* 'x86-microcode-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, microcode, AMD: Fix signedness bug in generic_load_microcode()
x86, microcode, AMD: Extend ucode size verification
x86, microcode, AMD: Cleanup dmesg output
x86, microcode, AMD: Remove unneeded memset call
x86, microcode, AMD: Simplify get_next_ucode
x86, microcode, AMD: Simplify install_equiv_cpu_table
x86, microcode, AMD: Release firmware on error
x86, microcode: Correct sysdev_add error path
*.gz
*.bz2
*.lzma
+*.xz
*.lzo
*.patch
*.gcno
services.
</para>
<para>
- The core of every DRM driver is struct drm_device. Drivers
- will typically statically initialize a drm_device structure,
+ The core of every DRM driver is struct drm_driver. Drivers
+ will typically statically initialize a drm_driver structure,
then pass it to drm_init() at load time.
</para>
<title>Driver initialization</title>
<para>
Before calling the DRM initialization routines, the driver must
- first create and fill out a struct drm_device structure.
+ first create and fill out a struct drm_driver structure.
</para>
<programlisting>
static struct drm_driver driver = {
</sect1>
</chapter>
+ <chapter id="fs_events">
+ <title>Events based on file descriptors</title>
+!Efs/eventfd.c
+ </chapter>
+
<chapter id="sysfs">
<title>The Filesystem for Exporting Kernel Objects</title>
!Efs/sysfs/file.c
--- /dev/null
+* Freescale 8xxx/3.0 Gb/s SATA nodes
+
+SATA nodes are defined to describe on-chip Serial ATA controllers.
+Each SATA port should have its own node.
+
+Required properties:
+- compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-sata", where CHIP is the processor
+ (mpc8315, mpc8379, etc.) and the second is
+ "fsl,pq-sata"
+- interrupts : <interrupt mapping for SATA IRQ>
+- cell-index : controller index.
+ 1 for controller @ 0x18000
+ 2 for controller @ 0x19000
+ 3 for controller @ 0x1a000
+ 4 for controller @ 0x1b000
+
+Optional properties:
+- interrupt-parent : optional, if needed for interrupt mapping
+- reg : <registers mapping>
+
+Example:
+ sata@18000 {
+ compatible = "fsl,mpc8379-sata", "fsl,pq-sata";
+ reg = <0x18000 0x1000>;
+ cell-index = <1>;
+ interrupts = <2c 8>;
+ interrupt-parent = < &ipic >;
+ };
--- /dev/null
+EEPROMs (I2C)
+
+Required properties:
+
+ - compatible : should be "<manufacturer>,<type>"
+ If there is no specific driver for <manufacturer>, a generic
+ driver based on <type> is selected. Possible types are:
+ 24c00, 24c01, 24c02, 24c04, 24c08, 24c16, 24c32, 24c64,
+ 24c128, 24c256, 24c512, 24c1024, spd
+
+ - reg : the I2C address of the EEPROM
+
+Optional properties:
+
+ - pagesize : the length of the pagesize for writing. Please consult the
+ manual of your device, that value varies a lot. A wrong value
+ may result in data loss! If not specified, a safety value of
+ '1' is used which will be very slow.
+
+ - read-only: this parameterless property disables writes to the eeprom
+
+Example:
+
+eeprom@52 {
+ compatible = "atmel,24c32";
+ reg = <0x52>;
+ pagesize = <32>;
+};
--- /dev/null
+GPIO controllers on MPC8xxx SoCs
+
+This is for the non-QE/CPM/GUTs GPIO controllers as found on
+8349, 8572, 8610 and compatible.
+
+Every GPIO controller node must have #gpio-cells property defined,
+this information will be used to translate gpio-specifiers.
+
+Required properties:
+- compatible : "fsl,<CHIP>-gpio" followed by "fsl,mpc8349-gpio" for
+ 83xx, "fsl,mpc8572-gpio" for 85xx and "fsl,mpc8610-gpio" for 86xx.
+- #gpio-cells : Should be two. The first cell is the pin number and the
+ second cell is used to specify optional parameters (currently unused).
+ - interrupts : Interrupt mapping for GPIO IRQ.
+ - interrupt-parent : Phandle for the interrupt controller that
+ services interrupts for this device.
+- gpio-controller : Marks the port as GPIO controller.
+
+Example of gpio-controller nodes for a MPC8347 SoC:
+
+ gpio1: gpio-controller@c00 {
+ #gpio-cells = <2>;
+ compatible = "fsl,mpc8347-gpio", "fsl,mpc8349-gpio";
+ reg = <0xc00 0x100>;
+ interrupts = <74 0x8>;
+ interrupt-parent = <&ipic>;
+ gpio-controller;
+ };
+
+ gpio2: gpio-controller@d00 {
+ #gpio-cells = <2>;
+ compatible = "fsl,mpc8347-gpio", "fsl,mpc8349-gpio";
+ reg = <0xd00 0x100>;
+ interrupts = <75 0x8>;
+ interrupt-parent = <&ipic>;
+ gpio-controller;
+ };
+
+See booting-without-of.txt for details of how to specify GPIO
+information for devices.
+
+To use GPIO pins as interrupt sources for peripherals, specify the
+GPIO controller as the interrupt parent and define GPIO number +
+trigger mode using the interrupts property, which is defined like
+this:
+
+interrupts = <number trigger>, where:
+ - number: GPIO pin (0..31)
+ - trigger: trigger mode:
+ 2 = trigger on falling edge
+ 3 = trigger on both edges
+
+Example of device using this is:
+
+ funkyfpga@0 {
+ compatible = "funky-fpga";
+ ...
+ interrupts = <4 3>;
+ interrupt-parent = <&gpio1>;
+ };
--- /dev/null
+Specifying GPIO information for devices
+============================================
+
+1) gpios property
+-----------------
+
+Nodes that makes use of GPIOs should define them using `gpios' property,
+format of which is: <&gpio-controller1-phandle gpio1-specifier
+ &gpio-controller2-phandle gpio2-specifier
+ 0 /* holes are permitted, means no GPIO 3 */
+ &gpio-controller4-phandle gpio4-specifier
+ ...>;
+
+Note that gpio-specifier length is controller dependent.
+
+gpio-specifier may encode: bank, pin position inside the bank,
+whether pin is open-drain and whether pin is logically inverted.
+
+Example of the node using GPIOs:
+
+ node {
+ gpios = <&qe_pio_e 18 0>;
+ };
+
+In this example gpio-specifier is "18 0" and encodes GPIO pin number,
+and empty GPIO flags as accepted by the "qe_pio_e" gpio-controller.
+
+2) gpio-controller nodes
+------------------------
+
+Every GPIO controller node must have #gpio-cells property defined,
+this information will be used to translate gpio-specifiers.
+
+Example of two SOC GPIO banks defined as gpio-controller nodes:
+
+ qe_pio_a: gpio-controller@1400 {
+ #gpio-cells = <2>;
+ compatible = "fsl,qe-pario-bank-a", "fsl,qe-pario-bank";
+ reg = <0x1400 0x18>;
+ gpio-controller;
+ };
+
+ qe_pio_e: gpio-controller@1460 {
+ #gpio-cells = <2>;
+ compatible = "fsl,qe-pario-bank-e", "fsl,qe-pario-bank";
+ reg = <0x1460 0x18>;
+ gpio-controller;
+ };
+
+
--- /dev/null
+LEDs connected to GPIO lines
+
+Required properties:
+- compatible : should be "gpio-leds".
+
+Each LED is represented as a sub-node of the gpio-leds device. Each
+node's name represents the name of the corresponding LED.
+
+LED sub-node properties:
+- gpios : Should specify the LED's GPIO, see "Specifying GPIO information
+ for devices" in Documentation/powerpc/booting-without-of.txt. Active
+ low LEDs should be indicated using flags in the GPIO specifier.
+- label : (optional) The label for this LED. If omitted, the label is
+ taken from the node name (excluding the unit address).
+- linux,default-trigger : (optional) This parameter, if present, is a
+ string defining the trigger assigned to the LED. Current triggers are:
+ "backlight" - LED will act as a back-light, controlled by the framebuffer
+ system
+ "default-on" - LED will turn on, but see "default-state" below
+ "heartbeat" - LED "double" flashes at a load average based rate
+ "ide-disk" - LED indicates disk activity
+ "timer" - LED flashes at a fixed, configurable rate
+- default-state: (optional) The initial state of the LED. Valid
+ values are "on", "off", and "keep". If the LED is already on or off
+ and the default-state property is set the to same value, then no
+ glitch should be produced where the LED momentarily turns off (or
+ on). The "keep" setting will keep the LED at whatever its current
+ state is, without producing a glitch. The default is off if this
+ property is not present.
+
+Examples:
+
+leds {
+ compatible = "gpio-leds";
+ hdd {
+ label = "IDE Activity";
+ gpios = <&mcu_pio 0 1>; /* Active low */
+ linux,default-trigger = "ide-disk";
+ };
+
+ fault {
+ gpios = <&mcu_pio 1 0>;
+ /* Keep LED on if BIOS detected hardware fault */
+ default-state = "keep";
+ };
+};
+
+run-control {
+ compatible = "gpio-leds";
+ red {
+ gpios = <&mpc8572 6 0>;
+ default-state = "off";
+ };
+ green {
+ gpios = <&mpc8572 7 0>;
+ default-state = "on";
+ };
+}
--- /dev/null
+* I2C
+
+Required properties :
+
+ - reg : Offset and length of the register set for the device
+ - compatible : should be "fsl,CHIP-i2c" where CHIP is the name of a
+ compatible processor, e.g. mpc8313, mpc8543, mpc8544, mpc5121,
+ mpc5200 or mpc5200b. For the mpc5121, an additional node
+ "fsl,mpc5121-i2c-ctrl" is required as shown in the example below.
+
+Recommended properties :
+
+ - interrupts : <a b> where a is the interrupt number and b is a
+ field that represents an encoding of the sense and level
+ information for the interrupt. This should be encoded based on
+ the information in section 2) depending on the type of interrupt
+ controller you have.
+ - interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+ - fsl,preserve-clocking : boolean; if defined, the clock settings
+ from the bootloader are preserved (not touched).
+ - clock-frequency : desired I2C bus clock frequency in Hz.
+ - fsl,timeout : I2C bus timeout in microseconds.
+
+Examples :
+
+ /* MPC5121 based board */
+ i2c@1740 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "fsl,mpc5121-i2c", "fsl-i2c";
+ reg = <0x1740 0x20>;
+ interrupts = <11 0x8>;
+ interrupt-parent = <&ipic>;
+ clock-frequency = <100000>;
+ };
+
+ i2ccontrol@1760 {
+ compatible = "fsl,mpc5121-i2c-ctrl";
+ reg = <0x1760 0x8>;
+ };
+
+ /* MPC5200B based board */
+ i2c@3d00 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "fsl,mpc5200b-i2c","fsl,mpc5200-i2c","fsl-i2c";
+ reg = <0x3d00 0x40>;
+ interrupts = <2 15 0>;
+ interrupt-parent = <&mpc5200_pic>;
+ fsl,preserve-clocking;
+ };
+
+ /* MPC8544 base board */
+ i2c@3100 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "fsl,mpc8544-i2c", "fsl-i2c";
+ reg = <0x3100 0x100>;
+ interrupts = <43 2>;
+ interrupt-parent = <&mpic>;
+ clock-frequency = <400000>;
+ fsl,timeout = <10000>;
+ };
--- /dev/null
+Marvell Discovery mv64[345]6x System Controller chips
+===========================================================
+
+The Marvell mv64[345]60 series of system controller chips contain
+many of the peripherals needed to implement a complete computer
+system. In this section, we define device tree nodes to describe
+the system controller chip itself and each of the peripherals
+which it contains. Compatible string values for each node are
+prefixed with the string "marvell,", for Marvell Technology Group Ltd.
+
+1) The /system-controller node
+
+ This node is used to represent the system-controller and must be
+ present when the system uses a system controller chip. The top-level
+ system-controller node contains information that is global to all
+ devices within the system controller chip. The node name begins
+ with "system-controller" followed by the unit address, which is
+ the base address of the memory-mapped register set for the system
+ controller chip.
+
+ Required properties:
+
+ - ranges : Describes the translation of system controller addresses
+ for memory mapped registers.
+ - clock-frequency: Contains the main clock frequency for the system
+ controller chip.
+ - reg : This property defines the address and size of the
+ memory-mapped registers contained within the system controller
+ chip. The address specified in the "reg" property should match
+ the unit address of the system-controller node.
+ - #address-cells : Address representation for system controller
+ devices. This field represents the number of cells needed to
+ represent the address of the memory-mapped registers of devices
+ within the system controller chip.
+ - #size-cells : Size representation for the memory-mapped
+ registers within the system controller chip.
+ - #interrupt-cells : Defines the width of cells used to represent
+ interrupts.
+
+ Optional properties:
+
+ - model : The specific model of the system controller chip. Such
+ as, "mv64360", "mv64460", or "mv64560".
+ - compatible : A string identifying the compatibility identifiers
+ of the system controller chip.
+
+ The system-controller node contains child nodes for each system
+ controller device that the platform uses. Nodes should not be created
+ for devices which exist on the system controller chip but are not used
+
+ Example Marvell Discovery mv64360 system-controller node:
+
+ system-controller@f1000000 { /* Marvell Discovery mv64360 */
+ #address-cells = <1>;
+ #size-cells = <1>;
+ model = "mv64360"; /* Default */
+ compatible = "marvell,mv64360";
+ clock-frequency = <133333333>;
+ reg = <0xf1000000 0x10000>;
+ virtual-reg = <0xf1000000>;
+ ranges = <0x88000000 0x88000000 0x1000000 /* PCI 0 I/O Space */
+ 0x80000000 0x80000000 0x8000000 /* PCI 0 MEM Space */
+ 0xa0000000 0xa0000000 0x4000000 /* User FLASH */
+ 0x00000000 0xf1000000 0x0010000 /* Bridge's regs */
+ 0xf2000000 0xf2000000 0x0040000>;/* Integrated SRAM */
+
+ [ child node definitions... ]
+ }
+
+2) Child nodes of /system-controller
+
+ a) Marvell Discovery MDIO bus
+
+ The MDIO is a bus to which the PHY devices are connected. For each
+ device that exists on this bus, a child node should be created. See
+ the definition of the PHY node below for an example of how to define
+ a PHY.
+
+ Required properties:
+ - #address-cells : Should be <1>
+ - #size-cells : Should be <0>
+ - device_type : Should be "mdio"
+ - compatible : Should be "marvell,mv64360-mdio"
+
+ Example:
+
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ device_type = "mdio";
+ compatible = "marvell,mv64360-mdio";
+
+ ethernet-phy@0 {
+ ......
+ };
+ };
+
+
+ b) Marvell Discovery ethernet controller
+
+ The Discover ethernet controller is described with two levels
+ of nodes. The first level describes an ethernet silicon block
+ and the second level describes up to 3 ethernet nodes within
+ that block. The reason for the multiple levels is that the
+ registers for the node are interleaved within a single set
+ of registers. The "ethernet-block" level describes the
+ shared register set, and the "ethernet" nodes describe ethernet
+ port-specific properties.
+
+ Ethernet block node
+
+ Required properties:
+ - #address-cells : <1>
+ - #size-cells : <0>
+ - compatible : "marvell,mv64360-eth-block"
+ - reg : Offset and length of the register set for this block
+
+ Example Discovery Ethernet block node:
+ ethernet-block@2000 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "marvell,mv64360-eth-block";
+ reg = <0x2000 0x2000>;
+ ethernet@0 {
+ .......
+ };
+ };
+
+ Ethernet port node
+
+ Required properties:
+ - device_type : Should be "network".
+ - compatible : Should be "marvell,mv64360-eth".
+ - reg : Should be <0>, <1>, or <2>, according to which registers
+ within the silicon block the device uses.
+ - interrupts : <a> where a is the interrupt number for the port.
+ - interrupt-parent : the phandle for the interrupt controller
+ that services interrupts for this device.
+ - phy : the phandle for the PHY connected to this ethernet
+ controller.
+ - local-mac-address : 6 bytes, MAC address
+
+ Example Discovery Ethernet port node:
+ ethernet@0 {
+ device_type = "network";
+ compatible = "marvell,mv64360-eth";
+ reg = <0>;
+ interrupts = <32>;
+ interrupt-parent = <&PIC>;
+ phy = <&PHY0>;
+ local-mac-address = [ 00 00 00 00 00 00 ];
+ };
+
+
+
+ c) Marvell Discovery PHY nodes
+
+ Required properties:
+ - device_type : Should be "ethernet-phy"
+ - interrupts : <a> where a is the interrupt number for this phy.
+ - interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+ - reg : The ID number for the phy, usually a small integer
+
+ Example Discovery PHY node:
+ ethernet-phy@1 {
+ device_type = "ethernet-phy";
+ compatible = "broadcom,bcm5421";
+ interrupts = <76>; /* GPP 12 */
+ interrupt-parent = <&PIC>;
+ reg = <1>;
+ };
+
+
+ d) Marvell Discovery SDMA nodes
+
+ Represent DMA hardware associated with the MPSC (multiprotocol
+ serial controllers).
+
+ Required properties:
+ - compatible : "marvell,mv64360-sdma"
+ - reg : Offset and length of the register set for this device
+ - interrupts : <a> where a is the interrupt number for the DMA
+ device.
+ - interrupt-parent : the phandle for the interrupt controller
+ that services interrupts for this device.
+
+ Example Discovery SDMA node:
+ sdma@4000 {
+ compatible = "marvell,mv64360-sdma";
+ reg = <0x4000 0xc18>;
+ virtual-reg = <0xf1004000>;
+ interrupts = <36>;
+ interrupt-parent = <&PIC>;
+ };
+
+
+ e) Marvell Discovery BRG nodes
+
+ Represent baud rate generator hardware associated with the MPSC
+ (multiprotocol serial controllers).
+
+ Required properties:
+ - compatible : "marvell,mv64360-brg"
+ - reg : Offset and length of the register set for this device
+ - clock-src : A value from 0 to 15 which selects the clock
+ source for the baud rate generator. This value corresponds
+ to the CLKS value in the BRGx configuration register. See
+ the mv64x60 User's Manual.
+ - clock-frequence : The frequency (in Hz) of the baud rate
+ generator's input clock.
+ - current-speed : The current speed setting (presumably by
+ firmware) of the baud rate generator.
+
+ Example Discovery BRG node:
+ brg@b200 {
+ compatible = "marvell,mv64360-brg";
+ reg = <0xb200 0x8>;
+ clock-src = <8>;
+ clock-frequency = <133333333>;
+ current-speed = <9600>;
+ };
+
+
+ f) Marvell Discovery CUNIT nodes
+
+ Represent the Serial Communications Unit device hardware.
+
+ Required properties:
+ - reg : Offset and length of the register set for this device
+
+ Example Discovery CUNIT node:
+ cunit@f200 {
+ reg = <0xf200 0x200>;
+ };
+
+
+ g) Marvell Discovery MPSCROUTING nodes
+
+ Represent the Discovery's MPSC routing hardware
+
+ Required properties:
+ - reg : Offset and length of the register set for this device
+
+ Example Discovery CUNIT node:
+ mpscrouting@b500 {
+ reg = <0xb400 0xc>;
+ };
+
+
+ h) Marvell Discovery MPSCINTR nodes
+
+ Represent the Discovery's MPSC DMA interrupt hardware registers
+ (SDMA cause and mask registers).
+
+ Required properties:
+ - reg : Offset and length of the register set for this device
+
+ Example Discovery MPSCINTR node:
+ mpsintr@b800 {
+ reg = <0xb800 0x100>;
+ };
+
+
+ i) Marvell Discovery MPSC nodes
+
+ Represent the Discovery's MPSC (Multiprotocol Serial Controller)
+ serial port.
+
+ Required properties:
+ - device_type : "serial"
+ - compatible : "marvell,mv64360-mpsc"
+ - reg : Offset and length of the register set for this device
+ - sdma : the phandle for the SDMA node used by this port
+ - brg : the phandle for the BRG node used by this port
+ - cunit : the phandle for the CUNIT node used by this port
+ - mpscrouting : the phandle for the MPSCROUTING node used by this port
+ - mpscintr : the phandle for the MPSCINTR node used by this port
+ - cell-index : the hardware index of this cell in the MPSC core
+ - max_idle : value needed for MPSC CHR3 (Maximum Frame Length)
+ register
+ - interrupts : <a> where a is the interrupt number for the MPSC.
+ - interrupt-parent : the phandle for the interrupt controller
+ that services interrupts for this device.
+
+ Example Discovery MPSCINTR node:
+ mpsc@8000 {
+ device_type = "serial";
+ compatible = "marvell,mv64360-mpsc";
+ reg = <0x8000 0x38>;
+ virtual-reg = <0xf1008000>;
+ sdma = <&SDMA0>;
+ brg = <&BRG0>;
+ cunit = <&CUNIT>;
+ mpscrouting = <&MPSCROUTING>;
+ mpscintr = <&MPSCINTR>;
+ cell-index = <0>;
+ max_idle = <40>;
+ interrupts = <40>;
+ interrupt-parent = <&PIC>;
+ };
+
+
+ j) Marvell Discovery Watch Dog Timer nodes
+
+ Represent the Discovery's watchdog timer hardware
+
+ Required properties:
+ - compatible : "marvell,mv64360-wdt"
+ - reg : Offset and length of the register set for this device
+
+ Example Discovery Watch Dog Timer node:
+ wdt@b410 {
+ compatible = "marvell,mv64360-wdt";
+ reg = <0xb410 0x8>;
+ };
+
+
+ k) Marvell Discovery I2C nodes
+
+ Represent the Discovery's I2C hardware
+
+ Required properties:
+ - device_type : "i2c"
+ - compatible : "marvell,mv64360-i2c"
+ - reg : Offset and length of the register set for this device
+ - interrupts : <a> where a is the interrupt number for the I2C.
+ - interrupt-parent : the phandle for the interrupt controller
+ that services interrupts for this device.
+
+ Example Discovery I2C node:
+ compatible = "marvell,mv64360-i2c";
+ reg = <0xc000 0x20>;
+ virtual-reg = <0xf100c000>;
+ interrupts = <37>;
+ interrupt-parent = <&PIC>;
+ };
+
+
+ l) Marvell Discovery PIC (Programmable Interrupt Controller) nodes
+
+ Represent the Discovery's PIC hardware
+
+ Required properties:
+ - #interrupt-cells : <1>
+ - #address-cells : <0>
+ - compatible : "marvell,mv64360-pic"
+ - reg : Offset and length of the register set for this device
+ - interrupt-controller
+
+ Example Discovery PIC node:
+ pic {
+ #interrupt-cells = <1>;
+ #address-cells = <0>;
+ compatible = "marvell,mv64360-pic";
+ reg = <0x0 0x88>;
+ interrupt-controller;
+ };
+
+
+ m) Marvell Discovery MPP (Multipurpose Pins) multiplexing nodes
+
+ Represent the Discovery's MPP hardware
+
+ Required properties:
+ - compatible : "marvell,mv64360-mpp"
+ - reg : Offset and length of the register set for this device
+
+ Example Discovery MPP node:
+ mpp@f000 {
+ compatible = "marvell,mv64360-mpp";
+ reg = <0xf000 0x10>;
+ };
+
+
+ n) Marvell Discovery GPP (General Purpose Pins) nodes
+
+ Represent the Discovery's GPP hardware
+
+ Required properties:
+ - compatible : "marvell,mv64360-gpp"
+ - reg : Offset and length of the register set for this device
+
+ Example Discovery GPP node:
+ gpp@f000 {
+ compatible = "marvell,mv64360-gpp";
+ reg = <0xf100 0x20>;
+ };
+
+
+ o) Marvell Discovery PCI host bridge node
+
+ Represents the Discovery's PCI host bridge device. The properties
+ for this node conform to Rev 2.1 of the PCI Bus Binding to IEEE
+ 1275-1994. A typical value for the compatible property is
+ "marvell,mv64360-pci".
+
+ Example Discovery PCI host bridge node
+ pci@80000000 {
+ #address-cells = <3>;
+ #size-cells = <2>;
+ #interrupt-cells = <1>;
+ device_type = "pci";
+ compatible = "marvell,mv64360-pci";
+ reg = <0xcf8 0x8>;
+ ranges = <0x01000000 0x0 0x0
+ 0x88000000 0x0 0x01000000
+ 0x02000000 0x0 0x80000000
+ 0x80000000 0x0 0x08000000>;
+ bus-range = <0 255>;
+ clock-frequency = <66000000>;
+ interrupt-parent = <&PIC>;
+ interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+ interrupt-map = <
+ /* IDSEL 0x0a */
+ 0x5000 0 0 1 &PIC 80
+ 0x5000 0 0 2 &PIC 81
+ 0x5000 0 0 3 &PIC 91
+ 0x5000 0 0 4 &PIC 93
+
+ /* IDSEL 0x0b */
+ 0x5800 0 0 1 &PIC 91
+ 0x5800 0 0 2 &PIC 93
+ 0x5800 0 0 3 &PIC 80
+ 0x5800 0 0 4 &PIC 81
+
+ /* IDSEL 0x0c */
+ 0x6000 0 0 1 &PIC 91
+ 0x6000 0 0 2 &PIC 93
+ 0x6000 0 0 3 &PIC 80
+ 0x6000 0 0 4 &PIC 81
+
+ /* IDSEL 0x0d */
+ 0x6800 0 0 1 &PIC 93
+ 0x6800 0 0 2 &PIC 80
+ 0x6800 0 0 3 &PIC 81
+ 0x6800 0 0 4 &PIC 91
+ >;
+ };
+
+
+ p) Marvell Discovery CPU Error nodes
+
+ Represent the Discovery's CPU error handler device.
+
+ Required properties:
+ - compatible : "marvell,mv64360-cpu-error"
+ - reg : Offset and length of the register set for this device
+ - interrupts : the interrupt number for this device
+ - interrupt-parent : the phandle for the interrupt controller
+ that services interrupts for this device.
+
+ Example Discovery CPU Error node:
+ cpu-error@0070 {
+ compatible = "marvell,mv64360-cpu-error";
+ reg = <0x70 0x10 0x128 0x28>;
+ interrupts = <3>;
+ interrupt-parent = <&PIC>;
+ };
+
+
+ q) Marvell Discovery SRAM Controller nodes
+
+ Represent the Discovery's SRAM controller device.
+
+ Required properties:
+ - compatible : "marvell,mv64360-sram-ctrl"
+ - reg : Offset and length of the register set for this device
+ - interrupts : the interrupt number for this device
+ - interrupt-parent : the phandle for the interrupt controller
+ that services interrupts for this device.
+
+ Example Discovery SRAM Controller node:
+ sram-ctrl@0380 {
+ compatible = "marvell,mv64360-sram-ctrl";
+ reg = <0x380 0x80>;
+ interrupts = <13>;
+ interrupt-parent = <&PIC>;
+ };
+
+
+ r) Marvell Discovery PCI Error Handler nodes
+
+ Represent the Discovery's PCI error handler device.
+
+ Required properties:
+ - compatible : "marvell,mv64360-pci-error"
+ - reg : Offset and length of the register set for this device
+ - interrupts : the interrupt number for this device
+ - interrupt-parent : the phandle for the interrupt controller
+ that services interrupts for this device.
+
+ Example Discovery PCI Error Handler node:
+ pci-error@1d40 {
+ compatible = "marvell,mv64360-pci-error";
+ reg = <0x1d40 0x40 0xc28 0x4>;
+ interrupts = <12>;
+ interrupt-parent = <&PIC>;
+ };
+
+
+ s) Marvell Discovery Memory Controller nodes
+
+ Represent the Discovery's memory controller device.
+
+ Required properties:
+ - compatible : "marvell,mv64360-mem-ctrl"
+ - reg : Offset and length of the register set for this device
+ - interrupts : the interrupt number for this device
+ - interrupt-parent : the phandle for the interrupt controller
+ that services interrupts for this device.
+
+ Example Discovery Memory Controller node:
+ mem-ctrl@1400 {
+ compatible = "marvell,mv64360-mem-ctrl";
+ reg = <0x1400 0x60>;
+ interrupts = <17>;
+ interrupt-parent = <&PIC>;
+ };
+
+
--- /dev/null
+* Freescale Enhanced Secure Digital Host Controller (eSDHC)
+
+The Enhanced Secure Digital Host Controller provides an interface
+for MMC, SD, and SDIO types of memory cards.
+
+Required properties:
+ - compatible : should be
+ "fsl,<chip>-esdhc", "fsl,esdhc"
+ - reg : should contain eSDHC registers location and length.
+ - interrupts : should contain eSDHC interrupt.
+ - interrupt-parent : interrupt source phandle.
+ - clock-frequency : specifies eSDHC base clock frequency.
+ - sdhci,wp-inverted : (optional) specifies that eSDHC controller
+ reports inverted write-protect state;
+ - sdhci,1-bit-only : (optional) specifies that a controller can
+ only handle 1-bit data transfers.
+ - sdhci,auto-cmd12: (optional) specifies that a controller can
+ only handle auto CMD12.
+
+Example:
+
+sdhci@2e000 {
+ compatible = "fsl,mpc8378-esdhc", "fsl,esdhc";
+ reg = <0x2e000 0x1000>;
+ interrupts = <42 0x8>;
+ interrupt-parent = <&ipic>;
+ /* Filled in by U-Boot */
+ clock-frequency = <0>;
+};
--- /dev/null
+MMC/SD/SDIO slot directly connected to a SPI bus
+
+Required properties:
+- compatible : should be "mmc-spi-slot".
+- reg : should specify SPI address (chip-select number).
+- spi-max-frequency : maximum frequency for this device (Hz).
+- voltage-ranges : two cells are required, first cell specifies minimum
+ slot voltage (mV), second cell specifies maximum slot voltage (mV).
+ Several ranges could be specified.
+- gpios : (optional) may specify GPIOs in this order: Card-Detect GPIO,
+ Write-Protect GPIO.
+
+Example:
+
+ mmc-slot@0 {
+ compatible = "fsl,mpc8323rdb-mmc-slot",
+ "mmc-spi-slot";
+ reg = <0>;
+ gpios = <&qe_pio_d 14 1
+ &qe_pio_d 15 0>;
+ voltage-ranges = <3300 3300>;
+ spi-max-frequency = <50000000>;
+ };
--- /dev/null
+Freescale Localbus UPM programmed to work with NAND flash
+
+Required properties:
+- compatible : "fsl,upm-nand".
+- reg : should specify localbus chip select and size used for the chip.
+- fsl,upm-addr-offset : UPM pattern offset for the address latch.
+- fsl,upm-cmd-offset : UPM pattern offset for the command latch.
+
+Optional properties:
+- fsl,upm-wait-flags : add chip-dependent short delays after running the
+ UPM pattern (0x1), after writing a data byte (0x2) or after
+ writing out a buffer (0x4).
+- fsl,upm-addr-line-cs-offsets : address offsets for multi-chip support.
+ The corresponding address lines are used to select the chip.
+- gpios : may specify optional GPIOs connected to the Ready-Not-Busy pins
+ (R/B#). For multi-chip devices, "n" GPIO definitions are required
+ according to the number of chips.
+- chip-delay : chip dependent delay for transfering data from array to
+ read registers (tR). Required if property "gpios" is not used
+ (R/B# pins not connected).
+
+Examples:
+
+upm@1,0 {
+ compatible = "fsl,upm-nand";
+ reg = <1 0 1>;
+ fsl,upm-addr-offset = <16>;
+ fsl,upm-cmd-offset = <8>;
+ gpios = <&qe_pio_e 18 0>;
+
+ flash {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "...";
+
+ partition@0 {
+ ...
+ };
+ };
+};
+
+upm@3,0 {
+ #address-cells = <0>;
+ #size-cells = <0>;
+ compatible = "tqc,tqm8548-upm-nand", "fsl,upm-nand";
+ reg = <3 0x0 0x800>;
+ fsl,upm-addr-offset = <0x10>;
+ fsl,upm-cmd-offset = <0x08>;
+ /* Multi-chip NAND device */
+ fsl,upm-addr-line-cs-offsets = <0x0 0x200>;
+ fsl,upm-wait-flags = <0x5>;
+ chip-delay = <25>; // in micro-seconds
+
+ nand@0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ partition@0 {
+ label = "fs";
+ reg = <0x00000000 0x10000000>;
+ };
+ };
+};
--- /dev/null
+CFI or JEDEC memory-mapped NOR flash, MTD-RAM (NVRAM...)
+
+Flash chips (Memory Technology Devices) are often used for solid state
+file systems on embedded devices.
+
+ - compatible : should contain the specific model of mtd chip(s)
+ used, if known, followed by either "cfi-flash", "jedec-flash"
+ or "mtd-ram".
+ - reg : Address range(s) of the mtd chip(s)
+ It's possible to (optionally) define multiple "reg" tuples so that
+ non-identical chips can be described in one node.
+ - bank-width : Width (in bytes) of the bank. Equal to the
+ device width times the number of interleaved chips.
+ - device-width : (optional) Width of a single mtd chip. If
+ omitted, assumed to be equal to 'bank-width'.
+ - #address-cells, #size-cells : Must be present if the device has
+ sub-nodes representing partitions (see below). In this case
+ both #address-cells and #size-cells must be equal to 1.
+
+For JEDEC compatible devices, the following additional properties
+are defined:
+
+ - vendor-id : Contains the flash chip's vendor id (1 byte).
+ - device-id : Contains the flash chip's device id (1 byte).
+
+In addition to the information on the mtd bank itself, the
+device tree may optionally contain additional information
+describing partitions of the address space. This can be
+used on platforms which have strong conventions about which
+portions of a flash are used for what purposes, but which don't
+use an on-flash partition table such as RedBoot.
+
+Each partition is represented as a sub-node of the mtd device.
+Each node's name represents the name of the corresponding
+partition of the mtd device.
+
+Flash partitions
+ - reg : The partition's offset and size within the mtd bank.
+ - label : (optional) The label / name for this partition.
+ If omitted, the label is taken from the node name (excluding
+ the unit address).
+ - read-only : (optional) This parameter, if present, is a hint to
+ Linux that this partition should only be mounted
+ read-only. This is usually used for flash partitions
+ containing early-boot firmware images or data which should not
+ be clobbered.
+
+Example:
+
+ flash@ff000000 {
+ compatible = "amd,am29lv128ml", "cfi-flash";
+ reg = <ff000000 01000000>;
+ bank-width = <4>;
+ device-width = <1>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ fs@0 {
+ label = "fs";
+ reg = <0 f80000>;
+ };
+ firmware@f80000 {
+ label ="firmware";
+ reg = <f80000 80000>;
+ read-only;
+ };
+ };
+
+Here an example with multiple "reg" tuples:
+
+ flash@f0000000,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "intel,PC48F4400P0VB", "cfi-flash";
+ reg = <0 0x00000000 0x02000000
+ 0 0x02000000 0x02000000>;
+ bank-width = <2>;
+ partition@0 {
+ label = "test-part1";
+ reg = <0 0x04000000>;
+ };
+ };
+
+An example using SRAM:
+
+ sram@2,0 {
+ compatible = "samsung,k6f1616u6a", "mtd-ram";
+ reg = <2 0 0x00200000>;
+ bank-width = <2>;
+ };
+
--- /dev/null
+CAN Device Tree Bindings
+------------------------
+
+(c) 2006-2009 Secret Lab Technologies Ltd
+Grant Likely <grant.likely@secretlab.ca>
+
+fsl,mpc5200-mscan nodes
+-----------------------
+In addition to the required compatible-, reg- and interrupt-properties, you can
+also specify which clock source shall be used for the controller:
+
+- fsl,mscan-clock-source : a string describing the clock source. Valid values
+ are: "ip" for ip bus clock
+ "ref" for reference clock (XTAL)
+ "ref" is default in case this property is not
+ present.
+
+fsl,mpc5121-mscan nodes
+-----------------------
+In addition to the required compatible-, reg- and interrupt-properties, you can
+also specify which clock source and divider shall be used for the controller:
+
+- fsl,mscan-clock-source : a string describing the clock source. Valid values
+ are: "ip" for ip bus clock
+ "ref" for reference clock
+ "sys" for system clock
+ If this property is not present, an optimal CAN
+ clock source and frequency based on the system
+ clock will be selected. If this is not possible,
+ the reference clock will be used.
+
+- fsl,mscan-clock-divider: for the reference and system clock, an additional
+ clock divider can be specified. By default, a
+ value of 1 is used.
+
+Note that the MPC5121 Rev. 1 processor is not supported.
+
+Examples:
+ can@1300 {
+ compatible = "fsl,mpc5121-mscan";
+ interrupts = <12 0x8>;
+ interrupt-parent = <&ipic>;
+ reg = <0x1300 0x80>;
+ };
+
+ can@1380 {
+ compatible = "fsl,mpc5121-mscan";
+ interrupts = <13 0x8>;
+ interrupt-parent = <&ipic>;
+ reg = <0x1380 0x80>;
+ fsl,mscan-clock-source = "ref";
+ fsl,mscan-clock-divider = <3>;
+ };
--- /dev/null
+Memory mapped SJA1000 CAN controller from NXP (formerly Philips)
+
+Required properties:
+
+- compatible : should be "nxp,sja1000".
+
+- reg : should specify the chip select, address offset and size required
+ to map the registers of the SJA1000. The size is usually 0x80.
+
+- interrupts: property with a value describing the interrupt source
+ (number and sensitivity) required for the SJA1000.
+
+Optional properties:
+
+- nxp,external-clock-frequency : Frequency of the external oscillator
+ clock in Hz. Note that the internal clock frequency used by the
+ SJA1000 is half of that value. If not specified, a default value
+ of 16000000 (16 MHz) is used.
+
+- nxp,tx-output-mode : operation mode of the TX output control logic:
+ <0x0> : bi-phase output mode
+ <0x1> : normal output mode (default)
+ <0x2> : test output mode
+ <0x3> : clock output mode
+
+- nxp,tx-output-config : TX output pin configuration:
+ <0x01> : TX0 invert
+ <0x02> : TX0 pull-down (default)
+ <0x04> : TX0 pull-up
+ <0x06> : TX0 push-pull
+ <0x08> : TX1 invert
+ <0x10> : TX1 pull-down
+ <0x20> : TX1 pull-up
+ <0x30> : TX1 push-pull
+
+- nxp,clock-out-frequency : clock frequency in Hz on the CLKOUT pin.
+ If not specified or if the specified value is 0, the CLKOUT pin
+ will be disabled.
+
+- nxp,no-comparator-bypass : Allows to disable the CAN input comperator.
+
+For futher information, please have a look to the SJA1000 data sheet.
+
+Examples:
+
+can@3,100 {
+ compatible = "nxp,sja1000";
+ reg = <3 0x100 0x80>;
+ interrupts = <2 0>;
+ interrupt-parent = <&mpic>;
+ nxp,external-clock-frequency = <16000000>;
+};
+
--- /dev/null
+* MDIO IO device
+
+The MDIO is a bus to which the PHY devices are connected. For each
+device that exists on this bus, a child node should be created. See
+the definition of the PHY node in booting-without-of.txt for an example
+of how to define a PHY.
+
+Required properties:
+ - reg : Offset and length of the register set for the device
+ - compatible : Should define the compatible device type for the
+ mdio. Currently, this is most likely to be "fsl,gianfar-mdio"
+
+Example:
+
+ mdio@24520 {
+ reg = <24520 20>;
+ compatible = "fsl,gianfar-mdio";
+
+ ethernet-phy@0 {
+ ......
+ };
+ };
+
+* TBI Internal MDIO bus
+
+As of this writing, every tsec is associated with an internal TBI PHY.
+This PHY is accessed through the local MDIO bus. These buses are defined
+similarly to the mdio buses, except they are compatible with "fsl,gianfar-tbi".
+The TBI PHYs underneath them are similar to normal PHYs, but the reg property
+is considered instructive, rather than descriptive. The reg property should
+be chosen so it doesn't interfere with other PHYs on the bus.
+
+* Gianfar-compatible ethernet nodes
+
+Properties:
+
+ - device_type : Should be "network"
+ - model : Model of the device. Can be "TSEC", "eTSEC", or "FEC"
+ - compatible : Should be "gianfar"
+ - reg : Offset and length of the register set for the device
+ - local-mac-address : List of bytes representing the ethernet address of
+ this controller
+ - interrupts : For FEC devices, the first interrupt is the device's
+ interrupt. For TSEC and eTSEC devices, the first interrupt is
+ transmit, the second is receive, and the third is error.
+ - phy-handle : The phandle for the PHY connected to this ethernet
+ controller.
+ - fixed-link : <a b c d e> where a is emulated phy id - choose any,
+ but unique to the all specified fixed-links, b is duplex - 0 half,
+ 1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no
+ pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause.
+ - phy-connection-type : a string naming the controller/PHY interface type,
+ i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id", "sgmii",
+ "tbi", or "rtbi". This property is only really needed if the connection
+ is of type "rgmii-id", as all other connection types are detected by
+ hardware.
+ - fsl,magic-packet : If present, indicates that the hardware supports
+ waking up via magic packet.
+ - bd-stash : If present, indicates that the hardware supports stashing
+ buffer descriptors in the L2.
+ - rx-stash-len : Denotes the number of bytes of a received buffer to stash
+ in the L2.
+ - rx-stash-idx : Denotes the index of the first byte from the received
+ buffer to stash in the L2.
+
+Example:
+ ethernet@24000 {
+ device_type = "network";
+ model = "TSEC";
+ compatible = "gianfar";
+ reg = <0x24000 0x1000>;
+ local-mac-address = [ 00 E0 0C 00 73 00 ];
+ interrupts = <29 2 30 2 34 2>;
+ interrupt-parent = <&mpic>;
+ phy-handle = <&phy0>
+ };
--- /dev/null
+MDIO on GPIOs
+
+Currently defined compatibles:
+- virtual,gpio-mdio
+
+MDC and MDIO lines connected to GPIO controllers are listed in the
+gpios property as described in section VIII.1 in the following order:
+
+MDC, MDIO.
+
+Example:
+
+mdio {
+ compatible = "virtual,mdio-gpio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ gpios = <&qe_pio_a 11
+ &qe_pio_c 6>;
+};
--- /dev/null
+PHY nodes
+
+Required properties:
+
+ - device_type : Should be "ethernet-phy"
+ - interrupts : <a b> where a is the interrupt number and b is a
+ field that represents an encoding of the sense and level
+ information for the interrupt. This should be encoded based on
+ the information in section 2) depending on the type of interrupt
+ controller you have.
+ - interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+ - reg : The ID number for the phy, usually a small integer
+ - linux,phandle : phandle for this node; likely referenced by an
+ ethernet controller node.
+
+Example:
+
+ethernet-phy@0 {
+ linux,phandle = <2452000>
+ interrupt-parent = <40000>;
+ interrupts = <35 1>;
+ reg = <0>;
+ device_type = "ethernet-phy";
+};
--- /dev/null
+* Freescale 83xx and 512x PCI bridges
+
+Freescale 83xx and 512x SOCs include the same pci bridge core.
+
+83xx/512x specific notes:
+- reg: should contain two address length tuples
+ The first is for the internal pci bridge registers
+ The second is for the pci config space access registers
+
+Example (MPC8313ERDB)
+ pci0: pci@e0008500 {
+ cell-index = <1>;
+ interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+ interrupt-map = <
+ /* IDSEL 0x0E -mini PCI */
+ 0x7000 0x0 0x0 0x1 &ipic 18 0x8
+ 0x7000 0x0 0x0 0x2 &ipic 18 0x8
+ 0x7000 0x0 0x0 0x3 &ipic 18 0x8
+ 0x7000 0x0 0x0 0x4 &ipic 18 0x8
+
+ /* IDSEL 0x0F - PCI slot */
+ 0x7800 0x0 0x0 0x1 &ipic 17 0x8
+ 0x7800 0x0 0x0 0x2 &ipic 18 0x8
+ 0x7800 0x0 0x0 0x3 &ipic 17 0x8
+ 0x7800 0x0 0x0 0x4 &ipic 18 0x8>;
+ interrupt-parent = <&ipic>;
+ interrupts = <66 0x8>;
+ bus-range = <0x0 0x0>;
+ ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000
+ 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000
+ 0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>;
+ clock-frequency = <66666666>;
+ #interrupt-cells = <1>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ reg = <0xe0008500 0x100 /* internal registers */
+ 0xe0008300 0x8>; /* config space access registers */
+ compatible = "fsl,mpc8349-pci";
+ device_type = "pci";
+ };
--- /dev/null
+PPC4xx Clock Power Management (CPM) node
+
+Required properties:
+ - compatible : compatible list, currently only "ibm,cpm"
+ - dcr-access-method : "native"
+ - dcr-reg : < DCR register range >
+
+Optional properties:
+ - er-offset : All 4xx SoCs with a CPM controller have
+ one of two different order for the CPM
+ registers. Some have the CPM registers
+ in the following order (ER,FR,SR). The
+ others have them in the following order
+ (SR,ER,FR). For the second case set
+ er-offset = <1>.
+ - unused-units : specifier consist of one cell. For each
+ bit in the cell, the corresponding bit
+ in CPM will be set to turn off unused
+ devices.
+ - idle-doze : specifier consist of one cell. For each
+ bit in the cell, the corresponding bit
+ in CPM will be set to turn off unused
+ devices. This is usually just CPM[CPU].
+ - standby : specifier consist of one cell. For each
+ bit in the cell, the corresponding bit
+ in CPM will be set on standby and
+ restored on resume.
+ - suspend : specifier consist of one cell. For each
+ bit in the cell, the corresponding bit
+ in CPM will be set on suspend (mem) and
+ restored on resume. Note, for standby
+ and suspend the corresponding bits can
+ be different or the same. Usually for
+ standby only class 2 and 3 units are set.
+ However, the interface does not care.
+ If they are the same, the additional
+ power saving will be seeing if support
+ is available to put the DDR in self
+ refresh mode and any additional power
+ saving techniques for the specific SoC.
+
+Example:
+ CPM0: cpm {
+ compatible = "ibm,cpm";
+ dcr-access-method = "native";
+ dcr-reg = <0x160 0x003>;
+ er-offset = <0>;
+ unused-units = <0x00000100>;
+ idle-doze = <0x02000000>;
+ standby = <0xfeff0000>;
+ suspend = <0xfeff791d>;
+};
--- /dev/null
+ 4xx/Axon EMAC ethernet nodes
+
+ The EMAC ethernet controller in IBM and AMCC 4xx chips, and also
+ the Axon bridge. To operate this needs to interact with a ths
+ special McMAL DMA controller, and sometimes an RGMII or ZMII
+ interface. In addition to the nodes and properties described
+ below, the node for the OPB bus on which the EMAC sits must have a
+ correct clock-frequency property.
+
+ i) The EMAC node itself
+
+ Required properties:
+ - device_type : "network"
+
+ - compatible : compatible list, contains 2 entries, first is
+ "ibm,emac-CHIP" where CHIP is the host ASIC (440gx,
+ 405gp, Axon) and second is either "ibm,emac" or
+ "ibm,emac4". For Axon, thus, we have: "ibm,emac-axon",
+ "ibm,emac4"
+ - interrupts : <interrupt mapping for EMAC IRQ and WOL IRQ>
+ - interrupt-parent : optional, if needed for interrupt mapping
+ - reg : <registers mapping>
+ - local-mac-address : 6 bytes, MAC address
+ - mal-device : phandle of the associated McMAL node
+ - mal-tx-channel : 1 cell, index of the tx channel on McMAL associated
+ with this EMAC
+ - mal-rx-channel : 1 cell, index of the rx channel on McMAL associated
+ with this EMAC
+ - cell-index : 1 cell, hardware index of the EMAC cell on a given
+ ASIC (typically 0x0 and 0x1 for EMAC0 and EMAC1 on
+ each Axon chip)
+ - max-frame-size : 1 cell, maximum frame size supported in bytes
+ - rx-fifo-size : 1 cell, Rx fifo size in bytes for 10 and 100 Mb/sec
+ operations.
+ For Axon, 2048
+ - tx-fifo-size : 1 cell, Tx fifo size in bytes for 10 and 100 Mb/sec
+ operations.
+ For Axon, 2048.
+ - fifo-entry-size : 1 cell, size of a fifo entry (used to calculate
+ thresholds).
+ For Axon, 0x00000010
+ - mal-burst-size : 1 cell, MAL burst size (used to calculate thresholds)
+ in bytes.
+ For Axon, 0x00000100 (I think ...)
+ - phy-mode : string, mode of operations of the PHY interface.
+ Supported values are: "mii", "rmii", "smii", "rgmii",
+ "tbi", "gmii", rtbi", "sgmii".
+ For Axon on CAB, it is "rgmii"
+ - mdio-device : 1 cell, required iff using shared MDIO registers
+ (440EP). phandle of the EMAC to use to drive the
+ MDIO lines for the PHY used by this EMAC.
+ - zmii-device : 1 cell, required iff connected to a ZMII. phandle of
+ the ZMII device node
+ - zmii-channel : 1 cell, required iff connected to a ZMII. Which ZMII
+ channel or 0xffffffff if ZMII is only used for MDIO.
+ - rgmii-device : 1 cell, required iff connected to an RGMII. phandle
+ of the RGMII device node.
+ For Axon: phandle of plb5/plb4/opb/rgmii
+ - rgmii-channel : 1 cell, required iff connected to an RGMII. Which
+ RGMII channel is used by this EMAC.
+ Fox Axon: present, whatever value is appropriate for each
+ EMAC, that is the content of the current (bogus) "phy-port"
+ property.
+
+ Optional properties:
+ - phy-address : 1 cell, optional, MDIO address of the PHY. If absent,
+ a search is performed.
+ - phy-map : 1 cell, optional, bitmap of addresses to probe the PHY
+ for, used if phy-address is absent. bit 0x00000001 is
+ MDIO address 0.
+ For Axon it can be absent, though my current driver
+ doesn't handle phy-address yet so for now, keep
+ 0x00ffffff in it.
+ - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
+ operations (if absent the value is the same as
+ rx-fifo-size). For Axon, either absent or 2048.
+ - tx-fifo-size-gige : 1 cell, Tx fifo size in bytes for 1000 Mb/sec
+ operations (if absent the value is the same as
+ tx-fifo-size). For Axon, either absent or 2048.
+ - tah-device : 1 cell, optional. If connected to a TAH engine for
+ offload, phandle of the TAH device node.
+ - tah-channel : 1 cell, optional. If appropriate, channel used on the
+ TAH engine.
+
+ Example:
+
+ EMAC0: ethernet@40000800 {
+ device_type = "network";
+ compatible = "ibm,emac-440gp", "ibm,emac";
+ interrupt-parent = <&UIC1>;
+ interrupts = <1c 4 1d 4>;
+ reg = <40000800 70>;
+ local-mac-address = [00 04 AC E3 1B 1E];
+ mal-device = <&MAL0>;
+ mal-tx-channel = <0 1>;
+ mal-rx-channel = <0>;
+ cell-index = <0>;
+ max-frame-size = <5dc>;
+ rx-fifo-size = <1000>;
+ tx-fifo-size = <800>;
+ phy-mode = "rmii";
+ phy-map = <00000001>;
+ zmii-device = <&ZMII0>;
+ zmii-channel = <0>;
+ };
+
+ ii) McMAL node
+
+ Required properties:
+ - device_type : "dma-controller"
+ - compatible : compatible list, containing 2 entries, first is
+ "ibm,mcmal-CHIP" where CHIP is the host ASIC (like
+ emac) and the second is either "ibm,mcmal" or
+ "ibm,mcmal2".
+ For Axon, "ibm,mcmal-axon","ibm,mcmal2"
+ - interrupts : <interrupt mapping for the MAL interrupts sources:
+ 5 sources: tx_eob, rx_eob, serr, txde, rxde>.
+ For Axon: This is _different_ from the current
+ firmware. We use the "delayed" interrupts for txeob
+ and rxeob. Thus we end up with mapping those 5 MPIC
+ interrupts, all level positive sensitive: 10, 11, 32,
+ 33, 34 (in decimal)
+ - dcr-reg : < DCR registers range >
+ - dcr-parent : if needed for dcr-reg
+ - num-tx-chans : 1 cell, number of Tx channels
+ - num-rx-chans : 1 cell, number of Rx channels
+
+ iii) ZMII node
+
+ Required properties:
+ - compatible : compatible list, containing 2 entries, first is
+ "ibm,zmii-CHIP" where CHIP is the host ASIC (like
+ EMAC) and the second is "ibm,zmii".
+ For Axon, there is no ZMII node.
+ - reg : <registers mapping>
+
+ iv) RGMII node
+
+ Required properties:
+ - compatible : compatible list, containing 2 entries, first is
+ "ibm,rgmii-CHIP" where CHIP is the host ASIC (like
+ EMAC) and the second is "ibm,rgmii".
+ For Axon, "ibm,rgmii-axon","ibm,rgmii"
+ - reg : <registers mapping>
+ - revision : as provided by the RGMII new version register if
+ available.
+ For Axon: 0x0000012a
+
--- /dev/null
+AMCC NDFC (NanD Flash Controller)
+
+Required properties:
+- compatible : "ibm,ndfc".
+- reg : should specify chip select and size used for the chip (0x2000).
+
+Optional properties:
+- ccr : NDFC config and control register value (default 0).
+- bank-settings : NDFC bank configuration register value (default 0).
+
+Notes:
+- partition(s) - follows the OF MTD standard for partitions
+
+Example:
+
+ndfc@1,0 {
+ compatible = "ibm,ndfc";
+ reg = <0x00000001 0x00000000 0x00002000>;
+ ccr = <0x00001000>;
+ bank-settings = <0x80002222>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ nand {
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ partition@0 {
+ label = "kernel";
+ reg = <0x00000000 0x00200000>;
+ };
+ partition@200000 {
+ label = "root";
+ reg = <0x00200000 0x03E00000>;
+ };
+ };
+};
+
+
--- /dev/null
+PPC440SPe DMA/XOR (DMA Controller and XOR Accelerator)
+
+Device nodes needed for operation of the ppc440spe-adma driver
+are specified hereby. These are I2O/DMA, DMA and XOR nodes
+for DMA engines and Memory Queue Module node. The latter is used
+by ADMA driver for configuration of RAID-6 H/W capabilities of
+the PPC440SPe. In addition to the nodes and properties described
+below, the ranges property of PLB node must specify ranges for
+DMA devices.
+
+ i) The I2O node
+
+ Required properties:
+
+ - compatible : "ibm,i2o-440spe";
+ - reg : <registers mapping>
+ - dcr-reg : <DCR registers range>
+
+ Example:
+
+ I2O: i2o@400100000 {
+ compatible = "ibm,i2o-440spe";
+ reg = <0x00000004 0x00100000 0x100>;
+ dcr-reg = <0x060 0x020>;
+ };
+
+
+ ii) The DMA node
+
+ Required properties:
+
+ - compatible : "ibm,dma-440spe";
+ - cell-index : 1 cell, hardware index of the DMA engine
+ (typically 0x0 and 0x1 for DMA0 and DMA1)
+ - reg : <registers mapping>
+ - dcr-reg : <DCR registers range>
+ - interrupts : <interrupt mapping for DMA0/1 interrupts sources:
+ 2 sources: DMAx CS FIFO Needs Service IRQ (on UIC0)
+ and DMA Error IRQ (on UIC1). The latter is common
+ for both DMA engines>.
+ - interrupt-parent : needed for interrupt mapping
+
+ Example:
+
+ DMA0: dma0@400100100 {
+ compatible = "ibm,dma-440spe";
+ cell-index = <0>;
+ reg = <0x00000004 0x00100100 0x100>;
+ dcr-reg = <0x060 0x020>;
+ interrupt-parent = <&DMA0>;
+ interrupts = <0 1>;
+ #interrupt-cells = <1>;
+ #address-cells = <0>;
+ #size-cells = <0>;
+ interrupt-map = <
+ 0 &UIC0 0x14 4
+ 1 &UIC1 0x16 4>;
+ };
+
+
+ iii) XOR Accelerator node
+
+ Required properties:
+
+ - compatible : "amcc,xor-accelerator";
+ - reg : <registers mapping>
+ - interrupts : <interrupt mapping for XOR interrupt source>
+ - interrupt-parent : for interrupt mapping
+
+ Example:
+
+ xor-accel@400200000 {
+ compatible = "amcc,xor-accelerator";
+ reg = <0x00000004 0x00200000 0x400>;
+ interrupt-parent = <&UIC1>;
+ interrupts = <0x1f 4>;
+ };
+
+
+ iv) Memory Queue Module node
+
+ Required properties:
+
+ - compatible : "ibm,mq-440spe";
+ - dcr-reg : <DCR registers range>
+
+ Example:
+
+ MQ0: mq {
+ compatible = "ibm,mq-440spe";
+ dcr-reg = <0x040 0x020>;
+ };
+
--- /dev/null
+Reboot property to control system reboot on PPC4xx systems:
+
+By setting "reset_type" to one of the following values, the default
+software reset mechanism may be overidden. Here the possible values of
+"reset_type":
+
+ 1 - PPC4xx core reset
+ 2 - PPC4xx chip reset
+ 3 - PPC4xx system reset (default)
+
+Example:
+
+ cpu@0 {
+ device_type = "cpu";
+ model = "PowerPC,440SPe";
+ ...
+ reset-type = <2>; /* Use chip-reset */
+ };
--- /dev/null
+* Board Control and Status (BCSR)
+
+Required properties:
+
+ - compatible : Should be "fsl,<board>-bcsr"
+ - reg : Offset and length of the register set for the device
+
+Example:
+
+ bcsr@f8000000 {
+ compatible = "fsl,mpc8360mds-bcsr";
+ reg = <f8000000 8000>;
+ };
+
+* Freescale on board FPGA
+
+This is the memory-mapped registers for on board FPGA.
+
+Required properities:
+- compatible : should be "fsl,fpga-pixis".
+- reg : should contain the address and the length of the FPPGA register
+ set.
+- interrupt-parent: should specify phandle for the interrupt controller.
+- interrupts : should specify event (wakeup) IRQ.
+
+Example (MPC8610HPCD):
+
+ board-control@e8000000 {
+ compatible = "fsl,fpga-pixis";
+ reg = <0xe8000000 32>;
+ interrupt-parent = <&mpic>;
+ interrupts = <8 8>;
+ };
+
+* Freescale BCSR GPIO banks
+
+Some BCSR registers act as simple GPIO controllers, each such
+register can be represented by the gpio-controller node.
+
+Required properities:
+- compatible : Should be "fsl,<board>-bcsr-gpio".
+- reg : Should contain the address and the length of the GPIO bank
+ register.
+- #gpio-cells : Should be two. The first cell is the pin number and the
+ second cell is used to specify optional parameters (currently unused).
+- gpio-controller : Marks the port as GPIO controller.
+
+Example:
+
+ bcsr@1,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,mpc8360mds-bcsr";
+ reg = <1 0 0x8000>;
+ ranges = <0 1 0 0x8000>;
+
+ bcsr13: gpio-controller@d {
+ #gpio-cells = <2>;
+ compatible = "fsl,mpc8360mds-bcsr-gpio";
+ reg = <0xd 1>;
+ gpio-controller;
+ };
+ };
--- /dev/null
+* Freescale Communications Processor Module
+
+NOTE: This is an interim binding, and will likely change slightly,
+as more devices are supported. The QE bindings especially are
+incomplete.
+
+* Root CPM node
+
+Properties:
+- compatible : "fsl,cpm1", "fsl,cpm2", or "fsl,qe".
+- reg : A 48-byte region beginning with CPCR.
+
+Example:
+ cpm@119c0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ #interrupt-cells = <2>;
+ compatible = "fsl,mpc8272-cpm", "fsl,cpm2";
+ reg = <119c0 30>;
+ }
+
+* Properties common to multiple CPM/QE devices
+
+- fsl,cpm-command : This value is ORed with the opcode and command flag
+ to specify the device on which a CPM command operates.
+
+- fsl,cpm-brg : Indicates which baud rate generator the device
+ is associated with. If absent, an unused BRG
+ should be dynamically allocated. If zero, the
+ device uses an external clock rather than a BRG.
+
+- reg : Unless otherwise specified, the first resource represents the
+ scc/fcc/ucc registers, and the second represents the device's
+ parameter RAM region (if it has one).
+
+* Multi-User RAM (MURAM)
+
+The multi-user/dual-ported RAM is expressed as a bus under the CPM node.
+
+Ranges must be set up subject to the following restrictions:
+
+- Children's reg nodes must be offsets from the start of all muram, even
+ if the user-data area does not begin at zero.
+- If multiple range entries are used, the difference between the parent
+ address and the child address must be the same in all, so that a single
+ mapping can cover them all while maintaining the ability to determine
+ CPM-side offsets with pointer subtraction. It is recommended that
+ multiple range entries not be used.
+- A child address of zero must be translatable, even if no reg resources
+ contain it.
+
+A child "data" node must exist, compatible with "fsl,cpm-muram-data", to
+indicate the portion of muram that is usable by the OS for arbitrary
+purposes. The data node may have an arbitrary number of reg resources,
+all of which contribute to the allocatable muram pool.
+
+Example, based on mpc8272:
+ muram@0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <0 0 10000>;
+
+ data@0 {
+ compatible = "fsl,cpm-muram-data";
+ reg = <0 2000 9800 800>;
+ };
+ };
--- /dev/null
+* Baud Rate Generators
+
+Currently defined compatibles:
+fsl,cpm-brg
+fsl,cpm1-brg
+fsl,cpm2-brg
+
+Properties:
+- reg : There may be an arbitrary number of reg resources; BRG
+ numbers are assigned to these in order.
+- clock-frequency : Specifies the base frequency driving
+ the BRG.
+
+Example:
+ brg@119f0 {
+ compatible = "fsl,mpc8272-brg",
+ "fsl,cpm2-brg",
+ "fsl,cpm-brg";
+ reg = <119f0 10 115f0 10>;
+ clock-frequency = <d#25000000>;
+ };
--- /dev/null
+* I2C
+
+The I2C controller is expressed as a bus under the CPM node.
+
+Properties:
+- compatible : "fsl,cpm1-i2c", "fsl,cpm2-i2c"
+- reg : On CPM2 devices, the second resource doesn't specify the I2C
+ Parameter RAM itself, but the I2C_BASE field of the CPM2 Parameter RAM
+ (typically 0x8afc 0x2).
+- #address-cells : Should be one. The cell is the i2c device address with
+ the r/w bit set to zero.
+- #size-cells : Should be zero.
+- clock-frequency : Can be used to set the i2c clock frequency. If
+ unspecified, a default frequency of 60kHz is being used.
+The following two properties are deprecated. They are only used by legacy
+i2c drivers to find the bus to probe:
+- linux,i2c-index : Can be used to hard code an i2c bus number. By default,
+ the bus number is dynamically assigned by the i2c core.
+- linux,i2c-class : Can be used to override the i2c class. The class is used
+ by legacy i2c device drivers to find a bus in a specific context like
+ system management, video or sound. By default, I2C_CLASS_HWMON (1) is
+ being used. The definition of the classes can be found in
+ include/i2c/i2c.h
+
+Example, based on mpc823:
+
+ i2c@860 {
+ compatible = "fsl,mpc823-i2c",
+ "fsl,cpm1-i2c";
+ reg = <0x860 0x20 0x3c80 0x30>;
+ interrupts = <16>;
+ interrupt-parent = <&CPM_PIC>;
+ fsl,cpm-command = <0x10>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ rtc@68 {
+ compatible = "dallas,ds1307";
+ reg = <0x68>;
+ };
+ };
--- /dev/null
+* Interrupt Controllers
+
+Currently defined compatibles:
+- fsl,cpm1-pic
+ - only one interrupt cell
+- fsl,pq1-pic
+- fsl,cpm2-pic
+ - second interrupt cell is level/sense:
+ - 2 is falling edge
+ - 8 is active low
+
+Example:
+ interrupt-controller@10c00 {
+ #interrupt-cells = <2>;
+ interrupt-controller;
+ reg = <10c00 80>;
+ compatible = "mpc8272-pic", "fsl,cpm2-pic";
+ };
--- /dev/null
+* USB (Universal Serial Bus Controller)
+
+Properties:
+- compatible : "fsl,cpm1-usb", "fsl,cpm2-usb", "fsl,qe-usb"
+
+Example:
+ usb@11bc0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "fsl,cpm2-usb";
+ reg = <11b60 18 8b00 100>;
+ interrupts = <b 8>;
+ interrupt-parent = <&PIC>;
+ fsl,cpm-command = <2e600000>;
+ };
--- /dev/null
+Every GPIO controller node must have #gpio-cells property defined,
+this information will be used to translate gpio-specifiers.
+
+On CPM1 devices, all ports are using slightly different register layouts.
+Ports A, C and D are 16bit ports and Ports B and E are 32bit ports.
+
+On CPM2 devices, all ports are 32bit ports and use a common register layout.
+
+Required properties:
+- compatible : "fsl,cpm1-pario-bank-a", "fsl,cpm1-pario-bank-b",
+ "fsl,cpm1-pario-bank-c", "fsl,cpm1-pario-bank-d",
+ "fsl,cpm1-pario-bank-e", "fsl,cpm2-pario-bank"
+- #gpio-cells : Should be two. The first cell is the pin number and the
+ second cell is used to specify optional parameters (currently unused).
+- gpio-controller : Marks the port as GPIO controller.
+
+Example of three SOC GPIO banks defined as gpio-controller nodes:
+
+ CPM1_PIO_A: gpio-controller@950 {
+ #gpio-cells = <2>;
+ compatible = "fsl,cpm1-pario-bank-a";
+ reg = <0x950 0x10>;
+ gpio-controller;
+ };
+
+ CPM1_PIO_B: gpio-controller@ab8 {
+ #gpio-cells = <2>;
+ compatible = "fsl,cpm1-pario-bank-b";
+ reg = <0xab8 0x10>;
+ gpio-controller;
+ };
+
+ CPM1_PIO_E: gpio-controller@ac8 {
+ #gpio-cells = <2>;
+ compatible = "fsl,cpm1-pario-bank-e";
+ reg = <0xac8 0x18>;
+ gpio-controller;
+ };
--- /dev/null
+* Network
+
+Currently defined compatibles:
+- fsl,cpm1-scc-enet
+- fsl,cpm2-scc-enet
+- fsl,cpm1-fec-enet
+- fsl,cpm2-fcc-enet (third resource is GFEMR)
+- fsl,qe-enet
+
+Example:
+
+ ethernet@11300 {
+ device_type = "network";
+ compatible = "fsl,mpc8272-fcc-enet",
+ "fsl,cpm2-fcc-enet";
+ reg = <11300 20 8400 100 11390 1>;
+ local-mac-address = [ 00 00 00 00 00 00 ];
+ interrupts = <20 8>;
+ interrupt-parent = <&PIC>;
+ phy-handle = <&PHY0>;
+ fsl,cpm-command = <12000300>;
+ };
+
+* MDIO
+
+Currently defined compatibles:
+fsl,pq1-fec-mdio (reg is same as first resource of FEC device)
+fsl,cpm2-mdio-bitbang (reg is port C registers)
+
+Properties for fsl,cpm2-mdio-bitbang:
+fsl,mdio-pin : pin of port C controlling mdio data
+fsl,mdc-pin : pin of port C controlling mdio clock
+
+Example:
+ mdio@10d40 {
+ device_type = "mdio";
+ compatible = "fsl,mpc8272ads-mdio-bitbang",
+ "fsl,mpc8272-mdio-bitbang",
+ "fsl,cpm2-mdio-bitbang";
+ reg = <10d40 14>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ fsl,mdio-pin = <12>;
+ fsl,mdc-pin = <13>;
+ };
--- /dev/null
+* Freescale QUICC Engine module (QE)
+This represents qe module that is installed on PowerQUICC II Pro.
+
+NOTE: This is an interim binding; it should be updated to fit
+in with the CPM binding later in this document.
+
+Basically, it is a bus of devices, that could act more or less
+as a complete entity (UCC, USB etc ). All of them should be siblings on
+the "root" qe node, using the common properties from there.
+The description below applies to the qe of MPC8360 and
+more nodes and properties would be extended in the future.
+
+i) Root QE device
+
+Required properties:
+- compatible : should be "fsl,qe";
+- model : precise model of the QE, Can be "QE", "CPM", or "CPM2"
+- reg : offset and length of the device registers.
+- bus-frequency : the clock frequency for QUICC Engine.
+- fsl,qe-num-riscs: define how many RISC engines the QE has.
+- fsl,qe-num-snums: define how many serial number(SNUM) the QE can use for the
+ threads.
+
+Optional properties:
+- fsl,firmware-phandle:
+ Usage: required only if there is no fsl,qe-firmware child node
+ Value type: <phandle>
+ Definition: Points to a firmware node (see "QE Firmware Node" below)
+ that contains the firmware that should be uploaded for this QE.
+ The compatible property for the firmware node should say,
+ "fsl,qe-firmware".
+
+Recommended properties
+- brg-frequency : the internal clock source frequency for baud-rate
+ generators in Hz.
+
+Example:
+ qe@e0100000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ #interrupt-cells = <2>;
+ compatible = "fsl,qe";
+ ranges = <0 e0100000 00100000>;
+ reg = <e0100000 480>;
+ brg-frequency = <0>;
+ bus-frequency = <179A7B00>;
+ }
+
+* Multi-User RAM (MURAM)
+
+Required properties:
+- compatible : should be "fsl,qe-muram", "fsl,cpm-muram".
+- mode : the could be "host" or "slave".
+- ranges : Should be defined as specified in 1) to describe the
+ translation of MURAM addresses.
+- data-only : sub-node which defines the address area under MURAM
+ bus that can be allocated as data/parameter
+
+Example:
+
+ muram@10000 {
+ compatible = "fsl,qe-muram", "fsl,cpm-muram";
+ ranges = <0 00010000 0000c000>;
+
+ data-only@0{
+ compatible = "fsl,qe-muram-data",
+ "fsl,cpm-muram-data";
+ reg = <0 c000>;
+ };
+ };
+
+* QE Firmware Node
+
+This node defines a firmware binary that is embedded in the device tree, for
+the purpose of passing the firmware from bootloader to the kernel, or from
+the hypervisor to the guest.
+
+The firmware node itself contains the firmware binary contents, a compatible
+property, and any firmware-specific properties. The node should be placed
+inside a QE node that needs it. Doing so eliminates the need for a
+fsl,firmware-phandle property. Other QE nodes that need the same firmware
+should define an fsl,firmware-phandle property that points to the firmware node
+in the first QE node.
+
+The fsl,firmware property can be specified in the DTS (possibly using incbin)
+or can be inserted by the boot loader at boot time.
+
+Required properties:
+ - compatible
+ Usage: required
+ Value type: <string>
+ Definition: A standard property. Specify a string that indicates what
+ kind of firmware it is. For QE, this should be "fsl,qe-firmware".
+
+ - fsl,firmware
+ Usage: required
+ Value type: <prop-encoded-array>, encoded as an array of bytes
+ Definition: A standard property. This property contains the firmware
+ binary "blob".
+
+Example:
+ qe1@e0080000 {
+ compatible = "fsl,qe";
+ qe_firmware:qe-firmware {
+ compatible = "fsl,qe-firmware";
+ fsl,firmware = [0x70 0xcd 0x00 0x00 0x01 0x46 0x45 ...];
+ };
+ ...
+ };
+
+ qe2@e0090000 {
+ compatible = "fsl,qe";
+ fsl,firmware-phandle = <&qe_firmware>;
+ ...
+ };
--- /dev/null
+* Uploaded QE firmware
+
+ If a new firmware has been uploaded to the QE (usually by the
+ boot loader), then a 'firmware' child node should be added to the QE
+ node. This node provides information on the uploaded firmware that
+ device drivers may need.
+
+ Required properties:
+ - id: The string name of the firmware. This is taken from the 'id'
+ member of the qe_firmware structure of the uploaded firmware.
+ Device drivers can search this string to determine if the
+ firmware they want is already present.
+ - extended-modes: The Extended Modes bitfield, taken from the
+ firmware binary. It is a 64-bit number represented
+ as an array of two 32-bit numbers.
+ - virtual-traps: The virtual traps, taken from the firmware binary.
+ It is an array of 8 32-bit numbers.
+
+Example:
+ firmware {
+ id = "Soft-UART";
+ extended-modes = <0 0>;
+ virtual-traps = <0 0 0 0 0 0 0 0>;
+ };
--- /dev/null
+* Parallel I/O Ports
+
+This node configures Parallel I/O ports for CPUs with QE support.
+The node should reside in the "soc" node of the tree. For each
+device that using parallel I/O ports, a child node should be created.
+See the definition of the Pin configuration nodes below for more
+information.
+
+Required properties:
+- device_type : should be "par_io".
+- reg : offset to the register set and its length.
+- num-ports : number of Parallel I/O ports
+
+Example:
+par_io@1400 {
+ reg = <1400 100>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ device_type = "par_io";
+ num-ports = <7>;
+ ucc_pin@01 {
+ ......
+ };
+
+Note that "par_io" nodes are obsolete, and should not be used for
+the new device trees. Instead, each Par I/O bank should be represented
+via its own gpio-controller node:
+
+Required properties:
+- #gpio-cells : should be "2".
+- compatible : should be "fsl,<chip>-qe-pario-bank",
+ "fsl,mpc8323-qe-pario-bank".
+- reg : offset to the register set and its length.
+- gpio-controller : node to identify gpio controllers.
+
+Example:
+ qe_pio_a: gpio-controller@1400 {
+ #gpio-cells = <2>;
+ compatible = "fsl,mpc8360-qe-pario-bank",
+ "fsl,mpc8323-qe-pario-bank";
+ reg = <0x1400 0x18>;
+ gpio-controller;
+ };
+
+ qe_pio_e: gpio-controller@1460 {
+ #gpio-cells = <2>;
+ compatible = "fsl,mpc8360-qe-pario-bank",
+ "fsl,mpc8323-qe-pario-bank";
+ reg = <0x1460 0x18>;
+ gpio-controller;
+ };
--- /dev/null
+* Pin configuration nodes
+
+Required properties:
+- linux,phandle : phandle of this node; likely referenced by a QE
+ device.
+- pio-map : array of pin configurations. Each pin is defined by 6
+ integers. The six numbers are respectively: port, pin, dir,
+ open_drain, assignment, has_irq.
+ - port : port number of the pin; 0-6 represent port A-G in UM.
+ - pin : pin number in the port.
+ - dir : direction of the pin, should encode as follows:
+
+ 0 = The pin is disabled
+ 1 = The pin is an output
+ 2 = The pin is an input
+ 3 = The pin is I/O
+
+ - open_drain : indicates the pin is normal or wired-OR:
+
+ 0 = The pin is actively driven as an output
+ 1 = The pin is an open-drain driver. As an output, the pin is
+ driven active-low, otherwise it is three-stated.
+
+ - assignment : function number of the pin according to the Pin Assignment
+ tables in User Manual. Each pin can have up to 4 possible functions in
+ QE and two options for CPM.
+ - has_irq : indicates if the pin is used as source of external
+ interrupts.
+
+Example:
+ ucc_pin@01 {
+ linux,phandle = <140001>;
+ pio-map = <
+ /* port pin dir open_drain assignment has_irq */
+ 0 3 1 0 1 0 /* TxD0 */
+ 0 4 1 0 1 0 /* TxD1 */
+ 0 5 1 0 1 0 /* TxD2 */
+ 0 6 1 0 1 0 /* TxD3 */
+ 1 6 1 0 3 0 /* TxD4 */
+ 1 7 1 0 1 0 /* TxD5 */
+ 1 9 1 0 2 0 /* TxD6 */
+ 1 a 1 0 2 0 /* TxD7 */
+ 0 9 2 0 1 0 /* RxD0 */
+ 0 a 2 0 1 0 /* RxD1 */
+ 0 b 2 0 1 0 /* RxD2 */
+ 0 c 2 0 1 0 /* RxD3 */
+ 0 d 2 0 1 0 /* RxD4 */
+ 1 1 2 0 2 0 /* RxD5 */
+ 1 0 2 0 2 0 /* RxD6 */
+ 1 4 2 0 2 0 /* RxD7 */
+ 0 7 1 0 1 0 /* TX_EN */
+ 0 8 1 0 1 0 /* TX_ER */
+ 0 f 2 0 1 0 /* RX_DV */
+ 0 10 2 0 1 0 /* RX_ER */
+ 0 0 2 0 1 0 /* RX_CLK */
+ 2 9 1 0 3 0 /* GTX_CLK - CLK10 */
+ 2 8 2 0 1 0>; /* GTX125 - CLK9 */
+ };
+
+
--- /dev/null
+* UCC (Unified Communications Controllers)
+
+Required properties:
+- device_type : should be "network", "hldc", "uart", "transparent"
+ "bisync", "atm", or "serial".
+- compatible : could be "ucc_geth" or "fsl_atm" and so on.
+- cell-index : the ucc number(1-8), corresponding to UCCx in UM.
+- reg : Offset and length of the register set for the device
+- interrupts : <a b> where a is the interrupt number and b is a
+ field that represents an encoding of the sense and level
+ information for the interrupt. This should be encoded based on
+ the information in section 2) depending on the type of interrupt
+ controller you have.
+- interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+- pio-handle : The phandle for the Parallel I/O port configuration.
+- port-number : for UART drivers, the port number to use, between 0 and 3.
+ This usually corresponds to the /dev/ttyQE device, e.g. <0> = /dev/ttyQE0.
+ The port number is added to the minor number of the device. Unlike the
+ CPM UART driver, the port-number is required for the QE UART driver.
+- soft-uart : for UART drivers, if specified this means the QE UART device
+ driver should use "Soft-UART" mode, which is needed on some SOCs that have
+ broken UART hardware. Soft-UART is provided via a microcode upload.
+- rx-clock-name: the UCC receive clock source
+ "none": clock source is disabled
+ "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+ "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- tx-clock-name: the UCC transmit clock source
+ "none": clock source is disabled
+ "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+ "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+The following two properties are deprecated. rx-clock has been replaced
+with rx-clock-name, and tx-clock has been replaced with tx-clock-name.
+Drivers that currently use the deprecated properties should continue to
+do so, in order to support older device trees, but they should be updated
+to check for the new properties first.
+- rx-clock : represents the UCC receive clock source.
+ 0x00 : clock source is disabled;
+ 0x1~0x10 : clock source is BRG1~BRG16 respectively;
+ 0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
+- tx-clock: represents the UCC transmit clock source;
+ 0x00 : clock source is disabled;
+ 0x1~0x10 : clock source is BRG1~BRG16 respectively;
+ 0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
+
+Required properties for network device_type:
+- mac-address : list of bytes representing the ethernet address.
+- phy-handle : The phandle for the PHY connected to this controller.
+
+Recommended properties:
+- phy-connection-type : a string naming the controller/PHY interface type,
+ i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id" (Internal
+ Delay), "rgmii-txid" (delay on TX only), "rgmii-rxid" (delay on RX only),
+ "tbi", or "rtbi".
+
+Example:
+ ucc@2000 {
+ device_type = "network";
+ compatible = "ucc_geth";
+ cell-index = <1>;
+ reg = <2000 200>;
+ interrupts = <a0 0>;
+ interrupt-parent = <700>;
+ mac-address = [ 00 04 9f 00 23 23 ];
+ rx-clock = "none";
+ tx-clock = "clk9";
+ phy-handle = <212000>;
+ phy-connection-type = "gmii";
+ pio-handle = <140001>;
+ };
--- /dev/null
+Freescale QUICC Engine USB Controller
+
+Required properties:
+- compatible : should be "fsl,<chip>-qe-usb", "fsl,mpc8323-qe-usb".
+- reg : the first two cells should contain usb registers location and
+ length, the next two two cells should contain PRAM location and
+ length.
+- interrupts : should contain USB interrupt.
+- interrupt-parent : interrupt source phandle.
+- fsl,fullspeed-clock : specifies the full speed USB clock source:
+ "none": clock source is disabled
+ "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+ "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- fsl,lowspeed-clock : specifies the low speed USB clock source:
+ "none": clock source is disabled
+ "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+ "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- hub-power-budget : USB power budget for the root hub, in mA.
+- gpios : should specify GPIOs in this order: USBOE, USBTP, USBTN, USBRP,
+ USBRN, SPEED (optional), and POWER (optional).
+
+Example:
+
+usb@6c0 {
+ compatible = "fsl,mpc8360-qe-usb", "fsl,mpc8323-qe-usb";
+ reg = <0x6c0 0x40 0x8b00 0x100>;
+ interrupts = <11>;
+ interrupt-parent = <&qeic>;
+ fsl,fullspeed-clock = "clk21";
+ gpios = <&qe_pio_b 2 0 /* USBOE */
+ &qe_pio_b 3 0 /* USBTP */
+ &qe_pio_b 8 0 /* USBTN */
+ &qe_pio_b 9 0 /* USBRP */
+ &qe_pio_b 11 0 /* USBRN */
+ &qe_pio_e 20 0 /* SPEED */
+ &qe_pio_e 21 0 /* POWER */>;
+};
--- /dev/null
+* Serial
+
+Currently defined compatibles:
+- fsl,cpm1-smc-uart
+- fsl,cpm2-smc-uart
+- fsl,cpm1-scc-uart
+- fsl,cpm2-scc-uart
+- fsl,qe-uart
+
+Modem control lines connected to GPIO controllers are listed in the gpios
+property as described in booting-without-of.txt, section IX.1 in the following
+order:
+
+CTS, RTS, DCD, DSR, DTR, and RI.
+
+The gpios property is optional and can be left out when control lines are
+not used.
+
+Example:
+
+ serial@11a00 {
+ device_type = "serial";
+ compatible = "fsl,mpc8272-scc-uart",
+ "fsl,cpm2-scc-uart";
+ reg = <11a00 20 8000 100>;
+ interrupts = <28 8>;
+ interrupt-parent = <&PIC>;
+ fsl,cpm-brg = <1>;
+ fsl,cpm-command = <00800000>;
+ gpios = <&gpio_c 15 0
+ &gpio_d 29 0>;
+ };
--- /dev/null
+* Freescale Display Interface Unit
+
+The Freescale DIU is a LCD controller, with proper hardware, it can also
+drive DVI monitors.
+
+Required properties:
+- compatible : should be "fsl,diu" or "fsl,mpc5121-diu".
+- reg : should contain at least address and length of the DIU register
+ set.
+- interrupts : one DIU interrupt should be described here.
+- interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+
+Optional properties:
+- edid : verbatim EDID data block describing attached display.
+ Data from the detailed timing descriptor will be used to
+ program the display controller.
+
+Example (MPC8610HPCD):
+ display@2c000 {
+ compatible = "fsl,diu";
+ reg = <0x2c000 100>;
+ interrupts = <72 2>;
+ interrupt-parent = <&mpic>;
+ };
+
+Example for MPC5121:
+ display@2100 {
+ compatible = "fsl,mpc5121-diu";
+ reg = <0x2100 0x100>;
+ interrupts = <64 0x8>;
+ interrupt-parent = <&ipic>;
+ edid = [edid-data];
+ };
--- /dev/null
+* Freescale 83xx DMA Controller
+
+Freescale PowerPC 83xx have on chip general purpose DMA controllers.
+
+Required properties:
+
+- compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-dma", where CHIP is the processor
+ (mpc8349, mpc8360, etc.) and the second is
+ "fsl,elo-dma"
+- reg : <registers mapping for DMA general status reg>
+- ranges : Should be defined as specified in 1) to describe the
+ DMA controller channels.
+- cell-index : controller index. 0 for controller @ 0x8100
+- interrupts : <interrupt mapping for DMA IRQ>
+- interrupt-parent : optional, if needed for interrupt mapping
+
+
+- DMA channel nodes:
+ - compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-dma-channel", where CHIP is the processor
+ (mpc8349, mpc8350, etc.) and the second is
+ "fsl,elo-dma-channel". However, see note below.
+ - reg : <registers mapping for channel>
+ - cell-index : dma channel index starts at 0.
+
+Optional properties:
+ - interrupts : <interrupt mapping for DMA channel IRQ>
+ (on 83xx this is expected to be identical to
+ the interrupts property of the parent node)
+ - interrupt-parent : optional, if needed for interrupt mapping
+
+Example:
+ dma@82a8 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,mpc8349-dma", "fsl,elo-dma";
+ reg = <0x82a8 4>;
+ ranges = <0 0x8100 0x1a4>;
+ interrupt-parent = <&ipic>;
+ interrupts = <71 8>;
+ cell-index = <0>;
+ dma-channel@0 {
+ compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+ cell-index = <0>;
+ reg = <0 0x80>;
+ interrupt-parent = <&ipic>;
+ interrupts = <71 8>;
+ };
+ dma-channel@80 {
+ compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+ cell-index = <1>;
+ reg = <0x80 0x80>;
+ interrupt-parent = <&ipic>;
+ interrupts = <71 8>;
+ };
+ dma-channel@100 {
+ compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+ cell-index = <2>;
+ reg = <0x100 0x80>;
+ interrupt-parent = <&ipic>;
+ interrupts = <71 8>;
+ };
+ dma-channel@180 {
+ compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
+ cell-index = <3>;
+ reg = <0x180 0x80>;
+ interrupt-parent = <&ipic>;
+ interrupts = <71 8>;
+ };
+ };
+
+* Freescale 85xx/86xx DMA Controller
+
+Freescale PowerPC 85xx/86xx have on chip general purpose DMA controllers.
+
+Required properties:
+
+- compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-dma", where CHIP is the processor
+ (mpc8540, mpc8540, etc.) and the second is
+ "fsl,eloplus-dma"
+- reg : <registers mapping for DMA general status reg>
+- cell-index : controller index. 0 for controller @ 0x21000,
+ 1 for controller @ 0xc000
+- ranges : Should be defined as specified in 1) to describe the
+ DMA controller channels.
+
+- DMA channel nodes:
+ - compatible : compatible list, contains 2 entries, first is
+ "fsl,CHIP-dma-channel", where CHIP is the processor
+ (mpc8540, mpc8560, etc.) and the second is
+ "fsl,eloplus-dma-channel". However, see note below.
+ - cell-index : dma channel index starts at 0.
+ - reg : <registers mapping for channel>
+ - interrupts : <interrupt mapping for DMA channel IRQ>
+ - interrupt-parent : optional, if needed for interrupt mapping
+
+Example:
+ dma@21300 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,mpc8540-dma", "fsl,eloplus-dma";
+ reg = <0x21300 4>;
+ ranges = <0 0x21100 0x200>;
+ cell-index = <0>;
+ dma-channel@0 {
+ compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+ reg = <0 0x80>;
+ cell-index = <0>;
+ interrupt-parent = <&mpic>;
+ interrupts = <20 2>;
+ };
+ dma-channel@80 {
+ compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+ reg = <0x80 0x80>;
+ cell-index = <1>;
+ interrupt-parent = <&mpic>;
+ interrupts = <21 2>;
+ };
+ dma-channel@100 {
+ compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+ reg = <0x100 0x80>;
+ cell-index = <2>;
+ interrupt-parent = <&mpic>;
+ interrupts = <22 2>;
+ };
+ dma-channel@180 {
+ compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
+ reg = <0x180 0x80>;
+ cell-index = <3>;
+ interrupt-parent = <&mpic>;
+ interrupts = <23 2>;
+ };
+ };
+
+Note on DMA channel compatible properties: The compatible property must say
+"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel" to be used by the Elo DMA
+driver (fsldma). Any DMA channel used by fsldma cannot be used by another
+DMA driver, such as the SSI sound drivers for the MPC8610. Therefore, any DMA
+channel that should be used for another driver should not use
+"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel". For the SSI drivers, for
+example, the compatible property should be "fsl,ssi-dma-channel". See ssi.txt
+for more information.
--- /dev/null
+=====================================================================
+E500 LAW & Coherency Module Device Tree Binding
+Copyright (C) 2009 Freescale Semiconductor Inc.
+=====================================================================
+
+Local Access Window (LAW) Node
+
+The LAW node represents the region of CCSR space where local access
+windows are configured. For ECM based devices this is the first 4k
+of CCSR space that includes CCSRBAR, ALTCBAR, ALTCAR, BPTR, and some
+number of local access windows as specified by fsl,num-laws.
+
+PROPERTIES
+
+ - compatible
+ Usage: required
+ Value type: <string>
+ Definition: Must include "fsl,ecm-law"
+
+ - reg
+ Usage: required
+ Value type: <prop-encoded-array>
+ Definition: A standard property. The value specifies the
+ physical address offset and length of the CCSR space
+ registers.
+
+ - fsl,num-laws
+ Usage: required
+ Value type: <u32>
+ Definition: The value specifies the number of local access
+ windows for this device.
+
+=====================================================================
+
+E500 Coherency Module Node
+
+The E500 LAW node represents the region of CCSR space where ECM config
+and error reporting registers exist, this is the second 4k (0x1000)
+of CCSR space.
+
+PROPERTIES
+
+ - compatible
+ Usage: required
+ Value type: <string>
+ Definition: Must include "fsl,CHIP-ecm", "fsl,ecm" where
+ CHIP is the processor (mpc8572, mpc8544, etc.)
+
+ - reg
+ Usage: required
+ Value type: <prop-encoded-array>
+ Definition: A standard property. The value specifies the
+ physical address offset and length of the CCSR space
+ registers.
+
+ - interrupts
+ Usage: required
+ Value type: <prop-encoded-array>
+
+ - interrupt-parent
+ Usage: required
+ Value type: <phandle>
+
+=====================================================================
--- /dev/null
+* Freescale General-purpose Timers Module
+
+Required properties:
+ - compatible : should be
+ "fsl,<chip>-gtm", "fsl,gtm" for SOC GTMs
+ "fsl,<chip>-qe-gtm", "fsl,qe-gtm", "fsl,gtm" for QE GTMs
+ "fsl,<chip>-cpm2-gtm", "fsl,cpm2-gtm", "fsl,gtm" for CPM2 GTMs
+ - reg : should contain gtm registers location and length (0x40).
+ - interrupts : should contain four interrupts.
+ - interrupt-parent : interrupt source phandle.
+ - clock-frequency : specifies the frequency driving the timer.
+
+Example:
+
+timer@500 {
+ compatible = "fsl,mpc8360-gtm", "fsl,gtm";
+ reg = <0x500 0x40>;
+ interrupts = <90 8 78 8 84 8 72 8>;
+ interrupt-parent = <&ipic>;
+ /* filled by u-boot */
+ clock-frequency = <0>;
+};
+
+timer@440 {
+ compatible = "fsl,mpc8360-qe-gtm", "fsl,qe-gtm", "fsl,gtm";
+ reg = <0x440 0x40>;
+ interrupts = <12 13 14 15>;
+ interrupt-parent = <&qeic>;
+ /* filled by u-boot */
+ clock-frequency = <0>;
+};
--- /dev/null
+* Global Utilities Block
+
+The global utilities block controls power management, I/O device
+enabling, power-on-reset configuration monitoring, general-purpose
+I/O signal configuration, alternate function selection for multiplexed
+signals, and clock control.
+
+Required properties:
+
+ - compatible : Should define the compatible device type for
+ global-utilities.
+ - reg : Offset and length of the register set for the device.
+
+Recommended properties:
+
+ - fsl,has-rstcr : Indicates that the global utilities register set
+ contains a functioning "reset control register" (i.e. the board
+ is wired to reset upon setting the HRESET_REQ bit in this register).
+
+Example:
+ global-utilities@e0000 { /* global utilities block */
+ compatible = "fsl,mpc8548-guts";
+ reg = <e0000 1000>;
+ fsl,has-rstcr;
+ };
--- /dev/null
+* Chipselect/Local Bus
+
+Properties:
+- name : Should be localbus
+- #address-cells : Should be either two or three. The first cell is the
+ chipselect number, and the remaining cells are the
+ offset into the chipselect.
+- #size-cells : Either one or two, depending on how large each chipselect
+ can be.
+- ranges : Each range corresponds to a single chipselect, and cover
+ the entire access window as configured.
+
+Example:
+ localbus@f0010100 {
+ compatible = "fsl,mpc8272-localbus",
+ "fsl,pq2-localbus";
+ #address-cells = <2>;
+ #size-cells = <1>;
+ reg = <f0010100 40>;
+
+ ranges = <0 0 fe000000 02000000
+ 1 0 f4500000 00008000>;
+
+ flash@0,0 {
+ compatible = "jedec-flash";
+ reg = <0 0 2000000>;
+ bank-width = <4>;
+ device-width = <1>;
+ };
+
+ board-control@1,0 {
+ reg = <1 0 20>;
+ compatible = "fsl,mpc8272ads-bcsr";
+ };
+ };
--- /dev/null
+=====================================================================
+MPX LAW & Coherency Module Device Tree Binding
+Copyright (C) 2009 Freescale Semiconductor Inc.
+=====================================================================
+
+Local Access Window (LAW) Node
+
+The LAW node represents the region of CCSR space where local access
+windows are configured. For MCM based devices this is the first 4k
+of CCSR space that includes CCSRBAR, ALTCBAR, ALTCAR, BPTR, and some
+number of local access windows as specified by fsl,num-laws.
+
+PROPERTIES
+
+ - compatible
+ Usage: required
+ Value type: <string>
+ Definition: Must include "fsl,mcm-law"
+
+ - reg
+ Usage: required
+ Value type: <prop-encoded-array>
+ Definition: A standard property. The value specifies the
+ physical address offset and length of the CCSR space
+ registers.
+
+ - fsl,num-laws
+ Usage: required
+ Value type: <u32>
+ Definition: The value specifies the number of local access
+ windows for this device.
+
+=====================================================================
+
+MPX Coherency Module Node
+
+The MPX LAW node represents the region of CCSR space where MCM config
+and error reporting registers exist, this is the second 4k (0x1000)
+of CCSR space.
+
+PROPERTIES
+
+ - compatible
+ Usage: required
+ Value type: <string>
+ Definition: Must include "fsl,CHIP-mcm", "fsl,mcm" where
+ CHIP is the processor (mpc8641, mpc8610, etc.)
+
+ - reg
+ Usage: required
+ Value type: <prop-encoded-array>
+ Definition: A standard property. The value specifies the
+ physical address offset and length of the CCSR space
+ registers.
+
+ - interrupts
+ Usage: required
+ Value type: <prop-encoded-array>
+
+ - interrupt-parent
+ Usage: required
+ Value type: <phandle>
+
+=====================================================================
--- /dev/null
+Freescale MPC8349E-mITX-compatible Power Management Micro Controller Unit (MCU)
+
+Required properties:
+- compatible : "fsl,<mcu-chip>-<board>", "fsl,mcu-mpc8349emitx".
+- reg : should specify I2C address (0x0a).
+- #gpio-cells : should be 2.
+- gpio-controller : should be present.
+
+Example:
+
+mcu@0a {
+ #gpio-cells = <2>;
+ compatible = "fsl,mc9s08qg8-mpc8349emitx",
+ "fsl,mcu-mpc8349emitx";
+ reg = <0x0a>;
+ gpio-controller;
+};
--- /dev/null
+MPC5121 PSC Device Tree Bindings
+
+PSC in UART mode
+----------------
+
+For PSC in UART mode the needed PSC serial devices
+are specified by fsl,mpc5121-psc-uart nodes in the
+fsl,mpc5121-immr SoC node. Additionally the PSC FIFO
+Controller node fsl,mpc5121-psc-fifo is requered there:
+
+fsl,mpc5121-psc-uart nodes
+--------------------------
+
+Required properties :
+ - compatible : Should contain "fsl,mpc5121-psc-uart" and "fsl,mpc5121-psc"
+ - cell-index : Index of the PSC in hardware
+ - reg : Offset and length of the register set for the PSC device
+ - interrupts : <a b> where a is the interrupt number of the
+ PSC FIFO Controller and b is a field that represents an
+ encoding of the sense and level information for the interrupt.
+ - interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+
+Recommended properties :
+ - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
+ - fsl,tx-fifo-size : the size of the TX fifo slice (a multiple of 4)
+
+
+fsl,mpc5121-psc-fifo node
+-------------------------
+
+Required properties :
+ - compatible : Should be "fsl,mpc5121-psc-fifo"
+ - reg : Offset and length of the register set for the PSC
+ FIFO Controller
+ - interrupts : <a b> where a is the interrupt number of the
+ PSC FIFO Controller and b is a field that represents an
+ encoding of the sense and level information for the interrupt.
+ - interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+
+
+Example for a board using PSC0 and PSC1 devices in serial mode:
+
+serial@11000 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <0>;
+ reg = <0x11000 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+};
+
+serial@11100 {
+ compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+ cell-index = <1>;
+ reg = <0x11100 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+ fsl,rx-fifo-size = <16>;
+ fsl,tx-fifo-size = <16>;
+};
+
+pscfifo@11f00 {
+ compatible = "fsl,mpc5121-psc-fifo";
+ reg = <0x11f00 0x100>;
+ interrupts = <40 0x8>;
+ interrupt-parent = < &ipic >;
+};
--- /dev/null
+MPC5200 Device Tree Bindings
+----------------------------
+
+(c) 2006-2009 Secret Lab Technologies Ltd
+Grant Likely <grant.likely@secretlab.ca>
+
+Naming conventions
+------------------
+For mpc5200 on-chip devices, the format for each compatible value is
+<chip>-<device>[-<mode>]. The OS should be able to match a device driver
+to the device based solely on the compatible value. If two drivers
+match on the compatible list; the 'most compatible' driver should be
+selected.
+
+The split between the MPC5200 and the MPC5200B leaves a bit of a
+conundrum. How should the compatible property be set up to provide
+maximum compatibility information; but still accurately describe the
+chip? For the MPC5200; the answer is easy. Most of the SoC devices
+originally appeared on the MPC5200. Since they didn't exist anywhere
+else; the 5200 compatible properties will contain only one item;
+"fsl,mpc5200-<device>".
+
+The 5200B is almost the same as the 5200, but not quite. It fixes
+silicon bugs and it adds a small number of enhancements. Most of the
+devices either provide exactly the same interface as on the 5200. A few
+devices have extra functions but still have a backwards compatible mode.
+To express this information as completely as possible, 5200B device trees
+should have two items in the compatible list:
+ compatible = "fsl,mpc5200b-<device>","fsl,mpc5200-<device>";
+
+It is *strongly* recommended that 5200B device trees follow this convention
+(instead of only listing the base mpc5200 item).
+
+ie. ethernet on mpc5200: compatible = "fsl,mpc5200-fec";
+ ethernet on mpc5200b: compatible = "fsl,mpc5200b-fec", "fsl,mpc5200-fec";
+
+Modal devices, like PSCs, also append the configured function to the
+end of the compatible field. ie. A PSC in i2s mode would specify
+"fsl,mpc5200-psc-i2s", not "fsl,mpc5200-i2s". This convention is chosen to
+avoid naming conflicts with non-psc devices providing the same
+function. For example, "fsl,mpc5200-spi" and "fsl,mpc5200-psc-spi" describe
+the mpc5200 simple spi device and a PSC spi mode respectively.
+
+At the time of writing, exact chip may be either 'fsl,mpc5200' or
+'fsl,mpc5200b'.
+
+The soc node
+------------
+This node describes the on chip SOC peripherals. Every mpc5200 based
+board will have this node, and as such there is a common naming
+convention for SOC devices.
+
+Required properties:
+name description
+---- -----------
+ranges Memory range of the internal memory mapped registers.
+ Should be <0 [baseaddr] 0xc000>
+reg Should be <[baseaddr] 0x100>
+compatible mpc5200: "fsl,mpc5200-immr"
+ mpc5200b: "fsl,mpc5200b-immr"
+system-frequency 'fsystem' frequency in Hz; XLB, IPB, USB and PCI
+ clocks are derived from the fsystem clock.
+bus-frequency IPB bus frequency in Hz. Clock rate
+ used by most of the soc devices.
+
+soc child nodes
+---------------
+Any on chip SOC devices available to Linux must appear as soc5200 child nodes.
+
+Note: The tables below show the value for the mpc5200. A mpc5200b device
+tree should use the "fsl,mpc5200b-<device>","fsl,mpc5200-<device>" form.
+
+Required soc5200 child nodes:
+name compatible Description
+---- ---------- -----------
+cdm@<addr> fsl,mpc5200-cdm Clock Distribution
+interrupt-controller@<addr> fsl,mpc5200-pic need an interrupt
+ controller to boot
+bestcomm@<addr> fsl,mpc5200-bestcomm Bestcomm DMA controller
+
+Recommended soc5200 child nodes; populate as needed for your board
+name compatible Description
+---- ---------- -----------
+timer@<addr> fsl,mpc5200-gpt General purpose timers
+gpio@<addr> fsl,mpc5200-gpio MPC5200 simple gpio controller
+gpio@<addr> fsl,mpc5200-gpio-wkup MPC5200 wakeup gpio controller
+rtc@<addr> fsl,mpc5200-rtc Real time clock
+mscan@<addr> fsl,mpc5200-mscan CAN bus controller
+pci@<addr> fsl,mpc5200-pci PCI bridge
+serial@<addr> fsl,mpc5200-psc-uart PSC in serial mode
+i2s@<addr> fsl,mpc5200-psc-i2s PSC in i2s mode
+ac97@<addr> fsl,mpc5200-psc-ac97 PSC in ac97 mode
+spi@<addr> fsl,mpc5200-psc-spi PSC in spi mode
+irda@<addr> fsl,mpc5200-psc-irda PSC in IrDA mode
+spi@<addr> fsl,mpc5200-spi MPC5200 spi device
+ethernet@<addr> fsl,mpc5200-fec MPC5200 ethernet device
+ata@<addr> fsl,mpc5200-ata IDE ATA interface
+i2c@<addr> fsl,mpc5200-i2c I2C controller
+usb@<addr> fsl,mpc5200-ohci,ohci-be USB controller
+xlb@<addr> fsl,mpc5200-xlb XLB arbitrator
+
+fsl,mpc5200-gpt nodes
+---------------------
+On the mpc5200 and 5200b, GPT0 has a watchdog timer function. If the board
+design supports the internal wdt, then the device node for GPT0 should
+include the empty property 'fsl,has-wdt'. Note that this does not activate
+the watchdog. The timer will function as a GPT if the timer api is used, and
+it will function as watchdog if the watchdog device is used. The watchdog
+mode has priority over the gpt mode, i.e. if the watchdog is activated, any
+gpt api call to this timer will fail with -EBUSY.
+
+If you add the property
+ fsl,wdt-on-boot = <n>;
+GPT0 will be marked as in-use watchdog, i.e. blocking every gpt access to it.
+If n>0, the watchdog is started with a timeout of n seconds. If n=0, the
+configuration of the watchdog is not touched. This is useful in two cases:
+- just mark GPT0 as watchdog, blocking gpt accesses, and configure it later;
+- do not touch a configuration assigned by the boot loader which supervises
+ the boot process itself.
+
+The watchdog will respect the CONFIG_WATCHDOG_NOWAYOUT option.
+
+An mpc5200-gpt can be used as a single line GPIO controller. To do so,
+add the following properties to the gpt node:
+ gpio-controller;
+ #gpio-cells = <2>;
+When referencing the GPIO line from another node, the first cell must always
+be zero and the second cell represents the gpio flags and described in the
+gpio device tree binding.
+
+An mpc5200-gpt can be used as a single line edge sensitive interrupt
+controller. To do so, add the following properties to the gpt node:
+ interrupt-controller;
+ #interrupt-cells = <1>;
+When referencing the IRQ line from another node, the cell represents the
+sense mode; 1 for edge rising, 2 for edge falling.
+
+fsl,mpc5200-psc nodes
+---------------------
+The PSCs should include a cell-index which is the index of the PSC in
+hardware. cell-index is used to determine which shared SoC registers to
+use when setting up PSC clocking. cell-index number starts at '0'. ie:
+ PSC1 has 'cell-index = <0>'
+ PSC4 has 'cell-index = <3>'
+
+PSC in i2s mode: The mpc5200 and mpc5200b PSCs are not compatible when in
+i2s mode. An 'mpc5200b-psc-i2s' node cannot include 'mpc5200-psc-i2s' in the
+compatible field.
+
+
+fsl,mpc5200-gpio and fsl,mpc5200-gpio-wkup nodes
+------------------------------------------------
+Each GPIO controller node should have the empty property gpio-controller and
+#gpio-cells set to 2. First cell is the GPIO number which is interpreted
+according to the bit numbers in the GPIO control registers. The second cell
+is for flags which is currently unused.
+
+fsl,mpc5200-fec nodes
+---------------------
+The FEC node can specify one of the following properties to configure
+the MII link:
+- fsl,7-wire-mode - An empty property that specifies the link uses 7-wire
+ mode instead of MII
+- current-speed - Specifies that the MII should be configured for a fixed
+ speed. This property should contain two cells. The
+ first cell specifies the speed in Mbps and the second
+ should be '0' for half duplex and '1' for full duplex
+- phy-handle - Contains a phandle to an Ethernet PHY.
+
+Interrupt controller (fsl,mpc5200-pic) node
+-------------------------------------------
+The mpc5200 pic binding splits hardware IRQ numbers into two levels. The
+split reflects the layout of the PIC hardware itself, which groups
+interrupts into one of three groups; CRIT, MAIN or PERP. Also, the
+Bestcomm dma engine has it's own set of interrupt sources which are
+cascaded off of peripheral interrupt 0, which the driver interprets as a
+fourth group, SDMA.
+
+The interrupts property for device nodes using the mpc5200 pic consists
+of three cells; <L1 L2 level>
+
+ L1 := [CRIT=0, MAIN=1, PERP=2, SDMA=3]
+ L2 := interrupt number; directly mapped from the value in the
+ "ICTL PerStat, MainStat, CritStat Encoded Register"
+ level := [LEVEL_HIGH=0, EDGE_RISING=1, EDGE_FALLING=2, LEVEL_LOW=3]
+
+For external IRQs, use the following interrupt property values (how to
+specify external interrupts is a frequently asked question):
+External interrupts:
+ external irq0: interrupts = <0 0 n>;
+ external irq1: interrupts = <1 1 n>;
+ external irq2: interrupts = <1 2 n>;
+ external irq3: interrupts = <1 3 n>;
+'n' is sense (0: level high, 1: edge rising, 2: edge falling 3: level low)
+
+fsl,mpc5200-mscan nodes
+-----------------------
+See file can.txt in this directory.
--- /dev/null
+* OpenPIC and its interrupt numbers on Freescale's e500/e600 cores
+
+The OpenPIC specification does not specify which interrupt source has to
+become which interrupt number. This is up to the software implementation
+of the interrupt controller. The only requirement is that every
+interrupt source has to have an unique interrupt number / vector number.
+To accomplish this the current implementation assigns the number zero to
+the first source, the number one to the second source and so on until
+all interrupt sources have their unique number.
+Usually the assigned vector number equals the interrupt number mentioned
+in the documentation for a given core / CPU. This is however not true
+for the e500 cores (MPC85XX CPUs) where the documentation distinguishes
+between internal and external interrupt sources and starts counting at
+zero for both of them.
+
+So what to write for external interrupt source X or internal interrupt
+source Y into the device tree? Here is an example:
+
+The memory map for the interrupt controller in the MPC8544[0] shows,
+that the first interrupt source starts at 0x5_0000 (PIC Register Address
+Map-Interrupt Source Configuration Registers). This source becomes the
+number zero therefore:
+ External interrupt 0 = interrupt number 0
+ External interrupt 1 = interrupt number 1
+ External interrupt 2 = interrupt number 2
+ ...
+Every interrupt number allocates 0x20 bytes register space. So to get
+its number it is sufficient to shift the lower 16bits to right by five.
+So for the external interrupt 10 we have:
+ 0x0140 >> 5 = 10
+
+After the external sources, the internal sources follow. The in core I2C
+controller on the MPC8544 for instance has the internal source number
+27. Oo obtain its interrupt number we take the lower 16bits of its memory
+address (0x5_0560) and shift it right:
+ 0x0560 >> 5 = 43
+
+Therefore the I2C device node for the MPC8544 CPU has to have the
+interrupt number 43 specified in the device tree.
+
+[0] MPC8544E PowerQUICCTM III, Integrated Host Processor Family Reference Manual
+ MPC8544ERM Rev. 1 10/2007
--- /dev/null
+* Freescale MSI interrupt controller
+
+Required properties:
+- compatible : compatible list, contains 2 entries,
+ first is "fsl,CHIP-msi", where CHIP is the processor(mpc8610, mpc8572,
+ etc.) and the second is "fsl,mpic-msi" or "fsl,ipic-msi" depending on
+ the parent type.
+- reg : should contain the address and the length of the shared message
+ interrupt register set.
+- msi-available-ranges: use <start count> style section to define which
+ msi interrupt can be used in the 256 msi interrupts. This property is
+ optional, without this, all the 256 MSI interrupts can be used.
+- interrupts : each one of the interrupts here is one entry per 32 MSIs,
+ and routed to the host interrupt controller. the interrupts should
+ be set as edge sensitive.
+- interrupt-parent: the phandle for the interrupt controller
+ that services interrupts for this device. for 83xx cpu, the interrupts
+ are routed to IPIC, and for 85xx/86xx cpu the interrupts are routed
+ to MPIC.
+
+Example:
+ msi@41600 {
+ compatible = "fsl,mpc8610-msi", "fsl,mpic-msi";
+ reg = <0x41600 0x80>;
+ msi-available-ranges = <0 0x100>;
+ interrupts = <
+ 0xe0 0
+ 0xe1 0
+ 0xe2 0
+ 0xe3 0
+ 0xe4 0
+ 0xe5 0
+ 0xe6 0
+ 0xe7 0>;
+ interrupt-parent = <&mpic>;
+ };
--- /dev/null
+* Power Management Controller
+
+Properties:
+- compatible: "fsl,<chip>-pmc".
+
+ "fsl,mpc8349-pmc" should be listed for any chip whose PMC is
+ compatible. "fsl,mpc8313-pmc" should also be listed for any chip
+ whose PMC is compatible, and implies deep-sleep capability.
+
+ "fsl,mpc8548-pmc" should be listed for any chip whose PMC is
+ compatible. "fsl,mpc8536-pmc" should also be listed for any chip
+ whose PMC is compatible, and implies deep-sleep capability.
+
+ "fsl,mpc8641d-pmc" should be listed for any chip whose PMC is
+ compatible; all statements below that apply to "fsl,mpc8548-pmc" also
+ apply to "fsl,mpc8641d-pmc".
+
+ Compatibility does not include bit assignments in SCCR/PMCDR/DEVDISR; these
+ bit assignments are indicated via the sleep specifier in each device's
+ sleep property.
+
+- reg: For devices compatible with "fsl,mpc8349-pmc", the first resource
+ is the PMC block, and the second resource is the Clock Configuration
+ block.
+
+ For devices compatible with "fsl,mpc8548-pmc", the first resource
+ is a 32-byte block beginning with DEVDISR.
+
+- interrupts: For "fsl,mpc8349-pmc"-compatible devices, the first
+ resource is the PMC block interrupt.
+
+- fsl,mpc8313-wakeup-timer: For "fsl,mpc8313-pmc"-compatible devices,
+ this is a phandle to an "fsl,gtm" node on which timer 4 can be used as
+ a wakeup source from deep sleep.
+
+Sleep specifiers:
+
+ fsl,mpc8349-pmc: Sleep specifiers consist of one cell. For each bit
+ that is set in the cell, the corresponding bit in SCCR will be saved
+ and cleared on suspend, and restored on resume. This sleep controller
+ supports disabling and resuming devices at any time.
+
+ fsl,mpc8536-pmc: Sleep specifiers consist of three cells, the third of
+ which will be ORed into PMCDR upon suspend, and cleared from PMCDR
+ upon resume. The first two cells are as described for fsl,mpc8578-pmc.
+ This sleep controller only supports disabling devices during system
+ sleep, or permanently.
+
+ fsl,mpc8548-pmc: Sleep specifiers consist of one or two cells, the
+ first of which will be ORed into DEVDISR (and the second into
+ DEVDISR2, if present -- this cell should be zero or absent if the
+ hardware does not have DEVDISR2) upon a request for permanent device
+ disabling. This sleep controller does not support configuring devices
+ to disable during system sleep (unless supported by another compatible
+ match), or dynamically.
+
+Example:
+
+ power@b00 {
+ compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc";
+ reg = <0xb00 0x100 0xa00 0x100>;
+ interrupts = <80 8>;
+ };
--- /dev/null
+Freescale SoC SEC Security Engines
+
+Required properties:
+
+- compatible : Should contain entries for this and backward compatible
+ SEC versions, high to low, e.g., "fsl,sec2.1", "fsl,sec2.0"
+- reg : Offset and length of the register set for the device
+- interrupts : the SEC's interrupt number
+- fsl,num-channels : An integer representing the number of channels
+ available.
+- fsl,channel-fifo-len : An integer representing the number of
+ descriptor pointers each channel fetch fifo can hold.
+- fsl,exec-units-mask : The bitmask representing what execution units
+ (EUs) are available. It's a single 32-bit cell. EU information
+ should be encoded following the SEC's Descriptor Header Dword
+ EU_SEL0 field documentation, i.e. as follows:
+
+ bit 0 = reserved - should be 0
+ bit 1 = set if SEC has the ARC4 EU (AFEU)
+ bit 2 = set if SEC has the DES/3DES EU (DEU)
+ bit 3 = set if SEC has the message digest EU (MDEU/MDEU-A)
+ bit 4 = set if SEC has the random number generator EU (RNG)
+ bit 5 = set if SEC has the public key EU (PKEU)
+ bit 6 = set if SEC has the AES EU (AESU)
+ bit 7 = set if SEC has the Kasumi EU (KEU)
+ bit 8 = set if SEC has the CRC EU (CRCU)
+ bit 11 = set if SEC has the message digest EU extended alg set (MDEU-B)
+
+remaining bits are reserved for future SEC EUs.
+
+- fsl,descriptor-types-mask : The bitmask representing what descriptors
+ are available. It's a single 32-bit cell. Descriptor type information
+ should be encoded following the SEC's Descriptor Header Dword DESC_TYPE
+ field documentation, i.e. as follows:
+
+ bit 0 = set if SEC supports the aesu_ctr_nonsnoop desc. type
+ bit 1 = set if SEC supports the ipsec_esp descriptor type
+ bit 2 = set if SEC supports the common_nonsnoop desc. type
+ bit 3 = set if SEC supports the 802.11i AES ccmp desc. type
+ bit 4 = set if SEC supports the hmac_snoop_no_afeu desc. type
+ bit 5 = set if SEC supports the srtp descriptor type
+ bit 6 = set if SEC supports the non_hmac_snoop_no_afeu desc.type
+ bit 7 = set if SEC supports the pkeu_assemble descriptor type
+ bit 8 = set if SEC supports the aesu_key_expand_output desc.type
+ bit 9 = set if SEC supports the pkeu_ptmul descriptor type
+ bit 10 = set if SEC supports the common_nonsnoop_afeu desc. type
+ bit 11 = set if SEC supports the pkeu_ptadd_dbl descriptor type
+
+ ..and so on and so forth.
+
+Optional properties:
+
+- interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+
+Example:
+
+ /* MPC8548E */
+ crypto@30000 {
+ compatible = "fsl,sec2.1", "fsl,sec2.0";
+ reg = <0x30000 0x10000>;
+ interrupts = <29 2>;
+ interrupt-parent = <&mpic>;
+ fsl,num-channels = <4>;
+ fsl,channel-fifo-len = <24>;
+ fsl,exec-units-mask = <0xfe>;
+ fsl,descriptor-types-mask = <0x12b0ebf>;
+ };
--- /dev/null
+Freescale Synchronous Serial Interface
+
+The SSI is a serial device that communicates with audio codecs. It can
+be programmed in AC97, I2S, left-justified, or right-justified modes.
+
+Required properties:
+- compatible: Compatible list, contains "fsl,ssi".
+- cell-index: The SSI, <0> = SSI1, <1> = SSI2, and so on.
+- reg: Offset and length of the register set for the device.
+- interrupts: <a b> where a is the interrupt number and b is a
+ field that represents an encoding of the sense and
+ level information for the interrupt. This should be
+ encoded based on the information in section 2)
+ depending on the type of interrupt controller you
+ have.
+- interrupt-parent: The phandle for the interrupt controller that
+ services interrupts for this device.
+- fsl,mode: The operating mode for the SSI interface.
+ "i2s-slave" - I2S mode, SSI is clock slave
+ "i2s-master" - I2S mode, SSI is clock master
+ "lj-slave" - left-justified mode, SSI is clock slave
+ "lj-master" - l.j. mode, SSI is clock master
+ "rj-slave" - right-justified mode, SSI is clock slave
+ "rj-master" - r.j., SSI is clock master
+ "ac97-slave" - AC97 mode, SSI is clock slave
+ "ac97-master" - AC97 mode, SSI is clock master
+- fsl,playback-dma: Phandle to a node for the DMA channel to use for
+ playback of audio. This is typically dictated by SOC
+ design. See the notes below.
+- fsl,capture-dma: Phandle to a node for the DMA channel to use for
+ capture (recording) of audio. This is typically dictated
+ by SOC design. See the notes below.
+- fsl,fifo-depth: The number of elements in the transmit and receive FIFOs.
+ This number is the maximum allowed value for SFCSR[TFWM0].
+- fsl,ssi-asynchronous:
+ If specified, the SSI is to be programmed in asynchronous
+ mode. In this mode, pins SRCK, STCK, SRFS, and STFS must
+ all be connected to valid signals. In synchronous mode,
+ SRCK and SRFS are ignored. Asynchronous mode allows
+ playback and capture to use different sample sizes and
+ sample rates. Some drivers may require that SRCK and STCK
+ be connected together, and SRFS and STFS be connected
+ together. This would still allow different sample sizes,
+ but not different sample rates.
+
+Optional properties:
+- codec-handle: Phandle to a 'codec' node that defines an audio
+ codec connected to this SSI. This node is typically
+ a child of an I2C or other control node.
+
+Child 'codec' node required properties:
+- compatible: Compatible list, contains the name of the codec
+
+Child 'codec' node optional properties:
+- clock-frequency: The frequency of the input clock, which typically comes
+ from an on-board dedicated oscillator.
+
+Notes on fsl,playback-dma and fsl,capture-dma:
+
+On SOCs that have an SSI, specific DMA channels are hard-wired for playback
+and capture. On the MPC8610, for example, SSI1 must use DMA channel 0 for
+playback and DMA channel 1 for capture. SSI2 must use DMA channel 2 for
+playback and DMA channel 3 for capture. The developer can choose which
+DMA controller to use, but the channels themselves are hard-wired. The
+purpose of these two properties is to represent this hardware design.
+
+The device tree nodes for the DMA channels that are referenced by
+"fsl,playback-dma" and "fsl,capture-dma" must be marked as compatible with
+"fsl,ssi-dma-channel". The SOC-specific compatible string (e.g.
+"fsl,mpc8610-dma-channel") can remain. If these nodes are left as
+"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel", then the generic Elo DMA
+drivers (fsldma) will attempt to use them, and it will conflict with the
+sound drivers.
--- /dev/null
+
+Nintendo GameCube device tree
+=============================
+
+1) The "flipper" node
+
+ This node represents the multi-function "Flipper" chip, which packages
+ many of the devices found in the Nintendo GameCube.
+
+ Required properties:
+
+ - compatible : Should be "nintendo,flipper"
+
+1.a) The Video Interface (VI) node
+
+ Represents the interface between the graphics processor and a external
+ video encoder.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-vi"
+ - reg : should contain the VI registers location and length
+ - interrupts : should contain the VI interrupt
+
+1.b) The Processor Interface (PI) node
+
+ Represents the data and control interface between the main processor
+ and graphics and audio processor.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-pi"
+ - reg : should contain the PI registers location and length
+
+1.b.i) The "Flipper" interrupt controller node
+
+ Represents the interrupt controller within the "Flipper" chip.
+ The node for the "Flipper" interrupt controller must be placed under
+ the PI node.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-pic"
+
+1.c) The Digital Signal Procesor (DSP) node
+
+ Represents the digital signal processor interface, designed to offload
+ audio related tasks.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-dsp"
+ - reg : should contain the DSP registers location and length
+ - interrupts : should contain the DSP interrupt
+
+1.c.i) The Auxiliary RAM (ARAM) node
+
+ Represents the non cpu-addressable ram designed mainly to store audio
+ related information.
+ The ARAM node must be placed under the DSP node.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-aram"
+ - reg : should contain the ARAM start (zero-based) and length
+
+1.d) The Disk Interface (DI) node
+
+ Represents the interface used to communicate with mass storage devices.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-di"
+ - reg : should contain the DI registers location and length
+ - interrupts : should contain the DI interrupt
+
+1.e) The Audio Interface (AI) node
+
+ Represents the interface to the external 16-bit stereo digital-to-analog
+ converter.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-ai"
+ - reg : should contain the AI registers location and length
+ - interrupts : should contain the AI interrupt
+
+1.f) The Serial Interface (SI) node
+
+ Represents the interface to the four single bit serial interfaces.
+ The SI is a proprietary serial interface used normally to control gamepads.
+ It's NOT a RS232-type interface.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-si"
+ - reg : should contain the SI registers location and length
+ - interrupts : should contain the SI interrupt
+
+1.g) The External Interface (EXI) node
+
+ Represents the multi-channel SPI-like interface.
+
+ Required properties:
+
+ - compatible : should be "nintendo,flipper-exi"
+ - reg : should contain the EXI registers location and length
+ - interrupts : should contain the EXI interrupt
+
--- /dev/null
+
+Nintendo Wii device tree
+========================
+
+0) The root node
+
+ This node represents the Nintendo Wii video game console.
+
+ Required properties:
+
+ - model : Should be "nintendo,wii"
+ - compatible : Should be "nintendo,wii"
+
+1) The "hollywood" node
+
+ This node represents the multi-function "Hollywood" chip, which packages
+ many of the devices found in the Nintendo Wii.
+
+ Required properties:
+
+ - compatible : Should be "nintendo,hollywood"
+
+1.a) The Video Interface (VI) node
+
+ Represents the interface between the graphics processor and a external
+ video encoder.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-vi","nintendo,flipper-vi"
+ - reg : should contain the VI registers location and length
+ - interrupts : should contain the VI interrupt
+
+1.b) The Processor Interface (PI) node
+
+ Represents the data and control interface between the main processor
+ and graphics and audio processor.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-pi","nintendo,flipper-pi"
+ - reg : should contain the PI registers location and length
+
+1.b.i) The "Flipper" interrupt controller node
+
+ Represents the "Flipper" interrupt controller within the "Hollywood" chip.
+ The node for the "Flipper" interrupt controller must be placed under
+ the PI node.
+
+ Required properties:
+
+ - #interrupt-cells : <1>
+ - compatible : should be "nintendo,flipper-pic"
+ - interrupt-controller
+
+1.c) The Digital Signal Procesor (DSP) node
+
+ Represents the digital signal processor interface, designed to offload
+ audio related tasks.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-dsp","nintendo,flipper-dsp"
+ - reg : should contain the DSP registers location and length
+ - interrupts : should contain the DSP interrupt
+
+1.d) The Serial Interface (SI) node
+
+ Represents the interface to the four single bit serial interfaces.
+ The SI is a proprietary serial interface used normally to control gamepads.
+ It's NOT a RS232-type interface.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-si","nintendo,flipper-si"
+ - reg : should contain the SI registers location and length
+ - interrupts : should contain the SI interrupt
+
+1.e) The Audio Interface (AI) node
+
+ Represents the interface to the external 16-bit stereo digital-to-analog
+ converter.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-ai","nintendo,flipper-ai"
+ - reg : should contain the AI registers location and length
+ - interrupts : should contain the AI interrupt
+
+1.f) The External Interface (EXI) node
+
+ Represents the multi-channel SPI-like interface.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-exi","nintendo,flipper-exi"
+ - reg : should contain the EXI registers location and length
+ - interrupts : should contain the EXI interrupt
+
+1.g) The Open Host Controller Interface (OHCI) nodes
+
+ Represent the USB 1.x Open Host Controller Interfaces.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-usb-ohci","usb-ohci"
+ - reg : should contain the OHCI registers location and length
+ - interrupts : should contain the OHCI interrupt
+
+1.h) The Enhanced Host Controller Interface (EHCI) node
+
+ Represents the USB 2.0 Enhanced Host Controller Interface.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-usb-ehci","usb-ehci"
+ - reg : should contain the EHCI registers location and length
+ - interrupts : should contain the EHCI interrupt
+
+1.i) The Secure Digital Host Controller Interface (SDHCI) nodes
+
+ Represent the Secure Digital Host Controller Interfaces.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-sdhci","sdhci"
+ - reg : should contain the SDHCI registers location and length
+ - interrupts : should contain the SDHCI interrupt
+
+1.j) The Inter-Processsor Communication (IPC) node
+
+ Represent the Inter-Processor Communication interface. This interface
+ enables communications between the Broadway and the Starlet processors.
+
+ - compatible : should be "nintendo,hollywood-ipc"
+ - reg : should contain the IPC registers location and length
+ - interrupts : should contain the IPC interrupt
+
+1.k) The "Hollywood" interrupt controller node
+
+ Represents the "Hollywood" interrupt controller within the
+ "Hollywood" chip.
+
+ Required properties:
+
+ - #interrupt-cells : <1>
+ - compatible : should be "nintendo,hollywood-pic"
+ - reg : should contain the controller registers location and length
+ - interrupt-controller
+ - interrupts : should contain the cascade interrupt of the "flipper" pic
+ - interrupt-parent: should contain the phandle of the "flipper" pic
+
+1.l) The General Purpose I/O (GPIO) controller node
+
+ Represents the dual access 32 GPIO controller interface.
+
+ Required properties:
+
+ - #gpio-cells : <2>
+ - compatible : should be "nintendo,hollywood-gpio"
+ - reg : should contain the IPC registers location and length
+ - gpio-controller
+
+1.m) The control node
+
+ Represents the control interface used to setup several miscellaneous
+ settings of the "Hollywood" chip like boot memory mappings, resets,
+ disk interface mode, etc.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-control"
+ - reg : should contain the control registers location and length
+
+1.n) The Disk Interface (DI) node
+
+ Represents the interface used to communicate with mass storage devices.
+
+ Required properties:
+
+ - compatible : should be "nintendo,hollywood-di"
+ - reg : should contain the DI registers location and length
+ - interrupts : should contain the DI interrupt
+
--- /dev/null
+* SPI (Serial Peripheral Interface)
+
+Required properties:
+- cell-index : QE SPI subblock index.
+ 0: QE subblock SPI1
+ 1: QE subblock SPI2
+- compatible : should be "fsl,spi".
+- mode : the SPI operation mode, it can be "cpu" or "cpu-qe".
+- reg : Offset and length of the register set for the device
+- interrupts : <a b> where a is the interrupt number and b is a
+ field that represents an encoding of the sense and level
+ information for the interrupt. This should be encoded based on
+ the information in section 2) depending on the type of interrupt
+ controller you have.
+- interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+
+Optional properties:
+- gpios : specifies the gpio pins to be used for chipselects.
+ The gpios will be referred to as reg = <index> in the SPI child nodes.
+ If unspecified, a single SPI device without a chip select can be used.
+
+Example:
+ spi@4c0 {
+ cell-index = <0>;
+ compatible = "fsl,spi";
+ reg = <4c0 40>;
+ interrupts = <82 0>;
+ interrupt-parent = <700>;
+ mode = "cpu";
+ gpios = <&gpio 18 1 // device reg=<0>
+ &gpio 19 1>; // device reg=<1>
+ };
+
+
+* eSPI (Enhanced Serial Peripheral Interface)
+
+Required properties:
+- compatible : should be "fsl,mpc8536-espi".
+- reg : Offset and length of the register set for the device.
+- interrupts : should contain eSPI interrupt, the device has one interrupt.
+- fsl,espi-num-chipselects : the number of the chipselect signals.
+
+Example:
+ spi@110000 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "fsl,mpc8536-espi";
+ reg = <0x110000 0x1000>;
+ interrupts = <53 0x2>;
+ interrupt-parent = <&mpic>;
+ fsl,espi-num-chipselects = <4>;
+ };
--- /dev/null
+SPI (Serial Peripheral Interface) busses
+
+SPI busses can be described with a node for the SPI master device
+and a set of child nodes for each SPI slave on the bus. For this
+discussion, it is assumed that the system's SPI controller is in
+SPI master mode. This binding does not describe SPI controllers
+in slave mode.
+
+The SPI master node requires the following properties:
+- #address-cells - number of cells required to define a chip select
+ address on the SPI bus.
+- #size-cells - should be zero.
+- compatible - name of SPI bus controller following generic names
+ recommended practice.
+No other properties are required in the SPI bus node. It is assumed
+that a driver for an SPI bus device will understand that it is an SPI bus.
