caller_stat, callsite_cmp);
+ &root_caller_stat,
+ slab_callsite_cmp);
if (!s_caller)
return -1;
s_caller->pingpong++;
static unsigned long nr_page_nomatch;
static bool use_pfn;
+static bool live_page;
+static struct perf_session *kmem_session;
#define MAX_MIGRATE_TYPES 6
#define MAX_PAGE_ORDER 11
struct page_stat {
struct rb_node node;
u64 page;
+ u64 callsite;
int order;
unsigned gfp_flags;
unsigned migrate_type;
int nr_free;
};
-static struct rb_root page_tree;
+static struct rb_root page_live_tree;
static struct rb_root page_alloc_tree;
static struct rb_root page_alloc_sorted;
+static struct rb_root page_caller_tree;
+static struct rb_root page_caller_sorted;
-static struct page_stat *search_page(unsigned long page, bool create)
+struct alloc_func {
+ u64 start;
+ u64 end;
+ char *name;
+};
+
+static int nr_alloc_funcs;
+static struct alloc_func *alloc_func_list;
+
+static int funcmp(const void *a, const void *b)
+{
+ const struct alloc_func *fa = a;
+ const struct alloc_func *fb = b;
+
+ if (fa->start > fb->start)
+ return 1;
+ else
+ return -1;
+}
+
+static int callcmp(const void *a, const void *b)
+{
+ const struct alloc_func *fa = a;
+ const struct alloc_func *fb = b;
+
+ if (fb->start <= fa->start && fa->end < fb->end)
+ return 0;
+
+ if (fa->start > fb->start)
+ return 1;
+ else
+ return -1;
+}
+
+static int build_alloc_func_list(void)
{
- struct rb_node **node = &page_tree.rb_node;
+ int ret;
+ struct map *kernel_map;
+ struct symbol *sym;
+ struct rb_node *node;
+ struct alloc_func *func;
+ struct machine *machine = &kmem_session->machines.host;
+ regex_t alloc_func_regex;
+ const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
+
+ ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);
+ if (ret) {
+ char err[BUFSIZ];
+
+ regerror(ret, &alloc_func_regex, err, sizeof(err));
+ pr_err("Invalid regex: %s\n%s", pattern, err);
+ return -EINVAL;
+ }
+
+ kernel_map = machine->vmlinux_maps[MAP__FUNCTION];
+ if (map__load(kernel_map, NULL) < 0) {
+ pr_err("cannot load kernel map\n");
+ return -ENOENT;
+ }
+
+ map__for_each_symbol(kernel_map, sym, node) {
+ if (regexec(&alloc_func_regex, sym->name, 0, NULL, 0))
+ continue;
+
+ func = realloc(alloc_func_list,
+ (nr_alloc_funcs + 1) * sizeof(*func));
+ if (func == NULL)
+ return -ENOMEM;
+
+ pr_debug("alloc func: %s\n", sym->name);
+ func[nr_alloc_funcs].start = sym->start;
+ func[nr_alloc_funcs].end = sym->end;
+ func[nr_alloc_funcs].name = sym->name;
+
+ alloc_func_list = func;
+ nr_alloc_funcs++;
+ }
+
+ qsort(alloc_func_list, nr_alloc_funcs, sizeof(*func), funcmp);
+
+ regfree(&alloc_func_regex);
+ return 0;
+}
+
+/*
+ * Find first non-memory allocation function from callchain.
+ * The allocation functions are in the 'alloc_func_list'.
+ */
+static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+ struct addr_location al;
+ struct machine *machine = &kmem_session->machines.host;
+ struct callchain_cursor_node *node;
+
+ if (alloc_func_list == NULL) {
+ if (build_alloc_func_list() < 0)
+ goto out;
+ }
+
+ al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+ sample__resolve_callchain(sample, NULL, evsel, &al, 16);
+
+ callchain_cursor_commit(&callchain_cursor);
+ while (true) {
+ struct alloc_func key, *caller;
+ u64 addr;
+
+ node = callchain_cursor_current(&callchain_cursor);
+ if (node == NULL)
+ break;
+
+ key.start = key.end = node->ip;
+ caller = bsearch(&key, alloc_func_list, nr_alloc_funcs,
+ sizeof(key), callcmp);
+ if (!caller) {
+ /* found */
+ if (node->map)
+ addr = map__unmap_ip(node->map, node->ip);
+ else
+ addr = node->ip;
+
+ return addr;
+ } else
+ pr_debug3("skipping alloc function: %s\n", caller->name);
+
+ callchain_cursor_advance(&callchain_cursor);
+ }
+
+out:
+ pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
+ return sample->ip;
+}
+
+struct sort_dimension {
+ const char name[20];
+ sort_fn_t cmp;
+ struct list_head list;
+};
+
+static LIST_HEAD(page_alloc_sort_input);
+static LIST_HEAD(page_caller_sort_input);
+
+static struct page_stat *
+__page_stat__findnew_page(struct page_stat *pstat, bool create)
+{
+ struct rb_node **node = &page_live_tree.rb_node;
struct rb_node *parent = NULL;
struct page_stat *data;
parent = *node;
data = rb_entry(*node, struct page_stat, node);
- cmp = data->page - page;
+ cmp = data->page - pstat->page;
if (cmp < 0)
node = &parent->rb_left;
else if (cmp > 0)
data = zalloc(sizeof(*data));
if (data != NULL) {
- data->page = page;
+ data->page = pstat->page;
+ data->order = pstat->order;
+ data->gfp_flags = pstat->gfp_flags;
+ data->migrate_type = pstat->migrate_type;
rb_link_node(&data->node, parent, node);
- rb_insert_color(&data->node, &page_tree);
+ rb_insert_color(&data->node, &page_live_tree);
}
return data;
}
-static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
+static struct page_stat *page_stat__find_page(struct page_stat *pstat)
{
- if (a->page > b->page)
- return -1;
- if (a->page < b->page)
- return 1;
- if (a->order > b->order)
- return -1;
- if (a->order < b->order)
- return 1;
- if (a->migrate_type > b->migrate_type)
- return -1;
- if (a->migrate_type < b->migrate_type)
- return 1;
- if (a->gfp_flags > b->gfp_flags)
- return -1;
- if (a->gfp_flags < b->gfp_flags)
- return 1;
- return 0;
+ return __page_stat__findnew_page(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_page(struct page_stat *pstat)
+{
+ return __page_stat__findnew_page(pstat, true);
}
-static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create)
+static struct page_stat *
+__page_stat__findnew_alloc(struct page_stat *pstat, bool create)
{
struct rb_node **node = &page_alloc_tree.rb_node;
struct rb_node *parent = NULL;
struct page_stat *data;
+ struct sort_dimension *sort;
while (*node) {
- s64 cmp;
+ int cmp = 0;
parent = *node;
data = rb_entry(*node, struct page_stat, node);
- cmp = page_stat_cmp(data, pstat);
+ list_for_each_entry(sort, &page_alloc_sort_input, list) {
+ cmp = sort->cmp(pstat, data);
+ if (cmp)
+ break;
+ }
+
if (cmp < 0)
node = &parent->rb_left;
else if (cmp > 0)
return data;
}
+static struct page_stat *page_stat__find_alloc(struct page_stat *pstat)
+{
+ return __page_stat__findnew_alloc(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_alloc(struct page_stat *pstat)
+{
+ return __page_stat__findnew_alloc(pstat, true);
+}
+
+static struct page_stat *
+__page_stat__findnew_caller(struct page_stat *pstat, bool create)
+{
+ struct rb_node **node = &page_caller_tree.rb_node;
+ struct rb_node *parent = NULL;
+ struct page_stat *data;
+ struct sort_dimension *sort;
+
+ while (*node) {
+ int cmp = 0;
+
+ parent = *node;
+ data = rb_entry(*node, struct page_stat, node);
+
+ list_for_each_entry(sort, &page_caller_sort_input, list) {
+ cmp = sort->cmp(pstat, data);
+ if (cmp)
+ break;
+ }
+
+ if (cmp < 0)
+ node = &parent->rb_left;
+ else if (cmp > 0)
+ node = &parent->rb_right;
+ else
+ return data;
+ }
+
+ if (!create)
+ return NULL;
+
+ data = zalloc(sizeof(*data));
+ if (data != NULL) {
+ data->callsite = pstat->callsite;
+ data->order = pstat->order;
+ data->gfp_flags = pstat->gfp_flags;
+ data->migrate_type = pstat->migrate_type;
+
+ rb_link_node(&data->node, parent, node);
+ rb_insert_color(&data->node, &page_caller_tree);
+ }
+
+ return data;
+}
+
+static struct page_stat *page_stat__find_caller(struct page_stat *pstat)
+{
+ return __page_stat__findnew_caller(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_caller(struct page_stat *pstat)
+{
+ return __page_stat__findnew_caller(pstat, true);
+}
+
static bool valid_page(u64 pfn_or_page)
{
if (use_pfn && pfn_or_page == -1UL)
return true;
}
+struct gfp_flag {
+ unsigned int flags;
+ char *compact_str;
+ char *human_readable;
+};
+
+static struct gfp_flag *gfps;
+static int nr_gfps;
+
+static int gfpcmp(const void *a, const void *b)
+{
+ const struct gfp_flag *fa = a;
+ const struct gfp_flag *fb = b;
+
+ return fa->flags - fb->flags;
+}
+
+/* see include/trace/events/gfpflags.h */
+static const struct {
+ const char *original;
+ const char *compact;
+} gfp_compact_table[] = {
+ { "GFP_TRANSHUGE", "THP" },
+ { "GFP_HIGHUSER_MOVABLE", "HUM" },
+ { "GFP_HIGHUSER", "HU" },
+ { "GFP_USER", "U" },
+ { "GFP_TEMPORARY", "TMP" },
+ { "GFP_KERNEL", "K" },
+ { "GFP_NOFS", "NF" },
+ { "GFP_ATOMIC", "A" },
+ { "GFP_NOIO", "NI" },
+ { "GFP_HIGH", "H" },
+ { "GFP_WAIT", "W" },
+ { "GFP_IO", "I" },
+ { "GFP_COLD", "CO" },
+ { "GFP_NOWARN", "NWR" },
+ { "GFP_REPEAT", "R" },
+ { "GFP_NOFAIL", "NF" },
+ { "GFP_NORETRY", "NR" },
+ { "GFP_COMP", "C" },
+ { "GFP_ZERO", "Z" },
+ { "GFP_NOMEMALLOC", "NMA" },
+ { "GFP_MEMALLOC", "MA" },
+ { "GFP_HARDWALL", "HW" },
+ { "GFP_THISNODE", "TN" },
+ { "GFP_RECLAIMABLE", "RC" },
+ { "GFP_MOVABLE", "M" },
+ { "GFP_NOTRACK", "NT" },
+ { "GFP_NO_KSWAPD", "NK" },
+ { "GFP_OTHER_NODE", "ON" },
+ { "GFP_NOWAIT", "NW" },
+};
+
+static size_t max_gfp_len;
+
+static char *compact_gfp_flags(char *gfp_flags)
+{
+ char *orig_flags = strdup(gfp_flags);
+ char *new_flags = NULL;
+ char *str, *pos = NULL;
+ size_t len = 0;
+
+ if (orig_flags == NULL)
+ return NULL;
+
+ str = strtok_r(orig_flags, "|", &pos);
+ while (str) {
+ size_t i;
+ char *new;
+ const char *cpt;
+
+ for (i = 0; i < ARRAY_SIZE(gfp_compact_table); i++) {
+ if (strcmp(gfp_compact_table[i].original, str))
+ continue;
+
+ cpt = gfp_compact_table[i].compact;
+ new = realloc(new_flags, len + strlen(cpt) + 2);
+ if (new == NULL) {
+ free(new_flags);
+ return NULL;
+ }
+
+ new_flags = new;
+
+ if (!len) {
+ strcpy(new_flags, cpt);
+ } else {
+ strcat(new_flags, "|");
+ strcat(new_flags, cpt);
+ len++;
+ }
+
+ len += strlen(cpt);
+ }
+
+ str = strtok_r(NULL, "|", &pos);
+ }
+
+ if (max_gfp_len < len)
+ max_gfp_len = len;
+
+ free(orig_flags);
+ return new_flags;
+}
+
+static char *compact_gfp_string(unsigned long gfp_flags)
+{
+ struct gfp_flag key = {
+ .flags = gfp_flags,
+ };
+ struct gfp_flag *gfp;
+
+ gfp = bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+ if (gfp)
+ return gfp->compact_str;
+
+ return NULL;
+}
+
+static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample,
+ unsigned int gfp_flags)
+{
+ struct pevent_record record = {
+ .cpu = sample->cpu,
+ .data = sample->raw_data,
+ .size = sample->raw_size,
+ };
+ struct trace_seq seq;
+ char *str, *pos = NULL;
+
+ if (nr_gfps) {
+ struct gfp_flag key = {
+ .flags = gfp_flags,
+ };
+
+ if (bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp))
+ return 0;
+ }
+
+ trace_seq_init(&seq);
+ pevent_event_info(&seq, evsel->tp_format, &record);
+
+ str = strtok_r(seq.buffer, " ", &pos);
+ while (str) {
+ if (!strncmp(str, "gfp_flags=", 10)) {
+ struct gfp_flag *new;
+
+ new = realloc(gfps, (nr_gfps + 1) * sizeof(*gfps));
+ if (new == NULL)
+ return -ENOMEM;
+
+ gfps = new;
+ new += nr_gfps++;
+
+ new->flags = gfp_flags;
+ new->human_readable = strdup(str + 10);
+ new->compact_str = compact_gfp_flags(str + 10);
+ if (!new->human_readable || !new->compact_str)
+ return -ENOMEM;
+
+ qsort(gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+ }
+
+ str = strtok_r(NULL, " ", &pos);
+ }
+
+ trace_seq_destroy(&seq);
+ return 0;
+}
+
static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
struct perf_sample *sample)
{
unsigned int migrate_type = perf_evsel__intval(evsel, sample,
"migratetype");
u64 bytes = kmem_page_size << order;
+ u64 callsite;
struct page_stat *pstat;
struct page_stat this = {
.order = order,
return 0;
}
+ if (parse_gfp_flags(evsel, sample, gfp_flags) < 0)
+ return -1;
+
+ callsite = find_callsite(evsel, sample);
+
/*
* This is to find the current page (with correct gfp flags and
* migrate type) at free event.
*/
- pstat = search_page(page, true);
+ this.page = page;
+ pstat = page_stat__findnew_page(&this);
if (pstat == NULL)
return -ENOMEM;
- pstat->order = order;
- pstat->gfp_flags = gfp_flags;
- pstat->migrate_type = migrate_type;
+ pstat->nr_alloc++;
+ pstat->alloc_bytes += bytes;
+ pstat->callsite = callsite;
+
+ if (!live_page) {
+ pstat = page_stat__findnew_alloc(&this);
+ if (pstat == NULL)
+ return -ENOMEM;
- this.page = page;
- pstat = search_page_alloc_stat(&this, true);
+ pstat->nr_alloc++;
+ pstat->alloc_bytes += bytes;
+ pstat->callsite = callsite;
+ }
+
+ this.callsite = callsite;
+ pstat = page_stat__findnew_caller(&this);
if (pstat == NULL)
return -ENOMEM;
nr_page_frees++;
total_page_free_bytes += bytes;
- pstat = search_page(page, false);
+ this.page = page;
+ pstat = page_stat__find_page(&this);
if (pstat == NULL) {
pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
page, order);
return 0;
}
- this.page = page;
this.gfp_flags = pstat->gfp_flags;
this.migrate_type = pstat->migrate_type;
+ this.callsite = pstat->callsite;
- rb_erase(&pstat->node, &page_tree);
+ rb_erase(&pstat->node, &page_live_tree);
free(pstat);
- pstat = search_page_alloc_stat(&this, false);
+ if (live_page) {
+ order_stats[this.order][this.migrate_type]--;
+ } else {
+ pstat = page_stat__find_alloc(&this);
+ if (pstat == NULL)
+ return -ENOMEM;
+
+ pstat->nr_free++;
+ pstat->free_bytes += bytes;
+ }
+
+ pstat = page_stat__find_caller(&this);
if (pstat == NULL)
return -ENOENT;
pstat->nr_free++;
pstat->free_bytes += bytes;
+ if (live_page) {
+ pstat->nr_alloc--;
+ pstat->alloc_bytes -= bytes;
+
+ if (pstat->nr_alloc == 0) {
+ rb_erase(&pstat->node, &page_caller_tree);
+ free(pstat);
+ }
+ }
+
return 0;
}
struct perf_evsel *evsel,
struct machine *machine)
{
+ int err = 0;
struct thread *thread = machine__findnew_thread(machine, sample->pid,
sample->tid);
if (evsel->handler != NULL) {
tracepoint_handler f = evsel->handler;
- return f(evsel, sample);
+ err = f(evsel, sample);
}
- return 0;
+ thread__put(thread);
+
+ return err;
}
static struct perf_tool perf_kmem = {
"UNKNOWN",
};
-static void __print_page_result(struct rb_root *root,
- struct perf_session *session __maybe_unused,
- int n_lines)
+static void __print_page_alloc_result(struct perf_session *session, int n_lines)
{
- struct rb_node *next = rb_first(root);
+ struct rb_node *next = rb_first(&page_alloc_sorted);
+ struct machine *machine = &session->machines.host;
const char *format;
+ int gfp_len = max(strlen("GFP flags"), max_gfp_len);
- printf("\n%.80s\n", graph_dotted_line);
- printf(" %-16s | Total alloc (KB) | Hits | Order | Mig.type | GFP flags\n",
- use_pfn ? "PFN" : "Page");
- printf("%.80s\n", graph_dotted_line);
+ printf("\n%.105s\n", graph_dotted_line);
+ printf(" %-16s | %5s alloc (KB) | Hits | Order | Mig.type | %-*s | Callsite\n",
+ use_pfn ? "PFN" : "Page", live_page ? "Live" : "Total",
+ gfp_len, "GFP flags");
+ printf("%.105s\n", graph_dotted_line);
if (use_pfn)
- format = " %16llu | %'16llu | %'9d | %5d | %8s | %08lx\n";
+ format = " %16llu | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
else
- format = " %016llx | %'16llu | %'9d | %5d | %8s | %08lx\n";
+ format = " %016llx | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
while (next && n_lines--) {
struct page_stat *data;
+ struct symbol *sym;
+ struct map *map;
+ char buf[32];
+ char *caller = buf;
data = rb_entry(next, struct page_stat, node);
+ sym = machine__find_kernel_function(machine, data->callsite,
+ &map, NULL);
+ if (sym && sym->name)
+ caller = sym->name;
+ else
+ scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
printf(format, (unsigned long long)data->page,
(unsigned long long)data->alloc_bytes / 1024,
data->nr_alloc, data->order,
migrate_type_str[data->migrate_type],
- (unsigned long)data->gfp_flags);
+ gfp_len, compact_gfp_string(data->gfp_flags), caller);
next = rb_next(next);
}
- if (n_lines == -1)
- printf(" ... | ... | ... | ... | ... | ... \n");
+ if (n_lines == -1) {
+ printf(" ... | ... | ... | ... | ... | %-*s | ...\n",
+ gfp_len, "...");
+ }
+
+ printf("%.105s\n", graph_dotted_line);
+}
+
+static void __print_page_caller_result(struct perf_session *session, int n_lines)
+{
+ struct rb_node *next = rb_first(&page_caller_sorted);
+ struct machine *machine = &session->machines.host;
+ int gfp_len = max(strlen("GFP flags"), max_gfp_len);
+
+ printf("\n%.105s\n", graph_dotted_line);
+ printf(" %5s alloc (KB) | Hits | Order | Mig.type | %-*s | Callsite\n",
+ live_page ? "Live" : "Total", gfp_len, "GFP flags");
+ printf("%.105s\n", graph_dotted_line);
+
+ while (next && n_lines--) {
+ struct page_stat *data;
+ struct symbol *sym;
+ struct map *map;
+ char buf[32];
+ char *caller = buf;
+
+ data = rb_entry(next, struct page_stat, node);
+ sym = machine__find_kernel_function(machine, data->callsite,
+ &map, NULL);
+ if (sym && sym->name)
+ caller = sym->name;
+ else
+ scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
+
+ printf(" %'16llu | %'9d | %5d | %8s | %-*s | %s\n",
+ (unsigned long long)data->alloc_bytes / 1024,
+ data->nr_alloc, data->order,
+ migrate_type_str[data->migrate_type],
+ gfp_len, compact_gfp_string(data->gfp_flags), caller);
+
+ next = rb_next(next);
+ }
+
+ if (n_lines == -1) {
+ printf(" ... | ... | ... | ... | %-*s | ...\n",
+ gfp_len, "...");
+ }
- printf("%.80s\n", graph_dotted_line);
+ printf("%.105s\n", graph_dotted_line);
+}
+
+static void print_gfp_flags(void)
+{
+ int i;
+
+ printf("#\n");
+ printf("# GFP flags\n");
+ printf("# ---------\n");
+ for (i = 0; i < nr_gfps; i++) {
+ printf("# %08x: %*s: %s\n", gfps[i].flags,
+ (int) max_gfp_len, gfps[i].compact_str,
+ gfps[i].human_readable);
+ }
}
static void print_slab_summary(void)
static void print_page_result(struct perf_session *session)
{
+ if (caller_flag || alloc_flag)
+ print_gfp_flags();
+ if (caller_flag)
+ __print_page_caller_result(session, caller_lines);
if (alloc_flag)
- __print_page_result(&page_alloc_sorted, session, alloc_lines);
+ __print_page_alloc_result(session, alloc_lines);
print_page_summary();
}
print_page_result(session);
}
-struct sort_dimension {
- const char name[20];
- sort_fn_t cmp;
- struct list_head list;
-};
-
-static LIST_HEAD(caller_sort);
-static LIST_HEAD(alloc_sort);
+static LIST_HEAD(slab_caller_sort);
+static LIST_HEAD(slab_alloc_sort);
+static LIST_HEAD(page_caller_sort);
+static LIST_HEAD(page_alloc_sort);
static void sort_slab_insert(struct rb_root *root, struct alloc_stat *data,
struct list_head *sort_list)
}
}
-static void sort_page_insert(struct rb_root *root, struct page_stat *data)
+static void sort_page_insert(struct rb_root *root, struct page_stat *data,
+ struct list_head *sort_list)
{
struct rb_node **new = &root->rb_node;
struct rb_node *parent = NULL;
+ struct sort_dimension *sort;
while (*new) {
struct page_stat *this;
this = rb_entry(*new, struct page_stat, node);
parent = *new;
- /* TODO: support more sort key */
- cmp = data->alloc_bytes - this->alloc_bytes;
+ list_for_each_entry(sort, sort_list, list) {
+ cmp = sort->cmp(data, this);
+ if (cmp)
+ break;
+ }
if (cmp > 0)
new = &parent->rb_left;
rb_insert_color(&data->node, root);
}
-static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted)
+static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted,
+ struct list_head *sort_list)
{
struct rb_node *node;
struct page_stat *data;
rb_erase(node, root);
data = rb_entry(node, struct page_stat, node);
- sort_page_insert(root_sorted, data);
+ sort_page_insert(root_sorted, data, sort_list);
}
}
{
if (kmem_slab) {
__sort_slab_result(&root_alloc_stat, &root_alloc_sorted,
- &alloc_sort);
+ &slab_alloc_sort);
__sort_slab_result(&root_caller_stat, &root_caller_sorted,
- &caller_sort);
+ &slab_caller_sort);
}
if (kmem_page) {
- __sort_page_result(&page_alloc_tree, &page_alloc_sorted);
+ if (live_page)
+ __sort_page_result(&page_live_tree, &page_alloc_sorted,
+ &page_alloc_sort);
+ else
+ __sort_page_result(&page_alloc_tree, &page_alloc_sorted,
+ &page_alloc_sort);
+
+ __sort_page_result(&page_caller_tree, &page_caller_sorted,
+ &page_caller_sort);
}
}
return err;
}
-static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r)
+/* slab sort keys */
+static int ptr_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->ptr < r->ptr)
return -1;
else if (l->ptr > r->ptr)
.cmp = ptr_cmp,
};
-static int callsite_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int slab_callsite_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->call_site < r->call_site)
return -1;
else if (l->call_site > r->call_site)
static struct sort_dimension callsite_sort_dimension = {
.name = "callsite",
- .cmp = callsite_cmp,
+ .cmp = slab_callsite_cmp,
};
-static int hit_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int hit_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->hit < r->hit)
return -1;
else if (l->hit > r->hit)
.cmp = hit_cmp,
};
-static int bytes_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int bytes_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->bytes_alloc < r->bytes_alloc)
return -1;
else if (l->bytes_alloc > r->bytes_alloc)
.cmp = bytes_cmp,
};
-static int frag_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int frag_cmp(void *a, void *b)
{
double x, y;
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
x = fragmentation(l->bytes_req, l->bytes_alloc);
y = fragmentation(r->bytes_req, r->bytes_alloc);
.cmp = frag_cmp,
};
-static int pingpong_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int pingpong_cmp(void *a, void *b)
{
+ struct alloc_stat *l = a;
+ struct alloc_stat *r = b;
+
if (l->pingpong < r->pingpong)
return -1;
else if (l->pingpong > r->pingpong)
.cmp = pingpong_cmp,
};
-static struct sort_dimension *avail_sorts[] = {
+/* page sort keys */
+static int page_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->page < r->page)
+ return -1;
+ else if (l->page > r->page)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_sort_dimension = {
+ .name = "page",
+ .cmp = page_cmp,
+};
+
+static int page_callsite_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->callsite < r->callsite)
+ return -1;
+ else if (l->callsite > r->callsite)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_callsite_sort_dimension = {
+ .name = "callsite",
+ .cmp = page_callsite_cmp,
+};
+
+static int page_hit_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->nr_alloc < r->nr_alloc)
+ return -1;
+ else if (l->nr_alloc > r->nr_alloc)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_hit_sort_dimension = {
+ .name = "hit",
+ .cmp = page_hit_cmp,
+};
+
+static int page_bytes_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->alloc_bytes < r->alloc_bytes)
+ return -1;
+ else if (l->alloc_bytes > r->alloc_bytes)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_bytes_sort_dimension = {
+ .name = "bytes",
+ .cmp = page_bytes_cmp,
+};
+
+static int page_order_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ if (l->order < r->order)
+ return -1;
+ else if (l->order > r->order)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension page_order_sort_dimension = {
+ .name = "order",
+ .cmp = page_order_cmp,
+};
+
+static int migrate_type_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ /* for internal use to find free'd page */
+ if (l->migrate_type == -1U)
+ return 0;
+
+ if (l->migrate_type < r->migrate_type)
+ return -1;
+ else if (l->migrate_type > r->migrate_type)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension migrate_type_sort_dimension = {
+ .name = "migtype",
+ .cmp = migrate_type_cmp,
+};
+
+static int gfp_flags_cmp(void *a, void *b)
+{
+ struct page_stat *l = a;
+ struct page_stat *r = b;
+
+ /* for internal use to find free'd page */
+ if (l->gfp_flags == -1U)
+ return 0;
+
+ if (l->gfp_flags < r->gfp_flags)
+ return -1;
+ else if (l->gfp_flags > r->gfp_flags)
+ return 1;
+ return 0;
+}
+
+static struct sort_dimension gfp_flags_sort_dimension = {
+ .name = "gfp",
+ .cmp = gfp_flags_cmp,
+};
+
+static struct sort_dimension *slab_sorts[] = {
&ptr_sort_dimension,
&callsite_sort_dimension,
&hit_sort_dimension,
&pingpong_sort_dimension,
};
-#define NUM_AVAIL_SORTS ((int)ARRAY_SIZE(avail_sorts))
+static struct sort_dimension *page_sorts[] = {
+ &page_sort_dimension,
+ &page_callsite_sort_dimension,
+ &page_hit_sort_dimension,
+ &page_bytes_sort_dimension,
+ &page_order_sort_dimension,
+ &migrate_type_sort_dimension,
+ &gfp_flags_sort_dimension,
+};
+
+static int slab_sort_dimension__add(const char *tok, struct list_head *list)
+{
+ struct sort_dimension *sort;
+ int i;
+
+ for (i = 0; i < (int)ARRAY_SIZE(slab_sorts); i++) {
+ if (!strcmp(slab_sorts[i]->name, tok)) {
+ sort = memdup(slab_sorts[i], sizeof(*slab_sorts[i]));
+ if (!sort) {
+ pr_err("%s: memdup failed\n", __func__);
+ return -1;
+ }
+ list_add_tail(&sort->list, list);
+ return 0;
+ }
+ }
+
+ return -1;
+}
-static int sort_dimension__add(const char *tok, struct list_head *list)
+static int page_sort_dimension__add(const char *tok, struct list_head *list)
{
struct sort_dimension *sort;
int i;
- for (i = 0; i < NUM_AVAIL_SORTS; i++) {
- if (!strcmp(avail_sorts[i]->name, tok)) {
- sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
+ for (i = 0; i < (int)ARRAY_SIZE(page_sorts); i++) {
+ if (!strcmp(page_sorts[i]->name, tok)) {
+ sort = memdup(page_sorts[i], sizeof(*page_sorts[i]));
if (!sort) {
pr_err("%s: memdup failed\n", __func__);
return -1;
return -1;
}
-static int setup_sorting(struct list_head *sort_list, const char *arg)
+static int setup_slab_sorting(struct list_head *sort_list, const char *arg)
+{
+ char *tok;
+ char *str = strdup(arg);
+ char *pos = str;
+
+ if (!str) {
+ pr_err("%s: strdup failed\n", __func__);
+ return -1;
+ }
+
+ while (true) {
+ tok = strsep(&pos, ",");
+ if (!tok)
+ break;
+ if (slab_sort_dimension__add(tok, sort_list) < 0) {
+ error("Unknown slab --sort key: '%s'", tok);
+ free(str);
+ return -1;
+ }
+ }
+
+ free(str);
+ return 0;
+}
+
+static int setup_page_sorting(struct list_head *sort_list, const char *arg)
{
char *tok;
char *str = strdup(arg);
tok = strsep(&pos, ",");
if (!tok)
break;
- if (sort_dimension__add(tok, sort_list) < 0) {
- error("Unknown --sort key: '%s'", tok);
+ if (page_sort_dimension__add(tok, sort_list) < 0) {
+ error("Unknown page --sort key: '%s'", tok);
free(str);
return -1;
}
if (!arg)
return -1;
- if (caller_flag > alloc_flag)
- return setup_sorting(&caller_sort, arg);
- else
- return setup_sorting(&alloc_sort, arg);
+ if (kmem_page > kmem_slab ||
+ (kmem_page == 0 && kmem_slab == 0 && kmem_default == KMEM_PAGE)) {
+ if (caller_flag > alloc_flag)
+ return setup_page_sorting(&page_caller_sort, arg);
+ else
+ return setup_page_sorting(&page_alloc_sort, arg);
+ } else {
+ if (caller_flag > alloc_flag)
+ return setup_slab_sorting(&slab_caller_sort, arg);
+ else
+ return setup_slab_sorting(&slab_alloc_sort, arg);
+ }
return 0;
}
if (kmem_slab)
rec_argc += ARRAY_SIZE(slab_events);
if (kmem_page)
- rec_argc += ARRAY_SIZE(page_events);
+ rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
rec_argv = calloc(rec_argc + 1, sizeof(char *));
rec_argv[i] = strdup(slab_events[j]);
}
if (kmem_page) {
+ rec_argv[i++] = strdup("-g");
+
for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
rec_argv[i] = strdup(page_events[j]);
}
return cmd_record(i, rec_argv, NULL);
}
+static int kmem_config(const char *var, const char *value, void *cb)
+{
+ if (!strcmp(var, "kmem.default")) {
+ if (!strcmp(value, "slab"))
+ kmem_default = KMEM_SLAB;
+ else if (!strcmp(value, "page"))
+ kmem_default = KMEM_PAGE;
+ else
+ pr_err("invalid default value ('slab' or 'page' required): %s\n",
+ value);
+ return 0;
+ }
+
+ return perf_default_config(var, value, cb);
+}
+
int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
{
- const char * const default_sort_order = "frag,hit,bytes";
+ const char * const default_slab_sort = "frag,hit,bytes";
+ const char * const default_page_sort = "bytes,hit";
struct perf_data_file file = {
.mode = PERF_DATA_MODE_READ,
};
OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
"show per-allocation statistics", parse_alloc_opt),
OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
- "sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
- parse_sort_opt),
+ "sort by keys: ptr, callsite, bytes, hit, pingpong, frag, "
+ "page, order, migtype, gfp", parse_sort_opt),
OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
parse_slab_opt),
OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
parse_page_opt),
+ OPT_BOOLEAN(0, "live", &live_page, "Show live page stat"),
OPT_END()
};
const char *const kmem_subcommands[] = { "record", "stat", NULL };
};
struct perf_session *session;
int ret = -1;
+ const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n";
+ perf_config(kmem_config, NULL);
argc = parse_options_subcommand(argc, argv, kmem_options,
kmem_subcommands, kmem_usage, 0);
if (!argc)
usage_with_options(kmem_usage, kmem_options);
- if (kmem_slab == 0 && kmem_page == 0)
- kmem_slab = 1; /* for backward compatibility */
+ if (kmem_slab == 0 && kmem_page == 0) {
+ if (kmem_default == KMEM_SLAB)
+ kmem_slab = 1;
+ else
+ kmem_page = 1;
+ }
if (!strncmp(argv[0], "rec", 3)) {
symbol__init(NULL);
file.path = input_name;
- session = perf_session__new(&file, false, &perf_kmem);
+ kmem_session = session = perf_session__new(&file, false, &perf_kmem);
if (session == NULL)
return -1;
+ if (kmem_slab) {
+ if (!perf_evlist__find_tracepoint_by_name(session->evlist,
+ "kmem:kmalloc")) {
+ pr_err(errmsg, "slab", "slab");
+ return -1;
+ }
+ }
+
if (kmem_page) {
- struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+ struct perf_evsel *evsel;
- if (evsel == NULL || evsel->tp_format == NULL) {
- pr_err("invalid event found.. aborting\n");
+ evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+ "kmem:mm_page_alloc");
+ if (evsel == NULL) {
+ pr_err(errmsg, "page", "page");
return -1;
}
kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+ symbol_conf.use_callchain = true;
}
symbol__init(&session->header.env);
if (cpu__setup_cpunode_map())
goto out_delete;
- if (list_empty(&caller_sort))
- setup_sorting(&caller_sort, default_sort_order);
- if (list_empty(&alloc_sort))
- setup_sorting(&alloc_sort, default_sort_order);
-
+ if (list_empty(&slab_caller_sort))
+ setup_slab_sorting(&slab_caller_sort, default_slab_sort);
+ if (list_empty(&slab_alloc_sort))
+ setup_slab_sorting(&slab_alloc_sort, default_slab_sort);
+ if (list_empty(&page_caller_sort))
+ setup_page_sorting(&page_caller_sort, default_page_sort);
+ if (list_empty(&page_alloc_sort))
+ setup_page_sorting(&page_alloc_sort, default_page_sort);
+
+ if (kmem_page) {
+ setup_page_sorting(&page_alloc_sort_input,
+ "page,order,migtype,gfp");
+ setup_page_sorting(&page_caller_sort_input,
+ "callsite,order,migtype,gfp");
+ }
ret = __cmd_kmem(session);
} else
usage_with_options(kmem_usage, kmem_options);
struct perf_evsel *evsel,
struct machine *machine)
{
+ int err = 0;
struct thread *thread;
struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
tool);
}
if (!handle_kvm_event(kvm, thread, evsel, sample))
- return -1;
+ err = -1;
- return 0;
+ thread__put(thread);
+ return err;
}
static int cpu_isa_config(struct perf_kvm_stat *kvm)
"show events other than"
" HLT (x86 only) or Wait state (s390 only)"
" that take longer than duration usecs"),
+ OPT_UINTEGER(0, "proc-map-timeout", &kvm->opts.proc_map_timeout,
+ "per thread proc mmap processing timeout in ms"),
OPT_END()
};
const char * const live_usage[] = {
kvm->opts.target.uses_mmap = false;
kvm->opts.target.uid_str = NULL;
kvm->opts.target.uid = UINT_MAX;
+ kvm->opts.proc_map_timeout = 500;
symbol__init(NULL);
disable_buildid_cache();
perf_session__set_id_hdr_size(kvm->session);
ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
- kvm->evlist->threads, false);
+ kvm->evlist->threads, false, kvm->opts.proc_map_timeout);
err = kvm_live_open_events(kvm);
if (err)
goto out;
t = perf_session__findnew(session, st->tid);
pr_info("%10d: %s\n", st->tid, thread__comm_str(t));
node = rb_next(node);
+ thread__put(t);
};
}
struct perf_evsel *evsel,
struct machine *machine)
{
+ int err = 0;
struct thread *thread = machine__findnew_thread(machine, sample->pid,
sample->tid);
if (evsel->handler != NULL) {
tracepoint_handler f = evsel->handler;
- return f(evsel, sample);
+ err = f(evsel, sample);
}
- return 0;
+ thread__put(thread);
+
+ return err;
}
static void sort_result(void)
}
if (al.filtered || (mem->hide_unresolved && al.sym == NULL))
- return 0;
+ goto out_put;
if (al.map != NULL)
al.map->dso->hit = 1;
symbol_conf.field_sep,
al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
al.sym ? al.sym->name : "???");
-
+out_put:
+ addr_location__put(&al);
return 0;
}
#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
#define DEFAULT_FUNC_FILTER "!_*"
+#define DEFAULT_LIST_FILTER "*:*"
/* Session management structure */
static struct {
+ int command; /* Command short_name */
bool list_events;
- bool force_add;
- bool show_lines;
- bool show_vars;
- bool show_ext_vars;
- bool show_funcs;
- bool mod_events;
bool uprobes;
bool quiet;
bool target_used;
int nevents;
struct perf_probe_event events[MAX_PROBES];
- struct strlist *dellist;
struct line_range line_range;
char *target;
- int max_probe_points;
struct strfilter *filter;
} params;
return ret;
}
+static int params_add_filter(const char *str)
+{
+ const char *err = NULL;
+ int ret = 0;
+
+ pr_debug2("Add filter: %s\n", str);
+ if (!params.filter) {
+ params.filter = strfilter__new(str, &err);
+ if (!params.filter)
+ ret = err ? -EINVAL : -ENOMEM;
+ } else
+ ret = strfilter__or(params.filter, str, &err);
+
+ if (ret == -EINVAL) {
+ pr_err("Filter parse error at %td.\n", err - str + 1);
+ pr_err("Source: \"%s\"\n", str);
+ pr_err(" %*c\n", (int)(err - str + 1), '^');
+ }
+
+ return ret;
+}
+
static int set_target(const char *ptr)
{
int found = 0;
len += sprintf(&buf[len], "%s ", argv[i]);
}
- params.mod_events = true;
ret = parse_probe_event(buf);
free(buf);
return ret;
}
-static int opt_add_probe_event(const struct option *opt __maybe_unused,
- const char *str, int unset __maybe_unused)
-{
- if (str) {
- params.mod_events = true;
- return parse_probe_event(str);
- } else
- return 0;
-}
-
-static int opt_del_probe_event(const struct option *opt __maybe_unused,
- const char *str, int unset __maybe_unused)
-{
- if (str) {
- params.mod_events = true;
- if (!params.dellist)
- params.dellist = strlist__new(true, NULL);
- strlist__add(params.dellist, str);
- }
- return 0;
-}
-
static int opt_set_target(const struct option *opt, const char *str,
int unset __maybe_unused)
{
return ret;
}
+/* Command option callbacks */
+
#ifdef HAVE_DWARF_SUPPORT
-static int opt_show_lines(const struct option *opt __maybe_unused,
+static int opt_show_lines(const struct option *opt,
const char *str, int unset __maybe_unused)
{
int ret = 0;
if (!str)
return 0;
- if (params.show_lines) {
+ if (params.command == 'L') {
pr_warning("Warning: more than one --line options are"
" detected. Only the first one is valid.\n");
return 0;
}
- params.show_lines = true;
+ params.command = opt->short_name;
ret = parse_line_range_desc(str, ¶ms.line_range);
return ret;
}
-static int opt_show_vars(const struct option *opt __maybe_unused,
+static int opt_show_vars(const struct option *opt,
const char *str, int unset __maybe_unused)
{
struct perf_probe_event *pev = ¶ms.events[params.nevents];
pr_err(" Error: '--vars' doesn't accept arguments.\n");
return -EINVAL;
}
- params.show_vars = true;
+ params.command = opt->short_name;
return ret;
}
#endif
+static int opt_add_probe_event(const struct option *opt,
+ const char *str, int unset __maybe_unused)
+{
+ if (str) {
+ params.command = opt->short_name;
+ return parse_probe_event(str);
+ }
+
+ return 0;
+}
+
+static int opt_set_filter_with_command(const struct option *opt,
+ const char *str, int unset)
+{
+ if (!unset)
+ params.command = opt->short_name;
+
+ if (str)
+ return params_add_filter(str);
+
+ return 0;
+}
static int opt_set_filter(const struct option *opt __maybe_unused,
const char *str, int unset __maybe_unused)
{
- const char *err;
-
- if (str) {
- pr_debug2("Set filter: %s\n", str);
- if (params.filter)
- strfilter__delete(params.filter);
- params.filter = strfilter__new(str, &err);
- if (!params.filter) {
- pr_err("Filter parse error at %td.\n", err - str + 1);
- pr_err("Source: \"%s\"\n", str);
- pr_err(" %*c\n", (int)(err - str + 1), '^');
- return -EINVAL;
- }
- }
+ if (str)
+ return params_add_filter(str);
return 0;
}
for (i = 0; i < params.nevents; i++)
clear_perf_probe_event(params.events + i);
- if (params.dellist)
- strlist__delete(params.dellist);
line_range__clear(¶ms.line_range);
free(params.target);
if (params.filter)
"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
"perf probe [<options>] --del '[GROUP:]EVENT' ...",
- "perf probe --list",
+ "perf probe --list [GROUP:]EVENT ...",
#ifdef HAVE_DWARF_SUPPORT
"perf probe [<options>] --line 'LINEDESC'",
"perf probe [<options>] --vars 'PROBEPOINT'",
#endif
+ "perf probe [<options>] --funcs",
NULL
-};
+ };
struct option options[] = {
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show parsed arguments, etc)"),
OPT_BOOLEAN('q', "quiet", ¶ms.quiet,
"be quiet (do not show any mesages)"),
- OPT_BOOLEAN('l', "list", ¶ms.list_events,
- "list up current probe events"),
+ OPT_CALLBACK_DEFAULT('l', "list", NULL, "[GROUP:]EVENT",
+ "list up probe events",
+ opt_set_filter_with_command, DEFAULT_LIST_FILTER),
OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
- opt_del_probe_event),
+ opt_set_filter_with_command),
OPT_CALLBACK('a', "add", NULL,
#ifdef HAVE_DWARF_SUPPORT
"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
"\t\tARG:\tProbe argument (kprobe-tracer argument format.)\n",
#endif
opt_add_probe_event),
- OPT_BOOLEAN('f', "force", ¶ms.force_add, "forcibly add events"
+ OPT_BOOLEAN('f', "force", &probe_conf.force_add, "forcibly add events"
" with existing name"),
#ifdef HAVE_DWARF_SUPPORT
OPT_CALLBACK('L', "line", NULL,
OPT_CALLBACK('V', "vars", NULL,
"FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT",
"Show accessible variables on PROBEDEF", opt_show_vars),
- OPT_BOOLEAN('\0', "externs", ¶ms.show_ext_vars,
+ OPT_BOOLEAN('\0', "externs", &probe_conf.show_ext_vars,
"Show external variables too (with --vars only)"),
+ OPT_BOOLEAN('\0', "range", &probe_conf.show_location_range,
+ "Show variables location range in scope (with --vars only)"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
OPT_STRING('s', "source", &symbol_conf.source_prefix,
OPT_CALLBACK('m', "module", NULL, "modname|path",
"target module name (for online) or path (for offline)",
opt_set_target),
+ OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines,
+ "Don't search inlined functions"),
#endif
OPT__DRY_RUN(&probe_event_dry_run),
- OPT_INTEGER('\0', "max-probes", ¶ms.max_probe_points,
+ OPT_INTEGER('\0', "max-probes", &probe_conf.max_probes,
"Set how many probe points can be found for a probe."),
- OPT_BOOLEAN('F', "funcs", ¶ms.show_funcs,
- "Show potential probe-able functions."),
+ OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
+ "Show potential probe-able functions.",
+ opt_set_filter_with_command, DEFAULT_FUNC_FILTER),
OPT_CALLBACK('\0', "filter", NULL,
"[!]FILTER", "Set a filter (with --vars/funcs only)\n"
"\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n"
set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
#endif
+ set_option_flag(options, 'F', "funcs", PARSE_OPT_EXCLUSIVE);
argc = parse_options(argc, argv, options, probe_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
pr_warning(" Error: '-' is not supported.\n");
usage_with_options(probe_usage, options);
}
+ if (params.command && params.command != 'a') {
+ pr_warning(" Error: another command except --add is set.\n");
+ usage_with_options(probe_usage, options);
+ }
ret = parse_probe_event_argv(argc, argv);
if (ret < 0) {
pr_err_with_code(" Error: Command Parse Error.", ret);
return ret;
}
+ params.command = 'a';
}
if (params.quiet) {
verbose = -1;
}
- if (params.max_probe_points == 0)
- params.max_probe_points = MAX_PROBES;
-
- if ((!params.nevents && !params.dellist && !params.list_events &&
- !params.show_lines && !params.show_funcs))
- usage_with_options(probe_usage, options);
+ if (probe_conf.max_probes == 0)
+ probe_conf.max_probes = MAX_PROBES;
/*
* Only consider the user's kernel image path if given.
*/
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
- if (params.list_events) {
+ switch (params.command) {
+ case 'l':
if (params.uprobes) {
pr_warning(" Error: Don't use --list with --exec.\n");
usage_with_options(probe_usage, options);
}
- ret = show_perf_probe_events();
+ ret = show_perf_probe_events(params.filter);
if (ret < 0)
pr_err_with_code(" Error: Failed to show event list.", ret);
return ret;
- }
- if (params.show_funcs) {
- if (!params.filter)
- params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
- NULL);
+ case 'F':
ret = show_available_funcs(params.target, params.filter,
params.uprobes);
- strfilter__delete(params.filter);
- params.filter = NULL;
if (ret < 0)
pr_err_with_code(" Error: Failed to show functions.", ret);
return ret;
- }
-
#ifdef HAVE_DWARF_SUPPORT
- if (params.show_lines) {
+ case 'L':
ret = show_line_range(¶ms.line_range, params.target,
params.uprobes);
if (ret < 0)
pr_err_with_code(" Error: Failed to show lines.", ret);
return ret;
- }
- if (params.show_vars) {
+ case 'V':
if (!params.filter)
params.filter = strfilter__new(DEFAULT_VAR_FILTER,
NULL);
ret = show_available_vars(params.events, params.nevents,
- params.max_probe_points,
- params.target,
- params.filter,
- params.show_ext_vars);
- strfilter__delete(params.filter);
- params.filter = NULL;
+ params.filter);
if (ret < 0)
pr_err_with_code(" Error: Failed to show vars.", ret);
return ret;
- }
#endif
-
- if (params.dellist) {
- ret = del_perf_probe_events(params.dellist);
+ case 'd':
+ ret = del_perf_probe_events(params.filter);
if (ret < 0) {
pr_err_with_code(" Error: Failed to delete events.", ret);
return ret;
}
- }
-
- if (params.nevents) {
+ break;
+ case 'a':
/* Ensure the last given target is used */
if (params.target && !params.target_used) {
pr_warning(" Error: -x/-m must follow the probe definitions.\n");
usage_with_options(probe_usage, options);
}
- ret = add_perf_probe_events(params.events, params.nevents,
- params.max_probe_points,
- params.force_add);
+ ret = add_perf_probe_events(params.events, params.nevents);
if (ret < 0) {
pr_err_with_code(" Error: Failed to add events.", ret);
return ret;
}
+ break;
+ default:
+ usage_with_options(probe_usage, options);
}
return 0;
}
cleanup_params();
}
- return ret;
+ return ret < 0 ? ret : 0;
}
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/data.h"
+#include "util/auxtrace.h"
+#include "util/parse-branch-options.h"
#include <unistd.h>
#include <sched.h>
struct record_opts opts;
u64 bytes_written;
struct perf_data_file file;
+ struct auxtrace_record *itr;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
return rc;
}
-static volatile int done = 0;
+static volatile int done;
static volatile int signr = -1;
-static volatile int child_finished = 0;
+static volatile int child_finished;
+static volatile int auxtrace_snapshot_enabled;
+static volatile int auxtrace_snapshot_err;
+static volatile int auxtrace_record__snapshot_started;
static void sig_handler(int sig)
{
raise(signr);
}
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int record__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event, void *data1,
+ size_t len1, void *data2, size_t len2)
+{
+ struct record *rec = container_of(tool, struct record, tool);
+ struct perf_data_file *file = &rec->file;
+ size_t padding;
+ u8 pad[8] = {0};
+
+ if (!perf_data_file__is_pipe(file)) {
+ off_t file_offset;
+ int fd = perf_data_file__fd(file);
+ int err;
+
+ file_offset = lseek(fd, 0, SEEK_CUR);
+ if (file_offset == -1)
+ return -1;
+ err = auxtrace_index__auxtrace_event(&rec->session->auxtrace_index,
+ event, file_offset);
+ if (err)
+ return err;
+ }
+
+ /* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
+ padding = (len1 + len2) & 7;
+ if (padding)
+ padding = 8 - padding;
+
+ record__write(rec, event, event->header.size);
+ record__write(rec, data1, len1);
+ if (len2)
+ record__write(rec, data2, len2);
+ record__write(rec, &pad, padding);
+
+ return 0;
+}
+
+static int record__auxtrace_mmap_read(struct record *rec,
+ struct auxtrace_mmap *mm)
+{
+ int ret;
+
+ ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+ record__process_auxtrace);
+ if (ret < 0)
+ return ret;
+
+ if (ret)
+ rec->samples++;
+
+ return 0;
+}
+
+static int record__auxtrace_mmap_read_snapshot(struct record *rec,
+ struct auxtrace_mmap *mm)
+{
+ int ret;
+
+ ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
+ record__process_auxtrace,
+ rec->opts.auxtrace_snapshot_size);
+ if (ret < 0)
+ return ret;
+
+ if (ret)
+ rec->samples++;
+
+ return 0;
+}
+
+static int record__auxtrace_read_snapshot_all(struct record *rec)
+{
+ int i;
+ int rc = 0;
+
+ for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+ struct auxtrace_mmap *mm =
+ &rec->evlist->mmap[i].auxtrace_mmap;
+
+ if (!mm->base)
+ continue;
+
+ if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
+ rc = -1;
+ goto out;
+ }
+ }
+out:
+ return rc;
+}
+
+static void record__read_auxtrace_snapshot(struct record *rec)
+{
+ pr_debug("Recording AUX area tracing snapshot\n");
+ if (record__auxtrace_read_snapshot_all(rec) < 0) {
+ auxtrace_snapshot_err = -1;
+ } else {
+ auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr);
+ if (!auxtrace_snapshot_err)
+ auxtrace_snapshot_enabled = 1;
+ }
+}
+
+#else
+
+static inline
+int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
+ struct auxtrace_mmap *mm __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+void record__read_auxtrace_snapshot(struct record *rec __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
+{
+ return 0;
+}
+
+#endif
+
static int record__open(struct record *rec)
{
char msg[512];
goto out;
}
- if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+ if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+ opts->auxtrace_mmap_pages,
+ opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
"/proc/sys/kernel/perf_event_mlock_kb,\n"
"or try again with a smaller value of -m/--mmap_pages.\n"
- "(current value: %u)\n", opts->mmap_pages);
+ "(current value: %u,%u)\n",
+ opts->mmap_pages, opts->auxtrace_mmap_pages);
rc = -errno;
} else {
pr_err("failed to mmap with %d (%s)\n", errno,
struct perf_data_file *file = &rec->file;
struct perf_session *session = rec->session;
- u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
- if (size == 0)
+ if (file->size == 0)
return 0;
- file->size = size;
-
/*
* During this process, it'll load kernel map and replace the
* dso->long_name to a real pathname it found. In this case
int rc = 0;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+ struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+
if (rec->evlist->mmap[i].base) {
if (record__mmap_read(rec, i) != 0) {
rc = -1;
goto out;
}
}
+
+ if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
+ record__auxtrace_mmap_read(rec, mm) != 0) {
+ rc = -1;
+ goto out;
+ }
}
/*
if (!rec->opts.branch_stack)
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+
+ if (!rec->opts.full_auxtrace)
+ perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
}
static volatile int workload_exec_errno;
child_finished = 1;
}
+static void snapshot_sig_handler(int sig);
+
static int __cmd_record(struct record *rec, int argc, const char **argv)
{
int err;
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGTERM, sig_handler);
+ if (rec->opts.auxtrace_snapshot_mode)
+ signal(SIGUSR2, snapshot_sig_handler);
+ else
+ signal(SIGUSR2, SIG_IGN);
session = perf_session__new(file, false, tool);
if (session == NULL) {
}
}
+ if (rec->opts.full_auxtrace) {
+ err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+ session, process_synthesized_event);
+ if (err)
+ goto out_delete_session;
+ }
+
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine);
if (err < 0)
}
err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
- process_synthesized_event, opts->sample_address);
+ process_synthesized_event, opts->sample_address,
+ opts->proc_map_timeout);
if (err != 0)
goto out_child;
perf_evlist__enable(rec->evlist);
}
+ auxtrace_snapshot_enabled = 1;
for (;;) {
int hits = rec->samples;
if (record__mmap_read_all(rec) < 0) {
+ auxtrace_snapshot_enabled = 0;
err = -1;
goto out_child;
}
+ if (auxtrace_record__snapshot_started) {
+ auxtrace_record__snapshot_started = 0;
+ if (!auxtrace_snapshot_err)
+ record__read_auxtrace_snapshot(rec);
+ if (auxtrace_snapshot_err) {
+ pr_err("AUX area tracing snapshot failed\n");
+ err = -1;
+ goto out_child;
+ }
+ }
+
if (hits == rec->samples) {
if (done || draining)
break;
* disable events in this case.
*/
if (done && !disabled && !target__none(&opts->target)) {
+ auxtrace_snapshot_enabled = 0;
perf_evlist__disable(rec->evlist);
disabled = true;
}
}
+ auxtrace_snapshot_enabled = 0;
if (forks && workload_exec_errno) {
char msg[STRERR_BUFSIZE];
if (!err && !file->is_pipe) {
rec->session->header.data_size += rec->bytes_written;
+ file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
- if (!rec->no_buildid)
+ if (!rec->no_buildid) {
process_buildids(rec);
+ /*
+ * We take all buildids when the file contains
+ * AUX area tracing data because we do not decode the
+ * trace because it would take too long.
+ */
+ if (rec->opts.full_auxtrace)
+ dsos__hit_all(rec->session);
+ }
perf_session__write_header(rec->session, rec->evlist, fd, true);
}
if (!err && !quiet) {
char samples[128];
- if (rec->samples)
+ if (rec->samples && !rec->opts.full_auxtrace)
scnprintf(samples, sizeof(samples),
" (%" PRIu64 " samples)", rec->samples);
else
return status;
}
-#define BRANCH_OPT(n, m) \
- { .name = n, .mode = (m) }
-
-#define BRANCH_END { .name = NULL }
-
-struct branch_mode {
- const char *name;
- int mode;
-};
-
-static const struct branch_mode branch_modes[] = {
- BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
- BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
- BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
- BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
- BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
- BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
- BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
- BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
- BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
- BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
- BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
- BRANCH_END
-};
-
-static int
-parse_branch_stack(const struct option *opt, const char *str, int unset)
-{
-#define ONLY_PLM \
- (PERF_SAMPLE_BRANCH_USER |\
- PERF_SAMPLE_BRANCH_KERNEL |\
- PERF_SAMPLE_BRANCH_HV)
-
- uint64_t *mode = (uint64_t *)opt->value;
- const struct branch_mode *br;
- char *s, *os = NULL, *p;
- int ret = -1;
-
- if (unset)
- return 0;
-
- /*
- * cannot set it twice, -b + --branch-filter for instance
- */
- if (*mode)
- return -1;
-
- /* str may be NULL in case no arg is passed to -b */
- if (str) {
- /* because str is read-only */
- s = os = strdup(str);
- if (!s)
- return -1;
-
- for (;;) {
- p = strchr(s, ',');
- if (p)
- *p = '\0';
-
- for (br = branch_modes; br->name; br++) {
- if (!strcasecmp(s, br->name))
- break;
- }
- if (!br->name) {
- ui__warning("unknown branch filter %s,"
- " check man page\n", s);
- goto error;
- }
-
- *mode |= br->mode;
-
- if (!p)
- break;
-
- s = p + 1;
- }
- }
- ret = 0;
-
- /* default to any branch */
- if ((*mode & ~ONLY_PLM) == 0) {
- *mode = PERF_SAMPLE_BRANCH_ANY;
- }
-error:
- free(os);
- return ret;
-}
-
static void callchain_debug(void)
{
static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" };
return -1;
}
+static int record__parse_mmap_pages(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct record_opts *opts = opt->value;
+ char *s, *p;
+ unsigned int mmap_pages;
+ int ret;
+
+ if (!str)
+ return -EINVAL;
+
+ s = strdup(str);
+ if (!s)
+ return -ENOMEM;
+
+ p = strchr(s, ',');
+ if (p)
+ *p = '\0';
+
+ if (*s) {
+ ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
+ if (ret)
+ goto out_free;
+ opts->mmap_pages = mmap_pages;
+ }
+
+ if (!p) {
+ ret = 0;
+ goto out_free;
+ }
+
+ ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
+ if (ret)
+ goto out_free;
+
+ opts->auxtrace_mmap_pages = mmap_pages;
+
+out_free:
+ free(s);
+ return ret;
+}
+
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
.uses_mmap = true,
.default_per_cpu = true,
},
+ .proc_map_timeout = 500,
},
.tool = {
.sample = process_sample_event,
&record.opts.no_inherit_set,
"child tasks do not inherit counters"),
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
- OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
- "number of mmap data pages",
- perf_evlist__parse_mmap_pages),
+ OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
+ "number of mmap data pages and AUX area tracing mmap pages",
+ record__parse_mmap_pages),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
"per thread counts"),
- OPT_BOOLEAN('d', "data", &record.opts.sample_address,
- "Sample addresses"),
- OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
- OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
+ OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+ OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Record the sample timestamps"),
+ OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
"don't sample"),
OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
OPT_CALLBACK('k', "clockid", &record.opts,
"clockid", "clockid to use for events, see clock_gettime()",
parse_clockid),
+ OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
+ "opts", "AUX area tracing Snapshot Mode", ""),
+ OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
+ "per thread proc mmap processing timeout in ms"),
OPT_END()
};
int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
{
- int err = -ENOMEM;
+ int err;
struct record *rec = &record;
char errbuf[BUFSIZ];
usage_with_options(record_usage, record_options);
}
+ if (!rec->itr) {
+ rec->itr = auxtrace_record__init(rec->evlist, &err);
+ if (err)
+ return err;
+ }
+
+ err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
+ rec->opts.auxtrace_snapshot_opts);
+ if (err)
+ return err;
+
+ err = -ENOMEM;
+
symbol__init(NULL);
if (symbol_conf.kptr_restrict)
if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
+ err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
+ if (err)
+ goto out_symbol_exit;
+
if (record_opts__config(&rec->opts)) {
err = -EINVAL;
goto out_symbol_exit;
out_symbol_exit:
perf_evlist__delete(rec->evlist);
symbol__exit();
+ auxtrace_record__free(rec->itr);
return err;
}
+
+static void snapshot_sig_handler(int sig __maybe_unused)
+{
+ if (!auxtrace_snapshot_enabled)
+ return;
+ auxtrace_snapshot_enabled = 0;
+ auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr);
+ auxtrace_record__snapshot_started = 1;
+}
#include "util/data.h"
#include "arch/common.h"
+#include "util/auxtrace.h"
+
#include <dlfcn.h>
#include <linux/bitmap.h>
struct report *rep = container_of(tool, struct report, tool);
struct addr_location al;
struct hist_entry_iter iter = {
- .hide_unresolved = rep->hide_unresolved,
- .add_entry_cb = hist_iter__report_callback,
+ .evsel = evsel,
+ .sample = sample,
+ .hide_unresolved = rep->hide_unresolved,
+ .add_entry_cb = hist_iter__report_callback,
};
- int ret;
+ int ret = 0;
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
pr_debug("problem processing %d event, skipping it.\n",
}
if (rep->hide_unresolved && al.sym == NULL)
- return 0;
+ goto out_put;
if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
- return 0;
+ goto out_put;
if (sort__mode == SORT_MODE__BRANCH)
iter.ops = &hist_iter_branch;
if (al.map != NULL)
al.map->dso->hit = 1;
- ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
- rep);
+ ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep);
if (ret < 0)
pr_debug("problem adding hist entry, skipping event\n");
-
+out_put:
+ addr_location__put(&al);
return ret;
}
{
struct perf_evsel *pos;
+ fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
evlist__for_each(evlist, pos) {
struct hists *hists = evsel__hists(pos);
const char *evname = perf_evsel__name(pos);
}
if (sort_order == NULL &&
- parent_pattern == default_parent_pattern) {
+ parent_pattern == default_parent_pattern)
fprintf(stdout, "#\n# (%s)\n#\n", help);
- if (rep->show_threads) {
- bool style = !strcmp(rep->pretty_printing_style, "raw");
- perf_read_values_display(stdout, &rep->show_threads_values,
- style);
- perf_read_values_destroy(&rep->show_threads_values);
- }
+ if (rep->show_threads) {
+ bool style = !strcmp(rep->pretty_printing_style, "raw");
+ perf_read_values_display(stdout, &rep->show_threads_values,
+ style);
+ perf_read_values_destroy(&rep->show_threads_values);
}
return 0;
int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
{
struct perf_session *session;
+ struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
struct stat st;
bool has_br_stack = false;
int branch_mode = -1;
.attr = perf_event__process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .id_index = perf_event__process_id_index,
+ .auxtrace_info = perf_event__process_auxtrace_info,
+ .auxtrace = perf_event__process_auxtrace,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
"Don't show entries under that percent", parse_percent_limit),
OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
"how to display percentage of filtered entries", parse_filter_percentage),
+ OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+ "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
struct perf_data_file file = {
report.queue_size);
}
+ session->itrace_synth_opts = &itrace_synth_opts;
+
report.session = session;
has_br_stack = perf_header__has_feat(&session->header,
goto error;
}
- /* Force tty output for header output. */
- if (report.header || report.header_only)
+ /* Force tty output for header output and per-thread stat. */
+ if (report.header || report.header_only || report.show_threads)
use_browser = 0;
if (strcmp(input_name, "-") != 0)
u64 total_lat;
u64 nb_atoms;
u64 total_runtime;
+ int num_merged;
};
typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);
u64 all_runtime;
u64 all_count;
u64 cpu_last_switched[MAX_CPUS];
- struct rb_root atom_root, sorted_atom_root;
+ struct rb_root atom_root, sorted_atom_root, merged_atom_root;
struct list_head sort_list, cmp_pid;
bool force;
+ bool skip_merge;
};
static u64 get_nsecs(void)
if (child == NULL || parent == NULL) {
pr_debug("thread does not exist on fork event: child %p, parent %p\n",
child, parent);
- return 0;
+ goto out_put;
}
if (verbose) {
register_pid(sched, parent->tid, thread__comm_str(parent));
register_pid(sched, child->tid, thread__comm_str(child));
+out_put:
+ thread__put(child);
+ thread__put(parent);
return 0;
}
struct work_atoms *out_events, *in_events;
struct thread *sched_out, *sched_in;
u64 timestamp0, timestamp = sample->time;
- int cpu = sample->cpu;
+ int cpu = sample->cpu, err = -1;
s64 delta;
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
sched_out = machine__findnew_thread(machine, -1, prev_pid);
sched_in = machine__findnew_thread(machine, -1, next_pid);
+ if (sched_out == NULL || sched_in == NULL)
+ goto out_put;
out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
if (!out_events) {
if (thread_atoms_insert(sched, sched_out))
- return -1;
+ goto out_put;
out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
if (!out_events) {
pr_err("out-event: Internal tree error");
- return -1;
+ goto out_put;
}
}
if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp))
in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
if (!in_events) {
if (thread_atoms_insert(sched, sched_in))
- return -1;
+ goto out_put;
in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
if (!in_events) {
pr_err("in-event: Internal tree error");
- return -1;
+ goto out_put;
}
/*
* Take came in we have not heard about yet,
* add in an initial atom in runnable state:
*/
if (add_sched_out_event(in_events, 'R', timestamp))
- return -1;
+ goto out_put;
}
add_sched_in_event(in_events, timestamp);
-
- return 0;
+ err = 0;
+out_put:
+ thread__put(sched_out);
+ thread__put(sched_in);
+ return err;
}
static int latency_runtime_event(struct perf_sched *sched,
struct thread *thread = machine__findnew_thread(machine, -1, pid);
struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
u64 timestamp = sample->time;
- int cpu = sample->cpu;
+ int cpu = sample->cpu, err = -1;
+
+ if (thread == NULL)
+ return -1;
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
if (!atoms) {
if (thread_atoms_insert(sched, thread))
- return -1;
+ goto out_put;
atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
if (!atoms) {
pr_err("in-event: Internal tree error");
- return -1;
+ goto out_put;
}
if (add_sched_out_event(atoms, 'R', timestamp))
- return -1;
+ goto out_put;
}
add_runtime_event(atoms, runtime, timestamp);
- return 0;
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
}
static int latency_wakeup_event(struct perf_sched *sched,
struct work_atom *atom;
struct thread *wakee;
u64 timestamp = sample->time;
+ int err = -1;
wakee = machine__findnew_thread(machine, -1, pid);
+ if (wakee == NULL)
+ return -1;
atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
if (!atoms) {
if (thread_atoms_insert(sched, wakee))
- return -1;
+ goto out_put;
atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
if (!atoms) {
pr_err("wakeup-event: Internal tree error");
- return -1;
+ goto out_put;
}
if (add_sched_out_event(atoms, 'S', timestamp))
- return -1;
+ goto out_put;
}
BUG_ON(list_empty(&atoms->work_list));
* skip in this case.
*/
if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING)
- return 0;
+ goto out_ok;
sched->nr_timestamps++;
if (atom->sched_out_time > timestamp) {
sched->nr_unordered_timestamps++;
- return 0;
+ goto out_ok;
}
atom->state = THREAD_WAIT_CPU;
atom->wake_up_time = timestamp;
- return 0;
+out_ok:
+ err = 0;
+out_put:
+ thread__put(wakee);
+ return err;
}
static int latency_migrate_task_event(struct perf_sched *sched,
struct work_atoms *atoms;
struct work_atom *atom;
struct thread *migrant;
+ int err = -1;
/*
* Only need to worry about migration when profiling one CPU.
return 0;
migrant = machine__findnew_thread(machine, -1, pid);
+ if (migrant == NULL)
+ return -1;
atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
if (!atoms) {
if (thread_atoms_insert(sched, migrant))
- return -1;
+ goto out_put;
register_pid(sched, migrant->tid, thread__comm_str(migrant));
atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
if (!atoms) {
pr_err("migration-event: Internal tree error");
- return -1;
+ goto out_put;
}
if (add_sched_out_event(atoms, 'R', timestamp))
- return -1;
+ goto out_put;
}
BUG_ON(list_empty(&atoms->work_list));
if (atom->sched_out_time > timestamp)
sched->nr_unordered_timestamps++;
-
- return 0;
+ err = 0;
+out_put:
+ thread__put(migrant);
+ return err;
}
static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list)
sched->all_runtime += work_list->total_runtime;
sched->all_count += work_list->nb_atoms;
- ret = printf(" %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
+ if (work_list->num_merged > 1)
+ ret = printf(" %s:(%d) ", thread__comm_str(work_list->thread), work_list->num_merged);
+ else
+ ret = printf(" %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
for (i = 0; i < 24 - ret; i++)
printf(" ");
static void perf_sched__sort_lat(struct perf_sched *sched)
{
struct rb_node *node;
-
+ struct rb_root *root = &sched->atom_root;
+again:
for (;;) {
struct work_atoms *data;
- node = rb_first(&sched->atom_root);
+ node = rb_first(root);
if (!node)
break;
- rb_erase(node, &sched->atom_root);
+ rb_erase(node, root);
data = rb_entry(node, struct work_atoms, node);
__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
}
+ if (root == &sched->atom_root) {
+ root = &sched->merged_atom_root;
+ goto again;
+ }
}
static int process_sched_wakeup_event(struct perf_tool *tool,
}
sched_in = machine__findnew_thread(machine, -1, next_pid);
+ if (sched_in == NULL)
+ return -1;
- sched->curr_thread[this_cpu] = sched_in;
+ sched->curr_thread[this_cpu] = thread__get(sched_in);
printf(" ");
printf("\n");
}
+ thread__put(sched_in);
+
return 0;
}
}
}
+static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+ struct work_atoms *this;
+ const char *comm = thread__comm_str(data->thread), *this_comm;
+
+ while (*new) {
+ int cmp;
+
+ this = container_of(*new, struct work_atoms, node);
+ parent = *new;
+
+ this_comm = thread__comm_str(this->thread);
+ cmp = strcmp(comm, this_comm);
+ if (cmp > 0) {
+ new = &((*new)->rb_left);
+ } else if (cmp < 0) {
+ new = &((*new)->rb_right);
+ } else {
+ this->num_merged++;
+ this->total_runtime += data->total_runtime;
+ this->nb_atoms += data->nb_atoms;
+ this->total_lat += data->total_lat;
+ list_splice(&data->work_list, &this->work_list);
+ if (this->max_lat < data->max_lat) {
+ this->max_lat = data->max_lat;
+ this->max_lat_at = data->max_lat_at;
+ }
+ zfree(&data);
+ return;
+ }
+ }
+
+ data->num_merged++;
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+}
+
+static void perf_sched__merge_lat(struct perf_sched *sched)
+{
+ struct work_atoms *data;
+ struct rb_node *node;
+
+ if (sched->skip_merge)
+ return;
+
+ while ((node = rb_first(&sched->atom_root))) {
+ rb_erase(node, &sched->atom_root);
+ data = rb_entry(node, struct work_atoms, node);
+ __merge_work_atoms(&sched->merged_atom_root, data);
+ }
+}
+
static int perf_sched__lat(struct perf_sched *sched)
{
struct rb_node *next;
if (perf_sched__read_events(sched))
return -1;
+ perf_sched__merge_lat(sched);
perf_sched__sort_lat(sched);
printf("\n -----------------------------------------------------------------------------------------------------------------\n");
.profile_cpu = -1,
.next_shortname1 = 'A',
.next_shortname2 = '0',
+ .skip_merge = 0,
};
const struct option latency_options[] = {
OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
"CPU to profile on"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
+ OPT_BOOLEAN('p', "pids", &sched.skip_merge,
+ "latency stats per pid instead of per comm"),
OPT_END()
};
const struct option replay_options[] = {
#include "util/evsel.h"
#include "util/sort.h"
#include "util/data.h"
+#include "util/auxtrace.h"
#include <linux/bitmap.h>
static char const *script_name;
static bool no_callchain;
static bool latency_format;
static bool system_wide;
+static bool print_flags;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
#define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x)
-static int perf_evsel__check_stype(struct perf_evsel *evsel,
- u64 sample_type, const char *sample_msg,
- enum perf_output_field field)
+static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
+ u64 sample_type, const char *sample_msg,
+ enum perf_output_field field,
+ bool allow_user_set)
{
struct perf_event_attr *attr = &evsel->attr;
int type = attr->type;
return 0;
if (output[type].user_set) {
+ if (allow_user_set)
+ return 0;
evname = perf_evsel__name(evsel);
pr_err("Samples for '%s' event do not have %s attribute set. "
"Cannot print '%s' field.\n",
return 0;
}
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+ u64 sample_type, const char *sample_msg,
+ enum perf_output_field field)
+{
+ return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field,
+ false);
+}
+
static int perf_evsel__check_attr(struct perf_evsel *evsel,
struct perf_session *session)
{
struct perf_event_attr *attr = &evsel->attr;
+ bool allow_user_set;
+
+ allow_user_set = perf_header__has_feat(&session->header,
+ HEADER_AUXTRACE);
if (PRINT_FIELD(TRACE) &&
!perf_session__has_traces(session, "record -R"))
}
if (PRINT_FIELD(ADDR) &&
- perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
- PERF_OUTPUT_ADDR))
+ perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+ PERF_OUTPUT_ADDR, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
return -EINVAL;
if (PRINT_FIELD(CPU) &&
- perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
- PERF_OUTPUT_CPU))
+ perf_evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+ PERF_OUTPUT_CPU, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(PERIOD) &&
printf("\n");
}
+static void print_sample_flags(u32 flags)
+{
+ const char *chars = PERF_IP_FLAG_CHARS;
+ const int n = strlen(PERF_IP_FLAG_CHARS);
+ char str[33];
+ int i, pos = 0;
+
+ for (i = 0; i < n; i++, flags >>= 1) {
+ if (flags & 1)
+ str[pos++] = chars[i];
+ }
+ for (; i < 32; i++, flags >>= 1) {
+ if (flags & 1)
+ str[pos++] = '?';
+ }
+ str[pos] = 0;
+ printf(" %-4s ", str);
+}
+
static void process_event(union perf_event *event, struct perf_sample *sample,
struct perf_evsel *evsel, struct addr_location *al)
{
printf("%s: ", evname ? evname : "[unknown]");
}
+ if (print_flags)
+ print_sample_flags(sample->flags);
+
if (is_bts_event(attr)) {
print_sample_bts(event, sample, evsel, thread, al);
return;
}
if (al.filtered)
- return 0;
+ goto out_put;
if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
- return 0;
+ goto out_put;
scripting_ops->process_event(event, sample, evsel, &al);
-
+out_put:
+ addr_location__put(&al);
return 0;
}
print_sample_start(sample, thread, evsel);
perf_event__fprintf(event, stdout);
ret = 0;
-
out:
+ thread__put(thread);
return ret;
}
}
print_sample_start(sample, thread, evsel);
perf_event__fprintf(event, stdout);
+ thread__put(thread);
return 0;
}
struct perf_sample *sample,
struct machine *machine)
{
+ int err = 0;
struct thread *thread;
struct perf_script *script = container_of(tool, struct perf_script, tool);
struct perf_session *session = script->session;
perf_event__fprintf(event, stdout);
if (perf_event__process_exit(tool, event, sample, machine) < 0)
- return -1;
+ err = -1;
- return 0;
+ thread__put(thread);
+ return err;
}
static int process_mmap_event(struct perf_tool *tool,
}
print_sample_start(sample, thread, evsel);
perf_event__fprintf(event, stdout);
-
+ thread__put(thread);
return 0;
}
}
print_sample_start(sample, thread, evsel);
perf_event__fprintf(event, stdout);
-
+ thread__put(thread);
return 0;
}
}
}
- tok = strtok(tok, ",");
- while (tok) {
+ for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) {
for (i = 0; i < imax; ++i) {
if (strcmp(tok, all_output_options[i].str) == 0)
break;
}
+ if (i == imax && strcmp(tok, "flags") == 0) {
+ print_flags = true;
+ continue;
+ }
if (i == imax) {
fprintf(stderr, "Invalid field requested.\n");
rc = -EINVAL;
}
output[type].fields |= all_output_options[i].field;
}
-
- tok = strtok(NULL, ",");
}
if (type >= 0) {
char *rec_script_path = NULL;
char *rep_script_path = NULL;
struct perf_session *session;
+ struct itrace_synth_opts itrace_synth_opts = { .set = false, };
char *script_path = NULL;
const char **__argv;
int i, j, err = 0;
.attr = process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .id_index = perf_event__process_id_index,
+ .auxtrace_info = perf_event__process_auxtrace_info,
+ .auxtrace = perf_event__process_auxtrace,
+ .auxtrace_error = perf_event__process_auxtrace_error,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
"comma separated output fields prepend with 'type:'. "
"Valid types: hw,sw,trace,raw. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
- "addr,symoff,period", parse_output_fields),
+ "addr,symoff,period,flags", parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
"Show the mmap events"),
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+ "Instruction Tracing options",
+ itrace_parse_synth_opts),
OPT_END()
};
const char * const script_subcommands[] = { "record", "report", NULL };
script.session = session;
+ session->itrace_synth_opts = &itrace_synth_opts;
+
if (cpu_list) {
err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
if (err < 0)
static void print_aggr(char *prefix);
/* Default events used for perf stat -T */
-static const char * const transaction_attrs[] = {
- "task-clock",
+static const char *transaction_attrs = {
+ "task-clock,"
"{"
"instructions,"
"cycles,"
};
/* More limited version when the CPU does not have all events. */
-static const char * const transaction_limited_attrs[] = {
- "task-clock",
+static const char * transaction_limited_attrs = {
+ "task-clock,"
"{"
"instructions,"
"cycles,"
"}"
};
-/* must match transaction_attrs and the beginning limited_attrs */
-enum {
- T_TASK_CLOCK,
- T_INSTRUCTIONS,
- T_CYCLES,
- T_CYCLES_IN_TX,
- T_TRANSACTION_START,
- T_ELISION_START,
- T_CYCLES_IN_TX_CP,
-};
-
static struct perf_evlist *evsel_list;
static struct target target = {
.uid = UINT_MAX,
};
-enum aggr_mode {
- AGGR_NONE,
- AGGR_GLOBAL,
- AGGR_SOCKET,
- AGGR_CORE,
-};
-
static int run_count = 1;
static bool no_inherit = false;
static bool scale = true;
static volatile int done = 0;
-struct perf_stat {
- struct stats res_stats[3];
-};
-
static inline void diff_timespec(struct timespec *r, struct timespec *a,
struct timespec *b)
{
for (i = 0; i < 3; i++)
init_stats(&ps->res_stats[i]);
+
+ perf_stat_evsel_id_init(evsel);
}
static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
{
- void *addr;
- size_t sz;
+ struct perf_counts *counts;
- sz = sizeof(*evsel->counts) +
- (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
+ counts = perf_counts__new(perf_evsel__nr_cpus(evsel));
+ if (counts)
+ evsel->prev_raw_counts = counts;
- addr = zalloc(sz);
- if (!addr)
- return -ENOMEM;
-
- evsel->prev_raw_counts = addr;
-
- return 0;
+ return counts ? 0 : -ENOMEM;
}
static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
{
- zfree(&evsel->prev_raw_counts);
+ perf_counts__delete(evsel->prev_raw_counts);
+ evsel->prev_raw_counts = NULL;
}
static void perf_evlist__free_stats(struct perf_evlist *evlist)
return -1;
}
-static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_stats[MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
-static struct stats runtime_branches_stats[MAX_NR_CPUS];
-static struct stats runtime_cacherefs_stats[MAX_NR_CPUS];
-static struct stats runtime_l1_dcache_stats[MAX_NR_CPUS];
-static struct stats runtime_l1_icache_stats[MAX_NR_CPUS];
-static struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS];
-static struct stats walltime_nsecs_stats;
-static struct stats runtime_transaction_stats[MAX_NR_CPUS];
-static struct stats runtime_elision_stats[MAX_NR_CPUS];
-
static void perf_stat__reset_stats(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
}
- memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
- memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
- memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
- memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
- memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
- memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
- memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
- memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
- memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
- memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
- memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
- memset(runtime_cycles_in_tx_stats, 0,
- sizeof(runtime_cycles_in_tx_stats));
- memset(runtime_transaction_stats, 0,
- sizeof(runtime_transaction_stats));
- memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
- memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+ perf_stat__reset_shadow_stats();
}
static int create_perf_stat_counter(struct perf_evsel *evsel)
return 0;
}
-static struct perf_evsel *nth_evsel(int n)
-{
- static struct perf_evsel **array;
- static int array_len;
- struct perf_evsel *ev;
- int j;
-
- /* Assumes this only called when evsel_list does not change anymore. */
- if (!array) {
- evlist__for_each(evsel_list, ev)
- array_len++;
- array = malloc(array_len * sizeof(void *));
- if (!array)
- exit(ENOMEM);
- j = 0;
- evlist__for_each(evsel_list, ev)
- array[j++] = ev;
- }
- if (n < array_len)
- return array[n];
- return NULL;
-}
-
-/*
- * Update various tracking values we maintain to print
- * more semantic information such as miss/hit ratios,
- * instruction rates, etc:
- */
-static void update_shadow_stats(struct perf_evsel *counter, u64 *count,
- int cpu)
-{
- if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
- update_stats(&runtime_nsecs_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_stats(&runtime_cycles_stats[cpu], count[0]);
- else if (transaction_run &&
- perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
- update_stats(&runtime_cycles_in_tx_stats[cpu], count[0]);
- else if (transaction_run &&
- perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
- update_stats(&runtime_transaction_stats[cpu], count[0]);
- else if (transaction_run &&
- perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
- update_stats(&runtime_elision_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
- update_stats(&runtime_stalled_cycles_front_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
- update_stats(&runtime_stalled_cycles_back_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_stats(&runtime_branches_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_stats(&runtime_cacherefs_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_stats(&runtime_l1_dcache_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_stats(&runtime_l1_icache_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_stats(&runtime_ll_cache_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_stats(&runtime_dtlb_cache_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_stats(&runtime_itlb_cache_stats[cpu], count[0]);
-}
-
static void zero_per_pkg(struct perf_evsel *counter)
{
if (counter->per_pkg_mask)
perf_counts_values__scale(count, scale, NULL);
evsel->counts->cpu[cpu] = *count;
if (aggr_mode == AGGR_NONE)
- update_shadow_stats(evsel, count->values, cpu);
+ perf_stat__update_shadow_stats(evsel, count->values, cpu);
break;
case AGGR_GLOBAL:
aggr->val += count->val;
/*
* Save the full runtime - to allow normalization during printout:
*/
- update_shadow_stats(counter, count, 0);
+ perf_stat__update_shadow_stats(counter, count, 0);
return 0;
}
ui__warning("%s event is not supported by the kernel.\n",
perf_evsel__name(counter));
counter->supported = false;
- continue;
+
+ if ((counter->leader != counter) ||
+ !(counter->leader->nr_members > 1))
+ continue;
}
perf_evsel__open_strerror(counter, &target,
fprintf(output, " ");
}
-/* used for get_ratio_color() */
-enum grc_type {
- GRC_STALLED_CYCLES_FE,
- GRC_STALLED_CYCLES_BE,
- GRC_CACHE_MISSES,
- GRC_MAX_NR
-};
-
-static const char *get_ratio_color(enum grc_type type, double ratio)
-{
- static const double grc_table[GRC_MAX_NR][3] = {
- [GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
- [GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
- [GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 },
- };
- const char *color = PERF_COLOR_NORMAL;
-
- if (ratio > grc_table[type][0])
- color = PERF_COLOR_RED;
- else if (ratio > grc_table[type][1])
- color = PERF_COLOR_MAGENTA;
- else if (ratio > grc_table[type][2])
- color = PERF_COLOR_YELLOW;
-
- return color;
-}
-
-static void print_stalled_cycles_frontend(int cpu,
- struct perf_evsel *evsel
- __maybe_unused, double avg)
-{
- double total, ratio = 0.0;
- const char *color;
-
- total = avg_stats(&runtime_cycles_stats[cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
-
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " frontend cycles idle ");
-}
-
-static void print_stalled_cycles_backend(int cpu,
- struct perf_evsel *evsel
- __maybe_unused, double avg)
-{
- double total, ratio = 0.0;
- const char *color;
-
- total = avg_stats(&runtime_cycles_stats[cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
-
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " backend cycles idle ");
-}
-
-static void print_branch_misses(int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
-
- total = avg_stats(&runtime_branches_stats[cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all branches ");
-}
-
-static void print_l1_dcache_misses(int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
-
- total = avg_stats(&runtime_l1_dcache_stats[cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all L1-dcache hits ");
-}
-
-static void print_l1_icache_misses(int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
-
- total = avg_stats(&runtime_l1_icache_stats[cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all L1-icache hits ");
-}
-
-static void print_dtlb_cache_misses(int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
-
- total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all dTLB cache hits ");
-}
-
-static void print_itlb_cache_misses(int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
-
- total = avg_stats(&runtime_itlb_cache_stats[cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all iTLB cache hits ");
-}
-
-static void print_ll_cache_misses(int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
-
- total = avg_stats(&runtime_ll_cache_stats[cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(output, " # ");
- color_fprintf(output, color, "%6.2f%%", ratio);
- fprintf(output, " of all LL-cache hits ");
-}
-
static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
- double total, ratio = 0.0, total2;
double sc = evsel->scale;
const char *fmt;
int cpu = cpu_map__id_to_cpu(id);
if (csv_output || interval)
return;
- if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = avg_stats(&runtime_cycles_stats[cpu]);
- if (total) {
- ratio = avg / total;
- fprintf(output, " # %5.2f insns per cycle ", ratio);
- } else {
- fprintf(output, " ");
- }
- total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
- total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
-
- if (total && avg) {
- ratio = total / avg;
- fprintf(output, "\n");
- if (aggr_mode == AGGR_NONE)
- fprintf(output, " ");
- fprintf(output, " # %5.2f stalled cycles per insn", ratio);
- }
-
- } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
- runtime_branches_stats[cpu].n != 0) {
- print_branch_misses(cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_l1_dcache_stats[cpu].n != 0) {
- print_l1_dcache_misses(cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_l1_icache_stats[cpu].n != 0) {
- print_l1_icache_misses(cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_dtlb_cache_stats[cpu].n != 0) {
- print_dtlb_cache_misses(cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_itlb_cache_stats[cpu].n != 0) {
- print_itlb_cache_misses(cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_ll_cache_stats[cpu].n != 0) {
- print_ll_cache_misses(cpu, evsel, avg);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
- runtime_cacherefs_stats[cpu].n != 0) {
- total = avg_stats(&runtime_cacherefs_stats[cpu]);
-
- if (total)
- ratio = avg * 100 / total;
-
- fprintf(output, " # %8.3f %% of all cache refs ", ratio);
-
- } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(cpu, evsel, avg);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(cpu, evsel, avg);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = avg_stats(&runtime_nsecs_stats[cpu]);
-
- if (total) {
- ratio = avg / total;
- fprintf(output, " # %8.3f GHz ", ratio);
- } else {
- fprintf(output, " ");
- }
- } else if (transaction_run &&
- perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {
- total = avg_stats(&runtime_cycles_stats[cpu]);
- if (total)
- fprintf(output,
- " # %5.2f%% transactional cycles ",
- 100.0 * (avg / total));
- } else if (transaction_run &&
- perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) {
- total = avg_stats(&runtime_cycles_stats[cpu]);
- total2 = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
- if (total2 < avg)
- total2 = avg;
- if (total)
- fprintf(output,
- " # %5.2f%% aborted cycles ",
- 100.0 * ((total2-avg) / total));
- } else if (transaction_run &&
- perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&
- avg > 0 &&
- runtime_cycles_in_tx_stats[cpu].n != 0) {
- total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
-
- if (total)
- ratio = total / avg;
-
- fprintf(output, " # %8.0f cycles / transaction ", ratio);
- } else if (transaction_run &&
- perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&
- avg > 0 &&
- runtime_cycles_in_tx_stats[cpu].n != 0) {
- total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
-
- if (total)
- ratio = total / avg;
-
- fprintf(output, " # %8.0f cycles / elision ", ratio);
- } else if (runtime_nsecs_stats[cpu].n != 0) {
- char unit = 'M';
-
- total = avg_stats(&runtime_nsecs_stats[cpu]);
-
- if (total)
- ratio = 1000.0 * avg / total;
- if (ratio < 0.001) {
- ratio *= 1000;
- unit = 'K';
- }
-
- fprintf(output, " # %8.3f %c/sec ", ratio, unit);
- } else {
- fprintf(output, " ");
- }
+ perf_stat__print_shadow_stats(output, evsel, avg, cpu, aggr_mode);
}
static void print_aggr(char *prefix)
return 0;
}
-static int setup_events(const char * const *attrs, unsigned len)
-{
- unsigned i;
-
- for (i = 0; i < len; i++) {
- if (parse_events(evsel_list, attrs[i]))
- return -1;
- }
- return 0;
-}
-
/*
* Add default attributes, if there were no attributes specified or
* if -d/--detailed, -d -d or -d -d -d is used:
int err;
if (pmu_have_event("cpu", "cycles-ct") &&
pmu_have_event("cpu", "el-start"))
- err = setup_events(transaction_attrs,
- ARRAY_SIZE(transaction_attrs));
+ err = parse_events(evsel_list, transaction_attrs, NULL);
else
- err = setup_events(transaction_limited_attrs,
- ARRAY_SIZE(transaction_limited_attrs));
- if (err < 0) {
+ err = parse_events(evsel_list, transaction_limited_attrs, NULL);
+ if (err) {
fprintf(stderr, "Cannot set up transaction events\n");
return -1;
}
tasks_only,
with_backtrace,
topology;
+ bool force;
/* IO related settings */
- u64 io_events;
bool io_only,
skip_eagain;
+ u64 io_events;
u64 min_time,
merge_dist;
- bool force;
};
struct per_pidcomm;
* Discard all.
*/
zfree(&p);
- goto exit;
+ goto exit_put;
}
continue;
}
else
fprintf(f, "..... %016" PRIx64 "\n", ip);
}
-
+exit_put:
+ addr_location__put(&al);
exit:
fclose(f);
more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel,
0, top->sym_pcnt_filter, top->print_entries, 4);
- if (top->zero)
- symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
- else
- symbol__annotate_decay_histogram(symbol, top->sym_evsel->idx);
+
+ if (top->evlist->enabled) {
+ if (top->zero)
+ symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
+ else
+ symbol__annotate_decay_histogram(symbol, top->sym_evsel->idx);
+ }
if (more != 0)
printf("%d lines not displayed, maybe increase display entries [e]\n", more);
out_unlock:
return;
}
- if (top->zero) {
- hists__delete_entries(hists);
- } else {
- hists__decay_entries(hists, top->hide_user_symbols,
- top->hide_kernel_symbols);
+ if (top->evlist->enabled) {
+ if (top->zero) {
+ hists__delete_entries(hists);
+ } else {
+ hists__decay_entries(hists, top->hide_user_symbols,
+ top->hide_kernel_symbols);
+ }
}
hists__collapse_resort(hists, NULL);
hists = evsel__hists(t->sym_evsel);
- if (t->zero) {
- hists__delete_entries(hists);
- } else {
- hists__decay_entries(hists, t->hide_user_symbols,
- t->hide_kernel_symbols);
+ if (t->evlist->enabled) {
+ if (t->zero) {
+ hists__delete_entries(hists);
+ } else {
+ hists__decay_entries(hists, t->hide_user_symbols,
+ t->hide_kernel_symbols);
+ }
}
hists__collapse_resort(hists, NULL);
hists->uid_filter_str = top->record_opts.target.uid_str;
}
- perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
- &top->session->header.env);
+ while (true) {
+ int key = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+ top->min_percent,
+ &top->session->header.env);
+
+ if (key != 'f')
+ break;
+
+ perf_evlist__toggle_enable(top->evlist);
+ /*
+ * No need to refresh, resort/decay histogram entries
+ * if we are not collecting samples:
+ */
+ if (top->evlist->enabled) {
+ hbt.refresh = top->delay_secs;
+ help = "Press 'f' to disable the events or 'h' to see other hotkeys";
+ } else {
+ help = "Press 'f' again to re-enable the events";
+ hbt.refresh = 0;
+ }
+ }
done = 1;
return NULL;
if (al.sym == NULL || !al.sym->ignore) {
struct hists *hists = evsel__hists(evsel);
struct hist_entry_iter iter = {
- .add_entry_cb = hist_iter__top_callback,
+ .evsel = evsel,
+ .sample = sample,
+ .add_entry_cb = hist_iter__top_callback,
};
if (symbol_conf.cumulate_callchain)
pthread_mutex_lock(&hists->lock);
- err = hist_entry_iter__add(&iter, &al, evsel, sample,
- top->max_stack, top);
+ err = hist_entry_iter__add(&iter, &al, top->max_stack, top);
if (err < 0)
pr_err("Problem incrementing symbol period, skipping event\n");
pthread_mutex_unlock(&hists->lock);
}
- return;
+ addr_location__put(&al);
}
static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
goto out_delete;
machine__synthesize_threads(&top->session->machines.host, &opts->target,
- top->evlist->threads, false);
+ top->evlist->threads, false, opts->proc_map_timeout);
ret = perf_top__start_counters(top);
if (ret)
goto out_delete;
.target = {
.uses_mmap = true,
},
+ .proc_map_timeout = 500,
},
.max_stack = PERF_MAX_STACK_DEPTH,
.sym_pcnt_filter = 5,
OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
"width[,width...]",
"don't try to adjust column width, use these fixed values"),
+ OPT_UINTEGER(0, "proc-map-timeout", &opts->proc_map_timeout,
+ "per thread proc mmap processing timeout in ms"),
OPT_END()
};
const char * const top_usage[] = {
#include <libaudit.h>
#include <stdlib.h>
-#include <sys/eventfd.h>
#include <sys/mman.h>
#include <linux/futex.h>
# define EFD_SEMAPHORE 1
#endif
+#ifndef EFD_NONBLOCK
+# define EFD_NONBLOCK 00004000
+#endif
+
+#ifndef EFD_CLOEXEC
+# define EFD_CLOEXEC 02000000
+#endif
+
+#ifndef O_CLOEXEC
+# define O_CLOEXEC 02000000
+#endif
+
+#ifndef SOCK_DCCP
+# define SOCK_DCCP 6
+#endif
+
+#ifndef SOCK_CLOEXEC
+# define SOCK_CLOEXEC 02000000
+#endif
+
+#ifndef SOCK_NONBLOCK
+# define SOCK_NONBLOCK 00004000
+#endif
+
+#ifndef MSG_CMSG_CLOEXEC
+# define MSG_CMSG_CLOEXEC 0x40000000
+#endif
+
+#ifndef PERF_FLAG_FD_NO_GROUP
+# define PERF_FLAG_FD_NO_GROUP (1UL << 0)
+#endif
+
+#ifndef PERF_FLAG_FD_OUTPUT
+# define PERF_FLAG_FD_OUTPUT (1UL << 1)
+#endif
+
+#ifndef PERF_FLAG_PID_CGROUP
+# define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */
+#endif
+
+#ifndef PERF_FLAG_FD_CLOEXEC
+# define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */
+#endif
+
+
struct tp_field {
int offset;
union {
#define SCA_HEX syscall_arg__scnprintf_hex
+static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ return scnprintf(bf, size, "%d", arg->val);
+}
+
+#define SCA_INT syscall_arg__scnprintf_int
+
static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
struct syscall_arg *arg)
{
#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
+static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+ if (flags == 0)
+ return 0;
+
+#define P_FLAG(n) \
+ if (flags & PERF_FLAG_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~PERF_FLAG_##n; \
+ }
+
+ P_FLAG(FD_NO_GROUP);
+ P_FLAG(FD_OUTPUT);
+ P_FLAG(PID_CGROUP);
+ P_FLAG(FD_CLOEXEC);
+#undef P_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags
+
static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
struct syscall_arg *arg)
{
{ .name = "openat", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
+ { .name = "perf_event_open", .errmsg = true,
+ .arg_scnprintf = { [1] = SCA_INT, /* pid */
+ [2] = SCA_INT, /* cpu */
+ [3] = SCA_FD, /* group_fd */
+ [4] = SCA_PERF_FLAGS, /* flags */ }, },
{ .name = "pipe2", .errmsg = true,
.arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
{ .name = "poll", .errmsg = true, .timeout = true, },
return -ENOMEM;
err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
- evlist->threads, trace__tool_process, false);
+ evlist->threads, trace__tool_process, false,
+ trace->opts.proc_map_timeout);
if (err)
symbol__exit();
void *args;
size_t printed = 0;
struct thread *thread;
- int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+ int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
- return -1;
+ goto out_put;
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
if (ttrace->entry_str == NULL) {
ttrace->entry_str = malloc(1024);
if (!ttrace->entry_str)
- return -1;
+ goto out_put;
}
if (!trace->summary_only)
thread__put(trace->current);
trace->current = thread__get(thread);
}
-
- return 0;
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
}
static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
long ret;
u64 duration = 0;
struct thread *thread;
- int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+ int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
- return -1;
+ goto out_put;
if (trace->summary)
thread__update_stats(ttrace, id, sample);
fputc('\n', trace->output);
out:
ttrace->entry_pending = false;
-
- return 0;
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
}
static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
ttrace->runtime_ms += runtime_ms;
trace->runtime_ms += runtime_ms;
+ thread__put(thread);
return 0;
out_dump:
(pid_t)perf_evsel__intval(evsel, sample, "pid"),
runtime,
perf_evsel__intval(evsel, sample, "vruntime"));
+ thread__put(thread);
return 0;
}
struct addr_location al;
char map_type = 'd';
struct thread_trace *ttrace;
+ int err = -1;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
- return -1;
+ goto out_put;
if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
ttrace->pfmaj++;
ttrace->pfmin++;
if (trace->summary_only)
- return 0;
+ goto out;
thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
sample->ip, &al);
print_location(trace->output, sample, &al, true, false);
fprintf(trace->output, " (%c%c)\n", map_type, al.level);
-
- return 0;
+out:
+ err = 0;
+out_put:
+ thread__put(thread);
+ return err;
}
static bool skip_sample(struct trace *trace, struct perf_sample *sample)
.user_interval = ULLONG_MAX,
.no_buffering = true,
.mmap_pages = UINT_MAX,
+ .proc_map_timeout = 500,
},
.output = stdout,
.show_comm = true,
OPT_BOOLEAN(0, "comm", &trace.show_comm,
"show the thread COMM next to its id"),
OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
- OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
- "list of events to trace"),
+ OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
"trace events on existing process id"),
OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
"trace events on existing thread id"),
- OPT_CALLBACK(0, "filter-pids", &trace, "float",
- "show only events with duration > N.M ms", trace__set_filter_pids),
+ OPT_CALLBACK(0, "filter-pids", &trace, "CSV list of pids",
+ "pids to filter (by the kernel)", trace__set_filter_pids),
OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
"Trace pagefaults", parse_pagefaults, "maj"),
OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
+ OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
+ "per thread proc mmap processing timeout in ms"),
OPT_END()
};
const char * const trace_subcommands[] = { "record", NULL };
signal(SIGFPE, sighandler_dump_stack);
trace.evlist = perf_evlist__new();
- if (trace.evlist == NULL)
- return -ENOMEM;
if (trace.evlist == NULL) {
pr_err("Not enough memory to run!\n");
+ err = -ENOMEM;
goto out;
}
LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
$(call detected,CONFIG_X86_64)
else
- LIBUNWIND_LIBS = -lunwind -lunwind-x86
+ LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind
endif
NO_PERF_REGS := 0
endif
ifeq ($(DEBUG),0)
CFLAGS += -O6
+else
+ CFLAGS += $(call cc-option,-Og,-O0)
endif
ifdef PARSER_DEBUG
endif # libelf support
endif # NO_LIBELF
+ifdef NO_DWARF
+ NO_LIBDW_DWARF_UNWIND := 1
+endif
+
ifndef NO_LIBELF
CFLAGS += -DHAVE_LIBELF_SUPPORT
EXTLIBS += -lelf
endif
endif
+ifndef NO_AUXTRACE
+ $(call detected,CONFIG_AUXTRACE)
+ CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+endif
+
# Among the variables below, these:
# perfexecdir
# template_dir
endef
_ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2)))
_gea_err = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-run
+# Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
+# Exit code chooses option. "$$TMP" is can be used as temporary file and
+# is automatically cleaned up.
+try-run = $(shell set -e; \
+ TMP="$(TMPOUT).$$$$.tmp"; \
+ TMPO="$(TMPOUT).$$$$.o"; \
+ if ($(1)) >/dev/null 2>&1; \
+ then echo "$(2)"; \
+ else echo "$(3)"; \
+ fi; \
+ rm -f "$$TMP" "$$TMPO")
+
+# cc-option
+# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
+
+cc-option = $(call try-run,\
+ $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
#include <sys/syscall.h>
#include <linux/types.h>
#include <linux/perf_event.h>
+#include <asm/barrier.h>
#if defined(__i386__)
-#define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
#define CPUINFO_PROC {"model name"}
#ifndef __NR_perf_event_open
#endif
#if defined(__x86_64__)
-#define mb() asm volatile("mfence" ::: "memory")
-#define wmb() asm volatile("sfence" ::: "memory")
-#define rmb() asm volatile("lfence" ::: "memory")
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
#define CPUINFO_PROC {"model name"}
#ifndef __NR_perf_event_open
#ifdef __powerpc__
#include "../../arch/powerpc/include/uapi/asm/unistd.h"
-#define mb() asm volatile ("sync" ::: "memory")
-#define wmb() asm volatile ("sync" ::: "memory")
-#define rmb() asm volatile ("sync" ::: "memory")
#define CPUINFO_PROC {"cpu"}
#endif
#ifdef __s390__
-#define mb() asm volatile("bcr 15,0" ::: "memory")
-#define wmb() asm volatile("bcr 15,0" ::: "memory")
-#define rmb() asm volatile("bcr 15,0" ::: "memory")
#define CPUINFO_PROC {"vendor_id"}
#endif
#ifdef __sh__
-#if defined(__SH4A__) || defined(__SH5__)
-# define mb() asm volatile("synco" ::: "memory")
-# define wmb() asm volatile("synco" ::: "memory")
-# define rmb() asm volatile("synco" ::: "memory")
-#else
-# define mb() asm volatile("" ::: "memory")
-# define wmb() asm volatile("" ::: "memory")
-# define rmb() asm volatile("" ::: "memory")
-#endif
#define CPUINFO_PROC {"cpu type"}
#endif
#ifdef __hppa__
-#define mb() asm volatile("" ::: "memory")
-#define wmb() asm volatile("" ::: "memory")
-#define rmb() asm volatile("" ::: "memory")
#define CPUINFO_PROC {"cpu"}
#endif
#ifdef __sparc__
-#ifdef __LP64__
-#define mb() asm volatile("ba,pt %%xcc, 1f\n" \
- "membar #StoreLoad\n" \
- "1:\n":::"memory")
-#else
-#define mb() asm volatile("":::"memory")
-#endif
-#define wmb() asm volatile("":::"memory")
-#define rmb() asm volatile("":::"memory")
#define CPUINFO_PROC {"cpu"}
#endif
#ifdef __alpha__
-#define mb() asm volatile("mb" ::: "memory")
-#define wmb() asm volatile("wmb" ::: "memory")
-#define rmb() asm volatile("mb" ::: "memory")
#define CPUINFO_PROC {"cpu model"}
#endif
#ifdef __ia64__
-#define mb() asm volatile ("mf" ::: "memory")
-#define wmb() asm volatile ("mf" ::: "memory")
-#define rmb() asm volatile ("mf" ::: "memory")
#define cpu_relax() asm volatile ("hint @pause" ::: "memory")
#define CPUINFO_PROC {"model name"}
#endif
#ifdef __arm__
-/*
- * Use the __kuser_memory_barrier helper in the CPU helper page. See
- * arch/arm/kernel/entry-armv.S in the kernel source for details.
- */
-#define mb() ((void(*)(void))0xffff0fa0)()
-#define wmb() ((void(*)(void))0xffff0fa0)()
-#define rmb() ((void(*)(void))0xffff0fa0)()
#define CPUINFO_PROC {"model name", "Processor"}
#endif
#ifdef __aarch64__
-#define mb() asm volatile("dmb ish" ::: "memory")
-#define wmb() asm volatile("dmb ishst" ::: "memory")
-#define rmb() asm volatile("dmb ishld" ::: "memory")
#define cpu_relax() asm volatile("yield" ::: "memory")
#endif
#ifdef __mips__
-#define mb() asm volatile( \
- ".set mips2\n\t" \
- "sync\n\t" \
- ".set mips0" \
- : /* no output */ \
- : /* no input */ \
- : "memory")
-#define wmb() mb()
-#define rmb() mb()
#define CPUINFO_PROC {"cpu model"}
#endif
#ifdef __arc__
-#define mb() asm volatile("" ::: "memory")
-#define wmb() asm volatile("" ::: "memory")
-#define rmb() asm volatile("" ::: "memory")
#define CPUINFO_PROC {"Processor"}
#endif
#ifdef __metag__
-#define mb() asm volatile("" ::: "memory")
-#define wmb() asm volatile("" ::: "memory")
-#define rmb() asm volatile("" ::: "memory")
#define CPUINFO_PROC {"CPU"}
#endif
#ifdef __xtensa__
-#define mb() asm volatile("memw" ::: "memory")
-#define wmb() asm volatile("memw" ::: "memory")
-#define rmb() asm volatile("" ::: "memory")
#define CPUINFO_PROC {"core ID"}
#endif
#ifdef __tile__
-#define mb() asm volatile ("mf" ::: "memory")
-#define wmb() asm volatile ("mf" ::: "memory")
-#define rmb() asm volatile ("mf" ::: "memory")
#define cpu_relax() asm volatile ("mfspr zero, PASS" ::: "memory")
#define CPUINFO_PROC {"model name"}
#endif
-#define barrier() asm volatile ("" ::: "memory")
-
#ifndef cpu_relax
#define cpu_relax() barrier()
#endif
bool period;
bool sample_intr_regs;
bool running_time;
+ bool full_auxtrace;
+ bool auxtrace_snapshot_mode;
unsigned int freq;
unsigned int mmap_pages;
+ unsigned int auxtrace_mmap_pages;
unsigned int user_freq;
u64 branch_stack;
u64 default_interval;
u64 user_interval;
+ size_t auxtrace_snapshot_size;
+ const char *auxtrace_snapshot_opts;
bool sample_transaction;
unsigned initial_delay;
bool use_clockid;
clockid_t clockid;
+ unsigned int proc_map_timeout;
};
struct option;
perf-y += dso-data.o
perf-y += attr.o
perf-y += vmlinux-kallsyms.o
-perf-y += open-syscall.o
-perf-y += open-syscall-all-cpus.o
-perf-y += open-syscall-tp-fields.o
+perf-y += openat-syscall.o
+perf-y += openat-syscall-all-cpus.o
+perf-y += openat-syscall-tp-fields.o
perf-y += mmap-basic.o
perf-y += perf-record.o
perf-y += rdpmc.o
perf-$(CONFIG_X86) += perf-time-to-tsc.o
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
endif
.func = test__vmlinux_matches_kallsyms,
},
{
- .desc = "detect open syscall event",
- .func = test__open_syscall_event,
+ .desc = "detect openat syscall event",
+ .func = test__openat_syscall_event,
},
{
- .desc = "detect open syscall event on all cpus",
- .func = test__open_syscall_event_on_all_cpus,
+ .desc = "detect openat syscall event on all cpus",
+ .func = test__openat_syscall_event_on_all_cpus,
},
{
.desc = "read samples using the mmap interface",
.func = test__perf_evsel__tp_sched_test,
},
{
- .desc = "Generate and check syscalls:sys_enter_open event fields",
- .func = test__syscall_open_tp_fields,
+ .desc = "Generate and check syscalls:sys_enter_openat event fields",
+ .func = test__syscall_openat_tp_fields,
},
{
.desc = "struct perf_event_attr setup",
.desc = "Test parsing with no sample_id_all bit set",
.func = test__parse_no_sample_id_all,
},
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT
{
.desc = "Test dwarf unwind",
wait(&status);
if (WIFEXITED(status)) {
- err = WEXITSTATUS(status);
+ err = (signed char)WEXITSTATUS(status);
pr_debug("test child finished with %d\n", err);
} else if (WIFSIGNALED(status)) {
err = -1;
struct perf_sample sample;
struct thread *thread;
u8 cpumode;
+ int ret;
if (perf_evlist__parse_sample(evlist, event, &sample)) {
pr_debug("perf_evlist__parse_sample failed\n");
cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- return read_object_code(sample.ip, READLEN, cpumode, thread, state);
+ ret = read_object_code(sample.ip, READLEN, cpumode, thread, state);
+ thread__put(thread);
+ return ret;
}
static int process_event(struct machine *machine, struct perf_evlist *evlist,
}
ret = perf_event__synthesize_thread_map(NULL, threads,
- perf_event__process, machine, false);
+ perf_event__process, machine, false, 500);
if (ret < 0) {
pr_debug("perf_event__synthesize_thread_map failed\n");
goto out_err;
thread = machine__findnew_thread(machine, pid, pid);
if (!thread) {
pr_debug("machine__findnew_thread failed\n");
- goto out_err;
+ goto out_put;
}
cpus = cpu_map__new(NULL);
if (!cpus) {
pr_debug("cpu_map__new failed\n");
- goto out_err;
+ goto out_put;
}
while (1) {
evlist = perf_evlist__new();
if (!evlist) {
pr_debug("perf_evlist__new failed\n");
- goto out_err;
+ goto out_put;
}
perf_evlist__set_maps(evlist, cpus, threads);
else
str = "cycles";
pr_debug("Parsing event '%s'\n", str);
- ret = parse_events(evlist, str);
+ ret = parse_events(evlist, str, NULL);
if (ret < 0) {
pr_debug("parse_events failed\n");
- goto out_err;
+ goto out_put;
}
perf_evlist__config(evlist, &opts);
continue;
}
pr_debug("perf_evlist__open failed\n");
- goto out_err;
+ goto out_put;
}
break;
}
ret = perf_evlist__mmap(evlist, UINT_MAX, false);
if (ret < 0) {
pr_debug("perf_evlist__mmap failed\n");
- goto out_err;
+ goto out_put;
}
perf_evlist__enable(evlist);
ret = process_events(machine, evlist, &state);
if (ret < 0)
- goto out_err;
+ goto out_put;
if (!have_vmlinux && !have_kcore && !try_kcore)
err = TEST_CODE_READING_NO_KERNEL_OBJ;
err = TEST_CODE_READING_NO_ACCESS;
else
err = TEST_CODE_READING_OK;
+out_put:
+ thread__put(thread);
out_err:
+
if (evlist) {
perf_evlist__delete(evlist);
} else {
},
};
+/* move it from util/dso.c for compatibility */
+static int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+ int fd = dso__data_get_fd(dso, machine);
+
+ if (fd >= 0)
+ dso__data_put_fd(dso);
+
+ return fd;
+}
+
int test__dso_data(void)
{
struct machine machine;
free(buf);
}
- dso__delete(dso);
+ dso__put(dso);
unlink(file);
return 0;
}
struct dso *dso = dsos[i];
unlink(dso->name);
- dso__delete(dso);
+ dso__put(dso);
}
free(dsos);
pid_t pid = getpid();
return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
- mmap_handler, machine, true);
+ mmap_handler, machine, true, 500);
}
#define MAX_STACK 8
}
err = krava_1(thread);
+ thread__put(thread);
out:
machine__delete_threads(machine);
for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
__perf_evsel__hw_cache_type_op_res_name(type, op, i,
name, sizeof(name));
- err = parse_events(evlist, name);
+ err = parse_events(evlist, name, NULL);
if (err)
ret = err;
}
return -ENOMEM;
for (i = 0; i < nr_names; ++i) {
- err = parse_events(evlist, names[i]);
+ err = parse_events(evlist, names[i], NULL);
if (err) {
pr_debug("failed to parse event '%s', err %d\n",
names[i], err);
goto out;
thread__set_comm(thread, fake_threads[i].comm, 0);
+ thread__put(thread);
}
for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
size_t k;
struct dso *dso;
- dso = __dsos__findnew(&machine->user_dsos,
- fake_symbols[i].dso_name);
+ dso = machine__findnew_dso(machine, fake_symbols[i].dso_name);
if (dso == NULL)
goto out;
sym = symbol__new(fsym->start, fsym->length,
STB_GLOBAL, fsym->name);
- if (sym == NULL)
+ if (sym == NULL) {
+ dso__put(dso);
goto out;
+ }
symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
}
+
+ dso__put(dso);
}
return machine;
},
};
struct hist_entry_iter iter = {
+ .evsel = evsel,
+ .sample = &sample,
.hide_unresolved = false,
};
&sample) < 0)
goto out;
- if (hist_entry_iter__add(&iter, &al, evsel, &sample,
- PERF_MAX_STACK_DEPTH, NULL) < 0)
+ if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+ NULL) < 0) {
+ addr_location__put(&al);
goto out;
+ }
fake_samples[i].thread = al.thread;
fake_samples[i].map = al.map;
TEST_ASSERT_VAL("No memory", evlist);
- err = parse_events(evlist, "cpu-clock");
+ err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
},
};
struct hist_entry_iter iter = {
+ .evsel = evsel,
+ .sample = &sample,
.ops = &hist_iter_normal,
.hide_unresolved = false,
};
&sample) < 0)
goto out;
- if (hist_entry_iter__add(&iter, &al, evsel, &sample,
- PERF_MAX_STACK_DEPTH, NULL) < 0)
+ if (hist_entry_iter__add(&iter, &al,
+ PERF_MAX_STACK_DEPTH, NULL) < 0) {
+ addr_location__put(&al);
goto out;
+ }
fake_samples[i].thread = al.thread;
fake_samples[i].map = al.map;
TEST_ASSERT_VAL("No memory", evlist);
- err = parse_events(evlist, "cpu-clock");
+ err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
- err = parse_events(evlist, "task-clock");
+ err = parse_events(evlist, "task-clock", NULL);
if (err)
goto out;
he = __hists__add_entry(hists, &al, NULL,
NULL, NULL, 1, 1, 0, true);
- if (he == NULL)
+ if (he == NULL) {
+ addr_location__put(&al);
goto out;
+ }
fake_common_samples[k].thread = al.thread;
fake_common_samples[k].map = al.map;
he = __hists__add_entry(hists, &al, NULL,
NULL, NULL, 1, 1, 0, true);
- if (he == NULL)
+ if (he == NULL) {
+ addr_location__put(&al);
goto out;
+ }
fake_samples[i][k].thread = al.thread;
fake_samples[i][k].map = al.map;
if (evlist == NULL)
return -ENOMEM;
- err = parse_events(evlist, "cpu-clock");
+ err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
- err = parse_events(evlist, "task-clock");
+ err = parse_events(evlist, "task-clock", NULL);
if (err)
goto out;
},
};
struct hist_entry_iter iter = {
+ .evsel = evsel,
+ .sample = &sample,
.ops = &hist_iter_normal,
.hide_unresolved = false,
};
&sample) < 0)
goto out;
- if (hist_entry_iter__add(&iter, &al, evsel, &sample,
- PERF_MAX_STACK_DEPTH, NULL) < 0)
+ if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+ NULL) < 0) {
+ addr_location__put(&al);
goto out;
+ }
fake_samples[i].thread = al.thread;
fake_samples[i].map = al.map;
TEST_ASSERT_VAL("No memory", evlist);
- err = parse_events(evlist, "cpu-clock");
+ err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
perf_evlist__set_maps(evlist, cpus, threads);
- CHECK__(parse_events(evlist, "dummy:u"));
- CHECK__(parse_events(evlist, "cycles:u"));
+ CHECK__(parse_events(evlist, "dummy:u", NULL));
+ CHECK__(parse_events(evlist, "cycles:u", NULL));
perf_evlist__config(evlist, &opts);
return 0;
}
+static int test_is_kernel_module(const char *path, int cpumode, bool expect)
+{
+ TEST_ASSERT_VAL("is_kernel_module",
+ (!!is_kernel_module(path, cpumode)) == (!!expect));
+ pr_debug("%s (cpumode: %d) - is_kernel_module: %s\n",
+ path, cpumode, expect ? "true" : "false");
+ return 0;
+}
+
#define T(path, an, ae, k, c, n, e) \
TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e))
+#define M(path, c, e) \
+ TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
+
int test__kmod_path__parse(void)
{
/* path alloc_name alloc_ext kmod comp name ext */
T("/xxxx/xxxx/x-x.ko", false , true , true, false, NULL , NULL);
T("/xxxx/xxxx/x-x.ko", true , false , true, false, "[x_x]", NULL);
T("/xxxx/xxxx/x-x.ko", false , false , true, false, NULL , NULL);
+ M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+ M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true);
+ M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false);
/* path alloc_name alloc_ext kmod comp name ext */
T("/xxxx/xxxx/x.ko.gz", true , true , true, true, "[x]", "gz");
T("/xxxx/xxxx/x.ko.gz", false , true , true, true, NULL , "gz");
T("/xxxx/xxxx/x.ko.gz", true , false , true, true, "[x]", NULL);
T("/xxxx/xxxx/x.ko.gz", false , false , true, true, NULL , NULL);
+ M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+ M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_KERNEL, true);
+ M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_USER, false);
/* path alloc_name alloc_ext kmod comp name ext */
T("/xxxx/xxxx/x.gz", true , true , false, true, "x.gz" ,"gz");
T("/xxxx/xxxx/x.gz", false , true , false, true, NULL ,"gz");
T("/xxxx/xxxx/x.gz", true , false , false, true, "x.gz" , NULL);
T("/xxxx/xxxx/x.gz", false , false , false, true, NULL , NULL);
+ M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+ M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_KERNEL, false);
+ M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_USER, false);
/* path alloc_name alloc_ext kmod comp name ext */
T("x.gz", true , true , false, true, "x.gz", "gz");
T("x.gz", false , true , false, true, NULL , "gz");
T("x.gz", true , false , false, true, "x.gz", NULL);
T("x.gz", false , false , false, true, NULL , NULL);
+ M("x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+ M("x.gz", PERF_RECORD_MISC_KERNEL, false);
+ M("x.gz", PERF_RECORD_MISC_USER, false);
/* path alloc_name alloc_ext kmod comp name ext */
T("x.ko.gz", true , true , true, true, "[x]", "gz");
T("x.ko.gz", false , true , true, true, NULL , "gz");
T("x.ko.gz", true , false , true, true, "[x]", NULL);
T("x.ko.gz", false , false , true, true, NULL , NULL);
+ M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+ M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true);
+ M("x.ko.gz", PERF_RECORD_MISC_USER, false);
+
+ /* path alloc_name alloc_ext kmod comp name ext */
+ T("[test_module]", true , true , true, false, "[test_module]", NULL);
+ T("[test_module]", false , true , true, false, NULL , NULL);
+ T("[test_module]", true , false , true, false, "[test_module]", NULL);
+ T("[test_module]", false , false , true, false, NULL , NULL);
+ M("[test_module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+ M("[test_module]", PERF_RECORD_MISC_KERNEL, true);
+ M("[test_module]", PERF_RECORD_MISC_USER, false);
+
+ /* path alloc_name alloc_ext kmod comp name ext */
+ T("[test.module]", true , true , true, false, "[test.module]", NULL);
+ T("[test.module]", false , true , true, false, NULL , NULL);
+ T("[test.module]", true , false , true, false, "[test.module]", NULL);
+ T("[test.module]", false , false , true, false, NULL , NULL);
+ M("[test.module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+ M("[test.module]", PERF_RECORD_MISC_KERNEL, true);
+ M("[test.module]", PERF_RECORD_MISC_USER, false);
+
+ /* path alloc_name alloc_ext kmod comp name ext */
+ T("[vdso]", true , true , false, false, "[vdso]", NULL);
+ T("[vdso]", false , true , false, false, NULL , NULL);
+ T("[vdso]", true , false , false, false, "[vdso]", NULL);
+ T("[vdso]", false , false , false, false, NULL , NULL);
+ M("[vdso]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+ M("[vdso]", PERF_RECORD_MISC_KERNEL, false);
+ M("[vdso]", PERF_RECORD_MISC_USER, false);
+
+ /* path alloc_name alloc_ext kmod comp name ext */
+ T("[vsyscall]", true , true , false, false, "[vsyscall]", NULL);
+ T("[vsyscall]", false , true , false, false, NULL , NULL);
+ T("[vsyscall]", true , false , false, false, "[vsyscall]", NULL);
+ T("[vsyscall]", false , false , false, false, NULL , NULL);
+ M("[vsyscall]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+ M("[vsyscall]", PERF_RECORD_MISC_KERNEL, false);
+ M("[vsyscall]", PERF_RECORD_MISC_USER, false);
+
+ /* path alloc_name alloc_ext kmod comp name ext */
+ T("[kernel.kallsyms]", true , true , false, false, "[kernel.kallsyms]", NULL);
+ T("[kernel.kallsyms]", false , true , false, false, NULL , NULL);
+ T("[kernel.kallsyms]", true , false , false, false, "[kernel.kallsyms]", NULL);
+ T("[kernel.kallsyms]", false , false , false, false, NULL , NULL);
+ M("[kernel.kallsyms]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+ M("[kernel.kallsyms]", PERF_RECORD_MISC_KERNEL, false);
+ M("[kernel.kallsyms]", PERF_RECORD_MISC_USER, false);
return 0;
}
make_no_libnuma := NO_LIBNUMA=1
make_no_libaudit := NO_LIBAUDIT=1
make_no_libbionic := NO_LIBBIONIC=1
+make_no_auxtrace := NO_AUXTRACE=1
make_tags := tags
make_cscope := cscope
make_help := help
make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
-make_minimal += NO_LIBDW_DWARF_UNWIND=1
+make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1
# $(run) contains all available tests
run := make_pure
run += make_no_libnuma
run += make_no_libaudit
run += make_no_libbionic
+run += make_no_auxtrace
run += make_help
run += make_doc
run += make_perf_o
echo "- $@: $$cmd" && echo $$cmd > $@ && \
( eval $$cmd ) >> $@ 2>&1
-all: $(run) $(run_O) tarpkg
+make_kernelsrc:
+ @echo " - make -C <kernelsrc> tools/perf"
+ $(call clean); \
+ (make -C ../.. tools/perf) > $@ 2>&1 && \
+ test -x perf && rm -f $@ || (cat $@ ; false)
+
+make_kernelsrc_tools:
+ @echo " - make -C <kernelsrc>/tools perf"
+ $(call clean); \
+ (make -C ../../tools perf) > $@ 2>&1 && \
+ test -x perf && rm -f $@ || (cat $@ ; false)
+
+all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
@echo OK
out: $(run_O)
struct cpu_map *cpus;
struct perf_evlist *evlist;
cpu_set_t cpu_set;
- const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
- "getpgid", };
- pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
- (void*)getpgid };
+ const char *syscall_names[] = { "getsid", "getppid", "getpgid", };
+ pid_t (*syscalls[])(void) = { (void *)getsid, getppid, (void*)getpgid };
#define nsyscalls ARRAY_SIZE(syscall_names)
unsigned int nr_events[nsyscalls],
expected_nr_events[nsyscalls], i, j;
{
return perf_event__synthesize_threads(NULL,
perf_event__process,
- machine, 0);
+ machine, 0, 500);
}
static int synth_process(struct machine *machine)
err = perf_event__synthesize_thread_map(NULL, map,
perf_event__process,
- machine, 0);
+ machine, 0, 500);
thread_map__delete(map);
return err;
PERF_RECORD_MISC_USER, MAP__FUNCTION,
(unsigned long) (td->map + 1), &al);
+ thread__put(thread);
+
if (!al.map) {
pr_debug("failed, couldn't find map\n");
err = -1;
+++ /dev/null
-#include "evsel.h"
-#include "tests.h"
-#include "thread_map.h"
-#include "cpumap.h"
-#include "debug.h"
-
-int test__open_syscall_event_on_all_cpus(void)
-{
- int err = -1, fd, cpu;
- struct cpu_map *cpus;
- struct perf_evsel *evsel;
- unsigned int nr_open_calls = 111, i;
- cpu_set_t cpu_set;
- struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
- char sbuf[STRERR_BUFSIZE];
-
- if (threads == NULL) {
- pr_debug("thread_map__new\n");
- return -1;
- }
-
- cpus = cpu_map__new(NULL);
- if (cpus == NULL) {
- pr_debug("cpu_map__new\n");
- goto out_thread_map_delete;
- }
-
- CPU_ZERO(&cpu_set);
-
- evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
- if (evsel == NULL) {
- if (tracefs_configured())
- pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
- else if (debugfs_configured())
- pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
- else
- pr_debug("Neither tracefs or debugfs is enabled in this kernel\n");
- goto out_thread_map_delete;
- }
-
- if (perf_evsel__open(evsel, cpus, threads) < 0) {
- pr_debug("failed to open counter: %s, "
- "tweak /proc/sys/kernel/perf_event_paranoid?\n",
- strerror_r(errno, sbuf, sizeof(sbuf)));
- goto out_evsel_delete;
- }
-
- for (cpu = 0; cpu < cpus->nr; ++cpu) {
- unsigned int ncalls = nr_open_calls + cpu;
- /*
- * XXX eventually lift this restriction in a way that
- * keeps perf building on older glibc installations
- * without CPU_ALLOC. 1024 cpus in 2010 still seems
- * a reasonable upper limit tho :-)
- */
- if (cpus->map[cpu] >= CPU_SETSIZE) {
- pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
- continue;
- }
-
- CPU_SET(cpus->map[cpu], &cpu_set);
- if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
- pr_debug("sched_setaffinity() failed on CPU %d: %s ",
- cpus->map[cpu],
- strerror_r(errno, sbuf, sizeof(sbuf)));
- goto out_close_fd;
- }
- for (i = 0; i < ncalls; ++i) {
- fd = open("/etc/passwd", O_RDONLY);
- close(fd);
- }
- CPU_CLR(cpus->map[cpu], &cpu_set);
- }
-
- /*
- * Here we need to explicitely preallocate the counts, as if
- * we use the auto allocation it will allocate just for 1 cpu,
- * as we start by cpu 0.