+However, the binding does not attempt to define the specific method for
+assigning chip select numbers. Since SPI chip select configuration is
+flexible and non-standardized, it is left out of this binding with the
+assumption that board specific platform code will be used to manage
+chip selects. Individual drivers can define additional properties to
+support describing the chip select layout.
+
+SPI slave nodes must be children of the SPI master node and can
+contain the following properties.
+- reg - (required) chip select address of device.
+- compatible - (required) name of SPI device following generic names
+ recommended practice
+- spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz
+- spi-cpol - (optional) Empty property indicating device requires
+ inverse clock polarity (CPOL) mode
+- spi-cpha - (optional) Empty property indicating device requires
+ shifted clock phase (CPHA) mode
+- spi-cs-high - (optional) Empty property indicating device requires
+ chip select active high
+
+SPI example for an MPC5200 SPI bus:
+ spi@f00 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi";
+ reg = <0xf00 0x20>;
+ interrupts = <2 13 0 2 14 0>;
+ interrupt-parent = <&mpc5200_pic>;
+
+ ethernet-switch@0 {
+ compatible = "micrel,ks8995m";
+ spi-max-frequency = <1000000>;
+ reg = <0>;
+ };
+
+ codec@1 {
+ compatible = "ti,tlv320aic26";
+ spi-max-frequency = <100000>;
+ reg = <1>;
+ };
+ };
--- /dev/null
+Freescale SOC USB controllers
+
+The device node for a USB controller that is part of a Freescale
+SOC is as described in the document "Open Firmware Recommended
+Practice : Universal Serial Bus" with the following modifications
+and additions :
+
+Required properties :
+ - compatible : Should be "fsl-usb2-mph" for multi port host USB
+ controllers, or "fsl-usb2-dr" for dual role USB controllers
+ or "fsl,mpc5121-usb2-dr" for dual role USB controllers of MPC5121
+ - phy_type : For multi port host USB controllers, should be one of
+ "ulpi", or "serial". For dual role USB controllers, should be
+ one of "ulpi", "utmi", "utmi_wide", or "serial".
+ - reg : Offset and length of the register set for the device
+ - port0 : boolean; if defined, indicates port0 is connected for
+ fsl-usb2-mph compatible controllers. Either this property or
+ "port1" (or both) must be defined for "fsl-usb2-mph" compatible
+ controllers.
+ - port1 : boolean; if defined, indicates port1 is connected for
+ fsl-usb2-mph compatible controllers. Either this property or
+ "port0" (or both) must be defined for "fsl-usb2-mph" compatible
+ controllers.
+ - dr_mode : indicates the working mode for "fsl-usb2-dr" compatible
+ controllers. Can be "host", "peripheral", or "otg". Default to
+ "host" if not defined for backward compatibility.
+
+Recommended properties :
+ - interrupts : <a b> where a is the interrupt number and b is a
+ field that represents an encoding of the sense and level
+ information for the interrupt. This should be encoded based on
+ the information in section 2) depending on the type of interrupt
+ controller you have.
+ - interrupt-parent : the phandle for the interrupt controller that
+ services interrupts for this device.
+
+Optional properties :
+ - fsl,invert-drvvbus : boolean; for MPC5121 USB0 only. Indicates the
+ port power polarity of internal PHY signal DRVVBUS is inverted.
+ - fsl,invert-pwr-fault : boolean; for MPC5121 USB0 only. Indicates
+ the PWR_FAULT signal polarity is inverted.
+
+Example multi port host USB controller device node :
+ usb@22000 {
+ compatible = "fsl-usb2-mph";
+ reg = <22000 1000>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ interrupt-parent = <700>;
+ interrupts = <27 1>;
+ phy_type = "ulpi";
+ port0;
+ port1;
+ };
+
+Example dual role USB controller device node :
+ usb@23000 {
+ compatible = "fsl-usb2-dr";
+ reg = <23000 1000>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ interrupt-parent = <700>;
+ interrupts = <26 1>;
+ dr_mode = "otg";
+ phy = "ulpi";
+ };
+
+Example dual role USB controller device node for MPC5121ADS:
+
+ usb@4000 {
+ compatible = "fsl,mpc5121-usb2-dr";
+ reg = <0x4000 0x1000>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ interrupt-parent = < &ipic >;
+ interrupts = <44 0x8>;
+ dr_mode = "otg";
+ phy_type = "utmi_wide";
+ fsl,invert-drvvbus;
+ fsl,invert-pwr-fault;
+ };
--- /dev/null
+USB EHCI controllers
+
+Required properties:
+ - compatible : should be "usb-ehci".
+ - reg : should contain at least address and length of the standard EHCI
+ register set for the device. Optional platform-dependent registers
+ (debug-port or other) can be also specified here, but only after
+ definition of standard EHCI registers.
+ - interrupts : one EHCI interrupt should be described here.
+If device registers are implemented in big endian mode, the device
+node should have "big-endian-regs" property.
+If controller implementation operates with big endian descriptors,
+"big-endian-desc" property should be specified.
+If both big endian registers and descriptors are used by the controller
+implementation, "big-endian" property can be specified instead of having
+both "big-endian-regs" and "big-endian-desc".
+
+Example (Sequoia 440EPx):
+ ehci@e0000300 {
+ compatible = "ibm,usb-ehci-440epx", "usb-ehci";
+ interrupt-parent = <&UIC0>;
+ interrupts = <1a 4>;
+ reg = <0 e0000300 90 0 e0000390 70>;
+ big-endian;
+ };
--- /dev/null
+ d) Xilinx IP cores
+
+ The Xilinx EDK toolchain ships with a set of IP cores (devices) for use
+ in Xilinx Spartan and Virtex FPGAs. The devices cover the whole range
+ of standard device types (network, serial, etc.) and miscellaneous
+ devices (gpio, LCD, spi, etc). Also, since these devices are
+ implemented within the fpga fabric every instance of the device can be
+ synthesised with different options that change the behaviour.
+
+ Each IP-core has a set of parameters which the FPGA designer can use to
+ control how the core is synthesized. Historically, the EDK tool would
+ extract the device parameters relevant to device drivers and copy them
+ into an 'xparameters.h' in the form of #define symbols. This tells the
+ device drivers how the IP cores are configured, but it requires the kernel
+ to be recompiled every time the FPGA bitstream is resynthesized.
+
+ The new approach is to export the parameters into the device tree and
+ generate a new device tree each time the FPGA bitstream changes. The
+ parameters which used to be exported as #defines will now become
+ properties of the device node. In general, device nodes for IP-cores
+ will take the following form:
+
+ (name): (generic-name)@(base-address) {
+ compatible = "xlnx,(ip-core-name)-(HW_VER)"
+ [, (list of compatible devices), ...];
+ reg = <(baseaddr) (size)>;
+ interrupt-parent = <&interrupt-controller-phandle>;
+ interrupts = < ... >;
+ xlnx,(parameter1) = "(string-value)";
+ xlnx,(parameter2) = <(int-value)>;
+ };
+
+ (generic-name): an open firmware-style name that describes the
+ generic class of device. Preferably, this is one word, such
+ as 'serial' or 'ethernet'.
+ (ip-core-name): the name of the ip block (given after the BEGIN
+ directive in system.mhs). Should be in lowercase
+ and all underscores '_' converted to dashes '-'.
+ (name): is derived from the "PARAMETER INSTANCE" value.
+ (parameter#): C_* parameters from system.mhs. The C_ prefix is
+ dropped from the parameter name, the name is converted
+ to lowercase and all underscore '_' characters are
+ converted to dashes '-'.
+ (baseaddr): the baseaddr parameter value (often named C_BASEADDR).
+ (HW_VER): from the HW_VER parameter.
+ (size): the address range size (often C_HIGHADDR - C_BASEADDR + 1).
+
+ Typically, the compatible list will include the exact IP core version
+ followed by an older IP core version which implements the same
+ interface or any other device with the same interface.
+
+ 'reg', 'interrupt-parent' and 'interrupts' are all optional properties.
+
+ For example, the following block from system.mhs:
+
+ BEGIN opb_uartlite
+ PARAMETER INSTANCE = opb_uartlite_0
+ PARAMETER HW_VER = 1.00.b
+ PARAMETER C_BAUDRATE = 115200
+ PARAMETER C_DATA_BITS = 8
+ PARAMETER C_ODD_PARITY = 0
+ PARAMETER C_USE_PARITY = 0
+ PARAMETER C_CLK_FREQ = 50000000
+ PARAMETER C_BASEADDR = 0xEC100000
+ PARAMETER C_HIGHADDR = 0xEC10FFFF
+ BUS_INTERFACE SOPB = opb_7
+ PORT OPB_Clk = CLK_50MHz
+ PORT Interrupt = opb_uartlite_0_Interrupt
+ PORT RX = opb_uartlite_0_RX
+ PORT TX = opb_uartlite_0_TX
+ PORT OPB_Rst = sys_bus_reset_0
+ END
+
+ becomes the following device tree node:
+
+ opb_uartlite_0: serial@ec100000 {
+ device_type = "serial";
+ compatible = "xlnx,opb-uartlite-1.00.b";
+ reg = <ec100000 10000>;
+ interrupt-parent = <&opb_intc_0>;
+ interrupts = <1 0>; // got this from the opb_intc parameters
+ current-speed = <d#115200>; // standard serial device prop
+ clock-frequency = <d#50000000>; // standard serial device prop
+ xlnx,data-bits = <8>;
+ xlnx,odd-parity = <0>;
+ xlnx,use-parity = <0>;
+ };
+
+ Some IP cores actually implement 2 or more logical devices. In
+ this case, the device should still describe the whole IP core with
+ a single node and add a child node for each logical device. The
+ ranges property can be used to translate from parent IP-core to the
+ registers of each device. In addition, the parent node should be
+ compatible with the bus type 'xlnx,compound', and should contain
+ #address-cells and #size-cells, as with any other bus. (Note: this
+ makes the assumption that both logical devices have the same bus
+ binding. If this is not true, then separate nodes should be used
+ for each logical device). The 'cell-index' property can be used to
+ enumerate logical devices within an IP core. For example, the
+ following is the system.mhs entry for the dual ps2 controller found
+ on the ml403 reference design.
+
+ BEGIN opb_ps2_dual_ref
+ PARAMETER INSTANCE = opb_ps2_dual_ref_0
+ PARAMETER HW_VER = 1.00.a
+ PARAMETER C_BASEADDR = 0xA9000000
+ PARAMETER C_HIGHADDR = 0xA9001FFF
+ BUS_INTERFACE SOPB = opb_v20_0
+ PORT Sys_Intr1 = ps2_1_intr
+ PORT Sys_Intr2 = ps2_2_intr
+ PORT Clkin1 = ps2_clk_rx_1
+ PORT Clkin2 = ps2_clk_rx_2
+ PORT Clkpd1 = ps2_clk_tx_1
+ PORT Clkpd2 = ps2_clk_tx_2
+ PORT Rx1 = ps2_d_rx_1
+ PORT Rx2 = ps2_d_rx_2
+ PORT Txpd1 = ps2_d_tx_1
+ PORT Txpd2 = ps2_d_tx_2
+ END
+
+ It would result in the following device tree nodes:
+
+ opb_ps2_dual_ref_0: opb-ps2-dual-ref@a9000000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "xlnx,compound";
+ ranges = <0 a9000000 2000>;
+ // If this device had extra parameters, then they would
+ // go here.
+ ps2@0 {
+ compatible = "xlnx,opb-ps2-dual-ref-1.00.a";
+ reg = <0 40>;
+ interrupt-parent = <&opb_intc_0>;
+ interrupts = <3 0>;
+ cell-index = <0>;
+ };
+ ps2@1000 {
+ compatible = "xlnx,opb-ps2-dual-ref-1.00.a";
+ reg = <1000 40>;
+ interrupt-parent = <&opb_intc_0>;
+ interrupts = <3 0>;
+ cell-index = <0>;
+ };
+ };
+
+ Also, the system.mhs file defines bus attachments from the processor
+ to the devices. The device tree structure should reflect the bus
+ attachments. Again an example; this system.mhs fragment:
+
+ BEGIN ppc405_virtex4
+ PARAMETER INSTANCE = ppc405_0
+ PARAMETER HW_VER = 1.01.a
+ BUS_INTERFACE DPLB = plb_v34_0
+ BUS_INTERFACE IPLB = plb_v34_0
+ END
+
+ BEGIN opb_intc
+ PARAMETER INSTANCE = opb_intc_0
+ PARAMETER HW_VER = 1.00.c
+ PARAMETER C_BASEADDR = 0xD1000FC0
+ PARAMETER C_HIGHADDR = 0xD1000FDF
+ BUS_INTERFACE SOPB = opb_v20_0
+ END
+
+ BEGIN opb_uart16550
+ PARAMETER INSTANCE = opb_uart16550_0
+ PARAMETER HW_VER = 1.00.d
+ PARAMETER C_BASEADDR = 0xa0000000
+ PARAMETER C_HIGHADDR = 0xa0001FFF
+ BUS_INTERFACE SOPB = opb_v20_0
+ END
+
+ BEGIN plb_v34
+ PARAMETER INSTANCE = plb_v34_0
+ PARAMETER HW_VER = 1.02.a
+ END
+
+ BEGIN plb_bram_if_cntlr
+ PARAMETER INSTANCE = plb_bram_if_cntlr_0
+ PARAMETER HW_VER = 1.00.b
+ PARAMETER C_BASEADDR = 0xFFFF0000
+ PARAMETER C_HIGHADDR = 0xFFFFFFFF
+ BUS_INTERFACE SPLB = plb_v34_0
+ END
+
+ BEGIN plb2opb_bridge
+ PARAMETER INSTANCE = plb2opb_bridge_0
+ PARAMETER HW_VER = 1.01.a
+ PARAMETER C_RNG0_BASEADDR = 0x20000000
+ PARAMETER C_RNG0_HIGHADDR = 0x3FFFFFFF
+ PARAMETER C_RNG1_BASEADDR = 0x60000000
+ PARAMETER C_RNG1_HIGHADDR = 0x7FFFFFFF
+ PARAMETER C_RNG2_BASEADDR = 0x80000000
+ PARAMETER C_RNG2_HIGHADDR = 0xBFFFFFFF
+ PARAMETER C_RNG3_BASEADDR = 0xC0000000
+ PARAMETER C_RNG3_HIGHADDR = 0xDFFFFFFF
+ BUS_INTERFACE SPLB = plb_v34_0
+ BUS_INTERFACE MOPB = opb_v20_0
+ END
+
+ Gives this device tree (some properties removed for clarity):
+
+ plb@0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "xlnx,plb-v34-1.02.a";
+ device_type = "ibm,plb";
+ ranges; // 1:1 translation
+
+ plb_bram_if_cntrl_0: bram@ffff0000 {
+ reg = <ffff0000 10000>;
+ }
+
+ opb@20000000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <20000000 20000000 20000000
+ 60000000 60000000 20000000
+ 80000000 80000000 40000000
+ c0000000 c0000000 20000000>;
+
+ opb_uart16550_0: serial@a0000000 {
+ reg = <a00000000 2000>;
+ };
+
+ opb_intc_0: interrupt-controller@d1000fc0 {
+ reg = <d1000fc0 20>;
+ };
+ };
+ };
+
+ That covers the general approach to binding xilinx IP cores into the
+ device tree. The following are bindings for specific devices:
+
+ i) Xilinx ML300 Framebuffer
+
+ Simple framebuffer device from the ML300 reference design (also on the
+ ML403 reference design as well as others).
+
+ Optional properties:
+ - resolution = <xres yres> : pixel resolution of framebuffer. Some
+ implementations use a different resolution.
+ Default is <d#640 d#480>
+ - virt-resolution = <xvirt yvirt> : Size of framebuffer in memory.
+ Default is <d#1024 d#480>.
+ - rotate-display (empty) : rotate display 180 degrees.
+
+ ii) Xilinx SystemACE
+
+ The Xilinx SystemACE device is used to program FPGAs from an FPGA
+ bitstream stored on a CF card. It can also be used as a generic CF
+ interface device.
+
+ Optional properties:
+ - 8-bit (empty) : Set this property for SystemACE in 8 bit mode
+
+ iii) Xilinx EMAC and Xilinx TEMAC
+
+ Xilinx Ethernet devices. In addition to general xilinx properties
+ listed above, nodes for these devices should include a phy-handle
+ property, and may include other common network device properties
+ like local-mac-address.
+
+ iv) Xilinx Uartlite
+
+ Xilinx uartlite devices are simple fixed speed serial ports.
+
+ Required properties:
+ - current-speed : Baud rate of uartlite
+
+ v) Xilinx hwicap
+
+ Xilinx hwicap devices provide access to the configuration logic
+ of the FPGA through the Internal Configuration Access Port
+ (ICAP). The ICAP enables partial reconfiguration of the FPGA,
+ readback of the configuration information, and some control over
+ 'warm boots' of the FPGA fabric.
+
+ Required properties:
+ - xlnx,family : The family of the FPGA, necessary since the
+ capabilities of the underlying ICAP hardware
+ differ between different families. May be
+ 'virtex2p', 'virtex4', or 'virtex5'.
+
+ vi) Xilinx Uart 16550
+
+ Xilinx UART 16550 devices are very similar to the NS16550 but with
+ different register spacing and an offset from the base address.
+
+ Required properties:
+ - clock-frequency : Frequency of the clock input
+ - reg-offset : A value of 3 is required
+ - reg-shift : A value of 2 is required
+
+ vii) Xilinx USB Host controller
+
+ The Xilinx USB host controller is EHCI compatible but with a different
+ base address for the EHCI registers, and it is always a big-endian
+ USB Host controller. The hardware can be configured as high speed only,
+ or high speed/full speed hybrid.
+
+ Required properties:
+ - xlnx,support-usb-fs: A value 0 means the core is built as high speed
+ only. A value 1 means the core also supports
+ full speed devices.
+
--- /dev/null
+ Booting the Linux/ppc kernel without Open Firmware
+ --------------------------------------------------
+
+(c) 2005 Benjamin Herrenschmidt <benh at kernel.crashing.org>,
+ IBM Corp.
+(c) 2005 Becky Bruce <becky.bruce at freescale.com>,
+ Freescale Semiconductor, FSL SOC and 32-bit additions
+(c) 2006 MontaVista Software, Inc.
+ Flash chip node definition
+
+Table of Contents
+=================
+
+ I - Introduction
+ 1) Entry point for arch/powerpc
+
+ II - The DT block format
+ 1) Header
+ 2) Device tree generalities
+ 3) Device tree "structure" block
+ 4) Device tree "strings" block
+
+ III - Required content of the device tree
+ 1) Note about cells and address representation
+ 2) Note about "compatible" properties
+ 3) Note about "name" properties
+ 4) Note about node and property names and character set
+ 5) Required nodes and properties
+ a) The root node
+ b) The /cpus node
+ c) The /cpus/* nodes
+ d) the /memory node(s)
+ e) The /chosen node
+ f) the /soc<SOCname> node
+
+ IV - "dtc", the device tree compiler
+
+ V - Recommendations for a bootloader
+
+ VI - System-on-a-chip devices and nodes
+ 1) Defining child nodes of an SOC
+ 2) Representing devices without a current OF specification
+
+ VII - Specifying interrupt information for devices
+ 1) interrupts property
+ 2) interrupt-parent property
+ 3) OpenPIC Interrupt Controllers
+ 4) ISA Interrupt Controllers
+
+ VIII - Specifying device power management information (sleep property)
+
+ Appendix A - Sample SOC node for MPC8540
+
+
+Revision Information
+====================
+
+ May 18, 2005: Rev 0.1 - Initial draft, no chapter III yet.
+
+ May 19, 2005: Rev 0.2 - Add chapter III and bits & pieces here or
+ clarifies the fact that a lot of things are
+ optional, the kernel only requires a very
+ small device tree, though it is encouraged
+ to provide an as complete one as possible.
+
+ May 24, 2005: Rev 0.3 - Precise that DT block has to be in RAM
+ - Misc fixes
+ - Define version 3 and new format version 16
+ for the DT block (version 16 needs kernel
+ patches, will be fwd separately).
+ String block now has a size, and full path
+ is replaced by unit name for more
+ compactness.
+ linux,phandle is made optional, only nodes
+ that are referenced by other nodes need it.
+ "name" property is now automatically
+ deduced from the unit name
+
+ June 1, 2005: Rev 0.4 - Correct confusion between OF_DT_END and
+ OF_DT_END_NODE in structure definition.
+ - Change version 16 format to always align
+ property data to 4 bytes. Since tokens are
+ already aligned, that means no specific
+ required alignment between property size
+ and property data. The old style variable
+ alignment would make it impossible to do
+ "simple" insertion of properties using
+ memmove (thanks Milton for
+ noticing). Updated kernel patch as well
+ - Correct a few more alignment constraints
+ - Add a chapter about the device-tree
+ compiler and the textural representation of
+ the tree that can be "compiled" by dtc.
+
+ November 21, 2005: Rev 0.5
+ - Additions/generalizations for 32-bit
+ - Changed to reflect the new arch/powerpc
+ structure
+ - Added chapter VI
+
+
+ ToDo:
+ - Add some definitions of interrupt tree (simple/complex)
+ - Add some definitions for PCI host bridges
+ - Add some common address format examples
+ - Add definitions for standard properties and "compatible"
+ names for cells that are not already defined by the existing
+ OF spec.
+ - Compare FSL SOC use of PCI to standard and make sure no new
+ node definition required.
+ - Add more information about node definitions for SOC devices
+ that currently have no standard, like the FSL CPM.
+
+
+I - Introduction
+================
+
+During the development of the Linux/ppc64 kernel, and more
+specifically, the addition of new platform types outside of the old
+IBM pSeries/iSeries pair, it was decided to enforce some strict rules
+regarding the kernel entry and bootloader <-> kernel interfaces, in
+order to avoid the degeneration that had become the ppc32 kernel entry
+point and the way a new platform should be added to the kernel. The
+legacy iSeries platform breaks those rules as it predates this scheme,
+but no new board support will be accepted in the main tree that
+doesn't follow them properly. In addition, since the advent of the
+arch/powerpc merged architecture for ppc32 and ppc64, new 32-bit
+platforms and 32-bit platforms which move into arch/powerpc will be
+required to use these rules as well.
+
+The main requirement that will be defined in more detail below is
+the presence of a device-tree whose format is defined after Open
+Firmware specification. However, in order to make life easier
+to embedded board vendors, the kernel doesn't require the device-tree
+to represent every device in the system and only requires some nodes
+and properties to be present. This will be described in detail in
+section III, but, for example, the kernel does not require you to
+create a node for every PCI device in the system. It is a requirement
+to have a node for PCI host bridges in order to provide interrupt
+routing informations and memory/IO ranges, among others. It is also
+recommended to define nodes for on chip devices and other buses that
+don't specifically fit in an existing OF specification. This creates a
+great flexibility in the way the kernel can then probe those and match
+drivers to device, without having to hard code all sorts of tables. It
+also makes it more flexible for board vendors to do minor hardware
+upgrades without significantly impacting the kernel code or cluttering
+it with special cases.
+
+
+1) Entry point for arch/powerpc
+-------------------------------
+
+ There is one single entry point to the kernel, at the start
+ of the kernel image. That entry point supports two calling
+ conventions:
+
+ a) Boot from Open Firmware. If your firmware is compatible
+ with Open Firmware (IEEE 1275) or provides an OF compatible
+ client interface API (support for "interpret" callback of
+ forth words isn't required), you can enter the kernel with:
+
+ r5 : OF callback pointer as defined by IEEE 1275
+ bindings to powerpc. Only the 32-bit client interface
+ is currently supported
+
+ r3, r4 : address & length of an initrd if any or 0
+
+ The MMU is either on or off; the kernel will run the
+ trampoline located in arch/powerpc/kernel/prom_init.c to
+ extract the device-tree and other information from open
+ firmware and build a flattened device-tree as described
+ in b). prom_init() will then re-enter the kernel using
+ the second method. This trampoline code runs in the
+ context of the firmware, which is supposed to handle all
+ exceptions during that time.
+
+ b) Direct entry with a flattened device-tree block. This entry
+ point is called by a) after the OF trampoline and can also be
+ called directly by a bootloader that does not support the Open
+ Firmware client interface. It is also used by "kexec" to
+ implement "hot" booting of a new kernel from a previous
+ running one. This method is what I will describe in more
+ details in this document, as method a) is simply standard Open
+ Firmware, and thus should be implemented according to the
+ various standard documents defining it and its binding to the
+ PowerPC platform. The entry point definition then becomes:
+
+ r3 : physical pointer to the device-tree block
+ (defined in chapter II) in RAM
+
+ r4 : physical pointer to the kernel itself. This is
+ used by the assembly code to properly disable the MMU
+ in case you are entering the kernel with MMU enabled
+ and a non-1:1 mapping.
+
+ r5 : NULL (as to differentiate with method a)
+
+ Note about SMP entry: Either your firmware puts your other
+ CPUs in some sleep loop or spin loop in ROM where you can get
+ them out via a soft reset or some other means, in which case
+ you don't need to care, or you'll have to enter the kernel
+ with all CPUs. The way to do that with method b) will be
+ described in a later revision of this document.
+
+ Board supports (platforms) are not exclusive config options. An
+ arbitrary set of board supports can be built in a single kernel
+ image. The kernel will "know" what set of functions to use for a
+ given platform based on the content of the device-tree. Thus, you
+ should:
+
+ a) add your platform support as a _boolean_ option in
+ arch/powerpc/Kconfig, following the example of PPC_PSERIES,
+ PPC_PMAC and PPC_MAPLE. The later is probably a good
+ example of a board support to start from.
+
+ b) create your main platform file as
+ "arch/powerpc/platforms/myplatform/myboard_setup.c" and add it
+ to the Makefile under the condition of your CONFIG_
+ option. This file will define a structure of type "ppc_md"
+ containing the various callbacks that the generic code will
+ use to get to your platform specific code
+
+ A kernel image may support multiple platforms, but only if the
+ platforms feature the same core architecture. A single kernel build
+ cannot support both configurations with Book E and configurations
+ with classic Powerpc architectures.
+
+
+II - The DT block format
+========================
+
+
+This chapter defines the actual format of the flattened device-tree
+passed to the kernel. The actual content of it and kernel requirements
+are described later. You can find example of code manipulating that
+format in various places, including arch/powerpc/kernel/prom_init.c
+which will generate a flattened device-tree from the Open Firmware
+representation, or the fs2dt utility which is part of the kexec tools
+which will generate one from a filesystem representation. It is
+expected that a bootloader like uboot provides a bit more support,
+that will be discussed later as well.
+
+Note: The block has to be in main memory. It has to be accessible in
+both real mode and virtual mode with no mapping other than main
+memory. If you are writing a simple flash bootloader, it should copy
+the block to RAM before passing it to the kernel.
+
+
+1) Header
+---------
+
+ The kernel is passed the physical address pointing to an area of memory
+ that is roughly described in include/linux/of_fdt.h by the structure
+ boot_param_header:
+
+struct boot_param_header {
+ u32 magic; /* magic word OF_DT_HEADER */
+ u32 totalsize; /* total size of DT block */
+ u32 off_dt_struct; /* offset to structure */
+ u32 off_dt_strings; /* offset to strings */
+ u32 off_mem_rsvmap; /* offset to memory reserve map
+ */
+ u32 version; /* format version */
+ u32 last_comp_version; /* last compatible version */
+
+ /* version 2 fields below */
+ u32 boot_cpuid_phys; /* Which physical CPU id we're
+ booting on */
+ /* version 3 fields below */
+ u32 size_dt_strings; /* size of the strings block */
+
+ /* version 17 fields below */
+ u32 size_dt_struct; /* size of the DT structure block */
+};
+
+ Along with the constants:
+
+/* Definitions used by the flattened device tree */
+#define OF_DT_HEADER 0xd00dfeed /* 4: version,
+ 4: total size */
+#define OF_DT_BEGIN_NODE 0x1 /* Start node: full name
+ */
+#define OF_DT_END_NODE 0x2 /* End node */
+#define OF_DT_PROP 0x3 /* Property: name off,
+ size, content */
+#define OF_DT_END 0x9
+
+ All values in this header are in big endian format, the various
+ fields in this header are defined more precisely below. All
+ "offset" values are in bytes from the start of the header; that is
+ from the physical base address of the device tree block.
+
+ - magic
+
+ This is a magic value that "marks" the beginning of the
+ device-tree block header. It contains the value 0xd00dfeed and is
+ defined by the constant OF_DT_HEADER
+
+ - totalsize
+
+ This is the total size of the DT block including the header. The
+ "DT" block should enclose all data structures defined in this
+ chapter (who are pointed to by offsets in this header). That is,
+ the device-tree structure, strings, and the memory reserve map.
+
+ - off_dt_struct
+
+ This is an offset from the beginning of the header to the start
+ of the "structure" part the device tree. (see 2) device tree)
+
+ - off_dt_strings
+
+ This is an offset from the beginning of the header to the start
+ of the "strings" part of the device-tree
+
+ - off_mem_rsvmap
+
+ This is an offset from the beginning of the header to the start
+ of the reserved memory map. This map is a list of pairs of 64-
+ bit integers. Each pair is a physical address and a size. The
+ list is terminated by an entry of size 0. This map provides the
+ kernel with a list of physical memory areas that are "reserved"
+ and thus not to be used for memory allocations, especially during
+ early initialization. The kernel needs to allocate memory during
+ boot for things like un-flattening the device-tree, allocating an
+ MMU hash table, etc... Those allocations must be done in such a
+ way to avoid overriding critical things like, on Open Firmware
+ capable machines, the RTAS instance, or on some pSeries, the TCE
+ tables used for the iommu. Typically, the reserve map should
+ contain _at least_ this DT block itself (header,total_size). If
+ you are passing an initrd to the kernel, you should reserve it as
+ well. You do not need to reserve the kernel image itself. The map
+ should be 64-bit aligned.
+
+ - version
+
+ This is the version of this structure. Version 1 stops
+ here. Version 2 adds an additional field boot_cpuid_phys.
+ Version 3 adds the size of the strings block, allowing the kernel
+ to reallocate it easily at boot and free up the unused flattened
+ structure after expansion. Version 16 introduces a new more
+ "compact" format for the tree itself that is however not backward
+ compatible. Version 17 adds an additional field, size_dt_struct,
+ allowing it to be reallocated or moved more easily (this is
+ particularly useful for bootloaders which need to make
+ adjustments to a device tree based on probed information). You
+ should always generate a structure of the highest version defined
+ at the time of your implementation. Currently that is version 17,
+ unless you explicitly aim at being backward compatible.
+
+ - last_comp_version
+
+ Last compatible version. This indicates down to what version of
+ the DT block you are backward compatible. For example, version 2
+ is backward compatible with version 1 (that is, a kernel build
+ for version 1 will be able to boot with a version 2 format). You
+ should put a 1 in this field if you generate a device tree of
+ version 1 to 3, or 16 if you generate a tree of version 16 or 17
+ using the new unit name format.
+
+ - boot_cpuid_phys
+
+ This field only exist on version 2 headers. It indicate which
+ physical CPU ID is calling the kernel entry point. This is used,
+ among others, by kexec. If you are on an SMP system, this value
+ should match the content of the "reg" property of the CPU node in
+ the device-tree corresponding to the CPU calling the kernel entry
+ point (see further chapters for more informations on the required
+ device-tree contents)
+
+ - size_dt_strings
+
+ This field only exists on version 3 and later headers. It
+ gives the size of the "strings" section of the device tree (which
+ starts at the offset given by off_dt_strings).
+
+ - size_dt_struct
+
+ This field only exists on version 17 and later headers. It gives
+ the size of the "structure" section of the device tree (which
+ starts at the offset given by off_dt_struct).
+
+ So the typical layout of a DT block (though the various parts don't
+ need to be in that order) looks like this (addresses go from top to
+ bottom):
+
+
+ ------------------------------
+ base -> | struct boot_param_header |
+ ------------------------------
+ | (alignment gap) (*) |
+ ------------------------------
+ | memory reserve map |
+ ------------------------------
+ | (alignment gap) |
+ ------------------------------
+ | |
+ | device-tree structure |
+ | |
+ ------------------------------
+ | (alignment gap) |
+ ------------------------------
+ | |
+ | device-tree strings |
+ | |
+ -----> ------------------------------
+ |
+ |
+ --- (base + totalsize)
+
+ (*) The alignment gaps are not necessarily present; their presence
+ and size are dependent on the various alignment requirements of
+ the individual data blocks.
+
+
+2) Device tree generalities
+---------------------------
+
+This device-tree itself is separated in two different blocks, a
+structure block and a strings block. Both need to be aligned to a 4
+byte boundary.
+
+First, let's quickly describe the device-tree concept before detailing
+the storage format. This chapter does _not_ describe the detail of the
+required types of nodes & properties for the kernel, this is done
+later in chapter III.
+
+The device-tree layout is strongly inherited from the definition of
+the Open Firmware IEEE 1275 device-tree. It's basically a tree of
+nodes, each node having two or more named properties. A property can
+have a value or not.
+
+It is a tree, so each node has one and only one parent except for the
+root node who has no parent.
+
+A node has 2 names. The actual node name is generally contained in a
+property of type "name" in the node property list whose value is a
+zero terminated string and is mandatory for version 1 to 3 of the
+format definition (as it is in Open Firmware). Version 16 makes it
+optional as it can generate it from the unit name defined below.
+
+There is also a "unit name" that is used to differentiate nodes with
+the same name at the same level, it is usually made of the node
+names, the "@" sign, and a "unit address", which definition is
+specific to the bus type the node sits on.
+
+The unit name doesn't exist as a property per-se but is included in
+the device-tree structure. It is typically used to represent "path" in
+the device-tree. More details about the actual format of these will be
+below.
+
+The kernel generic code does not make any formal use of the
+unit address (though some board support code may do) so the only real
+requirement here for the unit address is to ensure uniqueness of
+the node unit name at a given level of the tree. Nodes with no notion
+of address and no possible sibling of the same name (like /memory or
+/cpus) may omit the unit address in the context of this specification,
+or use the "@0" default unit address. The unit name is used to define
+a node "full path", which is the concatenation of all parent node
+unit names separated with "/".
+
+The root node doesn't have a defined name, and isn't required to have
+a name property either if you are using version 3 or earlier of the
+format. It also has no unit address (no @ symbol followed by a unit
+address). The root node unit name is thus an empty string. The full
+path to the root node is "/".
+
+Every node which actually represents an actual device (that is, a node
+which isn't only a virtual "container" for more nodes, like "/cpus"
+is) is also required to have a "compatible" property indicating the
+specific hardware and an optional list of devices it is fully
+backwards compatible with.
+
+Finally, every node that can be referenced from a property in another
+node is required to have either a "phandle" or a "linux,phandle"
+property. Real Open Firmware implementations provide a unique
+"phandle" value for every node that the "prom_init()" trampoline code
+turns into "linux,phandle" properties. However, this is made optional
+if the flattened device tree is used directly. An example of a node
+referencing another node via "phandle" is when laying out the
+interrupt tree which will be described in a further version of this
+document.
+
+The "phandle" property is a 32-bit value that uniquely
+identifies a node. You are free to use whatever values or system of
+values, internal pointers, or whatever to generate these, the only
+requirement is that every node for which you provide that property has
+a unique value for it.
+
+Here is an example of a simple device-tree. In this example, an "o"
+designates a node followed by the node unit name. Properties are
+presented with their name followed by their content. "content"
+represents an ASCII string (zero terminated) value, while <content>
+represents a 32-bit hexadecimal value. The various nodes in this
+example will be discussed in a later chapter. At this point, it is
+only meant to give you a idea of what a device-tree looks like. I have
+purposefully kept the "name" and "linux,phandle" properties which
+aren't necessary in order to give you a better idea of what the tree
+looks like in practice.
+
+ / o device-tree
+ |- name = "device-tree"
+ |- model = "MyBoardName"
+ |- compatible = "MyBoardFamilyName"
+ |- #address-cells = <2>
+ |- #size-cells = <2>
+ |- linux,phandle = <0>
+ |
+ o cpus
+ | | - name = "cpus"
+ | | - linux,phandle = <1>
+ | | - #address-cells = <1>
+ | | - #size-cells = <0>
+ | |
+ | o PowerPC,970@0
+ | |- name = "PowerPC,970"
+ | |- device_type = "cpu"
+ | |- reg = <0>
+ | |- clock-frequency = <5f5e1000>
+ | |- 64-bit
+ | |- linux,phandle = <2>
+ |
+ o memory@0
+ | |- name = "memory"
+ | |- device_type = "memory"
+ | |- reg = <00000000 00000000 00000000 20000000>
+ | |- linux,phandle = <3>
+ |
+ o chosen
+ |- name = "chosen"
+ |- bootargs = "root=/dev/sda2"
+ |- linux,phandle = <4>
+
+This tree is almost a minimal tree. It pretty much contains the
+minimal set of required nodes and properties to boot a linux kernel;
+that is, some basic model informations at the root, the CPUs, and the
+physical memory layout. It also includes misc information passed
+through /chosen, like in this example, the platform type (mandatory)
+and the kernel command line arguments (optional).
+
+The /cpus/PowerPC,970@0/64-bit property is an example of a
+property without a value. All other properties have a value. The
+significance of the #address-cells and #size-cells properties will be
+explained in chapter IV which defines precisely the required nodes and
+properties and their content.
+
+
+3) Device tree "structure" block
+
+The structure of the device tree is a linearized tree structure. The
+"OF_DT_BEGIN_NODE" token starts a new node, and the "OF_DT_END_NODE"
+ends that node definition. Child nodes are simply defined before
+"OF_DT_END_NODE" (that is nodes within the node). A 'token' is a 32
+bit value. The tree has to be "finished" with a OF_DT_END token
+
+Here's the basic structure of a single node:
+
+ * token OF_DT_BEGIN_NODE (that is 0x00000001)
+ * for version 1 to 3, this is the node full path as a zero
+ terminated string, starting with "/". For version 16 and later,
+ this is the node unit name only (or an empty string for the
+ root node)
+ * [align gap to next 4 bytes boundary]
+ * for each property:
+ * token OF_DT_PROP (that is 0x00000003)
+ * 32-bit value of property value size in bytes (or 0 if no
+ value)
+ * 32-bit value of offset in string block of property name
+ * property value data if any
+ * [align gap to next 4 bytes boundary]
+ * [child nodes if any]
+ * token OF_DT_END_NODE (that is 0x00000002)
+
+So the node content can be summarized as a start token, a full path,
+a list of properties, a list of child nodes, and an end token. Every
+child node is a full node structure itself as defined above.
+
+NOTE: The above definition requires that all property definitions for
+a particular node MUST precede any subnode definitions for that node.
+Although the structure would not be ambiguous if properties and
+subnodes were intermingled, the kernel parser requires that the
+properties come first (up until at least 2.6.22). Any tools
+manipulating a flattened tree must take care to preserve this
+constraint.
+
+4) Device tree "strings" block
+
+In order to save space, property names, which are generally redundant,
+are stored separately in the "strings" block. This block is simply the
+whole bunch of zero terminated strings for all property names
+concatenated together. The device-tree property definitions in the
+structure block will contain offset values from the beginning of the
+strings block.
+
+
+III - Required content of the device tree
+=========================================
+
+WARNING: All "linux,*" properties defined in this document apply only
+to a flattened device-tree. If your platform uses a real
+implementation of Open Firmware or an implementation compatible with
+the Open Firmware client interface, those properties will be created
+by the trampoline code in the kernel's prom_init() file. For example,
+that's where you'll have to add code to detect your board model and
+set the platform number. However, when using the flattened device-tree
+entry point, there is no prom_init() pass, and thus you have to
+provide those properties yourself.
+
+
+1) Note about cells and address representation
+----------------------------------------------
+
+The general rule is documented in the various Open Firmware
+documentations. If you choose to describe a bus with the device-tree
+and there exist an OF bus binding, then you should follow the
+specification. However, the kernel does not require every single
+device or bus to be described by the device tree.
+
+In general, the format of an address for a device is defined by the
+parent bus type, based on the #address-cells and #size-cells
+properties. Note that the parent's parent definitions of #address-cells
+and #size-cells are not inherited so every node with children must specify
+them. The kernel requires the root node to have those properties defining
+addresses format for devices directly mapped on the processor bus.
+
+Those 2 properties define 'cells' for representing an address and a
+size. A "cell" is a 32-bit number. For example, if both contain 2
+like the example tree given above, then an address and a size are both
+composed of 2 cells, and each is a 64-bit number (cells are
+concatenated and expected to be in big endian format). Another example
+is the way Apple firmware defines them, with 2 cells for an address
+and one cell for a size. Most 32-bit implementations should define
+#address-cells and #size-cells to 1, which represents a 32-bit value.
+Some 32-bit processors allow for physical addresses greater than 32
+bits; these processors should define #address-cells as 2.
+
+"reg" properties are always a tuple of the type "address size" where
+the number of cells of address and size is specified by the bus
+#address-cells and #size-cells. When a bus supports various address
+spaces and other flags relative to a given address allocation (like
+prefetchable, etc...) those flags are usually added to the top level
+bits of the physical address. For example, a PCI physical address is
+made of 3 cells, the bottom two containing the actual address itself
+while the top cell contains address space indication, flags, and pci
+bus & device numbers.
+
+For buses that support dynamic allocation, it's the accepted practice
+to then not provide the address in "reg" (keep it 0) though while
+providing a flag indicating the address is dynamically allocated, and
+then, to provide a separate "assigned-addresses" property that
+contains the fully allocated addresses. See the PCI OF bindings for
+details.
+
+In general, a simple bus with no address space bits and no dynamic
+allocation is preferred if it reflects your hardware, as the existing
+kernel address parsing functions will work out of the box. If you
+define a bus type with a more complex address format, including things
+like address space bits, you'll have to add a bus translator to the
+prom_parse.c file of the recent kernels for your bus type.
+
+The "reg" property only defines addresses and sizes (if #size-cells is
+non-0) within a given bus. In order to translate addresses upward
+(that is into parent bus addresses, and possibly into CPU physical
+addresses), all buses must contain a "ranges" property. If the
+"ranges" property is missing at a given level, it's assumed that
+translation isn't possible, i.e., the registers are not visible on the
+parent bus. The format of the "ranges" property for a bus is a list
+of:
+
+ bus address, parent bus address, size
+
+"bus address" is in the format of the bus this bus node is defining,
+that is, for a PCI bridge, it would be a PCI address. Thus, (bus
+address, size) defines a range of addresses for child devices. "parent
+bus address" is in the format of the parent bus of this bus. For
+example, for a PCI host controller, that would be a CPU address. For a
+PCI<->ISA bridge, that would be a PCI address. It defines the base
+address in the parent bus where the beginning of that range is mapped.
+
+For new 64-bit board support, I recommend either the 2/2 format or
+Apple's 2/1 format which is slightly more compact since sizes usually
+fit in a single 32-bit word. New 32-bit board support should use a
+1/1 format, unless the processor supports physical addresses greater
+than 32-bits, in which case a 2/1 format is recommended.
+
+Alternatively, the "ranges" property may be empty, indicating that the
+registers are visible on the parent bus using an identity mapping
+translation. In other words, the parent bus address space is the same
+as the child bus address space.
+
+2) Note about "compatible" properties
+-------------------------------------
+
+These properties are optional, but recommended in devices and the root
+node. The format of a "compatible" property is a list of concatenated
+zero terminated strings. They allow a device to express its
+compatibility with a family of similar devices, in some cases,
+allowing a single driver to match against several devices regardless
+of their actual names.
+
+3) Note about "name" properties
+-------------------------------
+
+While earlier users of Open Firmware like OldWorld macintoshes tended
+to use the actual device name for the "name" property, it's nowadays
+considered a good practice to use a name that is closer to the device
+class (often equal to device_type). For example, nowadays, Ethernet
+controllers are named "ethernet", an additional "model" property
+defining precisely the chip type/model, and "compatible" property
+defining the family in case a single driver can driver more than one
+of these chips. However, the kernel doesn't generally put any
+restriction on the "name" property; it is simply considered good
+practice to follow the standard and its evolutions as closely as
+possible.
+
+Note also that the new format version 16 makes the "name" property
+optional. If it's absent for a node, then the node's unit name is then
+used to reconstruct the name. That is, the part of the unit name
+before the "@" sign is used (or the entire unit name if no "@" sign
+is present).
+
+4) Note about node and property names and character set
+-------------------------------------------------------
+
+While Open Firmware provides more flexible usage of 8859-1, this
+specification enforces more strict rules. Nodes and properties should
+be comprised only of ASCII characters 'a' to 'z', '0' to
+'9', ',', '.', '_', '+', '#', '?', and '-'. Node names additionally
+allow uppercase characters 'A' to 'Z' (property names should be
+lowercase. The fact that vendors like Apple don't respect this rule is
+irrelevant here). Additionally, node and property names should always
+begin with a character in the range 'a' to 'z' (or 'A' to 'Z' for node
+names).
+
+The maximum number of characters for both nodes and property names
+is 31. In the case of node names, this is only the leftmost part of
+a unit name (the pure "name" property), it doesn't include the unit
+address which can extend beyond that limit.
+
+
+5) Required nodes and properties
+--------------------------------
+ These are all that are currently required. However, it is strongly
+ recommended that you expose PCI host bridges as documented in the
+ PCI binding to Open Firmware, and your interrupt tree as documented
+ in OF interrupt tree specification.
+
+ a) The root node
+
+ The root node requires some properties to be present:
+
+ - model : this is your board name/model
+ - #address-cells : address representation for "root" devices
+ - #size-cells: the size representation for "root" devices
+ - compatible : the board "family" generally finds its way here,
+ for example, if you have 2 board models with a similar layout,
+ that typically get driven by the same platform code in the
+ kernel, you would specify the exact board model in the
+ compatible property followed by an entry that represents the SoC
+ model.
+
+ The root node is also generally where you add additional properties
+ specific to your board like the serial number if any, that sort of
+ thing. It is recommended that if you add any "custom" property whose
+ name may clash with standard defined ones, you prefix them with your
+ vendor name and a comma.
+
+ b) The /cpus node
+
+ This node is the parent of all individual CPU nodes. It doesn't
+ have any specific requirements, though it's generally good practice
+ to have at least:
+
+ #address-cells = <00000001>
+ #size-cells = <00000000>
+
+ This defines that the "address" for a CPU is a single cell, and has
+ no meaningful size. This is not necessary but the kernel will assume
+ that format when reading the "reg" properties of a CPU node, see
+ below
+
+ c) The /cpus/* nodes
+
+ So under /cpus, you are supposed to create a node for every CPU on
+ the machine. There is no specific restriction on the name of the
+ CPU, though it's common to call it <architecture>,<core>. For
+ example, Apple uses PowerPC,G5 while IBM uses PowerPC,970FX.
+ However, the Generic Names convention suggests that it would be
+ better to simply use 'cpu' for each cpu node and use the compatible
+ property to identify the specific cpu core.
+
+ Required properties:
+
+ - device_type : has to be "cpu"
+ - reg : This is the physical CPU number, it's a single 32-bit cell
+ and is also used as-is as the unit number for constructing the
+ unit name in the full path. For example, with 2 CPUs, you would
+ have the full path:
+ /cpus/PowerPC,970FX@0
+ /cpus/PowerPC,970FX@1
+ (unit addresses do not require leading zeroes)
+ - d-cache-block-size : one cell, L1 data cache block size in bytes (*)
+ - i-cache-block-size : one cell, L1 instruction cache block size in
+ bytes
+ - d-cache-size : one cell, size of L1 data cache in bytes
+ - i-cache-size : one cell, size of L1 instruction cache in bytes
+
+(*) The cache "block" size is the size on which the cache management
+instructions operate. Historically, this document used the cache
+"line" size here which is incorrect. The kernel will prefer the cache
+block size and will fallback to cache line size for backward
+compatibility.
+
+ Recommended properties:
+
+ - timebase-frequency : a cell indicating the frequency of the
+ timebase in Hz. This is not directly used by the generic code,
+ but you are welcome to copy/paste the pSeries code for setting
+ the kernel timebase/decrementer calibration based on this
+ value.
+ - clock-frequency : a cell indicating the CPU core clock frequency
+ in Hz. A new property will be defined for 64-bit values, but if
+ your frequency is < 4Ghz, one cell is enough. Here as well as
+ for the above, the common code doesn't use that property, but
+ you are welcome to re-use the pSeries or Maple one. A future
+ kernel version might provide a common function for this.
+ - d-cache-line-size : one cell, L1 data cache line size in bytes
+ if different from the block size
+ - i-cache-line-size : one cell, L1 instruction cache line size in
+ bytes if different from the block size
+
+ You are welcome to add any property you find relevant to your board,
+ like some information about the mechanism used to soft-reset the
+ CPUs. For example, Apple puts the GPIO number for CPU soft reset
+ lines in there as a "soft-reset" property since they start secondary
+ CPUs by soft-resetting them.
+
+
+ d) the /memory node(s)
+
+ To define the physical memory layout of your board, you should
+ create one or more memory node(s). You can either create a single
+ node with all memory ranges in its reg property, or you can create
+ several nodes, as you wish. The unit address (@ part) used for the
+ full path is the address of the first range of memory defined by a
+ given node. If you use a single memory node, this will typically be
+ @0.
+
+ Required properties:
+
+ - device_type : has to be "memory"
+ - reg : This property contains all the physical memory ranges of
+ your board. It's a list of addresses/sizes concatenated
+ together, with the number of cells of each defined by the
+ #address-cells and #size-cells of the root node. For example,
+ with both of these properties being 2 like in the example given
+ earlier, a 970 based machine with 6Gb of RAM could typically
+ have a "reg" property here that looks like:
+
+ 00000000 00000000 00000000 80000000
+ 00000001 00000000 00000001 00000000
+
+ That is a range starting at 0 of 0x80000000 bytes and a range
+ starting at 0x100000000 and of 0x100000000 bytes. You can see
+ that there is no memory covering the IO hole between 2Gb and
+ 4Gb. Some vendors prefer splitting those ranges into smaller
+ segments, but the kernel doesn't care.
+
+ e) The /chosen node
+
+ This node is a bit "special". Normally, that's where Open Firmware
+ puts some variable environment information, like the arguments, or
+ the default input/output devices.
+
+ This specification makes a few of these mandatory, but also defines
+ some linux-specific properties that would be normally constructed by
+ the prom_init() trampoline when booting with an OF client interface,
+ but that you have to provide yourself when using the flattened format.
+
+ Recommended properties:
+
+ - bootargs : This zero-terminated string is passed as the kernel
+ command line
+ - linux,stdout-path : This is the full path to your standard
+ console device if any. Typically, if you have serial devices on
+ your board, you may want to put the full path to the one set as
+ the default console in the firmware here, for the kernel to pick
+ it up as its own default console.
+
+ Note that u-boot creates and fills in the chosen node for platforms
+ that use it.
+
+ (Note: a practice that is now obsolete was to include a property
+ under /chosen called interrupt-controller which had a phandle value
+ that pointed to the main interrupt controller)
+
+ f) the /soc<SOCname> node
+
+ This node is used to represent a system-on-a-chip (SoC) and must be
+ present if the processor is a SoC. The top-level soc node contains
+ information that is global to all devices on the SoC. The node name
+ should contain a unit address for the SoC, which is the base address
+ of the memory-mapped register set for the SoC. The name of an SoC
+ node should start with "soc", and the remainder of the name should
+ represent the part number for the soc. For example, the MPC8540's
+ soc node would be called "soc8540".
+
+ Required properties:
+
+ - ranges : Should be defined as specified in 1) to describe the
+ translation of SoC addresses for memory mapped SoC registers.
+ - bus-frequency: Contains the bus frequency for the SoC node.
+ Typically, the value of this field is filled in by the boot
+ loader.
+ - compatible : Exact model of the SoC
+
+
+ Recommended properties:
+
+ - reg : This property defines the address and size of the
+ memory-mapped registers that are used for the SOC node itself.
+ It does not include the child device registers - these will be
+ defined inside each child node. The address specified in the
+ "reg" property should match the unit address of the SOC node.
+ - #address-cells : Address representation for "soc" devices. The
+ format of this field may vary depending on whether or not the
+ device registers are memory mapped. For memory mapped
+ registers, this field represents the number of cells needed to
+ represent the address of the registers. For SOCs that do not
+ use MMIO, a special address format should be defined that
+ contains enough cells to represent the required information.
+ See 1) above for more details on defining #address-cells.
+ - #size-cells : Size representation for "soc" devices
+ - #interrupt-cells : Defines the width of cells used to represent
+ interrupts. Typically this value is <2>, which includes a
+ 32-bit number that represents the interrupt number, and a
+ 32-bit number that represents the interrupt sense and level.
+ This field is only needed if the SOC contains an interrupt
+ controller.
+
+ The SOC node may contain child nodes for each SOC device that the
+ platform uses. Nodes should not be created for devices which exist
+ on the SOC but are not used by a particular platform. See chapter VI
+ for more information on how to specify devices that are part of a SOC.
+
+ Example SOC node for the MPC8540:
+
+ soc8540@e0000000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ #interrupt-cells = <2>;
+ device_type = "soc";
+ ranges = <00000000 e0000000 00100000>
+ reg = <e0000000 00003000>;
+ bus-frequency = <0>;
+ }
+
+
+
+IV - "dtc", the device tree compiler
+====================================
+
+
+dtc source code can be found at
+<http://git.jdl.com/gitweb/?p=dtc.git>
+
+WARNING: This version is still in early development stage; the
+resulting device-tree "blobs" have not yet been validated with the
+kernel. The current generated block lacks a useful reserve map (it will
+be fixed to generate an empty one, it's up to the bootloader to fill
+it up) among others. The error handling needs work, bugs are lurking,
+etc...
+
+dtc basically takes a device-tree in a given format and outputs a
+device-tree in another format. The currently supported formats are:
+
+ Input formats:
+ -------------
+
+ - "dtb": "blob" format, that is a flattened device-tree block
+ with
+ header all in a binary blob.
+ - "dts": "source" format. This is a text file containing a
+ "source" for a device-tree. The format is defined later in this
+ chapter.
+ - "fs" format. This is a representation equivalent to the
+ output of /proc/device-tree, that is nodes are directories and
+ properties are files
+
+ Output formats:
+ ---------------
+
+ - "dtb": "blob" format
+ - "dts": "source" format
+ - "asm": assembly language file. This is a file that can be
+ sourced by gas to generate a device-tree "blob". That file can
+ then simply be added to your Makefile. Additionally, the
+ assembly file exports some symbols that can be used.
+
+
+The syntax of the dtc tool is
+
+ dtc [-I <input-format>] [-O <output-format>]
+ [-o output-filename] [-V output_version] input_filename
+
+
+The "output_version" defines what version of the "blob" format will be
+generated. Supported versions are 1,2,3 and 16. The default is
+currently version 3 but that may change in the future to version 16.
+
+Additionally, dtc performs various sanity checks on the tree, like the
+uniqueness of linux, phandle properties, validity of strings, etc...
+
+The format of the .dts "source" file is "C" like, supports C and C++
+style comments.
+
+/ {
+}
+
+The above is the "device-tree" definition. It's the only statement
+supported currently at the toplevel.
+
+/ {
+ property1 = "string_value"; /* define a property containing a 0
+ * terminated string
+ */
+
+ property2 = <1234abcd>; /* define a property containing a
+ * numerical 32-bit value (hexadecimal)
+ */
+
+ property3 = <12345678 12345678 deadbeef>;
+ /* define a property containing 3
+ * numerical 32-bit values (cells) in
+ * hexadecimal
+ */
+ property4 = [0a 0b 0c 0d de ea ad be ef];
+ /* define a property whose content is
+ * an arbitrary array of bytes
+ */
+
+ childnode@address { /* define a child node named "childnode"
+ * whose unit name is "childnode at
+ * address"
+ */
+
+ childprop = "hello\n"; /* define a property "childprop" of
+ * childnode (in this case, a string)
+ */
+ };
+};
+
+Nodes can contain other nodes etc... thus defining the hierarchical
+structure of the tree.
+
+Strings support common escape sequences from C: "\n", "\t", "\r",
+"\(octal value)", "\x(hex value)".
+
+It is also suggested that you pipe your source file through cpp (gcc
+preprocessor) so you can use #include's, #define for constants, etc...
+
+Finally, various options are planned but not yet implemented, like
+automatic generation of phandles, labels (exported to the asm file so
+you can point to a property content and change it easily from whatever
+you link the device-tree with), label or path instead of numeric value
+in some cells to "point" to a node (replaced by a phandle at compile
+time), export of reserve map address to the asm file, ability to
+specify reserve map content at compile time, etc...
+
+We may provide a .h include file with common definitions of that
+proves useful for some properties (like building PCI properties or
+interrupt maps) though it may be better to add a notion of struct
+definitions to the compiler...
+
+
+V - Recommendations for a bootloader
+====================================
+
+
+Here are some various ideas/recommendations that have been proposed
+while all this has been defined and implemented.
+
+ - The bootloader may want to be able to use the device-tree itself
+ and may want to manipulate it (to add/edit some properties,
+ like physical memory size or kernel arguments). At this point, 2
+ choices can be made. Either the bootloader works directly on the
+ flattened format, or the bootloader has its own internal tree
+ representation with pointers (similar to the kernel one) and
+ re-flattens the tree when booting the kernel. The former is a bit
+ more difficult to edit/modify, the later requires probably a bit
+ more code to handle the tree structure. Note that the structure
+ format has been designed so it's relatively easy to "insert"
+ properties or nodes or delete them by just memmoving things
+ around. It contains no internal offsets or pointers for this
+ purpose.
+
+ - An example of code for iterating nodes & retrieving properties
+ directly from the flattened tree format can be found in the kernel
+ file drivers/of/fdt.c. Look at the of_scan_flat_dt() function,
+ its usage in early_init_devtree(), and the corresponding various
+ early_init_dt_scan_*() callbacks. That code can be re-used in a
+ GPL bootloader, and as the author of that code, I would be happy
+ to discuss possible free licensing to any vendor who wishes to
+ integrate all or part of this code into a non-GPL bootloader.
+ (reference needed; who is 'I' here? ---gcl Jan 31, 2011)
+
+
+
+VI - System-on-a-chip devices and nodes
+=======================================
+
+Many companies are now starting to develop system-on-a-chip
+processors, where the processor core (CPU) and many peripheral devices
+exist on a single piece of silicon. For these SOCs, an SOC node
+should be used that defines child nodes for the devices that make
+up the SOC. While platforms are not required to use this model in
+order to boot the kernel, it is highly encouraged that all SOC
+implementations define as complete a flat-device-tree as possible to
+describe the devices on the SOC. This will allow for the
+genericization of much of the kernel code.
+
+
+1) Defining child nodes of an SOC
+---------------------------------
+
+Each device that is part of an SOC may have its own node entry inside
+the SOC node. For each device that is included in the SOC, the unit
+address property represents the address offset for this device's
+memory-mapped registers in the parent's address space. The parent's
+address space is defined by the "ranges" property in the top-level soc
+node. The "reg" property for each node that exists directly under the
+SOC node should contain the address mapping from the child address space
+to the parent SOC address space and the size of the device's
+memory-mapped register file.
+
+For many devices that may exist inside an SOC, there are predefined
+specifications for the format of the device tree node. All SOC child
+nodes should follow these specifications, except where noted in this
+document.
+
+See appendix A for an example partial SOC node definition for the
+MPC8540.
+
+
+2) Representing devices without a current OF specification
+----------------------------------------------------------
+
+Currently, there are many devices on SoCs that do not have a standard
+representation defined as part of the Open Firmware specifications,
+mainly because the boards that contain these SoCs are not currently
+booted using Open Firmware. Binding documentation for new devices
+should be added to the Documentation/devicetree/bindings directory.
+That directory will expand as device tree support is added to more and
+more SoCs.
+
+
+VII - Specifying interrupt information for devices
+===================================================
+
+The device tree represents the buses and devices of a hardware
+system in a form similar to the physical bus topology of the
+hardware.
+
+In addition, a logical 'interrupt tree' exists which represents the
+hierarchy and routing of interrupts in the hardware.
+
+The interrupt tree model is fully described in the
+document "Open Firmware Recommended Practice: Interrupt
+Mapping Version 0.9". The document is available at:
+<http://playground.sun.com/1275/practice>.
+
+1) interrupts property
+----------------------
+
+Devices that generate interrupts to a single interrupt controller
+should use the conventional OF representation described in the
+OF interrupt mapping documentation.
+
+Each device which generates interrupts must have an 'interrupt'
+property. The interrupt property value is an arbitrary number of
+of 'interrupt specifier' values which describe the interrupt or
+interrupts for the device.
+
+The encoding of an interrupt specifier is determined by the
+interrupt domain in which the device is located in the
+interrupt tree. The root of an interrupt domain specifies in
+its #interrupt-cells property the number of 32-bit cells
+required to encode an interrupt specifier. See the OF interrupt
+mapping documentation for a detailed description of domains.
+
+For example, the binding for the OpenPIC interrupt controller
+specifies an #interrupt-cells value of 2 to encode the interrupt
+number and level/sense information. All interrupt children in an
+OpenPIC interrupt domain use 2 cells per interrupt in their interrupts
+property.
+
+The PCI bus binding specifies a #interrupt-cell value of 1 to encode
+which interrupt pin (INTA,INTB,INTC,INTD) is used.
+
+2) interrupt-parent property
+----------------------------
+
+The interrupt-parent property is specified to define an explicit
+link between a device node and its interrupt parent in
+the interrupt tree. The value of interrupt-parent is the
+phandle of the parent node.
+
+If the interrupt-parent property is not defined for a node, its
+interrupt parent is assumed to be an ancestor in the node's
+_device tree_ hierarchy.
+
+3) OpenPIC Interrupt Controllers
+--------------------------------
+
+OpenPIC interrupt controllers require 2 cells to encode
+interrupt information. The first cell defines the interrupt
+number. The second cell defines the sense and level
+information.
+
+Sense and level information should be encoded as follows:
+
+ 0 = low to high edge sensitive type enabled
+ 1 = active low level sensitive type enabled
+ 2 = active high level sensitive type enabled
+ 3 = high to low edge sensitive type enabled
+
+4) ISA Interrupt Controllers
+----------------------------
+
+ISA PIC interrupt controllers require 2 cells to encode
+interrupt information. The first cell defines the interrupt
+number. The second cell defines the sense and level
+information.
+
+ISA PIC interrupt controllers should adhere to the ISA PIC
+encodings listed below:
+
+ 0 = active low level sensitive type enabled
+ 1 = active high level sensitive type enabled
+ 2 = high to low edge sensitive type enabled
+ 3 = low to high edge sensitive type enabled
+
+VIII - Specifying Device Power Management Information (sleep property)
+===================================================================
+
+Devices on SOCs often have mechanisms for placing devices into low-power
+states that are decoupled from the devices' own register blocks. Sometimes,
+this information is more complicated than a cell-index property can
+reasonably describe. Thus, each device controlled in such a manner
+may contain a "sleep" property which describes these connections.
+
+The sleep property consists of one or more sleep resources, each of
+which consists of a phandle to a sleep controller, followed by a
+controller-specific sleep specifier of zero or more cells.
+
+The semantics of what type of low power modes are possible are defined
+by the sleep controller. Some examples of the types of low power modes
+that may be supported are:
+
+ - Dynamic: The device may be disabled or enabled at any time.
+ - System Suspend: The device may request to be disabled or remain
+ awake during system suspend, but will not be disabled until then.
+ - Permanent: The device is disabled permanently (until the next hard
+ reset).
+
+Some devices may share a clock domain with each other, such that they should
+only be suspended when none of the devices are in use. Where reasonable,
+such nodes should be placed on a virtual bus, where the bus has the sleep
+property. If the clock domain is shared among devices that cannot be
+reasonably grouped in this manner, then create a virtual sleep controller
+(similar to an interrupt nexus, except that defining a standardized
+sleep-map should wait until its necessity is demonstrated).
+
+Appendix A - Sample SOC node for MPC8540
+========================================
+
+ soc@e0000000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,mpc8540-ccsr", "simple-bus";
+ device_type = "soc";
+ ranges = <0x00000000 0xe0000000 0x00100000>
+ bus-frequency = <0>;
+ interrupt-parent = <&pic>;
+
+ ethernet@24000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ device_type = "network";
+ model = "TSEC";
+ compatible = "gianfar", "simple-bus";
+ reg = <0x24000 0x1000>;
+ local-mac-address = [ 00 E0 0C 00 73 00 ];
+ interrupts = <29 2 30 2 34 2>;
+ phy-handle = <&phy0>;
+ sleep = <&pmc 00000080>;
+ ranges;
+
+ mdio@24520 {
+ reg = <0x24520 0x20>;
+ compatible = "fsl,gianfar-mdio";
+
+ phy0: ethernet-phy@0 {
+ interrupts = <5 1>;
+ reg = <0>;
+ device_type = "ethernet-phy";
+ };
+
+ phy1: ethernet-phy@1 {
+ interrupts = <5 1>;
+ reg = <1>;
+ device_type = "ethernet-phy";
+ };
+
+ phy3: ethernet-phy@3 {
+ interrupts = <7 1>;
+ reg = <3>;
+ device_type = "ethernet-phy";
+ };
+ };
+ };
+
+ ethernet@25000 {
+ device_type = "network";
+ model = "TSEC";
+ compatible = "gianfar";
+ reg = <0x25000 0x1000>;
+ local-mac-address = [ 00 E0 0C 00 73 01 ];
+ interrupts = <13 2 14 2 18 2>;
+ phy-handle = <&phy1>;
+ sleep = <&pmc 00000040>;
+ };
+
+ ethernet@26000 {
+ device_type = "network";
+ model = "FEC";
+ compatible = "gianfar";
+ reg = <0x26000 0x1000>;
+ local-mac-address = [ 00 E0 0C 00 73 02 ];
+ interrupts = <41 2>;
+ phy-handle = <&phy3>;
+ sleep = <&pmc 00000020>;
+ };
+
+ serial@4500 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,mpc8540-duart", "simple-bus";
+ sleep = <&pmc 00000002>;
+ ranges;
+
+ serial@4500 {
+ device_type = "serial";
+ compatible = "ns16550";
+ reg = <0x4500 0x100>;
+ clock-frequency = <0>;
+ interrupts = <42 2>;
+ };
+
+ serial@4600 {
+ device_type = "serial";
+ compatible = "ns16550";
+ reg = <0x4600 0x100>;
+ clock-frequency = <0>;
+ interrupts = <42 2>;
+ };
+ };
+
+ pic: pic@40000 {
+ interrupt-controller;
+ #address-cells = <0>;
+ #interrupt-cells = <2>;
+ reg = <0x40000 0x40000>;
+ compatible = "chrp,open-pic";
+ device_type = "open-pic";
+ };
+
+ i2c@3000 {
+ interrupts = <43 2>;
+ reg = <0x3000 0x100>;
+ compatible = "fsl-i2c";
+ dfsrr;
+ sleep = <&pmc 00000004>;
+ };
+
+ pmc: power@e0070 {
+ compatible = "fsl,mpc8540-pmc", "fsl,mpc8548-pmc";
+ reg = <0xe0070 0x20>;
+ };
+ };
* JEDEC JC 42.4 compliant temperature sensor chips
Prefix: 'jc42'
Addresses scanned: I2C 0x18 - 0x1f
- Datasheet: -
+ Datasheet:
+ http://www.jedec.org/sites/default/files/docs/4_01_04R19.pdf
Author:
Guenter Roeck <guenter.roeck@ericsson.com>
Description
-----------
-This driver implements support for JEDEC JC 42.4 compliant temperature sensors.
+This driver implements support for JEDEC JC 42.4 compliant temperature sensors,
+which are used on many DDR3 memory modules for mobile devices and servers. Some
+systems use the sensor to prevent memory overheating by automatically throttling
+the memory controller.
+
The driver auto-detects the chips listed above, but can be manually instantiated
to support other JC 42.4 compliant chips.
which applies to all limits. This register can be written by writing into
temp1_crit_hyst. Other hysteresis attributes are read-only.
+If the BIOS has configured the sensor for automatic temperature management, it
+is likely that it has locked the registers, i.e., that the temperature limits
+cannot be changed.
+
Sysfs entries
-------------
temp1_input Temperature (RO)
-temp1_min Minimum temperature (RW)
-temp1_max Maximum temperature (RW)
-temp1_crit Critical high temperature (RW)
+temp1_min Minimum temperature (RO or RW)
+temp1_max Maximum temperature (RO or RW)
+temp1_crit Critical high temperature (RO or RW)
-temp1_crit_hyst Critical hysteresis temperature (RW)
+temp1_crit_hyst Critical hysteresis temperature (RO or RW)
temp1_max_hyst Maximum hysteresis temperature (RO)
temp1_min_alarm Temperature low alarm
Socket S1G3: Athlon II, Sempron, Turion II
* AMD Family 11h processors:
Socket S1G2: Athlon (X2), Sempron (X2), Turion X2 (Ultra)
+* AMD Family 12h processors: "Llano"
+* AMD Family 14h processors: "Brazos" (C/E/G-Series)
Prefix: 'k10temp'
Addresses scanned: PCI space
http://support.amd.com/us/Processor_TechDocs/31116.pdf
BIOS and Kernel Developer's Guide (BKDG) for AMD Family 11h Processors:
http://support.amd.com/us/Processor_TechDocs/41256.pdf
+ BIOS and Kernel Developer's Guide (BKDG) for AMD Family 14h Models 00h-0Fh Processors:
+ http://support.amd.com/us/Processor_TechDocs/43170.pdf
Revision Guide for AMD Family 10h Processors:
http://support.amd.com/us/Processor_TechDocs/41322.pdf
Revision Guide for AMD Family 11h Processors:
http://support.amd.com/us/Processor_TechDocs/41788.pdf
+ Revision Guide for AMD Family 14h Models 00h-0Fh Processors:
+ http://support.amd.com/us/Processor_TechDocs/47534.pdf
AMD Family 11h Processor Power and Thermal Data Sheet for Notebooks:
http://support.amd.com/us/Processor_TechDocs/43373.pdf
AMD Family 10h Server and Workstation Processor Power and Thermal Data Sheet:
-----------
This driver permits reading of the internal temperature sensor of AMD
-Family 10h and 11h processors.
+Family 10h/11h/12h/14h processors.
All these processors have a sensor, but on those for Socket F or AM2+,
the sensor may return inconsistent values (erratum 319). The driver
and is between 256 and 4096 characters. It is defined in the file
./include/asm/setup.h as COMMAND_LINE_SIZE.
+Finally, the [KMG] suffix is commonly described after a number of kernel
+parameter values. These 'K', 'M', and 'G' letters represent the _binary_
+multipliers 'Kilo', 'Mega', and 'Giga', equalling 2^10, 2^20, and 2^30
+bytes respectively. Such letter suffixes can also be entirely omitted.
+
acpi= [HW,ACPI,X86]
Advanced Configuration and Power Interface
Format:
<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
- crashkernel=nn[KMG]@ss[KMG]
- [KNL] Reserve a chunk of physical memory to
- hold a kernel to switch to with kexec on panic.
+ crashkernel=size[KMG][@offset[KMG]]
+ [KNL] Using kexec, Linux can switch to a 'crash kernel'
+ upon panic. This parameter reserves the physical
+ memory region [offset, offset + size] for that kernel
+ image. If '@offset' is omitted, then a suitable offset
+ is selected automatically. Check
+ Documentation/kdump/kdump.txt for further details.
crashkernel=range1:size1[,range2:size2,...][@offset]
[KNL] Same as above, but depends on the memory
in the running system. The syntax of range is
start-[end] where start and end are both
a memory unit (amount[KMG]). See also
- Documentation/kdump/kdump.txt for a example.
+ Documentation/kdump/kdump.txt for an example.
cs89x0_dma= [HW,NET]
Format: <dma>
6 (KERN_INFO) informational
7 (KERN_DEBUG) debug-level messages
- log_buf_len=n Sets the size of the printk ring buffer, in bytes.
- Format: { n | nk | nM }
- n must be a power of two. The default size
- is set in the kernel config file.
+ log_buf_len=n[KMG] Sets the size of the printk ring buffer,
+ in bytes. n must be a power of two. The default
+ size is set in the kernel config file.
logo.nologo [FB] Disables display of the built-in Linux logo.
This may be used to provide more screen space for
<deci-seconds>: poll all this frequency
0: no polling (default)
+ threadirqs [KNL]
+ Force threading of all interrupt handlers except those
+ marked explicitely IRQF_NO_THREAD.
+
topology= [S390]
Format: {off | on}
Specify if the kernel should make use of the cpu
- info on using the DECnet networking layer in Linux.
depca.txt
- the Digital DEPCA/EtherWORKS DE1?? and DE2?? LANCE Ethernet driver
-dgrs.txt
- - the Digi International RightSwitch SE-X Ethernet driver
dmfe.txt
- info on the Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver.
e100.txt
- info on Intel's E1000 line of gigabit ethernet boards
eql.txt
- serial IP load balancing
-ethertap.txt
- - the Ethertap user space packet reception and transmission driver
ewrk3.txt
- the Digital EtherWORKS 3 DE203/4/5 Ethernet driver
filter.txt
- TUN/TAP device driver, allowing user space Rx/Tx of packets.
vortex.txt
- info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards.
-wavelan.txt
- - AT&T GIS (nee NCR) WaveLAN card: An Ethernet-like radio transceiver
x25.txt
- general info on X.25 development.
x25-iface.txt
# List of programs to build
hostprogs-y := ifenslave
+HOSTCFLAGS_ifenslave.o += -I$(objtree)/usr/include
+
# Tell kbuild to always build the programs
always := $(hostprogs-y)
create dns_resolver foo:* * /usr/sbin/dns.foo %k
-
=====
USAGE
=====
returned also.
+===============================
+READING DNS KEYS FROM USERSPACE
+===============================
+
+Keys of dns_resolver type can be read from userspace using keyctl_read() or
+"keyctl read/print/pipe".
+
+
=========
MECHANISM
=========
+++ /dev/null
- Booting the Linux/ppc kernel without Open Firmware
- --------------------------------------------------
-
-(c) 2005 Benjamin Herrenschmidt <benh at kernel.crashing.org>,
- IBM Corp.
-(c) 2005 Becky Bruce <becky.bruce at freescale.com>,
- Freescale Semiconductor, FSL SOC and 32-bit additions
-(c) 2006 MontaVista Software, Inc.
- Flash chip node definition
-
-Table of Contents
-=================
-
- I - Introduction
- 1) Entry point for arch/powerpc
- 2) Board support
-
- II - The DT block format
- 1) Header
- 2) Device tree generalities
- 3) Device tree "structure" block
- 4) Device tree "strings" block
-
- III - Required content of the device tree
- 1) Note about cells and address representation
- 2) Note about "compatible" properties
- 3) Note about "name" properties
- 4) Note about node and property names and character set
- 5) Required nodes and properties
- a) The root node
- b) The /cpus node
- c) The /cpus/* nodes
- d) the /memory node(s)
- e) The /chosen node
- f) the /soc<SOCname> node
-
- IV - "dtc", the device tree compiler
-
- V - Recommendations for a bootloader
-
- VI - System-on-a-chip devices and nodes
- 1) Defining child nodes of an SOC
- 2) Representing devices without a current OF specification
- a) PHY nodes
- b) Interrupt controllers
- c) 4xx/Axon EMAC ethernet nodes
- d) Xilinx IP cores
- e) USB EHCI controllers
- f) MDIO on GPIOs
- g) SPI busses
-
- VII - Specifying interrupt information for devices
- 1) interrupts property
- 2) interrupt-parent property
- 3) OpenPIC Interrupt Controllers
- 4) ISA Interrupt Controllers
-
- VIII - Specifying device power management information (sleep property)
-
- Appendix A - Sample SOC node for MPC8540
-
-
-Revision Information
-====================
-
- May 18, 2005: Rev 0.1 - Initial draft, no chapter III yet.
-
- May 19, 2005: Rev 0.2 - Add chapter III and bits & pieces here or
- clarifies the fact that a lot of things are
- optional, the kernel only requires a very
- small device tree, though it is encouraged
- to provide an as complete one as possible.
-
- May 24, 2005: Rev 0.3 - Precise that DT block has to be in RAM
- - Misc fixes
- - Define version 3 and new format version 16
- for the DT block (version 16 needs kernel
- patches, will be fwd separately).
- String block now has a size, and full path
- is replaced by unit name for more
- compactness.
- linux,phandle is made optional, only nodes
- that are referenced by other nodes need it.
- "name" property is now automatically
- deduced from the unit name
-
- June 1, 2005: Rev 0.4 - Correct confusion between OF_DT_END and
- OF_DT_END_NODE in structure definition.
- - Change version 16 format to always align
- property data to 4 bytes. Since tokens are
- already aligned, that means no specific
- required alignment between property size
- and property data. The old style variable
- alignment would make it impossible to do
- "simple" insertion of properties using
- memmove (thanks Milton for
- noticing). Updated kernel patch as well
- - Correct a few more alignment constraints
- - Add a chapter about the device-tree
- compiler and the textural representation of
- the tree that can be "compiled" by dtc.
-
- November 21, 2005: Rev 0.5
- - Additions/generalizations for 32-bit
- - Changed to reflect the new arch/powerpc
- structure
- - Added chapter VI
-
-
- ToDo:
- - Add some definitions of interrupt tree (simple/complex)
- - Add some definitions for PCI host bridges
- - Add some common address format examples
- - Add definitions for standard properties and "compatible"
- names for cells that are not already defined by the existing
- OF spec.
- - Compare FSL SOC use of PCI to standard and make sure no new
- node definition required.
- - Add more information about node definitions for SOC devices
- that currently have no standard, like the FSL CPM.
-
-
-I - Introduction
-================
-
-During the recent development of the Linux/ppc64 kernel, and more
-specifically, the addition of new platform types outside of the old
-IBM pSeries/iSeries pair, it was decided to enforce some strict rules
-regarding the kernel entry and bootloader <-> kernel interfaces, in
-order to avoid the degeneration that had become the ppc32 kernel entry
-point and the way a new platform should be added to the kernel. The
-legacy iSeries platform breaks those rules as it predates this scheme,
-but no new board support will be accepted in the main tree that
-doesn't follow them properly. In addition, since the advent of the
-arch/powerpc merged architecture for ppc32 and ppc64, new 32-bit
-platforms and 32-bit platforms which move into arch/powerpc will be
-required to use these rules as well.
-
-The main requirement that will be defined in more detail below is
-the presence of a device-tree whose format is defined after Open
-Firmware specification. However, in order to make life easier
-to embedded board vendors, the kernel doesn't require the device-tree
-to represent every device in the system and only requires some nodes
-and properties to be present. This will be described in detail in
-section III, but, for example, the kernel does not require you to
-create a node for every PCI device in the system. It is a requirement
-to have a node for PCI host bridges in order to provide interrupt
-routing informations and memory/IO ranges, among others. It is also
-recommended to define nodes for on chip devices and other busses that
-don't specifically fit in an existing OF specification. This creates a
-great flexibility in the way the kernel can then probe those and match
-drivers to device, without having to hard code all sorts of tables. It
-also makes it more flexible for board vendors to do minor hardware
-upgrades without significantly impacting the kernel code or cluttering
-it with special cases.
-
-
-1) Entry point for arch/powerpc
--------------------------------
-
- There is one and one single entry point to the kernel, at the start
- of the kernel image. That entry point supports two calling
- conventions:
-
- a) Boot from Open Firmware. If your firmware is compatible
- with Open Firmware (IEEE 1275) or provides an OF compatible
- client interface API (support for "interpret" callback of
- forth words isn't required), you can enter the kernel with:
-
- r5 : OF callback pointer as defined by IEEE 1275
- bindings to powerpc. Only the 32-bit client interface
- is currently supported
-
- r3, r4 : address & length of an initrd if any or 0
-
- The MMU is either on or off; the kernel will run the
- trampoline located in arch/powerpc/kernel/prom_init.c to
- extract the device-tree and other information from open
- firmware and build a flattened device-tree as described
- in b). prom_init() will then re-enter the kernel using
- the second method. This trampoline code runs in the
- context of the firmware, which is supposed to handle all
- exceptions during that time.
-
- b) Direct entry with a flattened device-tree block. This entry
- point is called by a) after the OF trampoline and can also be
- called directly by a bootloader that does not support the Open
- Firmware client interface. It is also used by "kexec" to
- implement "hot" booting of a new kernel from a previous
- running one. This method is what I will describe in more
- details in this document, as method a) is simply standard Open
- Firmware, and thus should be implemented according to the
- various standard documents defining it and its binding to the
- PowerPC platform. The entry point definition then becomes:
-
- r3 : physical pointer to the device-tree block
- (defined in chapter II) in RAM
-
- r4 : physical pointer to the kernel itself. This is
- used by the assembly code to properly disable the MMU
- in case you are entering the kernel with MMU enabled
- and a non-1:1 mapping.
-
- r5 : NULL (as to differentiate with method a)
-
- Note about SMP entry: Either your firmware puts your other
- CPUs in some sleep loop or spin loop in ROM where you can get
- them out via a soft reset or some other means, in which case
- you don't need to care, or you'll have to enter the kernel
- with all CPUs. The way to do that with method b) will be
- described in a later revision of this document.
-
-
-2) Board support
-----------------
-
-64-bit kernels:
-
- Board supports (platforms) are not exclusive config options. An
- arbitrary set of board supports can be built in a single kernel
- image. The kernel will "know" what set of functions to use for a
- given platform based on the content of the device-tree. Thus, you
- should:
-
- a) add your platform support as a _boolean_ option in
- arch/powerpc/Kconfig, following the example of PPC_PSERIES,
- PPC_PMAC and PPC_MAPLE. The later is probably a good
- example of a board support to start from.
-
- b) create your main platform file as
- "arch/powerpc/platforms/myplatform/myboard_setup.c" and add it
- to the Makefile under the condition of your CONFIG_
- option. This file will define a structure of type "ppc_md"
- containing the various callbacks that the generic code will
- use to get to your platform specific code
-
- c) Add a reference to your "ppc_md" structure in the
- "machines" table in arch/powerpc/kernel/setup_64.c if you are
- a 64-bit platform.
-
- d) request and get assigned a platform number (see PLATFORM_*
- constants in arch/powerpc/include/asm/processor.h
-
-32-bit embedded kernels:
-
- Currently, board support is essentially an exclusive config option.
- The kernel is configured for a single platform. Part of the reason
- for this is to keep kernels on embedded systems small and efficient;
- part of this is due to the fact the code is already that way. In the
- future, a kernel may support multiple platforms, but only if the
- platforms feature the same core architecture. A single kernel build
- cannot support both configurations with Book E and configurations
- with classic Powerpc architectures.
-
- 32-bit embedded platforms that are moved into arch/powerpc using a
- flattened device tree should adopt the merged tree practice of
- setting ppc_md up dynamically, even though the kernel is currently
- built with support for only a single platform at a time. This allows
- unification of the setup code, and will make it easier to go to a
- multiple-platform-support model in the future.
-
-NOTE: I believe the above will be true once Ben's done with the merge
-of the boot sequences.... someone speak up if this is wrong!
-
- To add a 32-bit embedded platform support, follow the instructions
- for 64-bit platforms above, with the exception that the Kconfig
- option should be set up such that the kernel builds exclusively for
- the platform selected. The processor type for the platform should
- enable another config option to select the specific board
- supported.
-
-NOTE: If Ben doesn't merge the setup files, may need to change this to
-point to setup_32.c
-
-
- I will describe later the boot process and various callbacks that
- your platform should implement.
-
-
-II - The DT block format
-========================
-
-
-This chapter defines the actual format of the flattened device-tree
-passed to the kernel. The actual content of it and kernel requirements
-are described later. You can find example of code manipulating that
-format in various places, including arch/powerpc/kernel/prom_init.c
-which will generate a flattened device-tree from the Open Firmware
-representation, or the fs2dt utility which is part of the kexec tools
-which will generate one from a filesystem representation. It is
-expected that a bootloader like uboot provides a bit more support,
-that will be discussed later as well.
-
-Note: The block has to be in main memory. It has to be accessible in
-both real mode and virtual mode with no mapping other than main
-memory. If you are writing a simple flash bootloader, it should copy
-the block to RAM before passing it to the kernel.
-
-
-1) Header
----------
-
- The kernel is entered with r3 pointing to an area of memory that is
- roughly described in arch/powerpc/include/asm/prom.h by the structure
- boot_param_header:
-
-struct boot_param_header {
- u32 magic; /* magic word OF_DT_HEADER */
- u32 totalsize; /* total size of DT block */
- u32 off_dt_struct; /* offset to structure */
- u32 off_dt_strings; /* offset to strings */
- u32 off_mem_rsvmap; /* offset to memory reserve map
- */
- u32 version; /* format version */
- u32 last_comp_version; /* last compatible version */
-
- /* version 2 fields below */
- u32 boot_cpuid_phys; /* Which physical CPU id we're
- booting on */
- /* version 3 fields below */
- u32 size_dt_strings; /* size of the strings block */
-
- /* version 17 fields below */
- u32 size_dt_struct; /* size of the DT structure block */
-};
-
- Along with the constants:
-
-/* Definitions used by the flattened device tree */
-#define OF_DT_HEADER 0xd00dfeed /* 4: version,
- 4: total size */
-#define OF_DT_BEGIN_NODE 0x1 /* Start node: full name
- */
-#define OF_DT_END_NODE 0x2 /* End node */
-#define OF_DT_PROP 0x3 /* Property: name off,
- size, content */
-#define OF_DT_END 0x9
-
- All values in this header are in big endian format, the various
- fields in this header are defined more precisely below. All
- "offset" values are in bytes from the start of the header; that is
- from the value of r3.
-
- - magic
-
- This is a magic value that "marks" the beginning of the
- device-tree block header. It contains the value 0xd00dfeed and is
- defined by the constant OF_DT_HEADER
-
- - totalsize
-
- This is the total size of the DT block including the header. The
- "DT" block should enclose all data structures defined in this
- chapter (who are pointed to by offsets in this header). That is,
- the device-tree structure, strings, and the memory reserve map.
-
- - off_dt_struct
-
- This is an offset from the beginning of the header to the start
- of the "structure" part the device tree. (see 2) device tree)
-
- - off_dt_strings
-
- This is an offset from the beginning of the header to the start
- of the "strings" part of the device-tree
-
- - off_mem_rsvmap
-
- This is an offset from the beginning of the header to the start
- of the reserved memory map. This map is a list of pairs of 64-
- bit integers. Each pair is a physical address and a size. The
- list is terminated by an entry of size 0. This map provides the
- kernel with a list of physical memory areas that are "reserved"
- and thus not to be used for memory allocations, especially during
- early initialization. The kernel needs to allocate memory during
- boot for things like un-flattening the device-tree, allocating an
- MMU hash table, etc... Those allocations must be done in such a
- way to avoid overriding critical things like, on Open Firmware
- capable machines, the RTAS instance, or on some pSeries, the TCE
- tables used for the iommu. Typically, the reserve map should
- contain _at least_ this DT block itself (header,total_size). If
- you are passing an initrd to the kernel, you should reserve it as
- well. You do not need to reserve the kernel image itself. The map
- should be 64-bit aligned.
-
- - version
-
- This is the version of this structure. Version 1 stops
- here. Version 2 adds an additional field boot_cpuid_phys.
- Version 3 adds the size of the strings block, allowing the kernel
- to reallocate it easily at boot and free up the unused flattened
- structure after expansion. Version 16 introduces a new more
- "compact" format for the tree itself that is however not backward
- compatible. Version 17 adds an additional field, size_dt_struct,
- allowing it to be reallocated or moved more easily (this is
- particularly useful for bootloaders which need to make
- adjustments to a device tree based on probed information). You
- should always generate a structure of the highest version defined
- at the time of your implementation. Currently that is version 17,
- unless you explicitly aim at being backward compatible.
-
- - last_comp_version
-
- Last compatible version. This indicates down to what version of
- the DT block you are backward compatible. For example, version 2
- is backward compatible with version 1 (that is, a kernel build
- for version 1 will be able to boot with a version 2 format). You
- should put a 1 in this field if you generate a device tree of
- version 1 to 3, or 16 if you generate a tree of version 16 or 17
- using the new unit name format.
-
- - boot_cpuid_phys
-
- This field only exist on version 2 headers. It indicate which
- physical CPU ID is calling the kernel entry point. This is used,
- among others, by kexec. If you are on an SMP system, this value
- should match the content of the "reg" property of the CPU node in
- the device-tree corresponding to the CPU calling the kernel entry
- point (see further chapters for more informations on the required
- device-tree contents)
-
- - size_dt_strings
-
- This field only exists on version 3 and later headers. It
- gives the size of the "strings" section of the device tree (which
- starts at the offset given by off_dt_strings).
-
- - size_dt_struct
-
- This field only exists on version 17 and later headers. It gives
- the size of the "structure" section of the device tree (which
- starts at the offset given by off_dt_struct).
-
- So the typical layout of a DT block (though the various parts don't
- need to be in that order) looks like this (addresses go from top to
- bottom):
-
-
- ------------------------------
- r3 -> | struct boot_param_header |
- ------------------------------
- | (alignment gap) (*) |
- ------------------------------
- | memory reserve map |
- ------------------------------
- | (alignment gap) |
- ------------------------------
- | |
- | device-tree structure |
- | |
- ------------------------------
- | (alignment gap) |
- ------------------------------
- | |
- | device-tree strings |
- | |
- -----> ------------------------------
- |
- |
- --- (r3 + totalsize)
-
- (*) The alignment gaps are not necessarily present; their presence
- and size are dependent on the various alignment requirements of
- the individual data blocks.
-
-
-2) Device tree generalities
----------------------------
-
-This device-tree itself is separated in two different blocks, a
-structure block and a strings block. Both need to be aligned to a 4
-byte boundary.
-
-First, let's quickly describe the device-tree concept before detailing
-the storage format. This chapter does _not_ describe the detail of the
-required types of nodes & properties for the kernel, this is done
-later in chapter III.
-
-The device-tree layout is strongly inherited from the definition of
-the Open Firmware IEEE 1275 device-tree. It's basically a tree of
-nodes, each node having two or more named properties. A property can
-have a value or not.
-
-It is a tree, so each node has one and only one parent except for the
-root node who has no parent.
-
-A node has 2 names. The actual node name is generally contained in a
-property of type "name" in the node property list whose value is a
-zero terminated string and is mandatory for version 1 to 3 of the
-format definition (as it is in Open Firmware). Version 16 makes it
-optional as it can generate it from the unit name defined below.
-
-There is also a "unit name" that is used to differentiate nodes with
-the same name at the same level, it is usually made of the node
-names, the "@" sign, and a "unit address", which definition is
-specific to the bus type the node sits on.
-
-The unit name doesn't exist as a property per-se but is included in
-the device-tree structure. It is typically used to represent "path" in
-the device-tree. More details about the actual format of these will be
-below.
-
-The kernel powerpc generic code does not make any formal use of the
-unit address (though some board support code may do) so the only real
-requirement here for the unit address is to ensure uniqueness of
-the node unit name at a given level of the tree. Nodes with no notion
-of address and no possible sibling of the same name (like /memory or
-/cpus) may omit the unit address in the context of this specification,
-or use the "@0" default unit address. The unit name is used to define
-a node "full path", which is the concatenation of all parent node
-unit names separated with "/".
-
-The root node doesn't have a defined name, and isn't required to have
-a name property either if you are using version 3 or earlier of the
-format. It also has no unit address (no @ symbol followed by a unit
-address). The root node unit name is thus an empty string. The full
-path to the root node is "/".
-
-Every node which actually represents an actual device (that is, a node
-which isn't only a virtual "container" for more nodes, like "/cpus"
-is) is also required to have a "device_type" property indicating the
-type of node .
-
-Finally, every node that can be referenced from a property in another
-node is required to have a "linux,phandle" property. Real open
-firmware implementations provide a unique "phandle" value for every
-node that the "prom_init()" trampoline code turns into
-"linux,phandle" properties. However, this is made optional if the
-flattened device tree is used directly. An example of a node
-referencing another node via "phandle" is when laying out the
-interrupt tree which will be described in a further version of this
-document.
-
-This "linux, phandle" property is a 32-bit value that uniquely
-identifies a node. You are free to use whatever values or system of
-values, internal pointers, or whatever to generate these, the only
-requirement is that every node for which you provide that property has
-a unique value for it.
-
-Here is an example of a simple device-tree. In this example, an "o"
-designates a node followed by the node unit name. Properties are
-presented with their name followed by their content. "content"
-represents an ASCII string (zero terminated) value, while <content>
-represents a 32-bit hexadecimal value. The various nodes in this
-example will be discussed in a later chapter. At this point, it is
-only meant to give you a idea of what a device-tree looks like. I have
-purposefully kept the "name" and "linux,phandle" properties which
-aren't necessary in order to give you a better idea of what the tree
-looks like in practice.
-
- / o device-tree
- |- name = "device-tree"
- |- model = "MyBoardName"
- |- compatible = "MyBoardFamilyName"
- |- #address-cells = <2>
- |- #size-cells = <2>
- |- linux,phandle = <0>
- |
- o cpus
- | | - name = "cpus"
- | | - linux,phandle = <1>
- | | - #address-cells = <1>
- | | - #size-cells = <0>
- | |
- | o PowerPC,970@0
- | |- name = "PowerPC,970"
- | |- device_type = "cpu"
- | |- reg = <0>
- | |- clock-frequency = <5f5e1000>
- | |- 64-bit
- | |- linux,phandle = <2>
- |
- o memory@0
- | |- name = "memory"
- | |- device_type = "memory"
- | |- reg = <00000000 00000000 00000000 20000000>
- | |- linux,phandle = <3>
- |
- o chosen
- |- name = "chosen"
- |- bootargs = "root=/dev/sda2"
- |- linux,phandle = <4>
-
-This tree is almost a minimal tree. It pretty much contains the
-minimal set of required nodes and properties to boot a linux kernel;
-that is, some basic model informations at the root, the CPUs, and the
-physical memory layout. It also includes misc information passed
-through /chosen, like in this example, the platform type (mandatory)
-and the kernel command line arguments (optional).
-
-The /cpus/PowerPC,970@0/64-bit property is an example of a
-property without a value. All other properties have a value. The
-significance of the #address-cells and #size-cells properties will be
-explained in chapter IV which defines precisely the required nodes and
-properties and their content.
-
-
-3) Device tree "structure" block
-
-The structure of the device tree is a linearized tree structure. The
-"OF_DT_BEGIN_NODE" token starts a new node, and the "OF_DT_END_NODE"
-ends that node definition. Child nodes are simply defined before
-"OF_DT_END_NODE" (that is nodes within the node). A 'token' is a 32
-bit value. The tree has to be "finished" with a OF_DT_END token
-
-Here's the basic structure of a single node:
-
- * token OF_DT_BEGIN_NODE (that is 0x00000001)
- * for version 1 to 3, this is the node full path as a zero
- terminated string, starting with "/". For version 16 and later,
- this is the node unit name only (or an empty string for the
- root node)
- * [align gap to next 4 bytes boundary]
- * for each property:
- * token OF_DT_PROP (that is 0x00000003)
- * 32-bit value of property value size in bytes (or 0 if no
- value)
- * 32-bit value of offset in string block of property name
- * property value data if any
- * [align gap to next 4 bytes boundary]
- * [child nodes if any]
- * token OF_DT_END_NODE (that is 0x00000002)
-
-So the node content can be summarized as a start token, a full path,
-a list of properties, a list of child nodes, and an end token. Every
-child node is a full node structure itself as defined above.
-
-NOTE: The above definition requires that all property definitions for
-a particular node MUST precede any subnode definitions for that node.
-Although the structure would not be ambiguous if properties and
-subnodes were intermingled, the kernel parser requires that the
-properties come first (up until at least 2.6.22). Any tools
-manipulating a flattened tree must take care to preserve this
-constraint.
-
-4) Device tree "strings" block
-
-In order to save space, property names, which are generally redundant,
-are stored separately in the "strings" block. This block is simply the
-whole bunch of zero terminated strings for all property names
-concatenated together. The device-tree property definitions in the
-structure block will contain offset values from the beginning of the
-strings block.
-
-
-III - Required content of the device tree
-=========================================
-
-WARNING: All "linux,*" properties defined in this document apply only
-to a flattened device-tree. If your platform uses a real
-implementation of Open Firmware or an implementation compatible with
-the Open Firmware client interface, those properties will be created
-by the trampoline code in the kernel's prom_init() file. For example,
-that's where you'll have to add code to detect your board model and
-set the platform number. However, when using the flattened device-tree
-entry point, there is no prom_init() pass, and thus you have to
-provide those properties yourself.
-
-
-1) Note about cells and address representation
-----------------------------------------------
-
-The general rule is documented in the various Open Firmware
-documentations. If you choose to describe a bus with the device-tree
-and there exist an OF bus binding, then you should follow the
-specification. However, the kernel does not require every single
-device or bus to be described by the device tree.
-
-In general, the format of an address for a device is defined by the
-parent bus type, based on the #address-cells and #size-cells
-properties. Note that the parent's parent definitions of #address-cells
-and #size-cells are not inherited so every node with children must specify
-them. The kernel requires the root node to have those properties defining
-addresses format for devices directly mapped on the processor bus.
-
-Those 2 properties define 'cells' for representing an address and a
-size. A "cell" is a 32-bit number. For example, if both contain 2
-like the example tree given above, then an address and a size are both
-composed of 2 cells, and each is a 64-bit number (cells are
-concatenated and expected to be in big endian format). Another example
-is the way Apple firmware defines them, with 2 cells for an address
-and one cell for a size. Most 32-bit implementations should define
-#address-cells and #size-cells to 1, which represents a 32-bit value.
-Some 32-bit processors allow for physical addresses greater than 32
-bits; these processors should define #address-cells as 2.
-
-"reg" properties are always a tuple of the type "address size" where
-the number of cells of address and size is specified by the bus
-#address-cells and #size-cells. When a bus supports various address
-spaces and other flags relative to a given address allocation (like
-prefetchable, etc...) those flags are usually added to the top level
-bits of the physical address. For example, a PCI physical address is
-made of 3 cells, the bottom two containing the actual address itself
-while the top cell contains address space indication, flags, and pci
-bus & device numbers.
-
-For busses that support dynamic allocation, it's the accepted practice
-to then not provide the address in "reg" (keep it 0) though while
-providing a flag indicating the address is dynamically allocated, and
-then, to provide a separate "assigned-addresses" property that
-contains the fully allocated addresses. See the PCI OF bindings for
-details.
-
-In general, a simple bus with no address space bits and no dynamic
-allocation is preferred if it reflects your hardware, as the existing
-kernel address parsing functions will work out of the box. If you
-define a bus type with a more complex address format, including things
-like address space bits, you'll have to add a bus translator to the
-prom_parse.c file of the recent kernels for your bus type.
-
-The "reg" property only defines addresses and sizes (if #size-cells is
-non-0) within a given bus. In order to translate addresses upward
-(that is into parent bus addresses, and possibly into CPU physical
-addresses), all busses must contain a "ranges" property. If the
-"ranges" property is missing at a given level, it's assumed that
-translation isn't possible, i.e., the registers are not visible on the
-parent bus. The format of the "ranges" property for a bus is a list
-of:
-
- bus address, parent bus address, size
-
-"bus address" is in the format of the bus this bus node is defining,
-that is, for a PCI bridge, it would be a PCI address. Thus, (bus
-address, size) defines a range of addresses for child devices. "parent
-bus address" is in the format of the parent bus of this bus. For
-example, for a PCI host controller, that would be a CPU address. For a
-PCI<->ISA bridge, that would be a PCI address. It defines the base
-address in the parent bus where the beginning of that range is mapped.
-
-For a new 64-bit powerpc board, I recommend either the 2/2 format or
-Apple's 2/1 format which is slightly more compact since sizes usually
-fit in a single 32-bit word. New 32-bit powerpc boards should use a
-1/1 format, unless the processor supports physical addresses greater
-than 32-bits, in which case a 2/1 format is recommended.
-
-Alternatively, the "ranges" property may be empty, indicating that the
-registers are visible on the parent bus using an identity mapping
-translation. In other words, the parent bus address space is the same
-as the child bus address space.
-
-2) Note about "compatible" properties
--------------------------------------
-
-These properties are optional, but recommended in devices and the root
-node. The format of a "compatible" property is a list of concatenated
-zero terminated strings. They allow a device to express its
-compatibility with a family of similar devices, in some cases,
-allowing a single driver to match against several devices regardless
-of their actual names.
-
-3) Note about "name" properties
--------------------------------
-
-While earlier users of Open Firmware like OldWorld macintoshes tended
-to use the actual device name for the "name" property, it's nowadays
-considered a good practice to use a name that is closer to the device
-class (often equal to device_type). For example, nowadays, ethernet
-controllers are named "ethernet", an additional "model" property
-defining precisely the chip type/model, and "compatible" property
-defining the family in case a single driver can driver more than one
-of these chips. However, the kernel doesn't generally put any
-restriction on the "name" property; it is simply considered good
-practice to follow the standard and its evolutions as closely as
-possible.
-
-Note also that the new format version 16 makes the "name" property
-optional. If it's absent for a node, then the node's unit name is then
-used to reconstruct the name. That is, the part of the unit name
-before the "@" sign is used (or the entire unit name if no "@" sign
-is present).
-
-4) Note about node and property names and character set
--------------------------------------------------------
-
-While open firmware provides more flexible usage of 8859-1, this
-specification enforces more strict rules. Nodes and properties should
-be comprised only of ASCII characters 'a' to 'z', '0' to
-'9', ',', '.', '_', '+', '#', '?', and '-'. Node names additionally
-allow uppercase characters 'A' to 'Z' (property names should be
-lowercase. The fact that vendors like Apple don't respect this rule is
-irrelevant here). Additionally, node and property names should always
-begin with a character in the range 'a' to 'z' (or 'A' to 'Z' for node
-names).
-
-The maximum number of characters for both nodes and property names
-is 31. In the case of node names, this is only the leftmost part of
-a unit name (the pure "name" property), it doesn't include the unit
-address which can extend beyond that limit.
-
-
-5) Required nodes and properties
---------------------------------
- These are all that are currently required. However, it is strongly
- recommended that you expose PCI host bridges as documented in the
- PCI binding to open firmware, and your interrupt tree as documented
- in OF interrupt tree specification.
-
- a) The root node
-
- The root node requires some properties to be present:
-
- - model : this is your board name/model
- - #address-cells : address representation for "root" devices
- - #size-cells: the size representation for "root" devices
- - device_type : This property shouldn't be necessary. However, if
- you decide to create a device_type for your root node, make sure it
- is _not_ "chrp" unless your platform is a pSeries or PAPR compliant
- one for 64-bit, or a CHRP-type machine for 32-bit as this will
- matched by the kernel this way.
-
- Additionally, some recommended properties are:
-
- - compatible : the board "family" generally finds its way here,
- for example, if you have 2 board models with a similar layout,
- that typically get driven by the same platform code in the
- kernel, you would use a different "model" property but put a
- value in "compatible". The kernel doesn't directly use that
- value but it is generally useful.
-
- The root node is also generally where you add additional properties
- specific to your board like the serial number if any, that sort of
- thing. It is recommended that if you add any "custom" property whose
- name may clash with standard defined ones, you prefix them with your
- vendor name and a comma.
-
- b) The /cpus node
-
- This node is the parent of all individual CPU nodes. It doesn't
- have any specific requirements, though it's generally good practice
- to have at least:
-
- #address-cells = <00000001>
- #size-cells = <00000000>
-
- This defines that the "address" for a CPU is a single cell, and has
- no meaningful size. This is not necessary but the kernel will assume
- that format when reading the "reg" properties of a CPU node, see
- below
-
- c) The /cpus/* nodes
-
- So under /cpus, you are supposed to create a node for every CPU on
- the machine. There is no specific restriction on the name of the
- CPU, though It's common practice to call it PowerPC,<name>. For
- example, Apple uses PowerPC,G5 while IBM uses PowerPC,970FX.
-
- Required properties:
-
- - device_type : has to be "cpu"
- - reg : This is the physical CPU number, it's a single 32-bit cell
- and is also used as-is as the unit number for constructing the
- unit name in the full path. For example, with 2 CPUs, you would
- have the full path:
- /cpus/PowerPC,970FX@0
- /cpus/PowerPC,970FX@1
- (unit addresses do not require leading zeroes)
- - d-cache-block-size : one cell, L1 data cache block size in bytes (*)
- - i-cache-block-size : one cell, L1 instruction cache block size in
- bytes
- - d-cache-size : one cell, size of L1 data cache in bytes
- - i-cache-size : one cell, size of L1 instruction cache in bytes
-
-(*) The cache "block" size is the size on which the cache management
-instructions operate. Historically, this document used the cache
-"line" size here which is incorrect. The kernel will prefer the cache
-block size and will fallback to cache line size for backward
-compatibility.
-
- Recommended properties:
-
- - timebase-frequency : a cell indicating the frequency of the
- timebase in Hz. This is not directly used by the generic code,
- but you are welcome to copy/paste the pSeries code for setting
- the kernel timebase/decrementer calibration based on this
- value.
- - clock-frequency : a cell indicating the CPU core clock frequency
- in Hz. A new property will be defined for 64-bit values, but if
- your frequency is < 4Ghz, one cell is enough. Here as well as
- for the above, the common code doesn't use that property, but
- you are welcome to re-use the pSeries or Maple one. A future
- kernel version might provide a common function for this.
- - d-cache-line-size : one cell, L1 data cache line size in bytes
- if different from the block size
- - i-cache-line-size : one cell, L1 instruction cache line size in
- bytes if different from the block size
-
- You are welcome to add any property you find relevant to your board,
- like some information about the mechanism used to soft-reset the
- CPUs. For example, Apple puts the GPIO number for CPU soft reset
- lines in there as a "soft-reset" property since they start secondary
- CPUs by soft-resetting them.
-
-
- d) the /memory node(s)
-
- To define the physical memory layout of your board, you should
- create one or more memory node(s). You can either create a single
- node with all memory ranges in its reg property, or you can create
- several nodes, as you wish. The unit address (@ part) used for the
- full path is the address of the first range of memory defined by a
- given node. If you use a single memory node, this will typically be
- @0.
-
- Required properties:
-
- - device_type : has to be "memory"
- - reg : This property contains all the physical memory ranges of
- your board. It's a list of addresses/sizes concatenated
- together, with the number of cells of each defined by the
- #address-cells and #size-cells of the root node. For example,
- with both of these properties being 2 like in the example given
- earlier, a 970 based machine with 6Gb of RAM could typically
- have a "reg" property here that looks like:
-
- 00000000 00000000 00000000 80000000
- 00000001 00000000 00000001 00000000
-
- That is a range starting at 0 of 0x80000000 bytes and a range
- starting at 0x100000000 and of 0x100000000 bytes. You can see
- that there is no memory covering the IO hole between 2Gb and
- 4Gb. Some vendors prefer splitting those ranges into smaller
- segments, but the kernel doesn't care.
-
- e) The /chosen node
-
- This node is a bit "special". Normally, that's where open firmware
- puts some variable environment information, like the arguments, or
- the default input/output devices.
-
- This specification makes a few of these mandatory, but also defines
- some linux-specific properties that would be normally constructed by
- the prom_init() trampoline when booting with an OF client interface,
- but that you have to provide yourself when using the flattened format.
-
- Recommended properties:
-
- - bootargs : This zero-terminated string is passed as the kernel
- command line
- - linux,stdout-path : This is the full path to your standard
- console device if any. Typically, if you have serial devices on
- your board, you may want to put the full path to the one set as
- the default console in the firmware here, for the kernel to pick
- it up as its own default console. If you look at the function
- set_preferred_console() in arch/ppc64/kernel/setup.c, you'll see
- that the kernel tries to find out the default console and has
- knowledge of various types like 8250 serial ports. You may want
- to extend this function to add your own.
-
- Note that u-boot creates and fills in the chosen node for platforms
- that use it.
-
- (Note: a practice that is now obsolete was to include a property
- under /chosen called interrupt-controller which had a phandle value
- that pointed to the main interrupt controller)
-
- f) the /soc<SOCname> node
-
- This node is used to represent a system-on-a-chip (SOC) and must be
- present if the processor is a SOC. The top-level soc node contains
- information that is global to all devices on the SOC. The node name
- should contain a unit address for the SOC, which is the base address
- of the memory-mapped register set for the SOC. The name of an soc
- node should start with "soc", and the remainder of the name should
- represent the part number for the soc. For example, the MPC8540's
- soc node would be called "soc8540".
-
- Required properties:
-
- - device_type : Should be "soc"
- - ranges : Should be defined as specified in 1) to describe the
- translation of SOC addresses for memory mapped SOC registers.
- - bus-frequency: Contains the bus frequency for the SOC node.
- Typically, the value of this field is filled in by the boot
- loader.
-
-
- Recommended properties:
-
- - reg : This property defines the address and size of the
- memory-mapped registers that are used for the SOC node itself.
- It does not include the child device registers - these will be
- defined inside each child node. The address specified in the
- "reg" property should match the unit address of the SOC node.
- - #address-cells : Address representation for "soc" devices. The
- format of this field may vary depending on whether or not the
- device registers are memory mapped. For memory mapped
- registers, this field represents the number of cells needed to
- represent the address of the registers. For SOCs that do not
- use MMIO, a special address format should be defined that
- contains enough cells to represent the required information.
- See 1) above for more details on defining #address-cells.
- - #size-cells : Size representation for "soc" devices
- - #interrupt-cells : Defines the width of cells used to represent
- interrupts. Typically this value is <2>, which includes a
- 32-bit number that represents the interrupt number, and a
- 32-bit number that represents the interrupt sense and level.
- This field is only needed if the SOC contains an interrupt
- controller.
-
- The SOC node may contain child nodes for each SOC device that the
- platform uses. Nodes should not be created for devices which exist
- on the SOC but are not used by a particular platform. See chapter VI
- for more information on how to specify devices that are part of a SOC.
-
- Example SOC node for the MPC8540:
-
- soc8540@e0000000 {
- #address-cells = <1>;
- #size-cells = <1>;
- #interrupt-cells = <2>;
- device_type = "soc";
- ranges = <00000000 e0000000 00100000>
- reg = <e0000000 00003000>;
- bus-frequency = <0>;
- }
-
-
-
-IV - "dtc", the device tree compiler
-====================================
-
-
-dtc source code can be found at
-<http://git.jdl.com/gitweb/?p=dtc.git>
-
-WARNING: This version is still in early development stage; the
-resulting device-tree "blobs" have not yet been validated with the
-kernel. The current generated block lacks a useful reserve map (it will
-be fixed to generate an empty one, it's up to the bootloader to fill
-it up) among others. The error handling needs work, bugs are lurking,
-etc...
-
-dtc basically takes a device-tree in a given format and outputs a
-device-tree in another format. The currently supported formats are:
-
- Input formats:
- -------------
-
- - "dtb": "blob" format, that is a flattened device-tree block
- with
- header all in a binary blob.
- - "dts": "source" format. This is a text file containing a
- "source" for a device-tree. The format is defined later in this
- chapter.
- - "fs" format. This is a representation equivalent to the
- output of /proc/device-tree, that is nodes are directories and
- properties are files
-
- Output formats:
- ---------------
-
- - "dtb": "blob" format
- - "dts": "source" format
- - "asm": assembly language file. This is a file that can be
- sourced by gas to generate a device-tree "blob". That file can
- then simply be added to your Makefile. Additionally, the
- assembly file exports some symbols that can be used.
-
-
-The syntax of the dtc tool is
-
- dtc [-I <input-format>] [-O <output-format>]
- [-o output-filename] [-V output_version] input_filename
-
-
-The "output_version" defines what version of the "blob" format will be
-generated. Supported versions are 1,2,3 and 16. The default is
-currently version 3 but that may change in the future to version 16.
-
-Additionally, dtc performs various sanity checks on the tree, like the
-uniqueness of linux, phandle properties, validity of strings, etc...
-
-The format of the .dts "source" file is "C" like, supports C and C++
-style comments.
-
-/ {
-}
-
-The above is the "device-tree" definition. It's the only statement
-supported currently at the toplevel.
-
-/ {
- property1 = "string_value"; /* define a property containing a 0
- * terminated string
- */
-
- property2 = <1234abcd>; /* define a property containing a
- * numerical 32-bit value (hexadecimal)
- */
-
- property3 = <12345678 12345678 deadbeef>;
- /* define a property containing 3
- * numerical 32-bit values (cells) in
- * hexadecimal
- */
- property4 = [0a 0b 0c 0d de ea ad be ef];
- /* define a property whose content is
- * an arbitrary array of bytes
- */
-
- childnode@address { /* define a child node named "childnode"
- * whose unit name is "childnode at
- * address"
- */
-
- childprop = "hello\n"; /* define a property "childprop" of
- * childnode (in this case, a string)
- */
- };
-};
-
-Nodes can contain other nodes etc... thus defining the hierarchical
-structure of the tree.
-
-Strings support common escape sequences from C: "\n", "\t", "\r",
-"\(octal value)", "\x(hex value)".
-
-It is also suggested that you pipe your source file through cpp (gcc
-preprocessor) so you can use #include's, #define for constants, etc...
-
-Finally, various options are planned but not yet implemented, like
-automatic generation of phandles, labels (exported to the asm file so
-you can point to a property content and change it easily from whatever
-you link the device-tree with), label or path instead of numeric value
-in some cells to "point" to a node (replaced by a phandle at compile
-time), export of reserve map address to the asm file, ability to
-specify reserve map content at compile time, etc...
-
-We may provide a .h include file with common definitions of that
-proves useful for some properties (like building PCI properties or
-interrupt maps) though it may be better to add a notion of struct
-definitions to the compiler...
-
-
-V - Recommendations for a bootloader
-====================================
-
-
-Here are some various ideas/recommendations that have been proposed
-while all this has been defined and implemented.
-
- - The bootloader may want to be able to use the device-tree itself
- and may want to manipulate it (to add/edit some properties,
- like physical memory size or kernel arguments). At this point, 2
- choices can be made. Either the bootloader works directly on the
- flattened format, or the bootloader has its own internal tree
- representation with pointers (similar to the kernel one) and
- re-flattens the tree when booting the kernel. The former is a bit
- more difficult to edit/modify, the later requires probably a bit
- more code to handle the tree structure. Note that the structure
- format has been designed so it's relatively easy to "insert"
- properties or nodes or delete them by just memmoving things
- around. It contains no internal offsets or pointers for this
- purpose.
-
- - An example of code for iterating nodes & retrieving properties
- directly from the flattened tree format can be found in the kernel
- file arch/ppc64/kernel/prom.c, look at scan_flat_dt() function,
- its usage in early_init_devtree(), and the corresponding various
- early_init_dt_scan_*() callbacks. That code can be re-used in a
- GPL bootloader, and as the author of that code, I would be happy
- to discuss possible free licensing to any vendor who wishes to
- integrate all or part of this code into a non-GPL bootloader.
-
-
-
-VI - System-on-a-chip devices and nodes
-=======================================
-
-Many companies are now starting to develop system-on-a-chip
-processors, where the processor core (CPU) and many peripheral devices
-exist on a single piece of silicon. For these SOCs, an SOC node
-should be used that defines child nodes for the devices that make
-up the SOC. While platforms are not required to use this model in
-order to boot the kernel, it is highly encouraged that all SOC
-implementations define as complete a flat-device-tree as possible to
-describe the devices on the SOC. This will allow for the
-genericization of much of the kernel code.
-
-
-1) Defining child nodes of an SOC
----------------------------------
-
-Each device that is part of an SOC may have its own node entry inside
-the SOC node. For each device that is included in the SOC, the unit
-address property represents the address offset for this device's
-memory-mapped registers in the parent's address space. The parent's
-address space is defined by the "ranges" property in the top-level soc
-node. The "reg" property for each node that exists directly under the
-SOC node should contain the address mapping from the child address space
-to the parent SOC address space and the size of the device's
-memory-mapped register file.
-
-For many devices that may exist inside an SOC, there are predefined
-specifications for the format of the device tree node. All SOC child
-nodes should follow these specifications, except where noted in this
-document.
-
-See appendix A for an example partial SOC node definition for the
-MPC8540.
-
-
-2) Representing devices without a current OF specification
-----------------------------------------------------------
-
-Currently, there are many devices on SOCs that do not have a standard
-representation pre-defined as part of the open firmware
-specifications, mainly because the boards that contain these SOCs are
-not currently booted using open firmware. This section contains
-descriptions for the SOC devices for which new nodes have been
-defined; this list will expand as more and more SOC-containing
-platforms are moved over to use the flattened-device-tree model.
-
-VII - Specifying interrupt information for devices
-===================================================
-
-The device tree represents the busses and devices of a hardware
-system in a form similar to the physical bus topology of the
-hardware.
-
-In addition, a logical 'interrupt tree' exists which represents the
-hierarchy and routing of interrupts in the hardware.
-
-The interrupt tree model is fully described in the
-document "Open Firmware Recommended Practice: Interrupt
-Mapping Version 0.9". The document is available at:
-<http://playground.sun.com/1275/practice>.
-
-1) interrupts property
-----------------------
-
-Devices that generate interrupts to a single interrupt controller
-should use the conventional OF representation described in the
-OF interrupt mapping documentation.
-
-Each device which generates interrupts must have an 'interrupt'
-property. The interrupt property value is an arbitrary number of
-of 'interrupt specifier' values which describe the interrupt or
-interrupts for the device.
-
-The encoding of an interrupt specifier is determined by the
-interrupt domain in which the device is located in the
-interrupt tree. The root of an interrupt domain specifies in
-its #interrupt-cells property the number of 32-bit cells
-required to encode an interrupt specifier. See the OF interrupt
-mapping documentation for a detailed description of domains.
-
-For example, the binding for the OpenPIC interrupt controller
-specifies an #interrupt-cells value of 2 to encode the interrupt
-number and level/sense information. All interrupt children in an
-OpenPIC interrupt domain use 2 cells per interrupt in their interrupts
-property.
-
-The PCI bus binding specifies a #interrupt-cell value of 1 to encode
-which interrupt pin (INTA,INTB,INTC,INTD) is used.
-
-2) interrupt-parent property
-----------------------------
-
-The interrupt-parent property is specified to define an explicit
-link between a device node and its interrupt parent in
-the interrupt tree. The value of interrupt-parent is the
-phandle of the parent node.
-
-If the interrupt-parent property is not defined for a node, its
-interrupt parent is assumed to be an ancestor in the node's
-_device tree_ hierarchy.
-
-3) OpenPIC Interrupt Controllers
---------------------------------
-
-OpenPIC interrupt controllers require 2 cells to encode
-interrupt information. The first cell defines the interrupt
-number. The second cell defines the sense and level
-information.
-
-Sense and level information should be encoded as follows:
-
- 0 = low to high edge sensitive type enabled
- 1 = active low level sensitive type enabled
- 2 = active high level sensitive type enabled
- 3 = high to low edge sensitive type enabled
-
-4) ISA Interrupt Controllers
-----------------------------
-
-ISA PIC interrupt controllers require 2 cells to encode
-interrupt information. The first cell defines the interrupt
-number. The second cell defines the sense and level
-information.
-
-ISA PIC interrupt controllers should adhere to the ISA PIC
-encodings listed below:
-
- 0 = active low level sensitive type enabled
- 1 = active high level sensitive type enabled
- 2 = high to low edge sensitive type enabled
- 3 = low to high edge sensitive type enabled
-
-VIII - Specifying Device Power Management Information (sleep property)
-===================================================================
-
-Devices on SOCs often have mechanisms for placing devices into low-power
-states that are decoupled from the devices' own register blocks. Sometimes,
-this information is more complicated than a cell-index property can
-reasonably describe. Thus, each device controlled in such a manner
-may contain a "sleep" property which describes these connections.
-
-The sleep property consists of one or more sleep resources, each of
-which consists of a phandle to a sleep controller, followed by a
-controller-specific sleep specifier of zero or more cells.
-
-The semantics of what type of low power modes are possible are defined
-by the sleep controller. Some examples of the types of low power modes
-that may be supported are:
-
- - Dynamic: The device may be disabled or enabled at any time.
- - System Suspend: The device may request to be disabled or remain
- awake during system suspend, but will not be disabled until then.
- - Permanent: The device is disabled permanently (until the next hard
- reset).
-
-Some devices may share a clock domain with each other, such that they should
-only be suspended when none of the devices are in use. Where reasonable,
-such nodes should be placed on a virtual bus, where the bus has the sleep
-property. If the clock domain is shared among devices that cannot be
-reasonably grouped in this manner, then create a virtual sleep controller
-(similar to an interrupt nexus, except that defining a standardized
-sleep-map should wait until its necessity is demonstrated).
-
-Appendix A - Sample SOC node for MPC8540
-========================================
-
- soc@e0000000 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "fsl,mpc8540-ccsr", "simple-bus";
- device_type = "soc";
- ranges = <0x00000000 0xe0000000 0x00100000>
- bus-frequency = <0>;
- interrupt-parent = <&pic>;
-
- ethernet@24000 {
- #address-cells = <1>;
- #size-cells = <1>;
- device_type = "network";
- model = "TSEC";
- compatible = "gianfar", "simple-bus";
- reg = <0x24000 0x1000>;
- local-mac-address = [ 00 E0 0C 00 73 00 ];
- interrupts = <29 2 30 2 34 2>;
- phy-handle = <&phy0>;
- sleep = <&pmc 00000080>;
- ranges;
-
- mdio@24520 {
- reg = <0x24520 0x20>;
- compatible = "fsl,gianfar-mdio";
-
- phy0: ethernet-phy@0 {
- interrupts = <5 1>;
- reg = <0>;
- device_type = "ethernet-phy";
- };
-
- phy1: ethernet-phy@1 {
- interrupts = <5 1>;
- reg = <1>;
- device_type = "ethernet-phy";
- };
-
- phy3: ethernet-phy@3 {
- interrupts = <7 1>;
- reg = <3>;
- device_type = "ethernet-phy";
- };
- };
- };
-
- ethernet@25000 {
- device_type = "network";
- model = "TSEC";
- compatible = "gianfar";
- reg = <0x25000 0x1000>;
- local-mac-address = [ 00 E0 0C 00 73 01 ];
- interrupts = <13 2 14 2 18 2>;
- phy-handle = <&phy1>;
- sleep = <&pmc 00000040>;
- };
-
- ethernet@26000 {
- device_type = "network";
- model = "FEC";
- compatible = "gianfar";
- reg = <0x26000 0x1000>;
- local-mac-address = [ 00 E0 0C 00 73 02 ];
- interrupts = <41 2>;
- phy-handle = <&phy3>;
- sleep = <&pmc 00000020>;
- };
-
- serial@4500 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "fsl,mpc8540-duart", "simple-bus";
- sleep = <&pmc 00000002>;
- ranges;
-
- serial@4500 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0x4500 0x100>;
- clock-frequency = <0>;
- interrupts = <42 2>;
- };
-
- serial@4600 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0x4600 0x100>;
- clock-frequency = <0>;
- interrupts = <42 2>;
- };
- };
-
- pic: pic@40000 {
- interrupt-controller;
- #address-cells = <0>;
- #interrupt-cells = <2>;
- reg = <0x40000 0x40000>;
- compatible = "chrp,open-pic";
- device_type = "open-pic";
- };
-
- i2c@3000 {
- interrupts = <43 2>;
- reg = <0x3000 0x100>;
- compatible = "fsl-i2c";
- dfsrr;
- sleep = <&pmc 00000004>;
- };
-
- pmc: power@e0070 {
- compatible = "fsl,mpc8540-pmc", "fsl,mpc8548-pmc";
- reg = <0xe0070 0x20>;
- };
- };
+++ /dev/null
-PPC4xx Clock Power Management (CPM) node
-
-Required properties:
- - compatible : compatible list, currently only "ibm,cpm"
- - dcr-access-method : "native"
- - dcr-reg : < DCR register range >
-
-Optional properties:
- - er-offset : All 4xx SoCs with a CPM controller have
- one of two different order for the CPM
- registers. Some have the CPM registers
- in the following order (ER,FR,SR). The
- others have them in the following order
- (SR,ER,FR). For the second case set
- er-offset = <1>.
- - unused-units : specifier consist of one cell. For each
- bit in the cell, the corresponding bit
- in CPM will be set to turn off unused
- devices.
- - idle-doze : specifier consist of one cell. For each
- bit in the cell, the corresponding bit
- in CPM will be set to turn off unused
- devices. This is usually just CPM[CPU].
- - standby : specifier consist of one cell. For each
- bit in the cell, the corresponding bit
- in CPM will be set on standby and
- restored on resume.
- - suspend : specifier consist of one cell. For each
- bit in the cell, the corresponding bit
- in CPM will be set on suspend (mem) and
- restored on resume. Note, for standby
- and suspend the corresponding bits can
- be different or the same. Usually for
- standby only class 2 and 3 units are set.
- However, the interface does not care.
- If they are the same, the additional
- power saving will be seeing if support
- is available to put the DDR in self
- refresh mode and any additional power
- saving techniques for the specific SoC.
-
-Example:
- CPM0: cpm {
- compatible = "ibm,cpm";
- dcr-access-method = "native";
- dcr-reg = <0x160 0x003>;
- er-offset = <0>;
- unused-units = <0x00000100>;
- idle-doze = <0x02000000>;
- standby = <0xfeff0000>;
- suspend = <0xfeff791d>;
-};
+++ /dev/null
- 4xx/Axon EMAC ethernet nodes
-
- The EMAC ethernet controller in IBM and AMCC 4xx chips, and also
- the Axon bridge. To operate this needs to interact with a ths
- special McMAL DMA controller, and sometimes an RGMII or ZMII
- interface. In addition to the nodes and properties described
- below, the node for the OPB bus on which the EMAC sits must have a
- correct clock-frequency property.
-
- i) The EMAC node itself
-
- Required properties:
- - device_type : "network"
-
- - compatible : compatible list, contains 2 entries, first is
- "ibm,emac-CHIP" where CHIP is the host ASIC (440gx,
- 405gp, Axon) and second is either "ibm,emac" or
- "ibm,emac4". For Axon, thus, we have: "ibm,emac-axon",
- "ibm,emac4"
- - interrupts : <interrupt mapping for EMAC IRQ and WOL IRQ>
- - interrupt-parent : optional, if needed for interrupt mapping
- - reg : <registers mapping>
- - local-mac-address : 6 bytes, MAC address
- - mal-device : phandle of the associated McMAL node
- - mal-tx-channel : 1 cell, index of the tx channel on McMAL associated
- with this EMAC
- - mal-rx-channel : 1 cell, index of the rx channel on McMAL associated
- with this EMAC
- - cell-index : 1 cell, hardware index of the EMAC cell on a given
- ASIC (typically 0x0 and 0x1 for EMAC0 and EMAC1 on
- each Axon chip)
- - max-frame-size : 1 cell, maximum frame size supported in bytes
- - rx-fifo-size : 1 cell, Rx fifo size in bytes for 10 and 100 Mb/sec
- operations.
- For Axon, 2048
- - tx-fifo-size : 1 cell, Tx fifo size in bytes for 10 and 100 Mb/sec
- operations.
- For Axon, 2048.
- - fifo-entry-size : 1 cell, size of a fifo entry (used to calculate
- thresholds).
- For Axon, 0x00000010
- - mal-burst-size : 1 cell, MAL burst size (used to calculate thresholds)
- in bytes.
- For Axon, 0x00000100 (I think ...)
- - phy-mode : string, mode of operations of the PHY interface.
- Supported values are: "mii", "rmii", "smii", "rgmii",
- "tbi", "gmii", rtbi", "sgmii".
- For Axon on CAB, it is "rgmii"
- - mdio-device : 1 cell, required iff using shared MDIO registers
- (440EP). phandle of the EMAC to use to drive the
- MDIO lines for the PHY used by this EMAC.
- - zmii-device : 1 cell, required iff connected to a ZMII. phandle of
- the ZMII device node
- - zmii-channel : 1 cell, required iff connected to a ZMII. Which ZMII
- channel or 0xffffffff if ZMII is only used for MDIO.
- - rgmii-device : 1 cell, required iff connected to an RGMII. phandle
- of the RGMII device node.
- For Axon: phandle of plb5/plb4/opb/rgmii
- - rgmii-channel : 1 cell, required iff connected to an RGMII. Which
- RGMII channel is used by this EMAC.
- Fox Axon: present, whatever value is appropriate for each
- EMAC, that is the content of the current (bogus) "phy-port"
- property.
-
- Optional properties:
- - phy-address : 1 cell, optional, MDIO address of the PHY. If absent,
- a search is performed.