- */
- if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
- pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
- goto out_close_fd;
- }
-
- err = 0;
-
- for (cpu = 0; cpu < cpus->nr; ++cpu) {
- unsigned int expected;
-
- if (cpus->map[cpu] >= CPU_SETSIZE)
- continue;
-
- if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
- pr_debug("perf_evsel__read_on_cpu\n");
- err = -1;
- break;
- }
-
- expected = nr_open_calls + cpu;
- if (evsel->counts->cpu[cpu].val != expected) {
- pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
- expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
- err = -1;
- }
- }
-
- perf_evsel__free_counts(evsel);
-out_close_fd:
- perf_evsel__close_fd(evsel, 1, threads->nr);
-out_evsel_delete:
- perf_evsel__delete(evsel);
-out_thread_map_delete:
- thread_map__delete(threads);
- return err;
-}
+++ /dev/null
-#include "perf.h"
-#include "evlist.h"
-#include "evsel.h"
-#include "thread_map.h"
-#include "tests.h"
-#include "debug.h"
-
-int test__syscall_open_tp_fields(void)
-{
- struct record_opts opts = {
- .target = {
- .uid = UINT_MAX,
- .uses_mmap = true,
- },
- .no_buffering = true,
- .freq = 1,
- .mmap_pages = 256,
- .raw_samples = true,
- };
- const char *filename = "/etc/passwd";
- int flags = O_RDONLY | O_DIRECTORY;
- struct perf_evlist *evlist = perf_evlist__new();
- struct perf_evsel *evsel;
- int err = -1, i, nr_events = 0, nr_polls = 0;
- char sbuf[STRERR_BUFSIZE];
-
- if (evlist == NULL) {
- pr_debug("%s: perf_evlist__new\n", __func__);
- goto out;
- }
-
- evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
- if (evsel == NULL) {
- pr_debug("%s: perf_evsel__newtp\n", __func__);
- goto out_delete_evlist;
- }
-
- perf_evlist__add(evlist, evsel);
-
- err = perf_evlist__create_maps(evlist, &opts.target);
- if (err < 0) {
- pr_debug("%s: perf_evlist__create_maps\n", __func__);
- goto out_delete_evlist;
- }
-
- perf_evsel__config(evsel, &opts);
-
- evlist->threads->map[0] = getpid();
-
- err = perf_evlist__open(evlist);
- if (err < 0) {
- pr_debug("perf_evlist__open: %s\n",
- strerror_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
- }
-
- err = perf_evlist__mmap(evlist, UINT_MAX, false);
- if (err < 0) {
- pr_debug("perf_evlist__mmap: %s\n",
- strerror_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
- }
-
- perf_evlist__enable(evlist);
-
- /*
- * Generate the event:
- */
- open(filename, flags);
-
- while (1) {
- int before = nr_events;
-
- for (i = 0; i < evlist->nr_mmaps; i++) {
- union perf_event *event;
-
- while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
- const u32 type = event->header.type;
- int tp_flags;
- struct perf_sample sample;
-
- ++nr_events;
-
- if (type != PERF_RECORD_SAMPLE) {
- perf_evlist__mmap_consume(evlist, i);
- continue;
- }
-
- err = perf_evsel__parse_sample(evsel, event, &sample);
- if (err) {
- pr_err("Can't parse sample, err = %d\n", err);
- goto out_delete_evlist;
- }
-
- tp_flags = perf_evsel__intval(evsel, &sample, "flags");
-
- if (flags != tp_flags) {
- pr_debug("%s: Expected flags=%#x, got %#x\n",
- __func__, flags, tp_flags);
- goto out_delete_evlist;
- }
-
- goto out_ok;
- }
- }
-
- if (nr_events == before)
- perf_evlist__poll(evlist, 10);
-
- if (++nr_polls > 5) {
- pr_debug("%s: no events!\n", __func__);
- goto out_delete_evlist;
- }
- }
-out_ok:
- err = 0;
-out_delete_evlist:
- perf_evlist__delete(evlist);
-out:
- return err;
-}
+++ /dev/null
-#include "thread_map.h"
-#include "evsel.h"
-#include "debug.h"
-#include "tests.h"
-
-int test__open_syscall_event(void)
-{
- int err = -1, fd;
- struct perf_evsel *evsel;
- unsigned int nr_open_calls = 111, i;
- struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
- char sbuf[STRERR_BUFSIZE];
-
- if (threads == NULL) {
- pr_debug("thread_map__new\n");
- return -1;
- }
-
- evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
- if (evsel == NULL) {
- if (tracefs_configured())
- pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
- else if (debugfs_configured())
- pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
- else
- pr_debug("Neither tracefs or debugfs is enabled in this kernel\n");
- goto out_thread_map_delete;
- }
-
- if (perf_evsel__open_per_thread(evsel, threads) < 0) {
- pr_debug("failed to open counter: %s, "
- "tweak /proc/sys/kernel/perf_event_paranoid?\n",
- strerror_r(errno, sbuf, sizeof(sbuf)));
- goto out_evsel_delete;
- }
-
- for (i = 0; i < nr_open_calls; ++i) {
- fd = open("/etc/passwd", O_RDONLY);
- close(fd);
- }
-
- if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
- pr_debug("perf_evsel__read_on_cpu\n");
- goto out_close_fd;
- }
-
- if (evsel->counts->cpu[0].val != nr_open_calls) {
- pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
- nr_open_calls, evsel->counts->cpu[0].val);
- goto out_close_fd;
- }
-
- err = 0;
-out_close_fd:
- perf_evsel__close_fd(evsel, 1, threads->nr);
-out_evsel_delete:
- perf_evsel__delete(evsel);
-out_thread_map_delete:
- thread_map__delete(threads);
- return err;
-}
--- /dev/null
+#include "evsel.h"
+#include "tests.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "debug.h"
+#include "stat.h"
+
+int test__openat_syscall_event_on_all_cpus(void)
+{
+ int err = -1, fd, cpu;
+ struct cpu_map *cpus;
+ struct perf_evsel *evsel;
+ unsigned int nr_openat_calls = 111, i;
+ cpu_set_t cpu_set;
+ struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+ char sbuf[STRERR_BUFSIZE];
+
+ if (threads == NULL) {
+ pr_debug("thread_map__new\n");
+ return -1;
+ }
+
+ cpus = cpu_map__new(NULL);
+ if (cpus == NULL) {
+ pr_debug("cpu_map__new\n");
+ goto out_thread_map_delete;
+ }
+
+ CPU_ZERO(&cpu_set);
+
+ evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
+ if (evsel == NULL) {
+ if (tracefs_configured())
+ pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
+ else if (debugfs_configured())
+ pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+ else
+ pr_debug("Neither tracefs or debugfs is enabled in this kernel\n");
+ goto out_thread_map_delete;
+ }
+
+ if (perf_evsel__open(evsel, cpus, threads) < 0) {
+ pr_debug("failed to open counter: %s, "
+ "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
+ goto out_evsel_delete;
+ }
+
+ for (cpu = 0; cpu < cpus->nr; ++cpu) {
+ unsigned int ncalls = nr_openat_calls + cpu;
+ /*
+ * XXX eventually lift this restriction in a way that
+ * keeps perf building on older glibc installations
+ * without CPU_ALLOC. 1024 cpus in 2010 still seems
+ * a reasonable upper limit tho :-)
+ */
+ if (cpus->map[cpu] >= CPU_SETSIZE) {
+ pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
+ continue;
+ }
+
+ CPU_SET(cpus->map[cpu], &cpu_set);
+ if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+ pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+ cpus->map[cpu],
+ strerror_r(errno, sbuf, sizeof(sbuf)));
+ goto out_close_fd;
+ }
+ for (i = 0; i < ncalls; ++i) {
+ fd = openat(0, "/etc/passwd", O_RDONLY);
+ close(fd);
+ }
+ CPU_CLR(cpus->map[cpu], &cpu_set);
+ }
+
+ /*
+ * Here we need to explicitely preallocate the counts, as if
+ * we use the auto allocation it will allocate just for 1 cpu,
+ * as we start by cpu 0.
+ */
+ if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+ pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
+ goto out_close_fd;
+ }
+
+ err = 0;
+
+ for (cpu = 0; cpu < cpus->nr; ++cpu) {
+ unsigned int expected;
+
+ if (cpus->map[cpu] >= CPU_SETSIZE)
+ continue;
+
+ if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+ pr_debug("perf_evsel__read_on_cpu\n");
+ err = -1;
+ break;
+ }
+
+ expected = nr_openat_calls + cpu;
+ if (evsel->counts->cpu[cpu].val != expected) {
+ pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
+ expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
+ err = -1;
+ }
+ }
+
+ perf_evsel__free_counts(evsel);
+out_close_fd:
+ perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+ perf_evsel__delete(evsel);
+out_thread_map_delete:
+ thread_map__delete(threads);
+ return err;
+}
--- /dev/null
+#include "perf.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "tests.h"
+#include "debug.h"
+
+int test__syscall_openat_tp_fields(void)
+{
+ struct record_opts opts = {
+ .target = {
+ .uid = UINT_MAX,
+ .uses_mmap = true,
+ },
+ .no_buffering = true,
+ .freq = 1,
+ .mmap_pages = 256,
+ .raw_samples = true,
+ };
+ const char *filename = "/etc/passwd";
+ int flags = O_RDONLY | O_DIRECTORY;
+ struct perf_evlist *evlist = perf_evlist__new();
+ struct perf_evsel *evsel;
+ int err = -1, i, nr_events = 0, nr_polls = 0;
+ char sbuf[STRERR_BUFSIZE];
+
+ if (evlist == NULL) {
+ pr_debug("%s: perf_evlist__new\n", __func__);
+ goto out;
+ }
+
+ evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
+ if (evsel == NULL) {
+ pr_debug("%s: perf_evsel__newtp\n", __func__);
+ goto out_delete_evlist;
+ }
+
+ perf_evlist__add(evlist, evsel);
+
+ err = perf_evlist__create_maps(evlist, &opts.target);
+ if (err < 0) {
+ pr_debug("%s: perf_evlist__create_maps\n", __func__);
+ goto out_delete_evlist;
+ }
+
+ perf_evsel__config(evsel, &opts);
+
+ evlist->threads->map[0] = getpid();
+
+ err = perf_evlist__open(evlist);
+ if (err < 0) {
+ pr_debug("perf_evlist__open: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
+ goto out_delete_evlist;
+ }
+
+ err = perf_evlist__mmap(evlist, UINT_MAX, false);
+ if (err < 0) {
+ pr_debug("perf_evlist__mmap: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
+ goto out_delete_evlist;
+ }
+
+ perf_evlist__enable(evlist);
+
+ /*
+ * Generate the event:
+ */
+ openat(AT_FDCWD, filename, flags);
+
+ while (1) {
+ int before = nr_events;
+
+ for (i = 0; i < evlist->nr_mmaps; i++) {
+ union perf_event *event;
+
+ while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+ const u32 type = event->header.type;
+ int tp_flags;
+ struct perf_sample sample;
+
+ ++nr_events;
+
+ if (type != PERF_RECORD_SAMPLE) {
+ perf_evlist__mmap_consume(evlist, i);
+ continue;
+ }
+
+ err = perf_evsel__parse_sample(evsel, event, &sample);
+ if (err) {
+ pr_err("Can't parse sample, err = %d\n", err);
+ goto out_delete_evlist;
+ }
+
+ tp_flags = perf_evsel__intval(evsel, &sample, "flags");
+
+ if (flags != tp_flags) {
+ pr_debug("%s: Expected flags=%#x, got %#x\n",
+ __func__, flags, tp_flags);
+ goto out_delete_evlist;
+ }
+
+ goto out_ok;
+ }
+ }
+
+ if (nr_events == before)
+ perf_evlist__poll(evlist, 10);
+
+ if (++nr_polls > 5) {
+ pr_debug("%s: no events!\n", __func__);
+ goto out_delete_evlist;
+ }
+ }
+out_ok:
+ err = 0;
+out_delete_evlist:
+ perf_evlist__delete(evlist);
+out:
+ return err;
+}
--- /dev/null
+#include "thread_map.h"
+#include "evsel.h"
+#include "debug.h"
+#include "tests.h"
+
+int test__openat_syscall_event(void)
+{
+ int err = -1, fd;
+ struct perf_evsel *evsel;
+ unsigned int nr_openat_calls = 111, i;
+ struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+ char sbuf[STRERR_BUFSIZE];
+
+ if (threads == NULL) {
+ pr_debug("thread_map__new\n");
+ return -1;
+ }
+
+ evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
+ if (evsel == NULL) {
+ if (tracefs_configured())
+ pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
+ else if (debugfs_configured())
+ pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+ else
+ pr_debug("Neither tracefs or debugfs is enabled in this kernel\n");
+ goto out_thread_map_delete;
+ }
+
+ if (perf_evsel__open_per_thread(evsel, threads) < 0) {
+ pr_debug("failed to open counter: %s, "
+ "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
+ goto out_evsel_delete;
+ }
+
+ for (i = 0; i < nr_openat_calls; ++i) {
+ fd = openat(0, "/etc/passwd", O_RDONLY);
+ close(fd);
+ }
+
+ if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
+ pr_debug("perf_evsel__read_on_cpu\n");
+ goto out_close_fd;
+ }
+
+ if (evsel->counts->cpu[0].val != nr_openat_calls) {
+ pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
+ nr_openat_calls, evsel->counts->cpu[0].val);
+ goto out_close_fd;
+ }
+
+ err = 0;
+out_close_fd:
+ perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+ perf_evsel__delete(evsel);
+out_thread_map_delete:
+ thread_map__delete(threads);
+ return err;
+}
TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
- /* syscalls:sys_enter_open:k */
+ /* syscalls:sys_enter_openat:k */
evsel = perf_evsel__next(evsel);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
TEST_ASSERT_VAL("wrong sample_type",
TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
- /* group1 syscalls:sys_enter_open:H */
+ /* group1 syscalls:sys_enter_openat:H */
evsel = leader = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
TEST_ASSERT_VAL("wrong sample_type",
static struct evlist_test test__events[] = {
{
- .name = "syscalls:sys_enter_open",
+ .name = "syscalls:sys_enter_openat",
.check = test__checkevent_tracepoint,
.id = 0,
},
.id = 11,
},
{
- .name = "syscalls:sys_enter_open:k",
+ .name = "syscalls:sys_enter_openat:k",
.check = test__checkevent_tracepoint_modifier,
.id = 12,
},
.id = 22,
},
{
- .name = "r1,syscalls:sys_enter_open:k,1:1:hp",
+ .name = "r1,syscalls:sys_enter_openat:k,1:1:hp",
.check = test__checkevent_list,
.id = 23,
},
.id = 29,
},
{
- .name = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
+ .name = "group1{syscalls:sys_enter_openat:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
.check = test__group3,
.id = 30,
},
if (evlist == NULL)
return -ENOMEM;
- ret = parse_events(evlist, e->name);
+ ret = parse_events(evlist, e->name, NULL);
if (ret) {
pr_debug("failed to parse event '%s', err %d\n",
e->name, ret);
perf_evlist__set_maps(evlist, cpus, threads);
- CHECK__(parse_events(evlist, "cycles:u"));
+ CHECK__(parse_events(evlist, "cycles:u", NULL));
perf_evlist__config(evlist, &opts);
if (ret)
break;
- ret = perf_pmu__config_terms(&formats, &attr, terms, false);
+ ret = perf_pmu__config_terms(&formats, &attr, terms,
+ false, NULL);
if (ret)
break;
perf_evlist__set_maps(evlist, cpus, threads);
/* First event */
- err = parse_events(evlist, "cpu-clock:u");
+ err = parse_events(evlist, "cpu-clock:u", NULL);
if (err) {
pr_debug("Failed to parse event dummy:u\n");
goto out_err;
cpu_clocks_evsel = perf_evlist__last(evlist);
/* Second event */
- err = parse_events(evlist, "cycles:u");
+ err = parse_events(evlist, "cycles:u", NULL);
if (err) {
pr_debug("Failed to parse event cycles:u\n");
goto out_err;
goto out;
}
- err = parse_events(evlist, sched_switch);
+ err = parse_events(evlist, sched_switch, NULL);
if (err) {
pr_debug("Failed to parse event %s\n", sched_switch);
goto out_err;
perf_evsel__set_sample_bit(cycles_evsel, TIME);
/* Fourth event */
- err = parse_events(evlist, "dummy:u");
+ err = parse_events(evlist, "dummy:u", NULL);
if (err) {
pr_debug("Failed to parse event dummy:u\n");
goto out_err;
} \
} while (0)
+#define TEST_ASSERT_EQUAL(text, val, expected) \
+do { \
+ if (val != expected) { \
+ pr_debug("FAILED %s:%d %s (%d != %d)\n", \
+ __FILE__, __LINE__, text, val, expected); \
+ return -1; \
+ } \
+} while (0)
+
enum {
TEST_OK = 0,
TEST_FAIL = -1,
/* Tests */
int test__vmlinux_matches_kallsyms(void);
-int test__open_syscall_event(void);
-int test__open_syscall_event_on_all_cpus(void);
+int test__openat_syscall_event(void);
+int test__openat_syscall_event_on_all_cpus(void);
int test__basic_mmap(void);
int test__PERF_RECORD(void);
int test__rdpmc(void);
int test__perf_evsel__roundtrip_name_test(void);
int test__perf_evsel__tp_sched_test(void);
-int test__syscall_open_tp_fields(void);
+int test__syscall_openat_tp_fields(void);
int test__pmu(void);
int test__attr(void);
int test__dso_data(void);
int test__fdarray__add(void);
int test__kmod_path__parse(void);
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT
struct thread;
struct perf_sample;
leader && t1 && t2 && t3 && other);
mg = leader->mg;
- TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 4);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4);
/* test the map groups pointer is shared */
TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
other_leader = machine__find_thread(machine, 4, 4);
TEST_ASSERT_VAL("failed to find other leader", other_leader);
+ /*
+ * Ok, now that all the rbtree related operations were done,
+ * lets remove all of them from there so that we can do the
+ * refcounting tests.
+ */
+ machine__remove_thread(machine, leader);
+ machine__remove_thread(machine, t1);
+ machine__remove_thread(machine, t2);
+ machine__remove_thread(machine, t3);
+ machine__remove_thread(machine, other);
+ machine__remove_thread(machine, other_leader);
+
other_mg = other->mg;
- TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2);
TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
/* release thread group */
- thread__delete(leader);
- TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 3);
+ thread__put(leader);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3);
- thread__delete(t1);
- TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2);
+ thread__put(t1);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2);
- thread__delete(t2);
- TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1);
+ thread__put(t2);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1);
- thread__delete(t3);
+ thread__put(t3);
/* release other group */
- thread__delete(other_leader);
- TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1);
+ thread__put(other_leader);
+ TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1);
- thread__delete(other);
-
- /*
- * Cannot call machine__delete_threads(machine) now,
- * because we've already released all the threads.
- */
+ thread__put(other);
machines__exit(&machines);
return 0;
int err = -1;
struct rb_node *nd;
struct symbol *sym;
- struct map *kallsyms_map, *vmlinux_map;
+ struct map *kallsyms_map, *vmlinux_map, *map;
struct machine kallsyms, vmlinux;
enum map_type type = MAP__FUNCTION;
+ struct maps *maps = &vmlinux.kmaps.maps[type];
u64 mem_start, mem_end;
/*
pr_info("Maps only in vmlinux:\n");
- for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
- struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+ for (map = maps__first(maps); map; map = map__next(map)) {
+ struct map *
/*
* If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
* the kernel will have the path for the vmlinux file being used,
* both cases.
*/
pair = map_groups__find_by_name(&kallsyms.kmaps, type,
- (pos->dso->kernel ?
- pos->dso->short_name :
- pos->dso->name));
+ (map->dso->kernel ?
+ map->dso->short_name :
+ map->dso->name));
if (pair)
pair->priv = 1;
else
- map__fprintf(pos, stderr);
+ map__fprintf(map, stderr);
}
pr_info("Maps in vmlinux with a different name in kallsyms:\n");
- for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
- struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+ for (map = maps__first(maps); map; map = map__next(map)) {
+ struct map *pair;
- mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start);
- mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end);
+ mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start);
+ mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end);
pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
if (pair == NULL || pair->priv)
if (pair->start == mem_start) {
pair->priv = 1;
pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
- pos->start, pos->end, pos->pgoff, pos->dso->name);
+ map->start, map->end, map->pgoff, map->dso->name);
if (mem_end != pair->end)
pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
pair->start, pair->end, pair->pgoff);
pr_info("Maps only in kallsyms:\n");
- for (nd = rb_first(&kallsyms.kmaps.maps[type]);
- nd; nd = rb_next(nd)) {
- struct map *pos = rb_entry(nd, struct map, rb_node);
+ maps = &kallsyms.kmaps.maps[type];
- if (!pos->priv)
- map__fprintf(pos, stderr);
+ for (map = maps__first(maps); map; map = map__next(map)) {
+ if (!map->priv)
+ map__fprintf(map, stderr);
}
out:
machine__exit(&kallsyms);
#include "../../util/evsel.h"
#include <pthread.h>
+struct disasm_line_samples {
+ double percent;
+ u64 nr;
+};
+
struct browser_disasm_line {
- struct rb_node rb_node;
- u32 idx;
- int idx_asm;
- int jump_sources;
+ struct rb_node rb_node;
+ u32 idx;
+ int idx_asm;
+ int jump_sources;
/*
* actual length of this array is saved on the nr_events field
* of the struct annotate_browser
*/
- double percent[1];
+ struct disasm_line_samples samples[1];
};
static struct annotate_browser_opt {
use_offset,
jump_arrows,
show_linenr,
- show_nr_jumps;
+ show_nr_jumps,
+ show_total_period;
} annotate_browser__opts = {
.use_offset = true,
.jump_arrows = true,
char bf[256];
for (i = 0; i < ab->nr_events; i++) {
- if (bdl->percent[i] > percent_max)
- percent_max = bdl->percent[i];
+ if (bdl->samples[i].percent > percent_max)
+ percent_max = bdl->samples[i].percent;
}
if (dl->offset != -1 && percent_max != 0.0) {
for (i = 0; i < ab->nr_events; i++) {
- ui_browser__set_percent_color(browser, bdl->percent[i],
+ ui_browser__set_percent_color(browser,
+ bdl->samples[i].percent,
current_entry);
- slsmg_printf("%6.2f ", bdl->percent[i]);
+ if (annotate_browser__opts.show_total_period)
+ slsmg_printf("%6" PRIu64 " ",
+ bdl->samples[i].nr);
+ else
+ slsmg_printf("%6.2f ", bdl->samples[i].percent);
}
} else {
ui_browser__set_percent_color(browser, 0, current_entry);
int i;
for (i = 0; i < nr_pcnt; i++) {
- if (a->percent[i] == b->percent[i])
+ if (a->samples[i].percent == b->samples[i].percent)
continue;
- return a->percent[i] < b->percent[i];
+ return a->samples[i].percent < b->samples[i].percent;
}
return 0;
}
next = disasm__get_next_ip_line(¬es->src->source, pos);
for (i = 0; i < browser->nr_events; i++) {
- bpos->percent[i] = disasm__calc_percent(notes,
+ u64 nr_samples;
+
+ bpos->samples[i].percent = disasm__calc_percent(notes,
evsel->idx + i,
pos->offset,
next ? next->offset : len,
- &path);
+ &path, &nr_samples);
+ bpos->samples[i].nr = nr_samples;
- if (max_percent < bpos->percent[i])
- max_percent = bpos->percent[i];
+ if (max_percent < bpos->samples[i].percent)
+ max_percent = bpos->samples[i].percent;
}
if (max_percent < 0.01) {
"n Search next string\n"
"o Toggle disassembler output/simplified view\n"
"s Toggle source code view\n"
+ "t Toggle total period view\n"
"/ Search string\n"
"k Toggle line numbers\n"
"r Run available scripts\n"
ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
}
continue;
+ case 't':
+ annotate_browser__opts.show_total_period =
+ !annotate_browser__opts.show_total_period;
+ annotate_browser__update_addr_width(browser);
+ continue;
case K_LEFT:
case K_ESC:
case 'q':
int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
struct hist_browser_timer *hbt)
{
+ /* Set default value for show_total_period. */
+ annotate_browser__opts.show_total_period =
+ symbol_conf.show_total_period;
+
return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt);
}
int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
struct hist_browser_timer *hbt)
{
+ /* reset abort key so that it can get Ctrl-C as a key */
+ SLang_reset_tty();
+ SLang_init_tty(0, 0, 0);
+
return map_symbol__tui_annotate(&he->ms, evsel, hbt);
}
if (perf_evsel__is_group_event(evsel)) {
nr_pcnt = evsel->nr_members;
- sizeof_bdl += sizeof(double) * (nr_pcnt - 1);
+ sizeof_bdl += sizeof(struct disasm_line_samples) *
+ (nr_pcnt - 1);
}
if (symbol__annotate(sym, map, sizeof_bdl) < 0) {
ANNOTATE_CFG(show_linenr),
ANNOTATE_CFG(show_nr_jumps),
ANNOTATE_CFG(use_offset),
+ ANNOTATE_CFG(show_total_period),
};
#undef ANNOTATE_CFG
struct hists *hists;
struct hist_entry *he_selection;
struct map_symbol *selection;
+ struct hist_browser_timer *hbt;
+ struct pstack *pstack;
+ struct perf_session_env *env;
int print_seq;
bool show_dso;
bool show_headers;
struct hist_entry *he =
rb_entry(nd, struct hist_entry, rb_node);
- if (he->ms.unfolded)
+ if (he->unfolded)
unfolded_rows += he->nr_rows;
}
return unfolded_rows;
return unfolded ? '-' : '+';
}
-static char map_symbol__folded(const struct map_symbol *ms)
-{
- return ms->has_children ? tree__folded_sign(ms->unfolded) : ' ';
-}
-
static char hist_entry__folded(const struct hist_entry *he)
{
- return map_symbol__folded(&he->ms);
+ return he->has_children ? tree__folded_sign(he->unfolded) : ' ';
}
static char callchain_list__folded(const struct callchain_list *cl)
{
- return map_symbol__folded(&cl->ms);
+ return cl->has_children ? tree__folded_sign(cl->unfolded) : ' ';
}
-static void map_symbol__set_folding(struct map_symbol *ms, bool unfold)
+static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
{
- ms->unfolded = unfold ? ms->has_children : false;
+ cl->unfolded = unfold ? cl->has_children : false;
}
static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
list_for_each_entry(chain, &node->val, list) {
++n;
- unfolded = chain->ms.unfolded;
+ unfolded = chain->unfolded;
}
if (unfolded)
return n;
}
-static bool map_symbol__toggle_fold(struct map_symbol *ms)
+static bool hist_entry__toggle_fold(struct hist_entry *he)
{
- if (!ms)
+ if (!he)
return false;
- if (!ms->has_children)
+ if (!he->has_children)
return false;
- ms->unfolded = !ms->unfolded;
+ he->unfolded = !he->unfolded;
+ return true;
+}
+
+static bool callchain_list__toggle_fold(struct callchain_list *cl)
+{
+ if (!cl)
+ return false;
+
+ if (!cl->has_children)
+ return false;
+
+ cl->unfolded = !cl->unfolded;
return true;
}
list_for_each_entry(chain, &child->val, list) {
if (first) {
first = false;
- chain->ms.has_children = chain->list.next != &child->val ||
+ chain->has_children = chain->list.next != &child->val ||
!RB_EMPTY_ROOT(&child->rb_root);
} else
- chain->ms.has_children = chain->list.next == &child->val &&
+ chain->has_children = chain->list.next == &child->val &&
!RB_EMPTY_ROOT(&child->rb_root);
}
struct callchain_list *chain;
chain = list_entry(node->val.next, struct callchain_list, list);
- chain->ms.has_children = has_sibling;
+ chain->has_children = has_sibling;
if (!list_empty(&node->val)) {
chain = list_entry(node->val.prev, struct callchain_list, list);
- chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+ chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
}
callchain_node__init_have_children_rb_tree(node);
static void hist_entry__init_have_children(struct hist_entry *he)
{
if (!he->init_have_children) {
- he->ms.has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
+ he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
callchain__init_have_children(&he->sorted_chain);
he->init_have_children = true;
}
static bool hist_browser__toggle_fold(struct hist_browser *browser)
{
- if (map_symbol__toggle_fold(browser->selection)) {
- struct hist_entry *he = browser->he_selection;
+ struct hist_entry *he = browser->he_selection;
+ struct map_symbol *ms = browser->selection;
+ struct callchain_list *cl = container_of(ms, struct callchain_list, ms);
+ bool has_children;
+ if (ms == &he->ms)
+ has_children = hist_entry__toggle_fold(he);
+ else
+ has_children = callchain_list__toggle_fold(cl);
+
+ if (has_children) {
hist_entry__init_have_children(he);
browser->b.nr_entries -= he->nr_rows;
browser->nr_callchain_rows -= he->nr_rows;
- if (he->ms.unfolded)
+ if (he->unfolded)
he->nr_rows = callchain__count_rows(&he->sorted_chain);
else
he->nr_rows = 0;
list_for_each_entry(chain, &child->val, list) {
++n;
- map_symbol__set_folding(&chain->ms, unfold);
- has_children = chain->ms.has_children;
+ callchain_list__set_folding(chain, unfold);
+ has_children = chain->has_children;
}
if (has_children)
list_for_each_entry(chain, &node->val, list) {
++n;
- map_symbol__set_folding(&chain->ms, unfold);
- has_children = chain->ms.has_children;
+ callchain_list__set_folding(chain, unfold);
+ has_children = chain->has_children;
}
if (has_children)
static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
{
hist_entry__init_have_children(he);
- map_symbol__set_folding(&he->ms, unfold);
+ he->unfolded = unfold ? he->has_children : false;
- if (he->ms.has_children) {
+ if (he->has_children) {
int n = callchain__set_folding(&he->sorted_chain, unfold);
he->nr_rows = unfold ? n : 0;
} else
"Or reduce the sampling frequency.");
}
-static int hist_browser__run(struct hist_browser *browser,
- struct hist_browser_timer *hbt)
+static int hist_browser__run(struct hist_browser *browser, const char *help)
{
int key;
char title[160];
+ struct hist_browser_timer *hbt = browser->hbt;
int delay_secs = hbt ? hbt->refresh : 0;
browser->b.entries = &browser->hists->entries;
hists__browser_title(browser->hists, hbt, title, sizeof(title));
- if (ui_browser__show(&browser->b, title,
- "Press '?' for help on key bindings") < 0)
+ if (ui_browser__show(&browser->b, title, help) < 0)
return -1;
while (1) {
if (offset > 0) {
do {
h = rb_entry(nd, struct hist_entry, rb_node);
- if (h->ms.unfolded) {
+ if (h->unfolded) {
u16 remaining = h->nr_rows - h->row_offset;
if (offset > remaining) {
offset -= remaining;
} else if (offset < 0) {
while (1) {
h = rb_entry(nd, struct hist_entry, rb_node);
- if (h->ms.unfolded) {
+ if (h->unfolded) {
if (first) {
if (-offset > h->row_offset) {
offset += h->row_offset;
* row_offset at its last entry.
*/
h = rb_entry(nd, struct hist_entry, rb_node);
- if (h->ms.unfolded)
+ if (h->unfolded)
h->row_offset = h->nr_rows;
break;
}
return 0;
}
-static struct hist_browser *hist_browser__new(struct hists *hists)
+static struct hist_browser *hist_browser__new(struct hists *hists,
+ struct hist_browser_timer *hbt,
+ struct perf_session_env *env)
{
struct hist_browser *browser = zalloc(sizeof(*browser));
browser->b.seek = ui_browser__hists_seek;
browser->b.use_navkeypressed = true;
browser->show_headers = symbol_conf.show_hist_headers;
+ browser->hbt = hbt;
+ browser->env = env;
}
return browser;
return ret;
}
+struct popup_action {
+ struct thread *thread;
+ struct dso *dso;
+ struct map_symbol ms;
+
+ int (*fn)(struct hist_browser *browser, struct popup_action *act);
+};
+
+static int
+do_annotate(struct hist_browser *browser, struct popup_action *act)
+{
+ struct perf_evsel *evsel;
+ struct annotation *notes;
+ struct hist_entry *he;
+ int err;
+
+ if (!objdump_path && perf_session_env__lookup_objdump(browser->env))
+ return 0;
+
+ notes = symbol__annotation(act->ms.sym);
+ if (!notes->src)
+ return 0;
+
+ evsel = hists_to_evsel(browser->hists);
+ err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt);
+ he = hist_browser__selected_entry(browser);
+ /*
+ * offer option to annotate the other branch source or target
+ * (if they exists) when returning from annotate
+ */
+ if ((err == 'q' || err == CTRL('c')) && he->branch_info)
+ return 1;
+
+ ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
+ if (err)
+ ui_browser__handle_resize(&browser->b);
+ return 0;
+}
+
+static int
+add_annotate_opt(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act, char **optstr,
+ struct map *map, struct symbol *sym)
+{
+ if (sym == NULL || map->dso->annotate_warned)
+ return 0;
+
+ if (asprintf(optstr, "Annotate %s", sym->name) < 0)
+ return 0;
+
+ act->ms.map = map;
+ act->ms.sym = sym;
+ act->fn = do_annotate;
+ return 1;
+}
+
+static int
+do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
+{
+ struct thread *thread = act->thread;
+
+ if (browser->hists->thread_filter) {
+ pstack__remove(browser->pstack, &browser->hists->thread_filter);
+ perf_hpp__set_elide(HISTC_THREAD, false);
+ thread__zput(browser->hists->thread_filter);
+ ui_helpline__pop();
+ } else {
+ ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
+ thread->comm_set ? thread__comm_str(thread) : "",
+ thread->tid);
+ browser->hists->thread_filter = thread__get(thread);
+ perf_hpp__set_elide(HISTC_THREAD, false);
+ pstack__push(browser->pstack, &browser->hists->thread_filter);
+ }
+
+ hists__filter_by_thread(browser->hists);
+ hist_browser__reset(browser);
+ return 0;
+}
+
+static int
+add_thread_opt(struct hist_browser *browser, struct popup_action *act,
+ char **optstr, struct thread *thread)
+{
+ if (thread == NULL)
+ return 0;
+
+ if (asprintf(optstr, "Zoom %s %s(%d) thread",
+ browser->hists->thread_filter ? "out of" : "into",
+ thread->comm_set ? thread__comm_str(thread) : "",
+ thread->tid) < 0)
+ return 0;
+
+ act->thread = thread;
+ act->fn = do_zoom_thread;
+ return 1;
+}
+
+static int
+do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
+{
+ struct dso *dso = act->dso;
+
+ if (browser->hists->dso_filter) {
+ pstack__remove(browser->pstack, &browser->hists->dso_filter);
+ perf_hpp__set_elide(HISTC_DSO, false);
+ browser->hists->dso_filter = NULL;
+ ui_helpline__pop();
+ } else {
+ if (dso == NULL)
+ return 0;
+ ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
+ dso->kernel ? "the Kernel" : dso->short_name);
+ browser->hists->dso_filter = dso;
+ perf_hpp__set_elide(HISTC_DSO, true);
+ pstack__push(browser->pstack, &browser->hists->dso_filter);
+ }
+
+ hists__filter_by_dso(browser->hists);
+ hist_browser__reset(browser);
+ return 0;
+}
+
+static int
+add_dso_opt(struct hist_browser *browser, struct popup_action *act,
+ char **optstr, struct dso *dso)
+{
+ if (dso == NULL)
+ return 0;
+
+ if (asprintf(optstr, "Zoom %s %s DSO",
+ browser->hists->dso_filter ? "out of" : "into",
+ dso->kernel ? "the Kernel" : dso->short_name) < 0)
+ return 0;
+
+ act->dso = dso;
+ act->fn = do_zoom_dso;
+ return 1;
+}
+
+static int
+do_browse_map(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act)
+{
+ map__browse(act->ms.map);
+ return 0;
+}
+
+static int
+add_map_opt(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act, char **optstr, struct map *map)
+{
+ if (map == NULL)
+ return 0;
+
+ if (asprintf(optstr, "Browse map details") < 0)
+ return 0;
+
+ act->ms.map = map;
+ act->fn = do_browse_map;
+ return 1;
+}
+
+static int
+do_run_script(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act)
+{
+ char script_opt[64];
+ memset(script_opt, 0, sizeof(script_opt));
+
+ if (act->thread) {
+ scnprintf(script_opt, sizeof(script_opt), " -c %s ",
+ thread__comm_str(act->thread));
+ } else if (act->ms.sym) {
+ scnprintf(script_opt, sizeof(script_opt), " -S %s ",
+ act->ms.sym->name);
+ }
+
+ script_browse(script_opt);
+ return 0;
+}
+
+static int
+add_script_opt(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act, char **optstr,
+ struct thread *thread, struct symbol *sym)
+{
+ if (thread) {
+ if (asprintf(optstr, "Run scripts for samples of thread [%s]",
+ thread__comm_str(thread)) < 0)
+ return 0;
+ } else if (sym) {
+ if (asprintf(optstr, "Run scripts for samples of symbol [%s]",
+ sym->name) < 0)
+ return 0;
+ } else {
+ if (asprintf(optstr, "Run scripts for all samples") < 0)
+ return 0;
+ }
+
+ act->thread = thread;
+ act->ms.sym = sym;
+ act->fn = do_run_script;
+ return 1;
+}
+
+static int
+do_switch_data(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act __maybe_unused)
+{
+ if (switch_data_file()) {
+ ui__warning("Won't switch the data files due to\n"
+ "no valid data file get selected!\n");
+ return 0;
+ }
+
+ return K_SWITCH_INPUT_DATA;
+}
+
+static int
+add_switch_opt(struct hist_browser *browser,
+ struct popup_action *act, char **optstr)
+{
+ if (!is_report_browser(browser->hbt))
+ return 0;
+
+ if (asprintf(optstr, "Switch to another data file in PWD") < 0)
+ return 0;
+
+ act->fn = do_switch_data;
+ return 1;
+}
+
+static int
+do_exit_browser(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act __maybe_unused)
+{
+ return 0;
+}
+
+static int
+add_exit_opt(struct hist_browser *browser __maybe_unused,
+ struct popup_action *act, char **optstr)
+{
+ if (asprintf(optstr, "Exit") < 0)
+ return 0;
+
+ act->fn = do_exit_browser;
+ return 1;
+}
+
static void hist_browser__update_nr_entries(struct hist_browser *hb)
{
u64 nr_entries = 0;
struct perf_session_env *env)
{
struct hists *hists = evsel__hists(evsel);
- struct hist_browser *browser = hist_browser__new(hists);
+ struct hist_browser *browser = hist_browser__new(hists, hbt, env);
struct branch_info *bi;
- struct pstack *fstack;
- char *options[16];
+#define MAX_OPTIONS 16
+ char *options[MAX_OPTIONS];
+ struct popup_action actions[MAX_OPTIONS];
int nr_options = 0;
int key = -1;
char buf[64];
- char script_opt[64];
int delay_secs = hbt ? hbt->refresh : 0;
struct perf_hpp_fmt *fmt;
"t Zoom into current Thread\n"
"V Verbose (DSO names in callchains, etc)\n"
"z Toggle zeroing of samples\n"
+ "f Enable/Disable events\n"
"/ Filter symbol by name";
if (browser == NULL)
return -1;
+ /* reset abort key so that it can get Ctrl-C as a key */
+ SLang_reset_tty();
+ SLang_init_tty(0, 0, 0);
+
if (min_pcnt) {
browser->min_pcnt = min_pcnt;
hist_browser__update_nr_entries(browser);
}
- fstack = pstack__new(2);
- if (fstack == NULL)
+ browser->pstack = pstack__new(2);
+ if (browser->pstack == NULL)
goto out;
ui_helpline__push(helpline);
memset(options, 0, sizeof(options));
+ memset(actions, 0, sizeof(actions));
perf_hpp__for_each_format(fmt)
perf_hpp__reset_width(fmt, hists);
while (1) {
struct thread *thread = NULL;
- const struct dso *dso = NULL;
- int choice = 0,
- annotate = -2, zoom_dso = -2, zoom_thread = -2,
- annotate_f = -2, annotate_t = -2, browse_map = -2;
- int scripts_comm = -2, scripts_symbol = -2,
- scripts_all = -2, switch_data = -2;
+ struct dso *dso = NULL;
+ int choice = 0;
nr_options = 0;
- key = hist_browser__run(browser, hbt);
+ key = hist_browser__run(browser, helpline);
if (browser->he_selection != NULL) {
thread = hist_browser__selected_thread(browser);
browser->selection->sym == NULL ||
browser->selection->map->dso->annotate_warned)
continue;
- goto do_annotate;
+
+ actions->ms.map = browser->selection->map;
+ actions->ms.sym = browser->selection->sym;
+ do_annotate(browser, actions);
+ continue;
case 'P':
hist_browser__dump(browser);
continue;
case 'd':
- goto zoom_dso;
+ actions->dso = dso;
+ do_zoom_dso(browser, actions);
+ continue;
case 'V':
browser->show_dso = !browser->show_dso;
continue;
case 't':
- goto zoom_thread;
+ actions->thread = thread;
+ do_zoom_thread(browser, actions);
+ continue;
case '/':
if (ui_browser__input_window("Symbol to show",
"Please enter the name of symbol you want to see",
}
continue;
case 'r':
- if (is_report_browser(hbt))
- goto do_scripts;
+ if (is_report_browser(hbt)) {
+ actions->thread = NULL;
+ actions->ms.sym = NULL;
+ do_run_script(browser, actions);
+ }
continue;
case 's':
- if (is_report_browser(hbt))
- goto do_data_switch;
+ if (is_report_browser(hbt)) {
+ key = do_switch_data(browser, actions);
+ if (key == K_SWITCH_INPUT_DATA)
+ goto out_free_stack;
+ }
continue;
case 'i':
/* env->arch is NULL for live-mode (i.e. perf top) */
case K_LEFT: {
const void *top;
- if (pstack__empty(fstack)) {
+ if (pstack__empty(browser->pstack)) {
/*
* Go back to the perf_evsel_menu__run or other user
*/
goto out_free_stack;
continue;
}
- top = pstack__pop(fstack);
- if (top == &browser->hists->dso_filter)
- goto zoom_out_dso;
+ top = pstack__peek(browser->pstack);
+ if (top == &browser->hists->dso_filter) {
+ /*
+ * No need to set actions->dso here since
+ * it's just to remove the current filter.
+ * Ditto for thread below.
+ */
+ do_zoom_dso(browser, actions);
+ }
if (top == &browser->hists->thread_filter)
- goto zoom_out_thread;
+ do_zoom_thread(browser, actions);
continue;
}
case K_ESC:
case 'q':
case CTRL('c'):
goto out_free_stack;
+ case 'f':
+ if (!is_report_browser(hbt))
+ goto out_free_stack;
+ /* Fall thru */
default:
+ helpline = "Press '?' for help on key bindings";
continue;
}
if (bi == NULL)
goto skip_annotation;
- if (bi->from.sym != NULL &&
- !bi->from.map->dso->annotate_warned &&
- asprintf(&options[nr_options], "Annotate %s", bi->from.sym->name) > 0) {
- annotate_f = nr_options++;
- }
-
- if (bi->to.sym != NULL &&
- !bi->to.map->dso->annotate_warned &&
- (bi->to.sym != bi->from.sym ||
- bi->to.map->dso != bi->from.map->dso) &&
- asprintf(&options[nr_options], "Annotate %s", bi->to.sym->name) > 0) {
- annotate_t = nr_options++;
- }
+ nr_options += add_annotate_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ bi->from.map,
+ bi->from.sym);
+ if (bi->to.sym != bi->from.sym)
+ nr_options += add_annotate_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ bi->to.map,
+ bi->to.sym);
} else {
- if (browser->selection->sym != NULL &&
- !browser->selection->map->dso->annotate_warned) {
- struct annotation *notes;
-
- notes = symbol__annotation(browser->selection->sym);
-
- if (notes->src &&
- asprintf(&options[nr_options], "Annotate %s",
- browser->selection->sym->name) > 0) {
- annotate = nr_options++;
- }
- }
+ nr_options += add_annotate_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ browser->selection->map,
+ browser->selection->sym);
}
skip_annotation:
- if (thread != NULL &&
- asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
- (browser->hists->thread_filter ? "out of" : "into"),
- (thread->comm_set ? thread__comm_str(thread) : ""),
- thread->tid) > 0)
- zoom_thread = nr_options++;
-
- if (dso != NULL &&
- asprintf(&options[nr_options], "Zoom %s %s DSO",
- (browser->hists->dso_filter ? "out of" : "into"),
- (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
- zoom_dso = nr_options++;
-
- if (browser->selection != NULL &&
- browser->selection->map != NULL &&
- asprintf(&options[nr_options], "Browse map details") > 0)
- browse_map = nr_options++;
+ nr_options += add_thread_opt(browser, &actions[nr_options],
+ &options[nr_options], thread);
+ nr_options += add_dso_opt(browser, &actions[nr_options],
+ &options[nr_options], dso);
+ nr_options += add_map_opt(browser, &actions[nr_options],
+ &options[nr_options],
+ browser->selection->map);
/* perf script support */
if (browser->he_selection) {
- struct symbol *sym;
-
- if (asprintf(&options[nr_options], "Run scripts for samples of thread [%s]",
- thread__comm_str(browser->he_selection->thread)) > 0)
- scripts_comm = nr_options++;
-
- sym = browser->he_selection->ms.sym;
- if (sym && sym->namelen &&
- asprintf(&options[nr_options], "Run scripts for samples of symbol [%s]",
- sym->name) > 0)
- scripts_symbol = nr_options++;
+ nr_options += add_script_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ thread, NULL);
+ nr_options += add_script_opt(browser,
+ &actions[nr_options],
+ &options[nr_options],
+ NULL, browser->selection->sym);
}
-
- if (asprintf(&options[nr_options], "Run scripts for all samples") > 0)
- scripts_all = nr_options++;
-
- if (is_report_browser(hbt) && asprintf(&options[nr_options],
- "Switch to another data file in PWD") > 0)
- switch_data = nr_options++;
+ nr_options += add_script_opt(browser, &actions[nr_options],
+ &options[nr_options], NULL, NULL);
+ nr_options += add_switch_opt(browser, &actions[nr_options],
+ &options[nr_options]);
add_exit_option:
- options[nr_options++] = (char *)"Exit";
-retry_popup_menu:
- choice = ui__popup_menu(nr_options, options);
-
- if (choice == nr_options - 1)
- break;
-
- if (choice == -1) {
- free_popup_options(options, nr_options - 1);
- continue;
- }
-
- if (choice == annotate || choice == annotate_t || choice == annotate_f) {
- struct hist_entry *he;
- struct annotation *notes;
- struct map_symbol ms;
- int err;
-do_annotate:
- if (!objdump_path && perf_session_env__lookup_objdump(env))
- continue;
-
- he = hist_browser__selected_entry(browser);
- if (he == NULL)
- continue;
-
- if (choice == annotate_f) {
- ms.map = he->branch_info->from.map;
- ms.sym = he->branch_info->from.sym;
- } else if (choice == annotate_t) {
- ms.map = he->branch_info->to.map;
- ms.sym = he->branch_info->to.sym;
- } else {
- ms = *browser->selection;
- }
+ nr_options += add_exit_opt(browser, &actions[nr_options],
+ &options[nr_options]);
- notes = symbol__annotation(ms.sym);
- if (!notes->src)
- continue;
-
- err = map_symbol__tui_annotate(&ms, evsel, hbt);
- /*
- * offer option to annotate the other branch source or target
- * (if they exists) when returning from annotate
- */
- if ((err == 'q' || err == CTRL('c'))
- && annotate_t != -2 && annotate_f != -2)
- goto retry_popup_menu;
-
- ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
- if (err)
- ui_browser__handle_resize(&browser->b);
-
- } else if (choice == browse_map)
- map__browse(browser->selection->map);
- else if (choice == zoom_dso) {
-zoom_dso:
- if (browser->hists->dso_filter) {
- pstack__remove(fstack, &browser->hists->dso_filter);
-zoom_out_dso:
- ui_helpline__pop();
- browser->hists->dso_filter = NULL;
- perf_hpp__set_elide(HISTC_DSO, false);
- } else {
- if (dso == NULL)
- continue;
- ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
- dso->kernel ? "the Kernel" : dso->short_name);
- browser->hists->dso_filter = dso;
- perf_hpp__set_elide(HISTC_DSO, true);
- pstack__push(fstack, &browser->hists->dso_filter);
- }
- hists__filter_by_dso(hists);
- hist_browser__reset(browser);
- } else if (choice == zoom_thread) {
-zoom_thread:
- if (browser->hists->thread_filter) {
- pstack__remove(fstack, &browser->hists->thread_filter);
-zoom_out_thread:
- ui_helpline__pop();
- thread__zput(browser->hists->thread_filter);
- perf_hpp__set_elide(HISTC_THREAD, false);
- } else {
- ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
- thread->comm_set ? thread__comm_str(thread) : "",
- thread->tid);
- browser->hists->thread_filter = thread__get(thread);
- perf_hpp__set_elide(HISTC_THREAD, false);
- pstack__push(fstack, &browser->hists->thread_filter);
- }
- hists__filter_by_thread(hists);
- hist_browser__reset(browser);
- }
- /* perf scripts support */
- else if (choice == scripts_all || choice == scripts_comm ||
- choice == scripts_symbol) {
-do_scripts:
- memset(script_opt, 0, 64);
+ do {
+ struct popup_action *act;
- if (choice == scripts_comm)
- sprintf(script_opt, " -c %s ", thread__comm_str(browser->he_selection->thread));
+ choice = ui__popup_menu(nr_options, options);
+ if (choice == -1 || choice >= nr_options)
+ break;
- if (choice == scripts_symbol)
- sprintf(script_opt, " -S %s ", browser->he_selection->ms.sym->name);
+ act = &actions[choice];
+ key = act->fn(browser, act);
+ } while (key == 1);
- script_browse(script_opt);
- }
- /* Switch to another data file */
- else if (choice == switch_data) {
-do_data_switch:
- if (!switch_data_file()) {
- key = K_SWITCH_INPUT_DATA;
- break;
- } else
- ui__warning("Won't switch the data files due to\n"
- "no valid data file get selected!\n");
- }
+ if (key == K_SWITCH_INPUT_DATA)
+ break;
}
out_free_stack:
- pstack__delete(fstack);
+ pstack__delete(browser->pstack);
out:
hist_browser__delete(browser);
- free_popup_options(options, nr_options - 1);
+ free_popup_options(options, MAX_OPTIONS);
return key;
}
err = SLsmg_init_smg();
if (err < 0)
goto out;
- err = SLang_init_tty(0, 0, 0);
+ err = SLang_init_tty(-1, 0, 0);
if (err < 0)
goto out;
libperf-y += intlist.o
libperf-y += vdso.o
libperf-y += stat.o
+libperf-y += stat-shadow.o
libperf-y += record.o
libperf-y += srcline.o
libperf-y += data.o
libperf-$(CONFIG_X86) += tsc.o
libperf-y += cloexec.o
libperf-y += thread-stack.o
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
+libperf-y += parse-branch-options.o
libperf-$(CONFIG_LIBELF) += symbol-elf.o
libperf-$(CONFIG_LIBELF) += probe-event.o
$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
$(call rule_mkdir)
- @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
+ $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
$(OUTPUT)util/parse-events-bison.c: util/parse-events.y
$(call rule_mkdir)
- @$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
+ $(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
$(call rule_mkdir)
- @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
+ $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
$(OUTPUT)util/pmu-bison.c: util/pmu.y
$(call rule_mkdir)
- @$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
+ $(Q)$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
CFLAGS_parse-events-flex.o += -w
CFLAGS_pmu-flex.o += -w
-CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
+CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
return 0;
}
+static struct annotation *symbol__get_annotation(struct symbol *sym)
+{
+ struct annotation *notes = symbol__annotation(sym);
+
+ if (notes->src == NULL) {
+ if (symbol__alloc_hist(sym) < 0)
+ return NULL;
+ }
+ return notes;
+}
+
static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
int evidx, u64 addr)
{
if (sym == NULL)
return 0;
-
- notes = symbol__annotation(sym);
- if (notes->src == NULL) {
- if (symbol__alloc_hist(sym) < 0)
- return -ENOMEM;
- }
-
+ notes = symbol__get_annotation(sym);
+ if (notes == NULL)
+ return -ENOMEM;
return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
}
}
double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
- s64 end, const char **path)
+ s64 end, const char **path, u64 *nr_samples)
{
struct source_line *src_line = notes->src->lines;
double percent = 0.0;
+ *nr_samples = 0;
if (src_line) {
size_t sizeof_src_line = sizeof(*src_line) +
- sizeof(src_line->p) * (src_line->nr_pcnt - 1);
+ sizeof(src_line->samples) * (src_line->nr_pcnt - 1);
while (offset < end) {
src_line = (void *)notes->src->lines +
if (*path == NULL)
*path = src_line->path;
- percent += src_line->p[evidx].percent;
+ percent += src_line->samples[evidx].percent;
+ *nr_samples += src_line->samples[evidx].nr;
offset++;
}
} else {
while (offset < end)
hits += h->addr[offset++];
- if (h->sum)
+ if (h->sum) {
+ *nr_samples = hits;
percent = 100.0 * hits / h->sum;
+ }
}
return percent;
if (dl->offset != -1) {
const char *path = NULL;
+ u64 nr_samples;
double percent, max_percent = 0.0;
double *ppercents = &percent;
+ u64 *psamples = &nr_samples;
int i, nr_percent = 1;
const char *color;
struct annotation *notes = symbol__annotation(sym);
if (perf_evsel__is_group_event(evsel)) {
nr_percent = evsel->nr_members;
ppercents = calloc(nr_percent, sizeof(double));
- if (ppercents == NULL)
+ psamples = calloc(nr_percent, sizeof(u64));
+ if (ppercents == NULL || psamples == NULL) {
return -1;
+ }
}
for (i = 0; i < nr_percent; i++) {
notes->src->lines ? i : evsel->idx + i,
offset,
next ? next->offset : (s64) len,
- &path);
+ &path, &nr_samples);
ppercents[i] = percent;
+ psamples[i] = nr_samples;
if (percent > max_percent)
max_percent = percent;
}
for (i = 0; i < nr_percent; i++) {
percent = ppercents[i];
+ nr_samples = psamples[i];
color = get_percent_color(percent);
- color_fprintf(stdout, color, " %7.2f", percent);
+
+ if (symbol_conf.show_total_period)
+ color_fprintf(stdout, color, " %7" PRIu64,
+ nr_samples);
+ else
+ color_fprintf(stdout, color, " %7.2f", percent);
}
printf(" : ");
if (ppercents != &percent)
free(ppercents);
+ if (psamples != &nr_samples)
+ free(psamples);
+
} else if (max_lines && printed >= max_lines)
return 1;
else {
ret = strcmp(iter->path, src_line->path);
if (ret == 0) {
for (i = 0; i < src_line->nr_pcnt; i++)
- iter->p[i].percent_sum += src_line->p[i].percent;
+ iter->samples[i].percent_sum += src_line->samples[i].percent;
return;
}
}
for (i = 0; i < src_line->nr_pcnt; i++)
- src_line->p[i].percent_sum = src_line->p[i].percent;
+ src_line->samples[i].percent_sum = src_line->samples[i].percent;
rb_link_node(&src_line->node, parent, p);
rb_insert_color(&src_line->node, root);
int i;
for (i = 0; i < a->nr_pcnt; i++) {
- if (a->p[i].percent_sum == b->p[i].percent_sum)
+ if (a->samples[i].percent_sum == b->samples[i].percent_sum)
continue;
- return a->p[i].percent_sum > b->p[i].percent_sum;
+ return a->samples[i].percent_sum > b->samples[i].percent_sum;
}
return 0;
int i;
sizeof_src_line = sizeof(*src_line) +
- (sizeof(src_line->p) * (src_line->nr_pcnt - 1));
+ (sizeof(src_line->samples) * (src_line->nr_pcnt - 1));
for (i = 0; i < len; i++) {
free_srcline(src_line->path);
h_sum += h->sum;
}
nr_pcnt = evsel->nr_members;
- sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p);
+ sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples);
}
if (!h_sum)
for (k = 0; k < nr_pcnt; k++) {
h = annotation__histogram(notes, evidx + k);
- src_line->p[k].percent = 100.0 * h->addr[i] / h->sum;
+ src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum;
- if (src_line->p[k].percent > percent_max)
- percent_max = src_line->p[k].percent;
+ if (src_line->samples[k].percent > percent_max)
+ percent_max = src_line->samples[k].percent;
}
if (percent_max <= 0.5)
src_line = rb_entry(node, struct source_line, node);
for (i = 0; i < src_line->nr_pcnt; i++) {
- percent = src_line->p[i].percent_sum;
+ percent = src_line->samples[i].percent_sum;
color = get_percent_color(percent);
color_fprintf(stdout, color, " %7.2f", percent);
int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
size_t disasm__fprintf(struct list_head *head, FILE *fp);
double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
- s64 end, const char **path);
+ s64 end, const char **path, u64 *nr_samples);
struct sym_hist {
u64 sum;
u64 addr[0];
};
-struct source_line_percent {
+struct source_line_samples {
double percent;
double percent_sum;
+ double nr;
};
struct source_line {
struct rb_node node;
char *path;
int nr_pcnt;
- struct source_line_percent p[1];
+ struct source_line_samples samples[1];
};
/** struct annotated_source - symbols with hits have this attached as in sannotation
--- /dev/null
+/*
+ * auxtrace.c: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <linux/string.h>
+
+#include <sys/param.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <limits.h>
+#include <errno.h>
+#include <linux/list.h>
+
+#include "../perf.h"
+#include "util.h"
+#include "evlist.h"
+#include "cpumap.h"
+#include "thread_map.h"
+#include "asm/bug.h"
+#include "auxtrace.h"
+
+#include <linux/hash.h>
+
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+#include "parse-options.h"
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd)
+{
+ struct perf_event_mmap_page *pc = userpg;
+
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pr_err("Cannot use AUX area tracing mmaps\n");
+ return -1;
+#endif
+
+ WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
+
+ mm->userpg = userpg;
+ mm->mask = mp->mask;
+ mm->len = mp->len;
+ mm->prev = 0;
+ mm->idx = mp->idx;
+ mm->tid = mp->tid;
+ mm->cpu = mp->cpu;
+
+ if (!mp->len) {
+ mm->base = NULL;
+ return 0;
+ }
+
+ pc->aux_offset = mp->offset;
+ pc->aux_size = mp->len;
+
+ mm->base = mmap(NULL, mp->len, mp->prot, MAP_SHARED, fd, mp->offset);
+ if (mm->base == MAP_FAILED) {
+ pr_debug2("failed to mmap AUX area\n");
+ mm->base = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm)
+{
+ if (mm->base) {
+ munmap(mm->base, mm->len);
+ mm->base = NULL;
+ }
+}
+
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite)
+{
+ if (auxtrace_pages) {
+ mp->offset = auxtrace_offset;
+ mp->len = auxtrace_pages * (size_t)page_size;
+ mp->mask = is_power_of_2(mp->len) ? mp->len - 1 : 0;
+ mp->prot = PROT_READ | (auxtrace_overwrite ? 0 : PROT_WRITE);
+ pr_debug2("AUX area mmap length %zu\n", mp->len);
+ } else {
+ mp->len = 0;
+ }
+}
+
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu)
+{
+ mp->idx = idx;
+
+ if (per_cpu) {
+ mp->cpu = evlist->cpus->map[idx];
+ if (evlist->threads)
+ mp->tid = evlist->threads->map[0];
+ else
+ mp->tid = -1;
+ } else {
+ mp->cpu = -1;
+ mp->tid = evlist->threads->map[idx];
+ }
+}
+
+#define AUXTRACE_INIT_NR_QUEUES 32
+
+static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
+{
+ struct auxtrace_queue *queue_array;
+ unsigned int max_nr_queues, i;
+
+ max_nr_queues = UINT_MAX / sizeof(struct auxtrace_queue);
+ if (nr_queues > max_nr_queues)
+ return NULL;
+
+ queue_array = calloc(nr_queues, sizeof(struct auxtrace_queue));
+ if (!queue_array)
+ return NULL;
+
+ for (i = 0; i < nr_queues; i++) {
+ INIT_LIST_HEAD(&queue_array[i].head);
+ queue_array[i].priv = NULL;
+ }
+
+ return queue_array;
+}
+
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+ queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+ queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
+ if (!queues->queue_array)
+ return -ENOMEM;
+ return 0;
+}
+
+static int auxtrace_queues__grow(struct auxtrace_queues *queues,
+ unsigned int new_nr_queues)
+{
+ unsigned int nr_queues = queues->nr_queues;
+ struct auxtrace_queue *queue_array;
+ unsigned int i;
+
+ if (!nr_queues)
+ nr_queues = AUXTRACE_INIT_NR_QUEUES;
+
+ while (nr_queues && nr_queues < new_nr_queues)
+ nr_queues <<= 1;
+
+ if (nr_queues < queues->nr_queues || nr_queues < new_nr_queues)
+ return -EINVAL;
+
+ queue_array = auxtrace_alloc_queue_array(nr_queues);
+ if (!queue_array)
+ return -ENOMEM;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ list_splice_tail(&queues->queue_array[i].head,
+ &queue_array[i].head);
+ queue_array[i].priv = queues->queue_array[i].priv;
+ }
+
+ queues->nr_queues = nr_queues;
+ queues->queue_array = queue_array;
+
+ return 0;
+}
+
+static void *auxtrace_copy_data(u64 size, struct perf_session *session)
+{
+ int fd = perf_data_file__fd(session->file);
+ void *p;
+ ssize_t ret;
+
+ if (size > SSIZE_MAX)
+ return NULL;
+
+ p = malloc(size);
+ if (!p)
+ return NULL;
+
+ ret = readn(fd, p, size);
+ if (ret != (ssize_t)size) {
+ free(p);
+ return NULL;
+ }
+
+ return p;
+}
+
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ struct auxtrace_queue *queue;
+ int err;
+
+ if (idx >= queues->nr_queues) {
+ err = auxtrace_queues__grow(queues, idx + 1);
+ if (err)
+ return err;
+ }
+
+ queue = &queues->queue_array[idx];
+
+ if (!queue->set) {
+ queue->set = true;
+ queue->tid = buffer->tid;
+ queue->cpu = buffer->cpu;
+ } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
+ pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
+ queue->cpu, queue->tid, buffer->cpu, buffer->tid);
+ return -EINVAL;
+ }
+
+ buffer->buffer_nr = queues->next_buffer_nr++;
+
+ list_add_tail(&buffer->list, &queue->head);
+
+ queues->new_data = true;
+ queues->populated = true;
+
+ return 0;
+}
+
+/* Limit buffers to 32MiB on 32-bit */
+#define BUFFER_LIMIT_FOR_32_BIT (32 * 1024 * 1024)
+
+static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ u64 sz = buffer->size;
+ bool consecutive = false;
+ struct auxtrace_buffer *b;
+ int err;
+
+ while (sz > BUFFER_LIMIT_FOR_32_BIT) {
+ b = memdup(buffer, sizeof(struct auxtrace_buffer));
+ if (!b)
+ return -ENOMEM;
+ b->size = BUFFER_LIMIT_FOR_32_BIT;
+ b->consecutive = consecutive;
+ err = auxtrace_queues__add_buffer(queues, idx, b);
+ if (err) {
+ auxtrace_buffer__free(b);
+ return err;
+ }
+ buffer->data_offset += BUFFER_LIMIT_FOR_32_BIT;
+ sz -= BUFFER_LIMIT_FOR_32_BIT;
+ consecutive = true;
+ }
+
+ buffer->size = sz;
+ buffer->consecutive = consecutive;
+
+ return 0;
+}
+
+static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ unsigned int idx,
+ struct auxtrace_buffer *buffer)
+{
+ if (session->one_mmap) {
+ buffer->data = buffer->data_offset - session->one_mmap_offset +
+ session->one_mmap_addr;
+ } else if (perf_data_file__is_pipe(session->file)) {
+ buffer->data = auxtrace_copy_data(buffer->size, session);
+ if (!buffer->data)
+ return -ENOMEM;
+ buffer->data_needs_freeing = true;
+ } else if (BITS_PER_LONG == 32 &&
+ buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
+ int err;
+
+ err = auxtrace_queues__split_buffer(queues, idx, buffer);
+ if (err)
+ return err;
+ }
+
+ return auxtrace_queues__add_buffer(queues, idx, buffer);
+}
+
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr)
+{
+ struct auxtrace_buffer *buffer;
+ unsigned int idx;
+ int err;
+
+ buffer = zalloc(sizeof(struct auxtrace_buffer));
+ if (!buffer)
+ return -ENOMEM;
+
+ buffer->pid = -1;
+ buffer->tid = event->auxtrace.tid;
+ buffer->cpu = event->auxtrace.cpu;
+ buffer->data_offset = data_offset;
+ buffer->offset = event->auxtrace.offset;
+ buffer->reference = event->auxtrace.reference;
+ buffer->size = event->auxtrace.size;
+ idx = event->auxtrace.idx;
+
+ err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+ if (err)
+ goto out_err;
+
+ if (buffer_ptr)
+ *buffer_ptr = buffer;
+
+ return 0;
+
+out_err:
+ auxtrace_buffer__free(buffer);
+ return err;
+}
+
+static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ off_t file_offset, size_t sz)
+{
+ union perf_event *event;
+ int err;
+ char buf[PERF_SAMPLE_MAX_SIZE];
+
+ err = perf_session__peek_event(session, file_offset, buf,
+ PERF_SAMPLE_MAX_SIZE, &event, NULL);
+ if (err)
+ return err;
+
+ if (event->header.type == PERF_RECORD_AUXTRACE) {
+ if (event->header.size < sizeof(struct auxtrace_event) ||
+ event->header.size != sz) {
+ err = -EINVAL;
+ goto out;
+ }
+ file_offset += event->header.size;
+ err = auxtrace_queues__add_event(queues, session, event,
+ file_offset, NULL);
+ }
+out:
+ return err;
+}
+
+void auxtrace_queues__free(struct auxtrace_queues *queues)
+{
+ unsigned int i;
+
+ for (i = 0; i < queues->nr_queues; i++) {
+ while (!list_empty(&queues->queue_array[i].head)) {
+ struct auxtrace_buffer *buffer;
+
+ buffer = list_entry(queues->queue_array[i].head.next,
+ struct auxtrace_buffer, list);
+ list_del(&buffer->list);
+ auxtrace_buffer__free(buffer);
+ }
+ }
+
+ zfree(&queues->queue_array);
+ queues->nr_queues = 0;
+}
+
+static void auxtrace_heapify(struct auxtrace_heap_item *heap_array,
+ unsigned int pos, unsigned int queue_nr,
+ u64 ordinal)
+{
+ unsigned int parent;
+
+ while (pos) {
+ parent = (pos - 1) >> 1;
+ if (heap_array[parent].ordinal <= ordinal)
+ break;
+ heap_array[pos] = heap_array[parent];
+ pos = parent;
+ }
+ heap_array[pos].queue_nr = queue_nr;
+ heap_array[pos].ordinal = ordinal;
+}
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+ u64 ordinal)
+{
+ struct auxtrace_heap_item *heap_array;
+
+ if (queue_nr >= heap->heap_sz) {
+ unsigned int heap_sz = AUXTRACE_INIT_NR_QUEUES;
+
+ while (heap_sz <= queue_nr)
+ heap_sz <<= 1;
+ heap_array = realloc(heap->heap_array,
+ heap_sz * sizeof(struct auxtrace_heap_item));
+ if (!heap_array)
+ return -ENOMEM;
+ heap->heap_array = heap_array;
+ heap->heap_sz = heap_sz;
+ }
+
+ auxtrace_heapify(heap->heap_array, heap->heap_cnt++, queue_nr, ordinal);
+
+ return 0;
+}
+
+void auxtrace_heap__free(struct auxtrace_heap *heap)
+{
+ zfree(&heap->heap_array);
+ heap->heap_cnt = 0;
+ heap->heap_sz = 0;
+}
+
+void auxtrace_heap__pop(struct auxtrace_heap *heap)
+{
+ unsigned int pos, last, heap_cnt = heap->heap_cnt;
+ struct auxtrace_heap_item *heap_array;
+
+ if (!heap_cnt)
+ return;
+
+ heap->heap_cnt -= 1;
+
+ heap_array = heap->heap_array;
+
+ pos = 0;
+ while (1) {
+ unsigned int left, right;
+
+ left = (pos << 1) + 1;
+ if (left >= heap_cnt)
+ break;
+ right = left + 1;
+ if (right >= heap_cnt) {
+ heap_array[pos] = heap_array[left];
+ return;
+ }
+ if (heap_array[left].ordinal < heap_array[right].ordinal) {
+ heap_array[pos] = heap_array[left];
+ pos = left;
+ } else {
+ heap_array[pos] = heap_array[right];
+ pos = right;
+ }
+ }
+
+ last = heap_cnt - 1;
+ auxtrace_heapify(heap_array, pos, heap_array[last].queue_nr,
+ heap_array[last].ordinal);
+}
+
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+{
+ if (itr)
+ return itr->info_priv_size(itr);
+ return 0;
+}
+
+static int auxtrace_not_supported(void)
+{
+ pr_err("AUX area tracing is not supported on this architecture\n");
+ return -EINVAL;
+}
+
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size)
+{
+ if (itr)
+ return itr->info_fill(itr, session, auxtrace_info, priv_size);
+ return auxtrace_not_supported();
+}
+
+void auxtrace_record__free(struct auxtrace_record *itr)
+{
+ if (itr)
+ itr->free(itr);
+}
+
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr)
+{
+ if (itr && itr->snapshot_start)
+ return itr->snapshot_start(itr);
+ return 0;
+}
+
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr)
+{
+ if (itr && itr->snapshot_finish)
+ return itr->snapshot_finish(itr);
+ return 0;
+}
+
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm,
+ unsigned char *data, u64 *head, u64 *old)
+{
+ if (itr && itr->find_snapshot)
+ return itr->find_snapshot(itr, idx, mm, data, head, old);
+ return 0;
+}
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts)
+{
+ if (itr)
+ return itr->recording_options(itr, evlist, opts);
+ return 0;
+}
+
+u64 auxtrace_record__reference(struct auxtrace_record *itr)
+{
+ if (itr)
+ return itr->reference(itr);
+ return 0;
+}
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+ struct record_opts *opts, const char *str)
+{
+ if (!str)
+ return 0;
+
+ if (itr)
+ return itr->parse_snapshot_options(itr, opts, str);
+
+ pr_err("No AUX area tracing to snapshot\n");
+ return -EINVAL;
+}
+
+struct auxtrace_record *__weak
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
+{
+ *err = 0;
+ return NULL;
+}
+
+static int auxtrace_index__alloc(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+
+ auxtrace_index = malloc(sizeof(struct auxtrace_index));
+ if (!auxtrace_index)
+ return -ENOMEM;
+
+ auxtrace_index->nr = 0;
+ INIT_LIST_HEAD(&auxtrace_index->list);
+
+ list_add_tail(&auxtrace_index->list, head);
+
+ return 0;
+}
+
+void auxtrace_index__free(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index, *n;
+
+ list_for_each_entry_safe(auxtrace_index, n, head, list) {
+ list_del(&auxtrace_index->list);
+ free(auxtrace_index);
+ }
+}
+
+static struct auxtrace_index *auxtrace_index__last(struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+ int err;
+
+ if (list_empty(head)) {
+ err = auxtrace_index__alloc(head);
+ if (err)
+ return NULL;
+ }
+
+ auxtrace_index = list_entry(head->prev, struct auxtrace_index, list);
+
+ if (auxtrace_index->nr >= PERF_AUXTRACE_INDEX_ENTRY_COUNT) {
+ err = auxtrace_index__alloc(head);
+ if (err)
+ return NULL;
+ auxtrace_index = list_entry(head->prev, struct auxtrace_index,
+ list);
+ }
+
+ return auxtrace_index;
+}
+
+int auxtrace_index__auxtrace_event(struct list_head *head,
+ union perf_event *event, off_t file_offset)
+{
+ struct auxtrace_index *auxtrace_index;
+ size_t nr;
+
+ auxtrace_index = auxtrace_index__last(head);
+ if (!auxtrace_index)
+ return -ENOMEM;
+
+ nr = auxtrace_index->nr;
+ auxtrace_index->entries[nr].file_offset = file_offset;
+ auxtrace_index->entries[nr].sz = event->header.size;
+ auxtrace_index->nr += 1;
+
+ return 0;
+}
+
+static int auxtrace_index__do_write(int fd,
+ struct auxtrace_index *auxtrace_index)
+{
+ struct auxtrace_index_entry ent;
+ size_t i;
+
+ for (i = 0; i < auxtrace_index->nr; i++) {
+ ent.file_offset = auxtrace_index->entries[i].file_offset;
+ ent.sz = auxtrace_index->entries[i].sz;
+ if (writen(fd, &ent, sizeof(ent)) != sizeof(ent))
+ return -errno;
+ }
+ return 0;
+}
+
+int auxtrace_index__write(int fd, struct list_head *head)
+{
+ struct auxtrace_index *auxtrace_index;
+ u64 total = 0;
+ int err;
+
+ list_for_each_entry(auxtrace_index, head, list)
+ total += auxtrace_index->nr;
+
+ if (writen(fd, &total, sizeof(total)) != sizeof(total))
+ return -errno;
+
+ list_for_each_entry(auxtrace_index, head, list) {
+ err = auxtrace_index__do_write(fd, auxtrace_index);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int auxtrace_index__process_entry(int fd, struct list_head *head,
+ bool needs_swap)
+{
+ struct auxtrace_index *auxtrace_index;
+ struct auxtrace_index_entry ent;
+ size_t nr;
+
+ if (readn(fd, &ent, sizeof(ent)) != sizeof(ent))
+ return -1;
+
+ auxtrace_index = auxtrace_index__last(head);
+ if (!auxtrace_index)
+ return -1;
+
+ nr = auxtrace_index->nr;
+ if (needs_swap) {
+ auxtrace_index->entries[nr].file_offset =
+ bswap_64(ent.file_offset);
+ auxtrace_index->entries[nr].sz = bswap_64(ent.sz);
+ } else {
+ auxtrace_index->entries[nr].file_offset = ent.file_offset;
+ auxtrace_index->entries[nr].sz = ent.sz;
+ }
+
+ auxtrace_index->nr = nr + 1;
+
+ return 0;
+}
+
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+ bool needs_swap)
+{
+ struct list_head *head = &session->auxtrace_index;
+ u64 nr;
+
+ if (readn(fd, &nr, sizeof(u64)) != sizeof(u64))
+ return -1;
+
+ if (needs_swap)
+ nr = bswap_64(nr);
+
+ if (sizeof(u64) + nr * sizeof(struct auxtrace_index_entry) > size)
+ return -1;
+
+ while (nr--) {
+ int err;
+
+ err = auxtrace_index__process_entry(fd, head, needs_swap);
+ if (err)
+ return -1;
+ }
+
+ return 0;
+}
+
+static int auxtrace_queues__process_index_entry(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ struct auxtrace_index_entry *ent)
+{
+ return auxtrace_queues__add_indexed_event(queues, session,
+ ent->file_offset, ent->sz);
+}
+
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+ struct perf_session *session)
+{
+ struct auxtrace_index *auxtrace_index;
+ struct auxtrace_index_entry *ent;
+ size_t i;
+ int err;
+
+ list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+ for (i = 0; i < auxtrace_index->nr; i++) {
+ ent = &auxtrace_index->entries[i];
+ err = auxtrace_queues__process_index_entry(queues,
+ session,
+ ent);
+ if (err)
+ return err;
+ }
+ }
+ return 0;
+}
+
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer)
+{
+ if (buffer) {
+ if (list_is_last(&buffer->list, &queue->head))
+ return NULL;
+ return list_entry(buffer->list.next, struct auxtrace_buffer,
+ list);
+ } else {
+ if (list_empty(&queue->head))
+ return NULL;
+ return list_entry(queue->head.next, struct auxtrace_buffer,
+ list);
+ }
+}
+
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd)
+{
+ size_t adj = buffer->data_offset & (page_size - 1);
+ size_t size = buffer->size + adj;
+ off_t file_offset = buffer->data_offset - adj;
+ void *addr;
+
+ if (buffer->data)
+ return buffer->data;
+
+ addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, file_offset);
+ if (addr == MAP_FAILED)
+ return NULL;
+
+ buffer->mmap_addr = addr;
+ buffer->mmap_size = size;
+
+ buffer->data = addr + adj;
+
+ return buffer->data;
+}
+
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer)
+{
+ if (!buffer->data || !buffer->mmap_addr)
+ return;
+ munmap(buffer->mmap_addr, buffer->mmap_size);
+ buffer->mmap_addr = NULL;
+ buffer->mmap_size = 0;
+ buffer->data = NULL;
+ buffer->use_data = NULL;
+}
+
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__put_data(buffer);
+ if (buffer->data_needs_freeing) {
+ buffer->data_needs_freeing = false;
+ zfree(&buffer->data);
+ buffer->use_data = NULL;
+ buffer->size = 0;
+ }
+}
+
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
+{
+ auxtrace_buffer__drop_data(buffer);
+ free(buffer);
+}
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+ int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+ const char *msg)
+{
+ size_t size;
+
+ memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event));
+
+ auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR;
+ auxtrace_error->type = type;
+ auxtrace_error->code = code;
+ auxtrace_error->cpu = cpu;
+ auxtrace_error->pid = pid;
+ auxtrace_error->tid = tid;
+ auxtrace_error->ip = ip;
+ strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
+
+ size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
+ strlen(auxtrace_error->msg) + 1;
+ auxtrace_error->header.size = PERF_ALIGN(size, sizeof(u64));
+}
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+ struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process)
+{
+ union perf_event *ev;
+ size_t priv_size;
+ int err;
+
+ pr_debug2("Synthesizing auxtrace information\n");
+ priv_size = auxtrace_record__info_priv_size(itr);
+ ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
+ if (!ev)
+ return -ENOMEM;
+
+ ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
+ ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
+ priv_size;
+ err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
+ priv_size);
+ if (err)
+ goto out_free;
+
+ err = process(tool, ev, NULL, NULL);
+out_free:
+ free(ev);
+ return err;
+}
+
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+ return !session->itrace_synth_opts ||
+ session->itrace_synth_opts->dont_decode;
+}
+
+int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session __maybe_unused)
+{
+ enum auxtrace_type type = event->auxtrace_info.type;
+
+ if (dump_trace)
+ fprintf(stdout, " type: %u\n", type);
+
+ switch (type) {
+ case PERF_AUXTRACE_UNKNOWN:
+ default:
+ return -EINVAL;
+ }
+}
+
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ s64 err;
+
+ if (dump_trace)
+ fprintf(stdout, " size: %#"PRIx64" offset: %#"PRIx64" ref: %#"PRIx64" idx: %u tid: %d cpu: %d\n",
+ event->auxtrace.size, event->auxtrace.offset,
+ event->auxtrace.reference, event->auxtrace.idx,
+ event->auxtrace.tid, event->auxtrace.cpu);
+
+ if (auxtrace__dont_decode(session))
+ return event->auxtrace.size;
+
+ if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
+ return -EINVAL;
+
+ err = session->auxtrace->process_auxtrace_event(session, event, tool);
+ if (err < 0)
+ return err;
+
+ return event->auxtrace.size;
+}
+
+#define PERF_ITRACE_DEFAULT_PERIOD_TYPE PERF_ITRACE_PERIOD_NANOSECS
+#define PERF_ITRACE_DEFAULT_PERIOD 100000
+#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ 16
+#define PERF_ITRACE_MAX_CALLCHAIN_SZ 1024
+
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+{
+ synth_opts->instructions = true;
+ synth_opts->branches = true;
+ synth_opts->transactions = true;
+ synth_opts->errors = true;
+ synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+}
+
+/*
+ * Please check tools/perf/Documentation/perf-script.txt for information
+ * about the options parsed here, which is introduced after this cset,
+ * when support in 'perf script' for these options is introduced.