- - phy-map : 1 cell, optional, bitmap of addresses to probe the PHY
- for, used if phy-address is absent. bit 0x00000001 is
- MDIO address 0.
- For Axon it can be absent, though my current driver
- doesn't handle phy-address yet so for now, keep
- 0x00ffffff in it.
- - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
- operations (if absent the value is the same as
- rx-fifo-size). For Axon, either absent or 2048.
- - tx-fifo-size-gige : 1 cell, Tx fifo size in bytes for 1000 Mb/sec
- operations (if absent the value is the same as
- tx-fifo-size). For Axon, either absent or 2048.
- - tah-device : 1 cell, optional. If connected to a TAH engine for
- offload, phandle of the TAH device node.
- - tah-channel : 1 cell, optional. If appropriate, channel used on the
- TAH engine.
-
- Example:
-
- EMAC0: ethernet@40000800 {
- device_type = "network";
- compatible = "ibm,emac-440gp", "ibm,emac";
- interrupt-parent = <&UIC1>;
- interrupts = <1c 4 1d 4>;
- reg = <40000800 70>;
- local-mac-address = [00 04 AC E3 1B 1E];
- mal-device = <&MAL0>;
- mal-tx-channel = <0 1>;
- mal-rx-channel = <0>;
- cell-index = <0>;
- max-frame-size = <5dc>;
- rx-fifo-size = <1000>;
- tx-fifo-size = <800>;
- phy-mode = "rmii";
- phy-map = <00000001>;
- zmii-device = <&ZMII0>;
- zmii-channel = <0>;
- };
-
- ii) McMAL node
-
- Required properties:
- - device_type : "dma-controller"
- - compatible : compatible list, containing 2 entries, first is
- "ibm,mcmal-CHIP" where CHIP is the host ASIC (like
- emac) and the second is either "ibm,mcmal" or
- "ibm,mcmal2".
- For Axon, "ibm,mcmal-axon","ibm,mcmal2"
- - interrupts : <interrupt mapping for the MAL interrupts sources:
- 5 sources: tx_eob, rx_eob, serr, txde, rxde>.
- For Axon: This is _different_ from the current
- firmware. We use the "delayed" interrupts for txeob
- and rxeob. Thus we end up with mapping those 5 MPIC
- interrupts, all level positive sensitive: 10, 11, 32,
- 33, 34 (in decimal)
- - dcr-reg : < DCR registers range >
- - dcr-parent : if needed for dcr-reg
- - num-tx-chans : 1 cell, number of Tx channels
- - num-rx-chans : 1 cell, number of Rx channels
-
- iii) ZMII node
-
- Required properties:
- - compatible : compatible list, containing 2 entries, first is
- "ibm,zmii-CHIP" where CHIP is the host ASIC (like
- EMAC) and the second is "ibm,zmii".
- For Axon, there is no ZMII node.
- - reg : <registers mapping>
-
- iv) RGMII node
-
- Required properties:
- - compatible : compatible list, containing 2 entries, first is
- "ibm,rgmii-CHIP" where CHIP is the host ASIC (like
- EMAC) and the second is "ibm,rgmii".
- For Axon, "ibm,rgmii-axon","ibm,rgmii"
- - reg : <registers mapping>
- - revision : as provided by the RGMII new version register if
- available.
- For Axon: 0x0000012a
-
+++ /dev/null
-AMCC NDFC (NanD Flash Controller)
-
-Required properties:
-- compatible : "ibm,ndfc".
-- reg : should specify chip select and size used for the chip (0x2000).
-
-Optional properties:
-- ccr : NDFC config and control register value (default 0).
-- bank-settings : NDFC bank configuration register value (default 0).
-
-Notes:
-- partition(s) - follows the OF MTD standard for partitions
-
-Example:
-
-ndfc@1,0 {
- compatible = "ibm,ndfc";
- reg = <0x00000001 0x00000000 0x00002000>;
- ccr = <0x00001000>;
- bank-settings = <0x80002222>;
- #address-cells = <1>;
- #size-cells = <1>;
-
- nand {
- #address-cells = <1>;
- #size-cells = <1>;
-
- partition@0 {
- label = "kernel";
- reg = <0x00000000 0x00200000>;
- };
- partition@200000 {
- label = "root";
- reg = <0x00200000 0x03E00000>;
- };
- };
-};
-
-
+++ /dev/null
-PPC440SPe DMA/XOR (DMA Controller and XOR Accelerator)
-
-Device nodes needed for operation of the ppc440spe-adma driver
-are specified hereby. These are I2O/DMA, DMA and XOR nodes
-for DMA engines and Memory Queue Module node. The latter is used
-by ADMA driver for configuration of RAID-6 H/W capabilities of
-the PPC440SPe. In addition to the nodes and properties described
-below, the ranges property of PLB node must specify ranges for
-DMA devices.
-
- i) The I2O node
-
- Required properties:
-
- - compatible : "ibm,i2o-440spe";
- - reg : <registers mapping>
- - dcr-reg : <DCR registers range>
-
- Example:
-
- I2O: i2o@400100000 {
- compatible = "ibm,i2o-440spe";
- reg = <0x00000004 0x00100000 0x100>;
- dcr-reg = <0x060 0x020>;
- };
-
-
- ii) The DMA node
-
- Required properties:
-
- - compatible : "ibm,dma-440spe";
- - cell-index : 1 cell, hardware index of the DMA engine
- (typically 0x0 and 0x1 for DMA0 and DMA1)
- - reg : <registers mapping>
- - dcr-reg : <DCR registers range>
- - interrupts : <interrupt mapping for DMA0/1 interrupts sources:
- 2 sources: DMAx CS FIFO Needs Service IRQ (on UIC0)
- and DMA Error IRQ (on UIC1). The latter is common
- for both DMA engines>.
- - interrupt-parent : needed for interrupt mapping
-
- Example:
-
- DMA0: dma0@400100100 {
- compatible = "ibm,dma-440spe";
- cell-index = <0>;
- reg = <0x00000004 0x00100100 0x100>;
- dcr-reg = <0x060 0x020>;
- interrupt-parent = <&DMA0>;
- interrupts = <0 1>;
- #interrupt-cells = <1>;
- #address-cells = <0>;
- #size-cells = <0>;
- interrupt-map = <
- 0 &UIC0 0x14 4
- 1 &UIC1 0x16 4>;
- };
-
-
- iii) XOR Accelerator node
-
- Required properties:
-
- - compatible : "amcc,xor-accelerator";
- - reg : <registers mapping>
- - interrupts : <interrupt mapping for XOR interrupt source>
- - interrupt-parent : for interrupt mapping
-
- Example:
-
- xor-accel@400200000 {
- compatible = "amcc,xor-accelerator";
- reg = <0x00000004 0x00200000 0x400>;
- interrupt-parent = <&UIC1>;
- interrupts = <0x1f 4>;
- };
-
-
- iv) Memory Queue Module node
-
- Required properties:
-
- - compatible : "ibm,mq-440spe";
- - dcr-reg : <DCR registers range>
-
- Example:
-
- MQ0: mq {
- compatible = "ibm,mq-440spe";
- dcr-reg = <0x040 0x020>;
- };
-
+++ /dev/null
-Reboot property to control system reboot on PPC4xx systems:
-
-By setting "reset_type" to one of the following values, the default
-software reset mechanism may be overidden. Here the possible values of
-"reset_type":
-
- 1 - PPC4xx core reset
- 2 - PPC4xx chip reset
- 3 - PPC4xx system reset (default)
-
-Example:
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,440SPe";
- ...
- reset-type = <2>; /* Use chip-reset */
- };
+++ /dev/null
-Memory mapped SJA1000 CAN controller from NXP (formerly Philips)
-
-Required properties:
-
-- compatible : should be "nxp,sja1000".
-
-- reg : should specify the chip select, address offset and size required
- to map the registers of the SJA1000. The size is usually 0x80.
-
-- interrupts: property with a value describing the interrupt source
- (number and sensitivity) required for the SJA1000.
-
-Optional properties:
-
-- nxp,external-clock-frequency : Frequency of the external oscillator
- clock in Hz. Note that the internal clock frequency used by the
- SJA1000 is half of that value. If not specified, a default value
- of 16000000 (16 MHz) is used.
-
-- nxp,tx-output-mode : operation mode of the TX output control logic:
- <0x0> : bi-phase output mode
- <0x1> : normal output mode (default)
- <0x2> : test output mode
- <0x3> : clock output mode
-
-- nxp,tx-output-config : TX output pin configuration:
- <0x01> : TX0 invert
- <0x02> : TX0 pull-down (default)
- <0x04> : TX0 pull-up
- <0x06> : TX0 push-pull
- <0x08> : TX1 invert
- <0x10> : TX1 pull-down
- <0x20> : TX1 pull-up
- <0x30> : TX1 push-pull
-
-- nxp,clock-out-frequency : clock frequency in Hz on the CLKOUT pin.
- If not specified or if the specified value is 0, the CLKOUT pin
- will be disabled.
-
-- nxp,no-comparator-bypass : Allows to disable the CAN input comperator.
-
-For futher information, please have a look to the SJA1000 data sheet.
-
-Examples:
-
-can@3,100 {
- compatible = "nxp,sja1000";
- reg = <3 0x100 0x80>;
- interrupts = <2 0>;
- interrupt-parent = <&mpic>;
- nxp,external-clock-frequency = <16000000>;
-};
-
+++ /dev/null
-=====================================================================
-E500 LAW & Coherency Module Device Tree Binding
-Copyright (C) 2009 Freescale Semiconductor Inc.
-=====================================================================
-
-Local Access Window (LAW) Node
-
-The LAW node represents the region of CCSR space where local access
-windows are configured. For ECM based devices this is the first 4k
-of CCSR space that includes CCSRBAR, ALTCBAR, ALTCAR, BPTR, and some
-number of local access windows as specified by fsl,num-laws.
-
-PROPERTIES
-
- - compatible
- Usage: required
- Value type: <string>
- Definition: Must include "fsl,ecm-law"
-
- - reg
- Usage: required
- Value type: <prop-encoded-array>
- Definition: A standard property. The value specifies the
- physical address offset and length of the CCSR space
- registers.
-
- - fsl,num-laws
- Usage: required
- Value type: <u32>
- Definition: The value specifies the number of local access
- windows for this device.
-
-=====================================================================
-
-E500 Coherency Module Node
-
-The E500 LAW node represents the region of CCSR space where ECM config
-and error reporting registers exist, this is the second 4k (0x1000)
-of CCSR space.
-
-PROPERTIES
-
- - compatible
- Usage: required
- Value type: <string>
- Definition: Must include "fsl,CHIP-ecm", "fsl,ecm" where
- CHIP is the processor (mpc8572, mpc8544, etc.)
-
- - reg
- Usage: required
- Value type: <prop-encoded-array>
- Definition: A standard property. The value specifies the
- physical address offset and length of the CCSR space
- registers.
-
- - interrupts
- Usage: required
- Value type: <prop-encoded-array>
-
- - interrupt-parent
- Usage: required
- Value type: <phandle>
-
-=====================================================================
+++ /dev/null
-EEPROMs (I2C)
-
-Required properties:
-
- - compatible : should be "<manufacturer>,<type>"
- If there is no specific driver for <manufacturer>, a generic
- driver based on <type> is selected. Possible types are:
- 24c00, 24c01, 24c02, 24c04, 24c08, 24c16, 24c32, 24c64,
- 24c128, 24c256, 24c512, 24c1024, spd
-
- - reg : the I2C address of the EEPROM
-
-Optional properties:
-
- - pagesize : the length of the pagesize for writing. Please consult the
- manual of your device, that value varies a lot. A wrong value
- may result in data loss! If not specified, a safety value of
- '1' is used which will be very slow.
-
- - read-only: this parameterless property disables writes to the eeprom
-
-Example:
-
-eeprom@52 {
- compatible = "atmel,24c32";
- reg = <0x52>;
- pagesize = <32>;
-};
+++ /dev/null
-* Freescale 83xx and 512x PCI bridges
-
-Freescale 83xx and 512x SOCs include the same pci bridge core.
-
-83xx/512x specific notes:
-- reg: should contain two address length tuples
- The first is for the internal pci bridge registers
- The second is for the pci config space access registers
-
-Example (MPC8313ERDB)
- pci0: pci@e0008500 {
- cell-index = <1>;
- interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
- interrupt-map = <
- /* IDSEL 0x0E -mini PCI */
- 0x7000 0x0 0x0 0x1 &ipic 18 0x8
- 0x7000 0x0 0x0 0x2 &ipic 18 0x8
- 0x7000 0x0 0x0 0x3 &ipic 18 0x8
- 0x7000 0x0 0x0 0x4 &ipic 18 0x8
-
- /* IDSEL 0x0F - PCI slot */
- 0x7800 0x0 0x0 0x1 &ipic 17 0x8
- 0x7800 0x0 0x0 0x2 &ipic 18 0x8
- 0x7800 0x0 0x0 0x3 &ipic 17 0x8
- 0x7800 0x0 0x0 0x4 &ipic 18 0x8>;
- interrupt-parent = <&ipic>;
- interrupts = <66 0x8>;
- bus-range = <0x0 0x0>;
- ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000
- 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000
- 0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>;
- clock-frequency = <66666666>;
- #interrupt-cells = <1>;
- #size-cells = <2>;
- #address-cells = <3>;
- reg = <0xe0008500 0x100 /* internal registers */
- 0xe0008300 0x8>; /* config space access registers */
- compatible = "fsl,mpc8349-pci";
- device_type = "pci";
- };
+++ /dev/null
-GPIO controllers on MPC8xxx SoCs
-
-This is for the non-QE/CPM/GUTs GPIO controllers as found on
-8349, 8572, 8610 and compatible.
-
-Every GPIO controller node must have #gpio-cells property defined,
-this information will be used to translate gpio-specifiers.
-
-Required properties:
-- compatible : "fsl,<CHIP>-gpio" followed by "fsl,mpc8349-gpio" for
- 83xx, "fsl,mpc8572-gpio" for 85xx and "fsl,mpc8610-gpio" for 86xx.
-- #gpio-cells : Should be two. The first cell is the pin number and the
- second cell is used to specify optional parameters (currently unused).
- - interrupts : Interrupt mapping for GPIO IRQ.
- - interrupt-parent : Phandle for the interrupt controller that
- services interrupts for this device.
-- gpio-controller : Marks the port as GPIO controller.
-
-Example of gpio-controller nodes for a MPC8347 SoC:
-
- gpio1: gpio-controller@c00 {
- #gpio-cells = <2>;
- compatible = "fsl,mpc8347-gpio", "fsl,mpc8349-gpio";
- reg = <0xc00 0x100>;
- interrupts = <74 0x8>;
- interrupt-parent = <&ipic>;
- gpio-controller;
- };
-
- gpio2: gpio-controller@d00 {
- #gpio-cells = <2>;
- compatible = "fsl,mpc8347-gpio", "fsl,mpc8349-gpio";
- reg = <0xd00 0x100>;
- interrupts = <75 0x8>;
- interrupt-parent = <&ipic>;
- gpio-controller;
- };
-
-See booting-without-of.txt for details of how to specify GPIO
-information for devices.
-
-To use GPIO pins as interrupt sources for peripherals, specify the
-GPIO controller as the interrupt parent and define GPIO number +
-trigger mode using the interrupts property, which is defined like
-this:
-
-interrupts = <number trigger>, where:
- - number: GPIO pin (0..31)
- - trigger: trigger mode:
- 2 = trigger on falling edge
- 3 = trigger on both edges
-
-Example of device using this is:
-
- funkyfpga@0 {
- compatible = "funky-fpga";
- ...
- interrupts = <4 3>;
- interrupt-parent = <&gpio1>;
- };
+++ /dev/null
-* Board Control and Status (BCSR)
-
-Required properties:
-
- - compatible : Should be "fsl,<board>-bcsr"
- - reg : Offset and length of the register set for the device
-
-Example:
-
- bcsr@f8000000 {
- compatible = "fsl,mpc8360mds-bcsr";
- reg = <f8000000 8000>;
- };
-
-* Freescale on board FPGA
-
-This is the memory-mapped registers for on board FPGA.
-
-Required properities:
-- compatible : should be "fsl,fpga-pixis".
-- reg : should contain the address and the length of the FPPGA register
- set.
-- interrupt-parent: should specify phandle for the interrupt controller.
-- interrupts : should specify event (wakeup) IRQ.
-
-Example (MPC8610HPCD):
-
- board-control@e8000000 {
- compatible = "fsl,fpga-pixis";
- reg = <0xe8000000 32>;
- interrupt-parent = <&mpic>;
- interrupts = <8 8>;
- };
-
-* Freescale BCSR GPIO banks
-
-Some BCSR registers act as simple GPIO controllers, each such
-register can be represented by the gpio-controller node.
-
-Required properities:
-- compatible : Should be "fsl,<board>-bcsr-gpio".
-- reg : Should contain the address and the length of the GPIO bank
- register.
-- #gpio-cells : Should be two. The first cell is the pin number and the
- second cell is used to specify optional parameters (currently unused).
-- gpio-controller : Marks the port as GPIO controller.
-
-Example:
-
- bcsr@1,0 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "fsl,mpc8360mds-bcsr";
- reg = <1 0 0x8000>;
- ranges = <0 1 0 0x8000>;
-
- bcsr13: gpio-controller@d {
- #gpio-cells = <2>;
- compatible = "fsl,mpc8360mds-bcsr-gpio";
- reg = <0xd 1>;
- gpio-controller;
- };
- };
+++ /dev/null
-CAN Device Tree Bindings
-------------------------
-
-(c) 2006-2009 Secret Lab Technologies Ltd
-Grant Likely <grant.likely@secretlab.ca>
-
-fsl,mpc5200-mscan nodes
------------------------
-In addition to the required compatible-, reg- and interrupt-properties, you can
-also specify which clock source shall be used for the controller:
-
-- fsl,mscan-clock-source : a string describing the clock source. Valid values
- are: "ip" for ip bus clock
- "ref" for reference clock (XTAL)
- "ref" is default in case this property is not
- present.
-
-fsl,mpc5121-mscan nodes
------------------------
-In addition to the required compatible-, reg- and interrupt-properties, you can
-also specify which clock source and divider shall be used for the controller:
-
-- fsl,mscan-clock-source : a string describing the clock source. Valid values
- are: "ip" for ip bus clock
- "ref" for reference clock
- "sys" for system clock
- If this property is not present, an optimal CAN
- clock source and frequency based on the system
- clock will be selected. If this is not possible,
- the reference clock will be used.
-
-- fsl,mscan-clock-divider: for the reference and system clock, an additional
- clock divider can be specified. By default, a
- value of 1 is used.
-
-Note that the MPC5121 Rev. 1 processor is not supported.
-
-Examples:
- can@1300 {
- compatible = "fsl,mpc5121-mscan";
- interrupts = <12 0x8>;
- interrupt-parent = <&ipic>;
- reg = <0x1300 0x80>;
- };
-
- can@1380 {
- compatible = "fsl,mpc5121-mscan";
- interrupts = <13 0x8>;
- interrupt-parent = <&ipic>;
- reg = <0x1380 0x80>;
- fsl,mscan-clock-source = "ref";
- fsl,mscan-clock-divider = <3>;
- };
+++ /dev/null
-* Freescale Communications Processor Module
-
-NOTE: This is an interim binding, and will likely change slightly,
-as more devices are supported. The QE bindings especially are
-incomplete.
-
-* Root CPM node
-
-Properties:
-- compatible : "fsl,cpm1", "fsl,cpm2", or "fsl,qe".
-- reg : A 48-byte region beginning with CPCR.
-
-Example:
- cpm@119c0 {
- #address-cells = <1>;
- #size-cells = <1>;
- #interrupt-cells = <2>;
- compatible = "fsl,mpc8272-cpm", "fsl,cpm2";
- reg = <119c0 30>;
- }
-
-* Properties common to multiple CPM/QE devices
-
-- fsl,cpm-command : This value is ORed with the opcode and command flag
- to specify the device on which a CPM command operates.
-
-- fsl,cpm-brg : Indicates which baud rate generator the device
- is associated with. If absent, an unused BRG
- should be dynamically allocated. If zero, the
- device uses an external clock rather than a BRG.
-
-- reg : Unless otherwise specified, the first resource represents the
- scc/fcc/ucc registers, and the second represents the device's
- parameter RAM region (if it has one).
-
-* Multi-User RAM (MURAM)
-
-The multi-user/dual-ported RAM is expressed as a bus under the CPM node.
-
-Ranges must be set up subject to the following restrictions:
-
-- Children's reg nodes must be offsets from the start of all muram, even
- if the user-data area does not begin at zero.
-- If multiple range entries are used, the difference between the parent
- address and the child address must be the same in all, so that a single
- mapping can cover them all while maintaining the ability to determine
- CPM-side offsets with pointer subtraction. It is recommended that
- multiple range entries not be used.
-- A child address of zero must be translatable, even if no reg resources
- contain it.
-
-A child "data" node must exist, compatible with "fsl,cpm-muram-data", to
-indicate the portion of muram that is usable by the OS for arbitrary
-purposes. The data node may have an arbitrary number of reg resources,
-all of which contribute to the allocatable muram pool.
-
-Example, based on mpc8272:
- muram@0 {
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0 0 10000>;
-
- data@0 {
- compatible = "fsl,cpm-muram-data";
- reg = <0 2000 9800 800>;
- };
- };
+++ /dev/null
-* Baud Rate Generators
-
-Currently defined compatibles:
-fsl,cpm-brg
-fsl,cpm1-brg
-fsl,cpm2-brg
-
-Properties:
-- reg : There may be an arbitrary number of reg resources; BRG
- numbers are assigned to these in order.
-- clock-frequency : Specifies the base frequency driving
- the BRG.
-
-Example:
- brg@119f0 {
- compatible = "fsl,mpc8272-brg",
- "fsl,cpm2-brg",
- "fsl,cpm-brg";
- reg = <119f0 10 115f0 10>;
- clock-frequency = <d#25000000>;
- };
+++ /dev/null
-* I2C
-
-The I2C controller is expressed as a bus under the CPM node.
-
-Properties:
-- compatible : "fsl,cpm1-i2c", "fsl,cpm2-i2c"
-- reg : On CPM2 devices, the second resource doesn't specify the I2C
- Parameter RAM itself, but the I2C_BASE field of the CPM2 Parameter RAM
- (typically 0x8afc 0x2).
-- #address-cells : Should be one. The cell is the i2c device address with
- the r/w bit set to zero.
-- #size-cells : Should be zero.
-- clock-frequency : Can be used to set the i2c clock frequency. If
- unspecified, a default frequency of 60kHz is being used.
-The following two properties are deprecated. They are only used by legacy
-i2c drivers to find the bus to probe:
-- linux,i2c-index : Can be used to hard code an i2c bus number. By default,
- the bus number is dynamically assigned by the i2c core.
-- linux,i2c-class : Can be used to override the i2c class. The class is used
- by legacy i2c device drivers to find a bus in a specific context like
- system management, video or sound. By default, I2C_CLASS_HWMON (1) is
- being used. The definition of the classes can be found in
- include/i2c/i2c.h
-
-Example, based on mpc823:
-
- i2c@860 {
- compatible = "fsl,mpc823-i2c",
- "fsl,cpm1-i2c";
- reg = <0x860 0x20 0x3c80 0x30>;
- interrupts = <16>;
- interrupt-parent = <&CPM_PIC>;
- fsl,cpm-command = <0x10>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- rtc@68 {
- compatible = "dallas,ds1307";
- reg = <0x68>;
- };
- };
+++ /dev/null
-* Interrupt Controllers
-
-Currently defined compatibles:
-- fsl,cpm1-pic
- - only one interrupt cell
-- fsl,pq1-pic
-- fsl,cpm2-pic
- - second interrupt cell is level/sense:
- - 2 is falling edge
- - 8 is active low
-
-Example:
- interrupt-controller@10c00 {
- #interrupt-cells = <2>;
- interrupt-controller;
- reg = <10c00 80>;
- compatible = "mpc8272-pic", "fsl,cpm2-pic";
- };
+++ /dev/null
-* USB (Universal Serial Bus Controller)
-
-Properties:
-- compatible : "fsl,cpm1-usb", "fsl,cpm2-usb", "fsl,qe-usb"
-
-Example:
- usb@11bc0 {
- #address-cells = <1>;
- #size-cells = <0>;
- compatible = "fsl,cpm2-usb";
- reg = <11b60 18 8b00 100>;
- interrupts = <b 8>;
- interrupt-parent = <&PIC>;
- fsl,cpm-command = <2e600000>;
- };
+++ /dev/null
-Every GPIO controller node must have #gpio-cells property defined,
-this information will be used to translate gpio-specifiers.
-
-On CPM1 devices, all ports are using slightly different register layouts.
-Ports A, C and D are 16bit ports and Ports B and E are 32bit ports.
-
-On CPM2 devices, all ports are 32bit ports and use a common register layout.
-
-Required properties:
-- compatible : "fsl,cpm1-pario-bank-a", "fsl,cpm1-pario-bank-b",
- "fsl,cpm1-pario-bank-c", "fsl,cpm1-pario-bank-d",
- "fsl,cpm1-pario-bank-e", "fsl,cpm2-pario-bank"
-- #gpio-cells : Should be two. The first cell is the pin number and the
- second cell is used to specify optional parameters (currently unused).
-- gpio-controller : Marks the port as GPIO controller.
-
-Example of three SOC GPIO banks defined as gpio-controller nodes:
-
- CPM1_PIO_A: gpio-controller@950 {
- #gpio-cells = <2>;
- compatible = "fsl,cpm1-pario-bank-a";
- reg = <0x950 0x10>;
- gpio-controller;
- };
-
- CPM1_PIO_B: gpio-controller@ab8 {
- #gpio-cells = <2>;
- compatible = "fsl,cpm1-pario-bank-b";
- reg = <0xab8 0x10>;
- gpio-controller;
- };
-
- CPM1_PIO_E: gpio-controller@ac8 {
- #gpio-cells = <2>;
- compatible = "fsl,cpm1-pario-bank-e";
- reg = <0xac8 0x18>;
- gpio-controller;
- };
+++ /dev/null
-* Network
-
-Currently defined compatibles:
-- fsl,cpm1-scc-enet
-- fsl,cpm2-scc-enet
-- fsl,cpm1-fec-enet
-- fsl,cpm2-fcc-enet (third resource is GFEMR)
-- fsl,qe-enet
-
-Example:
-
- ethernet@11300 {
- device_type = "network";
- compatible = "fsl,mpc8272-fcc-enet",
- "fsl,cpm2-fcc-enet";
- reg = <11300 20 8400 100 11390 1>;
- local-mac-address = [ 00 00 00 00 00 00 ];
- interrupts = <20 8>;
- interrupt-parent = <&PIC>;
- phy-handle = <&PHY0>;
- fsl,cpm-command = <12000300>;
- };
-
-* MDIO
-
-Currently defined compatibles:
-fsl,pq1-fec-mdio (reg is same as first resource of FEC device)
-fsl,cpm2-mdio-bitbang (reg is port C registers)
-
-Properties for fsl,cpm2-mdio-bitbang:
-fsl,mdio-pin : pin of port C controlling mdio data
-fsl,mdc-pin : pin of port C controlling mdio clock
-
-Example:
- mdio@10d40 {
- device_type = "mdio";
- compatible = "fsl,mpc8272ads-mdio-bitbang",
- "fsl,mpc8272-mdio-bitbang",
- "fsl,cpm2-mdio-bitbang";
- reg = <10d40 14>;
- #address-cells = <1>;
- #size-cells = <0>;
- fsl,mdio-pin = <12>;
- fsl,mdc-pin = <13>;
- };
+++ /dev/null
-* Freescale QUICC Engine module (QE)
-This represents qe module that is installed on PowerQUICC II Pro.
-
-NOTE: This is an interim binding; it should be updated to fit
-in with the CPM binding later in this document.
-
-Basically, it is a bus of devices, that could act more or less
-as a complete entity (UCC, USB etc ). All of them should be siblings on
-the "root" qe node, using the common properties from there.
-The description below applies to the qe of MPC8360 and
-more nodes and properties would be extended in the future.
-
-i) Root QE device
-
-Required properties:
-- compatible : should be "fsl,qe";
-- model : precise model of the QE, Can be "QE", "CPM", or "CPM2"
-- reg : offset and length of the device registers.
-- bus-frequency : the clock frequency for QUICC Engine.
-- fsl,qe-num-riscs: define how many RISC engines the QE has.
-- fsl,qe-num-snums: define how many serial number(SNUM) the QE can use for the
- threads.
-
-Optional properties:
-- fsl,firmware-phandle:
- Usage: required only if there is no fsl,qe-firmware child node
- Value type: <phandle>
- Definition: Points to a firmware node (see "QE Firmware Node" below)
- that contains the firmware that should be uploaded for this QE.
- The compatible property for the firmware node should say,
- "fsl,qe-firmware".
-
-Recommended properties
-- brg-frequency : the internal clock source frequency for baud-rate
- generators in Hz.
-
-Example:
- qe@e0100000 {
- #address-cells = <1>;
- #size-cells = <1>;
- #interrupt-cells = <2>;
- compatible = "fsl,qe";
- ranges = <0 e0100000 00100000>;
- reg = <e0100000 480>;
- brg-frequency = <0>;
- bus-frequency = <179A7B00>;
- }
-
-* Multi-User RAM (MURAM)
-
-Required properties:
-- compatible : should be "fsl,qe-muram", "fsl,cpm-muram".
-- mode : the could be "host" or "slave".
-- ranges : Should be defined as specified in 1) to describe the
- translation of MURAM addresses.
-- data-only : sub-node which defines the address area under MURAM
- bus that can be allocated as data/parameter
-
-Example:
-
- muram@10000 {
- compatible = "fsl,qe-muram", "fsl,cpm-muram";
- ranges = <0 00010000 0000c000>;
-
- data-only@0{
- compatible = "fsl,qe-muram-data",
- "fsl,cpm-muram-data";
- reg = <0 c000>;
- };
- };
-
-* QE Firmware Node
-
-This node defines a firmware binary that is embedded in the device tree, for
-the purpose of passing the firmware from bootloader to the kernel, or from
-the hypervisor to the guest.
-
-The firmware node itself contains the firmware binary contents, a compatible
-property, and any firmware-specific properties. The node should be placed
-inside a QE node that needs it. Doing so eliminates the need for a
-fsl,firmware-phandle property. Other QE nodes that need the same firmware
-should define an fsl,firmware-phandle property that points to the firmware node
-in the first QE node.
-
-The fsl,firmware property can be specified in the DTS (possibly using incbin)
-or can be inserted by the boot loader at boot time.
-
-Required properties:
- - compatible
- Usage: required
- Value type: <string>
- Definition: A standard property. Specify a string that indicates what
- kind of firmware it is. For QE, this should be "fsl,qe-firmware".
-
- - fsl,firmware
- Usage: required
- Value type: <prop-encoded-array>, encoded as an array of bytes
- Definition: A standard property. This property contains the firmware
- binary "blob".
-
-Example:
- qe1@e0080000 {
- compatible = "fsl,qe";
- qe_firmware:qe-firmware {
- compatible = "fsl,qe-firmware";
- fsl,firmware = [0x70 0xcd 0x00 0x00 0x01 0x46 0x45 ...];
- };
- ...
- };
-
- qe2@e0090000 {
- compatible = "fsl,qe";
- fsl,firmware-phandle = <&qe_firmware>;
- ...
- };
+++ /dev/null
-* Uploaded QE firmware
-
- If a new firmware has been uploaded to the QE (usually by the
- boot loader), then a 'firmware' child node should be added to the QE
- node. This node provides information on the uploaded firmware that
- device drivers may need.
-
- Required properties:
- - id: The string name of the firmware. This is taken from the 'id'
- member of the qe_firmware structure of the uploaded firmware.
- Device drivers can search this string to determine if the
- firmware they want is already present.
- - extended-modes: The Extended Modes bitfield, taken from the
- firmware binary. It is a 64-bit number represented
- as an array of two 32-bit numbers.
- - virtual-traps: The virtual traps, taken from the firmware binary.
- It is an array of 8 32-bit numbers.
-
-Example:
- firmware {
- id = "Soft-UART";
- extended-modes = <0 0>;
- virtual-traps = <0 0 0 0 0 0 0 0>;
- };
+++ /dev/null
-* Parallel I/O Ports
-
-This node configures Parallel I/O ports for CPUs with QE support.
-The node should reside in the "soc" node of the tree. For each
-device that using parallel I/O ports, a child node should be created.
-See the definition of the Pin configuration nodes below for more
-information.
-
-Required properties:
-- device_type : should be "par_io".
-- reg : offset to the register set and its length.
-- num-ports : number of Parallel I/O ports
-
-Example:
-par_io@1400 {
- reg = <1400 100>;
- #address-cells = <1>;
- #size-cells = <0>;
- device_type = "par_io";
- num-ports = <7>;
- ucc_pin@01 {
- ......
- };
-
-Note that "par_io" nodes are obsolete, and should not be used for
-the new device trees. Instead, each Par I/O bank should be represented
-via its own gpio-controller node:
-
-Required properties:
-- #gpio-cells : should be "2".
-- compatible : should be "fsl,<chip>-qe-pario-bank",
- "fsl,mpc8323-qe-pario-bank".
-- reg : offset to the register set and its length.
-- gpio-controller : node to identify gpio controllers.
-
-Example:
- qe_pio_a: gpio-controller@1400 {
- #gpio-cells = <2>;
- compatible = "fsl,mpc8360-qe-pario-bank",
- "fsl,mpc8323-qe-pario-bank";
- reg = <0x1400 0x18>;
- gpio-controller;
- };
-
- qe_pio_e: gpio-controller@1460 {
- #gpio-cells = <2>;
- compatible = "fsl,mpc8360-qe-pario-bank",
- "fsl,mpc8323-qe-pario-bank";
- reg = <0x1460 0x18>;
- gpio-controller;
- };
+++ /dev/null
-* Pin configuration nodes
-
-Required properties:
-- linux,phandle : phandle of this node; likely referenced by a QE
- device.
-- pio-map : array of pin configurations. Each pin is defined by 6
- integers. The six numbers are respectively: port, pin, dir,
- open_drain, assignment, has_irq.
- - port : port number of the pin; 0-6 represent port A-G in UM.
- - pin : pin number in the port.
- - dir : direction of the pin, should encode as follows:
-
- 0 = The pin is disabled
- 1 = The pin is an output
- 2 = The pin is an input
- 3 = The pin is I/O
-
- - open_drain : indicates the pin is normal or wired-OR:
-
- 0 = The pin is actively driven as an output
- 1 = The pin is an open-drain driver. As an output, the pin is
- driven active-low, otherwise it is three-stated.
-
- - assignment : function number of the pin according to the Pin Assignment
- tables in User Manual. Each pin can have up to 4 possible functions in
- QE and two options for CPM.
- - has_irq : indicates if the pin is used as source of external
- interrupts.
-
-Example:
- ucc_pin@01 {
- linux,phandle = <140001>;
- pio-map = <
- /* port pin dir open_drain assignment has_irq */
- 0 3 1 0 1 0 /* TxD0 */
- 0 4 1 0 1 0 /* TxD1 */
- 0 5 1 0 1 0 /* TxD2 */
- 0 6 1 0 1 0 /* TxD3 */
- 1 6 1 0 3 0 /* TxD4 */
- 1 7 1 0 1 0 /* TxD5 */
- 1 9 1 0 2 0 /* TxD6 */
- 1 a 1 0 2 0 /* TxD7 */
- 0 9 2 0 1 0 /* RxD0 */
- 0 a 2 0 1 0 /* RxD1 */
- 0 b 2 0 1 0 /* RxD2 */
- 0 c 2 0 1 0 /* RxD3 */
- 0 d 2 0 1 0 /* RxD4 */
- 1 1 2 0 2 0 /* RxD5 */
- 1 0 2 0 2 0 /* RxD6 */
- 1 4 2 0 2 0 /* RxD7 */
- 0 7 1 0 1 0 /* TX_EN */
- 0 8 1 0 1 0 /* TX_ER */
- 0 f 2 0 1 0 /* RX_DV */
- 0 10 2 0 1 0 /* RX_ER */
- 0 0 2 0 1 0 /* RX_CLK */
- 2 9 1 0 3 0 /* GTX_CLK - CLK10 */
- 2 8 2 0 1 0>; /* GTX125 - CLK9 */
- };
-
-
+++ /dev/null
-* UCC (Unified Communications Controllers)
-
-Required properties:
-- device_type : should be "network", "hldc", "uart", "transparent"
- "bisync", "atm", or "serial".
-- compatible : could be "ucc_geth" or "fsl_atm" and so on.
-- cell-index : the ucc number(1-8), corresponding to UCCx in UM.
-- reg : Offset and length of the register set for the device
-- interrupts : <a b> where a is the interrupt number and b is a
- field that represents an encoding of the sense and level
- information for the interrupt. This should be encoded based on
- the information in section 2) depending on the type of interrupt
- controller you have.
-- interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
-- pio-handle : The phandle for the Parallel I/O port configuration.
-- port-number : for UART drivers, the port number to use, between 0 and 3.
- This usually corresponds to the /dev/ttyQE device, e.g. <0> = /dev/ttyQE0.
- The port number is added to the minor number of the device. Unlike the
- CPM UART driver, the port-number is required for the QE UART driver.
-- soft-uart : for UART drivers, if specified this means the QE UART device
- driver should use "Soft-UART" mode, which is needed on some SOCs that have
- broken UART hardware. Soft-UART is provided via a microcode upload.
-- rx-clock-name: the UCC receive clock source
- "none": clock source is disabled
- "brg1" through "brg16": clock source is BRG1-BRG16, respectively
- "clk1" through "clk24": clock source is CLK1-CLK24, respectively
-- tx-clock-name: the UCC transmit clock source
- "none": clock source is disabled
- "brg1" through "brg16": clock source is BRG1-BRG16, respectively
- "clk1" through "clk24": clock source is CLK1-CLK24, respectively
-The following two properties are deprecated. rx-clock has been replaced
-with rx-clock-name, and tx-clock has been replaced with tx-clock-name.
-Drivers that currently use the deprecated properties should continue to
-do so, in order to support older device trees, but they should be updated
-to check for the new properties first.
-- rx-clock : represents the UCC receive clock source.
- 0x00 : clock source is disabled;
- 0x1~0x10 : clock source is BRG1~BRG16 respectively;
- 0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
-- tx-clock: represents the UCC transmit clock source;
- 0x00 : clock source is disabled;
- 0x1~0x10 : clock source is BRG1~BRG16 respectively;
- 0x11~0x28: clock source is QE_CLK1~QE_CLK24 respectively.
-
-Required properties for network device_type:
-- mac-address : list of bytes representing the ethernet address.
-- phy-handle : The phandle for the PHY connected to this controller.
-
-Recommended properties:
-- phy-connection-type : a string naming the controller/PHY interface type,
- i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id" (Internal
- Delay), "rgmii-txid" (delay on TX only), "rgmii-rxid" (delay on RX only),
- "tbi", or "rtbi".
-
-Example:
- ucc@2000 {
- device_type = "network";
- compatible = "ucc_geth";
- cell-index = <1>;
- reg = <2000 200>;
- interrupts = <a0 0>;
- interrupt-parent = <700>;
- mac-address = [ 00 04 9f 00 23 23 ];
- rx-clock = "none";
- tx-clock = "clk9";
- phy-handle = <212000>;
- phy-connection-type = "gmii";
- pio-handle = <140001>;
- };
+++ /dev/null
-Freescale QUICC Engine USB Controller
-
-Required properties:
-- compatible : should be "fsl,<chip>-qe-usb", "fsl,mpc8323-qe-usb".
-- reg : the first two cells should contain usb registers location and
- length, the next two two cells should contain PRAM location and
- length.
-- interrupts : should contain USB interrupt.
-- interrupt-parent : interrupt source phandle.
-- fsl,fullspeed-clock : specifies the full speed USB clock source:
- "none": clock source is disabled
- "brg1" through "brg16": clock source is BRG1-BRG16, respectively
- "clk1" through "clk24": clock source is CLK1-CLK24, respectively
-- fsl,lowspeed-clock : specifies the low speed USB clock source:
- "none": clock source is disabled
- "brg1" through "brg16": clock source is BRG1-BRG16, respectively
- "clk1" through "clk24": clock source is CLK1-CLK24, respectively
-- hub-power-budget : USB power budget for the root hub, in mA.
-- gpios : should specify GPIOs in this order: USBOE, USBTP, USBTN, USBRP,
- USBRN, SPEED (optional), and POWER (optional).
-
-Example:
-
-usb@6c0 {
- compatible = "fsl,mpc8360-qe-usb", "fsl,mpc8323-qe-usb";
- reg = <0x6c0 0x40 0x8b00 0x100>;
- interrupts = <11>;
- interrupt-parent = <&qeic>;
- fsl,fullspeed-clock = "clk21";
- gpios = <&qe_pio_b 2 0 /* USBOE */
- &qe_pio_b 3 0 /* USBTP */
- &qe_pio_b 8 0 /* USBTN */
- &qe_pio_b 9 0 /* USBRP */
- &qe_pio_b 11 0 /* USBRN */
- &qe_pio_e 20 0 /* SPEED */
- &qe_pio_e 21 0 /* POWER */>;
-};
+++ /dev/null
-* Serial
-
-Currently defined compatibles:
-- fsl,cpm1-smc-uart
-- fsl,cpm2-smc-uart
-- fsl,cpm1-scc-uart
-- fsl,cpm2-scc-uart
-- fsl,qe-uart
-
-Modem control lines connected to GPIO controllers are listed in the gpios
-property as described in booting-without-of.txt, section IX.1 in the following
-order:
-
-CTS, RTS, DCD, DSR, DTR, and RI.
-
-The gpios property is optional and can be left out when control lines are
-not used.
-
-Example:
-
- serial@11a00 {
- device_type = "serial";
- compatible = "fsl,mpc8272-scc-uart",
- "fsl,cpm2-scc-uart";
- reg = <11a00 20 8000 100>;
- interrupts = <28 8>;
- interrupt-parent = <&PIC>;
- fsl,cpm-brg = <1>;
- fsl,cpm-command = <00800000>;
- gpios = <&gpio_c 15 0
- &gpio_d 29 0>;
- };
+++ /dev/null
-* Freescale Display Interface Unit
-
-The Freescale DIU is a LCD controller, with proper hardware, it can also
-drive DVI monitors.
-
-Required properties:
-- compatible : should be "fsl,diu" or "fsl,mpc5121-diu".
-- reg : should contain at least address and length of the DIU register
- set.
-- interrupts : one DIU interrupt should be described here.
-- interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
-
-Optional properties:
-- edid : verbatim EDID data block describing attached display.
- Data from the detailed timing descriptor will be used to
- program the display controller.
-
-Example (MPC8610HPCD):
- display@2c000 {
- compatible = "fsl,diu";
- reg = <0x2c000 100>;
- interrupts = <72 2>;
- interrupt-parent = <&mpic>;
- };
-
-Example for MPC5121:
- display@2100 {
- compatible = "fsl,mpc5121-diu";
- reg = <0x2100 0x100>;
- interrupts = <64 0x8>;
- interrupt-parent = <&ipic>;
- edid = [edid-data];
- };
+++ /dev/null
-* Freescale 83xx DMA Controller
-
-Freescale PowerPC 83xx have on chip general purpose DMA controllers.
-
-Required properties:
-
-- compatible : compatible list, contains 2 entries, first is
- "fsl,CHIP-dma", where CHIP is the processor
- (mpc8349, mpc8360, etc.) and the second is
- "fsl,elo-dma"
-- reg : <registers mapping for DMA general status reg>
-- ranges : Should be defined as specified in 1) to describe the
- DMA controller channels.
-- cell-index : controller index. 0 for controller @ 0x8100
-- interrupts : <interrupt mapping for DMA IRQ>
-- interrupt-parent : optional, if needed for interrupt mapping
-
-
-- DMA channel nodes:
- - compatible : compatible list, contains 2 entries, first is
- "fsl,CHIP-dma-channel", where CHIP is the processor
- (mpc8349, mpc8350, etc.) and the second is
- "fsl,elo-dma-channel". However, see note below.
- - reg : <registers mapping for channel>
- - cell-index : dma channel index starts at 0.
-
-Optional properties:
- - interrupts : <interrupt mapping for DMA channel IRQ>
- (on 83xx this is expected to be identical to
- the interrupts property of the parent node)
- - interrupt-parent : optional, if needed for interrupt mapping
-
-Example:
- dma@82a8 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "fsl,mpc8349-dma", "fsl,elo-dma";
- reg = <0x82a8 4>;
- ranges = <0 0x8100 0x1a4>;
- interrupt-parent = <&ipic>;
- interrupts = <71 8>;
- cell-index = <0>;
- dma-channel@0 {
- compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
- cell-index = <0>;
- reg = <0 0x80>;
- interrupt-parent = <&ipic>;
- interrupts = <71 8>;
- };
- dma-channel@80 {
- compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
- cell-index = <1>;
- reg = <0x80 0x80>;
- interrupt-parent = <&ipic>;
- interrupts = <71 8>;
- };
- dma-channel@100 {
- compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
- cell-index = <2>;
- reg = <0x100 0x80>;
- interrupt-parent = <&ipic>;
- interrupts = <71 8>;
- };
- dma-channel@180 {
- compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
- cell-index = <3>;
- reg = <0x180 0x80>;
- interrupt-parent = <&ipic>;
- interrupts = <71 8>;
- };
- };
-
-* Freescale 85xx/86xx DMA Controller
-
-Freescale PowerPC 85xx/86xx have on chip general purpose DMA controllers.
-
-Required properties:
-
-- compatible : compatible list, contains 2 entries, first is
- "fsl,CHIP-dma", where CHIP is the processor
- (mpc8540, mpc8540, etc.) and the second is
- "fsl,eloplus-dma"
-- reg : <registers mapping for DMA general status reg>
-- cell-index : controller index. 0 for controller @ 0x21000,
- 1 for controller @ 0xc000
-- ranges : Should be defined as specified in 1) to describe the
- DMA controller channels.
-
-- DMA channel nodes:
- - compatible : compatible list, contains 2 entries, first is
- "fsl,CHIP-dma-channel", where CHIP is the processor
- (mpc8540, mpc8560, etc.) and the second is
- "fsl,eloplus-dma-channel". However, see note below.
- - cell-index : dma channel index starts at 0.
- - reg : <registers mapping for channel>
- - interrupts : <interrupt mapping for DMA channel IRQ>
- - interrupt-parent : optional, if needed for interrupt mapping
-
-Example:
- dma@21300 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "fsl,mpc8540-dma", "fsl,eloplus-dma";
- reg = <0x21300 4>;
- ranges = <0 0x21100 0x200>;
- cell-index = <0>;
- dma-channel@0 {
- compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
- reg = <0 0x80>;
- cell-index = <0>;
- interrupt-parent = <&mpic>;
- interrupts = <20 2>;
- };
- dma-channel@80 {
- compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
- reg = <0x80 0x80>;
- cell-index = <1>;
- interrupt-parent = <&mpic>;
- interrupts = <21 2>;
- };
- dma-channel@100 {
- compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
- reg = <0x100 0x80>;
- cell-index = <2>;
- interrupt-parent = <&mpic>;
- interrupts = <22 2>;
- };
- dma-channel@180 {
- compatible = "fsl,mpc8540-dma-channel", "fsl,eloplus-dma-channel";
- reg = <0x180 0x80>;
- cell-index = <3>;
- interrupt-parent = <&mpic>;
- interrupts = <23 2>;
- };
- };
-
-Note on DMA channel compatible properties: The compatible property must say
-"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel" to be used by the Elo DMA
-driver (fsldma). Any DMA channel used by fsldma cannot be used by another
-DMA driver, such as the SSI sound drivers for the MPC8610. Therefore, any DMA
-channel that should be used for another driver should not use
-"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel". For the SSI drivers, for
-example, the compatible property should be "fsl,ssi-dma-channel". See ssi.txt
-for more information.
+++ /dev/null
-* Freescale Enhanced Secure Digital Host Controller (eSDHC)
-
-The Enhanced Secure Digital Host Controller provides an interface
-for MMC, SD, and SDIO types of memory cards.
-
-Required properties:
- - compatible : should be
- "fsl,<chip>-esdhc", "fsl,esdhc"
- - reg : should contain eSDHC registers location and length.
- - interrupts : should contain eSDHC interrupt.
- - interrupt-parent : interrupt source phandle.
- - clock-frequency : specifies eSDHC base clock frequency.
- - sdhci,wp-inverted : (optional) specifies that eSDHC controller
- reports inverted write-protect state;
- - sdhci,1-bit-only : (optional) specifies that a controller can
- only handle 1-bit data transfers.
- - sdhci,auto-cmd12: (optional) specifies that a controller can
- only handle auto CMD12.
-
-Example:
-
-sdhci@2e000 {
- compatible = "fsl,mpc8378-esdhc", "fsl,esdhc";
- reg = <0x2e000 0x1000>;
- interrupts = <42 0x8>;
- interrupt-parent = <&ipic>;
- /* Filled in by U-Boot */
- clock-frequency = <0>;
-};
+++ /dev/null
-* Freescale General-purpose Timers Module
-
-Required properties:
- - compatible : should be
- "fsl,<chip>-gtm", "fsl,gtm" for SOC GTMs
- "fsl,<chip>-qe-gtm", "fsl,qe-gtm", "fsl,gtm" for QE GTMs
- "fsl,<chip>-cpm2-gtm", "fsl,cpm2-gtm", "fsl,gtm" for CPM2 GTMs
- - reg : should contain gtm registers location and length (0x40).
- - interrupts : should contain four interrupts.
- - interrupt-parent : interrupt source phandle.
- - clock-frequency : specifies the frequency driving the timer.
-
-Example:
-
-timer@500 {
- compatible = "fsl,mpc8360-gtm", "fsl,gtm";
- reg = <0x500 0x40>;
- interrupts = <90 8 78 8 84 8 72 8>;
- interrupt-parent = <&ipic>;
- /* filled by u-boot */
- clock-frequency = <0>;
-};
-
-timer@440 {
- compatible = "fsl,mpc8360-qe-gtm", "fsl,qe-gtm", "fsl,gtm";
- reg = <0x440 0x40>;
- interrupts = <12 13 14 15>;
- interrupt-parent = <&qeic>;
- /* filled by u-boot */
- clock-frequency = <0>;
-};
+++ /dev/null
-* Global Utilities Block
-
-The global utilities block controls power management, I/O device
-enabling, power-on-reset configuration monitoring, general-purpose
-I/O signal configuration, alternate function selection for multiplexed
-signals, and clock control.
-
-Required properties:
-
- - compatible : Should define the compatible device type for
- global-utilities.
- - reg : Offset and length of the register set for the device.
-
-Recommended properties:
-
- - fsl,has-rstcr : Indicates that the global utilities register set
- contains a functioning "reset control register" (i.e. the board
- is wired to reset upon setting the HRESET_REQ bit in this register).
-
-Example:
- global-utilities@e0000 { /* global utilities block */
- compatible = "fsl,mpc8548-guts";
- reg = <e0000 1000>;
- fsl,has-rstcr;
- };
+++ /dev/null
-* I2C
-
-Required properties :
-
- - reg : Offset and length of the register set for the device
- - compatible : should be "fsl,CHIP-i2c" where CHIP is the name of a
- compatible processor, e.g. mpc8313, mpc8543, mpc8544, mpc5121,
- mpc5200 or mpc5200b. For the mpc5121, an additional node
- "fsl,mpc5121-i2c-ctrl" is required as shown in the example below.
-
-Recommended properties :
-
- - interrupts : <a b> where a is the interrupt number and b is a
- field that represents an encoding of the sense and level
- information for the interrupt. This should be encoded based on
- the information in section 2) depending on the type of interrupt
- controller you have.
- - interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
- - fsl,preserve-clocking : boolean; if defined, the clock settings
- from the bootloader are preserved (not touched).
- - clock-frequency : desired I2C bus clock frequency in Hz.
- - fsl,timeout : I2C bus timeout in microseconds.
-
-Examples :
-
- /* MPC5121 based board */
- i2c@1740 {
- #address-cells = <1>;
- #size-cells = <0>;
- compatible = "fsl,mpc5121-i2c", "fsl-i2c";
- reg = <0x1740 0x20>;
- interrupts = <11 0x8>;
- interrupt-parent = <&ipic>;
- clock-frequency = <100000>;
- };
-
- i2ccontrol@1760 {
- compatible = "fsl,mpc5121-i2c-ctrl";
- reg = <0x1760 0x8>;
- };
-
- /* MPC5200B based board */
- i2c@3d00 {
- #address-cells = <1>;
- #size-cells = <0>;
- compatible = "fsl,mpc5200b-i2c","fsl,mpc5200-i2c","fsl-i2c";
- reg = <0x3d00 0x40>;
- interrupts = <2 15 0>;
- interrupt-parent = <&mpc5200_pic>;
- fsl,preserve-clocking;
- };
-
- /* MPC8544 base board */
- i2c@3100 {
- #address-cells = <1>;
- #size-cells = <0>;
- compatible = "fsl,mpc8544-i2c", "fsl-i2c";
- reg = <0x3100 0x100>;
- interrupts = <43 2>;
- interrupt-parent = <&mpic>;
- clock-frequency = <400000>;
- fsl,timeout = <10000>;
- };
+++ /dev/null
-* Chipselect/Local Bus
-
-Properties:
-- name : Should be localbus
-- #address-cells : Should be either two or three. The first cell is the
- chipselect number, and the remaining cells are the
- offset into the chipselect.
-- #size-cells : Either one or two, depending on how large each chipselect
- can be.
-- ranges : Each range corresponds to a single chipselect, and cover
- the entire access window as configured.
-
-Example:
- localbus@f0010100 {
- compatible = "fsl,mpc8272-localbus",
- "fsl,pq2-localbus";
- #address-cells = <2>;
- #size-cells = <1>;
- reg = <f0010100 40>;
-
- ranges = <0 0 fe000000 02000000
- 1 0 f4500000 00008000>;
-
- flash@0,0 {
- compatible = "jedec-flash";
- reg = <0 0 2000000>;
- bank-width = <4>;
- device-width = <1>;
- };
-
- board-control@1,0 {
- reg = <1 0 20>;
- compatible = "fsl,mpc8272ads-bcsr";
- };
- };
+++ /dev/null
-=====================================================================
-MPX LAW & Coherency Module Device Tree Binding
-Copyright (C) 2009 Freescale Semiconductor Inc.
-=====================================================================
-
-Local Access Window (LAW) Node
-
-The LAW node represents the region of CCSR space where local access
-windows are configured. For MCM based devices this is the first 4k
-of CCSR space that includes CCSRBAR, ALTCBAR, ALTCAR, BPTR, and some
-number of local access windows as specified by fsl,num-laws.
-
-PROPERTIES
-
- - compatible
- Usage: required
- Value type: <string>
- Definition: Must include "fsl,mcm-law"
-
- - reg
- Usage: required
- Value type: <prop-encoded-array>
- Definition: A standard property. The value specifies the
- physical address offset and length of the CCSR space
- registers.
-
- - fsl,num-laws
- Usage: required
- Value type: <u32>
- Definition: The value specifies the number of local access
- windows for this device.
-
-=====================================================================
-
-MPX Coherency Module Node
-
-The MPX LAW node represents the region of CCSR space where MCM config
-and error reporting registers exist, this is the second 4k (0x1000)
-of CCSR space.
-
-PROPERTIES
-
- - compatible
- Usage: required
- Value type: <string>
- Definition: Must include "fsl,CHIP-mcm", "fsl,mcm" where
- CHIP is the processor (mpc8641, mpc8610, etc.)
-
- - reg
- Usage: required
- Value type: <prop-encoded-array>
- Definition: A standard property. The value specifies the
- physical address offset and length of the CCSR space
- registers.
-
- - interrupts
- Usage: required
- Value type: <prop-encoded-array>
-
- - interrupt-parent
- Usage: required
- Value type: <phandle>
-
-=====================================================================
+++ /dev/null
-Freescale MPC8349E-mITX-compatible Power Management Micro Controller Unit (MCU)
-
-Required properties:
-- compatible : "fsl,<mcu-chip>-<board>", "fsl,mcu-mpc8349emitx".
-- reg : should specify I2C address (0x0a).
-- #gpio-cells : should be 2.
-- gpio-controller : should be present.
-
-Example:
-
-mcu@0a {
- #gpio-cells = <2>;
- compatible = "fsl,mc9s08qg8-mpc8349emitx",
- "fsl,mcu-mpc8349emitx";
- reg = <0x0a>;
- gpio-controller;
-};
+++ /dev/null
-MPC5121 PSC Device Tree Bindings
-
-PSC in UART mode
-----------------
-
-For PSC in UART mode the needed PSC serial devices
-are specified by fsl,mpc5121-psc-uart nodes in the
-fsl,mpc5121-immr SoC node. Additionally the PSC FIFO
-Controller node fsl,mpc5121-psc-fifo is requered there:
-
-fsl,mpc5121-psc-uart nodes
---------------------------
-
-Required properties :
- - compatible : Should contain "fsl,mpc5121-psc-uart" and "fsl,mpc5121-psc"
- - cell-index : Index of the PSC in hardware
- - reg : Offset and length of the register set for the PSC device
- - interrupts : <a b> where a is the interrupt number of the
- PSC FIFO Controller and b is a field that represents an
- encoding of the sense and level information for the interrupt.
- - interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
-
-Recommended properties :
- - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
- - fsl,tx-fifo-size : the size of the TX fifo slice (a multiple of 4)
-
-
-fsl,mpc5121-psc-fifo node
--------------------------
-
-Required properties :
- - compatible : Should be "fsl,mpc5121-psc-fifo"
- - reg : Offset and length of the register set for the PSC
- FIFO Controller
- - interrupts : <a b> where a is the interrupt number of the
- PSC FIFO Controller and b is a field that represents an
- encoding of the sense and level information for the interrupt.
- - interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
-
-
-Example for a board using PSC0 and PSC1 devices in serial mode:
-
-serial@11000 {
- compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
- cell-index = <0>;
- reg = <0x11000 0x100>;
- interrupts = <40 0x8>;
- interrupt-parent = < &ipic >;
- fsl,rx-fifo-size = <16>;
- fsl,tx-fifo-size = <16>;
-};
-
-serial@11100 {
- compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
- cell-index = <1>;
- reg = <0x11100 0x100>;
- interrupts = <40 0x8>;
- interrupt-parent = < &ipic >;
- fsl,rx-fifo-size = <16>;
- fsl,tx-fifo-size = <16>;
-};
-
-pscfifo@11f00 {
- compatible = "fsl,mpc5121-psc-fifo";
- reg = <0x11f00 0x100>;
- interrupts = <40 0x8>;
- interrupt-parent = < &ipic >;
-};
+++ /dev/null
-MPC5200 Device Tree Bindings
-----------------------------
-
-(c) 2006-2009 Secret Lab Technologies Ltd
-Grant Likely <grant.likely@secretlab.ca>
-
-Naming conventions
-------------------
-For mpc5200 on-chip devices, the format for each compatible value is
-<chip>-<device>[-<mode>]. The OS should be able to match a device driver
-to the device based solely on the compatible value. If two drivers
-match on the compatible list; the 'most compatible' driver should be
-selected.
-
-The split between the MPC5200 and the MPC5200B leaves a bit of a
-conundrum. How should the compatible property be set up to provide
-maximum compatibility information; but still accurately describe the
-chip? For the MPC5200; the answer is easy. Most of the SoC devices
-originally appeared on the MPC5200. Since they didn't exist anywhere
-else; the 5200 compatible properties will contain only one item;
-"fsl,mpc5200-<device>".
-
-The 5200B is almost the same as the 5200, but not quite. It fixes
-silicon bugs and it adds a small number of enhancements. Most of the
-devices either provide exactly the same interface as on the 5200. A few
-devices have extra functions but still have a backwards compatible mode.
-To express this information as completely as possible, 5200B device trees
-should have two items in the compatible list:
- compatible = "fsl,mpc5200b-<device>","fsl,mpc5200-<device>";
-
-It is *strongly* recommended that 5200B device trees follow this convention
-(instead of only listing the base mpc5200 item).
-
-ie. ethernet on mpc5200: compatible = "fsl,mpc5200-fec";
- ethernet on mpc5200b: compatible = "fsl,mpc5200b-fec", "fsl,mpc5200-fec";
-
-Modal devices, like PSCs, also append the configured function to the
-end of the compatible field. ie. A PSC in i2s mode would specify
-"fsl,mpc5200-psc-i2s", not "fsl,mpc5200-i2s". This convention is chosen to
-avoid naming conflicts with non-psc devices providing the same
-function. For example, "fsl,mpc5200-spi" and "fsl,mpc5200-psc-spi" describe
-the mpc5200 simple spi device and a PSC spi mode respectively.
-
-At the time of writing, exact chip may be either 'fsl,mpc5200' or
-'fsl,mpc5200b'.
-
-The soc node
-------------
-This node describes the on chip SOC peripherals. Every mpc5200 based
-board will have this node, and as such there is a common naming
-convention for SOC devices.
-
-Required properties:
-name description
----- -----------
-ranges Memory range of the internal memory mapped registers.
- Should be <0 [baseaddr] 0xc000>
-reg Should be <[baseaddr] 0x100>
-compatible mpc5200: "fsl,mpc5200-immr"
- mpc5200b: "fsl,mpc5200b-immr"
-system-frequency 'fsystem' frequency in Hz; XLB, IPB, USB and PCI
- clocks are derived from the fsystem clock.
-bus-frequency IPB bus frequency in Hz. Clock rate
- used by most of the soc devices.
-
-soc child nodes
----------------
-Any on chip SOC devices available to Linux must appear as soc5200 child nodes.
-
-Note: The tables below show the value for the mpc5200. A mpc5200b device
-tree should use the "fsl,mpc5200b-<device>","fsl,mpc5200-<device>" form.
-
-Required soc5200 child nodes:
-name compatible Description
----- ---------- -----------
-cdm@<addr> fsl,mpc5200-cdm Clock Distribution
-interrupt-controller@<addr> fsl,mpc5200-pic need an interrupt
- controller to boot
-bestcomm@<addr> fsl,mpc5200-bestcomm Bestcomm DMA controller
-
-Recommended soc5200 child nodes; populate as needed for your board
-name compatible Description
----- ---------- -----------
-timer@<addr> fsl,mpc5200-gpt General purpose timers
-gpio@<addr> fsl,mpc5200-gpio MPC5200 simple gpio controller
-gpio@<addr> fsl,mpc5200-gpio-wkup MPC5200 wakeup gpio controller
-rtc@<addr> fsl,mpc5200-rtc Real time clock
-mscan@<addr> fsl,mpc5200-mscan CAN bus controller
-pci@<addr> fsl,mpc5200-pci PCI bridge
-serial@<addr> fsl,mpc5200-psc-uart PSC in serial mode
-i2s@<addr> fsl,mpc5200-psc-i2s PSC in i2s mode
-ac97@<addr> fsl,mpc5200-psc-ac97 PSC in ac97 mode
-spi@<addr> fsl,mpc5200-psc-spi PSC in spi mode
-irda@<addr> fsl,mpc5200-psc-irda PSC in IrDA mode
-spi@<addr> fsl,mpc5200-spi MPC5200 spi device
-ethernet@<addr> fsl,mpc5200-fec MPC5200 ethernet device
-ata@<addr> fsl,mpc5200-ata IDE ATA interface
-i2c@<addr> fsl,mpc5200-i2c I2C controller
-usb@<addr> fsl,mpc5200-ohci,ohci-be USB controller
-xlb@<addr> fsl,mpc5200-xlb XLB arbitrator
-
-fsl,mpc5200-gpt nodes
----------------------
-On the mpc5200 and 5200b, GPT0 has a watchdog timer function. If the board
-design supports the internal wdt, then the device node for GPT0 should
-include the empty property 'fsl,has-wdt'. Note that this does not activate
-the watchdog. The timer will function as a GPT if the timer api is used, and
-it will function as watchdog if the watchdog device is used. The watchdog
-mode has priority over the gpt mode, i.e. if the watchdog is activated, any
-gpt api call to this timer will fail with -EBUSY.
-
-If you add the property
- fsl,wdt-on-boot = <n>;
-GPT0 will be marked as in-use watchdog, i.e. blocking every gpt access to it.
-If n>0, the watchdog is started with a timeout of n seconds. If n=0, the
-configuration of the watchdog is not touched. This is useful in two cases:
-- just mark GPT0 as watchdog, blocking gpt accesses, and configure it later;
-- do not touch a configuration assigned by the boot loader which supervises
- the boot process itself.
-
-The watchdog will respect the CONFIG_WATCHDOG_NOWAYOUT option.
-
-An mpc5200-gpt can be used as a single line GPIO controller. To do so,
-add the following properties to the gpt node:
- gpio-controller;
- #gpio-cells = <2>;
-When referencing the GPIO line from another node, the first cell must always
-be zero and the second cell represents the gpio flags and described in the
-gpio device tree binding.
-
-An mpc5200-gpt can be used as a single line edge sensitive interrupt
-controller. To do so, add the following properties to the gpt node:
- interrupt-controller;
- #interrupt-cells = <1>;
-When referencing the IRQ line from another node, the cell represents the
-sense mode; 1 for edge rising, 2 for edge falling.
-
-fsl,mpc5200-psc nodes
----------------------
-The PSCs should include a cell-index which is the index of the PSC in
-hardware. cell-index is used to determine which shared SoC registers to
-use when setting up PSC clocking. cell-index number starts at '0'. ie:
- PSC1 has 'cell-index = <0>'
- PSC4 has 'cell-index = <3>'
-
-PSC in i2s mode: The mpc5200 and mpc5200b PSCs are not compatible when in
-i2s mode. An 'mpc5200b-psc-i2s' node cannot include 'mpc5200-psc-i2s' in the
-compatible field.
-
-
-fsl,mpc5200-gpio and fsl,mpc5200-gpio-wkup nodes
-------------------------------------------------
-Each GPIO controller node should have the empty property gpio-controller and
-#gpio-cells set to 2. First cell is the GPIO number which is interpreted
-according to the bit numbers in the GPIO control registers. The second cell
-is for flags which is currently unused.
-
-fsl,mpc5200-fec nodes
----------------------
-The FEC node can specify one of the following properties to configure
-the MII link:
-- fsl,7-wire-mode - An empty property that specifies the link uses 7-wire
- mode instead of MII
-- current-speed - Specifies that the MII should be configured for a fixed
- speed. This property should contain two cells. The
- first cell specifies the speed in Mbps and the second
- should be '0' for half duplex and '1' for full duplex
-- phy-handle - Contains a phandle to an Ethernet PHY.
-
-Interrupt controller (fsl,mpc5200-pic) node
--------------------------------------------
-The mpc5200 pic binding splits hardware IRQ numbers into two levels. The
-split reflects the layout of the PIC hardware itself, which groups
-interrupts into one of three groups; CRIT, MAIN or PERP. Also, the
-Bestcomm dma engine has it's own set of interrupt sources which are
-cascaded off of peripheral interrupt 0, which the driver interprets as a
-fourth group, SDMA.
-
-The interrupts property for device nodes using the mpc5200 pic consists
-of three cells; <L1 L2 level>
-
- L1 := [CRIT=0, MAIN=1, PERP=2, SDMA=3]
- L2 := interrupt number; directly mapped from the value in the
- "ICTL PerStat, MainStat, CritStat Encoded Register"
- level := [LEVEL_HIGH=0, EDGE_RISING=1, EDGE_FALLING=2, LEVEL_LOW=3]
-
-For external IRQs, use the following interrupt property values (how to
-specify external interrupts is a frequently asked question):
-External interrupts:
- external irq0: interrupts = <0 0 n>;
- external irq1: interrupts = <1 1 n>;
- external irq2: interrupts = <1 2 n>;
- external irq3: interrupts = <1 3 n>;
-'n' is sense (0: level high, 1: edge rising, 2: edge falling 3: level low)
-
-fsl,mpc5200-mscan nodes
------------------------
-See file can.txt in this directory.
+++ /dev/null
-* OpenPIC and its interrupt numbers on Freescale's e500/e600 cores
-
-The OpenPIC specification does not specify which interrupt source has to
-become which interrupt number. This is up to the software implementation
-of the interrupt controller. The only requirement is that every
-interrupt source has to have an unique interrupt number / vector number.
-To accomplish this the current implementation assigns the number zero to
-the first source, the number one to the second source and so on until
-all interrupt sources have their unique number.
-Usually the assigned vector number equals the interrupt number mentioned
-in the documentation for a given core / CPU. This is however not true
-for the e500 cores (MPC85XX CPUs) where the documentation distinguishes
-between internal and external interrupt sources and starts counting at
-zero for both of them.
-
-So what to write for external interrupt source X or internal interrupt
-source Y into the device tree? Here is an example:
-
-The memory map for the interrupt controller in the MPC8544[0] shows,
-that the first interrupt source starts at 0x5_0000 (PIC Register Address
-Map-Interrupt Source Configuration Registers). This source becomes the
-number zero therefore:
- External interrupt 0 = interrupt number 0
- External interrupt 1 = interrupt number 1
- External interrupt 2 = interrupt number 2
- ...
-Every interrupt number allocates 0x20 bytes register space. So to get
-its number it is sufficient to shift the lower 16bits to right by five.
-So for the external interrupt 10 we have:
- 0x0140 >> 5 = 10
-
-After the external sources, the internal sources follow. The in core I2C
-controller on the MPC8544 for instance has the internal source number
-27. Oo obtain its interrupt number we take the lower 16bits of its memory
-address (0x5_0560) and shift it right:
- 0x0560 >> 5 = 43
-
-Therefore the I2C device node for the MPC8544 CPU has to have the
-interrupt number 43 specified in the device tree.
-
-[0] MPC8544E PowerQUICCTM III, Integrated Host Processor Family Reference Manual
- MPC8544ERM Rev. 1 10/2007
+++ /dev/null
-* Freescale MSI interrupt controller
-
-Required properties:
-- compatible : compatible list, contains 2 entries,
- first is "fsl,CHIP-msi", where CHIP is the processor(mpc8610, mpc8572,
- etc.) and the second is "fsl,mpic-msi" or "fsl,ipic-msi" depending on
- the parent type.
-- reg : should contain the address and the length of the shared message
- interrupt register set.
-- msi-available-ranges: use <start count> style section to define which
- msi interrupt can be used in the 256 msi interrupts. This property is
- optional, without this, all the 256 MSI interrupts can be used.
-- interrupts : each one of the interrupts here is one entry per 32 MSIs,
- and routed to the host interrupt controller. the interrupts should
- be set as edge sensitive.
-- interrupt-parent: the phandle for the interrupt controller
- that services interrupts for this device. for 83xx cpu, the interrupts
- are routed to IPIC, and for 85xx/86xx cpu the interrupts are routed
- to MPIC.
-
-Example:
- msi@41600 {
- compatible = "fsl,mpc8610-msi", "fsl,mpic-msi";
- reg = <0x41600 0x80>;
- msi-available-ranges = <0 0x100>;
- interrupts = <
- 0xe0 0
- 0xe1 0
- 0xe2 0
- 0xe3 0
- 0xe4 0
- 0xe5 0
- 0xe6 0
- 0xe7 0>;
- interrupt-parent = <&mpic>;
- };
+++ /dev/null
-* Power Management Controller
-
-Properties:
-- compatible: "fsl,<chip>-pmc".
-
- "fsl,mpc8349-pmc" should be listed for any chip whose PMC is
- compatible. "fsl,mpc8313-pmc" should also be listed for any chip
- whose PMC is compatible, and implies deep-sleep capability.
-
- "fsl,mpc8548-pmc" should be listed for any chip whose PMC is
- compatible. "fsl,mpc8536-pmc" should also be listed for any chip
- whose PMC is compatible, and implies deep-sleep capability.
-
- "fsl,mpc8641d-pmc" should be listed for any chip whose PMC is
- compatible; all statements below that apply to "fsl,mpc8548-pmc" also
- apply to "fsl,mpc8641d-pmc".
-
- Compatibility does not include bit assignments in SCCR/PMCDR/DEVDISR; these
- bit assignments are indicated via the sleep specifier in each device's
- sleep property.
-
-- reg: For devices compatible with "fsl,mpc8349-pmc", the first resource
- is the PMC block, and the second resource is the Clock Configuration
- block.
-
- For devices compatible with "fsl,mpc8548-pmc", the first resource
- is a 32-byte block beginning with DEVDISR.
-
-- interrupts: For "fsl,mpc8349-pmc"-compatible devices, the first
- resource is the PMC block interrupt.
-
-- fsl,mpc8313-wakeup-timer: For "fsl,mpc8313-pmc"-compatible devices,
- this is a phandle to an "fsl,gtm" node on which timer 4 can be used as
- a wakeup source from deep sleep.
-
-Sleep specifiers:
-
- fsl,mpc8349-pmc: Sleep specifiers consist of one cell. For each bit
- that is set in the cell, the corresponding bit in SCCR will be saved
- and cleared on suspend, and restored on resume. This sleep controller
- supports disabling and resuming devices at any time.
-
- fsl,mpc8536-pmc: Sleep specifiers consist of three cells, the third of
- which will be ORed into PMCDR upon suspend, and cleared from PMCDR
- upon resume. The first two cells are as described for fsl,mpc8578-pmc.
- This sleep controller only supports disabling devices during system
- sleep, or permanently.
-
- fsl,mpc8548-pmc: Sleep specifiers consist of one or two cells, the
- first of which will be ORed into DEVDISR (and the second into
- DEVDISR2, if present -- this cell should be zero or absent if the
- hardware does not have DEVDISR2) upon a request for permanent device
- disabling. This sleep controller does not support configuring devices
- to disable during system sleep (unless supported by another compatible
- match), or dynamically.
-
-Example:
-
- power@b00 {
- compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc";
- reg = <0xb00 0x100 0xa00 0x100>;
- interrupts = <80 8>;
- };
+++ /dev/null
-* Freescale 8xxx/3.0 Gb/s SATA nodes
-
-SATA nodes are defined to describe on-chip Serial ATA controllers.
-Each SATA port should have its own node.
-
-Required properties:
-- compatible : compatible list, contains 2 entries, first is
- "fsl,CHIP-sata", where CHIP is the processor
- (mpc8315, mpc8379, etc.) and the second is
- "fsl,pq-sata"
-- interrupts : <interrupt mapping for SATA IRQ>
-- cell-index : controller index.
- 1 for controller @ 0x18000
- 2 for controller @ 0x19000
- 3 for controller @ 0x1a000
- 4 for controller @ 0x1b000
-
-Optional properties:
-- interrupt-parent : optional, if needed for interrupt mapping
-- reg : <registers mapping>
-
-Example:
- sata@18000 {
- compatible = "fsl,mpc8379-sata", "fsl,pq-sata";
- reg = <0x18000 0x1000>;
- cell-index = <1>;
- interrupts = <2c 8>;
- interrupt-parent = < &ipic >;
- };
+++ /dev/null
-Freescale SoC SEC Security Engines
-
-Required properties:
-
-- compatible : Should contain entries for this and backward compatible
- SEC versions, high to low, e.g., "fsl,sec2.1", "fsl,sec2.0"
-- reg : Offset and length of the register set for the device
-- interrupts : the SEC's interrupt number
-- fsl,num-channels : An integer representing the number of channels
- available.
-- fsl,channel-fifo-len : An integer representing the number of
- descriptor pointers each channel fetch fifo can hold.
-- fsl,exec-units-mask : The bitmask representing what execution units
- (EUs) are available. It's a single 32-bit cell. EU information
- should be encoded following the SEC's Descriptor Header Dword
- EU_SEL0 field documentation, i.e. as follows:
-
- bit 0 = reserved - should be 0
- bit 1 = set if SEC has the ARC4 EU (AFEU)
- bit 2 = set if SEC has the DES/3DES EU (DEU)
- bit 3 = set if SEC has the message digest EU (MDEU/MDEU-A)
- bit 4 = set if SEC has the random number generator EU (RNG)
- bit 5 = set if SEC has the public key EU (PKEU)
- bit 6 = set if SEC has the AES EU (AESU)
- bit 7 = set if SEC has the Kasumi EU (KEU)
- bit 8 = set if SEC has the CRC EU (CRCU)
- bit 11 = set if SEC has the message digest EU extended alg set (MDEU-B)
-
-remaining bits are reserved for future SEC EUs.
-
-- fsl,descriptor-types-mask : The bitmask representing what descriptors
- are available. It's a single 32-bit cell. Descriptor type information
- should be encoded following the SEC's Descriptor Header Dword DESC_TYPE
- field documentation, i.e. as follows:
-
- bit 0 = set if SEC supports the aesu_ctr_nonsnoop desc. type
- bit 1 = set if SEC supports the ipsec_esp descriptor type
- bit 2 = set if SEC supports the common_nonsnoop desc. type
- bit 3 = set if SEC supports the 802.11i AES ccmp desc. type
- bit 4 = set if SEC supports the hmac_snoop_no_afeu desc. type
- bit 5 = set if SEC supports the srtp descriptor type
- bit 6 = set if SEC supports the non_hmac_snoop_no_afeu desc.type
- bit 7 = set if SEC supports the pkeu_assemble descriptor type
- bit 8 = set if SEC supports the aesu_key_expand_output desc.type
- bit 9 = set if SEC supports the pkeu_ptmul descriptor type
- bit 10 = set if SEC supports the common_nonsnoop_afeu desc. type
- bit 11 = set if SEC supports the pkeu_ptadd_dbl descriptor type
-
- ..and so on and so forth.
-
-Optional properties:
-
-- interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
-
-Example:
-
- /* MPC8548E */
- crypto@30000 {
- compatible = "fsl,sec2.1", "fsl,sec2.0";
- reg = <0x30000 0x10000>;
- interrupts = <29 2>;
- interrupt-parent = <&mpic>;
- fsl,num-channels = <4>;
- fsl,channel-fifo-len = <24>;
- fsl,exec-units-mask = <0xfe>;
- fsl,descriptor-types-mask = <0x12b0ebf>;
- };
+++ /dev/null
-* SPI (Serial Peripheral Interface)
-
-Required properties:
-- cell-index : QE SPI subblock index.
- 0: QE subblock SPI1
- 1: QE subblock SPI2
-- compatible : should be "fsl,spi".
-- mode : the SPI operation mode, it can be "cpu" or "cpu-qe".
-- reg : Offset and length of the register set for the device
-- interrupts : <a b> where a is the interrupt number and b is a
- field that represents an encoding of the sense and level
- information for the interrupt. This should be encoded based on
- the information in section 2) depending on the type of interrupt
- controller you have.
-- interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
-
-Optional properties:
-- gpios : specifies the gpio pins to be used for chipselects.
- The gpios will be referred to as reg = <index> in the SPI child nodes.
- If unspecified, a single SPI device without a chip select can be used.
-
-Example:
- spi@4c0 {
- cell-index = <0>;
- compatible = "fsl,spi";
- reg = <4c0 40>;
- interrupts = <82 0>;
- interrupt-parent = <700>;
- mode = "cpu";
- gpios = <&gpio 18 1 // device reg=<0>
- &gpio 19 1>; // device reg=<1>
- };
-
-
-* eSPI (Enhanced Serial Peripheral Interface)
-
-Required properties:
-- compatible : should be "fsl,mpc8536-espi".
-- reg : Offset and length of the register set for the device.
-- interrupts : should contain eSPI interrupt, the device has one interrupt.
-- fsl,espi-num-chipselects : the number of the chipselect signals.
-
-Example:
- spi@110000 {
- #address-cells = <1>;
- #size-cells = <0>;
- compatible = "fsl,mpc8536-espi";
- reg = <0x110000 0x1000>;
- interrupts = <53 0x2>;
- interrupt-parent = <&mpic>;
- fsl,espi-num-chipselects = <4>;
- };
+++ /dev/null
-Freescale Synchronous Serial Interface
-
-The SSI is a serial device that communicates with audio codecs. It can
-be programmed in AC97, I2S, left-justified, or right-justified modes.
-
-Required properties:
-- compatible: Compatible list, contains "fsl,ssi".
-- cell-index: The SSI, <0> = SSI1, <1> = SSI2, and so on.
-- reg: Offset and length of the register set for the device.
-- interrupts: <a b> where a is the interrupt number and b is a
- field that represents an encoding of the sense and
- level information for the interrupt. This should be
- encoded based on the information in section 2)
- depending on the type of interrupt controller you
- have.
-- interrupt-parent: The phandle for the interrupt controller that
- services interrupts for this device.
-- fsl,mode: The operating mode for the SSI interface.
- "i2s-slave" - I2S mode, SSI is clock slave
- "i2s-master" - I2S mode, SSI is clock master
- "lj-slave" - left-justified mode, SSI is clock slave
- "lj-master" - l.j. mode, SSI is clock master
- "rj-slave" - right-justified mode, SSI is clock slave
- "rj-master" - r.j., SSI is clock master
- "ac97-slave" - AC97 mode, SSI is clock slave
- "ac97-master" - AC97 mode, SSI is clock master
-- fsl,playback-dma: Phandle to a node for the DMA channel to use for
- playback of audio. This is typically dictated by SOC
- design. See the notes below.
-- fsl,capture-dma: Phandle to a node for the DMA channel to use for
- capture (recording) of audio. This is typically dictated
- by SOC design. See the notes below.
-- fsl,fifo-depth: The number of elements in the transmit and receive FIFOs.
- This number is the maximum allowed value for SFCSR[TFWM0].
-- fsl,ssi-asynchronous:
- If specified, the SSI is to be programmed in asynchronous
- mode. In this mode, pins SRCK, STCK, SRFS, and STFS must
- all be connected to valid signals. In synchronous mode,
- SRCK and SRFS are ignored. Asynchronous mode allows
- playback and capture to use different sample sizes and
- sample rates. Some drivers may require that SRCK and STCK
- be connected together, and SRFS and STFS be connected
- together. This would still allow different sample sizes,
- but not different sample rates.
-
-Optional properties:
-- codec-handle: Phandle to a 'codec' node that defines an audio
- codec connected to this SSI. This node is typically
- a child of an I2C or other control node.
-
-Child 'codec' node required properties:
-- compatible: Compatible list, contains the name of the codec
-
-Child 'codec' node optional properties:
-- clock-frequency: The frequency of the input clock, which typically comes
- from an on-board dedicated oscillator.
-
-Notes on fsl,playback-dma and fsl,capture-dma:
-
-On SOCs that have an SSI, specific DMA channels are hard-wired for playback
-and capture. On the MPC8610, for example, SSI1 must use DMA channel 0 for
-playback and DMA channel 1 for capture. SSI2 must use DMA channel 2 for
-playback and DMA channel 3 for capture. The developer can choose which
-DMA controller to use, but the channels themselves are hard-wired. The
-purpose of these two properties is to represent this hardware design.
-
-The device tree nodes for the DMA channels that are referenced by
-"fsl,playback-dma" and "fsl,capture-dma" must be marked as compatible with
-"fsl,ssi-dma-channel". The SOC-specific compatible string (e.g.
-"fsl,mpc8610-dma-channel") can remain. If these nodes are left as
-"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel", then the generic Elo DMA
-drivers (fsldma) will attempt to use them, and it will conflict with the
-sound drivers.
+++ /dev/null
-* MDIO IO device
-
-The MDIO is a bus to which the PHY devices are connected. For each
-device that exists on this bus, a child node should be created. See
-the definition of the PHY node in booting-without-of.txt for an example
-of how to define a PHY.
-
-Required properties:
- - reg : Offset and length of the register set for the device
- - compatible : Should define the compatible device type for the
- mdio. Currently, this is most likely to be "fsl,gianfar-mdio"
-
-Example:
-
- mdio@24520 {
- reg = <24520 20>;
- compatible = "fsl,gianfar-mdio";
-
- ethernet-phy@0 {
- ......
- };
- };
-
-* TBI Internal MDIO bus
-
-As of this writing, every tsec is associated with an internal TBI PHY.
-This PHY is accessed through the local MDIO bus. These buses are defined
-similarly to the mdio buses, except they are compatible with "fsl,gianfar-tbi".
-The TBI PHYs underneath them are similar to normal PHYs, but the reg property
-is considered instructive, rather than descriptive. The reg property should
-be chosen so it doesn't interfere with other PHYs on the bus.
-
-* Gianfar-compatible ethernet nodes
-
-Properties:
-
- - device_type : Should be "network"
- - model : Model of the device. Can be "TSEC", "eTSEC", or "FEC"
- - compatible : Should be "gianfar"
- - reg : Offset and length of the register set for the device
- - local-mac-address : List of bytes representing the ethernet address of
- this controller
- - interrupts : For FEC devices, the first interrupt is the device's
- interrupt. For TSEC and eTSEC devices, the first interrupt is
- transmit, the second is receive, and the third is error.
- - phy-handle : The phandle for the PHY connected to this ethernet
- controller.
- - fixed-link : <a b c d e> where a is emulated phy id - choose any,
- but unique to the all specified fixed-links, b is duplex - 0 half,
- 1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no
- pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause.
- - phy-connection-type : a string naming the controller/PHY interface type,
- i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id", "sgmii",
- "tbi", or "rtbi". This property is only really needed if the connection
- is of type "rgmii-id", as all other connection types are detected by
- hardware.
- - fsl,magic-packet : If present, indicates that the hardware supports
- waking up via magic packet.
- - bd-stash : If present, indicates that the hardware supports stashing
- buffer descriptors in the L2.
- - rx-stash-len : Denotes the number of bytes of a received buffer to stash
- in the L2.
- - rx-stash-idx : Denotes the index of the first byte from the received
- buffer to stash in the L2.
-
-Example:
- ethernet@24000 {
- device_type = "network";
- model = "TSEC";
- compatible = "gianfar";
- reg = <0x24000 0x1000>;
- local-mac-address = [ 00 E0 0C 00 73 00 ];
- interrupts = <29 2 30 2 34 2>;
- interrupt-parent = <&mpic>;
- phy-handle = <&phy0>
- };
+++ /dev/null
-Freescale Localbus UPM programmed to work with NAND flash
-
-Required properties:
-- compatible : "fsl,upm-nand".
-- reg : should specify localbus chip select and size used for the chip.
-- fsl,upm-addr-offset : UPM pattern offset for the address latch.
-- fsl,upm-cmd-offset : UPM pattern offset for the command latch.
-
-Optional properties:
-- fsl,upm-wait-flags : add chip-dependent short delays after running the
- UPM pattern (0x1), after writing a data byte (0x2) or after
- writing out a buffer (0x4).
-- fsl,upm-addr-line-cs-offsets : address offsets for multi-chip support.
- The corresponding address lines are used to select the chip.
-- gpios : may specify optional GPIOs connected to the Ready-Not-Busy pins
- (R/B#). For multi-chip devices, "n" GPIO definitions are required
- according to the number of chips.
-- chip-delay : chip dependent delay for transfering data from array to
- read registers (tR). Required if property "gpios" is not used
- (R/B# pins not connected).
-
-Examples:
-
-upm@1,0 {
- compatible = "fsl,upm-nand";
- reg = <1 0 1>;
- fsl,upm-addr-offset = <16>;
- fsl,upm-cmd-offset = <8>;
- gpios = <&qe_pio_e 18 0>;
-
- flash {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "...";
-
- partition@0 {
- ...
- };
- };
-};
-
-upm@3,0 {
- #address-cells = <0>;
- #size-cells = <0>;
- compatible = "tqc,tqm8548-upm-nand", "fsl,upm-nand";
- reg = <3 0x0 0x800>;
- fsl,upm-addr-offset = <0x10>;
- fsl,upm-cmd-offset = <0x08>;
- /* Multi-chip NAND device */
- fsl,upm-addr-line-cs-offsets = <0x0 0x200>;
- fsl,upm-wait-flags = <0x5>;
- chip-delay = <25>; // in micro-seconds
-
- nand@0 {
- #address-cells = <1>;
- #size-cells = <1>;
-
- partition@0 {
- label = "fs";
- reg = <0x00000000 0x10000000>;
- };
- };
-};
+++ /dev/null
-Freescale SOC USB controllers
-
-The device node for a USB controller that is part of a Freescale
-SOC is as described in the document "Open Firmware Recommended
-Practice : Universal Serial Bus" with the following modifications
-and additions :
-
-Required properties :
- - compatible : Should be "fsl-usb2-mph" for multi port host USB
- controllers, or "fsl-usb2-dr" for dual role USB controllers
- or "fsl,mpc5121-usb2-dr" for dual role USB controllers of MPC5121
- - phy_type : For multi port host USB controllers, should be one of
- "ulpi", or "serial". For dual role USB controllers, should be
- one of "ulpi", "utmi", "utmi_wide", or "serial".
- - reg : Offset and length of the register set for the device
- - port0 : boolean; if defined, indicates port0 is connected for
- fsl-usb2-mph compatible controllers. Either this property or
- "port1" (or both) must be defined for "fsl-usb2-mph" compatible
- controllers.
- - port1 : boolean; if defined, indicates port1 is connected for
- fsl-usb2-mph compatible controllers. Either this property or
- "port0" (or both) must be defined for "fsl-usb2-mph" compatible
- controllers.
- - dr_mode : indicates the working mode for "fsl-usb2-dr" compatible
- controllers. Can be "host", "peripheral", or "otg". Default to
- "host" if not defined for backward compatibility.
-
-Recommended properties :
- - interrupts : <a b> where a is the interrupt number and b is a
- field that represents an encoding of the sense and level
- information for the interrupt. This should be encoded based on
- the information in section 2) depending on the type of interrupt
- controller you have.
- - interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
-
-Optional properties :
- - fsl,invert-drvvbus : boolean; for MPC5121 USB0 only. Indicates the
- port power polarity of internal PHY signal DRVVBUS is inverted.
- - fsl,invert-pwr-fault : boolean; for MPC5121 USB0 only. Indicates
- the PWR_FAULT signal polarity is inverted.
-
-Example multi port host USB controller device node :
- usb@22000 {
- compatible = "fsl-usb2-mph";
- reg = <22000 1000>;
- #address-cells = <1>;
- #size-cells = <0>;
- interrupt-parent = <700>;
- interrupts = <27 1>;
- phy_type = "ulpi";
- port0;
- port1;
- };
-
-Example dual role USB controller device node :
- usb@23000 {
- compatible = "fsl-usb2-dr";
- reg = <23000 1000>;
- #address-cells = <1>;
- #size-cells = <0>;
- interrupt-parent = <700>;
- interrupts = <26 1>;
- dr_mode = "otg";
- phy = "ulpi";
- };
-
-Example dual role USB controller device node for MPC5121ADS:
-
- usb@4000 {
- compatible = "fsl,mpc5121-usb2-dr";
- reg = <0x4000 0x1000>;
- #address-cells = <1>;
- #size-cells = <0>;
- interrupt-parent = < &ipic >;
- interrupts = <44 0x8>;
- dr_mode = "otg";
- phy_type = "utmi_wide";
- fsl,invert-drvvbus;
- fsl,invert-pwr-fault;
- };
+++ /dev/null
-Specifying GPIO information for devices
-============================================
-
-1) gpios property
------------------
-
-Nodes that makes use of GPIOs should define them using `gpios' property,
-format of which is: <&gpio-controller1-phandle gpio1-specifier
- &gpio-controller2-phandle gpio2-specifier
- 0 /* holes are permitted, means no GPIO 3 */
- &gpio-controller4-phandle gpio4-specifier
- ...>;
-
-Note that gpio-specifier length is controller dependent.
-
-gpio-specifier may encode: bank, pin position inside the bank,
-whether pin is open-drain and whether pin is logically inverted.
-
-Example of the node using GPIOs:
-
- node {
- gpios = <&qe_pio_e 18 0>;
- };
-
-In this example gpio-specifier is "18 0" and encodes GPIO pin number,
-and empty GPIO flags as accepted by the "qe_pio_e" gpio-controller.
-
-2) gpio-controller nodes
-------------------------
-
-Every GPIO controller node must have #gpio-cells property defined,
-this information will be used to translate gpio-specifiers.
-
-Example of two SOC GPIO banks defined as gpio-controller nodes:
-
- qe_pio_a: gpio-controller@1400 {
- #gpio-cells = <2>;
- compatible = "fsl,qe-pario-bank-a", "fsl,qe-pario-bank";
- reg = <0x1400 0x18>;
- gpio-controller;
- };
-
- qe_pio_e: gpio-controller@1460 {
- #gpio-cells = <2>;
- compatible = "fsl,qe-pario-bank-e", "fsl,qe-pario-bank";
- reg = <0x1460 0x18>;
- gpio-controller;
- };
-
-
+++ /dev/null
-LEDs connected to GPIO lines
-
-Required properties:
-- compatible : should be "gpio-leds".
-
-Each LED is represented as a sub-node of the gpio-leds device. Each
-node's name represents the name of the corresponding LED.
-
-LED sub-node properties:
-- gpios : Should specify the LED's GPIO, see "Specifying GPIO information
- for devices" in Documentation/powerpc/booting-without-of.txt. Active
- low LEDs should be indicated using flags in the GPIO specifier.
-- label : (optional) The label for this LED. If omitted, the label is
- taken from the node name (excluding the unit address).
-- linux,default-trigger : (optional) This parameter, if present, is a
- string defining the trigger assigned to the LED. Current triggers are:
- "backlight" - LED will act as a back-light, controlled by the framebuffer
- system
- "default-on" - LED will turn on, but see "default-state" below
- "heartbeat" - LED "double" flashes at a load average based rate
- "ide-disk" - LED indicates disk activity
- "timer" - LED flashes at a fixed, configurable rate
-- default-state: (optional) The initial state of the LED. Valid
- values are "on", "off", and "keep". If the LED is already on or off
- and the default-state property is set the to same value, then no
- glitch should be produced where the LED momentarily turns off (or
- on). The "keep" setting will keep the LED at whatever its current
- state is, without producing a glitch. The default is off if this
- property is not present.
-
-Examples:
-
-leds {
- compatible = "gpio-leds";
- hdd {
- label = "IDE Activity";
- gpios = <&mcu_pio 0 1>; /* Active low */
- linux,default-trigger = "ide-disk";
- };
-
- fault {
- gpios = <&mcu_pio 1 0>;
- /* Keep LED on if BIOS detected hardware fault */
- default-state = "keep";
- };
-};
-
-run-control {
- compatible = "gpio-leds";
- red {
- gpios = <&mpc8572 6 0>;
- default-state = "off";
- };
- green {
- gpios = <&mpc8572 7 0>;
- default-state = "on";
- };
-}
+++ /dev/null
-MDIO on GPIOs
-
-Currently defined compatibles:
-- virtual,gpio-mdio
-
-MDC and MDIO lines connected to GPIO controllers are listed in the
-gpios property as described in section VIII.1 in the following order:
-
-MDC, MDIO.
-
-Example:
-
-mdio {
- compatible = "virtual,mdio-gpio";
- #address-cells = <1>;
- #size-cells = <0>;
- gpios = <&qe_pio_a 11
- &qe_pio_c 6>;
-};
+++ /dev/null
-Marvell Discovery mv64[345]6x System Controller chips
-===========================================================
-
-The Marvell mv64[345]60 series of system controller chips contain
-many of the peripherals needed to implement a complete computer
-system. In this section, we define device tree nodes to describe
-the system controller chip itself and each of the peripherals
-which it contains. Compatible string values for each node are
-prefixed with the string "marvell,", for Marvell Technology Group Ltd.
-
-1) The /system-controller node
-
- This node is used to represent the system-controller and must be
- present when the system uses a system controller chip. The top-level
- system-controller node contains information that is global to all
- devices within the system controller chip. The node name begins
- with "system-controller" followed by the unit address, which is
- the base address of the memory-mapped register set for the system
- controller chip.
-
- Required properties:
-
- - ranges : Describes the translation of system controller addresses
- for memory mapped registers.
- - clock-frequency: Contains the main clock frequency for the system
- controller chip.
- - reg : This property defines the address and size of the
- memory-mapped registers contained within the system controller
- chip. The address specified in the "reg" property should match
- the unit address of the system-controller node.
- - #address-cells : Address representation for system controller
- devices. This field represents the number of cells needed to
- represent the address of the memory-mapped registers of devices
- within the system controller chip.
- - #size-cells : Size representation for the memory-mapped
- registers within the system controller chip.
- - #interrupt-cells : Defines the width of cells used to represent
- interrupts.
-
- Optional properties:
-
- - model : The specific model of the system controller chip. Such
- as, "mv64360", "mv64460", or "mv64560".
- - compatible : A string identifying the compatibility identifiers
- of the system controller chip.
-
- The system-controller node contains child nodes for each system
- controller device that the platform uses. Nodes should not be created
- for devices which exist on the system controller chip but are not used
-
- Example Marvell Discovery mv64360 system-controller node:
-
- system-controller@f1000000 { /* Marvell Discovery mv64360 */
- #address-cells = <1>;
- #size-cells = <1>;
- model = "mv64360"; /* Default */
- compatible = "marvell,mv64360";
- clock-frequency = <133333333>;
- reg = <0xf1000000 0x10000>;
- virtual-reg = <0xf1000000>;
- ranges = <0x88000000 0x88000000 0x1000000 /* PCI 0 I/O Space */
- 0x80000000 0x80000000 0x8000000 /* PCI 0 MEM Space */
- 0xa0000000 0xa0000000 0x4000000 /* User FLASH */
- 0x00000000 0xf1000000 0x0010000 /* Bridge's regs */
- 0xf2000000 0xf2000000 0x0040000>;/* Integrated SRAM */
-
- [ child node definitions... ]
- }
-
-2) Child nodes of /system-controller
-
- a) Marvell Discovery MDIO bus
-
- The MDIO is a bus to which the PHY devices are connected. For each
- device that exists on this bus, a child node should be created. See
- the definition of the PHY node below for an example of how to define
- a PHY.
-
- Required properties:
- - #address-cells : Should be <1>
- - #size-cells : Should be <0>
- - device_type : Should be "mdio"
- - compatible : Should be "marvell,mv64360-mdio"
-
- Example:
-
- mdio {
- #address-cells = <1>;
- #size-cells = <0>;
- device_type = "mdio";
- compatible = "marvell,mv64360-mdio";
-
- ethernet-phy@0 {
- ......
- };
- };
-
-
- b) Marvell Discovery ethernet controller
-
- The Discover ethernet controller is described with two levels
- of nodes. The first level describes an ethernet silicon block
- and the second level describes up to 3 ethernet nodes within
- that block. The reason for the multiple levels is that the
- registers for the node are interleaved within a single set
- of registers. The "ethernet-block" level describes the
- shared register set, and the "ethernet" nodes describe ethernet
- port-specific properties.
-
- Ethernet block node
-
- Required properties:
- - #address-cells : <1>
- - #size-cells : <0>
- - compatible : "marvell,mv64360-eth-block"
- - reg : Offset and length of the register set for this block
-
- Example Discovery Ethernet block node:
- ethernet-block@2000 {
- #address-cells = <1>;
- #size-cells = <0>;
- compatible = "marvell,mv64360-eth-block";
- reg = <0x2000 0x2000>;
- ethernet@0 {
- .......
- };
- };
-
- Ethernet port node
-
- Required properties:
- - device_type : Should be "network".
- - compatible : Should be "marvell,mv64360-eth".
- - reg : Should be <0>, <1>, or <2>, according to which registers
- within the silicon block the device uses.
- - interrupts : <a> where a is the interrupt number for the port.
- - interrupt-parent : the phandle for the interrupt controller
- that services interrupts for this device.
- - phy : the phandle for the PHY connected to this ethernet
- controller.
- - local-mac-address : 6 bytes, MAC address
-
- Example Discovery Ethernet port node:
- ethernet@0 {
- device_type = "network";
- compatible = "marvell,mv64360-eth";
- reg = <0>;
- interrupts = <32>;
- interrupt-parent = <&PIC>;
- phy = <&PHY0>;
- local-mac-address = [ 00 00 00 00 00 00 ];
- };
-
-
-
- c) Marvell Discovery PHY nodes
-
- Required properties:
- - device_type : Should be "ethernet-phy"
- - interrupts : <a> where a is the interrupt number for this phy.
- - interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
- - reg : The ID number for the phy, usually a small integer
-
- Example Discovery PHY node:
- ethernet-phy@1 {
- device_type = "ethernet-phy";
- compatible = "broadcom,bcm5421";
- interrupts = <76>; /* GPP 12 */
- interrupt-parent = <&PIC>;
- reg = <1>;
- };
-
-
- d) Marvell Discovery SDMA nodes
-
- Represent DMA hardware associated with the MPSC (multiprotocol
- serial controllers).
-
- Required properties:
- - compatible : "marvell,mv64360-sdma"
- - reg : Offset and length of the register set for this device
- - interrupts : <a> where a is the interrupt number for the DMA
- device.
- - interrupt-parent : the phandle for the interrupt controller
- that services interrupts for this device.
-
- Example Discovery SDMA node:
- sdma@4000 {
- compatible = "marvell,mv64360-sdma";
- reg = <0x4000 0xc18>;
- virtual-reg = <0xf1004000>;
- interrupts = <36>;
- interrupt-parent = <&PIC>;
- };
-
-
- e) Marvell Discovery BRG nodes
-
- Represent baud rate generator hardware associated with the MPSC
- (multiprotocol serial controllers).
-
- Required properties:
- - compatible : "marvell,mv64360-brg"
- - reg : Offset and length of the register set for this device
- - clock-src : A value from 0 to 15 which selects the clock
- source for the baud rate generator. This value corresponds
- to the CLKS value in the BRGx configuration register. See
- the mv64x60 User's Manual.
- - clock-frequence : The frequency (in Hz) of the baud rate
- generator's input clock.
- - current-speed : The current speed setting (presumably by
- firmware) of the baud rate generator.
-
- Example Discovery BRG node:
- brg@b200 {
- compatible = "marvell,mv64360-brg";
- reg = <0xb200 0x8>;
- clock-src = <8>;
- clock-frequency = <133333333>;
- current-speed = <9600>;
- };
-
-
- f) Marvell Discovery CUNIT nodes
-
- Represent the Serial Communications Unit device hardware.
-
- Required properties:
- - reg : Offset and length of the register set for this device
-
- Example Discovery CUNIT node:
- cunit@f200 {
- reg = <0xf200 0x200>;
- };
-
-
- g) Marvell Discovery MPSCROUTING nodes
-
- Represent the Discovery's MPSC routing hardware
-
- Required properties:
- - reg : Offset and length of the register set for this device
-
- Example Discovery CUNIT node:
- mpscrouting@b500 {
- reg = <0xb400 0xc>;
- };
-
-
- h) Marvell Discovery MPSCINTR nodes
-
- Represent the Discovery's MPSC DMA interrupt hardware registers
- (SDMA cause and mask registers).
-
- Required properties:
- - reg : Offset and length of the register set for this device
-
- Example Discovery MPSCINTR node:
- mpsintr@b800 {
- reg = <0xb800 0x100>;
- };
-
-
- i) Marvell Discovery MPSC nodes
-
- Represent the Discovery's MPSC (Multiprotocol Serial Controller)
- serial port.
-
- Required properties:
- - device_type : "serial"
- - compatible : "marvell,mv64360-mpsc"
- - reg : Offset and length of the register set for this device
- - sdma : the phandle for the SDMA node used by this port
- - brg : the phandle for the BRG node used by this port
- - cunit : the phandle for the CUNIT node used by this port
- - mpscrouting : the phandle for the MPSCROUTING node used by this port
- - mpscintr : the phandle for the MPSCINTR node used by this port
- - cell-index : the hardware index of this cell in the MPSC core
- - max_idle : value needed for MPSC CHR3 (Maximum Frame Length)
- register
- - interrupts : <a> where a is the interrupt number for the MPSC.
- - interrupt-parent : the phandle for the interrupt controller
- that services interrupts for this device.
-
- Example Discovery MPSCINTR node:
- mpsc@8000 {
- device_type = "serial";
- compatible = "marvell,mv64360-mpsc";
- reg = <0x8000 0x38>;
- virtual-reg = <0xf1008000>;
- sdma = <&SDMA0>;
- brg = <&BRG0>;
- cunit = <&CUNIT>;
- mpscrouting = <&MPSCROUTING>;
- mpscintr = <&MPSCINTR>;
- cell-index = <0>;
- max_idle = <40>;
- interrupts = <40>;
- interrupt-parent = <&PIC>;
- };
-
-
- j) Marvell Discovery Watch Dog Timer nodes
-
- Represent the Discovery's watchdog timer hardware
-
- Required properties:
- - compatible : "marvell,mv64360-wdt"
- - reg : Offset and length of the register set for this device
-
- Example Discovery Watch Dog Timer node:
- wdt@b410 {
- compatible = "marvell,mv64360-wdt";
- reg = <0xb410 0x8>;
- };
-
-
- k) Marvell Discovery I2C nodes
-
- Represent the Discovery's I2C hardware
-
- Required properties:
- - device_type : "i2c"
- - compatible : "marvell,mv64360-i2c"
- - reg : Offset and length of the register set for this device
- - interrupts : <a> where a is the interrupt number for the I2C.
- - interrupt-parent : the phandle for the interrupt controller
- that services interrupts for this device.
-
- Example Discovery I2C node:
- compatible = "marvell,mv64360-i2c";
- reg = <0xc000 0x20>;
- virtual-reg = <0xf100c000>;
- interrupts = <37>;
- interrupt-parent = <&PIC>;
- };
-
-
- l) Marvell Discovery PIC (Programmable Interrupt Controller) nodes
-
- Represent the Discovery's PIC hardware
-
- Required properties:
- - #interrupt-cells : <1>
- - #address-cells : <0>
- - compatible : "marvell,mv64360-pic"
- - reg : Offset and length of the register set for this device
- - interrupt-controller
-
- Example Discovery PIC node:
- pic {
- #interrupt-cells = <1>;
- #address-cells = <0>;
- compatible = "marvell,mv64360-pic";
- reg = <0x0 0x88>;
- interrupt-controller;
- };
-
-
- m) Marvell Discovery MPP (Multipurpose Pins) multiplexing nodes
-
- Represent the Discovery's MPP hardware
-
- Required properties:
- - compatible : "marvell,mv64360-mpp"
- - reg : Offset and length of the register set for this device
-
- Example Discovery MPP node:
- mpp@f000 {
- compatible = "marvell,mv64360-mpp";
- reg = <0xf000 0x10>;
- };
-
-
- n) Marvell Discovery GPP (General Purpose Pins) nodes
-
- Represent the Discovery's GPP hardware
-
- Required properties:
- - compatible : "marvell,mv64360-gpp"
- - reg : Offset and length of the register set for this device
-
- Example Discovery GPP node:
- gpp@f000 {
- compatible = "marvell,mv64360-gpp";
- reg = <0xf100 0x20>;
- };
-
-
- o) Marvell Discovery PCI host bridge node
-
- Represents the Discovery's PCI host bridge device. The properties
- for this node conform to Rev 2.1 of the PCI Bus Binding to IEEE
- 1275-1994. A typical value for the compatible property is
- "marvell,mv64360-pci".
-
- Example Discovery PCI host bridge node
- pci@80000000 {
- #address-cells = <3>;
- #size-cells = <2>;
- #interrupt-cells = <1>;
- device_type = "pci";
- compatible = "marvell,mv64360-pci";
- reg = <0xcf8 0x8>;
- ranges = <0x01000000 0x0 0x0
- 0x88000000 0x0 0x01000000
- 0x02000000 0x0 0x80000000
- 0x80000000 0x0 0x08000000>;
- bus-range = <0 255>;
- clock-frequency = <66000000>;
- interrupt-parent = <&PIC>;
- interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
- interrupt-map = <
- /* IDSEL 0x0a */
- 0x5000 0 0 1 &PIC 80
- 0x5000 0 0 2 &PIC 81
- 0x5000 0 0 3 &PIC 91
- 0x5000 0 0 4 &PIC 93
-
- /* IDSEL 0x0b */
- 0x5800 0 0 1 &PIC 91
- 0x5800 0 0 2 &PIC 93
- 0x5800 0 0 3 &PIC 80
- 0x5800 0 0 4 &PIC 81
-
- /* IDSEL 0x0c */
- 0x6000 0 0 1 &PIC 91
- 0x6000 0 0 2 &PIC 93
- 0x6000 0 0 3 &PIC 80
- 0x6000 0 0 4 &PIC 81
-
- /* IDSEL 0x0d */
- 0x6800 0 0 1 &PIC 93
- 0x6800 0 0 2 &PIC 80
- 0x6800 0 0 3 &PIC 81
- 0x6800 0 0 4 &PIC 91
- >;
- };
-
-
- p) Marvell Discovery CPU Error nodes
-
- Represent the Discovery's CPU error handler device.
-
- Required properties:
- - compatible : "marvell,mv64360-cpu-error"
- - reg : Offset and length of the register set for this device
- - interrupts : the interrupt number for this device
- - interrupt-parent : the phandle for the interrupt controller
- that services interrupts for this device.
-
- Example Discovery CPU Error node:
- cpu-error@0070 {
- compatible = "marvell,mv64360-cpu-error";
- reg = <0x70 0x10 0x128 0x28>;
- interrupts = <3>;
- interrupt-parent = <&PIC>;
- };
-
-
- q) Marvell Discovery SRAM Controller nodes
-
- Represent the Discovery's SRAM controller device.
-
- Required properties:
- - compatible : "marvell,mv64360-sram-ctrl"
- - reg : Offset and length of the register set for this device
- - interrupts : the interrupt number for this device
- - interrupt-parent : the phandle for the interrupt controller
- that services interrupts for this device.
-
- Example Discovery SRAM Controller node:
- sram-ctrl@0380 {
- compatible = "marvell,mv64360-sram-ctrl";
- reg = <0x380 0x80>;
- interrupts = <13>;
- interrupt-parent = <&PIC>;
- };
-
-
- r) Marvell Discovery PCI Error Handler nodes
-
- Represent the Discovery's PCI error handler device.
-
- Required properties:
- - compatible : "marvell,mv64360-pci-error"
- - reg : Offset and length of the register set for this device
- - interrupts : the interrupt number for this device
- - interrupt-parent : the phandle for the interrupt controller
- that services interrupts for this device.
-
- Example Discovery PCI Error Handler node:
- pci-error@1d40 {
- compatible = "marvell,mv64360-pci-error";
- reg = <0x1d40 0x40 0xc28 0x4>;
- interrupts = <12>;
- interrupt-parent = <&PIC>;
- };
-
-
- s) Marvell Discovery Memory Controller nodes
-
- Represent the Discovery's memory controller device.
-
- Required properties:
- - compatible : "marvell,mv64360-mem-ctrl"
- - reg : Offset and length of the register set for this device
- - interrupts : the interrupt number for this device
- - interrupt-parent : the phandle for the interrupt controller
- that services interrupts for this device.
-
- Example Discovery Memory Controller node:
- mem-ctrl@1400 {
- compatible = "marvell,mv64360-mem-ctrl";
- reg = <0x1400 0x60>;
- interrupts = <17>;
- interrupt-parent = <&PIC>;
- };
-
-
+++ /dev/null
-MMC/SD/SDIO slot directly connected to a SPI bus
-
-Required properties:
-- compatible : should be "mmc-spi-slot".
-- reg : should specify SPI address (chip-select number).
-- spi-max-frequency : maximum frequency for this device (Hz).
-- voltage-ranges : two cells are required, first cell specifies minimum
- slot voltage (mV), second cell specifies maximum slot voltage (mV).
- Several ranges could be specified.
-- gpios : (optional) may specify GPIOs in this order: Card-Detect GPIO,
- Write-Protect GPIO.
-
-Example:
-
- mmc-slot@0 {
- compatible = "fsl,mpc8323rdb-mmc-slot",
- "mmc-spi-slot";
- reg = <0>;
- gpios = <&qe_pio_d 14 1
- &qe_pio_d 15 0>;
- voltage-ranges = <3300 3300>;
- spi-max-frequency = <50000000>;
- };
+++ /dev/null
-CFI or JEDEC memory-mapped NOR flash, MTD-RAM (NVRAM...)
-
-Flash chips (Memory Technology Devices) are often used for solid state
-file systems on embedded devices.
-
- - compatible : should contain the specific model of mtd chip(s)
- used, if known, followed by either "cfi-flash", "jedec-flash"
- or "mtd-ram".
- - reg : Address range(s) of the mtd chip(s)
- It's possible to (optionally) define multiple "reg" tuples so that
- non-identical chips can be described in one node.
- - bank-width : Width (in bytes) of the bank. Equal to the
- device width times the number of interleaved chips.
- - device-width : (optional) Width of a single mtd chip. If
- omitted, assumed to be equal to 'bank-width'.
- - #address-cells, #size-cells : Must be present if the device has
- sub-nodes representing partitions (see below). In this case
- both #address-cells and #size-cells must be equal to 1.
-
-For JEDEC compatible devices, the following additional properties
-are defined:
-
- - vendor-id : Contains the flash chip's vendor id (1 byte).
- - device-id : Contains the flash chip's device id (1 byte).
-
-In addition to the information on the mtd bank itself, the
-device tree may optionally contain additional information
-describing partitions of the address space. This can be
-used on platforms which have strong conventions about which
-portions of a flash are used for what purposes, but which don't
-use an on-flash partition table such as RedBoot.
-
-Each partition is represented as a sub-node of the mtd device.
-Each node's name represents the name of the corresponding
-partition of the mtd device.
-
-Flash partitions
- - reg : The partition's offset and size within the mtd bank.
- - label : (optional) The label / name for this partition.
- If omitted, the label is taken from the node name (excluding
- the unit address).
- - read-only : (optional) This parameter, if present, is a hint to
- Linux that this partition should only be mounted
- read-only. This is usually used for flash partitions
- containing early-boot firmware images or data which should not
- be clobbered.
-
-Example:
-
- flash@ff000000 {
- compatible = "amd,am29lv128ml", "cfi-flash";
- reg = <ff000000 01000000>;
- bank-width = <4>;
- device-width = <1>;
- #address-cells = <1>;
- #size-cells = <1>;
- fs@0 {
- label = "fs";
- reg = <0 f80000>;
- };
- firmware@f80000 {
- label ="firmware";
- reg = <f80000 80000>;
- read-only;
- };
- };
-
-Here an example with multiple "reg" tuples:
-
- flash@f0000000,0 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "intel,PC48F4400P0VB", "cfi-flash";
- reg = <0 0x00000000 0x02000000
- 0 0x02000000 0x02000000>;
- bank-width = <2>;
- partition@0 {
- label = "test-part1";
- reg = <0 0x04000000>;
- };
- };
-
-An example using SRAM:
-
- sram@2,0 {
- compatible = "samsung,k6f1616u6a", "mtd-ram";
- reg = <2 0 0x00200000>;
- bank-width = <2>;
- };
-
+++ /dev/null
-
-Nintendo GameCube device tree
-=============================
-
-1) The "flipper" node
-
- This node represents the multi-function "Flipper" chip, which packages
- many of the devices found in the Nintendo GameCube.
-
- Required properties:
-
- - compatible : Should be "nintendo,flipper"
-
-1.a) The Video Interface (VI) node
-
- Represents the interface between the graphics processor and a external
- video encoder.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-vi"
- - reg : should contain the VI registers location and length
- - interrupts : should contain the VI interrupt
-
-1.b) The Processor Interface (PI) node
-
- Represents the data and control interface between the main processor
- and graphics and audio processor.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-pi"
- - reg : should contain the PI registers location and length
-
-1.b.i) The "Flipper" interrupt controller node
-
- Represents the interrupt controller within the "Flipper" chip.
- The node for the "Flipper" interrupt controller must be placed under
- the PI node.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-pic"
-
-1.c) The Digital Signal Procesor (DSP) node
-
- Represents the digital signal processor interface, designed to offload
- audio related tasks.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-dsp"
- - reg : should contain the DSP registers location and length
- - interrupts : should contain the DSP interrupt
-
-1.c.i) The Auxiliary RAM (ARAM) node
-
- Represents the non cpu-addressable ram designed mainly to store audio
- related information.
- The ARAM node must be placed under the DSP node.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-aram"
- - reg : should contain the ARAM start (zero-based) and length
-
-1.d) The Disk Interface (DI) node
-
- Represents the interface used to communicate with mass storage devices.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-di"
- - reg : should contain the DI registers location and length
- - interrupts : should contain the DI interrupt
-
-1.e) The Audio Interface (AI) node
-
- Represents the interface to the external 16-bit stereo digital-to-analog
- converter.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-ai"
- - reg : should contain the AI registers location and length
- - interrupts : should contain the AI interrupt
-
-1.f) The Serial Interface (SI) node
-
- Represents the interface to the four single bit serial interfaces.
- The SI is a proprietary serial interface used normally to control gamepads.
- It's NOT a RS232-type interface.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-si"
- - reg : should contain the SI registers location and length
- - interrupts : should contain the SI interrupt
-
-1.g) The External Interface (EXI) node
-
- Represents the multi-channel SPI-like interface.
-
- Required properties:
-
- - compatible : should be "nintendo,flipper-exi"
- - reg : should contain the EXI registers location and length
- - interrupts : should contain the EXI interrupt
-
+++ /dev/null
-
-Nintendo Wii device tree
-========================
-
-0) The root node
-
- This node represents the Nintendo Wii video game console.
-
- Required properties:
-
- - model : Should be "nintendo,wii"
- - compatible : Should be "nintendo,wii"
-
-1) The "hollywood" node
-
- This node represents the multi-function "Hollywood" chip, which packages
- many of the devices found in the Nintendo Wii.
-
- Required properties:
-
- - compatible : Should be "nintendo,hollywood"
-
-1.a) The Video Interface (VI) node
-
- Represents the interface between the graphics processor and a external
- video encoder.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-vi","nintendo,flipper-vi"
- - reg : should contain the VI registers location and length
- - interrupts : should contain the VI interrupt
-
-1.b) The Processor Interface (PI) node
-
- Represents the data and control interface between the main processor
- and graphics and audio processor.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-pi","nintendo,flipper-pi"
- - reg : should contain the PI registers location and length
-
-1.b.i) The "Flipper" interrupt controller node
-
- Represents the "Flipper" interrupt controller within the "Hollywood" chip.
- The node for the "Flipper" interrupt controller must be placed under
- the PI node.
-
- Required properties:
-
- - #interrupt-cells : <1>
- - compatible : should be "nintendo,flipper-pic"
- - interrupt-controller
-
-1.c) The Digital Signal Procesor (DSP) node
-
- Represents the digital signal processor interface, designed to offload
- audio related tasks.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-dsp","nintendo,flipper-dsp"
- - reg : should contain the DSP registers location and length
- - interrupts : should contain the DSP interrupt
-
-1.d) The Serial Interface (SI) node
-
- Represents the interface to the four single bit serial interfaces.
- The SI is a proprietary serial interface used normally to control gamepads.
- It's NOT a RS232-type interface.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-si","nintendo,flipper-si"
- - reg : should contain the SI registers location and length
- - interrupts : should contain the SI interrupt
-
-1.e) The Audio Interface (AI) node
-
- Represents the interface to the external 16-bit stereo digital-to-analog
- converter.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-ai","nintendo,flipper-ai"
- - reg : should contain the AI registers location and length
- - interrupts : should contain the AI interrupt
-
-1.f) The External Interface (EXI) node
-
- Represents the multi-channel SPI-like interface.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-exi","nintendo,flipper-exi"
- - reg : should contain the EXI registers location and length
- - interrupts : should contain the EXI interrupt
-
-1.g) The Open Host Controller Interface (OHCI) nodes
-
- Represent the USB 1.x Open Host Controller Interfaces.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-usb-ohci","usb-ohci"
- - reg : should contain the OHCI registers location and length
- - interrupts : should contain the OHCI interrupt
-
-1.h) The Enhanced Host Controller Interface (EHCI) node
-
- Represents the USB 2.0 Enhanced Host Controller Interface.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-usb-ehci","usb-ehci"
- - reg : should contain the EHCI registers location and length
- - interrupts : should contain the EHCI interrupt
-
-1.i) The Secure Digital Host Controller Interface (SDHCI) nodes
-
- Represent the Secure Digital Host Controller Interfaces.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-sdhci","sdhci"
- - reg : should contain the SDHCI registers location and length
- - interrupts : should contain the SDHCI interrupt
-
-1.j) The Inter-Processsor Communication (IPC) node
-
- Represent the Inter-Processor Communication interface. This interface
- enables communications between the Broadway and the Starlet processors.
-
- - compatible : should be "nintendo,hollywood-ipc"
- - reg : should contain the IPC registers location and length
- - interrupts : should contain the IPC interrupt
-
-1.k) The "Hollywood" interrupt controller node
-
- Represents the "Hollywood" interrupt controller within the
- "Hollywood" chip.
-
- Required properties:
-
- - #interrupt-cells : <1>
- - compatible : should be "nintendo,hollywood-pic"
- - reg : should contain the controller registers location and length
- - interrupt-controller
- - interrupts : should contain the cascade interrupt of the "flipper" pic
- - interrupt-parent: should contain the phandle of the "flipper" pic
-
-1.l) The General Purpose I/O (GPIO) controller node
-
- Represents the dual access 32 GPIO controller interface.
-
- Required properties:
-
- - #gpio-cells : <2>
- - compatible : should be "nintendo,hollywood-gpio"
- - reg : should contain the IPC registers location and length
- - gpio-controller
-
-1.m) The control node
-
- Represents the control interface used to setup several miscellaneous
- settings of the "Hollywood" chip like boot memory mappings, resets,
- disk interface mode, etc.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-control"
- - reg : should contain the control registers location and length
-
-1.n) The Disk Interface (DI) node
-
- Represents the interface used to communicate with mass storage devices.
-
- Required properties:
-
- - compatible : should be "nintendo,hollywood-di"
- - reg : should contain the DI registers location and length
- - interrupts : should contain the DI interrupt
-
+++ /dev/null
-PHY nodes
-
-Required properties:
-
- - device_type : Should be "ethernet-phy"
- - interrupts : <a b> where a is the interrupt number and b is a
- field that represents an encoding of the sense and level
- information for the interrupt. This should be encoded based on
- the information in section 2) depending on the type of interrupt
- controller you have.
- - interrupt-parent : the phandle for the interrupt controller that
- services interrupts for this device.
- - reg : The ID number for the phy, usually a small integer
- - linux,phandle : phandle for this node; likely referenced by an
- ethernet controller node.
-
-Example:
-
-ethernet-phy@0 {
- linux,phandle = <2452000>
- interrupt-parent = <40000>;
- interrupts = <35 1>;
- reg = <0>;
- device_type = "ethernet-phy";
-};
+++ /dev/null
-SPI (Serial Peripheral Interface) busses
-
-SPI busses can be described with a node for the SPI master device
-and a set of child nodes for each SPI slave on the bus. For this
-discussion, it is assumed that the system's SPI controller is in
-SPI master mode. This binding does not describe SPI controllers
-in slave mode.
-
-The SPI master node requires the following properties:
-- #address-cells - number of cells required to define a chip select
- address on the SPI bus.
-- #size-cells - should be zero.
-- compatible - name of SPI bus controller following generic names
- recommended practice.
-No other properties are required in the SPI bus node. It is assumed
-that a driver for an SPI bus device will understand that it is an SPI bus.
-However, the binding does not attempt to define the specific method for
-assigning chip select numbers. Since SPI chip select configuration is
-flexible and non-standardized, it is left out of this binding with the
-assumption that board specific platform code will be used to manage
-chip selects. Individual drivers can define additional properties to
-support describing the chip select layout.
-
-SPI slave nodes must be children of the SPI master node and can
-contain the following properties.
-- reg - (required) chip select address of device.
-- compatible - (required) name of SPI device following generic names
- recommended practice
-- spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz
-- spi-cpol - (optional) Empty property indicating device requires
- inverse clock polarity (CPOL) mode
-- spi-cpha - (optional) Empty property indicating device requires
- shifted clock phase (CPHA) mode
-- spi-cs-high - (optional) Empty property indicating device requires
- chip select active high
-
-SPI example for an MPC5200 SPI bus:
- spi@f00 {
- #address-cells = <1>;
- #size-cells = <0>;
- compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi";
- reg = <0xf00 0x20>;
- interrupts = <2 13 0 2 14 0>;
- interrupt-parent = <&mpc5200_pic>;
-
- ethernet-switch@0 {
- compatible = "micrel,ks8995m";
- spi-max-frequency = <1000000>;
- reg = <0>;
- };
-
- codec@1 {
- compatible = "ti,tlv320aic26";
- spi-max-frequency = <100000>;
- reg = <1>;
- };
- };
+++ /dev/null
-USB EHCI controllers
-
-Required properties:
- - compatible : should be "usb-ehci".
- - reg : should contain at least address and length of the standard EHCI
- register set for the device. Optional platform-dependent registers
- (debug-port or other) can be also specified here, but only after
- definition of standard EHCI registers.
- - interrupts : one EHCI interrupt should be described here.
-If device registers are implemented in big endian mode, the device
-node should have "big-endian-regs" property.
-If controller implementation operates with big endian descriptors,
-"big-endian-desc" property should be specified.
-If both big endian registers and descriptors are used by the controller
-implementation, "big-endian" property can be specified instead of having
-both "big-endian-regs" and "big-endian-desc".
-
-Example (Sequoia 440EPx):
- ehci@e0000300 {
- compatible = "ibm,usb-ehci-440epx", "usb-ehci";
- interrupt-parent = <&UIC0>;
- interrupts = <1a 4>;
- reg = <0 e0000300 90 0 e0000390 70>;
- big-endian;
- };
+++ /dev/null
- d) Xilinx IP cores
-
- The Xilinx EDK toolchain ships with a set of IP cores (devices) for use
- in Xilinx Spartan and Virtex FPGAs. The devices cover the whole range
- of standard device types (network, serial, etc.) and miscellaneous
- devices (gpio, LCD, spi, etc). Also, since these devices are
- implemented within the fpga fabric every instance of the device can be
- synthesised with different options that change the behaviour.
-
- Each IP-core has a set of parameters which the FPGA designer can use to
- control how the core is synthesized. Historically, the EDK tool would
- extract the device parameters relevant to device drivers and copy them
- into an 'xparameters.h' in the form of #define symbols. This tells the
- device drivers how the IP cores are configured, but it requires the kernel
- to be recompiled every time the FPGA bitstream is resynthesized.
-
- The new approach is to export the parameters into the device tree and
- generate a new device tree each time the FPGA bitstream changes. The
- parameters which used to be exported as #defines will now become
- properties of the device node. In general, device nodes for IP-cores
- will take the following form:
-
- (name): (generic-name)@(base-address) {
- compatible = "xlnx,(ip-core-name)-(HW_VER)"
- [, (list of compatible devices), ...];
- reg = <(baseaddr) (size)>;
- interrupt-parent = <&interrupt-controller-phandle>;
- interrupts = < ... >;
- xlnx,(parameter1) = "(string-value)";
- xlnx,(parameter2) = <(int-value)>;
- };
-
- (generic-name): an open firmware-style name that describes the
- generic class of device. Preferably, this is one word, such
- as 'serial' or 'ethernet'.
- (ip-core-name): the name of the ip block (given after the BEGIN
- directive in system.mhs). Should be in lowercase
- and all underscores '_' converted to dashes '-'.
- (name): is derived from the "PARAMETER INSTANCE" value.
- (parameter#): C_* parameters from system.mhs. The C_ prefix is
- dropped from the parameter name, the name is converted
- to lowercase and all underscore '_' characters are
- converted to dashes '-'.
- (baseaddr): the baseaddr parameter value (often named C_BASEADDR).
- (HW_VER): from the HW_VER parameter.
- (size): the address range size (often C_HIGHADDR - C_BASEADDR + 1).
-
- Typically, the compatible list will include the exact IP core version
- followed by an older IP core version which implements the same
- interface or any other device with the same interface.
-
- 'reg', 'interrupt-parent' and 'interrupts' are all optional properties.
-
- For example, the following block from system.mhs:
-
- BEGIN opb_uartlite
- PARAMETER INSTANCE = opb_uartlite_0
- PARAMETER HW_VER = 1.00.b
- PARAMETER C_BAUDRATE = 115200
- PARAMETER C_DATA_BITS = 8
- PARAMETER C_ODD_PARITY = 0
- PARAMETER C_USE_PARITY = 0
- PARAMETER C_CLK_FREQ = 50000000
- PARAMETER C_BASEADDR = 0xEC100000
- PARAMETER C_HIGHADDR = 0xEC10FFFF
- BUS_INTERFACE SOPB = opb_7
- PORT OPB_Clk = CLK_50MHz
- PORT Interrupt = opb_uartlite_0_Interrupt
- PORT RX = opb_uartlite_0_RX
- PORT TX = opb_uartlite_0_TX
- PORT OPB_Rst = sys_bus_reset_0
- END
-
- becomes the following device tree node:
-
- opb_uartlite_0: serial@ec100000 {
- device_type = "serial";
- compatible = "xlnx,opb-uartlite-1.00.b";
- reg = <ec100000 10000>;
- interrupt-parent = <&opb_intc_0>;
- interrupts = <1 0>; // got this from the opb_intc parameters
- current-speed = <d#115200>; // standard serial device prop
- clock-frequency = <d#50000000>; // standard serial device prop
- xlnx,data-bits = <8>;
- xlnx,odd-parity = <0>;
- xlnx,use-parity = <0>;
- };
-
- Some IP cores actually implement 2 or more logical devices. In
- this case, the device should still describe the whole IP core with
- a single node and add a child node for each logical device. The
- ranges property can be used to translate from parent IP-core to the
- registers of each device. In addition, the parent node should be
- compatible with the bus type 'xlnx,compound', and should contain
- #address-cells and #size-cells, as with any other bus. (Note: this
- makes the assumption that both logical devices have the same bus
- binding. If this is not true, then separate nodes should be used
- for each logical device). The 'cell-index' property can be used to
- enumerate logical devices within an IP core. For example, the
- following is the system.mhs entry for the dual ps2 controller found
- on the ml403 reference design.
-
- BEGIN opb_ps2_dual_ref
- PARAMETER INSTANCE = opb_ps2_dual_ref_0
- PARAMETER HW_VER = 1.00.a
- PARAMETER C_BASEADDR = 0xA9000000
- PARAMETER C_HIGHADDR = 0xA9001FFF
- BUS_INTERFACE SOPB = opb_v20_0
- PORT Sys_Intr1 = ps2_1_intr
- PORT Sys_Intr2 = ps2_2_intr
- PORT Clkin1 = ps2_clk_rx_1
- PORT Clkin2 = ps2_clk_rx_2
- PORT Clkpd1 = ps2_clk_tx_1
- PORT Clkpd2 = ps2_clk_tx_2
- PORT Rx1 = ps2_d_rx_1
- PORT Rx2 = ps2_d_rx_2
- PORT Txpd1 = ps2_d_tx_1
- PORT Txpd2 = ps2_d_tx_2
- END
-
- It would result in the following device tree nodes:
-
- opb_ps2_dual_ref_0: opb-ps2-dual-ref@a9000000 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "xlnx,compound";
- ranges = <0 a9000000 2000>;
- // If this device had extra parameters, then they would
- // go here.
- ps2@0 {
- compatible = "xlnx,opb-ps2-dual-ref-1.00.a";
- reg = <0 40>;
- interrupt-parent = <&opb_intc_0>;
- interrupts = <3 0>;
- cell-index = <0>;
- };
- ps2@1000 {
- compatible = "xlnx,opb-ps2-dual-ref-1.00.a";
- reg = <1000 40>;
- interrupt-parent = <&opb_intc_0>;
- interrupts = <3 0>;
- cell-index = <0>;
- };
- };
-
- Also, the system.mhs file defines bus attachments from the processor
- to the devices. The device tree structure should reflect the bus
- attachments. Again an example; this system.mhs fragment:
-
- BEGIN ppc405_virtex4
- PARAMETER INSTANCE = ppc405_0
- PARAMETER HW_VER = 1.01.a
- BUS_INTERFACE DPLB = plb_v34_0
- BUS_INTERFACE IPLB = plb_v34_0
- END
-
- BEGIN opb_intc
- PARAMETER INSTANCE = opb_intc_0
- PARAMETER HW_VER = 1.00.c
- PARAMETER C_BASEADDR = 0xD1000FC0
- PARAMETER C_HIGHADDR = 0xD1000FDF
- BUS_INTERFACE SOPB = opb_v20_0
- END
-
- BEGIN opb_uart16550
- PARAMETER INSTANCE = opb_uart16550_0
- PARAMETER HW_VER = 1.00.d
- PARAMETER C_BASEADDR = 0xa0000000
- PARAMETER C_HIGHADDR = 0xa0001FFF
- BUS_INTERFACE SOPB = opb_v20_0
- END
-
- BEGIN plb_v34
- PARAMETER INSTANCE = plb_v34_0
- PARAMETER HW_VER = 1.02.a
- END
-
- BEGIN plb_bram_if_cntlr
- PARAMETER INSTANCE = plb_bram_if_cntlr_0
- PARAMETER HW_VER = 1.00.b
- PARAMETER C_BASEADDR = 0xFFFF0000
- PARAMETER C_HIGHADDR = 0xFFFFFFFF
- BUS_INTERFACE SPLB = plb_v34_0
- END
-
- BEGIN plb2opb_bridge
- PARAMETER INSTANCE = plb2opb_bridge_0
- PARAMETER HW_VER = 1.01.a
- PARAMETER C_RNG0_BASEADDR = 0x20000000
- PARAMETER C_RNG0_HIGHADDR = 0x3FFFFFFF
- PARAMETER C_RNG1_BASEADDR = 0x60000000
- PARAMETER C_RNG1_HIGHADDR = 0x7FFFFFFF
- PARAMETER C_RNG2_BASEADDR = 0x80000000
- PARAMETER C_RNG2_HIGHADDR = 0xBFFFFFFF
- PARAMETER C_RNG3_BASEADDR = 0xC0000000
- PARAMETER C_RNG3_HIGHADDR = 0xDFFFFFFF
- BUS_INTERFACE SPLB = plb_v34_0
- BUS_INTERFACE MOPB = opb_v20_0
- END
-
- Gives this device tree (some properties removed for clarity):
-
- plb@0 {
- #address-cells = <1>;
- #size-cells = <1>;
- compatible = "xlnx,plb-v34-1.02.a";
- device_type = "ibm,plb";
- ranges; // 1:1 translation
-
- plb_bram_if_cntrl_0: bram@ffff0000 {
- reg = <ffff0000 10000>;
- }
-
- opb@20000000 {
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <20000000 20000000 20000000
- 60000000 60000000 20000000
- 80000000 80000000 40000000
- c0000000 c0000000 20000000>;
-
- opb_uart16550_0: serial@a0000000 {
- reg = <a00000000 2000>;
- };
-
- opb_intc_0: interrupt-controller@d1000fc0 {
- reg = <d1000fc0 20>;
- };
- };
- };
-
- That covers the general approach to binding xilinx IP cores into the
- device tree. The following are bindings for specific devices:
-
- i) Xilinx ML300 Framebuffer
-
- Simple framebuffer device from the ML300 reference design (also on the
- ML403 reference design as well as others).
-
- Optional properties:
- - resolution = <xres yres> : pixel resolution of framebuffer. Some
- implementations use a different resolution.
- Default is <d#640 d#480>
- - virt-resolution = <xvirt yvirt> : Size of framebuffer in memory.
- Default is <d#1024 d#480>.
- - rotate-display (empty) : rotate display 180 degrees.
-
- ii) Xilinx SystemACE
-
- The Xilinx SystemACE device is used to program FPGAs from an FPGA
- bitstream stored on a CF card. It can also be used as a generic CF
- interface device.
-
- Optional properties:
- - 8-bit (empty) : Set this property for SystemACE in 8 bit mode
-
- iii) Xilinx EMAC and Xilinx TEMAC
-
- Xilinx Ethernet devices. In addition to general xilinx properties
- listed above, nodes for these devices should include a phy-handle
- property, and may include other common network device properties
- like local-mac-address.
-
- iv) Xilinx Uartlite
-
- Xilinx uartlite devices are simple fixed speed serial ports.
-
- Required properties:
- - current-speed : Baud rate of uartlite
-
- v) Xilinx hwicap
-
- Xilinx hwicap devices provide access to the configuration logic
- of the FPGA through the Internal Configuration Access Port
- (ICAP). The ICAP enables partial reconfiguration of the FPGA,
- readback of the configuration information, and some control over
- 'warm boots' of the FPGA fabric.
-
- Required properties:
- - xlnx,family : The family of the FPGA, necessary since the
- capabilities of the underlying ICAP hardware
- differ between different families. May be
- 'virtex2p', 'virtex4', or 'virtex5'.
-
- vi) Xilinx Uart 16550
-
- Xilinx UART 16550 devices are very similar to the NS16550 but with
- different register spacing and an offset from the base address.
-
- Required properties:
- - clock-frequency : Frequency of the clock input
- - reg-offset : A value of 3 is required
- - reg-shift : A value of 2 is required
-
- vii) Xilinx USB Host controller
-
- The Xilinx USB host controller is EHCI compatible but with a different
- base address for the EHCI registers, and it is always a big-endian
- USB Host controller. The hardware can be configured as high speed only,
- or high speed/full speed hybrid.
-
- Required properties:
- - xlnx,support-usb-fs: A value 0 means the core is built as high speed
- only. A value 1 means the core also supports
- full speed devices.
-
setting the longer alarm time and enabling its IRQ using a single
request (using the same model as EFI firmware).
- * RTC_UIE_ON, RTC_UIE_OFF ... if the RTC offers IRQs, it probably
- also offers update IRQs whenever the "seconds" counter changes.
- If needed, the RTC framework can emulate this mechanism.
+ * RTC_UIE_ON, RTC_UIE_OFF ... if the RTC offers IRQs, the RTC framework
+ will emulate this mechanism.
- * RTC_PIE_ON, RTC_PIE_OFF, RTC_IRQP_SET, RTC_IRQP_READ ... another
- feature often accessible with an IRQ line is a periodic IRQ, issued
- at settable frequencies (usually 2^N Hz).
+ * RTC_PIE_ON, RTC_PIE_OFF, RTC_IRQP_SET, RTC_IRQP_READ ... these icotls
+ are emulated via a kernel hrtimer.
In many cases, the RTC alarm can be a system wake event, used to force
Linux out of a low power sleep state (or hibernation) back to a fully
operational state. For example, a system could enter a deep power saving
state until it's time to execute some scheduled tasks.
-Note that many of these ioctls need not actually be implemented by your
-driver. The common rtc-dev interface handles many of these nicely if your
-driver returns ENOIOCTLCMD. Some common examples:
+Note that many of these ioctls are handled by the common rtc-dev interface.
+Some common examples:
* RTC_RD_TIME, RTC_SET_TIME: the read_time/set_time functions will be
called with appropriate values.
- * RTC_ALM_SET, RTC_ALM_READ, RTC_WKALM_SET, RTC_WKALM_RD: the
- set_alarm/read_alarm functions will be called.
+ * RTC_ALM_SET, RTC_ALM_READ, RTC_WKALM_SET, RTC_WKALM_RD: gets or sets
+ the alarm rtc_timer. May call the set_alarm driver function.
- * RTC_IRQP_SET, RTC_IRQP_READ: the irq_set_freq function will be called
- to set the frequency while the framework will handle the read for you
- since the frequency is stored in the irq_freq member of the rtc_device
- structure. Your driver needs to initialize the irq_freq member during
- init. Make sure you check the requested frequency is in range of your
- hardware in the irq_set_freq function. If it isn't, return -EINVAL. If
- you cannot actually change the frequency, do not define irq_set_freq.
+ * RTC_IRQP_SET, RTC_IRQP_READ: These are emulated by the generic code.
- * RTC_PIE_ON, RTC_PIE_OFF: the irq_set_state function will be called.
+ * RTC_PIE_ON, RTC_PIE_OFF: These are also emulated by the generic code.
If all else fails, check out the rtc-test.c driver!
The routines look the same as above:
- rwlock_t xxx_lock = RW_LOCK_UNLOCKED;
+ rwlock_t xxx_lock = __RW_LOCK_UNLOCKED(xxx_lock);
unsigned long flags;
For static initialization, use DEFINE_SPINLOCK() / DEFINE_RWLOCK() or
__SPIN_LOCK_UNLOCKED() / __RW_LOCK_UNLOCKED() as appropriate.
-
-SPIN_LOCK_UNLOCKED and RW_LOCK_UNLOCKED are deprecated. These interfere
-with lockdep state tracking.
-
-Most of the time, you can simply turn:
- static spinlock_t xxx_lock = SPIN_LOCK_UNLOCKED;
-into:
- static DEFINE_SPINLOCK(xxx_lock);
-
-Static structure member variables go from:
-
- struct foo bar {
- .lock = SPIN_LOCK_UNLOCKED;
- };
-
-to:
-
- struct foo bar {
- .lock = __SPIN_LOCK_UNLOCKED(bar.lock);
- };
-
-Declaration of static rw_locks undergo a similar transformation.
- Support the TIF_SYSCALL_TRACEPOINT thread flags.
- Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace
in the ptrace syscalls tracing path.
+- If the system call table on this arch is more complicated than a simple array
+ of addresses of the system calls, implement an arch_syscall_addr to return
+ the address of a given system call.
+- If the symbol names of the system calls do not match the function names on
+ this arch, define ARCH_HAS_SYSCALL_MATCH_SYM_NAME in asm/ftrace.h and
+ implement arch_syscall_match_sym_name with the appropriate logic to return
+ true if the function name corresponds with the symbol name.
- Tag this arch as HAVE_SYSCALL_TRACEPOINTS.
tracers listed here can be configured by
echoing their name into current_tracer.
- tracing_enabled:
+ tracing_on:
- This sets or displays whether the current_tracer
- is activated and tracing or not. Echo 0 into this
- file to disable the tracer or 1 to enable it.
+ This sets or displays whether writing to the trace
+ ring buffer is enabled. Echo 0 into this file to disable
+ the tracer or 1 to enable it.
trace:
to draw a graph of function calls similar to C code
source.
- "sched_switch"
-
- Traces the context switches and wakeups between tasks.
-
"irqsoff"
Traces the areas that disable interrupts and saves
parent function that called this function "path_walk". The
timestamp is the time at which the function was entered.
-The sched_switch tracer also includes tracing of task wakeups
-and context switches.
-
- ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 2916:115:S
- ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 10:115:S
- ksoftirqd/1-7 [01] 1453.070013: 7:115:R ==> 10:115:R
- events/1-10 [01] 1453.070013: 10:115:S ==> 2916:115:R
- kondemand/1-2916 [01] 1453.070013: 2916:115:S ==> 7:115:R
- ksoftirqd/1-7 [01] 1453.070013: 7:115:S ==> 0:140:R
-
-Wake ups are represented by a "+" and the context switches are
-shown as "==>". The format is:
-
- Context switches:
-
- Previous task Next Task
-
- <pid>:<prio>:<state> ==> <pid>:<prio>:<state>
-
- Wake ups:
-
- Current task Task waking up
-
- <pid>:<prio>:<state> + <pid>:<prio>:<state>
-
-The prio is the internal kernel priority, which is the inverse
-of the priority that is usually displayed by user-space tools.
-Zero represents the highest priority (99). Prio 100 starts the
-"nice" priorities with 100 being equal to nice -20 and 139 being
-nice 19. The prio "140" is reserved for the idle task which is
-the lowest priority thread (pid 0).
-
-
Latency trace format
--------------------
latencies, as described in "Latency
trace format".
-sched_switch
-------------
-
-This tracer simply records schedule switches. Here is an example
-of how to use it.
-
- # echo sched_switch > current_tracer
- # echo 1 > tracing_enabled
- # sleep 1
- # echo 0 > tracing_enabled
- # cat trace
-
-# tracer: sched_switch
-#
-# TASK-PID CPU# TIMESTAMP FUNCTION
-# | | | | |
- bash-3997 [01] 240.132281: 3997:120:R + 4055:120:R
- bash-3997 [01] 240.132284: 3997:120:R ==> 4055:120:R
- sleep-4055 [01] 240.132371: 4055:120:S ==> 3997:120:R
- bash-3997 [01] 240.132454: 3997:120:R + 4055:120:S
- bash-3997 [01] 240.132457: 3997:120:R ==> 4055:120:R
- sleep-4055 [01] 240.132460: 4055:120:D ==> 3997:120:R
- bash-3997 [01] 240.132463: 3997:120:R + 4055:120:D
- bash-3997 [01] 240.132465: 3997:120:R ==> 4055:120:R
- <idle>-0 [00] 240.132589: 0:140:R + 4:115:S
- <idle>-0 [00] 240.132591: 0:140:R ==> 4:115:R
- ksoftirqd/0-4 [00] 240.132595: 4:115:S ==> 0:140:R
- <idle>-0 [00] 240.132598: 0:140:R + 4:115:S
- <idle>-0 [00] 240.132599: 0:140:R ==> 4:115:R
- ksoftirqd/0-4 [00] 240.132603: 4:115:S ==> 0:140:R
- sleep-4055 [01] 240.133058: 4055:120:S ==> 3997:120:R
- [...]
-
-
-As we have discussed previously about this format, the header
-shows the name of the trace and points to the options. The
-"FUNCTION" is a misnomer since here it represents the wake ups
-and context switches.
-
-The sched_switch file only lists the wake ups (represented with
-'+') and context switches ('==>') with the previous task or
-current task first followed by the next task or task waking up.
-The format for both of these is PID:KERNEL-PRIO:TASK-STATE.
-Remember that the KERNEL-PRIO is the inverse of the actual
-priority with zero (0) being the highest priority and the nice
-values starting at 100 (nice -20). Below is a quick chart to map
-the kernel priority to user land priorities.
-
- Kernel Space User Space
- ===============================================================
- 0(high) to 98(low) user RT priority 99(high) to 1(low)
- with SCHED_RR or SCHED_FIFO
- ---------------------------------------------------------------
- 99 sched_priority is not used in scheduling
- decisions(it must be specified as 0)
- ---------------------------------------------------------------
- 100(high) to 139(low) user nice -20(high) to 19(low)
- ---------------------------------------------------------------
- 140 idle task priority
- ---------------------------------------------------------------
-
-The task states are:
-
- R - running : wants to run, may not actually be running
- S - sleep : process is waiting to be woken up (handles signals)
- D - disk sleep (uninterruptible sleep) : process must be woken up
- (ignores signals)
- T - stopped : process suspended
- t - traced : process is being traced (with something like gdb)
- Z - zombie : process waiting to be cleaned up
- X - unknown
-
+ overwrite - This controls what happens when the trace buffer is
+ full. If "1" (default), the oldest events are
+ discarded and overwritten. If "0", then the newest
+ events are discarded.
ftrace_enabled
--------------
# echo irqsoff > current_tracer
# echo latency-format > trace_options
# echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
# ls -ltr
[...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
# cat trace
# tracer: irqsoff
#
# echo preemptoff > current_tracer
# echo latency-format > trace_options
# echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
# ls -ltr
[...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
# cat trace
# tracer: preemptoff
#
# echo preemptirqsoff > current_tracer
# echo latency-format > trace_options
# echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
# ls -ltr
[...]
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
# cat trace
# tracer: preemptirqsoff
#
# echo wakeup > current_tracer
# echo latency-format > trace_options
# echo 0 > tracing_max_latency
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
# chrt -f 5 sleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
# cat trace
# tracer: wakeup
#
# sysctl kernel.ftrace_enabled=1
# echo function > current_tracer
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
# usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
# cat trace
# tracer: function
#
[...]
int main(int argc, char *argv[]) {
[...]
- trace_fd = open(tracing_file("tracing_enabled"), O_WRONLY);
+ trace_fd = open(tracing_file("tracing_on"), O_WRONLY);
[...]
if (condition_hit()) {
write(trace_fd, "0", 1);
# echo sys_nanosleep hrtimer_interrupt \
> set_ftrace_filter
# echo function > current_tracer
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
# usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
# cat trace
# tracer: ftrace
#
# echo function > current_tracer
# cat trace_pipe > /tmp/trace.out &
[1] 4153
- # echo 1 > tracing_enabled
+ # echo 1 > tracing_on
# usleep 1
- # echo 0 > tracing_enabled
+ # echo 0 > tracing_on
# cat trace
# tracer: function
#
+|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
- (u8/u16/u32/u64/s8/s16/s32/s64) and string are supported.
+ (u8/u16/u32/u64/s8/s16/s32/s64), "string" and bitfield
+ are supported.
(*) only for return probe.
(**) this is useful for fetching a field of data structures.
+Types
+-----
+Several types are supported for fetch-args. Kprobe tracer will access memory
+by given type. Prefix 's' and 'u' means those types are signed and unsigned
+respectively. Traced arguments are shown in decimal (signed) or hex (unsigned).
+String type is a special type, which fetches a "null-terminated" string from
+kernel space. This means it will fail and store NULL if the string container
+has been paged out.
+Bitfield is another special type, which takes 3 parameters, bit-width, bit-
+offset, and container-size (usually 32). The syntax is;
+
+ b<bit-width>@<bit-offset>/<container-size>
+
Per-Probe Event Filtering
-------------------------
* Long running CPU intensive workloads which can be better
managed by the system scheduler.
- WQ_FREEZEABLE
+ WQ_FREEZABLE
- A freezeable wq participates in the freeze phase of the system
+ A freezable wq participates in the freeze phase of the system
suspend operations. Work items on the wq are drained and no
new work item starts execution until thawed.
ARM/QUALCOMM MSM MACHINE SUPPORT
M: David Brown <davidb@codeaurora.org>
-M: Daniel Walker <dwalker@codeaurora.org>
+M: Daniel Walker <dwalker@fifo99.com>
M: Bryan Huntsman <bryanh@codeaurora.org>
L: linux-arm-msm@vger.kernel.org
F: arch/arm/mach-msm/
S: Maintained
F: arch/arm/mach-s5p*/
+ARM/SAMSUNG MOBILE MACHINE SUPPORT
+M: Kyungmin Park <kyungmin.park@samsung.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: arch/arm/mach-s5pv210/mach-aquila.c
+F: arch/arm/mach-s5pv210/mach-goni.c
+F: arch/arm/mach-exynos4/mach-universal_c210.c
+F: arch/arm/mach-exynos4/mach-nuri.c
+
ARM/SAMSUNG S5P SERIES FIMC SUPPORT
M: Kyungmin Park <kyungmin.park@samsung.com>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
BONDING DRIVER
M: Jay Vosburgh <fubar@us.ibm.com>
+M: Andy Gospodarek <andy@greyhouse.net>
L: netdev@vger.kernel.org
W: http://sourceforge.net/projects/bonding/
S: Supported
S: Supported
F: scripts/checkpatch.pl
+CHINESE DOCUMENTATION
+M: Harry Wei <harryxiyou@gmail.com>
+L: xiyoulinuxkernelgroup@googlegroups.com
+L: linux-kernel@zh-kernel.org (moderated for non-subscribers)
+S: Maintained
+F: Documentation/zh_CN/
+
CISCO VIC ETHERNET NIC DRIVER
M: Vasanthy Kolluri <vkolluri@cisco.com>
M: Roopa Prabhu <roprabhu@cisco.com>
F: drivers/scsi/dc395x.*
DCCP PROTOCOL
-M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
+M: Gerrit Renker <gerrit@erg.abdn.ac.uk>
L: dccp@vger.kernel.org
W: http://www.linuxfoundation.org/collaborate/workgroups/networking/dccp
S: Maintained
F: fs/dlm/
DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
+M: Vinod Koul <vinod.koul@intel.com>
M: Dan Williams <dan.j.williams@intel.com>
S: Supported
F: drivers/dma/
F: drivers/isdn/gigaset/
F: include/linux/gigaset_dev.h
+GPIO SUBSYSTEM
+M: Grant Likely <grant.likely@secretlab.ca>
+L: linux-kernel@vger.kernel.org
+S: Maintained
+T: git git://git.secretlab.ca/git/linux-2.6.git
+F: Documentation/gpio/gpio.txt
+F: drivers/gpio/
+F: include/linux/gpio*
+
GRETH 10/100/1G Ethernet MAC device driver
M: Kristoffer Glembo <kristoffer@gaisler.com>
L: netdev@vger.kernel.org
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 kernel.org/pub/linux/kernel/people/groeck/linux-staging/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
S: Maintained
F: Documentation/hwmon/
F: Documentation/hwmon/jc42
JFS FILESYSTEM
-M: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
+M: Dave Kleikamp <shaggy@kernel.org>
L: jfs-discussion@lists.sourceforge.net
W: http://jfs.sourceforge.net/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shaggy/jfs-2.6.git
F: net/sched/sch_netem.c
NETERION 10GbE DRIVERS (s2io/vxge)
-M: Ramkrishna Vepa <ramkrishna.vepa@exar.com>
-M: Sivakumar Subramani <sivakumar.subramani@exar.com>
-M: Sreenivasa Honnur <sreenivasa.honnur@exar.com>
-M: Jon Mason <jon.mason@exar.com>
+M: Jon Mason <jdmason@kudzu.us>
L: netdev@vger.kernel.org
W: http://trac.neterion.com/cgi-bin/trac.cgi/wiki/Linux?Anonymous
W: http://trac.neterion.com/cgi-bin/trac.cgi/wiki/X3100Linux?Anonymous
OPEN FIRMWARE AND FLATTENED DEVICE TREE
M: Grant Likely <grant.likely@secretlab.ca>
-L: devicetree-discuss@lists.ozlabs.org
+L: devicetree-discuss@lists.ozlabs.org (moderated for non-subscribers)
W: http://fdt.secretlab.ca
T: git git://git.secretlab.ca/git/linux-2.6.git
S: Maintained
RAPIDIO SUBSYSTEM
M: Matt Porter <mporter@kernel.crashing.org>
+M: Alexandre Bounine <alexandre.bounine@idt.com>
S: Maintained
F: drivers/rapidio/
F: drivers/net/wireless/rtl818x/rtl8180/
RTL8187 WIRELESS DRIVER
-M: Herton Ronaldo Krzesinski <herton@mandriva.com.br>
+M: Herton Ronaldo Krzesinski <herton@canonical.com>
M: Hin-Tak Leung <htl10@users.sourceforge.net>
M: Larry Finger <Larry.Finger@lwfinger.net>
L: linux-wireless@vger.kernel.org
F: security/tomoyo/
TOPSTAR LAPTOP EXTRAS DRIVER
-M: Herton Ronaldo Krzesinski <herton@mandriva.com.br>
+M: Herton Ronaldo Krzesinski <herton@canonical.com>
L: platform-driver-x86@vger.kernel.org
S: Maintained
F: drivers/platform/x86/topstar-laptop.c
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 38
-EXTRAVERSION = -rc4
+EXTRAVERSION =
NAME = Flesh-Eating Bats with Fangs
# *DOCUMENTATION*
select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_PROBE
select AUTO_IRQ_AFFINITY if SMP
+ select GENERIC_HARDIRQS_NO_DEPRECATED
help
The Alpha is a 64-bit general-purpose processor designed and
marketed by the Digital Equipment Corporation of blessed memory,
: "r" (uaddr), "r"(oparg) \
: "memory")
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- int prev, cmp;
+ int ret = 0, cmp;
+ u32 prev;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
__asm__ __volatile__ (
__ASM_SMP_MB
- "1: ldl_l %0,0(%2)\n"
- " cmpeq %0,%3,%1\n"
- " beq %1,3f\n"
- " mov %4,%1\n"
- "2: stl_c %1,0(%2)\n"
- " beq %1,4f\n"
+ "1: ldl_l %1,0(%3)\n"
+ " cmpeq %1,%4,%2\n"
+ " beq %2,3f\n"
+ " mov %5,%2\n"
+ "2: stl_c %2,0(%3)\n"
+ " beq %2,4f\n"
"3: .subsection 2\n"
"4: br 1b\n"
" .previous\n"
" .long 2b-.\n"
" lda $31,3b-2b(%0)\n"
" .previous\n"
- : "=&r"(prev), "=&r"(cmp)
+ : "+r"(ret), "=&r"(prev), "=&r"(cmp)
: "r"(uaddr), "r"((long)oldval), "r"(newval)
: "memory");
- return prev;
+ *uval = prev;
+ return ret;
}
#endif /* __KERNEL__ */
#ifdef __KERNEL__
#include <linux/compiler.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-struct rwsem_waiter;
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
- long count;
#define RWSEM_UNLOCKED_VALUE 0x0000000000000000L
#define RWSEM_ACTIVE_BIAS 0x0000000000000001L
#define RWSEM_ACTIVE_MASK 0x00000000ffffffffL
#define RWSEM_WAITING_BIAS (-0x0000000100000000L)
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
- spinlock_t wait_lock;
- struct list_head wait_list;
-};
-
-#define __RWSEM_INITIALIZER(name) \
- { RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \
- LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
- sem->count = RWSEM_UNLOCKED_VALUE;
- spin_lock_init(&sem->wait_lock);
- INIT_LIST_HEAD(&sem->wait_list);
-}
static inline void __down_read(struct rw_semaphore *sem)
{
#endif
}
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
- return (sem->count != 0);
-}
-
#endif /* __KERNEL__ */
#endif /* _ALPHA_RWSEM_H */
int irq_select_affinity(unsigned int irq)
{
- struct irq_desc *desc = irq_to_desc[irq];
+ struct irq_data *data = irq_get_irq_data(irq);
+ struct irq_chip *chip;
static int last_cpu;
int cpu = last_cpu + 1;
- if (!desc || !get_irq_desc_chip(desc)->set_affinity || irq_user_affinity[irq])
+ if (!data)
+ return 1;
+ chip = irq_data_get_irq_chip(data);
+
+ if (!chip->irq_set_affinity || irq_user_affinity[irq])
return 1;
while (!cpu_possible(cpu) ||
cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
last_cpu = cpu;
- cpumask_copy(desc->affinity, cpumask_of(cpu));
- get_irq_desc_chip(desc)->set_affinity(irq, cpumask_of(cpu));
+ cpumask_copy(data->affinity, cpumask_of(cpu));
+ chip->irq_set_affinity(data, cpumask_of(cpu), false);
return 0;
}
#endif /* CONFIG_SMP */
void __init
init_rtc_irq(void)
{
- struct irq_desc *desc = irq_to_desc(RTC_IRQ);
-
- if (desc) {
- desc->status |= IRQ_DISABLED;
- set_irq_chip_and_handler_name(RTC_IRQ, &no_irq_chip,
- handle_simple_irq, "RTC");
- setup_irq(RTC_IRQ, &timer_irqaction);
- }
+ set_irq_chip_and_handler_name(RTC_IRQ, &no_irq_chip,
+ handle_simple_irq, "RTC");
+ setup_irq(RTC_IRQ, &timer_irqaction);
}
/* Dummy irqactions. */
}
inline void
-i8259a_enable_irq(unsigned int irq)
+i8259a_enable_irq(struct irq_data *d)
{
spin_lock(&i8259_irq_lock);
- i8259_update_irq_hw(irq, cached_irq_mask &= ~(1 << irq));
+ i8259_update_irq_hw(d->irq, cached_irq_mask &= ~(1 << d->irq));
spin_unlock(&i8259_irq_lock);
}
}
void
-i8259a_disable_irq(unsigned int irq)
+i8259a_disable_irq(struct irq_data *d)
{
spin_lock(&i8259_irq_lock);
- __i8259a_disable_irq(irq);
+ __i8259a_disable_irq(d->irq);
spin_unlock(&i8259_irq_lock);
}
void
-i8259a_mask_and_ack_irq(unsigned int irq)
+i8259a_mask_and_ack_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
+
spin_lock(&i8259_irq_lock);
__i8259a_disable_irq(irq);
struct irq_chip i8259a_irq_type = {
.name = "XT-PIC",
- .unmask = i8259a_enable_irq,
- .mask = i8259a_disable_irq,
- .mask_ack = i8259a_mask_and_ack_irq,
+ .irq_unmask = i8259a_enable_irq,
+ .irq_mask = i8259a_disable_irq,
+ .irq_mask_ack = i8259a_mask_and_ack_irq,
};
void __init
extern void common_init_isa_dma(void);
-extern void i8259a_enable_irq(unsigned int);
-extern void i8259a_disable_irq(unsigned int);
-extern void i8259a_mask_and_ack_irq(unsigned int);
-extern unsigned int i8259a_startup_irq(unsigned int);
-extern void i8259a_end_irq(unsigned int);
+extern void i8259a_enable_irq(struct irq_data *d);
+extern void i8259a_disable_irq(struct irq_data *d);
+extern void i8259a_mask_and_ack_irq(struct irq_data *d);
extern struct irq_chip i8259a_irq_type;
extern void init_i8259a_irqs(void);
}
static inline void
-pyxis_enable_irq(unsigned int irq)
+pyxis_enable_irq(struct irq_data *d)
{
- pyxis_update_irq_hw(cached_irq_mask |= 1UL << (irq - 16));
+ pyxis_update_irq_hw(cached_irq_mask |= 1UL << (d->irq - 16));
}
static void
-pyxis_disable_irq(unsigned int irq)
+pyxis_disable_irq(struct irq_data *d)
{
- pyxis_update_irq_hw(cached_irq_mask &= ~(1UL << (irq - 16)));
+ pyxis_update_irq_hw(cached_irq_mask &= ~(1UL << (d->irq - 16)));
}
static void
-pyxis_mask_and_ack_irq(unsigned int irq)
+pyxis_mask_and_ack_irq(struct irq_data *d)
{
- unsigned long bit = 1UL << (irq - 16);
+ unsigned long bit = 1UL << (d->irq - 16);
unsigned long mask = cached_irq_mask &= ~bit;
/* Disable the interrupt. */
static struct irq_chip pyxis_irq_type = {
.name = "PYXIS",
- .mask_ack = pyxis_mask_and_ack_irq,
- .mask = pyxis_disable_irq,
- .unmask = pyxis_enable_irq,
+ .irq_mask_ack = pyxis_mask_and_ack_irq,
+ .irq_mask = pyxis_disable_irq,
+ .irq_unmask = pyxis_enable_irq,
};
void
if ((ignore_mask >> i) & 1)
continue;
set_irq_chip_and_handler(i, &pyxis_irq_type, handle_level_irq);
- irq_to_desc(i)->status |= IRQ_LEVEL;
+ irq_set_status_flags(i, IRQ_LEVEL);
}
setup_irq(16+7, &isa_cascade_irqaction);
DEFINE_SPINLOCK(srm_irq_lock);
static inline void
-srm_enable_irq(unsigned int irq)
+srm_enable_irq(struct irq_data *d)
{
spin_lock(&srm_irq_lock);
- cserve_ena(irq - 16);
+ cserve_ena(d->irq - 16);
spin_unlock(&srm_irq_lock);
}
static void
-srm_disable_irq(unsigned int irq)
+srm_disable_irq(struct irq_data *d)
{
spin_lock(&srm_irq_lock);
- cserve_dis(irq - 16);
+ cserve_dis(d->irq - 16);
spin_unlock(&srm_irq_lock);
}
/* Handle interrupts from the SRM, assuming no additional weirdness. */
static struct irq_chip srm_irq_type = {
.name = "SRM",
- .unmask = srm_enable_irq,
- .mask = srm_disable_irq,
- .mask_ack = srm_disable_irq,
+ .irq_unmask = srm_enable_irq,
+ .irq_mask = srm_disable_irq,
+ .irq_mask_ack = srm_disable_irq,
};
void __init
if (i < 64 && ((ignore_mask >> i) & 1))
continue;
set_irq_chip_and_handler(i, &srm_irq_type, handle_level_irq);
- irq_to_desc(i)->status |= IRQ_LEVEL;
+ irq_set_status_flags(i, IRQ_LEVEL);
}
}
return copy_to_user(osf_stat, &tmp_stat, bufsiz) ? -EFAULT : 0;
}
-static int
-do_osf_statfs(struct path *path, struct osf_statfs __user *buffer,
- unsigned long bufsiz)
+SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname,
+ struct osf_statfs __user *, buffer, unsigned long, bufsiz)
{
struct kstatfs linux_stat;
- int error = vfs_statfs(path, &linux_stat);
+ int error = user_statfs(pathname, &linux_stat);
if (!error)
error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz);
return error;
}
-SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname,
- struct osf_statfs __user *, buffer, unsigned long, bufsiz)
-{
- struct path path;
- int retval;
-
- retval = user_path(pathname, &path);
- if (!retval) {
- retval = do_osf_statfs(&path, buffer, bufsiz);
- path_put(&path);
- }
- return retval;
-}
-
SYSCALL_DEFINE3(osf_fstatfs, unsigned long, fd,
struct osf_statfs __user *, buffer, unsigned long, bufsiz)
{
- struct file *file;
- int retval;
-
- retval = -EBADF;
- file = fget(fd);
- if (file) {
- retval = do_osf_statfs(&file->f_path, buffer, bufsiz);
- fput(file);
- }
- return retval;
+ struct kstatfs linux_stat;
+ int error = fd_statfs(fd, &linux_stat);
+ if (!error)
+ error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz);
+ return error;
}
/*
}
static inline void
-alcor_enable_irq(unsigned int irq)
+alcor_enable_irq(struct irq_data *d)
{
- alcor_update_irq_hw(cached_irq_mask |= 1UL << (irq - 16));
+ alcor_update_irq_hw(cached_irq_mask |= 1UL << (d->irq - 16));
}
static void
-alcor_disable_irq(unsigned int irq)
+alcor_disable_irq(struct irq_data *d)
{
- alcor_update_irq_hw(cached_irq_mask &= ~(1UL << (irq - 16)));
+ alcor_update_irq_hw(cached_irq_mask &= ~(1UL << (d->irq - 16)));
}
static void
-alcor_mask_and_ack_irq(unsigned int irq)
+alcor_mask_and_ack_irq(struct irq_data *d)
{
- alcor_disable_irq(irq);
+ alcor_disable_irq(d);
/* On ALCOR/XLT, need to dismiss interrupt via GRU. */
- *(vuip)GRU_INT_CLEAR = 1 << (irq - 16); mb();
+ *(vuip)GRU_INT_CLEAR = 1 << (d->irq - 16); mb();
*(vuip)GRU_INT_CLEAR = 0; mb();
}
static void
-alcor_isa_mask_and_ack_irq(unsigned int irq)
+alcor_isa_mask_and_ack_irq(struct irq_data *d)
{
- i8259a_mask_and_ack_irq(irq);
+ i8259a_mask_and_ack_irq(d);
/* On ALCOR/XLT, need to dismiss interrupt via GRU. */
*(vuip)GRU_INT_CLEAR = 0x80000000; mb();
static struct irq_chip alcor_irq_type = {
.name = "ALCOR",
- .unmask = alcor_enable_irq,
- .mask = alcor_disable_irq,
- .mask_ack = alcor_mask_and_ack_irq,
+ .irq_unmask = alcor_enable_irq,
+ .irq_mask = alcor_disable_irq,
+ .irq_mask_ack = alcor_mask_and_ack_irq,
};
static void
if (i >= 16+20 && i <= 16+30)
continue;
set_irq_chip_and_handler(i, &alcor_irq_type, handle_level_irq);
- irq_to_desc(i)->status |= IRQ_LEVEL;
+ irq_set_status_flags(i, IRQ_LEVEL);
}
- i8259a_irq_type.ack = alcor_isa_mask_and_ack_irq;
+ i8259a_irq_type.irq_ack = alcor_isa_mask_and_ack_irq;
init_i8259a_irqs();
common_init_isa_dma();
}
static inline void
-cabriolet_enable_irq(unsigned int irq)
+cabriolet_enable_irq(struct irq_data *d)
{
- cabriolet_update_irq_hw(irq, cached_irq_mask &= ~(1UL << irq));
+ cabriolet_update_irq_hw(d->irq, cached_irq_mask &= ~(1UL << d->irq));
}
static void
-cabriolet_disable_irq(unsigned int irq)
+cabriolet_disable_irq(struct irq_data *d)
{
- cabriolet_update_irq_hw(irq, cached_irq_mask |= 1UL << irq);
+ cabriolet_update_irq_hw(d->irq, cached_irq_mask |= 1UL << d->irq);
}
static struct irq_chip cabriolet_irq_type = {
.name = "CABRIOLET",
- .unmask = cabriolet_enable_irq,
- .mask = cabriolet_disable_irq,
- .mask_ack = cabriolet_disable_irq,
+ .irq_unmask = cabriolet_enable_irq,
+ .irq_mask = cabriolet_disable_irq,
+ .irq_mask_ack = cabriolet_disable_irq,
};
static void
for (i = 16; i < 35; ++i) {
set_irq_chip_and_handler(i, &cabriolet_irq_type,
handle_level_irq);
- irq_to_desc(i)->status |= IRQ_LEVEL;
+ irq_set_status_flags(i, IRQ_LEVEL);
}
}
}
static void
-dp264_enable_irq(unsigned int irq)
+dp264_enable_irq(struct irq_data *d)
{
spin_lock(&dp264_irq_lock);
- cached_irq_mask |= 1UL << irq;
+ cached_irq_mask |= 1UL << d->irq;
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
}
static void
-dp264_disable_irq(unsigned int irq)
+dp264_disable_irq(struct irq_data *d)
{
spin_lock(&dp264_irq_lock);
- cached_irq_mask &= ~(1UL << irq);
+ cached_irq_mask &= ~(1UL << d->irq);
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
}
static void
-clipper_enable_irq(unsigned int irq)
+clipper_enable_irq(struct irq_data *d)
{
spin_lock(&dp264_irq_lock);
- cached_irq_mask |= 1UL << (irq - 16);
+ cached_irq_mask |= 1UL << (d->irq - 16);
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
}
static void
-clipper_disable_irq(unsigned int irq)
+clipper_disable_irq(struct irq_data *d)
{
spin_lock(&dp264_irq_lock);
- cached_irq_mask &= ~(1UL << (irq - 16));
+ cached_irq_mask &= ~(1UL << (d->irq - 16));
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
}
}
static int
-dp264_set_affinity(unsigned int irq, const struct cpumask *affinity)
-{
+dp264_set_affinity(struct irq_data *d, const struct cpumask *affinity,
+ bool force)
+{
spin_lock(&dp264_irq_lock);
- cpu_set_irq_affinity(irq, *affinity);
+ cpu_set_irq_affinity(d->irq, *affinity);
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
}
static int
-clipper_set_affinity(unsigned int irq, const struct cpumask *affinity)
-{
+clipper_set_affinity(struct irq_data *d, const struct cpumask *affinity,
+ bool force)
+{
spin_lock(&dp264_irq_lock);
- cpu_set_irq_affinity(irq - 16, *affinity);
+ cpu_set_irq_affinity(d->irq - 16, *affinity);
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
}
static struct irq_chip dp264_irq_type = {
- .name = "DP264",
- .unmask = dp264_enable_irq,
- .mask = dp264_disable_irq,
- .mask_ack = dp264_disable_irq,
- .set_affinity = dp264_set_affinity,
+ .name = "DP264",
+ .irq_unmask = dp264_enable_irq,
+ .irq_mask = dp264_disable_irq,
+ .irq_mask_ack = dp264_disable_irq,
+ .irq_set_affinity = dp264_set_affinity,
};
static struct irq_chip clipper_irq_type = {
- .name = "CLIPPER",
- .unmask = clipper_enable_irq,
- .mask = clipper_disable_irq,
- .mask_ack = clipper_disable_irq,
- .set_affinity = clipper_set_affinity,
+ .name = "CLIPPER",
+ .irq_unmask = clipper_enable_irq,
+ .irq_mask = clipper_disable_irq,
+ .irq_mask_ack = clipper_disable_irq,
+ .irq_set_affinity = clipper_set_affinity,
};
static void
{
long i;
for (i = imin; i <= imax; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, ops, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
}
}
static inline void
-eb64p_enable_irq(unsigned int irq)
+eb64p_enable_irq(struct irq_data *d)
{
- eb64p_update_irq_hw(irq, cached_irq_mask &= ~(1 << irq));
+ eb64p_update_irq_hw(d->irq, cached_irq_mask &= ~(1 << d->irq));
}
static void
-eb64p_disable_irq(unsigned int irq)
+eb64p_disable_irq(struct irq_data *d)
{
- eb64p_update_irq_hw(irq, cached_irq_mask |= 1 << irq);
+ eb64p_update_irq_hw(d->irq, cached_irq_mask |= 1 << d->irq);
}
static struct irq_chip eb64p_irq_type = {
.name = "EB64P",
- .unmask = eb64p_enable_irq,
- .mask = eb64p_disable_irq,
- .mask_ack = eb64p_disable_irq,
+ .irq_unmask = eb64p_enable_irq,
+ .irq_mask = eb64p_disable_irq,
+ .irq_mask_ack = eb64p_disable_irq,
};
static void
init_i8259a_irqs();
for (i = 16; i < 32; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, &eb64p_irq_type, handle_level_irq);
- }
+ irq_set_status_flags(i, IRQ_LEVEL);
+ }
common_init_isa_dma();
setup_irq(16+5, &isa_cascade_irqaction);
}
static inline void
-eiger_enable_irq(unsigned int irq)
+eiger_enable_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
unsigned long mask;
mask = (cached_irq_mask[irq >= 64] &= ~(1UL << (irq & 63)));
eiger_update_irq_hw(irq, mask);
}
static void
-eiger_disable_irq(unsigned int irq)
+eiger_disable_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
unsigned long mask;
mask = (cached_irq_mask[irq >= 64] |= 1UL << (irq & 63));
eiger_update_irq_hw(irq, mask);
static struct irq_chip eiger_irq_type = {
.name = "EIGER",
- .unmask = eiger_enable_irq,
- .mask = eiger_disable_irq,
- .mask_ack = eiger_disable_irq,
+ .irq_unmask = eiger_enable_irq,
+ .irq_mask = eiger_disable_irq,
+ .irq_mask_ack = eiger_disable_irq,
};
static void
init_i8259a_irqs();
for (i = 16; i < 128; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, &eiger_irq_type, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
}
*/
static void
-jensen_local_enable(unsigned int irq)
+jensen_local_enable(struct irq_data *d)
{
/* the parport is really hw IRQ 1, silly Jensen. */
- if (irq == 7)
- i8259a_enable_irq(1);
+ if (d->irq == 7)
+ i8259a_enable_irq(d);
}
static void
-jensen_local_disable(unsigned int irq)
+jensen_local_disable(struct irq_data *d)
{
/* the parport is really hw IRQ 1, silly Jensen. */
- if (irq == 7)
- i8259a_disable_irq(1);
+ if (d->irq == 7)
+ i8259a_disable_irq(d);
}
static void
-jensen_local_mask_ack(unsigned int irq)
+jensen_local_mask_ack(struct irq_data *d)
{
/* the parport is really hw IRQ 1, silly Jensen. */
- if (irq == 7)
- i8259a_mask_and_ack_irq(1);
+ if (d->irq == 7)
+ i8259a_mask_and_ack_irq(d);
}
static struct irq_chip jensen_local_irq_type = {
.name = "LOCAL",
- .unmask = jensen_local_enable,
- .mask = jensen_local_disable,
- .mask_ack = jensen_local_mask_ack,
+ .irq_unmask = jensen_local_enable,
+ .irq_mask = jensen_local_disable,
+ .irq_mask_ack = jensen_local_mask_ack,
};
static void
}
static void
-io7_enable_irq(unsigned int irq)
+io7_enable_irq(struct irq_data *d)
{
volatile unsigned long *ctl;
+ unsigned int irq = d->irq;
struct io7 *io7;
ctl = io7_get_irq_ctl(irq, &io7);
__func__, irq);
return;
}
-
+
spin_lock(&io7->irq_lock);
*ctl |= 1UL << 24;
mb();
}
static void
-io7_disable_irq(unsigned int irq)
+io7_disable_irq(struct irq_data *d)
{
volatile unsigned long *ctl;
+ unsigned int irq = d->irq;
struct io7 *io7;
ctl = io7_get_irq_ctl(irq, &io7);
__func__, irq);
return;
}
-
+
spin_lock(&io7->irq_lock);
*ctl &= ~(1UL << 24);
mb();
}
static void
-marvel_irq_noop(unsigned int irq)
-{
- return;
-}
-
-static unsigned int
-marvel_irq_noop_return(unsigned int irq)
-{
- return 0;
+marvel_irq_noop(struct irq_data *d)
+{
+ return;
}
static struct irq_chip marvel_legacy_irq_type = {
.name = "LEGACY",
- .mask = marvel_irq_noop,
- .unmask = marvel_irq_noop,
+ .irq_mask = marvel_irq_noop,
+ .irq_unmask = marvel_irq_noop,
};
static struct irq_chip io7_lsi_irq_type = {
.name = "LSI",
- .unmask = io7_enable_irq,
- .mask = io7_disable_irq,
- .mask_ack = io7_disable_irq,
+ .irq_unmask = io7_enable_irq,
+ .irq_mask = io7_disable_irq,
+ .irq_mask_ack = io7_disable_irq,
};
static struct irq_chip io7_msi_irq_type = {
.name = "MSI",
- .unmask = io7_enable_irq,
- .mask = io7_disable_irq,
- .ack = marvel_irq_noop,
+ .irq_unmask = io7_enable_irq,
+ .irq_mask = io7_disable_irq,
+ .irq_ack = marvel_irq_noop,
};
static void
/* Set up the lsi irqs. */
for (i = 0; i < 128; ++i) {
- irq_to_desc(base + i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(base + i, lsi_ops, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
/* Disable the implemented irqs in hardware. */
/* Set up the msi irqs. */
for (i = 128; i < (128 + 512); ++i) {
- irq_to_desc(base + i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(base + i, msi_ops, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
for (i = 0; i < 16; ++i)
}
static inline void
-mikasa_enable_irq(unsigned int irq)
+mikasa_enable_irq(struct irq_data *d)
{
- mikasa_update_irq_hw(cached_irq_mask |= 1 << (irq - 16));
+ mikasa_update_irq_hw(cached_irq_mask |= 1 << (d->irq - 16));
}
static void
-mikasa_disable_irq(unsigned int irq)
+mikasa_disable_irq(struct irq_data *d)
{
- mikasa_update_irq_hw(cached_irq_mask &= ~(1 << (irq - 16)));
+ mikasa_update_irq_hw(cached_irq_mask &= ~(1 << (d->irq - 16)));
}
static struct irq_chip mikasa_irq_type = {
.name = "MIKASA",
- .unmask = mikasa_enable_irq,
- .mask = mikasa_disable_irq,
- .mask_ack = mikasa_disable_irq,
+ .irq_unmask = mikasa_enable_irq,
+ .irq_mask = mikasa_disable_irq,
+ .irq_mask_ack = mikasa_disable_irq,
};
static void
mikasa_update_irq_hw(0);
for (i = 16; i < 32; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, &mikasa_irq_type, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
init_i8259a_irqs();
}
static void
-noritake_enable_irq(unsigned int irq)
+noritake_enable_irq(struct irq_data *d)
{
- noritake_update_irq_hw(irq, cached_irq_mask |= 1 << (irq - 16));
+ noritake_update_irq_hw(d->irq, cached_irq_mask |= 1 << (d->irq - 16));
}
static void
-noritake_disable_irq(unsigned int irq)
+noritake_disable_irq(struct irq_data *d)
{
- noritake_update_irq_hw(irq, cached_irq_mask &= ~(1 << (irq - 16)));
+ noritake_update_irq_hw(d->irq, cached_irq_mask &= ~(1 << (d->irq - 16)));
}
static struct irq_chip noritake_irq_type = {
.name = "NORITAKE",
- .unmask = noritake_enable_irq,
- .mask = noritake_disable_irq,
- .mask_ack = noritake_disable_irq,
+ .irq_unmask = noritake_enable_irq,
+ .irq_mask = noritake_disable_irq,
+ .irq_mask_ack = noritake_disable_irq,
};
static void
outw(0, 0x54c);
for (i = 16; i < 48; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, &noritake_irq_type, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
init_i8259a_irqs();
(((h) < MCPCIA_MAX_HOSES) && (cached_irq_masks[(h)] != 0))
static inline void
-rawhide_enable_irq(unsigned int irq)
+rawhide_enable_irq(struct irq_data *d)
{
unsigned int mask, hose;
+ unsigned int irq = d->irq;
irq -= 16;
hose = irq / 24;
}
static void
-rawhide_disable_irq(unsigned int irq)
+rawhide_disable_irq(struct irq_data *d)
{
unsigned int mask, hose;
+ unsigned int irq = d->irq;
irq -= 16;
hose = irq / 24;
}
static void
-rawhide_mask_and_ack_irq(unsigned int irq)
+rawhide_mask_and_ack_irq(struct irq_data *d)
{
unsigned int mask, mask1, hose;
+ unsigned int irq = d->irq;
irq -= 16;
hose = irq / 24;
static struct irq_chip rawhide_irq_type = {
.name = "RAWHIDE",
- .unmask = rawhide_enable_irq,
- .mask = rawhide_disable_irq,
- .mask_ack = rawhide_mask_and_ack_irq,
+ .irq_unmask = rawhide_enable_irq,
+ .irq_mask = rawhide_disable_irq,
+ .irq_mask_ack = rawhide_mask_and_ack_irq,
};
static void
}
for (i = 16; i < 128; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, &rawhide_irq_type, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
init_i8259a_irqs();
}
static inline void
-rx164_enable_irq(unsigned int irq)
+rx164_enable_irq(struct irq_data *d)
{
- rx164_update_irq_hw(cached_irq_mask |= 1UL << (irq - 16));
+ rx164_update_irq_hw(cached_irq_mask |= 1UL << (d->irq - 16));
}
static void
-rx164_disable_irq(unsigned int irq)
+rx164_disable_irq(struct irq_data *d)
{
- rx164_update_irq_hw(cached_irq_mask &= ~(1UL << (irq - 16)));
+ rx164_update_irq_hw(cached_irq_mask &= ~(1UL << (d->irq - 16)));
}
static struct irq_chip rx164_irq_type = {
.name = "RX164",
- .unmask = rx164_enable_irq,
- .mask = rx164_disable_irq,
- .mask_ack = rx164_disable_irq,
+ .irq_unmask = rx164_enable_irq,
+ .irq_mask = rx164_disable_irq,
+ .irq_mask_ack = rx164_disable_irq,
};
static void
rx164_update_irq_hw(0);
for (i = 16; i < 40; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, &rx164_irq_type, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
init_i8259a_irqs();
/* GENERIC irq routines */
static inline void
-sable_lynx_enable_irq(unsigned int irq)
+sable_lynx_enable_irq(struct irq_data *d)
{
unsigned long bit, mask;
- bit = sable_lynx_irq_swizzle->irq_to_mask[irq];
+ bit = sable_lynx_irq_swizzle->irq_to_mask[d->irq];
spin_lock(&sable_lynx_irq_lock);
mask = sable_lynx_irq_swizzle->shadow_mask &= ~(1UL << bit);
sable_lynx_irq_swizzle->update_irq_hw(bit, mask);
}
static void
-sable_lynx_disable_irq(unsigned int irq)
+sable_lynx_disable_irq(struct irq_data *d)
{
unsigned long bit, mask;
- bit = sable_lynx_irq_swizzle->irq_to_mask[irq];
+ bit = sable_lynx_irq_swizzle->irq_to_mask[d->irq];
spin_lock(&sable_lynx_irq_lock);
mask = sable_lynx_irq_swizzle->shadow_mask |= 1UL << bit;
sable_lynx_irq_swizzle->update_irq_hw(bit, mask);
}
static void
-sable_lynx_mask_and_ack_irq(unsigned int irq)
+sable_lynx_mask_and_ack_irq(struct irq_data *d)
{
unsigned long bit, mask;
- bit = sable_lynx_irq_swizzle->irq_to_mask[irq];
+ bit = sable_lynx_irq_swizzle->irq_to_mask[d->irq];
spin_lock(&sable_lynx_irq_lock);
mask = sable_lynx_irq_swizzle->shadow_mask |= 1UL << bit;
sable_lynx_irq_swizzle->update_irq_hw(bit, mask);
static struct irq_chip sable_lynx_irq_type = {
.name = "SABLE/LYNX",
- .unmask = sable_lynx_enable_irq,
- .mask = sable_lynx_disable_irq,
- .mask_ack = sable_lynx_mask_and_ack_irq,
+ .irq_unmask = sable_lynx_enable_irq,
+ .irq_mask = sable_lynx_disable_irq,
+ .irq_mask_ack = sable_lynx_mask_and_ack_irq,
};
static void
long i;
for (i = 0; i < nr_of_irqs; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, &sable_lynx_irq_type,
handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
common_init_isa_dma();
}
static inline void
-takara_enable_irq(unsigned int irq)
+takara_enable_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
unsigned long mask;
mask = (cached_irq_mask[irq >= 64] &= ~(1UL << (irq & 63)));
takara_update_irq_hw(irq, mask);
}
static void
-takara_disable_irq(unsigned int irq)
+takara_disable_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
unsigned long mask;
mask = (cached_irq_mask[irq >= 64] |= 1UL << (irq & 63));
takara_update_irq_hw(irq, mask);
static struct irq_chip takara_irq_type = {
.name = "TAKARA",
- .unmask = takara_enable_irq,
- .mask = takara_disable_irq,
- .mask_ack = takara_disable_irq,
+ .irq_unmask = takara_enable_irq,
+ .irq_mask = takara_disable_irq,
+ .irq_mask_ack = takara_disable_irq,
};
static void
takara_update_irq_hw(i, -1);
for (i = 16; i < 128; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, &takara_irq_type, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
common_init_isa_dma();
}
static inline void
-titan_enable_irq(unsigned int irq)
+titan_enable_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
spin_lock(&titan_irq_lock);
titan_cached_irq_mask |= 1UL << (irq - 16);
titan_update_irq_hw(titan_cached_irq_mask);
}
static inline void
-titan_disable_irq(unsigned int irq)
+titan_disable_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
spin_lock(&titan_irq_lock);
titan_cached_irq_mask &= ~(1UL << (irq - 16));
titan_update_irq_hw(titan_cached_irq_mask);
}
static int
-titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
+titan_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity,
+ bool force)
{
+ unsigned int irq = d->irq;
spin_lock(&titan_irq_lock);
titan_cpu_set_irq_affinity(irq - 16, *affinity);
titan_update_irq_hw(titan_cached_irq_mask);
{
long i;
for (i = imin; i <= imax; ++i) {
- irq_to_desc(i)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i, ops, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
}
}
static struct irq_chip titan_irq_type = {
- .name = "TITAN",
- .unmask = titan_enable_irq,
- .mask = titan_disable_irq,
- .mask_ack = titan_disable_irq,
- .set_affinity = titan_set_irq_affinity,
+ .name = "TITAN",
+ .irq_unmask = titan_enable_irq,
+ .irq_mask = titan_disable_irq,
+ .irq_mask_ack = titan_disable_irq,
+ .irq_set_affinity = titan_set_irq_affinity,
};
static irqreturn_t
}
static void
-wildfire_enable_irq(unsigned int irq)
+wildfire_enable_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
+
if (irq < 16)
- i8259a_enable_irq(irq);
+ i8259a_enable_irq(d);
spin_lock(&wildfire_irq_lock);
set_bit(irq, &cached_irq_mask);
}
static void
-wildfire_disable_irq(unsigned int irq)
+wildfire_disable_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
+
if (irq < 16)
- i8259a_disable_irq(irq);
+ i8259a_disable_irq(d);
spin_lock(&wildfire_irq_lock);
clear_bit(irq, &cached_irq_mask);
}
static void
-wildfire_mask_and_ack_irq(unsigned int irq)
+wildfire_mask_and_ack_irq(struct irq_data *d)
{
+ unsigned int irq = d->irq;
+
if (irq < 16)
- i8259a_mask_and_ack_irq(irq);
+ i8259a_mask_and_ack_irq(d);
spin_lock(&wildfire_irq_lock);
clear_bit(irq, &cached_irq_mask);
static struct irq_chip wildfire_irq_type = {
.name = "WILDFIRE",
- .unmask = wildfire_enable_irq,
- .mask = wildfire_disable_irq,
- .mask_ack = wildfire_mask_and_ack_irq,
+ .irq_unmask = wildfire_enable_irq,
+ .irq_mask = wildfire_disable_irq,
+ .irq_mask_ack = wildfire_mask_and_ack_irq,
};
static void __init
for (i = 0; i < 16; ++i) {
if (i == 2)
continue;
- irq_to_desc(i+irq_bias)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i+irq_bias, &wildfire_irq_type,
handle_level_irq);
+ irq_set_status_flags(i + irq_bias, IRQ_LEVEL);
}
- irq_to_desc(36+irq_bias)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(36+irq_bias, &wildfire_irq_type,
handle_level_irq);
+ irq_set_status_flags(36 + irq_bias, IRQ_LEVEL);
for (i = 40; i < 64; ++i) {
- irq_to_desc(i+irq_bias)->status |= IRQ_LEVEL;
set_irq_chip_and_handler(i+irq_bias, &wildfire_irq_type,
handle_level_irq);
+ irq_set_status_flags(i + irq_bias, IRQ_LEVEL);
}
- setup_irq(32+irq_bias, &isa_enable);
+ setup_irq(32+irq_bias, &isa_enable);
}
static void __init
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
irqreturn_t timer_interrupt(int irq, void *dev)
{
profile_tick(CPU_PROFILING);
#endif
- write_seqlock(&xtime_lock);
-
/*
* Calculate how many ticks have passed since the last update,
* including any previous partial leftover. Save any resulting
nticks = delta >> FIX_SHIFT;
if (nticks)
- do_timer(nticks);
-
- write_sequnlock(&xtime_lock);
+ xtime_update(nticks);
if (test_irq_work_pending()) {
clear_irq_work_pending();
visible impact on the overall performance or power consumption of the
processor.
+config ARM_ERRATA_751472
+ bool "ARM errata: Interrupted ICIALLUIS may prevent completion of broadcasted operation"
+ depends on CPU_V7 && SMP
+ help
+ This option enables the workaround for the 751472 Cortex-A9 (prior
+ to r3p0) erratum. An interrupted ICIALLUIS operation may prevent the
+ completion of a following broadcasted operation if the second
+ operation is received by a CPU before the ICIALLUIS has completed,
+ potentially leading to corrupted entries in the cache or TLB.
+
+config ARM_ERRATA_753970
+ bool "ARM errata: cache sync operation may be faulty"
+ depends on CACHE_PL310
+ help
+ This option enables the workaround for the 753970 PL310 (r3p0) erratum.
+
+ Under some condition the effect of cache sync operation on
+ the store buffer still remains when the operation completes.
+ This means that the store buffer is always asked to drain and
+ this prevents it from merging any further writes. The workaround
+ is to replace the normal offset of cache sync operation (0x730)
+ by another offset targeting an unmapped PL310 register 0x740.
+ This has the same effect as the cache sync operation: store buffer
+ drain and waiting for all buffers empty.
+
endmenu
source "arch/arm/common/Kconfig"
config OABI_COMPAT
bool "Allow old ABI binaries to run with this kernel (EXPERIMENTAL)"
- depends on AEABI && EXPERIMENTAL
+ depends on AEABI && EXPERIMENTAL && !THUMB2_KERNEL
default y
help
This option preserves the old syscall interface along with the
LDFLAGS_vmlinux += --be8
endif
-OBJCOPYFLAGS :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
+OBJCOPYFLAGS :=-O binary -R .comment -S
GZFLAGS :=-9
#KBUILD_CFLAGS +=-pipe
# Explicitly specifiy 32-bit ARM ISA since toolchain default can be -mthumb:
font.c
-piggy.gz
+lib1funcs.S
+piggy.gzip
+piggy.lzo
+piggy.lzma
+vmlinux
vmlinux.lds
config ARM_VIC_NR
int
+ default 4 if ARCH_S5PV210
+ default 3 if ARCH_S5P6442 || ARCH_S5PC100
default 2
depends on ARM_VIC
help
: "cc", "memory")
static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable(); /* implies preempt_disable() */
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- int val;
+ int ret = 0;
+ u32 val;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- pagefault_disable(); /* implies preempt_disable() */
-
__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
- "1: " T(ldr) " %0, [%3]\n"
- " teq %0, %1\n"
+ "1: " T(ldr) " %1, [%4]\n"
+ " teq %1, %2\n"
" it eq @ explicit IT needed for the 2b label\n"
- "2: " T(streq) " %2, [%3]\n"
+ "2: " T(streq) " %3, [%4]\n"
"3:\n"
" .pushsection __ex_table,\"a\"\n"
" .align 3\n"
" .long 1b, 4f, 2b, 4f\n"
" .popsection\n"
" .pushsection .fixup,\"ax\"\n"
- "4: mov %0, %4\n"
+ "4: mov %0, %5\n"
" b 3b\n"
" .popsection"
- : "=&r" (val)
+ : "+r" (ret), "=&r" (val)
: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
: "cc", "memory");
- pagefault_enable(); /* subsumes preempt_enable() */
-
- return val;
+ *uval = val;
+ return ret;
}
#endif /* !SMP */
#define L2X0_RAW_INTR_STAT 0x21C
#define L2X0_INTR_CLEAR 0x220
#define L2X0_CACHE_SYNC 0x730
+#define L2X0_DUMMY_REG 0x740
#define L2X0_INV_LINE_PA 0x770
#define L2X0_INV_WAY 0x77C
#define L2X0_CLEAN_LINE_PA 0x7B0
static inline void sysctl_soft_reset(void __iomem *base)
{
+ /* switch to slow mode */
+ writel(0x2, base + SCCTRL);
+
/* writing any value to SCSYSSTAT reg will reset system */
writel(0, base + SCSYSSTAT);
}
struct sys_timer;
struct machine_desc {
- /*
- * Note! The first two elements are used
- * by assembler code in head.S, head-common.S
- */
unsigned int nr; /* architecture number */
const char *name; /* architecture name */
unsigned long boot_params; /* tagged list */
#ifndef _ASMARM_PGALLOC_H
#define _ASMARM_PGALLOC_H
+#include <linux/pagemap.h>
+
#include <asm/domain.h>
#include <asm/pgtable-hwdef.h>
#include <asm/processor.h>
#define __ASMARM_TLB_H
#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
#ifndef CONFIG_MMU
#include <linux/pagemap.h>
+
+#define tlb_flush(tlb) ((void) tlb)
+
#include <asm-generic/tlb.h>
#else /* !CONFIG_MMU */
+#include <linux/swap.h>
#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+/*
+ * We need to delay page freeing for SMP as other CPUs can access pages
+ * which have been removed but not yet had their TLB entries invalidated.
+ * Also, as ARMv7 speculative prefetch can drag new entries into the TLB,
+ * we need to apply this same delaying tactic to ensure correct operation.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_CPU_32v7)
+#define tlb_fast_mode(tlb) 0
+#define FREE_PTE_NR 500
+#else
+#define tlb_fast_mode(tlb) 1
+#define FREE_PTE_NR 0
+#endif
/*
* TLB handling. This allows us to remove pages from the page
struct mmu_gather {
struct mm_struct *mm;
unsigned int fullmm;
+ struct vm_area_struct *vma;
unsigned long range_start;
unsigned long range_end;
+ unsigned int nr;
+ struct page *pages[FREE_PTE_NR];
};
DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
+/*
+ * This is unnecessarily complex. There's three ways the TLB shootdown
+ * code is used:
+ * 1. Unmapping a range of vmas. See zap_page_range(), unmap_region().
+ * tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
+ * tlb->vma will be non-NULL.
+ * 2. Unmapping all vmas. See exit_mmap().
+ * tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
+ * tlb->vma will be non-NULL. Additionally, page tables will be freed.
+ * 3. Unmapping argument pages. See shift_arg_pages().
+ * tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
+ * tlb->vma will be NULL.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+ if (tlb->fullmm || !tlb->vma)
+ flush_tlb_mm(tlb->mm);
+ else if (tlb->range_end > 0) {
+ flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
+ tlb->range_start = TASK_SIZE;
+ tlb->range_end = 0;
+ }
+}
+
+static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
+{
+ if (!tlb->fullmm) {
+ if (addr < tlb->range_start)
+ tlb->range_start = addr;
+ if (addr + PAGE_SIZE > tlb->range_end)
+ tlb->range_end = addr + PAGE_SIZE;
+ }
+}
+
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+ tlb_flush(tlb);
+ if (!tlb_fast_mode(tlb)) {
+ free_pages_and_swap_cache(tlb->pages, tlb->nr);
+ tlb->nr = 0;
+ }
+}
+
static inline struct mmu_gather *
tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
{
tlb->mm = mm;
tlb->fullmm = full_mm_flush;
+ tlb->vma = NULL;
+ tlb->nr = 0;
return tlb;
}
static inline void
tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
{
- if (tlb->fullmm)
- flush_tlb_mm(tlb->mm);
+ tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
check_pgt_cache();
static inline void
tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
{
- if (!tlb->fullmm) {
- if (addr < tlb->range_start)
- tlb->range_start = addr;
- if (addr + PAGE_SIZE > tlb->range_end)
- tlb->range_end = addr + PAGE_SIZE;
- }
+ tlb_add_flush(tlb, addr);
}
/*
{
if (!tlb->fullmm) {
flush_cache_range(vma, vma->vm_start, vma->vm_end);
+ tlb->vma = vma;
tlb->range_start = TASK_SIZE;
tlb->range_end = 0;
}
static inline void
tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
- if (!tlb->fullmm && tlb->range_end > 0)
- flush_tlb_range(vma, tlb->range_start, tlb->range_end);
+ if (!tlb->fullmm)
+ tlb_flush(tlb);
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+ if (tlb_fast_mode(tlb)) {
+ free_page_and_swap_cache(page);
+ } else {
+ tlb->pages[tlb->nr++] = page;
+ if (tlb->nr >= FREE_PTE_NR)
+ tlb_flush_mmu(tlb);
+ }
+}
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
+ unsigned long addr)
+{
+ pgtable_page_dtor(pte);
+ tlb_add_flush(tlb, addr);
+ tlb_remove_page(tlb, pte);
}
-#define tlb_remove_page(tlb,page) free_page_and_swap_cache(page)
-#define pte_free_tlb(tlb, ptep, addr) pte_free((tlb)->mm, ptep)
+#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
#define pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, pmdp)
#define tlb_migrate_finish(mm) do { } while (0)
#ifndef _ASMARM_TLBFLUSH_H
#define _ASMARM_TLBFLUSH_H
-
-#ifndef CONFIG_MMU
-
-#define tlb_flush(tlb) ((void) tlb)
-
-#else /* CONFIG_MMU */
+#ifdef CONFIG_MMU
#include <asm/glue.h>
#ifdef CONFIG_SMP_ON_UP
+ __INIT
__fixup_smp:
and r3, r9, #0x000f0000 @ architecture version
teq r3, #0x000f0000 @ CPU ID supported?
sub r3, r0, r3
add r4, r4, r3
add r5, r5, r3
-2: cmp r4, r5
- movhs pc, lr
- ldmia r4!, {r0, r6}
- ARM( str r6, [r0, r3] )
- THUMB( add r0, r0, r3 )
-#ifdef __ARMEB__
- THUMB( mov r6, r6, ror #16 ) @ Convert word order for big-endian.
-#endif
- THUMB( strh r6, [r0], #2 ) @ For Thumb-2, store as two halfwords
- THUMB( mov r6, r6, lsr #16 ) @ to be robust against misaligned r3.
- THUMB( strh r6, [r0] )
- b 2b
+ b __do_fixup_smp_on_up
ENDPROC(__fixup_smp)
.align
ALT_SMP(.long 1)
ALT_UP(.long 0)
.popsection
+#endif
+ .text
+__do_fixup_smp_on_up:
+ cmp r4, r5
+ movhs pc, lr
+ ldmia r4!, {r0, r6}
+ ARM( str r6, [r0, r3] )
+ THUMB( add r0, r0, r3 )
+#ifdef __ARMEB__
+ THUMB( mov r6, r6, ror #16 ) @ Convert word order for big-endian.
#endif
+ THUMB( strh r6, [r0], #2 ) @ For Thumb-2, store as two halfwords
+ THUMB( mov r6, r6, lsr #16 ) @ to be robust against misaligned r3.
+ THUMB( strh r6, [r0] )
+ b __do_fixup_smp_on_up
+ENDPROC(__do_fixup_smp_on_up)
+
+ENTRY(fixup_smp)
+ stmfd sp!, {r4 - r6, lr}
+ mov r4, r0
+ add r5, r0, r1
+ mov r3, #0
+ bl __do_fixup_smp_on_up
+ ldmfd sp!, {r4 - r6, pc}
+ENDPROC(fixup_smp)
#include "head-common.S"
u32 didr;
/* Do we implement the extended CPUID interface? */
- if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
- pr_warning("CPUID feature registers not supported. "
- "Assuming v6 debug is present.\n");
+ if (WARN_ONCE((((read_cpuid_id() >> 16) & 0xf) != 0xf),
+ "CPUID feature registers not supported. "
+ "Assuming v6 debug is present.\n"))
return ARM_DEBUG_ARCH_V6;
- }
ARM_DBG_READ(c0, 0, didr);
return (didr >> 16) & 0xf;
return debug_arch;
}
+static int debug_arch_supported(void)
+{
+ u8 arch = get_debug_arch();
+ return arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14;
+}
+
/* Determine number of BRP register available. */
static int get_num_brp_resources(void)
{
int hw_breakpoint_slots(int type)
{
+ if (!debug_arch_supported())
+ return 0;
+
/*
* We can be called early, so don't rely on
* our static variables being initialised.
/*
* One-time initialisation.
*/
-static void reset_ctrl_regs(void *unused)
+static void reset_ctrl_regs(void *info)
{
- int i;
+ int i, cpu = smp_processor_id();
+ u32 dbg_power;
+ cpumask_t *cpumask = info;
/*
* v7 debug contains save and restore registers so that debug state
- * can be maintained across low-power modes without leaving
- * the debug logic powered up. It is IMPLEMENTATION DEFINED whether
- * we can write to the debug registers out of reset, so we must
- * unlock the OS Lock Access Register to avoid taking undefined
- * instruction exceptions later on.
+ * can be maintained across low-power modes without leaving the debug
+ * logic powered up. It is IMPLEMENTATION DEFINED whether we can access
+ * the debug registers out of reset, so we must unlock the OS Lock
+ * Access Register to avoid taking undefined instruction exceptions
+ * later on.
*/
if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) {
+ /*
+ * Ensure sticky power-down is clear (i.e. debug logic is
+ * powered up).
+ */
+ asm volatile("mrc p14, 0, %0, c1, c5, 4" : "=r" (dbg_power));
+ if ((dbg_power & 0x1) == 0) {
+ pr_warning("CPU %d debug is powered down!\n", cpu);
+ cpumask_or(cpumask, cpumask, cpumask_of(cpu));
+ return;
+ }
+
/*
* Unconditionally clear the lock by writing a value
* other than 0xC5ACCE55 to the access register.
static int __init arch_hw_breakpoint_init(void)
{
u32 dscr;
+ cpumask_t cpumask = { CPU_BITS_NONE };
debug_arch = get_debug_arch();
- if (debug_arch > ARM_DEBUG_ARCH_V7_ECP14) {
+ if (!debug_arch_supported()) {
pr_info("debug architecture 0x%x unsupported.\n", debug_arch);
return 0;
}
pr_info("%d breakpoint(s) reserved for watchpoint "
"single-step.\n", core_num_reserved_brps);
+ /*
+ * Reset the breakpoint resources. We assume that a halting
+ * debugger will leave the world in a nice state for us.
+ */
+ on_each_cpu(reset_ctrl_regs, &cpumask, 1);
+ if (!cpumask_empty(&cpumask)) {
+ core_num_brps = 0;
+ core_num_reserved_brps = 0;
+ core_num_wrps = 0;
+ return 0;
+ }
+
ARM_DBG_READ(c1, 0, dscr);
if (dscr & ARM_DSCR_HDBGEN) {
+ max_watchpoint_len = 4;
pr_warning("halting debug mode enabled. Assuming maximum "
- "watchpoint size of 4 bytes.");
+ "watchpoint size of %u bytes.", max_watchpoint_len);
} else {
- /*
- * Reset the breakpoint resources. We assume that a halting
- * debugger will leave the world in a nice state for us.
- */
- smp_call_function(reset_ctrl_regs, NULL, 1);
- reset_ctrl_regs(NULL);
-
/* Work out the maximum supported watchpoint length. */
max_watchpoint_len = get_max_wp_len();
pr_info("maximum watchpoint size is %u bytes.\n",
return space_cccc_1100_010x(insn, asi);
- } else if ((insn & 0x0e000000) == 0x0c400000) {
+ } else if ((insn & 0x0e000000) == 0x0c000000) {
return space_cccc_110x(insn, asi);
#include <asm/pgtable.h>
#include <asm/sections.h>
+#include <asm/smp_plat.h>
#include <asm/unwind.h>
#ifdef CONFIG_XIP_KERNEL
const Elf_Shdr *txt_sec;
};
+static const Elf_Shdr *find_mod_section(const Elf32_Ehdr *hdr,
+ const Elf_Shdr *sechdrs, const char *name)
+{
+ const Elf_Shdr *s, *se;
+ const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+ for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++)
+ if (strcmp(name, secstrs + s->sh_name) == 0)
+ return s;
+
+ return NULL;
+}
+
+extern void fixup_smp(const void *, unsigned long);
+
int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
struct module *mod)
{
+ const Elf_Shdr * __maybe_unused s = NULL;
#ifdef CONFIG_ARM_UNWIND
const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
- const Elf_Shdr *s, *sechdrs_end = sechdrs + hdr->e_shnum;
+ const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum;
struct mod_unwind_map maps[ARM_SEC_MAX];
int i;
maps[i].txt_sec->sh_addr,
maps[i].txt_sec->sh_size);
#endif
+ s = find_mod_section(hdr, sechdrs, ".alt.smp.init");
+ if (s && !is_smp())
+ fixup_smp((void *)s->sh_addr, s->sh_size);
return 0;
}
* Frame pointers should strictly progress back up the stack
* (towards higher addresses).
*/
- if (tail >= buftail.fp)
+ if (tail + 1 >= buftail.fp)
return NULL;
return buftail.fp - 1;
irq, cpu);
return err;
#else
- return 0;
+ return -EINVAL;
#endif
}
static int
init_cpu_pmu(void)
{
- int i, err = 0;
+ int i, irqs, err = 0;
struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU];
- if (!pdev) {
- err = -ENODEV;
- goto out;
- }
+ if (!pdev)
+ return -ENODEV;
+
+ irqs = pdev->num_resources;
+
+ /*
+ * If we have a single PMU interrupt that we can't shift, assume that
+ * we're running on a uniprocessor machine and continue.
+ */
+ if (irqs == 1 && !irq_can_set_affinity(platform_get_irq(pdev, 0)))
+ return 0;
- for (i = 0; i < pdev->num_resources; ++i) {
+ for (i = 0; i < irqs; ++i) {
err = set_irq_affinity(platform_get_irq(pdev, i), i);
if (err)
break;
}
-out:
return err;
}
while (!(arch_ctrl.len & 0x1))
arch_ctrl.len >>= 1;
- if (idx & 0x1)
- reg = encode_ctrl_reg(arch_ctrl);
- else
+ if (num & 0x1)
reg = bp->attr.bp_addr;
+ else
+ reg = encode_ctrl_reg(arch_ctrl);
}
put:
* Register 0 and check for VMSAv7 or PMSAv7 */
asm("mrc p15, 0, %0, c0, c1, 4"
: "=r" (mmfr0));
- if ((mmfr0 & 0x0000000f) == 0x00000003 ||
- (mmfr0 & 0x000000f0) == 0x00000030)
+ if ((mmfr0 & 0x0000000f) >= 0x00000003 ||
+ (mmfr0 & 0x000000f0) >= 0x00000030)
cpu_arch = CPU_ARCH_ARMv7;
else if ((mmfr0 & 0x0000000f) == 0x00000002 ||
(mmfr0 & 0x000000f0) == 0x00000020)
unsigned long handler = (unsigned long)ka->sa.sa_handler;
unsigned long retcode;
int thumb = 0;
- unsigned long cpsr = regs->ARM_cpsr & ~PSR_f;
+ unsigned long cpsr = regs->ARM_cpsr & ~(PSR_f | PSR_E_BIT);
+
+ cpsr |= PSR_ENDSTATE;
/*
* Maybe we need to deliver a 32-bit signal to a 26-bit task.
{
profile_tick(CPU_PROFILING);
do_leds();
- write_seqlock(&xtime_lock);
- do_timer(1);
- write_sequnlock(&xtime_lock);
+ xtime_update(1);
#ifndef CONFIG_SMP
update_process_times(user_mode(get_irq_regs()));
#endif
#define ARM_CPU_KEEP(x)
#endif
+#if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)
+#define ARM_EXIT_KEEP(x) x
+#else
+#define ARM_EXIT_KEEP(x)
+#endif
+
OUTPUT_ARCH(arm)
ENTRY(stext)
_sinittext = .;
HEAD_TEXT
INIT_TEXT
+ ARM_EXIT_KEEP(EXIT_TEXT)
_einittext = .;
ARM_CPU_DISCARD(PROC_INFO)
__arch_info_begin = .;
#ifndef CONFIG_XIP_KERNEL
__init_begin = _stext;
INIT_DATA
+ ARM_EXIT_KEEP(EXIT_DATA)
#endif
}
. = ALIGN(PAGE_SIZE);
__init_begin = .;
INIT_DATA
+ ARM_EXIT_KEEP(EXIT_DATA)
. = ALIGN(PAGE_SIZE);
__init_end = .;
#endif
}
#endif
+ NOTES
+
BSS_SECTION(0, 0, 0)
_end = .;
{
struct pt_regs *regs = get_irq_regs();
do_leds();
- do_timer(1);
+ xtime_update(1);
#ifndef CONFIG_SMP
update_process_times(user_mode(regs));
#endif
return ret;
}
-static int __init davinci_cpu_init(struct cpufreq_policy *policy)
+static int davinci_cpu_init(struct cpufreq_policy *policy)
{
int result = 0;
struct davinci_cpufreq_config *pdata = cpufreq.dev->platform_data;
.resource = da850_mcasp_resources,
};
+struct platform_device davinci_pcm_device = {
+ .name = "davinci-pcm-audio",
+ .id = -1,
+};
+
void __init da8xx_register_mcasp(int id, struct snd_platform_data *pdata)
{
+ platform_device_register(&davinci_pcm_device);
+
/* DA830/OMAP-L137 has 3 instances of McASP */
if (cpu_is_davinci_da830() && id == 1) {
da830_mcasp1_device.dev.platform_data = pdata;
spin_lock_irqsave(&ctlr->lock, flags);
- gpio_reg_set_bit(®s->enable, gpio);
+ gpio_reg_set_bit(regs->enable, gpio);
spin_unlock_irqrestore(&ctlr->lock, flags);
spin_lock_irqsave(&ctlr->lock, flags);
- gpio_reg_clear_bit(®s->enable, gpio);
+ gpio_reg_clear_bit(regs->enable, gpio);
spin_unlock_irqrestore(&ctlr->lock, flags);
}
spin_lock_irqsave(&ctlr->lock, flags);
- gpio_reg_set_bit(®s->direction, gpio);
+ gpio_reg_set_bit(regs->direction, gpio);
spin_unlock_irqrestore(&ctlr->lock, flags);
spin_lock_irqsave(&ctlr->lock, flags);
if (value)
- gpio_reg_set_bit(®s->data_out, gpio);
+ gpio_reg_set_bit(regs->data_out, gpio);
else
- gpio_reg_clear_bit(®s->data_out, gpio);
+ gpio_reg_clear_bit(regs->data_out, gpio);
- gpio_reg_clear_bit(®s->direction, gpio);
+ gpio_reg_clear_bit(regs->direction, gpio);
spin_unlock_irqrestore(&ctlr->lock, flags);
unsigned gpio = chip->base + offset;
int ret;
- ret = gpio_reg_get_bit(®s->data_in, gpio);
+ ret = gpio_reg_get_bit(regs->data_in, gpio);
return ret ? 1 : 0;
}
spin_lock_irqsave(&ctlr->lock, flags);
if (value)
- gpio_reg_set_bit(®s->data_out, gpio);
+ gpio_reg_set_bit(regs->data_out, gpio);
else
- gpio_reg_clear_bit(®s->data_out, gpio);
+ gpio_reg_clear_bit(regs->data_out, gpio);
spin_unlock_irqrestore(&ctlr->lock, flags);
}
#ifndef __MACH_CLKDEV_H
#define __MACH_CLKDEV_H
+struct clk;
+
static inline int __clk_get(struct clk *clk)
{
return 1;
dd = clk->dpll_data;
/* DPLL divider must result in a valid jitter correction val */
- fint = clk->parent->rate / (n + 1);
+ fint = clk->parent->rate / n;
if (fint < DPLL_FINT_BAND1_MIN) {
pr_debug("rejecting n=%d due to Fint failure, "
omap_mbox_type_t irq)
{
struct omap_mbox2_priv *p = mbox->priv;
- u32 l, bit = (irq == IRQ_TX) ? p->notfull_bit : p->newmsg_bit;
- l = mbox_read_reg(p->irqdisable);
- l &= ~bit;
- mbox_write_reg(l, p->irqdisable);
+ u32 bit = (irq == IRQ_TX) ? p->notfull_bit : p->newmsg_bit;
+
+ if (!cpu_is_omap44xx())
+ bit = mbox_read_reg(p->irqdisable) & ~bit;
+
+ mbox_write_reg(bit, p->irqdisable);
}
static void omap2_mbox_ack_irq(struct omap_mbox *mbox,
.priv = &omap2_mbox_iva_priv,
};
-struct omap_mbox *omap2_mboxes[] = { &mbox_iva_info, &mbox_dsp_info, NULL };
+struct omap_mbox *omap2_mboxes[] = { &mbox_dsp_info, &mbox_iva_info, NULL };
#endif
#if defined(CONFIG_ARCH_OMAP4)
list_for_each_entry(e, &partition->muxmodes, node) {
struct omap_mux *m = &e->mux;
- (void)debugfs_create_file(m->muxnames[0], S_IWUGO, mux_dbg_dir,
+ (void)debugfs_create_file(m->muxnames[0], S_IWUSR, mux_dbg_dir,
m, &omap_mux_dbg_signal_fops);
}
}
}
- (void) debugfs_create_file("enable_off_mode", S_IRUGO | S_IWUGO, d,
+ (void) debugfs_create_file("enable_off_mode", S_IRUGO | S_IWUSR, d,
&enable_off_mode, &pm_dbg_option_fops);
- (void) debugfs_create_file("sleep_while_idle", S_IRUGO | S_IWUGO, d,
+ (void) debugfs_create_file("sleep_while_idle", S_IRUGO | S_IWUSR, d,
&sleep_while_idle, &pm_dbg_option_fops);
- (void) debugfs_create_file("wakeup_timer_seconds", S_IRUGO | S_IWUGO, d,
+ (void) debugfs_create_file("wakeup_timer_seconds", S_IRUGO | S_IWUSR, d,
&wakeup_timer_seconds, &pm_dbg_option_fops);
(void) debugfs_create_file("wakeup_timer_milliseconds",
- S_IRUGO | S_IWUGO, d, &wakeup_timer_milliseconds,
+ S_IRUGO | S_IWUSR, d, &wakeup_timer_milliseconds,
&pm_dbg_option_fops);
pm_dbg_init_done = 1;
#define OMAP4430_PRCM_MPU_CPU1_INST 0x0800
/* PRCM_MPU clockdomain register offsets (from instance start) */
-#define OMAP4430_PRCM_MPU_CPU0_MPU_CDOFFS 0x0000
-#define OMAP4430_PRCM_MPU_CPU1_MPU_CDOFFS 0x0000
+#define OMAP4430_PRCM_MPU_CPU0_MPU_CDOFFS 0x0018
+#define OMAP4430_PRCM_MPU_CPU1_MPU_CDOFFS 0x0018
/*
dev_err(&sr_info->pdev->dev, "%s: ERROR in registering"
"interrupt handler. Smartreflex will"
"not function as desired\n", __func__);
+ kfree(name);
kfree(sr_info);
return ret;
}
ret = sr_late_init(sr_info);
if (ret) {
pr_warning("%s: Error in SR late init\n", __func__);
- return ret;
+ goto err_release_region;
}
}
* not try to create rest of the debugfs entries.
*/
vdd_dbg_dir = omap_voltage_get_dbgdir(sr_info->voltdm);
- if (!vdd_dbg_dir)
- return -EINVAL;
+ if (!vdd_dbg_dir) {
+ ret = -EINVAL;
+ goto err_release_region;
+ }
dbg_dir = debugfs_create_dir("smartreflex", vdd_dbg_dir);
if (IS_ERR(dbg_dir)) {
dev_err(&pdev->dev, "%s: Unable to create debugfs directory\n",
__func__);
- return PTR_ERR(dbg_dir);
+ ret = PTR_ERR(dbg_dir);
+ goto err_release_region;
}
- (void) debugfs_create_file("autocomp", S_IRUGO | S_IWUGO, dbg_dir,
+ (void) debugfs_create_file("autocomp", S_IRUGO | S_IWUSR, dbg_dir,
(void *)sr_info, &pm_sr_fops);
(void) debugfs_create_x32("errweight", S_IRUGO, dbg_dir,
&sr_info->err_weight);
if (IS_ERR(nvalue_dir)) {
dev_err(&pdev->dev, "%s: Unable to create debugfs directory"
"for n-values\n", __func__);
- return PTR_ERR(nvalue_dir);
+ ret = PTR_ERR(nvalue_dir);
+ goto err_release_region;
}
omap_voltage_get_volttable(sr_info->voltdm, &volt_data);
" corresponding vdd vdd_%s. Cannot create debugfs"
"entries for n-values\n",
__func__, sr_info->voltdm->name);
- return -ENODATA;
+ ret = -ENODATA;
+ goto err_release_region;
}
for (i = 0; i < sr_info->nvalue_count; i++) {
- char *name;
- char volt_name[32];
-
- name = kzalloc(NVALUE_NAME_LEN + 1, GFP_KERNEL);
- if (!name) {
- dev_err(&pdev->dev, "%s: Unable to allocate memory"
- " for n-value directory name\n", __func__);
- return -ENOMEM;
- }
+ char name[NVALUE_NAME_LEN + 1];
- strcpy(name, "volt_");
- sprintf(volt_name, "%d", volt_data[i].volt_nominal);
- strcat(name, volt_name);
- (void) debugfs_create_x32(name, S_IRUGO | S_IWUGO, nvalue_dir,
+ snprintf(name, sizeof(name), "volt_%d",
+ volt_data[i].volt_nominal);
+ (void) debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir,
&(sr_info->nvalue_table[i].nvalue));
}
#include <asm/mach/time.h>
#include <plat/dmtimer.h>
#include <asm/localtimer.h>
+#include <asm/sched_clock.h>
#include "timer-gp.h"
/*
* clocksource
*/
+static DEFINE_CLOCK_DATA(cd);
static struct omap_dm_timer *gpt_clocksource;
static cycle_t clocksource_read_cycles(struct clocksource *cs)
{
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
+static void notrace dmtimer_update_sched_clock(void)
+{
+ u32 cyc;
+
+ cyc = omap_dm_timer_read_counter(gpt_clocksource);
+
+ update_sched_clock(&cd, cyc, (u32)~0);
+}
+
/* Setup free-running counter for clocksource */
static void __init omap2_gp_clocksource_init(void)
{
omap_dm_timer_set_load_start(gpt, 1, 0);
+ init_sched_clock(&cd, dmtimer_update_sched_clock, 32, tick_rate);
+
if (clocksource_register_hz(&clocksource_gpt, tick_rate))
printk(err2, clocksource_gpt.name);
}
GPIO0_COLIBRI_PXA270_SD_DETECT;
if (machine_is_colibri300()) /* PXA300 Colibri */
colibri_mci_platform_data.gpio_card_detect =
- GPIO39_COLIBRI_PXA300_SD_DETECT;
+ GPIO13_COLIBRI_PXA300_SD_DETECT;
else /* PXA320 Colibri */
colibri_mci_platform_data.gpio_card_detect =
GPIO28_COLIBRI_PXA320_SD_DETECT;
GPIO4_MMC1_DAT1,
GPIO5_MMC1_DAT2,
GPIO6_MMC1_DAT3,
- GPIO39_GPIO, /* SD detect */
+ GPIO13_GPIO, /* GPIO13_COLIBRI_PXA300_SD_DETECT */
/* UHC */
GPIO0_2_USBH_PEN,
#define GPIO113_COLIBRI_PXA270_TS_IRQ 113
/* GPIO definitions for Colibri PXA300/310 */
-#define GPIO39_COLIBRI_PXA300_SD_DETECT 39
+#define GPIO13_COLIBRI_PXA300_SD_DETECT 13
/* GPIO definitions for Colibri PXA320 */
#define GPIO28_COLIBRI_PXA320_SD_DETECT 28
.pwm_id = 0,
.max_brightness = 0xfe,
.dft_brightness = 0x7e,
- .pwm_period_ns = 3500,
+ .pwm_period_ns = 3500 * 1024,
.init = palm27x_backlight_init,
.notify = palm27x_backlight_notify,
.exit = palm27x_backlight_exit,
#endif
/* skip registers saving for standby */
- if (state != PM_SUSPEND_STANDBY) {
+ if (state != PM_SUSPEND_STANDBY && pxa_cpu_pm_fns->save) {
pxa_cpu_pm_fns->save(sleep_save);
/* before sleeping, calculate and save a checksum */
for (i = 0; i < pxa_cpu_pm_fns->save_count - 1; i++)
pxa_cpu_pm_fns->enter(state);
cpu_init();
- if (state != PM_SUSPEND_STANDBY) {
+ if (state != PM_SUSPEND_STANDBY && pxa_cpu_pm_fns->restore) {
/* after sleeping, validate the checksum */
for (i = 0; i < pxa_cpu_pm_fns->save_count - 1; i++)
checksum += sleep_save[i];
&pxa25x_device_assp,
&pxa25x_device_pwm0,
&pxa25x_device_pwm1,
+ &pxa_device_asoc_platform,
};
static struct sys_device pxa25x_sysdev[] = {
goto err_rfk_alloc;
}
- rfkill_set_led_trigger_name(rfk, "tosa-bt");
-
rc = rfkill_register(rfk);
if (rc)
goto err_rfkill;
.dev.platform_data = &sharpsl_rom_data,
};
+static struct platform_device wm9712_device = {
+ .name = "wm9712-codec",
+ .id = -1,
+};
+
static struct platform_device *devices[] __initdata = {
&tosascoop_device,
&tosascoop_jc_device,
&tosaled_device,
&tosa_bt_device,
&sharpsl_rom_device,
+ &wm9712_device,
};
static void tosa_poweroff(void)
select POWER_SUPPLY
select MACH_NEO1973
select S3C2410_PWM
+ select S3C_DEV_USB_HOST
help
Say Y here if you are using the Openmoko GTA02 / Freerunner GSM Phone
#define GTA02v3_GPIO_nUSB_FLT S3C2410_GPG(10) /* v3 + v4 only */
#define GTA02v3_GPIO_nGSM_OC S3C2410_GPG(11) /* v3 + v4 only */
-#define GTA02_GPIO_AMP_SHUT S3C2440_GPJ1 /* v2 + v3 + v4 only */
-#define GTA02v1_GPIO_WLAN_GPIO10 S3C2440_GPJ2
-#define GTA02_GPIO_HP_IN S3C2440_GPJ2 /* v2 + v3 + v4 only */
-#define GTA02_GPIO_INT0 S3C2440_GPJ3 /* v2 + v3 + v4 only */
-#define GTA02_GPIO_nGSM_EN S3C2440_GPJ4
-#define GTA02_GPIO_3D_RESET S3C2440_GPJ5
-#define GTA02_GPIO_nDL_GSM S3C2440_GPJ6 /* v4 + v5 only */
-#define GTA02_GPIO_WLAN_GPIO0 S3C2440_GPJ7
-#define GTA02v1_GPIO_BAT_ID S3C2440_GPJ8
-#define GTA02_GPIO_KEEPACT S3C2440_GPJ8
-#define GTA02v1_GPIO_HP_IN S3C2440_GPJ10
-#define GTA02_CHIP_PWD S3C2440_GPJ11 /* v2 + v3 + v4 only */
-#define GTA02_GPIO_nWLAN_RESET S3C2440_GPJ12 /* v2 + v3 + v4 only */
+#define GTA02_GPIO_AMP_SHUT S3C2410_GPJ(1) /* v2 + v3 + v4 only */
+#define GTA02v1_GPIO_WLAN_GPIO10 S3C2410_GPJ(2)
+#define GTA02_GPIO_HP_IN S3C2410_GPJ(2) /* v2 + v3 + v4 only */
+#define GTA02_GPIO_INT0 S3C2410_GPJ(3) /* v2 + v3 + v4 only */
+#define GTA02_GPIO_nGSM_EN S3C2410_GPJ(4)
+#define GTA02_GPIO_3D_RESET S3C2410_GPJ(5)
+#define GTA02_GPIO_nDL_GSM S3C2410_GPJ(6) /* v4 + v5 only */
+#define GTA02_GPIO_WLAN_GPIO0 S3C2410_GPJ(7)
+#define GTA02v1_GPIO_BAT_ID S3C2410_GPJ(8)
+#define GTA02_GPIO_KEEPACT S3C2410_GPJ(8)
+#define GTA02v1_GPIO_HP_IN S3C2410_GPJ(10)
+#define GTA02_CHIP_PWD S3C2410_GPJ(11) /* v2 + v3 + v4 only */
+#define GTA02_GPIO_nWLAN_RESET S3C2410_GPJ(12) /* v2 + v3 + v4 only */
#define GTA02_IRQ_GSENSOR_1 IRQ_EINT0
#define GTA02_IRQ_MODEM IRQ_EINT1
.parent = &clk_p,
.enable = s3c64xx_pclk_ctrl,
.ctrlbit = S3C_CLKCON_PCLK_IIC,
+ }, {
+ .name = "i2c",
+ .id = 1,
+ .parent = &clk_p,
+ .enable = s3c64xx_pclk_ctrl,
+ .ctrlbit = S3C6410_CLKCON_PCLK_I2C1,
}, {
.name = "iis",
.id = 0,
regptr = regs + PL080_Cx_BASE(0);
- for (ch = 0; ch < 8; ch++, chno++, chptr++) {
- printk(KERN_INFO "%s: registering DMA %d (%p)\n",
- __func__, chno, regptr);
+ for (ch = 0; ch < 8; ch++, chptr++) {
+ pr_debug("%s: registering DMA %d (%p)\n",
+ __func__, chno + ch, regptr);
chptr->bit = 1 << ch;
- chptr->number = chno;
+ chptr->number = chno + ch;
chptr->dmac = dmac;
chptr->regs = regptr;
regptr += PL080_Cx_STRIDE;
/* for the moment, permanently enable the controller */
writel(PL080_CONFIG_ENABLE, regs + PL080_CONFIG);
- printk(KERN_INFO "PL080: IRQ %d, at %p\n", irq, regs);
+ printk(KERN_INFO "PL080: IRQ %d, at %p, channels %d..%d\n",
+ irq, regs, chno, chno+8);
return 0;
.get_pull = s3c_gpio_getpull_updown,
};
-int s3c64xx_gpio2int_gpm(struct gpio_chip *chip, unsigned pin)
+static int s3c64xx_gpio2int_gpm(struct gpio_chip *chip, unsigned pin)
{
return pin < 5 ? IRQ_EINT(23) + pin : -ENXIO;
}
},
};
-int s3c64xx_gpio2int_gpl(struct gpio_chip *chip, unsigned pin)
+static int s3c64xx_gpio2int_gpl(struct gpio_chip *chip, unsigned pin)
{
return pin >= 8 ? IRQ_EINT(16) + pin - 8 : -ENXIO;
}
#include <linux/delay.h>
#include <linux/smsc911x.h>
#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
#ifdef CONFIG_SMDK6410_WM1190_EV1
#include <linux/mfd/wm8350/core.h>
/* VDD_UH_MMC, LDO5 on J5 */
static struct regulator_init_data smdk6410_vdduh_mmc = {
.constraints = {
- .name = "PVDD_UH/PVDD_MMC",
+ .name = "PVDD_UH+PVDD_MMC",
.always_on = 1,
},
};
/* S3C64xx internal logic & PLL */
static struct regulator_init_data wm8350_dcdc1_data = {
.constraints = {
- .name = "PVDD_INT/PVDD_PLL",
+ .name = "PVDD_INT+PVDD_PLL",
.min_uV = 1200000,
.max_uV = 1200000,
.always_on = 1,
static struct regulator_init_data wm8350_dcdc4_data = {
.constraints = {
- .name = "PVDD_HI/PVDD_EXT/PVDD_SYS/PVCCM2MTV",
+ .name = "PVDD_HI+PVDD_EXT+PVDD_SYS+PVCCM2MTV",
.min_uV = 3000000,
.max_uV = 3000000,
.always_on = 1,
/* OTGi/1190-EV1 HPVDD & AVDD */
static struct regulator_init_data wm8350_ldo4_data = {
.constraints = {
- .name = "PVDD_OTGI/HPVDD/AVDD",
+ .name = "PVDD_OTGI+HPVDD+AVDD",
.min_uV = 1200000,
.max_uV = 1200000,
.apply_uV = 1,
static struct regulator_init_data wm1192_dcdc3 = {
.constraints = {
- .name = "PVDD_MEM/PVDD_GPS",
+ .name = "PVDD_MEM+PVDD_GPS",
.always_on = 1,
},
};
static struct regulator_init_data wm1192_ldo1 = {
.constraints = {
- .name = "PVDD_LCD/PVDD_EXT",
+ .name = "PVDD_LCD+PVDD_EXT",
.always_on = 1,
},
.consumer_supplies = wm1192_ldo1_consumers,
void samsung_keypad_cfg_gpio(unsigned int rows, unsigned int cols)
{
/* Set all the necessary GPK pins to special-function 3: KP_ROW[x] */
- s3c_gpio_cfgrange_nopull(S3C64XX_GPK(8), 8 + rows, S3C_GPIO_SFN(3));
+ s3c_gpio_cfgrange_nopull(S3C64XX_GPK(8), rows, S3C_GPIO_SFN(3));
/* Set all the necessary GPL pins to special-function 3: KP_COL[x] */
s3c_gpio_cfgrange_nopull(S3C64XX_GPL(0), cols, S3C_GPIO_SFN(3));
else
ctrl3 = (S3C_SDHCI_CTRL3_FCSEL1 | S3C_SDHCI_CTRL3_FCSEL0);
- printk(KERN_INFO "%s: CTRL 2=%08x, 3=%08x\n", __func__, ctrl2, ctrl3);
+ pr_debug("%s: CTRL 2=%08x, 3=%08x\n", __func__, ctrl2, ctrl3);
writel(ctrl2, r + S3C_SDHCI_CONTROL2);
writel(ctrl3, r + S3C_SDHCI_CONTROL3);
}
/* linux/arch/arm/mach-s5p6442/include/mach/map.h
*
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* S5P6442 - Memory map definitions
#include <plat/map-base.h>
#include <plat/map-s5p.h>
-#define S5P6442_PA_CHIPID (0xE0000000)
-#define S5P_PA_CHIPID S5P6442_PA_CHIPID
+#define S5P6442_PA_SDRAM 0x20000000
-#define S5P6442_PA_SYSCON (0xE0100000)
-#define S5P_PA_SYSCON S5P6442_PA_SYSCON
+#define S5P6442_PA_I2S0 0xC0B00000
+#define S5P6442_PA_I2S1 0xF2200000
-#define S5P6442_PA_GPIO (0xE0200000)
+#define S5P6442_PA_CHIPID 0xE0000000
-#define S5P6442_PA_VIC0 (0xE4000000)
-#define S5P6442_PA_VIC1 (0xE4100000)
-#define S5P6442_PA_VIC2 (0xE4200000)
+#define S5P6442_PA_SYSCON 0xE0100000
-#define S5P6442_PA_SROMC (0xE7000000)
-#define S5P_PA_SROMC S5P6442_PA_SROMC
+#define S5P6442_PA_GPIO 0xE0200000
-#define S5P6442_PA_MDMA 0xE8000000
-#define S5P6442_PA_PDMA 0xE9000000
+#define S5P6442_PA_VIC0 0xE4000000
+#define S5P6442_PA_VIC1 0xE4100000
+#define S5P6442_PA_VIC2 0xE4200000
-#define S5P6442_PA_TIMER (0xEA000000)
-#define S5P_PA_TIMER S5P6442_PA_TIMER
+#define S5P6442_PA_SROMC 0xE7000000
-#define S5P6442_PA_SYSTIMER (0xEA100000)
+#define S5P6442_PA_MDMA 0xE8000000
+#define S5P6442_PA_PDMA 0xE9000000
-#define S5P6442_PA_WATCHDOG (0xEA200000)
+#define S5P6442_PA_TIMER 0xEA000000
-#define S5P6442_PA_UART (0xEC000000)
+#define S5P6442_PA_SYSTIMER 0xEA100000
-#define S5P_PA_UART0 (S5P6442_PA_UART + 0x0)
-#define S5P_PA_UART1 (S5P6442_PA_UART + 0x400)
-#define S5P_PA_UART2 (S5P6442_PA_UART + 0x800)
-#define S5P_SZ_UART SZ_256
+#define S5P6442_PA_WATCHDOG 0xEA200000
-#define S5P6442_PA_IIC0 (0xEC100000)
+#define S5P6442_PA_UART 0xEC000000
-#define S5P6442_PA_SDRAM (0x20000000)
-#define S5P_PA_SDRAM S5P6442_PA_SDRAM
+#define S5P6442_PA_IIC0 0xEC100000
#define S5P6442_PA_SPI 0xEC300000
-/* I2S */
-#define S5P6442_PA_I2S0 0xC0B00000
-#define S5P6442_PA_I2S1 0xF2200000
-
-/* PCM */
#define S5P6442_PA_PCM0 0xF2400000
#define S5P6442_PA_PCM1 0xF2500000
-/* compatibiltiy defines. */
+/* Compatibiltiy Defines */
+
+#define S3C_PA_IIC S5P6442_PA_IIC0
#define S3C_PA_WDT S5P6442_PA_WATCHDOG
+
+#define S5P_PA_CHIPID S5P6442_PA_CHIPID
+#define S5P_PA_SDRAM S5P6442_PA_SDRAM
+#define S5P_PA_SROMC S5P6442_PA_SROMC
+#define S5P_PA_SYSCON S5P6442_PA_SYSCON
+#define S5P_PA_TIMER S5P6442_PA_TIMER
+
+/* UART */
+
#define S3C_PA_UART S5P6442_PA_UART
-#define S3C_PA_IIC S5P6442_PA_IIC0
+
+#define S5P_PA_UART(x) (S3C_PA_UART + ((x) * S3C_UART_OFFSET))
+#define S5P_PA_UART0 S5P_PA_UART(0)
+#define S5P_PA_UART1 S5P_PA_UART(1)
+#define S5P_PA_UART2 S5P_PA_UART(2)
+
+#define S5P_SZ_UART SZ_256
#endif /* __ASM_ARCH_MAP_H */
#define S5P6440_GPIO_A_NR (6)
#define S5P6440_GPIO_B_NR (7)
#define S5P6440_GPIO_C_NR (8)
-#define S5P6440_GPIO_F_NR (2)
+#define S5P6440_GPIO_F_NR (16)
#define S5P6440_GPIO_G_NR (7)
#define S5P6440_GPIO_H_NR (10)
#define S5P6440_GPIO_I_NR (16)
#define S5P6450_GPIO_B_NR (7)
#define S5P6450_GPIO_C_NR (8)
#define S5P6450_GPIO_D_NR (8)
-#define S5P6450_GPIO_F_NR (2)
+#define S5P6450_GPIO_F_NR (16)
#define S5P6450_GPIO_G_NR (14)
#define S5P6450_GPIO_H_NR (10)
#define S5P6450_GPIO_I_NR (16)
/* linux/arch/arm/mach-s5p64x0/include/mach/map.h
*
- * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2009-2011 Samsung Electronics Co., Ltd.
* http://www.samsung.com
*
* S5P64X0 - Memory map definitions
#include <plat/map-base.h>
#include <plat/map-s5p.h>
-#define S5P64X0_PA_SDRAM (0x20000000)
+#define S5P64X0_PA_SDRAM 0x20000000
-#define S5P64X0_PA_CHIPID (0xE0000000)
-#define S5P_PA_CHIPID S5P64X0_PA_CHIPID
-
-#define S5P64X0_PA_SYSCON (0xE0100000)
-#define S5P_PA_SYSCON S5P64X0_PA_SYSCON
-
-#define S5P64X0_PA_GPIO (0xE0308000)
-
-#define S5P64X0_PA_VIC0 (0xE4000000)
-#define S5P64X0_PA_VIC1 (0xE4100000)
+#define S5P64X0_PA_CHIPID 0xE0000000
-#define S5P64X0_PA_SROMC (0xE7000000)
-#define S5P_PA_SROMC S5P64X0_PA_SROMC
-
-#define S5P64X0_PA_PDMA (0xE9000000)
-
-#define S5P64X0_PA_TIMER (0xEA000000)
-#define S5P_PA_TIMER S5P64X0_PA_TIMER
+#define S5P64X0_PA_SYSCON 0xE0100000
-#define S5P64X0_PA_RTC (0xEA100000)
+#define S5P64X0_PA_GPIO 0xE0308000
-#define S5P64X0_PA_WDT (0xEA200000)
+#define S5P64X0_PA_VIC0 0xE4000000
+#define S5P64X0_PA_VIC1 0xE4100000
-#define S5P6440_PA_UART(x) (0xEC000000 + ((x) * S3C_UART_OFFSET))
-#define S5P6450_PA_UART(x) ((x < 5) ? (0xEC800000 + ((x) * S3C_UART_OFFSET)) : (0xEC000000))
+#define S5P64X0_PA_SROMC 0xE7000000
-#define S5P_PA_UART0 S5P6450_PA_UART(0)
-#define S5P_PA_UART1 S5P6450_PA_UART(1)
-#define S5P_PA_UART2 S5P6450_PA_UART(2)
-#define S5P_PA_UART3 S5P6450_PA_UART(3)
-#define S5P_PA_UART4 S5P6450_PA_UART(4)
-#define S5P_PA_UART5 S5P6450_PA_UART(5)
+#define S5P64X0_PA_PDMA 0xE9000000
-#define S5P_SZ_UART SZ_256
+#define S5P64X0_PA_TIMER 0xEA000000
+#define S5P64X0_PA_RTC 0xEA100000
+#define S5P64X0_PA_WDT 0xEA200000
-#define S5P6440_PA_IIC0 (0xEC104000)
-#define S5P6440_PA_IIC1 (0xEC20F000)
-#define S5P6450_PA_IIC0 (0xEC100000)
-#define S5P6450_PA_IIC1 (0xEC200000)
+#define S5P6440_PA_IIC0 0xEC104000
+#define S5P6440_PA_IIC1 0xEC20F000
+#define S5P6450_PA_IIC0 0xEC100000
+#define S5P6450_PA_IIC1 0xEC200000
-#define S5P64X0_PA_SPI0 (0xEC400000)
-#define S5P64X0_PA_SPI1 (0xEC500000)
+#define S5P64X0_PA_SPI0 0xEC400000
+#define S5P64X0_PA_SPI1 0xEC500000
-#define S5P64X0_PA_HSOTG (0xED100000)
+#define S5P64X0_PA_HSOTG 0xED100000
#define S5P64X0_PA_HSMMC(x) (0xED800000 + ((x) * 0x100000))
-#define S5P64X0_PA_I2S (0xF2000000)
+#define S5P64X0_PA_I2S 0xF2000000
#define S5P6450_PA_I2S1 0xF2800000
#define S5P6450_PA_I2S2 0xF2900000
-#define S5P64X0_PA_PCM (0xF2100000)
+#define S5P64X0_PA_PCM 0xF2100000
-#define S5P64X0_PA_ADC (0xF3000000)
+#define S5P64X0_PA_ADC 0xF3000000
-/* compatibiltiy defines. */
+/* Compatibiltiy Defines */
#define S3C_PA_HSMMC0 S5P64X0_PA_HSMMC(0)
#define S3C_PA_HSMMC1 S5P64X0_PA_HSMMC(1)
#define S3C_PA_RTC S5P64X0_PA_RTC
#define S3C_PA_WDT S5P64X0_PA_WDT
+#define S5P_PA_CHIPID S5P64X0_PA_CHIPID
+#define S5P_PA_SROMC S5P64X0_PA_SROMC
+#define S5P_PA_SYSCON S5P64X0_PA_SYSCON
+#define S5P_PA_TIMER S5P64X0_PA_TIMER
+
#define SAMSUNG_PA_ADC S5P64X0_PA_ADC
+/* UART */
+
+#define S5P6440_PA_UART(x) (0xEC000000 + ((x) * S3C_UART_OFFSET))
+#define S5P6450_PA_UART(x) ((x < 5) ? (0xEC800000 + ((x) * S3C_UART_OFFSET)) : (0xEC000000))
+
+#define S5P_PA_UART0 S5P6450_PA_UART(0)
+#define S5P_PA_UART1 S5P6450_PA_UART(1)
+#define S5P_PA_UART2 S5P6450_PA_UART(2)
+#define S5P_PA_UART3 S5P6450_PA_UART(3)
+#define S5P_PA_UART4 S5P6450_PA_UART(4)
+#define S5P_PA_UART5 S5P6450_PA_UART(5)
+
+#define S5P_SZ_UART SZ_256
+
#endif /* __ASM_ARCH_MAP_H */
/* linux/arch/arm/mach-s5pc100/include/mach/map.h
+ *
+ * Copyright (c) 2011 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com/
*
* Copyright 2009 Samsung Electronics Co.