+ */
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+ int unset)
+{
+ struct itrace_synth_opts *synth_opts = opt->value;
+ const char *p;
+ char *endptr;
+
+ synth_opts->set = true;
+
+ if (unset) {
+ synth_opts->dont_decode = true;
+ return 0;
+ }
+
+ if (!str) {
+ itrace_synth_opts__set_default(synth_opts);
+ return 0;
+ }
+
+ for (p = str; *p;) {
+ switch (*p++) {
+ case 'i':
+ synth_opts->instructions = true;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ if (isdigit(*p)) {
+ synth_opts->period = strtoull(p, &endptr, 10);
+ p = endptr;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ switch (*p++) {
+ case 'i':
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_INSTRUCTIONS;
+ break;
+ case 't':
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_TICKS;
+ break;
+ case 'm':
+ synth_opts->period *= 1000;
+ /* Fall through */
+ case 'u':
+ synth_opts->period *= 1000;
+ /* Fall through */
+ case 'n':
+ if (*p++ != 's')
+ goto out_err;
+ synth_opts->period_type =
+ PERF_ITRACE_PERIOD_NANOSECS;
+ break;
+ case '\0':
+ goto out;
+ default:
+ goto out_err;
+ }
+ }
+ break;
+ case 'b':
+ synth_opts->branches = true;
+ break;
+ case 'x':
+ synth_opts->transactions = true;
+ break;
+ case 'e':
+ synth_opts->errors = true;
+ break;
+ case 'd':
+ synth_opts->log = true;
+ break;
+ case 'c':
+ synth_opts->branches = true;
+ synth_opts->calls = true;
+ break;
+ case 'r':
+ synth_opts->branches = true;
+ synth_opts->returns = true;
+ break;
+ case 'g':
+ synth_opts->callchain = true;
+ synth_opts->callchain_sz =
+ PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+ while (*p == ' ' || *p == ',')
+ p += 1;
+ if (isdigit(*p)) {
+ unsigned int val;
+
+ val = strtoul(p, &endptr, 10);
+ p = endptr;
+ if (!val || val > PERF_ITRACE_MAX_CALLCHAIN_SZ)
+ goto out_err;
+ synth_opts->callchain_sz = val;
+ }
+ break;
+ case ' ':
+ case ',':
+ break;
+ default:
+ goto out_err;
+ }
+ }
+out:
+ if (synth_opts->instructions) {
+ if (!synth_opts->period_type)
+ synth_opts->period_type =
+ PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+ if (!synth_opts->period)
+ synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+ }
+
+ return 0;
+
+out_err:
+ pr_err("Bad Instruction Tracing options '%s'\n", str);
+ return -EINVAL;
+}
+
+static const char * const auxtrace_error_type_name[] = {
+ [PERF_AUXTRACE_ERROR_ITRACE] = "instruction trace",
+};
+
+static const char *auxtrace_error_name(int type)
+{
+ const char *error_type_name = NULL;
+
+ if (type < PERF_AUXTRACE_ERROR_MAX)
+ error_type_name = auxtrace_error_type_name[type];
+ if (!error_type_name)
+ error_type_name = "unknown AUX";
+ return error_type_name;
+}
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
+{
+ struct auxtrace_error_event *e = &event->auxtrace_error;
+ int ret;
+
+ ret = fprintf(fp, " %s error type %u",
+ auxtrace_error_name(e->type), e->type);
+ ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
+ e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+ return ret;
+}
+
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+ union perf_event *event)
+{
+ struct auxtrace_error_event *e = &event->auxtrace_error;
+
+ if (e->type < PERF_AUXTRACE_ERROR_MAX)
+ session->evlist->stats.nr_auxtrace_errors[e->type] += 1;
+}
+
+void events_stats__auxtrace_error_warn(const struct events_stats *stats)
+{
+ int i;
+
+ for (i = 0; i < PERF_AUXTRACE_ERROR_MAX; i++) {
+ if (!stats->nr_auxtrace_errors[i])
+ continue;
+ ui__warning("%u %s errors\n",
+ stats->nr_auxtrace_errors[i],
+ auxtrace_error_name(i));
+ }
+}
+
+int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ if (auxtrace__dont_decode(session))
+ return 0;
+
+ perf_event__fprintf_auxtrace_error(event, stdout);
+ return 0;
+}
+
+static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ bool snapshot, size_t snapshot_size)
+{
+ u64 head, old = mm->prev, offset, ref;
+ unsigned char *data = mm->base;
+ size_t size, head_off, old_off, len1, len2, padding;
+ union perf_event ev;
+ void *data1, *data2;
+
+ if (snapshot) {
+ head = auxtrace_mmap__read_snapshot_head(mm);
+ if (auxtrace_record__find_snapshot(itr, mm->idx, mm, data,
+ &head, &old))
+ return -1;
+ } else {
+ head = auxtrace_mmap__read_head(mm);
+ }
+
+ if (old == head)
+ return 0;
+
+ pr_debug3("auxtrace idx %d old %#"PRIx64" head %#"PRIx64" diff %#"PRIx64"\n",
+ mm->idx, old, head, head - old);
+
+ if (mm->mask) {
+ head_off = head & mm->mask;
+ old_off = old & mm->mask;
+ } else {
+ head_off = head % mm->len;
+ old_off = old % mm->len;
+ }
+
+ if (head_off > old_off)
+ size = head_off - old_off;
+ else
+ size = mm->len - (old_off - head_off);
+
+ if (snapshot && size > snapshot_size)
+ size = snapshot_size;
+
+ ref = auxtrace_record__reference(itr);
+
+ if (head > old || size <= head || mm->mask) {
+ offset = head - size;
+ } else {
+ /*
+ * When the buffer size is not a power of 2, 'head' wraps at the
+ * highest multiple of the buffer size, so we have to subtract
+ * the remainder here.
+ */
+ u64 rem = (0ULL - mm->len) % mm->len;
+
+ offset = head - size - rem;
+ }
+
+ if (size > head_off) {
+ len1 = size - head_off;
+ data1 = &data[mm->len - len1];
+ len2 = head_off;
+ data2 = &data[0];
+ } else {
+ len1 = size;
+ data1 = &data[head_off - len1];
+ len2 = 0;
+ data2 = NULL;
+ }
+
+ /* padding must be written by fn() e.g. record__process_auxtrace() */
+ padding = size & 7;
+ if (padding)
+ padding = 8 - padding;
+
+ memset(&ev, 0, sizeof(ev));
+ ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
+ ev.auxtrace.header.size = sizeof(ev.auxtrace);
+ ev.auxtrace.size = size + padding;
+ ev.auxtrace.offset = offset;
+ ev.auxtrace.reference = ref;
+ ev.auxtrace.idx = mm->idx;
+ ev.auxtrace.tid = mm->tid;
+ ev.auxtrace.cpu = mm->cpu;
+
+ if (fn(tool, &ev, data1, len1, data2, len2))
+ return -1;
+
+ mm->prev = head;
+
+ if (!snapshot) {
+ auxtrace_mmap__write_tail(mm, head);
+ if (itr->read_finish) {
+ int err;
+
+ err = itr->read_finish(itr, mm->idx);
+ if (err < 0)
+ return err;
+ }
+ }
+
+ return 1;
+}
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn)
+{
+ return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+}
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ size_t snapshot_size)
+{
+ return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+}
+
+/**
+ * struct auxtrace_cache - hash table to implement a cache
+ * @hashtable: the hashtable
+ * @sz: hashtable size (number of hlists)
+ * @entry_size: size of an entry
+ * @limit: limit the number of entries to this maximum, when reached the cache
+ * is dropped and caching begins again with an empty cache
+ * @cnt: current number of entries
+ * @bits: hashtable size (@sz = 2^@bits)
+ */
+struct auxtrace_cache {
+ struct hlist_head *hashtable;
+ size_t sz;
+ size_t entry_size;
+ size_t limit;
+ size_t cnt;
+ unsigned int bits;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+ unsigned int limit_percent)
+{
+ struct auxtrace_cache *c;
+ struct hlist_head *ht;
+ size_t sz, i;
+
+ c = zalloc(sizeof(struct auxtrace_cache));
+ if (!c)
+ return NULL;
+
+ sz = 1UL << bits;
+
+ ht = calloc(sz, sizeof(struct hlist_head));
+ if (!ht)
+ goto out_free;
+
+ for (i = 0; i < sz; i++)
+ INIT_HLIST_HEAD(&ht[i]);
+
+ c->hashtable = ht;
+ c->sz = sz;
+ c->entry_size = entry_size;
+ c->limit = (c->sz * limit_percent) / 100;
+ c->bits = bits;
+
+ return c;
+
+out_free:
+ free(c);
+ return NULL;
+}
+
+static void auxtrace_cache__drop(struct auxtrace_cache *c)
+{
+ struct auxtrace_cache_entry *entry;
+ struct hlist_node *tmp;
+ size_t i;
+
+ if (!c)
+ return;
+
+ for (i = 0; i < c->sz; i++) {
+ hlist_for_each_entry_safe(entry, tmp, &c->hashtable[i], hash) {
+ hlist_del(&entry->hash);
+ auxtrace_cache__free_entry(c, entry);
+ }
+ }
+
+ c->cnt = 0;
+}
+
+void auxtrace_cache__free(struct auxtrace_cache *c)
+{
+ if (!c)
+ return;
+
+ auxtrace_cache__drop(c);
+ free(c->hashtable);
+ free(c);
+}
+
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c)
+{
+ return malloc(c->entry_size);
+}
+
+void auxtrace_cache__free_entry(struct auxtrace_cache *c __maybe_unused,
+ void *entry)
+{
+ free(entry);
+}
+
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+ struct auxtrace_cache_entry *entry)
+{
+ if (c->limit && ++c->cnt > c->limit)
+ auxtrace_cache__drop(c);
+
+ entry->key = key;
+ hlist_add_head(&entry->hash, &c->hashtable[hash_32(key, c->bits)]);
+
+ return 0;
+}
+
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
+{
+ struct auxtrace_cache_entry *entry;
+ struct hlist_head *hlist;
+
+ if (!c)
+ return NULL;
+
+ hlist = &c->hashtable[hash_32(key, c->bits)];
+ hlist_for_each_entry(entry, hlist, hash) {
+ if (entry->key == key)
+ return entry;
+ }
+
+ return NULL;
+}
--- /dev/null
+/*
+ * auxtrace.h: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_AUXTRACE_H
+#define __PERF_AUXTRACE_H
+
+#include <sys/types.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <linux/list.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "../perf.h"
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+
+union perf_event;
+struct perf_session;
+struct perf_evlist;
+struct perf_tool;
+struct option;
+struct record_opts;
+struct auxtrace_info_event;
+struct events_stats;
+
+enum auxtrace_type {
+ PERF_AUXTRACE_UNKNOWN,
+};
+
+enum itrace_period_type {
+ PERF_ITRACE_PERIOD_INSTRUCTIONS,
+ PERF_ITRACE_PERIOD_TICKS,
+ PERF_ITRACE_PERIOD_NANOSECS,
+};
+
+/**
+ * struct itrace_synth_opts - AUX area tracing synthesis options.
+ * @set: indicates whether or not options have been set
+ * @inject: indicates the event (not just the sample) must be fully synthesized
+ * because 'perf inject' will write it out
+ * @instructions: whether to synthesize 'instructions' events
+ * @branches: whether to synthesize 'branches' events
+ * @transactions: whether to synthesize events for transactions
+ * @errors: whether to synthesize decoder error events
+ * @dont_decode: whether to skip decoding entirely
+ * @log: write a decoding log
+ * @calls: limit branch samples to calls (can be combined with @returns)
+ * @returns: limit branch samples to returns (can be combined with @calls)
+ * @callchain: add callchain to 'instructions' events
+ * @callchain_sz: maximum callchain size
+ * @period: 'instructions' events period
+ * @period_type: 'instructions' events period type
+ */
+struct itrace_synth_opts {
+ bool set;
+ bool inject;
+ bool instructions;
+ bool branches;
+ bool transactions;
+ bool errors;
+ bool dont_decode;
+ bool log;
+ bool calls;
+ bool returns;
+ bool callchain;
+ unsigned int callchain_sz;
+ unsigned long long period;
+ enum itrace_period_type period_type;
+};
+
+/**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ * perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+ u64 file_offset;
+ u64 sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ * file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+ struct list_head list;
+ size_t nr;
+ struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+/**
+ * struct auxtrace - session callbacks to allow AUX area data decoding.
+ * @process_event: lets the decoder see all session events
+ * @flush_events: process any remaining data
+ * @free_events: free resources associated with event processing
+ * @free: free resources associated with the session
+ */
+struct auxtrace {
+ int (*process_event)(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool);
+ int (*process_auxtrace_event)(struct perf_session *session,
+ union perf_event *event,
+ struct perf_tool *tool);
+ int (*flush_events)(struct perf_session *session,
+ struct perf_tool *tool);
+ void (*free_events)(struct perf_session *session);
+ void (*free)(struct perf_session *session);
+};
+
+/**
+ * struct auxtrace_buffer - a buffer containing AUX area tracing data.
+ * @list: buffers are queued in a list held by struct auxtrace_queue
+ * @size: size of the buffer in bytes
+ * @pid: in per-thread mode, the pid this buffer is associated with
+ * @tid: in per-thread mode, the tid this buffer is associated with
+ * @cpu: in per-cpu mode, the cpu this buffer is associated with
+ * @data: actual buffer data (can be null if the data has not been loaded)
+ * @data_offset: file offset at which the buffer can be read
+ * @mmap_addr: mmap address at which the buffer can be read
+ * @mmap_size: size of the mmap at @mmap_addr
+ * @data_needs_freeing: @data was malloc'd so free it when it is no longer
+ * needed
+ * @consecutive: the original data was split up and this buffer is consecutive
+ * to the previous buffer
+ * @offset: offset as determined by aux_head / aux_tail members of struct
+ * perf_event_mmap_page
+ * @reference: an implementation-specific reference determined when the data is
+ * recorded
+ * @buffer_nr: used to number each buffer
+ * @use_size: implementation actually only uses this number of bytes
+ * @use_data: implementation actually only uses data starting at this address
+ */
+struct auxtrace_buffer {
+ struct list_head list;
+ size_t size;
+ pid_t pid;
+ pid_t tid;
+ int cpu;
+ void *data;
+ off_t data_offset;
+ void *mmap_addr;
+ size_t mmap_size;
+ bool data_needs_freeing;
+ bool consecutive;
+ u64 offset;
+ u64 reference;
+ u64 buffer_nr;
+ size_t use_size;
+ void *use_data;
+};
+
+/**
+ * struct auxtrace_queue - a queue of AUX area tracing data buffers.
+ * @head: head of buffer list
+ * @tid: in per-thread mode, the tid this queue is associated with
+ * @cpu: in per-cpu mode, the cpu this queue is associated with
+ * @set: %true once this queue has been dedicated to a specific thread or cpu
+ * @priv: implementation-specific data
+ */
+struct auxtrace_queue {
+ struct list_head head;
+ pid_t tid;
+ int cpu;
+ bool set;
+ void *priv;
+};
+
+/**
+ * struct auxtrace_queues - an array of AUX area tracing queues.
+ * @queue_array: array of queues
+ * @nr_queues: number of queues
+ * @new_data: set whenever new data is queued
+ * @populated: queues have been fully populated using the auxtrace_index
+ * @next_buffer_nr: used to number each buffer
+ */
+struct auxtrace_queues {
+ struct auxtrace_queue *queue_array;
+ unsigned int nr_queues;
+ bool new_data;
+ bool populated;
+ u64 next_buffer_nr;
+};
+
+/**
+ * struct auxtrace_heap_item - element of struct auxtrace_heap.
+ * @queue_nr: queue number
+ * @ordinal: value used for sorting (lowest ordinal is top of the heap) expected
+ * to be a timestamp
+ */
+struct auxtrace_heap_item {
+ unsigned int queue_nr;
+ u64 ordinal;
+};
+
+/**
+ * struct auxtrace_heap - a heap suitable for sorting AUX area tracing queues.
+ * @heap_array: the heap
+ * @heap_cnt: the number of elements in the heap
+ * @heap_sz: maximum number of elements (grows as needed)
+ */
+struct auxtrace_heap {
+ struct auxtrace_heap_item *heap_array;
+ unsigned int heap_cnt;
+ unsigned int heap_sz;
+};
+
+/**
+ * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
+ * @base: address of mapped area
+ * @userpg: pointer to buffer's perf_event_mmap_page
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @len: size of mapped area
+ * @prev: previous aux_head
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ * mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap {
+ void *base;
+ void *userpg;
+ size_t mask;
+ size_t len;
+ u64 prev;
+ int idx;
+ pid_t tid;
+ int cpu;
+};
+
+/**
+ * struct auxtrace_mmap_params - parameters to set up struct auxtrace_mmap.
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @offset: file offset of mapped area
+ * @len: size of mapped area
+ * @prot: mmap memory protection
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ * mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap_params {
+ size_t mask;
+ off_t offset;
+ size_t len;
+ int prot;
+ int idx;
+ pid_t tid;
+ int cpu;
+};
+
+/**
+ * struct auxtrace_record - callbacks for recording AUX area data.
+ * @recording_options: validate and process recording options
+ * @info_priv_size: return the size of the private data in auxtrace_info_event
+ * @info_fill: fill-in the private data in auxtrace_info_event
+ * @free: free this auxtrace record structure
+ * @snapshot_start: starting a snapshot
+ * @snapshot_finish: finishing a snapshot
+ * @find_snapshot: find data to snapshot within auxtrace mmap
+ * @parse_snapshot_options: parse snapshot options
+ * @reference: provide a 64-bit reference number for auxtrace_event
+ * @read_finish: called after reading from an auxtrace mmap
+ */
+struct auxtrace_record {
+ int (*recording_options)(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts);
+ size_t (*info_priv_size)(struct auxtrace_record *itr);
+ int (*info_fill)(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size);
+ void (*free)(struct auxtrace_record *itr);
+ int (*snapshot_start)(struct auxtrace_record *itr);
+ int (*snapshot_finish)(struct auxtrace_record *itr);
+ int (*find_snapshot)(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm, unsigned char *data,
+ u64 *head, u64 *old);
+ int (*parse_snapshot_options)(struct auxtrace_record *itr,
+ struct record_opts *opts,
+ const char *str);
+ u64 (*reference)(struct auxtrace_record *itr);
+ int (*read_finish)(struct auxtrace_record *itr, int idx);
+};
+
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+/*
+ * In snapshot mode the mmapped page is read-only which makes using
+ * __sync_val_compare_and_swap() problematic. However, snapshot mode expects
+ * the buffer is not updated while the snapshot is made (e.g. Intel PT disables
+ * the event) so there is not a race anyway.
+ */
+static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+ u64 head = ACCESS_ONCE(pc->aux_head);
+
+ /* Ensure all reads are done after we read the head */
+ rmb();
+ return head;
+}
+
+static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ u64 head = ACCESS_ONCE(pc->aux_head);
+#else
+ u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
+#endif
+
+ /* Ensure all reads are done after we read the head */
+ rmb();
+ return head;
+}
+
+static inline void auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail)
+{
+ struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG != 64 && defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ u64 old_tail;
+#endif
+
+ /* Ensure all reads are done before we write the tail out */
+ mb();
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+ pc->aux_tail = tail;
+#else
+ do {
+ old_tail = __sync_val_compare_and_swap(&pc->aux_tail, 0, 0);
+ } while (!__sync_bool_compare_and_swap(&pc->aux_tail, old_tail, tail));
+#endif
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu);
+
+typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+ union perf_event *event, void *data1,
+ size_t len1, void *data2, size_t len2);
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn);
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+ struct auxtrace_record *itr,
+ struct perf_tool *tool, process_auxtrace_t fn,
+ size_t snapshot_size);
+
+int auxtrace_queues__init(struct auxtrace_queues *queues);
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+ struct perf_session *session,
+ union perf_event *event, off_t data_offset,
+ struct auxtrace_buffer **buffer_ptr);
+void auxtrace_queues__free(struct auxtrace_queues *queues);
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+ struct perf_session *session);
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+ struct auxtrace_buffer *buffer);
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+ u64 ordinal);
+void auxtrace_heap__pop(struct auxtrace_heap *heap);
+void auxtrace_heap__free(struct auxtrace_heap *heap);
+
+struct auxtrace_cache_entry {
+ struct hlist_node hash;
+ u32 key;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+ unsigned int limit_percent);
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache);
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c);
+void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry);
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+ struct auxtrace_cache_entry *entry);
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+ int *err);
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+ struct record_opts *opts,
+ const char *str);
+int auxtrace_record__options(struct auxtrace_record *itr,
+ struct perf_evlist *evlist,
+ struct record_opts *opts);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+ struct perf_session *session,
+ struct auxtrace_info_event *auxtrace_info,
+ size_t priv_size);
+void auxtrace_record__free(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr);
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+ struct auxtrace_mmap *mm,
+ unsigned char *data, u64 *head, u64 *old);
+u64 auxtrace_record__reference(struct auxtrace_record *itr);
+
+int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
+ off_t file_offset);
+int auxtrace_index__write(int fd, struct list_head *head);
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+ bool needs_swap);
+void auxtrace_index__free(struct list_head *head);
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+ int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+ const char *msg);
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+ struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process);
+int perf_event__process_auxtrace_info(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+int perf_event__process_auxtrace_error(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+ int unset);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+ union perf_event *event);
+void events_stats__auxtrace_error_warn(const struct events_stats *stats);
+
+static inline int auxtrace__process_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool)
+{
+ if (!session->auxtrace)
+ return 0;
+
+ return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+static inline int auxtrace__flush_events(struct perf_session *session,
+ struct perf_tool *tool)
+{
+ if (!session->auxtrace)
+ return 0;
+
+ return session->auxtrace->flush_events(session, tool);
+}
+
+static inline void auxtrace__free_events(struct perf_session *session)
+{
+ if (!session->auxtrace)
+ return;
+
+ return session->auxtrace->free_events(session);
+}
+
+static inline void auxtrace__free(struct perf_session *session)
+{
+ if (!session->auxtrace)
+ return;
+
+ return session->auxtrace->free(session);
+}
+
+#else
+
+static inline struct auxtrace_record *
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+ int *err __maybe_unused)
+{
+ *err = 0;
+ return NULL;
+}
+
+static inline
+void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused)
+{
+}
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+ struct perf_tool *tool __maybe_unused,
+ struct perf_session *session __maybe_unused,
+ perf_event__handler_t process __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused,
+ struct record_opts *opts __maybe_unused)
+{
+ return 0;
+}
+
+#define perf_event__process_auxtrace_info 0
+#define perf_event__process_auxtrace 0
+#define perf_event__process_auxtrace_error 0
+
+static inline
+void perf_session__auxtrace_error_inc(struct perf_session *session
+ __maybe_unused,
+ union perf_event *event
+ __maybe_unused)
+{
+}
+
+static inline
+void events_stats__auxtrace_error_warn(const struct events_stats *stats
+ __maybe_unused)
+{
+}
+
+static inline
+int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+ struct record_opts *opts __maybe_unused,
+ const char *str)
+{
+ if (!str)
+ return 0;
+ pr_err("AUX area tracing not supported\n");
+ return -EINVAL;
+}
+
+static inline
+int auxtrace__process_event(struct perf_session *session __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_sample *sample __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+int auxtrace__flush_events(struct perf_session *session __maybe_unused,
+ struct perf_tool *tool __maybe_unused)
+{
+ return 0;
+}
+
+static inline
+void auxtrace__free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache __maybe_unused)
+{
+}
+
+static inline
+void auxtrace__free(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_index__write(int fd __maybe_unused,
+ struct list_head *head __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+int auxtrace_index__process(int fd __maybe_unused,
+ u64 size __maybe_unused,
+ struct perf_session *session __maybe_unused,
+ bool needs_swap __maybe_unused)
+{
+ return -EINVAL;
+}
+
+static inline
+void auxtrace_index__free(struct list_head *head __maybe_unused)
+{
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+ struct auxtrace_mmap_params *mp,
+ void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+ off_t auxtrace_offset,
+ unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+ struct perf_evlist *evlist, int idx,
+ bool per_cpu);
+
+#endif
+
+#endif
if (al.map != NULL)
al.map->dso->hit = 1;
+ thread__put(thread);
return 0;
}
dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
event->fork.ppid, event->fork.ptid);
- if (thread)
+ if (thread) {
machine__remove_thread(machine, thread);
+ thread__put(thread);
+ }
return 0;
}
return write_padded(fd, name, name_len + 1, len);
}
-static int __dsos__write_buildid_table(struct list_head *head,
- struct machine *machine,
- pid_t pid, u16 misc, int fd)
+static int machine__write_buildid_table(struct machine *machine, int fd)
{
+ int err = 0;
char nm[PATH_MAX];
struct dso *pos;
+ u16 kmisc = PERF_RECORD_MISC_KERNEL,
+ umisc = PERF_RECORD_MISC_USER;
- dsos__for_each_with_build_id(pos, head) {
- int err;
+ if (!machine__is_host(machine)) {
+ kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+ umisc = PERF_RECORD_MISC_GUEST_USER;
+ }
+
+ dsos__for_each_with_build_id(pos, &machine->dsos.head) {
const char *name;
size_t name_len;
name_len = pos->long_name_len + 1;
}
- err = write_buildid(name, name_len, pos->build_id,
- pid, misc, fd);
+ err = write_buildid(name, name_len, pos->build_id, machine->pid,
+ pos->kernel ? kmisc : umisc, fd);
if (err)
- return err;
- }
-
- return 0;
-}
-
-static int machine__write_buildid_table(struct machine *machine, int fd)
-{
- int err;
- u16 kmisc = PERF_RECORD_MISC_KERNEL,
- umisc = PERF_RECORD_MISC_USER;
-
- if (!machine__is_host(machine)) {
- kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
- umisc = PERF_RECORD_MISC_GUEST_USER;
+ break;
}
- err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
- machine->pid, kmisc, fd);
- if (err == 0)
- err = __dsos__write_buildid_table(&machine->user_dsos.head,
- machine, machine->pid, umisc,
- fd);
return err;
}
static int machine__hit_all_dsos(struct machine *machine)
{
- int err;
-
- err = __dsos__hit_all(&machine->kernel_dsos.head);
- if (err)
- return err;
-
- return __dsos__hit_all(&machine->user_dsos.head);
+ return __dsos__hit_all(&machine->dsos.head);
}
int dsos__hit_all(struct perf_session *session)
static int machine__cache_build_ids(struct machine *machine)
{
- int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine);
- ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine);
- return ret;
+ return __dsos__cache_build_ids(&machine->dsos.head, machine);
}
int perf_session__cache_build_ids(struct perf_session *session)
static bool machine__read_build_ids(struct machine *machine, bool with_hits)
{
- bool ret;
-
- ret = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
- ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
- return ret;
+ return __dsos__read_build_ids(&machine->dsos.head, with_hits);
}
bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
/* pager.c */
extern void setup_pager(void);
-extern const char *pager_program;
extern int pager_in_use(void);
extern int pager_use_color;
struct callchain_list {
u64 ip;
struct map_symbol ms;
+ struct /* for TUI */ {
+ bool unfolded;
+ bool has_children;
+ };
char *srcline;
struct list_head list;
};
goto found;
n++;
}
- if (cgrp->refcnt == 0)
+ if (atomic_read(&cgrp->refcnt) == 0)
free(cgrp);
return -1;
found:
- cgrp->refcnt++;
+ atomic_inc(&cgrp->refcnt);
counter->cgrp = cgrp;
return 0;
}
void close_cgroup(struct cgroup_sel *cgrp)
{
- if (!cgrp)
- return;
-
- /* XXX: not reentrant */
- if (--cgrp->refcnt == 0) {
+ if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
close(cgrp->fd);
zfree(&cgrp->name);
free(cgrp);
#ifndef __CGROUP_H__
#define __CGROUP_H__
+#include <linux/atomic.h>
+
struct option;
struct cgroup_sel {
char *name;
int fd;
- int refcnt;
+ atomic_t refcnt;
};
#include "util.h"
#include <stdlib.h>
#include <stdio.h>
+#include <linux/atomic.h>
struct comm_str {
char *str;
struct rb_node rb_node;
- int ref;
+ atomic_t refcnt;
};
/* Should perhaps be moved to struct machine */
static struct rb_root comm_str_root;
-static void comm_str__get(struct comm_str *cs)
+static struct comm_str *comm_str__get(struct comm_str *cs)
{
- cs->ref++;
+ if (cs)
+ atomic_inc(&cs->refcnt);
+ return cs;
}
static void comm_str__put(struct comm_str *cs)
{
- if (!--cs->ref) {
+ if (cs && atomic_dec_and_test(&cs->refcnt)) {
rb_erase(&cs->rb_node, &comm_str_root);
zfree(&cs->str);
free(cs);
return NULL;
}
+ atomic_set(&cs->refcnt, 0);
+
return cs;
}
#include <babeltrace/ctf-writer/event.h>
#include <babeltrace/ctf-writer/event-types.h>
#include <babeltrace/ctf-writer/event-fields.h>
+#include <babeltrace/ctf-ir/utils.h>
#include <babeltrace/ctf/events.h>
#include <traceevent/event-parse.h>
#include "asm/bug.h"
struct bt_ctf_event_class *event_class;
};
+#define MAX_CPUS 4096
+
+struct ctf_stream {
+ struct bt_ctf_stream *stream;
+ int cpu;
+ u32 count;
+};
+
struct ctf_writer {
/* writer primitives */
- struct bt_ctf_writer *writer;
- struct bt_ctf_stream *stream;
- struct bt_ctf_stream_class *stream_class;
- struct bt_ctf_clock *clock;
+ struct bt_ctf_writer *writer;
+ struct ctf_stream **stream;
+ int stream_cnt;
+ struct bt_ctf_stream_class *stream_class;
+ struct bt_ctf_clock *clock;
/* data types */
union {
u64 events_size;
u64 events_count;
+
+ /* Ordered events configured queue size. */
+ u64 queue_size;
};
static int value_set(struct bt_ctf_field_type *type,
return cw->data.u32;
}
+static unsigned long long adjust_signedness(unsigned long long value_int, int size)
+{
+ unsigned long long value_mask;
+
+ /*
+ * value_mask = (1 << (size * 8 - 1)) - 1.
+ * Directly set value_mask for code readers.
+ */
+ switch (size) {
+ case 1:
+ value_mask = 0x7fULL;
+ break;
+ case 2:
+ value_mask = 0x7fffULL;
+ break;
+ case 4:
+ value_mask = 0x7fffffffULL;
+ break;
+ case 8:
+ /*
+ * For 64 bit value, return it self. There is no need
+ * to fill high bit.
+ */
+ /* Fall through */
+ default:
+ /* BUG! */
+ return value_int;
+ }
+
+ /* If it is a positive value, don't adjust. */
+ if ((value_int & (~0ULL - value_mask)) == 0)
+ return value_int;
+
+ /* Fill upper part of value_int with 1 to make it a negative long long. */
+ return (value_int & value_mask) | ~value_mask;
+}
+
static int add_tracepoint_field_value(struct ctf_writer *cw,
struct bt_ctf_event_class *event_class,
struct bt_ctf_event *event,
struct bt_ctf_field *field;
const char *name = fmtf->name;
void *data = sample->raw_data;
- unsigned long long value_int;
unsigned long flags = fmtf->flags;
unsigned int n_items;
unsigned int i;
unsigned int len;
int ret;
+ name = fmtf->alias;
offset = fmtf->offset;
len = fmtf->size;
if (flags & FIELD_IS_STRING)
type = get_tracepoint_field_type(cw, fmtf);
for (i = 0; i < n_items; i++) {
- if (!(flags & FIELD_IS_STRING))
- value_int = pevent_read_number(
- fmtf->event->pevent,
- data + offset + i * len, len);
-
if (flags & FIELD_IS_ARRAY)
field = bt_ctf_field_array_get_field(array_field, i);
else
if (flags & FIELD_IS_STRING)
ret = bt_ctf_field_string_set_value(field,
data + offset + i * len);
- else if (!(flags & FIELD_IS_SIGNED))
- ret = bt_ctf_field_unsigned_integer_set_value(
- field, value_int);
- else
- ret = bt_ctf_field_signed_integer_set_value(
- field, value_int);
+ else {
+ unsigned long long value_int;
+
+ value_int = pevent_read_number(
+ fmtf->event->pevent,
+ data + offset + i * len, len);
+
+ if (!(flags & FIELD_IS_SIGNED))
+ ret = bt_ctf_field_unsigned_integer_set_value(
+ field, value_int);
+ else
+ ret = bt_ctf_field_signed_integer_set_value(
+ field, adjust_signedness(value_int, len));
+ }
+
if (ret) {
pr_err("failed to set file value %s\n", name);
goto err_put_field;
return -1;
}
- if (type & PERF_SAMPLE_CPU) {
- ret = value_set_u32(cw, event, "perf_cpu", sample->cpu);
- if (ret)
- return -1;
- }
-
if (type & PERF_SAMPLE_PERIOD) {
ret = value_set_u64(cw, event, "perf_period", sample->period);
if (ret)
return 0;
}
+static int ctf_stream__flush(struct ctf_stream *cs)
+{
+ int err = 0;
+
+ if (cs) {
+ err = bt_ctf_stream_flush(cs->stream);
+ if (err)
+ pr_err("CTF stream %d flush failed\n", cs->cpu);
+
+ pr("Flush stream for cpu %d (%u samples)\n",
+ cs->cpu, cs->count);
+
+ cs->count = 0;
+ }
+
+ return err;
+}
+
+static struct ctf_stream *ctf_stream__create(struct ctf_writer *cw, int cpu)
+{
+ struct ctf_stream *cs;
+ struct bt_ctf_field *pkt_ctx = NULL;
+ struct bt_ctf_field *cpu_field = NULL;
+ struct bt_ctf_stream *stream = NULL;
+ int ret;
+
+ cs = zalloc(sizeof(*cs));
+ if (!cs) {
+ pr_err("Failed to allocate ctf stream\n");
+ return NULL;
+ }
+
+ stream = bt_ctf_writer_create_stream(cw->writer, cw->stream_class);
+ if (!stream) {
+ pr_err("Failed to create CTF stream\n");
+ goto out;
+ }
+
+ pkt_ctx = bt_ctf_stream_get_packet_context(stream);
+ if (!pkt_ctx) {
+ pr_err("Failed to obtain packet context\n");
+ goto out;
+ }
+
+ cpu_field = bt_ctf_field_structure_get_field(pkt_ctx, "cpu_id");
+ bt_ctf_field_put(pkt_ctx);
+ if (!cpu_field) {
+ pr_err("Failed to obtain cpu field\n");
+ goto out;
+ }
+
+ ret = bt_ctf_field_unsigned_integer_set_value(cpu_field, (u32) cpu);
+ if (ret) {
+ pr_err("Failed to update CPU number\n");
+ goto out;
+ }
+
+ bt_ctf_field_put(cpu_field);
+
+ cs->cpu = cpu;
+ cs->stream = stream;
+ return cs;
+
+out:
+ if (cpu_field)
+ bt_ctf_field_put(cpu_field);
+ if (stream)
+ bt_ctf_stream_put(stream);
+
+ free(cs);
+ return NULL;
+}
+
+static void ctf_stream__delete(struct ctf_stream *cs)
+{
+ if (cs) {
+ bt_ctf_stream_put(cs->stream);
+ free(cs);
+ }
+}
+
+static struct ctf_stream *ctf_stream(struct ctf_writer *cw, int cpu)
+{
+ struct ctf_stream *cs = cw->stream[cpu];
+
+ if (!cs) {
+ cs = ctf_stream__create(cw, cpu);
+ cw->stream[cpu] = cs;
+ }
+
+ return cs;
+}
+
+static int get_sample_cpu(struct ctf_writer *cw, struct perf_sample *sample,
+ struct perf_evsel *evsel)
+{
+ int cpu = 0;
+
+ if (evsel->attr.sample_type & PERF_SAMPLE_CPU)
+ cpu = sample->cpu;
+
+ if (cpu > cw->stream_cnt) {
+ pr_err("Event was recorded for CPU %d, limit is at %d.\n",
+ cpu, cw->stream_cnt);
+ cpu = 0;
+ }
+
+ return cpu;
+}
+
+#define STREAM_FLUSH_COUNT 100000
+
+/*
+ * Currently we have no other way to determine the
+ * time for the stream flush other than keep track
+ * of the number of events and check it against
+ * threshold.
+ */
+static bool is_flush_needed(struct ctf_stream *cs)
+{
+ return cs->count >= STREAM_FLUSH_COUNT;
+}
+
static int process_sample_event(struct perf_tool *tool,
union perf_event *_event __maybe_unused,
struct perf_sample *sample,
struct convert *c = container_of(tool, struct convert, tool);
struct evsel_priv *priv = evsel->priv;
struct ctf_writer *cw = &c->writer;
+ struct ctf_stream *cs;
struct bt_ctf_event_class *event_class;
struct bt_ctf_event *event;
int ret;
return -1;
}
- bt_ctf_stream_append_event(cw->stream, event);
+ cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
+ if (cs) {
+ if (is_flush_needed(cs))
+ ctf_stream__flush(cs);
+
+ cs->count++;
+ bt_ctf_stream_append_event(cs->stream, event);
+ }
+
bt_ctf_event_put(event);
- return 0;
+ return cs ? 0 : -1;
+}
+
+/* If dup < 0, add a prefix. Else, add _dupl_X suffix. */
+static char *change_name(char *name, char *orig_name, int dup)
+{
+ char *new_name = NULL;
+ size_t len;
+
+ if (!name)
+ name = orig_name;
+
+ if (dup >= 10)
+ goto out;
+ /*
+ * Add '_' prefix to potential keywork. According to
+ * Mathieu Desnoyers (https://lkml.org/lkml/2015/1/23/652),
+ * futher CTF spec updating may require us to use '$'.
+ */
+ if (dup < 0)
+ len = strlen(name) + sizeof("_");
+ else
+ len = strlen(orig_name) + sizeof("_dupl_X");
+
+ new_name = malloc(len);
+ if (!new_name)
+ goto out;
+
+ if (dup < 0)
+ snprintf(new_name, len, "_%s", name);
+ else
+ snprintf(new_name, len, "%s_dupl_%d", orig_name, dup);
+
+out:
+ if (name != orig_name)
+ free(name);
+ return new_name;
+}
+
+static int event_class_add_field(struct bt_ctf_event_class *event_class,
+ struct bt_ctf_field_type *type,
+ struct format_field *field)
+{
+ struct bt_ctf_field_type *t = NULL;
+ char *name;
+ int dup = 1;
+ int ret;
+
+ /* alias was already assigned */
+ if (field->alias != field->name)
+ return bt_ctf_event_class_add_field(event_class, type,
+ (char *)field->alias);
+
+ name = field->name;
+
+ /* If 'name' is a keywork, add prefix. */
+ if (bt_ctf_validate_identifier(name))
+ name = change_name(name, field->name, -1);
+
+ if (!name) {
+ pr_err("Failed to fix invalid identifier.");
+ return -1;
+ }
+ while ((t = bt_ctf_event_class_get_field_by_name(event_class, name))) {
+ bt_ctf_field_type_put(t);
+ name = change_name(name, field->name, dup++);
+ if (!name) {
+ pr_err("Failed to create dup name for '%s'\n", field->name);
+ return -1;
+ }
+ }
+
+ ret = bt_ctf_event_class_add_field(event_class, type, name);
+ if (!ret)
+ field->alias = name;
+
+ return ret;
}
static int add_tracepoint_fields_types(struct ctf_writer *cw,
if (flags & FIELD_IS_ARRAY)
type = bt_ctf_field_type_array_create(type, field->arraylen);
- ret = bt_ctf_event_class_add_field(event_class, type,
- field->name);
+ ret = event_class_add_field(event_class, type, field);
if (flags & FIELD_IS_ARRAY)
bt_ctf_field_type_put(type);
if (ret) {
- pr_err("Failed to add field '%s\n", field->name);
+ pr_err("Failed to add field '%s': %d\n",
+ field->name, ret);
return -1;
}
}
do { \
pr2(" field '%s'\n", n); \
if (bt_ctf_event_class_add_field(cl, t, n)) { \
- pr_err("Failed to add field '%s;\n", n); \
+ pr_err("Failed to add field '%s';\n", n); \
return -1; \
} \
} while (0)
if (type & PERF_SAMPLE_STREAM_ID)
ADD_FIELD(event_class, cw->data.u64, "perf_stream_id");
- if (type & PERF_SAMPLE_CPU)
- ADD_FIELD(event_class, cw->data.u32, "perf_cpu");
-
if (type & PERF_SAMPLE_PERIOD)
ADD_FIELD(event_class, cw->data.u64, "perf_period");
return 0;
}
+static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
+{
+ struct ctf_stream **stream;
+ struct perf_header *ph = &session->header;
+ int ncpus;
+
+ /*
+ * Try to get the number of cpus used in the data file,
+ * if not present fallback to the MAX_CPUS.
+ */
+ ncpus = ph->env.nr_cpus_avail ?: MAX_CPUS;
+
+ stream = zalloc(sizeof(*stream) * ncpus);
+ if (!stream) {
+ pr_err("Failed to allocate streams.\n");
+ return -ENOMEM;
+ }
+
+ cw->stream = stream;
+ cw->stream_cnt = ncpus;
+ return 0;
+}
+
+static void free_streams(struct ctf_writer *cw)
+{
+ int cpu;
+
+ for (cpu = 0; cpu < cw->stream_cnt; cpu++)
+ ctf_stream__delete(cw->stream[cpu]);
+
+ free(cw->stream);
+}
+
static int ctf_writer__setup_env(struct ctf_writer *cw,
struct perf_session *session)
{
ctf_writer__cleanup_data(cw);
bt_ctf_clock_put(cw->clock);
- bt_ctf_stream_put(cw->stream);
+ free_streams(cw);
bt_ctf_stream_class_put(cw->stream_class);
bt_ctf_writer_put(cw->writer);
{
struct bt_ctf_writer *writer;
struct bt_ctf_stream_class *stream_class;
- struct bt_ctf_stream *stream;
struct bt_ctf_clock *clock;
+ struct bt_ctf_field_type *pkt_ctx_type;
+ int ret;
/* CTF writer */
writer = bt_ctf_writer_create(path);
if (ctf_writer__init_data(cw))
goto err_cleanup;
- /* CTF stream instance */
- stream = bt_ctf_writer_create_stream(writer, stream_class);
- if (!stream) {
- pr("Failed to create CTF stream.\n");
+ /* Add cpu_id for packet context */
+ pkt_ctx_type = bt_ctf_stream_class_get_packet_context_type(stream_class);
+ if (!pkt_ctx_type)
goto err_cleanup;
- }
- cw->stream = stream;
+ ret = bt_ctf_field_type_structure_add_field(pkt_ctx_type, cw->data.u32, "cpu_id");
+ bt_ctf_field_type_put(pkt_ctx_type);
+ if (ret)
+ goto err_cleanup;
/* CTF clock writer setup */
if (bt_ctf_writer_add_clock(writer, clock)) {
return -1;
}
+static int ctf_writer__flush_streams(struct ctf_writer *cw)
+{
+ int cpu, ret = 0;
+
+ for (cpu = 0; cpu < cw->stream_cnt && !ret; cpu++)
+ ret = ctf_stream__flush(cw->stream[cpu]);
+
+ return ret;
+}
+
+static int convert__config(const char *var, const char *value, void *cb)
+{
+ struct convert *c = cb;
+
+ if (!strcmp(var, "convert.queue-size")) {
+ c->queue_size = perf_config_u64(var, value);
+ return 0;
+ }
+
+ return perf_default_config(var, value, cb);
+}
+
int bt_convert__perf2ctf(const char *input, const char *path, bool force)
{
struct perf_session *session;
struct ctf_writer *cw = &c.writer;
int err = -1;
+ perf_config(convert__config, &c);
+
/* CTF writer */
if (ctf_writer__init(cw, path))
return -1;
if (!session)
goto free_writer;
+ if (c.queue_size) {
+ ordered_events__set_alloc_size(&session->ordered_events,
+ c.queue_size);
+ }
+
/* CTF writer env/clock setup */
if (ctf_writer__setup_env(cw, session))
goto free_session;
if (setup_events(cw, session))
goto free_session;
+ if (setup_streams(cw, session))
+ goto free_session;
+
err = perf_session__process_events(session);
if (!err)
- err = bt_ctf_stream_flush(cw->stream);
+ err = ctf_writer__flush_streams(cw);
+ else
+ pr_err("Error during conversion.\n");
fprintf(stderr,
"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
(double) c.events_size / 1024.0 / 1024.0,
c.events_count);
- /* its all good */
-free_session:
perf_session__delete(session);
+ ctf_writer__cleanup(cw);
+
+ return err;
+free_session:
+ perf_session__delete(session);
free_writer:
ctf_writer__cleanup(cw);
+ pr_err("Error during conversion setup.\n");
return err;
}
int db_export__thread(struct db_export *dbe, struct thread *thread,
struct machine *machine, struct comm *comm)
{
+ struct thread *main_thread;
u64 main_thread_db_id = 0;
int err;
thread->db_id = ++dbe->thread_last_db_id;
if (thread->pid_ != -1) {
- struct thread *main_thread;
-
if (thread->pid_ == thread->tid) {
main_thread = thread;
} else {
err = db_export__thread(dbe, main_thread, machine,
comm);
if (err)
- return err;
+ goto out_put;
if (comm) {
err = db_export__comm_thread(dbe, comm, thread);
if (err)
- return err;
+ goto out_put;
}
}
main_thread_db_id = main_thread->db_id;
+ if (main_thread != thread)
+ thread__put(main_thread);
}
if (dbe->export_thread)
machine);
return 0;
+
+out_put:
+ thread__put(main_thread);
+ return err;
}
int db_export__comm(struct db_export *dbe, struct comm *comm,
static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
{
if (thread->pid_ == thread->tid)
- return thread;
+ return thread__get(thread);
if (thread->pid_ == -1)
return NULL;
err = db_export__thread(dbe, thread, al->machine, comm);
if (err)
- return err;
+ goto out_put;
if (comm) {
err = db_export__comm(dbe, comm, main_thread);
if (err)
- return err;
+ goto out_put;
es.comm_db_id = comm->db_id;
}
err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset);
if (err)
- return err;
+ goto out_put;
if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
sample_addr_correlates_sym(&evsel->attr)) {
err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
&es.addr_sym_db_id, &es.addr_offset);
if (err)
- return err;
+ goto out_put;
if (dbe->crp) {
err = thread_stack__process(thread, comm, sample, al,
&addr_al, es.db_id,
dbe->crp);
if (err)
- return err;
+ goto out_put;
}
}
if (dbe->export_sample)
- return dbe->export_sample(dbe, &es);
+ err = dbe->export_sample(dbe, &es);
- return 0;
+out_put:
+ thread__put(main_thread);
+ return err;
}
static struct {
#include "symbol.h"
#include "dso.h"
#include "machine.h"
+#include "auxtrace.h"
#include "util.h"
#include "debug.h"
return false;
}
-bool is_kernel_module(const char *pathname)
+bool is_kernel_module(const char *pathname, int cpumode)
{
struct kmod_path m;
-
- if (kmod_path__parse(&m, pathname))
- return NULL;
+ int mode = cpumode & PERF_RECORD_MISC_CPUMODE_MASK;
+
+ WARN_ONCE(mode != cpumode,
+ "Internal error: passing unmasked cpumode (%x) to is_kernel_module",
+ cpumode);
+
+ switch (mode) {
+ case PERF_RECORD_MISC_USER:
+ case PERF_RECORD_MISC_HYPERVISOR:
+ case PERF_RECORD_MISC_GUEST_USER:
+ return false;
+ /* Treat PERF_RECORD_MISC_CPUMODE_UNKNOWN as kernel */
+ default:
+ if (kmod_path__parse(&m, pathname)) {
+ pr_err("Failed to check whether %s is a kernel module or not. Assume it is.",
+ pathname);
+ return true;
+ }
+ }
return m.kmod;
}
{
const char *name = strrchr(path, '/');
const char *ext = strrchr(path, '.');
+ bool is_simple_name = false;
memset(m, 0x0, sizeof(*m));
name = name ? name + 1 : path;
+ /*
+ * '.' is also a valid character for module name. For example:
+ * [aaa.bbb] is a valid module name. '[' should have higher
+ * priority than '.ko' suffix.
+ *
+ * The kernel names are from machine__mmap_name. Such
+ * name should belong to kernel itself, not kernel module.
+ */
+ if (name[0] == '[') {
+ is_simple_name = true;
+ if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) ||
+ (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) ||
+ (strncmp(name, "[vdso]", 6) == 0) ||
+ (strncmp(name, "[vsyscall]", 10) == 0)) {
+ m->kmod = false;
+
+ } else
+ m->kmod = true;
+ }
+
/* No extension, just return name. */
- if (ext == NULL) {
+ if ((ext == NULL) || is_simple_name) {
if (alloc_name) {
m->name = strdup(name);
return m->name ? 0 : -ENOMEM;
*/
static LIST_HEAD(dso__data_open);
static long dso__data_open_cnt;
+static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;
static void dso__list_add(struct dso *dso)
{
*/
void dso__data_close(struct dso *dso)
{
+ pthread_mutex_lock(&dso__data_open_lock);
close_dso(dso);
+ pthread_mutex_unlock(&dso__data_open_lock);
}
-/**
- * dso__data_fd - Get dso's data file descriptor
- * @dso: dso object
- * @machine: machine object
- *
- * External interface to find dso's file, open it and
- * returns file descriptor.
- */
-int dso__data_fd(struct dso *dso, struct machine *machine)
+static void try_to_open_dso(struct dso *dso, struct machine *machine)
{
enum dso_binary_type binary_type_data[] = {
DSO_BINARY_TYPE__BUILD_ID_CACHE,
};
int i = 0;
- if (dso->data.status == DSO_DATA_STATUS_ERROR)
- return -1;
-
if (dso->data.fd >= 0)
- goto out;
+ return;
if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
dso->data.fd = open_dso(dso, machine);
dso->data.status = DSO_DATA_STATUS_OK;
else
dso->data.status = DSO_DATA_STATUS_ERROR;
+}
+
+/**
+ * dso__data_get_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor. It should be paired with
+ * dso__data_put_fd() if it returns non-negative value.
+ */
+int dso__data_get_fd(struct dso *dso, struct machine *machine)
+{
+ if (dso->data.status == DSO_DATA_STATUS_ERROR)
+ return -1;
+
+ if (pthread_mutex_lock(&dso__data_open_lock) < 0)
+ return -1;
+
+ try_to_open_dso(dso, machine);
+
+ if (dso->data.fd < 0)
+ pthread_mutex_unlock(&dso__data_open_lock);
return dso->data.fd;
}
+void dso__data_put_fd(struct dso *dso __maybe_unused)
+{
+ pthread_mutex_unlock(&dso__data_open_lock);
+}
+
bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
{
u32 flag = 1 << by;
}
static void
-dso_cache__free(struct rb_root *root)
+dso_cache__free(struct dso *dso)
{
+ struct rb_root *root = &dso->data.cache;
struct rb_node *next = rb_first(root);
+ pthread_mutex_lock(&dso->lock);
while (next) {
struct dso_cache *cache;
rb_erase(&cache->rb_node, root);
free(cache);
}
+ pthread_mutex_unlock(&dso->lock);
}
-static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
{
+ const struct rb_root *root = &dso->data.cache;
struct rb_node * const *p = &root->rb_node;
const struct rb_node *parent = NULL;
struct dso_cache *cache;
else
return cache;
}
+
return NULL;
}
-static void
-dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+static struct dso_cache *
+dso_cache__insert(struct dso *dso, struct dso_cache *new)
{
+ struct rb_root *root = &dso->data.cache;
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct dso_cache *cache;
u64 offset = new->offset;
+ pthread_mutex_lock(&dso->lock);
while (*p != NULL) {
u64 end;
p = &(*p)->rb_left;
else if (offset >= end)
p = &(*p)->rb_right;
+ else
+ goto out;
}
rb_link_node(&new->rb_node, parent, p);
rb_insert_color(&new->rb_node, root);
+
+ cache = NULL;
+out:
+ pthread_mutex_unlock(&dso->lock);
+ return cache;
}
static ssize_t
}
static ssize_t
-dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
struct dso_cache *cache;
+ struct dso_cache *old;
ssize_t ret;
do {
u64 cache_offset;
- ret = -ENOMEM;
-
cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
if (!cache)
+ return -ENOMEM;
+
+ pthread_mutex_lock(&dso__data_open_lock);
+
+ /*
+ * dso->data.fd might be closed if other thread opened another
+ * file (dso) due to open file limit (RLIMIT_NOFILE).
+ */
+ try_to_open_dso(dso, machine);
+
+ if (dso->data.fd < 0) {
+ ret = -errno;
+ dso->data.status = DSO_DATA_STATUS_ERROR;
break;
+ }
cache_offset = offset & DSO__DATA_CACHE_MASK;
cache->offset = cache_offset;
cache->size = ret;
- dso_cache__insert(&dso->data.cache, cache);
+ } while (0);
- ret = dso_cache__memcpy(cache, offset, data, size);
+ pthread_mutex_unlock(&dso__data_open_lock);
- } while (0);
+ if (ret > 0) {
+ old = dso_cache__insert(dso, cache);
+ if (old) {
+ /* we lose the race */
+ free(cache);
+ cache = old;
+ }
+
+ ret = dso_cache__memcpy(cache, offset, data, size);
+ }
if (ret <= 0)
free(cache);
return ret;
}
-static ssize_t dso_cache_read(struct dso *dso, u64 offset,
- u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
struct dso_cache *cache;
- cache = dso_cache__find(&dso->data.cache, offset);
+ cache = dso_cache__find(dso, offset);
if (cache)
return dso_cache__memcpy(cache, offset, data, size);
else
- return dso_cache__read(dso, offset, data, size);
+ return dso_cache__read(dso, machine, offset, data, size);
}
/*
* in the rb_tree. Any read to already cached data is served
* by cached data.
*/
-static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+static ssize_t cached_read(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
ssize_t r = 0;
u8 *p = data;
do {
ssize_t ret;
- ret = dso_cache_read(dso, offset, p, size);
+ ret = dso_cache_read(dso, machine, offset, p, size);
if (ret < 0)
return ret;
return r;
}
-static int data_file_size(struct dso *dso)
+static int data_file_size(struct dso *dso, struct machine *machine)
{
+ int ret = 0;
struct stat st;
char sbuf[STRERR_BUFSIZE];
- if (!dso->data.file_size) {
- if (fstat(dso->data.fd, &st)) {
- pr_err("dso mmap failed, fstat: %s\n",
- strerror_r(errno, sbuf, sizeof(sbuf)));
- return -1;
- }
- dso->data.file_size = st.st_size;
+ if (dso->data.file_size)
+ return 0;
+
+ if (dso->data.status == DSO_DATA_STATUS_ERROR)
+ return -1;
+
+ pthread_mutex_lock(&dso__data_open_lock);
+
+ /*
+ * dso->data.fd might be closed if other thread opened another
+ * file (dso) due to open file limit (RLIMIT_NOFILE).
+ */
+ try_to_open_dso(dso, machine);
+
+ if (dso->data.fd < 0) {
+ ret = -errno;
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+ goto out;
}
- return 0;
+ if (fstat(dso->data.fd, &st) < 0) {
+ ret = -errno;
+ pr_err("dso cache fstat failed: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+ goto out;
+ }
+ dso->data.file_size = st.st_size;
+
+out:
+ pthread_mutex_unlock(&dso__data_open_lock);
+ return ret;
}
/**
*/
off_t dso__data_size(struct dso *dso, struct machine *machine)
{
- int fd;
-
- fd = dso__data_fd(dso, machine);
- if (fd < 0)
- return fd;
-
- if (data_file_size(dso))
+ if (data_file_size(dso, machine))
return -1;
/* For now just estimate dso data size is close to file size */
return dso->data.file_size;
}
-static ssize_t data_read_offset(struct dso *dso, u64 offset,
- u8 *data, ssize_t size)
+static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
{
- if (data_file_size(dso))
+ if (data_file_size(dso, machine))
return -1;
/* Check the offset sanity. */
if (offset + size < offset)
return -1;
- return cached_read(dso, offset, data, size);
+ return cached_read(dso, machine, offset, data, size);
}
/**
ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
- if (dso__data_fd(dso, machine) < 0)
+ if (dso->data.status == DSO_DATA_STATUS_ERROR)
return -1;
- return data_read_offset(dso, offset, data, size);
+ return data_read_offset(dso, machine, offset, data, size);
}
/**
return map;
}
-struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
- const char *short_name, int dso_type)
+struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
+ const char *short_name, int dso_type)
{
/*
* The kernel dso could be created by build_id processing.
*/
- struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name);
+ struct dso *dso = machine__findnew_dso(machine, name);
/*
* We need to run this in all cases, since during the build_id
* Either one of the dso or name parameter must be non-NULL or the
* function will not work.
*/
-static struct dso *dso__findlink_by_longname(struct rb_root *root,
- struct dso *dso, const char *name)
+static struct dso *__dso__findlink_by_longname(struct rb_root *root,
+ struct dso *dso, const char *name)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
return NULL;
}
-static inline struct dso *
-dso__find_by_longname(const struct rb_root *root, const char *name)
+static inline struct dso *__dso__find_by_longname(struct rb_root *root,
+ const char *name)
{
- return dso__findlink_by_longname((struct rb_root *)root, NULL, name);
+ return __dso__findlink_by_longname(root, NULL, name);
}
void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
RB_CLEAR_NODE(&dso->rb_node);
INIT_LIST_HEAD(&dso->node);
INIT_LIST_HEAD(&dso->data.open_entry);
+ pthread_mutex_init(&dso->lock, NULL);
+ atomic_set(&dso->refcnt, 1);
}
return dso;
}
dso__data_close(dso);
- dso_cache__free(&dso->data.cache);
+ auxtrace_cache__free(dso->auxtrace_cache);
+ dso_cache__free(dso);
dso__free_a2l(dso);
zfree(&dso->symsrc_filename);
+ pthread_mutex_destroy(&dso->lock);
free(dso);
}
+struct dso *dso__get(struct dso *dso)
+{
+ if (dso)
+ atomic_inc(&dso->refcnt);
+ return dso;
+}
+
+void dso__put(struct dso *dso)
+{
+ if (dso && atomic_dec_and_test(&dso->refcnt))
+ dso__delete(dso);
+}
+
void dso__set_build_id(struct dso *dso, void *build_id)
{
memcpy(dso->build_id, build_id, sizeof(dso->build_id));
return have_build_id;
}
-void dsos__add(struct dsos *dsos, struct dso *dso)
+void __dsos__add(struct dsos *dsos, struct dso *dso)
{
list_add_tail(&dso->node, &dsos->head);
- dso__findlink_by_longname(&dsos->root, dso, NULL);
+ __dso__findlink_by_longname(&dsos->root, dso, NULL);
+ /*
+ * It is now in the linked list, grab a reference, then garbage collect
+ * this when needing memory, by looking at LRU dso instances in the
+ * list with atomic_read(&dso->refcnt) == 1, i.e. no references
+ * anywhere besides the one for the list, do, under a lock for the
+ * list: remove it from the list, then a dso__put(), that probably will
+ * be the last and will then call dso__delete(), end of life.
+ *
+ * That, or at the end of the 'struct machine' lifetime, when all
+ * 'struct dso' instances will be removed from the list, in
+ * dsos__exit(), if they have no other reference from some other data
+ * structure.
+ *
+ * E.g.: after processing a 'perf.data' file and storing references
+ * to objects instantiated while processing events, we will have
+ * references to the 'thread', 'map', 'dso' structs all from 'struct
+ * hist_entry' instances, but we may not need anything not referenced,
+ * so we might as well call machines__exit()/machines__delete() and
+ * garbage collect it.
+ */
+ dso__get(dso);
+}
+
+void dsos__add(struct dsos *dsos, struct dso *dso)
+{
+ pthread_rwlock_wrlock(&dsos->lock);
+ __dsos__add(dsos, dso);
+ pthread_rwlock_unlock(&dsos->lock);
}
-struct dso *dsos__find(const struct dsos *dsos, const char *name,
- bool cmp_short)
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
{
struct dso *pos;
return pos;
return NULL;
}
- return dso__find_by_longname(&dsos->root, name);
+ return __dso__find_by_longname(&dsos->root, name);
+}
+
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+{
+ struct dso *dso;
+ pthread_rwlock_rdlock(&dsos->lock);
+ dso = __dsos__find(dsos, name, cmp_short);
+ pthread_rwlock_unlock(&dsos->lock);
+ return dso;
}
-struct dso *dsos__addnew(struct dsos *dsos, const char *name)
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
{
struct dso *dso = dso__new(name);
if (dso != NULL) {
- dsos__add(dsos, dso);
+ __dsos__add(dsos, dso);
dso__set_basename(dso);
}
return dso;
struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
{
- struct dso *dso = dsos__find(dsos, name, false);
+ struct dso *dso = __dsos__find(dsos, name, false);
- return dso ? dso : dsos__addnew(dsos, name);
+ return dso ? dso : __dsos__addnew(dsos, name);
+}
+
+struct dso *dsos__findnew(struct dsos *dsos, const char *name)
+{
+ struct dso *dso;
+ pthread_rwlock_wrlock(&dsos->lock);
+ dso = dso__get(__dsos__findnew(dsos, name));
+ pthread_rwlock_unlock(&dsos->lock);
+ return dso;
}
size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
enum dso_type dso__type(struct dso *dso, struct machine *machine)
{
int fd;
+ enum dso_type type = DSO__TYPE_UNKNOWN;
- fd = dso__data_fd(dso, machine);
- if (fd < 0)
- return DSO__TYPE_UNKNOWN;
+ fd = dso__data_get_fd(dso, machine);
+ if (fd >= 0) {
+ type = dso__type_fd(fd);
+ dso__data_put_fd(dso);
+ }
- return dso__type_fd(fd);
+ return type;
}
int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
#ifndef __PERF_DSO
#define __PERF_DSO
+#include <linux/atomic.h>
#include <linux/types.h>
#include <linux/rbtree.h>
#include <stdbool.h>
+#include <pthread.h>
#include <linux/types.h>
#include <linux/bitops.h>
#include "map.h"
struct dsos {
struct list_head head;
struct rb_root root; /* rbtree root sorted by long name */
+ pthread_rwlock_t lock;
};
+struct auxtrace_cache;
+
struct dso {
+ pthread_mutex_t lock;
struct list_head node;
struct rb_node rb_node; /* rbtree node sorted by long name */
struct rb_root symbols[MAP__NR_TYPES];
u16 long_name_len;
u16 short_name_len;
void *dwfl; /* DWARF debug info */
+ struct auxtrace_cache *auxtrace_cache;
/* dso data file */
struct {
void *priv;
u64 db_id;
};
-
+ atomic_t refcnt;
char name[0];
};
int dso__name_len(const struct dso *dso);
+struct dso *dso__get(struct dso *dso);
+void dso__put(struct dso *dso);
+
+static inline void __dso__zput(struct dso **dso)
+{
+ dso__put(*dso);
+ *dso = NULL;
+}
+
+#define dso__zput(dso) __dso__zput(&dso)
+
bool dso__loaded(const struct dso *dso, enum map_type type);
bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
char *root_dir, char *filename, size_t size);
bool is_supported_compression(const char *ext);
-bool is_kernel_module(const char *pathname);
+bool is_kernel_module(const char *pathname, int cpumode);
bool decompress_to_file(const char *ext, const char *filename, int output_fd);
bool dso__needs_decompress(struct dso *dso);
/*
* The dso__data_* external interface provides following functions:
- * dso__data_fd
+ * dso__data_get_fd
+ * dso__data_put_fd
* dso__data_close
* dso__data_size
* dso__data_read_offset
* The current usage of the dso__data_* interface is as follows:
*
* Get DSO's fd:
- * int fd = dso__data_fd(dso, machine);
- * USE 'fd' SOMEHOW
+ * int fd = dso__data_get_fd(dso, machine);
+ * if (fd >= 0) {
+ * USE 'fd' SOMEHOW
+ * dso__data_put_fd(dso);
+ * }
*
* Read DSO's data:
* n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
*
* TODO
*/
-int dso__data_fd(struct dso *dso, struct machine *machine);
+int dso__data_get_fd(struct dso *dso, struct machine *machine);
+void dso__data_put_fd(struct dso *dso __maybe_unused);
void dso__data_close(struct dso *dso);
off_t dso__data_size(struct dso *dso, struct machine *machine);
bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by);
struct map *dso__new_map(const char *name);
-struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
- const char *short_name, int dso_type);
+struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
+ const char *short_name, int dso_type);
+void __dsos__add(struct dsos *dsos, struct dso *dso);
void dsos__add(struct dsos *dsos, struct dso *dso);
-struct dso *dsos__addnew(struct dsos *dsos, const char *name);
-struct dso *dsos__find(const struct dsos *dsos, const char *name,
- bool cmp_short);
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
+struct dso *dsos__findnew(struct dsos *dsos, const char *name);
bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
{
const char *name;
+
name = dwarf_diename(dw_die);
return name ? (strcmp(tname, name) == 0) : false;
}
+/**
+ * die_match_name - Match diename and glob
+ * @dw_die: a DIE
+ * @glob: a string of target glob pattern
+ *
+ * Glob matching the name of @dw_die and @glob. Return false if matching fail.
+ */
+bool die_match_name(Dwarf_Die *dw_die, const char *glob)
+{
+ const char *name;
+
+ name = dwarf_diename(dw_die);
+ return name ? strglobmatch(name, glob) : false;
+}
+
/**
* die_get_call_lineno - Get callsite line number of inline-function instance
* @in_die: a DIE of an inlined function instance
Dwarf_Die *die_mem;
};
+static int __die_search_func_tail_cb(Dwarf_Die *fn_die, void *data)
+{
+ struct __addr_die_search_param *ad = data;
+ Dwarf_Addr addr = 0;
+
+ if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+ !dwarf_highpc(fn_die, &addr) &&
+ addr == ad->addr) {
+ memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+ return DWARF_CB_ABORT;
+ }
+ return DWARF_CB_OK;
+}
+
+/**
+ * die_find_tailfunc - Search for a non-inlined function with tail call at
+ * given address
+ * @cu_die: a CU DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search for a non-inlined function DIE with tail call at @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+ Dwarf_Die *die_mem)
+{
+ struct __addr_die_search_param ad;
+ ad.addr = addr;
+ ad.die_mem = die_mem;
+ /* dwarf_getscopes can't find subprogram. */
+ if (!dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0))
+ return NULL;
+ else
+ return die_mem;
+}
+
/* die_find callback for non-inlined function search */
static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
{
/**
* die_get_typename - Get the name of given variable DIE
* @vr_die: a variable DIE
- * @buf: a buffer for result type name
- * @len: a max-length of @buf
+ * @buf: a strbuf for result type name
*
- * Get the name of @vr_die and stores it to @buf. Return the actual length
- * of type name if succeeded. Return -E2BIG if @len is not enough long, and
- * Return -ENOENT if failed to find type name.
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
* Note that the result will stores typedef name if possible, and stores
* "*(function_type)" if the type is a function pointer.
*/
-int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
{
Dwarf_Die type;
- int tag, ret, ret2;
+ int tag, ret;
const char *tmp = "";
if (__die_get_real_type(vr_die, &type) == NULL)
tmp = "*";
else if (tag == DW_TAG_subroutine_type) {
/* Function pointer */
- ret = snprintf(buf, len, "(function_type)");
- return (ret >= len) ? -E2BIG : ret;
+ strbuf_addf(buf, "(function_type)");
+ return 0;
} else {
if (!dwarf_diename(&type))
return -ENOENT;
else if (tag == DW_TAG_enumeration_type)
tmp = "enum ";
/* Write a base name */
- ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
- return (ret >= len) ? -E2BIG : ret;
- }
- ret = die_get_typename(&type, buf, len);
- if (ret > 0) {
- ret2 = snprintf(buf + ret, len - ret, "%s", tmp);
- ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+ strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type));
+ return 0;
}
+ ret = die_get_typename(&type, buf);
+ if (ret == 0)
+ strbuf_addf(buf, "%s", tmp);
+
return ret;
}
/**
* die_get_varname - Get the name and type of given variable DIE
* @vr_die: a variable DIE
- * @buf: a buffer for type and variable name
- * @len: the max-length of @buf
+ * @buf: a strbuf for type and variable name
*
* Get the name and type of @vr_die and stores it in @buf as "type\tname".
*/
-int die_get_varname(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
{
- int ret, ret2;
+ int ret;
- ret = die_get_typename(vr_die, buf, len);
+ ret = die_get_typename(vr_die, buf);
if (ret < 0) {
pr_debug("Failed to get type, make it unknown.\n");
- ret = snprintf(buf, len, "(unknown_type)");
+ strbuf_addf(buf, "(unknown_type)");
}
- if (ret > 0) {
- ret2 = snprintf(buf + ret, len - ret, "\t%s",
- dwarf_diename(vr_die));
- ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+
+ strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
+
+ return 0;
+}
+
+/**
+ * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for variable byte offset range
+ *
+ * Get the innermost scope range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+ struct strbuf *buf)
+{
+ Dwarf_Die *scopes;
+ int count;
+ size_t offset = 0;
+ Dwarf_Addr base;
+ Dwarf_Addr start, end;
+ Dwarf_Addr entry;
+ int ret;
+ bool first = true;
+ const char *name;
+
+ ret = dwarf_entrypc(sp_die, &entry);
+ if (ret)
+ return ret;
+
+ name = dwarf_diename(sp_die);
+ if (!name)
+ return -ENOENT;
+
+ count = dwarf_getscopes_die(vr_die, &scopes);
+
+ /* (*SCOPES)[1] is the DIE for the scope containing that scope */
+ if (count <= 1) {
+ ret = -EINVAL;
+ goto out;
}
+
+ while ((offset = dwarf_ranges(&scopes[1], offset, &base,
+ &start, &end)) > 0) {
+ start -= entry;
+ end -= entry;
+
+ if (first) {
+ strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+ name, start, end);
+ first = false;
+ } else {
+ strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+ start, end);
+ }
+ }
+
+ if (!first)
+ strbuf_addf(buf, "]>");
+
+out:
+ free(scopes);
return ret;
}
+/**
+ * die_get_var_range - Get byte offset range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for type and variable name and byte offset range
+ *
+ * Get the byte offset range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
+{
+ int ret = 0;
+ Dwarf_Addr base;
+ Dwarf_Addr start, end;
+ Dwarf_Addr entry;
+ Dwarf_Op *op;
+ size_t nops;
+ size_t offset = 0;
+ Dwarf_Attribute attr;
+ bool first = true;
+ const char *name;
+
+ ret = dwarf_entrypc(sp_die, &entry);
+ if (ret)
+ return ret;
+
+ name = dwarf_diename(sp_die);
+ if (!name)
+ return -ENOENT;
+
+ if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
+ return -EINVAL;
+
+ while ((offset = dwarf_getlocations(
+ &attr, offset, &base,
+ &start, &end, &op, &nops)) > 0) {
+ if (start == 0) {
+ /* Single Location Descriptions */
+ ret = die_get_var_innermost_scope(sp_die, vr_die, buf);
+ return ret;
+ }
+
+ /* Location Lists */
+ start -= entry;
+ end -= entry;
+ if (first) {
+ strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+ name, start, end);
+ first = false;
+ } else {
+ strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+ start, end);
+ }
+ }
+
+ if (!first)
+ strbuf_addf(buf, "]>");
+
+ return ret;
+}
/* Compare diename and tname */
extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
+/* Matching diename with glob pattern */
+extern bool die_match_name(Dwarf_Die *dw_die, const char *glob);
+
/* Get callsite line number of inline-function instance */
extern int die_get_call_lineno(Dwarf_Die *in_die);
extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
+/* Search a non-inlined function with tail call at given address */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+ Dwarf_Die *die_mem);
+
/* Search the top inlined function including given address */
extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
Dwarf_Die *die_mem);
/* Get the name of given variable DIE */
-extern int die_get_typename(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
/* Get the name and type of given variable DIE, stored as "type\tname" */
-extern int die_get_varname(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
+extern int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+ struct strbuf *buf);
#endif
*/
#include "cache.h"
-const char *pager_program;
int pager_use_color = 1;
[PERF_RECORD_FORK] = "FORK",
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
+ [PERF_RECORD_AUX] = "AUX",
+ [PERF_RECORD_ITRACE_START] = "ITRACE_START",
+ [PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
[PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID",
[PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND",
[PERF_RECORD_ID_INDEX] = "ID_INDEX",
+ [PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO",
+ [PERF_RECORD_AUXTRACE] = "AUXTRACE",
+ [PERF_RECORD_AUXTRACE_ERROR] = "AUXTRACE_ERROR",
};
const char *perf_event__name(unsigned int id)
pid_t pid, pid_t tgid,
perf_event__handler_t process,
struct machine *machine,
- bool mmap_data)
+ bool mmap_data,
+ unsigned int proc_map_timeout)
{
char filename[PATH_MAX];
FILE *fp;
+ unsigned long long t;
+ bool truncation = false;
+ unsigned long long timeout = proc_map_timeout * 1000000ULL;
int rc = 0;
if (machine__is_default_guest(machine))
}
event->header.type = PERF_RECORD_MMAP2;
+ t = rdclock();
while (1) {
char bf[BUFSIZ];
if (fgets(bf, sizeof(bf), fp) == NULL)
break;
+ if ((rdclock() - t) > timeout) {
+ pr_warning("Reading %s time out. "
+ "You may want to increase "
+ "the time limit by --proc-map-timeout\n",
+ filename);
+ truncation = true;
+ goto out;
+ }
+
/* ensure null termination since stack will be reused. */
strcpy(execname, "");
event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
}
+out:
+ if (truncation)
+ event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
+
if (!strcmp(execname, ""))
strcpy(execname, anonstr);
rc = -1;
break;
}
+
+ if (truncation)
+ break;
}
fclose(fp);
struct machine *machine)
{
int rc = 0;
- struct rb_node *nd;
+ struct map *pos;
struct map_groups *kmaps = &machine->kmaps;
+ struct maps *maps = &kmaps->maps[MAP__FUNCTION];
union perf_event *event = zalloc((sizeof(event->mmap) +
machine->id_hdr_size));
if (event == NULL) {
else
event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
- for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
- nd; nd = rb_next(nd)) {
+ for (pos = maps__first(maps); pos; pos = map__next(pos)) {
size_t size;
- struct map *pos = rb_entry(nd, struct map, rb_node);
if (pos->dso->kernel)
continue;
pid_t pid, int full,
perf_event__handler_t process,
struct perf_tool *tool,
- struct machine *machine, bool mmap_data)
+ struct machine *machine,
+ bool mmap_data,
+ unsigned int proc_map_timeout)
{
char filename[PATH_MAX];
DIR *tasks;
return -1;
return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
- process, machine, mmap_data);
+ process, machine, mmap_data,
+ proc_map_timeout);
}
if (machine__is_default_guest(machine))
if (_pid == pid) {
/* process the parent's maps too */
rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
- process, machine, mmap_data);
+ process, machine, mmap_data, proc_map_timeout);
if (rc)
break;
}
struct thread_map *threads,
perf_event__handler_t process,
struct machine *machine,
- bool mmap_data)
+ bool mmap_data,
+ unsigned int proc_map_timeout)
{
union perf_event *comm_event, *mmap_event, *fork_event;
int err = -1, thread, j;
fork_event,
threads->map[thread], 0,
process, tool, machine,
- mmap_data)) {
+ mmap_data, proc_map_timeout)) {
err = -1;
break;
}
fork_event,
comm_event->comm.pid, 0,
process, tool, machine,
- mmap_data)) {
+ mmap_data, proc_map_timeout)) {
err = -1;
break;
}
int perf_event__synthesize_threads(struct perf_tool *tool,
perf_event__handler_t process,
- struct machine *machine, bool mmap_data)
+ struct machine *machine,
+ bool mmap_data,
+ unsigned int proc_map_timeout)
{
DIR *proc;
char proc_path[PATH_MAX];
* one thread couldn't be synthesized.
*/
__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
- 1, process, tool, machine, mmap_data);
+ 1, process, tool, machine, mmap_data,
+ proc_map_timeout);
}
err = 0;
return machine__process_lost_event(machine, event, sample);
}
+int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_aux_event(machine, event);
+}
+
+int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine)
+{
+ return machine__process_itrace_start_event(machine, event);
+}
+
+int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ return machine__process_lost_samples_event(machine, event, sample);
+}
+
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
{
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
return machine__process_exit_event(machine, event, sample);
}
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
+{
+ return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+ event->aux.aux_offset, event->aux.aux_size,
+ event->aux.flags,
+ event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
+ event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+}
+
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
+{
+ return fprintf(fp, " pid: %u tid: %u\n",
+ event->itrace_start.pid, event->itrace_start.tid);
+}
+
size_t perf_event__fprintf(union perf_event *event, FILE *fp)
{
size_t ret = fprintf(fp, "PERF_RECORD_%s",
case PERF_RECORD_MMAP2:
ret += perf_event__fprintf_mmap2(event, fp);
break;
+ case PERF_RECORD_AUX:
+ ret += perf_event__fprintf_aux(event, fp);
+ break;
+ case PERF_RECORD_ITRACE_START:
+ ret += perf_event__fprintf_itrace_start(event, fp);
+ break;
default:
ret += fprintf(fp, "\n");
}
al->sym = NULL;
}
+/*
+ * Callers need to drop the reference to al->thread, obtained in
+ * machine__findnew_thread()
+ */
int perf_event__preprocess_sample(const union perf_event *event,
struct machine *machine,
struct addr_location *al,
return 0;
}
+/*
+ * The preprocess_sample method will return with reference counts for the
+ * in it, when done using (and perhaps getting ref counts if needing to
+ * keep a pointer to one of those entries) it must be paired with
+ * addr_location__put(), so that the refcounts can be decremented.
+ */
+void addr_location__put(struct addr_location *al)
+{
+ thread__zput(al->thread);
+}
+
bool is_bts_event(struct perf_event_attr *attr)
{
return attr->type == PERF_TYPE_HARDWARE &&
u64 lost;
};
+struct lost_samples_event {
+ struct perf_event_header header;
+ u64 lost;
+};
+
/*
* PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
*/
PERF_IP_FLAG_IN_TX = 1ULL << 10,
};
+#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+
#define PERF_BRANCH_MASK (\
PERF_IP_FLAG_BRANCH |\
PERF_IP_FLAG_CALL |\
PERF_RECORD_HEADER_BUILD_ID = 67,
PERF_RECORD_FINISHED_ROUND = 68,
PERF_RECORD_ID_INDEX = 69,
+ PERF_RECORD_AUXTRACE_INFO = 70,
+ PERF_RECORD_AUXTRACE = 71,
+ PERF_RECORD_AUXTRACE_ERROR = 72,
PERF_RECORD_HEADER_MAX
};
+enum auxtrace_error_type {
+ PERF_AUXTRACE_ERROR_ITRACE = 1,
+ PERF_AUXTRACE_ERROR_MAX
+};
+
/*
* The kernel collects the number of events it couldn't send in a stretch and
* when possible sends this number in a PERF_RECORD_LOST event. The number of
* total_lost tells exactly how many events the kernel in fact lost, i.e. it is
* the sum of all struct lost_event.lost fields reported.
*
+ * The kernel discards mixed up samples and sends the number in a
+ * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored
+ * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells
+ * exactly how many samples the kernel in fact dropped, i.e. it is the sum of
+ * all struct lost_samples_event.lost fields reported.
+ *
* The total_period is needed because by default auto-freq is used, so
* multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
* the total number of low level events, it is necessary to to sum all struct
u64 total_period;
u64 total_non_filtered_period;
u64 total_lost;
+ u64 total_lost_samples;
u64 total_invalid_chains;
u32 nr_events[PERF_RECORD_HEADER_MAX];
u32 nr_non_filtered_samples;
u32 nr_invalid_chains;
u32 nr_unknown_id;
u32 nr_unprocessable_samples;
+ u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
+ u32 nr_proc_map_timeout;
};
struct attr_event {
struct id_index_entry entries[0];
};
+struct auxtrace_info_event {
+ struct perf_event_header header;
+ u32 type;
+ u32 reserved__; /* For alignment */
+ u64 priv[];
+};
+
+struct auxtrace_event {
+ struct perf_event_header header;
+ u64 size;
+ u64 offset;
+ u64 reference;
+ u32 idx;
+ u32 tid;
+ u32 cpu;
+ u32 reserved__; /* For alignment */
+};
+
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+ struct perf_event_header header;
+ u32 type;
+ u32 code;
+ u32 cpu;
+ u32 pid;
+ u32 tid;
+ u32 reserved__; /* For alignment */
+ u64 ip;
+ char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
+struct aux_event {
+ struct perf_event_header header;
+ u64 aux_offset;
+ u64 aux_size;
+ u64 flags;
+};
+
+struct itrace_start_event {
+ struct perf_event_header header;
+ u32 pid, tid;
+};
+
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
struct comm_event comm;
struct fork_event fork;
struct lost_event lost;
+ struct lost_samples_event lost_samples;
struct read_event read;
struct throttle_event throttle;
struct sample_event sample;
struct tracing_data_event tracing_data;
struct build_id_event build_id;
struct id_index_event id_index;
+ struct auxtrace_info_event auxtrace_info;
+ struct auxtrace_event auxtrace;
+ struct auxtrace_error_event auxtrace_error;
+ struct aux_event aux;
+ struct itrace_start_event itrace_start;
};
void perf_event__print_totals(void);
int perf_event__synthesize_thread_map(struct perf_tool *tool,
struct thread_map *threads,
perf_event__handler_t process,
- struct machine *machine, bool mmap_data);
+ struct machine *machine, bool mmap_data,
+ unsigned int proc_map_timeout);
int perf_event__synthesize_threads(struct perf_tool *tool,
perf_event__handler_t process,
- struct machine *machine, bool mmap_data);
+ struct machine *machine, bool mmap_data,
+ unsigned int proc_map_timeout);
int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine);
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_event__process_lost_samples(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
+int perf_event__process_aux(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
+int perf_event__process_itrace_start(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
int perf_event__process_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct addr_location *al,
struct perf_sample *sample);
+void addr_location__put(struct addr_location *al);
+
struct thread;
bool is_bts_event(struct perf_event_attr *attr);
pid_t pid, pid_t tgid,
perf_event__handler_t process,
struct machine *machine,
- bool mmap_data);
+ bool mmap_data,
+ unsigned int proc_map_timeout);
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
u64 kallsyms__get_function_start(const char *kallsyms_filename,
PERF_EVENT_IOC_DISABLE, 0);
}
}
+
+ evlist->enabled = false;
}
void perf_evlist__enable(struct perf_evlist *evlist)
PERF_EVENT_IOC_ENABLE, 0);
}
}
+
+ evlist->enabled = true;
+}
+
+void perf_evlist__toggle_enable(struct perf_evlist *evlist)
+{
+ (evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist);
}
int perf_evlist__disable_event(struct perf_evlist *evlist,
union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
{
struct perf_mmap *md = &evlist->mmap[idx];
- u64 head = perf_mmap__read_head(md);
+ u64 head;
u64 old = md->prev;
unsigned char *data = md->base + page_size;
union perf_event *event = NULL;
+ /*
+ * Check if event was unmapped due to a POLLHUP/POLLERR.
+ */
+ if (!atomic_read(&md->refcnt))
+ return NULL;
+
+ head = perf_mmap__read_head(md);
if (evlist->overwrite) {
/*
* If we're further behind than half the buffer, there's a chance
static bool perf_mmap__empty(struct perf_mmap *md)
{
- return perf_mmap__read_head(md) == md->prev;
+ return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
}
static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
{
- ++evlist->mmap[idx].refcnt;
+ atomic_inc(&evlist->mmap[idx].refcnt);
}
static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
{
- BUG_ON(evlist->mmap[idx].refcnt == 0);
+ BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
- if (--evlist->mmap[idx].refcnt == 0)
+ if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
__perf_evlist__munmap(evlist, idx);
}
perf_mmap__write_tail(md, old);
}
- if (md->refcnt == 1 && perf_mmap__empty(md))
+ if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
perf_evlist__mmap_put(evlist, idx);
}
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ void *userpg __maybe_unused,
+ int fd __maybe_unused)
+{
+ return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ off_t auxtrace_offset __maybe_unused,
+ unsigned int auxtrace_pages __maybe_unused,
+ bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(
+ struct auxtrace_mmap_params *mp __maybe_unused,
+ struct perf_evlist *evlist __maybe_unused,
+ int idx __maybe_unused,
+ bool per_cpu __maybe_unused)
+{
+}
+
static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
{
if (evlist->mmap[idx].base != NULL) {
munmap(evlist->mmap[idx].base, evlist->mmap_len);
evlist->mmap[idx].base = NULL;
- evlist->mmap[idx].refcnt = 0;
+ atomic_set(&evlist->mmap[idx].refcnt, 0);
}
+ auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
}
void perf_evlist__munmap(struct perf_evlist *evlist)
struct mmap_params {
int prot;
int mask;
+ struct auxtrace_mmap_params auxtrace_mp;
};
static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
* evlist layer can't just drop it when filtering events in
* perf_evlist__filter_pollfd().
*/
- evlist->mmap[idx].refcnt = 2;
+ atomic_set(&evlist->mmap[idx].refcnt, 2);
evlist->mmap[idx].prev = 0;
evlist->mmap[idx].mask = mp->mask;
evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
return -1;
}
+ if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
+ &mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+ return -1;
+
return 0;
}
for (cpu = 0; cpu < nr_cpus; cpu++) {
int output = -1;
+ auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
+ true);
+
for (thread = 0; thread < nr_threads; thread++) {
if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
thread, &output))
for (thread = 0; thread < nr_threads; thread++) {
int output = -1;
+ auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
+ false);
+
if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
&output))
goto out_unmap;
return pages;
}
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
- int unset __maybe_unused)
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
{
- unsigned int *mmap_pages = opt->value;
unsigned long max = UINT_MAX;
long pages;
return 0;
}
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ return __perf_evlist__parse_mmap_pages(opt->value, str);
+}
+
/**
- * perf_evlist__mmap - Create mmaps to receive events.
+ * perf_evlist__mmap_ex - Create mmaps to receive events.
* @evlist: list of events
* @pages: map length in pages
* @overwrite: overwrite older events?
+ * @auxtrace_pages - auxtrace map length in pages
+ * @auxtrace_overwrite - overwrite older auxtrace data?
*
* If @overwrite is %false the user needs to signal event consumption using
* perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this
* automatically.
*
+ * Similarly, if @auxtrace_overwrite is %false the user needs to signal data
+ * consumption using auxtrace_mmap__write_tail().
+ *
* Return: %0 on success, negative error code otherwise.
*/
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
- bool overwrite)
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite, unsigned int auxtrace_pages,
+ bool auxtrace_overwrite)
{
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
+ auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
+ auxtrace_pages, auxtrace_overwrite);
+
evlist__for_each(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
return perf_evlist__mmap_per_cpu(evlist, &mp);
}
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite)
+{
+ return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+}
+
int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
{
evlist->threads = thread_map__new_str(target->pid, target->tid,
#ifndef __PERF_EVLIST_H
#define __PERF_EVLIST_H 1
+#include <linux/atomic.h>
#include <linux/list.h>
#include <api/fd/array.h>
#include <stdio.h>
#include "event.h"
#include "evsel.h"
#include "util.h"
+#include "auxtrace.h"
#include <unistd.h>
struct pollfd;
struct perf_mmap {
void *base;
int mask;
- int refcnt;
+ atomic_t refcnt;
u64 prev;
+ struct auxtrace_mmap auxtrace_mmap;
char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
};
int nr_entries;
int nr_groups;
int nr_mmaps;
+ bool overwrite;
+ bool enabled;
size_t mmap_len;
int id_pos;
int is_pos;
int cork_fd;
pid_t pid;
} workload;
- bool overwrite;
struct fdarray pollfd;
struct perf_mmap *mmap;
struct thread_map *threads;
struct option;
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
int perf_evlist__parse_mmap_pages(const struct option *opt,
const char *str,
int unset);
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite, unsigned int auxtrace_pages,
+ bool auxtrace_overwrite);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
void perf_evlist__disable(struct perf_evlist *evlist);
void perf_evlist__enable(struct perf_evlist *evlist);
+void perf_evlist__toggle_enable(struct perf_evlist *evlist);
int perf_evlist__disable_event(struct perf_evlist *evlist,
struct perf_evsel *evsel);
#include "perf_regs.h"
#include "debug.h"
#include "trace-event.h"
+#include "stat.h"
static struct {
bool sample_id_all;
return 0;
}
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
-{
- memset(evsel->counts, 0, (sizeof(*evsel->counts) +
- (ncpus * sizeof(struct perf_counts_values))));
-}
-
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
-{
- evsel->counts = zalloc((sizeof(*evsel->counts) +
- (ncpus * sizeof(struct perf_counts_values))));
- return evsel->counts != NULL ? 0 : -ENOMEM;
-}
-
static void perf_evsel__free_fd(struct perf_evsel *evsel)
{
xyarray__delete(evsel->fd);
}
}
-void perf_evsel__free_counts(struct perf_evsel *evsel)
-{
- zfree(&evsel->counts);
-}
-
void perf_evsel__exit(struct perf_evsel *evsel)
{
assert(list_empty(&evsel->node));
#define BUF_SIZE 1024
-#define p_hex(val) snprintf(buf, BUF_SIZE, "%"PRIx64, (uint64_t)(val))
+#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val)
PRINT_ATTRf(sample_stack_user, p_unsigned);
PRINT_ATTRf(clockid, p_signed);
PRINT_ATTRf(sample_regs_intr, p_hex);
+ PRINT_ATTRf(aux_watermark, p_unsigned);
return ret;
}
case EMFILE:
return scnprintf(msg, size, "%s",
"Too many events are opened.\n"
- "Try again after reducing the number of events.");
+ "Probably the maximum number of open file descriptors has been reached.\n"
+ "Hint: Try again after reducing the number of events.\n"
+ "Hint: Try increasing the limit with 'ulimit -n <limit>'");
case ENODEV:
if (target->cpu_list)
return scnprintf(msg, size, "%s",
char *name;
double scale;
const char *unit;
- bool snapshot;
struct event_format *tp_format;
union {
void *priv;
unsigned int sample_size;
int id_pos;
int is_pos;
+ bool snapshot;
bool supported;
bool needs_swap;
bool no_aux_samples;
bool system_wide;
bool tracking;
bool per_pkg;
- unsigned long *per_pkg_mask;
/* parse modifier helper */
int exclude_GH;
int nr_members;
int sample_read;
+ unsigned long *per_pkg_mask;
struct perf_evsel *leader;
char *group_name;
};
int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__free_counts(struct perf_evsel *evsel);
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
return 0;
}
+static int write_auxtrace(int fd, struct perf_header *h,
+ struct perf_evlist *evlist __maybe_unused)
+{
+ struct perf_session *session;
+ int err;
+
+ session = container_of(h, struct perf_session, header);
+
+ err = auxtrace_index__write(fd, &session->auxtrace_index);
+ if (err < 0)
+ pr_err("Failed to write auxtrace index\n");
+ return err;
+}
+
static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
fprintf(fp, "# contains samples with branch stack\n");
}
+static void print_auxtrace(struct perf_header *ph __maybe_unused,
+ int fd __maybe_unused, FILE *fp)
+{
+ fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
+}
+
static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
FILE *fp)
{
struct perf_session *session)
{
int err = -1;
- struct dsos *dsos;
struct machine *machine;
- u16 misc;
+ u16 cpumode;
struct dso *dso;
enum dso_kernel_type dso_type;
if (!machine)
goto out;
- misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ cpumode = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- switch (misc) {
+ switch (cpumode) {
case PERF_RECORD_MISC_KERNEL:
dso_type = DSO_TYPE_KERNEL;
- dsos = &machine->kernel_dsos;
break;
case PERF_RECORD_MISC_GUEST_KERNEL:
dso_type = DSO_TYPE_GUEST_KERNEL;
- dsos = &machine->kernel_dsos;
break;
case PERF_RECORD_MISC_USER:
case PERF_RECORD_MISC_GUEST_USER:
dso_type = DSO_TYPE_USER;
- dsos = &machine->user_dsos;
break;
default:
goto out;
}
- dso = __dsos__findnew(dsos, filename);
+ dso = machine__findnew_dso(machine, filename);
if (dso != NULL) {
char sbuild_id[BUILD_ID_SIZE * 2 + 1];
dso__set_build_id(dso, &bev->build_id);
- if (!is_kernel_module(filename))
+ if (!is_kernel_module(filename, cpumode))
dso->kernel = dso_type;
build_id__sprintf(dso->build_id, sizeof(dso->build_id),
sbuild_id);
pr_debug("build id event received for %s: %s\n",
dso->long_name, sbuild_id);
+ dso__put(dso);
}
err = 0;
return ret;
}
+static int process_auxtrace(struct perf_file_section *section,
+ struct perf_header *ph, int fd,
+ void *data __maybe_unused)
+{
+ struct perf_session *session;
+ int err;
+
+ session = container_of(ph, struct perf_session, header);
+
+ err = auxtrace_index__process(fd, section->size, session,
+ ph->needs_swap);
+ if (err < 0)
+ pr_err("Failed to process auxtrace index\n");
+ return err;
+}
+
struct feature_ops {
int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
void (*print)(struct perf_header *h, int fd, FILE *fp);
FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings),
FEAT_OPP(HEADER_GROUP_DESC, group_desc),
+ FEAT_OPP(HEADER_AUXTRACE, auxtrace),
};
struct header_print_data {
HEADER_BRANCH_STACK,
HEADER_PMU_MAPPINGS,
HEADER_GROUP_DESC,
+ HEADER_AUXTRACE,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};
memset(&he->stat, 0, sizeof(he->stat));
}
- if (he->ms.map)
- he->ms.map->referenced = true;
+ map__get(he->ms.map);
if (he->branch_info) {
/*
*/
he->branch_info = malloc(sizeof(*he->branch_info));
if (he->branch_info == NULL) {
+ map__zput(he->ms.map);
free(he->stat_acc);
free(he);
return NULL;
memcpy(he->branch_info, template->branch_info,
sizeof(*he->branch_info));
- if (he->branch_info->from.map)
- he->branch_info->from.map->referenced = true;
- if (he->branch_info->to.map)
- he->branch_info->to.map->referenced = true;
+ map__get(he->branch_info->from.map);
+ map__get(he->branch_info->to.map);
}
if (he->mem_info) {
- if (he->mem_info->iaddr.map)
- he->mem_info->iaddr.map->referenced = true;
- if (he->mem_info->daddr.map)
- he->mem_info->daddr.map->referenced = true;
+ map__get(he->mem_info->iaddr.map);
+ map__get(he->mem_info->daddr.map);
}
if (symbol_conf.use_callchain)
return 0;
}
-static struct hist_entry *add_hist_entry(struct hists *hists,
- struct hist_entry *entry,
- struct addr_location *al,
- bool sample_self)
+static struct hist_entry *hists__findnew_entry(struct hists *hists,
+ struct hist_entry *entry,
+ struct addr_location *al,
+ bool sample_self)
{
struct rb_node **p;
struct rb_node *parent = NULL;
* the history counter to increment.
*/
if (he->ms.map != entry->ms.map) {
- he->ms.map = entry->ms.map;
- if (he->ms.map)
- he->ms.map->referenced = true;
+ map__put(he->ms.map);
+ he->ms.map = map__get(entry->ms.map);
}
goto out;
}
.transaction = transaction,
};
- return add_hist_entry(hists, &entry, al, sample_self);
+ return hists__findnew_entry(hists, &entry, al, sample_self);
}
static int
out:
/*
- * We don't need to free iter->priv (mem_info) here since
- * the mem info was either already freed in add_hist_entry() or
- * passed to a new hist entry by hist_entry__new().
+ * We don't need to free iter->priv (mem_info) here since the mem info
+ * was either already freed in hists__findnew_entry() or passed to a
+ * new hist entry by hist_entry__new().
*/
iter->priv = NULL;
};
int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
- struct perf_evsel *evsel, struct perf_sample *sample,
int max_stack_depth, void *arg)
{
int err, err2;
- err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
- max_stack_depth);
+ err = sample__resolve_callchain(iter->sample, &iter->parent,
+ iter->evsel, al, max_stack_depth);
if (err)
return err;
- iter->evsel = evsel;
- iter->sample = sample;
-
err = iter->ops->prepare_entry(iter, al);
if (err)
goto out;
void hist_entry__delete(struct hist_entry *he)
{
thread__zput(he->thread);
- zfree(&he->branch_info);
- zfree(&he->mem_info);
+ map__zput(he->ms.map);
+
+ if (he->branch_info) {
+ map__zput(he->branch_info->from.map);
+ map__zput(he->branch_info->to.map);
+ zfree(&he->branch_info);
+ }
+
+ if (he->mem_info) {
+ map__zput(he->mem_info->iaddr.map);
+ map__zput(he->mem_info->daddr.map);
+ zfree(&he->mem_info);
+ }
+
zfree(&he->stat_acc);
free_srcline(he->srcline);
free_callchain(he->callchain);
return;
/* force fold unfiltered entry for simplicity */
- h->ms.unfolded = false;
+ h->unfolded = false;
h->row_offset = 0;
h->nr_rows = 0;
u64 weight, u64 transaction,
bool sample_self);
int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
- struct perf_evsel *evsel, struct perf_sample *sample,
int max_stack_depth, void *arg);
int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
+++ /dev/null
-#ifndef PERF_LINUX_KERNEL_H_
-#define PERF_LINUX_KERNEL_H_
-
-#include <stdarg.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <assert.h>
-
-#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
-
-#define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
-#define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask))
-
-#ifndef offsetof
-#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
-#endif
-
-#ifndef container_of
-/**
- * container_of - cast a member of a structure out to the containing structure
- * @ptr: the pointer to the member.
- * @type: the type of the container struct this is embedded in.
- * @member: the name of the member within the struct.
- *
- */
-#define container_of(ptr, type, member) ({ \
- const typeof(((type *)0)->member) * __mptr = (ptr); \
- (type *)((char *)__mptr - offsetof(type, member)); })
-#endif
-
-#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
-
-#ifndef max
-#define max(x, y) ({ \
- typeof(x) _max1 = (x); \
- typeof(y) _max2 = (y); \
- (void) (&_max1 == &_max2); \
- _max1 > _max2 ? _max1 : _max2; })
-#endif
-
-#ifndef min
-#define min(x, y) ({ \
- typeof(x) _min1 = (x); \
- typeof(y) _min2 = (y); \
- (void) (&_min1 == &_min2); \
- _min1 < _min2 ? _min1 : _min2; })
-#endif
-
-#ifndef roundup
-#define roundup(x, y) ( \
-{ \
- const typeof(y) __y = y; \
- (((x) + (__y - 1)) / __y) * __y; \
-} \
-)
-#endif
-
-#ifndef BUG_ON
-#ifdef NDEBUG
-#define BUG_ON(cond) do { if (cond) {} } while (0)
-#else
-#define BUG_ON(cond) assert(!(cond))
-#endif
-#endif
-
-/*
- * Both need more care to handle endianness
- * (Don't use bitmap_copy_le() for now)
- */
-#define cpu_to_le64(x) (x)
-#define cpu_to_le32(x) (x)
-
-static inline int
-vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
-{
- int i;
- ssize_t ssize = size;
-
- i = vsnprintf(buf, size, fmt, args);
-
- return (i >= ssize) ? (ssize - 1) : i;
-}
-
-static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
-{
- va_list args;
- ssize_t ssize = size;
- int i;
-
- va_start(args, fmt);
- i = vsnprintf(buf, size, fmt, args);
- va_end(args);
-
- return (i >= ssize) ? (ssize - 1) : i;
-}
-
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x, y) ((__typeof__(x))((y)-1))
-#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
-#define round_down(x, y) ((x) & ~__round_mask(x, y))
-
-#endif
+++ /dev/null
-#include <linux/kernel.h>
-#include <linux/types.h>
-
-#include "../../../../include/linux/list.h"
-
-#ifndef PERF_LIST_H
-#define PERF_LIST_H
-/**
- * list_del_range - deletes range of entries from list.
- * @begin: first element in the range to delete from the list.
- * @end: last element in the range to delete from the list.
- * Note: list_empty on the range of entries does not return true after this,
- * the entries is in an undefined state.
- */
-static inline void list_del_range(struct list_head *begin,
- struct list_head *end)
-{
- begin->prev->next = end->next;
- end->next->prev = begin->prev;
-}
-
-/**
- * list_for_each_from - iterate over a list from one of its nodes
- * @pos: the &struct list_head to use as a loop cursor, from where to start
- * @head: the head for your list.
- */
-#define list_for_each_from(pos, head) \
- for (; pos != (head); pos = pos->next)
-#endif
+++ /dev/null
-#include "../../../../include/linux/poison.h"
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
#include <stdbool.h>
#include "../../../../include/linux/rbtree.h"
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+ rb_erase(n, root);
+ RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
#include "unwind.h"
#include "linux/hash.h"
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
+
static void dsos__init(struct dsos *dsos)
{
INIT_LIST_HEAD(&dsos->head);
dsos->root = RB_ROOT;
+ pthread_rwlock_init(&dsos->lock, NULL);
}
int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
{
map_groups__init(&machine->kmaps, machine);
RB_CLEAR_NODE(&machine->rb_node);
- dsos__init(&machine->user_dsos);
- dsos__init(&machine->kernel_dsos);
+ dsos__init(&machine->dsos);
machine->threads = RB_ROOT;
+ pthread_rwlock_init(&machine->threads_lock, NULL);
INIT_LIST_HEAD(&machine->dead_threads);
machine->last_match = NULL;
snprintf(comm, sizeof(comm), "[guest/%d]", pid);
thread__set_comm(thread, comm, 0);
+ thread__put(thread);
}
machine->current_tid = NULL;
return NULL;
}
-static void dsos__delete(struct dsos *dsos)
+static void dsos__purge(struct dsos *dsos)
{
struct dso *pos, *n;
+ pthread_rwlock_wrlock(&dsos->lock);
+
list_for_each_entry_safe(pos, n, &dsos->head, node) {
RB_CLEAR_NODE(&pos->rb_node);
- list_del(&pos->node);
- dso__delete(pos);
+ list_del_init(&pos->node);
+ dso__put(pos);
}
+
+ pthread_rwlock_unlock(&dsos->lock);
+}
+
+static void dsos__exit(struct dsos *dsos)
+{
+ dsos__purge(dsos);
+ pthread_rwlock_destroy(&dsos->lock);
}
void machine__delete_threads(struct machine *machine)
{
- struct rb_node *nd = rb_first(&machine->threads);
+ struct rb_node *nd;
+ pthread_rwlock_wrlock(&machine->threads_lock);
+ nd = rb_first(&machine->threads);
while (nd) {
struct thread *t = rb_entry(nd, struct thread, rb_node);
nd = rb_next(nd);
- machine__remove_thread(machine, t);
+ __machine__remove_thread(machine, t, false);
}
+ pthread_rwlock_unlock(&machine->threads_lock);
}
void machine__exit(struct machine *machine)
{
map_groups__exit(&machine->kmaps);
- dsos__delete(&machine->user_dsos);
- dsos__delete(&machine->kernel_dsos);
- vdso__exit(machine);
+ dsos__exit(&machine->dsos);
+ machine__exit_vdso(machine);
zfree(&machine->root_dir);
zfree(&machine->current_tid);
+ pthread_rwlock_destroy(&machine->threads_lock);
}
void machine__delete(struct machine *machine)
if (th->pid_ == th->tid)
return;
- leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+ leader = __machine__findnew_thread(machine, th->pid_, th->pid_);
if (!leader)
goto out_err;
if (!map_groups__empty(th->mg))
pr_err("Discarding thread maps for %d:%d\n",
th->pid_, th->tid);
- map_groups__delete(th->mg);
+ map_groups__put(th->mg);
}
th->mg = map_groups__get(leader->mg);
pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
}
-static struct thread *__machine__findnew_thread(struct machine *machine,
- pid_t pid, pid_t tid,
- bool create)
+static struct thread *____machine__findnew_thread(struct machine *machine,
+ pid_t pid, pid_t tid,
+ bool create)
{
struct rb_node **p = &machine->threads.rb_node;
struct rb_node *parent = NULL;
return th;
}
- thread__zput(machine->last_match);
+ machine->last_match = NULL;
}
while (*p != NULL) {
th = rb_entry(parent, struct thread, rb_node);
if (th->tid == tid) {
- machine->last_match = thread__get(th);
+ machine->last_match = th;
machine__update_thread_pid(machine, th, pid);
return th;
}
* leader and that would screwed the rb tree.