* Byungho Min <bhmin@samsung.com>
#include <plat/map-base.h>
#include <plat/map-s5p.h>
-/*
- * map-base.h has already defined virtual memory address
- * S3C_VA_IRQ S3C_ADDR(0x00000000) irq controller(s)
- * S3C_VA_SYS S3C_ADDR(0x00100000) system control
- * S3C_VA_MEM S3C_ADDR(0x00200000) system control (not used)
- * S3C_VA_TIMER S3C_ADDR(0x00300000) timer block
- * S3C_VA_WATCHDOG S3C_ADDR(0x00400000) watchdog
- * S3C_VA_UART S3C_ADDR(0x01000000) UART
- *
- * S5PC100 specific virtual memory address can be defined here
- * S5PC1XX_VA_GPIO S3C_ADDR(0x00500000) GPIO
- *
- */
+#define S5PC100_PA_SDRAM 0x20000000
+
+#define S5PC100_PA_ONENAND 0xE7100000
+#define S5PC100_PA_ONENAND_BUF 0xB0000000
+
+#define S5PC100_PA_CHIPID 0xE0000000
-#define S5PC100_PA_ONENAND_BUF (0xB0000000)
-#define S5PC100_SZ_ONENAND_BUF (SZ_256M - SZ_32M)
+#define S5PC100_PA_SYSCON 0xE0100000
-/* Chip ID */
+#define S5PC100_PA_OTHERS 0xE0200000
-#define S5PC100_PA_CHIPID (0xE0000000)
-#define S5P_PA_CHIPID S5PC100_PA_CHIPID
+#define S5PC100_PA_GPIO 0xE0300000
-#define S5PC100_PA_SYSCON (0xE0100000)
-#define S5P_PA_SYSCON S5PC100_PA_SYSCON
+#define S5PC100_PA_VIC0 0xE4000000
+#define S5PC100_PA_VIC1 0xE4100000
+#define S5PC100_PA_VIC2 0xE4200000
-#define S5PC100_PA_OTHERS (0xE0200000)
-#define S5PC100_VA_OTHERS (S3C_VA_SYS + 0x10000)
+#define S5PC100_PA_SROMC 0xE7000000
-#define S5PC100_PA_GPIO (0xE0300000)
-#define S5PC1XX_VA_GPIO S3C_ADDR(0x00500000)
+#define S5PC100_PA_CFCON 0xE7800000
-/* Interrupt */
-#define S5PC100_PA_VIC0 (0xE4000000)
-#define S5PC100_PA_VIC1 (0xE4100000)
-#define S5PC100_PA_VIC2 (0xE4200000)
-#define S5PC100_VA_VIC S3C_VA_IRQ
-#define S5PC100_VA_VIC_OFFSET 0x10000
-#define S5PC1XX_VA_VIC(x) (S5PC100_VA_VIC + ((x) * S5PC100_VA_VIC_OFFSET))
+#define S5PC100_PA_MDMA 0xE8100000
+#define S5PC100_PA_PDMA0 0xE9000000
+#define S5PC100_PA_PDMA1 0xE9200000
-#define S5PC100_PA_SROMC (0xE7000000)
-#define S5P_PA_SROMC S5PC100_PA_SROMC
+#define S5PC100_PA_TIMER 0xEA000000
+#define S5PC100_PA_SYSTIMER 0xEA100000
+#define S5PC100_PA_WATCHDOG 0xEA200000
+#define S5PC100_PA_RTC 0xEA300000
-#define S5PC100_PA_ONENAND (0xE7100000)
+#define S5PC100_PA_UART 0xEC000000
-#define S5PC100_PA_CFCON (0xE7800000)
+#define S5PC100_PA_IIC0 0xEC100000
+#define S5PC100_PA_IIC1 0xEC200000
-/* DMA */
-#define S5PC100_PA_MDMA (0xE8100000)
-#define S5PC100_PA_PDMA0 (0xE9000000)
-#define S5PC100_PA_PDMA1 (0xE9200000)
+#define S5PC100_PA_SPI0 0xEC300000
+#define S5PC100_PA_SPI1 0xEC400000
+#define S5PC100_PA_SPI2 0xEC500000
-/* Timer */
-#define S5PC100_PA_TIMER (0xEA000000)
-#define S5P_PA_TIMER S5PC100_PA_TIMER
+#define S5PC100_PA_USB_HSOTG 0xED200000
+#define S5PC100_PA_USB_HSPHY 0xED300000
-#define S5PC100_PA_SYSTIMER (0xEA100000)
+#define S5PC100_PA_HSMMC(x) (0xED800000 + ((x) * 0x100000))
-#define S5PC100_PA_WATCHDOG (0xEA200000)
-#define S5PC100_PA_RTC (0xEA300000)
+#define S5PC100_PA_FB 0xEE000000
-#define S5PC100_PA_UART (0xEC000000)
+#define S5PC100_PA_FIMC0 0xEE200000
+#define S5PC100_PA_FIMC1 0xEE300000
+#define S5PC100_PA_FIMC2 0xEE400000
-#define S5P_PA_UART0 (S5PC100_PA_UART + 0x0)
-#define S5P_PA_UART1 (S5PC100_PA_UART + 0x400)
-#define S5P_PA_UART2 (S5PC100_PA_UART + 0x800)
-#define S5P_PA_UART3 (S5PC100_PA_UART + 0xC00)
-#define S5P_SZ_UART SZ_256
+#define S5PC100_PA_I2S0 0xF2000000
+#define S5PC100_PA_I2S1 0xF2100000
+#define S5PC100_PA_I2S2 0xF2200000
-#define S5PC100_PA_IIC0 (0xEC100000)
-#define S5PC100_PA_IIC1 (0xEC200000)
+#define S5PC100_PA_AC97 0xF2300000
-/* SPI */
-#define S5PC100_PA_SPI0 0xEC300000
-#define S5PC100_PA_SPI1 0xEC400000
-#define S5PC100_PA_SPI2 0xEC500000
+#define S5PC100_PA_PCM0 0xF2400000
+#define S5PC100_PA_PCM1 0xF2500000
-/* USB HS OTG */
-#define S5PC100_PA_USB_HSOTG (0xED200000)
-#define S5PC100_PA_USB_HSPHY (0xED300000)
+#define S5PC100_PA_SPDIF 0xF2600000
-#define S5PC100_PA_FB (0xEE000000)
+#define S5PC100_PA_TSADC 0xF3000000
-#define S5PC100_PA_FIMC0 (0xEE200000)
-#define S5PC100_PA_FIMC1 (0xEE300000)
-#define S5PC100_PA_FIMC2 (0xEE400000)
+#define S5PC100_PA_KEYPAD 0xF3100000
-#define S5PC100_PA_I2S0 (0xF2000000)
-#define S5PC100_PA_I2S1 (0xF2100000)
-#define S5PC100_PA_I2S2 (0xF2200000)
+/* Compatibiltiy Defines */
-#define S5PC100_PA_AC97 0xF2300000
+#define S3C_PA_FB S5PC100_PA_FB
+#define S3C_PA_HSMMC0 S5PC100_PA_HSMMC(0)
+#define S3C_PA_HSMMC1 S5PC100_PA_HSMMC(1)
+#define S3C_PA_HSMMC2 S5PC100_PA_HSMMC(2)
+#define S3C_PA_IIC S5PC100_PA_IIC0
+#define S3C_PA_IIC1 S5PC100_PA_IIC1
+#define S3C_PA_KEYPAD S5PC100_PA_KEYPAD
+#define S3C_PA_ONENAND S5PC100_PA_ONENAND
+#define S3C_PA_ONENAND_BUF S5PC100_PA_ONENAND_BUF
+#define S3C_PA_RTC S5PC100_PA_RTC
+#define S3C_PA_TSADC S5PC100_PA_TSADC
+#define S3C_PA_USB_HSOTG S5PC100_PA_USB_HSOTG
+#define S3C_PA_USB_HSPHY S5PC100_PA_USB_HSPHY
+#define S3C_PA_WDT S5PC100_PA_WATCHDOG
-/* PCM */
-#define S5PC100_PA_PCM0 0xF2400000
-#define S5PC100_PA_PCM1 0xF2500000
+#define S5P_PA_CHIPID S5PC100_PA_CHIPID
+#define S5P_PA_FIMC0 S5PC100_PA_FIMC0
+#define S5P_PA_FIMC1 S5PC100_PA_FIMC1
+#define S5P_PA_FIMC2 S5PC100_PA_FIMC2
+#define S5P_PA_SDRAM S5PC100_PA_SDRAM
+#define S5P_PA_SROMC S5PC100_PA_SROMC
+#define S5P_PA_SYSCON S5PC100_PA_SYSCON
+#define S5P_PA_TIMER S5PC100_PA_TIMER
-#define S5PC100_PA_SPDIF 0xF2600000
+#define SAMSUNG_PA_ADC S5PC100_PA_TSADC
+#define SAMSUNG_PA_CFCON S5PC100_PA_CFCON
+#define SAMSUNG_PA_KEYPAD S5PC100_PA_KEYPAD
-#define S5PC100_PA_TSADC (0xF3000000)
+#define S5PC100_VA_OTHERS (S3C_VA_SYS + 0x10000)
-/* KEYPAD */
-#define S5PC100_PA_KEYPAD (0xF3100000)
+#define S3C_SZ_ONENAND_BUF (SZ_256M - SZ_32M)
-#define S5PC100_PA_HSMMC(x) (0xED800000 + ((x) * 0x100000))
+/* UART */
-#define S5PC100_PA_SDRAM (0x20000000)
-#define S5P_PA_SDRAM S5PC100_PA_SDRAM
+#define S3C_PA_UART S5PC100_PA_UART
-/* compatibiltiy defines. */
-#define S3C_PA_UART S5PC100_PA_UART
-#define S3C_PA_IIC S5PC100_PA_IIC0
-#define S3C_PA_IIC1 S5PC100_PA_IIC1
-#define S3C_PA_FB S5PC100_PA_FB
-#define S3C_PA_G2D S5PC100_PA_G2D
-#define S3C_PA_G3D S5PC100_PA_G3D
-#define S3C_PA_JPEG S5PC100_PA_JPEG
-#define S3C_PA_ROTATOR S5PC100_PA_ROTATOR
-#define S5P_VA_VIC0 S5PC1XX_VA_VIC(0)
-#define S5P_VA_VIC1 S5PC1XX_VA_VIC(1)
-#define S5P_VA_VIC2 S5PC1XX_VA_VIC(2)
-#define S3C_PA_USB_HSOTG S5PC100_PA_USB_HSOTG
-#define S3C_PA_USB_HSPHY S5PC100_PA_USB_HSPHY
-#define S3C_PA_HSMMC0 S5PC100_PA_HSMMC(0)
-#define S3C_PA_HSMMC1 S5PC100_PA_HSMMC(1)
-#define S3C_PA_HSMMC2 S5PC100_PA_HSMMC(2)
-#define S3C_PA_KEYPAD S5PC100_PA_KEYPAD
-#define S3C_PA_WDT S5PC100_PA_WATCHDOG
-#define S3C_PA_TSADC S5PC100_PA_TSADC
-#define S3C_PA_ONENAND S5PC100_PA_ONENAND
-#define S3C_PA_ONENAND_BUF S5PC100_PA_ONENAND_BUF
-#define S3C_SZ_ONENAND_BUF S5PC100_SZ_ONENAND_BUF
-#define S3C_PA_RTC S5PC100_PA_RTC
-
-#define SAMSUNG_PA_ADC S5PC100_PA_TSADC
-#define SAMSUNG_PA_CFCON S5PC100_PA_CFCON
-#define SAMSUNG_PA_KEYPAD S5PC100_PA_KEYPAD
+#define S5P_PA_UART(x) (S3C_PA_UART + ((x) * S3C_UART_OFFSET))
+#define S5P_PA_UART0 S5P_PA_UART(0)
+#define S5P_PA_UART1 S5P_PA_UART(1)
+#define S5P_PA_UART2 S5P_PA_UART(2)
+#define S5P_PA_UART3 S5P_PA_UART(3)
-#define S5P_PA_FIMC0 S5PC100_PA_FIMC0
-#define S5P_PA_FIMC1 S5PC100_PA_FIMC1
-#define S5P_PA_FIMC2 S5PC100_PA_FIMC2
+#define S5P_SZ_UART SZ_256
-#endif /* __ASM_ARCH_C100_MAP_H */
+#endif /* __ASM_ARCH_MAP_H */
/* linux/arch/arm/mach-s5pv210/include/mach/map.h
*
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* S5PV210 - Memory map definitions
#include <plat/map-base.h>
#include <plat/map-s5p.h>
-#define S5PV210_PA_SROM_BANK5 (0xA8000000)
+#define S5PV210_PA_SDRAM 0x20000000
-#define S5PC110_PA_ONENAND (0xB0000000)
-#define S5P_PA_ONENAND S5PC110_PA_ONENAND
+#define S5PV210_PA_SROM_BANK5 0xA8000000
-#define S5PC110_PA_ONENAND_DMA (0xB0600000)
-#define S5P_PA_ONENAND_DMA S5PC110_PA_ONENAND_DMA
+#define S5PC110_PA_ONENAND 0xB0000000
+#define S5PC110_PA_ONENAND_DMA 0xB0600000
-#define S5PV210_PA_CHIPID (0xE0000000)
-#define S5P_PA_CHIPID S5PV210_PA_CHIPID
+#define S5PV210_PA_CHIPID 0xE0000000
-#define S5PV210_PA_SYSCON (0xE0100000)
-#define S5P_PA_SYSCON S5PV210_PA_SYSCON
+#define S5PV210_PA_SYSCON 0xE0100000
-#define S5PV210_PA_GPIO (0xE0200000)
+#define S5PV210_PA_GPIO 0xE0200000
-/* SPI */
-#define S5PV210_PA_SPI0 0xE1300000
-#define S5PV210_PA_SPI1 0xE1400000
+#define S5PV210_PA_SPDIF 0xE1100000
-#define S5PV210_PA_KEYPAD (0xE1600000)
+#define S5PV210_PA_SPI0 0xE1300000
+#define S5PV210_PA_SPI1 0xE1400000
-#define S5PV210_PA_IIC0 (0xE1800000)
-#define S5PV210_PA_IIC1 (0xFAB00000)
-#define S5PV210_PA_IIC2 (0xE1A00000)
+#define S5PV210_PA_KEYPAD 0xE1600000
-#define S5PV210_PA_TIMER (0xE2500000)
-#define S5P_PA_TIMER S5PV210_PA_TIMER
+#define S5PV210_PA_ADC 0xE1700000
-#define S5PV210_PA_SYSTIMER (0xE2600000)
+#define S5PV210_PA_IIC0 0xE1800000
+#define S5PV210_PA_IIC1 0xFAB00000
+#define S5PV210_PA_IIC2 0xE1A00000
-#define S5PV210_PA_WATCHDOG (0xE2700000)
+#define S5PV210_PA_AC97 0xE2200000
-#define S5PV210_PA_RTC (0xE2800000)
-#define S5PV210_PA_UART (0xE2900000)
+#define S5PV210_PA_PCM0 0xE2300000
+#define S5PV210_PA_PCM1 0xE1200000
+#define S5PV210_PA_PCM2 0xE2B00000
-#define S5P_PA_UART0 (S5PV210_PA_UART + 0x0)
-#define S5P_PA_UART1 (S5PV210_PA_UART + 0x400)
-#define S5P_PA_UART2 (S5PV210_PA_UART + 0x800)
-#define S5P_PA_UART3 (S5PV210_PA_UART + 0xC00)
+#define S5PV210_PA_TIMER 0xE2500000
+#define S5PV210_PA_SYSTIMER 0xE2600000
+#define S5PV210_PA_WATCHDOG 0xE2700000
+#define S5PV210_PA_RTC 0xE2800000
-#define S5P_SZ_UART SZ_256
+#define S5PV210_PA_UART 0xE2900000
-#define S3C_VA_UARTx(x) (S3C_VA_UART + ((x) * S3C_UART_OFFSET))
+#define S5PV210_PA_SROMC 0xE8000000
-#define S5PV210_PA_SROMC (0xE8000000)
-#define S5P_PA_SROMC S5PV210_PA_SROMC
+#define S5PV210_PA_CFCON 0xE8200000
-#define S5PV210_PA_CFCON (0xE8200000)
+#define S5PV210_PA_HSMMC(x) (0xEB000000 + ((x) * 0x100000))
-#define S5PV210_PA_MDMA 0xFA200000
-#define S5PV210_PA_PDMA0 0xE0900000
-#define S5PV210_PA_PDMA1 0xE0A00000
+#define S5PV210_PA_HSOTG 0xEC000000
+#define S5PV210_PA_HSPHY 0xEC100000
-#define S5PV210_PA_FB (0xF8000000)
+#define S5PV210_PA_IIS0 0xEEE30000
+#define S5PV210_PA_IIS1 0xE2100000
+#define S5PV210_PA_IIS2 0xE2A00000
-#define S5PV210_PA_FIMC0 (0xFB200000)
-#define S5PV210_PA_FIMC1 (0xFB300000)
-#define S5PV210_PA_FIMC2 (0xFB400000)
+#define S5PV210_PA_DMC0 0xF0000000
+#define S5PV210_PA_DMC1 0xF1400000
-#define S5PV210_PA_HSMMC(x) (0xEB000000 + ((x) * 0x100000))
+#define S5PV210_PA_VIC0 0xF2000000
+#define S5PV210_PA_VIC1 0xF2100000
+#define S5PV210_PA_VIC2 0xF2200000
+#define S5PV210_PA_VIC3 0xF2300000
-#define S5PV210_PA_HSOTG (0xEC000000)
-#define S5PV210_PA_HSPHY (0xEC100000)
+#define S5PV210_PA_FB 0xF8000000
-#define S5PV210_PA_VIC0 (0xF2000000)
-#define S5PV210_PA_VIC1 (0xF2100000)
-#define S5PV210_PA_VIC2 (0xF2200000)
-#define S5PV210_PA_VIC3 (0xF2300000)
+#define S5PV210_PA_MDMA 0xFA200000
+#define S5PV210_PA_PDMA0 0xE0900000
+#define S5PV210_PA_PDMA1 0xE0A00000
-#define S5PV210_PA_SDRAM (0x20000000)
-#define S5P_PA_SDRAM S5PV210_PA_SDRAM
+#define S5PV210_PA_MIPI_CSIS 0xFA600000
-/* S/PDIF */
-#define S5PV210_PA_SPDIF 0xE1100000
+#define S5PV210_PA_FIMC0 0xFB200000
+#define S5PV210_PA_FIMC1 0xFB300000
+#define S5PV210_PA_FIMC2 0xFB400000
-/* I2S */
-#define S5PV210_PA_IIS0 0xEEE30000
-#define S5PV210_PA_IIS1 0xE2100000
-#define S5PV210_PA_IIS2 0xE2A00000
+/* Compatibiltiy Defines */
-/* PCM */
-#define S5PV210_PA_PCM0 0xE2300000
-#define S5PV210_PA_PCM1 0xE1200000
-#define S5PV210_PA_PCM2 0xE2B00000
+#define S3C_PA_FB S5PV210_PA_FB
+#define S3C_PA_HSMMC0 S5PV210_PA_HSMMC(0)
+#define S3C_PA_HSMMC1 S5PV210_PA_HSMMC(1)
+#define S3C_PA_HSMMC2 S5PV210_PA_HSMMC(2)
+#define S3C_PA_HSMMC3 S5PV210_PA_HSMMC(3)
+#define S3C_PA_IIC S5PV210_PA_IIC0
+#define S3C_PA_IIC1 S5PV210_PA_IIC1
+#define S3C_PA_IIC2 S5PV210_PA_IIC2
+#define S3C_PA_RTC S5PV210_PA_RTC
+#define S3C_PA_USB_HSOTG S5PV210_PA_HSOTG
+#define S3C_PA_WDT S5PV210_PA_WATCHDOG
-/* AC97 */
-#define S5PV210_PA_AC97 0xE2200000
+#define S5P_PA_CHIPID S5PV210_PA_CHIPID
+#define S5P_PA_FIMC0 S5PV210_PA_FIMC0
+#define S5P_PA_FIMC1 S5PV210_PA_FIMC1
+#define S5P_PA_FIMC2 S5PV210_PA_FIMC2
+#define S5P_PA_MIPI_CSIS0 S5PV210_PA_MIPI_CSIS
+#define S5P_PA_ONENAND S5PC110_PA_ONENAND
+#define S5P_PA_ONENAND_DMA S5PC110_PA_ONENAND_DMA
+#define S5P_PA_SDRAM S5PV210_PA_SDRAM
+#define S5P_PA_SROMC S5PV210_PA_SROMC
+#define S5P_PA_SYSCON S5PV210_PA_SYSCON
+#define S5P_PA_TIMER S5PV210_PA_TIMER
-#define S5PV210_PA_ADC (0xE1700000)
+#define SAMSUNG_PA_ADC S5PV210_PA_ADC
+#define SAMSUNG_PA_CFCON S5PV210_PA_CFCON
+#define SAMSUNG_PA_KEYPAD S5PV210_PA_KEYPAD
-#define S5PV210_PA_DMC0 (0xF0000000)
-#define S5PV210_PA_DMC1 (0xF1400000)
+/* UART */
-#define S5PV210_PA_MIPI_CSIS 0xFA600000
+#define S3C_VA_UARTx(x) (S3C_VA_UART + ((x) * S3C_UART_OFFSET))
-/* compatibiltiy defines. */
-#define S3C_PA_UART S5PV210_PA_UART
-#define S3C_PA_HSMMC0 S5PV210_PA_HSMMC(0)
-#define S3C_PA_HSMMC1 S5PV210_PA_HSMMC(1)
-#define S3C_PA_HSMMC2 S5PV210_PA_HSMMC(2)
-#define S3C_PA_HSMMC3 S5PV210_PA_HSMMC(3)
-#define S3C_PA_IIC S5PV210_PA_IIC0
-#define S3C_PA_IIC1 S5PV210_PA_IIC1
-#define S3C_PA_IIC2 S5PV210_PA_IIC2
-#define S3C_PA_FB S5PV210_PA_FB
-#define S3C_PA_RTC S5PV210_PA_RTC
-#define S3C_PA_WDT S5PV210_PA_WATCHDOG
-#define S3C_PA_USB_HSOTG S5PV210_PA_HSOTG
-#define S5P_PA_FIMC0 S5PV210_PA_FIMC0
-#define S5P_PA_FIMC1 S5PV210_PA_FIMC1
-#define S5P_PA_FIMC2 S5PV210_PA_FIMC2
-#define S5P_PA_MIPI_CSIS0 S5PV210_PA_MIPI_CSIS
+#define S3C_PA_UART S5PV210_PA_UART
-#define SAMSUNG_PA_ADC S5PV210_PA_ADC
-#define SAMSUNG_PA_CFCON S5PV210_PA_CFCON
-#define SAMSUNG_PA_KEYPAD S5PV210_PA_KEYPAD
+#define S5P_PA_UART(x) (S3C_PA_UART + ((x) * S3C_UART_OFFSET))
+#define S5P_PA_UART0 S5P_PA_UART(0)
+#define S5P_PA_UART1 S5P_PA_UART(1)
+#define S5P_PA_UART2 S5P_PA_UART(2)
+#define S5P_PA_UART3 S5P_PA_UART(3)
+
+#define S5P_SZ_UART SZ_256
#endif /* __ASM_ARCH_MAP_H */
static struct regulator_init_data aquila_ldo3_data = {
.constraints = {
- .name = "VUSB/MIPI_1.1V",
+ .name = "VUSB+MIPI_1.1V",
.min_uV = 1100000,
.max_uV = 1100000,
.apply_uV = 1,
static struct regulator_init_data aquila_ldo8_data = {
.constraints = {
- .name = "VUSB/VADC_3.3V",
+ .name = "VUSB+VADC_3.3V",
.min_uV = 3300000,
.max_uV = 3300000,
.apply_uV = 1,
static struct regulator_init_data aquila_ldo9_data = {
.constraints = {
- .name = "VCC/VCAM_2.8V",
+ .name = "VCC+VCAM_2.8V",
.min_uV = 2800000,
.max_uV = 2800000,
.apply_uV = 1,
.buck1_set1 = S5PV210_GPH0(3),
.buck1_set2 = S5PV210_GPH0(4),
.buck2_set3 = S5PV210_GPH0(5),
- .buck1_max_voltage1 = 1200000,
- .buck1_max_voltage2 = 1200000,
- .buck2_max_voltage = 1200000,
+ .buck1_voltage1 = 1200000,
+ .buck1_voltage2 = 1200000,
+ .buck1_voltage3 = 1200000,
+ .buck1_voltage4 = 1200000,
+ .buck2_voltage1 = 1200000,
+ .buck2_voltage2 = 1200000,
};
#endif
static struct regulator_init_data goni_ldo3_data = {
.constraints = {
- .name = "VUSB/MIPI_1.1V",
+ .name = "VUSB+MIPI_1.1V",
.min_uV = 1100000,
.max_uV = 1100000,
.apply_uV = 1,
static struct regulator_init_data goni_ldo8_data = {
.constraints = {
- .name = "VUSB/VADC_3.3V",
+ .name = "VUSB+VADC_3.3V",
.min_uV = 3300000,
.max_uV = 3300000,
.apply_uV = 1,
static struct regulator_init_data goni_ldo9_data = {
.constraints = {
- .name = "VCC/VCAM_2.8V",
+ .name = "VCC+VCAM_2.8V",
.min_uV = 2800000,
.max_uV = 2800000,
.apply_uV = 1,
.buck1_set1 = S5PV210_GPH0(3),
.buck1_set2 = S5PV210_GPH0(4),
.buck2_set3 = S5PV210_GPH0(5),
- .buck1_max_voltage1 = 1200000,
- .buck1_max_voltage2 = 1200000,
- .buck2_max_voltage = 1200000,
+ .buck1_voltage1 = 1200000,
+ .buck1_voltage2 = 1200000,
+ .buck1_voltage3 = 1200000,
+ .buck1_voltage4 = 1200000,
+ .buck2_voltage1 = 1200000,
+ .buck2_voltage2 = 1200000,
};
#endif
select S3C_DEV_HSMMC2
select S3C_DEV_HSMMC3
select S5PV310_DEV_PD
+ select S5PV310_DEV_SYSMMU
select S5PV310_SETUP_I2C1
select S5PV310_SETUP_SDHCI
help
/* linux/arch/arm/mach-s5pv310/include/mach/map.h
*
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* S5PV310 - Memory map definitions
#include <plat/map-s5p.h>
-#define S5PV310_PA_SYSRAM (0x02025000)
+#define S5PV310_PA_SYSRAM 0x02025000
-#define S5PV310_PA_SROM_BANK(x) (0x04000000 + ((x) * 0x01000000))
-
-#define S5PC210_PA_ONENAND (0x0C000000)
-#define S5P_PA_ONENAND S5PC210_PA_ONENAND
-
-#define S5PC210_PA_ONENAND_DMA (0x0C600000)
-#define S5P_PA_ONENAND_DMA S5PC210_PA_ONENAND_DMA
-
-#define S5PV310_PA_CHIPID (0x10000000)
-#define S5P_PA_CHIPID S5PV310_PA_CHIPID
-
-#define S5PV310_PA_SYSCON (0x10010000)
-#define S5P_PA_SYSCON S5PV310_PA_SYSCON
+#define S5PV310_PA_I2S0 0x03830000
+#define S5PV310_PA_I2S1 0xE3100000
+#define S5PV310_PA_I2S2 0xE2A00000
-#define S5PV310_PA_PMU (0x10020000)
+#define S5PV310_PA_PCM0 0x03840000
+#define S5PV310_PA_PCM1 0x13980000
+#define S5PV310_PA_PCM2 0x13990000
-#define S5PV310_PA_CMU (0x10030000)
-
-#define S5PV310_PA_WATCHDOG (0x10060000)
-#define S5PV310_PA_RTC (0x10070000)
-
-#define S5PV310_PA_DMC0 (0x10400000)
-
-#define S5PV310_PA_COMBINER (0x10448000)
-
-#define S5PV310_PA_COREPERI (0x10500000)
-#define S5PV310_PA_GIC_CPU (0x10500100)
-#define S5PV310_PA_TWD (0x10500600)
-#define S5PV310_PA_GIC_DIST (0x10501000)
-#define S5PV310_PA_L2CC (0x10502000)
-
-/* DMA */
-#define S5PV310_PA_MDMA 0x10810000
-#define S5PV310_PA_PDMA0 0x12680000
-#define S5PV310_PA_PDMA1 0x12690000
-
-#define S5PV310_PA_GPIO1 (0x11400000)
-#define S5PV310_PA_GPIO2 (0x11000000)
-#define S5PV310_PA_GPIO3 (0x03860000)
-
-#define S5PV310_PA_MIPI_CSIS0 0x11880000
-#define S5PV310_PA_MIPI_CSIS1 0x11890000
+#define S5PV310_PA_SROM_BANK(x) (0x04000000 + ((x) * 0x01000000))
-#define S5PV310_PA_HSMMC(x) (0x12510000 + ((x) * 0x10000))
+#define S5PC210_PA_ONENAND 0x0C000000
+#define S5PC210_PA_ONENAND_DMA 0x0C600000
-#define S5PV310_PA_SROMC (0x12570000)
-#define S5P_PA_SROMC S5PV310_PA_SROMC
+#define S5PV310_PA_CHIPID 0x10000000
-/* S/PDIF */
-#define S5PV310_PA_SPDIF 0xE1100000
+#define S5PV310_PA_SYSCON 0x10010000
+#define S5PV310_PA_PMU 0x10020000
+#define S5PV310_PA_CMU 0x10030000
-/* I2S */
-#define S5PV310_PA_I2S0 0x03830000
-#define S5PV310_PA_I2S1 0xE3100000
-#define S5PV310_PA_I2S2 0xE2A00000
+#define S5PV310_PA_WATCHDOG 0x10060000
+#define S5PV310_PA_RTC 0x10070000
-/* PCM */
-#define S5PV310_PA_PCM0 0x03840000
-#define S5PV310_PA_PCM1 0x13980000
-#define S5PV310_PA_PCM2 0x13990000
+#define S5PV310_PA_DMC0 0x10400000
-/* AC97 */
-#define S5PV310_PA_AC97 0x139A0000
+#define S5PV310_PA_COMBINER 0x10448000
-#define S5PV310_PA_UART (0x13800000)
+#define S5PV310_PA_COREPERI 0x10500000
+#define S5PV310_PA_GIC_CPU 0x10500100
+#define S5PV310_PA_TWD 0x10500600
+#define S5PV310_PA_GIC_DIST 0x10501000
+#define S5PV310_PA_L2CC 0x10502000
-#define S5P_PA_UART(x) (S5PV310_PA_UART + ((x) * S3C_UART_OFFSET))
-#define S5P_PA_UART0 S5P_PA_UART(0)
-#define S5P_PA_UART1 S5P_PA_UART(1)
-#define S5P_PA_UART2 S5P_PA_UART(2)
-#define S5P_PA_UART3 S5P_PA_UART(3)
-#define S5P_PA_UART4 S5P_PA_UART(4)
-
-#define S5P_SZ_UART SZ_256
-
-#define S5PV310_PA_IIC(x) (0x13860000 + ((x) * 0x10000))
-
-#define S5PV310_PA_TIMER (0x139D0000)
-#define S5P_PA_TIMER S5PV310_PA_TIMER
-
-#define S5PV310_PA_SDRAM (0x40000000)
-#define S5P_PA_SDRAM S5PV310_PA_SDRAM
+#define S5PV310_PA_MDMA 0x10810000
+#define S5PV310_PA_PDMA0 0x12680000
+#define S5PV310_PA_PDMA1 0x12690000
#define S5PV310_PA_SYSMMU_MDMA 0x10A40000
#define S5PV310_PA_SYSMMU_SSS 0x10A50000
#define S5PV310_PA_SYSMMU_TV 0x12E20000
#define S5PV310_PA_SYSMMU_MFC_L 0x13620000
#define S5PV310_PA_SYSMMU_MFC_R 0x13630000
-#define S5PV310_SYSMMU_TOTAL_IPNUM 16
-#define S5P_SYSMMU_TOTAL_IPNUM S5PV310_SYSMMU_TOTAL_IPNUM
-/* compatibiltiy defines. */
-#define S3C_PA_UART S5PV310_PA_UART
+#define S5PV310_PA_GPIO1 0x11400000
+#define S5PV310_PA_GPIO2 0x11000000
+#define S5PV310_PA_GPIO3 0x03860000
+
+#define S5PV310_PA_MIPI_CSIS0 0x11880000
+#define S5PV310_PA_MIPI_CSIS1 0x11890000
+
+#define S5PV310_PA_HSMMC(x) (0x12510000 + ((x) * 0x10000))
+
+#define S5PV310_PA_SROMC 0x12570000
+
+#define S5PV310_PA_UART 0x13800000
+
+#define S5PV310_PA_IIC(x) (0x13860000 + ((x) * 0x10000))
+
+#define S5PV310_PA_AC97 0x139A0000
+
+#define S5PV310_PA_TIMER 0x139D0000
+
+#define S5PV310_PA_SDRAM 0x40000000
+
+#define S5PV310_PA_SPDIF 0xE1100000
+
+/* Compatibiltiy Defines */
+
#define S3C_PA_HSMMC0 S5PV310_PA_HSMMC(0)
#define S3C_PA_HSMMC1 S5PV310_PA_HSMMC(1)
#define S3C_PA_HSMMC2 S5PV310_PA_HSMMC(2)
#define S3C_PA_IIC7 S5PV310_PA_IIC(7)
#define S3C_PA_RTC S5PV310_PA_RTC
#define S3C_PA_WDT S5PV310_PA_WATCHDOG
+
+#define S5P_PA_CHIPID S5PV310_PA_CHIPID
#define S5P_PA_MIPI_CSIS0 S5PV310_PA_MIPI_CSIS0
#define S5P_PA_MIPI_CSIS1 S5PV310_PA_MIPI_CSIS1
+#define S5P_PA_ONENAND S5PC210_PA_ONENAND
+#define S5P_PA_ONENAND_DMA S5PC210_PA_ONENAND_DMA
+#define S5P_PA_SDRAM S5PV310_PA_SDRAM
+#define S5P_PA_SROMC S5PV310_PA_SROMC
+#define S5P_PA_SYSCON S5PV310_PA_SYSCON
+#define S5P_PA_TIMER S5PV310_PA_TIMER
+
+/* UART */
+
+#define S3C_PA_UART S5PV310_PA_UART
+
+#define S5P_PA_UART(x) (S3C_PA_UART + ((x) * S3C_UART_OFFSET))
+#define S5P_PA_UART0 S5P_PA_UART(0)
+#define S5P_PA_UART1 S5P_PA_UART(1)
+#define S5P_PA_UART2 S5P_PA_UART(2)
+#define S5P_PA_UART3 S5P_PA_UART(3)
+#define S5P_PA_UART4 S5P_PA_UART(4)
+
+#define S5P_SZ_UART SZ_256
#endif /* __ASM_ARCH_MAP_H */
#ifndef __ASM_ARM_ARCH_SYSMMU_H
#define __ASM_ARM_ARCH_SYSMMU_H __FILE__
+#define S5PV310_SYSMMU_TOTAL_IPNUM 16
+#define S5P_SYSMMU_TOTAL_IPNUM S5PV310_SYSMMU_TOTAL_IPNUM
+
enum s5pv310_sysmmu_ips {
SYSMMU_MDMA,
SYSMMU_SSS,
SYSMMU_MFC_R,
};
-static char *sysmmu_ips_name[S5P_SYSMMU_TOTAL_IPNUM] = {
+static char *sysmmu_ips_name[S5PV310_SYSMMU_TOTAL_IPNUM] = {
"SYSMMU_MDMA" ,
"SYSMMU_SSS" ,
"SYSMMU_FIMC0" ,
struct platform_device collie_locomo_device = {
.name = "locomo",
.id = 0,
+ .dev = {
+ .platform_data = &locomo_info,
+ },
.num_resources = ARRAY_SIZE(locomo_resources),
.resource = locomo_resources,
};
gpio_direction_output(GPIO_PORT217, 0);
mdelay(1);
gpio_set_value(GPIO_PORT217, 1);
+ mdelay(100);
/* LCD backlight controller */
gpio_request(GPIO_PORT235, NULL); /* RESET */
lcdc_info.clock_source = LCDC_CLK_BUS;
lcdc_info.ch[0].interface_type = RGB18;
- lcdc_info.ch[0].clock_divider = 2;
+ lcdc_info.ch[0].clock_divider = 3;
lcdc_info.ch[0].flags = 0;
lcdc_info.ch[0].lcd_size_cfg.width = 152;
lcdc_info.ch[0].lcd_size_cfg.height = 91;
.lcd_cfg = mackerel_lcdc_modes,
.num_cfg = ARRAY_SIZE(mackerel_lcdc_modes),
.interface_type = RGB24,
- .clock_divider = 2,
+ .clock_divider = 3,
.flags = 0,
.lcd_size_cfg.width = 152,
.lcd_size_cfg.height = 91,
};
enum { MSTP001,
- MSTP125, MSTP118, MSTP116, MSTP100,
+ MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP116, MSTP100,
MSTP219,
MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
MSTP331, MSTP329, MSTP325, MSTP323, MSTP312,
static struct clk mstp_clks[MSTP_NR] = {
[MSTP001] = MSTP(&div4_clks[DIV4_HP], SMSTPCR0, 1, 0), /* IIC2 */
+ [MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* CEU1 */
+ [MSTP128] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 28, 0), /* CSI2-RX1 */
+ [MSTP127] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 27, 0), /* CEU0 */
+ [MSTP126] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 26, 0), /* CSI2-RX0 */
[MSTP125] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 25, 0), /* TMU0 */
[MSTP118] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 18, 0), /* DSITX0 */
[MSTP116] = MSTP(&div4_clks[DIV4_HP], SMSTPCR1, 16, 0), /* IIC0 */
CLKDEV_CON_ID("r_clk", &r_clk),
/* DIV6 clocks */
+ CLKDEV_CON_ID("vck1_clk", &div6_clks[DIV6_VCK1]),
+ CLKDEV_CON_ID("vck2_clk", &div6_clks[DIV6_VCK2]),
+ CLKDEV_CON_ID("vck3_clk", &div6_clks[DIV6_VCK3]),
CLKDEV_ICK_ID("dsit_clk", "sh-mipi-dsi.0", &div6_clks[DIV6_DSIT]),
CLKDEV_ICK_ID("dsit_clk", "sh-mipi-dsi.1", &div6_clks[DIV6_DSIT]),
CLKDEV_ICK_ID("dsi0p_clk", "sh-mipi-dsi.0", &div6_clks[DIV6_DSI0P]),
/* MSTP32 clocks */
CLKDEV_DEV_ID("i2c-sh_mobile.2", &mstp_clks[MSTP001]), /* I2C2 */
- CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
+ CLKDEV_DEV_ID("sh_mobile_ceu.1", &mstp_clks[MSTP129]), /* CEU1 */
+ CLKDEV_DEV_ID("sh-mobile-csi2.1", &mstp_clks[MSTP128]), /* CSI2-RX1 */
+ CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[MSTP127]), /* CEU0 */
+ CLKDEV_DEV_ID("sh-mobile-csi2.0", &mstp_clks[MSTP126]), /* CSI2-RX0 */
CLKDEV_DEV_ID("sh_tmu.0", &mstp_clks[MSTP125]), /* TMU00 */
CLKDEV_DEV_ID("sh_tmu.1", &mstp_clks[MSTP125]), /* TMU01 */
- CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* I2C0 */
CLKDEV_DEV_ID("sh-mipi-dsi.0", &mstp_clks[MSTP118]), /* DSITX */
+ CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* I2C0 */
+ CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
CLKDEV_DEV_ID("sh-sci.7", &mstp_clks[MSTP219]), /* SCIFA7 */
CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
CLKDEV_DEV_ID("sh-sci.8", &mstp_clks[MSTP206]), /* SCIFB */
EW 0xE6020004, 0xA500
EW 0xE6030004, 0xA500
-DD 0x01001000, 0x01001000
-
LIST "GPIO Setting"
EB 0xE6051013, 0xA2
LIST "CPG"
-ED 0xE6150080, 0x00000180
ED 0xE61500C0, 0x00000002
WAIT 1, 0xFE40009C
WAIT 1, 0xFE40009C
+LIST "SUB/USBClk"
+ED 0xE6150080, 0x00000180
+
LIST "BSC"
ED 0xFEC10000, 0x00E0001B
ED 0xFE40004C, 0x00110209
ED 0xFE400010, 0x00000087
-WAIT 10, 0xFE40009C
+WAIT 30, 0xFE40009C
ED 0xFE400084, 0x0000003F
EB 0xFE500000, 0x00
WAIT 1, 0xFE40009C
-ED 0xE6150354, 0x00000002
+ED 0xFE400354, 0x01AD8002
LIST "SCIF0 - Serial port for earlyprintk"
EB 0xE6053098, 0x11
EW 0xE6020004, 0xA500
EW 0xE6030004, 0xA500
-DD 0x01001000, 0x01001000
-
LIST "GPIO Setting"
EB 0xE6051013, 0xA2
LIST "CPG"
-ED 0xE6150080, 0x00000180
ED 0xE61500C0, 0x00000002
WAIT 1, 0xFE40009C
WAIT 1, 0xFE40009C
+LIST "SUB/USBClk"
+ED 0xE6150080, 0x00000180
+
LIST "BSC"
ED 0xFEC10000, 0x00E0001B
ED 0xFE40004C, 0x00110209
ED 0xFE400010, 0x00000087
-WAIT 10, 0xFE40009C
+WAIT 30, 0xFE40009C
ED 0xFE400084, 0x0000003F
EB 0xFE500000, 0x00
WAIT 1, 0xFE40009C
-ED 0xE6150354, 0x00000002
+ED 0xFE400354, 0x01AD8002
LIST "SCIF0 - Serial port for earlyprintk"
EB 0xE6053098, 0x11
#define SPEAR320_SMII1_BASE 0xAB000000
#define SPEAR320_SMII1_SIZE 0x01000000
-#define SPEAR320_SOC_CONFIG_BASE 0xB4000000
+#define SPEAR320_SOC_CONFIG_BASE 0xB3000000
#define SPEAR320_SOC_CONFIG_SIZE 0x00000070
/* Interrupt registers offsets and masks */
#define INT_STS_MASK_REG 0x04
const struct matrix_keymap_data *keymap_data;
bool wakeup;
+ bool use_fn_map;
};
#endif
config CPU_32v6K
bool "Support ARM V6K processor extensions" if !SMP
depends on CPU_V6 || CPU_V7
- default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
+ default y if SMP
help
Say Y here if your ARMv6 processor supports the 'K' extension.
This enables the kernel to use some instructions not present
# ARMv7
config CPU_V7
bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
- select CPU_32v6K if !ARCH_OMAP2
+ select CPU_32v6K
select CPU_32v7
select CPU_ABRT_EV7
select CPU_PABRT_V7
config SWP_EMULATE
bool "Emulate SWP/SWPB instructions"
- depends on CPU_V7 && !CPU_V6
+ depends on !CPU_USE_DOMAINS && CPU_V7 && !CPU_V6
select HAVE_PROC_CPU if PROC_FS
default y if SMP
help
static inline void cache_sync(void)
{
void __iomem *base = l2x0_base;
+
+#ifdef CONFIG_ARM_ERRATA_753970
+ /* write to an unmmapped register */
+ writel_relaxed(0, base + L2X0_DUMMY_REG);
+#else
writel_relaxed(0, base + L2X0_CACHE_SYNC);
+#endif
cache_wait(base + L2X0_CACHE_SYNC, 1);
}
orreq r10, r10, #1 << 6 @ set bit #6
mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register
#endif
+#ifdef CONFIG_ARM_ERRATA_751472
+ cmp r6, #0x30 @ present prior to r3p0
+ mrclt p15, 0, r10, c15, c0, 1 @ read diagnostic register
+ orrlt r10, r10, #1 << 11 @ set bit #11
+ mcrlt p15, 0, r10, c15, c0, 1 @ write diagnostic register
+#endif
3: mov r10, #0
#ifdef HARVARD_CACHE
*/
#include <linux/cpumask.h>
-#include <linux/err.h>
-#include <linux/errno.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/oprofile.h>
return NULL;
}
}
+#endif
static int report_trace(struct stackframe *frame, void *d)
{
/* frame pointers should strictly progress back up the stack
* (towards higher addresses) */
- if (tail >= buftail[0].fp)
+ if (tail + 1 >= buftail[0].fp)
return NULL;
return buftail[0].fp-1;
int __init oprofile_arch_init(struct oprofile_operations *ops)
{
+ /* provide backtrace support also in timer mode: */
ops->backtrace = arm_backtrace;
return oprofile_perf_init(ops);
{
oprofile_perf_exit();
}
-#else
-int __init oprofile_arch_init(struct oprofile_operations *ops)
-{
- pr_info("oprofile: hardware counters not available\n");
- return -ENODEV;
-}
-void __exit oprofile_arch_exit(void) {}
-#endif /* CONFIG_HW_PERF_EVENTS */
struct omap_mbox *omap_mbox_get(const char *name, struct notifier_block *nb)
{
- struct omap_mbox *mbox;
- int ret;
+ struct omap_mbox *_mbox, *mbox = NULL;
+ int i, ret;
if (!mboxes)
return ERR_PTR(-EINVAL);
- for (mbox = *mboxes; mbox; mbox++)
- if (!strcmp(mbox->name, name))
+ for (i = 0; (_mbox = mboxes[i]); i++) {
+ if (!strcmp(_mbox->name, name)) {
+ mbox = _mbox;
break;
+ }
+ }
if (!mbox)
return ERR_PTR(-ENOENT);
#define mfp_configured(p) ((p)->config != -1)
/*
- * perform a read-back of any MFPR register to make sure the
+ * perform a read-back of any valid MFPR register to make sure the
* previous writings are finished
*/
-#define mfpr_sync() (void)__raw_readl(mfpr_mmio_base + 0)
+static unsigned long mfpr_off_readback;
+#define mfpr_sync() (void)__raw_readl(mfpr_mmio_base + mfpr_off_readback)
static inline void __mfp_config_run(struct mfp_pin *p)
{
spin_lock_irqsave(&mfp_spin_lock, flags);
+ /* mfp offset for readback */
+ mfpr_off_readback = map[0].offset;
+
for (p = map; p->start != MFP_PIN_INVALID; p++) {
offset = p->offset;
i = p->start;
help
Common code for the GPIO interrupts (other than external interrupts.)
+comment "System MMU"
+
+config S5P_SYSTEM_MMU
+ bool "S5P SYSTEM MMU"
+ depends on ARCH_S5PV310
+ help
+ Say Y here if you want to enable System MMU
+
config S5P_DEV_FIMC0
bool
help
bool
help
Compile in platform device definitions for MIPI-CSIS channel 1
-
-menuconfig S5P_SYSMMU
- bool "SYSMMU support"
- depends on ARCH_S5PV310
- help
- This is a System MMU driver for Samsung ARM based Soc.
-
-if S5P_SYSMMU
-
-config S5P_SYSMMU_DEBUG
- bool "Enables debug messages"
- depends on S5P_SYSMMU
- help
- This enables SYSMMU driver debug massages.
-
-endif
obj-y += irq.o
obj-$(CONFIG_S5P_EXT_INT) += irq-eint.o
obj-$(CONFIG_S5P_GPIO_INT) += irq-gpioint.o
+obj-$(CONFIG_S5P_SYSTEM_MMU) += sysmmu.o
obj-$(CONFIG_PM) += pm.o
obj-$(CONFIG_PM) += irq-pm.o
obj-$(CONFIG_S5P_DEV_ONENAND) += dev-onenand.o
obj-$(CONFIG_S5P_DEV_CSIS0) += dev-csis0.o
obj-$(CONFIG_S5P_DEV_CSIS1) += dev-csis1.o
-obj-$(CONFIG_S5P_SYSMMU) += sysmmu.o
static struct resource s5p_uart0_resource[] = {
[0] = {
.start = S5P_PA_UART0,
- .end = S5P_PA_UART0 + S5P_SZ_UART,
+ .end = S5P_PA_UART0 + S5P_SZ_UART - 1,
.flags = IORESOURCE_MEM,
},
[1] = {
static struct resource s5p_uart1_resource[] = {
[0] = {
.start = S5P_PA_UART1,
- .end = S5P_PA_UART1 + S5P_SZ_UART,
+ .end = S5P_PA_UART1 + S5P_SZ_UART - 1,
.flags = IORESOURCE_MEM,
},
[1] = {
static struct resource s5p_uart2_resource[] = {
[0] = {
.start = S5P_PA_UART2,
- .end = S5P_PA_UART2 + S5P_SZ_UART,
+ .end = S5P_PA_UART2 + S5P_SZ_UART - 1,
.flags = IORESOURCE_MEM,
},
[1] = {
#if CONFIG_SERIAL_SAMSUNG_UARTS > 3
[0] = {
.start = S5P_PA_UART3,
- .end = S5P_PA_UART3 + S5P_SZ_UART,
+ .end = S5P_PA_UART3 + S5P_SZ_UART - 1,
.flags = IORESOURCE_MEM,
},
[1] = {
#if CONFIG_SERIAL_SAMSUNG_UARTS > 4
[0] = {
.start = S5P_PA_UART4,
- .end = S5P_PA_UART4 + S5P_SZ_UART,
+ .end = S5P_PA_UART4 + S5P_SZ_UART - 1,
.flags = IORESOURCE_MEM,
},
[1] = {
#if CONFIG_SERIAL_SAMSUNG_UARTS > 5
[0] = {
.start = S5P_PA_UART5,
- .end = S5P_PA_UART5 + S5P_SZ_UART,
+ .end = S5P_PA_UART5 + S5P_SZ_UART - 1,
.flags = IORESOURCE_MEM,
},
[1] = {
+++ /dev/null
-/* linux/arch/arm/plat-s5p/include/plat/sysmmu.h
- *
- * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- * http://www.samsung.com/
- *
- * Samsung sysmmu driver
- *
- * 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.
-*/
-
-#ifndef __ASM_PLAT_S5P_SYSMMU_H
-#define __ASM_PLAT_S5P_SYSMMU_H __FILE__
-
-/* debug macro */
-#ifdef CONFIG_S5P_SYSMMU_DEBUG
-#define sysmmu_debug(fmt, arg...) printk(KERN_INFO "[%s] " fmt, __func__, ## arg)
-#else
-#define sysmmu_debug(fmt, arg...) do { } while (0)
-#endif
-
-#endif /* __ASM_PLAT_S5P_SYSMMU_H */
#include <mach/regs-sysmmu.h>
#include <mach/sysmmu.h>
-#include <plat/sysmmu.h>
-
struct sysmmu_controller s5p_sysmmu_cntlrs[S5P_SYSMMU_TOTAL_IPNUM];
void s5p_sysmmu_register(struct sysmmu_controller *sysmmuconp)
: "=r" (pg) : : "cc"); \
pg &= ~0x3fff;
- sysmmu_debug("CP15 TTBR0 : 0x%x\n", pg);
+ printk(KERN_INFO "%s: CP15 TTBR0 : 0x%x\n", __func__, pg);
/* Set sysmmu page table base address */
__raw_writel(pg, sysmmuconp->regs + S5P_PT_BASE_ADDR);
s3c_device_ts.dev.platform_data = npd;
}
-EXPORT_SYMBOL(s3c24xx_ts_set_platdata);
#include <linux/kernel.h>
#include <linux/platform_device.h>
+#include <plat/devs.h>
+
/* uart devices */
static struct platform_device s3c24xx_uart_device0 = {
#include <linux/irq.h>
+struct sys_device;
+
#ifdef CONFIG_PM
extern __init int s3c_pm_init(void);
{
void __iomem *base = (void __iomem *)SPEAR_DBG_UART_BASE;
- while (readl(base + UART01x_FR) & UART01x_FR_TXFF)
+ while (readl_relaxed(base + UART01x_FR) & UART01x_FR_TXFF)
barrier();
- writel(c, base + UART01x_DR);
+ writel_relaxed(c, base + UART01x_DR);
}
static inline void flush(void)
#ifndef __PLAT_VMALLOC_H
#define __PLAT_VMALLOC_H
-#define VMALLOC_END 0xF0000000
+#define VMALLOC_END 0xF0000000UL
#endif /* __PLAT_VMALLOC_H */
#define __BFIN_ASM_SERIAL_H__
#include <linux/serial_core.h>
+#include <linux/spinlock.h>
#include <mach/anomaly.h>
#include <mach/bfin_serial.h>
struct circ_buf rx_dma_buf;
struct timer_list rx_dma_timer;
int rx_dma_nrows;
+ spinlock_t rx_lock;
unsigned int tx_dma_channel;
unsigned int rx_dma_channel;
struct work_struct tx_dma_workqueue;
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
#ifdef CONFIG_CORE_TIMER_IRQ_L1
__attribute__((l1_text))
#endif
irqreturn_t timer_interrupt(int irq, void *dummy)
{
- write_seqlock(&xtime_lock);
- do_timer(1);
- write_sequnlock(&xtime_lock);
+ xtime_update(1);
#ifdef CONFIG_IPIPE
update_root_process_times(get_irq_regs());
.align 2
ENTRY(_outsl)
+ CC = R2 == 0;
+ IF CC JUMP 1f;
P0 = R0; /* P0 = port */
P1 = R1; /* P1 = address */
P2 = R2; /* P2 = count */
LSETUP( .Llong_loop_s, .Llong_loop_e) LC0 = P2;
.Llong_loop_s: R0 = [P1++];
.Llong_loop_e: [P0] = R0;
- RTS;
+1: RTS;
ENDPROC(_outsl)
ENTRY(_outsw)
+ CC = R2 == 0;
+ IF CC JUMP 1f;
P0 = R0; /* P0 = port */
P1 = R1; /* P1 = address */
P2 = R2; /* P2 = count */
LSETUP( .Lword_loop_s, .Lword_loop_e) LC0 = P2;
.Lword_loop_s: R0 = W[P1++];
.Lword_loop_e: W[P0] = R0;
- RTS;
+1: RTS;
ENDPROC(_outsw)
ENTRY(_outsb)
+ CC = R2 == 0;
+ IF CC JUMP 1f;
P0 = R0; /* P0 = port */
P1 = R1; /* P1 = address */
P2 = R2; /* P2 = count */
LSETUP( .Lbyte_loop_s, .Lbyte_loop_e) LC0 = P2;
.Lbyte_loop_s: R0 = B[P1++];
.Lbyte_loop_e: B[P0] = R0;
- RTS;
+1: RTS;
ENDPROC(_outsb)
ENTRY(_outsw_8)
+ CC = R2 == 0;
+ IF CC JUMP 1f;
P0 = R0; /* P0 = port */
P1 = R1; /* P1 = address */
P2 = R2; /* P2 = count */
R0 = R0 << 8;
R0 = R0 + R1;
.Lword8_loop_e: W[P0] = R0;
- RTS;
+1: RTS;
ENDPROC(_outsw_8)
1:
.ifeqs "\flushins", BROK_FLUSH_INST
\flushins [P0++];
+ nop;
+ nop;
2: nop;
.else
2: \flushins [P0++];
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
//static unsigned short myjiff; /* used by our debug routine print_timestamp */
/* call the real timer interrupt handler */
- do_timer(1);
+ xtime_update(1);
cris_do_profile(regs); /* Save profiling information */
return IRQ_HANDLED;
#define FLUSH_ALL (void*)0xffffffff
/* Vector of locks used for various atomic operations */
-spinlock_t cris_atomic_locks[] = { [0 ... LOCK_COUNT - 1] = SPIN_LOCK_UNLOCKED};
+spinlock_t cris_atomic_locks[] = {
+ [0 ... LOCK_COUNT - 1] = __SPIN_LOCK_UNLOCKED(cris_atomic_locks)
+};
/* CPU masks */
cpumask_t phys_cpu_present_map = CPU_MASK_NONE;
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick.
+ * as well as call the "xtime_update()" routine every clocktick.
*/
extern void cris_do_profile(struct pt_regs *regs);
return IRQ_HANDLED;
/* Call the real timer interrupt handler */
- write_seqlock(&xtime_lock);
- do_timer(1);
- write_sequnlock(&xtime_lock);
+ xtime_update(1);
return IRQ_HANDLED;
}
INIT_TEXT_SECTION(PAGE_SIZE)
.init.data : { INIT_DATA }
.init.setup : { INIT_SETUP(16) }
-#ifdef CONFIG_ETRAX_ARCH_V32
- __start___param = .;
- __param : { *(__param) }
- __stop___param = .;
-#endif
.initcall.init : {
INIT_CALLS
}
#include <asm/errno.h>
#include <asm/uaccess.h>
-extern int futex_atomic_op_inuser(int encoded_op, int __user *uaddr);
+extern int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr);
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
return -ENOSYS;
}
* the various futex operations; MMU fault checking is ignored under no-MMU
* conditions
*/
-static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr, int *_oldval)
{
int oldval, ret;
return ret;
}
-static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr, int *_oldval)
{
int oldval, ret;
return ret;
}
-static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr, int *_oldval)
{
int oldval, ret;
return ret;
}
-static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr, int *_oldval)
{
int oldval, ret;
return ret;
}
-static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr, int *_oldval)
{
int oldval, ret;
/*
* do the futex operations
*/
-int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
static irqreturn_t timer_interrupt(int irq, void *dummy)
{
profile_tick(CPU_PROFILING);
- /*
- * Here we are in the timer irq handler. We just have irqs locally
- * disabled but we don't know if the timer_bh is running on the other
- * CPU. We need to avoid to SMP race with it. NOTE: we don't need
- * the irq version of write_lock because as just said we have irq
- * locally disabled. -arca
- */
- write_seqlock(&xtime_lock);
- do_timer(1);
+ xtime_update(1);
#ifdef CONFIG_HEARTBEAT
static unsigned short n;
__set_LEDS(n);
#endif /* CONFIG_HEARTBEAT */
- write_sequnlock(&xtime_lock);
-
update_process_times(user_mode(get_irq_regs()));
return IRQ_HANDLED;
{
if (current->pid)
profile_tick(CPU_PROFILING);
- write_seqlock(&xtime_lock);
- do_timer(1);
- write_sequnlock(&xtime_lock);
+ xtime_update(1);
update_process_times(user_mode(get_irq_regs()));
}
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
static irqreturn_t timer_interrupt(int irq, void *dev_id)
} while (0)
static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+ if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
{
- register unsigned long r8 __asm ("r8");
+ register unsigned long r8 __asm ("r8") = 0;
+ unsigned long prev;
__asm__ __volatile__(
" mf;; \n"
" mov ar.ccv=%3;; \n"
"[1:] cmpxchg4.acq %0=[%1],%2,ar.ccv \n"
" .xdata4 \"__ex_table\", 1b-., 2f-. \n"
"[2:]"
- : "=r" (r8)
+ : "=r" (prev)
: "r" (uaddr), "r" (newval),
"rO" ((long) (unsigned) oldval)
: "memory");
+ *uval = prev;
return r8;
}
}
#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
#endif
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
#include <asm/intrinsics.h>
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
- signed long count;
- spinlock_t wait_lock;
- struct list_head wait_list;
-};
-
#define RWSEM_UNLOCKED_VALUE __IA64_UL_CONST(0x0000000000000000)
#define RWSEM_ACTIVE_BIAS (1L)
#define RWSEM_ACTIVE_MASK (0xffffffffL)
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-#define __RWSEM_INITIALIZER(name) \
- { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
- LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-static inline void
-init_rwsem (struct rw_semaphore *sem)
-{
- sem->count = RWSEM_UNLOCKED_VALUE;
- spin_lock_init(&sem->wait_lock);
- INIT_LIST_HEAD(&sem->wait_list);
-}
-
/*
* lock for reading
*/
#define rwsem_atomic_add(delta, sem) atomic64_add(delta, (atomic64_t *)(&(sem)->count))
#define rwsem_atomic_update(delta, sem) atomic64_add_return(delta, (atomic64_t *)(&(sem)->count))
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
- return (sem->count != 0);
-}
-
#endif /* _ASM_IA64_RWSEM_H */
static inline int
xencomm_arch_hypercall_sched_op(int cmd, struct xencomm_handle *arg)
{
- return _hypercall2(int, sched_op_new, cmd, arg);
+ return _hypercall2(int, sched_op, cmd, arg);
}
static inline long
new_itm += local_cpu_data->itm_delta;
- if (smp_processor_id() == time_keeper_id) {
- /*
- * Here we are in the timer irq handler. We have irqs locally
- * disabled, but we don't know if the timer_bh is running on
- * another CPU. We need to avoid to SMP race by acquiring the
- * xtime_lock.
- */
- write_seqlock(&xtime_lock);
- do_timer(1);
- local_cpu_data->itm_next = new_itm;
- write_sequnlock(&xtime_lock);
- } else
- local_cpu_data->itm_next = new_itm;
+ if (smp_processor_id() == time_keeper_id)
+ xtime_update(1);
+
+ local_cpu_data->itm_next = new_itm;
if (time_after(new_itm, ia64_get_itc()))
break;
* comfort, we increase the safety margin by
* intentionally dropping the next tick(s). We do NOT
* update itm.next because that would force us to call
- * do_timer() which in turn would let our clock run
+ * xtime_update() which in turn would let our clock run
* too fast (with the potentially devastating effect
* of losing monotony of time).
*/
/* nothing */
}
-void xen_pre_device_suspend(void)
-{
- /* nothing */
-}
-
void
-xen_pre_suspend()
+xen_arch_pre_suspend()
{
/* nothing */
}
void
-xen_post_suspend(int suspend_cancelled)
+xen_arch_post_suspend(int suspend_cancelled)
{
if (suspend_cancelled)
return;
run_posix_cpu_timers(p);
delta_itm += local_cpu_data->itm_delta * (stolen + blocked);
- if (cpu == time_keeper_id) {
- write_seqlock(&xtime_lock);
- do_timer(stolen + blocked);
- local_cpu_data->itm_next = delta_itm + new_itm;
- write_sequnlock(&xtime_lock);
- } else {
- local_cpu_data->itm_next = delta_itm + new_itm;
- }
+ if (cpu == time_keeper_id)
+ xtime_update(stolen + blocked);
+
+ local_cpu_data->itm_next = delta_itm + new_itm;
+
per_cpu(xen_stolen_time, cpu) += NS_PER_TICK * stolen;
per_cpu(xen_blocked_time, cpu) += NS_PER_TICK * blocked;
}
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
static irqreturn_t timer_interrupt(int irq, void *dev_id)
{
#ifndef CONFIG_SMP
profile_tick(CPU_PROFILING);
#endif
- /* XXX FIXME. Uh, the xtime_lock should be held here, no? */
- do_timer(1);
+ xtime_update(1);
#ifndef CONFIG_SMP
update_process_times(user_mode(get_irq_regs()));
extern void bvme6000_reset (void);
void bvme6000_set_vectors (void);
-/* Save tick handler routine pointer, will point to do_timer() in
- * kernel/sched.c, called via bvme6000_process_int() */
+/* Save tick handler routine pointer, will point to xtime_update() in
+ * kernel/timer/timekeeping.c, called via bvme6000_process_int() */
static irq_handler_t tick_handler;
: "+a" (cs), "+a" (ct), "=d" (res));
return res;
}
+#endif /* CONFIG_COLDFIRE */
#define __HAVE_ARCH_MEMMOVE
extern void *memmove(void *, const void *, __kernel_size_t);
-#define __HAVE_ARCH_MEMCMP
-extern int memcmp(const void *, const void *, __kernel_size_t);
#define memcmp(d, s, n) __builtin_memcmp(d, s, n)
-#endif /* CONFIG_COLDFIRE */
#define __HAVE_ARCH_MEMSET
extern void *memset(void *, int, __kernel_size_t);
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
static irqreturn_t timer_interrupt(int irq, void *dummy)
{
- do_timer(1);
+ xtime_update(1);
update_process_times(user_mode(get_irq_regs()));
profile_tick(CPU_PROFILING);
return xdest;
}
EXPORT_SYMBOL(memmove);
-
-int memcmp(const void *cs, const void *ct, size_t count)
-{
- const unsigned char *su1, *su2;
-
- for (su1 = cs, su2 = ct; count > 0; ++su1, ++su2, count--)
- if (*su1 != *su2)
- return *su1 < *su2 ? -1 : +1;
- return 0;
-}
-EXPORT_SYMBOL(memcmp);
static int bcd2int (unsigned char b);
-/* Save tick handler routine pointer, will point to do_timer() in
- * kernel/sched.c, called via mvme147_process_int() */
+/* Save tick handler routine pointer, will point to xtime_update() in
+ * kernel/time/timekeeping.c, called via mvme147_process_int() */
irq_handler_t tick_handler;
int bcd2int (unsigned char b);
-/* Save tick handler routine pointer, will point to do_timer() in
- * kernel/sched.c, called via mvme16x_process_int() */
+/* Save tick handler routine pointer, will point to xtime_update() in
+ * kernel/time/timekeeping.c, called via mvme16x_process_int() */
static irq_handler_t tick_handler;
#ifdef CONFIG_SUN3
intersil_clear();
#endif
- do_timer(1);
+ xtime_update(1);
update_process_times(user_mode(get_irq_regs()));
if (!(kstat_cpu(0).irqs[irq] % 20))
sun3_leds(led_pattern[(kstat_cpu(0).irqs[irq] % 160) / 20]);
#ifndef CONFIG_GENERIC_CLOCKEVENTS
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
irqreturn_t arch_timer_interrupt(int irq, void *dummy)
{
if (current->pid)
profile_tick(CPU_PROFILING);
- write_seqlock(&xtime_lock);
-
- do_timer(1);
-
- write_sequnlock(&xtime_lock);
+ xtime_update(1);
update_process_times(user_mode(get_irq_regs()));
*(__param)
__stop___param = .;
+ /* Built-in module versions */
+ . = ALIGN(4) ;
+ __start___modver = .;
+ *(__modver)
+ __stop___modver = .;
+
. = ALIGN(4) ;
_etext = . ;
} > TEXT
lib-y := ashldi3.o ashrdi3.o lshrdi3.o \
muldi3.o mulsi3.o divsi3.o udivsi3.o modsi3.o umodsi3.o \
- checksum.o memcpy.o memset.o delay.o
+ checksum.o memcpy.o memmove.o memset.o delay.o
--- /dev/null
+/*
+ * 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.
+ */
+
+#define __IN_STRING_C
+
+#include <linux/module.h>
+#include <linux/string.h>
+
+void *memmove(void *dest, const void *src, size_t n)
+{
+ void *xdest = dest;
+ size_t temp;
+
+ if (!n)
+ return xdest;
+
+ if (dest < src) {
+ if ((long)dest & 1) {
+ char *cdest = dest;
+ const char *csrc = src;
+ *cdest++ = *csrc++;
+ dest = cdest;
+ src = csrc;
+ n--;
+ }
+ if (n > 2 && (long)dest & 2) {
+ short *sdest = dest;
+ const short *ssrc = src;
+ *sdest++ = *ssrc++;
+ dest = sdest;
+ src = ssrc;
+ n -= 2;
+ }
+ temp = n >> 2;
+ if (temp) {
+ long *ldest = dest;
+ const long *lsrc = src;
+ temp--;
+ do
+ *ldest++ = *lsrc++;
+ while (temp--);
+ dest = ldest;
+ src = lsrc;
+ }
+ if (n & 2) {
+ short *sdest = dest;
+ const short *ssrc = src;
+ *sdest++ = *ssrc++;
+ dest = sdest;
+ src = ssrc;
+ }
+ if (n & 1) {
+ char *cdest = dest;
+ const char *csrc = src;
+ *cdest = *csrc;
+ }
+ } else {
+ dest = (char *)dest + n;
+ src = (const char *)src + n;
+ if ((long)dest & 1) {
+ char *cdest = dest;
+ const char *csrc = src;
+ *--cdest = *--csrc;
+ dest = cdest;
+ src = csrc;
+ n--;
+ }
+ if (n > 2 && (long)dest & 2) {
+ short *sdest = dest;
+ const short *ssrc = src;
+ *--sdest = *--ssrc;
+ dest = sdest;
+ src = ssrc;
+ n -= 2;
+ }
+ temp = n >> 2;
+ if (temp) {
+ long *ldest = dest;
+ const long *lsrc = src;
+ temp--;
+ do
+ *--ldest = *--lsrc;
+ while (temp--);
+ dest = ldest;
+ src = lsrc;
+ }
+ if (n & 2) {
+ short *sdest = dest;
+ const short *ssrc = src;
+ *--sdest = *--ssrc;
+ dest = sdest;
+ src = ssrc;
+ }
+ if (n & 1) {
+ char *cdest = dest;
+ const char *csrc = src;
+ *--cdest = *--csrc;
+ }
+ }
+ return xdest;
+}
+EXPORT_SYMBOL(memmove);
int irq;
/* GPIO interrupt sources */
- for (irq = MCFINTC2_GPIOIRQ0; (irq <= MCFINTC2_GPIOIRQ7); irq++)
+ for (irq = MCFINTC2_GPIOIRQ0; (irq <= MCFINTC2_GPIOIRQ7); irq++) {
irq_desc[irq].chip = &intc2_irq_gpio_chip;
+ set_irq_handler(irq, handle_edge_irq);
+ }
return 0;
}
movel %d1,%a2
1:
move %a2@(TI_FLAGS),%d1 /* thread_info->flags */
- andl #_TIF_WORK_MASK,%d1
jne Lwork_to_do
RESTORE_ALL
cpm_install_handler(int vec, void (*handler)(), void *dev_id)
{
- request_irq(vec, handler, IRQ_FLG_LOCK, "timer", dev_id);
+ request_irq(vec, handler, 0, "timer", dev_id);
/* if (cpm_vecs[vec].handler != 0) */
/* printk(KERN_INFO "CPM interrupt %x replacing %x\n", */
/* Set compare register 32Khz / 32 / 10 = 100 */
TCMP = 10;
- request_irq(IRQ_MACHSPEC | 1, timer_routine, IRQ_FLG_LOCK, "timer", NULL);
+ request_irq(IRQ_MACHSPEC | 1, timer_routine, 0, "timer", NULL);
#endif
/* General purpose quicc timers: MC68360UM p7-20 */
movel %d1,%a2
1:
move %a2@(TI_FLAGS),%d1 /* thread_info->flags */
- andl #_TIF_WORK_MASK,%d1
jne Lwork_to_do
RESTORE_ALL
pquicc->intr_cimr = 0x00000000;
for (i = 0; (i < NR_IRQS); i++) {
- set_irq_chip(irq, &intc_irq_chip);
- set_irq_handler(irq, handle_level_irq);
+ set_irq_chip(i, &intc_irq_chip);
+ set_irq_handler(i, handle_level_irq);
}
}
andl #-THREAD_SIZE,%d1 /* at base of kernel stack */
movel %d1,%a0
movel %a0@(TI_FLAGS),%d1 /* get thread_info->flags */
- andl #0xefff,%d1
jne Lwork_to_do /* still work to do */
Lreturn:
})
static inline int
-futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- int prev, cmp;
+ int ret = 0, cmp;
+ u32 prev;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- __asm__ __volatile__ ("1: lwx %0, %2, r0; \
- cmp %1, %0, %3; \
- beqi %1, 3f; \
- 2: swx %4, %2, r0; \
- addic %1, r0, 0; \
- bnei %1, 1b; \
+ __asm__ __volatile__ ("1: lwx %1, %3, r0; \
+ cmp %2, %1, %4; \
+ beqi %2, 3f; \
+ 2: swx %5, %3, r0; \
+ addic %2, r0, 0; \
+ bnei %2, 1b; \
3: \
.section .fixup,\"ax\"; \
4: brid 3b; \
- addik %0, r0, %5; \
+ addik %0, r0, %6; \
.previous; \
.section __ex_table,\"a\"; \
.word 1b,4b,2b,4b; \
.previous;" \
- : "=&r" (prev), "=&r"(cmp) \
+ : "+r" (ret), "=&r" (prev), "=&r"(cmp) \
: "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT));
- return prev;
+ *uval = prev;
+ return ret;
}
#endif /* __KERNEL__ */
#include <linux/types.h>
#include <asm/registers.h>
-#ifdef CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR
+#if CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR
static inline unsigned long arch_local_irq_save(void)
{
static inline unsigned long pte_update(pte_t *p, unsigned long clr,
unsigned long set)
{
- unsigned long old, tmp, msr;
-
- __asm__ __volatile__("\
- msrclr %2, 0x2\n\
- nop\n\
- lw %0, %4, r0\n\
- andn %1, %0, %5\n\
- or %1, %1, %6\n\
- sw %1, %4, r0\n\
- mts rmsr, %2\n\
- nop"
- : "=&r" (old), "=&r" (tmp), "=&r" (msr), "=m" (*p)
- : "r" ((unsigned long)(p + 1) - 4), "r" (clr), "r" (set), "m" (*p)
- : "cc");
+ unsigned long flags, old, tmp;
+
+ raw_local_irq_save(flags);
+
+ __asm__ __volatile__( "lw %0, %2, r0 \n"
+ "andn %1, %0, %3 \n"
+ "or %1, %1, %4 \n"
+ "sw %1, %2, r0 \n"
+ : "=&r" (old), "=&r" (tmp)
+ : "r" ((unsigned long)(p + 1) - 4), "r" (clr), "r" (set)
+ : "cc");
+
+ raw_local_irq_restore(flags);
return old;
}
register unsigned tmp __asm__("r3"); \
tmp = 0x0; /* Prevent warning about unused */ \
__asm__ __volatile__ ( \
- "mfs %0, rpvr" #pvrid ";" \
+ "mfs %0, rpvr" #pvrid ";" \
: "=r" (tmp) : : "memory"); \
val = tmp; \
}
if (!(flags & PVR_MSR_BIT))
return 0;
- get_single_pvr(0x00, pvr0);
+ get_single_pvr(0, pvr0);
pr_debug("%s: pvr0 is 0x%08x\n", __func__, pvr0);
if (pvr0 & PVR0_PVR_FULL_MASK)
andi r1, r1, ~2
mts rmsr, r1
/*
- * Here is checking mechanism which check if Microblaze has msr instructions
- * We load msr and compare it with previous r1 value - if is the same,
- * msr instructions works if not - cpu don't have them.
+ * According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc'
+ * if the msrclr instruction is not enabled. We use this to detect
+ * if the opcode is available, by issuing msrclr and then testing the result.
+ * r8 == 0 - msr instructions are implemented
+ * r8 != 0 - msr instructions are not implemented
*/
- /* r8=0 - I have msr instr, 1 - I don't have them */
- rsubi r0, r0, 1 /* set the carry bit */
- msrclr r0, 0x4 /* try to clear it */
- /* read the carry bit, r8 will be '0' if msrclr exists */
- addik r8, r0, 0
+ msrclr r8, 0 /* clear nothing - just read msr for test */
+ cmpu r8, r8, r1 /* r1 must contain msr reg content */
/* r7 may point to an FDT, or there may be one linked in.
if it's in r7, we've got to save it away ASAP.
#if CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR
if (msr)
eprintk("!!!Your kernel has setup MSR instruction but "
- "CPU don't have it %d\n", msr);
+ "CPU don't have it %x\n", msr);
#else
if (!msr)
eprintk("!!!Your kernel not setup MSR instruction but "
- "CPU have it %d\n", msr);
+ "CPU have it %x\n", msr);
#endif
for (src = __ivt_start; src < __ivt_end; src++, dst++)
select HAVE_GENERIC_DMA_COHERENT
select HAVE_IDE
select HAVE_OPROFILE
+ select HAVE_IRQ_WORK
select HAVE_PERF_EVENTS
select PERF_USE_VMALLOC
select HAVE_ARCH_KGDB
select ARCH_REQUIRE_GPIOLIB
select SYS_HAS_EARLY_PRINTK
select HAVE_PWM
+ select HAVE_CLK
config LASAT
bool "LASAT Networks platforms"
config PMC_MSP
bool "PMC-Sierra MSP chipsets"
depends on EXPERIMENTAL
+ select CEVT_R4K
+ select CSRC_R4K
select DMA_NONCOHERENT
select SWAP_IO_SPACE
select NO_EXCEPT_FILL
static void mtx1_reset(char *c)
{
- /* Hit BCSR.SYSTEM_CONTROL[SW_RST] */
- au_writel(0x00000000, 0xAE00001C);
+ /* Jump to the reset vector */
+ __asm__ __volatile__("jr\t%0"::"r"(0xbfc00000));
}
static void mtx1_power_off(void)
#include <linux/mtd/physmap.h>
#include <mtd/mtd-abi.h>
+#include <asm/mach-au1x00/au1xxx_eth.h>
+
static struct gpio_keys_button mtx1_gpio_button[] = {
{
.gpio = 207,
&mtx1_mtd,
};
+static struct au1000_eth_platform_data mtx1_au1000_eth0_pdata = {
+ .phy_search_highest_addr = 1,
+ .phy1_search_mac0 = 1,
+};
+
static int __init mtx1_register_devices(void)
{
int rc;
+ au1xxx_override_eth_cfg(0, &mtx1_au1000_eth0_pdata);
+
rc = gpio_request(mtx1_gpio_button[0].gpio,
mtx1_gpio_button[0].desc);
if (rc < 0) {
static void xxs1500_reset(char *c)
{
- /* Hit BCSR.SYSTEM_CONTROL[SW_RST] */
- au_writel(0x00000000, 0xAE00001C);
+ /* Jump to the reset vector */
+ __asm__ __volatile__("jr\t%0"::"r"(0xbfc00000));
}
static void xxs1500_power_off(void)
}
static inline int
-futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+ if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- int retval;
+ int ret = 0;
+ u32 val;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
if (cpu_has_llsc && R10000_LLSC_WAR) {
" .set push \n"
" .set noat \n"
" .set mips3 \n"
- "1: ll %0, %2 \n"
- " bne %0, %z3, 3f \n"
+ "1: ll %1, %3 \n"
+ " bne %1, %z4, 3f \n"
" .set mips0 \n"
- " move $1, %z4 \n"
+ " move $1, %z5 \n"
" .set mips3 \n"
- "2: sc $1, %1 \n"
+ "2: sc $1, %2 \n"
" beqzl $1, 1b \n"
__WEAK_LLSC_MB
"3: \n"
" .set pop \n"
" .section .fixup,\"ax\" \n"
- "4: li %0, %5 \n"
+ "4: li %0, %6 \n"
" j 3b \n"
" .previous \n"
" .section __ex_table,\"a\" \n"
" "__UA_ADDR "\t1b, 4b \n"
" "__UA_ADDR "\t2b, 4b \n"
" .previous \n"
- : "=&r" (retval), "=R" (*uaddr)
+ : "+r" (ret), "=&r" (val), "=R" (*uaddr)
: "R" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT)
: "memory");
} else if (cpu_has_llsc) {
" .set push \n"
" .set noat \n"
" .set mips3 \n"
- "1: ll %0, %2 \n"
- " bne %0, %z3, 3f \n"
+ "1: ll %1, %3 \n"
+ " bne %1, %z4, 3f \n"
" .set mips0 \n"
- " move $1, %z4 \n"
+ " move $1, %z5 \n"
" .set mips3 \n"
- "2: sc $1, %1 \n"
+ "2: sc $1, %2 \n"
" beqz $1, 1b \n"
__WEAK_LLSC_MB
"3: \n"
" .set pop \n"
" .section .fixup,\"ax\" \n"
- "4: li %0, %5 \n"
+ "4: li %0, %6 \n"
" j 3b \n"
" .previous \n"
" .section __ex_table,\"a\" \n"
" "__UA_ADDR "\t1b, 4b \n"
" "__UA_ADDR "\t2b, 4b \n"
" .previous \n"
- : "=&r" (retval), "=R" (*uaddr)
+ : "+r" (ret), "=&r" (val), "=R" (*uaddr)
: "R" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT)
: "memory");
} else
return -ENOSYS;
- return retval;
+ *uval = val;
+ return ret;
}
#endif
#ifndef __MIPS_PERF_EVENT_H__
#define __MIPS_PERF_EVENT_H__
-
-/*
- * MIPS performance counters do not raise NMI upon overflow, a regular
- * interrupt will be signaled. Hence we can do the pending perf event
- * work at the tail of the irq handler.
- */
-static inline void
-set_perf_event_pending(void)
-{
-}
-
+/* Leave it empty here. The file is required by linux/perf_event.h */
#endif /* __MIPS_PERF_EVENT_H__ */
#include <asm/cacheflush.h>
#include <asm/uasm.h>
-/*
- * If the Instruction Pointer is in module space (0xc0000000), return true;
- * otherwise, it is in kernel space (0x80000000), return false.
- *
- * FIXME: This will not work when the kernel space and module space are the
- * same. If they are the same, we need to modify scripts/recordmcount.pl,
- * ftrace_make_nop/call() and the other related parts to ensure the
- * enabling/disabling of the calling site to _mcount is right for both kernel
- * and module.
- */
-
-static inline int in_module(unsigned long ip)
-{
- return ip & 0x40000000;
-}
+#include <asm-generic/sections.h>
#ifdef CONFIG_DYNAMIC_FTRACE
#define JAL 0x0c000000 /* jump & link: ip --> ra, jump to target */
#define ADDR_MASK 0x03ffffff /* op_code|addr : 31...26|25 ....0 */
-#define INSN_B_1F_4 0x10000004 /* b 1f; offset = 4 */
-#define INSN_B_1F_5 0x10000005 /* b 1f; offset = 5 */
#define INSN_NOP 0x00000000 /* nop */
#define INSN_JAL(addr) \
((unsigned int)(JAL | (((addr) >> 2) & ADDR_MASK)))
#endif
}
+/*
+ * Check if the address is in kernel space
+ *
+ * Clone core_kernel_text() from kernel/extable.c, but doesn't call
+ * init_kernel_text() for Ftrace doesn't trace functions in init sections.
+ */
+static inline int in_kernel_space(unsigned long ip)
+{
+ if (ip >= (unsigned long)_stext &&
+ ip <= (unsigned long)_etext)
+ return 1;
+ return 0;
+}
+
static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
{
int faulted;
return 0;
}
+/*
+ * The details about the calling site of mcount on MIPS
+ *
+ * 1. For kernel:
+ *
+ * move at, ra
+ * jal _mcount --> nop
+ *
+ * 2. For modules:
+ *
+ * 2.1 For KBUILD_MCOUNT_RA_ADDRESS and CONFIG_32BIT
+ *
+ * lui v1, hi_16bit_of_mcount --> b 1f (0x10000005)
+ * addiu v1, v1, low_16bit_of_mcount
+ * move at, ra
+ * move $12, ra_address
+ * jalr v1
+ * sub sp, sp, 8
+ * 1: offset = 5 instructions
+ * 2.2 For the Other situations
+ *
+ * lui v1, hi_16bit_of_mcount --> b 1f (0x10000004)
+ * addiu v1, v1, low_16bit_of_mcount
+ * move at, ra
+ * jalr v1
+ * nop | move $12, ra_address | sub sp, sp, 8
+ * 1: offset = 4 instructions
+ */
+
+#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT)
+#define MCOUNT_OFFSET_INSNS 5
+#else
+#define MCOUNT_OFFSET_INSNS 4
+#endif
+#define INSN_B_1F (0x10000000 | MCOUNT_OFFSET_INSNS)
+
int ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long ip = rec->ip;
/*
- * We have compiled module with -mlong-calls, but compiled the kernel
- * without it, we need to cope with them respectively.
+ * If ip is in kernel space, no long call, otherwise, long call is
+ * needed.
*/
- if (in_module(ip)) {
-#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT)
- /*
- * lui v1, hi_16bit_of_mcount --> b 1f (0x10000005)
- * addiu v1, v1, low_16bit_of_mcount
- * move at, ra
- * move $12, ra_address
- * jalr v1
- * sub sp, sp, 8
- * 1: offset = 5 instructions
- */
- new = INSN_B_1F_5;
-#else
- /*
- * lui v1, hi_16bit_of_mcount --> b 1f (0x10000004)
- * addiu v1, v1, low_16bit_of_mcount
- * move at, ra
- * jalr v1
- * nop | move $12, ra_address | sub sp, sp, 8
- * 1: offset = 4 instructions
- */
- new = INSN_B_1F_4;
-#endif
- } else {
- /*
- * move at, ra
- * jal _mcount --> nop
- */
- new = INSN_NOP;
- }
+ new = in_kernel_space(ip) ? INSN_NOP : INSN_B_1F;
+
return ftrace_modify_code(ip, new);
}
unsigned int new;
unsigned long ip = rec->ip;
- /* ip, module: 0xc0000000, kernel: 0x80000000 */
- new = in_module(ip) ? insn_lui_v1_hi16_mcount : insn_jal_ftrace_caller;
+ new = in_kernel_space(ip) ? insn_jal_ftrace_caller :
+ insn_lui_v1_hi16_mcount;
return ftrace_modify_code(ip, new);
}
#define S_R_SP (0xafb0 << 16) /* s{d,w} R, offset(sp) */
#define OFFSET_MASK 0xffff /* stack offset range: 0 ~ PT_SIZE */
-unsigned long ftrace_get_parent_addr(unsigned long self_addr,
- unsigned long parent,
- unsigned long parent_addr,
- unsigned long fp)
+unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long
+ old_parent_ra, unsigned long parent_ra_addr, unsigned long fp)
{
- unsigned long sp, ip, ra;
+ unsigned long sp, ip, tmp;
unsigned int code;
int faulted;
/*
- * For module, move the ip from calling site of mcount to the
- * instruction "lui v1, hi_16bit_of_mcount"(offset is 20), but for
- * kernel, move to the instruction "move ra, at"(offset is 12)
+ * For module, move the ip from the return address after the
+ * instruction "lui v1, hi_16bit_of_mcount"(offset is 24), but for
+ * kernel, move after the instruction "move ra, at"(offset is 16)
*/
- ip = self_addr - (in_module(self_addr) ? 20 : 12);
+ ip = self_ra - (in_kernel_space(self_ra) ? 16 : 24);
/*
* search the text until finding the non-store instruction or "s{d,w}
* ra, offset(sp)" instruction
*/
do {
- ip -= 4;
-
/* get the code at "ip": code = *(unsigned int *)ip; */
safe_load_code(code, ip, faulted);
* store the ra on the stack
*/
if ((code & S_R_SP) != S_R_SP)
- return parent_addr;
+ return parent_ra_addr;
- } while (((code & S_RA_SP) != S_RA_SP));
+ /* Move to the next instruction */
+ ip -= 4;
+ } while ((code & S_RA_SP) != S_RA_SP);
sp = fp + (code & OFFSET_MASK);
- /* ra = *(unsigned long *)sp; */
- safe_load_stack(ra, sp, faulted);
+ /* tmp = *(unsigned long *)sp; */
+ safe_load_stack(tmp, sp, faulted);
if (unlikely(faulted))
return 0;
- if (ra == parent)
+ if (tmp == old_parent_ra)
return sp;
return 0;
}
* Hook the return address and push it in the stack of return addrs
* in current thread info.
*/
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra,
unsigned long fp)
{
- unsigned long old;
+ unsigned long old_parent_ra;
struct ftrace_graph_ent trace;
unsigned long return_hooker = (unsigned long)
&return_to_handler;
- int faulted;
+ int faulted, insns;
if (unlikely(atomic_read(¤t->tracing_graph_pause)))
return;
/*
- * "parent" is the stack address saved the return address of the caller
- * of _mcount.
+ * "parent_ra_addr" is the stack address saved the return address of
+ * the caller of _mcount.
*
* if the gcc < 4.5, a leaf function does not save the return address
* in the stack address, so, we "emulate" one in _mcount's stack space,
* do it in ftrace_graph_caller of mcount.S.
*/
- /* old = *parent; */
- safe_load_stack(old, parent, faulted);
+ /* old_parent_ra = *parent_ra_addr; */
+ safe_load_stack(old_parent_ra, parent_ra_addr, faulted);
if (unlikely(faulted))
goto out;
#ifndef KBUILD_MCOUNT_RA_ADDRESS
- parent = (unsigned long *)ftrace_get_parent_addr(self_addr, old,
- (unsigned long)parent, fp);
+ parent_ra_addr = (unsigned long *)ftrace_get_parent_ra_addr(self_ra,
+ old_parent_ra, (unsigned long)parent_ra_addr, fp);
/*
* If fails when getting the stack address of the non-leaf function's
* ra, stop function graph tracer and return
*/
- if (parent == 0)
+ if (parent_ra_addr == 0)
goto out;
#endif
- /* *parent = return_hooker; */
- safe_store_stack(return_hooker, parent, faulted);
+ /* *parent_ra_addr = return_hooker; */
+ safe_store_stack(return_hooker, parent_ra_addr, faulted);
if (unlikely(faulted))
goto out;
- if (ftrace_push_return_trace(old, self_addr, &trace.depth, fp) ==
- -EBUSY) {
- *parent = old;
+ if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp)
+ == -EBUSY) {
+ *parent_ra_addr = old_parent_ra;
return;
}
- trace.func = self_addr;
+ /*
+ * Get the recorded ip of the current mcount calling site in the
+ * __mcount_loc section, which will be used to filter the function
+ * entries configured through the tracing/set_graph_function interface.
+ */
+
+ insns = in_kernel_space(self_ra) ? 2 : MCOUNT_OFFSET_INSNS + 1;
+ trace.func = self_ra - (MCOUNT_INSN_SIZE * insns);
/* Only trace if the calling function expects to */
if (!ftrace_graph_entry(&trace)) {
current->curr_ret_stack--;
- *parent = old;
+ *parent_ra_addr = old_parent_ra;
}
return;
out:
return ret;
}
-static int mipspmu_enable(struct perf_event *event)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct hw_perf_event *hwc = &event->hw;
- int idx;
- int err = 0;
-
- /* To look for a free counter for this event. */
- idx = mipspmu->alloc_counter(cpuc, hwc);
- if (idx < 0) {
- err = idx;
- goto out;
- }
-
- /*
- * If there is an event in the counter we are going to use then
- * make sure it is disabled.
- */
- event->hw.idx = idx;
- mipspmu->disable_event(idx);
- cpuc->events[idx] = event;
-
- /* Set the period for the event. */
- mipspmu_event_set_period(event, hwc, idx);
-
- /* Enable the event. */
- mipspmu->enable_event(hwc, idx);
-
- /* Propagate our changes to the userspace mapping. */
- perf_event_update_userpage(event);
-
-out:
- return err;
-}
-
static void mipspmu_event_update(struct perf_event *event,
struct hw_perf_event *hwc,
int idx)
unsigned long flags;
int shift = 64 - TOTAL_BITS;
s64 prev_raw_count, new_raw_count;
- s64 delta;
+ u64 delta;
again:
prev_raw_count = local64_read(&hwc->prev_count);
return;
}
-static void mipspmu_disable(struct perf_event *event)
+static void mipspmu_start(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!mipspmu)
+ return;
+
+ if (flags & PERF_EF_RELOAD)
+ WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+ hwc->state = 0;
+
+ /* Set the period for the event. */
+ mipspmu_event_set_period(event, hwc, hwc->idx);
+
+ /* Enable the event. */
+ mipspmu->enable_event(hwc, hwc->idx);
+}
+
+static void mipspmu_stop(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!mipspmu)
+ return;
+
+ if (!(hwc->state & PERF_HES_STOPPED)) {
+ /* We are working on a local event. */
+ mipspmu->disable_event(hwc->idx);
+ barrier();
+ mipspmu_event_update(event, hwc, hwc->idx);
+ hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+ }
+}
+
+static int mipspmu_add(struct perf_event *event, int flags)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx;
+ int idx;
+ int err = 0;
+ perf_pmu_disable(event->pmu);
- WARN_ON(idx < 0 || idx >= mipspmu->num_counters);
+ /* To look for a free counter for this event. */
+ idx = mipspmu->alloc_counter(cpuc, hwc);
+ if (idx < 0) {
+ err = idx;
+ goto out;
+ }
- /* We are working on a local event. */
+ /*
+ * If there is an event in the counter we are going to use then
+ * make sure it is disabled.
+ */
+ event->hw.idx = idx;
mipspmu->disable_event(idx);
+ cpuc->events[idx] = event;
- barrier();
-
- mipspmu_event_update(event, hwc, idx);
- cpuc->events[idx] = NULL;
- clear_bit(idx, cpuc->used_mask);
+ hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+ if (flags & PERF_EF_START)
+ mipspmu_start(event, PERF_EF_RELOAD);
+ /* Propagate our changes to the userspace mapping. */
perf_event_update_userpage(event);
+
+out:
+ perf_pmu_enable(event->pmu);
+ return err;
}
-static void mipspmu_unthrottle(struct perf_event *event)
+static void mipspmu_del(struct perf_event *event, int flags)
{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
- mipspmu->enable_event(hwc, hwc->idx);
+ WARN_ON(idx < 0 || idx >= mipspmu->num_counters);
+
+ mipspmu_stop(event, PERF_EF_UPDATE);
+ cpuc->events[idx] = NULL;
+ clear_bit(idx, cpuc->used_mask);
+
+ perf_event_update_userpage(event);
}
static void mipspmu_read(struct perf_event *event)
mipspmu_event_update(event, hwc, hwc->idx);
}
-static struct pmu pmu = {
- .enable = mipspmu_enable,
- .disable = mipspmu_disable,
- .unthrottle = mipspmu_unthrottle,
- .read = mipspmu_read,
-};
+static void mipspmu_enable(struct pmu *pmu)
+{
+ if (mipspmu)
+ mipspmu->start();
+}
+
+static void mipspmu_disable(struct pmu *pmu)
+{
+ if (mipspmu)
+ mipspmu->stop();
+}
static atomic_t active_events = ATOMIC_INIT(0);
static DEFINE_MUTEX(pmu_reserve_mutex);
perf_irq = save_perf_irq;
}
+/*
+ * mipsxx/rm9000/loongson2 have different performance counters, they have
+ * specific low-level init routines.
+ */
+static void reset_counters(void *arg);
+static int __hw_perf_event_init(struct perf_event *event);
+
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+ if (atomic_dec_and_mutex_lock(&active_events,
+ &pmu_reserve_mutex)) {
+ /*
+ * We must not call the destroy function with interrupts
+ * disabled.
+ */
+ on_each_cpu(reset_counters,
+ (void *)(long)mipspmu->num_counters, 1);
+ mipspmu_free_irq();
+ mutex_unlock(&pmu_reserve_mutex);
+ }
+}
+
+static int mipspmu_event_init(struct perf_event *event)
+{
+ int err = 0;
+
+ switch (event->attr.type) {
+ case PERF_TYPE_RAW:
+ case PERF_TYPE_HARDWARE:
+ case PERF_TYPE_HW_CACHE:
+ break;
+
+ default:
+ return -ENOENT;
+ }
+
+ if (!mipspmu || event->cpu >= nr_cpumask_bits ||
+ (event->cpu >= 0 && !cpu_online(event->cpu)))
+ return -ENODEV;
+
+ if (!atomic_inc_not_zero(&active_events)) {
+ if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
+ atomic_dec(&active_events);
+ return -ENOSPC;
+ }
+
+ mutex_lock(&pmu_reserve_mutex);
+ if (atomic_read(&active_events) == 0)
+ err = mipspmu_get_irq();
+
+ if (!err)
+ atomic_inc(&active_events);
+ mutex_unlock(&pmu_reserve_mutex);
+ }
+
+ if (err)
+ return err;
+
+ err = __hw_perf_event_init(event);
+ if (err)
+ hw_perf_event_destroy(event);
+
+ return err;
+}
+
+static struct pmu pmu = {
+ .pmu_enable = mipspmu_enable,
+ .pmu_disable = mipspmu_disable,
+ .event_init = mipspmu_event_init,
+ .add = mipspmu_add,
+ .del = mipspmu_del,
+ .start = mipspmu_start,
+ .stop = mipspmu_stop,
+ .read = mipspmu_read,
+};
+
static inline unsigned int
mipspmu_perf_event_encode(const struct mips_perf_event *pev)
{
{
struct hw_perf_event fake_hwc = event->hw;
- if (event->pmu && event->pmu != &pmu)
- return 0;
+ /* Allow mixed event group. So return 1 to pass validation. */
+ if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
+ return 1;
return mipspmu->alloc_counter(cpuc, &fake_hwc) >= 0;
}
return 0;
}
-/*
- * mipsxx/rm9000/loongson2 have different performance counters, they have
- * specific low-level init routines.
- */
-static void reset_counters(void *arg);
-static int __hw_perf_event_init(struct perf_event *event);
-
-static void hw_perf_event_destroy(struct perf_event *event)
-{
- if (atomic_dec_and_mutex_lock(&active_events,
- &pmu_reserve_mutex)) {
- /*
- * We must not call the destroy function with interrupts
- * disabled.
- */
- on_each_cpu(reset_counters,
- (void *)(long)mipspmu->num_counters, 1);
- mipspmu_free_irq();
- mutex_unlock(&pmu_reserve_mutex);
- }
-}
-
-const struct pmu *hw_perf_event_init(struct perf_event *event)
-{
- int err = 0;
-
- if (!mipspmu || event->cpu >= nr_cpumask_bits ||
- (event->cpu >= 0 && !cpu_online(event->cpu)))
- return ERR_PTR(-ENODEV);
-
- if (!atomic_inc_not_zero(&active_events)) {
- if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
- atomic_dec(&active_events);
- return ERR_PTR(-ENOSPC);
- }
-
- mutex_lock(&pmu_reserve_mutex);
- if (atomic_read(&active_events) == 0)
- err = mipspmu_get_irq();
-
- if (!err)
- atomic_inc(&active_events);
- mutex_unlock(&pmu_reserve_mutex);
- }
-
- if (err)
- return ERR_PTR(err);
-
- err = __hw_perf_event_init(event);
- if (err)
- hw_perf_event_destroy(event);
-
- return err ? ERR_PTR(err) : &pmu;
-}
-
-void hw_perf_enable(void)
-{
- if (mipspmu)
- mipspmu->start();
-}
-
-void hw_perf_disable(void)
-{
- if (mipspmu)
- mipspmu->stop();
-}
-
/* This is needed by specific irq handlers in perf_event_*.c */
static void
handle_associated_event(struct cpu_hw_events *cpuc,
#include "perf_event_mipsxx.c"
/* Callchain handling code. */
-static inline void
-callchain_store(struct perf_callchain_entry *entry,
- u64 ip)
-{
- if (entry->nr < PERF_MAX_STACK_DEPTH)
- entry->ip[entry->nr++] = ip;
-}
/*
* Leave userspace callchain empty for now. When we find a way to trace
* the user stack callchains, we add here.
*/
-static void
-perf_callchain_user(struct pt_regs *regs,
- struct perf_callchain_entry *entry)
+void perf_callchain_user(struct perf_callchain_entry *entry,
+ struct pt_regs *regs)
{
}
while (!kstack_end(sp)) {
addr = *sp++;
if (__kernel_text_address(addr)) {
- callchain_store(entry, addr);
+ perf_callchain_store(entry, addr);
if (entry->nr >= PERF_MAX_STACK_DEPTH)
break;
}
}
}
-static void
-perf_callchain_kernel(struct pt_regs *regs,
- struct perf_callchain_entry *entry)
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+ struct pt_regs *regs)
{
unsigned long sp = regs->regs[29];
#ifdef CONFIG_KALLSYMS
unsigned long ra = regs->regs[31];
unsigned long pc = regs->cp0_epc;
- callchain_store(entry, PERF_CONTEXT_KERNEL);
if (raw_show_trace || !__kernel_text_address(pc)) {
unsigned long stack_page =
(unsigned long)task_stack_page(current);
return;
}
do {
- callchain_store(entry, pc);
+ perf_callchain_store(entry, pc);
if (entry->nr >= PERF_MAX_STACK_DEPTH)
break;
pc = unwind_stack(current, &sp, pc, &ra);
} while (pc);
#else
- callchain_store(entry, PERF_CONTEXT_KERNEL);
save_raw_perf_callchain(entry, sp);
#endif
}
-
-static void
-perf_do_callchain(struct pt_regs *regs,
- struct perf_callchain_entry *entry)
-{
- int is_user;
-
- if (!regs)
- return;
-
- is_user = user_mode(regs);
-
- if (!current || !current->pid)
- return;
-
- if (is_user && current->state != TASK_RUNNING)
- return;
-
- if (!is_user) {
- perf_callchain_kernel(regs, entry);
- if (current->mm)
- regs = task_pt_regs(current);
- else
- regs = NULL;
- }
- if (regs)
- perf_callchain_user(regs, entry);
-}
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-
-struct perf_callchain_entry *
-perf_callchain(struct pt_regs *regs)
-{
- struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry);
-
- entry->nr = 0;
- perf_do_callchain(regs, entry);
- return entry;
-}
* interrupt, not NMI.
*/
if (handled == IRQ_HANDLED)
- perf_event_do_pending();
+ irq_work_run();
#ifdef CONFIG_MIPS_MT_SMP
read_unlock(&pmuint_rwlock);
"CPU, irq %d%s\n", mipspmu->name, counters, irq,
irq < 0 ? " (share with timer interrupt)" : "");
+ perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+
return 0;
}
early_initcall(init_hw_perf_events);
static int protected_restore_fp_context(struct sigcontext __user *sc)
{
- int err, tmp;
+ int err, tmp __maybe_unused;
while (1) {
lock_fpu_owner();
own_fpu_inatomic(0);
static int protected_restore_fp_context32(struct sigcontext32 __user *sc)
{
- int err, tmp;
+ int err, tmp __maybe_unused;
while (1) {
lock_fpu_owner();
own_fpu_inatomic(0);
*/
static struct task_struct *cpu_idle_thread[NR_CPUS];
+struct create_idle {
+ struct work_struct work;
+ struct task_struct *idle;
+ struct completion done;
+ int cpu;
+};
+
+static void __cpuinit do_fork_idle(struct work_struct *work)
+{
+ struct create_idle *c_idle =
+ container_of(work, struct create_idle, work);
+
+ c_idle->idle = fork_idle(c_idle->cpu);
+ complete(&c_idle->done);
+}
+
int __cpuinit __cpu_up(unsigned int cpu)
{
struct task_struct *idle;
* Linux can schedule processes on this slave.
*/
if (!cpu_idle_thread[cpu]) {
- idle = fork_idle(cpu);
- cpu_idle_thread[cpu] = idle;
+ /*
+ * Schedule work item to avoid forking user task
+ * Ported from arch/x86/kernel/smpboot.c
+ */
+ struct create_idle c_idle = {
+ .cpu = cpu,
+ .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
+ };
+
+ INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
+ schedule_work(&c_idle.work);
+ wait_for_completion(&c_idle.done);
+ idle = cpu_idle_thread[cpu] = c_idle.idle;
if (IS_ERR(idle))
panic(KERN_ERR "Fork failed for CPU %d", cpu);
static int __used noinline
_sys_sysmips(nabi_no_regargs struct pt_regs regs)
{
- long cmd, arg1, arg2, arg3;
+ long cmd, arg1, arg2;
cmd = regs.regs[4];
arg1 = regs.regs[5];
arg2 = regs.regs[6];
- arg3 = regs.regs[7];
switch (cmd) {
case MIPS_ATOMIC_SET:
if (arg1 & 2)
set_thread_flag(TIF_LOGADE);
else
- clear_thread_flag(TIF_FIXADE);
+ clear_thread_flag(TIF_LOGADE);
return 0;
spinlock_t tc_list_lock;
struct list_head tc_list; /* Thread contexts */
} vpecontrol = {
- .vpe_list_lock = SPIN_LOCK_UNLOCKED,
+ .vpe_list_lock = __SPIN_LOCK_UNLOCKED(vpe_list_lock),
.vpe_list = LIST_HEAD_INIT(vpecontrol.vpe_list),
- .tc_list_lock = SPIN_LOCK_UNLOCKED,
+ .tc_list_lock = __SPIN_LOCK_UNLOCKED(tc_list_lock),
.tc_list = LIST_HEAD_INIT(vpecontrol.tc_list)
};
+if MACH_LOONGSON
+
choice
prompt "Machine Type"
- depends on MACH_LOONGSON
config LEMOTE_FULOONG2E
bool "Lemote Fuloong(2e) mini-PC"
config LOONGSON_MC146818
bool
default n
+
+endif # MACH_LOONGSON
strcat(arcs_cmdline, " ");
}
- if ((strstr(arcs_cmdline, "console=")) == NULL)
- strcat(arcs_cmdline, " console=ttyS0,115200");
- if ((strstr(arcs_cmdline, "root=")) == NULL)
- strcat(arcs_cmdline, " root=/dev/hda1");
-
prom_init_machtype();
}
void __init prom_init_machtype(void)
{
- char *p, str[MACHTYPE_LEN];
+ char *p, str[MACHTYPE_LEN + 1];
int machtype = MACH_LEMOTE_FL2E;
mips_machtype = LOONGSON_MACHTYPE;
}
p += strlen("machtype=");
strncpy(str, p, MACHTYPE_LEN);
+ str[MACHTYPE_LEN] = '\0';
p = strstr(str, " ");
if (p)
*p = '\0';
#define COMPXSP \
- unsigned xm; int xe; int xs; int xc
+ unsigned xm; int xe; int xs __maybe_unused; int xc
#define COMPYSP \
unsigned ym; int ye; int ys; int yc
#define COMPXDP \
-u64 xm; int xe; int xs; int xc
+u64 xm; int xe; int xs __maybe_unused; int xc
#define COMPYDP \
u64 ym; int ye; int ys; int yc
void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
- unsigned long lastpfn;
+ unsigned long lastpfn __maybe_unused;
pagetable_init();
static int scratchpad_offset(int i)
{
BUG();
+ /* Really unreachable, but evidently some GCC want this. */
+ return 0;
}
#endif
/*
* RETURNS: PCIBIOS_SUCCESSFUL - success
*
****************************************************************************/
-static int bpci_interrupt(int irq, void *dev_id)
+static irqreturn_t bpci_interrupt(int irq, void *dev_id)
{
struct msp_pci_regs *preg = (void *)PCI_BASE_REG;
unsigned int stat = preg->if_status;
/* write to clear all asserted interrupts */
preg->if_status = stat;
- return PCIBIOS_SUCCESSFUL;
+ return IRQ_HANDLED;
}
/*****************************************************************************
config PMC_MSP4200_EVAL
bool "PMC-Sierra MSP4200 Eval Board"
- select CEVT_R4K
- select CSRC_R4K
select IRQ_MSP_SLP
select HW_HAS_PCI
config PMC_MSP4200_GW
bool "PMC-Sierra MSP4200 VoIP Gateway"
- select CEVT_R4K
- select CSRC_R4K
select IRQ_MSP_SLP
select HW_HAS_PCI
mips_hpt_frequency = cpu_rate/2;
}
-unsigned int __init get_c0_compare_int(void)
+unsigned int __cpuinit get_c0_compare_int(void)
{
return MSP_INT_VPE0_TIMER;
}
* Atomically reads the value of @v. Note that the guaranteed
* useful range of an atomic_t is only 24 bits.
*/
-#define atomic_read(v) ((v)->counter)
+#define atomic_read(v) (ACCESS_ONCE((v)->counter))
/**
* atomic_set - set atomic variable
#define __get_user_check(x, ptr, size) \
({ \
+ const __typeof__(ptr) __guc_ptr = (ptr); \
int _e; \
- if (likely(__access_ok((unsigned long) (ptr), (size)))) \
- _e = __get_user_nocheck((x), (ptr), (size)); \
+ if (likely(__access_ok((unsigned long) __guc_ptr, (size)))) \
+ _e = __get_user_nocheck((x), __guc_ptr, (size)); \
else { \
_e = -EFAULT; \
(x) = (__typeof__(x))0; \
unsigned tsc, elapse;
irqreturn_t ret;
- write_seqlock(&xtime_lock);
-
while (tsc = get_cycles(),
elapse = tsc - mn10300_last_tsc, /* time elapsed since last
* tick */
mn10300_last_tsc += MN10300_TSC_PER_HZ;
/* advance the kernel's time tracking system */
- do_timer(1);
+ xtime_update(1);
}
- write_sequnlock(&xtime_lock);
-
ret = local_timer_interrupt();
#ifdef CONFIG_SMP
send_IPI_allbutself(LOCAL_TIMER_IPI);
/* invalidate the icache coverage on that region */
mn10300_local_icache_inv_range2(addr + off, size);
- smp_cache_call(SMP_ICACHE_INV_FLUSH_RANGE, start, end);
+ smp_cache_call(SMP_ICACHE_INV_RANGE, start, end);
}
/**
* directly */
start_page = (start >= 0x80000000UL) ? start : 0x80000000UL;
mn10300_icache_inv_range(start_page, end);
- smp_cache_call(SMP_ICACHE_INV_FLUSH_RANGE, start, end);
+ smp_cache_call(SMP_ICACHE_INV_RANGE, start, end);
if (start_page == start)
goto done;
end = start_page;
int16_t f_pad;
};
-static int do_statfs_hpux(struct path *path, struct hpux_statfs *buf)
+static int do_statfs_hpux(struct kstatfs *st, struct hpux_statfs __user *p)
{
- struct kstatfs st;
- int retval;
-
- retval = vfs_statfs(path, &st);
- if (retval)
- return retval;
-
- memset(buf, 0, sizeof(*buf));
- buf->f_type = st.f_type;
- buf->f_bsize = st.f_bsize;
- buf->f_blocks = st.f_blocks;
- buf->f_bfree = st.f_bfree;
- buf->f_bavail = st.f_bavail;
- buf->f_files = st.f_files;
- buf->f_ffree = st.f_ffree;
- buf->f_fsid[0] = st.f_fsid.val[0];
- buf->f_fsid[1] = st.f_fsid.val[1];
-
+ struct hpux_statfs buf;
+ memset(&buf, 0, sizeof(buf));
+ buf.f_type = st->f_type;
+ buf.f_bsize = st->f_bsize;
+ buf.f_blocks = st->f_blocks;
+ buf.f_bfree = st->f_bfree;
+ buf.f_bavail = st->f_bavail;
+ buf.f_files = st->f_files;
+ buf.f_ffree = st->f_ffree;
+ buf.f_fsid[0] = st->f_fsid.val[0];
+ buf.f_fsid[1] = st->f_fsid.val[1];
+ if (copy_to_user(p, &buf, sizeof(buf)))
+ return -EFAULT;
return 0;
}
asmlinkage long hpux_statfs(const char __user *pathname,
struct hpux_statfs __user *buf)
{
- struct path path;
- int error;
-
- error = user_path(pathname, &path);
- if (!error) {
- struct hpux_statfs tmp;
- error = do_statfs_hpux(&path, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- path_put(&path);
- }
+ struct kstatfs st;
+ int error = user_statfs(pathname, &st);
+ if (!error)
+ error = do_statfs_hpux(&st, buf);
return error;
}
asmlinkage long hpux_fstatfs(unsigned int fd, struct hpux_statfs __user * buf)
{
- struct file *file;
- struct hpux_statfs tmp;
- int error;
-
- error = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
- error = do_statfs_hpux(&file->f_path, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- fput(file);
- out:
+ struct kstatfs st;
+ int error = fd_statfs(fd, &st);
+ if (!error)
+ error = do_statfs_hpux(&st, buf);
return error;
}
#include <asm/errno.h>
static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+ if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
/* Non-atomic version */
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- int err = 0;
- int uval;
+ u32 val;
/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
* our gateway page, and causes no end of trouble...
if (segment_eq(KERNEL_DS, get_fs()) && !uaddr)
return -EFAULT;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- err = get_user(uval, uaddr);
- if (err) return -EFAULT;
- if (uval == oldval)
- err = put_user(newval, uaddr);
- if (err) return -EFAULT;
- return uval;
+ if (get_user(val, uaddr))
+ return -EFAULT;
+ if (val == oldval && put_user(newval, uaddr))
+ return -EFAULT;
+ *uval = val;
+ return 0;
}
#endif /*__KERNEL__*/
update_process_times(user_mode(get_irq_regs()));
}
- if (cpu == 0) {
- write_seqlock(&xtime_lock);
- do_timer(ticks_elapsed);
- write_sequnlock(&xtime_lock);
- }
+ if (cpu == 0)
+ xtime_update(ticks_elapsed);
return IRQ_HANDLED;
}
: "b" (uaddr), "i" (-EFAULT), "r" (oparg) \
: "cr0", "memory")
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+ if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- int prev;
+ int ret = 0;
+ u32 prev;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
__asm__ __volatile__ (
PPC_RELEASE_BARRIER
-"1: lwarx %0,0,%2 # futex_atomic_cmpxchg_inatomic\n\
- cmpw 0,%0,%3\n\
+"1: lwarx %1,0,%3 # futex_atomic_cmpxchg_inatomic\n\
+ cmpw 0,%1,%4\n\
bne- 3f\n"
- PPC405_ERR77(0,%2)
-"2: stwcx. %4,0,%2\n\
+ PPC405_ERR77(0,%3)
+"2: stwcx. %5,0,%3\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"3: .section .fixup,\"ax\"\n\
-4: li %0,%5\n\
+4: li %0,%6\n\
b 3b\n\
.previous\n\
.section __ex_table,\"a\"\n\
.align 3\n\
" PPC_LONG "1b,4b,2b,4b\n\
.previous" \
- : "=&r" (prev), "+m" (*uaddr)
+ : "+r" (ret), "=&r" (prev), "+m" (*uaddr)
: "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT)
: "cc", "memory");
- return prev;
+ *uval = prev;
+ return ret;
}
#endif /* __KERNEL__ */
//
//----------------------------------------------------------------------------
#include <linux/cache.h>
+#include <linux/threads.h>
#include <asm/types.h>
#include <asm/mmu.h>
+/*
+ * We only have to have statically allocated lppaca structs on
+ * legacy iSeries, which supports at most 64 cpus.
+ */
+#ifdef CONFIG_PPC_ISERIES
+#if NR_CPUS < 64
+#define NR_LPPACAS NR_CPUS
+#else
+#define NR_LPPACAS 64
+#endif
+#else /* not iSeries */
+#define NR_LPPACAS 1
+#endif
+
+
/* The Hypervisor barfs if the lppaca crosses a page boundary. A 1k
* alignment is sufficient to prevent this */
struct lppaca {
* claims to support kexec.
*/
int (*machine_kexec_prepare)(struct kimage *image);
+
+ /* Called to perform the _real_ kexec.
+ * Do NOT allocate memory or fail here. We are past the point of
+ * no return.
+ */
+ void (*machine_kexec)(struct kimage *image);
#endif /* CONFIG_KEXEC */
#ifdef CONFIG_SUSPEND
* by Paul Mackerras <paulus@samba.org>.
*/
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
/*
* the semaphore definition
*/
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-struct rw_semaphore {
- long count;
- spinlock_t wait_lock;
- struct list_head wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lockdep_map dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-{ \
- RWSEM_UNLOCKED_VALUE, \
- __SPIN_LOCK_UNLOCKED((name).wait_lock), \
- LIST_HEAD_INIT((name).wait_list) \
- __RWSEM_DEP_MAP_INIT(name) \
-}
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
- struct lock_class_key *key);
-
-#define init_rwsem(sem) \
- do { \
- static struct lock_class_key __key; \
- \
- __init_rwsem((sem), #sem, &__key); \
- } while (0)
-
/*
* lock for reading
*/
return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
}
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
- return sem->count != 0;
-}
-
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_RWSEM_H */
save_ftrace_enabled = __ftrace_enabled_save();
- default_machine_kexec(image);
+ if (ppc_md.machine_kexec)
+ ppc_md.machine_kexec(image);
+ else
+ default_machine_kexec(image);
__ftrace_enabled_restore(save_ftrace_enabled);
#ifdef CONFIG_PPC_BOOK3S
-/*
- * We only have to have statically allocated lppaca structs on
- * legacy iSeries, which supports at most 64 cpus.
- */
-#ifdef CONFIG_PPC_ISERIES
-#if NR_CPUS < 64
-#define NR_LPPACAS NR_CPUS
-#else
-#define NR_LPPACAS 64
-#endif
-#else /* not iSeries */
-#define NR_LPPACAS 1
-#endif
-
/*
* The structure which the hypervisor knows about - this structure
* should not cross a page boundary. The vpa_init/register_vpa call
prime_debug_regs(new_thread);
}
#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
+#ifndef CONFIG_HAVE_HW_BREAKPOINT
static void set_debug_reg_defaults(struct thread_struct *thread)
{
if (thread->dabr) {
set_dabr(0);
}
}
+#endif /* !CONFIG_HAVE_HW_BREAKPOINT */
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
int set_dabr(unsigned long dabr)
{
discard_lazy_cpu_state();
-#ifdef CONFIG_HAVE_HW_BREAKPOINTS
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
flush_ptrace_hw_breakpoint(current);
-#else /* CONFIG_HAVE_HW_BREAKPOINTS */
+#else /* CONFIG_HAVE_HW_BREAKPOINT */
set_debug_reg_defaults(¤t->thread);
-#endif /* CONFIG_HAVE_HW_BREAKPOINTS */
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
}
void
{
int rc = 0;
- if (firmware_has_feature(FW_FEATURE_VPHN) &&
+ /* Disabled until races with load balancing are fixed */
+ if (0 && firmware_has_feature(FW_FEATURE_VPHN) &&
get_lppaca()->shared_proc) {
vphn_enabled = 1;
setup_cpu_associativity_change_counters();
* neesd to be flushed. This function will either perform the flush
* immediately or will batch it up if the current CPU has an active
* batch on it.
- *
- * Must be called from within some kind of spinlock/non-preempt region...
*/
void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long pte, int huge)
{
- struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+ struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
unsigned long vsid, vaddr;
unsigned int psize;
int ssize;
*/
if (!batch->active) {
flush_hash_page(vaddr, rpte, psize, ssize, 0);
+ put_cpu_var(ppc64_tlb_batch);
return;
}
batch->index = ++i;
if (i >= PPC64_TLB_BATCH_NR)
__flush_tlb_pending(batch);
+ put_cpu_var(ppc64_tlb_batch);
}
/*
if (!IS_ERR(tmp)) {
struct nameidata nd;
- ret = path_lookup(tmp, LOOKUP_PARENT, &nd);
+ ret = kern_path_parent(tmp, &nd);
if (!ret) {
nd.flags |= LOOKUP_OPEN | LOOKUP_CREATE;
ret = spufs_create(&nd, flags, mode, neighbor);
pft_size[0] = 0; /* NUMA CEC cookie, 0 for non NUMA */
pft_size[1] = __ilog2(HvCallHpt_getHptPages() * HW_PAGE_SIZE);
- for (i = 0; i < NR_CPUS; i++) {
- if (lppaca_of(i).dyn_proc_status >= 2)
+ for (i = 0; i < NR_LPPACAS; i++) {
+ if (lppaca[i].dyn_proc_status >= 2)
continue;
snprintf(p, 32 - (p - buf), "@%d", i);
dt_prop_str(dt, "device_type", device_type_cpu);
- index = lppaca_of(i).dyn_hv_phys_proc_index;
+ index = lppaca[i].dyn_hv_phys_proc_index;
d = &xIoHriProcessorVpd[index];
dt_prop_u32(dt, "i-cache-size", d->xInstCacheSize * 1024);
* on but calling this function multiple times is fine.
*/
identify_cpu(0, mfspr(SPRN_PVR));
+ initialise_paca(&boot_paca, 0);
powerpc_firmware_features |= FW_FEATURE_ISERIES;
powerpc_firmware_features |= FW_FEATURE_LPAR;
unsigned long output_addr;
unsigned char *output;
- check_ipl_parmblock((void *) 0, (unsigned long) output + SZ__bss_start);
+ output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL;
+ check_ipl_parmblock((void *) 0, output_addr + SZ__bss_start);
memset(&_bss, 0, &_ebss - &_bss);
free_mem_ptr = (unsigned long)&_end;
free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
- output = (unsigned char *) ((free_mem_end_ptr + 4095UL) & -4096UL);
+ output = (unsigned char *) output_addr;
#ifdef CONFIG_BLK_DEV_INITRD
/*
BUG_ON(ret != bsize);
data += bsize - index;
len -= bsize - index;
+ index = 0;
}
/* process as many blocks as possible */
static inline int atomic_read(const atomic_t *v)
{
- barrier();
- return v->counter;
+ int c;
+
+ asm volatile(
+ " l %0,%1\n"
+ : "=d" (c) : "Q" (v->counter));
+ return c;
}
static inline void atomic_set(atomic_t *v, int i)
{
- v->counter = i;
- barrier();
+ asm volatile(
+ " st %1,%0\n"
+ : "=Q" (v->counter) : "d" (i));
}
static inline int atomic_add_return(int i, atomic_t *v)
static inline long long atomic64_read(const atomic64_t *v)
{
- barrier();
- return v->counter;
+ long long c;
+
+ asm volatile(
+ " lg %0,%1\n"
+ : "=d" (c) : "Q" (v->counter));
+ return c;
}
static inline void atomic64_set(atomic64_t *v, long long i)
{
- v->counter = i;
- barrier();
+ asm volatile(
+ " stg %1,%0\n"
+ : "=Q" (v->counter) : "d" (i));
}
static inline long long atomic64_add_return(long long i, atomic64_t *v)
#define L1_CACHE_BYTES 256
#define L1_CACHE_SHIFT 8
+#define NET_SKB_PAD 32
#define __read_mostly __attribute__((__section__(".data..read_mostly")))
#include <linux/uaccess.h>
#include <asm/errno.h>
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+ if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
return ret;
}
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr,
- int oldval, int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+ if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- return uaccess.futex_atomic_cmpxchg(uaddr, oldval, newval);
+ return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval);
}
#endif /* __KERNEL__ */
*/
extern unsigned long thread_saved_pc(struct task_struct *t);
-/*
- * Print register of task into buffer. Used in fs/proc/array.c.
- */
-extern void task_show_regs(struct seq_file *m, struct task_struct *task);
-
extern void show_code(struct pt_regs *regs);
unsigned long get_wchan(struct task_struct *p);
#ifdef __KERNEL__
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_write(struct rw_semaphore *);
-
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
- signed long count;
- spinlock_t wait_lock;
- struct list_head wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lockdep_map dep_map;
-#endif
-};
-
#ifndef __s390x__
#define RWSEM_UNLOCKED_VALUE 0x00000000
#define RWSEM_ACTIVE_BIAS 0x00000001
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-/*
- * initialisation
- */
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
- { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait.lock), \
- LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
- sem->count = RWSEM_UNLOCKED_VALUE;
- spin_lock_init(&sem->wait_lock);
- INIT_LIST_HEAD(&sem->wait_list);
-}
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
- struct lock_class_key *key);
-
-#define init_rwsem(sem) \
-do { \
- static struct lock_class_key __key; \
- \
- __init_rwsem((sem), #sem, &__key); \
-} while (0)
-
-
/*
* lock for reading
*/
return new;
}
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
- return (sem->count != 0);
-}
-
#endif /* __KERNEL__ */
#endif /* _S390_RWSEM_H */
size_t (*clear_user)(size_t, void __user *);
size_t (*strnlen_user)(size_t, const char __user *);
size_t (*strncpy_from_user)(size_t, const char __user *, char *);
- int (*futex_atomic_op)(int op, int __user *, int oparg, int *old);
- int (*futex_atomic_cmpxchg)(int __user *, int old, int new);
+ int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old);
+ int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new);
};
extern struct uaccess_ops uaccess;
show_last_breaking_event(regs);
}
-/* This is called from fs/proc/array.c */
-void task_show_regs(struct seq_file *m, struct task_struct *task)
-{
- struct pt_regs *regs;
-
- regs = task_pt_regs(task);
- seq_printf(m, "task: %p, ksp: %p\n",
- task, (void *)task->thread.ksp);
- seq_printf(m, "User PSW : %p %p\n",
- (void *) regs->psw.mask, (void *)regs->psw.addr);
-
- seq_printf(m, "User GPRS: " FOURLONG,
- regs->gprs[0], regs->gprs[1],
- regs->gprs[2], regs->gprs[3]);
- seq_printf(m, " " FOURLONG,
- regs->gprs[4], regs->gprs[5],
- regs->gprs[6], regs->gprs[7]);
- seq_printf(m, " " FOURLONG,
- regs->gprs[8], regs->gprs[9],
- regs->gprs[10], regs->gprs[11]);
- seq_printf(m, " " FOURLONG,
- regs->gprs[12], regs->gprs[13],
- regs->gprs[14], regs->gprs[15]);
- seq_printf(m, "User ACRS: %08x %08x %08x %08x\n",
- task->thread.acrs[0], task->thread.acrs[1],
- task->thread.acrs[2], task->thread.acrs[3]);
- seq_printf(m, " %08x %08x %08x %08x\n",
- task->thread.acrs[4], task->thread.acrs[5],
- task->thread.acrs[6], task->thread.acrs[7]);
- seq_printf(m, " %08x %08x %08x %08x\n",
- task->thread.acrs[8], task->thread.acrs[9],
- task->thread.acrs[10], task->thread.acrs[11]);
- seq_printf(m, " %08x %08x %08x %08x\n",
- task->thread.acrs[12], task->thread.acrs[13],
- task->thread.acrs[14], task->thread.acrs[15]);
-}
-
static DEFINE_SPINLOCK(die_lock);
void die(const char * str, struct pt_regs * regs, long err)
extern size_t copy_to_user_std(size_t, void __user *, const void *);
extern size_t strnlen_user_std(size_t, const char __user *);
extern size_t strncpy_from_user_std(size_t, const char __user *, char *);
-extern int futex_atomic_cmpxchg_std(int __user *, int, int);
-extern int futex_atomic_op_std(int, int __user *, int, int *);
+extern int futex_atomic_cmpxchg_std(u32 *, u32 __user *, u32, u32);
+extern int futex_atomic_op_std(int, u32 __user *, int, int *);
extern size_t copy_from_user_pt(size_t, const void __user *, void *);
extern size_t copy_to_user_pt(size_t, void __user *, const void *);
-extern int futex_atomic_op_pt(int, int __user *, int, int *);
-extern int futex_atomic_cmpxchg_pt(int __user *, int, int);
+extern int futex_atomic_op_pt(int, u32 __user *, int, int *);
+extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32);
#endif /* __ARCH_S390_LIB_UACCESS_H */
: "0" (-EFAULT), "d" (oparg), "a" (uaddr), \
"m" (*uaddr) : "cc" );
-static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
+static int __futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
{
int oldval = 0, newval, ret;
return ret;
}
-int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
+int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
{
int ret;
return ret;
}
-static int __futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
+static int __futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
int ret;
asm volatile("0: cs %1,%4,0(%5)\n"
- "1: lr %0,%1\n"
+ "1: la %0,0\n"
"2:\n"
EX_TABLE(0b,2b) EX_TABLE(1b,2b)
: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
: "cc", "memory" );
+ *uval = oldval;
return ret;
}
-int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
+int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
int ret;
if (segment_eq(get_fs(), KERNEL_DS))
- return __futex_atomic_cmpxchg_pt(uaddr, oldval, newval);
+ return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
spin_lock(¤t->mm->page_table_lock);
uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr);
if (!uaddr) {
}
get_page(virt_to_page(uaddr));
spin_unlock(¤t->mm->page_table_lock);
- ret = __futex_atomic_cmpxchg_pt(uaddr, oldval, newval);
+ ret = __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
put_page(virt_to_page(uaddr));
return ret;
}
: "0" (-EFAULT), "d" (oparg), "a" (uaddr), \
"m" (*uaddr) : "cc");
-int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old)
+int futex_atomic_op_std(int op, u32 __user *uaddr, int oparg, int *old)
{
int oldval = 0, newval, ret;
return ret;
}
-int futex_atomic_cmpxchg_std(int __user *uaddr, int oldval, int newval)
+int futex_atomic_cmpxchg_std(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
int ret;
asm volatile(
" sacf 256\n"
"0: cs %1,%4,0(%5)\n"
- "1: lr %0,%1\n"
+ "1: la %0,0\n"
"2: sacf 0\n"
EX_TABLE(0b,2b) EX_TABLE(1b,2b)
: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
: "cc", "memory" );
+ *uval = oldval;
return ret;
}
#include <asm/system.h>
-static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr,
int *oldval)
{
unsigned long flags;
return ret;
}
-static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr,
int *oldval)
{
unsigned long flags;
return ret;
}
-static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr,
int *oldval)
{
unsigned long flags;
return ret;
}
-static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr,
int *oldval)
{
unsigned long flags;
return ret;
}
-static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr,
int *oldval)
{
unsigned long flags;
return ret;
}
-static inline int atomic_futex_op_cmpxchg_inatomic(int __user *uaddr,
- int oldval, int newval)
+static inline int atomic_futex_op_cmpxchg_inatomic(u32 *uval,
+ u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
unsigned long flags;
- int ret, prev = 0;
+ int ret;
+ u32 prev = 0;
local_irq_save(flags);
local_irq_restore(flags);
- if (ret)
- return ret;
-
- return prev;
+ *uval = prev;
+ return ret;
}
#endif /* __ASM_SH_FUTEX_IRQ_H */
/* XXX: UP variants, fix for SH-4A and SMP.. */
#include <asm/futex-irq.h>
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- return atomic_futex_op_cmpxchg_inatomic(uaddr, oldval, newval);
+ return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval);
}
#endif /* __KERNEL__ */
#endif
#ifdef __KERNEL__
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
- long count;
#define RWSEM_UNLOCKED_VALUE 0x00000000
#define RWSEM_ACTIVE_BIAS 0x00000001
#define RWSEM_ACTIVE_MASK 0x0000ffff
#define RWSEM_WAITING_BIAS (-0x00010000)
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
- spinlock_t wait_lock;
- struct list_head wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lockdep_map dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
- { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
- LIST_HEAD_INIT((name).wait_list) \
- __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
- struct lock_class_key *key);
-
-#define init_rwsem(sem) \
-do { \
- static struct lock_class_key __key; \
- \
- __init_rwsem((sem), #sem, &__key); \
-} while (0)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
- sem->count = RWSEM_UNLOCKED_VALUE;
- spin_lock_init(&sem->wait_lock);
- INIT_LIST_HEAD(&sem->wait_list);
-}
/*
* lock for reading
return atomic_add_return(delta, (atomic_t *)(&sem->count));
}
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
- return (sem->count != 0);
-}
-
#endif /* __KERNEL__ */
#endif /* _ASM_SH_RWSEM_H */
#include <asm-generic/sections.h>
-extern void __nosave_begin, __nosave_end;
+extern long __nosave_begin, __nosave_end;
extern long __machvec_start, __machvec_end;
extern char __uncached_start, __uncached_end;
extern char _ebss[];
#include <linux/io.h>
#include <linux/sh_timer.h>
#include <linux/serial_sci.h>
-#include <asm/machtypes.h>
+#include <generated/machtypes.h>
static struct resource rtc_resources[] = {
[0] = {
void __init plat_early_device_setup(void)
{
+ struct platform_device *dev[1];
+
if (mach_is_rts7751r2d()) {
scif_platform_data.scscr |= SCSCR_CKE1;
- early_platform_add_devices(&scif_device, 1);
+ dev[0] = &scif_device;
+ early_platform_add_devices(dev, 1);
} else {
- early_platform_add_devices(&sci_device, 1);
- early_platform_add_devices(&scif_device, 1);
+ dev[0] = &sci_device;
+ early_platform_add_devices(dev, 1);
+ dev[0] = &scif_device;
+ early_platform_add_devices(dev, 1);
}
early_platform_add_devices(sh7750_early_devices,
void __delay(unsigned long loops)
{
__asm__ __volatile__(
+ /*
+ * ST40-300 appears to have an issue with this code,
+ * normally taking two cycles each loop, as with all
+ * other SH variants. If however the branch and the
+ * delay slot straddle an 8 byte boundary, this increases
+ * to 3 cycles.
+ * This align directive ensures this doesn't occur.
+ */
+ ".balign 8\n\t"
+
"tst %0, %0\n\t"
"1:\t"
"bf/s 1b\n\t"
kunmap_atomic(vfrom, KM_USER0);
}
- if (pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK))
+ if (pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK) ||
+ (vma->vm_flags & VM_EXEC))
__flush_purge_region(vto, PAGE_SIZE);
kunmap_atomic(vto, KM_USER1);
: "r" (uaddr), "r" (oparg), "i" (-EFAULT) \
: "memory")
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
int cmparg = (encoded_op << 20) >> 20;
int oldval = 0, ret, tem;
- if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(int))))
+ if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
return -EFAULT;
if (unlikely((((unsigned long) uaddr) & 0x3UL)))
return -EINVAL;
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
+ int ret = 0;
+
__asm__ __volatile__(
- "\n1: casa [%3] %%asi, %2, %0\n"
+ "\n1: casa [%4] %%asi, %3, %1\n"
"2:\n"
" .section .fixup,#alloc,#execinstr\n"
" .align 4\n"
"3: sethi %%hi(2b), %0\n"
" jmpl %0 + %%lo(2b), %%g0\n"
- " mov %4, %0\n"
+ " mov %5, %0\n"
" .previous\n"
" .section __ex_table,\"a\"\n"
" .align 4\n"
" .word 1b, 3b\n"
" .previous\n"
- : "=r" (newval)
- : "0" (newval), "r" (oldval), "r" (uaddr), "i" (-EFAULT)
+ : "+r" (ret), "=r" (newval)
+ : "1" (newval), "r" (oldval), "r" (uaddr), "i" (-EFAULT)
: "memory");
- return newval;
+ *uval = newval;
+ return ret;
}
#endif /* !(_SPARC64_FUTEX_H) */
extern u64 pcr_enable;
+extern int pcr_arch_init(void);
+
#endif /* __PCR_H */
#ifdef __KERNEL__
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
-
-struct rw_semaphore {
- signed long count;
#define RWSEM_UNLOCKED_VALUE 0x00000000L
#define RWSEM_ACTIVE_BIAS 0x00000001L
#define RWSEM_ACTIVE_MASK 0xffffffffL
#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1)
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
- spinlock_t wait_lock;
- struct list_head wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lockdep_map dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
- LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
- struct lock_class_key *key);
-
-#define init_rwsem(sem) \
-do { \
- static struct lock_class_key __key; \
- \
- __init_rwsem((sem), #sem, &__key); \
-} while (0)
/*
* lock for reading
return atomic64_add_return(delta, (atomic64_t *)(&sem->count));
}
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
- return (sem->count != 0);
-}
-
#endif /* __KERNEL__ */
#endif /* _SPARC64_RWSEM_H */
static int iommu_alloc_ctx(struct iommu *iommu)
{
int lowest = iommu->ctx_lowest_free;
- int sz = IOMMU_NUM_CTXS - lowest;
- int n = find_next_zero_bit(iommu->ctx_bitmap, sz, lowest);
+ int n = find_next_zero_bit(iommu->ctx_bitmap, IOMMU_NUM_CTXS, lowest);
- if (unlikely(n == sz)) {
+ if (unlikely(n == IOMMU_NUM_CTXS)) {
n = find_next_zero_bit(iommu->ctx_bitmap, lowest, 1);
if (unlikely(n == lowest)) {
printk(KERN_WARNING "IOMMU: Ran out of contexts.\n");
static irqreturn_t pcic_timer_handler (int irq, void *h)
{
- write_seqlock(&xtime_lock); /* Dummy, to show that we remember */
pcic_clear_clock_irq();
- do_timer(1);
- write_sequnlock(&xtime_lock);
+ xtime_update(1);
#ifndef CONFIG_SMP
update_process_times(user_mode(get_irq_regs()));
#endif
unregister_perf_hsvc();
return err;
}
-
-early_initcall(pcr_arch_init);
#include <asm/mdesc.h>
#include <asm/ldc.h>
#include <asm/hypervisor.h>
+#include <asm/pcr.h>
#include "cpumap.h"
void __init smp_cpus_done(unsigned int max_cpus)
{
+ pcr_arch_init();
}
void smp_send_reschedule(int cpu)
/*
* timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
+ * as well as call the "xtime_update()" routine every clocktick
*/
#define TICK_SIZE (tick_nsec / 1000)
profile_tick(CPU_PROFILING);
#endif
- /* Protect counter clear so that do_gettimeoffset works */
- write_seqlock(&xtime_lock);
-
clear_clock_irq();
- do_timer(1);
-
- write_sequnlock(&xtime_lock);
+ xtime_update(1);
#ifndef CONFIG_SMP
update_process_times(user_mode(get_irq_regs()));
.globl __do_int_store
__do_int_store:
ld [%o2], %g1
- cmp %1, 2
+ cmp %o1, 2
be 2f
- cmp %1, 4
+ cmp %o1, 4
be 1f
srl %g1, 24, %g2
srl %g1, 16, %g7
#define ATOMIC_HASH(a) (&__atomic_hash[(((unsigned long)a)>>8) & (ATOMIC_HASH_SIZE-1)])
spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] = {
- [0 ... (ATOMIC_HASH_SIZE-1)] = SPIN_LOCK_UNLOCKED
+ [0 ... (ATOMIC_HASH_SIZE-1)] = __SPIN_LOCK_UNLOCKED(__atomic_hash)
};
#else /* SMP */
*/
#include <linux/string.h>
-#include <linux/bitops.h>
+#include <linux/bitmap.h>
#include <asm/bitext.h>
while (test_bit(offset + i, t->map) == 0) {
i++;
if (i == len) {
- for (i = 0; i < len; i++)
- __set_bit(offset + i, t->map);
+ bitmap_set(t->map, offset, len);
if (offset == t->first_free)
t->first_free = find_next_zero_bit
(t->map, t->size,
#include <linux/uaccess.h>
#include <linux/errno.h>
-extern struct __get_user futex_set(int __user *v, int i);
-extern struct __get_user futex_add(int __user *v, int n);
-extern struct __get_user futex_or(int __user *v, int n);
-extern struct __get_user futex_andn(int __user *v, int n);
-extern struct __get_user futex_cmpxchg(int __user *v, int o, int n);
+extern struct __get_user futex_set(u32 __user *v, int i);
+extern struct __get_user futex_add(u32 __user *v, int n);
+extern struct __get_user futex_or(u32 __user *v, int n);
+extern struct __get_user futex_andn(u32 __user *v, int n);
+extern struct __get_user futex_cmpxchg(u32 __user *v, int o, int n);
#ifndef __tilegx__
-extern struct __get_user futex_xor(int __user *v, int n);
+extern struct __get_user futex_xor(u32 __user *v, int n);
#else
-static inline struct __get_user futex_xor(int __user *uaddr, int n)
+static inline struct __get_user futex_xor(u32 __user *uaddr, int n)
{
struct __get_user asm_ret = __get_user_4(uaddr);
if (!asm_ret.err) {
}
#endif
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
return ret;
}
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
- int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
struct __get_user asm_ret;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
asm_ret = futex_cmpxchg(uaddr, oldval, newval);
- return asm_ret.err ? asm_ret.err : asm_ret.val;
+ *uval = asm_ret.val;
+ return asm_ret.err;
}
#ifndef __tilegx__
bool
default y
select HAVE_GENERIC_HARDIRQS
+ select GENERIC_HARDIRQS_NO_DEPRECATED
config MMU
bool
config UML_X86
def_bool y
+ select GENERIC_FIND_FIRST_BIT
+ select GENERIC_FIND_NEXT_BIT
config 64BIT
bool
def_bool !64BIT
select HAVE_AOUT
+config X86_64
+ def_bool 64BIT
+
config RWSEM_XCHGADD_ALGORITHM
def_bool X86_XADD
#if 0
void mconsole_proc(struct mc_request *req)
{
- struct nameidata nd;
struct vfsmount *mnt = current->nsproxy->pid_ns->proc_mnt;
struct file *file;
- int n, err;
+ int n;
char *ptr = req->request.data, *buf;
mm_segment_t old_fs = get_fs();
ptr += strlen("proc");
ptr = skip_spaces(ptr);
- err = vfs_path_lookup(mnt->mnt_root, mnt, ptr, LOOKUP_FOLLOW, &nd);
- if (err) {
- mconsole_reply(req, "Failed to look up file", 1, 0);
- goto out;
- }
-
- err = may_open(&nd.path, MAY_READ, O_RDONLY);
- if (result) {
- mconsole_reply(req, "Failed to open file", 1, 0);
- path_put(&nd.path);
- goto out;
- }
-
- file = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY,
- current_cred());
- err = PTR_ERR(file);
+ file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY);
if (IS_ERR(file)) {
mconsole_reply(req, "Failed to open file", 1, 0);
- path_put(&nd.path);
goto out;
}
.no_cow = 0, \
.shared = 0, \
.cow = DEFAULT_COW, \
- .lock = SPIN_LOCK_UNLOCKED, \
+ .lock = __SPIN_LOCK_UNLOCKED(ubd_devs.lock), \
.request = NULL, \
.start_sg = 0, \
.end_sg = 0, \
}
if (i < NR_IRQS) {
- raw_spin_lock_irqsave(&irq_desc[i].lock, flags);
- action = irq_desc[i].action;
+ struct irq_desc *desc = irq_to_desc(i);
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+ action = desc->action;
if (!action)
goto skip;
seq_printf(p, "%3d: ",i);
for_each_online_cpu(j)
seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
#endif
- seq_printf(p, " %14s", irq_desc[i].chip->name);
+ seq_printf(p, " %14s", get_irq_desc_chip(desc)->name);
seq_printf(p, " %s", action->name);
for (action=action->next; action; action = action->next)
seq_putc(p, '\n');
skip:
- raw_spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
} else if (i == NR_IRQS)
seq_putc(p, '\n');
EXPORT_SYMBOL(reactivate_fd);
/*
- * irq_chip must define (startup || enable) &&
- * (shutdown || disable) && end
+ * irq_chip must define at least enable/disable and ack when
+ * the edge handler is used.
*/
-static void dummy(unsigned int irq)
+static void dummy(struct irq_data *d)
{
}
static struct irq_chip normal_irq_type = {
.name = "SIGIO",
.release = free_irq_by_irq_and_dev,
- .disable = dummy,
- .enable = dummy,
- .ack = dummy,
- .end = dummy
+ .irq_disable = dummy,
+ .irq_enable = dummy,
+ .irq_ack = dummy,
};
static struct irq_chip SIGVTALRM_irq_type = {
.name = "SIGVTALRM",
.release = free_irq_by_irq_and_dev,
- .shutdown = dummy, /* never called */
- .disable = dummy,
- .enable = dummy,
- .ack = dummy,
- .end = dummy
+ .irq_disable = dummy,
+ .irq_enable = dummy,
+ .irq_ack = dummy,
};
void __init init_IRQ(void)
select HAVE_TEXT_POKE_SMP
select HAVE_GENERIC_HARDIRQS
select HAVE_SPARSE_IRQ
+ select GENERIC_FIND_FIRST_BIT
+ select GENERIC_FIND_NEXT_BIT
select GENERIC_IRQ_PROBE
select GENERIC_PENDING_IRQ if SMP
+ select GENERIC_IRQ_SHOW
+ select IRQ_FORCED_THREADING
select USE_GENERIC_SMP_HELPERS if SMP
config INSTRUCTION_DECODER
config X86_IO_APIC
def_bool y
- depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
+ depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
config X86_VISWS_APIC
def_bool y
endif
-config X86_CPU
- def_bool y
- select GENERIC_FIND_FIRST_BIT
- select GENERIC_FIND_NEXT_BIT
-
#
# Define implied options from the CPU selection here
config X86_INTERNODE_CACHE_SHIFT
if (fseek(f, -4L, SEEK_END)) {
perror(argv[1]);
}
- fread(&olen, sizeof olen, 1, f);
+
+ if (fread(&olen, sizeof(olen), 1, f) != 1) {
+ perror(argv[1]);
+ return 1;
+ }
+
ilen = ftell(f);
olen = getle32(&olen);
fclose(f);
#define sysretl_audit ia32_ret_from_sys_call
#endif
+ .section .entry.text, "ax"
+
#define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
.macro IA32_ARG_FIXUP noebp=0
*/
ENABLE_INTERRUPTS(CLBR_NONE)
movl %ebp,%ebp /* zero extension */
- pushq $__USER32_DS
- CFI_ADJUST_CFA_OFFSET 8
+ pushq_cfi $__USER32_DS
/*CFI_REL_OFFSET ss,0*/
- pushq %rbp
- CFI_ADJUST_CFA_OFFSET 8
+ pushq_cfi %rbp
CFI_REL_OFFSET rsp,0
- pushfq
- CFI_ADJUST_CFA_OFFSET 8
+ pushfq_cfi
/*CFI_REL_OFFSET rflags,0*/
movl 8*3-THREAD_SIZE+TI_sysenter_return(%rsp), %r10d
CFI_REGISTER rip,r10
- pushq $__USER32_CS
- CFI_ADJUST_CFA_OFFSET 8
+ pushq_cfi $__USER32_CS
/*CFI_REL_OFFSET cs,0*/
movl %eax, %eax
- pushq %r10
- CFI_ADJUST_CFA_OFFSET 8
+ pushq_cfi %r10
CFI_REL_OFFSET rip,0
- pushq %rax
- CFI_ADJUST_CFA_OFFSET 8
+ pushq_cfi %rax
cld
SAVE_ARGS 0,0,1
/* no need to do an access_ok check here because rbp has been
xorq %r9,%r9
xorq %r10,%r10
xorq %r11,%r11
- popfq
- CFI_ADJUST_CFA_OFFSET -8
+ popfq_cfi
/*CFI_RESTORE rflags*/
- popq %rcx /* User %esp */
- CFI_ADJUST_CFA_OFFSET -8
+ popq_cfi %rcx /* User %esp */
CFI_REGISTER rsp,rcx
TRACE_IRQS_ON
ENABLE_INTERRUPTS_SYSEXIT32
*/
ENABLE_INTERRUPTS(CLBR_NONE)
movl %eax,%eax
- pushq %rax
- CFI_ADJUST_CFA_OFFSET 8
+ pushq_cfi %rax
cld
/* note the registers are not zero extended to the sf.
this could be a problem. */
.quad sys_fanotify_init
.quad sys32_fanotify_mark
.quad sys_prlimit64 /* 340 */
+ .quad sys_name_to_handle_at
+ .quad compat_sys_open_by_handle_at
+ .quad compat_sys_clock_adjtime
ia32_syscall_end:
extern int acpi_pci_disabled;
extern int acpi_skip_timer_override;
extern int acpi_use_timer_override;
+extern int acpi_fix_pin2_polarity;
extern u8 acpi_sci_flags;
extern int acpi_sci_override_gsi;
extern void init_bsp_APIC(void);
extern void setup_local_APIC(void);
extern void end_local_APIC_setup(void);
+extern void bsp_end_local_APIC_setup(void);
extern void init_apic_mappings(void);
void register_lapic_address(unsigned long address);
extern void setup_boot_APIC_clock(void);
#else
#define BAD_APICID 0xFFFFu
#endif
+
+enum ioapic_irq_destination_types {
+ dest_Fixed = 0,
+ dest_LowestPrio = 1,
+ dest_SMI = 2,
+ dest__reserved_1 = 3,
+ dest_NMI = 4,
+ dest_INIT = 5,
+ dest__reserved_2 = 6,
+ dest_ExtINT = 7
+};
+
#endif /* _ASM_X86_APICDEF_H */
--- /dev/null
+#ifndef _ASM_CE4100_H_
+#define _ASM_CE4100_H_
+
+int ce4100_pci_init(void);
+
+#endif
DECLARE_PER_CPU(int, cpu_state);
-int __cpuinit mwait_usable(const struct cpuinfo_x86 *);
+int mwait_usable(const struct cpuinfo_x86 *);
#endif /* _ASM_X86_CPU_H */
#define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */
#define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */
#define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
/*
* Auxiliary flags: Linux defined - For features scattered in various
#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR)
#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ)
+#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
# define cpu_has_invlpg 1
frame pointer later */
#ifdef CONFIG_FRAME_POINTER
.macro FRAME
- pushl %ebp
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ebp
CFI_REL_OFFSET ebp,0
movl %esp,%ebp
.endm
.macro ENDFRAME
- popl %ebp
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %ebp
CFI_RESTORE ebp
.endm
#else
"+m" (*uaddr), "=&r" (tem) \
: "r" (oparg), "i" (-EFAULT), "1" (0))
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
return ret;
}
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
- int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
+ int ret = 0;
#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
/* Real i386 machines have no cmpxchg instruction */
return -ENOSYS;
#endif
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
+ asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
"2:\t.section .fixup, \"ax\"\n"
- "3:\tmov %2, %0\n"
+ "3:\tmov %3, %0\n"
"\tjmp 2b\n"
"\t.previous\n"
_ASM_EXTABLE(1b, 3b)
- : "=a" (oldval), "+m" (*uaddr)
- : "i" (-EFAULT), "r" (newval), "0" (oldval)
+ : "+r" (ret), "=a" (oldval), "+m" (*uaddr)
+ : "i" (-EFAULT), "r" (newval), "1" (oldval)
: "memory"
);
- return oldval;
+ *uval = oldval;
+ return ret;
}
#endif
} __attribute__ ((packed)) bits;
};
-enum ioapic_irq_destination_types {
- dest_Fixed = 0,
- dest_LowestPrio = 1,
- dest_SMI = 2,
- dest__reserved_1 = 3,
- dest_NMI = 4,
- dest_INIT = 5,
- dest__reserved_2 = 6,
- dest_ExtINT = 7
-};
-
struct IO_APIC_route_entry {
__u32 vector : 8,
delivery_mode : 3, /* 000: FIXED
index : 15;
} __attribute__ ((packed));
+#define IOAPIC_AUTO -1
+#define IOAPIC_EDGE 0
+#define IOAPIC_LEVEL 1
+
#ifdef CONFIG_X86_IO_APIC
/*
#define io_apic_assign_pci_irqs \
(mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
-extern u8 io_apic_unique_id(u8 id);
-extern int io_apic_get_unique_id(int ioapic, int apic_id);
-extern int io_apic_get_version(int ioapic);
-extern int io_apic_get_redir_entries(int ioapic);
-
struct io_apic_irq_attr;
extern int io_apic_set_pci_routing(struct device *dev, int irq,
struct io_apic_irq_attr *irq_attr);
extern void ioapic_and_gsi_init(void);
extern void ioapic_insert_resources(void);
+int io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr);
+
extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
extern void mp_save_irq(struct mpc_intsrc *m);
+extern void disable_ioapic_support(void);
+
#else /* !CONFIG_X86_IO_APIC */
#define io_apic_assign_pci_irqs 0
struct io_apic_irq_attr;
static inline int io_apic_set_pci_routing(struct device *dev, int irq,
struct io_apic_irq_attr *irq_attr) { return 0; }
+
+static inline struct IO_APIC_route_entry **alloc_ioapic_entries(void)
+{
+ return NULL;
+}
+
+static inline void free_ioapic_entries(struct IO_APIC_route_entry **ent) { }
+static inline int save_IO_APIC_setup(struct IO_APIC_route_entry **ent)
+{
+ return -ENOMEM;
+}
+
+static inline void mask_IO_APIC_setup(struct IO_APIC_route_entry **ent) { }
+static inline int restore_IO_APIC_setup(struct IO_APIC_route_entry **ent)
+{
+ return -ENOMEM;
+}
+
+static inline void mp_save_irq(struct mpc_intsrc *m) { };
+static inline void disable_ioapic_support(void) { }
#endif
#endif /* _ASM_X86_IO_APIC_H */
DIE_PANIC,
DIE_NMI,
DIE_DIE,
- DIE_NMIWATCHDOG,
DIE_KERNELDEBUG,
DIE_TRAP,
DIE_GPF,
#define MSR_IA32_PERFCTR1 0x000000c2
#define MSR_FSB_FREQ 0x000000cd
+#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 MSR_MTRRcap 0x000000fe
#define MSR_IA32_BBL_CR_CTL 0x00000119
#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_IA32_PEBS_ENABLE 0x000003f1
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
#ifdef CONFIG_X86_LOCAL_APIC
-extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
extern int reserve_perfctr_nmi(unsigned int);
extern void release_perfctr_nmi(unsigned int);
#define ARCH_P4_CNTRVAL_BITS (40)
#define ARCH_P4_CNTRVAL_MASK ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1)
+#define ARCH_P4_UNFLAGGED_BIT ((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1))
#define P4_ESCR_EVENT_MASK 0x7e000000U
#define P4_ESCR_EVENT_SHIFT 25
int x86_cache_alignment; /* In bytes */
int x86_power;
unsigned long loops_per_jiffy;
-#ifdef CONFIG_SMP
- /* cpus sharing the last level cache: */
- cpumask_var_t llc_shared_map;
-#endif
/* cpuid returned max cores value: */
u16 x86_max_cores;
u16 apicid;
#endif
#ifdef __KERNEL__
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/lockdep.h>
#include <asm/asm.h>
-struct rwsem_waiter;
-
-extern asmregparm struct rw_semaphore *
- rwsem_down_read_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_down_write_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_wake(struct rw_semaphore *);
-extern asmregparm struct rw_semaphore *
- rwsem_downgrade_wake(struct rw_semaphore *sem);
-
/*
- * the semaphore definition
- *
* The bias values and the counter type limits the number of
* potential readers/writers to 32767 for 32 bits and 2147483647
* for 64 bits.
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-typedef signed long rwsem_count_t;
-
-struct rw_semaphore {
- rwsem_count_t count;
- spinlock_t wait_lock;
- struct list_head wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lockdep_map dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-
-#define __RWSEM_INITIALIZER(name) \
-{ \
- RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
- LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \
-}
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
- struct lock_class_key *key);
-
-#define init_rwsem(sem) \
-do { \
- static struct lock_class_key __key; \
- \
- __init_rwsem((sem), #sem, &__key); \
-} while (0)
-
/*
* lock for reading
*/
*/
static inline int __down_read_trylock(struct rw_semaphore *sem)
{
- rwsem_count_t result, tmp;
+ long result, tmp;
asm volatile("# beginning __down_read_trylock\n\t"
" mov %0,%1\n\t"
"1:\n\t"
*/
static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
{
- rwsem_count_t tmp;
+ long tmp;
asm volatile("# beginning down_write\n\t"
LOCK_PREFIX " xadd %1,(%2)\n\t"
/* adds 0xffff0001, returns the old value */
*/
static inline int __down_write_trylock(struct rw_semaphore *sem)
{
- rwsem_count_t ret = cmpxchg(&sem->count,
- RWSEM_UNLOCKED_VALUE,
- RWSEM_ACTIVE_WRITE_BIAS);
+ long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+ RWSEM_ACTIVE_WRITE_BIAS);
if (ret == RWSEM_UNLOCKED_VALUE)
return 1;
return 0;
*/
static inline void __up_read(struct rw_semaphore *sem)
{
- rwsem_count_t tmp;
+ long tmp;
asm volatile("# beginning __up_read\n\t"
LOCK_PREFIX " xadd %1,(%2)\n\t"
/* subtracts 1, returns the old value */
*/
static inline void __up_write(struct rw_semaphore *sem)
{
- rwsem_count_t tmp;
+ long tmp;
asm volatile("# beginning __up_write\n\t"
LOCK_PREFIX " xadd %1,(%2)\n\t"
/* subtracts 0xffff0001, returns the old value */
/*
* implement atomic add functionality
*/
-static inline void rwsem_atomic_add(rwsem_count_t delta,
- struct rw_semaphore *sem)
+static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
{
asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
: "+m" (sem->count)
/*
* implement exchange and add functionality
*/
-static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta,
- struct rw_semaphore *sem)
+static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
{
- rwsem_count_t tmp = delta;
+ long tmp = delta;
asm volatile(LOCK_PREFIX "xadd %0,%1"
: "+r" (tmp), "+m" (sem->count)
return tmp + delta;
}
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
- return (sem->count != 0);
-}
-
#endif /* __KERNEL__ */
#endif /* _ASM_X86_RWSEM_H */
#endif
#include <asm/thread_info.h>
#include <asm/cpumask.h>
+#include <asm/cpufeature.h>
extern int smp_num_siblings;
extern unsigned int num_processors;
+static inline bool cpu_has_ht_siblings(void)
+{
+ bool has_siblings = false;
+#ifdef CONFIG_SMP
+ has_siblings = cpu_has_ht && smp_num_siblings > 1;
+#endif
+ return has_siblings;
+}
+
DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
+/* cpus sharing the last level cache: */
+DECLARE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
DECLARE_PER_CPU(u16, cpu_llc_id);
DECLARE_PER_CPU(int, cpu_number);
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);
+}
+
DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
*/
CMOS_WRITE(0, 0xf);
- *((volatile long *)phys_to_virt(apic->trampoline_phys_low)) = 0;
+ *((volatile u32 *)phys_to_virt(apic->trampoline_phys_low)) = 0;
}
static inline void __init smpboot_setup_io_apic(void)
*/
#define HAVE_DISABLE_HLT
#else
-#define __SAVE(reg, offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
-#define __RESTORE(reg, offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
/* frame pointer must be last for get_wchan */
#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
#define __NR_fanotify_init 338
#define __NR_fanotify_mark 339
#define __NR_prlimit64 340
+#define __NR_name_to_handle_at 341
+#define __NR_open_by_handle_at 342
+#define __NR_clock_adjtime 343
#ifdef __KERNEL__
-#define NR_syscalls 341
+#define NR_syscalls 344
#define __ARCH_WANT_IPC_PARSE_VERSION
#define __ARCH_WANT_OLD_READDIR
__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
#define __NR_prlimit64 302
__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_name_to_handle_at 303
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at 304
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
+#define __NR_clock_adjtime 305
+__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
#ifndef __NO_STUBS
#define __ARCH_WANT_OLD_READDIR
struct bau_msg_header {
unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */
/* bits 5:0 */
- unsigned int base_dest_nodeid:15; /* nasid (pnode<<1) of */
+ unsigned int base_dest_nodeid:15; /* nasid of the */
/* bits 20:6 */ /* first bit in uvhub map */
unsigned int command:8; /* message type */
/* bits 28:21 */
static inline int
HYPERVISOR_sched_op(int cmd, void *arg)
{
- return _hypercall2(int, sched_op_new, cmd, arg);
+ return _hypercall2(int, sched_op, cmd, arg);
}
static inline long
#endif
static inline int
-HYPERVISOR_suspend(unsigned long srec)
+HYPERVISOR_suspend(unsigned long start_info_mfn)
{
- return _hypercall3(int, sched_op, SCHEDOP_shutdown,
- SHUTDOWN_suspend, srec);
+ struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
+
+ /*
+ * For a PV guest the tools require that the start_info mfn be
+ * present in rdx/edx when the hypercall is made. Per the
+ * hypercall calling convention this is the third hypercall
+ * argument, which is start_info_mfn here.
+ */
+ return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn);
}
static inline int
/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
#define INVALID_P2M_ENTRY (~0UL)
-#define FOREIGN_FRAME_BIT (1UL<<31)
+#define FOREIGN_FRAME_BIT (1UL<<(BITS_PER_LONG-1))
+#define IDENTITY_FRAME_BIT (1UL<<(BITS_PER_LONG-2))
#define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT)
+#define IDENTITY_FRAME(m) ((m) | IDENTITY_FRAME_BIT)
/* Maximum amount of memory we can handle in a domain in pages */
#define MAX_DOMAIN_PAGES \
extern unsigned long get_phys_to_machine(unsigned long pfn);
extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern unsigned long set_phys_range_identity(unsigned long pfn_s,
+ unsigned long pfn_e);
extern int m2p_add_override(unsigned long mfn, struct page *page);
extern int m2p_remove_override(struct page *page);
extern struct page *m2p_find_override(unsigned long mfn);
extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
+#ifdef CONFIG_XEN_DEBUG_FS
+extern int p2m_dump_show(struct seq_file *m, void *v);
+#endif
static inline unsigned long pfn_to_mfn(unsigned long pfn)
{
unsigned long mfn;
mfn = get_phys_to_machine(pfn);
if (mfn != INVALID_P2M_ENTRY)
- mfn &= ~FOREIGN_FRAME_BIT;
+ mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
return mfn;
}
static inline unsigned long mfn_to_pfn(unsigned long mfn)
{
unsigned long pfn;
+ int ret = 0;
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
+ if (unlikely((mfn >> machine_to_phys_order) != 0)) {
+ pfn = ~0;
+ goto try_override;
+ }
pfn = 0;
/*
* The array access can fail (e.g., device space beyond end of RAM).
* In such cases it doesn't matter what we return (we return garbage),
* but we must handle the fault without crashing!
*/
- __get_user(pfn, &machine_to_phys_mapping[mfn]);
-
- /*
- * If this appears to be a foreign mfn (because the pfn
- * doesn't map back to the mfn), then check the local override
- * table to see if there's a better pfn to use.
+ ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+try_override:
+ /* ret might be < 0 if there are no entries in the m2p for mfn */
+ if (ret < 0)
+ pfn = ~0;
+ else if (get_phys_to_machine(pfn) != mfn)
+ /*
+ * If this appears to be a foreign mfn (because the pfn
+ * doesn't map back to the mfn), then check the local override
+ * table to see if there's a better pfn to use.
+ *
+ * m2p_find_override_pfn returns ~0 if it doesn't find anything.
+ */
+ pfn = m2p_find_override_pfn(mfn, ~0);
+
+ /*
+ * pfn is ~0 if there are no entries in the m2p for mfn or if the
+ * entry doesn't map back to the mfn and m2p_override doesn't have a
+ * valid entry for it.
*/
- if (get_phys_to_machine(pfn) != mfn)
- pfn = m2p_find_override_pfn(mfn, pfn);
+ if (pfn == ~0 &&
+ get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn))
+ pfn = mfn;
return pfn;
}
* its own functions.
*/
struct xen_pci_frontend_ops {
- int (*enable_msi)(struct pci_dev *dev, int **vectors);
+ int (*enable_msi)(struct pci_dev *dev, int vectors[]);
void (*disable_msi)(struct pci_dev *dev);
- int (*enable_msix)(struct pci_dev *dev, int **vectors, int nvec);
+ int (*enable_msix)(struct pci_dev *dev, int vectors[], int nvec);
void (*disable_msix)(struct pci_dev *dev);
};
extern struct xen_pci_frontend_ops *xen_pci_frontend;
static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
- int **vectors)
+ int vectors[])
{
if (xen_pci_frontend && xen_pci_frontend->enable_msi)
return xen_pci_frontend->enable_msi(dev, vectors);
xen_pci_frontend->disable_msi(dev);
}
static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
- int **vectors, int nvec)
+ int vectors[], int nvec)
{
if (xen_pci_frontend && xen_pci_frontend->enable_msix)
return xen_pci_frontend->enable_msix(dev, vectors, nvec);
int acpi_sci_override_gsi __initdata;
int acpi_skip_timer_override __initdata;
int acpi_use_timer_override __initdata;
+int acpi_fix_pin2_polarity __initdata;
#ifdef CONFIG_X86_LOCAL_APIC
static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
return 0;
}
- if (acpi_skip_timer_override &&
- intsrc->source_irq == 0 && intsrc->global_irq == 2) {
- printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n");
- return 0;
+ if (intsrc->source_irq == 0 && intsrc->global_irq == 2) {
+ if (acpi_skip_timer_override) {
+ printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n");
+ return 0;
+ }
+ if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) {
+ intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK;
+ printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n");
+ }
}
mp_override_legacy_irq(intsrc->source_irq,
atomic_set(&stop_machine_first, 1);
wrote_text = 0;
- stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+ __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
}
#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device));
if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) {
- apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100;
+ adev->evt.rating = APBT_CLOCKEVENT_RATING - 100;
global_clock_event = &adev->evt;
printk(KERN_DEBUG "%s clockevent registered as global\n",
global_clock_event->name);
#include <asm/i8259.h>
#include <asm/proto.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
#include <asm/idle.h>
rdtscll(tsc);
if (disable_apic) {
- arch_disable_smp_support();
+ disable_ioapic_support();
return;
}
#endif
apic_pm_activate();
+}
+
+void __init bsp_end_local_APIC_setup(void)
+{
+ end_local_APIC_setup();
/*
* Now that local APIC setup is completed for BP, configure the fault
* handling for interrupt remapping.
*/
- if (!smp_processor_id() && intr_remapping_enabled)
+ if (intr_remapping_enabled)
enable_drhd_fault_handling();
}
void __init enable_IR_x2apic(void)
{
unsigned long flags;
- struct IO_APIC_route_entry **ioapic_entries = NULL;
+ struct IO_APIC_route_entry **ioapic_entries;
int ret, x2apic_enabled = 0;
int dmar_table_init_ret;
enable_IO_APIC();
#endif
- end_local_APIC_setup();
+ bsp_end_local_APIC_setup();
#ifdef CONFIG_X86_IO_APIC
if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
{
int cpu;
- /*
- * Validate version
- */
- if (version == 0x0) {
- pr_warning("BIOS bug, APIC version is 0 for CPU#%d! "
- "fixing up to 0x10. (tell your hw vendor)\n",
- version);
- version = 0x10;
- }
- apic_version[apicid] = version;
-
if (num_processors >= nr_cpu_ids) {
int max = nr_cpu_ids;
int thiscpu = max + disabled_cpus;
}
num_processors++;
- cpu = cpumask_next_zero(-1, cpu_present_mask);
-
- if (version != apic_version[boot_cpu_physical_apicid])
- WARN_ONCE(1,
- "ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
- apic_version[boot_cpu_physical_apicid], cpu, version);
-
- physid_set(apicid, phys_cpu_present_map);
if (apicid == boot_cpu_physical_apicid) {
/*
* x86_bios_cpu_apicid is required to have processors listed
* in same order as logical cpu numbers. Hence the first
* entry is BSP, and so on.
+ * boot_cpu_init() already hold bit 0 in cpu_present_mask
+ * for BSP.
*/
cpu = 0;
+ } else
+ cpu = cpumask_next_zero(-1, cpu_present_mask);
+
+ /*
+ * Validate version
+ */
+ if (version == 0x0) {
+ pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
+ cpu, apicid);
+ version = 0x10;
+ }
+ apic_version[apicid] = version;
+
+ if (version != apic_version[boot_cpu_physical_apicid]) {
+ pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
+ apic_version[boot_cpu_physical_apicid], cpu, version);
}
+
+ physid_set(apicid, phys_cpu_present_map);
if (apicid > max_physical_apicid)
max_physical_apicid = apicid;
arch_spin_lock(&lock);
printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
show_regs(regs);
- dump_stack();
arch_spin_unlock(&lock);
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return NOTIFY_STOP;
int skip_ioapic_setup;
-void arch_disable_smp_support(void)
+/**
+ * disable_ioapic_support() - disables ioapic support at runtime
+ */
+void disable_ioapic_support(void)
{
#ifdef CONFIG_PCI
noioapicquirk = 1;
static int __init parse_noapic(char *str)
{
/* disable IO-APIC */
- arch_disable_smp_support();
+ disable_ioapic_support();
return 0;
}
early_param("noapic", parse_noapic);
+static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
+ struct io_apic_irq_attr *attr);
+
/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
void mp_save_irq(struct mpc_intsrc *m)
{
irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
for (i = 0; i < count; i++) {
- set_irq_chip_data(i, &cfg[i]);
+ irq_set_chip_data(i, &cfg[i]);
zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
/*
#ifdef CONFIG_SPARSE_IRQ
static struct irq_cfg *irq_cfg(unsigned int irq)
{
- return get_irq_chip_data(irq);
+ return irq_get_chip_data(irq);
}
static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
{
if (!cfg)
return;
- set_irq_chip_data(at, NULL);
+ irq_set_chip_data(at, NULL);
free_cpumask_var(cfg->domain);
free_cpumask_var(cfg->old_domain);
kfree(cfg);
if (res < 0) {
if (res != -EEXIST)
return NULL;
- cfg = get_irq_chip_data(at);
+ cfg = irq_get_chip_data(at);
if (cfg)
return cfg;
}
cfg = alloc_irq_cfg(at, node);
if (cfg)
- set_irq_chip_data(at, cfg);
+ irq_set_chip_data(at, cfg);
else
irq_free_desc(at);
return cfg;
#define default_MCA_trigger(idx) (1)
#define default_MCA_polarity(idx) default_ISA_polarity(idx)
-static int MPBIOS_polarity(int idx)
+static int irq_polarity(int idx)
{
int bus = mp_irqs[idx].srcbus;
int polarity;
return polarity;
}
-static int MPBIOS_trigger(int idx)
+static int irq_trigger(int idx)
{
int bus = mp_irqs[idx].srcbus;
int trigger;
return trigger;
}
-static inline int irq_polarity(int idx)
-{
- return MPBIOS_polarity(idx);
-}
-
-static inline int irq_trigger(int idx)
-{
- return MPBIOS_trigger(idx);
-}
-
static int pin_2_irq(int idx, int apic, int pin)
{
int irq;
raw_spin_lock(&vector_lock);
/* Mark the inuse vectors */
for_each_active_irq(irq) {
- cfg = get_irq_chip_data(irq);
+ cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
/*
static struct irq_chip ioapic_chip;
static struct irq_chip ir_ioapic_chip;
-#define IOAPIC_AUTO -1
-#define IOAPIC_EDGE 0
-#define IOAPIC_LEVEL 1
-
#ifdef CONFIG_X86_32
static inline int IO_APIC_irq_trigger(int irq)
{
}
#endif
-static void ioapic_register_intr(unsigned int irq, unsigned long trigger)
+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)
+ trigger == IOAPIC_LEVEL) {
irq_set_status_flags(irq, IRQ_LEVEL);
- else
+ fasteoi = true;
+ } else {
irq_clear_status_flags(irq, IRQ_LEVEL);
+ fasteoi = false;
+ }
- if (irq_remapped(get_irq_chip_data(irq))) {
+ if (irq_remapped(cfg)) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- if (trigger)
- set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
- handle_fasteoi_irq,
- "fasteoi");
- else
- set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
- handle_edge_irq, "edge");
- return;
+ chip = &ir_ioapic_chip;
+ fasteoi = trigger != 0;
}
- if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
- trigger == IOAPIC_LEVEL)
- set_irq_chip_and_handler_name(irq, &ioapic_chip,
- handle_fasteoi_irq,
- "fasteoi");
- else
- set_irq_chip_and_handler_name(irq, &ioapic_chip,
- handle_edge_irq, "edge");
+ hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
+ irq_set_chip_and_handler_name(irq, chip, hdl,
+ fasteoi ? "fasteoi" : "edge");
}
static int setup_ioapic_entry(int apic_id, int irq,
return;
}
- ioapic_register_intr(irq, trigger);
+ ioapic_register_intr(irq, cfg, trigger);
if (irq < legacy_pic->nr_legacy_irqs)
legacy_pic->mask(irq);
DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
} mp_ioapic_routing[MAX_IO_APICS];
-static void __init setup_IO_APIC_irqs(void)
+static bool __init io_apic_pin_not_connected(int idx, int apic_id, int pin)
{
- int apic_id, pin, idx, irq, notcon = 0;
- int node = cpu_to_node(0);
- struct irq_cfg *cfg;
+ if (idx != -1)
+ return false;
- apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+ apic_printk(APIC_VERBOSE, KERN_DEBUG " apic %d pin %d not connected\n",
+ mp_ioapics[apic_id].apicid, pin);
+ return true;
+}
+
+static void __init __io_apic_setup_irqs(unsigned int apic_id)
+{
+ int idx, node = cpu_to_node(0);
+ struct io_apic_irq_attr attr;
+ unsigned int pin, irq;
- for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
idx = find_irq_entry(apic_id, pin, mp_INT);
- if (idx == -1) {
- if (!notcon) {
- notcon = 1;
- apic_printk(APIC_VERBOSE,
- KERN_DEBUG " %d-%d",
- mp_ioapics[apic_id].apicid, pin);
- } else
- apic_printk(APIC_VERBOSE, " %d-%d",
- mp_ioapics[apic_id].apicid, pin);
+ if (io_apic_pin_not_connected(idx, apic_id, pin))
continue;
- }
- if (notcon) {
- apic_printk(APIC_VERBOSE,
- " (apicid-pin) not connected\n");
- notcon = 0;
- }
irq = pin_2_irq(idx, apic_id, pin);
* installed and if it returns 1:
*/
if (apic->multi_timer_check &&
- apic->multi_timer_check(apic_id, irq))
+ apic->multi_timer_check(apic_id, irq))
continue;
- cfg = alloc_irq_and_cfg_at(irq, node);
- if (!cfg)
- continue;
+ set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx),
+ irq_polarity(idx));
- add_pin_to_irq_node(cfg, node, apic_id, pin);
- /*
- * don't mark it in pin_programmed, so later acpi could
- * set it correctly when irq < 16
- */
- setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx),
- irq_polarity(idx));
+ io_apic_setup_irq_pin(irq, node, &attr);
}
+}
- if (notcon)
- apic_printk(APIC_VERBOSE,
- " (apicid-pin) not connected\n");
+static void __init setup_IO_APIC_irqs(void)
+{
+ unsigned int apic_id;
+
+ apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
+
+ for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
+ __io_apic_setup_irqs(apic_id);
}
/*
void setup_IO_APIC_irq_extra(u32 gsi)
{
int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
- struct irq_cfg *cfg;
+ struct io_apic_irq_attr attr;
/*
* Convert 'gsi' to 'ioapic.pin'.
if (apic_id == 0 || irq < NR_IRQS_LEGACY)
return;
- cfg = alloc_irq_and_cfg_at(irq, node);
- if (!cfg)
- return;
-
- add_pin_to_irq_node(cfg, node, apic_id, pin);
+ set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx),
+ irq_polarity(idx));
- if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
- pr_debug("Pin %d-%d already programmed\n",
- mp_ioapics[apic_id].apicid, pin);
- return;
- }
- set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
-
- setup_ioapic_irq(apic_id, pin, irq, cfg,
- irq_trigger(idx), irq_polarity(idx));
+ io_apic_setup_irq_pin_once(irq, node, &attr);
}
/*
* The timer IRQ doesn't have to know that behind the
* scene we may have a 8259A-master in AEOI mode ...
*/
- set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
+ irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
+ "edge");
/*
* Add it to the IO-APIC irq-routing table:
for_each_active_irq(irq) {
struct irq_pin_list *entry;
- cfg = get_irq_chip_data(irq);
+ cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
entry = cfg->irq_2_pin;
void irq_force_complete_move(int irq)
{
- struct irq_cfg *cfg = get_irq_chip_data(irq);
+ struct irq_cfg *cfg = irq_get_chip_data(irq);
if (!cfg)
return;
static void ack_apic_edge(struct irq_data *data)
{
irq_complete_move(data->chip_data);
- move_native_irq(data->irq);
+ irq_move_irq(data);
ack_APIC_irq();
}
irq_complete_move(cfg);
#ifdef CONFIG_GENERIC_PENDING_IRQ
/* If we are moving the irq we need to mask it */
- if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
+ if (unlikely(irqd_is_setaffinity_pending(data))) {
do_unmask_irq = 1;
mask_ioapic(cfg);
}
* and you can go talk to the chipset vendor about it.
*/
if (!io_apic_level_ack_pending(cfg))
- move_masked_irq(irq);
+ irq_move_masked_irq(data);
unmask_ioapic(cfg);
}
}
* 0x80, because int 0x80 is hm, kind of importantish. ;)
*/
for_each_active_irq(irq) {
- cfg = get_irq_chip_data(irq);
+ cfg = irq_get_chip_data(irq);
if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
/*
* Hmm.. We don't have an entry for this,
legacy_pic->make_irq(irq);
else
/* Strange. Oh, well.. */
- set_irq_chip(irq, &no_irq_chip);
+ irq_set_chip(irq, &no_irq_chip);
}
}
}
static void lapic_register_intr(int irq)
{
irq_clear_status_flags(irq, IRQ_LEVEL);
- set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+ irq_set_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
"edge");
}
*/
static inline void __init check_timer(void)
{
- struct irq_cfg *cfg = get_irq_chip_data(0);
+ struct irq_cfg *cfg = irq_get_chip_data(0);
int node = cpu_to_node(0);
int apic1, pin1, apic2, pin2;
unsigned long flags;
raw_spin_unlock_irqrestore(&vector_lock, flags);
if (ret) {
- set_irq_chip_data(irq, cfg);
+ irq_set_chip_data(irq, cfg);
irq_clear_status_flags(irq, IRQ_NOREQUEST);
} else {
free_irq_at(irq, cfg);
void destroy_irq(unsigned int irq)
{
- struct irq_cfg *cfg = get_irq_chip_data(irq);
+ struct irq_cfg *cfg = irq_get_chip_data(irq);
unsigned long flags;
irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
- if (irq_remapped(get_irq_chip_data(irq))) {
+ if (irq_remapped(cfg)) {
struct irte irte;
int ir_index;
u16 sub_handle;
static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
{
+ struct irq_chip *chip = &msi_chip;
struct msi_msg msg;
int ret;
if (ret < 0)
return ret;
- set_irq_msi(irq, msidesc);
+ irq_set_msi_desc(irq, msidesc);
write_msi_msg(irq, &msg);
- if (irq_remapped(get_irq_chip_data(irq))) {
+ if (irq_remapped(irq_get_chip_data(irq))) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
- } else
- set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+ chip = &msi_ir_chip;
+ }
+
+ irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq);
if (ret < 0)
return ret;
dmar_msi_write(irq, &msg);
- set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
+ irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
+ "edge");
return 0;
}
#endif
int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
{
+ struct irq_chip *chip = &hpet_msi_type;
struct msi_msg msg;
int ret;
if (ret < 0)
return ret;
- hpet_msi_write(get_irq_data(irq), &msg);
+ hpet_msi_write(irq_get_handler_data(irq), &msg);
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- if (irq_remapped(get_irq_chip_data(irq)))
- set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
- handle_edge_irq, "edge");
- else
- set_irq_chip_and_handler_name(irq, &hpet_msi_type,
- handle_edge_irq, "edge");
+ if (irq_remapped(irq_get_chip_data(irq)))
+ chip = &ir_hpet_msi_type;
+ irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
return 0;
}
#endif
write_ht_irq_msg(irq, &msg);
- set_irq_chip_and_handler_name(irq, &ht_irq_chip,
+ irq_set_chip_and_handler_name(irq, &ht_irq_chip,
handle_edge_irq, "edge");
dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq);
}
#endif /* CONFIG_HT_IRQ */
-int __init io_apic_get_redir_entries (int ioapic)
+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(attr->ioapic, attr->ioapic_pin, irq, cfg,
+ attr->trigger, attr->polarity);
+ return ret;
+}
+
+static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
+ struct io_apic_irq_attr *attr)
+{
+ unsigned int id = attr->ioapic, pin = attr->ioapic_pin;
+ int ret;
+
+ /* Avoid redundant programming */
+ if (test_bit(pin, mp_ioapic_routing[id].pin_programmed)) {
+ pr_debug("Pin %d-%d already programmed\n",
+ mp_ioapics[id].apicid, pin);
+ return 0;
+ }
+ ret = io_apic_setup_irq_pin(irq, node, attr);
+ if (!ret)
+ set_bit(pin, mp_ioapic_routing[id].pin_programmed);
+ return ret;
+}
+
+static int __init io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
}
#endif
-static int __io_apic_set_pci_routing(struct device *dev, int irq,
- struct io_apic_irq_attr *irq_attr)
+int io_apic_set_pci_routing(struct device *dev, int irq,
+ struct io_apic_irq_attr *irq_attr)
{
- struct irq_cfg *cfg;
int node;
- int ioapic, pin;
- int trigger, polarity;
- ioapic = irq_attr->ioapic;
if (!IO_APIC_IRQ(irq)) {
apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
- ioapic);
+ irq_attr->ioapic);
return -EINVAL;
}
- if (dev)
- node = dev_to_node(dev);
- else
- node = cpu_to_node(0);
+ node = dev ? dev_to_node(dev) : cpu_to_node(0);
- cfg = alloc_irq_and_cfg_at(irq, node);
- if (!cfg)
- return 0;
-
- pin = irq_attr->ioapic_pin;
- trigger = irq_attr->trigger;
- polarity = irq_attr->polarity;
-
- /*
- * IRQs < 16 are already in the irq_2_pin[] map
- */
- if (irq >= legacy_pic->nr_legacy_irqs) {
- if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) {
- printk(KERN_INFO "can not add pin %d for irq %d\n",
- pin, irq);
- return 0;
- }
- }
-
- setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity);
-
- return 0;
-}
-
-int io_apic_set_pci_routing(struct device *dev, int irq,
- struct io_apic_irq_attr *irq_attr)
-{
- int ioapic, pin;
- /*
- * Avoid pin reprogramming. PRTs typically include entries
- * with redundant pin->gsi mappings (but unique PCI devices);
- * we only program the IOAPIC on the first.
- */
- ioapic = irq_attr->ioapic;
- pin = irq_attr->ioapic_pin;
- if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
- pr_debug("Pin %d-%d already programmed\n",
- mp_ioapics[ioapic].apicid, pin);
- return 0;
- }
- set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
-
- return __io_apic_set_pci_routing(dev, irq, irq_attr);
-}
-
-u8 __init io_apic_unique_id(u8 id)
-{
-#ifdef CONFIG_X86_32
- if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
- !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
- return io_apic_get_unique_id(nr_ioapics, id);
- else
- return id;
-#else
- int i;
- DECLARE_BITMAP(used, 256);
-
- bitmap_zero(used, 256);
- for (i = 0; i < nr_ioapics; i++) {
- struct mpc_ioapic *ia = &mp_ioapics[i];
- __set_bit(ia->apicid, used);
- }
- if (!test_bit(id, used))
- return id;
- return find_first_zero_bit(used, 256);
-#endif
+ return io_apic_setup_irq_pin_once(irq, node, irq_attr);
}
#ifdef CONFIG_X86_32
-int __init io_apic_get_unique_id(int ioapic, int apic_id)
+static int __init io_apic_get_unique_id(int ioapic, int apic_id)
{
union IO_APIC_reg_00 reg_00;
static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
return apic_id;
}
+
+static u8 __init io_apic_unique_id(u8 id)
+{
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+ !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+ return io_apic_get_unique_id(nr_ioapics, id);
+ else
+ return id;
+}
+#else
+static u8 __init io_apic_unique_id(u8 id)
+{
+ int i;
+ DECLARE_BITMAP(used, 256);
+
+ bitmap_zero(used, 256);
+ for (i = 0; i < nr_ioapics; i++) {
+ struct mpc_ioapic *ia = &mp_ioapics[i];
+ __set_bit(ia->apicid, used);
+ }
+ if (!test_bit(id, used))
+ return id;
+ return find_first_zero_bit(used, 256);
+}
#endif
-int __init io_apic_get_version(int ioapic)
+static int __init io_apic_get_version(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
void __init setup_ioapic_dest(void)
{
int pin, ioapic, irq, irq_entry;
- struct irq_desc *desc;
const struct cpumask *mask;
+ struct irq_data *idata;
if (skip_ioapic_setup == 1)
return;
if ((ioapic > 0) && (irq > 16))
continue;
- desc = irq_to_desc(irq);
+ idata = irq_get_irq_data(irq);
/*
* Honour affinities which have been set in early boot
*/
- if (desc->status &
- (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
- mask = desc->irq_data.affinity;
+ if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata))
+ mask = idata->affinity;
else
mask = apic->target_cpus();
if (intr_remapping_enabled)
- ir_ioapic_set_affinity(&desc->irq_data, mask, false);
+ ir_ioapic_set_affinity(idata, mask, false);
else
- ioapic_set_affinity(&desc->irq_data, mask, false);
+ ioapic_set_affinity(idata, mask, false);
}
}
{
int i = 0;
+ if (nr_ioapics == 0)
+ return -1;
+
/* Find the IOAPIC that manages this GSI. */
for (i = 0; i < nr_ioapics; i++) {
if ((gsi >= mp_gsi_routing[i].gsi_base)
return gsi - mp_gsi_routing[ioapic].gsi_base;
}
-static int bad_ioapic(unsigned long address)
+static __init int bad_ioapic(unsigned long address)
{
if (nr_ioapics >= MAX_IO_APICS) {
printk(KERN_WARNING "WARING: Max # of I/O APICs (%d) exceeded "
/* Enable IOAPIC early just for system timer */
void __init pre_init_apic_IRQ0(void)
{
- struct irq_cfg *cfg;
+ struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
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
- /* Make sure the irq descriptor is set up */
- cfg = alloc_irq_and_cfg_at(0, 0);
-
setup_local_APIC();
- add_pin_to_irq_node(cfg, 0, 0, 0);
- set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
-
- setup_ioapic_irq(0, 0, 0, cfg, 0, 0);
+ io_apic_setup_irq_pin(0, 0, &attr);
+ irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
+ "edge");
}
+/*
+ * Generate definitions needed by assembly language modules.
+ * This code generates raw asm output which is post-processed to extract
+ * and format the required data.
+ */
+#define COMPILE_OFFSETS
+
+#include <linux/crypto.h>
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/hardirq.h>
+#include <linux/suspend.h>
+#include <linux/kbuild.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+#include <asm/sigframe.h>
+#include <asm/bootparam.h>
+#include <asm/suspend.h>
+
+#ifdef CONFIG_XEN
+#include <xen/interface/xen.h>
+#endif
+
#ifdef CONFIG_X86_32
# include "asm-offsets_32.c"
#else
# include "asm-offsets_64.c"
#endif
+
+void common(void) {
+ BLANK();
+ OFFSET(TI_flags, thread_info, flags);
+ OFFSET(TI_status, thread_info, status);
+ OFFSET(TI_addr_limit, thread_info, addr_limit);
+ OFFSET(TI_preempt_count, thread_info, preempt_count);
+
+ BLANK();
+ OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
+
+ BLANK();
+ OFFSET(pbe_address, pbe, address);
+ OFFSET(pbe_orig_address, pbe, orig_address);
+ OFFSET(pbe_next, pbe, next);
+
+#ifdef CONFIG_PARAVIRT
+ BLANK();
+ OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
+ OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
+ OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
+ 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);
+ OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+ OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
+ OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
+#endif
+
+#ifdef CONFIG_XEN
+ BLANK();
+ OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
+ OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
+#endif
+
+ BLANK();
+ OFFSET(BP_scratch, boot_params, scratch);
+ OFFSET(BP_loadflags, boot_params, hdr.loadflags);
+ OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
+ OFFSET(BP_version, boot_params, hdr.version);
+ OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
+}
-/*
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed
- * to extract and format the required data.
- */
-
-#include <linux/crypto.h>
-#include <linux/sched.h>
-#include <linux/signal.h>
-#include <linux/personality.h>
-#include <linux/suspend.h>
-#include <linux/kbuild.h>
#include <asm/ucontext.h>
-#include <asm/sigframe.h>
-#include <asm/pgtable.h>
-#include <asm/fixmap.h>
-#include <asm/processor.h>
-#include <asm/thread_info.h>
-#include <asm/bootparam.h>
-#include <asm/elf.h>
-#include <asm/suspend.h>
-
-#include <xen/interface/xen.h>
#include <linux/lguest.h>
#include "../../../drivers/lguest/lg.h"
OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
BLANK();
- OFFSET(TI_task, thread_info, task);
- OFFSET(TI_exec_domain, thread_info, exec_domain);
- OFFSET(TI_flags, thread_info, flags);
- OFFSET(TI_status, thread_info, status);
- OFFSET(TI_preempt_count, thread_info, preempt_count);
- OFFSET(TI_addr_limit, thread_info, addr_limit);
- OFFSET(TI_restart_block, thread_info, restart_block);
OFFSET(TI_sysenter_return, thread_info, sysenter_return);
OFFSET(TI_cpu, thread_info, cpu);
BLANK();
- OFFSET(GDS_size, desc_ptr, size);
- OFFSET(GDS_address, desc_ptr, address);
- 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(EXEC_DOMAIN_handler, exec_domain, handler);
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
BLANK();
- OFFSET(pbe_address, pbe, address);
- OFFSET(pbe_orig_address, pbe, orig_address);
- OFFSET(pbe_next, pbe, next);
-
/* Offset from the sysenter stack to tss.sp0 */
DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
sizeof(struct tss_struct));
- DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
- DEFINE(PAGE_SHIFT_asm, PAGE_SHIFT);
- DEFINE(THREAD_SIZE_asm, THREAD_SIZE);
-
- OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
-
-#ifdef CONFIG_PARAVIRT
- BLANK();
- OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
- OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
- OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
- 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);
- OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
- OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
-#endif
-
-#ifdef CONFIG_XEN
- BLANK();
- OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
- OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
-#endif
-
#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
BLANK();
OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode);
OFFSET(LGUEST_PAGES_regs, lguest_pages, regs);
#endif
-
- BLANK();
- OFFSET(BP_scratch, boot_params, scratch);
- OFFSET(BP_loadflags, boot_params, hdr.loadflags);
- OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
- OFFSET(BP_version, boot_params, hdr.version);
- OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
}
-/*
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed to extract
- * and format the required data.
- */
-#define COMPILE_OFFSETS
-
-#include <linux/crypto.h>
-#include <linux/sched.h>
-#include <linux/stddef.h>
-#include <linux/errno.h>
-#include <linux/hardirq.h>
-#include <linux/suspend.h>
-#include <linux/kbuild.h>
-#include <asm/processor.h>
-#include <asm/segment.h>
-#include <asm/thread_info.h>
#include <asm/ia32.h>
-#include <asm/bootparam.h>
-#include <asm/suspend.h>
-
-#include <xen/interface/xen.h>
-
-#include <asm/sigframe.h>
#define __NO_STUBS 1
#undef __SYSCALL
int main(void)
{
-#define ENTRY(entry) DEFINE(tsk_ ## entry, offsetof(struct task_struct, entry))
- ENTRY(state);
- ENTRY(flags);
- ENTRY(pid);
- BLANK();
-#undef ENTRY
-#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry))
- ENTRY(flags);
- ENTRY(addr_limit);
- ENTRY(preempt_count);
- ENTRY(status);
-#ifdef CONFIG_IA32_EMULATION
- ENTRY(sysenter_return);
-#endif
- BLANK();
-#undef ENTRY
#ifdef CONFIG_PARAVIRT
- BLANK();
- OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
- OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
- OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
- OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
- OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame);
- OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32);
OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
- OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
- OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
+ BLANK();
#endif
-
#ifdef CONFIG_IA32_EMULATION
-#define ENTRY(entry) DEFINE(IA32_SIGCONTEXT_ ## entry, offsetof(struct sigcontext_ia32, entry))
+ 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(ip);
BLANK();
#undef ENTRY
- DEFINE(IA32_RT_SIGFRAME_sigcontext,
- offsetof (struct rt_sigframe_ia32, uc.uc_mcontext));
+
+ OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
BLANK();
#endif
- DEFINE(pbe_address, offsetof(struct pbe, address));
- DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
- DEFINE(pbe_next, offsetof(struct pbe, next));
- BLANK();
-#define ENTRY(entry) DEFINE(pt_regs_ ## entry, offsetof(struct pt_regs, entry))
+
+#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
ENTRY(bx);
ENTRY(bx);
ENTRY(cx);
ENTRY(flags);
BLANK();
#undef ENTRY
-#define ENTRY(entry) DEFINE(saved_context_ ## entry, offsetof(struct saved_context, entry))
+
+#define ENTRY(entry) OFFSET(saved_context_ ## entry, saved_context, entry)
ENTRY(cr0);
ENTRY(cr2);
ENTRY(cr3);
ENTRY(cr8);
BLANK();
#undef ENTRY
- DEFINE(TSS_ist, offsetof(struct tss_struct, x86_tss.ist));
- BLANK();
- DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx));
- BLANK();
- DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
+ OFFSET(TSS_ist, tss_struct, x86_tss.ist);
BLANK();
- OFFSET(BP_scratch, boot_params, scratch);
- OFFSET(BP_loadflags, boot_params, hdr.loadflags);
- OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
- OFFSET(BP_version, boot_params, hdr.version);
- OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
- BLANK();
- DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
-#ifdef CONFIG_XEN
- BLANK();
- OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
- OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
-#undef ENTRY
-#endif
+ DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
+
return 0;
}
addr += size;
}
- printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
- num_scan_areas);
+ if (num_scan_areas)
+ printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas);
}
{
check_for_bios_corruption();
schedule_delayed_work(&bios_check_work,
- round_jiffies_relative(corruption_check_period*HZ));
+ round_jiffies_relative(corruption_check_period*HZ));
}
static int start_periodic_check_for_corruption(void)
{
- if (!memory_corruption_check || corruption_check_period == 0)
+ if (!num_scan_areas || !memory_corruption_check || corruption_check_period == 0)
return 0;
printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
const struct cpu_dev *const *cdev;
int count = 0;
-#ifdef PROCESSOR_SELECT
+#ifdef CONFIG_PROCESSOR_SELECT
printk(KERN_INFO "KERNEL supported cpus:\n");
#endif
cpu_devs[count] = cpudev;
count++;
-#ifdef PROCESSOR_SELECT
+#ifdef CONFIG_PROCESSOR_SELECT
{
unsigned int j;
{
if (c->x86 == 0x06) {
if (cpu_has(c, X86_FEATURE_EST))
- printk(KERN_WARNING PFX "Warning: EST-capable CPU "
- "detected. The acpi-cpufreq module offers "
- "voltage scaling in addition of frequency "
+ printk_once(KERN_WARNING PFX "Warning: EST-capable "
+ "CPU detected. The acpi-cpufreq module offers "
+ "voltage scaling in addition to frequency "
"scaling. You should use that instead of "
"p4-clockmod, if possible.\n");
switch (c->x86_model) {
cmd_incomplete:
iowrite16(0, &pcch_hdr->status);
spin_unlock(&pcc_lock);
- return -EINVAL;
+ return 0;
}
static int pcc_cpufreq_target(struct cpufreq_policy *policy,
static int __cpuinit powernowk8_init(void)
{
unsigned int i, supported_cpus = 0, cpu;
+ int rv;
for_each_online_cpu(i) {
int rc;
cpb_capable = true;
- register_cpu_notifier(&cpb_nb);
-
msrs = msrs_alloc();
if (!msrs) {
printk(KERN_ERR "%s: Error allocating msrs!\n", __func__);
return -ENOMEM;
}
+ register_cpu_notifier(&cpb_nb);
+
rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
for_each_cpu(cpu, cpu_online_mask) {
(cpb_enabled ? "on" : "off"));
}
- return cpufreq_register_driver(&cpufreq_amd64_driver);
+ rv = cpufreq_register_driver(&cpufreq_amd64_driver);
+ if (rv < 0 && boot_cpu_has(X86_FEATURE_CPB)) {
+ unregister_cpu_notifier(&cpb_nb);
+ msrs_free(msrs);
+ msrs = NULL;
+ }
+ return rv;
}
/* driver entry point for term */
struct cpuinfo_x86 *c = &cpu_data(cpu);
if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
- for_each_cpu(i, c->llc_shared_map) {
+ for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
if (!per_cpu(ici_cpuid4_info, i))
continue;
this_leaf = CPUID4_INFO_IDX(i, index);
- for_each_cpu(sibling, c->llc_shared_map) {
+ for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
if (!cpu_online(sibling))
continue;
set_bit(sibling, this_leaf->shared_cpu_map);
int i, err = 0;
struct threshold_bank *b = NULL;
char name[32];
-#ifdef CONFIG_SMP
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-#endif
sprintf(name, "threshold_bank%i", bank);
#ifdef CONFIG_SMP
if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
- i = cpumask_first(c->llc_shared_map);
+ i = cpumask_first(cpu_llc_shared_mask(cpu));
/* first core not up yet */
if (cpu_data(i).cpu_core_id)
if (err)
goto out;
- cpumask_copy(b->cpus, c->llc_shared_map);
+ cpumask_copy(b->cpus, cpu_llc_shared_mask(cpu));
per_cpu(threshold_banks, cpu)[bank] = b;
goto out;
#include <asm/stacktrace.h>
#include <asm/nmi.h>
#include <asm/compat.h>
+#include <asm/smp.h>
#if 0
#undef wrmsrl
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
+struct intel_percore;
+
#define MAX_LBR_ENTRIES 16
struct cpu_hw_events {
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
+ /*
+ * Intel percore register state.
+ * Coordinate shared resources between HT threads.
+ */
+ int percore_used; /* Used by this CPU? */
+ struct intel_percore *per_core;
+
/*
* AMD specific bits
*/
/*
* Constraint on the Event code + UMask
*/
-#define PEBS_EVENT_CONSTRAINT(c, n) \
+#define INTEL_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
+#define PEBS_EVENT_CONSTRAINT(c, n) \
+ INTEL_UEVENT_CONSTRAINT(c, n)
#define EVENT_CONSTRAINT_END \
EVENT_CONSTRAINT(0, 0, 0)
#define for_each_event_constraint(e, c) \
for ((e) = (c); (e)->weight; (e)++)
+/*
+ * Extra registers for specific events.
+ * Some events need large masks and require external MSRs.
+ * Define a mapping to these extra registers.
+ */
+struct extra_reg {
+ unsigned int event;
+ unsigned int msr;
+ u64 config_mask;
+ u64 valid_mask;
+};
+
+#define EVENT_EXTRA_REG(e, ms, m, vm) { \
+ .event = (e), \
+ .msr = (ms), \
+ .config_mask = (m), \
+ .valid_mask = (vm), \
+ }
+#define INTEL_EVENT_EXTRA_REG(event, msr, vm) \
+ EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm)
+#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0)
+
union perf_capabilities {
struct {
u64 lbr_format : 6;
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
struct event_constraint *event_constraints;
+ struct event_constraint *percore_constraints;
void (*quirks)(void);
int perfctr_second_write;
*/
unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */
int lbr_nr; /* hardware stack size */
+
+ /*
+ * Extra registers for events
+ */
+ struct extra_reg *extra_regs;
};
static struct x86_pmu x86_pmu __read_mostly;
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
+static u64 __read_mostly hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX];
/*
* Propagate event elapsed time into the generic event.
*/
again:
prev_raw_count = local64_read(&hwc->prev_count);
- rdmsrl(hwc->event_base + idx, new_raw_count);
+ rdmsrl(hwc->event_base, new_raw_count);
if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
new_raw_count) != prev_raw_count)
return new_raw_count;
}
+/* using X86_FEATURE_PERFCTR_CORE to later implement ALTERNATIVE() here */
+static inline int x86_pmu_addr_offset(int index)
+{
+ if (boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
+ return index << 1;
+ return index;
+}
+
+static inline unsigned int x86_pmu_config_addr(int index)
+{
+ return x86_pmu.eventsel + x86_pmu_addr_offset(index);
+}
+
+static inline unsigned int x86_pmu_event_addr(int index)
+{
+ return x86_pmu.perfctr + x86_pmu_addr_offset(index);
+}
+
+/*
+ * Find and validate any extra registers to set up.
+ */
+static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
+{
+ struct extra_reg *er;
+
+ event->hw.extra_reg = 0;
+ event->hw.extra_config = 0;
+
+ if (!x86_pmu.extra_regs)
+ return 0;
+
+ for (er = x86_pmu.extra_regs; er->msr; er++) {
+ if (er->event != (config & er->config_mask))
+ continue;
+ if (event->attr.config1 & ~er->valid_mask)
+ return -EINVAL;
+ event->hw.extra_reg = er->msr;
+ event->hw.extra_config = event->attr.config1;
+ break;
+ }
+ return 0;
+}
+
static atomic_t active_events;
static DEFINE_MUTEX(pmc_reserve_mutex);
int i;
for (i = 0; i < x86_pmu.num_counters; i++) {
- if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
+ if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
goto perfctr_fail;
}
for (i = 0; i < x86_pmu.num_counters; i++) {
- if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
+ if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
goto eventsel_fail;
}
eventsel_fail:
for (i--; i >= 0; i--)
- release_evntsel_nmi(x86_pmu.eventsel + i);
+ release_evntsel_nmi(x86_pmu_config_addr(i));
i = x86_pmu.num_counters;
perfctr_fail:
for (i--; i >= 0; i--)
- release_perfctr_nmi(x86_pmu.perfctr + i);
+ release_perfctr_nmi(x86_pmu_event_addr(i));
return false;
}
int i;
for (i = 0; i < x86_pmu.num_counters; i++) {
- release_perfctr_nmi(x86_pmu.perfctr + i);
- release_evntsel_nmi(x86_pmu.eventsel + i);
+ release_perfctr_nmi(x86_pmu_event_addr(i));
+ release_evntsel_nmi(x86_pmu_config_addr(i));
}
}
* complain and bail.
*/
for (i = 0; i < x86_pmu.num_counters; i++) {
- reg = x86_pmu.eventsel + i;
+ reg = x86_pmu_config_addr(i);
ret = rdmsrl_safe(reg, &val);
if (ret)
goto msr_fail;
* that don't trap on the MSR access and always return 0s.
*/
val = 0xabcdUL;
- ret = checking_wrmsrl(x86_pmu.perfctr, val);
- ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
+ ret = checking_wrmsrl(x86_pmu_event_addr(0), val);
+ ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new);
if (ret || val != val_new)
goto msr_fail;
}
static inline int
-set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
+set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
{
+ struct perf_event_attr *attr = &event->attr;
unsigned int cache_type, cache_op, cache_result;
u64 config, val;
return -EINVAL;
hwc->config |= val;
-
- return 0;
+ attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result];
+ return x86_pmu_extra_regs(val, event);
}
static int x86_setup_perfctr(struct perf_event *event)
}
if (attr->type == PERF_TYPE_RAW)
- return 0;
+ return x86_pmu_extra_regs(event->attr.config, event);
if (attr->type == PERF_TYPE_HW_CACHE)
- return set_ext_hw_attr(hwc, attr);
+ return set_ext_hw_attr(hwc, event);
if (attr->config >= x86_pmu.max_events)
return -EINVAL;
if (!test_bit(idx, cpuc->active_mask))
continue;
- rdmsrl(x86_pmu.eventsel + idx, val);
+ rdmsrl(x86_pmu_config_addr(idx), val);
if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
continue;
val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
- wrmsrl(x86_pmu.eventsel + idx, val);
+ wrmsrl(x86_pmu_config_addr(idx), val);
}
}
x86_pmu.disable_all();
}
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
+ u64 enable_mask)
+{
+ if (hwc->extra_reg)
+ wrmsrl(hwc->extra_reg, hwc->extra_config);
+ wrmsrl(hwc->config_base, hwc->config | enable_mask);
+}
+
static void x86_pmu_enable_all(int added)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
int idx;
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- struct perf_event *event = cpuc->events[idx];
- u64 val;
+ struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
if (!test_bit(idx, cpuc->active_mask))
continue;
- val = event->hw.config;
- val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- wrmsrl(x86_pmu.eventsel + idx, val);
+ __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
}
hwc->event_base = 0;
} else if (hwc->idx >= X86_PMC_IDX_FIXED) {
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- /*
- * We set it so that event_base + idx in wrmsr/rdmsr maps to
- * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
- */
- hwc->event_base =
- MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
+ hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0;
} else {
- hwc->config_base = x86_pmu.eventsel;
- hwc->event_base = x86_pmu.perfctr;
+ hwc->config_base = x86_pmu_config_addr(hwc->idx);
+ hwc->event_base = x86_pmu_event_addr(hwc->idx);
}
}
x86_pmu.enable_all(added);
}
-static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
- u64 enable_mask)
-{
- wrmsrl(hwc->config_base + hwc->idx, hwc->config | enable_mask);
-}
-
static inline void x86_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base + hwc->idx, hwc->config);
+ wrmsrl(hwc->config_base, hwc->config);
}
static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
*/
local64_set(&hwc->prev_count, (u64)-left);
- wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask);
+ wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
/*
* Due to erratum on certan cpu we need
* is updated properly
*/
if (x86_pmu.perfctr_second_write) {
- wrmsrl(hwc->event_base + idx,
+ wrmsrl(hwc->event_base,
(u64)(-left) & x86_pmu.cntval_mask);
}
pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
- rdmsrl(x86_pmu.perfctr + idx, pmc_count);
+ rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
+ rdmsrl(x86_pmu_event_addr(idx), pmc_count);
prev_left = per_cpu(pmc_prev_left[idx], cpu);
pr_info("no hardware sampling interrupt available.\n");
}
-int __init init_hw_perf_events(void)
+static int __init init_hw_perf_events(void)
{
struct event_constraint *c;
int err;
return ret;
}
-int x86_pmu_event_init(struct perf_event *event)
+static int x86_pmu_event_init(struct perf_event *event)
{
struct pmu *tmp;
int err;
/*
* AMD64 events are detected based on their event codes.
*/
+static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
+{
+ return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff);
+}
+
static inline int amd_is_nb_event(struct hw_perf_event *hwc)
{
return (hwc->config & 0xe0) == 0xe0;
.cpu_dead = amd_pmu_cpu_dead,
};
+/* AMD Family 15h */
+
+#define AMD_EVENT_TYPE_MASK 0x000000F0ULL
+
+#define AMD_EVENT_FP 0x00000000ULL ... 0x00000010ULL
+#define AMD_EVENT_LS 0x00000020ULL ... 0x00000030ULL
+#define AMD_EVENT_DC 0x00000040ULL ... 0x00000050ULL
+#define AMD_EVENT_CU 0x00000060ULL ... 0x00000070ULL
+#define AMD_EVENT_IC_DE 0x00000080ULL ... 0x00000090ULL
+#define AMD_EVENT_EX_LS 0x000000C0ULL
+#define AMD_EVENT_DE 0x000000D0ULL
+#define AMD_EVENT_NB 0x000000E0ULL ... 0x000000F0ULL
+
+/*
+ * AMD family 15h event code/PMC mappings:
+ *
+ * type = event_code & 0x0F0:
+ *
+ * 0x000 FP PERF_CTL[5:3]
+ * 0x010 FP PERF_CTL[5:3]
+ * 0x020 LS PERF_CTL[5:0]
+ * 0x030 LS PERF_CTL[5:0]
+ * 0x040 DC PERF_CTL[5:0]
+ * 0x050 DC PERF_CTL[5:0]
+ * 0x060 CU PERF_CTL[2:0]
+ * 0x070 CU PERF_CTL[2:0]
+ * 0x080 IC/DE PERF_CTL[2:0]
+ * 0x090 IC/DE PERF_CTL[2:0]
+ * 0x0A0 ---
+ * 0x0B0 ---
+ * 0x0C0 EX/LS PERF_CTL[5:0]
+ * 0x0D0 DE PERF_CTL[2:0]
+ * 0x0E0 NB NB_PERF_CTL[3:0]
+ * 0x0F0 NB NB_PERF_CTL[3:0]
+ *
+ * Exceptions:
+ *
+ * 0x003 FP PERF_CTL[3]
+ * 0x00B FP PERF_CTL[3]
+ * 0x00D FP PERF_CTL[3]
+ * 0x023 DE PERF_CTL[2:0]
+ * 0x02D LS PERF_CTL[3]
+ * 0x02E LS PERF_CTL[3,0]
+ * 0x043 CU PERF_CTL[2:0]
+ * 0x045 CU PERF_CTL[2:0]
+ * 0x046 CU PERF_CTL[2:0]
+ * 0x054 CU PERF_CTL[2:0]
+ * 0x055 CU PERF_CTL[2:0]
+ * 0x08F IC PERF_CTL[0]
+ * 0x187 DE PERF_CTL[0]
+ * 0x188 DE PERF_CTL[0]
+ * 0x0DB EX PERF_CTL[5:0]
+ * 0x0DC LS PERF_CTL[5:0]
+ * 0x0DD LS PERF_CTL[5:0]
+ * 0x0DE LS PERF_CTL[5:0]
+ * 0x0DF LS PERF_CTL[5:0]
+ * 0x1D6 EX PERF_CTL[5:0]
+ * 0x1D8 EX PERF_CTL[5:0]
+ */
+
+static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0);
+static struct event_constraint amd_f15_PMC20 = EVENT_CONSTRAINT(0, 0x07, 0);
+static struct event_constraint amd_f15_PMC3 = EVENT_CONSTRAINT(0, 0x08, 0);
+static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT(0, 0x09, 0);
+static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
+static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
+
+static struct event_constraint *
+amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+ unsigned int event_code = amd_get_event_code(&event->hw);
+
+ switch (event_code & AMD_EVENT_TYPE_MASK) {
+ case AMD_EVENT_FP:
+ switch (event_code) {
+ case 0x003:
+ case 0x00B:
+ case 0x00D:
+ return &amd_f15_PMC3;
+ default:
+ return &amd_f15_PMC53;
+ }
+ case AMD_EVENT_LS:
+ case AMD_EVENT_DC:
+ case AMD_EVENT_EX_LS:
+ switch (event_code) {
+ case 0x023:
+ case 0x043:
+ case 0x045:
+ case 0x046:
+ case 0x054:
+ case 0x055:
+ return &amd_f15_PMC20;
+ case 0x02D:
+ return &amd_f15_PMC3;
+ case 0x02E:
+ return &amd_f15_PMC30;
+ default:
+ return &amd_f15_PMC50;
+ }
+ case AMD_EVENT_CU:
+ case AMD_EVENT_IC_DE:
+ case AMD_EVENT_DE:
+ switch (event_code) {
+ case 0x08F:
+ case 0x187:
+ case 0x188:
+ return &amd_f15_PMC0;
+ case 0x0DB ... 0x0DF:
+ case 0x1D6:
+ case 0x1D8:
+ return &amd_f15_PMC50;
+ default:
+ return &amd_f15_PMC20;
+ }
+ case AMD_EVENT_NB:
+ /* not yet implemented */
+ return &emptyconstraint;
+ default:
+ return &emptyconstraint;
+ }
+}
+
+static __initconst const struct x86_pmu amd_pmu_f15h = {
+ .name = "AMD Family 15h",
+ .handle_irq = x86_pmu_handle_irq,
+ .disable_all = x86_pmu_disable_all,
+ .enable_all = x86_pmu_enable_all,
+ .enable = x86_pmu_enable_event,
+ .disable = x86_pmu_disable_event,
+ .hw_config = amd_pmu_hw_config,
+ .schedule_events = x86_schedule_events,
+ .eventsel = MSR_F15H_PERF_CTL,
+ .perfctr = MSR_F15H_PERF_CTR,
+ .event_map = amd_pmu_event_map,
+ .max_events = ARRAY_SIZE(amd_perfmon_event_map),
+ .num_counters = 6,
+ .cntval_bits = 48,
+ .cntval_mask = (1ULL << 48) - 1,
+ .apic = 1,
+ /* use highest bit to detect overflow */
+ .max_period = (1ULL << 47) - 1,
+ .get_event_constraints = amd_get_event_constraints_f15h,
+ /* nortbridge counters not yet implemented: */
+#if 0
+ .put_event_constraints = amd_put_event_constraints,
+
+ .cpu_prepare = amd_pmu_cpu_prepare,
+ .cpu_starting = amd_pmu_cpu_starting,
+ .cpu_dead = amd_pmu_cpu_dead,
+#endif
+};
+
static __init int amd_pmu_init(void)
{
/* Performance-monitoring supported from K7 and later: */
if (boot_cpu_data.x86 < 6)
return -ENODEV;
- x86_pmu = amd_pmu;
+ /*
+ * If core performance counter extensions exists, it must be
+ * family 15h, otherwise fail. See x86_pmu_addr_offset().
+ */
+ switch (boot_cpu_data.x86) {
+ case 0x15:
+ if (!cpu_has_perfctr_core)
+ return -ENODEV;
+ x86_pmu = amd_pmu_f15h;
+ break;
+ default:
+ if (cpu_has_perfctr_core)
+ return -ENODEV;
+ x86_pmu = amd_pmu;
+ break;
+ }
/* Events are common for all AMDs */
memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
#ifdef CONFIG_CPU_SUP_INTEL
+#define MAX_EXTRA_REGS 2
+
+/*
+ * Per register state.
+ */
+struct er_account {
+ int ref; /* reference count */
+ unsigned int extra_reg; /* extra MSR number */
+ u64 extra_config; /* extra MSR config */
+};
+
+/*
+ * Per core state
+ * This used to coordinate shared registers for HT threads.
+ */
+struct intel_percore {
+ raw_spinlock_t lock; /* protect structure */
+ struct er_account regs[MAX_EXTRA_REGS];
+ int refcnt; /* number of threads */
+ unsigned core_id;
+};
+
/*
* Intel PerfMon, used on Core and later.
*/
EVENT_CONSTRAINT_END
};
+static struct extra_reg intel_nehalem_extra_regs[] =
+{
+ INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
+ EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_nehalem_percore_constraints[] =
+{
+ INTEL_EVENT_CONSTRAINT(0xb7, 0),
+ EVENT_CONSTRAINT_END
+};
+
static struct event_constraint intel_westmere_event_constraints[] =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
EVENT_CONSTRAINT_END
};
+static struct event_constraint intel_snb_event_constraints[] =
+{
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+ INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
+ INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */
+ INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */
+ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
+ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_westmere_extra_regs[] =
+{
+ INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
+ INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff),
+ EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_westmere_percore_constraints[] =
+{
+ INTEL_EVENT_CONSTRAINT(0xb7, 0),
+ INTEL_EVENT_CONSTRAINT(0xbb, 0),
+ EVENT_CONSTRAINT_END
+};
+
static struct event_constraint intel_gen_event_constraints[] =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
return intel_perfmon_event_map[hw_event];
}
+static __initconst const u64 snb_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0xf1d0, /* MEM_UOP_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPLACEMENT */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0xf2d0, /* MEM_UOP_RETIRED.STORES */
+ [ C(RESULT_MISS) ] = 0x0851, /* L1D.ALL_M_REPLACEMENT */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x024e, /* HW_PRE_REQ.DL1_MISS */
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0280, /* ICACHE.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(LL ) ] = {
+ /*
+ * TBD: Need Off-core Response Performance Monitoring support
+ */
+ [ C(OP_READ) ] = {
+ /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01bb,
+ },
+ [ C(OP_WRITE) ] = {
+ /* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01bb,
+ },
+ [ C(OP_PREFETCH) ] = {
+ /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01bb,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOP_RETIRED.ALL_LOADS */
+ [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.CAUSES_A_WALK */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOP_RETIRED.ALL_STORES */
+ [ C(RESULT_MISS) ] = 0x0149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x1085, /* ITLB_MISSES.STLB_HIT */
+ [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.CAUSES_A_WALK */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+ [ C(RESULT_MISS) ] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
static __initconst const u64 westmere_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
- [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
+ /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01bb,
},
+ /*
+ * Use RFO, not WRITEBACK, because a write miss would typically occur
+ * on RFO.
+ */
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
- [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
+ /* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
- [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
+ /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01bb,
},
},
[ C(DTLB) ] = {
},
};
+/*
+ * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
+ */
+
+#define DMND_DATA_RD (1 << 0)
+#define DMND_RFO (1 << 1)
+#define DMND_WB (1 << 3)
+#define PF_DATA_RD (1 << 4)
+#define PF_DATA_RFO (1 << 5)
+#define RESP_UNCORE_HIT (1 << 8)
+#define RESP_MISS (0xf600) /* non uncore hit */
+
+static __initconst const u64 nehalem_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
+ [ C(RESULT_MISS) ] = DMND_DATA_RD|RESP_MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
+ [ C(RESULT_MISS) ] = DMND_RFO|DMND_WB|RESP_MISS,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
+ [ C(RESULT_MISS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
+ },
+ }
+};
+
static __initconst const u64 nehalem_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
- [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
+ /*
+ * Use RFO, not WRITEBACK, because a write miss would typically occur
+ * on RFO.
+ */
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
- [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
- [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
printk("clearing PMU state on CPU#%d\n", smp_processor_id());
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
- checking_wrmsrl(x86_pmu.perfctr + idx, 0ull);
+ checking_wrmsrl(x86_pmu_config_addr(idx), 0ull);
+ checking_wrmsrl(x86_pmu_event_addr(idx), 0ull);
}
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
return NULL;
}
+static struct event_constraint *
+intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT;
+ struct event_constraint *c;
+ struct intel_percore *pc;
+ struct er_account *era;
+ int i;
+ int free_slot;
+ int found;
+
+ if (!x86_pmu.percore_constraints || hwc->extra_alloc)
+ return NULL;
+
+ for (c = x86_pmu.percore_constraints; c->cmask; c++) {
+ if (e != c->code)
+ continue;
+
+ /*
+ * Allocate resource per core.
+ */
+ pc = cpuc->per_core;
+ if (!pc)
+ break;
+ c = &emptyconstraint;
+ raw_spin_lock(&pc->lock);
+ free_slot = -1;
+ found = 0;
+ for (i = 0; i < MAX_EXTRA_REGS; i++) {
+ era = &pc->regs[i];
+ if (era->ref > 0 && hwc->extra_reg == era->extra_reg) {
+ /* Allow sharing same config */
+ if (hwc->extra_config == era->extra_config) {
+ era->ref++;
+ cpuc->percore_used = 1;
+ hwc->extra_alloc = 1;
+ c = NULL;
+ }
+ /* else conflict */
+ found = 1;
+ break;
+ } else if (era->ref == 0 && free_slot == -1)
+ free_slot = i;
+ }
+ if (!found && free_slot != -1) {
+ era = &pc->regs[free_slot];
+ era->ref = 1;
+ era->extra_reg = hwc->extra_reg;
+ era->extra_config = hwc->extra_config;
+ cpuc->percore_used = 1;
+ hwc->extra_alloc = 1;
+ c = NULL;
+ }
+ raw_spin_unlock(&pc->lock);
+ return c;
+ }
+
+ return NULL;
+}
+
static struct event_constraint *
intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
{
if (c)
return c;
+ c = intel_percore_constraints(cpuc, event);
+ if (c)
+ return c;
+
return x86_get_event_constraints(cpuc, event);
}
+static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
+ struct perf_event *event)
+{
+ struct extra_reg *er;
+ struct intel_percore *pc;
+ struct er_account *era;
+ struct hw_perf_event *hwc = &event->hw;
+ int i, allref;
+
+ if (!cpuc->percore_used)
+ return;
+
+ for (er = x86_pmu.extra_regs; er->msr; er++) {
+ if (er->event != (hwc->config & er->config_mask))
+ continue;
+
+ pc = cpuc->per_core;
+ raw_spin_lock(&pc->lock);
+ for (i = 0; i < MAX_EXTRA_REGS; i++) {
+ era = &pc->regs[i];
+ if (era->ref > 0 &&
+ era->extra_config == hwc->extra_config &&
+ era->extra_reg == er->msr) {
+ era->ref--;
+ hwc->extra_alloc = 0;
+ break;
+ }
+ }
+ allref = 0;
+ for (i = 0; i < MAX_EXTRA_REGS; i++)
+ allref += pc->regs[i].ref;
+ if (allref == 0)
+ cpuc->percore_used = 0;
+ raw_spin_unlock(&pc->lock);
+ break;
+ }
+}
+
static int intel_pmu_hw_config(struct perf_event *event)
{
int ret = x86_pmu_hw_config(event);
*/
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
+ .put_event_constraints = intel_put_event_constraints,
.event_constraints = intel_core_event_constraints,
};
+static int intel_pmu_cpu_prepare(int cpu)
+{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+ if (!cpu_has_ht_siblings())
+ return NOTIFY_OK;
+
+ cpuc->per_core = kzalloc_node(sizeof(struct intel_percore),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!cpuc->per_core)
+ return NOTIFY_BAD;
+
+ raw_spin_lock_init(&cpuc->per_core->lock);
+ cpuc->per_core->core_id = -1;
+ return NOTIFY_OK;
+}
+
static void intel_pmu_cpu_starting(int cpu)
{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ int core_id = topology_core_id(cpu);
+ int i;
+
init_debug_store_on_cpu(cpu);
/*
* Deal with CPUs that don't clear their LBRs on power-up.
*/
intel_pmu_lbr_reset();
+
+ if (!cpu_has_ht_siblings())
+ return;
+
+ for_each_cpu(i, topology_thread_cpumask(cpu)) {
+ struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core;
+
+ if (pc && pc->core_id == core_id) {
+ kfree(cpuc->per_core);
+ cpuc->per_core = pc;
+ break;
+ }
+ }
+
+ cpuc->per_core->core_id = core_id;
+ cpuc->per_core->refcnt++;
}
static void intel_pmu_cpu_dying(int cpu)
{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ struct intel_percore *pc = cpuc->per_core;
+
+ if (pc) {
+ if (pc->core_id == -1 || --pc->refcnt == 0)
+ kfree(pc);
+ cpuc->per_core = NULL;
+ }
+
fini_debug_store_on_cpu(cpu);
}
*/
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
+ .put_event_constraints = intel_put_event_constraints,
+ .cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
};
intel_pmu_lbr_init_core();
x86_pmu.event_constraints = intel_core2_event_constraints;
+ x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints;
pr_cont("Core2 events, ");
break;
case 46: /* 45 nm nehalem-ex, "Beckton" */
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
intel_pmu_lbr_init_nhm();
x86_pmu.event_constraints = intel_nehalem_event_constraints;
+ x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints;
+ x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+ x86_pmu.extra_regs = intel_nehalem_extra_regs;
pr_cont("Nehalem events, ");
break;
intel_pmu_lbr_init_atom();
x86_pmu.event_constraints = intel_gen_event_constraints;
+ x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints;
pr_cont("Atom events, ");
break;
case 44: /* 32 nm nehalem, "Gulftown" */
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
intel_pmu_lbr_init_nhm();
x86_pmu.event_constraints = intel_westmere_event_constraints;
+ x86_pmu.percore_constraints = intel_westmere_percore_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+ x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_westmere_extra_regs;
pr_cont("Westmere events, ");
break;
+ case 42: /* SandyBridge */
+ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ intel_pmu_lbr_init_nhm();
+
+ x86_pmu.event_constraints = intel_snb_event_constraints;
+ x86_pmu.pebs_constraints = intel_snb_pebs_events;
+ pr_cont("SandyBridge events, ");
+ break;
+
default:
/*
* default constraints for v2 and up
/*
* PEBS
*/
-
-static struct event_constraint intel_core_pebs_events[] = {
- PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */
+static struct event_constraint intel_core2_pebs_event_constraints[] = {
+ PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
- PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */
- PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
- PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */
- PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
- PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_atom_pebs_event_constraints[] = {
+ PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+ PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
EVENT_CONSTRAINT_END
};
-static struct event_constraint intel_nehalem_pebs_events[] = {
- PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */
- PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */
- PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */
- PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */
- PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */
- PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
- PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */
- PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
- PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */
+static struct event_constraint intel_nehalem_pebs_event_constraints[] = {
+ INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
+ PEBS_EVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+ INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
+ INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ PEBS_EVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+ INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
+ PEBS_EVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_westmere_pebs_event_constraints[] = {
+ INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
+ PEBS_EVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+ INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
+
+ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
+ PEBS_EVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+ INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_snb_pebs_events[] = {
+ PEBS_EVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ PEBS_EVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+ PEBS_EVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+ PEBS_EVENT_CONSTRAINT(0x01c4, 0xf), /* BR_INST_RETIRED.CONDITIONAL */
+ PEBS_EVENT_CONSTRAINT(0x02c4, 0xf), /* BR_INST_RETIRED.NEAR_CALL */
+ PEBS_EVENT_CONSTRAINT(0x04c4, 0xf), /* BR_INST_RETIRED.ALL_BRANCHES */
+ PEBS_EVENT_CONSTRAINT(0x08c4, 0xf), /* BR_INST_RETIRED.NEAR_RETURN */
+ PEBS_EVENT_CONSTRAINT(0x10c4, 0xf), /* BR_INST_RETIRED.NOT_TAKEN */
+ PEBS_EVENT_CONSTRAINT(0x20c4, 0xf), /* BR_INST_RETIRED.NEAR_TAKEN */
+ PEBS_EVENT_CONSTRAINT(0x40c4, 0xf), /* BR_INST_RETIRED.FAR_BRANCH */
+ PEBS_EVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */
+ PEBS_EVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+ PEBS_EVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */
+ PEBS_EVENT_CONSTRAINT(0x10c5, 0xf), /* BR_MISP_RETIRED.NOT_TAKEN */
+ PEBS_EVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.TAKEN */
+ PEBS_EVENT_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ PEBS_EVENT_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORE */
+ PEBS_EVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
+ PEBS_EVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
+ PEBS_EVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
+ PEBS_EVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
+ PEBS_EVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
+ PEBS_EVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
+ PEBS_EVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
+ PEBS_EVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+ PEBS_EVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */
+ PEBS_EVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */
+ PEBS_EVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.LLC_HIT */
+ PEBS_EVENT_CONSTRAINT(0x40d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
+ PEBS_EVENT_CONSTRAINT(0x01d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
+ PEBS_EVENT_CONSTRAINT(0x02d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
+ PEBS_EVENT_CONSTRAINT(0x04d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM */
+ PEBS_EVENT_CONSTRAINT(0x08d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE */
+ PEBS_EVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
EVENT_CONSTRAINT_END
};
printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
- x86_pmu.pebs_constraints = intel_core_pebs_events;
break;
case 1:
printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
- x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
break;
default:
printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
- break;
}
}
}
u64 v;
/* an official way for overflow indication */
- rdmsrl(hwc->config_base + hwc->idx, v);
+ rdmsrl(hwc->config_base, v);
if (v & P4_CCCR_OVF) {
- wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+ wrmsrl(hwc->config_base, v & ~P4_CCCR_OVF);
return 1;
}
- /* it might be unflagged overflow */
- rdmsrl(hwc->event_base + hwc->idx, v);
- if (!(v & ARCH_P4_CNTRVAL_MASK))
+ /*
+ * In some circumstances the overflow might issue an NMI but did
+ * not set P4_CCCR_OVF bit. Because a counter holds a negative value
+ * we simply check for high bit being set, if it's cleared it means
+ * the counter has reached zero value and continued counting before
+ * real NMI signal was received:
+ */
+ if (!(v & ARCH_P4_UNFLAGGED_BIT))
return 1;
return 0;
* state we need to clear P4_CCCR_OVF, otherwise interrupt get
* asserted again and again
*/
- (void)checking_wrmsrl(hwc->config_base + hwc->idx,
+ (void)checking_wrmsrl(hwc->config_base,
(u64)(p4_config_unpack_cccr(hwc->config)) &
~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
}
p4_pmu_enable_pebs(hwc->config);
(void)checking_wrmsrl(escr_addr, escr_conf);
- (void)checking_wrmsrl(hwc->config_base + hwc->idx,
+ (void)checking_wrmsrl(hwc->config_base,
(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
}
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
+ (void)checking_wrmsrl(hwc->config_base, val);
}
static void p6_pmu_enable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
+ (void)checking_wrmsrl(hwc->config_base, val);
}
static __initconst const struct x86_pmu p6_pmu = {
/* returns the bit offset of the performance counter register */
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
+ if (msr >= MSR_F15H_PERF_CTR)
+ return (msr - MSR_F15H_PERF_CTR) >> 1;
return msr - MSR_K7_PERFCTR0;
case X86_VENDOR_INTEL:
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
/* returns the bit offset of the event selection register */
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
+ if (msr >= MSR_F15H_PERF_CTL)
+ return (msr - MSR_F15H_PERF_CTL) >> 1;
return msr - MSR_K7_EVNTSEL0;
case X86_VENDOR_INTEL:
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
oops_end(flags, regs, sig);
}
-void notrace __kprobes
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
- unsigned long flags;
-
- if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
- return;
-
- /*
- * We are in trouble anyway, lets at least try
- * to get a message out.
- */
- flags = oops_begin();
- printk(KERN_EMERG "%s", str);
- printk(" on CPU%d, ip %08lx, registers:\n",
- smp_processor_id(), regs->ip);
- show_registers(regs);
- oops_end(flags, regs, 0);
- if (do_panic || panic_on_oops)
- panic("Non maskable interrupt");
- nmi_exit();
- local_irq_enable();
- do_exit(SIGBUS);
-}
-
static int __init oops_setup(char *s)
{
if (!s)
static u32 __init ati_sbx00_rev(int num, int slot, int func)
{
- u32 old, d;
+ u32 d;
- d = read_pci_config(num, slot, func, 0x70);
- old = d;
- d &= ~(1<<8);
- write_pci_config(num, slot, func, 0x70, d);
d = read_pci_config(num, slot, func, 0x8);
d &= 0xff;
- write_pci_config(num, slot, func, 0x70, old);
return d;
}
{
u32 d, rev;
- if (acpi_use_timer_override)
- return;
-
rev = ati_sbx00_rev(num, slot, func);
+ if (rev >= 0x40)
+ acpi_fix_pin2_polarity = 1;
+
if (rev > 0x13)
return;
+ if (acpi_use_timer_override)
+ return;
+
/* check for IRQ0 interrupt swap */
d = read_pci_config(num, slot, func, 0x64);
if (!(d & (1<<14)))
#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:
* A tiny bit of offset fixup is necessary - 4*4 means the 4 words
* pushed above; +8 corresponds to copy_thread's esp0 setting.
*/
- pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp)
+ pushl_cfi ((TI_sysenter_return)-THREAD_SIZE+8+4*4)(%esp)
CFI_REL_OFFSET eip, 0
pushl_cfi %eax
*/
.section .init.rodata,"a"
ENTRY(interrupt)
-.text
+.section .entry.text, "ax"
.p2align 5
.p2align CONFIG_X86_L1_CACHE_SHIFT
ENTRY(irq_entries_start)
.endif
.previous
.long 1b
- .text
+ .section .entry.text, "ax"
vector=vector+1
.endif
.endr
#ifdef CONFIG_KVM_GUEST
ENTRY(async_page_fault)
RING0_EC_FRAME
- pushl $do_async_page_fault
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi $do_async_page_fault
jmp error_code
CFI_ENDPROC
END(apf_page_fault)
#define __AUDIT_ARCH_LE 0x40000000
.code64
+ .section .entry.text, "ax"
+
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(mcount)
*/
.section .init.rodata,"a"
ENTRY(interrupt)
- .text
+ .section .entry.text
.p2align 5
.p2align CONFIG_X86_L1_CACHE_SHIFT
ENTRY(irq_entries_start)
.endif
.previous
.quad 1b
- .text
+ .section .entry.text
vector=vector+1
.endif
.endr
decl PER_CPU_VAR(irq_count)
jmp error_exit
CFI_ENDPROC
-END(do_hypervisor_callback)
+END(xen_do_hypervisor_callback)
/*
* Hypervisor uses this for application faults while it executes.
return;
}
- if (ftrace_push_return_trace(old, self_addr, &trace.depth,
- frame_pointer) == -EBUSY) {
- *parent = old;
- return;
- }
-
trace.func = self_addr;
+ trace.depth = current->curr_ret_stack + 1;
/* Only trace if the calling function expects to */
if (!ftrace_graph_entry(&trace)) {
- current->curr_ret_stack--;
*parent = old;
+ return;
+ }
+
+ if (ftrace_push_return_trace(old, self_addr, &trace.depth,
+ frame_pointer) == -EBUSY) {
+ *parent = old;
+ return;
}
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
*/
KERNEL_PAGES = LOWMEM_PAGES
-INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm
+INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE
RESERVE_BRK(pagetables, INIT_MAP_SIZE)
/*
* BSS section
*/
__PAGE_ALIGNED_BSS
- .align PAGE_SIZE_asm
+ .align PAGE_SIZE
#ifdef CONFIG_X86_PAE
initial_pg_pmd:
.fill 1024*KPMDS,4,0
#ifdef CONFIG_X86_PAE
__PAGE_ALIGNED_DATA
/* Page-aligned for the benefit of paravirt? */
- .align PAGE_SIZE_asm
+ .align PAGE_SIZE
ENTRY(initial_page_table)
.long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 /* low identity map */
# if KPMDS == 3
# else
# error "Kernel PMDs should be 1, 2 or 3"
# endif
- .align PAGE_SIZE_asm /* needs to be page-sized too */
+ .align PAGE_SIZE /* needs to be page-sized too */
#endif
.data
if (!irq)
return -EINVAL;
- set_irq_data(irq, dev);
+ irq_set_handler_data(irq, dev);
if (hpet_setup_msi_irq(irq))
return -EINVAL;
{
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
- set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
+ irq_set_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
i8259A_chip.name);
enable_irq(irq);
}
#include <linux/slab.h>
#include <linux/thread_info.h>
#include <linux/syscalls.h>
+#include <linux/bitmap.h>
#include <asm/syscalls.h>
-/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
-static void set_bitmap(unsigned long *bitmap, unsigned int base,
- unsigned int extent, int new_value)
-{
- unsigned int i;
-
- for (i = base; i < base + extent; i++) {
- if (new_value)
- __set_bit(i, bitmap);
- else
- __clear_bit(i, bitmap);
- }
-}
-
/*
* this changes the io permissions bitmap in the current task.
*/
*/
tss = &per_cpu(init_tss, get_cpu());
- set_bitmap(t->io_bitmap_ptr, from, num, !turn_on);
+ if (turn_on)
+ bitmap_clear(t->io_bitmap_ptr, from, num);
+ else
+ bitmap_set(t->io_bitmap_ptr, from, num);
/*
* Search for a (possibly new) maximum. This is simple and stupid,
#define irq_stats(x) (&per_cpu(irq_stat, x))
/*
- * /proc/interrupts printing:
+ * /proc/interrupts printing for arch specific interrupts
*/
-static int show_other_interrupts(struct seq_file *p, int prec)
+int arch_show_interrupts(struct seq_file *p, int prec)
{
int j;
return 0;
}
-int show_interrupts(struct seq_file *p, void *v)
-{
- unsigned long flags, any_count = 0;
- int i = *(loff_t *) v, j, prec;
- struct irqaction *action;
- struct irq_desc *desc;
-
- if (i > nr_irqs)
- return 0;
-
- for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
- j *= 10;
-
- if (i == nr_irqs)
- return show_other_interrupts(p, prec);
-
- /* print header */
- if (i == 0) {
- seq_printf(p, "%*s", prec + 8, "");
- for_each_online_cpu(j)
- seq_printf(p, "CPU%-8d", j);
- seq_putc(p, '\n');
- }
-
- desc = irq_to_desc(i);
- if (!desc)
- return 0;
-
- raw_spin_lock_irqsave(&desc->lock, flags);
- for_each_online_cpu(j)
- any_count |= kstat_irqs_cpu(i, j);
- action = desc->action;
- if (!action && !any_count)
- goto out;
-
- seq_printf(p, "%*d: ", prec, i);
- for_each_online_cpu(j)
- seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
- seq_printf(p, " %8s", desc->irq_data.chip->name);
- seq_printf(p, "-%-8s", desc->name);
-
- if (action) {
- seq_printf(p, " %s", action->name);
- while ((action = action->next) != NULL)
- seq_printf(p, ", %s", action->name);
- }
-
- seq_putc(p, '\n');
-out:
- raw_spin_unlock_irqrestore(&desc->lock, flags);
- return 0;
-}
-
/*
* /proc/stat helpers
*/
static int warned;
struct irq_desc *desc;
struct irq_data *data;
+ struct irq_chip *chip;
for_each_irq_desc(irq, desc) {
int break_affinity = 0;
/* interrupt's are disabled at this point */
raw_spin_lock(&desc->lock);
- data = &desc->irq_data;
+ data = irq_desc_get_irq_data(desc);
affinity = data->affinity;
if (!irq_has_action(irq) ||
- cpumask_equal(affinity, cpu_online_mask)) {
+ cpumask_subset(affinity, cpu_online_mask)) {
raw_spin_unlock(&desc->lock);
continue;
}
affinity = cpu_all_mask;
}
- if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
- data->chip->irq_mask(data);
+ chip = irq_data_get_irq_chip(data);
+ if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
+ chip->irq_mask(data);
- if (data->chip->irq_set_affinity)
- data->chip->irq_set_affinity(data, affinity, true);
+ if (chip->irq_set_affinity)
+ chip->irq_set_affinity(data, affinity, true);
else if (!(warned++))
set_affinity = 0;
- if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
- data->chip->irq_unmask(data);
+ if (!irqd_can_move_in_process_context(data) && chip->irq_unmask)
+ chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
if (irr & (1 << (vector % 32))) {
irq = __this_cpu_read(vector_irq[vector]);
- data = irq_get_irq_data(irq);
+ desc = irq_to_desc(irq);
+ data = irq_desc_get_irq_data(desc);
+ chip = irq_data_get_irq_chip(data);
raw_spin_lock(&desc->lock);
- if (data->chip->irq_retrigger)
- data->chip->irq_retrigger(data);
+ if (chip->irq_retrigger)
+ chip->irq_retrigger(data);
raw_spin_unlock(&desc->lock);
}
}
static struct irqaction fpu_irq = {
.handler = math_error_irq,
.name = "fpu",
+ .flags = IRQF_NO_THREAD,
};
#endif
static struct irqaction irq2 = {
.handler = no_action,
.name = "cascade",
+ .flags = IRQF_NO_THREAD,
};
DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
legacy_pic->init(0);
for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
- set_irq_chip_and_handler_name(i, chip, handle_level_irq, name);
+ irq_set_chip_and_handler_name(i, chip, handle_level_irq, name);
}
void __init init_IRQ(void)
}
return NOTIFY_DONE;
- case DIE_NMIWATCHDOG:
- if (atomic_read(&kgdb_active) != -1) {
- /* KGDB CPU roundup: */
- kgdb_nmicallback(raw_smp_processor_id(), regs);
- return NOTIFY_STOP;
- }
- /* Enter debugger: */
- break;
-
case DIE_DEBUG:
if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
if (user_mode(regs))
if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
return 0;
+ /*
+ * Do not optimize in the entry code due to the unstable
+ * stack handling.
+ */
+ if ((paddr >= (unsigned long )__entry_text_start) &&
+ (paddr < (unsigned long )__entry_text_end))
+ return 0;
+
/* Check there is enough space for a relative jump. */
if (size - offset < RELATIVEJUMP_SIZE)
return 0;
void show_regs_common(void)
{
- const char *board, *product;
+ const char *vendor, *product, *board;
- board = dmi_get_system_info(DMI_BOARD_NAME);
- if (!board)
- board = "";
+ vendor = dmi_get_system_info(DMI_SYS_VENDOR);
+ if (!vendor)
+ vendor = "";
product = dmi_get_system_info(DMI_PRODUCT_NAME);
if (!product)
product = "";
+ /* Board Name is optional */
+ board = dmi_get_system_info(DMI_BOARD_NAME);
+
printk(KERN_CONT "\n");
- printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n",
+ printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s",
current->pid, current->comm, print_tainted(),
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
- init_utsname()->version, board, product);
+ init_utsname()->version);
+ printk(KERN_CONT " %s %s", vendor, product);
+ if (board)
+ printk(KERN_CONT "/%s", board);
+ printk(KERN_CONT "\n");
}
void flush_thread(void)
#define MWAIT_ECX_EXTENDED_INFO 0x01
#define MWAIT_EDX_C1 0xf0
-int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
+int mwait_usable(const struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
},
},
+ { /* Handle problems with rebooting on VersaLogic Menlow boards */
+ .callback = set_bios_reboot,
+ .ident = "VersaLogic Menlow based board",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"),
+ DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
+ },
+ },
{ }
};
#include <asm/mtrr.h>
#include <asm/mwait.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
+
/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
cpu_idle();
}
-#ifdef CONFIG_CPUMASK_OFFSTACK
-/* In this case, llc_shared_map is a pointer to a cpumask. */
-static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
- const struct cpuinfo_x86 *src)
-{
- struct cpumask *llc = dst->llc_shared_map;
- *dst = *src;
- dst->llc_shared_map = llc;
-}
-#else
-static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
- const struct cpuinfo_x86 *src)
-{
- *dst = *src;
-}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
-
/*
* The bootstrap kernel entry code has set these up. Save them for
* a given CPU
{
struct cpuinfo_x86 *c = &cpu_data(id);
- copy_cpuinfo_x86(c, &boot_cpu_data);
+ *c = boot_cpu_data;
c->cpu_index = id;
if (id != 0)
identify_secondary_cpu(c);
static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
{
- struct cpuinfo_x86 *c1 = &cpu_data(cpu1);
- struct cpuinfo_x86 *c2 = &cpu_data(cpu2);
-
cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
- cpumask_set_cpu(cpu1, c2->llc_shared_map);
- cpumask_set_cpu(cpu2, c1->llc_shared_map);
+ cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
+ cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
}
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
}
- cpumask_set_cpu(cpu, c->llc_shared_map);
+ cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
for_each_cpu(i, cpu_sibling_setup_mask) {
if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
- cpumask_set_cpu(i, c->llc_shared_map);
- cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map);
+ cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
}
if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
cpumask_set_cpu(i, cpu_core_mask(cpu));
!(cpu_has(c, X86_FEATURE_AMD_DCM)))
return cpu_core_mask(cpu);
else
- return c->llc_shared_map;
+ return cpu_llc_shared_mask(cpu);
}
static void impress_friends(void)
return 0;
}
+/**
+ * arch_disable_smp_support() - disables SMP support for x86 at runtime
+ */
+void arch_disable_smp_support(void)
+{
+ disable_ioapic_support();
+}
+
/*
* Fall back to non SMP mode after errors.
*
"(tell your hw vendor)\n");
}
smpboot_clear_io_apic();
- arch_disable_smp_support();
+ disable_ioapic_support();
return -1;
}
connect_bsp_APIC();
setup_local_APIC();
- end_local_APIC_setup();
+ bsp_end_local_APIC_setup();
return -1;
}
preempt_disable();
smp_cpu_index_default();
- memcpy(__this_cpu_ptr(&cpu_info), &boot_cpu_data, sizeof(cpu_info));
- cpumask_copy(cpu_callin_mask, cpumask_of(0));
- mb();
+
/*
* Setup boot CPU information
*/
smp_store_cpu_info(0); /* Final full version of the data */
+ cpumask_copy(cpu_callin_mask, cpumask_of(0));
+ mb();
#ifdef CONFIG_X86_32
boot_cpu_logical_apicid = logical_smp_processor_id();
#endif
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
+ zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
set_cpu_sibling_map(0);
if (!skip_ioapic_setup && nr_ioapics)
enable_IO_APIC();
- end_local_APIC_setup();
+ bsp_end_local_APIC_setup();
map_cpu_to_logical_apicid();
.long sys_fanotify_init
.long sys_fanotify_mark
.long sys_prlimit64 /* 340 */
+ .long sys_name_to_handle_at
+ .long sys_open_by_handle_at
+ .long sys_clock_adjtime
SCHED_TEXT
LOCK_TEXT
KPROBES_TEXT
+ ENTRY_TEXT
IRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
}
#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
- PERCPU(THREAD_SIZE)
+ PERCPU(PAGE_SIZE)
#endif
. = ALIGN(PAGE_SIZE);
kvm_load_ldt(svm->host.ldt);
#ifdef CONFIG_X86_64
loadsegment(fs, svm->host.fs);
- load_gs_index(svm->host.gs);
wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
+ load_gs_index(svm->host.gs);
#else
loadsegment(gs, svm->host.gs);
#endif
kvm_register_write(&svm->vcpu, reg, val);
}
+ skip_emulated_instruction(&svm->vcpu);
+
return 1;
}
TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa),
TP_STRUCT__entry(
- __field( __u16, code )
- __field( bool, fast )
__field( __u16, rep_cnt )
__field( __u16, rep_idx )
__field( __u64, ingpa )
__field( __u64, outgpa )
+ __field( __u16, code )
+ __field( bool, fast )
),
TP_fast_assign(
- __entry->code = code;
- __entry->fast = fast;
__entry->rep_cnt = rep_cnt;
__entry->rep_idx = rep_idx;
__entry->ingpa = ingpa;
__entry->outgpa = outgpa;
+ __entry->code = code;
+ __entry->fast = fast;
),
TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx",
void lguest_setup_irq(unsigned int irq)
{
irq_alloc_desc_at(irq, 0);
- set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
+ irq_set_chip_and_handler_name(irq, &lguest_irq_controller,
handle_level_irq, "level");
}
static void lguest_time_init(void)
{
/* Set up the timer interrupt (0) to go to our simple timer routine */
- set_irq_handler(0, lguest_time_irq);
+ irq_set_handler(0, lguest_time_irq);
clocksource_register(&lguest_clock);
/* if you want SMP support, implement these with real spinlocks */
.macro LOCK reg
- pushfl
- CFI_ADJUST_CFA_OFFSET 4
+ pushfl_cfi
cli
.endm
.macro UNLOCK reg
- popfl
- CFI_ADJUST_CFA_OFFSET -4
+ popfl_cfi
.endm
#define BEGIN(op) \
#include <asm/dwarf2.h>
.macro SAVE reg
- pushl %\reg
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %\reg
CFI_REL_OFFSET \reg, 0
.endm
.macro RESTORE reg
- popl %\reg
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %\reg
CFI_RESTORE \reg
.endm
*/
ENTRY(csum_partial)
CFI_STARTPROC
- pushl %esi
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %esi
CFI_REL_OFFSET esi, 0
- pushl %ebx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ebx
CFI_REL_OFFSET ebx, 0
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
jz 8f
roll $8, %eax
8:
- popl %ebx
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %ebx
CFI_RESTORE ebx
- popl %esi
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %esi
CFI_RESTORE esi
ret
CFI_ENDPROC
ENTRY(csum_partial)
CFI_STARTPROC
- pushl %esi
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %esi
CFI_REL_OFFSET esi, 0
- pushl %ebx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ebx
CFI_REL_OFFSET ebx, 0
movl 20(%esp),%eax # Function arg: unsigned int sum
movl 16(%esp),%ecx # Function arg: int len
jz 90f
roll $8, %eax
90:
- popl %ebx
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %ebx
CFI_RESTORE ebx
- popl %esi
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %esi
CFI_RESTORE esi
ret
CFI_ENDPROC
CFI_STARTPROC
subl $4,%esp
CFI_ADJUST_CFA_OFFSET 4
- pushl %edi
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %edi
CFI_REL_OFFSET edi, 0
- pushl %esi
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %esi
CFI_REL_OFFSET esi, 0
- pushl %ebx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ebx
CFI_REL_OFFSET ebx, 0
movl ARGBASE+16(%esp),%eax # sum
movl ARGBASE+12(%esp),%ecx # len
.previous
- popl %ebx
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %ebx
CFI_RESTORE ebx
- popl %esi
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %esi
CFI_RESTORE esi
- popl %edi
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %edi
CFI_RESTORE edi
- popl %ecx # equivalent to addl $4,%esp
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %ecx # equivalent to addl $4,%esp
ret
CFI_ENDPROC
ENDPROC(csum_partial_copy_generic)
ENTRY(csum_partial_copy_generic)
CFI_STARTPROC
- pushl %ebx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ebx
CFI_REL_OFFSET ebx, 0
- pushl %edi
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %edi
CFI_REL_OFFSET edi, 0
- pushl %esi
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %esi
CFI_REL_OFFSET esi, 0
movl ARGBASE+4(%esp),%esi #src
movl ARGBASE+8(%esp),%edi #dst
jmp 7b
.previous
- popl %esi
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %esi
CFI_RESTORE esi
- popl %edi
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %edi
CFI_RESTORE edi
- popl %ebx
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %ebx
CFI_RESTORE ebx
ret
CFI_ENDPROC
#include <asm/dwarf2.h>
#define save_common_regs \
- pushq %rdi; \
- pushq %rsi; \
- pushq %rcx; \
- pushq %r8; \
- pushq %r9; \
- pushq %r10; \
- pushq %r11
+ pushq_cfi %rdi; CFI_REL_OFFSET rdi, 0; \
+ pushq_cfi %rsi; CFI_REL_OFFSET rsi, 0; \
+ pushq_cfi %rcx; CFI_REL_OFFSET rcx, 0; \
+ pushq_cfi %r8; CFI_REL_OFFSET r8, 0; \
+ pushq_cfi %r9; CFI_REL_OFFSET r9, 0; \
+ pushq_cfi %r10; CFI_REL_OFFSET r10, 0; \
+ pushq_cfi %r11; CFI_REL_OFFSET r11, 0
#define restore_common_regs \
- popq %r11; \
- popq %r10; \
- popq %r9; \
- popq %r8; \
- popq %rcx; \
- popq %rsi; \
- popq %rdi
+ popq_cfi %r11; CFI_RESTORE r11; \
+ popq_cfi %r10; CFI_RESTORE r10; \
+ popq_cfi %r9; CFI_RESTORE r9; \
+ popq_cfi %r8; CFI_RESTORE r8; \
+ popq_cfi %rcx; CFI_RESTORE rcx; \
+ popq_cfi %rsi; CFI_RESTORE rsi; \
+ popq_cfi %rdi; CFI_RESTORE rdi
/* Fix up special calling conventions */
ENTRY(call_rwsem_down_read_failed)
+ CFI_STARTPROC
save_common_regs
- pushq %rdx
+ pushq_cfi %rdx
+ CFI_REL_OFFSET rdx, 0
movq %rax,%rdi
call rwsem_down_read_failed
- popq %rdx
+ popq_cfi %rdx
+ CFI_RESTORE rdx
restore_common_regs
ret
- ENDPROC(call_rwsem_down_read_failed)
+ 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
- ENDPROC(call_rwsem_down_write_failed)
+ CFI_ENDPROC
+ENDPROC(call_rwsem_down_write_failed)
ENTRY(call_rwsem_wake)
+ CFI_STARTPROC
decl %edx /* do nothing if still outstanding active readers */
jnz 1f
save_common_regs
call rwsem_wake
restore_common_regs
1: ret
- ENDPROC(call_rwsem_wake)
+ CFI_ENDPROC
+ENDPROC(call_rwsem_wake)
/* Fix up special calling conventions */
ENTRY(call_rwsem_downgrade_wake)
+ CFI_STARTPROC
save_common_regs
- pushq %rdx
+ pushq_cfi %rdx
+ CFI_REL_OFFSET rdx, 0
movq %rax,%rdi
call rwsem_downgrade_wake
- popq %rdx
+ popq_cfi %rdx
+ CFI_RESTORE rdx
restore_common_regs
ret
- ENDPROC(call_rwsem_downgrade_wake)
+ CFI_ENDPROC
+ENDPROC(call_rwsem_downgrade_wake)
*/
#ifdef CONFIG_SMP
ENTRY(__write_lock_failed)
- CFI_STARTPROC simple
+ CFI_STARTPROC
FRAME
2: LOCK_PREFIX
addl $ RW_LOCK_BIAS,(%eax)
/* Fix up special calling conventions */
ENTRY(call_rwsem_down_read_failed)
CFI_STARTPROC
- push %ecx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ecx
CFI_REL_OFFSET ecx,0
- push %edx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %edx
CFI_REL_OFFSET edx,0
call rwsem_down_read_failed
- pop %edx
- CFI_ADJUST_CFA_OFFSET -4
- pop %ecx
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %edx
+ popl_cfi %ecx
ret
CFI_ENDPROC
ENDPROC(call_rwsem_down_read_failed)
ENTRY(call_rwsem_down_write_failed)
CFI_STARTPROC
- push %ecx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ecx
CFI_REL_OFFSET ecx,0
calll rwsem_down_write_failed
- pop %ecx
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %ecx
ret
CFI_ENDPROC
ENDPROC(call_rwsem_down_write_failed)
CFI_STARTPROC
decw %dx /* do nothing if still outstanding active readers */
jnz 1f
- push %ecx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ecx
CFI_REL_OFFSET ecx,0
call rwsem_wake
- pop %ecx
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %ecx
1: ret
CFI_ENDPROC
ENDPROC(call_rwsem_wake)
/* Fix up special calling conventions */
ENTRY(call_rwsem_downgrade_wake)
CFI_STARTPROC
- push %ecx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %ecx
CFI_REL_OFFSET ecx,0
- push %edx
- CFI_ADJUST_CFA_OFFSET 4
+ pushl_cfi %edx
CFI_REL_OFFSET edx,0
call rwsem_downgrade_wake
- pop %edx
- CFI_ADJUST_CFA_OFFSET -4
- pop %ecx
- CFI_ADJUST_CFA_OFFSET -4
+ popl_cfi %edx
+ popl_cfi %ecx
ret
CFI_ENDPROC
ENDPROC(call_rwsem_downgrade_wake)
#include <linux/linkage.h>
-#define ARCH_TRACE_IRQS_ON \
- pushl %eax; \
- pushl %ecx; \
- pushl %edx; \
- call trace_hardirqs_on; \
- popl %edx; \
- popl %ecx; \
- popl %eax;
-
-#define ARCH_TRACE_IRQS_OFF \
- pushl %eax; \
- pushl %ecx; \
- pushl %edx; \
- call trace_hardirqs_off; \
- popl %edx; \
- popl %ecx; \
- popl %eax;
-
#ifdef CONFIG_TRACE_IRQFLAGS
/* put return address in eax (arg1) */
.macro thunk_ra name,func
CFI_ENDPROC
.endm
- /* rdi: arg1 ... normal C conventions. rax is passed from C. */
- .macro thunk_retrax name,func
- .globl \name
-\name:
- CFI_STARTPROC
- SAVE_ARGS
- call \func
- jmp restore_norax
- CFI_ENDPROC
- .endm
-
-
- .section .sched.text, "ax"
-#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM
- thunk rwsem_down_read_failed_thunk,rwsem_down_read_failed
- thunk rwsem_down_write_failed_thunk,rwsem_down_write_failed
- thunk rwsem_wake_thunk,rwsem_wake
- thunk rwsem_downgrade_thunk,rwsem_downgrade_wake
-#endif
-
#ifdef CONFIG_TRACE_IRQFLAGS
/* put return address in rdi (arg1) */
.macro thunk_ra name,func
RESTORE_ARGS
ret
CFI_ENDPROC
-
- CFI_STARTPROC
- SAVE_ARGS
-restore_norax:
- RESTORE_ARGS 1
- ret
- CFI_ENDPROC
for (address = VMALLOC_START & PMD_MASK;
address >= TASK_SIZE && address < FIXADDR_TOP;
address += PMD_SIZE) {
-
- unsigned long flags;
struct page *page;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
spinlock_t *pgt_lock;
pmd_t *ret;
+ /* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
if (!ret)
break;
}
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
}
unsigned long address, unsigned int fault)
{
if (fault & VM_FAULT_OOM) {
+ /* Kernel mode? Handle exceptions or die: */
+ if (!(error_code & PF_USER)) {
+ up_read(¤t->mm->mmap_sem);
+ no_context(regs, error_code, address);
+ return;
+ }
+
out_of_memory(regs, error_code, address);
} else {
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
for (address = start; address <= end; address += PGDIR_SIZE) {
const pgd_t *pgd_ref = pgd_offset_k(address);
- unsigned long flags;
struct page *page;
if (pgd_none(*pgd_ref))
continue;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
pgd_t *pgd;
spinlock_t *pgt_lock;
pgd = (pgd_t *)page_address(page) + pgd_index(address);
+ /* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
spin_unlock(pgt_lock);
}
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
}
int physnid;
int nid = NUMA_NO_NODE;
- apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
- if (apicid != BAD_APICID)
- nid = apicid_to_node[apicid];
- if (nid == NUMA_NO_NODE)
- nid = early_cpu_to_node(cpu);
+ nid = early_cpu_to_node(cpu);
BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
/*
void update_page_count(int level, unsigned long pages)
{
- unsigned long flags;
-
/* Protect against CPA */
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
direct_pages_count[level] += pages;
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
static void split_page_count(int level)
try_preserve_large_page(pte_t *kpte, unsigned long address,
struct cpa_data *cpa)
{
- unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn;
+ unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn;
pte_t new_pte, old_pte, *tmp;
pgprot_t old_prot, new_prot, req_prot;
int i, do_split = 1;
if (cpa->force_split)
return 1;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
/*
* Check for races, another CPU might have split this page
* up already:
}
out_unlock:
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
return do_split;
}
static int split_large_page(pte_t *kpte, unsigned long address)
{
- unsigned long flags, pfn, pfninc = 1;
+ unsigned long pfn, pfninc = 1;
unsigned int i, level;
pte_t *pbase, *tmp;
pgprot_t ref_prot;
if (!base)
return -ENOMEM;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
/*
* Check for races, another CPU might have split this page
* up for us already:
*/
if (base)
__free_page(base);
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
return 0;
}
static void pgd_dtor(pgd_t *pgd)
{
- unsigned long flags; /* can be called from interrupt context */
-
if (SHARED_KERNEL_PMD)
return;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
pgd_list_del(pgd);
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
/*
{
pgd_t *pgd;
pmd_t *pmds[PREALLOCATED_PMDS];
- unsigned long flags;
pgd = (pgd_t *)__get_free_page(PGALLOC_GFP);
* respect to anything walking the pgd_list, so that they
* never see a partially populated pgd.
*/
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
pgd_ctor(mm, pgd);
pgd_prepopulate_pmd(mm, pgd, pmds);
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
return pgd;
#include <linux/pci.h>
#include <linux/init.h>
+#include <asm/ce4100.h>
#include <asm/pci_x86.h>
struct sim_reg {
.write = ce4100_conf_write,
};
-static int __init ce4100_pci_init(void)
+int __init ce4100_pci_init(void)
{
init_sim_regs();
raw_pci_ops = &ce4100_pci_conf;
- return 0;
+ /* Indicate caller that it should invoke pci_legacy_init() */
+ return 1;
}
-subsys_initcall(ce4100_pci_init);
#include <asm/xen/pci.h>
#ifdef CONFIG_ACPI
-static int xen_hvm_register_pirq(u32 gsi, int triggering)
+static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
+ int trigger, int polarity)
{
int rc, irq;
struct physdev_map_pirq map_irq;
return -1;
}
- if (triggering == ACPI_EDGE_SENSITIVE) {
+ if (trigger == ACPI_EDGE_SENSITIVE) {
shareable = 0;
name = "ioapic-edge";
} else {
return irq;
}
-
-static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
- int trigger, int polarity)
-{
- return xen_hvm_register_pirq(gsi, trigger);
-}
#endif
#if defined(CONFIG_PCI_MSI)
static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
- int irq, pirq, ret = 0;
+ int irq, pirq;
struct msi_desc *msidesc;
struct msi_msg msg;
__read_msi_msg(msidesc, &msg);
pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
- if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) {
- xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
- "msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ);
- if (irq < 0)
+ if (msg.data != XEN_PIRQ_MSI_DATA ||
+ xen_irq_from_pirq(pirq) < 0) {
+ pirq = xen_allocate_pirq_msi(dev, msidesc);
+ if (pirq < 0)
goto error;
- ret = set_irq_msi(irq, msidesc);
- if (ret < 0)
- goto error_while;
- printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d"
- " pirq=%d\n", irq, pirq);
- return 0;
+ xen_msi_compose_msg(dev, pirq, &msg);
+ __write_msi_msg(msidesc, &msg);
+ dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
+ } else {
+ dev_dbg(&dev->dev,
+ "xen: msi already bound to pirq=%d\n", pirq);
}
- xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
- "msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ));
- if (irq < 0 || pirq < 0)
+ irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0,
+ (type == PCI_CAP_ID_MSIX) ?
+ "msi-x" : "msi");
+ if (irq < 0)
goto error;
- printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq);
- xen_msi_compose_msg(dev, pirq, &msg);
- ret = set_irq_msi(irq, msidesc);
- if (ret < 0)
- goto error_while;
- write_msi_msg(irq, &msg);
+ dev_dbg(&dev->dev,
+ "xen: msi --> pirq=%d --> irq=%d\n", pirq, irq);
}
return 0;
-error_while:
- unbind_from_irqhandler(irq, NULL);
error:
- if (ret == -ENODEV)
- dev_err(&dev->dev, "Xen PCI frontend has not registered" \
- " MSI/MSI-X support!\n");
-
- return ret;
+ dev_err(&dev->dev,
+ "Xen PCI frontend has not registered MSI/MSI-X support!\n");
+ return -ENODEV;
}
/*
return -ENOMEM;
if (type == PCI_CAP_ID_MSIX)
- ret = xen_pci_frontend_enable_msix(dev, &v, nvec);
+ ret = xen_pci_frontend_enable_msix(dev, v, nvec);
else
- ret = xen_pci_frontend_enable_msi(dev, &v);
+ ret = xen_pci_frontend_enable_msi(dev, v);
if (ret)
goto error;
i = 0;
list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = xen_allocate_pirq(v[i], 0, /* not sharable */
- (type == PCI_CAP_ID_MSIX) ?
- "pcifront-msi-x" : "pcifront-msi");
- if (irq < 0) {
- ret = -1;
+ irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0,
+ (type == PCI_CAP_ID_MSIX) ?
+ "pcifront-msi-x" :
+ "pcifront-msi");
+ if (irq < 0)
goto free;
- }
-
- ret = set_irq_msi(irq, msidesc);
- if (ret)
- goto error_while;
i++;
}
kfree(v);
return 0;
-error_while:
- unbind_from_irqhandler(irq, NULL);
error:
- if (ret == -ENODEV)
- dev_err(&dev->dev, "Xen PCI frontend has not registered" \
- " MSI/MSI-X support!\n");
+ dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
free:
kfree(v);
return ret;
xen_pci_frontend_disable_msix(dev);
else
xen_pci_frontend_disable_msi(dev);
+
+ /* Free the IRQ's and the msidesc using the generic code. */
+ default_teardown_msi_irqs(dev);
}
static void xen_teardown_msi_irq(unsigned int irq)
xen_destroy_irq(irq);
}
+#ifdef CONFIG_XEN_DOM0
static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
- int irq, ret;
+ int ret = 0;
struct msi_desc *msidesc;
list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = xen_create_msi_irq(dev, msidesc, type);
- if (irq < 0)
- return -1;
+ struct physdev_map_pirq map_irq;
- ret = set_irq_msi(irq, msidesc);
- if (ret)
- goto error;
- }
- return 0;
+ memset(&map_irq, 0, sizeof(map_irq));
+ map_irq.domid = DOMID_SELF;
+ map_irq.type = MAP_PIRQ_TYPE_MSI;
+ map_irq.index = -1;
+ map_irq.pirq = -1;
+ map_irq.bus = dev->bus->number;
+ map_irq.devfn = dev->devfn;
-error:
- xen_destroy_irq(irq);
+ if (type == PCI_CAP_ID_MSIX) {
+ int pos;
+ u32 table_offset, bir;
+
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+
+ pci_read_config_dword(dev, pos + PCI_MSIX_TABLE,
+ &table_offset);
+ bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
+
+ map_irq.table_base = pci_resource_start(dev, bir);
+ map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
+ }
+
+ ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
+ if (ret) {
+ dev_warn(&dev->dev, "xen map irq failed %d\n", ret);
+ goto out;
+ }
+
+ ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
+ map_irq.pirq, map_irq.index,
+ (type == PCI_CAP_ID_MSIX) ?
+ "msi-x" : "msi");
+ if (ret < 0)
+ goto out;
+ }
+ ret = 0;
+out:
return ret;
}
#endif
+#endif
static int xen_pcifront_enable_irq(struct pci_dev *dev)
{
int rc;
int share = 1;
+ u8 gsi;
- dev_info(&dev->dev, "Xen PCI enabling IRQ: %d\n", dev->irq);
-
- if (dev->irq < 0)
- return -EINVAL;
+ rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
+ if (rc < 0) {
+ dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n",
+ rc);
+ return rc;
+ }
- if (dev->irq < NR_IRQS_LEGACY)
+ if (gsi < NR_IRQS_LEGACY)
share = 0;
- rc = xen_allocate_pirq(dev->irq, share, "pcifront");
+ rc = xen_allocate_pirq(gsi, share, "pcifront");
if (rc < 0) {
- dev_warn(&dev->dev, "Xen PCI IRQ: %d, failed to register:%d\n",
- dev->irq, rc);
+ dev_warn(&dev->dev, "Xen PCI: failed to register GSI%d: %d\n",
+ gsi, rc);
return rc;
}
+
+ dev->irq = rc;
+ dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq);
return 0;
}
#include <linux/serial_reg.h>
#include <linux/serial_8250.h>
+#include <asm/ce4100.h>
#include <asm/setup.h>
#include <asm/io.h>
x86_init.resources.probe_roms = x86_init_noop;
x86_init.mpparse.get_smp_config = x86_init_uint_noop;
x86_init.mpparse.find_smp_config = sdv_find_smp_config;
+ x86_init.pci.init = ce4100_pci_init;
}
* wasted bootmem) and hand off chunks of it to callers.
*/
res = alloc_bootmem(chunk_size);
- if (!res)
- return NULL;
+ BUG_ON(!res);
prom_early_allocated += chunk_size;
memset(res, 0, chunk_size);
free_mem = chunk_size;
memset(bd2, 0, sizeof(struct bau_desc));
bd2->header.sw_ack_flag = 1;
/*
- * base_dest_nodeid is the nasid (pnode<<1) of the first uvhub
+ * base_dest_nodeid is the nasid of the first uvhub
* in the partition. The bit map will indicate uvhub numbers,
* which are 0-N in a partition. Pnodes are unique system-wide.
*/
- bd2->header.base_dest_nodeid = uv_partition_base_pnode << 1;
+ bd2->header.base_dest_nodeid = UV_PNODE_TO_NASID(uv_partition_base_pnode);
bd2->header.dest_subnodeid = 0x10; /* the LB */
bd2->header.command = UV_NET_ENDPOINT_INTD;
bd2->header.int_both = 1;
unsigned long mmr_offset, int limit)
{
const struct cpumask *eligible_cpu = cpumask_of(cpu);
- struct irq_cfg *cfg = get_irq_chip_data(irq);
+ struct irq_cfg *cfg = irq_get_chip_data(irq);
unsigned long mmr_value;
struct uv_IO_APIC_route_entry *entry;
int mmr_pnode, err;
else
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
+ irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
irq_name);
mmr_value = 0;
static struct irqaction master_action = {
.handler = piix4_master_intr,
.name = "PIIX4-8259",
+ .flags = IRQF_NO_THREAD,
};
static struct irqaction cascade_action = {
.handler = no_action,
.name = "cascade",
+ .flags = IRQF_NO_THREAD,
};
static inline void set_piix4_virtual_irq_type(void)
chip = &cobalt_irq_type;
if (chip)
- set_irq_chip(i, chip);
+ irq_set_chip(i, chip);
}
setup_irq(CO_IRQ_8259, &master_action);
help
Enable statistics output and various tuning options in debugfs.
Enabling this option may incur a significant performance overhead.
+
+config XEN_DEBUG
+ bool "Enable Xen debug checks"
+ depends on XEN
+ default n
+ help
+ Enable various WARN_ON checks in the Xen MMU code.
+ Enabling this option WILL incur a significant performance overhead.
xen_setup_features();
- pv_info = xen_info;
- pv_info.kernel_rpl = 0;
+ pv_info.name = "Xen HVM";
xen_domain_type = XEN_HVM_DOMAIN;
return 0;
}
-void xen_hvm_init_shared_info(void)
+void __ref xen_hvm_init_shared_info(void)
{
int cpu;
struct xen_add_to_physmap xatp;
switch (action) {
case CPU_UP_PREPARE:
per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+ if (xen_have_vector_callback)
+ xen_init_lock_cpu(cpu);
break;
default:
break;
if (xen_feature(XENFEAT_hvm_callback_vector))
xen_have_vector_callback = 1;
+ xen_hvm_smp_init();
register_cpu_notifier(&xen_hvm_cpu_notifier);
xen_unplug_emulated_devices();
have_vcpu_info_placement = 0;
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/memblock.h>
+#include <linux/seq_file.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
if (val & _PAGE_PRESENT) {
unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
pteval_t flags = val & PTE_FLAGS_MASK;
- unsigned long mfn = pfn_to_mfn(pfn);
+ unsigned long mfn;
+ if (!xen_feature(XENFEAT_auto_translated_physmap))
+ mfn = get_phys_to_machine(pfn);
+ else
+ mfn = pfn;
/*
* If there's no mfn for the pfn, then just create an
* empty non-present pte. Unfortunately this loses
if (unlikely(mfn == INVALID_P2M_ENTRY)) {
mfn = 0;
flags = 0;
+ } else {
+ /*
+ * Paramount to do this test _after_ the
+ * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY &
+ * IDENTITY_FRAME_BIT resolves to true.
+ */
+ mfn &= ~FOREIGN_FRAME_BIT;
+ if (mfn & IDENTITY_FRAME_BIT) {
+ mfn &= ~IDENTITY_FRAME_BIT;
+ flags |= _PAGE_IOMAP;
+ }
}
-
val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
}
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
+#ifdef CONFIG_XEN_DEBUG
+pte_t xen_make_pte_debug(pteval_t pte)
+{
+ phys_addr_t addr = (pte & PTE_PFN_MASK);
+ phys_addr_t other_addr;
+ bool io_page = false;
+ pte_t _pte;
+
+ if (pte & _PAGE_IOMAP)
+ io_page = true;
+
+ _pte = xen_make_pte(pte);
+
+ if (!addr)
+ return _pte;
+
+ if (io_page &&
+ (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
+ other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
+ WARN(addr != other_addr,
+ "0x%lx is using VM_IO, but it is 0x%lx!\n",
+ (unsigned long)addr, (unsigned long)other_addr);
+ } else {
+ pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
+ other_addr = (_pte.pte & PTE_PFN_MASK);
+ WARN((addr == other_addr) && (!io_page) && (!iomap_set),
+ "0x%lx is missing VM_IO (and wasn't fixed)!\n",
+ (unsigned long)addr);
+ }
+
+ return _pte;
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
+#endif
+
pgd_t xen_make_pgd(pgdval_t pgd)
{
pgd = pte_pfn_to_mfn(pgd);
*/
void xen_mm_pin_all(void)
{
- unsigned long flags;
struct page *page;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
if (!PagePinned(page)) {
}
}
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
/*
*/
void xen_mm_unpin_all(void)
{
- unsigned long flags;
struct page *page;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
if (PageSavePinned(page)) {
}
}
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
static __init void xen_post_allocator_init(void)
{
+#ifdef CONFIG_XEN_DEBUG
+ pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
+#endif
pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
in_frames[i] = virt_to_mfn(vaddr);
MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
- set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+ __set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
if (out_frames)
out_frames[i] = virt_to_pfn(vaddr);
#ifdef CONFIG_XEN_DEBUG_FS
+static int p2m_dump_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, p2m_dump_show, NULL);
+}
+
+static const struct file_operations p2m_dump_fops = {
+ .open = p2m_dump_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
static struct dentry *d_mmu_debug;
static int __init xen_mmu_debugfs(void)
debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug,
&mmu_stats.prot_commit_batched);
+ debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
return 0;
}
fs_initcall(xen_mmu_debugfs);
* P2M_PER_PAGE depends on the architecture, as a mfn is always
* unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
* 512 and 1024 entries respectively.
+ *
+ * In short, these structures contain the Machine Frame Number (MFN) of the PFN.
+ *
+ * However not all entries are filled with MFNs. Specifically for all other
+ * leaf entries, or for the top root, or middle one, for which there is a void
+ * entry, we assume it is "missing". So (for example)
+ * pfn_to_mfn(0x90909090)=INVALID_P2M_ENTRY.
+ *
+ * We also have the possibility of setting 1-1 mappings on certain regions, so
+ * that:
+ * pfn_to_mfn(0xc0000)=0xc0000
+ *
+ * The benefit of this is, that we can assume for non-RAM regions (think
+ * PCI BARs, or ACPI spaces), we can create mappings easily b/c we
+ * get the PFN value to match the MFN.
+ *
+ * For this to work efficiently we have one new page p2m_identity and
+ * allocate (via reserved_brk) any other pages we need to cover the sides
+ * (1GB or 4MB boundary violations). All entries in p2m_identity are set to
+ * INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs,
+ * no other fancy value).
+ *
+ * On lookup we spot that the entry points to p2m_identity and return the
+ * identity value instead of dereferencing and returning INVALID_P2M_ENTRY.
+ * If the entry points to an allocated page, we just proceed as before and
+ * return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in
+ * appropriate functions (pfn_to_mfn).
+ *
+ * The reason for having the IDENTITY_FRAME_BIT instead of just returning the
+ * PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a
+ * non-identity pfn. To protect ourselves against we elect to set (and get) the
+ * IDENTITY_FRAME_BIT on all identity mapped PFNs.
+ *
+ * This simplistic diagram is used to explain the more subtle piece of code.
+ * There is also a digram of the P2M at the end that can help.
+ * Imagine your E820 looking as so:
+ *
+ * 1GB 2GB
+ * /-------------------+---------\/----\ /----------\ /---+-----\
+ * | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM |
+ * \-------------------+---------/\----/ \----------/ \---+-----/
+ * ^- 1029MB ^- 2001MB
+ *
+ * [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100),
+ * 2048MB = 524288 (0x80000)]
+ *
+ * And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB
+ * is actually not present (would have to kick the balloon driver to put it in).