*/
if (thread__init_map_groups(th, machine)) {
- rb_erase(&th->rb_node, &machine->threads);
+ rb_erase_init(&th->rb_node, &machine->threads);
+ RB_CLEAR_NODE(&th->rb_node);
thread__delete(th);
return NULL;
}
* It is now in the rbtree, get a ref
*/
thread__get(th);
- machine->last_match = thread__get(th);
+ machine->last_match = th;
}
return th;
}
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
+{
+ return ____machine__findnew_thread(machine, pid, tid, true);
+}
+
struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
pid_t tid)
{
- return __machine__findnew_thread(machine, pid, tid, true);
+ struct thread *th;
+
+ pthread_rwlock_wrlock(&machine->threads_lock);
+ th = thread__get(__machine__findnew_thread(machine, pid, tid));
+ pthread_rwlock_unlock(&machine->threads_lock);
+ return th;
}
struct thread *machine__find_thread(struct machine *machine, pid_t pid,
pid_t tid)
{
- return __machine__findnew_thread(machine, pid, tid, false);
+ struct thread *th;
+ pthread_rwlock_rdlock(&machine->threads_lock);
+ th = thread__get(____machine__findnew_thread(machine, pid, tid, false));
+ pthread_rwlock_unlock(&machine->threads_lock);
+ return th;
}
struct comm *machine__thread_exec_comm(struct machine *machine,
event->comm.pid,
event->comm.tid);
bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+ int err = 0;
if (exec)
machine->comm_exec = true;
if (thread == NULL ||
__thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
- return -1;
+ err = -1;
}
- return 0;
+ thread__put(thread);
+
+ return err;
}
int machine__process_lost_event(struct machine *machine __maybe_unused,
return 0;
}
-static struct dso*
-machine__module_dso(struct machine *machine, struct kmod_path *m,
- const char *filename)
+int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
+ union perf_event *event, struct perf_sample *sample)
+{
+ dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n",
+ sample->id, event->lost_samples.lost);
+ return 0;
+}
+
+static struct dso *machine__findnew_module_dso(struct machine *machine,
+ struct kmod_path *m,
+ const char *filename)
{
struct dso *dso;
- dso = dsos__find(&machine->kernel_dsos, m->name, true);
+ pthread_rwlock_wrlock(&machine->dsos.lock);
+
+ dso = __dsos__find(&machine->dsos, m->name, true);
if (!dso) {
- dso = dsos__addnew(&machine->kernel_dsos, m->name);
+ dso = __dsos__addnew(&machine->dsos, m->name);
if (dso == NULL)
- return NULL;
+ goto out_unlock;
if (machine__is_host(machine))
dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
dso__set_long_name(dso, strdup(filename), true);
}
+ dso__get(dso);
+out_unlock:
+ pthread_rwlock_unlock(&machine->dsos.lock);
return dso;
}
-struct map *machine__new_module(struct machine *machine, u64 start,
- const char *filename)
+int machine__process_aux_event(struct machine *machine __maybe_unused,
+ union perf_event *event)
+{
+ if (dump_trace)
+ perf_event__fprintf_aux(event, stdout);
+ return 0;
+}
+
+int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
+ union perf_event *event)
+{
+ if (dump_trace)
+ perf_event__fprintf_itrace_start(event, stdout);
+ return 0;
+}
+
+struct map *machine__findnew_module_map(struct machine *machine, u64 start,
+ const char *filename)
{
struct map *map = NULL;
struct dso *dso;
if (map)
goto out;
- dso = machine__module_dso(machine, &m, filename);
+ dso = machine__findnew_module_dso(machine, &m, filename);
if (dso == NULL)
goto out;
size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
{
struct rb_node *nd;
- size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) +
- __dsos__fprintf(&machines->host.user_dsos.head, fp);
+ size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node);
- ret += __dsos__fprintf(&pos->kernel_dsos.head, fp);
- ret += __dsos__fprintf(&pos->user_dsos.head, fp);
+ ret += __dsos__fprintf(&pos->dsos.head, fp);
}
return ret;
size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
bool (skip)(struct dso *dso, int parm), int parm)
{
- return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) +
- __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm);
+ return __dsos__fprintf_buildid(&m->dsos.head, fp, skip, parm);
}
size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
size_t ret = 0;
struct rb_node *nd;
+ pthread_rwlock_rdlock(&machine->threads_lock);
+
for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
struct thread *pos = rb_entry(nd, struct thread, rb_node);
ret += thread__fprintf(pos, fp);
}
+ pthread_rwlock_unlock(&machine->threads_lock);
+
return ret;
}
if (!vmlinux_name)
vmlinux_name = "[kernel.kallsyms]";
- kernel = dso__kernel_findnew(machine, vmlinux_name,
- "[kernel]",
- DSO_TYPE_KERNEL);
+ kernel = machine__findnew_kernel(machine, vmlinux_name,
+ "[kernel]", DSO_TYPE_KERNEL);
} else {
char bf[PATH_MAX];
vmlinux_name = machine__mmap_name(machine, bf,
sizeof(bf));
- kernel = dso__kernel_findnew(machine, vmlinux_name,
- "[guest.kernel]",
- DSO_TYPE_GUEST_KERNEL);
+ kernel = machine__findnew_kernel(machine, vmlinux_name,
+ "[guest.kernel]",
+ DSO_TYPE_GUEST_KERNEL);
}
if (kernel != NULL && (!kernel->has_build_id))
kmap->ref_reloc_sym = NULL;
}
- map__delete(machine->vmlinux_maps[type]);
machine->vmlinux_maps[type] = NULL;
}
}
struct machine *machine = arg;
struct map *map;
- map = machine__new_module(machine, start, name);
+ map = machine__findnew_module_map(machine, start, name);
if (map == NULL)
return -1;
{
struct dso *dso;
- list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
+ list_for_each_entry(dso, &machine->dsos.head, node) {
if (dso__is_kcore(dso))
return true;
}
strlen(kmmap_prefix) - 1) == 0;
if (event->mmap.filename[0] == '/' ||
(!is_kernel_mmap && event->mmap.filename[0] == '[')) {
- map = machine__new_module(machine, event->mmap.start,
- event->mmap.filename);
+ map = machine__findnew_module_map(machine, event->mmap.start,
+ event->mmap.filename);
if (map == NULL)
goto out_problem;
struct dso *kernel = NULL;
struct dso *dso;
- list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
- if (is_kernel_module(dso->long_name))
+ pthread_rwlock_rdlock(&machine->dsos.lock);
+
+ list_for_each_entry(dso, &machine->dsos.head, node) {
+
+ /*
+ * The cpumode passed to is_kernel_module is not the
+ * cpumode of *this* event. If we insist on passing
+ * correct cpumode to is_kernel_module, we should
+ * record the cpumode when we adding this dso to the
+ * linked list.
+ *
+ * However we don't really need passing correct
+ * cpumode. We know the correct cpumode must be kernel
+ * mode (if not, we should not link it onto kernel_dsos
+ * list).
+ *
+ * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
+ * is_kernel_module() treats it as a kernel cpumode.
+ */
+
+ if (!dso->kernel ||
+ is_kernel_module(dso->long_name,
+ PERF_RECORD_MISC_CPUMODE_UNKNOWN))
continue;
+
kernel = dso;
break;
}
+ pthread_rwlock_unlock(&machine->dsos.lock);
+
if (kernel == NULL)
- kernel = __dsos__findnew(&machine->kernel_dsos,
- kmmap_prefix);
+ kernel = machine__findnew_dso(machine, kmmap_prefix);
if (kernel == NULL)
goto out_problem;
kernel->kernel = kernel_type;
- if (__machine__create_kernel_maps(machine, kernel) < 0)
+ if (__machine__create_kernel_maps(machine, kernel) < 0) {
+ dso__put(kernel);
goto out_problem;
+ }
if (strstr(kernel->long_name, "vmlinux"))
dso__set_short_name(kernel, "[kernel.vmlinux]", false);
event->mmap2.filename, type, thread);
if (map == NULL)
- goto out_problem;
+ goto out_problem_map;
thread__insert_map(thread, map);
+ thread__put(thread);
+ map__put(map);
return 0;
+out_problem_map:
+ thread__put(thread);
out_problem:
dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
return 0;
type, thread);
if (map == NULL)
- goto out_problem;
+ goto out_problem_map;
thread__insert_map(thread, map);
+ thread__put(thread);
+ map__put(map);
return 0;
+out_problem_map:
+ thread__put(thread);
out_problem:
dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
return 0;
}
-void machine__remove_thread(struct machine *machine, struct thread *th)
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
{
if (machine->last_match == th)
- thread__zput(machine->last_match);
+ machine->last_match = NULL;
- rb_erase(&th->rb_node, &machine->threads);
+ BUG_ON(atomic_read(&th->refcnt) == 0);
+ if (lock)
+ pthread_rwlock_wrlock(&machine->threads_lock);
+ rb_erase_init(&th->rb_node, &machine->threads);
+ RB_CLEAR_NODE(&th->rb_node);
/*
* Move it first to the dead_threads list, then drop the reference,
* if this is the last reference, then the thread__delete destructor
* will be called and we will remove it from the dead_threads list.
*/
list_add_tail(&th->node, &machine->dead_threads);
+ if (lock)
+ pthread_rwlock_unlock(&machine->threads_lock);
thread__put(th);
}
+void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+ return __machine__remove_thread(machine, th, true);
+}
+
int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
{
struct thread *parent = machine__findnew_thread(machine,
event->fork.ppid,
event->fork.ptid);
+ int err = 0;
/* if a thread currently exists for the thread id remove it */
- if (thread != NULL)
+ if (thread != NULL) {
machine__remove_thread(machine, thread);
+ thread__put(thread);
+ }
thread = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
if (thread == NULL || parent == NULL ||
thread__fork(thread, parent, sample->time) < 0) {
dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
- return -1;
+ err = -1;
}
+ thread__put(thread);
+ thread__put(parent);
- return 0;
+ return err;
}
int machine__process_exit_event(struct machine *machine, union perf_event *event,
if (dump_trace)
perf_event__fprintf_task(event, stdout);
- if (thread != NULL)
+ if (thread != NULL) {
thread__exited(thread);
+ thread__put(thread);
+ }
return 0;
}
ret = machine__process_exit_event(machine, event, sample); break;
case PERF_RECORD_LOST:
ret = machine__process_lost_event(machine, event, sample); break;
+ case PERF_RECORD_AUX:
+ ret = machine__process_aux_event(machine, event); break;
+ case PERF_RECORD_ITRACE_START:
+ ret = machine__process_itrace_start_event(machine, event);
+ case PERF_RECORD_LOST_SAMPLES:
+ ret = machine__process_lost_samples_event(machine, event, sample); break;
+ break;
default:
ret = -1;
break;
return rc;
}
+int machines__for_each_thread(struct machines *machines,
+ int (*fn)(struct thread *thread, void *p),
+ void *priv)
+{
+ struct rb_node *nd;
+ int rc = 0;
+
+ rc = machine__for_each_thread(&machines->host, fn, priv);
+ if (rc != 0)
+ return rc;
+
+ for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+ struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+ rc = machine__for_each_thread(machine, fn, priv);
+ if (rc != 0)
+ return rc;
+ }
+ return rc;
+}
+
int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
struct target *target, struct thread_map *threads,
- perf_event__handler_t process, bool data_mmap)
+ perf_event__handler_t process, bool data_mmap,
+ unsigned int proc_map_timeout)
{
if (target__has_task(target))
- return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+ return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
else if (target__has_cpu(target))
- return perf_event__synthesize_threads(tool, process, machine, data_mmap);
+ return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout);
/* command specified */
return 0;
}
return -ENOMEM;
thread->cpu = cpu;
+ thread__put(thread);
return 0;
}
}
return err;
}
+
+struct dso *machine__findnew_dso(struct machine *machine, const char *filename)
+{
+ return dsos__findnew(&machine->dsos, filename);
+}
bool comm_exec;
char *root_dir;
struct rb_root threads;
+ pthread_rwlock_t threads_lock;
struct list_head dead_threads;
struct thread *last_match;
struct vdso_info *vdso_info;
- struct dsos user_dsos;
- struct dsos kernel_dsos;
+ struct dsos dsos;
struct map_groups kmaps;
struct map *vmlinux_maps[MAP__NR_TYPES];
u64 kernel_start;
struct perf_sample *sample);
int machine__process_lost_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
+int machine__process_lost_samples_event(struct machine *machine, union perf_event *event,
+ struct perf_sample *sample);
+int machine__process_aux_event(struct machine *machine,
+ union perf_event *event);
+int machine__process_itrace_start_event(struct machine *machine,
+ union perf_event *event);
int machine__process_mmap_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
return machine ? machine->pid == HOST_KERNEL_ID : false;
}
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
- pid_t tid);
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
+
+struct dso *machine__findnew_dso(struct machine *machine, const char *filename);
size_t machine__fprintf(struct machine *machine, FILE *fp);
filter);
}
-struct map *machine__new_module(struct machine *machine, u64 start,
- const char *filename);
+struct map *machine__findnew_module_map(struct machine *machine, u64 start,
+ const char *filename);
int machine__load_kallsyms(struct machine *machine, const char *filename,
enum map_type type, symbol_filter_t filter);
int machine__for_each_thread(struct machine *machine,
int (*fn)(struct thread *thread, void *p),
void *priv);
+int machines__for_each_thread(struct machines *machines,
+ int (*fn)(struct thread *thread, void *p),
+ void *priv);
int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
struct target *target, struct thread_map *threads,
- perf_event__handler_t process, bool data_mmap);
+ perf_event__handler_t process, bool data_mmap,
+ unsigned int proc_map_timeout);
static inline
int machine__synthesize_threads(struct machine *machine, struct target *target,
- struct thread_map *threads, bool data_mmap)
+ struct thread_map *threads, bool data_mmap,
+ unsigned int proc_map_timeout)
{
return __machine__synthesize_threads(machine, NULL, target, threads,
- perf_event__process, data_mmap);
+ perf_event__process, data_mmap,
+ proc_map_timeout);
}
pid_t machine__get_current_tid(struct machine *machine, int cpu);
#include "machine.h"
#include <linux/string.h>
+static void __maps__insert(struct maps *maps, struct map *map);
+
const char *map_type__name[MAP__NR_TYPES] = {
[MAP__FUNCTION] = "Functions",
[MAP__VARIABLE] = "Variables",
map->end = end;
map->pgoff = pgoff;
map->reloc = 0;
- map->dso = dso;
+ map->dso = dso__get(dso);
map->map_ip = map__map_ip;
map->unmap_ip = map__unmap_ip;
RB_CLEAR_NODE(&map->rb_node);
map->groups = NULL;
- map->referenced = false;
map->erange_warned = false;
+ atomic_set(&map->refcnt, 1);
}
struct map *map__new(struct machine *machine, u64 start, u64 len,
if (vdso) {
pgoff = 0;
- dso = vdso__dso_findnew(machine, thread);
+ dso = machine__findnew_vdso(machine, thread);
} else
- dso = __dsos__findnew(&machine->user_dsos, filename);
+ dso = machine__findnew_dso(machine, filename);
if (dso == NULL)
goto out_delete;
if (type != MAP__FUNCTION)
dso__set_loaded(dso, map->type);
}
+ dso__put(dso);
}
return map;
out_delete:
return map;
}
+static void map__exit(struct map *map)
+{
+ BUG_ON(!RB_EMPTY_NODE(&map->rb_node));
+ dso__zput(map->dso);
+}
+
void map__delete(struct map *map)
{
+ map__exit(map);
free(map);
}
+void map__put(struct map *map)
+{
+ if (map && atomic_dec_and_test(&map->refcnt))
+ map__delete(map);
+}
+
void map__fixup_start(struct map *map)
{
struct rb_root *symbols = &map->dso->symbols[map->type];
return 0;
}
+int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+ return strcmp(namea, nameb);
+}
+
struct symbol *map__find_symbol(struct map *map, u64 addr,
symbol_filter_t filter)
{
return ip + map->reloc;
}
+static void maps__init(struct maps *maps)
+{
+ maps->entries = RB_ROOT;
+ pthread_rwlock_init(&maps->lock, NULL);
+}
+
void map_groups__init(struct map_groups *mg, struct machine *machine)
{
int i;
for (i = 0; i < MAP__NR_TYPES; ++i) {
- mg->maps[i] = RB_ROOT;
- INIT_LIST_HEAD(&mg->removed_maps[i]);
+ maps__init(&mg->maps[i]);
}
mg->machine = machine;
- mg->refcnt = 1;
+ atomic_set(&mg->refcnt, 1);
}
-static void maps__delete(struct rb_root *maps)
+static void __maps__purge(struct maps *maps)
{
- struct rb_node *next = rb_first(maps);
+ struct rb_root *root = &maps->entries;
+ struct rb_node *next = rb_first(root);
while (next) {
struct map *pos = rb_entry(next, struct map, rb_node);
next = rb_next(&pos->rb_node);
- rb_erase(&pos->rb_node, maps);
- map__delete(pos);
+ rb_erase_init(&pos->rb_node, root);
+ map__put(pos);
}
}
-static void maps__delete_removed(struct list_head *maps)
+static void maps__exit(struct maps *maps)
{
- struct map *pos, *n;
-
- list_for_each_entry_safe(pos, n, maps, node) {
- list_del(&pos->node);
- map__delete(pos);
- }
+ pthread_rwlock_wrlock(&maps->lock);
+ __maps__purge(maps);
+ pthread_rwlock_unlock(&maps->lock);
}
void map_groups__exit(struct map_groups *mg)
{
int i;
- for (i = 0; i < MAP__NR_TYPES; ++i) {
- maps__delete(&mg->maps[i]);
- maps__delete_removed(&mg->removed_maps[i]);
- }
+ for (i = 0; i < MAP__NR_TYPES; ++i)
+ maps__exit(&mg->maps[i]);
}
bool map_groups__empty(struct map_groups *mg)
for (i = 0; i < MAP__NR_TYPES; ++i) {
if (maps__first(&mg->maps[i]))
return false;
- if (!list_empty(&mg->removed_maps[i]))
- return false;
}
return true;
void map_groups__put(struct map_groups *mg)
{
- if (--mg->refcnt == 0)
+ if (mg && atomic_dec_and_test(&mg->refcnt))
map_groups__delete(mg);
}
-void map_groups__flush(struct map_groups *mg)
-{
- int type;
-
- for (type = 0; type < MAP__NR_TYPES; type++) {
- struct rb_root *root = &mg->maps[type];
- struct rb_node *next = rb_first(root);
-
- while (next) {
- struct map *pos = rb_entry(next, struct map, rb_node);
- next = rb_next(&pos->rb_node);
- rb_erase(&pos->rb_node, root);
- /*
- * We may have references to this map, for
- * instance in some hist_entry instances, so
- * just move them to a separate list.
- */
- list_add_tail(&pos->node, &mg->removed_maps[pos->type]);
- }
- }
-}
-
struct symbol *map_groups__find_symbol(struct map_groups *mg,
enum map_type type, u64 addr,
struct map **mapp,
struct map **mapp,
symbol_filter_t filter)
{
+ struct maps *maps = &mg->maps[type];
+ struct symbol *sym;
struct rb_node *nd;
- for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
+ pthread_rwlock_rdlock(&maps->lock);
+
+ for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
struct map *pos = rb_entry(nd, struct map, rb_node);
- struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
+
+ sym = map__find_symbol_by_name(pos, name, filter);
if (sym == NULL)
continue;
if (mapp != NULL)
*mapp = pos;
- return sym;
+ goto out;
}
- return NULL;
+ sym = NULL;
+out:
+ pthread_rwlock_unlock(&maps->lock);
+ return sym;
}
int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
return ams->sym ? 0 : -1;
}
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
- FILE *fp)
+static size_t maps__fprintf(struct maps *maps, FILE *fp)
{
- size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+ size_t printed = 0;
struct rb_node *nd;
- for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
+ pthread_rwlock_rdlock(&maps->lock);
+
+ for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
struct map *pos = rb_entry(nd, struct map, rb_node);
printed += fprintf(fp, "Map:");
printed += map__fprintf(pos, fp);
if (verbose > 2) {
- printed += dso__fprintf(pos->dso, type, fp);
+ printed += dso__fprintf(pos->dso, pos->type, fp);
printed += fprintf(fp, "--\n");
}
}
- return printed;
-}
+ pthread_rwlock_unlock(&maps->lock);
-static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp)
-{
- size_t printed = 0, i;
- for (i = 0; i < MAP__NR_TYPES; ++i)
- printed += __map_groups__fprintf_maps(mg, i, fp);
return printed;
}
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
- enum map_type type, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+ FILE *fp)
{
- struct map *pos;
- size_t printed = 0;
-
- list_for_each_entry(pos, &mg->removed_maps[type], node) {
- printed += fprintf(fp, "Map:");
- printed += map__fprintf(pos, fp);
- if (verbose > 1) {
- printed += dso__fprintf(pos->dso, type, fp);
- printed += fprintf(fp, "--\n");
- }
- }
- return printed;
+ size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+ return printed += maps__fprintf(&mg->maps[type], fp);
}
-static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
- FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
{
size_t printed = 0, i;
for (i = 0; i < MAP__NR_TYPES; ++i)
- printed += __map_groups__fprintf_removed_maps(mg, i, fp);
+ printed += __map_groups__fprintf_maps(mg, i, fp);
return printed;
}
-size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
+static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
{
- size_t printed = map_groups__fprintf_maps(mg, fp);
- printed += fprintf(fp, "Removed maps:\n");
- return printed + map_groups__fprintf_removed_maps(mg, fp);
-}
-
-int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
- FILE *fp)
-{
- struct rb_root *root = &mg->maps[map->type];
- struct rb_node *next = rb_first(root);
+ struct rb_root *root;
+ struct rb_node *next;
int err = 0;
+ pthread_rwlock_wrlock(&maps->lock);
+
+ root = &maps->entries;
+ next = rb_first(root);
+
while (next) {
struct map *pos = rb_entry(next, struct map, rb_node);
next = rb_next(&pos->rb_node);
map__fprintf(pos, fp);
}
- rb_erase(&pos->rb_node, root);
+ rb_erase_init(&pos->rb_node, root);
/*
* Now check if we need to create new maps for areas not
* overlapped by the new map:
if (before == NULL) {
err = -ENOMEM;
- goto move_map;
+ goto put_map;
}
before->end = map->start;
- map_groups__insert(mg, before);
+ __maps__insert(maps, before);
if (verbose >= 2)
map__fprintf(before, fp);
}
if (after == NULL) {
err = -ENOMEM;
- goto move_map;
+ goto put_map;
}
after->start = map->end;
- map_groups__insert(mg, after);
+ __maps__insert(maps, after);
if (verbose >= 2)
map__fprintf(after, fp);
}
-move_map:
- /*
- * If we have references, just move them to a separate list.
- */
- if (pos->referenced)
- list_add_tail(&pos->node, &mg->removed_maps[map->type]);
- else
- map__delete(pos);
+put_map:
+ map__put(pos);
if (err)
- return err;
+ goto out;
}
- return 0;
+ err = 0;
+out:
+ pthread_rwlock_unlock(&maps->lock);
+ return err;
+}
+
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
+ FILE *fp)
+{
+ return maps__fixup_overlappings(&mg->maps[map->type], map, fp);
}
/*
int map_groups__clone(struct map_groups *mg,
struct map_groups *parent, enum map_type type)
{
- struct rb_node *nd;
- for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
- struct map *map = rb_entry(nd, struct map, rb_node);
+ int err = -ENOMEM;
+ struct map *map;
+ struct maps *maps = &parent->maps[type];
+
+ pthread_rwlock_rdlock(&maps->lock);
+
+ for (map = maps__first(maps); map; map = map__next(map)) {
struct map *new = map__clone(map);
if (new == NULL)
- return -ENOMEM;
+ goto out_unlock;
map_groups__insert(mg, new);
}
- return 0;
+
+ err = 0;
+out_unlock:
+ pthread_rwlock_unlock(&maps->lock);
+ return err;
}
-void maps__insert(struct rb_root *maps, struct map *map)
+static void __maps__insert(struct maps *maps, struct map *map)
{
- struct rb_node **p = &maps->rb_node;
+ struct rb_node **p = &maps->entries.rb_node;
struct rb_node *parent = NULL;
const u64 ip = map->start;
struct map *m;
}
rb_link_node(&map->rb_node, parent, p);
- rb_insert_color(&map->rb_node, maps);
+ rb_insert_color(&map->rb_node, &maps->entries);
+ map__get(map);
}
-void maps__remove(struct rb_root *maps, struct map *map)
+void maps__insert(struct maps *maps, struct map *map)
{
- rb_erase(&map->rb_node, maps);
+ pthread_rwlock_wrlock(&maps->lock);
+ __maps__insert(maps, map);
+ pthread_rwlock_unlock(&maps->lock);
}
-struct map *maps__find(struct rb_root *maps, u64 ip)
+static void __maps__remove(struct maps *maps, struct map *map)
{
- struct rb_node **p = &maps->rb_node;
- struct rb_node *parent = NULL;
+ rb_erase_init(&map->rb_node, &maps->entries);
+ map__put(map);
+}
+
+void maps__remove(struct maps *maps, struct map *map)
+{
+ pthread_rwlock_wrlock(&maps->lock);
+ __maps__remove(maps, map);
+ pthread_rwlock_unlock(&maps->lock);
+}
+
+struct map *maps__find(struct maps *maps, u64 ip)
+{
+ struct rb_node **p, *parent = NULL;
struct map *m;
+ pthread_rwlock_rdlock(&maps->lock);
+
+ p = &maps->entries.rb_node;
while (*p != NULL) {
parent = *p;
m = rb_entry(parent, struct map, rb_node);
else if (ip >= m->end)
p = &(*p)->rb_right;
else
- return m;
+ goto out;
}
- return NULL;
+ m = NULL;
+out:
+ pthread_rwlock_unlock(&maps->lock);
+ return m;
}
-struct map *maps__first(struct rb_root *maps)
+struct map *maps__first(struct maps *maps)
{
- struct rb_node *first = rb_first(maps);
+ struct rb_node *first = rb_first(&maps->entries);
if (first)
return rb_entry(first, struct map, rb_node);
return NULL;
}
-struct map *maps__next(struct map *map)
+struct map *map__next(struct map *map)
{
struct rb_node *next = rb_next(&map->rb_node);
#ifndef __PERF_MAP_H
#define __PERF_MAP_H
+#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/list.h>
#include <linux/rbtree.h>
+#include <pthread.h>
#include <stdio.h>
#include <stdbool.h>
#include <linux/types.h>
u64 start;
u64 end;
u8 /* enum map_type */ type;
- bool referenced;
bool erange_warned;
u32 priv;
u32 prot;
struct dso *dso;
struct map_groups *groups;
+ atomic_t refcnt;
};
struct kmap {
struct map_groups *kmaps;
};
+struct maps {
+ struct rb_root entries;
+ pthread_rwlock_t lock;
+};
+
struct map_groups {
- struct rb_root maps[MAP__NR_TYPES];
- struct list_head removed_maps[MAP__NR_TYPES];
+ struct maps maps[MAP__NR_TYPES];
struct machine *machine;
- int refcnt;
+ atomic_t refcnt;
};
struct map_groups *map_groups__new(struct machine *machine);
static inline struct map_groups *map_groups__get(struct map_groups *mg)
{
- ++mg->refcnt;
+ if (mg)
+ atomic_inc(&mg->refcnt);
return mg;
}
*/
#define __map__for_each_symbol_by_name(map, sym_name, pos, filter) \
for (pos = map__find_symbol_by_name(map, sym_name, filter); \
- pos && strcmp(pos->name, sym_name) == 0; \
+ pos && arch__compare_symbol_names(pos->name, sym_name) == 0; \
pos = symbol__next_by_name(pos))
#define map__for_each_symbol_by_name(map, sym_name, pos) \
typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
+int arch__compare_symbol_names(const char *namea, const char *nameb);
void map__init(struct map *map, enum map_type type,
u64 start, u64 end, u64 pgoff, struct dso *dso);
struct map *map__new(struct machine *machine, u64 start, u64 len,
struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
void map__delete(struct map *map);
struct map *map__clone(struct map *map);
+
+static inline struct map *map__get(struct map *map)
+{
+ if (map)
+ atomic_inc(&map->refcnt);
+ return map;
+}
+
+void map__put(struct map *map);
+
+static inline void __map__zput(struct map **map)
+{
+ map__put(*map);
+ *map = NULL;
+}
+
+#define map__zput(map) __map__zput(&map)
+
int map__overlap(struct map *l, struct map *r);
size_t map__fprintf(struct map *map, FILE *fp);
size_t map__fprintf_dsoname(struct map *map, FILE *fp);
size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
FILE *fp);
-void maps__insert(struct rb_root *maps, struct map *map);
-void maps__remove(struct rb_root *maps, struct map *map);
-struct map *maps__find(struct rb_root *maps, u64 addr);
-struct map *maps__first(struct rb_root *maps);
-struct map *maps__next(struct map *map);
+void maps__insert(struct maps *maps, struct map *map);
+void maps__remove(struct maps *maps, struct map *map);
+struct map *maps__find(struct maps *maps, u64 addr);
+struct map *maps__first(struct maps *maps);
+struct map *map__next(struct map *map);
void map_groups__init(struct map_groups *mg, struct machine *machine);
void map_groups__exit(struct map_groups *mg);
int map_groups__clone(struct map_groups *mg,
static inline struct map *map_groups__next(struct map *map)
{
- return maps__next(map);
+ return map__next(map);
}
struct symbol *map_groups__find_symbol(struct map_groups *mg,
struct map *map_groups__find_by_name(struct map_groups *mg,
enum map_type type, const char *name);
-void map_groups__flush(struct map_groups *mg);
-
#endif /* __PERF_MAP_H */
if (!isatty(1))
return;
- if (!pager) {
- if (!pager_program)
- perf_config(perf_default_config, NULL);
- pager = pager_program;
- }
if (!pager)
pager = getenv("PAGER");
if (!(pager || access("/usr/bin/pager", X_OK)))
--- /dev/null
+#include "perf.h"
+#include "util/util.h"
+#include "util/debug.h"
+#include "util/parse-options.h"
+#include "util/parse-branch-options.h"
+
+#define BRANCH_OPT(n, m) \
+ { .name = n, .mode = (m) }
+
+#define BRANCH_END { .name = NULL }
+
+struct branch_mode {
+ const char *name;
+ int mode;
+};
+
+static const struct branch_mode branch_modes[] = {
+ BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
+ BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
+ BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
+ BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
+ BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
+ BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
+ BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+ BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
+ BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
+ BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
+ BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
+ BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
+ BRANCH_END
+};
+
+int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+#define ONLY_PLM \
+ (PERF_SAMPLE_BRANCH_USER |\
+ PERF_SAMPLE_BRANCH_KERNEL |\
+ PERF_SAMPLE_BRANCH_HV)
+
+ uint64_t *mode = (uint64_t *)opt->value;
+ const struct branch_mode *br;
+ char *s, *os = NULL, *p;
+ int ret = -1;
+
+ if (unset)
+ return 0;
+
+ /*
+ * cannot set it twice, -b + --branch-filter for instance
+ */
+ if (*mode)
+ return -1;
+
+ /* str may be NULL in case no arg is passed to -b */
+ if (str) {
+ /* because str is read-only */
+ s = os = strdup(str);
+ if (!s)
+ return -1;
+
+ for (;;) {
+ p = strchr(s, ',');
+ if (p)
+ *p = '\0';
+
+ for (br = branch_modes; br->name; br++) {
+ if (!strcasecmp(s, br->name))
+ break;
+ }
+ if (!br->name) {
+ ui__warning("unknown branch filter %s,"
+ " check man page\n", s);
+ goto error;
+ }
+
+ *mode |= br->mode;
+
+ if (!p)
+ break;
+
+ s = p + 1;
+ }
+ }
+ ret = 0;
+
+ /* default to any branch */
+ if ((*mode & ~ONLY_PLM) == 0) {
+ *mode = PERF_SAMPLE_BRANCH_ANY;
+ }
+error:
+ free(os);
+ return ret;
+}
--- /dev/null
+#ifndef _PERF_PARSE_BRANCH_OPTIONS_H
+#define _PERF_PARSE_BRANCH_OPTIONS_H 1
+struct option;
+int parse_branch_stack(const struct option *opt, const char *str, int unset);
+#endif /* _PERF_PARSE_BRANCH_OPTIONS_H */
#include "parse-events-flex.h"
#include "pmu.h"
#include "thread_map.h"
+#include "asm/bug.h"
#define MAX_NAME_LEN 100
return add_event(list, idx, &attr, NULL);
}
+static int check_type_val(struct parse_events_term *term,
+ struct parse_events_error *err,
+ int type)
+{
+ if (type == term->type_val)
+ return 0;
+
+ if (err) {
+ err->idx = term->err_val;
+ if (type == PARSE_EVENTS__TERM_TYPE_NUM)
+ err->str = strdup("expected numeric value");
+ else
+ err->str = strdup("expected string value");
+ }
+ return -EINVAL;
+}
+
static int config_term(struct perf_event_attr *attr,
- struct parse_events_term *term)
+ struct parse_events_term *term,
+ struct parse_events_error *err)
{
-#define CHECK_TYPE_VAL(type) \
-do { \
- if (PARSE_EVENTS__TERM_TYPE_ ## type != term->type_val) \
- return -EINVAL; \
+#define CHECK_TYPE_VAL(type) \
+do { \
+ if (check_type_val(term, err, PARSE_EVENTS__TERM_TYPE_ ## type)) \
+ return -EINVAL; \
} while (0)
switch (term->type_term) {
+ case PARSE_EVENTS__TERM_TYPE_USER:
+ /*
+ * Always succeed for sysfs terms, as we dont know
+ * at this point what type they need to have.
+ */
+ return 0;
case PARSE_EVENTS__TERM_TYPE_CONFIG:
CHECK_TYPE_VAL(NUM);
attr->config = term->val.num;
}
static int config_attr(struct perf_event_attr *attr,
- struct list_head *head, int fail)
+ struct list_head *head,
+ struct parse_events_error *err)
{
struct parse_events_term *term;
list_for_each_entry(term, head, list)
- if (config_term(attr, term) && fail)
+ if (config_term(attr, term, err))
return -EINVAL;
return 0;
}
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+ struct list_head *list,
u32 type, u64 config,
struct list_head *head_config)
{
attr.config = config;
if (head_config &&
- config_attr(&attr, head_config, 1))
+ config_attr(&attr, head_config, data->error))
return -EINVAL;
- return add_event(list, idx, &attr, NULL);
+ return add_event(list, &data->idx, &attr, NULL);
}
static int parse_events__is_name_term(struct parse_events_term *term)
return NULL;
}
-int parse_events_add_pmu(struct list_head *list, int *idx,
- char *name, struct list_head *head_config)
+int parse_events_add_pmu(struct parse_events_evlist *data,
+ struct list_head *list, char *name,
+ struct list_head *head_config)
{
struct perf_event_attr attr;
struct perf_pmu_info info;
if (!head_config) {
attr.type = pmu->type;
- evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+ evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus);
return evsel ? 0 : -ENOMEM;
}
* Configure hardcoded terms first, no need to check
* return value when called with fail == 0 ;)
*/
- config_attr(&attr, head_config, 0);
+ if (config_attr(&attr, head_config, data->error))
+ return -EINVAL;
- if (perf_pmu__config(pmu, &attr, head_config))
+ if (perf_pmu__config(pmu, &attr, head_config, data->error))
return -EINVAL;
- evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
- pmu->cpus);
+ evsel = __add_event(list, &data->idx, &attr,
+ pmu_event_name(head_config), pmu->cpus);
if (evsel) {
evsel->unit = info.unit;
evsel->scale = info.scale;
return ret;
}
-int parse_events(struct perf_evlist *evlist, const char *str)
+int parse_events(struct perf_evlist *evlist, const char *str,
+ struct parse_events_error *err)
{
struct parse_events_evlist data = {
- .list = LIST_HEAD_INIT(data.list),
- .idx = evlist->nr_entries,
+ .list = LIST_HEAD_INIT(data.list),
+ .idx = evlist->nr_entries,
+ .error = err,
};
int ret;
return ret;
}
+#define MAX_WIDTH 1000
+static int get_term_width(void)
+{
+ struct winsize ws;
+
+ get_term_dimensions(&ws);
+ return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
+}
+
+static void parse_events_print_error(struct parse_events_error *err,
+ const char *event)
+{
+ const char *str = "invalid or unsupported event: ";
+ char _buf[MAX_WIDTH];
+ char *buf = (char *) event;
+ int idx = 0;
+
+ if (err->str) {
+ /* -2 for extra '' in the final fprintf */
+ int width = get_term_width() - 2;
+ int len_event = strlen(event);
+ int len_str, max_len, cut = 0;
+
+ /*
+ * Maximum error index indent, we will cut
+ * the event string if it's bigger.
+ */
+ int max_err_idx = 10;
+
+ /*
+ * Let's be specific with the message when
+ * we have the precise error.
+ */
+ str = "event syntax error: ";
+ len_str = strlen(str);
+ max_len = width - len_str;
+
+ buf = _buf;
+
+ /* We're cutting from the beggining. */
+ if (err->idx > max_err_idx)
+ cut = err->idx - max_err_idx;
+
+ strncpy(buf, event + cut, max_len);
+
+ /* Mark cut parts with '..' on both sides. */
+ if (cut)
+ buf[0] = buf[1] = '.';
+
+ if ((len_event - cut) > max_len) {
+ buf[max_len - 1] = buf[max_len - 2] = '.';
+ buf[max_len] = 0;
+ }
+
+ idx = len_str + err->idx - cut;
+ }
+
+ fprintf(stderr, "%s'%s'\n", str, buf);
+ if (idx) {
+ fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
+ if (err->help)
+ fprintf(stderr, "\n%s\n", err->help);
+ free(err->str);
+ free(err->help);
+ }
+
+ fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+}
+
+#undef MAX_WIDTH
+
int parse_events_option(const struct option *opt, const char *str,
int unset __maybe_unused)
{
struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
- int ret = parse_events(evlist, str);
+ struct parse_events_error err = { .idx = 0, };
+ int ret = parse_events(evlist, str, &err);
+
+ if (ret)
+ parse_events_print_error(&err, str);
- if (ret) {
- fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
- fprintf(stderr, "Run 'perf list' for a list of valid events\n");
- }
return ret;
}
static int new_term(struct parse_events_term **_term, int type_val,
int type_term, char *config,
- char *str, u64 num)
+ char *str, u64 num, int err_term, int err_val)
{
struct parse_events_term *term;
term->type_val = type_val;
term->type_term = type_term;
term->config = config;
+ term->err_term = err_term;
+ term->err_val = err_val;
switch (type_val) {
case PARSE_EVENTS__TERM_TYPE_NUM:
}
int parse_events_term__num(struct parse_events_term **term,
- int type_term, char *config, u64 num)
+ int type_term, char *config, u64 num,
+ void *loc_term_, void *loc_val_)
{
+ YYLTYPE *loc_term = loc_term_;
+ YYLTYPE *loc_val = loc_val_;
+
return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
- config, NULL, num);
+ config, NULL, num,
+ loc_term ? loc_term->first_column : 0,
+ loc_val ? loc_val->first_column : 0);
}
int parse_events_term__str(struct parse_events_term **term,
- int type_term, char *config, char *str)
+ int type_term, char *config, char *str,
+ void *loc_term_, void *loc_val_)
{
+ YYLTYPE *loc_term = loc_term_;
+ YYLTYPE *loc_val = loc_val_;
+
return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
- config, str, 0);
+ config, str, 0,
+ loc_term ? loc_term->first_column : 0,
+ loc_val ? loc_val->first_column : 0);
}
int parse_events_term__sym_hw(struct parse_events_term **term,
if (config)
return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
PARSE_EVENTS__TERM_TYPE_USER, config,
- (char *) sym->symbol, 0);
+ (char *) sym->symbol, 0, 0, 0);
else
return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
PARSE_EVENTS__TERM_TYPE_USER,
- (char *) "event", (char *) sym->symbol, 0);
+ (char *) "event", (char *) sym->symbol,
+ 0, 0, 0);
}
int parse_events_term__clone(struct parse_events_term **new,
struct parse_events_term *term)
{
return new_term(new, term->type_val, term->type_term, term->config,
- term->val.str, term->val.num);
+ term->val.str, term->val.num,
+ term->err_term, term->err_val);
}
void parse_events__free_terms(struct list_head *terms)
list_for_each_entry_safe(term, h, terms, list)
free(term);
}
+
+void parse_events_evlist_error(struct parse_events_evlist *data,
+ int idx, const char *str)
+{
+ struct parse_events_error *err = data->error;
+
+ if (!err)
+ return;
+ err->idx = idx;
+ err->str = strdup(str);
+ WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
+}
struct list_head;
struct perf_evsel;
struct perf_evlist;
+struct parse_events_error;
struct option;
extern int parse_events_option(const struct option *opt, const char *str,
int unset);
-extern int parse_events(struct perf_evlist *evlist, const char *str);
+extern int parse_events(struct perf_evlist *evlist, const char *str,
+ struct parse_events_error *error);
extern int parse_events_terms(struct list_head *terms, const char *str);
extern int parse_filter(const struct option *opt, const char *str, int unset);
int type_term;
struct list_head list;
bool used;
+
+ /* error string indexes for within parsed string */
+ int err_term;
+ int err_val;
+};
+
+struct parse_events_error {
+ int idx; /* index in the parsed string */
+ char *str; /* string to display at the index */
+ char *help; /* optional help string */
};
struct parse_events_evlist {
- struct list_head list;
- int idx;
- int nr_groups;
+ struct list_head list;
+ int idx;
+ int nr_groups;
+ struct parse_events_error *error;
};
struct parse_events_terms {
};
int parse_events__is_hardcoded_term(struct parse_events_term *term);
-int parse_events_term__num(struct parse_events_term **_term,
- int type_term, char *config, u64 num);
-int parse_events_term__str(struct parse_events_term **_term,
- int type_term, char *config, char *str);
+int parse_events_term__num(struct parse_events_term **term,
+ int type_term, char *config, u64 num,
+ void *loc_term, void *loc_val);
+int parse_events_term__str(struct parse_events_term **term,
+ int type_term, char *config, char *str,
+ void *loc_term, void *loc_val);
int parse_events_term__sym_hw(struct parse_events_term **term,
char *config, unsigned idx);
int parse_events_term__clone(struct parse_events_term **new,
int parse_events_name(struct list_head *list, char *name);
int parse_events_add_tracepoint(struct list_head *list, int *idx,
char *sys, char *event);
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+ struct list_head *list,
u32 type, u64 config,
struct list_head *head_config);
int parse_events_add_cache(struct list_head *list, int *idx,
char *type, char *op_result1, char *op_result2);
int parse_events_add_breakpoint(struct list_head *list, int *idx,
void *ptr, char *type, u64 len);
-int parse_events_add_pmu(struct list_head *list, int *idx,
- char *pmu , struct list_head *head_config);
+int parse_events_add_pmu(struct parse_events_evlist *data,
+ struct list_head *list, char *name,
+ struct list_head *head_config);
enum perf_pmu_event_symbol_type
perf_pmu__parse_check(const char *name);
void parse_events__set_leader(char *name, struct list_head *list);
void parse_events_update_lists(struct list_head *list_event,
struct list_head *list_all);
-void parse_events_error(void *data, void *scanner, char const *msg);
+void parse_events_evlist_error(struct parse_events_evlist *data,
+ int idx, const char *str);
void print_events(const char *event_glob, bool name_only);
%option bison-bridge
%option prefix="parse_events_"
%option stack
+%option bison-locations
+%option yylineno
%{
#include <errno.h>
return token;
}
+#define REWIND(__alloc) \
+do { \
+ YYSTYPE *__yylval = parse_events_get_lval(yyscanner); \
+ char *text = parse_events_get_text(yyscanner); \
+ \
+ if (__alloc) \
+ __yylval->str = strdup(text); \
+ \
+ yycolumn -= strlen(text); \
+ yyless(0); \
+} while (0)
+
static int pmu_str_check(yyscan_t scanner)
{
YYSTYPE *yylval = parse_events_get_lval(scanner);
return PE_TERM;
}
+#define YY_USER_ACTION \
+do { \
+ yylloc->last_column = yylloc->first_column; \
+ yylloc->first_column = yycolumn; \
+ yycolumn += yyleng; \
+} while (0);
+
%}
%x mem
if (start_token) {
parse_events_set_extra(NULL, yyscanner);
+ /*
+ * The flex parser does not init locations variable
+ * via the scan_string interface, so we need do the
+ * init in here.
+ */
+ yycolumn = 0;
return start_token;
}
}
<event>{
{group} {
- BEGIN(INITIAL); yyless(0);
+ BEGIN(INITIAL);
+ REWIND(0);
}
{event_pmu} |
{event} {
- str(yyscanner, PE_EVENT_NAME);
- BEGIN(INITIAL); yyless(0);
+ BEGIN(INITIAL);
+ REWIND(1);
return PE_EVENT_NAME;
}
. |
<<EOF>> {
- BEGIN(INITIAL); yyless(0);
+ BEGIN(INITIAL);
+ REWIND(0);
}
}
<config>{
+ /*
+ * Please update formats_error_string any time
+ * new static term is added.
+ */
config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
%parse-param {void *_data}
%parse-param {void *scanner}
%lex-param {void* scanner}
+%locations
%{
#include "parse-events.h"
#include "parse-events-bison.h"
-extern int parse_events_lex (YYSTYPE* lvalp, void* scanner);
-
#define ABORT_ON(val) \
do { \
if (val) \
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3));
+ ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
parse_events__free_terms($3);
$$ = list;
}
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+ ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
$$ = list;
}
|
ALLOC_LIST(head);
ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, 1));
+ $1, 1, &@1, NULL));
list_add_tail(&term->list, head);
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+ ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
parse_events__free_terms(head);
$$ = list;
}
ALLOC_LIST(head);
ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- &pmu_name, 1));
+ &pmu_name, 1, &@1, NULL));
list_add_tail(&term->list, head);
ALLOC_LIST(list);
int config = $1 & 255;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_numeric(list, &data->idx,
- type, config, $3));
+ ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
parse_events__free_terms($3);
$$ = list;
}
int config = $1 & 255;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_numeric(list, &data->idx,
- type, config, NULL));
+ ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL));
$$ = list;
}
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3));
+ if (parse_events_add_tracepoint(list, &data->idx, $1, $3)) {
+ struct parse_events_error *error = data->error;
+
+ if (error) {
+ error->idx = @1.first_column;
+ error->str = strdup("unknown tracepoint");
+ }
+ return -1;
+ }
$$ = list;
}
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL));
+ ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
$$ = list;
}
struct list_head *list;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_numeric(list, &data->idx,
- PERF_TYPE_RAW, $1, NULL));
+ ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
$$ = list;
}
struct parse_events_term *term;
ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $3));
+ $1, $3, &@1, &@3));
$$ = term;
}
|
struct parse_events_term *term;
ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $3));
+ $1, $3, &@1, &@3));
$$ = term;
}
|
struct parse_events_term *term;
ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, 1));
+ $1, 1, &@1, NULL));
$$ = term;
}
|
{
struct parse_events_term *term;
- ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3));
+ ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3));
$$ = term;
}
|
{
struct parse_events_term *term;
- ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3));
+ ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3));
$$ = term;
}
|
{
struct parse_events_term *term;
- ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1));
+ ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
$$ = term;
}
%%
-void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused,
+void parse_events_error(YYLTYPE *loc, void *data,
+ void *scanner __maybe_unused,
char const *msg __maybe_unused)
{
+ parse_events_evlist_error(data, loc->last_column, "parser error");
}
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
+ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+ .value = check_vtype(v, const char **), (a), .help = (h), \
+ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
#define OPT_DATE(s, l, v, h) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
if (sret < 0)
goto error;
- scale[sret] = '\0';
+ if (scale[sret - 1] == '\n')
+ scale[sret - 1] = '\0';
+ else
+ scale[sret] = '\0';
+
/*
* save current locale
*/
close(fd);
- alias->unit[sret] = '\0';
+ if (alias->unit[sret - 1] == '\n')
+ alias->unit[sret - 1] = '\0';
+ else
+ alias->unit[sret] = '\0';
return 0;
error:
LIST_HEAD(aliases);
__u32 type;
+ /* No support for intel_bts or intel_pt so disallow them */
+ if (!strcmp(name, "intel_bts") || !strcmp(name, "intel_pt"))
+ return NULL;
+
/*
* The pmu data we store & need consists of the pmu
* type value and format definitions. Load both right
return -1;
}
+static char *formats_error_string(struct list_head *formats)
+{
+ struct perf_pmu_format *format;
+ char *err, *str;
+ static const char *static_terms = "config,config1,config2,name,period,branch_type\n";
+ unsigned i = 0;
+
+ if (!asprintf(&str, "valid terms:"))
+ return NULL;
+
+ /* sysfs exported terms */
+ list_for_each_entry(format, formats, list) {
+ char c = i++ ? ',' : ' ';
+
+ err = str;
+ if (!asprintf(&str, "%s%c%s", err, c, format->name))
+ goto fail;
+ free(err);
+ }
+
+ /* static terms */
+ err = str;
+ if (!asprintf(&str, "%s,%s", err, static_terms))
+ goto fail;
+
+ free(err);
+ return str;
+fail:
+ free(err);
+ return NULL;
+}
+
/*
* Setup one of config[12] attr members based on the
* user input data - term parameter.
struct perf_event_attr *attr,
struct parse_events_term *term,
struct list_head *head_terms,
- bool zero)
+ bool zero, struct parse_events_error *err)
{
struct perf_pmu_format *format;
__u64 *vp;
if (!format) {
if (verbose)
printf("Invalid event/parameter '%s'\n", term->config);
+ if (err) {
+ err->idx = term->err_term;
+ err->str = strdup("unknown term");
+ err->help = formats_error_string(formats);
+ }
return -EINVAL;
}
val = term->val.num;
else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
if (strcmp(term->val.str, "?")) {
- if (verbose)
+ if (verbose) {
pr_info("Invalid sysfs entry %s=%s\n",
term->config, term->val.str);
+ }
+ if (err) {
+ err->idx = term->err_val;
+ err->str = strdup("expected numeric value");
+ }
return -EINVAL;
}
int perf_pmu__config_terms(struct list_head *formats,
struct perf_event_attr *attr,
struct list_head *head_terms,
- bool zero)
+ bool zero, struct parse_events_error *err)
{
struct parse_events_term *term;
list_for_each_entry(term, head_terms, list) {
- if (pmu_config_term(formats, attr, term, head_terms, zero))
+ if (pmu_config_term(formats, attr, term, head_terms,
+ zero, err))
return -EINVAL;
}
* 2) pmu format definitions - specified by pmu parameter
*/
int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
- struct list_head *head_terms)
+ struct list_head *head_terms,
+ struct parse_events_error *err)
{
bool zero = !!pmu->default_config;
attr->type = pmu->type;
- return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
+ return perf_pmu__config_terms(&pmu->format, attr, head_terms,
+ zero, err);
}
static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
#include <linux/bitmap.h>
#include <linux/perf_event.h>
#include <stdbool.h>
+#include "parse-events.h"
enum {
PERF_PMU_FORMAT_VALUE_CONFIG,
struct perf_pmu *perf_pmu__find(const char *name);
int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
- struct list_head *head_terms);
+ struct list_head *head_terms,
+ struct parse_events_error *error);
int perf_pmu__config_terms(struct list_head *formats,
struct perf_event_attr *attr,
struct list_head *head_terms,
- bool zero);
+ bool zero, struct parse_events_error *error);
int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
struct perf_pmu_info *info);
struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
#define PERFPROBE_GROUP "probe"
bool probe_event_dry_run; /* Dry run flag */
+struct probe_conf probe_conf;
#define semantic_error(msg ...) pr_err("Semantic error :" msg)
static struct map *kernel_get_module_map(const char *module)
{
- struct rb_node *nd;
struct map_groups *grp = &host_machine->kmaps;
+ struct maps *maps = &grp->maps[MAP__FUNCTION];
+ struct map *pos;
/* A file path -- this is an offline module */
if (module && strchr(module, '/'))
- return machine__new_module(host_machine, 0, module);
+ return machine__findnew_module_map(host_machine, 0, module);
if (!module)
module = "kernel";
- for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) {
- struct map *pos = rb_entry(nd, struct map, rb_node);
+ for (pos = maps__first(maps); pos; pos = map__next(pos)) {
if (strncmp(pos->dso->short_name + 1, module,
pos->dso->short_name_len - 2) == 0) {
return pos;
{
if (map && user) {
/* Only the user map needs to be released */
- dso__delete(map->dso);
- map__delete(map);
+ map__put(map);
}
}
-static struct dso *kernel_get_module_dso(const char *module)
-{
- struct dso *dso;
- struct map *map;
- const char *vmlinux_name;
-
- if (module) {
- list_for_each_entry(dso, &host_machine->kernel_dsos.head,
- node) {
- if (strncmp(dso->short_name + 1, module,
- dso->short_name_len - 2) == 0)
- goto found;
- }
- pr_debug("Failed to find module %s.\n", module);
- return NULL;
- }
-
- map = host_machine->vmlinux_maps[MAP__FUNCTION];
- dso = map->dso;
-
- vmlinux_name = symbol_conf.vmlinux_name;
- if (vmlinux_name) {
- if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0)
- return NULL;
- } else {
- if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
- pr_debug("Failed to load kernel map.\n");
- return NULL;
- }
- }
-found:
- return dso;
-}
-
-const char *kernel_get_module_path(const char *module)
-{
- struct dso *dso = kernel_get_module_dso(module);
- return (dso) ? dso->long_name : NULL;
-}
-
static int convert_exec_to_group(const char *exec, char **result)
{
char *ptr1, *ptr2, *exec_copy;
clear_probe_trace_event(tevs + i);
}
+static bool kprobe_blacklist__listed(unsigned long address);
+static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
+{
+ /* Get the address of _etext for checking non-probable text symbol */
+ if (kernel_get_symbol_address_by_name("_etext", false) < address)
+ pr_warning("%s is out of .text, skip it.\n", symbol);
+ else if (kprobe_blacklist__listed(address))
+ pr_warning("%s is blacklisted function, skip it.\n", symbol);
+ else
+ return false;
+
+ return true;
+}
+
#ifdef HAVE_DWARF_SUPPORT
+
+static int kernel_get_module_dso(const char *module, struct dso **pdso)
+{
+ struct dso *dso;
+ struct map *map;
+ const char *vmlinux_name;
+ int ret = 0;
+
+ if (module) {
+ list_for_each_entry(dso, &host_machine->dsos.head, node) {
+ if (!dso->kernel)
+ continue;
+ if (strncmp(dso->short_name + 1, module,
+ dso->short_name_len - 2) == 0)
+ goto found;
+ }
+ pr_debug("Failed to find module %s.\n", module);
+ return -ENOENT;
+ }
+
+ map = host_machine->vmlinux_maps[MAP__FUNCTION];
+ dso = map->dso;
+
+ vmlinux_name = symbol_conf.vmlinux_name;
+ dso->load_errno = 0;
+ if (vmlinux_name)
+ ret = dso__load_vmlinux(dso, map, vmlinux_name, false, NULL);
+ else
+ ret = dso__load_vmlinux_path(dso, map, NULL);
+found:
+ *pdso = dso;
+ return ret;
+}
+
/*
* Some binaries like glibc have special symbols which are on the symbol
* table, but not in the debuginfo. If we can find the address of the
static int get_alternative_probe_event(struct debuginfo *dinfo,
struct perf_probe_event *pev,
- struct perf_probe_point *tmp,
- const char *target)
+ struct perf_probe_point *tmp)
{
int ret;
memcpy(tmp, &pev->point, sizeof(*tmp));
memset(&pev->point, 0, sizeof(pev->point));
ret = find_alternative_probe_point(dinfo, tmp, &pev->point,
- target, pev->uprobes);
+ pev->target, pev->uprobes);
if (ret < 0)
memcpy(&pev->point, tmp, sizeof(*tmp));
static struct debuginfo *open_debuginfo(const char *module, bool silent)
{
const char *path = module;
- struct debuginfo *ret;
+ char reason[STRERR_BUFSIZE];
+ struct debuginfo *ret = NULL;
+ struct dso *dso = NULL;
+ int err;
if (!module || !strchr(module, '/')) {
- path = kernel_get_module_path(module);
- if (!path) {
+ err = kernel_get_module_dso(module, &dso);
+ if (err < 0) {
+ if (!dso || dso->load_errno == 0) {
+ if (!strerror_r(-err, reason, STRERR_BUFSIZE))
+ strcpy(reason, "(unknown)");
+ } else
+ dso__strerror_load(dso, reason, STRERR_BUFSIZE);
if (!silent)
- pr_err("Failed to find path of %s module.\n",
- module ?: "kernel");
+ pr_err("Failed to find the path for %s: %s\n",
+ module ?: "kernel", reason);
return NULL;
}
+ path = dso->long_name;
}
ret = debuginfo__new(path);
if (!ret && !silent) {
return ret;
}
+/* For caching the last debuginfo */
+static struct debuginfo *debuginfo_cache;
+static char *debuginfo_cache_path;
+
+static struct debuginfo *debuginfo_cache__open(const char *module, bool silent)
+{
+ if ((debuginfo_cache_path && !strcmp(debuginfo_cache_path, module)) ||
+ (!debuginfo_cache_path && !module && debuginfo_cache))
+ goto out;
+
+ /* Copy module path */
+ free(debuginfo_cache_path);
+ if (module) {
+ debuginfo_cache_path = strdup(module);
+ if (!debuginfo_cache_path) {
+ debuginfo__delete(debuginfo_cache);
+ debuginfo_cache = NULL;
+ goto out;
+ }
+ }
+
+ debuginfo_cache = open_debuginfo(module, silent);
+ if (!debuginfo_cache)
+ zfree(&debuginfo_cache_path);
+out:
+ return debuginfo_cache;
+}
+
+static void debuginfo_cache__exit(void)
+{
+ debuginfo__delete(debuginfo_cache);
+ debuginfo_cache = NULL;
+ zfree(&debuginfo_cache_path);
+}
+
static int get_text_start_address(const char *exec, unsigned long *address)
{
pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
tp->module ? : "kernel");
- dinfo = open_debuginfo(tp->module, verbose == 0);
- if (dinfo) {
+ dinfo = debuginfo_cache__open(tp->module, verbose == 0);
+ if (dinfo)
ret = debuginfo__find_probe_point(dinfo,
(unsigned long)addr, pp);
- debuginfo__delete(dinfo);
- } else
+ else
ret = -ENOENT;
if (ret > 0) {
{
struct ref_reloc_sym *reloc_sym;
char *tmp;
- int i;
+ int i, skipped = 0;
if (uprobe)
return add_exec_to_probe_trace_events(tevs, ntevs, module);
}
for (i = 0; i < ntevs; i++) {
- if (tevs[i].point.address && !tevs[i].point.retprobe) {
+ if (!tevs[i].point.address || tevs[i].point.retprobe)
+ continue;
+ /* If we found a wrong one, mark it by NULL symbol */
+ if (kprobe_warn_out_range(tevs[i].point.symbol,
+ tevs[i].point.address)) {
+ tmp = NULL;
+ skipped++;
+ } else {
tmp = strdup(reloc_sym->name);
if (!tmp)
return -ENOMEM;
- free(tevs[i].point.symbol);
- tevs[i].point.symbol = tmp;
- tevs[i].point.offset = tevs[i].point.address -
- reloc_sym->unrelocated_addr;
}
+ /* If we have no realname, use symbol for it */
+ if (!tevs[i].point.realname)
+ tevs[i].point.realname = tevs[i].point.symbol;
+ else
+ free(tevs[i].point.symbol);
+ tevs[i].point.symbol = tmp;
+ tevs[i].point.offset = tevs[i].point.address -
+ reloc_sym->unrelocated_addr;
}
- return 0;
+ return skipped;
}
/* Try to find perf_probe_event with debuginfo */
static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
- struct probe_trace_event **tevs,
- int max_tevs, const char *target)
+ struct probe_trace_event **tevs)
{
bool need_dwarf = perf_probe_event_need_dwarf(pev);
struct perf_probe_point tmp;
struct debuginfo *dinfo;
int ntevs, ret = 0;
- dinfo = open_debuginfo(target, !need_dwarf);
-
+ dinfo = open_debuginfo(pev->target, !need_dwarf);
if (!dinfo) {
if (need_dwarf)
return -ENOENT;
pr_debug("Try to find probe point from debuginfo.\n");
/* Searching trace events corresponding to a probe event */
- ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
+ ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
if (ntevs == 0) { /* Not found, retry with an alternative */
- ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+ ret = get_alternative_probe_event(dinfo, pev, &tmp);
if (!ret) {
- ntevs = debuginfo__find_trace_events(dinfo, pev,
- tevs, max_tevs);
+ ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
/*
* Write back to the original probe_event for
* setting appropriate (user given) event name
if (ntevs > 0) { /* Succeeded to find trace events */
pr_debug("Found %d probe_trace_events.\n", ntevs);
ret = post_process_probe_trace_events(*tevs, ntevs,
- target, pev->uprobes);
- if (ret < 0) {
+ pev->target, pev->uprobes);
+ if (ret < 0 || ret == ntevs) {
clear_probe_trace_events(*tevs, ntevs);
zfree(tevs);
}
- return ret < 0 ? ret : ntevs;
+ if (ret != ntevs)
+ return ret < 0 ? ret : ntevs;
+ ntevs = 0;
+ /* Fall through */
}
if (ntevs == 0) { /* No error but failed to find probe point. */
static int show_available_vars_at(struct debuginfo *dinfo,
struct perf_probe_event *pev,
- int max_vls, struct strfilter *_filter,
- bool externs, const char *target)
+ struct strfilter *_filter)
{
char *buf;
int ret, i, nvars;
return -EINVAL;
pr_debug("Searching variables at %s\n", buf);
- ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
- max_vls, externs);
+ ret = debuginfo__find_available_vars_at(dinfo, pev, &vls);
if (!ret) { /* Not found, retry with an alternative */
- ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+ ret = get_alternative_probe_event(dinfo, pev, &tmp);
if (!ret) {
ret = debuginfo__find_available_vars_at(dinfo, pev,
- &vls, max_vls, externs);
+ &vls);
/* Release the old probe_point */
clear_perf_probe_point(&tmp);
}
/* Show available variables on given probe point */
int show_available_vars(struct perf_probe_event *pevs, int npevs,
- int max_vls, const char *module,
- struct strfilter *_filter, bool externs)
+ struct strfilter *_filter)
{
int i, ret = 0;
struct debuginfo *dinfo;
if (ret < 0)
return ret;
- dinfo = open_debuginfo(module, false);
+ dinfo = open_debuginfo(pevs->target, false);
if (!dinfo) {
ret = -ENOENT;
goto out;
setup_pager();
for (i = 0; i < npevs && ret >= 0; i++)
- ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter,
- externs, module);
+ ret = show_available_vars_at(dinfo, &pevs[i], _filter);
debuginfo__delete(dinfo);
out:
#else /* !HAVE_DWARF_SUPPORT */
+static void debuginfo_cache__exit(void)
+{
+}
+
static int
find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
struct perf_probe_point *pp __maybe_unused,
}
static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
- struct probe_trace_event **tevs __maybe_unused,
- int max_tevs __maybe_unused,
- const char *target __maybe_unused)
+ struct probe_trace_event **tevs __maybe_unused)
{
if (perf_probe_event_need_dwarf(pev)) {
pr_warning("Debuginfo-analysis is not supported.\n");
}
int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
- int npevs __maybe_unused, int max_vls __maybe_unused,
- const char *module __maybe_unused,
- struct strfilter *filter __maybe_unused,
- bool externs __maybe_unused)
+ int npevs __maybe_unused,
+ struct strfilter *filter __maybe_unused)
{
pr_warning("Debuginfo-analysis is not supported.\n");
return -ENOSYS;
return 0;
}
+/* Check the name is good for event, group or function */
+static bool is_c_func_name(const char *name)
+{
+ if (!isalpha(*name) && *name != '_')
+ return false;
+ while (*++name != '\0') {
+ if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+ return false;
+ }
+ return true;
+}
+
/*
* Stuff 'lr' according to the line range described by 'arg'.
* The line range syntax is described by:
goto err;
}
lr->function = name;
- } else if (strchr(name, '.'))
+ } else if (strchr(name, '/') || strchr(name, '.'))
lr->file = name;
- else
+ else if (is_c_func_name(name))/* We reuse it for checking funcname */
lr->function = name;
+ else { /* Invalid name */
+ semantic_error("'%s' is not a valid function name.\n", name);
+ err = -EINVAL;
+ goto err;
+ }
return 0;
err:
return err;
}
-/* Check the name is good for event/group */
-static bool check_event_name(const char *name)
-{
- if (!isalpha(*name) && *name != '_')
- return false;
- while (*++name != '\0') {
- if (!isalpha(*name) && !isdigit(*name) && *name != '_')
- return false;
- }
- return true;
-}
-
/* Parse probepoint definition. */
static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
{
struct perf_probe_point *pp = &pev->point;
char *ptr, *tmp;
char c, nc = 0;
+ bool file_spec = false;
/*
* <Syntax>
* perf probe [EVENT=]SRC[:LN|;PTN]
semantic_error("Group name is not supported yet.\n");
return -ENOTSUP;
}
- if (!check_event_name(arg)) {
+ if (!is_c_func_name(arg)) {
semantic_error("%s is bad for event name -it must "
"follow C symbol-naming rule.\n", arg);
return -EINVAL;
arg = tmp;
}
+ /*
+ * Check arg is function or file name and copy it.
+ *
+ * We consider arg to be a file spec if and only if it satisfies
+ * all of the below criteria::
+ * - it does not include any of "+@%",
+ * - it includes one of ":;", and
+ * - it has a period '.' in the name.
+ *
+ * Otherwise, we consider arg to be a function specification.
+ */
+ if (!strpbrk(arg, "+@%") && (ptr = strpbrk(arg, ";:")) != NULL) {
+ /* This is a file spec if it includes a '.' before ; or : */
+ if (memchr(arg, '.', ptr - arg))
+ file_spec = true;
+ }
+
ptr = strpbrk(arg, ";:+@%");
if (ptr) {
nc = *ptr;
if (tmp == NULL)
return -ENOMEM;
- /* Check arg is function or file and copy it */
- if (strchr(tmp, '.')) /* File */
+ if (file_spec)
pp->file = tmp;
- else /* Function */
+ else
pp->function = tmp;
/* Parse other options */
out:
if (map && !is_kprobe) {
- dso__delete(map->dso);
- map__delete(map);
+ map__put(map);
}
return ret;
free(tev->event);
free(tev->group);
free(tev->point.symbol);
+ free(tev->point.realname);
free(tev->point.module);
for (i = 0; i < tev->nargs; i++) {
free(tev->args[i].name);
if (ret >= 0) {
pr_debug("Opening %s write=%d\n", buf, readwrite);
if (readwrite && !probe_event_dry_run)
- ret = open(buf, O_RDWR, O_APPEND);
+ ret = open(buf, O_RDWR | O_APPEND, 0);
else
ret = open(buf, O_RDONLY, 0);
return NULL;
}
-/* Show an event */
-static int show_perf_probe_event(struct perf_probe_event *pev,
- const char *module)
+static LIST_HEAD(kprobe_blacklist);
+
+static void kprobe_blacklist__init(void)
+{
+ if (!list_empty(&kprobe_blacklist))
+ return;
+
+ if (kprobe_blacklist__load(&kprobe_blacklist) < 0)
+ pr_debug("No kprobe blacklist support, ignored\n");
+}
+
+static void kprobe_blacklist__release(void)
+{
+ kprobe_blacklist__delete(&kprobe_blacklist);
+}
+
+static bool kprobe_blacklist__listed(unsigned long address)
+{
+ return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address);
+}
+
+static int perf_probe_event__sprintf(const char *group, const char *event,
+ struct perf_probe_event *pev,
+ const char *module,
+ struct strbuf *result)
{
int i, ret;
char buf[128];
if (!place)
return -EINVAL;
- ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event);
+ ret = e_snprintf(buf, 128, "%s:%s", group, event);
if (ret < 0)
- return ret;
+ goto out;
- pr_info(" %-20s (on %s", buf, place);
+ strbuf_addf(result, " %-20s (on %s", buf, place);
if (module)
- pr_info(" in %s", module);
+ strbuf_addf(result, " in %s", module);
if (pev->nargs > 0) {
- pr_info(" with");
+ strbuf_addstr(result, " with");
for (i = 0; i < pev->nargs; i++) {
ret = synthesize_perf_probe_arg(&pev->args[i],
buf, 128);
if (ret < 0)
- break;
- pr_info(" %s", buf);
+ goto out;
+ strbuf_addf(result, " %s", buf);
}
}
- pr_info(")\n");
+ strbuf_addch(result, ')');
+out:
free(place);
return ret;
}
-static int __show_perf_probe_events(int fd, bool is_kprobe)
+/* Show an event */
+static int show_perf_probe_event(const char *group, const char *event,
+ struct perf_probe_event *pev,
+ const char *module, bool use_stdout)
+{
+ struct strbuf buf = STRBUF_INIT;
+ int ret;
+
+ ret = perf_probe_event__sprintf(group, event, pev, module, &buf);
+ if (ret >= 0) {
+ if (use_stdout)
+ printf("%s\n", buf.buf);
+ else
+ pr_info("%s\n", buf.buf);
+ }
+ strbuf_release(&buf);
+
+ return ret;
+}
+
+static bool filter_probe_trace_event(struct probe_trace_event *tev,
+ struct strfilter *filter)
+{
+ char tmp[128];
+
+ /* At first, check the event name itself */
+ if (strfilter__compare(filter, tev->event))
+ return true;
+
+ /* Next, check the combination of name and group */
+ if (e_snprintf(tmp, 128, "%s:%s", tev->group, tev->event) < 0)
+ return false;
+ return strfilter__compare(filter, tmp);
+}
+
+static int __show_perf_probe_events(int fd, bool is_kprobe,
+ struct strfilter *filter)
{
int ret = 0;
struct probe_trace_event tev;
strlist__for_each(ent, rawlist) {
ret = parse_probe_trace_command(ent->s, &tev);
if (ret >= 0) {
+ if (!filter_probe_trace_event(&tev, filter))
+ goto next;
ret = convert_to_perf_probe_event(&tev, &pev,
is_kprobe);
- if (ret >= 0)
- ret = show_perf_probe_event(&pev,
- tev.point.module);
+ if (ret < 0)
+ goto next;
+ ret = show_perf_probe_event(pev.group, pev.event,
+ &pev, tev.point.module,
+ true);
}
+next:
clear_perf_probe_event(&pev);
clear_probe_trace_event(&tev);
if (ret < 0)
break;
}
strlist__delete(rawlist);
+ /* Cleanup cached debuginfo if needed */
+ debuginfo_cache__exit();
return ret;
}
/* List up current perf-probe events */
-int show_perf_probe_events(void)
+int show_perf_probe_events(struct strfilter *filter)
{
int kp_fd, up_fd, ret;
kp_fd = open_kprobe_events(false);
if (kp_fd >= 0) {
- ret = __show_perf_probe_events(kp_fd, true);
+ ret = __show_perf_probe_events(kp_fd, true, filter);
close(kp_fd);
if (ret < 0)
goto out;
}
if (up_fd >= 0) {
- ret = __show_perf_probe_events(up_fd, false);
+ ret = __show_perf_probe_events(up_fd, false, filter);
close(up_fd);
}
out:
struct strlist *namelist, bool allow_suffix)
{
int i, ret;
+ char *p;
+
+ if (*base == '.')
+ base++;
/* Try no suffix */
ret = e_snprintf(buf, len, "%s", base);
pr_debug("snprintf() failed: %d\n", ret);
return ret;
}
+ /* Cut off the postfixes (e.g. .const, .isra)*/
+ p = strchr(buf, '.');
+ if (p && p != buf)
+ *p = '\0';
if (!strlist__has_entry(namelist, buf))
return 0;
int i, fd, ret;
struct probe_trace_event *tev = NULL;
char buf[64];
- const char *event, *group;
+ const char *event = NULL, *group = NULL;
struct strlist *namelist;
- LIST_HEAD(blacklist);
- struct kprobe_blacklist_node *node;
+ bool safename;
if (pev->uprobes)
fd = open_uprobe_events(true);
namelist = get_probe_trace_event_names(fd, false);
if (!namelist) {
pr_debug("Failed to get current event list.\n");
- return -EIO;
- }
- /* Get kprobe blacklist if exists */
- if (!pev->uprobes) {
- ret = kprobe_blacklist__load(&blacklist);
- if (ret < 0)
- pr_debug("No kprobe blacklist support, ignored\n");
+ ret = -ENOMEM;
+ goto close_out;
}
+ safename = (pev->point.function && !strisglob(pev->point.function));
ret = 0;
pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
for (i = 0; i < ntevs; i++) {
tev = &tevs[i];
- /* Ensure that the address is NOT blacklisted */
- node = kprobe_blacklist__find_by_address(&blacklist,
- tev->point.address);
- if (node) {
- pr_warning("Warning: Skipped probing on blacklisted function: %s\n", node->symbol);
+ /* Skip if the symbol is out of .text or blacklisted */
+ if (!tev->point.symbol)
continue;
- }
if (pev->event)
event = pev->event;
else
- if (pev->point.function)
+ if (safename)
event = pev->point.function;
else
- event = tev->point.symbol;
+ event = tev->point.realname;
if (pev->group)
group = pev->group;
else
/* Add added event name to namelist */
strlist__add(namelist, event);
- /* Trick here - save current event/group */
- event = pev->event;
- group = pev->group;
- pev->event = tev->event;
- pev->group = tev->group;
- show_perf_probe_event(pev, tev->point.module);
- /* Trick here - restore current event/group */
- pev->event = (char *)event;
- pev->group = (char *)group;
+ /* We use tev's name for showing new events */
+ show_perf_probe_event(tev->group, tev->event, pev,
+ tev->point.module, false);
+ /* Save the last valid name */
+ event = tev->event;
+ group = tev->group;
/*
* Probes after the first probe which comes from same
warn_uprobe_event_compat(tev);
/* Note that it is possible to skip all events because of blacklist */
- if (ret >= 0 && tev->event) {
+ if (ret >= 0 && event) {
/* Show how to use the event. */
pr_info("\nYou can now use it in all perf tools, such as:\n\n");
- pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
- tev->event);
+ pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", group, event);
}
- kprobe_blacklist__delete(&blacklist);
strlist__delete(namelist);
+close_out:
close(fd);
return ret;
}
-static int find_probe_functions(struct map *map, char *name)
+static int find_probe_functions(struct map *map, char *name,
+ struct symbol **syms)
{
int found = 0;
struct symbol *sym;
+ struct rb_node *tmp;
+
+ if (map__load(map, NULL) < 0)
+ return 0;
- map__for_each_symbol_by_name(map, name, sym) {
- found++;
+ map__for_each_symbol(map, sym, tmp) {
+ if (strglobmatch(sym->name, name)) {
+ found++;
+ if (syms && found < probe_conf.max_probes)
+ syms[found - 1] = sym;
+ }
}
return found;
#define strdup_or_goto(str, label) \
({ char *__p = strdup(str); if (!__p) goto label; __p; })
+void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
+ struct probe_trace_event *tev __maybe_unused,
+ struct map *map __maybe_unused) { }
+
/*
* Find probe function addresses from map.
* Return an error or the number of found probe_trace_event
*/
static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
- struct probe_trace_event **tevs,
- int max_tevs, const char *target)
+ struct probe_trace_event **tevs)
{
struct map *map = NULL;
struct ref_reloc_sym *reloc_sym = NULL;
struct symbol *sym;
+ struct symbol **syms = NULL;
struct probe_trace_event *tev;
struct perf_probe_point *pp = &pev->point;
struct probe_trace_point *tp;
int num_matched_functions;
- int ret, i;
+ int ret, i, j, skipped = 0;
- map = get_target_map(target, pev->uprobes);
+ map = get_target_map(pev->target, pev->uprobes);
if (!map) {
ret = -EINVAL;
goto out;
}
+ syms = malloc(sizeof(struct symbol *) * probe_conf.max_probes);
+ if (!syms) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
/*
* Load matched symbols: Since the different local symbols may have
* same name but different addresses, this lists all the symbols.
*/
- num_matched_functions = find_probe_functions(map, pp->function);
+ num_matched_functions = find_probe_functions(map, pp->function, syms);
if (num_matched_functions == 0) {
pr_err("Failed to find symbol %s in %s\n", pp->function,
- target ? : "kernel");
+ pev->target ? : "kernel");
ret = -ENOENT;
goto out;
- } else if (num_matched_functions > max_tevs) {
+ } else if (num_matched_functions > probe_conf.max_probes) {
pr_err("Too many functions matched in %s\n",
- target ? : "kernel");
+ pev->target ? : "kernel");
ret = -E2BIG;
goto out;
}
ret = 0;
- map__for_each_symbol_by_name(map, pp->function, sym) {
+ for (j = 0; j < num_matched_functions; j++) {
+ sym = syms[j];
+
tev = (*tevs) + ret;
tp = &tev->point;
if (ret == num_matched_functions) {
}
/* Add one probe point */
tp->address = map->unmap_ip(map, sym->start) + pp->offset;
- if (reloc_sym) {
+ /* If we found a wrong one, mark it by NULL symbol */
+ if (!pev->uprobes &&
+ kprobe_warn_out_range(sym->name, tp->address)) {
+ tp->symbol = NULL; /* Skip it */
+ skipped++;
+ } else if (reloc_sym) {
tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out);
tp->offset = tp->address - reloc_sym->addr;
} else {
tp->symbol = strdup_or_goto(sym->name, nomem_out);
tp->offset = pp->offset;
}
+ tp->realname = strdup_or_goto(sym->name, nomem_out);
+
tp->retprobe = pp->retprobe;
- if (target)
- tev->point.module = strdup_or_goto(target, nomem_out);
+ if (pev->target)
+ tev->point.module = strdup_or_goto(pev->target,
+ nomem_out);
tev->uprobes = pev->uprobes;
tev->nargs = pev->nargs;
if (tev->nargs) {
strdup_or_goto(pev->args[i].type,
nomem_out);
}
+ arch__fix_tev_from_maps(pev, tev, map);
+ }
+ if (ret == skipped) {
+ ret = -ENOENT;
+ goto err_out;
}
out:
put_target_map(map, pev->uprobes);
+ free(syms);
return ret;
nomem_out:
goto out;
}
+bool __weak arch__prefers_symtab(void) { return false; }
+
static int convert_to_probe_trace_events(struct perf_probe_event *pev,
- struct probe_trace_event **tevs,
- int max_tevs, const char *target)
+ struct probe_trace_event **tevs)
{
int ret;
if (pev->uprobes && !pev->group) {
/* Replace group name if not given */
- ret = convert_exec_to_group(target, &pev->group);
+ ret = convert_exec_to_group(pev->target, &pev->group);
if (ret != 0) {
pr_warning("Failed to make a group name.\n");
return ret;
}
}
+ if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
+ ret = find_probe_trace_events_from_map(pev, tevs);
+ if (ret > 0)
+ return ret; /* Found in symbol table */
+ }
+
/* Convert perf_probe_event with debuginfo */
- ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
+ ret = try_to_find_probe_trace_events(pev, tevs);
if (ret != 0)
return ret; /* Found in debuginfo or got an error */
- return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
+ return find_probe_trace_events_from_map(pev, tevs);
}
struct __event_package {
int ntevs;
};
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
- int max_tevs, bool force_add)
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
{
int i, j, ret;
struct __event_package *pkgs;
/* Loop 1: convert all events */
for (i = 0; i < npevs; i++) {
pkgs[i].pev = &pevs[i];
+ /* Init kprobe blacklist if needed */
+ if (!pkgs[i].pev->uprobes)
+ kprobe_blacklist__init();
/* Convert with or without debuginfo */
ret = convert_to_probe_trace_events(pkgs[i].pev,
- &pkgs[i].tevs,
- max_tevs,
- pkgs[i].pev->target);
+ &pkgs[i].tevs);
if (ret < 0)
goto end;
pkgs[i].ntevs = ret;
}
+ /* This just release blacklist only if allocated */
+ kprobe_blacklist__release();
/* Loop 2: add all events */
for (i = 0; i < npevs; i++) {
ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
- pkgs[i].ntevs, force_add);
+ pkgs[i].ntevs,
+ probe_conf.force_add);
if (ret < 0)
break;
}
return ret;
}
-static int del_trace_probe_event(int fd, const char *buf,
- struct strlist *namelist)
+static int del_trace_probe_events(int fd, struct strfilter *filter,
+ struct strlist *namelist)
{
- struct str_node *ent, *n;
- int ret = -1;
+ struct str_node *ent;
+ const char *p;
+ int ret = -ENOENT;
- if (strpbrk(buf, "*?")) { /* Glob-exp */
- strlist__for_each_safe(ent, n, namelist)
- if (strglobmatch(ent->s, buf)) {
- ret = __del_trace_probe_event(fd, ent);
- if (ret < 0)
- break;
- strlist__remove(namelist, ent);
- }
- } else {
- ent = strlist__find(namelist, buf);
- if (ent) {
+ if (!namelist)
+ return -ENOENT;
+
+ strlist__for_each(ent, namelist) {
+ p = strchr(ent->s, ':');
+ if ((p && strfilter__compare(filter, p + 1)) ||
+ strfilter__compare(filter, ent->s)) {
ret = __del_trace_probe_event(fd, ent);
- if (ret >= 0)
- strlist__remove(namelist, ent);
+ if (ret < 0)
+ break;
}
}
return ret;
}
-int del_perf_probe_events(struct strlist *dellist)
+int del_perf_probe_events(struct strfilter *filter)
{
- int ret = -1, ufd = -1, kfd = -1;
- char buf[128];
- const char *group, *event;
- char *p, *str;
- struct str_node *ent;
+ int ret, ret2, ufd = -1, kfd = -1;
struct strlist *namelist = NULL, *unamelist = NULL;
+ char *str = strfilter__string(filter);
+
+ if (!str)
+ return -EINVAL;
+
+ pr_debug("Delete filter: \'%s\'\n", str);
/* Get current event names */
kfd = open_kprobe_events(true);
if (kfd < 0 && ufd < 0) {
print_both_open_warning(kfd, ufd);
+ ret = kfd;
goto error;
}
- if (namelist == NULL && unamelist == NULL)
+ ret = del_trace_probe_events(kfd, filter, namelist);
+ if (ret < 0 && ret != -ENOENT)
goto error;
- strlist__for_each(ent, dellist) {
- str = strdup(ent->s);
- if (str == NULL) {
- ret = -ENOMEM;
- goto error;
- }
- pr_debug("Parsing: %s\n", str);
- p = strchr(str, ':');
- if (p) {
- group = str;
- *p = '\0';
- event = p + 1;
- } else {
- group = "*";
- event = str;
- }
-
- ret = e_snprintf(buf, 128, "%s:%s", group, event);
- if (ret < 0) {
- pr_err("Failed to copy event.");
- free(str);
- goto error;
- }
-
- pr_debug("Group: %s, Event: %s\n", group, event);
-
- if (namelist)
- ret = del_trace_probe_event(kfd, buf, namelist);
-
- if (unamelist && ret != 0)
- ret = del_trace_probe_event(ufd, buf, unamelist);
-
- if (ret != 0)
- pr_info("Info: Event \"%s\" does not exist.\n", buf);
-
- free(str);
+ ret2 = del_trace_probe_events(ufd, filter, unamelist);
+ if (ret2 < 0 && ret2 != -ENOENT) {
+ ret = ret2;
+ goto error;
}
+ if (ret == -ENOENT && ret2 == -ENOENT)
+ pr_debug("\"%s\" does not hit any event.\n", str);
+ /* Note that this is silently ignored */
+ ret = 0;
error:
if (kfd >= 0) {
strlist__delete(unamelist);
close(ufd);
}
+ free(str);
return ret;
}
dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
end:
if (user) {
- dso__delete(map->dso);
- map__delete(map);
+ map__put(map);
}
exit_symbol_maps();
#include "strlist.h"
#include "strfilter.h"
+/* Probe related configurations */
+struct probe_conf {
+ bool show_ext_vars;
+ bool show_location_range;
+ bool force_add;
+ bool no_inlines;
+ int max_probes;
+};
+extern struct probe_conf probe_conf;
extern bool probe_event_dry_run;
/* kprobe-tracer and uprobe-tracer tracing point */
struct probe_trace_point {
+ char *realname; /* function real name (if needed) */
char *symbol; /* Base symbol */
char *module; /* Module name */
unsigned long offset; /* Offset from symbol */
/* Initialize line range */
extern int line_range__init(struct line_range *lr);
-/* Internal use: Return kernel/module path */
-extern const char *kernel_get_module_path(const char *module);
-
-extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
- int max_probe_points, bool force_add);
-extern int del_perf_probe_events(struct strlist *dellist);
-extern int show_perf_probe_events(void);
+extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int del_perf_probe_events(struct strfilter *filter);
+extern int show_perf_probe_events(struct strfilter *filter);
extern int show_line_range(struct line_range *lr, const char *module,
bool user);
extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
- int max_probe_points, const char *module,
- struct strfilter *filter, bool externs);
+ struct strfilter *filter);
extern int show_available_funcs(const char *module, struct strfilter *filter,
bool user);
+bool arch__prefers_symtab(void);
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+ struct probe_trace_event *tev, struct map *map);
/* Maximum index number of event-name postfix */
#define MAX_EVENT_INDEX 1024
continue;
dinfo = __debuginfo__new(buf);
}
- dso__delete(dso);
+ dso__put(dso);
out:
/* if failed to open all distro debuginfo, open given binary */
Dwarf_Word offs = 0;
bool ref = false;
const char *regs;
- int ret;
+ int ret, ret2 = 0;
if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
goto static_var;
return -EINVAL; /* Broken DIE ? */
if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
ret = dwarf_entrypc(sp_die, &tmp);
- if (ret || addr != tmp ||
- dwarf_tag(vr_die) != DW_TAG_formal_parameter ||
- dwarf_highpc(sp_die, &tmp))
+ if (ret)
+ return -ENOENT;
+
+ if (probe_conf.show_location_range &&
+ (dwarf_tag(vr_die) == DW_TAG_variable)) {
+ ret2 = -ERANGE;
+ } else if (addr != tmp ||
+ dwarf_tag(vr_die) != DW_TAG_formal_parameter) {
+ return -ENOENT;
+ }
+
+ ret = dwarf_highpc(sp_die, &tmp);
+ if (ret)
return -ENOENT;
/*
* This is fuzzed by fentry mcount. We try to find the
if (op->atom == DW_OP_addr) {
static_var:
if (!tvar)
- return 0;
+ return ret2;
/* Static variables on memory (not stack), make @varname */
ret = strlen(dwarf_diename(vr_die));
tvar->value = zalloc(ret + 2);
tvar->ref = alloc_trace_arg_ref((long)offs);
if (tvar->ref == NULL)
return -ENOMEM;
- return 0;
+ return ret2;
}
/* If this is based on frame buffer, set the offset */
}
if (!tvar)
- return 0;
+ return ret2;
regs = get_arch_regstr(regn);
if (!regs) {
/* This should be a bug in DWARF or this tool */
pr_warning("Mapping for the register number %u "
"missing on this architecture.\n", regn);
- return -ERANGE;
+ return -ENOTSUP;
}
tvar->value = strdup(regs);
if (tvar->ref == NULL)
return -ENOMEM;
}
- return 0;
+ return ret2;
}
#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_LONG / sizeof(long))
ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
&pf->sp_die, pf->tvar);
- if (ret == -ENOENT || ret == -EINVAL)
- pr_err("Failed to find the location of %s at this address.\n"
- " Perhaps, it has been optimized out.\n", pf->pvar->var);
- else if (ret == -ENOTSUP)
+ if (ret == -ENOENT || ret == -EINVAL) {
+ pr_err("Failed to find the location of the '%s' variable at this address.\n"
+ " Perhaps it has been optimized out.\n"
+ " Use -V with the --range option to show '%s' location range.\n",
+ pf->pvar->var, pf->pvar->var);
+ } else if (ret == -ENOTSUP)
pr_err("Sorry, we don't support this variable location yet.\n");
else if (ret == 0 && pf->pvar->field) {
ret = convert_variable_fields(vr_die, pf->pvar->var,
/* If not a real subprogram, find a real one */
if (!die_is_func_def(sc_die)) {
if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
- pr_warning("Failed to find probe point in any "
- "functions.\n");
- return -ENOENT;
+ if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
+ pr_warning("Ignoring tail call from %s\n",
+ dwarf_diename(&pf->sp_die));
+ return 0;
+ } else {
+ pr_warning("Failed to find probe point in any "
+ "functions.\n");
+ return -ENOENT;
+ }
}
} else
memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
}
/* If the function name is given, that's what user expects */
if (fsp->function) {
- if (die_compare_name(fn_die, fsp->function)) {
+ if (die_match_name(fn_die, fsp->function)) {
memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
fsp->found = true;
return 1;
/* Check tag and diename */
if (!die_is_func_def(sp_die) ||
- !die_compare_name(sp_die, pp->function))
+ !die_match_name(sp_die, pp->function))
return DWARF_CB_OK;
/* Check declared file */
if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
return DWARF_CB_OK;
+ pr_debug("Matched function: %s\n", dwarf_diename(sp_die));
pf->fname = dwarf_decl_file(sp_die);
if (pp->line) { /* Function relative line */
dwarf_decl_line(sp_die, &pf->lno);
/* TODO: Check the address in this function */
param->retval = call_probe_finder(sp_die, pf);
}
- } else
+ } else if (!probe_conf.no_inlines) {
/* Inlined function: search instances */
param->retval = die_walk_instances(sp_die,
probe_point_inline_cb, (void *)pf);
+ /* This could be a non-existed inline definition */
+ if (param->retval == -ENOENT && strisglob(pp->function))
+ param->retval = 0;
+ }
+
+ /* We need to find other candidates */
+ if (strisglob(pp->function) && param->retval >= 0) {
+ param->retval = 0; /* We have to clear the result */
+ return DWARF_CB_OK;
+ }
return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
}
if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
return DWARF_CB_OK;
- if (die_compare_name(param->sp_die, param->function)) {
+ if (die_match_name(param->sp_die, param->function)) {
if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
return DWARF_CB_OK;
return -ENOMEM;
/* Fastpath: lookup by function name from .debug_pubnames section */
- if (pp->function) {
+ if (pp->function && !strisglob(pp->function)) {
struct pubname_callback_param pubname_param = {
.function = pp->function,
.file = pp->file,
struct local_vars_finder {
struct probe_finder *pf;
struct perf_probe_arg *args;
+ bool vars;
int max_args;
int nargs;
int ret;
tag = dwarf_tag(die_mem);
if (tag == DW_TAG_formal_parameter ||
- tag == DW_TAG_variable) {
+ (tag == DW_TAG_variable && vf->vars)) {
if (convert_variable_location(die_mem, vf->pf->addr,
vf->pf->fb_ops, &pf->sp_die,
NULL) == 0) {
Dwarf_Die die_mem;
int i;
int n = 0;
- struct local_vars_finder vf = {.pf = pf, .args = args,
+ struct local_vars_finder vf = {.pf = pf, .args = args, .vars = false,
.max_args = MAX_PROBE_ARGS, .ret = 0};
for (i = 0; i < pf->pev->nargs; i++) {
/* var never be NULL */
- if (strcmp(pf->pev->args[i].var, "$vars") == 0) {
- pr_debug("Expanding $vars into:");
- vf.nargs = n;
- /* Special local variables */
- die_find_child(sc_die, copy_variables_cb, (void *)&vf,
- &die_mem);
- pr_debug(" (%d)\n", vf.nargs - n);
- if (vf.ret < 0)
- return vf.ret;
- n = vf.nargs;
- } else {
+ if (strcmp(pf->pev->args[i].var, PROBE_ARG_VARS) == 0)
+ vf.vars = true;
+ else if (strcmp(pf->pev->args[i].var, PROBE_ARG_PARAMS) != 0) {
/* Copy normal argument */
args[n] = pf->pev->args[i];
n++;
+ continue;
}
+ pr_debug("Expanding %s into:", pf->pev->args[i].var);
+ vf.nargs = n;
+ /* Special local variables */
+ die_find_child(sc_die, copy_variables_cb, (void *)&vf,
+ &die_mem);
+ pr_debug(" (%d)\n", vf.nargs - n);
+ if (vf.ret < 0)
+ return vf.ret;
+ n = vf.nargs;
}
return n;
}
if (ret < 0)
return ret;
+ tev->point.realname = strdup(dwarf_diename(sc_die));
+ if (!tev->point.realname)
+ return -ENOMEM;
+
pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
tev->point.offset);
/* Find probe_trace_events specified by perf_probe_event from debuginfo */
int debuginfo__find_trace_events(struct debuginfo *dbg,
struct perf_probe_event *pev,
- struct probe_trace_event **tevs, int max_tevs)
+ struct probe_trace_event **tevs)
{
struct trace_event_finder tf = {
.pf = {.pev = pev, .callback = add_probe_trace_event},
- .mod = dbg->mod, .max_tevs = max_tevs};
+ .max_tevs = probe_conf.max_probes, .mod = dbg->mod};
int ret;
/* Allocate result tevs array */
- *tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs);
+ *tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs);
if (*tevs == NULL)
return -ENOMEM;
return (ret < 0) ? ret : tf.ntevs;
}
-#define MAX_VAR_LEN 64
-
/* Collect available variables in this scope */
static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
{
struct available_var_finder *af = data;
struct variable_list *vl;
- char buf[MAX_VAR_LEN];
int tag, ret;
vl = &af->vls[af->nvls - 1];
ret = convert_variable_location(die_mem, af->pf.addr,
af->pf.fb_ops, &af->pf.sp_die,
NULL);
- if (ret == 0) {
- ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
- pr_debug2("Add new var: %s\n", buf);
- if (ret > 0)
- strlist__add(vl->vars, buf);
+ if (ret == 0 || ret == -ERANGE) {
+ int ret2;
+ bool externs = !af->child;
+ struct strbuf buf;
+
+ strbuf_init(&buf, 64);
+
+ if (probe_conf.show_location_range) {
+ if (!externs) {
+ if (ret)
+ strbuf_addf(&buf, "[INV]\t");
+ else
+ strbuf_addf(&buf, "[VAL]\t");
+ } else
+ strbuf_addf(&buf, "[EXT]\t");
+ }
+
+ ret2 = die_get_varname(die_mem, &buf);
+
+ if (!ret2 && probe_conf.show_location_range &&
+ !externs) {
+ strbuf_addf(&buf, "\t");
+ ret2 = die_get_var_range(&af->pf.sp_die,
+ die_mem, &buf);
+ }
+
+ pr_debug("Add new var: %s\n", buf.buf);
+ if (ret2 == 0) {
+ strlist__add(vl->vars,
+ strbuf_detach(&buf, NULL));
+ }
+ strbuf_release(&buf);
}
}
die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem);
/* Find external variables */
- if (!af->externs)
+ if (!probe_conf.show_ext_vars)
goto out;
- /* Don't need to search child DIE for externs. */
+ /* Don't need to search child DIE for external vars. */
af->child = false;
die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem);
*/
int debuginfo__find_available_vars_at(struct debuginfo *dbg,
struct perf_probe_event *pev,
- struct variable_list **vls,
- int max_vls, bool externs)
+ struct variable_list **vls)
{
struct available_var_finder af = {
.pf = {.pev = pev, .callback = add_available_vars},
.mod = dbg->mod,
- .max_vls = max_vls, .externs = externs};
+ .max_vls = probe_conf.max_probes};
int ret;
/* Allocate result vls array */
- *vls = zalloc(sizeof(struct variable_list) * max_vls);
+ *vls = zalloc(sizeof(struct variable_list) * af.max_vls);
if (*vls == NULL)
return -ENOMEM;
return DWARF_CB_OK;
if (die_is_func_def(sp_die) &&
- die_compare_name(sp_die, lr->function)) {
+ die_match_name(sp_die, lr->function)) {
lf->fname = dwarf_decl_file(sp_die);
dwarf_decl_line(sp_die, &lr->offset);
pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
#define MAX_PROBES 128
#define MAX_PROBE_ARGS 128
+#define PROBE_ARG_VARS "$vars"
+#define PROBE_ARG_PARAMS "$params"
+
static inline int is_c_varname(const char *name)
{
/* TODO */
/* Find probe_trace_events specified by perf_probe_event from debuginfo */
extern int debuginfo__find_trace_events(struct debuginfo *dbg,
struct perf_probe_event *pev,
- struct probe_trace_event **tevs,
- int max_tevs);
+ struct probe_trace_event **tevs);
/* Find a perf_probe_point from debuginfo */
extern int debuginfo__find_probe_point(struct debuginfo *dbg,
/* Find available variables */
extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
struct perf_probe_event *pev,
- struct variable_list **vls,
- int max_points, bool externs);
+ struct variable_list **vls);
/* Find a src file from a DWARF tag path */
int get_real_path(const char *raw_path, const char *comp_dir,
struct variable_list *vls; /* Found variable lists */
int nvls; /* Number of variable lists */
int max_vls; /* Max no. of variable lists */
- bool externs; /* Find external vars too */
bool child; /* Search child scopes */
};
pstack->entries[pstack->top] = NULL;
return ret;
}
+
+void *pstack__peek(struct pstack *pstack)
+{
+ if (pstack->top == 0)
+ return NULL;
+ return pstack->entries[pstack->top - 1];
+}
void pstack__remove(struct pstack *pstack, void *key);
void pstack__push(struct pstack *pstack, void *key);
void *pstack__pop(struct pstack *pstack);
+void *pstack__peek(struct pstack *pstack);
#endif /* _PERF_PSTACK_ */
util/xyarray.c
util/cgroup.c
util/rblist.c
+util/stat.c
util/strlist.c
util/trace-event.c
../../lib/rbtree.c
if (!evlist)
return -ENOMEM;
- if (parse_events(evlist, str))
+ if (parse_events(evlist, str, NULL))
goto out_delete;
evsel = perf_evlist__first(evlist);
evsel->attr.comm_exec = 1;
}
- if (evlist->nr_entries > 1) {
+ if (opts->full_auxtrace) {
+ /*
+ * Need to be able to synthesize and parse selected events with
+ * arbitrary sample types, which requires always being able to
+ * match the id.
+ */
+ use_sample_identifier = perf_can_sample_identifier();
+ evlist__for_each(evlist, evsel)
+ perf_evsel__set_sample_id(evsel, use_sample_identifier);
+ } else if (evlist->nr_entries > 1) {
struct perf_evsel *first = perf_evlist__first(evlist);
evlist__for_each(evlist, evsel) {
if (!temp_evlist)
return false;
- err = parse_events(temp_evlist, str);
+ err = parse_events(temp_evlist, str, NULL);
if (err)
goto out_delete;
#include "cpumap.h"
#include "perf_regs.h"
#include "asm/bug.h"
+#include "auxtrace.h"
+#include "thread-stack.h"
-static int machines__deliver_event(struct machines *machines,
- struct perf_evlist *evlist,
- union perf_event *event,
- struct perf_sample *sample,
- struct perf_tool *tool, u64 file_offset);
+static int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool,
+ u64 file_offset);
static int perf_session__open(struct perf_session *session)
{
return ret;
}
- return machines__deliver_event(&session->machines, session->evlist, event->event,
- &sample, session->tool, event->file_offset);
+ return perf_session__deliver_event(session, event->event, &sample,
+ session->tool, event->file_offset);
}
struct perf_session *perf_session__new(struct perf_data_file *file,
session->repipe = repipe;
session->tool = tool;
+ INIT_LIST_HEAD(&session->auxtrace_index);
machines__init(&session->machines);
ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
void perf_session__delete(struct perf_session *session)
{
+ auxtrace__free(session);
+ auxtrace_index__free(&session->auxtrace_index);
perf_session__destroy_kernel_maps(session);
perf_session__delete_threads(session);
perf_session_env__delete(&session->header.env);
return 0;
}
+static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
+static int skipn(int fd, off_t n)
+{
+ char buf[4096];
+ ssize_t ret;
+
+ while (n > 0) {
+ ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
+ if (ret <= 0)
+ return ret;
+ n -= ret;
+ }
+
+ return 0;
+}
+
+static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_session *session
+ __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ if (perf_data_file__is_pipe(session->file))
+ skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+ return event->auxtrace.size;
+}
+
+static
+int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
+ union perf_event *event __maybe_unused,
+ struct perf_session *session __maybe_unused)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
void perf_tool__fill_defaults(struct perf_tool *tool)
{
if (tool->sample == NULL)
tool->exit = process_event_stub;
if (tool->lost == NULL)
tool->lost = perf_event__process_lost;
+ if (tool->lost_samples == NULL)
+ tool->lost_samples = perf_event__process_lost_samples;
+ if (tool->aux == NULL)
+ tool->aux = perf_event__process_aux;
+ if (tool->itrace_start == NULL)
+ tool->itrace_start = perf_event__process_itrace_start;
if (tool->read == NULL)
tool->read = process_event_sample_stub;
if (tool->throttle == NULL)
}
if (tool->id_index == NULL)
tool->id_index = process_id_index_stub;
+ if (tool->auxtrace_info == NULL)
+ tool->auxtrace_info = process_event_auxtrace_info_stub;
+ if (tool->auxtrace == NULL)
+ tool->auxtrace = process_event_auxtrace_stub;
+ if (tool->auxtrace_error == NULL)
+ tool->auxtrace_error = process_event_auxtrace_error_stub;
}
static void swap_sample_id_all(union perf_event *event, void *data)
swap_sample_id_all(event, &event->read + 1);
}
+static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
+{
+ event->aux.aux_offset = bswap_64(event->aux.aux_offset);
+ event->aux.aux_size = bswap_64(event->aux.aux_size);
+ event->aux.flags = bswap_64(event->aux.flags);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->aux + 1);
+}
+
+static void perf_event__itrace_start_swap(union perf_event *event,
+ bool sample_id_all)
+{
+ event->itrace_start.pid = bswap_32(event->itrace_start.pid);
+ event->itrace_start.tid = bswap_32(event->itrace_start.tid);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->itrace_start + 1);
+}
+
static void perf_event__throttle_swap(union perf_event *event,
bool sample_id_all)
{
{
attr->type = bswap_32(attr->type);
attr->size = bswap_32(attr->size);
- attr->config = bswap_64(attr->config);
- attr->sample_period = bswap_64(attr->sample_period);
- attr->sample_type = bswap_64(attr->sample_type);
- attr->read_format = bswap_64(attr->read_format);
- attr->wakeup_events = bswap_32(attr->wakeup_events);
- attr->bp_type = bswap_32(attr->bp_type);
- attr->bp_addr = bswap_64(attr->bp_addr);
- attr->bp_len = bswap_64(attr->bp_len);
- attr->branch_sample_type = bswap_64(attr->branch_sample_type);
- attr->sample_regs_user = bswap_64(attr->sample_regs_user);
- attr->sample_stack_user = bswap_32(attr->sample_stack_user);
- swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
+#define bswap_safe(f, n) \
+ (attr->size > (offsetof(struct perf_event_attr, f) + \
+ sizeof(attr->f) * (n)))
+#define bswap_field(f, sz) \
+do { \
+ if (bswap_safe(f, 0)) \
+ attr->f = bswap_##sz(attr->f); \
+} while(0)
+#define bswap_field_32(f) bswap_field(f, 32)
+#define bswap_field_64(f) bswap_field(f, 64)
+
+ bswap_field_64(config);
+ bswap_field_64(sample_period);
+ bswap_field_64(sample_type);
+ bswap_field_64(read_format);
+ bswap_field_32(wakeup_events);
+ bswap_field_32(bp_type);
+ bswap_field_64(bp_addr);
+ bswap_field_64(bp_len);
+ bswap_field_64(branch_sample_type);
+ bswap_field_64(sample_regs_user);
+ bswap_field_32(sample_stack_user);
+ bswap_field_32(aux_watermark);
+
+ /*
+ * After read_format are bitfields. Check read_format because
+ * we are unable to use offsetof on bitfield.
+ */
+ if (bswap_safe(read_format, 1))
+ swap_bitfield((u8 *) (&attr->read_format + 1),
+ sizeof(u64));
+#undef bswap_field_64
+#undef bswap_field_32
+#undef bswap_field
+#undef bswap_safe
}
static void perf_event__hdr_attr_swap(union perf_event *event,
event->tracing_data.size = bswap_32(event->tracing_data.size);
}
+static void perf_event__auxtrace_info_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ size_t size;
+
+ event->auxtrace_info.type = bswap_32(event->auxtrace_info.type);
+
+ size = event->header.size;
+ size -= (void *)&event->auxtrace_info.priv - (void *)event;
+ mem_bswap_64(event->auxtrace_info.priv, size);
+}
+
+static void perf_event__auxtrace_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ event->auxtrace.size = bswap_64(event->auxtrace.size);
+ event->auxtrace.offset = bswap_64(event->auxtrace.offset);
+ event->auxtrace.reference = bswap_64(event->auxtrace.reference);
+ event->auxtrace.idx = bswap_32(event->auxtrace.idx);
+ event->auxtrace.tid = bswap_32(event->auxtrace.tid);
+ event->auxtrace.cpu = bswap_32(event->auxtrace.cpu);
+}
+
+static void perf_event__auxtrace_error_swap(union perf_event *event,
+ bool sample_id_all __maybe_unused)
+{
+ event->auxtrace_error.type = bswap_32(event->auxtrace_error.type);
+ event->auxtrace_error.code = bswap_32(event->auxtrace_error.code);
+ event->auxtrace_error.cpu = bswap_32(event->auxtrace_error.cpu);
+ event->auxtrace_error.pid = bswap_32(event->auxtrace_error.pid);
+ event->auxtrace_error.tid = bswap_32(event->auxtrace_error.tid);
+ event->auxtrace_error.ip = bswap_64(event->auxtrace_error.ip);
+}
+
typedef void (*perf_event__swap_op)(union perf_event *event,
bool sample_id_all);
[PERF_RECORD_THROTTLE] = perf_event__throttle_swap,
[PERF_RECORD_UNTHROTTLE] = perf_event__throttle_swap,
[PERF_RECORD_SAMPLE] = perf_event__all64_swap,
+ [PERF_RECORD_AUX] = perf_event__aux_swap,
+ [PERF_RECORD_ITRACE_START] = perf_event__itrace_start_swap,
+ [PERF_RECORD_LOST_SAMPLES] = perf_event__all64_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
[PERF_RECORD_HEADER_BUILD_ID] = NULL,
[PERF_RECORD_ID_INDEX] = perf_event__all64_swap,
+ [PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap,
+ [PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap,
+ [PERF_RECORD_AUXTRACE_ERROR] = perf_event__auxtrace_error_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
case PERF_RECORD_MMAP:
return tool->mmap(tool, event, sample, machine);
case PERF_RECORD_MMAP2:
+ if (event->header.misc & PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT)
+ ++evlist->stats.nr_proc_map_timeout;
return tool->mmap2(tool, event, sample, machine);
case PERF_RECORD_COMM:
return tool->comm(tool, event, sample, machine);
if (tool->lost == perf_event__process_lost)
evlist->stats.total_lost += event->lost.lost;
return tool->lost(tool, event, sample, machine);
+ case PERF_RECORD_LOST_SAMPLES:
+ if (tool->lost_samples == perf_event__process_lost_samples)
+ evlist->stats.total_lost_samples += event->lost_samples.lost;
+ return tool->lost_samples(tool, event, sample, machine);
case PERF_RECORD_READ:
return tool->read(tool, event, sample, evsel, machine);
case PERF_RECORD_THROTTLE:
return tool->throttle(tool, event, sample, machine);
case PERF_RECORD_UNTHROTTLE:
return tool->unthrottle(tool, event, sample, machine);
+ case PERF_RECORD_AUX:
+ return tool->aux(tool, event, sample, machine);
+ case PERF_RECORD_ITRACE_START:
+ return tool->itrace_start(tool, event, sample, machine);
default:
++evlist->stats.nr_unknown_events;
return -1;
}
}
+static int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool,
+ u64 file_offset)
+{
+ int ret;
+
+ ret = auxtrace__process_event(session, event, sample, tool);
+ if (ret < 0)
+ return ret;
+ if (ret > 0)
+ return 0;
+
+ return machines__deliver_event(&session->machines, session->evlist,
+ event, sample, tool, file_offset);
+}
+
static s64 perf_session__process_user_event(struct perf_session *session,
union perf_event *event,
u64 file_offset)
return tool->finished_round(tool, event, oe);
case PERF_RECORD_ID_INDEX:
return tool->id_index(tool, event, session);
+ case PERF_RECORD_AUXTRACE_INFO:
+ return tool->auxtrace_info(tool, event, session);
+ case PERF_RECORD_AUXTRACE:
+ /* setup for reading amidst mmap */
+ lseek(fd, file_offset + event->header.size, SEEK_SET);
+ return tool->auxtrace(tool, event, session);
+ case PERF_RECORD_AUXTRACE_ERROR:
+ perf_session__auxtrace_error_inc(session, event);
+ return tool->auxtrace_error(tool, event, session);
default:
return -EINVAL;
}
return -1;
if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
- readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+ readn(fd, buf, hdr_sz) != (ssize_t)hdr_sz)
return -1;
event = (union perf_event *)buf;
if (session->header.needs_swap)
perf_event_header__bswap(&event->header);
- if (event->header.size < hdr_sz)
+ if (event->header.size < hdr_sz || event->header.size > buf_sz)
return -1;
rest = event->header.size - hdr_sz;
- if (readn(fd, &buf, rest) != (ssize_t)rest)
+ if (readn(fd, buf, rest) != (ssize_t)rest)
return -1;
if (session->header.needs_swap)
return ret;
}
- return machines__deliver_event(&session->machines, evlist, event,
- &sample, tool, file_offset);
+ return perf_session__deliver_event(session, event, &sample, tool,
+ file_offset);
}
void perf_event_header__bswap(struct perf_event_header *hdr)
stats->nr_events[PERF_RECORD_LOST]);
}
+ if (session->tool->lost_samples == perf_event__process_lost_samples) {
+ double drop_rate;
+
+ drop_rate = (double)stats->total_lost_samples /
+ (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
+ if (drop_rate > 0.05) {
+ ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n",
+ stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
+ drop_rate * 100.0);
+ }
+ }
+
if (stats->nr_unknown_events != 0) {
ui__warning("Found %u unknown events!\n\n"
"Is this an older tool processing a perf.data "
if (oe->nr_unordered_events != 0)
ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+
+ events_stats__auxtrace_error_warn(stats);
+
+ if (stats->nr_proc_map_timeout != 0) {
+ ui__warning("%d map information files for pre-existing threads were\n"
+ "not processed, if there are samples for addresses they\n"
+ "will not be resolved, you may find out which are these\n"
+ "threads by running with -v and redirecting the output\n"
+ "to a file.\n"
+ "The time limit to process proc map is too short?\n"
+ "Increase it by --proc-map-timeout\n",
+ stats->nr_proc_map_timeout);
+ }
+}
+
+static int perf_session__flush_thread_stack(struct thread *thread,
+ void *p __maybe_unused)
+{
+ return thread_stack__flush(thread);
+}
+
+static int perf_session__flush_thread_stacks(struct perf_session *session)
+{
+ return machines__for_each_thread(&session->machines,
+ perf_session__flush_thread_stack,
+ NULL);
}
volatile int session_done;
done:
/* do the final flush for ordered samples */
err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+ if (err)
+ goto out_err;
+ err = auxtrace__flush_events(session, tool);
+ if (err)
+ goto out_err;
+ err = perf_session__flush_thread_stacks(session);
out_err:
free(buf);
perf_session__warn_about_errors(session);
ordered_events__free(&session->ordered_events);
+ auxtrace__free_events(session);
return err;
}
out:
/* do the final flush for ordered samples */
err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+ if (err)
+ goto out_err;
+ err = auxtrace__flush_events(session, tool);
+ if (err)
+ goto out_err;
+ err = perf_session__flush_thread_stacks(session);
out_err:
ui_progress__finish();
perf_session__warn_about_errors(session);
ordered_events__free(&session->ordered_events);
+ auxtrace__free_events(session);
session->one_mmap = false;
return err;
}
size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
{
- size_t ret = fprintf(fp, "Aggregated stats:\n");
+ size_t ret;
+ const char *msg = "";
+
+ if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+ msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
+
+ ret = fprintf(fp, "Aggregated stats:%s\n", msg);
ret += events_stats__fprintf(&session->evlist->stats, fp);
return ret;
struct ip_callchain;
struct thread;
+struct auxtrace;
+struct itrace_synth_opts;
+
struct perf_session {
struct perf_header header;
struct machines machines;
struct perf_evlist *evlist;
+ struct auxtrace *auxtrace;
+ struct itrace_synth_opts *itrace_synth_opts;
+ struct list_head auxtrace_index;
struct trace_event tevent;
bool repipe;
bool one_mmap;
sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
{
/* Compare the addr that should be unique among comm */
- return comm__str(right->comm) - comm__str(left->comm);
+ return strcmp(comm__str(right->comm), comm__str(left->comm));
}
static int64_t
sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
{
/* Compare the addr that should be unique among comm */
- return comm__str(right->comm) - comm__str(left->comm);
+ return strcmp(comm__str(right->comm), comm__str(left->comm));
}
static int64_t
static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
{
- u64 ip_l, ip_r;
-
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
if (sym_l == sym_r)
return 0;
- ip_l = sym_l->start;
- ip_r = sym_r->start;
+ if (sym_l->start != sym_r->start)
+ return (int64_t)(sym_r->start - sym_l->start);
- return (int64_t)(ip_r - ip_l);
+ return (int64_t)(sym_r->end - sym_l->end);
}
static int64_t
struct hist_entry_diff {
bool computed;
+ union {
+ /* PERF_HPP__DELTA */
+ double period_ratio_delta;
- /* PERF_HPP__DELTA */
- double period_ratio_delta;
-
- /* PERF_HPP__RATIO */
- double period_ratio;
+ /* PERF_HPP__RATIO */
+ double period_ratio;
- /* HISTC_WEIGHTED_DIFF */
- s64 wdiff;
+ /* HISTC_WEIGHTED_DIFF */
+ s64 wdiff;
+ };
};
/**
s32 cpu;
u8 cpumode;
- struct hist_entry_diff diff;
-
/* We are added by hists__add_dummy_entry. */
bool dummy;
- /* XXX These two should move to some tree widget lib */
- u16 row_offset;
- u16 nr_rows;
-
- bool init_have_children;
char level;
u8 filtered;
+ union {
+ /*
+ * Since perf diff only supports the stdio output, TUI
+ * fields are only accessed from perf report (or perf
+ * top). So make it an union to reduce memory usage.
+ */
+ struct hist_entry_diff diff;
+ struct /* for TUI */ {
+ u16 row_offset;
+ u16 nr_rows;
+ bool init_have_children;
+ bool unfolded;
+ bool has_children;
+ };
+ };
char *srcline;
struct symbol *parent;
- unsigned long position;
struct rb_root sorted_chain;
struct branch_info *branch_info;
struct hists *hists;
--- /dev/null
+#include <stdio.h>
+#include "evsel.h"
+#include "stat.h"
+#include "color.h"
+
+enum {
+ CTX_BIT_USER = 1 << 0,
+ CTX_BIT_KERNEL = 1 << 1,
+ CTX_BIT_HV = 1 << 2,
+ CTX_BIT_HOST = 1 << 3,
+ CTX_BIT_IDLE = 1 << 4,
+ CTX_BIT_MAX = 1 << 5,
+};
+
+#define NUM_CTX CTX_BIT_MAX
+
+static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+
+struct stats walltime_nsecs_stats;
+
+static int evsel_context(struct perf_evsel *evsel)
+{
+ int ctx = 0;
+
+ if (evsel->attr.exclude_kernel)
+ ctx |= CTX_BIT_KERNEL;
+ if (evsel->attr.exclude_user)
+ ctx |= CTX_BIT_USER;
+ if (evsel->attr.exclude_hv)
+ ctx |= CTX_BIT_HV;
+ if (evsel->attr.exclude_host)
+ ctx |= CTX_BIT_HOST;
+ if (evsel->attr.exclude_idle)
+ ctx |= CTX_BIT_IDLE;
+
+ return ctx;
+}
+
+void perf_stat__reset_shadow_stats(void)
+{
+ memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
+ memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
+ memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
+ memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
+ memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
+ memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
+ memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
+ memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
+ memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
+ memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
+ memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
+ memset(runtime_cycles_in_tx_stats, 0,
+ sizeof(runtime_cycles_in_tx_stats));
+ memset(runtime_transaction_stats, 0,
+ sizeof(runtime_transaction_stats));
+ memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
+ memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
+
+/*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+ int cpu)
+{
+ int ctx = evsel_context(counter);
+
+ if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+ update_stats(&runtime_nsecs_stats[cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+ update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+ else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
+ update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+ else if (perf_stat_evsel__is(counter, TRANSACTION_START))
+ update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+ else if (perf_stat_evsel__is(counter, ELISION_START))
+ update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+ update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+ update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+ update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+ update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+ update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+ update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+ update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+}
+
+/* used for get_ratio_color() */
+enum grc_type {
+ GRC_STALLED_CYCLES_FE,
+ GRC_STALLED_CYCLES_BE,
+ GRC_CACHE_MISSES,
+ GRC_MAX_NR
+};
+
+static const char *get_ratio_color(enum grc_type type, double ratio)
+{
+ static const double grc_table[GRC_MAX_NR][3] = {
+ [GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
+ [GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
+ [GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 },
+ };
+ const char *color = PERF_COLOR_NORMAL;
+
+ if (ratio > grc_table[type][0])
+ color = PERF_COLOR_RED;
+ else if (ratio > grc_table[type][1])
+ color = PERF_COLOR_MAGENTA;
+ else if (ratio > grc_table[type][2])
+ color = PERF_COLOR_YELLOW;
+
+ return color;
+}
+
+static void print_stalled_cycles_frontend(FILE *out, int cpu,
+ struct perf_evsel *evsel
+ __maybe_unused, double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " frontend cycles idle ");
+}
+
+static void print_stalled_cycles_backend(FILE *out, int cpu,
+ struct perf_evsel *evsel
+ __maybe_unused, double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " backend cycles idle ");
+}
+
+static void print_branch_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_branches_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all branches ");
+}
+
+static void print_l1_dcache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all L1-dcache hits ");
+}
+
+static void print_l1_icache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all L1-icache hits ");
+}
+
+static void print_dtlb_cache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all LL-cache hits ");
+}
+
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+ double avg, int cpu, enum aggr_mode aggr)
+{
+ double total, ratio = 0.0, total2;
+ int ctx = evsel_context(evsel);
+
+ if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ if (total) {
+ ratio = avg / total;
+ fprintf(out, " # %5.2f insns per cycle ", ratio);
+ } else {
+ fprintf(out, " ");
+ }
+ total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
+ total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
+
+ if (total && avg) {
+ ratio = total / avg;
+ fprintf(out, "\n");
+ if (aggr == AGGR_NONE)
+ fprintf(out, " ");
+ fprintf(out, " # %5.2f stalled cycles per insn", ratio);
+ }
+
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
+ runtime_branches_stats[ctx][cpu].n != 0) {
+ print_branch_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_l1_dcache_stats[ctx][cpu].n != 0) {
+ print_l1_dcache_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_l1_icache_stats[ctx][cpu].n != 0) {
+ print_l1_icache_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
+ print_dtlb_cache_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_itlb_cache_stats[ctx][cpu].n != 0) {
+ print_itlb_cache_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_ll_cache_stats[ctx][cpu].n != 0) {
+ print_ll_cache_misses(out, cpu, evsel, avg);
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+ runtime_cacherefs_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg * 100 / total;
+
+ fprintf(out, " # %8.3f %% of all cache refs ", ratio);
+
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+ print_stalled_cycles_frontend(out, cpu, evsel, avg);
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+ print_stalled_cycles_backend(out, cpu, evsel, avg);
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+ total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+ if (total) {
+ ratio = avg / total;
+ fprintf(out, " # %8.3f GHz ", ratio);
+ } else {
+ fprintf(out, " ");
+ }
+ } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ if (total)
+ fprintf(out,
+ " # %5.2f%% transactional cycles ",
+ 100.0 * (avg / total));
+ } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+ if (total2 < avg)
+ total2 = avg;
+ if (total)
+ fprintf(out,
+ " # %5.2f%% aborted cycles ",
+ 100.0 * ((total2-avg) / total));
+ } else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
+ avg > 0 &&
+ runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+ if (total)
+ ratio = total / avg;
+
+ fprintf(out, " # %8.0f cycles / transaction ", ratio);
+ } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
+ avg > 0 &&
+ runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+ if (total)
+ ratio = total / avg;
+
+ fprintf(out, " # %8.0f cycles / elision ", ratio);
+ } else if (runtime_nsecs_stats[cpu].n != 0) {
+ char unit = 'M';
+
+ total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+ if (total)
+ ratio = 1000.0 * avg / total;
+ if (ratio < 0.001) {
+ ratio *= 1000;
+ unit = 'K';
+ }
+
+ fprintf(out, " # %8.3f %c/sec ", ratio, unit);
+ } else {
+ fprintf(out, " ");
+ }
+}
#include <math.h>
-
#include "stat.h"
+#include "evsel.h"
void update_stats(struct stats *stats, u64 val)
{
return pct;
}
+
+bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+ enum perf_stat_evsel_id id)
+{
+ struct perf_stat *ps = evsel->priv;
+
+ return ps->id == id;
+}
+
+#define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name
+static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
+ ID(NONE, x),
+ ID(CYCLES_IN_TX, cpu/cycles-t/),
+ ID(TRANSACTION_START, cpu/tx-start/),
+ ID(ELISION_START, cpu/el-start/),
+ ID(CYCLES_IN_TX_CP, cpu/cycles-ct/),
+};
+#undef ID
+
+void perf_stat_evsel_id_init(struct perf_evsel *evsel)
+{
+ struct perf_stat *ps = evsel->priv;
+ int i;
+
+ /* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
+
+ for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
+ if (!strcmp(perf_evsel__name(evsel), id_str[i])) {
+ ps->id = i;
+ break;
+ }
+ }
+}
+
+struct perf_counts *perf_counts__new(int ncpus)
+{
+ int size = sizeof(struct perf_counts) +
+ ncpus * sizeof(struct perf_counts_values);
+
+ return zalloc(size);
+}
+
+void perf_counts__delete(struct perf_counts *counts)
+{
+ free(counts);
+}
+
+static void perf_counts__reset(struct perf_counts *counts, int ncpus)
+{
+ memset(counts, 0, (sizeof(*counts) +
+ (ncpus * sizeof(struct perf_counts_values))));
+}
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+{
+ perf_counts__reset(evsel->counts, ncpus);
+}
+
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+{
+ evsel->counts = perf_counts__new(ncpus);
+ return evsel->counts != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_counts(struct perf_evsel *evsel)
+{
+ perf_counts__delete(evsel->counts);
+ evsel->counts = NULL;
+}
#define __PERF_STATS_H
#include <linux/types.h>
+#include <stdio.h>
struct stats
{
u64 max, min;
};
+enum perf_stat_evsel_id {
+ PERF_STAT_EVSEL_ID__NONE = 0,
+ PERF_STAT_EVSEL_ID__CYCLES_IN_TX,
+ PERF_STAT_EVSEL_ID__TRANSACTION_START,
+ PERF_STAT_EVSEL_ID__ELISION_START,
+ PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
+ PERF_STAT_EVSEL_ID__MAX,
+};
+
+struct perf_stat {
+ struct stats res_stats[3];
+ enum perf_stat_evsel_id id;
+};
+
+enum aggr_mode {
+ AGGR_NONE,
+ AGGR_GLOBAL,
+ AGGR_SOCKET,
+ AGGR_CORE,
+};
+
void update_stats(struct stats *stats, u64 val);
double avg_stats(struct stats *stats);
double stddev_stats(struct stats *stats);
stats->min = (u64) -1;
stats->max = 0;
}
+
+struct perf_evsel;
+bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+ enum perf_stat_evsel_id id);
+
+#define perf_stat_evsel__is(evsel, id) \
+ __perf_evsel_stat__is(evsel, PERF_STAT_EVSEL_ID__ ## id)
+
+void perf_stat_evsel_id_init(struct perf_evsel *evsel);
+
+extern struct stats walltime_nsecs_stats;
+
+void perf_stat__reset_shadow_stats(void);
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+ int cpu);
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+ double avg, int cpu, enum aggr_mode aggr);
+
+struct perf_counts *perf_counts__new(int ncpus);
+void perf_counts__delete(struct perf_counts *counts);
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__free_counts(struct perf_evsel *evsel);
#endif
return filter;
}
+static int strfilter__append(struct strfilter *filter, bool _or,
+ const char *rules, const char **err)
+{
+ struct strfilter_node *right, *root;
+ const char *ep = NULL;
+
+ if (!filter || !rules)
+ return -EINVAL;
+
+ right = strfilter_node__new(rules, &ep);
+ if (!right || *ep != '\0') {
+ if (err)
+ *err = ep;
+ goto error;
+ }
+ root = strfilter_node__alloc(_or ? OP_or : OP_and, filter->root, right);
+ if (!root) {
+ ep = NULL;
+ goto error;
+ }
+
+ filter->root = root;
+ return 0;
+
+error:
+ strfilter_node__delete(right);
+ return ep ? -EINVAL : -ENOMEM;
+}
+
+int strfilter__or(struct strfilter *filter, const char *rules, const char **err)
+{
+ return strfilter__append(filter, true, rules, err);
+}
+
+int strfilter__and(struct strfilter *filter, const char *rules,
+ const char **err)
+{
+ return strfilter__append(filter, false, rules, err);
+}
+
static bool strfilter_node__compare(struct strfilter_node *node,
const char *str)
{
return false;
return strfilter_node__compare(filter->root, str);
}
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf);
+
+/* sprint node in parenthesis if needed */
+static int strfilter_node__sprint_pt(struct strfilter_node *node, char *buf)
+{
+ int len;
+ int pt = node->r ? 2 : 0; /* don't need to check node->l */
+
+ if (buf && pt)
+ *buf++ = '(';
+ len = strfilter_node__sprint(node, buf);
+ if (len < 0)
+ return len;
+ if (buf && pt)
+ *(buf + len) = ')';
+ return len + pt;
+}
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
+{
+ int len = 0, rlen;
+
+ if (!node || !node->p)
+ return -EINVAL;
+
+ switch (*node->p) {
+ case '|':
+ case '&':
+ len = strfilter_node__sprint_pt(node->l, buf);
+ if (len < 0)
+ return len;
+ case '!':
+ if (buf) {
+ *(buf + len++) = *node->p;
+ buf += len;
+ } else
+ len++;
+ rlen = strfilter_node__sprint_pt(node->r, buf);
+ if (rlen < 0)
+ return rlen;
+ len += rlen;
+ break;
+ default:
+ len = strlen(node->p);
+ if (buf)
+ strcpy(buf, node->p);
+ }
+
+ return len;
+}
+
+char *strfilter__string(struct strfilter *filter)
+{
+ int len;
+ char *ret = NULL;
+
+ len = strfilter_node__sprint(filter->root, NULL);
+ if (len < 0)
+ return NULL;
+
+ ret = malloc(len + 1);
+ if (ret)
+ strfilter_node__sprint(filter->root, ret);
+
+ return ret;
+}
*/
struct strfilter *strfilter__new(const char *rules, const char **err);
+/**
+ * strfilter__or - Append an additional rule by logical-or
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ * @filter by using logical-or.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-or.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__or(struct strfilter *filter,
+ const char *rules, const char **err);
+
+/**
+ * strfilter__add - Append an additional rule by logical-and
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ * @filter by using logical-and.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-and.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__and(struct strfilter *filter,
+ const char *rules, const char **err);
+
/**
* strfilter__compare - compare given string and a string filter
* @filter: String filter
*/
void strfilter__delete(struct strfilter *filter);
+/**
+ * strfilter__string - Reconstruct a rule string from filter
+ * @filter: String filter to reconstruct
+ *
+ * Reconstruct a rule string from @filter. This will be good for
+ * debug messages. Note that returning string must be freed afterward.