+ *
+ * When we are told to set the PFNs for identity mapping (see patch: "xen/setup:
+ * Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start
+ * of the PFN and the end PFN (263424 and 512256 respectively). The first step
+ * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page
+ * covers 512^2 of page estate (1GB) and in case the start or end PFN is not
+ * aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn
+ * to end pfn. We reserve_brk top leaf pages if they are missing (means they
+ * point to p2m_mid_missing).
+ *
+ * With the E820 example above, 263424 is not 1GB aligned so we allocate a
+ * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000.
+ * Each entry in the allocate page is "missing" (points to p2m_missing).
+ *
+ * Next stage is to determine if we need to do a more granular boundary check
+ * on the 4MB (or 2MB depending on architecture) off the start and end pfn's.
+ * We check if the start pfn and end pfn violate that boundary check, and if
+ * so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer
+ * granularity of setting which PFNs are missing and which ones are identity.
+ * In our example 263424 and 512256 both fail the check so we reserve_brk two
+ * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing"
+ * values) and assign them to p2m[1][2] and p2m[1][488] respectively.
+ *
+ * At this point we would at minimum reserve_brk one page, but could be up to
+ * three. Each call to set_phys_range_identity has at maximum a three page
+ * cost. If we were to query the P2M at this stage, all those entries from
+ * start PFN through end PFN (so 1029MB -> 2001MB) would return
+ * INVALID_P2M_ENTRY ("missing").
+ *
+ * The next step is to walk from the start pfn to the end pfn setting
+ * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity.
+ * If we find that the middle leaf is pointing to p2m_missing we can swap it
+ * over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this
+ * point we do not need to worry about boundary aligment (so no need to
+ * reserve_brk a middle page, figure out which PFNs are "missing" and which
+ * ones are identity), as that has been done earlier. If we find that the
+ * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference
+ * that page (which covers 512 PFNs) and set the appropriate PFN with
+ * IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we
+ * set from p2m[1][2][256->511] and p2m[1][488][0->256] with
+ * IDENTITY_FRAME_BIT set.
+ *
+ * All other regions that are void (or not filled) either point to p2m_missing
+ * (considered missing) or have the default value of INVALID_P2M_ENTRY (also
+ * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511]
+ * contain the INVALID_P2M_ENTRY value and are considered "missing."
+ *
+ * This is what the p2m ends up looking (for the E820 above) with this
+ * fabulous drawing:
+ *
+ * p2m /--------------\
+ * /-----\ | &mfn_list[0],| /-----------------\
+ * | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. |
+ * |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] |
+ * | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] |
+ * |-----| \ | [p2m_identity]+\\ | .... |
+ * | 2 |--\ \-------------------->| ... | \\ \----------------/
+ * |-----| \ \---------------/ \\
+ * | 3 |\ \ \\ p2m_identity
+ * |-----| \ \-------------------->/---------------\ /-----------------\
+ * | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... |
+ * \-----/ / | [p2m_identity]+-->| ..., ~0 |
+ * / /---------------\ | .... | \-----------------/
+ * / | IDENTITY[@0] | /-+-[x], ~0, ~0.. |
+ * / | IDENTITY[@256]|<----/ \---------------/
+ * / | ~0, ~0, .... |
+ * | \---------------/
+ * |
+ * p2m_missing p2m_missing
+ * /------------------\ /------------\
+ * | [p2m_mid_missing]+---->| ~0, ~0, ~0 |
+ * | [p2m_mid_missing]+---->| ..., ~0 |
+ * \------------------/ \------------/
+ *
+ * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
*/
#include <linux/init.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/sched.h>
+#include <linux/seq_file.h>
#include <asm/cache.h>
#include <asm/setup.h>
static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
+static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE);
+
RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
+/* We might hit two boundary violations at the start and end, at max each
+ * boundary violation will require three middle nodes. */
+RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
+
static inline unsigned p2m_top_index(unsigned long pfn)
{
BUG_ON(pfn >= MAX_P2M_PFN);
* - After resume we're called from within stop_machine, but the mfn
* tree should alreay be completely allocated.
*/
-void xen_build_mfn_list_list(void)
+void __ref xen_build_mfn_list_list(void)
{
unsigned long pfn;
p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_init(p2m_top);
+ p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_init(p2m_identity);
+
/*
* The domain builder gives us a pre-constructed p2m array in
* mfn_list for all the pages initially given to us, so we just
mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
+ /*
+ * The INVALID_P2M_ENTRY is filled in both p2m_*identity
+ * and in p2m_*missing, so returning the INVALID_P2M_ENTRY
+ * would be wrong.
+ */
+ if (p2m_top[topidx][mididx] == p2m_identity)
+ return IDENTITY_FRAME(pfn);
+
return p2m_top[topidx][mididx][idx];
}
EXPORT_SYMBOL_GPL(get_phys_to_machine);
p2m_top_mfn_p[topidx] = mid_mfn;
}
- if (p2m_top[topidx][mididx] == p2m_missing) {
+ if (p2m_top[topidx][mididx] == p2m_identity ||
+ p2m_top[topidx][mididx] == p2m_missing) {
/* p2m leaf page is missing */
unsigned long *p2m;
+ unsigned long *p2m_orig = p2m_top[topidx][mididx];
p2m = alloc_p2m_page();
if (!p2m)
p2m_init(p2m);
- if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing)
+ if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig)
free_p2m_page(p2m);
else
mid_mfn[mididx] = virt_to_mfn(p2m);
return true;
}
+bool __early_alloc_p2m(unsigned long pfn)
+{
+ unsigned topidx, mididx, idx;
+
+ topidx = p2m_top_index(pfn);
+ mididx = p2m_mid_index(pfn);
+ idx = p2m_index(pfn);
+
+ /* Pfff.. No boundary cross-over, lets get out. */
+ if (!idx)
+ return false;
+
+ WARN(p2m_top[topidx][mididx] == p2m_identity,
+ "P2M[%d][%d] == IDENTITY, should be MISSING (or alloced)!\n",
+ topidx, mididx);
+
+ /*
+ * Could be done by xen_build_dynamic_phys_to_machine..
+ */
+ if (p2m_top[topidx][mididx] != p2m_missing)
+ return false;
+
+ /* Boundary cross-over for the edges: */
+ if (idx) {
+ unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+ p2m_init(p2m);
+
+ p2m_top[topidx][mididx] = p2m;
+
+ }
+ return idx != 0;
+}
+unsigned long set_phys_range_identity(unsigned long pfn_s,
+ unsigned long pfn_e)
+{
+ unsigned long pfn;
+
+ if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
+ return 0;
+
+ if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
+ return pfn_e - pfn_s;
+
+ if (pfn_s > pfn_e)
+ return 0;
+
+ for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
+ pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
+ pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
+ {
+ unsigned topidx = p2m_top_index(pfn);
+ if (p2m_top[topidx] == p2m_mid_missing) {
+ unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+ p2m_mid_init(mid);
+
+ p2m_top[topidx] = mid;
+ }
+ }
+
+ __early_alloc_p2m(pfn_s);
+ __early_alloc_p2m(pfn_e);
+
+ for (pfn = pfn_s; pfn < pfn_e; pfn++)
+ if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
+ break;
+
+ if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s),
+ "Identity mapping failed. We are %ld short of 1-1 mappings!\n",
+ (pfn_e - pfn_s) - (pfn - pfn_s)))
+ printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn);
+
+ return pfn - pfn_s;
+}
+
/* Try to install p2m mapping; fail if intermediate bits missing */
bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
unsigned topidx, mididx, idx;
+ if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
+ BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+ return true;
+ }
if (unlikely(pfn >= MAX_P2M_PFN)) {
BUG_ON(mfn != INVALID_P2M_ENTRY);
return true;
mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
+ /* For sparse holes were the p2m leaf has real PFN along with
+ * PCI holes, stick in the PFN as the MFN value.
+ */
+ if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) {
+ if (p2m_top[topidx][mididx] == p2m_identity)
+ return true;
+
+ /* Swap over from MISSING to IDENTITY if needed. */
+ if (p2m_top[topidx][mididx] == p2m_missing) {
+ WARN_ON(cmpxchg(&p2m_top[topidx][mididx], p2m_missing,
+ p2m_identity) != p2m_missing);
+ return true;
+ }
+ }
+
if (p2m_top[topidx][mididx] == p2m_missing)
return mfn == INVALID_P2M_ENTRY;
bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
- if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
- BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
- return true;
- }
-
if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
if (!alloc_p2m(pfn))
return false;
{
unsigned long flags;
unsigned long pfn;
- unsigned long address;
+ unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
unsigned long flags;
unsigned long mfn;
unsigned long pfn;
- unsigned long address;
+ unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
return ret;
}
EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
+
+#ifdef CONFIG_XEN_DEBUG_FS
+
+int p2m_dump_show(struct seq_file *m, void *v)
+{
+ static const char * const level_name[] = { "top", "middle",
+ "entry", "abnormal" };
+ static const char * const type_name[] = { "identity", "missing",
+ "pfn", "abnormal"};
+#define TYPE_IDENTITY 0
+#define TYPE_MISSING 1
+#define TYPE_PFN 2
+#define TYPE_UNKNOWN 3
+ unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0;
+ unsigned int uninitialized_var(prev_level);
+ unsigned int uninitialized_var(prev_type);
+
+ if (!p2m_top)
+ return 0;
+
+ for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn++) {
+ unsigned topidx = p2m_top_index(pfn);
+ unsigned mididx = p2m_mid_index(pfn);
+ unsigned idx = p2m_index(pfn);
+ unsigned lvl, type;
+
+ lvl = 4;
+ type = TYPE_UNKNOWN;
+ if (p2m_top[topidx] == p2m_mid_missing) {
+ lvl = 0; type = TYPE_MISSING;
+ } else if (p2m_top[topidx] == NULL) {
+ lvl = 0; type = TYPE_UNKNOWN;
+ } else if (p2m_top[topidx][mididx] == NULL) {
+ lvl = 1; type = TYPE_UNKNOWN;
+ } else if (p2m_top[topidx][mididx] == p2m_identity) {
+ lvl = 1; type = TYPE_IDENTITY;
+ } else if (p2m_top[topidx][mididx] == p2m_missing) {
+ lvl = 1; type = TYPE_MISSING;
+ } else if (p2m_top[topidx][mididx][idx] == 0) {
+ lvl = 2; type = TYPE_UNKNOWN;
+ } else if (p2m_top[topidx][mididx][idx] == IDENTITY_FRAME(pfn)) {
+ lvl = 2; type = TYPE_IDENTITY;
+ } else if (p2m_top[topidx][mididx][idx] == INVALID_P2M_ENTRY) {
+ lvl = 2; type = TYPE_MISSING;
+ } else if (p2m_top[topidx][mididx][idx] == pfn) {
+ lvl = 2; type = TYPE_PFN;
+ } else if (p2m_top[topidx][mididx][idx] != pfn) {
+ lvl = 2; type = TYPE_PFN;
+ }
+ if (pfn == 0) {
+ prev_level = lvl;
+ prev_type = type;
+ }
+ if (pfn == MAX_DOMAIN_PAGES-1) {
+ lvl = 3;
+ type = TYPE_UNKNOWN;
+ }
+ if (prev_type != type) {
+ seq_printf(m, " [0x%lx->0x%lx] %s\n",
+ prev_pfn_type, pfn, type_name[prev_type]);
+ prev_pfn_type = pfn;
+ prev_type = type;
+ }
+ if (prev_level != lvl) {
+ seq_printf(m, " [0x%lx->0x%lx] level %s\n",
+ prev_pfn_level, pfn, level_name[prev_level]);
+ prev_pfn_level = pfn;
+ prev_level = lvl;
+ }
+ }
+ return 0;
+#undef TYPE_IDENTITY
+#undef TYPE_MISSING
+#undef TYPE_PFN
+#undef TYPE_UNKNOWN
+}
+#endif
static __init void xen_add_extra_mem(unsigned long pages)
{
+ unsigned long pfn;
+
u64 size = (u64)pages * PAGE_SIZE;
u64 extra_start = xen_extra_mem_start + xen_extra_mem_size;
xen_extra_mem_size += size;
xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
+
+ for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++)
+ __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n",
start, end, ret);
if (ret == 1) {
- set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+ __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
len++;
}
}
return released;
}
+static unsigned long __init xen_set_identity(const struct e820entry *list,
+ ssize_t map_size)
+{
+ phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS;
+ phys_addr_t start_pci = last;
+ const struct e820entry *entry;
+ unsigned long identity = 0;
+ int i;
+
+ for (i = 0, entry = list; i < map_size; i++, entry++) {
+ phys_addr_t start = entry->addr;
+ phys_addr_t end = start + entry->size;
+
+ if (start < last)
+ start = last;
+
+ if (end <= start)
+ continue;
+
+ /* Skip over the 1MB region. */
+ if (last > end)
+ continue;
+
+ if (entry->type == E820_RAM) {
+ if (start > start_pci)
+ identity += set_phys_range_identity(
+ PFN_UP(start_pci), PFN_DOWN(start));
+
+ /* Without saving 'last' we would gooble RAM too
+ * at the end of the loop. */
+ last = end;
+ start_pci = end;
+ continue;
+ }
+ start_pci = min(start, start_pci);
+ last = end;
+ }
+ if (last > start_pci)
+ identity += set_phys_range_identity(
+ PFN_UP(start_pci), PFN_DOWN(last));
+ return identity;
+}
/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
char * __init xen_memory_setup(void)
{
static struct e820entry map[E820MAX] __initdata;
+ static struct e820entry map_raw[E820MAX] __initdata;
unsigned long max_pfn = xen_start_info->nr_pages;
unsigned long long mem_end;
struct xen_memory_map memmap;
unsigned long extra_pages = 0;
unsigned long extra_limit;
+ unsigned long identity_pages = 0;
int i;
int op;
}
BUG_ON(rc);
+ memcpy(map_raw, map, sizeof(map));
e820.nr_map = 0;
xen_extra_mem_start = mem_end;
for (i = 0; i < memmap.nr_entries; i++) {
end -= delta;
extra_pages += PFN_DOWN(delta);
+ /*
+ * Set RAM below 4GB that is not for us to be unusable.
+ * This prevents "System RAM" address space from being
+ * used as potential resource for I/O address (happens
+ * when 'allocate_resource' is called).
+ */
+ if (delta &&
+ (xen_initial_domain() && end < 0x100000000ULL))
+ e820_add_region(end, delta, E820_UNUSABLE);
}
if (map[i].size > 0 && end > xen_extra_mem_start)
xen_add_extra_mem(extra_pages);
+ /*
+ * Set P2M for all non-RAM pages and E820 gaps to be identity
+ * type PFNs. We supply it with the non-sanitized version
+ * of the E820.
+ */
+ identity_pages = xen_set_identity(map_raw, memmap.nr_entries);
+ printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages);
return "Xen";
}
xen_fill_possible_map();
xen_init_spinlocks();
}
+
+static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
+{
+ native_smp_prepare_cpus(max_cpus);
+ WARN_ON(xen_smp_intr_init(0));
+
+ if (!xen_have_vector_callback)
+ return;
+ xen_init_lock_cpu(0);
+ xen_init_spinlocks();
+}
+
+static int __cpuinit xen_hvm_cpu_up(unsigned int cpu)
+{
+ int rc;
+ rc = native_cpu_up(cpu);
+ WARN_ON (xen_smp_intr_init(cpu));
+ return rc;
+}
+
+static void xen_hvm_cpu_die(unsigned int cpu)
+{
+ unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
+ native_cpu_die(cpu);
+}
+
+void __init xen_hvm_smp_init(void)
+{
+ smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
+ smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
+ smp_ops.cpu_up = xen_hvm_cpu_up;
+ smp_ops.cpu_die = xen_hvm_cpu_die;
+ smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
+ smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
+}
#include "xen-ops.h"
#include "mmu.h"
-void xen_pre_suspend(void)
+void xen_arch_pre_suspend(void)
{
xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
xen_start_info->console.domU.mfn =
BUG();
}
-void xen_hvm_post_suspend(int suspend_cancelled)
+void xen_arch_hvm_post_suspend(int suspend_cancelled)
{
+#ifdef CONFIG_XEN_PVHVM
int cpu;
xen_hvm_init_shared_info();
xen_callback_vector();
xen_setup_runstate_info(cpu);
}
}
+#endif
}
-void xen_post_suspend(int suspend_cancelled)
+void xen_arch_post_suspend(int suspend_cancelled)
{
xen_build_mfn_list_list();
name = "<timer kasprintf failed>";
irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
- IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER,
+ IRQF_DISABLED|IRQF_PERCPU|
+ IRQF_NOBALANCING|IRQF_TIMER|
+ IRQF_FORCE_RESUME,
name, NULL);
evt = &per_cpu(xen_clock_events, cpu);
__FINIT
.pushsection .text
- .align PAGE_SIZE_asm
+ .align PAGE_SIZE
ENTRY(hypercall_page)
- .skip PAGE_SIZE_asm
+ .skip PAGE_SIZE
.popsection
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux")
#ifdef CONFIG_SMP
void xen_smp_init(void);
+void __init xen_hvm_smp_init(void);
extern cpumask_var_t xen_cpu_initialized_map;
#else
static inline void xen_smp_init(void) {}
+static inline void xen_hvm_smp_init(void) {}
#endif
#ifdef CONFIG_PARAVIRT_SPINLOCKS
#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
#endif
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
- signed long count;
#define RWSEM_UNLOCKED_VALUE 0x00000000
#define RWSEM_ACTIVE_BIAS 0x00000001
#define RWSEM_ACTIVE_MASK 0x0000ffff
#define RWSEM_WAITING_BIAS (-0x00010000)
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
- spinlock_t wait_lock;
- struct list_head wait_list;
-};
-
-#define __RWSEM_INITIALIZER(name) \
- { RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \
- LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
- sem->count = RWSEM_UNLOCKED_VALUE;
- spin_lock_init(&sem->wait_lock);
- INIT_LIST_HEAD(&sem->wait_list);
-}
/*
* lock for reading
return atomic_add_return(delta, (atomic_t *)(&sem->count));
}
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
- return (sem->count != 0);
-}
-
#endif /* _XTENSA_RWSEM_H */
update_process_times(user_mode(get_irq_regs()));
#endif
- write_seqlock(&xtime_lock);
-
- do_timer(1); /* Linux handler in kernel/timer.c */
+ xtime_update(1); /* Linux handler in kernel/time/timekeeping */
/* Note that writing CCOMPARE clears the interrupt. */
next += CCOUNT_PER_JIFFY;
set_linux_timer(next);
-
- write_sequnlock(&xtime_lock);
}
/* Allow platform to do something useful (Wdog). */
WARN_ON(!irqs_disabled());
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
- __blk_run_queue(q);
+ __blk_run_queue(q, false);
}
EXPORT_SYMBOL(blk_start_queue);
/**
* __blk_run_queue - run a single device queue
* @q: The queue to run
+ * @force_kblockd: Don't run @q->request_fn directly. Use kblockd.
*
* Description:
* See @blk_run_queue. This variant must be called with the queue lock
* held and interrupts disabled.
*
*/
-void __blk_run_queue(struct request_queue *q)
+void __blk_run_queue(struct request_queue *q, bool force_kblockd)
{
blk_remove_plug(q);
* Only recurse once to avoid overrunning the stack, let the unplug
* handling reinvoke the handler shortly if we already got there.
*/
- if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
+ if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
q->request_fn(q);
queue_flag_clear(QUEUE_FLAG_REENTER, q);
} else {
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
- __blk_run_queue(q);
+ __blk_run_queue(q, false);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_run_queue);
drive_stat_acct(rq, 1);
__elv_add_request(q, rq, where, 0);
- __blk_run_queue(q);
+ __blk_run_queue(q, false);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_insert_request);
}
EXPORT_SYMBOL(kblockd_schedule_work);
-int kblockd_schedule_delayed_work(struct request_queue *q,
- struct delayed_work *dwork, unsigned long delay)
-{
- return queue_delayed_work(kblockd_workqueue, dwork, delay);
-}
-EXPORT_SYMBOL(kblockd_schedule_delayed_work);
-
int __init blk_dev_init(void)
{
BUILD_BUG_ON(__REQ_NR_BITS > 8 *
/*
* Moving a request silently to empty queue_head may stall the
- * queue. Kick the queue in those cases.
+ * queue. Kick the queue in those cases. This function is called
+ * from request completion path and calling directly into
+ * request_fn may confuse the driver. Always use kblockd.
*/
if (was_empty && next_rq)
- __blk_run_queue(q);
+ __blk_run_queue(q, true);
}
static void pre_flush_end_io(struct request *rq, int error)
BUG();
}
- elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+ elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
return rq;
}
atomic_t done;
unsigned long flags;
struct completion *wait;
- bio_end_io_t *end_io;
};
static void bio_batch_end_io(struct bio *bio, int err)
else
clear_bit(BIO_UPTODATE, &bb->flags);
}
- if (bb) {
- if (bb->end_io)
- bb->end_io(bio, err);
- atomic_inc(&bb->done);
- complete(bb->wait);
- }
+ if (bb)
+ if (atomic_dec_and_test(&bb->done))
+ complete(bb->wait);
bio_put(bio);
}
/**
- * blkdev_issue_zeroout generate number of zero filed write bios
+ * blkdev_issue_zeroout - generate number of zero filed write bios
* @bdev: blockdev to issue
* @sector: start sector
* @nr_sects: number of sectors to write
int ret;
struct bio *bio;
struct bio_batch bb;
- unsigned int sz, issued = 0;
+ unsigned int sz;
DECLARE_COMPLETION_ONSTACK(wait);
- atomic_set(&bb.done, 0);
+ atomic_set(&bb.done, 1);
bb.flags = 1 << BIO_UPTODATE;
bb.wait = &wait;
- bb.end_io = NULL;
submit:
ret = 0;
break;
}
ret = 0;
- issued++;
+ atomic_inc(&bb.done);
submit_bio(WRITE, bio);
}
/* Wait for bios in-flight */
- while (issued != atomic_read(&bb.done))
+ if (!atomic_dec_and_test(&bb.done))
wait_for_completion(&wait);
if (!test_bit(BIO_UPTODATE, &bb.flags))
/* Throttling is performed over 100ms slice and after that slice is renewed */
static unsigned long throtl_slice = HZ/10; /* 100 ms */
+/* A workqueue to queue throttle related work */
+static struct workqueue_struct *kthrotld_workqueue;
+static void throtl_schedule_delayed_work(struct throtl_data *td,
+ unsigned long delay);
+
struct throtl_rb_root {
struct rb_root rb;
struct rb_node *left;
* tree of blkg (instead of traversing through hash list all
* the time.
*/
- tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
+
+ /*
+ * This is the common case when there are no blkio cgroups.
+ * Avoid lookup in this case
+ */
+ if (blkcg == &blkio_root_cgroup)
+ tg = &td->root_tg;
+ else
+ tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
/* Fill in device details for root group */
if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
update_min_dispatch_time(st);
if (time_before_eq(st->min_disptime, jiffies))
- throtl_schedule_delayed_work(td->queue, 0);
+ throtl_schedule_delayed_work(td, 0);
else
- throtl_schedule_delayed_work(td->queue,
- (st->min_disptime - jiffies));
+ throtl_schedule_delayed_work(td, (st->min_disptime - jiffies));
}
static inline void
}
/* Call with queue lock held */
-void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay)
+static void
+throtl_schedule_delayed_work(struct throtl_data *td, unsigned long delay)
{
- struct throtl_data *td = q->td;
struct delayed_work *dwork = &td->throtl_work;
if (total_nr_queued(td) > 0) {
* Cancel that and schedule a new one.
*/
__cancel_delayed_work(dwork);
- kblockd_schedule_delayed_work(q, dwork, delay);
+ queue_delayed_work(kthrotld_workqueue, dwork, delay);
throtl_log(td, "schedule work. delay=%lu jiffies=%lu",
delay, jiffies);
}
}
-EXPORT_SYMBOL(throtl_schedule_delayed_work);
static void
throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg)
smp_mb__after_atomic_inc();
/* Schedule a work now to process the limit change */
- throtl_schedule_delayed_work(td->queue, 0);
+ throtl_schedule_delayed_work(td, 0);
}
static void throtl_update_blkio_group_write_bps(void *key,
smp_mb__before_atomic_inc();
atomic_inc(&td->limits_changed);
smp_mb__after_atomic_inc();
- throtl_schedule_delayed_work(td->queue, 0);
+ throtl_schedule_delayed_work(td, 0);
}
static void throtl_update_blkio_group_read_iops(void *key,
smp_mb__before_atomic_inc();
atomic_inc(&td->limits_changed);
smp_mb__after_atomic_inc();
- throtl_schedule_delayed_work(td->queue, 0);
+ throtl_schedule_delayed_work(td, 0);
}
static void throtl_update_blkio_group_write_iops(void *key,
smp_mb__before_atomic_inc();
atomic_inc(&td->limits_changed);
smp_mb__after_atomic_inc();
- throtl_schedule_delayed_work(td->queue, 0);
+ throtl_schedule_delayed_work(td, 0);
}
void throtl_shutdown_timer_wq(struct request_queue *q)
static int __init throtl_init(void)
{
+ kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);
+ if (!kthrotld_workqueue)
+ panic("Failed to create kthrotld\n");
+
blkio_policy_register(&blkio_policy_throtl);
return 0;
}
}
static inline unsigned
-cfq_scaled_group_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
if (cfqd->cfq_latency) {
static inline void
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
- unsigned slice = cfq_scaled_group_slice(cfqd, cfqq);
+ unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
cfqq->slice_start = jiffies;
cfqq->slice_end = jiffies + slice;
*/
if (timed_out) {
if (cfq_cfqq_slice_new(cfqq))
- cfqq->slice_resid = cfq_scaled_group_slice(cfqd, cfqq);
+ cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
else
cfqq->slice_resid = cfqq->slice_end - jiffies;
cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
cfqd->busy_queues > 1) {
cfq_del_timer(cfqd, cfqq);
cfq_clear_cfqq_wait_request(cfqq);
- __blk_run_queue(cfqd->queue);
+ __blk_run_queue(cfqd->queue, false);
} else {
cfq_blkiocg_update_idle_time_stats(
&cfqq->cfqg->blkg);
* this new queue is RT and the current one is BE
*/
cfq_preempt_queue(cfqd, cfqq);
- __blk_run_queue(cfqd->queue);
+ __blk_run_queue(cfqd->queue, false);
}
}
{
struct cfq_io_context *cic = cfqd->active_cic;
+ /* If the queue already has requests, don't wait */
+ if (!RB_EMPTY_ROOT(&cfqq->sort_list))
+ return false;
+
/* If there are other queues in the group, don't wait */
if (cfqq->cfqg->nr_cfqq > 1)
return false;
struct request_queue *q = cfqd->queue;
spin_lock_irq(q->queue_lock);
- __blk_run_queue(cfqd->queue);
+ __blk_run_queue(cfqd->queue, false);
spin_unlock_irq(q->queue_lock);
}
*/
elv_drain_elevator(q);
while (q->rq.elvpriv) {
- __blk_run_queue(q);
+ __blk_run_queue(q, false);
spin_unlock_irq(q->queue_lock);
msleep(10);
spin_lock_irq(q->queue_lock);
* with anything. There's no point in delaying queue
* processing.
*/
- __blk_run_queue(q);
+ __blk_run_queue(q, false);
break;
case ELEVATOR_INSERT_SORT:
struct block_device *bdev = bdget_disk(disk, partno);
if (bdev) {
fsync_bdev(bdev);
- res = __invalidate_device(bdev);
+ res = __invalidate_device(bdev, true);
bdput(bdev);
}
return res;
return -EINVAL;
if (get_user(n, (int __user *) arg))
return -EFAULT;
- if (!(mode & FMODE_EXCL) &&
- blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
- return -EBUSY;
+ if (!(mode & FMODE_EXCL)) {
+ bdgrab(bdev);
+ if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
+ return -EBUSY;
+ }
ret = set_blocksize(bdev, n);
if (!(mode & FMODE_EXCL))
blkdev_put(bdev, mode | FMODE_EXCL);
u8 originally_enabled; /* True if GPE was originally enabled */
};
+struct acpi_gpe_notify_object {
+ struct acpi_namespace_node *node;
+ struct acpi_gpe_notify_object *next;
+};
+
union acpi_gpe_dispatch_info {
struct acpi_namespace_node *method_node; /* Method node for this GPE level */
struct acpi_gpe_handler_info *handler; /* Installed GPE handler */
- struct acpi_namespace_node *device_node; /* Parent _PRW device for implicit notify */
+ struct acpi_gpe_notify_object device; /* List of _PRW devices for implicit notify */
};
/*
acpi_status status;
struct acpi_gpe_event_info *local_gpe_event_info;
struct acpi_evaluate_info *info;
+ struct acpi_gpe_notify_object *notify_object;
ACPI_FUNCTION_TRACE(ev_asynch_execute_gpe_method);
* from this thread -- because handlers may in turn run other
* control methods.
*/
- status =
- acpi_ev_queue_notify_request(local_gpe_event_info->dispatch.
- device_node,
- ACPI_NOTIFY_DEVICE_WAKE);
+ status = acpi_ev_queue_notify_request(
+ local_gpe_event_info->dispatch.device.node,
+ ACPI_NOTIFY_DEVICE_WAKE);
+
+ notify_object = local_gpe_event_info->dispatch.device.next;
+ while (ACPI_SUCCESS(status) && notify_object) {
+ status = acpi_ev_queue_notify_request(
+ notify_object->node,
+ ACPI_NOTIFY_DEVICE_WAKE);
+ notify_object = notify_object->next;
+ }
+
break;
case ACPI_GPE_DISPATCH_METHOD:
acpi_status status = AE_BAD_PARAMETER;
struct acpi_gpe_event_info *gpe_event_info;
struct acpi_namespace_node *device_node;
+ struct acpi_gpe_notify_object *notify_object;
acpi_cpu_flags flags;
+ u8 gpe_dispatch_mask;
ACPI_FUNCTION_TRACE(acpi_setup_gpe_for_wake);
return_ACPI_STATUS(AE_BAD_PARAMETER);
}
+ flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
+
+ /* Ensure that we have a valid GPE number */
+
+ gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number);
+ if (!gpe_event_info) {
+ goto unlock_and_exit;
+ }
+
+ if (wake_device == ACPI_ROOT_OBJECT) {
+ goto out;
+ }
+
+ /*
+ * If there is no method or handler for this GPE, then the
+ * wake_device will be notified whenever this GPE fires (aka
+ * "implicit notify") Note: The GPE is assumed to be
+ * level-triggered (for windows compatibility).
+ */
+ gpe_dispatch_mask = gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK;
+ if (gpe_dispatch_mask != ACPI_GPE_DISPATCH_NONE
+ && gpe_dispatch_mask != ACPI_GPE_DISPATCH_NOTIFY) {
+ goto out;
+ }
+
/* Validate wake_device is of type Device */
device_node = ACPI_CAST_PTR(struct acpi_namespace_node, wake_device);
if (device_node->type != ACPI_TYPE_DEVICE) {
- return_ACPI_STATUS(AE_BAD_PARAMETER);
+ goto unlock_and_exit;
}
- flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
+ if (gpe_dispatch_mask == ACPI_GPE_DISPATCH_NONE) {
+ gpe_event_info->flags = (ACPI_GPE_DISPATCH_NOTIFY |
+ ACPI_GPE_LEVEL_TRIGGERED);
+ gpe_event_info->dispatch.device.node = device_node;
+ gpe_event_info->dispatch.device.next = NULL;
+ } else {
+ /* There are multiple devices to notify implicitly. */
- /* Ensure that we have a valid GPE number */
-
- gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number);
- if (gpe_event_info) {
- /*
- * If there is no method or handler for this GPE, then the
- * wake_device will be notified whenever this GPE fires (aka
- * "implicit notify") Note: The GPE is assumed to be
- * level-triggered (for windows compatibility).
- */
- if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) ==
- ACPI_GPE_DISPATCH_NONE) {
- gpe_event_info->flags =
- (ACPI_GPE_DISPATCH_NOTIFY |
- ACPI_GPE_LEVEL_TRIGGERED);
- gpe_event_info->dispatch.device_node = device_node;
+ notify_object = ACPI_ALLOCATE_ZEROED(sizeof(*notify_object));
+ if (!notify_object) {
+ status = AE_NO_MEMORY;
+ goto unlock_and_exit;
}
- gpe_event_info->flags |= ACPI_GPE_CAN_WAKE;
- status = AE_OK;
+ notify_object->node = device_node;
+ notify_object->next = gpe_event_info->dispatch.device.next;
+ gpe_event_info->dispatch.device.next = notify_object;
}
+ out:
+ gpe_event_info->flags |= ACPI_GPE_CAN_WAKE;
+ status = AE_OK;
+
+ unlock_and_exit:
acpi_os_release_lock(acpi_gbl_gpe_lock, flags);
return_ACPI_STATUS(status);
}
size_t count, loff_t *ppos)
{
static char *buf;
- static int uncopied_bytes;
+ static u32 max_size;
+ static u32 uncopied_bytes;
+
struct acpi_table_header table;
acpi_status status;
if (copy_from_user(&table, user_buf,
sizeof(struct acpi_table_header)))
return -EFAULT;
- uncopied_bytes = table.length;
- buf = kzalloc(uncopied_bytes, GFP_KERNEL);
+ uncopied_bytes = max_size = table.length;
+ buf = kzalloc(max_size, GFP_KERNEL);
if (!buf)
return -ENOMEM;
}
- if (uncopied_bytes < count) {
- kfree(buf);
+ if (buf == NULL)
+ return -EINVAL;
+
+ if ((*ppos > max_size) ||
+ (*ppos + count > max_size) ||
+ (*ppos + count < count) ||
+ (count > uncopied_bytes))
return -EINVAL;
- }
if (copy_from_user(buf + (*ppos), user_buf, count)) {
kfree(buf);
+ buf = NULL;
return -EFAULT;
}
if (!uncopied_bytes) {
status = acpi_install_method(buf);
kfree(buf);
+ buf = NULL;
if (ACPI_FAILURE(status))
return -EINVAL;
add_taint(TAINT_OVERRIDDEN_ACPI_TABLE);
acpi_status
acpi_os_read_memory(acpi_physical_address phys_addr, u32 * value, u32 width)
{
- u32 dummy;
void __iomem *virt_addr;
- int size = width / 8, unmap = 0;
+ unsigned int size = width / 8;
+ bool unmap = false;
+ u32 dummy;
rcu_read_lock();
virt_addr = acpi_map_vaddr_lookup(phys_addr, size);
- rcu_read_unlock();
if (!virt_addr) {
+ rcu_read_unlock();
virt_addr = acpi_os_ioremap(phys_addr, size);
- unmap = 1;
+ if (!virt_addr)
+ return AE_BAD_ADDRESS;
+ unmap = true;
}
+
if (!value)
value = &dummy;
if (unmap)
iounmap(virt_addr);
+ else
+ rcu_read_unlock();
return AE_OK;
}
acpi_os_write_memory(acpi_physical_address phys_addr, u32 value, u32 width)
{
void __iomem *virt_addr;
- int size = width / 8, unmap = 0;
+ unsigned int size = width / 8;
+ bool unmap = false;
rcu_read_lock();
virt_addr = acpi_map_vaddr_lookup(phys_addr, size);
- rcu_read_unlock();
if (!virt_addr) {
+ rcu_read_unlock();
virt_addr = acpi_os_ioremap(phys_addr, size);
- unmap = 1;
+ if (!virt_addr)
+ return AE_BAD_ADDRESS;
+ unmap = true;
}
switch (width) {
if (unmap)
iounmap(virt_addr);
+ else
+ rcu_read_unlock();
return AE_OK;
}
if (!device)
return 0;
+ /* Is this device able to support video switching ? */
+ if (ACPI_SUCCESS(acpi_get_handle(device->handle, "_DOD", &h_dummy)) ||
+ ACPI_SUCCESS(acpi_get_handle(device->handle, "_DOS", &h_dummy)))
+ video_caps |= ACPI_VIDEO_OUTPUT_SWITCHING;
+
/* Is this device able to retrieve a video ROM ? */
if (ACPI_SUCCESS(acpi_get_handle(device->handle, "_ROM", &h_dummy)))
video_caps |= ACPI_VIDEO_ROM_AVAILABLE;
struct acpi_device *dev = container_of(node,
struct acpi_device,
wakeup_list);
- if (device_can_wakeup(&dev->dev))
+ if (device_can_wakeup(&dev->dev)) {
+ /* Button GPEs are supposed to be always enabled. */
+ acpi_enable_gpe(dev->wakeup.gpe_device,
+ dev->wakeup.gpe_number);
device_set_wakeup_enable(&dev->dev, true);
+ }
}
mutex_unlock(&acpi_device_lock);
return 0;
}
skb = alloc_skb(sizeof(*header), GFP_ATOMIC);
- if (!skb && net_ratelimit()) {
- dev_warn(&card->dev->dev, "Failed to allocate sk_buff in popen()\n");
+ if (!skb) {
+ if (net_ratelimit())
+ dev_warn(&card->dev->dev, "Failed to allocate sk_buff in popen()\n");
return -ENOMEM;
}
header = (void *)skb_put(skb, sizeof(*header));
obj-$(CONFIG_BLK_DEV_DRBD) += drbd/
obj-$(CONFIG_BLK_DEV_RBD) += rbd.o
-swim_mod-objs := swim.o swim_asm.o
+swim_mod-y := swim.o swim_asm.o
#
obj-$(CONFIG_ATA_OVER_ETH) += aoe.o
-aoe-objs := aoeblk.o aoechr.o aoecmd.o aoedev.o aoemain.o aoenet.o
+aoe-y := aoeblk.o aoechr.o aoecmd.o aoedev.o aoemain.o aoenet.o
sector_t total_size;
InquiryData_struct *inq_buff = NULL;
- for (logvol = 0; logvol < CISS_MAX_LUN; logvol++) {
+ for (logvol = 0; logvol <= h->highest_lun; logvol++) {
if (!h->drv[logvol])
continue;
if (memcmp(h->drv[logvol]->LunID, drv->LunID,
struct block_device *bdev = opened_bdev[cnt];
if (!bdev || ITYPE(drive_state[cnt].fd_device) != type)
continue;
- __invalidate_device(bdev);
+ __invalidate_device(bdev, true);
}
mutex_unlock(&open_lock);
} else {
#include <asm/uaccess.h>
-static DEFINE_MUTEX(loop_mutex);
static LIST_HEAD(loop_devices);
static DEFINE_MUTEX(loop_devices_mutex);
{
struct loop_device *lo = bdev->bd_disk->private_data;
- mutex_lock(&loop_mutex);
mutex_lock(&lo->lo_ctl_mutex);
lo->lo_refcnt++;
mutex_unlock(&lo->lo_ctl_mutex);
- mutex_unlock(&loop_mutex);
return 0;
}
struct loop_device *lo = disk->private_data;
int err;
- mutex_lock(&loop_mutex);
mutex_lock(&lo->lo_ctl_mutex);
if (--lo->lo_refcnt)
out:
mutex_unlock(&lo->lo_ctl_mutex);
out_unlocked:
- mutex_unlock(&loop_mutex);
return 0;
}
static void loop_free(struct loop_device *lo)
{
+ if (!lo->lo_queue->queue_lock)
+ lo->lo_queue->queue_lock = &lo->lo_queue->__queue_lock;
+
blk_cleanup_queue(lo->lo_queue);
put_disk(lo->lo_disk);
list_del(&lo->lo_list);
#define DBG_BLKDEV 0x0100
#define DBG_RX 0x0200
#define DBG_TX 0x0400
-static DEFINE_MUTEX(nbd_mutex);
static unsigned int debugflags;
#endif /* NDEBUG */
dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n",
lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg);
- mutex_lock(&nbd_mutex);
mutex_lock(&lo->tx_lock);
error = __nbd_ioctl(bdev, lo, cmd, arg);
mutex_unlock(&lo->tx_lock);
- mutex_unlock(&nbd_mutex);
return error;
}
#define EXTENDED (1<<EXT_SHIFT)
#define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED))
#define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
+#define EMULATED_HD_DISK_MINOR_OFFSET (0)
+#define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
+#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16))
+#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4)
#define DEV_NAME "xvd" /* name in /dev */
info->shadow[id].request = req;
ring_req->id = id;
- ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req);
+ ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
ring_req->handle = info->handle;
ring_req->operation = rq_data_dir(req) ?
rq_data_dir(req) );
info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
- ring_req->seg[i] =
+ ring_req->u.rw.seg[i] =
(struct blkif_request_segment) {
.gref = ref,
.first_sect = fsect,
info->feature_flush ? "enabled" : "disabled");
}
+static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
+{
+ int major;
+ major = BLKIF_MAJOR(vdevice);
+ *minor = BLKIF_MINOR(vdevice);
+ switch (major) {
+ case XEN_IDE0_MAJOR:
+ *offset = (*minor / 64) + EMULATED_HD_DISK_NAME_OFFSET;
+ *minor = ((*minor / 64) * PARTS_PER_DISK) +
+ EMULATED_HD_DISK_MINOR_OFFSET;
+ break;
+ case XEN_IDE1_MAJOR:
+ *offset = (*minor / 64) + 2 + EMULATED_HD_DISK_NAME_OFFSET;
+ *minor = (((*minor / 64) + 2) * PARTS_PER_DISK) +
+ EMULATED_HD_DISK_MINOR_OFFSET;
+ break;
+ case XEN_SCSI_DISK0_MAJOR:
+ *offset = (*minor / PARTS_PER_DISK) + EMULATED_SD_DISK_NAME_OFFSET;
+ *minor = *minor + EMULATED_SD_DISK_MINOR_OFFSET;
+ break;
+ case XEN_SCSI_DISK1_MAJOR:
+ case XEN_SCSI_DISK2_MAJOR:
+ case XEN_SCSI_DISK3_MAJOR:
+ case XEN_SCSI_DISK4_MAJOR:
+ case XEN_SCSI_DISK5_MAJOR:
+ case XEN_SCSI_DISK6_MAJOR:
+ case XEN_SCSI_DISK7_MAJOR:
+ *offset = (*minor / PARTS_PER_DISK) +
+ ((major - XEN_SCSI_DISK1_MAJOR + 1) * 16) +
+ EMULATED_SD_DISK_NAME_OFFSET;
+ *minor = *minor +
+ ((major - XEN_SCSI_DISK1_MAJOR + 1) * 16 * PARTS_PER_DISK) +
+ EMULATED_SD_DISK_MINOR_OFFSET;
+ break;
+ case XEN_SCSI_DISK8_MAJOR:
+ case XEN_SCSI_DISK9_MAJOR:
+ case XEN_SCSI_DISK10_MAJOR:
+ case XEN_SCSI_DISK11_MAJOR:
+ case XEN_SCSI_DISK12_MAJOR:
+ case XEN_SCSI_DISK13_MAJOR:
+ case XEN_SCSI_DISK14_MAJOR:
+ case XEN_SCSI_DISK15_MAJOR:
+ *offset = (*minor / PARTS_PER_DISK) +
+ ((major - XEN_SCSI_DISK8_MAJOR + 8) * 16) +
+ EMULATED_SD_DISK_NAME_OFFSET;
+ *minor = *minor +
+ ((major - XEN_SCSI_DISK8_MAJOR + 8) * 16 * PARTS_PER_DISK) +
+ EMULATED_SD_DISK_MINOR_OFFSET;
+ break;
+ case XENVBD_MAJOR:
+ *offset = *minor / PARTS_PER_DISK;
+ break;
+ default:
+ printk(KERN_WARNING "blkfront: your disk configuration is "
+ "incorrect, please use an xvd device instead\n");
+ return -ENODEV;
+ }
+ return 0;
+}
static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
struct blkfront_info *info,
{
struct gendisk *gd;
int nr_minors = 1;
- int err = -ENODEV;
+ int err;
unsigned int offset;
int minor;
int nr_parts;
}
if (!VDEV_IS_EXTENDED(info->vdevice)) {
- minor = BLKIF_MINOR(info->vdevice);
- nr_parts = PARTS_PER_DISK;
+ err = xen_translate_vdev(info->vdevice, &minor, &offset);
+ if (err)
+ return err;
+ nr_parts = PARTS_PER_DISK;
} else {
minor = BLKIF_MINOR_EXT(info->vdevice);
nr_parts = PARTS_PER_EXT_DISK;
+ offset = minor / nr_parts;
+ if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4)
+ printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
+ "emulated IDE disks,\n\t choose an xvd device name"
+ "from xvde on\n", info->vdevice);
}
+ err = -ENODEV;
if ((minor % nr_parts) == 0)
nr_minors = nr_parts;
if (gd == NULL)
goto release;
- offset = minor / nr_parts;
-
if (nr_minors > 1) {
if (offset < 26)
sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset);
{
int i;
for (i = 0; i < s->req.nr_segments; i++)
- gnttab_end_foreign_access(s->req.seg[i].gref, 0, 0UL);
+ gnttab_end_foreign_access(s->req.u.rw.seg[i].gref, 0, 0UL);
}
static irqreturn_t blkif_interrupt(int irq, void *dev_id)
/* Rewrite any grant references invalidated by susp/resume. */
for (j = 0; j < req->nr_segments; j++)
gnttab_grant_foreign_access_ref(
- req->seg[j].gref,
+ req->u.rw.seg[j].gref,
info->xbdev->otherend_id,
pfn_to_mfn(info->shadow[req->id].frame[j]),
rq_data_dir(info->shadow[req->id].request));
/* Atheros AR3011 with sflash firmware*/
{ USB_DEVICE(0x0CF3, 0x3002) },
+ /* Atheros AR9285 Malbec with sflash firmware */
+ { USB_DEVICE(0x03F0, 0x311D) },
+
+ /* Atheros AR5BBU12 with sflash firmware */
+ { USB_DEVICE(0x0489, 0xE02C) },
{ } /* Terminating entry */
};
/* Atheros 3011 with sflash firmware */
{ USB_DEVICE(0x0cf3, 0x3002), .driver_info = BTUSB_IGNORE },
+ /* Atheros AR9285 Malbec with sflash firmware */
+ { USB_DEVICE(0x03f0, 0x311d), .driver_info = BTUSB_IGNORE },
+
+ /* Atheros AR5BBU12 with sflash firmware */
+ { USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE },
+
/* Broadcom BCM2035 */
{ USB_DEVICE(0x0a5c, 0x2035), .driver_info = BTUSB_WRONG_SCO_MTU },
{ USB_DEVICE(0x0a5c, 0x200a), .driver_info = BTUSB_WRONG_SCO_MTU },
if (hdev->conn_hash.sco_num > 0) {
if (!test_bit(BTUSB_DID_ISO_RESUME, &data->flags)) {
- err = usb_autopm_get_interface(data->isoc);
+ err = usb_autopm_get_interface(data->isoc ? data->isoc : data->intf);
if (err < 0) {
clear_bit(BTUSB_ISOC_RUNNING, &data->flags);
usb_kill_anchored_urbs(&data->isoc_anchor);
__set_isoc_interface(hdev, 0);
if (test_and_clear_bit(BTUSB_DID_ISO_RESUME, &data->flags))
- usb_autopm_put_interface(data->isoc);
+ usb_autopm_put_interface(data->isoc ? data->isoc : data->intf);
}
}
usb_set_intfdata(intf, data);
- usb_enable_autosuspend(interface_to_usbdev(intf));
-
return 0;
}
}
ENSURE(drive_status, CDC_DRIVE_STATUS );
- ENSURE(media_changed, CDC_MEDIA_CHANGED);
+ if (cdo->check_events == NULL && cdo->media_changed == NULL)
+ *change_capability = ~(CDC_MEDIA_CHANGED | CDC_SELECT_DISC);
ENSURE(tray_move, CDC_CLOSE_TRAY | CDC_OPEN_TRAY);
ENSURE(lock_door, CDC_LOCK);
ENSURE(select_speed, CDC_SELECT_SPEED);
obj-$(CONFIG_AMIGA_BUILTIN_SERIAL) += amiserial.o
obj-$(CONFIG_SX) += sx.o generic_serial.o
obj-$(CONFIG_RIO) += rio/ generic_serial.o
+obj-$(CONFIG_VIRTIO_CONSOLE) += virtio_console.o
obj-$(CONFIG_RAW_DRIVER) += raw.o
obj-$(CONFIG_SGI_SNSC) += snsc.o snsc_event.o
obj-$(CONFIG_MSPEC) += mspec.o
#else
printk(KERN_INFO PFX "You can boot with agp=try_unsupported\n");
#endif
+ pci_unregister_driver(&agp_amd64_pci_driver);
return -ENODEV;
}
/* First check that we have at least one AMD64 NB */
- if (!pci_dev_present(amd_nb_misc_ids))
+ if (!pci_dev_present(amd_nb_misc_ids)) {
+ pci_unregister_driver(&agp_amd64_pci_driver);
return -ENODEV;
+ }
/* Look for any AGP bridge */
agp_amd64_pci_driver.id_table = agp_amd64_pci_promisc_table;
err = driver_attach(&agp_amd64_pci_driver.driver);
- if (err == 0 && agp_bridges_found == 0)
+ if (err == 0 && agp_bridges_found == 0) {
+ pci_unregister_driver(&agp_amd64_pci_driver);
err = -ENODEV;
+ }
}
return err;
}
#define INTEL_GMCH_GMS_STOLEN_352M (0xd << 4)
#define I915_IFPADDR 0x60
+#define I830_HIC 0x70
/* Intel 965G registers */
#define I965_MSAC 0x62
#include <linux/kernel.h>
#include <linux/pagemap.h>
#include <linux/agp_backend.h>
+#include <linux/delay.h>
#include <asm/smp.h>
#include "agp.h"
#include "intel-agp.h"
u32 __iomem *gtt; /* I915G */
bool clear_fake_agp; /* on first access via agp, fill with scratch */
int num_dcache_entries;
- union {
- void __iomem *i9xx_flush_page;
- void *i8xx_flush_page;
- };
+ void __iomem *i9xx_flush_page;
char *i81x_gtt_table;
- struct page *i8xx_page;
struct resource ifp_resource;
int resource_valid;
struct page *scratch_page;
static void i830_cleanup(void)
{
- if (intel_private.i8xx_flush_page) {
- kunmap(intel_private.i8xx_flush_page);
- intel_private.i8xx_flush_page = NULL;
- }
-
- __free_page(intel_private.i8xx_page);
- intel_private.i8xx_page = NULL;
-}
-
-static void intel_i830_setup_flush(void)
-{
- /* return if we've already set the flush mechanism up */
- if (intel_private.i8xx_page)
- return;
-
- intel_private.i8xx_page = alloc_page(GFP_KERNEL);
- if (!intel_private.i8xx_page)
- return;
-
- intel_private.i8xx_flush_page = kmap(intel_private.i8xx_page);
- if (!intel_private.i8xx_flush_page)
- i830_cleanup();
}
/* The chipset_flush interface needs to get data that has already been
*/
static void i830_chipset_flush(void)
{
- unsigned int *pg = intel_private.i8xx_flush_page;
+ unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+
+ /* Forcibly evict everything from the CPU write buffers.
+ * clflush appears to be insufficient.
+ */
+ wbinvd_on_all_cpus();
+
+ /* Now we've only seen documents for this magic bit on 855GM,
+ * we hope it exists for the other gen2 chipsets...
+ *
+ * Also works as advertised on my 845G.
+ */
+ writel(readl(intel_private.registers+I830_HIC) | (1<<31),
+ intel_private.registers+I830_HIC);
- memset(pg, 0, 1024);
+ while (readl(intel_private.registers+I830_HIC) & (1<<31)) {
+ if (time_after(jiffies, timeout))
+ break;
- if (cpu_has_clflush)
- clflush_cache_range(pg, 1024);
- else if (wbinvd_on_all_cpus() != 0)
- printk(KERN_ERR "Timed out waiting for cache flush.\n");
+ udelay(50);
+ }
}
static void i830_write_entry(dma_addr_t addr, unsigned int entry,
intel_private.gtt_bus_addr = reg_addr + I810_PTE_BASE;
- intel_i830_setup_flush();
-
return 0;
}
static int add_smi(struct smi_info *smi);
static int try_smi_init(struct smi_info *smi);
static void cleanup_one_si(struct smi_info *to_clean);
+static void cleanup_ipmi_si(void);
static ATOMIC_NOTIFIER_HEAD(xaction_notifier_list);
static int register_xaction_notifier(struct notifier_block *nb)
printk("**Enqueue: %d.%9.9d\n", t.tv_sec, t.tv_usec);
#endif
+ /*
+ * last_timeout_jiffies is updated here to avoid
+ * smi_timeout() handler passing very large time_diff
+ * value to smi_event_handler() that causes
+ * the send command to abort.
+ */
+ smi_info->last_timeout_jiffies = jiffies;
+
mod_timer(&smi_info->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
if (smi_info->thread)
mutex_lock(&smi_infos_lock);
if (unload_when_empty && list_empty(&smi_infos)) {
mutex_unlock(&smi_infos_lock);
-#ifdef CONFIG_PCI
- if (pci_registered)
- pci_unregister_driver(&ipmi_pci_driver);
-#endif
-
-#ifdef CONFIG_PPC_OF
- if (of_registered)
- of_unregister_platform_driver(&ipmi_of_platform_driver);
-#endif
- driver_unregister(&ipmi_driver.driver);
+ cleanup_ipmi_si();
printk(KERN_WARNING PFX
"Unable to find any System Interface(s)\n");
return -ENODEV;
#define RTC_BITS 55 /* 55 bits for this implementation */
+static struct k_clock sgi_clock;
+
extern unsigned long sn_rtc_cycles_per_second;
#define RTC_COUNTER_ADDR ((long *)LOCAL_MMR_ADDR(SH_RTC))
return 0;
};
-static int sgi_clock_set(clockid_t clockid, struct timespec *tp)
+static int sgi_clock_set(const clockid_t clockid, const struct timespec *tp)
{
u64 nsec;
return err;
}
+static int sgi_clock_getres(const clockid_t which_clock, struct timespec *tp)
+{
+ tp->tv_sec = 0;
+ tp->tv_nsec = sgi_clock_period;
+ return 0;
+}
+
static struct k_clock sgi_clock = {
- .res = 0,
- .clock_set = sgi_clock_set,
- .clock_get = sgi_clock_get,
- .timer_create = sgi_timer_create,
- .nsleep = do_posix_clock_nonanosleep,
- .timer_set = sgi_timer_set,
- .timer_del = sgi_timer_del,
- .timer_get = sgi_timer_get
+ .clock_set = sgi_clock_set,
+ .clock_get = sgi_clock_get,
+ .clock_getres = sgi_clock_getres,
+ .timer_create = sgi_timer_create,
+ .timer_set = sgi_timer_set,
+ .timer_del = sgi_timer_del,
+ .timer_get = sgi_timer_get
};
/**
(unsigned long) node);
}
- sgi_clock_period = sgi_clock.res = NSEC_PER_SEC / sn_rtc_cycles_per_second;
- register_posix_clock(CLOCK_SGI_CYCLE, &sgi_clock);
+ sgi_clock_period = NSEC_PER_SEC / sn_rtc_cycles_per_second;
+ posix_timers_register_clock(CLOCK_SGI_CYCLE, &sgi_clock);
printk(KERN_INFO "%s: v%s, %ld MHz\n", MMTIMER_DESC, MMTIMER_VERSION,
sn_rtc_cycles_per_second/(unsigned long)1E6);
test_bit(IS_ANY_T1, &dev->flags))) {
DEBUGP(4, dev, "Perform AUTOPPS\n");
set_bit(IS_AUTOPPS_ACT, &dev->flags);
- ptsreq.protocol = ptsreq.protocol =
- (0x01 << dev->proto);
+ ptsreq.protocol = (0x01 << dev->proto);
ptsreq.flags = 0x01;
ptsreq.pts1 = 0x00;
ptsreq.pts2 = 0x00;
static int ipwireless_probe(struct pcmcia_device *p_dev, void *priv_data)
{
struct ipw_dev *ipw = priv_data;
- struct resource *io_resource;
int ret;
p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
if (ret)
return ret;
- io_resource = request_region(p_dev->resource[0]->start,
- resource_size(p_dev->resource[0]),
- IPWIRELESS_PCCARD_NAME);
+ if (!request_region(p_dev->resource[0]->start,
+ resource_size(p_dev->resource[0]),
+ IPWIRELESS_PCCARD_NAME)) {
+ ret = -EBUSY;
+ goto exit;
+ }
p_dev->resource[2]->flags |=
WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM | WIN_ENABLE;
ret = pcmcia_map_mem_page(p_dev, p_dev->resource[2], p_dev->card_addr);
if (ret != 0)
- goto exit2;
+ goto exit1;
ipw->is_v2_card = resource_size(p_dev->resource[2]) == 0x100;
- ipw->attr_memory = ioremap(p_dev->resource[2]->start,
+ ipw->common_memory = ioremap(p_dev->resource[2]->start,
resource_size(p_dev->resource[2]));
- request_mem_region(p_dev->resource[2]->start,
- resource_size(p_dev->resource[2]),
- IPWIRELESS_PCCARD_NAME);
+ if (!request_mem_region(p_dev->resource[2]->start,
+ resource_size(p_dev->resource[2]),
+ IPWIRELESS_PCCARD_NAME)) {
+ ret = -EBUSY;
+ goto exit2;
+ }
p_dev->resource[3]->flags |= WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_AM |
WIN_ENABLE;
p_dev->resource[3]->end = 0; /* this used to be 0x1000 */
ret = pcmcia_request_window(p_dev, p_dev->resource[3], 0);
if (ret != 0)
- goto exit2;
+ goto exit3;
ret = pcmcia_map_mem_page(p_dev, p_dev->resource[3], 0);
if (ret != 0)
ipw->attr_memory = ioremap(p_dev->resource[3]->start,
resource_size(p_dev->resource[3]));
- request_mem_region(p_dev->resource[3]->start,
- resource_size(p_dev->resource[3]),
- IPWIRELESS_PCCARD_NAME);
+ if (!request_mem_region(p_dev->resource[3]->start,
+ resource_size(p_dev->resource[3]),
+ IPWIRELESS_PCCARD_NAME)) {
+ ret = -EBUSY;
+ goto exit4;
+ }
return 0;
+exit4:
+ iounmap(ipw->attr_memory);
exit3:
+ release_mem_region(p_dev->resource[2]->start,
+ resource_size(p_dev->resource[2]));
exit2:
- if (ipw->common_memory) {
- release_mem_region(p_dev->resource[2]->start,
- resource_size(p_dev->resource[2]));
- iounmap(ipw->common_memory);
- }
+ iounmap(ipw->common_memory);
exit1:
- release_resource(io_resource);
+ release_region(p_dev->resource[0]->start,
+ resource_size(p_dev->resource[0]));
+exit:
pcmcia_disable_device(p_dev);
- return -1;
+ return ret;
}
static int config_ipwireless(struct ipw_dev *ipw)
static void release_ipwireless(struct ipw_dev *ipw)
{
+ release_region(ipw->link->resource[0]->start,
+ resource_size(ipw->link->resource[0]));
if (ipw->common_memory) {
release_mem_region(ipw->link->resource[2]->start,
resource_size(ipw->link->resource[2]));
tpm_protected_ordinal_duration[ordinal &
TPM_PROTECTED_ORDINAL_MASK];
- if (duration_idx != TPM_UNDEFINED) {
+ if (duration_idx != TPM_UNDEFINED)
duration = chip->vendor.duration[duration_idx];
- /* if duration is 0, it's because chip->vendor.duration wasn't */
- /* filled yet, so we set the lowest timeout just to give enough */
- /* time for tpm_get_timeouts() to succeed */
- return (duration <= 0 ? HZ : duration);
- } else
+ if (duration <= 0)
return 2 * 60 * HZ;
+ else
+ return duration;
}
EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration);
--- /dev/null
+/*
+ * Copyright (C) 2006, 2007, 2009 Rusty Russell, IBM Corporation
+ * Copyright (C) 2009, 2010, 2011 Red Hat, Inc.
+ * Copyright (C) 2009, 2010, 2011 Amit Shah <amit.shah@redhat.com>
+ *
+ * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#include <linux/cdev.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/virtio.h>
+#include <linux/virtio_console.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include "../tty/hvc/hvc_console.h"
+
+/*
+ * This is a global struct for storing common data for all the devices
+ * this driver handles.
+ *
+ * Mainly, it has a linked list for all the consoles in one place so
+ * that callbacks from hvc for get_chars(), put_chars() work properly
+ * across multiple devices and multiple ports per device.
+ */
+struct ports_driver_data {
+ /* Used for registering chardevs */
+ struct class *class;
+
+ /* Used for exporting per-port information to debugfs */
+ struct dentry *debugfs_dir;
+
+ /* List of all the devices we're handling */
+ struct list_head portdevs;
+
+ /* Number of devices this driver is handling */
+ unsigned int index;
+
+ /*
+ * This is used to keep track of the number of hvc consoles
+ * spawned by this driver. This number is given as the first
+ * argument to hvc_alloc(). To correctly map an initial
+ * console spawned via hvc_instantiate to the console being
+ * hooked up via hvc_alloc, we need to pass the same vtermno.
+ *
+ * We also just assume the first console being initialised was
+ * the first one that got used as the initial console.
+ */
+ unsigned int next_vtermno;
+
+ /* All the console devices handled by this driver */
+ struct list_head consoles;
+};
+static struct ports_driver_data pdrvdata;
+
+DEFINE_SPINLOCK(pdrvdata_lock);
+
+/* This struct holds information that's relevant only for console ports */
+struct console {
+ /* We'll place all consoles in a list in the pdrvdata struct */
+ struct list_head list;
+
+ /* The hvc device associated with this console port */
+ struct hvc_struct *hvc;
+
+ /* The size of the console */
+ struct winsize ws;
+
+ /*
+ * This number identifies the number that we used to register
+ * with hvc in hvc_instantiate() and hvc_alloc(); this is the
+ * number passed on by the hvc callbacks to us to
+ * differentiate between the other console ports handled by
+ * this driver
+ */
+ u32 vtermno;
+};
+
+struct port_buffer {
+ char *buf;
+
+ /* size of the buffer in *buf above */
+ size_t size;
+
+ /* used length of the buffer */
+ size_t len;
+ /* offset in the buf from which to consume data */
+ size_t offset;
+};
+
+/*
+ * This is a per-device struct that stores data common to all the
+ * ports for that device (vdev->priv).
+ */
+struct ports_device {
+ /* Next portdev in the list, head is in the pdrvdata struct */
+ struct list_head list;
+
+ /*
+ * Workqueue handlers where we process deferred work after
+ * notification
+ */
+ struct work_struct control_work;
+
+ struct list_head ports;
+
+ /* To protect the list of ports */
+ spinlock_t ports_lock;
+
+ /* To protect the vq operations for the control channel */
+ spinlock_t cvq_lock;
+
+ /* The current config space is stored here */
+ struct virtio_console_config config;
+
+ /* The virtio device we're associated with */
+ struct virtio_device *vdev;
+
+ /*
+ * A couple of virtqueues for the control channel: one for
+ * guest->host transfers, one for host->guest transfers
+ */
+ struct virtqueue *c_ivq, *c_ovq;
+
+ /* Array of per-port IO virtqueues */
+ struct virtqueue **in_vqs, **out_vqs;
+
+ /* Used for numbering devices for sysfs and debugfs */
+ unsigned int drv_index;
+
+ /* Major number for this device. Ports will be created as minors. */
+ int chr_major;
+};
+
+/* This struct holds the per-port data */
+struct port {
+ /* Next port in the list, head is in the ports_device */
+ struct list_head list;
+
+ /* Pointer to the parent virtio_console device */
+ struct ports_device *portdev;
+
+ /* The current buffer from which data has to be fed to readers */
+ struct port_buffer *inbuf;
+
+ /*
+ * To protect the operations on the in_vq associated with this
+ * port. Has to be a spinlock because it can be called from
+ * interrupt context (get_char()).
+ */
+ spinlock_t inbuf_lock;
+
+ /* Protect the operations on the out_vq. */
+ spinlock_t outvq_lock;
+
+ /* The IO vqs for this port */
+ struct virtqueue *in_vq, *out_vq;
+
+ /* File in the debugfs directory that exposes this port's information */
+ struct dentry *debugfs_file;
+
+ /*
+ * The entries in this struct will be valid if this port is
+ * hooked up to an hvc console
+ */
+ struct console cons;
+
+ /* Each port associates with a separate char device */
+ struct cdev *cdev;
+ struct device *dev;
+
+ /* Reference-counting to handle port hot-unplugs and file operations */
+ struct kref kref;
+
+ /* A waitqueue for poll() or blocking read operations */
+ wait_queue_head_t waitqueue;
+
+ /* The 'name' of the port that we expose via sysfs properties */
+ char *name;
+
+ /* We can notify apps of host connect / disconnect events via SIGIO */
+ struct fasync_struct *async_queue;
+
+ /* The 'id' to identify the port with the Host */
+ u32 id;
+
+ bool outvq_full;
+
+ /* Is the host device open */
+ bool host_connected;
+
+ /* We should allow only one process to open a port */
+ bool guest_connected;
+};
+
+/* This is the very early arch-specified put chars function. */
+static int (*early_put_chars)(u32, const char *, int);
+
+static struct port *find_port_by_vtermno(u32 vtermno)
+{
+ struct port *port;
+ struct console *cons;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pdrvdata_lock, flags);
+ list_for_each_entry(cons, &pdrvdata.consoles, list) {
+ if (cons->vtermno == vtermno) {
+ port = container_of(cons, struct port, cons);
+ goto out;
+ }
+ }
+ port = NULL;
+out:
+ spin_unlock_irqrestore(&pdrvdata_lock, flags);
+ return port;
+}
+
+static struct port *find_port_by_devt_in_portdev(struct ports_device *portdev,
+ dev_t dev)
+{
+ struct port *port;
+ unsigned long flags;
+
+ spin_lock_irqsave(&portdev->ports_lock, flags);
+ list_for_each_entry(port, &portdev->ports, list)
+ if (port->cdev->dev == dev)
+ goto out;
+ port = NULL;
+out:
+ spin_unlock_irqrestore(&portdev->ports_lock, flags);
+
+ return port;
+}
+
+static struct port *find_port_by_devt(dev_t dev)
+{
+ struct ports_device *portdev;
+ struct port *port;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pdrvdata_lock, flags);
+ list_for_each_entry(portdev, &pdrvdata.portdevs, list) {
+ port = find_port_by_devt_in_portdev(portdev, dev);
+ if (port)
+ goto out;
+ }
+ port = NULL;
+out:
+ spin_unlock_irqrestore(&pdrvdata_lock, flags);
+ return port;
+}
+
+static struct port *find_port_by_id(struct ports_device *portdev, u32 id)
+{
+ struct port *port;
+ unsigned long flags;
+
+ spin_lock_irqsave(&portdev->ports_lock, flags);
+ list_for_each_entry(port, &portdev->ports, list)
+ if (port->id == id)
+ goto out;
+ port = NULL;
+out:
+ spin_unlock_irqrestore(&portdev->ports_lock, flags);
+
+ return port;
+}
+
+static struct port *find_port_by_vq(struct ports_device *portdev,
+ struct virtqueue *vq)
+{
+ struct port *port;
+ unsigned long flags;
+
+ spin_lock_irqsave(&portdev->ports_lock, flags);
+ list_for_each_entry(port, &portdev->ports, list)
+ if (port->in_vq == vq || port->out_vq == vq)
+ goto out;
+ port = NULL;
+out:
+ spin_unlock_irqrestore(&portdev->ports_lock, flags);
+ return port;
+}
+
+static bool is_console_port(struct port *port)
+{
+ if (port->cons.hvc)
+ return true;
+ return false;
+}
+
+static inline bool use_multiport(struct ports_device *portdev)
+{
+ /*
+ * This condition can be true when put_chars is called from
+ * early_init
+ */
+ if (!portdev->vdev)
+ return 0;
+ return portdev->vdev->features[0] & (1 << VIRTIO_CONSOLE_F_MULTIPORT);
+}
+
+static void free_buf(struct port_buffer *buf)
+{
+ kfree(buf->buf);
+ kfree(buf);
+}
+
+static struct port_buffer *alloc_buf(size_t buf_size)
+{
+ struct port_buffer *buf;
+
+ buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+ if (!buf)
+ goto fail;
+ buf->buf = kzalloc(buf_size, GFP_KERNEL);
+ if (!buf->buf)
+ goto free_buf;
+ buf->len = 0;
+ buf->offset = 0;
+ buf->size = buf_size;
+ return buf;
+
+free_buf:
+ kfree(buf);
+fail:
+ return NULL;
+}
+
+/* Callers should take appropriate locks */
+static void *get_inbuf(struct port *port)
+{
+ struct port_buffer *buf;
+ struct virtqueue *vq;
+ unsigned int len;
+
+ vq = port->in_vq;
+ buf = virtqueue_get_buf(vq, &len);
+ if (buf) {
+ buf->len = len;
+ buf->offset = 0;
+ }
+ return buf;
+}
+
+/*
+ * Create a scatter-gather list representing our input buffer and put
+ * it in the queue.
+ *
+ * Callers should take appropriate locks.
+ */
+static int add_inbuf(struct virtqueue *vq, struct port_buffer *buf)
+{
+ struct scatterlist sg[1];
+ int ret;
+
+ sg_init_one(sg, buf->buf, buf->size);
+
+ ret = virtqueue_add_buf(vq, sg, 0, 1, buf);
+ virtqueue_kick(vq);
+ return ret;
+}
+
+/* Discard any unread data this port has. Callers lockers. */
+static void discard_port_data(struct port *port)
+{
+ struct port_buffer *buf;
+ struct virtqueue *vq;
+ unsigned int len;
+ int ret;
+
+ if (!port->portdev) {
+ /* Device has been unplugged. vqs are already gone. */
+ return;
+ }
+ vq = port->in_vq;
+ if (port->inbuf)
+ buf = port->inbuf;
+ else
+ buf = virtqueue_get_buf(vq, &len);
+
+ ret = 0;
+ while (buf) {
+ if (add_inbuf(vq, buf) < 0) {
+ ret++;
+ free_buf(buf);
+ }
+ buf = virtqueue_get_buf(vq, &len);
+ }
+ port->inbuf = NULL;
+ if (ret)
+ dev_warn(port->dev, "Errors adding %d buffers back to vq\n",
+ ret);
+}
+
+static bool port_has_data(struct port *port)
+{
+ unsigned long flags;
+ bool ret;
+
+ spin_lock_irqsave(&port->inbuf_lock, flags);
+ if (port->inbuf) {
+ ret = true;
+ goto out;
+ }
+ port->inbuf = get_inbuf(port);
+ if (port->inbuf) {
+ ret = true;
+ goto out;
+ }
+ ret = false;
+out:
+ spin_unlock_irqrestore(&port->inbuf_lock, flags);
+ return ret;
+}
+
+static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
+ unsigned int event, unsigned int value)
+{
+ struct scatterlist sg[1];
+ struct virtio_console_control cpkt;
+ struct virtqueue *vq;
+ unsigned int len;
+
+ if (!use_multiport(portdev))
+ return 0;
+
+ cpkt.id = port_id;
+ cpkt.event = event;
+ cpkt.value = value;
+
+ vq = portdev->c_ovq;
+
+ sg_init_one(sg, &cpkt, sizeof(cpkt));
+ if (virtqueue_add_buf(vq, sg, 1, 0, &cpkt) >= 0) {
+ virtqueue_kick(vq);
+ while (!virtqueue_get_buf(vq, &len))
+ cpu_relax();
+ }
+ return 0;
+}
+
+static ssize_t send_control_msg(struct port *port, unsigned int event,
+ unsigned int value)
+{
+ /* Did the port get unplugged before userspace closed it? */
+ if (port->portdev)
+ return __send_control_msg(port->portdev, port->id, event, value);
+ return 0;
+}
+
+/* Callers must take the port->outvq_lock */
+static void reclaim_consumed_buffers(struct port *port)
+{
+ void *buf;
+ unsigned int len;
+
+ if (!port->portdev) {
+ /* Device has been unplugged. vqs are already gone. */
+ return;
+ }
+ while ((buf = virtqueue_get_buf(port->out_vq, &len))) {
+ kfree(buf);
+ port->outvq_full = false;
+ }
+}
+
+static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count,
+ bool nonblock)
+{
+ struct scatterlist sg[1];
+ struct virtqueue *out_vq;
+ ssize_t ret;
+ unsigned long flags;
+ unsigned int len;
+
+ out_vq = port->out_vq;
+
+ spin_lock_irqsave(&port->outvq_lock, flags);
+
+ reclaim_consumed_buffers(port);
+
+ sg_init_one(sg, in_buf, in_count);
+ ret = virtqueue_add_buf(out_vq, sg, 1, 0, in_buf);
+
+ /* Tell Host to go! */
+ virtqueue_kick(out_vq);
+
+ if (ret < 0) {
+ in_count = 0;
+ goto done;
+ }
+
+ if (ret == 0)
+ port->outvq_full = true;
+
+ if (nonblock)
+ goto done;
+
+ /*
+ * Wait till the host acknowledges it pushed out the data we
+ * sent. This is done for data from the hvc_console; the tty
+ * operations are performed with spinlocks held so we can't
+ * sleep here. An alternative would be to copy the data to a
+ * buffer and relax the spinning requirement. The downside is
+ * we need to kmalloc a GFP_ATOMIC buffer each time the
+ * console driver writes something out.
+ */
+ while (!virtqueue_get_buf(out_vq, &len))
+ cpu_relax();
+done:
+ spin_unlock_irqrestore(&port->outvq_lock, flags);
+ /*
+ * We're expected to return the amount of data we wrote -- all
+ * of it
+ */
+ return in_count;
+}
+
+/*
+ * Give out the data that's requested from the buffer that we have
+ * queued up.
+ */
+static ssize_t fill_readbuf(struct port *port, char *out_buf, size_t out_count,
+ bool to_user)
+{
+ struct port_buffer *buf;
+ unsigned long flags;
+
+ if (!out_count || !port_has_data(port))
+ return 0;
+
+ buf = port->inbuf;
+ out_count = min(out_count, buf->len - buf->offset);
+
+ if (to_user) {
+ ssize_t ret;
+
+ ret = copy_to_user(out_buf, buf->buf + buf->offset, out_count);
+ if (ret)
+ return -EFAULT;
+ } else {
+ memcpy(out_buf, buf->buf + buf->offset, out_count);
+ }
+
+ buf->offset += out_count;
+
+ if (buf->offset == buf->len) {
+ /*
+ * We're done using all the data in this buffer.
+ * Re-queue so that the Host can send us more data.
+ */
+ spin_lock_irqsave(&port->inbuf_lock, flags);
+ port->inbuf = NULL;
+
+ if (add_inbuf(port->in_vq, buf) < 0)
+ dev_warn(port->dev, "failed add_buf\n");
+
+ spin_unlock_irqrestore(&port->inbuf_lock, flags);
+ }
+ /* Return the number of bytes actually copied */
+ return out_count;
+}
+
+/* The condition that must be true for polling to end */
+static bool will_read_block(struct port *port)
+{
+ if (!port->guest_connected) {
+ /* Port got hot-unplugged. Let's exit. */
+ return false;
+ }
+ return !port_has_data(port) && port->host_connected;
+}
+
+static bool will_write_block(struct port *port)
+{
+ bool ret;
+
+ if (!port->guest_connected) {
+ /* Port got hot-unplugged. Let's exit. */
+ return false;
+ }
+ if (!port->host_connected)
+ return true;
+
+ spin_lock_irq(&port->outvq_lock);
+ /*
+ * Check if the Host has consumed any buffers since we last
+ * sent data (this is only applicable for nonblocking ports).
+ */
+ reclaim_consumed_buffers(port);
+ ret = port->outvq_full;
+ spin_unlock_irq(&port->outvq_lock);
+
+ return ret;
+}
+
+static ssize_t port_fops_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *offp)
+{
+ struct port *port;
+ ssize_t ret;
+
+ port = filp->private_data;
+
+ if (!port_has_data(port)) {
+ /*
+ * If nothing's connected on the host just return 0 in
+ * case of list_empty; this tells the userspace app
+ * that there's no connection
+ */
+ if (!port->host_connected)
+ return 0;
+ if (filp->f_flags & O_NONBLOCK)
+ return -EAGAIN;
+
+ ret = wait_event_interruptible(port->waitqueue,
+ !will_read_block(port));
+ if (ret < 0)
+ return ret;
+ }
+ /* Port got hot-unplugged. */
+ if (!port->guest_connected)
+ return -ENODEV;
+ /*
+ * We could've received a disconnection message while we were
+ * waiting for more data.
+ *
+ * This check is not clubbed in the if() statement above as we
+ * might receive some data as well as the host could get
+ * disconnected after we got woken up from our wait. So we
+ * really want to give off whatever data we have and only then
+ * check for host_connected.
+ */
+ if (!port_has_data(port) && !port->host_connected)
+ return 0;
+
+ return fill_readbuf(port, ubuf, count, true);
+}
+
+static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
+ size_t count, loff_t *offp)
+{
+ struct port *port;
+ char *buf;
+ ssize_t ret;
+ bool nonblock;
+
+ /* Userspace could be out to fool us */
+ if (!count)
+ return 0;
+
+ port = filp->private_data;
+
+ nonblock = filp->f_flags & O_NONBLOCK;
+
+ if (will_write_block(port)) {
+ if (nonblock)
+ return -EAGAIN;
+
+ ret = wait_event_interruptible(port->waitqueue,
+ !will_write_block(port));
+ if (ret < 0)
+ return ret;
+ }
+ /* Port got hot-unplugged. */
+ if (!port->guest_connected)
+ return -ENODEV;
+
+ count = min((size_t)(32 * 1024), count);
+
+ buf = kmalloc(count, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = copy_from_user(buf, ubuf, count);
+ if (ret) {
+ ret = -EFAULT;
+ goto free_buf;
+ }
+
+ /*
+ * We now ask send_buf() to not spin for generic ports -- we
+ * can re-use the same code path that non-blocking file
+ * descriptors take for blocking file descriptors since the
+ * wait is already done and we're certain the write will go
+ * through to the host.
+ */
+ nonblock = true;
+ ret = send_buf(port, buf, count, nonblock);
+
+ if (nonblock && ret > 0)
+ goto out;
+
+free_buf:
+ kfree(buf);
+out:
+ return ret;
+}
+
+static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
+{
+ struct port *port;
+ unsigned int ret;
+
+ port = filp->private_data;
+ poll_wait(filp, &port->waitqueue, wait);
+
+ if (!port->guest_connected) {
+ /* Port got unplugged */
+ return POLLHUP;
+ }
+ ret = 0;
+ if (!will_read_block(port))
+ ret |= POLLIN | POLLRDNORM;
+ if (!will_write_block(port))
+ ret |= POLLOUT;
+ if (!port->host_connected)
+ ret |= POLLHUP;
+
+ return ret;
+}
+
+static void remove_port(struct kref *kref);
+
+static int port_fops_release(struct inode *inode, struct file *filp)
+{
+ struct port *port;
+
+ port = filp->private_data;
+
+ /* Notify host of port being closed */
+ send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 0);
+
+ spin_lock_irq(&port->inbuf_lock);
+ port->guest_connected = false;
+
+ discard_port_data(port);
+
+ spin_unlock_irq(&port->inbuf_lock);
+
+ spin_lock_irq(&port->outvq_lock);
+ reclaim_consumed_buffers(port);
+ spin_unlock_irq(&port->outvq_lock);
+
+ /*
+ * Locks aren't necessary here as a port can't be opened after
+ * unplug, and if a port isn't unplugged, a kref would already
+ * exist for the port. Plus, taking ports_lock here would
+ * create a dependency on other locks taken by functions
+ * inside remove_port if we're the last holder of the port,
+ * creating many problems.
+ */
+ kref_put(&port->kref, remove_port);
+
+ return 0;
+}
+
+static int port_fops_open(struct inode *inode, struct file *filp)
+{
+ struct cdev *cdev = inode->i_cdev;
+ struct port *port;
+ int ret;
+
+ port = find_port_by_devt(cdev->dev);
+ filp->private_data = port;
+
+ /* Prevent against a port getting hot-unplugged at the same time */
+ spin_lock_irq(&port->portdev->ports_lock);
+ kref_get(&port->kref);
+ spin_unlock_irq(&port->portdev->ports_lock);
+
+ /*
+ * Don't allow opening of console port devices -- that's done
+ * via /dev/hvc
+ */
+ if (is_console_port(port)) {
+ ret = -ENXIO;
+ goto out;
+ }
+
+ /* Allow only one process to open a particular port at a time */
+ spin_lock_irq(&port->inbuf_lock);
+ if (port->guest_connected) {
+ spin_unlock_irq(&port->inbuf_lock);
+ ret = -EMFILE;
+ goto out;
+ }
+
+ port->guest_connected = true;
+ spin_unlock_irq(&port->inbuf_lock);
+
+ spin_lock_irq(&port->outvq_lock);
+ /*
+ * There might be a chance that we missed reclaiming a few
+ * buffers in the window of the port getting previously closed
+ * and opening now.
+ */
+ reclaim_consumed_buffers(port);
+ spin_unlock_irq(&port->outvq_lock);
+
+ nonseekable_open(inode, filp);
+
+ /* Notify host of port being opened */
+ send_control_msg(filp->private_data, VIRTIO_CONSOLE_PORT_OPEN, 1);
+
+ return 0;
+out:
+ kref_put(&port->kref, remove_port);
+ return ret;
+}
+
+static int port_fops_fasync(int fd, struct file *filp, int mode)
+{
+ struct port *port;
+
+ port = filp->private_data;
+ return fasync_helper(fd, filp, mode, &port->async_queue);
+}
+
+/*
+ * The file operations that we support: programs in the guest can open
+ * a console device, read from it, write to it, poll for data and
+ * close it. The devices are at
+ * /dev/vport<device number>p<port number>
+ */
+static const struct file_operations port_fops = {
+ .owner = THIS_MODULE,
+ .open = port_fops_open,
+ .read = port_fops_read,
+ .write = port_fops_write,
+ .poll = port_fops_poll,
+ .release = port_fops_release,
+ .fasync = port_fops_fasync,
+ .llseek = no_llseek,
+};
+
+/*
+ * The put_chars() callback is pretty straightforward.
+ *
+ * We turn the characters into a scatter-gather list, add it to the
+ * output queue and then kick the Host. Then we sit here waiting for
+ * it to finish: inefficient in theory, but in practice
+ * implementations will do it immediately (lguest's Launcher does).
+ */
+static int put_chars(u32 vtermno, const char *buf, int count)
+{
+ struct port *port;
+
+ if (unlikely(early_put_chars))
+ return early_put_chars(vtermno, buf, count);
+
+ port = find_port_by_vtermno(vtermno);
+ if (!port)
+ return -EPIPE;
+
+ return send_buf(port, (void *)buf, count, false);
+}
+
+/*
+ * get_chars() is the callback from the hvc_console infrastructure
+ * when an interrupt is received.
+ *
+ * We call out to fill_readbuf that gets us the required data from the
+ * buffers that are queued up.
+ */
+static int get_chars(u32 vtermno, char *buf, int count)
+{
+ struct port *port;
+
+ /* If we've not set up the port yet, we have no input to give. */
+ if (unlikely(early_put_chars))
+ return 0;
+
+ port = find_port_by_vtermno(vtermno);
+ if (!port)
+ return -EPIPE;
+
+ /* If we don't have an input queue yet, we can't get input. */
+ BUG_ON(!port->in_vq);
+
+ return fill_readbuf(port, buf, count, false);
+}
+
+static void resize_console(struct port *port)
+{
+ struct virtio_device *vdev;
+
+ /* The port could have been hot-unplugged */
+ if (!port || !is_console_port(port))
+ return;
+
+ vdev = port->portdev->vdev;
+ if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_SIZE))
+ hvc_resize(port->cons.hvc, port->cons.ws);
+}
+
+/* We set the configuration at this point, since we now have a tty */
+static int notifier_add_vio(struct hvc_struct *hp, int data)
+{
+ struct port *port;
+
+ port = find_port_by_vtermno(hp->vtermno);
+ if (!port)
+ return -EINVAL;
+
+ hp->irq_requested = 1;
+ resize_console(port);
+
+ return 0;
+}
+
+static void notifier_del_vio(struct hvc_struct *hp, int data)
+{
+ hp->irq_requested = 0;
+}
+
+/* The operations for console ports. */
+static const struct hv_ops hv_ops = {
+ .get_chars = get_chars,
+ .put_chars = put_chars,
+ .notifier_add = notifier_add_vio,
+ .notifier_del = notifier_del_vio,
+ .notifier_hangup = notifier_del_vio,
+};
+
+/*
+ * Console drivers are initialized very early so boot messages can go
+ * out, so we do things slightly differently from the generic virtio
+ * initialization of the net and block drivers.
+ *
+ * At this stage, the console is output-only. It's too early to set
+ * up a virtqueue, so we let the drivers do some boutique early-output
+ * thing.
+ */
+int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int))
+{
+ early_put_chars = put_chars;
+ return hvc_instantiate(0, 0, &hv_ops);
+}
+
+int init_port_console(struct port *port)
+{
+ int ret;
+
+ /*
+ * The Host's telling us this port is a console port. Hook it
+ * up with an hvc console.
+ *
+ * To set up and manage our virtual console, we call
+ * hvc_alloc().
+ *
+ * The first argument of hvc_alloc() is the virtual console
+ * number. The second argument is the parameter for the
+ * notification mechanism (like irq number). We currently
+ * leave this as zero, virtqueues have implicit notifications.
+ *
+ * The third argument is a "struct hv_ops" containing the
+ * put_chars() get_chars(), notifier_add() and notifier_del()
+ * pointers. The final argument is the output buffer size: we
+ * can do any size, so we put PAGE_SIZE here.
+ */
+ port->cons.vtermno = pdrvdata.next_vtermno;
+
+ port->cons.hvc = hvc_alloc(port->cons.vtermno, 0, &hv_ops, PAGE_SIZE);
+ if (IS_ERR(port->cons.hvc)) {
+ ret = PTR_ERR(port->cons.hvc);
+ dev_err(port->dev,
+ "error %d allocating hvc for port\n", ret);
+ port->cons.hvc = NULL;
+ return ret;
+ }
+ spin_lock_irq(&pdrvdata_lock);
+ pdrvdata.next_vtermno++;
+ list_add_tail(&port->cons.list, &pdrvdata.consoles);
+ spin_unlock_irq(&pdrvdata_lock);
+ port->guest_connected = true;
+
+ /*
+ * Start using the new console output if this is the first
+ * console to come up.
+ */
+ if (early_put_chars)
+ early_put_chars = NULL;
+
+ /* Notify host of port being opened */
+ send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 1);
+
+ return 0;
+}
+
+static ssize_t show_port_name(struct device *dev,
+ struct device_attribute *attr, char *buffer)
+{
+ struct port *port;
+
+ port = dev_get_drvdata(dev);
+
+ return sprintf(buffer, "%s\n", port->name);
+}
+
+static DEVICE_ATTR(name, S_IRUGO, show_port_name, NULL);
+
+static struct attribute *port_sysfs_entries[] = {
+ &dev_attr_name.attr,
+ NULL
+};
+
+static struct attribute_group port_attribute_group = {
+ .name = NULL, /* put in device directory */
+ .attrs = port_sysfs_entries,
+};
+
+static int debugfs_open(struct inode *inode, struct file *filp)
+{
+ filp->private_data = inode->i_private;
+ return 0;
+}
+
+static ssize_t debugfs_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *offp)
+{
+ struct port *port;
+ char *buf;
+ ssize_t ret, out_offset, out_count;
+
+ out_count = 1024;
+ buf = kmalloc(out_count, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ port = filp->private_data;
+ out_offset = 0;
+ out_offset += snprintf(buf + out_offset, out_count,
+ "name: %s\n", port->name ? port->name : "");
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "guest_connected: %d\n", port->guest_connected);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "host_connected: %d\n", port->host_connected);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "outvq_full: %d\n", port->outvq_full);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "is_console: %s\n",
+ is_console_port(port) ? "yes" : "no");
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "console_vtermno: %u\n", port->cons.vtermno);
+
+ ret = simple_read_from_buffer(ubuf, count, offp, buf, out_offset);
+ kfree(buf);
+ return ret;
+}
+
+static const struct file_operations port_debugfs_ops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_open,
+ .read = debugfs_read,
+};
+
+static void set_console_size(struct port *port, u16 rows, u16 cols)
+{
+ if (!port || !is_console_port(port))
+ return;
+
+ port->cons.ws.ws_row = rows;
+ port->cons.ws.ws_col = cols;
+}
+
+static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
+{
+ struct port_buffer *buf;
+ unsigned int nr_added_bufs;
+ int ret;
+
+ nr_added_bufs = 0;
+ do {
+ buf = alloc_buf(PAGE_SIZE);
+ if (!buf)
+ break;
+
+ spin_lock_irq(lock);
+ ret = add_inbuf(vq, buf);
+ if (ret < 0) {
+ spin_unlock_irq(lock);
+ free_buf(buf);
+ break;
+ }
+ nr_added_bufs++;
+ spin_unlock_irq(lock);
+ } while (ret > 0);
+
+ return nr_added_bufs;
+}
+
+static void send_sigio_to_port(struct port *port)
+{
+ if (port->async_queue && port->guest_connected)
+ kill_fasync(&port->async_queue, SIGIO, POLL_OUT);
+}
+
+static int add_port(struct ports_device *portdev, u32 id)
+{
+ char debugfs_name[16];
+ struct port *port;
+ struct port_buffer *buf;
+ dev_t devt;
+ unsigned int nr_added_bufs;
+ int err;
+
+ port = kmalloc(sizeof(*port), GFP_KERNEL);
+ if (!port) {
+ err = -ENOMEM;
+ goto fail;
+ }
+ kref_init(&port->kref);
+
+ port->portdev = portdev;
+ port->id = id;
+
+ port->name = NULL;
+ port->inbuf = NULL;
+ port->cons.hvc = NULL;
+ port->async_queue = NULL;
+
+ port->cons.ws.ws_row = port->cons.ws.ws_col = 0;
+
+ port->host_connected = port->guest_connected = false;
+
+ port->outvq_full = false;
+
+ port->in_vq = portdev->in_vqs[port->id];
+ port->out_vq = portdev->out_vqs[port->id];
+
+ port->cdev = cdev_alloc();
+ if (!port->cdev) {
+ dev_err(&port->portdev->vdev->dev, "Error allocating cdev\n");
+ err = -ENOMEM;
+ goto free_port;
+ }
+ port->cdev->ops = &port_fops;
+
+ devt = MKDEV(portdev->chr_major, id);
+ err = cdev_add(port->cdev, devt, 1);
+ if (err < 0) {
+ dev_err(&port->portdev->vdev->dev,
+ "Error %d adding cdev for port %u\n", err, id);
+ goto free_cdev;
+ }
+ port->dev = device_create(pdrvdata.class, &port->portdev->vdev->dev,
+ devt, port, "vport%up%u",
+ port->portdev->drv_index, id);
+ if (IS_ERR(port->dev)) {
+ err = PTR_ERR(port->dev);
+ dev_err(&port->portdev->vdev->dev,
+ "Error %d creating device for port %u\n",
+ err, id);
+ goto free_cdev;
+ }
+
+ spin_lock_init(&port->inbuf_lock);
+ spin_lock_init(&port->outvq_lock);
+ init_waitqueue_head(&port->waitqueue);
+
+ /* Fill the in_vq with buffers so the host can send us data. */
+ nr_added_bufs = fill_queue(port->in_vq, &port->inbuf_lock);
+ if (!nr_added_bufs) {
+ dev_err(port->dev, "Error allocating inbufs\n");
+ err = -ENOMEM;
+ goto free_device;
+ }
+
+ /*
+ * If we're not using multiport support, this has to be a console port
+ */
+ if (!use_multiport(port->portdev)) {
+ err = init_port_console(port);
+ if (err)
+ goto free_inbufs;
+ }
+
+ spin_lock_irq(&portdev->ports_lock);
+ list_add_tail(&port->list, &port->portdev->ports);
+ spin_unlock_irq(&portdev->ports_lock);
+
+ /*
+ * Tell the Host we're set so that it can send us various
+ * configuration parameters for this port (eg, port name,
+ * caching, whether this is a console port, etc.)
+ */
+ send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1);
+
+ if (pdrvdata.debugfs_dir) {
+ /*
+ * Finally, create the debugfs file that we can use to
+ * inspect a port's state at any time
+ */
+ sprintf(debugfs_name, "vport%up%u",
+ port->portdev->drv_index, id);
+ port->debugfs_file = debugfs_create_file(debugfs_name, 0444,
+ pdrvdata.debugfs_dir,
+ port,
+ &port_debugfs_ops);
+ }
+ return 0;
+
+free_inbufs:
+ while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
+ free_buf(buf);
+free_device:
+ device_destroy(pdrvdata.class, port->dev->devt);
+free_cdev:
+ cdev_del(port->cdev);
+free_port:
+ kfree(port);
+fail:
+ /* The host might want to notify management sw about port add failure */
+ __send_control_msg(portdev, id, VIRTIO_CONSOLE_PORT_READY, 0);
+ return err;
+}
+
+/* No users remain, remove all port-specific data. */
+static void remove_port(struct kref *kref)
+{
+ struct port *port;
+
+ port = container_of(kref, struct port, kref);
+
+ sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
+ device_destroy(pdrvdata.class, port->dev->devt);
+ cdev_del(port->cdev);
+
+ kfree(port->name);
+
+ debugfs_remove(port->debugfs_file);
+
+ kfree(port);
+}
+
+/*
+ * Port got unplugged. Remove port from portdev's list and drop the
+ * kref reference. If no userspace has this port opened, it will
+ * result in immediate removal the port.
+ */
+static void unplug_port(struct port *port)
+{
+ struct port_buffer *buf;
+
+ spin_lock_irq(&port->portdev->ports_lock);
+ list_del(&port->list);
+ spin_unlock_irq(&port->portdev->ports_lock);
+
+ if (port->guest_connected) {
+ port->guest_connected = false;
+ port->host_connected = false;
+ wake_up_interruptible(&port->waitqueue);
+
+ /* Let the app know the port is going down. */
+ send_sigio_to_port(port);
+ }
+
+ if (is_console_port(port)) {
+ spin_lock_irq(&pdrvdata_lock);
+ list_del(&port->cons.list);
+ spin_unlock_irq(&pdrvdata_lock);
+#if 0
+ /*
+ * hvc_remove() not called as removing one hvc port
+ * results in other hvc ports getting frozen.
+ *
+ * Once this is resolved in hvc, this functionality
+ * will be enabled. Till that is done, the -EPIPE
+ * return from get_chars() above will help
+ * hvc_console.c to clean up on ports we remove here.
+ */
+ hvc_remove(port->cons.hvc);
+#endif
+ }
+
+ /* Remove unused data this port might have received. */
+ discard_port_data(port);
+
+ reclaim_consumed_buffers(port);
+
+ /* Remove buffers we queued up for the Host to send us data in. */
+ while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
+ free_buf(buf);
+
+ /*
+ * We should just assume the device itself has gone off --
+ * else a close on an open port later will try to send out a
+ * control message.
+ */
+ port->portdev = NULL;
+
+ /*
+ * Locks around here are not necessary - a port can't be
+ * opened after we removed the port struct from ports_list
+ * above.
+ */
+ kref_put(&port->kref, remove_port);
+}
+
+/* Any private messages that the Host and Guest want to share */
+static void handle_control_message(struct ports_device *portdev,
+ struct port_buffer *buf)
+{
+ struct virtio_console_control *cpkt;
+ struct port *port;
+ size_t name_size;
+ int err;
+
+ cpkt = (struct virtio_console_control *)(buf->buf + buf->offset);
+
+ port = find_port_by_id(portdev, cpkt->id);
+ if (!port && cpkt->event != VIRTIO_CONSOLE_PORT_ADD) {
+ /* No valid header at start of buffer. Drop it. */
+ dev_dbg(&portdev->vdev->dev,
+ "Invalid index %u in control packet\n", cpkt->id);
+ return;
+ }
+
+ switch (cpkt->event) {
+ case VIRTIO_CONSOLE_PORT_ADD:
+ if (port) {
+ dev_dbg(&portdev->vdev->dev,
+ "Port %u already added\n", port->id);
+ send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1);
+ break;
+ }
+ if (cpkt->id >= portdev->config.max_nr_ports) {
+ dev_warn(&portdev->vdev->dev,
+ "Request for adding port with out-of-bound id %u, max. supported id: %u\n",
+ cpkt->id, portdev->config.max_nr_ports - 1);
+ break;
+ }
+ add_port(portdev, cpkt->id);
+ break;
+ case VIRTIO_CONSOLE_PORT_REMOVE:
+ unplug_port(port);
+ break;
+ case VIRTIO_CONSOLE_CONSOLE_PORT:
+ if (!cpkt->value)
+ break;
+ if (is_console_port(port))
+ break;
+
+ init_port_console(port);
+ /*
+ * Could remove the port here in case init fails - but
+ * have to notify the host first.
+ */
+ break;
+ case VIRTIO_CONSOLE_RESIZE: {
+ struct {
+ __u16 rows;
+ __u16 cols;
+ } size;
+
+ if (!is_console_port(port))
+ break;
+
+ memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt),
+ sizeof(size));
+ set_console_size(port, size.rows, size.cols);
+
+ port->cons.hvc->irq_requested = 1;
+ resize_console(port);
+ break;
+ }
+ case VIRTIO_CONSOLE_PORT_OPEN:
+ port->host_connected = cpkt->value;
+ wake_up_interruptible(&port->waitqueue);
+ /*
+ * If the host port got closed and the host had any
+ * unconsumed buffers, we'll be able to reclaim them
+ * now.
+ */
+ spin_lock_irq(&port->outvq_lock);
+ reclaim_consumed_buffers(port);
+ spin_unlock_irq(&port->outvq_lock);
+
+ /*
+ * If the guest is connected, it'll be interested in
+ * knowing the host connection state changed.
+ */
+ send_sigio_to_port(port);
+ break;
+ case VIRTIO_CONSOLE_PORT_NAME:
+ /*
+ * Skip the size of the header and the cpkt to get the size
+ * of the name that was sent
+ */
+ name_size = buf->len - buf->offset - sizeof(*cpkt) + 1;
+
+ port->name = kmalloc(name_size, GFP_KERNEL);
+ if (!port->name) {
+ dev_err(port->dev,
+ "Not enough space to store port name\n");
+ break;
+ }
+ strncpy(port->name, buf->buf + buf->offset + sizeof(*cpkt),
+ name_size - 1);
+ port->name[name_size - 1] = 0;
+
+ /*
+ * Since we only have one sysfs attribute, 'name',
+ * create it only if we have a name for the port.
+ */
+ err = sysfs_create_group(&port->dev->kobj,
+ &port_attribute_group);
+ if (err) {
+ dev_err(port->dev,
+ "Error %d creating sysfs device attributes\n",
+ err);
+ } else {
+ /*
+ * Generate a udev event so that appropriate
+ * symlinks can be created based on udev
+ * rules.
+ */
+ kobject_uevent(&port->dev->kobj, KOBJ_CHANGE);
+ }
+ break;
+ }
+}
+
+static void control_work_handler(struct work_struct *work)
+{
+ struct ports_device *portdev;
+ struct virtqueue *vq;
+ struct port_buffer *buf;
+ unsigned int len;
+
+ portdev = container_of(work, struct ports_device, control_work);
+ vq = portdev->c_ivq;
+
+ spin_lock(&portdev->cvq_lock);
+ while ((buf = virtqueue_get_buf(vq, &len))) {
+ spin_unlock(&portdev->cvq_lock);
+
+ buf->len = len;
+ buf->offset = 0;
+
+ handle_control_message(portdev, buf);
+
+ spin_lock(&portdev->cvq_lock);
+ if (add_inbuf(portdev->c_ivq, buf) < 0) {
+ dev_warn(&portdev->vdev->dev,
+ "Error adding buffer to queue\n");
+ free_buf(buf);
+ }
+ }
+ spin_unlock(&portdev->cvq_lock);
+}
+
+static void out_intr(struct virtqueue *vq)
+{
+ struct port *port;
+
+ port = find_port_by_vq(vq->vdev->priv, vq);
+ if (!port)
+ return;
+
+ wake_up_interruptible(&port->waitqueue);
+}
+
+static void in_intr(struct virtqueue *vq)
+{
+ struct port *port;
+ unsigned long flags;
+
+ port = find_port_by_vq(vq->vdev->priv, vq);
+ if (!port)
+ return;
+
+ spin_lock_irqsave(&port->inbuf_lock, flags);
+ if (!port->inbuf)
+ port->inbuf = get_inbuf(port);
+
+ /*
+ * Don't queue up data when port is closed. This condition
+ * can be reached when a console port is not yet connected (no
+ * tty is spawned) and the host sends out data to console
+ * ports. For generic serial ports, the host won't
+ * (shouldn't) send data till the guest is connected.
+ */
+ if (!port->guest_connected)
+ discard_port_data(port);
+
+ spin_unlock_irqrestore(&port->inbuf_lock, flags);
+
+ wake_up_interruptible(&port->waitqueue);
+
+ /* Send a SIGIO indicating new data in case the process asked for it */
+ send_sigio_to_port(port);
+
+ if (is_console_port(port) && hvc_poll(port->cons.hvc))
+ hvc_kick();
+}
+
+static void control_intr(struct virtqueue *vq)
+{
+ struct ports_device *portdev;
+
+ portdev = vq->vdev->priv;
+ schedule_work(&portdev->control_work);
+}
+
+static void config_intr(struct virtio_device *vdev)
+{
+ struct ports_device *portdev;
+
+ portdev = vdev->priv;
+
+ if (!use_multiport(portdev)) {
+ struct port *port;
+ u16 rows, cols;
+
+ vdev->config->get(vdev,
+ offsetof(struct virtio_console_config, cols),
+ &cols, sizeof(u16));
+ vdev->config->get(vdev,
+ offsetof(struct virtio_console_config, rows),
+ &rows, sizeof(u16));
+
+ port = find_port_by_id(portdev, 0);
+ set_console_size(port, rows, cols);
+
+ /*
+ * We'll use this way of resizing only for legacy
+ * support. For newer userspace
+ * (VIRTIO_CONSOLE_F_MULTPORT+), use control messages
+ * to indicate console size changes so that it can be
+ * done per-port.
+ */
+ resize_console(port);
+ }
+}
+
+static int init_vqs(struct ports_device *portdev)
+{
+ vq_callback_t **io_callbacks;
+ char **io_names;
+ struct virtqueue **vqs;
+ u32 i, j, nr_ports, nr_queues;
+ int err;
+
+ nr_ports = portdev->config.max_nr_ports;
+ nr_queues = use_multiport(portdev) ? (nr_ports + 1) * 2 : 2;
+
+ vqs = kmalloc(nr_queues * sizeof(struct virtqueue *), GFP_KERNEL);
+ io_callbacks = kmalloc(nr_queues * sizeof(vq_callback_t *), GFP_KERNEL);
+ io_names = kmalloc(nr_queues * sizeof(char *), GFP_KERNEL);
+ portdev->in_vqs = kmalloc(nr_ports * sizeof(struct virtqueue *),
+ GFP_KERNEL);
+ portdev->out_vqs = kmalloc(nr_ports * sizeof(struct virtqueue *),
+ GFP_KERNEL);
+ if (!vqs || !io_callbacks || !io_names || !portdev->in_vqs ||
+ !portdev->out_vqs) {
+ err = -ENOMEM;
+ goto free;
+ }
+
+ /*
+ * For backward compat (newer host but older guest), the host
+ * spawns a console port first and also inits the vqs for port
+ * 0 before others.
+ */
+ j = 0;
+ io_callbacks[j] = in_intr;
+ io_callbacks[j + 1] = out_intr;
+ io_names[j] = "input";
+ io_names[j + 1] = "output";
+ j += 2;
+
+ if (use_multiport(portdev)) {
+ io_callbacks[j] = control_intr;
+ io_callbacks[j + 1] = NULL;
+ io_names[j] = "control-i";
+ io_names[j + 1] = "control-o";
+
+ for (i = 1; i < nr_ports; i++) {
+ j += 2;
+ io_callbacks[j] = in_intr;
+ io_callbacks[j + 1] = out_intr;
+ io_names[j] = "input";
+ io_names[j + 1] = "output";
+ }
+ }
+ /* Find the queues. */
+ err = portdev->vdev->config->find_vqs(portdev->vdev, nr_queues, vqs,
+ io_callbacks,
+ (const char **)io_names);
+ if (err)
+ goto free;
+
+ j = 0;
+ portdev->in_vqs[0] = vqs[0];
+ portdev->out_vqs[0] = vqs[1];
+ j += 2;
+ if (use_multiport(portdev)) {
+ portdev->c_ivq = vqs[j];
+ portdev->c_ovq = vqs[j + 1];
+
+ for (i = 1; i < nr_ports; i++) {
+ j += 2;
+ portdev->in_vqs[i] = vqs[j];
+ portdev->out_vqs[i] = vqs[j + 1];
+ }
+ }
+ kfree(io_names);
+ kfree(io_callbacks);
+ kfree(vqs);
+
+ return 0;
+
+free:
+ kfree(portdev->out_vqs);
+ kfree(portdev->in_vqs);
+ kfree(io_names);
+ kfree(io_callbacks);
+ kfree(vqs);
+
+ return err;
+}
+
+static const struct file_operations portdev_fops = {
+ .owner = THIS_MODULE,
+};
+
+/*
+ * Once we're further in boot, we get probed like any other virtio
+ * device.
+ *
+ * If the host also supports multiple console ports, we check the
+ * config space to see how many ports the host has spawned. We
+ * initialize each port found.
+ */
+static int __devinit virtcons_probe(struct virtio_device *vdev)
+{
+ struct ports_device *portdev;
+ int err;
+ bool multiport;
+
+ portdev = kmalloc(sizeof(*portdev), GFP_KERNEL);
+ if (!portdev) {
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ /* Attach this portdev to this virtio_device, and vice-versa. */
+ portdev->vdev = vdev;
+ vdev->priv = portdev;
+
+ spin_lock_irq(&pdrvdata_lock);
+ portdev->drv_index = pdrvdata.index++;
+ spin_unlock_irq(&pdrvdata_lock);
+
+ portdev->chr_major = register_chrdev(0, "virtio-portsdev",
+ &portdev_fops);
+ if (portdev->chr_major < 0) {
+ dev_err(&vdev->dev,
+ "Error %d registering chrdev for device %u\n",
+ portdev->chr_major, portdev->drv_index);
+ err = portdev->chr_major;
+ goto free;
+ }
+
+ multiport = false;
+ portdev->config.max_nr_ports = 1;
+ if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
+ multiport = true;
+ vdev->features[0] |= 1 << VIRTIO_CONSOLE_F_MULTIPORT;
+
+ vdev->config->get(vdev, offsetof(struct virtio_console_config,
+ max_nr_ports),
+ &portdev->config.max_nr_ports,
+ sizeof(portdev->config.max_nr_ports));
+ }
+
+ /* Let the Host know we support multiple ports.*/
+ vdev->config->finalize_features(vdev);
+
+ err = init_vqs(portdev);
+ if (err < 0) {
+ dev_err(&vdev->dev, "Error %d initializing vqs\n", err);
+ goto free_chrdev;
+ }
+
+ spin_lock_init(&portdev->ports_lock);
+ INIT_LIST_HEAD(&portdev->ports);
+
+ if (multiport) {
+ unsigned int nr_added_bufs;
+
+ spin_lock_init(&portdev->cvq_lock);
+ INIT_WORK(&portdev->control_work, &control_work_handler);
+
+ nr_added_bufs = fill_queue(portdev->c_ivq, &portdev->cvq_lock);
+ if (!nr_added_bufs) {
+ dev_err(&vdev->dev,
+ "Error allocating buffers for control queue\n");
+ err = -ENOMEM;
+ goto free_vqs;
+ }
+ } else {
+ /*
+ * For backward compatibility: Create a console port
+ * if we're running on older host.
+ */
+ add_port(portdev, 0);
+ }
+
+ spin_lock_irq(&pdrvdata_lock);
+ list_add_tail(&portdev->list, &pdrvdata.portdevs);
+ spin_unlock_irq(&pdrvdata_lock);
+
+ __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
+ VIRTIO_CONSOLE_DEVICE_READY, 1);
+ return 0;
+
+free_vqs:
+ /* The host might want to notify mgmt sw about device add failure */
+ __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
+ VIRTIO_CONSOLE_DEVICE_READY, 0);
+ vdev->config->del_vqs(vdev);
+ kfree(portdev->in_vqs);
+ kfree(portdev->out_vqs);
+free_chrdev:
+ unregister_chrdev(portdev->chr_major, "virtio-portsdev");
+free:
+ kfree(portdev);
+fail:
+ return err;
+}
+
+static void virtcons_remove(struct virtio_device *vdev)
+{
+ struct ports_device *portdev;
+ struct port *port, *port2;
+
+ portdev = vdev->priv;
+
+ spin_lock_irq(&pdrvdata_lock);
+ list_del(&portdev->list);
+ spin_unlock_irq(&pdrvdata_lock);
+
+ /* Disable interrupts for vqs */
+ vdev->config->reset(vdev);
+ /* Finish up work that's lined up */
+ cancel_work_sync(&portdev->control_work);
+
+ list_for_each_entry_safe(port, port2, &portdev->ports, list)
+ unplug_port(port);
+
+ unregister_chrdev(portdev->chr_major, "virtio-portsdev");
+
+ /*
+ * When yanking out a device, we immediately lose the
+ * (device-side) queues. So there's no point in keeping the
+ * guest side around till we drop our final reference. This
+ * also means that any ports which are in an open state will
+ * have to just stop using the port, as the vqs are going
+ * away.
+ */
+ if (use_multiport(portdev)) {
+ struct port_buffer *buf;
+ unsigned int len;
+
+ while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
+ free_buf(buf);
+
+ while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
+ free_buf(buf);
+ }
+
+ vdev->config->del_vqs(vdev);
+ kfree(portdev->in_vqs);
+ kfree(portdev->out_vqs);
+
+ kfree(portdev);
+}
+
+static struct virtio_device_id id_table[] = {
+ { VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
+ { 0 },
+};
+
+static unsigned int features[] = {
+ VIRTIO_CONSOLE_F_SIZE,
+ VIRTIO_CONSOLE_F_MULTIPORT,
+};
+
+static struct virtio_driver virtio_console = {
+ .feature_table = features,
+ .feature_table_size = ARRAY_SIZE(features),
+ .driver.name = KBUILD_MODNAME,
+ .driver.owner = THIS_MODULE,
+ .id_table = id_table,
+ .probe = virtcons_probe,
+ .remove = virtcons_remove,
+ .config_changed = config_intr,
+};
+
+static int __init init(void)
+{
+ int err;
+
+ pdrvdata.class = class_create(THIS_MODULE, "virtio-ports");
+ if (IS_ERR(pdrvdata.class)) {
+ err = PTR_ERR(pdrvdata.class);
+ pr_err("Error %d creating virtio-ports class\n", err);
+ return err;
+ }
+
+ pdrvdata.debugfs_dir = debugfs_create_dir("virtio-ports", NULL);
+ if (!pdrvdata.debugfs_dir) {
+ pr_warning("Error %ld creating debugfs dir for virtio-ports\n",
+ PTR_ERR(pdrvdata.debugfs_dir));
+ }
+ INIT_LIST_HEAD(&pdrvdata.consoles);
+ INIT_LIST_HEAD(&pdrvdata.portdevs);
+
+ return register_virtio_driver(&virtio_console);
+}
+
+static void __exit fini(void)
+{
+ unregister_virtio_driver(&virtio_console);
+
+ class_destroy(pdrvdata.class);
+ if (pdrvdata.debugfs_dir)
+ debugfs_remove_recursive(pdrvdata.debugfs_dir);
+}
+module_init(init);
+module_exit(fini);
+
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_DESCRIPTION("Virtio console driver");
+MODULE_LICENSE("GPL");
ret = sysdev_driver_register(&cpu_sysdev_class,
&cpufreq_sysdev_driver);
+ if (ret)
+ goto err_null_driver;
- if ((!ret) && !(cpufreq_driver->flags & CPUFREQ_STICKY)) {
+ if (!(cpufreq_driver->flags & CPUFREQ_STICKY)) {
int i;
ret = -ENODEV;
if (ret) {
dprintk("no CPU initialized for driver %s\n",
driver_data->name);
- sysdev_driver_unregister(&cpu_sysdev_class,
- &cpufreq_sysdev_driver);
-
- spin_lock_irqsave(&cpufreq_driver_lock, flags);
- cpufreq_driver = NULL;
- spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
+ goto err_sysdev_unreg;
}
}
- if (!ret) {
- register_hotcpu_notifier(&cpufreq_cpu_notifier);
- dprintk("driver %s up and running\n", driver_data->name);
- cpufreq_debug_enable_ratelimit();
- }
+ register_hotcpu_notifier(&cpufreq_cpu_notifier);
+ dprintk("driver %s up and running\n", driver_data->name);
+ cpufreq_debug_enable_ratelimit();
+ return 0;
+err_sysdev_unreg:
+ sysdev_driver_unregister(&cpu_sysdev_class,
+ &cpufreq_sysdev_driver);
+err_null_driver:
+ spin_lock_irqsave(&cpufreq_driver_lock, flags);
+ cpufreq_driver = NULL;
+ spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_register_driver);
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
+#include <linux/delay.h>
#include <linux/dmapool.h>
#include <linux/dmaengine.h>
#include <linux/amba/bus.h>
}
/*
- * Overall DMAC remains enabled always.
+ * Pause the channel by setting the HALT bit.
*
- * Disabling individual channels could lose data.
+ * For M->P transfers, pause the DMAC first and then stop the peripheral -
+ * the FIFO can only drain if the peripheral is still requesting data.
+ * (note: this can still timeout if the DMAC FIFO never drains of data.)
*
- * Disable the peripheral DMA after disabling the DMAC in order to allow
- * the DMAC FIFO to drain, and hence allow the channel to show inactive
+ * For P->M transfers, disable the peripheral first to stop it filling
+ * the DMAC FIFO, and then pause the DMAC.
*/
static void pl08x_pause_phy_chan(struct pl08x_phy_chan *ch)
{
u32 val;
+ int timeout;
/* Set the HALT bit and wait for the FIFO to drain */
val = readl(ch->base + PL080_CH_CONFIG);
writel(val, ch->base + PL080_CH_CONFIG);
/* Wait for channel inactive */
- while (pl08x_phy_channel_busy(ch))
- cpu_relax();
+ for (timeout = 1000; timeout; timeout--) {
+ if (!pl08x_phy_channel_busy(ch))
+ break;
+ udelay(1);
+ }
+ if (pl08x_phy_channel_busy(ch))
+ pr_err("pl08x: channel%u timeout waiting for pause\n", ch->id);
}
static void pl08x_resume_phy_chan(struct pl08x_phy_chan *ch)
}
-/* Stops the channel */
-static void pl08x_stop_phy_chan(struct pl08x_phy_chan *ch)
+/*
+ * pl08x_terminate_phy_chan() stops the channel, clears the FIFO and
+ * clears any pending interrupt status. This should not be used for
+ * an on-going transfer, but as a method of shutting down a channel
+ * (eg, when it's no longer used) or terminating a transfer.
+ */
+static void pl08x_terminate_phy_chan(struct pl08x_driver_data *pl08x,
+ struct pl08x_phy_chan *ch)
{
- u32 val;
+ u32 val = readl(ch->base + PL080_CH_CONFIG);
- pl08x_pause_phy_chan(ch);
+ val &= ~(PL080_CONFIG_ENABLE | PL080_CONFIG_ERR_IRQ_MASK |
+ PL080_CONFIG_TC_IRQ_MASK);
- /* Disable channel */
- val = readl(ch->base + PL080_CH_CONFIG);
- val &= ~PL080_CONFIG_ENABLE;
- val &= ~PL080_CONFIG_ERR_IRQ_MASK;
- val &= ~PL080_CONFIG_TC_IRQ_MASK;
writel(val, ch->base + PL080_CH_CONFIG);
+
+ writel(1 << ch->id, pl08x->base + PL080_ERR_CLEAR);
+ writel(1 << ch->id, pl08x->base + PL080_TC_CLEAR);
}
static inline u32 get_bytes_in_cctl(u32 cctl)
{
unsigned long flags;
+ spin_lock_irqsave(&ch->lock, flags);
+
/* Stop the channel and clear its interrupts */
- pl08x_stop_phy_chan(ch);
- writel((1 << ch->id), pl08x->base + PL080_ERR_CLEAR);
- writel((1 << ch->id), pl08x->base + PL080_TC_CLEAR);
+ pl08x_terminate_phy_chan(pl08x, ch);
/* Mark it as free */
- spin_lock_irqsave(&ch->lock, flags);
ch->serving = NULL;
spin_unlock_irqrestore(&ch->lock, flags);
}
plchan->state = PL08X_CHAN_IDLE;
if (plchan->phychan) {
- pl08x_stop_phy_chan(plchan->phychan);
+ pl08x_terminate_phy_chan(pl08x, plchan->phychan);
/*
* Mark physical channel as free and free any slave
struct imxdma_engine {
struct device *dev;
+ struct device_dma_parameters dma_parms;
struct dma_device dma_device;
struct imxdma_channel channel[MAX_DMA_CHANNELS];
};
else
dmamode = DMA_MODE_WRITE;
+ switch (imxdmac->word_size) {
+ case DMA_SLAVE_BUSWIDTH_4_BYTES:
+ if (sgl->length & 3 || sgl->dma_address & 3)
+ return NULL;
+ break;
+ case DMA_SLAVE_BUSWIDTH_2_BYTES:
+ if (sgl->length & 1 || sgl->dma_address & 1)
+ return NULL;
+ break;
+ case DMA_SLAVE_BUSWIDTH_1_BYTE:
+ break;
+ default:
+ return NULL;
+ }
+
ret = imx_dma_setup_sg(imxdmac->imxdma_channel, sgl, sg_len,
dma_length, imxdmac->per_address, dmamode);
if (ret)
INIT_LIST_HEAD(&imxdma->dma_device.channels);
+ dma_cap_set(DMA_SLAVE, imxdma->dma_device.cap_mask);
+ dma_cap_set(DMA_CYCLIC, imxdma->dma_device.cap_mask);
+
/* Initialize channel parameters */
for (i = 0; i < MAX_DMA_CHANNELS; i++) {
struct imxdma_channel *imxdmac = &imxdma->channel[i];
imxdmac->imxdma = imxdma;
spin_lock_init(&imxdmac->lock);
- dma_cap_set(DMA_SLAVE, imxdma->dma_device.cap_mask);
- dma_cap_set(DMA_CYCLIC, imxdma->dma_device.cap_mask);
-
imxdmac->chan.device = &imxdma->dma_device;
- imxdmac->chan.chan_id = i;
imxdmac->channel = i;
/* Add the channel to the DMAC list */
platform_set_drvdata(pdev, imxdma);
+ imxdma->dma_device.dev->dma_parms = &imxdma->dma_parms;
+ dma_set_max_seg_size(imxdma->dma_device.dev, 0xffffff);
+
ret = dma_async_device_register(&imxdma->dma_device);
if (ret) {
dev_err(&pdev->dev, "unable to register\n");
* struct sdma_channel - housekeeping for a SDMA channel
*
* @sdma pointer to the SDMA engine for this channel
- * @channel the channel number, matches dmaengine chan_id
+ * @channel the channel number, matches dmaengine chan_id + 1
* @direction transfer type. Needed for setting SDMA script
* @peripheral_type Peripheral type. Needed for setting SDMA script
* @event_id0 aka dma request line
struct sdma_engine {
struct device *dev;
+ struct device_dma_parameters dma_parms;
struct sdma_channel channel[MAX_DMA_CHANNELS];
struct sdma_channel_control *channel_control;
void __iomem *regs;
if (bd->mode.status & BD_RROR)
sdmac->status = DMA_ERROR;
else
- sdmac->status = DMA_SUCCESS;
+ sdmac->status = DMA_IN_PROGRESS;
bd->mode.status |= BD_DONE;
sdmac->buf_tail++;
__raw_writel(1 << channel, sdma->regs + SDMA_H_START);
}
-static dma_cookie_t sdma_assign_cookie(struct sdma_channel *sdma)
+static dma_cookie_t sdma_assign_cookie(struct sdma_channel *sdmac)
{
- dma_cookie_t cookie = sdma->chan.cookie;
+ dma_cookie_t cookie = sdmac->chan.cookie;
if (++cookie < 0)
cookie = 1;
- sdma->chan.cookie = cookie;
- sdma->desc.cookie = cookie;
+ sdmac->chan.cookie = cookie;
+ sdmac->desc.cookie = cookie;
return cookie;
}
cookie = sdma_assign_cookie(sdmac);
- sdma_enable_channel(sdma, tx->chan->chan_id);
+ sdma_enable_channel(sdma, sdmac->channel);
spin_unlock_irq(&sdmac->lock);
struct imx_dma_data *data = chan->private;
int prio, ret;
- /* No need to execute this for internal channel 0 */
- if (chan->chan_id == 0)
- return 0;
-
if (!data)
return -EINVAL;
struct sdma_channel *sdmac = to_sdma_chan(chan);
struct sdma_engine *sdma = sdmac->sdma;
int ret, i, count;
- int channel = chan->chan_id;
+ int channel = sdmac->channel;
struct scatterlist *sg;
if (sdmac->status == DMA_IN_PROGRESS)
ret = -EINVAL;
goto err_out;
}
- if (sdmac->word_size == DMA_SLAVE_BUSWIDTH_4_BYTES)
+
+ switch (sdmac->word_size) {
+ case DMA_SLAVE_BUSWIDTH_4_BYTES:
bd->mode.command = 0;
- else
- bd->mode.command = sdmac->word_size;
+ if (count & 3 || sg->dma_address & 3)
+ return NULL;
+ break;
+ case DMA_SLAVE_BUSWIDTH_2_BYTES:
+ bd->mode.command = 2;
+ if (count & 1 || sg->dma_address & 1)
+ return NULL;
+ break;
+ case DMA_SLAVE_BUSWIDTH_1_BYTE:
+ bd->mode.command = 1;
+ break;
+ default:
+ return NULL;
+ }
param = BD_DONE | BD_EXTD | BD_CONT;
- if (sdmac->flags & IMX_DMA_SG_LOOP) {
+ if (i + 1 == sg_len) {
param |= BD_INTR;
- if (i + 1 == sg_len)
- param |= BD_WRAP;
+ param |= BD_LAST;
+ param &= ~BD_CONT;
}
- if (i + 1 == sg_len)
- param |= BD_INTR;
-
dev_dbg(sdma->dev, "entry %d: count: %d dma: 0x%08x %s%s\n",
i, count, sg->dma_address,
param & BD_WRAP ? "wrap" : "",
return &sdmac->desc;
err_out:
+ sdmac->status = DMA_ERROR;
return NULL;
}
struct sdma_channel *sdmac = to_sdma_chan(chan);
struct sdma_engine *sdma = sdmac->sdma;
int num_periods = buf_len / period_len;
- int channel = chan->chan_id;
+ int channel = sdmac->channel;
int ret, i = 0, buf = 0;
dev_dbg(sdma->dev, "%s channel: %d\n", __func__, channel);
{
struct sdma_channel *sdmac = to_sdma_chan(chan);
dma_cookie_t last_used;
- enum dma_status ret;
last_used = chan->cookie;
- ret = dma_async_is_complete(cookie, sdmac->last_completed, last_used);
dma_set_tx_state(txstate, sdmac->last_completed, last_used, 0);
- return ret;
+ return sdmac->status;
}
static void sdma_issue_pending(struct dma_chan *chan)
/* download the RAM image for SDMA */
sdma_load_script(sdma, ram_code,
header->ram_code_size,
- sdma->script_addrs->ram_code_start_addr);
+ addr->ram_code_start_addr);
clk_disable(sdma->clk);
sdma_add_scripts(sdma, addr);
struct resource *iores;
struct sdma_platform_data *pdata = pdev->dev.platform_data;
int i;
- dma_cap_mask_t mask;
struct sdma_engine *sdma;
sdma = kzalloc(sizeof(*sdma), GFP_KERNEL);
sdma->version = pdata->sdma_version;
+ dma_cap_set(DMA_SLAVE, sdma->dma_device.cap_mask);
+ dma_cap_set(DMA_CYCLIC, sdma->dma_device.cap_mask);
+
INIT_LIST_HEAD(&sdma->dma_device.channels);
/* Initialize channel parameters */
for (i = 0; i < MAX_DMA_CHANNELS; i++) {
sdmac->sdma = sdma;
spin_lock_init(&sdmac->lock);
- dma_cap_set(DMA_SLAVE, sdma->dma_device.cap_mask);
- dma_cap_set(DMA_CYCLIC, sdma->dma_device.cap_mask);
-
sdmac->chan.device = &sdma->dma_device;
- sdmac->chan.chan_id = i;
sdmac->channel = i;
- /* Add the channel to the DMAC list */
- list_add_tail(&sdmac->chan.device_node, &sdma->dma_device.channels);
+ /*
+ * Add the channel to the DMAC list. Do not add channel 0 though
+ * because we need it internally in the SDMA driver. This also means
+ * that channel 0 in dmaengine counting matches sdma channel 1.
+ */
+ if (i)
+ list_add_tail(&sdmac->chan.device_node,
+ &sdma->dma_device.channels);
}
ret = sdma_init(sdma);
sdma->dma_device.device_prep_dma_cyclic = sdma_prep_dma_cyclic;
sdma->dma_device.device_control = sdma_control;
sdma->dma_device.device_issue_pending = sdma_issue_pending;
+ sdma->dma_device.dev->dma_parms = &sdma->dma_parms;
+ dma_set_max_seg_size(sdma->dma_device.dev, 65535);
ret = dma_async_device_register(&sdma->dma_device);
if (ret) {
goto err_init;
}
- /* request channel 0. This is an internal control channel
- * to the SDMA engine and not available to clients.
- */
- dma_cap_zero(mask);
- dma_cap_set(DMA_SLAVE, mask);
- dma_request_channel(mask, NULL, NULL);
-
dev_info(sdma->dev, "initialized\n");
return 0;
err_request_region:
err_irq:
kfree(sdma);
- return 0;
+ return ret;
}
static int __exit sdma_remove(struct platform_device *pdev)
reg = idmac_read_icreg(ipu, IDMAC_CHA_EN);
idmac_write_icreg(ipu, reg & ~chan_mask, IDMAC_CHA_EN);
- /*
- * Problem (observed with channel DMAIC_7): after enabling the channel
- * and initialising buffers, there comes an interrupt with current still
- * pointing at buffer 0, whereas it should use buffer 0 first and only
- * generate an interrupt when it is done, then current should already
- * point to buffer 1. This spurious interrupt also comes on channel
- * DMASDC_0. With DMAIC_7 normally, is we just leave the ISR after the
- * first interrupt, there comes the second with current correctly
- * pointing to buffer 1 this time. But sometimes this second interrupt
- * doesn't come and the channel hangs. Clearing BUFx_RDY when disabling
- * the channel seems to prevent the channel from hanging, but it doesn't
- * prevent the spurious interrupt. This might also be unsafe. Think
- * about the IDMAC controller trying to switch to a buffer, when we
- * clear the ready bit, and re-enable it a moment later.