+ */
+char *strfilter__string(struct strfilter *filter);
+
#endif
close(ss->fd);
}
+bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+ return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL;
+}
+
int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
enum dso_binary_type type)
{
}
if (!dso__build_id_equal(dso, build_id)) {
+ pr_debug("%s: build id mismatch for %s.\n", __func__, name);
dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
goto out_elf_end;
}
".gnu.prelink_undo",
NULL) != NULL);
} else {
- ss->adjust_symbols = ehdr.e_type == ET_EXEC ||
- ehdr.e_type == ET_REL;
+ ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
}
ss->name = strdup(name);
return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
}
+void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { }
+
int dso__load_sym(struct dso *dso, struct map *map,
struct symsrc *syms_ss, struct symsrc *runtime_ss,
symbol_filter_t filter, int kmodule)
(sym.st_value & 1))
--sym.st_value;
+ arch__elf_sym_adjust(&sym);
+
if (dso->kernel || kmodule) {
char dso_name[PATH_MAX];
map->unmap_ip = map__unmap_ip;
/* Ensure maps are correctly ordered */
if (kmaps) {
+ map__get(map);
map_groups__remove(kmaps, map);
map_groups__insert(kmaps, map);
+ map__put(map);
}
}
curr_map = map__new2(start, curr_dso,
map->type);
if (curr_map == NULL) {
- dso__delete(curr_dso);
+ dso__put(curr_dso);
goto out_elf_end;
}
if (adjust_kernel_syms) {
}
curr_dso->symtab_type = dso->symtab_type;
map_groups__insert(kmaps, curr_map);
- /*
- * The new DSO should go to the kernel DSOS
- */
- dsos__add(&map->groups->machine->kernel_dsos,
- curr_dso);
+ dsos__add(&map->groups->machine->dsos, curr_dso);
dso__set_loaded(curr_dso, map->type);
} else
curr_dso = curr_map->dso;
return tail - str;
}
-#define SYMBOL_A 0
-#define SYMBOL_B 1
+int __weak arch__choose_best_symbol(struct symbol *syma,
+ struct symbol *symb __maybe_unused)
+{
+ /* Avoid "SyS" kernel syscall aliases */
+ if (strlen(syma->name) >= 3 && !strncmp(syma->name, "SyS", 3))
+ return SYMBOL_B;
+ if (strlen(syma->name) >= 10 && !strncmp(syma->name, "compat_SyS", 10))
+ return SYMBOL_B;
+
+ return SYMBOL_A;
+}
static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
{
else if (na < nb)
return SYMBOL_B;
- /* Avoid "SyS" kernel syscall aliases */
- if (na >= 3 && !strncmp(syma->name, "SyS", 3))
- return SYMBOL_B;
- if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10))
- return SYMBOL_B;
-
- return SYMBOL_A;
+ return arch__choose_best_symbol(syma, symb);
}
void symbols__fixup_duplicate(struct rb_root *symbols)
void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
{
- struct map *prev, *curr;
- struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
+ struct maps *maps = &mg->maps[type];
+ struct map *next, *curr;
- if (prevnd == NULL)
- return;
+ pthread_rwlock_wrlock(&maps->lock);
- curr = rb_entry(prevnd, struct map, rb_node);
+ curr = maps__first(maps);
+ if (curr == NULL)
+ goto out_unlock;
- for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
- prev = curr;
- curr = rb_entry(nd, struct map, rb_node);
- prev->end = curr->start;
+ for (next = map__next(curr); next; next = map__next(curr)) {
+ curr->end = next->start;
+ curr = next;
}
/*
* last map final address.
*/
curr->end = ~0ULL;
+
+out_unlock:
+ pthread_rwlock_unlock(&maps->lock);
}
struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
const char *name)
{
struct rb_node *n;
- struct symbol_name_rb_node *s;
+ struct symbol_name_rb_node *s = NULL;
if (symbols == NULL)
return NULL;
int cmp;
s = rb_entry(n, struct symbol_name_rb_node, rb_node);
- cmp = strcmp(name, s->sym.name);
+ cmp = arch__compare_symbol_names(name, s->sym.name);
if (cmp < 0)
n = n->rb_left;
struct symbol_name_rb_node *tmp;
tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
- if (strcmp(tmp->sym.name, s->sym.name))
+ if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
break;
s = tmp;
curr_map = map_groups__find(kmaps, map->type, pos->start);
if (!curr_map || (filter && filter(curr_map, pos))) {
- rb_erase(&pos->rb_node, root);
+ rb_erase_init(&pos->rb_node, root);
symbol__delete(pos);
} else {
pos->start -= curr_map->start - curr_map->pgoff;
if (pos->end)
pos->end -= curr_map->start - curr_map->pgoff;
if (curr_map != map) {
- rb_erase(&pos->rb_node, root);
+ rb_erase_init(&pos->rb_node, root);
symbols__insert(
&curr_map->dso->symbols[curr_map->type],
pos);
curr_map = map__new2(pos->start, ndso, map->type);
if (curr_map == NULL) {
- dso__delete(ndso);
+ dso__put(ndso);
return -1;
}
/* Add new maps */
while (!list_empty(&md.maps)) {
new_map = list_entry(md.maps.next, struct map, node);
- list_del(&new_map->node);
+ list_del_init(&new_map->node);
if (new_map == replacement_map) {
map->start = new_map->start;
map->end = new_map->end;
map->pgoff = new_map->pgoff;
map->map_ip = new_map->map_ip;
map->unmap_ip = new_map->unmap_ip;
- map__delete(new_map);
/* Ensure maps are correctly ordered */
+ map__get(map);
map_groups__remove(kmaps, map);
map_groups__insert(kmaps, map);
+ map__put(map);
} else {
map_groups__insert(kmaps, new_map);
}
+
+ map__put(new_map);
}
/*
out_err:
while (!list_empty(&md.maps)) {
map = list_entry(md.maps.next, struct map, node);
- list_del(&map->node);
- map__delete(map);
+ list_del_init(&map->node);
+ map__put(map);
}
close(fd);
return -EINVAL;
case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
/*
* kernel modules know their symtab type - it's set when
- * creating a module dso in machine__new_module().
+ * creating a module dso in machine__findnew_module_map().
*/
return kmod && dso->symtab_type == type;
struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
bool kmod;
- dso__set_loaded(dso, map->type);
+ pthread_mutex_lock(&dso->lock);
+
+ /* check again under the dso->lock */
+ if (dso__loaded(dso, map->type)) {
+ ret = 1;
+ goto out;
+ }
- if (dso->kernel == DSO_TYPE_KERNEL)
- return dso__load_kernel_sym(dso, map, filter);
- else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
- return dso__load_guest_kernel_sym(dso, map, filter);
+ if (dso->kernel) {
+ if (dso->kernel == DSO_TYPE_KERNEL)
+ ret = dso__load_kernel_sym(dso, map, filter);
+ else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+ ret = dso__load_guest_kernel_sym(dso, map, filter);
+
+ goto out;
+ }
if (map->groups && map->groups->machine)
machine = map->groups->machine;
struct stat st;
if (lstat(dso->name, &st) < 0)
- return -1;
+ goto out;
if (st.st_uid && (st.st_uid != geteuid())) {
pr_warning("File %s not owned by current user or root, "
"ignoring it.\n", dso->name);
- return -1;
+ goto out;
}
ret = dso__load_perf_map(dso, map, filter);
dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
DSO_BINARY_TYPE__NOT_FOUND;
- return ret;
+ goto out;
}
if (machine)
name = malloc(PATH_MAX);
if (!name)
- return -1;
+ goto out;
kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
out_free:
free(name);
if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
- return 0;
+ ret = 0;
+out:
+ dso__set_loaded(dso, map->type);
+ pthread_mutex_unlock(&dso->lock);
+
return ret;
}
struct map *map_groups__find_by_name(struct map_groups *mg,
enum map_type type, const char *name)
{
- struct rb_node *nd;
+ struct maps *maps = &mg->maps[type];
+ struct map *map;
- for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
- struct map *map = rb_entry(nd, struct map, rb_node);
+ pthread_rwlock_rdlock(&maps->lock);
+ for (map = maps__first(maps); map; map = map__next(map)) {
if (map->dso && strcmp(map->dso->short_name, name) == 0)
- return map;
+ goto out_unlock;
}
- return NULL;
+ map = NULL;
+
+out_unlock:
+ pthread_rwlock_unlock(&maps->lock);
+ return map;
}
int dso__load_vmlinux(struct dso *dso, struct map *map,
{
while (--vmlinux_path__nr_entries >= 0)
zfree(&vmlinux_path[vmlinux_path__nr_entries]);
+ vmlinux_path__nr_entries = 0;
zfree(&vmlinux_path);
}
struct map_symbol {
struct map *map;
struct symbol *sym;
- bool unfolded;
- bool has_children;
};
struct addr_map_symbol {
int setup_intlist(struct intlist **list, const char *list_str,
const char *list_name);
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
+void arch__elf_sym_adjust(GElf_Sym *sym);
+#endif
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
+
#endif /* __PERF_SYMBOL */
return crp->process(&cr, crp->data);
}
-static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
{
struct call_return_processor *crp = ts->crp;
int err;
return 0;
}
+int thread_stack__flush(struct thread *thread)
+{
+ if (thread->ts)
+ return __thread_stack__flush(thread, thread->ts);
+
+ return 0;
+}
+
int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
u64 to_ip, u16 insn_len, u64 trace_nr)
{
*/
if (trace_nr != thread->ts->trace_nr) {
if (thread->ts->trace_nr)
- thread_stack__flush(thread, thread->ts);
+ __thread_stack__flush(thread, thread->ts);
thread->ts->trace_nr = trace_nr;
}
if (trace_nr != thread->ts->trace_nr) {
if (thread->ts->trace_nr)
- thread_stack__flush(thread, thread->ts);
+ __thread_stack__flush(thread, thread->ts);
thread->ts->trace_nr = trace_nr;
}
}
void thread_stack__free(struct thread *thread)
{
if (thread->ts) {
- thread_stack__flush(thread, thread->ts);
+ __thread_stack__flush(thread, thread->ts);
zfree(&thread->ts->stack);
zfree(&thread->ts);
}
/* Flush stack on exec */
if (ts->comm != comm && thread->pid_ == thread->tid) {
- err = thread_stack__flush(thread, ts);
+ err = __thread_stack__flush(thread, ts);
if (err)
return err;
ts->comm = comm;
void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
size_t sz, u64 ip);
+int thread_stack__flush(struct thread *thread);
void thread_stack__free(struct thread *thread);
struct call_return_processor *
if (pid == thread->tid || pid == -1) {
thread->mg = map_groups__new(machine);
} else {
- leader = machine__findnew_thread(machine, pid, pid);
+ leader = __machine__findnew_thread(machine, pid, pid);
if (leader)
thread->mg = map_groups__get(leader->mg);
}
goto err_thread;
list_add(&comm->list, &thread->comm_list);
-
+ atomic_set(&thread->refcnt, 0);
+ RB_CLEAR_NODE(&thread->rb_node);
}
return thread;
{
struct comm *comm, *tmp;
+ BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
+
thread_stack__free(thread);
if (thread->mg) {
struct thread *thread__get(struct thread *thread)
{
- ++thread->refcnt;
+ if (thread)
+ atomic_inc(&thread->refcnt);
return thread;
}
void thread__put(struct thread *thread)
{
- if (thread && --thread->refcnt == 0) {
+ if (thread && atomic_dec_and_test(&thread->refcnt)) {
list_del_init(&thread->node);
thread__delete(thread);
}
#ifndef __PERF_THREAD_H
#define __PERF_THREAD_H
+#include <linux/atomic.h>
#include <linux/rbtree.h>
#include <linux/list.h>
#include <unistd.h>
pid_t tid;
pid_t ppid;
int cpu;
- int refcnt;
+ atomic_t refcnt;
char shortname[3];
bool comm_set;
+ int comm_len;
bool dead; /* if set thread has exited */
struct list_head comm_list;
- int comm_len;
u64 db_id;
void *priv;
return 1;
}
+static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
+{
+ size_t size = sizeof(*map) + sizeof(pid_t) * nr;
+
+ return realloc(map, size);
+}
+
+#define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
+
struct thread_map *thread_map__new_by_pid(pid_t pid)
{
struct thread_map *threads;
if (items <= 0)
return NULL;
- threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+ threads = thread_map__alloc(items);
if (threads != NULL) {
for (i = 0; i < items; i++)
threads->map[i] = atoi(namelist[i]->d_name);
struct thread_map *thread_map__new_by_tid(pid_t tid)
{
- struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+ struct thread_map *threads = thread_map__alloc(1);
if (threads != NULL) {
threads->map[0] = tid;
int max_threads = 32, items, i;
char path[256];
struct dirent dirent, *next, **namelist = NULL;
- struct thread_map *threads = malloc(sizeof(*threads) +
- max_threads * sizeof(pid_t));
+ struct thread_map *threads = thread_map__alloc(max_threads);
+
if (threads == NULL)
goto out;
goto out_free_threads;
total_tasks += items;
- nt = realloc(threads, (sizeof(*threads) +
- sizeof(pid_t) * total_tasks));
+ nt = thread_map__realloc(threads, total_tasks);
if (nt == NULL)
goto out_free_namelist;
struct thread_map *thread_map__new_dummy(void)
{
- struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+ struct thread_map *threads = thread_map__alloc(1);
if (threads != NULL) {
threads->map[0] = -1;
continue;
ntasks++;
- nt = realloc(threads, sizeof(*threads) + sizeof(pid_t) * ntasks);
+ nt = thread_map__realloc(threads, ntasks);
if (nt == NULL)
goto out_free_threads;
#include <stdbool.h>
+#include <linux/types.h>
+
struct perf_session;
union perf_event;
struct perf_evlist;
typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
struct ordered_events *oe);
+typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
+ struct perf_session *session);
+
struct perf_tool {
event_sample sample,
read;
fork,
exit,
lost,
+ lost_samples,
+ aux,
+ itrace_start,
throttle,
unthrottle;
event_attr_op attr;
event_op2 tracing_data;
event_oe finished_round;
event_op2 build_id,
- id_index;
+ id_index,
+ auxtrace_info,
+ auxtrace_error;
+ event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;
};
char *line;
char *next = NULL;
char *addr_str;
- char *fmt;
+ char *fmt = NULL;
line = strtok_r(file, "\n", &next);
while (line) {
u64 offset = dso->data.eh_frame_hdr_offset;
if (offset == 0) {
- fd = dso__data_fd(dso, machine);
+ fd = dso__data_get_fd(dso, machine);
if (fd < 0)
return -EINVAL;
/* Check the .eh_frame section for unwinding info */
offset = elf_section_offset(fd, ".eh_frame_hdr");
dso->data.eh_frame_hdr_offset = offset;
+ dso__data_put_fd(dso);
}
if (offset)
u64 ofs = dso->data.debug_frame_offset;
if (ofs == 0) {
- fd = dso__data_fd(dso, machine);
+ fd = dso__data_get_fd(dso, machine);
if (fd < 0)
return -EINVAL;
/* Check the .debug_frame section for unwinding info */
ofs = elf_section_offset(fd, ".debug_frame");
dso->data.debug_frame_offset = ofs;
+ dso__data_put_fd(dso);
}
*offset = ofs;
#ifndef NO_LIBUNWIND_DEBUG_FRAME
/* Check the .debug_frame section for unwinding info */
if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
- int fd = dso__data_fd(map->dso, ui->machine);
+ int fd = dso__data_get_fd(map->dso, ui->machine);
int is_exec = elf_is_exec(fd, map->dso->name);
unw_word_t base = is_exec ? 0 : map->start;
+ if (fd >= 0)
+ dso__data_put_fd(map->dso);
+
memset(&di, 0, sizeof(di));
if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
map->start, map->end))
return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
}
-static int slow_copyfile(const char *from, const char *to, mode_t mode)
+int rm_rf(char *path)
+{
+ DIR *dir;
+ int ret = 0;
+ struct dirent *d;
+ char namebuf[PATH_MAX];
+
+ dir = opendir(path);
+ if (dir == NULL)
+ return 0;
+
+ while ((d = readdir(dir)) != NULL && !ret) {
+ struct stat statbuf;
+
+ if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+ continue;
+
+ scnprintf(namebuf, sizeof(namebuf), "%s/%s",
+ path, d->d_name);
+
+ ret = stat(namebuf, &statbuf);
+ if (ret < 0) {
+ pr_debug("stat failed: %s\n", namebuf);
+ break;
+ }
+
+ if (S_ISREG(statbuf.st_mode))
+ ret = unlink(namebuf);
+ else if (S_ISDIR(statbuf.st_mode))
+ ret = rm_rf(namebuf);
+ else {
+ pr_debug("unknown file: %s\n", namebuf);
+ ret = -1;
+ }
+ }
+ closedir(dir);
+
+ if (ret < 0)
+ return ret;
+
+ return rmdir(path);
+}
+
+static int slow_copyfile(const char *from, const char *to)
{
int err = -1;
char *line = NULL;
size_t n;
FILE *from_fp = fopen(from, "r"), *to_fp;
- mode_t old_umask;
if (from_fp == NULL)
goto out;
- old_umask = umask(mode ^ 0777);
to_fp = fopen(to, "w");
- umask(old_umask);
if (to_fp == NULL)
goto out_fclose_from;
return err;
}
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+{
+ void *ptr;
+ loff_t pgoff;
+
+ pgoff = off_in & ~(page_size - 1);
+ off_in -= pgoff;
+
+ ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff);
+ if (ptr == MAP_FAILED)
+ return -1;
+
+ while (size) {
+ ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out);
+ if (ret < 0 && errno == EINTR)
+ continue;
+ if (ret <= 0)
+ break;
+
+ size -= ret;
+ off_in += ret;
+ off_out -= ret;
+ }
+ munmap(ptr, off_in + size);
+
+ return size ? -1 : 0;
+}
+
int copyfile_mode(const char *from, const char *to, mode_t mode)
{
int fromfd, tofd;
struct stat st;
- void *addr;
int err = -1;
+ char *tmp = NULL, *ptr = NULL;
if (stat(from, &st))
goto out;
- if (st.st_size == 0) /* /proc? do it slowly... */
- return slow_copyfile(from, to, mode);
-
- fromfd = open(from, O_RDONLY);
- if (fromfd < 0)
+ /* extra 'x' at the end is to reserve space for '.' */
+ if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
+ tmp = NULL;
goto out;
+ }
+ ptr = strrchr(tmp, '/');
+ if (!ptr)
+ goto out;
+ ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1);
+ *ptr = '.';
- tofd = creat(to, mode);
+ tofd = mkstemp(tmp);
if (tofd < 0)
- goto out_close_from;
+ goto out;
+
+ if (fchmod(tofd, mode))
+ goto out_close_to;
+
+ if (st.st_size == 0) { /* /proc? do it slowly... */
+ err = slow_copyfile(from, tmp);
+ goto out_close_to;
+ }
- addr = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fromfd, 0);
- if (addr == MAP_FAILED)
+ fromfd = open(from, O_RDONLY);
+ if (fromfd < 0)
goto out_close_to;
- if (write(tofd, addr, st.st_size) == st.st_size)
- err = 0;
+ err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
- munmap(addr, st.st_size);
+ close(fromfd);
out_close_to:
close(tofd);
- if (err)
- unlink(to);
-out_close_from:
- close(fromfd);
+ if (!err)
+ err = link(tmp, to);
+ unlink(tmp);
out:
+ free(tmp);
return err;
}
}
int mkdir_p(char *path, mode_t mode);
+int rm_rf(char *path);
int copyfile(const char *from, const char *to);
int copyfile_mode(const char *from, const char *to, mode_t mode);
+int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
s64 perf_atoll(const char *str);
char **argv_split(const char *str, int *argcp);
void argv_free(char **argv);
bool strglobmatch(const char *str, const char *pat);
bool strlazymatch(const char *str, const char *pat);
+static inline bool strisglob(const char *str)
+{
+ return strpbrk(str, "*?[") != NULL;
+}
int strtailcmp(const char *s1, const char *s2);
char *strxfrchar(char *s, char from, char to);
unsigned long convert_unit(unsigned long value, char *unit);
return vdso;
}
-void vdso__exit(struct machine *machine)
+void machine__exit_vdso(struct machine *machine)
{
struct vdso_info *vdso_info = machine->vdso_info;
zfree(&machine->vdso_info);
}
-static struct dso *vdso__new(struct machine *machine, const char *short_name,
- const char *long_name)
+static struct dso *__machine__addnew_vdso(struct machine *machine, const char *short_name,
+ const char *long_name)
{
struct dso *dso;
dso = dso__new(short_name);
if (dso != NULL) {
- dsos__add(&machine->user_dsos, dso);
+ __dsos__add(&machine->dsos, dso);
dso__set_long_name(dso, long_name, false);
}
return vdso_file->temp_file_name;
}
-static struct dso *vdso__findnew_compat(struct machine *machine,
- struct vdso_file *vdso_file)
+static struct dso *__machine__findnew_compat(struct machine *machine,
+ struct vdso_file *vdso_file)
{
const char *file_name;
struct dso *dso;
- dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+ pthread_rwlock_wrlock(&machine->dsos.lock);
+ dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
if (dso)
- return dso;
+ goto out_unlock;
file_name = vdso__get_compat_file(vdso_file);
if (!file_name)
- return NULL;
+ goto out_unlock;
- return vdso__new(machine, vdso_file->dso_name, file_name);
+ dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
+out_unlock:
+ pthread_rwlock_unlock(&machine->dsos.lock);
+ return dso;
}
-static int vdso__dso_findnew_compat(struct machine *machine,
- struct thread *thread,
- struct vdso_info *vdso_info,
- struct dso **dso)
+static int __machine__findnew_vdso_compat(struct machine *machine,
+ struct thread *thread,
+ struct vdso_info *vdso_info,
+ struct dso **dso)
{
enum dso_type dso_type;
switch (dso_type) {
case DSO__TYPE_32BIT:
- *dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+ *dso = __machine__findnew_compat(machine, &vdso_info->vdso32);
return 1;
case DSO__TYPE_X32BIT:
- *dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+ *dso = __machine__findnew_compat(machine, &vdso_info->vdsox32);
return 1;
case DSO__TYPE_UNKNOWN:
case DSO__TYPE_64BIT:
#endif
-struct dso *vdso__dso_findnew(struct machine *machine,
- struct thread *thread __maybe_unused)
+struct dso *machine__findnew_vdso(struct machine *machine,
+ struct thread *thread __maybe_unused)
{
struct vdso_info *vdso_info;
- struct dso *dso;
+ struct dso *dso = NULL;
+ pthread_rwlock_wrlock(&machine->dsos.lock);
if (!machine->vdso_info)
machine->vdso_info = vdso_info__new();
vdso_info = machine->vdso_info;
if (!vdso_info)
- return NULL;
+ goto out_unlock;
#if BITS_PER_LONG == 64
- if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
- return dso;
+ if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
+ goto out_unlock;
#endif
- dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
+ dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
if (!dso) {
char *file;
file = get_file(&vdso_info->vdso);
- if (!file)
- return NULL;
-
- dso = vdso__new(machine, DSO__NAME_VDSO, file);
+ if (file)
+ dso = __machine__addnew_vdso(machine, DSO__NAME_VDSO, file);
}
+out_unlock:
+ dso__get(dso);
+ pthread_rwlock_unlock(&machine->dsos.lock);
return dso;
}
struct machine;
struct thread;
-struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread);
-void vdso__exit(struct machine *machine);
+struct dso *machine__findnew_vdso(struct machine *machine, struct thread *thread);
+void machine__exit_vdso(struct machine *machine);
#endif /* __PERF_VDSO__ */
if (xy != NULL) {
xy->entry_size = entry_size;
xy->row_size = row_size;
+ xy->entries = xlen * ylen;
}
return xy;
}
+void xyarray__reset(struct xyarray *xy)
+{
+ size_t n = xy->entries * xy->entry_size;
+
+ memset(xy->contents, 0, n);
+}
+
void xyarray__delete(struct xyarray *xy)
{
free(xy);
struct xyarray {
size_t row_size;
size_t entry_size;
+ size_t entries;
char contents[];
};
struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
void xyarray__delete(struct xyarray *xy);
+void xyarray__reset(struct xyarray *xy);
static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
{
turbostat : turbostat.c
CFLAGS += -Wall
-CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
+CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
%: %.c
@mkdir -p $(BUILD_OUTPUT)
unsigned int skip_c1;
unsigned int do_nhm_cstates;
unsigned int do_snb_cstates;
+unsigned int do_knl_cstates;
unsigned int do_pc2;
unsigned int do_pc3;
unsigned int do_pc6;
unsigned int do_ring_perf_limit_reasons;
unsigned int crystal_hz;
unsigned long long tsc_hz;
+int base_cpu;
#define RAPL_PKG (1 << 0)
/* 0x610 MSR_PKG_POWER_LIMIT */
if (do_nhm_cstates)
outp += sprintf(outp, " CPU%%c1");
- if (do_nhm_cstates && !do_slm_cstates)
+ if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
outp += sprintf(outp, " CPU%%c3");
if (do_nhm_cstates)
outp += sprintf(outp, " CPU%%c6");
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
goto done;
- if (do_nhm_cstates && !do_slm_cstates)
+ if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
outp += sprintf(outp, "%8.2f", 100.0 * c->c3/t->tsc);
if (do_nhm_cstates)
outp += sprintf(outp, "%8.2f", 100.0 * c->c6/t->tsc);
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
return 0;
- if (do_nhm_cstates && !do_slm_cstates) {
+ if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) {
if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
return -6;
}
- if (do_nhm_cstates) {
+ if (do_nhm_cstates && !do_knl_cstates) {
if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
return -7;
+ } else if (do_knl_cstates) {
+ if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6))
+ return -7;
}
if (do_snb_cstates)
unsigned long long msr;
unsigned int ratio;
- get_msr(0, MSR_NHM_PLATFORM_INFO, &msr);
+ get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr);
fprintf(stderr, "%d * %.0f = %.0f MHz base frequency\n",
ratio, bclk, ratio * bclk);
- get_msr(0, MSR_IA32_POWER_CTL, &msr);
+ get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
fprintf(stderr, "cpu0: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
msr, msr & 0x2 ? "EN" : "DIS");
unsigned long long msr;
unsigned int ratio;
- get_msr(0, MSR_TURBO_RATIO_LIMIT2, &msr);
+ get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT2, &msr);
fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", msr);
unsigned long long msr;
unsigned int ratio;
- get_msr(0, MSR_TURBO_RATIO_LIMIT1, &msr);
+ get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &msr);
fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", msr);
unsigned long long msr;
unsigned int ratio;
- get_msr(0, MSR_TURBO_RATIO_LIMIT, &msr);
+ get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr);
fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
return;
}
+static void
+dump_knl_turbo_ratio_limits(void)
+{
+ int cores;
+ unsigned int ratio;
+ unsigned long long msr;
+ int delta_cores;
+ int delta_ratio;
+ int i;
+
+ get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
+
+ fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n",
+ msr);
+
+ /**
+ * Turbo encoding in KNL is as follows:
+ * [7:0] -- Base value of number of active cores of bucket 1.
+ * [15:8] -- Base value of freq ratio of bucket 1.
+ * [20:16] -- +ve delta of number of active cores of bucket 2.
+ * i.e. active cores of bucket 2 =
+ * active cores of bucket 1 + delta
+ * [23:21] -- Negative delta of freq ratio of bucket 2.
+ * i.e. freq ratio of bucket 2 =
+ * freq ratio of bucket 1 - delta
+ * [28:24]-- +ve delta of number of active cores of bucket 3.
+ * [31:29]-- -ve delta of freq ratio of bucket 3.
+ * [36:32]-- +ve delta of number of active cores of bucket 4.
+ * [39:37]-- -ve delta of freq ratio of bucket 4.
+ * [44:40]-- +ve delta of number of active cores of bucket 5.
+ * [47:45]-- -ve delta of freq ratio of bucket 5.
+ * [52:48]-- +ve delta of number of active cores of bucket 6.
+ * [55:53]-- -ve delta of freq ratio of bucket 6.
+ * [60:56]-- +ve delta of number of active cores of bucket 7.
+ * [63:61]-- -ve delta of freq ratio of bucket 7.
+ */
+ cores = msr & 0xFF;
+ ratio = (msr >> 8) && 0xFF;
+ if (ratio > 0)
+ fprintf(stderr,
+ "%d * %.0f = %.0f MHz max turbo %d active cores\n",
+ ratio, bclk, ratio * bclk, cores);
+
+ for (i = 16; i < 64; i = i + 8) {
+ delta_cores = (msr >> i) & 0x1F;
+ delta_ratio = (msr >> (i + 5)) && 0x7;
+ if (!delta_cores || !delta_ratio)
+ return;
+ cores = cores + delta_cores;
+ ratio = ratio - delta_ratio;
+
+ /** -ve ratios will make successive ratio calculations
+ * negative. Hence return instead of carrying on.
+ */
+ if (ratio > 0)
+ fprintf(stderr,
+ "%d * %.0f = %.0f MHz max turbo %d active cores\n",
+ ratio, bclk, ratio * bclk, cores);
+ }
+}
+
static void
dump_nhm_cst_cfg(void)
{
unsigned long long msr;
- get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+ get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
}
/*
- * cpu_is_first_sibling_in_core(cpu)
- * return 1 if given CPU is 1st HT sibling in the core
+ * get_cpu_position_in_core(cpu)
+ * return the position of the CPU among its HT siblings in the core
+ * return -1 if the sibling is not in list
*/
-int cpu_is_first_sibling_in_core(int cpu)
+int get_cpu_position_in_core(int cpu)
{
- return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
+ char path[64];
+ FILE *filep;
+ int this_cpu;
+ char character;
+ int i;
+
+ sprintf(path,
+ "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list",
+ cpu);
+ filep = fopen(path, "r");
+ if (filep == NULL) {
+ perror(path);
+ exit(1);
+ }
+
+ for (i = 0; i < topo.num_threads_per_core; i++) {
+ fscanf(filep, "%d", &this_cpu);
+ if (this_cpu == cpu) {
+ fclose(filep);
+ return i;
+ }
+
+ /* Account for no separator after last thread*/
+ if (i != (topo.num_threads_per_core - 1))
+ fscanf(filep, "%c", &character);
+ }
+
+ fclose(filep);
+ return -1;
}
/*
{
char path[80];
FILE *filep;
- int sib1, sib2;
- int matches;
+ int sib1;
+ int matches = 0;
char character;
+ char str[100];
+ char *ch;
sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
filep = fopen_or_die(path, "r");
+
/*
* file format:
- * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4)
- * otherwinse 1 sibling (self).
+ * A ',' separated or '-' separated set of numbers
+ * (eg 1-2 or 1,3,4,5)
*/
- matches = fscanf(filep, "%d%c%d\n", &sib1, &character, &sib2);
+ fscanf(filep, "%d%c\n", &sib1, &character);
+ fseek(filep, 0, SEEK_SET);
+ fgets(str, 100, filep);
+ ch = strchr(str, character);
+ while (ch != NULL) {
+ matches++;
+ ch = strchr(ch+1, character);
+ }
fclose(filep);
-
- if (matches == 3)
- return 2;
- else
- return 1;
+ return matches+1;
}
/*
void check_dev_msr()
{
struct stat sb;
+ char pathname[32];
- if (stat("/dev/cpu/0/msr", &sb))
+ sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
+ if (stat(pathname, &sb))
if (system("/sbin/modprobe msr > /dev/null 2>&1"))
err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
}
cap_user_data_t cap_data = &cap_data_data;
extern int capget(cap_user_header_t hdrp, cap_user_data_t datap);
int do_exit = 0;
+ char pathname[32];
/* check for CAP_SYS_RAWIO */
cap_header->pid = getpid();
}
/* test file permissions */
- if (euidaccess("/dev/cpu/0/msr", R_OK)) {
+ sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
+ if (euidaccess(pathname, R_OK)) {
do_exit++;
warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr");
}
default:
return 0;
}
- get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+ get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
}
}
+int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+ if (!genuine_intel)
+ return 0;
+
+ if (family != 6)
+ return 0;
+
+ switch (model) {
+ case 0x57: /* Knights Landing */
+ return 1;
+ default:
+ return 0;
+ }
+}
static void
dump_cstate_pstate_config_info(family, model)
{
if (has_nhm_turbo_ratio_limit(family, model))
dump_nhm_turbo_ratio_limits();
+ if (has_knl_turbo_ratio_limit(family, model))
+ dump_knl_turbo_ratio_limits();
+
dump_nhm_cst_cfg();
}
if (get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr))
return 0;
- switch (msr & 0x7) {
+ switch (msr & 0xF) {
case ENERGY_PERF_BIAS_PERFORMANCE:
epb_string = "performance";
break;
unsigned long long msr;
if (do_rapl & RAPL_PKG_POWER_INFO)
- if (!get_msr(0, MSR_PKG_POWER_INFO, &msr))
+ if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr))
return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
switch (model) {
case 0x3F: /* HSX */
case 0x4F: /* BDX */
case 0x56: /* BDX-DE */
+ case 0x57: /* KNL */
return (rapl_dram_energy_units = 15.3 / 1000000);
default:
return (rapl_energy_units);
case 0x3F: /* HSX */
case 0x4F: /* BDX */
case 0x56: /* BDX-DE */
+ case 0x57: /* KNL */
do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
break;
case 0x2D:
}
/* units on package 0, verify later other packages match */
- if (get_msr(0, MSR_RAPL_POWER_UNIT, &msr))
+ if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr))
return;
rapl_power_units = 1.0 / (1 << (msr & 0xF));
return 0;
}
+int is_knl(unsigned int family, unsigned int model)
+{
+ if (!genuine_intel)
+ return 0;
+ switch (model) {
+ case 0x57: /* KNL */
+ return 1;
+ }
+ return 0;
+}
+
#define SLM_BCLK_FREQS 5
double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0};
unsigned int i;
double freq;
- if (get_msr(0, MSR_FSB_FREQ, &msr))
+ if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
fprintf(stderr, "SLM BCLK: unknown\n");
i = msr & 0xf;
if (!do_nhm_platform_info)
goto guess;
- if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr))
+ if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
goto guess;
target_c_local = (msr >> 16) & 0xFF;
do_c8_c9_c10 = has_hsw_msrs(family, model);
do_skl_residency = has_skl_msrs(family, model);
do_slm_cstates = is_slm(family, model);
+ do_knl_cstates = is_knl(family, model);
bclk = discover_bclk(family, model);
rapl_probe(family, model);
my_package_id = get_physical_package_id(cpu_id);
my_core_id = get_core_id(cpu_id);
-
- if (cpu_is_first_sibling_in_core(cpu_id)) {
- my_thread_id = 0;
+ my_thread_id = get_cpu_position_in_core(cpu_id);
+ if (!my_thread_id)
topo.num_cores++;
- } else {
- my_thread_id = 1;
- }
init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
for_all_proc_cpus(initialize_counters);
}
+void set_base_cpu(void)
+{
+ base_cpu = sched_getcpu();
+ if (base_cpu < 0)
+ err(-ENODEV, "No valid cpus found");
+
+ if (debug > 1)
+ fprintf(stderr, "base_cpu = %d\n", base_cpu);
+}
+
void turbostat_init()
{
+ setup_all_buffers();
+ set_base_cpu();
check_dev_msr();
check_permissions();
process_cpuid();
- setup_all_buffers();
if (debug)
for_all_cpus(print_epb, ODD_COUNTERS);
}
void print_version() {
- fprintf(stderr, "turbostat version 4.5 2 Apr, 2015"
+ fprintf(stderr, "turbostat version 4.7 27-May, 2015"
" - Len Brown <lenb@kernel.org>\n");
}
mv $builddir/.config $builddir/.config.sav
sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
cp $builddir/.config $builddir/.config.new
-yes '' | make $buildloc oldconfig > $builddir/Make.modconfig.out 2>&1
+yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err
# verify new config matches specification.
configcheck.sh $builddir/.config $c
if test -f "$i/console.log"
then
configcheck.sh $i/.config $i/ConfigFragment
+ if test -r $i/Make.oldconfig.err
+ then
+ cat $i/Make.oldconfig.err
+ fi
parse-build.sh $i/Make.out $configfile
parse-torture.sh $i/console.log $configfile
parse-console.sh $i/console.log $configfile
echo " --bootargs kernel-boot-arguments"
echo " --bootimage relative-path-to-kernel-boot-image"
echo " --buildonly"
- echo " --configs \"config-file list\""
+ echo " --configs \"config-file list w/ repeat factor (3*TINY01)\""
echo " --cpus N"
echo " --datestamp string"
echo " --defconfig string"
touch $T/cfgcpu
for CF in $configs
do
- if test -f "$CONFIGFRAG/$CF"
+ case $CF in
+ [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**)
+ config_reps=`echo $CF | sed -e 's/\*.*$//'`
+ CF1=`echo $CF | sed -e 's/^[^*]*\*//'`
+ ;;
+ *)
+ config_reps=1
+ CF1=$CF
+ ;;
+ esac
+ if test -f "$CONFIGFRAG/$CF1"
then
- cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF`
- cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF" "$cpu_count"`
- echo $CF $cpu_count >> $T/cfgcpu
+ cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1`
+ cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"`
+ for ((cur_rep=0;cur_rep<$config_reps;cur_rep++))
+ do
+ echo $CF1 $cpu_count >> $T/cfgcpu
+ done
else
- echo "The --configs file $CF does not exist, terminating."
+ echo "The --configs file $CF1 does not exist, terminating."
exit 1
fi
done
CONFIG_RCU_TORTURE_TEST=y
CONFIG_PRINTK_TIME=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_RCU_EXPERT=y
CONFIG_PREEMPT_NONE=n
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=y
+#CHECK#CONFIG_RCU_EXPERT=n
-rcutorture.torture_type=srcu
+rcutorture.torture_type=srcud
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=y
CONFIG_DEBUG_LOCK_ALLOC=y
-CONFIG_PROVE_RCU=y
-CONFIG_TASKS_RCU=y
+CONFIG_PROVE_LOCKING=n
+#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_RCU_EXPERT=y
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
-CONFIG_TASKS_RCU=y
CONFIG_PREEMPT_NONE=n
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=y
-CONFIG_TASKS_RCU=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=n
CONFIG_NO_HZ_FULL=y
CONFIG_NO_HZ_FULL_ALL=y
+#CHECK#CONFIG_RCU_EXPERT=n
CONFIG_NO_HZ_FULL=n
CONFIG_RCU_TRACE=y
CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_PREEMPT_COUNT=y
rcupdate.rcu_self_test=1
rcupdate.rcu_self_test_bh=1
+rcutorture.torture_type=rcu_bh
CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
CONFIG_HIBERNATION=n
CONFIG_RCU_FANOUT=3
CONFIG_RCU_FANOUT_LEAF=3
-CONFIG_RCU_FANOUT_EXACT=n
CONFIG_RCU_NOCB_CPU=n
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=n
CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
CONFIG_HIBERNATION=n
CONFIG_RCU_FANOUT=3
CONFIG_RCU_FANOUT_LEAF=3
-CONFIG_RCU_FANOUT_EXACT=n
CONFIG_RCU_NOCB_CPU=n
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=n
CONFIG_SMP=y
-CONFIG_NR_CPUS=8
+CONFIG_NR_CPUS=16
CONFIG_PREEMPT_NONE=n
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=y
CONFIG_NO_HZ_FULL=n
CONFIG_RCU_TRACE=y
CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_FANOUT=4
-CONFIG_RCU_FANOUT_LEAF=4
-CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_FANOUT=2
+CONFIG_RCU_FANOUT_LEAF=2
CONFIG_RCU_NOCB_CPU=n
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_RCU_BOOST=y
CONFIG_RCU_KTHREAD_PRIO=2
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
--- /dev/null
+rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
CONFIG_HOTPLUG_CPU=n
CONFIG_SUSPEND=n
CONFIG_HIBERNATION=n
-CONFIG_RCU_FANOUT=2
-CONFIG_RCU_FANOUT_LEAF=2
-CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_FANOUT=4
+CONFIG_RCU_FANOUT_LEAF=4
CONFIG_RCU_NOCB_CPU=n
CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
CONFIG_HOTPLUG_CPU=y
CONFIG_RCU_FANOUT=6
CONFIG_RCU_FANOUT_LEAF=6
-CONFIG_RCU_FANOUT_EXACT=n
CONFIG_RCU_NOCB_CPU=y
CONFIG_RCU_NOCB_CPU_NONE=y
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
CONFIG_HIBERNATION=n
CONFIG_RCU_FANOUT=6
CONFIG_RCU_FANOUT_LEAF=6
-CONFIG_RCU_FANOUT_EXACT=y
CONFIG_RCU_NOCB_CPU=n
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RCU_EXPERT=y
rcupdate.rcu_self_test=1
rcupdate.rcu_self_test_bh=1
rcupdate.rcu_self_test_sched=1
+rcutree.rcu_fanout_exact=1
CONFIG_HOTPLUG_CPU=y
CONFIG_RCU_FANOUT=2
CONFIG_RCU_FANOUT_LEAF=2
-CONFIG_RCU_FANOUT_EXACT=n
CONFIG_RCU_NOCB_CPU=n
CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
CONFIG_SMP=y
-CONFIG_NR_CPUS=16
+CONFIG_NR_CPUS=8
CONFIG_PREEMPT_NONE=n
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=y
CONFIG_SUSPEND=n
CONFIG_HIBERNATION=n
CONFIG_RCU_FANOUT=3
-CONFIG_RCU_FANOUT_EXACT=y
CONFIG_RCU_FANOUT_LEAF=2
CONFIG_RCU_NOCB_CPU=y
CONFIG_RCU_NOCB_CPU_ALL=y
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
CONFIG_SUSPEND=n
CONFIG_HIBERNATION=n
CONFIG_RCU_FANOUT=3
-CONFIG_RCU_FANOUT_EXACT=y
CONFIG_RCU_FANOUT_LEAF=2
CONFIG_RCU_NOCB_CPU=y
CONFIG_RCU_NOCB_CPU_ALL=y
--- /dev/null
+rcutree.rcu_fanout_exact=1
rcutorture.torture_type=sched
rcupdate.rcu_self_test=1
rcupdate.rcu_self_test_sched=1
+rcutree.rcu_fanout_exact=1
CONFIG_RCU_CPU_STALL_INFO=n
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+#CHECK#CONFIG_RCU_EXPERT=n
CONFIG_NO_HZ_FULL -- Do two, one with CONFIG_NO_HZ_FULL_SYSIDLE.
CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
CONFIG_PREEMPT -- Do half. (First three and #8.)
-CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not.
-CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING.
+CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not.
+CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING.
CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing.
-CONFIG_RCU_CPU_STALL_INFO -- Do one.
-CONFIG_RCU_FANOUT -- Cover hierarchy as currently, but overlap with others.
-CONFIG_RCU_FANOUT_EXACT -- Do one.
+CONFIG_RCU_CPU_STALL_INFO -- Now default, avoid at least twice.
+CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others.
CONFIG_RCU_FANOUT_LEAF -- Do one non-default.
CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL.
CONFIG_RCU_NOCB_CPU -- Do three, see below.
CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
CONFIG_RCU_TRACE -- Do half.
CONFIG_SMP -- Need one !SMP for PREEMPT_RCU.
+!RCU_EXPERT -- Do a few, but these have to be vanilla configurations.
RCU-bh: Do one with PREEMPT and one with !PREEMPT.
RCU-sched: Do one with PREEMPT but not BOOST.
-Hierarchy:
-
-TREE01. CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=8, CONFIG_RCU_FANOUT_EXACT=n.
-TREE02. CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=n,
- CONFIG_RCU_FANOUT_LEAF=3.
-TREE03. CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=4, CONFIG_RCU_FANOUT_EXACT=n,
- CONFIG_RCU_FANOUT_LEAF=4.
-TREE04. CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
- CONFIG_RCU_FANOUT_LEAF=2.
-TREE05. CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=n
- CONFIG_RCU_FANOUT_LEAF=6.
-TREE06. CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=y
- CONFIG_RCU_FANOUT_LEAF=6.
-TREE07. CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
- CONFIG_RCU_FANOUT_LEAF=2.
-TREE08. CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=y,
- CONFIG_RCU_FANOUT_LEAF=2.
-TREE09. CONFIG_NR_CPUS=1.
+Boot parameters:
+
+nohz_full - do at least one.
+maxcpu -- do at least one.
+rcupdate.rcu_self_test_bh -- Do at least one each, offloaded and not.
+rcupdate.rcu_self_test_sched -- Do at least one each, offloaded and not.
+rcupdate.rcu_self_test -- Do at least one each, offloaded and not.
+rcutree.rcu_fanout_exact -- Do at least one.
Kconfig Parameters Ignored:
#include <time.h>
#include <sys/time.h>
#include <sys/timex.h>
+#include <sys/errno.h>
#include <string.h>
#include <signal.h>
#include <unistd.h>
#define NSEC_PER_SEC 1000000000ULL
#define CLOCK_TAI 11
+time_t next_leap;
+int error_found;
+
/* returns 1 if a <= b, 0 otherwise */
static inline int in_order(struct timespec a, struct timespec b)
{
exit(0);
}
+void sigalarm(int signo)
+{
+ struct timex tx;
+ int ret;
+
+ tx.modes = 0;
+ ret = adjtimex(&tx);
+
+ if (tx.time.tv_sec < next_leap) {
+ printf("Error: Early timer expiration! (Should be %ld)\n", next_leap);
+ error_found = 1;
+ printf("adjtimex: %10ld sec + %6ld us (%i)\t%s\n",
+ tx.time.tv_sec,
+ tx.time.tv_usec,
+ tx.tai,
+ time_state_str(ret));
+ }
+ if (ret != TIME_WAIT) {
+ printf("Error: Timer seeing incorrect NTP state? (Should be TIME_WAIT)\n");
+ error_found = 1;
+ printf("adjtimex: %10ld sec + %6ld us (%i)\t%s\n",
+ tx.time.tv_sec,
+ tx.time.tv_usec,
+ tx.tai,
+ time_state_str(ret));
+ }
+}
+
+
/* Test for known hrtimer failure */
void test_hrtimer_failure(void)
{
clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &target, NULL);
clock_gettime(CLOCK_REALTIME, &now);
- if (!in_order(target, now))
+ if (!in_order(target, now)) {
printf("ERROR: hrtimer early expiration failure observed.\n");
+ error_found = 1;
+ }
}
int main(int argc, char **argv)
{
+ timer_t tm1;
+ struct itimerspec its1;
+ struct sigevent se;
+ struct sigaction act;
+ int signum = SIGRTMAX;
int settime = 0;
int tai_time = 0;
int insert = 1;
signal(SIGINT, handler);
signal(SIGKILL, handler);
+ /* Set up timer signal handler: */
+ sigfillset(&act.sa_mask);
+ act.sa_flags = 0;
+ act.sa_handler = sigalarm;
+ sigaction(signum, &act, NULL);
+
if (iterations < 0)
printf("This runs continuously. Press ctrl-c to stop\n");
else
int ret;
struct timespec ts;
struct timex tx;
- time_t now, next_leap;
+ time_t now;
/* Get the current time */
clock_gettime(CLOCK_REALTIME, &ts);
printf("Scheduling leap second for %s", ctime(&next_leap));
+ /* Set up timer */
+ printf("Setting timer for %ld - %s", next_leap, ctime(&next_leap));
+ memset(&se, 0, sizeof(se));
+ se.sigev_notify = SIGEV_SIGNAL;
+ se.sigev_signo = signum;
+ se.sigev_value.sival_int = 0;
+ if (timer_create(CLOCK_REALTIME, &se, &tm1) == -1) {
+ printf("Error: timer_create failed\n");
+ return ksft_exit_fail();
+ }
+ its1.it_value.tv_sec = next_leap;
+ its1.it_value.tv_nsec = 0;
+ its1.it_interval.tv_sec = 0;
+ its1.it_interval.tv_nsec = 0;
+ timer_settime(tm1, TIMER_ABSTIME, &its1, NULL);
+
/* Wake up 3 seconds before leap */
ts.tv_sec = next_leap - 3;
ts.tv_nsec = 0;
+
while (clock_nanosleep(CLOCK_REALTIME, TIMER_ABSTIME, &ts, NULL))
printf("Something woke us up, returning to sleep\n");
while (now < next_leap + 2) {
char buf[26];
struct timespec tai;
+ int ret;
tx.modes = 0;
ret = adjtimex(&tx);
/* Note if kernel has known hrtimer failure */
test_hrtimer_failure();
- printf("Leap complete\n\n");
-
+ printf("Leap complete\n");
+ if (error_found) {
+ printf("Errors observed\n");
+ clear_time_state();
+ return ksft_exit_fail();
+ }
+ printf("\n");
if ((iterations != -1) && !(--iterations))
break;
}
-.PHONY: all all_32 all_64 check_build32 clean run_tests
+all:
-TARGETS_C_BOTHBITS := sigreturn single_step_syscall
+include ../lib.mk
-BINARIES_32 := $(TARGETS_C_BOTHBITS:%=%_32)
+.PHONY: all all_32 all_64 warn_32bit_failure clean
+
+TARGETS_C_BOTHBITS := sigreturn single_step_syscall sysret_ss_attrs
+TARGETS_C_32BIT_ONLY := entry_from_vm86
+
+TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
+BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64)
CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
-UNAME_P := $(shell uname -p)
+UNAME_M := $(shell uname -m)
+CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
+CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
-# Always build 32-bit tests
+ifeq ($(CAN_BUILD_I386),1)
all: all_32
+TEST_PROGS += $(BINARIES_32)
+endif
-# If we're on a 64-bit host, build 64-bit tests as well
-ifeq ($(shell uname -p),x86_64)
+ifeq ($(CAN_BUILD_X86_64),1)
all: all_64
+TEST_PROGS += $(BINARIES_64)
endif
-all_32: check_build32 $(BINARIES_32)
+all_32: $(BINARIES_32)
all_64: $(BINARIES_64)
clean:
$(RM) $(BINARIES_32) $(BINARIES_64)
-run_tests:
- ./run_x86_tests.sh
-
-$(TARGETS_C_BOTHBITS:%=%_32): %_32: %.c
+$(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c
$(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
$(TARGETS_C_BOTHBITS:%=%_64): %_64: %.c
$(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
-check_build32:
- @if ! $(CC) -m32 -o /dev/null trivial_32bit_program.c; then \
- echo "Warning: you seem to have a broken 32-bit build" 2>&1; \
- echo "environment. If you are using a Debian-like"; \
- echo " distribution, try:"; \
- echo ""; \
- echo " apt-get install gcc-multilib libc6-i386 libc6-dev-i386"; \
- echo ""; \
- echo "If you are using a Fedora-like distribution, try:"; \
- echo ""; \
- echo " yum install glibc-devel.*i686"; \
- exit 1; \
- fi
+# x86_64 users should be encouraged to install 32-bit libraries
+ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),01)
+all: warn_32bit_failure
+
+warn_32bit_failure:
+ @echo "Warning: you seem to have a broken 32-bit build" 2>&1; \
+ echo "environment. This will reduce test coverage of 64-bit" 2>&1; \
+ echo "kernels. If you are using a Debian-like distribution," 2>&1; \
+ echo "try:"; 2>&1; \
+ echo ""; \
+ echo " apt-get install gcc-multilib libc6-i386 libc6-dev-i386"; \
+ echo ""; \
+ echo "If you are using a Fedora-like distribution, try:"; \
+ echo ""; \
+ echo " yum install glibc-devel.*i686"; \
+ exit 0;
+endif
+
+# Some tests have additional dependencies.
+sysret_ss_attrs_64: thunks.S
--- /dev/null
+#!/bin/sh
+# check_cc.sh - Helper to test userspace compilation support
+# Copyright (c) 2015 Andrew Lutomirski
+# GPL v2
+
+CC="$1"
+TESTPROG="$2"
+shift 2
+
+if "$CC" -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then
+ echo 1
+else
+ echo 0
+fi
+
+exit 0
--- /dev/null
+/*
+ * entry_from_vm86.c - tests kernel entries from vm86 mode
+ * Copyright (c) 2014-2015 Andrew Lutomirski
+ *
+ * This exercises a few paths that need to special-case vm86 mode.
+ *
+ * GPL v2.
+ */
+
+#define _GNU_SOURCE
+
+#include <assert.h>
+#include <stdlib.h>
+#include <sys/syscall.h>
+#include <sys/signal.h>
+#include <sys/ucontext.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <sys/mman.h>
+#include <err.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <sys/vm86.h>
+
+static unsigned long load_addr = 0x10000;
+static int nerrs = 0;
+
+asm (
+ ".pushsection .rodata\n\t"
+ ".type vmcode_bound, @object\n\t"
+ "vmcode:\n\t"
+ "vmcode_bound:\n\t"
+ ".code16\n\t"
+ "bound %ax, (2048)\n\t"
+ "int3\n\t"
+ "vmcode_sysenter:\n\t"
+ "sysenter\n\t"
+ ".size vmcode, . - vmcode\n\t"
+ "end_vmcode:\n\t"
+ ".code32\n\t"
+ ".popsection"
+ );
+
+extern unsigned char vmcode[], end_vmcode[];
+extern unsigned char vmcode_bound[], vmcode_sysenter[];
+
+static void do_test(struct vm86plus_struct *v86, unsigned long eip,
+ const char *text)
+{
+ long ret;
+
+ printf("[RUN]\t%s from vm86 mode\n", text);
+ v86->regs.eip = eip;
+ ret = vm86(VM86_ENTER, v86);
+
+ if (ret == -1 && errno == ENOSYS) {
+ printf("[SKIP]\tvm86 not supported\n");
+ return;
+ }
+
+ if (VM86_TYPE(ret) == VM86_INTx) {
+ char trapname[32];
+ int trapno = VM86_ARG(ret);
+ if (trapno == 13)
+ strcpy(trapname, "GP");
+ else if (trapno == 5)
+ strcpy(trapname, "BR");
+ else if (trapno == 14)
+ strcpy(trapname, "PF");
+ else
+ sprintf(trapname, "%d", trapno);
+
+ printf("[OK]\tExited vm86 mode due to #%s\n", trapname);
+ } else if (VM86_TYPE(ret) == VM86_UNKNOWN) {
+ printf("[OK]\tExited vm86 mode due to unhandled GP fault\n");
+ } else {
+ printf("[OK]\tExited vm86 mode due to type %ld, arg %ld\n",
+ VM86_TYPE(ret), VM86_ARG(ret));
+ }
+}
+
+int main(void)
+{
+ struct vm86plus_struct v86;
+ unsigned char *addr = mmap((void *)load_addr, 4096,
+ PROT_READ | PROT_WRITE | PROT_EXEC,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1,0);
+ if (addr != (unsigned char *)load_addr)
+ err(1, "mmap");
+
+ memcpy(addr, vmcode, end_vmcode - vmcode);
+ addr[2048] = 2;
+ addr[2050] = 3;
+
+ memset(&v86, 0, sizeof(v86));
+
+ v86.regs.cs = load_addr / 16;
+ v86.regs.ss = load_addr / 16;
+ v86.regs.ds = load_addr / 16;
+ v86.regs.es = load_addr / 16;
+
+ assert((v86.regs.cs & 3) == 0); /* Looks like RPL = 0 */
+
+ /* #BR -- should deliver SIG??? */
+ do_test(&v86, vmcode_bound - vmcode, "#BR");
+
+ /* SYSENTER -- should cause #GP or #UD depending on CPU */
+ do_test(&v86, vmcode_sysenter - vmcode, "SYSENTER");
+
+ return (nerrs == 0 ? 0 : 1);
+}
+++ /dev/null
-#!/bin/bash
-
-# This is deliberately minimal. IMO kselftests should provide a standard
-# script here.
-./sigreturn_32 || exit 1
-./single_step_syscall_32 || exit 1
-
-if [[ "$uname -p" -eq "x86_64" ]]; then
- ./sigreturn_64 || exit 1
- ./single_step_syscall_64 || exit 1
-fi
-
-exit 0
--- /dev/null
+/*
+ * sysret_ss_attrs.c - test that syscalls return valid hidden SS attributes
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * On AMD CPUs, SYSRET can return with a valid SS descriptor with with
+ * the hidden attributes set to an unusable state. Make sure the kernel
+ * doesn't let this happen.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <err.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <pthread.h>
+
+static void *threadproc(void *ctx)
+{
+ /*
+ * Do our best to cause sleeps on this CPU to exit the kernel and
+ * re-enter with SS = 0.
+ */
+ while (true)
+ ;
+
+ return NULL;
+}
+
+#ifdef __x86_64__
+extern unsigned long call32_from_64(void *stack, void (*function)(void));
+
+asm (".pushsection .text\n\t"
+ ".code32\n\t"
+ "test_ss:\n\t"
+ "pushl $0\n\t"
+ "popl %eax\n\t"
+ "ret\n\t"
+ ".code64");
+extern void test_ss(void);
+#endif
+
+int main()
+{
+ /*
+ * Start a busy-looping thread on the same CPU we're on.
+ * For simplicity, just stick everything to CPU 0. This will
+ * fail in some containers, but that's probably okay.
+ */
+ cpu_set_t cpuset;
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+ if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+ printf("[WARN]\tsched_setaffinity failed\n");
+
+ pthread_t thread;
+ if (pthread_create(&thread, 0, threadproc, 0) != 0)
+ err(1, "pthread_create");
+
+#ifdef __x86_64__
+ unsigned char *stack32 = mmap(NULL, 4096, PROT_READ | PROT_WRITE,
+ MAP_32BIT | MAP_ANONYMOUS | MAP_PRIVATE,
+ -1, 0);
+ if (stack32 == MAP_FAILED)
+ err(1, "mmap");
+#endif
+
+ printf("[RUN]\tSyscalls followed by SS validation\n");
+
+ for (int i = 0; i < 1000; i++) {
+ /*
+ * Go to sleep and return using sysret (if we're 64-bit
+ * or we're 32-bit on AMD on a 64-bit kernel). On AMD CPUs,
+ * SYSRET doesn't fix up the cached SS descriptor, so the
+ * kernel needs some kind of workaround to make sure that we
+ * end the system call with a valid stack segment. This
+ * can be a confusing failure because the SS *selector*
+ * is the same regardless.
+ */
+ usleep(2);
+
+#ifdef __x86_64__
+ /*
+ * On 32-bit, just doing a syscall through glibc is enough
+ * to cause a crash if our cached SS descriptor is invalid.
+ * On 64-bit, it's not, so try extra hard.
+ */
+ call32_from_64(stack32 + 4088, test_ss);
+#endif
+ }
+
+ printf("[OK]\tWe survived\n");
+
+#ifdef __x86_64__
+ munmap(stack32, 4096);
+#endif
+
+ return 0;
+}
--- /dev/null
+/*
+ * thunks.S - assembly helpers for mixed-bitness code
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * These are little helpers that make it easier to switch bitness on
+ * the fly.
+ */
+
+ .text
+
+ .global call32_from_64
+ .type call32_from_64, @function
+call32_from_64:
+ // rdi: stack to use
+ // esi: function to call
+
+ // Save registers
+ pushq %rbx
+ pushq %rbp
+ pushq %r12
+ pushq %r13
+ pushq %r14
+ pushq %r15
+ pushfq
+
+ // Switch stacks
+ mov %rsp,(%rdi)
+ mov %rdi,%rsp
+
+ // Switch to compatibility mode
+ pushq $0x23 /* USER32_CS */
+ pushq $1f
+ lretq
+
+1:
+ .code32
+ // Call the function
+ call *%esi
+ // Switch back to long mode
+ jmp $0x33,$1f
+ .code64
+
+1:
+ // Restore the stack
+ mov (%rsp),%rsp
+
+ // Restore registers
+ popfq
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbp
+ popq %rbx
+
+ ret
+
+.size call32_from_64, .-call32_from_64
* GPL v2
*/
+#ifndef __i386__
+# error wrong architecture
+#endif
+
#include <stdio.h>
int main()
--- /dev/null
+/*
+ * Trivial program to check that we have a valid 32-bit build environment.
+ * Copyright (c) 2015 Andy Lutomirski
+ * GPL v2
+ */
+
+#ifndef __x86_64__
+# error wrong architecture
+#endif
+
+#include <stdio.h>
+
+int main()
+{
+ printf("\n");
+
+ return 0;
+}
INSTALL_PROGRAM=install -m 755 -p
DEL_FILE=rm -f
-INSTALL_CONFIGFILE=install -m 644 -p
-CONFIG_FILE=
-CONFIG_PATH=
-
# Static builds might require -ltinfo, for instance
ifneq ($(findstring -static, $(LDFLAGS)),)
STATIC := --static
install:
- mkdir -p $(INSTALL_ROOT)/$(BINDIR)
- $(INSTALL_PROGRAM) "$(TARGET)" "$(INSTALL_ROOT)/$(BINDIR)/$(TARGET)"
- - mkdir -p $(INSTALL_ROOT)/$(CONFIG_PATH)
- - $(INSTALL_CONFIGFILE) "$(CONFIG_FILE)" "$(INSTALL_ROOT)/$(CONFIG_PATH)"
uninstall:
$(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/$(TARGET)"
- $(CONFIG_FILE) "$(CONFIG_PATH)"
-
clean:
find . -name "*.o" | xargs $(DEL_FILE)
TARGETS=page-types slabinfo page_owner_sort
LIB_DIR = ../lib/api
-LIBS = $(LIB_DIR)/libapikfs.a
+LIBS = $(LIB_DIR)/libapi.a
CC = $(CROSS_COMPILE)gcc
CFLAGS = -Wall -Wextra -I../lib/
projects / firefly-linux-kernel-4.4.55.git / commitdiff