- */
- reg = idmac_read_ipureg(ipu, IPU_CHA_BUF0_RDY);
- idmac_write_ipureg(ipu, 0, IPU_CHA_BUF0_RDY);
- idmac_write_ipureg(ipu, reg & ~(1UL << channel), IPU_CHA_BUF0_RDY);
-
- reg = idmac_read_ipureg(ipu, IPU_CHA_BUF1_RDY);
- idmac_write_ipureg(ipu, 0, IPU_CHA_BUF1_RDY);
- idmac_write_ipureg(ipu, reg & ~(1UL << channel), IPU_CHA_BUF1_RDY);
-
spin_unlock_irqrestore(&ipu->lock, flags);
return 0;
/* Other interrupts do not interfere with this channel */
spin_lock(&ichan->lock);
- if (unlikely(chan_id != IDMAC_SDC_0 && chan_id != IDMAC_SDC_1 &&
- ((curbuf >> chan_id) & 1) == ichan->active_buffer &&
- !list_is_last(ichan->queue.next, &ichan->queue))) {
- int i = 100;
-
- /* This doesn't help. See comment in ipu_disable_channel() */
- while (--i) {
- curbuf = idmac_read_ipureg(&ipu_data, IPU_CHA_CUR_BUF);
- if (((curbuf >> chan_id) & 1) != ichan->active_buffer)
- break;
- cpu_relax();
- }
-
- if (!i) {
- spin_unlock(&ichan->lock);
- dev_dbg(dev,
- "IRQ on active buffer on channel %x, active "
- "%d, ready %x, %x, current %x!\n", chan_id,
- ichan->active_buffer, ready0, ready1, curbuf);
- return IRQ_NONE;
- } else
- dev_dbg(dev,
- "Buffer deactivated on channel %x, active "
- "%d, ready %x, %x, current %x, rest %d!\n", chan_id,
- ichan->active_buffer, ready0, ready1, curbuf, i);
- }
-
if (unlikely((ichan->active_buffer && (ready1 >> chan_id) & 1) ||
(!ichan->active_buffer && (ready0 >> chan_id) & 1)
)) {
/* Display and decode various NB registers for debug purposes. */
static void amd64_dump_misc_regs(struct amd64_pvt *pvt)
{
- int ganged;
-
debugf1("F3xE8 (NB Cap): 0x%08x\n", pvt->nbcap);
debugf1(" NB two channel DRAM capable: %s\n",
debugf1(" DramHoleValid: %s\n",
(pvt->dhar & DHAR_VALID) ? "yes" : "no");
+ amd64_debug_display_dimm_sizes(0, pvt);
+
/* everything below this point is Fam10h and above */
- if (boot_cpu_data.x86 == 0xf) {
- amd64_debug_display_dimm_sizes(0, pvt);
+ if (boot_cpu_data.x86 == 0xf)
return;
- }
+
+ amd64_debug_display_dimm_sizes(1, pvt);
amd64_info("using %s syndromes.\n", ((pvt->syn_type == 8) ? "x8" : "x4"));
/* Only if NOT ganged does dclr1 have valid info */
if (!dct_ganging_enabled(pvt))
amd64_dump_dramcfg_low(pvt->dclr1, 1);
-
- /*
- * Determine if ganged and then dump memory sizes for first controller,
- * and if NOT ganged dump info for 2nd controller.
- */
- ganged = dct_ganging_enabled(pvt);
-
- amd64_debug_display_dimm_sizes(0, pvt);
-
- if (!ganged)
- amd64_debug_display_dimm_sizes(1, pvt);
}
/* Read in both of DBAM registers */
WARN_ON(ctrl != 0);
}
- debugf1("F2x%d80 (DRAM Bank Address Mapping): 0x%08x\n",
- ctrl, ctrl ? pvt->dbam1 : pvt->dbam0);
+ dbam = (ctrl && !dct_ganging_enabled(pvt)) ? pvt->dbam1 : pvt->dbam0;
+ dcsb = (ctrl && !dct_ganging_enabled(pvt)) ? pvt->dcsb1 : pvt->dcsb0;
- dbam = ctrl ? pvt->dbam1 : pvt->dbam0;
- dcsb = ctrl ? pvt->dcsb1 : pvt->dcsb0;
+ debugf1("F2x%d80 (DRAM Bank Address Mapping): 0x%08x\n", ctrl, dbam);
edac_printk(KERN_DEBUG, EDAC_MC, "DCT%d chip selects:\n", ctrl);
static void __init dmi_dump_ids(void)
{
+ const char *board; /* Board Name is optional */
+
printk(KERN_DEBUG "DMI: ");
- print_filtered(dmi_get_system_info(DMI_BOARD_NAME));
- printk(KERN_CONT "/");
+ print_filtered(dmi_get_system_info(DMI_SYS_VENDOR));
+ printk(KERN_CONT " ");
print_filtered(dmi_get_system_info(DMI_PRODUCT_NAME));
+ board = dmi_get_system_info(DMI_BOARD_NAME);
+ if (board) {
+ printk(KERN_CONT "/");
+ print_filtered(board);
+ }
printk(KERN_CONT ", BIOS ");
print_filtered(dmi_get_system_info(DMI_BIOS_VERSION));
printk(KERN_CONT " ");
{ PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x802E) },
{ 0, }
};
+MODULE_DEVICE_TABLE(pci, ioh_gpio_pcidev_id);
static struct pci_driver ioh_gpio_driver = {
.name = "ml_ioh_gpio",
unsigned gpio_start;
uint16_t reg_output;
uint16_t reg_direction;
+ struct mutex i2c_lock;
#ifdef CONFIG_GPIO_PCA953X_IRQ
struct mutex irq_lock;
chip = container_of(gc, struct pca953x_chip, gpio_chip);
+ mutex_lock(&chip->i2c_lock);
reg_val = chip->reg_direction | (1u << off);
ret = pca953x_write_reg(chip, PCA953X_DIRECTION, reg_val);
if (ret)
- return ret;
+ goto exit;
chip->reg_direction = reg_val;
- return 0;
+ ret = 0;
+exit:
+ mutex_unlock(&chip->i2c_lock);
+ return ret;
}
static int pca953x_gpio_direction_output(struct gpio_chip *gc,
chip = container_of(gc, struct pca953x_chip, gpio_chip);
+ mutex_lock(&chip->i2c_lock);
/* set output level */
if (val)
reg_val = chip->reg_output | (1u << off);
ret = pca953x_write_reg(chip, PCA953X_OUTPUT, reg_val);
if (ret)
- return ret;
+ goto exit;
chip->reg_output = reg_val;
reg_val = chip->reg_direction & ~(1u << off);
ret = pca953x_write_reg(chip, PCA953X_DIRECTION, reg_val);
if (ret)
- return ret;
+ goto exit;
chip->reg_direction = reg_val;
- return 0;
+ ret = 0;
+exit:
+ mutex_unlock(&chip->i2c_lock);
+ return ret;
}
static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off)
chip = container_of(gc, struct pca953x_chip, gpio_chip);
+ mutex_lock(&chip->i2c_lock);
ret = pca953x_read_reg(chip, PCA953X_INPUT, ®_val);
+ mutex_unlock(&chip->i2c_lock);
if (ret < 0) {
/* NOTE: diagnostic already emitted; that's all we should
* do unless gpio_*_value_cansleep() calls become different
chip = container_of(gc, struct pca953x_chip, gpio_chip);
+ mutex_lock(&chip->i2c_lock);
if (val)
reg_val = chip->reg_output | (1u << off);
else
ret = pca953x_write_reg(chip, PCA953X_OUTPUT, reg_val);
if (ret)
- return;
+ goto exit;
chip->reg_output = reg_val;
+exit:
+ mutex_unlock(&chip->i2c_lock);
}
static void pca953x_setup_gpio(struct pca953x_chip *chip, int gpios)
chip->names = pdata->names;
+ mutex_init(&chip->i2c_lock);
+
/* initialize cached registers from their original values.
* we can't share this chip with another i2c master.
*/
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x8803) },
{ 0, }
};
+MODULE_DEVICE_TABLE(pci, pch_gpio_pcidev_id);
static struct pci_driver pch_gpio_driver = {
.name = "pch_gpio",
struct drm_crtc_helper_funcs *crtc_funcs;
u16 *red, *green, *blue, *transp;
struct drm_crtc *crtc;
- int i, rc = 0;
+ int i, j, rc = 0;
int start;
for (i = 0; i < fb_helper->crtc_count; i++) {
transp = cmap->transp;
start = cmap->start;
- for (i = 0; i < cmap->len; i++) {
+ for (j = 0; j < cmap->len; j++) {
u16 hred, hgreen, hblue, htransp = 0xffff;
hred = *red++;
#endif
mutex_lock(&dev->struct_mutex);
- seq_printf(m, "vma use count: %d, high_memory = %p, 0x%08llx\n",
+ seq_printf(m, "vma use count: %d, high_memory = %pK, 0x%pK\n",
atomic_read(&dev->vma_count),
- high_memory, (u64)virt_to_phys(high_memory));
+ high_memory, (void *)virt_to_phys(high_memory));
list_for_each_entry(pt, &dev->vmalist, head) {
vma = pt->vma;
if (!vma)
continue;
seq_printf(m,
- "\n%5d 0x%08lx-0x%08lx %c%c%c%c%c%c 0x%08lx000",
- pt->pid, vma->vm_start, vma->vm_end,
+ "\n%5d 0x%pK-0x%pK %c%c%c%c%c%c 0x%08lx000",
+ pt->pid,
+ (void *)vma->vm_start, (void *)vma->vm_end,
vma->vm_flags & VM_READ ? 'r' : '-',
vma->vm_flags & VM_WRITE ? 'w' : '-',
vma->vm_flags & VM_EXEC ? 'x' : '-',
* available. In that case we can't account for this and just
* hope for the best.
*/
- if ((vblrc > 0) && (abs(diff_ns) > 1000000))
+ if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
atomic_inc(&dev->_vblank_count[crtc]);
+ smp_mb__after_atomic_inc();
+ }
/* Invalidate all timestamps while vblank irq's are off. */
clear_vblank_timestamps(dev, crtc);
/* Dot clock in Hz: */
dotclock = (u64) crtc->hwmode.clock * 1000;
+ /* Fields of interlaced scanout modes are only halve a frame duration.
+ * Double the dotclock to get halve the frame-/line-/pixelduration.
+ */
+ if (crtc->hwmode.flags & DRM_MODE_FLAG_INTERLACE)
+ dotclock *= 2;
+
/* Valid dotclock? */
if (dotclock > 0) {
/* Convert scanline length in pixels and video dot clock to
return -EAGAIN;
}
- /* Don't know yet how to handle interlaced or
- * double scan modes. Just no-op for now.
- */
- if (mode->flags & (DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLSCAN)) {
- DRM_DEBUG("crtc %d: Noop due to unsupported mode.\n", crtc);
- return -ENOTSUPP;
- }
-
/* Get current scanout position with system timestamp.
* Repeat query up to DRM_TIMESTAMP_MAXRETRIES times
* if single query takes longer than max_error nanoseconds.
if (rc) {
tslot = atomic_read(&dev->_vblank_count[crtc]) + diff;
vblanktimestamp(dev, crtc, tslot) = t_vblank;
- smp_wmb();
}
+ smp_mb__before_atomic_inc();
atomic_add(diff, &dev->_vblank_count[crtc]);
+ smp_mb__after_atomic_inc();
}
/**
struct drm_file *file_priv)
{
struct drm_modeset_ctl *modeset = data;
- int crtc, ret = 0;
+ int ret = 0;
+ unsigned int crtc;
/* If drm_vblank_init() hasn't been called yet, just no-op */
if (!dev->num_crtcs)
* e.g., due to spurious vblank interrupts. We need to
* ignore those for accounting.
*/
- if (abs(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) {
+ if (abs64(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) {
/* Store new timestamp in ringbuffer. */
vblanktimestamp(dev, crtc, vblcount + 1) = tvblank;
- smp_wmb();
/* Increment cooked vblank count. This also atomically commits
* the timestamp computed above.
*/
+ smp_mb__before_atomic_inc();
atomic_inc(&dev->_vblank_count[crtc]);
+ smp_mb__after_atomic_inc();
} else {
DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n",
crtc, (int) diff_ns);
int max_freq;
/* RPSTAT1 is in the GT power well */
- __gen6_force_wake_get(dev_priv);
+ __gen6_gt_force_wake_get(dev_priv);
seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
seq_printf(m, "RPSTAT1: 0x%08x\n", I915_READ(GEN6_RPSTAT1));
seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
max_freq * 100);
- __gen6_force_wake_put(dev_priv);
+ __gen6_gt_force_wake_put(dev_priv);
} else {
seq_printf(m, "no P-state info available\n");
}
if (IS_GEN2(dev))
dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30));
+ /* 965GM sometimes incorrectly writes to hardware status page (HWS)
+ * using 32bit addressing, overwriting memory if HWS is located
+ * above 4GB.
+ *
+ * The documentation also mentions an issue with undefined
+ * behaviour if any general state is accessed within a page above 4GB,
+ * which also needs to be handled carefully.
+ */
+ if (IS_BROADWATER(dev) || IS_CRESTLINE(dev))
+ dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32));
+
mmio_bar = IS_GEN2(dev) ? 1 : 0;
dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, 0);
if (!dev_priv->regs) {
unsigned int i915_powersave = 1;
module_param_named(powersave, i915_powersave, int, 0600);
+unsigned int i915_semaphores = 0;
+module_param_named(semaphores, i915_semaphores, int, 0600);
+
+unsigned int i915_enable_rc6 = 0;
+module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
+
unsigned int i915_lvds_downclock = 0;
module_param_named(lvds_downclock, i915_lvds_downclock, int, 0400);
}
}
-void __gen6_force_wake_get(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
{
int count;
udelay(10);
}
-void __gen6_force_wake_put(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
{
I915_WRITE_NOTRACE(FORCEWAKE, 0);
POSTING_READ(FORCEWAKE);
}
+void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
+{
+ int loop = 500;
+ u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+ while (fifo < 20 && loop--) {
+ udelay(10);
+ fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+ }
+}
+
static int i915_drm_freeze(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
/* Resume the modeset for every activated CRTC */
drm_helper_resume_force_mode(dev);
- if (dev_priv->renderctx && dev_priv->pwrctx)
+ if (IS_IRONLAKE_M(dev))
ironlake_enable_rc6(dev);
}
extern int i915_max_ioctl;
extern unsigned int i915_fbpercrtc;
extern unsigned int i915_powersave;
+extern unsigned int i915_semaphores;
extern unsigned int i915_lvds_downclock;
extern unsigned int i915_panel_use_ssc;
+extern unsigned int i915_enable_rc6;
extern int i915_suspend(struct drm_device *dev, pm_message_t state);
extern int i915_resume(struct drm_device *dev);
void i915_gem_free_all_phys_object(struct drm_device *dev);
void i915_gem_release(struct drm_device *dev, struct drm_file *file);
+uint32_t
+i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj);
+
/* i915_gem_gtt.c */
void i915_gem_restore_gtt_mappings(struct drm_device *dev);
int __must_check i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj);
* must be set to prevent GT core from power down and stale values being
* returned.
*/
-void __gen6_force_wake_get(struct drm_i915_private *dev_priv);
-void __gen6_force_wake_put (struct drm_i915_private *dev_priv);
-static inline u32 i915_safe_read(struct drm_i915_private *dev_priv, u32 reg)
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
+void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
+
+static inline u32 i915_gt_read(struct drm_i915_private *dev_priv, u32 reg)
{
u32 val;
if (dev_priv->info->gen >= 6) {
- __gen6_force_wake_get(dev_priv);
+ __gen6_gt_force_wake_get(dev_priv);
val = I915_READ(reg);
- __gen6_force_wake_put(dev_priv);
+ __gen6_gt_force_wake_put(dev_priv);
} else
val = I915_READ(reg);
return val;
}
+static inline void i915_gt_write(struct drm_i915_private *dev_priv,
+ u32 reg, u32 val)
+{
+ if (dev_priv->info->gen >= 6)
+ __gen6_gt_wait_for_fifo(dev_priv);
+ I915_WRITE(reg, val);
+}
+
static inline void
i915_write(struct drm_i915_private *dev_priv, u32 reg, u64 val, int len)
{
* Return the required GTT alignment for an object, only taking into account
* unfenced tiled surface requirements.
*/
-static uint32_t
+uint32_t
i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj)
{
struct drm_device *dev = obj->base.dev;
if (from == NULL || to == from)
return 0;
- /* XXX gpu semaphores are currently causing hard hangs on SNB mobile */
- if (INTEL_INFO(obj->base.dev)->gen < 6 || IS_MOBILE(obj->base.dev))
+ /* XXX gpu semaphores are implicated in various hard hangs on SNB */
+ if (INTEL_INFO(obj->base.dev)->gen < 6 || !i915_semaphores)
return i915_gem_object_wait_rendering(obj, true);
idx = intel_ring_sync_index(from, to);
(obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end &&
i915_gem_object_fence_ok(obj, args->tiling_mode));
- obj->tiling_changed = true;
- obj->tiling_mode = args->tiling_mode;
- obj->stride = args->stride;
+ /* Rebind if we need a change of alignment */
+ if (!obj->map_and_fenceable) {
+ u32 unfenced_alignment =
+ i915_gem_get_unfenced_gtt_alignment(obj);
+ if (obj->gtt_offset & (unfenced_alignment - 1))
+ ret = i915_gem_object_unbind(obj);
+ }
+
+ if (ret == 0) {
+ obj->tiling_changed = true;
+ obj->tiling_mode = args->tiling_mode;
+ obj->stride = args->stride;
+ }
}
+ /* we have to maintain this existing ABI... */
+ args->stride = obj->stride;
+ args->tiling_mode = obj->tiling_mode;
drm_gem_object_unreference(&obj->base);
mutex_unlock(&dev->struct_mutex);
- return 0;
+ return ret;
}
/**
struct drm_mode_config *mode_config = &dev->mode_config;
struct intel_encoder *encoder;
+ DRM_DEBUG_KMS("running encoder hotplug functions\n");
+
list_for_each_entry(encoder, &mode_config->encoder_list, base.head)
if (encoder->hot_plug)
encoder->hot_plug(encoder);
} else {
hotplug_mask = SDE_CRT_HOTPLUG | SDE_PORTB_HOTPLUG |
SDE_PORTC_HOTPLUG | SDE_PORTD_HOTPLUG;
- hotplug_mask |= SDE_AUX_MASK | SDE_FDI_MASK | SDE_TRANS_MASK;
- I915_WRITE(FDI_RXA_IMR, 0);
- I915_WRITE(FDI_RXB_IMR, 0);
+ hotplug_mask |= SDE_AUX_MASK;
}
dev_priv->pch_irq_mask = ~hotplug_mask;
* address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
*/
#define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*x-1)
-#define MI_FLUSH_DW MI_INSTR(0x26, 2) /* for GEN6 */
+#define MI_FLUSH_DW MI_INSTR(0x26, 1) /* for GEN6 */
+#define MI_INVALIDATE_TLB (1<<18)
+#define MI_INVALIDATE_BSD (1<<7)
#define MI_BATCH_BUFFER MI_INSTR(0x30, 1)
#define MI_BATCH_NON_SECURE (1)
#define MI_BATCH_NON_SECURE_I965 (1<<8)
#define FORCEWAKE 0xA18C
#define FORCEWAKE_ACK 0x130090
+#define GT_FIFO_FREE_ENTRIES 0x120008
+
#define GEN6_RPNSWREQ 0xA008
#define GEN6_TURBO_DISABLE (1<<31)
#define GEN6_FREQUENCY(x) ((x)<<25)
u32 blt_ecoskpd;
/* Make sure blitter notifies FBC of writes */
- __gen6_force_wake_get(dev_priv);
+ __gen6_gt_force_wake_get(dev_priv);
blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD);
blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY <<
GEN6_BLITTER_LOCK_SHIFT;
GEN6_BLITTER_LOCK_SHIFT);
I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
POSTING_READ(GEN6_BLITTER_ECOSKPD);
- __gen6_force_wake_put(dev_priv);
+ __gen6_gt_force_wake_put(dev_priv);
}
static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
struct drm_i915_gem_object *obj = to_intel_framebuffer(old_fb)->obj;
wait_event(dev_priv->pending_flip_queue,
+ atomic_read(&dev_priv->mm.wedged) ||
atomic_read(&obj->pending_flip) == 0);
/* Big Hammer, we also need to ensure that any pending
* MI_WAIT_FOR_EVENT inside a user batch buffer on the
* current scanout is retired before unpinning the old
* framebuffer.
+ *
+ * This should only fail upon a hung GPU, in which case we
+ * can safely continue.
*/
ret = i915_gem_object_flush_gpu(obj, false);
- if (ret) {
- i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj);
- mutex_unlock(&dev->struct_mutex);
- return ret;
- }
+ (void) ret;
}
ret = intel_pipe_set_base_atomic(crtc, crtc->fb, x, y,
atomic_read(&obj->pending_flip) == 0);
}
+static bool intel_crtc_driving_pch(struct drm_crtc *crtc)
+{
+ struct drm_device *dev = crtc->dev;
+ struct drm_mode_config *mode_config = &dev->mode_config;
+ struct intel_encoder *encoder;
+
+ /*
+ * If there's a non-PCH eDP on this crtc, it must be DP_A, and that
+ * must be driven by its own crtc; no sharing is possible.
+ */
+ list_for_each_entry(encoder, &mode_config->encoder_list, base.head) {
+ if (encoder->base.crtc != crtc)
+ continue;
+
+ switch (encoder->type) {
+ case INTEL_OUTPUT_EDP:
+ if (!intel_encoder_is_pch_edp(&encoder->base))
+ return false;
+ continue;
+ }
+ }
+
+ return true;
+}
+
static void ironlake_crtc_enable(struct drm_crtc *crtc)
{
struct drm_device *dev = crtc->dev;
int pipe = intel_crtc->pipe;
int plane = intel_crtc->plane;
u32 reg, temp;
+ bool is_pch_port = false;
if (intel_crtc->active)
return;
I915_WRITE(PCH_LVDS, temp | LVDS_PORT_EN);
}
- ironlake_fdi_enable(crtc);
+ is_pch_port = intel_crtc_driving_pch(crtc);
+
+ if (is_pch_port)
+ ironlake_fdi_enable(crtc);
+ else {
+ /* disable CPU FDI tx and PCH FDI rx */
+ reg = FDI_TX_CTL(pipe);
+ temp = I915_READ(reg);
+ I915_WRITE(reg, temp & ~FDI_TX_ENABLE);
+ POSTING_READ(reg);
+
+ reg = FDI_RX_CTL(pipe);
+ temp = I915_READ(reg);
+ temp &= ~(0x7 << 16);
+ temp |= (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) << 11;
+ I915_WRITE(reg, temp & ~FDI_RX_ENABLE);
+
+ POSTING_READ(reg);
+ udelay(100);
+
+ /* Ironlake workaround, disable clock pointer after downing FDI */
+ if (HAS_PCH_IBX(dev))
+ I915_WRITE(FDI_RX_CHICKEN(pipe),
+ I915_READ(FDI_RX_CHICKEN(pipe) &
+ ~FDI_RX_PHASE_SYNC_POINTER_ENABLE));
+
+ /* still set train pattern 1 */
+ reg = FDI_TX_CTL(pipe);
+ temp = I915_READ(reg);
+ temp &= ~FDI_LINK_TRAIN_NONE;
+ temp |= FDI_LINK_TRAIN_PATTERN_1;
+ I915_WRITE(reg, temp);
+
+ reg = FDI_RX_CTL(pipe);
+ temp = I915_READ(reg);
+ if (HAS_PCH_CPT(dev)) {
+ temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
+ temp |= FDI_LINK_TRAIN_PATTERN_1_CPT;
+ } else {
+ temp &= ~FDI_LINK_TRAIN_NONE;
+ temp |= FDI_LINK_TRAIN_PATTERN_1;
+ }
+ /* BPC in FDI rx is consistent with that in PIPECONF */
+ temp &= ~(0x07 << 16);
+ temp |= (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) << 11;
+ I915_WRITE(reg, temp);
+
+ POSTING_READ(reg);
+ udelay(100);
+ }
/* Enable panel fitting for LVDS */
if (dev_priv->pch_pf_size &&
intel_flush_display_plane(dev, plane);
}
+ /* Skip the PCH stuff if possible */
+ if (!is_pch_port)
+ goto done;
+
/* For PCH output, training FDI link */
if (IS_GEN6(dev))
gen6_fdi_link_train(crtc);
I915_WRITE(reg, temp | TRANS_ENABLE);
if (wait_for(I915_READ(reg) & TRANS_STATE_ENABLE, 100))
DRM_ERROR("failed to enable transcoder %d\n", pipe);
-
+done:
intel_crtc_load_lut(crtc);
intel_update_fbc(dev);
intel_crtc_update_cursor(crtc, true);
/* Reset flags back to the 'unknown' status so that they
* will be correctly set on the initial modeset.
*/
- intel_crtc->cursor_addr = 0;
intel_crtc->dpms_mode = -1;
- intel_crtc->active = true; /* force the pipe off on setup_init_config */
}
static struct drm_crtc_helper_funcs intel_helper_funcs = {
dev_priv->pipe_to_crtc_mapping[intel_crtc->pipe] = &intel_crtc->base;
intel_crtc_reset(&intel_crtc->base);
+ intel_crtc->active = true; /* force the pipe off on setup_init_config */
if (HAS_PCH_SPLIT(dev)) {
intel_helper_funcs.prepare = ironlake_crtc_prepare;
* userspace...
*/
I915_WRITE(GEN6_RC_STATE, 0);
- __gen6_force_wake_get(dev_priv);
+ __gen6_gt_force_wake_get(dev_priv);
/* disable the counters and set deterministic thresholds */
I915_WRITE(GEN6_RC_CONTROL, 0);
/* enable all PM interrupts */
I915_WRITE(GEN6_PMINTRMSK, 0);
- __gen6_force_wake_put(dev_priv);
+ __gen6_gt_force_wake_put(dev_priv);
}
void intel_enable_clock_gating(struct drm_device *dev)
}
}
-void intel_disable_clock_gating(struct drm_device *dev)
+static void ironlake_teardown_rc6(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
if (dev_priv->renderctx) {
- struct drm_i915_gem_object *obj = dev_priv->renderctx;
-
- I915_WRITE(CCID, 0);
- POSTING_READ(CCID);
-
- i915_gem_object_unpin(obj);
- drm_gem_object_unreference(&obj->base);
+ i915_gem_object_unpin(dev_priv->renderctx);
+ drm_gem_object_unreference(&dev_priv->renderctx->base);
dev_priv->renderctx = NULL;
}
if (dev_priv->pwrctx) {
- struct drm_i915_gem_object *obj = dev_priv->pwrctx;
+ i915_gem_object_unpin(dev_priv->pwrctx);
+ drm_gem_object_unreference(&dev_priv->pwrctx->base);
+ dev_priv->pwrctx = NULL;
+ }
+}
+
+static void ironlake_disable_rc6(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ if (I915_READ(PWRCTXA)) {
+ /* Wake the GPU, prevent RC6, then restore RSTDBYCTL */
+ I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) | RCX_SW_EXIT);
+ wait_for(((I915_READ(RSTDBYCTL) & RSX_STATUS_MASK) == RSX_STATUS_ON),
+ 50);
I915_WRITE(PWRCTXA, 0);
POSTING_READ(PWRCTXA);
- i915_gem_object_unpin(obj);
- drm_gem_object_unreference(&obj->base);
- dev_priv->pwrctx = NULL;
+ I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
+ POSTING_READ(RSTDBYCTL);
}
+
+ ironlake_teardown_rc6(dev);
}
-static void ironlake_disable_rc6(struct drm_device *dev)
+static int ironlake_setup_rc6(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- /* Wake the GPU, prevent RC6, then restore RSTDBYCTL */
- I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) | RCX_SW_EXIT);
- wait_for(((I915_READ(RSTDBYCTL) & RSX_STATUS_MASK) == RSX_STATUS_ON),
- 10);
- POSTING_READ(CCID);
- I915_WRITE(PWRCTXA, 0);
- POSTING_READ(PWRCTXA);
- I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
- POSTING_READ(RSTDBYCTL);
- i915_gem_object_unpin(dev_priv->renderctx);
- drm_gem_object_unreference(&dev_priv->renderctx->base);
- dev_priv->renderctx = NULL;
- i915_gem_object_unpin(dev_priv->pwrctx);
- drm_gem_object_unreference(&dev_priv->pwrctx->base);
- dev_priv->pwrctx = NULL;
+ if (dev_priv->renderctx == NULL)
+ dev_priv->renderctx = intel_alloc_context_page(dev);
+ if (!dev_priv->renderctx)
+ return -ENOMEM;
+
+ if (dev_priv->pwrctx == NULL)
+ dev_priv->pwrctx = intel_alloc_context_page(dev);
+ if (!dev_priv->pwrctx) {
+ ironlake_teardown_rc6(dev);
+ return -ENOMEM;
+ }
+
+ return 0;
}
void ironlake_enable_rc6(struct drm_device *dev)
struct drm_i915_private *dev_priv = dev->dev_private;
int ret;
+ /* rc6 disabled by default due to repeated reports of hanging during
+ * boot and resume.
+ */
+ if (!i915_enable_rc6)
+ return;
+
+ ret = ironlake_setup_rc6(dev);
+ if (ret)
+ return;
+
/*
* GPU can automatically power down the render unit if given a page
* to save state.
*/
ret = BEGIN_LP_RING(6);
if (ret) {
- ironlake_disable_rc6(dev);
+ ironlake_teardown_rc6(dev);
return;
}
+
OUT_RING(MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
OUT_RING(MI_SET_CONTEXT);
OUT_RING(dev_priv->renderctx->gtt_offset |
I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
}
+
/* Set up chip specific display functions */
static void intel_init_display(struct drm_device *dev)
{
if (IS_GEN6(dev))
gen6_enable_rps(dev_priv);
- if (IS_IRONLAKE_M(dev)) {
- dev_priv->renderctx = intel_alloc_context_page(dev);
- if (!dev_priv->renderctx)
- goto skip_rc6;
- dev_priv->pwrctx = intel_alloc_context_page(dev);
- if (!dev_priv->pwrctx) {
- i915_gem_object_unpin(dev_priv->renderctx);
- drm_gem_object_unreference(&dev_priv->renderctx->base);
- dev_priv->renderctx = NULL;
- goto skip_rc6;
- }
+ if (IS_IRONLAKE_M(dev))
ironlake_enable_rc6(dev);
- }
-skip_rc6:
INIT_WORK(&dev_priv->idle_work, intel_idle_update);
setup_timer(&dev_priv->idle_timer, intel_gpu_idle_timer,
(unsigned long)dev);
return 0;
}
+static bool
+intel_dp_detect_audio(struct drm_connector *connector)
+{
+ struct intel_dp *intel_dp = intel_attached_dp(connector);
+ struct edid *edid;
+ bool has_audio = false;
+
+ edid = drm_get_edid(connector, &intel_dp->adapter);
+ if (edid) {
+ has_audio = drm_detect_monitor_audio(edid);
+
+ connector->display_info.raw_edid = NULL;
+ kfree(edid);
+ }
+
+ return has_audio;
+}
+
static int
intel_dp_set_property(struct drm_connector *connector,
struct drm_property *property,
return ret;
if (property == intel_dp->force_audio_property) {
- if (val == intel_dp->force_audio)
+ int i = val;
+ bool has_audio;
+
+ if (i == intel_dp->force_audio)
return 0;
- intel_dp->force_audio = val;
+ intel_dp->force_audio = i;
- if (val > 0 && intel_dp->has_audio)
- return 0;
- if (val < 0 && !intel_dp->has_audio)
+ if (i == 0)
+ has_audio = intel_dp_detect_audio(connector);
+ else
+ has_audio = i > 0;
+
+ if (has_audio == intel_dp->has_audio)
return 0;
- intel_dp->has_audio = val > 0;
+ intel_dp->has_audio = has_audio;
goto done;
}
extern void intel_crtc_fb_gamma_get(struct drm_crtc *crtc, u16 *red, u16 *green,
u16 *blue, int regno);
extern void intel_enable_clock_gating(struct drm_device *dev);
-extern void intel_disable_clock_gating(struct drm_device *dev);
extern void ironlake_enable_drps(struct drm_device *dev);
extern void ironlake_disable_drps(struct drm_device *dev);
extern void gen6_enable_rps(struct drm_i915_private *dev_priv);
&dev_priv->gmbus[intel_hdmi->ddc_bus].adapter);
}
+static bool
+intel_hdmi_detect_audio(struct drm_connector *connector)
+{
+ struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+ struct drm_i915_private *dev_priv = connector->dev->dev_private;
+ struct edid *edid;
+ bool has_audio = false;
+
+ edid = drm_get_edid(connector,
+ &dev_priv->gmbus[intel_hdmi->ddc_bus].adapter);
+ if (edid) {
+ if (edid->input & DRM_EDID_INPUT_DIGITAL)
+ has_audio = drm_detect_monitor_audio(edid);
+
+ connector->display_info.raw_edid = NULL;
+ kfree(edid);
+ }
+
+ return has_audio;
+}
+
static int
intel_hdmi_set_property(struct drm_connector *connector,
struct drm_property *property,
return ret;
if (property == intel_hdmi->force_audio_property) {
- if (val == intel_hdmi->force_audio)
+ int i = val;
+ bool has_audio;
+
+ if (i == intel_hdmi->force_audio)
return 0;
- intel_hdmi->force_audio = val;
+ intel_hdmi->force_audio = i;
- if (val > 0 && intel_hdmi->has_audio)
- return 0;
- if (val < 0 && !intel_hdmi->has_audio)
+ if (i == 0)
+ has_audio = intel_hdmi_detect_audio(connector);
+ else
+ has_audio = i > 0;
+
+ if (has_audio == intel_hdmi->has_audio)
return 0;
- intel_hdmi->has_audio = val > 0;
+ intel_hdmi->has_audio = has_audio;
goto done;
}
return true;
}
- /* Make sure pre-965s set dither correctly */
- if (INTEL_INFO(dev)->gen < 4) {
- if (dev_priv->lvds_dither)
- pfit_control |= PANEL_8TO6_DITHER_ENABLE;
- }
-
/* Native modes don't need fitting */
if (adjusted_mode->hdisplay == mode->hdisplay &&
adjusted_mode->vdisplay == mode->vdisplay)
}
out:
+ /* If not enabling scaling, be consistent and always use 0. */
if ((pfit_control & PFIT_ENABLE) == 0) {
pfit_control = 0;
pfit_pgm_ratios = 0;
}
+
+ /* Make sure pre-965 set dither correctly */
+ if (INTEL_INFO(dev)->gen < 4 && dev_priv->lvds_dither)
+ pfit_control |= PANEL_8TO6_DITHER_ENABLE;
+
if (pfit_control != intel_lvds->pfit_control ||
pfit_pgm_ratios != intel_lvds->pfit_pgm_ratios) {
intel_lvds->pfit_control = pfit_control;
val &= ~1;
pci_read_config_byte(dev->pdev, PCI_LBPC, &lbpc);
val *= lbpc;
- val >>= 1;
}
}
if (is_backlight_combination_mode(dev)){
u32 max = intel_panel_get_max_backlight(dev);
- u8 lpbc;
+ u8 lbpc;
- lpbc = level * 0xfe / max + 1;
- level /= lpbc;
- pci_write_config_byte(dev->pdev, PCI_LBPC, lpbc);
+ lbpc = level * 0xfe / max + 1;
+ level /= lbpc;
+ pci_write_config_byte(dev->pdev, PCI_LBPC, lbpc);
}
tmp = I915_READ(BLC_PWM_CTL);
}
static int gen6_ring_flush(struct intel_ring_buffer *ring,
- u32 invalidate_domains,
- u32 flush_domains)
+ u32 invalidate, u32 flush)
{
+ uint32_t cmd;
int ret;
- if ((flush_domains & I915_GEM_DOMAIN_RENDER) == 0)
+ if (((invalidate | flush) & I915_GEM_GPU_DOMAINS) == 0)
return 0;
ret = intel_ring_begin(ring, 4);
if (ret)
return ret;
- intel_ring_emit(ring, MI_FLUSH_DW);
- intel_ring_emit(ring, 0);
+ cmd = MI_FLUSH_DW;
+ if (invalidate & I915_GEM_GPU_DOMAINS)
+ cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD;
+ intel_ring_emit(ring, cmd);
intel_ring_emit(ring, 0);
intel_ring_emit(ring, 0);
+ intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
return 0;
}
}
static int blt_ring_flush(struct intel_ring_buffer *ring,
- u32 invalidate_domains,
- u32 flush_domains)
+ u32 invalidate, u32 flush)
{
+ uint32_t cmd;
int ret;
- if ((flush_domains & I915_GEM_DOMAIN_RENDER) == 0)
+ if (((invalidate | flush) & I915_GEM_DOMAIN_RENDER) == 0)
return 0;
ret = blt_ring_begin(ring, 4);
if (ret)
return ret;
- intel_ring_emit(ring, MI_FLUSH_DW);
- intel_ring_emit(ring, 0);
+ cmd = MI_FLUSH_DW;
+ if (invalidate & I915_GEM_DOMAIN_RENDER)
+ cmd |= MI_INVALIDATE_TLB;
+ intel_ring_emit(ring, cmd);
intel_ring_emit(ring, 0);
intel_ring_emit(ring, 0);
+ intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
return 0;
}
struct drm_i915_gem_object *obj;
};
-#define I915_RING_READ(reg) i915_safe_read(dev_priv, reg)
+#define I915_RING_READ(reg) i915_gt_read(dev_priv, reg)
+#define I915_RING_WRITE(reg, val) i915_gt_write(dev_priv, reg, val)
#define I915_READ_TAIL(ring) I915_RING_READ(RING_TAIL((ring)->mmio_base))
-#define I915_WRITE_TAIL(ring, val) I915_WRITE(RING_TAIL((ring)->mmio_base), val)
+#define I915_WRITE_TAIL(ring, val) I915_RING_WRITE(RING_TAIL((ring)->mmio_base), val)
#define I915_READ_START(ring) I915_RING_READ(RING_START((ring)->mmio_base))
-#define I915_WRITE_START(ring, val) I915_WRITE(RING_START((ring)->mmio_base), val)
+#define I915_WRITE_START(ring, val) I915_RING_WRITE(RING_START((ring)->mmio_base), val)
#define I915_READ_HEAD(ring) I915_RING_READ(RING_HEAD((ring)->mmio_base))
-#define I915_WRITE_HEAD(ring, val) I915_WRITE(RING_HEAD((ring)->mmio_base), val)
+#define I915_WRITE_HEAD(ring, val) I915_RING_WRITE(RING_HEAD((ring)->mmio_base), val)
#define I915_READ_CTL(ring) I915_RING_READ(RING_CTL((ring)->mmio_base))
-#define I915_WRITE_CTL(ring, val) I915_WRITE(RING_CTL((ring)->mmio_base), val)
+#define I915_WRITE_CTL(ring, val) I915_RING_WRITE(RING_CTL((ring)->mmio_base), val)
-#define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
#define I915_READ_IMR(ring) I915_RING_READ(RING_IMR((ring)->mmio_base))
+#define I915_WRITE_IMR(ring, val) I915_RING_WRITE(RING_IMR((ring)->mmio_base), val)
#define I915_READ_NOPID(ring) I915_RING_READ(RING_NOPID((ring)->mmio_base))
#define I915_READ_SYNC_0(ring) I915_RING_READ(RING_SYNC_0((ring)->mmio_base))
SDVO_TV_MASK)
#define IS_TV(c) (c->output_flag & SDVO_TV_MASK)
+#define IS_TMDS(c) (c->output_flag & SDVO_TMDS_MASK)
#define IS_LVDS(c) (c->output_flag & SDVO_LVDS_MASK)
#define IS_TV_OR_LVDS(c) (c->output_flag & (SDVO_TV_MASK | SDVO_LVDS_MASK))
intel_sdvo->has_hdmi_monitor = drm_detect_hdmi_monitor(edid);
intel_sdvo->has_hdmi_audio = drm_detect_monitor_audio(edid);
}
- }
+ } else
+ status = connector_status_disconnected;
connector->display_info.raw_edid = NULL;
kfree(edid);
}
if ((intel_sdvo_connector->output_flag & response) == 0)
ret = connector_status_disconnected;
- else if (response & SDVO_TMDS_MASK)
+ else if (IS_TMDS(intel_sdvo_connector))
ret = intel_sdvo_hdmi_sink_detect(connector);
- else
- ret = connector_status_connected;
+ else {
+ struct edid *edid;
+
+ /* if we have an edid check it matches the connection */
+ edid = intel_sdvo_get_edid(connector);
+ if (edid == NULL)
+ edid = intel_sdvo_get_analog_edid(connector);
+ if (edid != NULL) {
+ if (edid->input & DRM_EDID_INPUT_DIGITAL)
+ ret = connector_status_disconnected;
+ else
+ ret = connector_status_connected;
+ connector->display_info.raw_edid = NULL;
+ kfree(edid);
+ } else
+ ret = connector_status_connected;
+ }
/* May update encoder flag for like clock for SDVO TV, etc.*/
if (ret == connector_status_connected) {
edid = intel_sdvo_get_analog_edid(connector);
if (edid != NULL) {
- if (edid->input & DRM_EDID_INPUT_DIGITAL) {
+ struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector);
+ bool monitor_is_digital = !!(edid->input & DRM_EDID_INPUT_DIGITAL);
+ bool connector_is_digital = !!IS_TMDS(intel_sdvo_connector);
+
+ if (connector_is_digital == monitor_is_digital) {
drm_mode_connector_update_edid_property(connector, edid);
drm_add_edid_modes(connector, edid);
}
+
connector->display_info.raw_edid = NULL;
kfree(edid);
}
kfree(connector);
}
+static bool intel_sdvo_detect_hdmi_audio(struct drm_connector *connector)
+{
+ struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+ struct edid *edid;
+ bool has_audio = false;
+
+ if (!intel_sdvo->is_hdmi)
+ return false;
+
+ edid = intel_sdvo_get_edid(connector);
+ if (edid != NULL && edid->input & DRM_EDID_INPUT_DIGITAL)
+ has_audio = drm_detect_monitor_audio(edid);
+
+ return has_audio;
+}
+
static int
intel_sdvo_set_property(struct drm_connector *connector,
struct drm_property *property,
return ret;
if (property == intel_sdvo_connector->force_audio_property) {
- if (val == intel_sdvo_connector->force_audio)
+ int i = val;
+ bool has_audio;
+
+ if (i == intel_sdvo_connector->force_audio)
return 0;
- intel_sdvo_connector->force_audio = val;
+ intel_sdvo_connector->force_audio = i;
- if (val > 0 && intel_sdvo->has_hdmi_audio)
- return 0;
- if (val < 0 && !intel_sdvo->has_hdmi_audio)
+ if (i == 0)
+ has_audio = intel_sdvo_detect_hdmi_audio(connector);
+ else
+ has_audio = i > 0;
+
+ if (has_audio == intel_sdvo->has_hdmi_audio)
return 0;
- intel_sdvo->has_hdmi_audio = val > 0;
+ intel_sdvo->has_hdmi_audio = has_audio;
goto done;
}
* \return false if TV is disconnected.
*/
static int
-intel_tv_detect_type (struct intel_tv *intel_tv)
+intel_tv_detect_type (struct intel_tv *intel_tv,
+ struct drm_connector *connector)
{
struct drm_encoder *encoder = &intel_tv->base.base;
struct drm_device *dev = encoder->dev;
int type;
/* Disable TV interrupts around load detect or we'll recurse */
- spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
- i915_disable_pipestat(dev_priv, 0,
- PIPE_HOTPLUG_INTERRUPT_ENABLE |
- PIPE_HOTPLUG_TV_INTERRUPT_ENABLE);
- spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+ if (connector->polled & DRM_CONNECTOR_POLL_HPD) {
+ spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+ i915_disable_pipestat(dev_priv, 0,
+ PIPE_HOTPLUG_INTERRUPT_ENABLE |
+ PIPE_HOTPLUG_TV_INTERRUPT_ENABLE);
+ spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+ }
save_tv_dac = tv_dac = I915_READ(TV_DAC);
save_tv_ctl = tv_ctl = I915_READ(TV_CTL);
I915_WRITE(TV_CTL, save_tv_ctl);
/* Restore interrupt config */
- spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
- i915_enable_pipestat(dev_priv, 0,
- PIPE_HOTPLUG_INTERRUPT_ENABLE |
- PIPE_HOTPLUG_TV_INTERRUPT_ENABLE);
- spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+ if (connector->polled & DRM_CONNECTOR_POLL_HPD) {
+ spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+ i915_enable_pipestat(dev_priv, 0,
+ PIPE_HOTPLUG_INTERRUPT_ENABLE |
+ PIPE_HOTPLUG_TV_INTERRUPT_ENABLE);
+ spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+ }
return type;
}
drm_mode_set_crtcinfo(&mode, CRTC_INTERLACE_HALVE_V);
if (intel_tv->base.base.crtc && intel_tv->base.base.crtc->enabled) {
- type = intel_tv_detect_type(intel_tv);
+ type = intel_tv_detect_type(intel_tv, connector);
} else if (force) {
struct drm_crtc *crtc;
int dpms_mode;
crtc = intel_get_load_detect_pipe(&intel_tv->base, connector,
&mode, &dpms_mode);
if (crtc) {
- type = intel_tv_detect_type(intel_tv);
+ type = intel_tv_detect_type(intel_tv, connector);
intel_release_load_detect_pipe(&intel_tv->base, connector,
dpms_mode);
} else
intel_encoder = &intel_tv->base;
connector = &intel_connector->base;
+ /* The documentation, for the older chipsets at least, recommend
+ * using a polling method rather than hotplug detection for TVs.
+ * This is because in order to perform the hotplug detection, the PLLs
+ * for the TV must be kept alive increasing power drain and starving
+ * bandwidth from other encoders. Notably for instance, it causes
+ * pipe underruns on Crestline when this encoder is supposedly idle.
+ *
+ * More recent chipsets favour HDMI rather than integrated S-Video.
+ */
+ connector->polled =
+ DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
+
drm_connector_init(dev, connector, &intel_tv_connector_funcs,
DRM_MODE_CONNECTOR_SVIDEO);
entry->tvconf.has_component_output = false;
break;
case OUTPUT_LVDS:
- if ((conn & 0x00003f00) != 0x10)
+ if ((conn & 0x00003f00) >> 8 != 0x10)
entry->lvdsconf.use_straps_for_mode = true;
entry->lvdsconf.use_power_scripts = true;
break;
DRM_ERROR("bo %p still attached to GEM object\n", bo);
nv10_mem_put_tile_region(dev, nvbo->tile, NULL);
- nouveau_vm_put(&nvbo->vma);
+ if (nvbo->vma.node) {
+ nouveau_vm_unmap(&nvbo->vma);
+ nouveau_vm_put(&nvbo->vma);
+ }
kfree(nvbo);
}
}
}
+ nvbo->bo.mem.num_pages = size >> PAGE_SHIFT;
nouveau_bo_placement_set(nvbo, flags, 0);
nvbo->channel = chan;
set_placement_range(struct nouveau_bo *nvbo, uint32_t type)
{
struct drm_nouveau_private *dev_priv = nouveau_bdev(nvbo->bo.bdev);
+ int vram_pages = dev_priv->vram_size >> PAGE_SHIFT;
if (dev_priv->card_type == NV_10 &&
- nvbo->tile_mode && (type & TTM_PL_FLAG_VRAM)) {
+ nvbo->tile_mode && (type & TTM_PL_FLAG_VRAM) &&
+ nvbo->bo.mem.num_pages < vram_pages / 2) {
/*
* Make sure that the color and depth buffers are handled
* by independent memory controller units. Up to a 9x
* speed up when alpha-blending and depth-test are enabled
* at the same time.
*/
- int vram_pages = dev_priv->vram_size >> PAGE_SHIFT;
-
if (nvbo->tile_flags & NOUVEAU_GEM_TILE_ZETA) {
nvbo->placement.fpfn = vram_pages / 2;
nvbo->placement.lpfn = ~0;
if (ret)
goto out;
- ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
+ ret = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, new_mem);
out:
ttm_bo_mem_put(bo, &tmp_mem);
return ret;
if (ret)
return ret;
- ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, &tmp_mem);
+ ret = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem);
if (ret)
goto out;
- ret = nouveau_bo_move_m2mf(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem);
+ ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_reserve, no_wait_gpu, new_mem);
if (ret)
goto out;
int high_w = 0, high_h = 0, high_v = 0;
list_for_each_entry(mode, &nv_connector->base.probed_modes, head) {
+ mode->vrefresh = drm_mode_vrefresh(mode);
if (helper->mode_valid(connector, mode) != MODE_OK ||
(mode->flags & DRM_MODE_FLAG_INTERLACE))
continue;
return ret;
/* NV_MEMORY_TO_MEMORY_FORMAT requires a notifier object */
- ret = nouveau_notifier_alloc(chan, NvNotify0, 32, &chan->m2mf_ntfy);
+ ret = nouveau_notifier_alloc(chan, NvNotify0, 32, 0xfd0, 0x1000,
+ &chan->m2mf_ntfy);
if (ret)
return ret;
extern int nouveau_notifier_init_channel(struct nouveau_channel *);
extern void nouveau_notifier_takedown_channel(struct nouveau_channel *);
extern int nouveau_notifier_alloc(struct nouveau_channel *, uint32_t handle,
- int cout, uint32_t *offset);
+ int cout, uint32_t start, uint32_t end,
+ uint32_t *offset);
extern int nouveau_notifier_offset(struct nouveau_gpuobj *, uint32_t *);
extern int nouveau_ioctl_notifier_alloc(struct drm_device *, void *data,
struct drm_file *);
ret = vram->get(dev, mem->num_pages << PAGE_SHIFT,
mem->page_alignment << PAGE_SHIFT, size_nc,
(nvbo->tile_flags >> 8) & 0xff, &node);
- if (ret)
- return ret;
+ if (ret) {
+ mem->mm_node = NULL;
+ return (ret == -ENOSPC) ? 0 : ret;
+ }
node->page_shift = 12;
if (nvbo->vma.node)
return 0;
}
- return -ENOMEM;
+ return -ENOSPC;
}
int
int
nouveau_notifier_alloc(struct nouveau_channel *chan, uint32_t handle,
- int size, uint32_t *b_offset)
+ int size, uint32_t start, uint32_t end,
+ uint32_t *b_offset)
{
struct drm_device *dev = chan->dev;
struct nouveau_gpuobj *nobj = NULL;
uint32_t offset;
int target, ret;
- mem = drm_mm_search_free(&chan->notifier_heap, size, 0, 0);
+ mem = drm_mm_search_free_in_range(&chan->notifier_heap, size, 0,
+ start, end, 0);
if (mem)
- mem = drm_mm_get_block(mem, size, 0);
+ mem = drm_mm_get_block_range(mem, size, 0, start, end);
if (!mem) {
NV_ERROR(dev, "Channel %d notifier block full\n", chan->id);
return -ENOMEM;
if (IS_ERR(chan))
return PTR_ERR(chan);
- ret = nouveau_notifier_alloc(chan, na->handle, na->size, &na->offset);
+ ret = nouveau_notifier_alloc(chan, na->handle, na->size, 0, 0x1000,
+ &na->offset);
nouveau_channel_put(&chan);
return ret;
}
struct nouveau_pm_engine *pm = &dev_priv->engine.pm;
struct nouveau_pm_level *perflvl;
- if (pm->cur == &pm->boot)
+ if (!pm->cur || pm->cur == &pm->boot)
return;
perflvl = pm->cur;
if (nv_encoder->dcb->type == OUTPUT_LVDS) {
bool duallink, dummy;
- nouveau_bios_parse_lvds_table(dev, nv_connector->native_mode->
- clock, &duallink, &dummy);
+ nouveau_bios_parse_lvds_table(dev, output_mode->clock,
+ &duallink, &dummy);
if (duallink)
regp->fp_control |= (8 << 28);
} else
return;
if (nv_encoder->dcb->lvdsconf.use_power_scripts) {
- struct nouveau_connector *nv_connector = nouveau_encoder_connector_get(nv_encoder);
-
/* when removing an output, crtc may not be set, but PANEL_OFF
* must still be run
*/
nv04_dfp_get_bound_head(dev, nv_encoder->dcb);
if (mode == DRM_MODE_DPMS_ON) {
- if (!nv_connector->native_mode) {
- NV_ERROR(dev, "Not turning on LVDS without native mode\n");
- return;
- }
call_lvds_script(dev, nv_encoder->dcb, head,
- LVDS_PANEL_ON, nv_connector->native_mode->clock);
+ LVDS_PANEL_ON, nv_encoder->mode.clock);
} else
/* pxclk of 0 is fine for PANEL_OFF, and for a
* disconnected LVDS encoder there is no native_mode
struct nouveau_tile_reg *tile = &dev_priv->tile.reg[i];
switch (dev_priv->chipset) {
+ case 0x40:
+ case 0x41: /* guess */
+ case 0x42:
+ case 0x43:
+ case 0x45: /* guess */
+ case 0x4e:
+ nv_wr32(dev, NV20_PGRAPH_TSIZE(i), tile->pitch);
+ nv_wr32(dev, NV20_PGRAPH_TLIMIT(i), tile->limit);
+ nv_wr32(dev, NV20_PGRAPH_TILE(i), tile->addr);
+ nv_wr32(dev, NV40_PGRAPH_TSIZE1(i), tile->pitch);
+ nv_wr32(dev, NV40_PGRAPH_TLIMIT1(i), tile->limit);
+ nv_wr32(dev, NV40_PGRAPH_TILE1(i), tile->addr);
+ break;
case 0x44:
case 0x4a:
- case 0x4e:
nv_wr32(dev, NV20_PGRAPH_TSIZE(i), tile->pitch);
nv_wr32(dev, NV20_PGRAPH_TLIMIT(i), tile->limit);
nv_wr32(dev, NV20_PGRAPH_TILE(i), tile->addr);
break;
-
case 0x46:
case 0x47:
case 0x49:
case 0x4b:
+ case 0x4c:
+ case 0x67:
+ default:
nv_wr32(dev, NV47_PGRAPH_TSIZE(i), tile->pitch);
nv_wr32(dev, NV47_PGRAPH_TLIMIT(i), tile->limit);
nv_wr32(dev, NV47_PGRAPH_TILE(i), tile->addr);
nv_wr32(dev, NV40_PGRAPH_TLIMIT1(i), tile->limit);
nv_wr32(dev, NV40_PGRAPH_TILE1(i), tile->addr);
break;
-
- default:
- nv_wr32(dev, NV20_PGRAPH_TSIZE(i), tile->pitch);
- nv_wr32(dev, NV20_PGRAPH_TLIMIT(i), tile->limit);
- nv_wr32(dev, NV20_PGRAPH_TILE(i), tile->addr);
- nv_wr32(dev, NV40_PGRAPH_TSIZE1(i), tile->pitch);
- nv_wr32(dev, NV40_PGRAPH_TLIMIT1(i), tile->limit);
- nv_wr32(dev, NV40_PGRAPH_TILE1(i), tile->addr);
- break;
}
}
break;
default:
switch (dev_priv->chipset) {
- case 0x46:
- case 0x47:
- case 0x49:
- case 0x4b:
- nv_wr32(dev, 0x400DF0, nv_rd32(dev, NV04_PFB_CFG0));
- nv_wr32(dev, 0x400DF4, nv_rd32(dev, NV04_PFB_CFG1));
- break;
- default:
+ case 0x41:
+ case 0x42:
+ case 0x43:
+ case 0x45:
+ case 0x4e:
+ case 0x44:
+ case 0x4a:
nv_wr32(dev, 0x4009F0, nv_rd32(dev, NV04_PFB_CFG0));
nv_wr32(dev, 0x4009F4, nv_rd32(dev, NV04_PFB_CFG1));
break;
+ default:
+ nv_wr32(dev, 0x400DF0, nv_rd32(dev, NV04_PFB_CFG0));
+ nv_wr32(dev, 0x400DF4, nv_rd32(dev, NV04_PFB_CFG1));
+ break;
}
nv_wr32(dev, 0x4069F0, nv_rd32(dev, NV04_PFB_CFG0));
nv_wr32(dev, 0x4069F4, nv_rd32(dev, NV04_PFB_CFG1));
void
nv50_instmem_flush(struct drm_device *dev)
{
+ struct drm_nouveau_private *dev_priv = dev->dev_private;
+
+ spin_lock(&dev_priv->ramin_lock);
nv_wr32(dev, 0x00330c, 0x00000001);
if (!nv_wait(dev, 0x00330c, 0x00000002, 0x00000000))
NV_ERROR(dev, "PRAMIN flush timeout\n");
+ spin_unlock(&dev_priv->ramin_lock);
}
void
nv84_instmem_flush(struct drm_device *dev)
{
+ struct drm_nouveau_private *dev_priv = dev->dev_private;
+
+ spin_lock(&dev_priv->ramin_lock);
nv_wr32(dev, 0x070000, 0x00000001);
if (!nv_wait(dev, 0x070000, 0x00000002, 0x00000000))
NV_ERROR(dev, "PRAMIN flush timeout\n");
+ spin_unlock(&dev_priv->ramin_lock);
}
void
nv50_vm_flush_engine(struct drm_device *dev, int engine)
{
+ struct drm_nouveau_private *dev_priv = dev->dev_private;
+
+ spin_lock(&dev_priv->ramin_lock);
nv_wr32(dev, 0x100c80, (engine << 16) | 1);
if (!nv_wait(dev, 0x100c80, 0x00000001, 0x00000000))
NV_ERROR(dev, "vm flush timeout: engine %d\n", engine);
+ spin_unlock(&dev_priv->ramin_lock);
}
switch (radeon_crtc->rmx_type) {
case RMX_CENTER:
- args.usOverscanTop = (adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2;
- args.usOverscanBottom = (adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2;
- args.usOverscanLeft = (adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2;
- args.usOverscanRight = (adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2;
+ args.usOverscanTop = cpu_to_le16((adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2);
+ args.usOverscanBottom = cpu_to_le16((adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2);
+ args.usOverscanLeft = cpu_to_le16((adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2);
+ args.usOverscanRight = cpu_to_le16((adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2);
break;
case RMX_ASPECT:
a1 = mode->crtc_vdisplay * adjusted_mode->crtc_hdisplay;
a2 = adjusted_mode->crtc_vdisplay * mode->crtc_hdisplay;
if (a1 > a2) {
- args.usOverscanLeft = (adjusted_mode->crtc_hdisplay - (a2 / mode->crtc_vdisplay)) / 2;
- args.usOverscanRight = (adjusted_mode->crtc_hdisplay - (a2 / mode->crtc_vdisplay)) / 2;
+ args.usOverscanLeft = cpu_to_le16((adjusted_mode->crtc_hdisplay - (a2 / mode->crtc_vdisplay)) / 2);
+ args.usOverscanRight = cpu_to_le16((adjusted_mode->crtc_hdisplay - (a2 / mode->crtc_vdisplay)) / 2);
} else if (a2 > a1) {
- args.usOverscanLeft = (adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2;
- args.usOverscanRight = (adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2;
+ args.usOverscanLeft = cpu_to_le16((adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2);
+ args.usOverscanRight = cpu_to_le16((adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2);
}
break;
case RMX_FULL:
default:
- args.usOverscanRight = radeon_crtc->h_border;
- args.usOverscanLeft = radeon_crtc->h_border;
- args.usOverscanBottom = radeon_crtc->v_border;
- args.usOverscanTop = radeon_crtc->v_border;
+ args.usOverscanRight = cpu_to_le16(radeon_crtc->h_border);
+ args.usOverscanLeft = cpu_to_le16(radeon_crtc->h_border);
+ args.usOverscanBottom = cpu_to_le16(radeon_crtc->v_border);
+ args.usOverscanTop = cpu_to_le16(radeon_crtc->v_border);
break;
}
atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
memset(&args, 0, sizeof(args));
if (ASIC_IS_DCE5(rdev)) {
- args.v3.usSpreadSpectrumAmountFrac = 0;
+ args.v3.usSpreadSpectrumAmountFrac = cpu_to_le16(0);
args.v3.ucSpreadSpectrumType = ss->type;
switch (pll_id) {
case ATOM_PPLL1:
args.v3.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V3_P1PLL;
- args.v3.usSpreadSpectrumAmount = ss->amount;
- args.v3.usSpreadSpectrumStep = ss->step;
+ args.v3.usSpreadSpectrumAmount = cpu_to_le16(ss->amount);
+ args.v3.usSpreadSpectrumStep = cpu_to_le16(ss->step);
break;
case ATOM_PPLL2:
args.v3.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V3_P2PLL;
- args.v3.usSpreadSpectrumAmount = ss->amount;
- args.v3.usSpreadSpectrumStep = ss->step;
+ args.v3.usSpreadSpectrumAmount = cpu_to_le16(ss->amount);
+ args.v3.usSpreadSpectrumStep = cpu_to_le16(ss->step);
break;
case ATOM_DCPLL:
args.v3.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V3_DCPLL;
- args.v3.usSpreadSpectrumAmount = 0;
- args.v3.usSpreadSpectrumStep = 0;
+ args.v3.usSpreadSpectrumAmount = cpu_to_le16(0);
+ args.v3.usSpreadSpectrumStep = cpu_to_le16(0);
break;
case ATOM_PPLL_INVALID:
return;
switch (pll_id) {
case ATOM_PPLL1:
args.v2.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V2_P1PLL;
- args.v2.usSpreadSpectrumAmount = ss->amount;
- args.v2.usSpreadSpectrumStep = ss->step;
+ args.v2.usSpreadSpectrumAmount = cpu_to_le16(ss->amount);
+ args.v2.usSpreadSpectrumStep = cpu_to_le16(ss->step);
break;
case ATOM_PPLL2:
args.v2.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V2_P2PLL;
- args.v2.usSpreadSpectrumAmount = ss->amount;
- args.v2.usSpreadSpectrumStep = ss->step;
+ args.v2.usSpreadSpectrumAmount = cpu_to_le16(ss->amount);
+ args.v2.usSpreadSpectrumStep = cpu_to_le16(ss->step);
break;
case ATOM_DCPLL:
args.v2.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V2_DCPLL;
- args.v2.usSpreadSpectrumAmount = 0;
- args.v2.usSpreadSpectrumStep = 0;
+ args.v2.usSpreadSpectrumAmount = cpu_to_le16(0);
+ args.v2.usSpreadSpectrumStep = cpu_to_le16(0);
break;
case ATOM_PPLL_INVALID:
return;
pll->flags |= RADEON_PLL_PREFER_HIGH_FB_DIV;
else
pll->flags |= RADEON_PLL_PREFER_LOW_REF_DIV;
-
}
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
dp_clock = dig_connector->dp_clock;
}
}
-/* this might work properly with the new pll algo */
-#if 0 /* doesn't work properly on some laptops */
+
/* use recommended ref_div for ss */
if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
if (ss_enabled) {
if (ss->refdiv) {
+ pll->flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
pll->flags |= RADEON_PLL_USE_REF_DIV;
pll->reference_div = ss->refdiv;
+ if (ASIC_IS_AVIVO(rdev))
+ pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV;
}
}
}
-#endif
+
if (ASIC_IS_AVIVO(rdev)) {
/* DVO wants 2x pixel clock if the DVO chip is in 12 bit mode */
if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1)
adjusted_clock = mode->clock * 2;
if (radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT))
pll->flags |= RADEON_PLL_PREFER_CLOSEST_LOWER;
- /* rv515 needs more testing with this option */
- if (rdev->family != CHIP_RV515) {
- if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
- pll->flags |= RADEON_PLL_IS_LCD;
- }
+ if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
+ pll->flags |= RADEON_PLL_IS_LCD;
} else {
if (encoder->encoder_type != DRM_MODE_ENCODER_DAC)
pll->flags |= RADEON_PLL_NO_ODD_POST_DIV;
index, (uint32_t *)&args);
adjusted_clock = le32_to_cpu(args.v3.sOutput.ulDispPllFreq) * 10;
if (args.v3.sOutput.ucRefDiv) {
+ pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV;
pll->flags |= RADEON_PLL_USE_REF_DIV;
pll->reference_div = args.v3.sOutput.ucRefDiv;
}
if (args.v3.sOutput.ucPostDiv) {
+ pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV;
pll->flags |= RADEON_PLL_USE_POST_DIV;
pll->post_div = args.v3.sOutput.ucPostDiv;
}
* SetPixelClock provides the dividers
*/
args.v5.ucCRTC = ATOM_CRTC_INVALID;
- args.v5.usPixelClock = dispclk;
+ args.v5.usPixelClock = cpu_to_le16(dispclk);
args.v5.ucPpll = ATOM_DCPLL;
break;
case 6:
/* if the default dcpll clock is specified,
* SetPixelClock provides the dividers
*/
- args.v6.ulDispEngClkFreq = dispclk;
+ args.v6.ulDispEngClkFreq = cpu_to_le32(dispclk);
args.v6.ucPpll = ATOM_DCPLL;
break;
default:
/* adjust pixel clock as needed */
adjusted_clock = atombios_adjust_pll(crtc, mode, pll, ss_enabled, &ss);
- /* rv515 seems happier with the old algo */
- if (rdev->family == CHIP_RV515)
- radeon_compute_pll_legacy(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div,
- &ref_div, &post_div);
- else if (ASIC_IS_AVIVO(rdev))
+ if (ASIC_IS_AVIVO(rdev))
radeon_compute_pll_avivo(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div,
&ref_div, &post_div);
else
}
}
-static int evergreen_crtc_do_set_base(struct drm_crtc *crtc,
- struct drm_framebuffer *fb,
- int x, int y, int atomic)
+static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
+ struct drm_framebuffer *fb,
+ int x, int y, int atomic)
{
struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
struct drm_device *dev = crtc->dev;
WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
(crtc->mode.hdisplay << 16) | crtc->mode.vdisplay);
- if (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE)
- WREG32(EVERGREEN_DATA_FORMAT + radeon_crtc->crtc_offset,
- EVERGREEN_INTERLEAVE_EN);
- else
- WREG32(EVERGREEN_DATA_FORMAT + radeon_crtc->crtc_offset, 0);
-
if (!atomic && fb && fb != crtc->fb) {
radeon_fb = to_radeon_framebuffer(fb);
rbo = radeon_fb->obj->driver_private;
WREG32(AVIVO_D1MODE_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
(crtc->mode.hdisplay << 16) | crtc->mode.vdisplay);
- if (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE)
- WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset,
- AVIVO_D1MODE_INTERLEAVE_EN);
- else
- WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset, 0);
-
if (!atomic && fb && fb != crtc->fb) {
radeon_fb = to_radeon_framebuffer(fb);
rbo = radeon_fb->obj->driver_private;
struct radeon_device *rdev = dev->dev_private;
if (ASIC_IS_DCE4(rdev))
- return evergreen_crtc_do_set_base(crtc, old_fb, x, y, 0);
+ return dce4_crtc_do_set_base(crtc, old_fb, x, y, 0);
else if (ASIC_IS_AVIVO(rdev))
return avivo_crtc_do_set_base(crtc, old_fb, x, y, 0);
else
struct radeon_device *rdev = dev->dev_private;
if (ASIC_IS_DCE4(rdev))
- return evergreen_crtc_do_set_base(crtc, fb, x, y, 1);
+ return dce4_crtc_do_set_base(crtc, fb, x, y, 1);
else if (ASIC_IS_AVIVO(rdev))
return avivo_crtc_do_set_base(crtc, fb, x, y, 1);
else
radeon_ring_write(rdev, 1);
/* FIXME: implement */
radeon_ring_write(rdev, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
- radeon_ring_write(rdev, ib->gpu_addr & 0xFFFFFFFC);
+ radeon_ring_write(rdev,
+#ifdef __BIG_ENDIAN
+ (2 << 0) |
+#endif
+ (ib->gpu_addr & 0xFFFFFFFC));
radeon_ring_write(rdev, upper_32_bits(ib->gpu_addr) & 0xFF);
radeon_ring_write(rdev, ib->length_dw);
}
return -EINVAL;
r700_cp_stop(rdev);
- WREG32(CP_RB_CNTL, RB_NO_UPDATE | (15 << 8) | (3 << 0));
+ WREG32(CP_RB_CNTL,
+#ifdef __BIG_ENDIAN
+ BUF_SWAP_32BIT |
+#endif
+ RB_NO_UPDATE | RB_BLKSZ(15) | RB_BUFSZ(3));
fw_data = (const __be32 *)rdev->pfp_fw->data;
WREG32(CP_PFP_UCODE_ADDR, 0);
WREG32(CP_RB_WPTR, 0);
/* set the wb address wether it's enabled or not */
- WREG32(CP_RB_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC);
+ WREG32(CP_RB_RPTR_ADDR,
+#ifdef __BIG_ENDIAN
+ RB_RPTR_SWAP(2) |
+#endif
+ ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC));
WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF);
WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF);
rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
}
rdev->mc.visible_vram_size = rdev->mc.aper_size;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
r700_vram_gtt_location(rdev, &rdev->mc);
radeon_update_bandwidth_info(rdev);
while (rptr != wptr) {
/* wptr/rptr are in bytes! */
ring_index = rptr / 4;
- src_id = rdev->ih.ring[ring_index] & 0xff;
- src_data = rdev->ih.ring[ring_index + 1] & 0xfffffff;
+ src_id = le32_to_cpu(rdev->ih.ring[ring_index]) & 0xff;
+ src_data = le32_to_cpu(rdev->ih.ring[ring_index + 1]) & 0xfffffff;
switch (src_id) {
case 1: /* D1 vblank/vline */
/* XXX: ontario has problems blitting to gart at the moment */
if (rdev->family == CHIP_PALM) {
rdev->asic->copy = NULL;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
}
/* allocate wb buffer */
if (h < 8)
h = 8;
- cb_color_info = ((format << 2) | (1 << 24));
+ cb_color_info = ((format << 2) | (1 << 24) | (1 << 8));
pitch = (w / 8) - 1;
slice = ((w * h) / 64) - 1;
/* high addr, stride */
sq_vtx_constant_word2 = ((upper_32_bits(gpu_addr) & 0xff) | (16 << 8));
+#ifdef __BIG_ENDIAN
+ sq_vtx_constant_word2 |= (2 << 30);
+#endif
/* xyzw swizzles */
sq_vtx_constant_word3 = (0 << 3) | (1 << 6) | (2 << 9) | (3 << 12);
sq_tex_resource_word0 = (1 << 0); /* 2D */
sq_tex_resource_word0 |= ((((pitch >> 3) - 1) << 6) |
((w - 1) << 18));
- sq_tex_resource_word1 = ((h - 1) << 0);
+ sq_tex_resource_word1 = ((h - 1) << 0) | (1 << 28);
/* xyzw swizzles */
sq_tex_resource_word4 = (0 << 16) | (1 << 19) | (2 << 22) | (3 << 25);
radeon_ring_write(rdev, DI_PT_RECTLIST);
radeon_ring_write(rdev, PACKET3(PACKET3_INDEX_TYPE, 0));
- radeon_ring_write(rdev, DI_INDEX_SIZE_16_BIT);
+ radeon_ring_write(rdev,
+#ifdef __BIG_ENDIAN
+ (2 << 2) |
+#endif
+ DI_INDEX_SIZE_16_BIT);
radeon_ring_write(rdev, PACKET3(PACKET3_NUM_INSTANCES, 0));
radeon_ring_write(rdev, 1);
int evergreen_blit_init(struct radeon_device *rdev)
{
u32 obj_size;
- int r, dwords;
+ int i, r, dwords;
void *ptr;
u32 packet2s[16];
int num_packet2s = 0;
dwords = rdev->r600_blit.state_len;
while (dwords & 0xf) {
- packet2s[num_packet2s++] = PACKET2(0);
+ packet2s[num_packet2s++] = cpu_to_le32(PACKET2(0));
dwords++;
}
if (num_packet2s)
memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
packet2s, num_packet2s * 4);
- memcpy(ptr + rdev->r600_blit.vs_offset, evergreen_vs, evergreen_vs_size * 4);
- memcpy(ptr + rdev->r600_blit.ps_offset, evergreen_ps, evergreen_ps_size * 4);
+ for (i = 0; i < evergreen_vs_size; i++)
+ *(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(evergreen_vs[i]);
+ for (i = 0; i < evergreen_ps_size; i++)
+ *(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(evergreen_ps[i]);
radeon_bo_kunmap(rdev->r600_blit.shader_obj);
radeon_bo_unreserve(rdev->r600_blit.shader_obj);
dev_err(rdev->dev, "(%d) pin blit object failed\n", r);
return r;
}
- rdev->mc.active_vram_size = rdev->mc.real_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
return 0;
}
{
int r;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
if (rdev->r600_blit.shader_obj == NULL)
return;
/* If we can't reserve the bo, unref should be enough to destroy
0x00000000,
0x3c000000,
0x67961001,
+#ifdef __BIG_ENDIAN
+ 0x000a0000,
+#else
0x00080000,
+#endif
0x00000000,
0x1c000000,
0x67961000,
+#ifdef __BIG_ENDIAN
+ 0x00020008,
+#else
0x00000008,
+#endif
0x00000000,
};
#define BUF_SWAP_32BIT (2 << 16)
#define CP_RB_RPTR 0x8700
#define CP_RB_RPTR_ADDR 0xC10C
+#define RB_RPTR_SWAP(x) ((x) << 0)
#define CP_RB_RPTR_ADDR_HI 0xC110
#define CP_RB_RPTR_WR 0xC108
#define CP_RB_WPTR 0xC114
last_reg = strtol(last_reg_s, NULL, 16);
do {
- if (fgets(buf, 1024, file) == NULL)
+ if (fgets(buf, 1024, file) == NULL) {
+ fclose(file);
return -1;
+ }
len = strlen(buf);
if (ftell(file) == end)
done = 1;
fprintf(stderr,
"Error matching regular expression %d in %s\n",
r, filename);
+ fclose(file);
return -1;
} else {
buf[match[0].rm_eo] = 0;
void r100_pre_page_flip(struct radeon_device *rdev, int crtc)
{
- struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc];
- u32 tmp;
-
- /* make sure flip is at vb rather than hb */
- tmp = RREG32(RADEON_CRTC_OFFSET_CNTL + radeon_crtc->crtc_offset);
- tmp &= ~RADEON_CRTC_OFFSET_FLIP_CNTL;
- /* make sure pending bit is asserted */
- tmp |= RADEON_CRTC_GUI_TRIG_OFFSET_LEFT_EN;
- WREG32(RADEON_CRTC_OFFSET_CNTL + radeon_crtc->crtc_offset, tmp);
-
- /* set pageflip to happen as late as possible in the vblank interval.
- * same field for crtc1/2
- */
- tmp = RREG32(RADEON_CRTC_GEN_CNTL);
- tmp &= ~RADEON_CRTC_VSTAT_MODE_MASK;
- WREG32(RADEON_CRTC_GEN_CNTL, tmp);
-
/* enable the pflip int */
radeon_irq_kms_pflip_irq_get(rdev, crtc);
}
return r;
}
rdev->cp.ready = true;
- rdev->mc.active_vram_size = rdev->mc.real_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
return 0;
}
void r100_cp_disable(struct radeon_device *rdev)
{
/* Disable ring */
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
rdev->cp.ready = false;
WREG32(RADEON_CP_CSQ_MODE, 0);
WREG32(RADEON_CP_CSQ_CNTL, 0);
}
track->zb.robj = reloc->robj;
track->zb.offset = idx_value;
+ track->zb_dirty = true;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
break;
case RADEON_RB3D_COLOROFFSET:
}
track->cb[0].robj = reloc->robj;
track->cb[0].offset = idx_value;
+ track->cb_dirty = true;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
break;
case RADEON_PP_TXOFFSET_0:
}
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
track->textures[i].robj = reloc->robj;
+ track->tex_dirty = true;
break;
case RADEON_PP_CUBIC_OFFSET_T0_0:
case RADEON_PP_CUBIC_OFFSET_T0_1:
track->textures[0].cube_info[i].offset = idx_value;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
track->textures[0].cube_info[i].robj = reloc->robj;
+ track->tex_dirty = true;
break;
case RADEON_PP_CUBIC_OFFSET_T1_0:
case RADEON_PP_CUBIC_OFFSET_T1_1:
track->textures[1].cube_info[i].offset = idx_value;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
track->textures[1].cube_info[i].robj = reloc->robj;
+ track->tex_dirty = true;
break;
case RADEON_PP_CUBIC_OFFSET_T2_0:
case RADEON_PP_CUBIC_OFFSET_T2_1:
track->textures[2].cube_info[i].offset = idx_value;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
track->textures[2].cube_info[i].robj = reloc->robj;
+ track->tex_dirty = true;
break;
case RADEON_RE_WIDTH_HEIGHT:
track->maxy = ((idx_value >> 16) & 0x7FF);
+ track->cb_dirty = true;
+ track->zb_dirty = true;
break;
case RADEON_RB3D_COLORPITCH:
r = r100_cs_packet_next_reloc(p, &reloc);
ib[idx] = tmp;
track->cb[0].pitch = idx_value & RADEON_COLORPITCH_MASK;
+ track->cb_dirty = true;
break;
case RADEON_RB3D_DEPTHPITCH:
track->zb.pitch = idx_value & RADEON_DEPTHPITCH_MASK;
+ track->zb_dirty = true;
break;
case RADEON_RB3D_CNTL:
switch ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f) {
return -EINVAL;
}
track->z_enabled = !!(idx_value & RADEON_Z_ENABLE);
+ track->cb_dirty = true;
+ track->zb_dirty = true;
break;
case RADEON_RB3D_ZSTENCILCNTL:
switch (idx_value & 0xf) {
default:
break;
}
+ track->zb_dirty = true;
break;
case RADEON_RB3D_ZPASS_ADDR:
r = r100_cs_packet_next_reloc(p, &reloc);
uint32_t temp = idx_value >> 4;
for (i = 0; i < track->num_texture; i++)
track->textures[i].enabled = !!(temp & (1 << i));
+ track->tex_dirty = true;
}
break;
case RADEON_SE_VF_CNTL:
i = (reg - RADEON_PP_TEX_SIZE_0) / 8;
track->textures[i].width = (idx_value & RADEON_TEX_USIZE_MASK) + 1;
track->textures[i].height = ((idx_value & RADEON_TEX_VSIZE_MASK) >> RADEON_TEX_VSIZE_SHIFT) + 1;
+ track->tex_dirty = true;
break;
case RADEON_PP_TEX_PITCH_0:
case RADEON_PP_TEX_PITCH_1:
case RADEON_PP_TEX_PITCH_2:
i = (reg - RADEON_PP_TEX_PITCH_0) / 8;
track->textures[i].pitch = idx_value + 32;
+ track->tex_dirty = true;
break;
case RADEON_PP_TXFILTER_0:
case RADEON_PP_TXFILTER_1:
tmp = (idx_value >> 27) & 0x7;
if (tmp == 2 || tmp == 6)
track->textures[i].roundup_h = false;
+ track->tex_dirty = true;
break;
case RADEON_PP_TXFORMAT_0:
case RADEON_PP_TXFORMAT_1:
}
track->textures[i].cube_info[4].width = 1 << ((idx_value >> 16) & 0xf);
track->textures[i].cube_info[4].height = 1 << ((idx_value >> 20) & 0xf);
+ track->tex_dirty = true;
break;
case RADEON_PP_CUBIC_FACES_0:
case RADEON_PP_CUBIC_FACES_1:
track->textures[i].cube_info[face].width = 1 << ((tmp >> (face * 8)) & 0xf);
track->textures[i].cube_info[face].height = 1 << ((tmp >> ((face * 8) + 4)) & 0xf);
}
+ track->tex_dirty = true;
break;
default:
printk(KERN_ERR "Forbidden register 0x%04X in cs at %d\n",
/* FIXME we don't use the second aperture yet when we could use it */
if (rdev->mc.visible_vram_size > rdev->mc.aper_size)
rdev->mc.visible_vram_size = rdev->mc.aper_size;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
config_aper_size = RREG32(RADEON_CONFIG_APER_SIZE);
if (rdev->flags & RADEON_IS_IGP) {
uint32_t tom;
unsigned long size;
unsigned prim_walk;
unsigned nverts;
- unsigned num_cb = track->num_cb;
+ unsigned num_cb = track->cb_dirty ? track->num_cb : 0;
- if (!track->zb_cb_clear && !track->color_channel_mask &&
+ if (num_cb && !track->zb_cb_clear && !track->color_channel_mask &&
!track->blend_read_enable)
num_cb = 0;
return -EINVAL;
}
}
- if (track->z_enabled) {
+ track->cb_dirty = false;
+
+ if (track->zb_dirty && track->z_enabled) {
if (track->zb.robj == NULL) {
DRM_ERROR("[drm] No buffer for z buffer !\n");
return -EINVAL;
return -EINVAL;
}
}
+ track->zb_dirty = false;
+
+ if (track->aa_dirty && track->aaresolve) {
+ if (track->aa.robj == NULL) {
+ DRM_ERROR("[drm] No buffer for AA resolve buffer %d !\n", i);
+ return -EINVAL;
+ }
+ /* I believe the format comes from colorbuffer0. */
+ size = track->aa.pitch * track->cb[0].cpp * track->maxy;
+ size += track->aa.offset;
+ if (size > radeon_bo_size(track->aa.robj)) {
+ DRM_ERROR("[drm] Buffer too small for AA resolve buffer %d "
+ "(need %lu have %lu) !\n", i, size,
+ radeon_bo_size(track->aa.robj));
+ DRM_ERROR("[drm] AA resolve buffer %d (%u %u %u %u)\n",
+ i, track->aa.pitch, track->cb[0].cpp,
+ track->aa.offset, track->maxy);
+ return -EINVAL;
+ }
+ }
+ track->aa_dirty = false;
+
prim_walk = (track->vap_vf_cntl >> 4) & 0x3;
if (track->vap_vf_cntl & (1 << 14)) {
nverts = track->vap_alt_nverts;
prim_walk);
return -EINVAL;
}
- return r100_cs_track_texture_check(rdev, track);
+
+ if (track->tex_dirty) {
+ track->tex_dirty = false;
+ return r100_cs_track_texture_check(rdev, track);
+ }
+ return 0;
}
void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track)
{
unsigned i, face;
+ track->cb_dirty = true;
+ track->zb_dirty = true;
+ track->tex_dirty = true;
+ track->aa_dirty = true;
+
if (rdev->family < CHIP_R300) {
track->num_cb = 1;
if (rdev->family <= CHIP_RS200)
track->num_texture = 16;
track->maxy = 4096;
track->separate_cube = 0;
+ track->aaresolve = false;
+ track->aa.robj = NULL;
}
for (i = 0; i < track->num_cb; i++) {
r100_mc_program(rdev);
/* Resume clock */
r100_clock_startup(rdev);
- /* Initialize GPU configuration (# pipes, ...) */
-// r100_gpu_init(rdev);
/* Initialize GART (initialize after TTM so we can allocate
* memory through TTM but finalize after TTM) */
r100_enable_bm(rdev);
unsigned compress_format;
};
-struct r100_cs_track_limits {
- unsigned num_cb;
- unsigned num_texture;
- unsigned max_levels;
-};
-
struct r100_cs_track {
- struct radeon_device *rdev;
unsigned num_cb;
unsigned num_texture;
unsigned maxy;
struct r100_cs_track_array arrays[11];
struct r100_cs_track_cb cb[R300_MAX_CB];
struct r100_cs_track_cb zb;
+ struct r100_cs_track_cb aa;
struct r100_cs_track_texture textures[R300_TRACK_MAX_TEXTURE];
bool z_enabled;
bool separate_cube;
bool zb_cb_clear;
bool blend_read_enable;
+ bool cb_dirty;
+ bool zb_dirty;
+ bool tex_dirty;
+ bool aa_dirty;
+ bool aaresolve;
};
int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track);
}
track->zb.robj = reloc->robj;
track->zb.offset = idx_value;
+ track->zb_dirty = true;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
break;
case RADEON_RB3D_COLOROFFSET:
}
track->cb[0].robj = reloc->robj;
track->cb[0].offset = idx_value;
+ track->cb_dirty = true;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
break;
case R200_PP_TXOFFSET_0:
}
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
track->textures[i].robj = reloc->robj;
+ track->tex_dirty = true;
break;
case R200_PP_CUBIC_OFFSET_F1_0:
case R200_PP_CUBIC_OFFSET_F2_0:
track->textures[i].cube_info[face - 1].offset = idx_value;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
track->textures[i].cube_info[face - 1].robj = reloc->robj;
+ track->tex_dirty = true;
break;
case RADEON_RE_WIDTH_HEIGHT:
track->maxy = ((idx_value >> 16) & 0x7FF);
+ track->cb_dirty = true;
+ track->zb_dirty = true;
break;
case RADEON_RB3D_COLORPITCH:
r = r100_cs_packet_next_reloc(p, &reloc);
ib[idx] = tmp;
track->cb[0].pitch = idx_value & RADEON_COLORPITCH_MASK;
+ track->cb_dirty = true;
break;
case RADEON_RB3D_DEPTHPITCH:
track->zb.pitch = idx_value & RADEON_DEPTHPITCH_MASK;
+ track->zb_dirty = true;
break;
case RADEON_RB3D_CNTL:
switch ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f) {
}
track->z_enabled = !!(idx_value & RADEON_Z_ENABLE);
+ track->cb_dirty = true;
+ track->zb_dirty = true;
break;
case RADEON_RB3D_ZSTENCILCNTL:
switch (idx_value & 0xf) {
default:
break;
}
+ track->zb_dirty = true;
break;
case RADEON_RB3D_ZPASS_ADDR:
r = r100_cs_packet_next_reloc(p, &reloc);
uint32_t temp = idx_value >> 4;
for (i = 0; i < track->num_texture; i++)
track->textures[i].enabled = !!(temp & (1 << i));
+ track->tex_dirty = true;
}
break;
case RADEON_SE_VF_CNTL:
i = (reg - R200_PP_TXSIZE_0) / 32;
track->textures[i].width = (idx_value & RADEON_TEX_USIZE_MASK) + 1;
track->textures[i].height = ((idx_value & RADEON_TEX_VSIZE_MASK) >> RADEON_TEX_VSIZE_SHIFT) + 1;
+ track->tex_dirty = true;
break;
case R200_PP_TXPITCH_0:
case R200_PP_TXPITCH_1:
case R200_PP_TXPITCH_5:
i = (reg - R200_PP_TXPITCH_0) / 32;
track->textures[i].pitch = idx_value + 32;
+ track->tex_dirty = true;
break;
case R200_PP_TXFILTER_0:
case R200_PP_TXFILTER_1:
tmp = (idx_value >> 27) & 0x7;
if (tmp == 2 || tmp == 6)
track->textures[i].roundup_h = false;
+ track->tex_dirty = true;
break;
case R200_PP_TXMULTI_CTL_0:
case R200_PP_TXMULTI_CTL_1:
track->textures[i].tex_coord_type = 1;
break;
}
+ track->tex_dirty = true;
break;
case R200_PP_TXFORMAT_0:
case R200_PP_TXFORMAT_1:
}
track->textures[i].cube_info[4].width = 1 << ((idx_value >> 16) & 0xf);
track->textures[i].cube_info[4].height = 1 << ((idx_value >> 20) & 0xf);
+ track->tex_dirty = true;
break;
case R200_PP_CUBIC_FACES_0:
case R200_PP_CUBIC_FACES_1:
track->textures[i].cube_info[face].width = 1 << ((tmp >> (face * 8)) & 0xf);
track->textures[i].cube_info[face].height = 1 << ((tmp >> ((face * 8) + 4)) & 0xf);
}
+ track->tex_dirty = true;
break;
default:
printk(KERN_ERR "Forbidden register 0x%04X in cs at %d\n",
}
track->cb[i].robj = reloc->robj;
track->cb[i].offset = idx_value;
+ track->cb_dirty = true;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
break;
case R300_ZB_DEPTHOFFSET:
}
track->zb.robj = reloc->robj;
track->zb.offset = idx_value;
+ track->zb_dirty = true;
ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
break;
case R300_TX_OFFSET_0:
tmp |= tile_flags;
ib[idx] = tmp;
track->textures[i].robj = reloc->robj;
+ track->tex_dirty = true;
break;
/* Tracked registers */
case 0x2084:
if (p->rdev->family < CHIP_RV515) {
track->maxy -= 1440;
}
+ track->cb_dirty = true;
+ track->zb_dirty = true;
break;
case 0x4E00:
/* RB3D_CCTL */
return -EINVAL;
}
track->num_cb = ((idx_value >> 5) & 0x3) + 1;
+ track->cb_dirty = true;
break;
case 0x4E38:
case 0x4E3C:
((idx_value >> 21) & 0xF));
return -EINVAL;
}
+ track->cb_dirty = true;
break;
case 0x4F00:
/* ZB_CNTL */
} else {
track->z_enabled = false;
}
+ track->zb_dirty = true;
break;
case 0x4F10:
/* ZB_FORMAT */
(idx_value & 0xF));
return -EINVAL;
}
+ track->zb_dirty = true;
break;
case 0x4F24:
/* ZB_DEPTHPITCH */
ib[idx] = tmp;
track->zb.pitch = idx_value & 0x3FFC;
+ track->zb_dirty = true;
break;
case 0x4104:
+ /* TX_ENABLE */
for (i = 0; i < 16; i++) {
bool enabled;
enabled = !!(idx_value & (1 << i));
track->textures[i].enabled = enabled;
}
+ track->tex_dirty = true;
break;
case 0x44C0:
case 0x44C4:
track->textures[i].compress_format = R100_TRACK_COMP_NONE;
break;
case R300_TX_FORMAT_X16:
+ case R300_TX_FORMAT_FL_I16:
case R300_TX_FORMAT_Y8X8:
case R300_TX_FORMAT_Z5Y6X5:
case R300_TX_FORMAT_Z6Y5X5:
track->textures[i].compress_format = R100_TRACK_COMP_NONE;
break;
case R300_TX_FORMAT_Y16X16:
+ case R300_TX_FORMAT_FL_I16A16:
case R300_TX_FORMAT_Z11Y11X10:
case R300_TX_FORMAT_Z10Y11X11:
case R300_TX_FORMAT_W8Z8Y8X8:
DRM_ERROR("Invalid texture format %u\n",
(idx_value & 0x1F));
return -EINVAL;
- break;
}
+ track->tex_dirty = true;
break;
case 0x4400:
case 0x4404:
if (tmp == 2 || tmp == 4 || tmp == 6) {
track->textures[i].roundup_h = false;
}
+ track->tex_dirty = true;
break;
case 0x4500:
case 0x4504:
DRM_ERROR("Forbidden bit TXFORMAT_MSB\n");
return -EINVAL;
}
+ track->tex_dirty = true;
break;
case 0x4480:
case 0x4484:
track->textures[i].use_pitch = !!tmp;
tmp = (idx_value >> 22) & 0xF;
track->textures[i].txdepth = tmp;
+ track->tex_dirty = true;
break;
case R300_ZB_ZPASS_ADDR:
r = r100_cs_packet_next_reloc(p, &reloc);
case 0x4e0c:
/* RB3D_COLOR_CHANNEL_MASK */
track->color_channel_mask = idx_value;
+ track->cb_dirty = true;
break;
case 0x43a4:
/* SC_HYPERZ_EN */
case 0x4f1c:
/* ZB_BW_CNTL */
track->zb_cb_clear = !!(idx_value & (1 << 5));
+ track->cb_dirty = true;
+ track->zb_dirty = true;
if (p->rdev->hyperz_filp != p->filp) {
if (idx_value & (R300_HIZ_ENABLE |
R300_RD_COMP_ENABLE |
case 0x4e04:
/* RB3D_BLENDCNTL */
track->blend_read_enable = !!(idx_value & (1 << 2));
+ track->cb_dirty = true;
+ break;
+ case R300_RB3D_AARESOLVE_OFFSET:
+ r = r100_cs_packet_next_reloc(p, &reloc);
+ if (r) {
+ DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+ idx, reg);
+ r100_cs_dump_packet(p, pkt);
+ return r;
+ }
+ track->aa.robj = reloc->robj;
+ track->aa.offset = idx_value;
+ track->aa_dirty = true;
+ ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+ break;
+ case R300_RB3D_AARESOLVE_PITCH:
+ track->aa.pitch = idx_value & 0x3FFE;
+ track->aa_dirty = true;
break;
- case 0x4f28: /* ZB_DEPTHCLEARVALUE */
+ case R300_RB3D_AARESOLVE_CTL:
+ track->aaresolve = idx_value & 0x1;
+ track->aa_dirty = true;
break;
case 0x4f30: /* ZB_MASK_OFFSET */
case 0x4f34: /* ZB_ZMASK_PITCH */
#define R300_RB3D_COLORPITCH2 0x4E40 /* GUESS */
#define R300_RB3D_COLORPITCH3 0x4E44 /* GUESS */
+#define R300_RB3D_AARESOLVE_OFFSET 0x4E80
+#define R300_RB3D_AARESOLVE_PITCH 0x4E84
#define R300_RB3D_AARESOLVE_CTL 0x4E88
/* gap */
rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE);
rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE);
rdev->mc.visible_vram_size = rdev->mc.aper_size;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
r600_vram_gtt_location(rdev, &rdev->mc);
if (rdev->flags & RADEON_IS_IGP) {
*/
void r600_cp_stop(struct radeon_device *rdev)
{
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(1));
WREG32(SCRATCH_UMSK, 0);
}
r600_cp_stop(rdev);
- WREG32(CP_RB_CNTL, RB_NO_UPDATE | RB_BLKSZ(15) | RB_BUFSZ(3));
+ WREG32(CP_RB_CNTL,
+#ifdef __BIG_ENDIAN
+ BUF_SWAP_32BIT |
+#endif
+ RB_NO_UPDATE | RB_BLKSZ(15) | RB_BUFSZ(3));
/* Reset cp */
WREG32(GRBM_SOFT_RESET, SOFT_RESET_CP);
WREG32(CP_RB_WPTR, 0);
/* set the wb address whether it's enabled or not */
- WREG32(CP_RB_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC);
+ WREG32(CP_RB_RPTR_ADDR,
+#ifdef __BIG_ENDIAN
+ RB_RPTR_SWAP(2) |
+#endif
+ ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC));
WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF);
WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF);
{
/* FIXME: implement */
radeon_ring_write(rdev, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
- radeon_ring_write(rdev, ib->gpu_addr & 0xFFFFFFFC);
+ radeon_ring_write(rdev,
+#ifdef __BIG_ENDIAN
+ (2 << 0) |
+#endif
+ (ib->gpu_addr & 0xFFFFFFFC));
radeon_ring_write(rdev, upper_32_bits(ib->gpu_addr) & 0xFF);
radeon_ring_write(rdev, ib->length_dw);
}
while (rptr != wptr) {
/* wptr/rptr are in bytes! */
ring_index = rptr / 4;
- src_id = rdev->ih.ring[ring_index] & 0xff;
- src_data = rdev->ih.ring[ring_index + 1] & 0xfffffff;
+ src_id = le32_to_cpu(rdev->ih.ring[ring_index]) & 0xff;
+ src_data = le32_to_cpu(rdev->ih.ring[ring_index + 1]) & 0xfffffff;
switch (src_id) {
case 1: /* D1 vblank/vline */
ps = (u32 *) ((char *)dev->agp_buffer_map->handle + dev_priv->blit_vb->offset + 256);
for (i = 0; i < r6xx_vs_size; i++)
- vs[i] = r6xx_vs[i];
+ vs[i] = cpu_to_le32(r6xx_vs[i]);
for (i = 0; i < r6xx_ps_size; i++)
- ps[i] = r6xx_ps[i];
+ ps[i] = cpu_to_le32(r6xx_ps[i]);
dev_priv->blit_vb->used = 512;
DRM_DEBUG("\n");
sq_vtx_constant_word2 = (((gpu_addr >> 32) & 0xff) | (16 << 8));
+#ifdef __BIG_ENDIAN
+ sq_vtx_constant_word2 |= (2 << 30);
+#endif
BEGIN_RING(9);
OUT_RING(CP_PACKET3(R600_IT_SET_RESOURCE, 7));
OUT_RING(DI_PT_RECTLIST);
OUT_RING(CP_PACKET3(R600_IT_INDEX_TYPE, 0));
+#ifdef __BIG_ENDIAN
+ OUT_RING((2 << 2) | DI_INDEX_SIZE_16_BIT);
+#else
OUT_RING(DI_INDEX_SIZE_16_BIT);
+#endif
OUT_RING(CP_PACKET3(R600_IT_NUM_INSTANCES, 0));
OUT_RING(1);
if (h < 8)
h = 8;
- cb_color_info = ((format << 2) | (1 << 27));
+ cb_color_info = ((format << 2) | (1 << 27) | (1 << 8));
pitch = (w / 8) - 1;
slice = ((w * h) / 64) - 1;
u32 sq_vtx_constant_word2;
sq_vtx_constant_word2 = ((upper_32_bits(gpu_addr) & 0xff) | (16 << 8));
+#ifdef __BIG_ENDIAN
+ sq_vtx_constant_word2 |= (2 << 30);
+#endif
radeon_ring_write(rdev, PACKET3(PACKET3_SET_RESOURCE, 7));
radeon_ring_write(rdev, 0x460);
if (h < 1)
h = 1;
- sq_tex_resource_word0 = (1 << 0);
+ sq_tex_resource_word0 = (1 << 0) | (1 << 3);
sq_tex_resource_word0 |= ((((pitch >> 3) - 1) << 8) |
((w - 1) << 19));
radeon_ring_write(rdev, DI_PT_RECTLIST);
radeon_ring_write(rdev, PACKET3(PACKET3_INDEX_TYPE, 0));
- radeon_ring_write(rdev, DI_INDEX_SIZE_16_BIT);
+ radeon_ring_write(rdev,
+#ifdef __BIG_ENDIAN
+ (2 << 2) |
+#endif
+ DI_INDEX_SIZE_16_BIT);
radeon_ring_write(rdev, PACKET3(PACKET3_NUM_INSTANCES, 0));
radeon_ring_write(rdev, 1);
dwords = ALIGN(rdev->r600_blit.state_len, 0x10);
gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.state_offset;
radeon_ring_write(rdev, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
- radeon_ring_write(rdev, gpu_addr & 0xFFFFFFFC);
+ radeon_ring_write(rdev,
+#ifdef __BIG_ENDIAN
+ (2 << 0) |
+#endif
+ (gpu_addr & 0xFFFFFFFC));
radeon_ring_write(rdev, upper_32_bits(gpu_addr) & 0xFF);
radeon_ring_write(rdev, dwords);
int r600_blit_init(struct radeon_device *rdev)
{
u32 obj_size;
- int r, dwords;
+ int i, r, dwords;
void *ptr;
u32 packet2s[16];
int num_packet2s = 0;
dwords = rdev->r600_blit.state_len;
while (dwords & 0xf) {
- packet2s[num_packet2s++] = PACKET2(0);
+ packet2s[num_packet2s++] = cpu_to_le32(PACKET2(0));
dwords++;
}
if (num_packet2s)
memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
packet2s, num_packet2s * 4);
- memcpy(ptr + rdev->r600_blit.vs_offset, r6xx_vs, r6xx_vs_size * 4);
- memcpy(ptr + rdev->r600_blit.ps_offset, r6xx_ps, r6xx_ps_size * 4);
+ for (i = 0; i < r6xx_vs_size; i++)
+ *(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(r6xx_vs[i]);
+ for (i = 0; i < r6xx_ps_size; i++)
+ *(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(r6xx_ps[i]);
radeon_bo_kunmap(rdev->r600_blit.shader_obj);
radeon_bo_unreserve(rdev->r600_blit.shader_obj);
dev_err(rdev->dev, "(%d) pin blit object failed\n", r);
return r;
}
- rdev->mc.active_vram_size = rdev->mc.real_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
return 0;
}
{
int r;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
if (rdev->r600_blit.shader_obj == NULL)
return;
/* If we can't reserve the bo, unref should be enough to destroy
0x00000000,
0x3c000000,
0x68cd1000,
+#ifdef __BIG_ENDIAN
+ 0x000a0000,
+#else
0x00080000,
+#endif
0x00000000,
};
r600_do_cp_stop(dev_priv);
RADEON_WRITE(R600_CP_RB_CNTL,
+#ifdef __BIG_ENDIAN
+ R600_BUF_SWAP_32BIT |
+#endif
R600_RB_NO_UPDATE |
R600_RB_BLKSZ(15) |
R600_RB_BUFSZ(3));
r600_do_cp_stop(dev_priv);
RADEON_WRITE(R600_CP_RB_CNTL,
+#ifdef __BIG_ENDIAN
+ R600_BUF_SWAP_32BIT |
+#endif
R600_RB_NO_UPDATE |
- (15 << 8) |
- (3 << 0));
+ R600_RB_BLKSZ(15) |
+ R600_RB_BUFSZ(3));
RADEON_WRITE(R600_GRBM_SOFT_RESET, R600_SOFT_RESET_CP);
RADEON_READ(R600_GRBM_SOFT_RESET);
if (!dev_priv->writeback_works) {
/* Disable writeback to avoid unnecessary bus master transfer */
- RADEON_WRITE(R600_CP_RB_CNTL, RADEON_READ(R600_CP_RB_CNTL) |
- RADEON_RB_NO_UPDATE);
+ RADEON_WRITE(R600_CP_RB_CNTL,
+#ifdef __BIG_ENDIAN
+ R600_BUF_SWAP_32BIT |
+#endif
+ RADEON_READ(R600_CP_RB_CNTL) |
+ R600_RB_NO_UPDATE);
RADEON_WRITE(R600_SCRATCH_UMSK, 0);
}
}
RADEON_WRITE(R600_CP_RB_WPTR_DELAY, 0);
cp_rb_cntl = RADEON_READ(R600_CP_RB_CNTL);
- RADEON_WRITE(R600_CP_RB_CNTL, R600_RB_RPTR_WR_ENA);
+ RADEON_WRITE(R600_CP_RB_CNTL,
+#ifdef __BIG_ENDIAN
+ R600_BUF_SWAP_32BIT |
+#endif
+ R600_RB_RPTR_WR_ENA);
RADEON_WRITE(R600_CP_RB_RPTR_WR, cp_ptr);
RADEON_WRITE(R600_CP_RB_WPTR, cp_ptr);
+ dev_priv->gart_vm_start;
}
RADEON_WRITE(R600_CP_RB_RPTR_ADDR,
- rptr_addr & 0xffffffff);
+#ifdef __BIG_ENDIAN
+ (2 << 0) |
+#endif
+ (rptr_addr & 0xfffffffc));
RADEON_WRITE(R600_CP_RB_RPTR_ADDR_HI,
upper_32_bits(rptr_addr));
{
u64 scratch_addr;
- scratch_addr = RADEON_READ(R600_CP_RB_RPTR_ADDR);
+ scratch_addr = RADEON_READ(R600_CP_RB_RPTR_ADDR) & 0xFFFFFFFC;
scratch_addr |= ((u64)RADEON_READ(R600_CP_RB_RPTR_ADDR_HI)) << 32;
scratch_addr += R600_SCRATCH_REG_OFFSET;
scratch_addr >>= 8;
}
if (!IS_ALIGNED(pitch, pitch_align)) {
- dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n",
- __func__, __LINE__, pitch);
+ dev_warn(p->dev, "%s:%d cb pitch (%d, 0x%x, %d) invalid\n",
+ __func__, __LINE__, pitch, pitch_align, array_mode);
return -EINVAL;
}
if (!IS_ALIGNED(height, height_align)) {
- dev_warn(p->dev, "%s:%d cb height (%d) invalid\n",
- __func__, __LINE__, height);
+ dev_warn(p->dev, "%s:%d cb height (%d, 0x%x, %d) invalid\n",
+ __func__, __LINE__, height, height_align, array_mode);
return -EINVAL;
}
if (!IS_ALIGNED(base_offset, base_align)) {
- dev_warn(p->dev, "%s offset[%d] 0x%llx not aligned\n", __func__, i, base_offset);
+ dev_warn(p->dev, "%s offset[%d] 0x%llx 0x%llx, %d not aligned\n", __func__, i,
+ base_offset, base_align, array_mode);
return -EINVAL;
}
* broken userspace.
*/
} else {
- dev_warn(p->dev, "%s offset[%d] %d %d %lu too big\n", __func__, i, track->cb_color_bo_offset[i], tmp, radeon_bo_size(track->cb_color_bo[i]));
+ dev_warn(p->dev, "%s offset[%d] %d %d %d %lu too big\n", __func__, i,
+ array_mode,
+ track->cb_color_bo_offset[i], tmp,
+ radeon_bo_size(track->cb_color_bo[i]));
return -EINVAL;
}
}
}
if (!IS_ALIGNED(pitch, pitch_align)) {
- dev_warn(p->dev, "%s:%d db pitch (%d) invalid\n",
- __func__, __LINE__, pitch);
+ dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n",
+ __func__, __LINE__, pitch, pitch_align, array_mode);
return -EINVAL;
}
if (!IS_ALIGNED(height, height_align)) {
- dev_warn(p->dev, "%s:%d db height (%d) invalid\n",
- __func__, __LINE__, height);
+ dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n",
+ __func__, __LINE__, height, height_align, array_mode);
return -EINVAL;
}
if (!IS_ALIGNED(base_offset, base_align)) {
- dev_warn(p->dev, "%s offset[%d] 0x%llx not aligned\n", __func__, i, base_offset);
+ dev_warn(p->dev, "%s offset[%d] 0x%llx, 0x%llx, %d not aligned\n", __func__, i,
+ base_offset, base_align, array_mode);
return -EINVAL;
}
nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
tmp = ntiles * bpe * 64 * nviews;
if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
- dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %d -> %u have %lu)\n",
- track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
- radeon_bo_size(track->db_bo));
+ dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
+ array_mode,
+ track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
+ radeon_bo_size(track->db_bo));
return -EINVAL;
}
}
/* XXX check height as well... */
if (!IS_ALIGNED(pitch, pitch_align)) {
- dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n",
- __func__, __LINE__, pitch);
+ dev_warn(p->dev, "%s:%d tex pitch (%d, 0x%x, %d) invalid\n",
+ __func__, __LINE__, pitch, pitch_align, G_038000_TILE_MODE(word0));
return -EINVAL;
}
if (!IS_ALIGNED(base_offset, base_align)) {
- dev_warn(p->dev, "%s:%d tex base offset (0x%llx) invalid\n",
- __func__, __LINE__, base_offset);
+ dev_warn(p->dev, "%s:%d tex base offset (0x%llx, 0x%llx, %d) invalid\n",
+ __func__, __LINE__, base_offset, base_align, G_038000_TILE_MODE(word0));
return -EINVAL;
}
if (!IS_ALIGNED(mip_offset, base_align)) {
- dev_warn(p->dev, "%s:%d tex mip offset (0x%llx) invalid\n",
- __func__, __LINE__, mip_offset);
+ dev_warn(p->dev, "%s:%d tex mip offset (0x%llx, 0x%llx, %d) invalid\n",
+ __func__, __LINE__, mip_offset, base_align, G_038000_TILE_MODE(word0));
return -EINVAL;
}
#define ROQ_IB2_START(x) ((x) << 8)
#define CP_RB_BASE 0xC100
#define CP_RB_CNTL 0xC104
-#define RB_BUFSZ(x) ((x)<<0)
-#define RB_BLKSZ(x) ((x)<<8)
-#define RB_NO_UPDATE (1<<27)
-#define RB_RPTR_WR_ENA (1<<31)
+#define RB_BUFSZ(x) ((x) << 0)
+#define RB_BLKSZ(x) ((x) << 8)
+#define RB_NO_UPDATE (1 << 27)
+#define RB_RPTR_WR_ENA (1 << 31)
#define BUF_SWAP_32BIT (2 << 16)
#define CP_RB_RPTR 0x8700
#define CP_RB_RPTR_ADDR 0xC10C
+#define RB_RPTR_SWAP(x) ((x) << 0)
#define CP_RB_RPTR_ADDR_HI 0xC110
#define CP_RB_RPTR_WR 0xC108
#define CP_RB_WPTR 0xC114
* about vram size near mc fb location */
u64 mc_vram_size;
u64 visible_vram_size;
- u64 active_vram_size;
u64 gtt_size;
u64 gtt_start;
u64 gtt_end;
extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
extern int radeon_resume_kms(struct drm_device *dev);
extern int radeon_suspend_kms(struct drm_device *dev, pm_message_t state);
+extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size);
/* r600, rv610, rv630, rv620, rv635, rv670, rs780, rs880 */
extern bool r600_card_posted(struct radeon_device *rdev);
.pm_finish = &evergreen_pm_finish,
.pm_init_profile = &rs780_pm_init_profile,
.pm_get_dynpm_state = &r600_pm_get_dynpm_state,
+ .pre_page_flip = &evergreen_pre_page_flip,
+ .page_flip = &evergreen_page_flip,
+ .post_page_flip = &evergreen_post_page_flip,
};
static struct radeon_asic btc_asic = {
/* some evergreen boards have bad data for this entry */
if (ASIC_IS_DCE4(rdev)) {
if ((i == 7) &&
- (gpio->usClkMaskRegisterIndex == 0x1936) &&
+ (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
(gpio->sucI2cId.ucAccess == 0)) {
gpio->sucI2cId.ucAccess = 0x97;
gpio->ucDataMaskShift = 8;
/* some DCE3 boards have bad data for this entry */
if (ASIC_IS_DCE3(rdev)) {
if ((i == 4) &&
- (gpio->usClkMaskRegisterIndex == 0x1fda) &&
+ (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
(gpio->sucI2cId.ucAccess == 0x94))
gpio->sucI2cId.ucAccess = 0x14;
}
/* some evergreen boards have bad data for this entry */
if (ASIC_IS_DCE4(rdev)) {
if ((i == 7) &&
- (gpio->usClkMaskRegisterIndex == 0x1936) &&
+ (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
(gpio->sucI2cId.ucAccess == 0)) {
gpio->sucI2cId.ucAccess = 0x97;
gpio->ucDataMaskShift = 8;
/* some DCE3 boards have bad data for this entry */
if (ASIC_IS_DCE3(rdev)) {
if ((i == 4) &&
- (gpio->usClkMaskRegisterIndex == 0x1fda) &&
+ (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
(gpio->sucI2cId.ucAccess == 0x94))
gpio->sucI2cId.ucAccess = 0x14;
}
pin = &gpio_info->asGPIO_Pin[i];
if (id == pin->ucGPIO_ID) {
gpio.id = pin->ucGPIO_ID;
- gpio.reg = pin->usGpioPin_AIndex * 4;
+ gpio.reg = le16_to_cpu(pin->usGpioPin_AIndex) * 4;
gpio.mask = (1 << pin->ucGpioPinBitShift);
gpio.valid = true;
break;
data_offset);
switch (crev) {
case 1:
- if (igp_info->info.ulBootUpMemoryClock)
+ if (le32_to_cpu(igp_info->info.ulBootUpMemoryClock))
return true;
break;
case 2:
- if (igp_info->info_2.ulBootUpSidePortClock)
+ if (le32_to_cpu(igp_info->info_2.ulBootUpSidePortClock))
return true;
break;
default:
for (i = 0; i < num_indices; i++) {
if ((ss_info->info.asSpreadSpectrum[i].ucClockIndication == id) &&
- (clock <= ss_info->info.asSpreadSpectrum[i].ulTargetClockRange)) {
+ (clock <= le32_to_cpu(ss_info->info.asSpreadSpectrum[i].ulTargetClockRange))) {
ss->percentage =
le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
ss->type = ss_info->info.asSpreadSpectrum[i].ucSpreadSpectrumMode;
sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2);
for (i = 0; i < num_indices; i++) {
if ((ss_info->info_2.asSpreadSpectrum[i].ucClockIndication == id) &&
- (clock <= ss_info->info_2.asSpreadSpectrum[i].ulTargetClockRange)) {
+ (clock <= le32_to_cpu(ss_info->info_2.asSpreadSpectrum[i].ulTargetClockRange))) {
ss->percentage =
le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
ss->type = ss_info->info_2.asSpreadSpectrum[i].ucSpreadSpectrumMode;
sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3);
for (i = 0; i < num_indices; i++) {
if ((ss_info->info_3.asSpreadSpectrum[i].ucClockIndication == id) &&
- (clock <= ss_info->info_3.asSpreadSpectrum[i].ulTargetClockRange)) {
+ (clock <= le32_to_cpu(ss_info->info_3.asSpreadSpectrum[i].ulTargetClockRange))) {
ss->percentage =
le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
ss->type = ss_info->info_3.asSpreadSpectrum[i].ucSpreadSpectrumMode;
if (misc & ATOM_DOUBLE_CLOCK_MODE)
lvds->native_mode.flags |= DRM_MODE_FLAG_DBLSCAN;
- lvds->native_mode.width_mm = lvds_info->info.sLCDTiming.usImageHSize;
- lvds->native_mode.height_mm = lvds_info->info.sLCDTiming.usImageVSize;
+ lvds->native_mode.width_mm = le16_to_cpu(lvds_info->info.sLCDTiming.usImageHSize);
+ lvds->native_mode.height_mm = le16_to_cpu(lvds_info->info.sLCDTiming.usImageVSize);
/* set crtc values */
drm_mode_set_crtcinfo(&lvds->native_mode, CRTC_INTERLACE_HALVE_V);
lvds->linkb = false;
/* parse the lcd record table */
- if (lvds_info->info.usModePatchTableOffset) {
+ if (le16_to_cpu(lvds_info->info.usModePatchTableOffset)) {
ATOM_FAKE_EDID_PATCH_RECORD *fake_edid_record;
ATOM_PANEL_RESOLUTION_PATCH_RECORD *panel_res_record;
bool bad_record = false;
u8 *record = (u8 *)(mode_info->atom_context->bios +
data_offset +
- lvds_info->info.usModePatchTableOffset);
+ le16_to_cpu(lvds_info->info.usModePatchTableOffset));
while (*record != ATOM_RECORD_END_TYPE) {
switch (*record) {
case LCD_MODE_PATCH_RECORD_MODE_TYPE:
firmware_info =
(union firmware_info *)(mode_info->atom_context->bios +
data_offset);
- vddc = firmware_info->info_14.usBootUpVDDCVoltage;
+ vddc = le16_to_cpu(firmware_info->info_14.usBootUpVDDCVoltage);
}
return vddc;
rdev->pm.power_state[state_index].clock_info[mode_index].voltage.type =
VOLTAGE_SW;
rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage =
- clock_info->evergreen.usVDDC;
+ le16_to_cpu(clock_info->evergreen.usVDDC);
} else {
sclk = le16_to_cpu(clock_info->r600.usEngineClockLow);
sclk |= clock_info->r600.ucEngineClockHigh << 16;
rdev->pm.power_state[state_index].clock_info[mode_index].voltage.type =
VOLTAGE_SW;
rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage =
- clock_info->r600.usVDDC;
+ le16_to_cpu(clock_info->r600.usVDDC);
}
if (rdev->flags & RADEON_IS_IGP) {
radeon_atombios_add_pplib_thermal_controller(rdev, &power_info->pplib.sThermalController);
state_array = (struct StateArray *)
(mode_info->atom_context->bios + data_offset +
- power_info->pplib.usStateArrayOffset);
+ le16_to_cpu(power_info->pplib.usStateArrayOffset));
clock_info_array = (struct ClockInfoArray *)
(mode_info->atom_context->bios + data_offset +
- power_info->pplib.usClockInfoArrayOffset);
+ le16_to_cpu(power_info->pplib.usClockInfoArrayOffset));
non_clock_info_array = (struct NonClockInfoArray *)
(mode_info->atom_context->bios + data_offset +
- power_info->pplib.usNonClockInfoArrayOffset);
+ le16_to_cpu(power_info->pplib.usNonClockInfoArrayOffset));
rdev->pm.power_state = kzalloc(sizeof(struct radeon_power_state) *
state_array->ucNumEntries, GFP_KERNEL);
if (!rdev->pm.power_state)
int index = GetIndexIntoMasterTable(COMMAND, GetEngineClock);
atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
- return args.ulReturnEngineClock;
+ return le32_to_cpu(args.ulReturnEngineClock);
}
uint32_t radeon_atom_get_memory_clock(struct radeon_device *rdev)
int index = GetIndexIntoMasterTable(COMMAND, GetMemoryClock);
atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
- return args.ulReturnMemoryClock;
+ return le32_to_cpu(args.ulReturnMemoryClock);
}
void radeon_atom_set_engine_clock(struct radeon_device *rdev,
SET_ENGINE_CLOCK_PS_ALLOCATION args;
int index = GetIndexIntoMasterTable(COMMAND, SetEngineClock);
- args.ulTargetEngineClock = eng_clock; /* 10 khz */
+ args.ulTargetEngineClock = cpu_to_le32(eng_clock); /* 10 khz */
atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
}
if (rdev->flags & RADEON_IS_IGP)
return;
- args.ulTargetMemoryClock = mem_clock; /* 10 khz */
+ args.ulTargetMemoryClock = cpu_to_le32(mem_clock); /* 10 khz */
atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
}
(rdev->pdev->subsystem_device == 0x4a48)) {
/* Mac X800 */
rdev->mode_info.connector_table = CT_MAC_X800;
+ } else if ((rdev->pdev->device == 0x4150) &&
+ (rdev->pdev->subsystem_vendor == 0x1002) &&
+ (rdev->pdev->subsystem_device == 0x4150)) {
+ /* Mac G5 9600 */
+ rdev->mode_info.connector_table = CT_MAC_G5_9600;
} else
#endif /* CONFIG_PPC_PMAC */
#ifdef CONFIG_PPC64
CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_I,
&hpd);
break;
+ case CT_MAC_G5_9600:
+ DRM_INFO("Connector Table: %d (mac g5 9600)\n",
+ rdev->mode_info.connector_table);
+ /* DVI - tv dac, dvo */
+ ddc_i2c = combios_setup_i2c_bus(rdev, DDC_DVI, 0, 0);
+ hpd.hpd = RADEON_HPD_1; /* ??? */
+ radeon_add_legacy_encoder(dev,
+ radeon_get_encoder_enum(dev,
+ ATOM_DEVICE_DFP2_SUPPORT,
+ 0),
+ ATOM_DEVICE_DFP2_SUPPORT);
+ radeon_add_legacy_encoder(dev,
+ radeon_get_encoder_enum(dev,
+ ATOM_DEVICE_CRT2_SUPPORT,
+ 2),
+ ATOM_DEVICE_CRT2_SUPPORT);
+ radeon_add_legacy_connector(dev, 0,
+ ATOM_DEVICE_DFP2_SUPPORT |
+ ATOM_DEVICE_CRT2_SUPPORT,
+ DRM_MODE_CONNECTOR_DVII, &ddc_i2c,
+ CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_I,
+ &hpd);
+ /* ADC - primary dac, internal tmds */
+ ddc_i2c = combios_setup_i2c_bus(rdev, DDC_VGA, 0, 0);
+ hpd.hpd = RADEON_HPD_2; /* ??? */
+ radeon_add_legacy_encoder(dev,
+ radeon_get_encoder_enum(dev,
+ ATOM_DEVICE_DFP1_SUPPORT,
+ 0),
+ ATOM_DEVICE_DFP1_SUPPORT);
+ radeon_add_legacy_encoder(dev,
+ radeon_get_encoder_enum(dev,
+ ATOM_DEVICE_CRT1_SUPPORT,
+ 1),
+ ATOM_DEVICE_CRT1_SUPPORT);
+ radeon_add_legacy_connector(dev, 1,
+ ATOM_DEVICE_DFP1_SUPPORT |
+ ATOM_DEVICE_CRT1_SUPPORT,
+ DRM_MODE_CONNECTOR_DVII, &ddc_i2c,
+ CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_I,
+ &hpd);
+ break;
default:
DRM_INFO("Connector table: %d (invalid)\n",
rdev->mode_info.connector_table);
int radeon_gpu_reset(struct radeon_device *rdev)
{
int r;
+ int resched;
radeon_save_bios_scratch_regs(rdev);
+ /* block TTM */
+ resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
radeon_suspend(rdev);
r = radeon_asic_reset(rdev);
radeon_resume(rdev);
radeon_restore_bios_scratch_regs(rdev);
drm_helper_resume_force_mode(rdev->ddev);
+ ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
return 0;
}
/* bad news, how to tell it to userspace ? */
tmp *= target_clock;
*fb_div = tmp / pll->reference_freq;
*frac_fb_div = tmp % pll->reference_freq;
+
+ if (*fb_div > pll->max_feedback_div)
+ *fb_div = pll->max_feedback_div;
+ else if (*fb_div < pll->min_feedback_div)
+ *fb_div = pll->min_feedback_div;
}
static u32 avivo_get_post_div(struct radeon_pll *pll,
post_div--;
}
+ if (post_div > pll->max_post_div)
+ post_div = pll->max_post_div;
+ else if (post_div < pll->min_post_div)
+ post_div = pll->min_post_div;
+
return post_div;
}
max_fractional_feed_div = pll->max_frac_feedback_div;
}
- for (post_div = min_post_div; post_div <= max_post_div; ++post_div) {
+ for (post_div = max_post_div; post_div >= min_post_div; --post_div) {
uint32_t ref_div;
if ((pll->flags & RADEON_PLL_NO_ODD_POST_DIV) && (post_div & 1))
#define R600_CP_RB_CNTL 0xc104
# define R600_RB_BUFSZ(x) ((x) << 0)
# define R600_RB_BLKSZ(x) ((x) << 8)
+# define R600_BUF_SWAP_32BIT (2 << 16)
# define R600_RB_NO_UPDATE (1 << 27)
# define R600_RB_RPTR_WR_ENA (1 << 31)
#define R600_CP_RB_RPTR_WR 0xc108
args.v1.ucAction = action;
if (action == ATOM_TRANSMITTER_ACTION_INIT) {
- args.v1.usInitInfo = connector_object_id;
+ args.v1.usInitInfo = cpu_to_le16(connector_object_id);
} else if (action == ATOM_TRANSMITTER_ACTION_SETUP_VSEMPH) {
args.v1.asMode.ucLaneSel = lane_num;
args.v1.asMode.ucLaneSet = lane_set;
case 3:
args.v3.sExtEncoder.ucAction = action;
if (action == EXTERNAL_ENCODER_ACTION_V3_ENCODER_INIT)
- args.v3.sExtEncoder.usConnectorId = connector_object_id;
+ args.v3.sExtEncoder.usConnectorId = cpu_to_le16(connector_object_id);
else
args.v3.sExtEncoder.usPixelClock = cpu_to_le16(radeon_encoder->pixel_clock / 10);
args.v3.sExtEncoder.ucEncoderMode = atombios_get_encoder_mode(encoder);
}
/* set scaler clears this on some chips */
- /* XXX check DCE4 */
- if (!(radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT))) {
- if (ASIC_IS_AVIVO(rdev) && (mode->flags & DRM_MODE_FLAG_INTERLACE))
- WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset,
- AVIVO_D1MODE_INTERLEAVE_EN);
+ if (ASIC_IS_AVIVO(rdev) &&
+ (!(radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT)))) {
+ if (ASIC_IS_DCE4(rdev)) {
+ if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+ WREG32(EVERGREEN_DATA_FORMAT + radeon_crtc->crtc_offset,
+ EVERGREEN_INTERLEAVE_EN);
+ else
+ WREG32(EVERGREEN_DATA_FORMAT + radeon_crtc->crtc_offset, 0);
+ } else {
+ if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+ WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset,
+ AVIVO_D1MODE_INTERLEAVE_EN);
+ else
+ WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset, 0);
+ }
}
}
u32 tiling_flags = 0;
int ret;
int aligned_size, size;
+ int height = mode_cmd->height;
/* need to align pitch with crtc limits */
mode_cmd->pitch = radeon_align_pitch(rdev, mode_cmd->width, mode_cmd->bpp, fb_tiled) * ((mode_cmd->bpp + 1) / 8);
- size = mode_cmd->pitch * mode_cmd->height;
+ if (rdev->family >= CHIP_R600)
+ height = ALIGN(mode_cmd->height, 8);
+ size = mode_cmd->pitch * height;
aligned_size = ALIGN(size, PAGE_SIZE);
ret = radeon_gem_object_create(rdev, aligned_size, 0,
RADEON_GEM_DOMAIN_VRAM,
{
struct radeon_device *rdev = dev->dev_private;
struct drm_radeon_gem_info *args = data;
+ struct ttm_mem_type_manager *man;
+
+ man = &rdev->mman.bdev.man[TTM_PL_VRAM];
args->vram_size = rdev->mc.real_vram_size;
- args->vram_visible = rdev->mc.real_vram_size;
+ args->vram_visible = (u64)man->size << PAGE_SHIFT;
if (rdev->stollen_vga_memory)
args->vram_visible -= radeon_bo_size(rdev->stollen_vga_memory);
args->vram_visible -= radeon_fbdev_total_size(rdev);
(target_fb->bits_per_pixel * 8));
crtc_pitch |= crtc_pitch << 16;
-
+ crtc_offset_cntl |= RADEON_CRTC_GUI_TRIG_OFFSET_LEFT_EN;
if (tiling_flags & RADEON_TILING_MACRO) {
if (ASIC_IS_R300(rdev))
crtc_offset_cntl |= (R300_CRTC_X_Y_MODE_EN |
gen_cntl_val = RREG32(gen_cntl_reg);
gen_cntl_val &= ~(0xf << 8);
gen_cntl_val |= (format << 8);
+ gen_cntl_val &= ~RADEON_CRTC_VSTAT_MODE_MASK;
WREG32(gen_cntl_reg, gen_cntl_val);
crtc_offset = (u32)base;
CT_EMAC,
CT_RN50_POWER,
CT_MAC_X800,
+ CT_MAC_G5_9600,
};
enum radeon_dvo_chip {
DRM_INFO("radeon: ttm finalized\n");
}
+/* this should only be called at bootup or when userspace
+ * isn't running */
+void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size)
+{
+ struct ttm_mem_type_manager *man;
+
+ if (!rdev->mman.initialized)
+ return;
+
+ man = &rdev->mman.bdev.man[TTM_PL_VRAM];
+ /* this just adjusts TTM size idea, which sets lpfn to the correct value */
+ man->size = size >> PAGE_SHIFT;
+}
+
static struct vm_operations_struct radeon_ttm_vm_ops;
static const struct vm_operations_struct *ttm_vm_ops = NULL;
radeon_mem_types_list[i].show = &radeon_mm_dump_table;
radeon_mem_types_list[i].driver_features = 0;
if (i == 0)
- radeon_mem_types_list[i].data = &rdev->mman.bdev.man[TTM_PL_VRAM].priv;
+ radeon_mem_types_list[i].data = rdev->mman.bdev.man[TTM_PL_VRAM].priv;
else
- radeon_mem_types_list[i].data = &rdev->mman.bdev.man[TTM_PL_TT].priv;
+ radeon_mem_types_list[i].data = rdev->mman.bdev.man[TTM_PL_TT].priv;
}
/* Add ttm page pool to debugfs */
0x4DF4 US_ALU_CONST_G_31
0x4DF8 US_ALU_CONST_B_31
0x4DFC US_ALU_CONST_A_31
-0x4E04 RB3D_BLENDCNTL_R3
0x4E08 RB3D_ABLENDCNTL_R3
-0x4E0C RB3D_COLOR_CHANNEL_MASK
0x4E10 RB3D_CONSTANT_COLOR
0x4E14 RB3D_COLOR_CLEAR_VALUE
0x4E18 RB3D_ROPCNTL_R3
0x4E74 RB3D_CMASK_WRINDEX
0x4E78 RB3D_CMASK_DWORD
0x4E7C RB3D_CMASK_RDINDEX
-0x4E80 RB3D_AARESOLVE_OFFSET
-0x4E84 RB3D_AARESOLVE_PITCH
-0x4E88 RB3D_AARESOLVE_CTL
0x4EA0 RB3D_DISCARD_SRC_PIXEL_LTE_THRESHOLD
0x4EA4 RB3D_DISCARD_SRC_PIXEL_GTE_THRESHOLD
0x4F04 ZB_ZSTENCILCNTL
0x4F08 ZB_STENCILREFMASK
0x4F14 ZB_ZTOP
0x4F18 ZB_ZCACHE_CTLSTAT
+0x4F28 ZB_DEPTHCLEARVALUE
0x4F58 ZB_ZPASS_DATA
0x401C GB_SELECT
0x4020 GB_AA_CONFIG
0x4024 GB_FIFO_SIZE
-0x4028 GB_Z_PEQ_CONFIG
0x4100 TX_INVALTAGS
0x4200 GA_POINT_S0
0x4204 GA_POINT_T0
0x4DF4 US_ALU_CONST_G_31
0x4DF8 US_ALU_CONST_B_31
0x4DFC US_ALU_CONST_A_31
-0x4E04 RB3D_BLENDCNTL_R3
0x4E08 RB3D_ABLENDCNTL_R3
-0x4E0C RB3D_COLOR_CHANNEL_MASK
0x4E10 RB3D_CONSTANT_COLOR
0x4E14 RB3D_COLOR_CLEAR_VALUE
0x4E18 RB3D_ROPCNTL_R3
0x4E74 RB3D_CMASK_WRINDEX
0x4E78 RB3D_CMASK_DWORD
0x4E7C RB3D_CMASK_RDINDEX
-0x4E80 RB3D_AARESOLVE_OFFSET
-0x4E84 RB3D_AARESOLVE_PITCH
-0x4E88 RB3D_AARESOLVE_CTL
0x4EA0 RB3D_DISCARD_SRC_PIXEL_LTE_THRESHOLD
0x4EA4 RB3D_DISCARD_SRC_PIXEL_GTE_THRESHOLD
0x4F04 ZB_ZSTENCILCNTL
0x4F08 ZB_STENCILREFMASK
0x4F14 ZB_ZTOP
0x4F18 ZB_ZCACHE_CTLSTAT
+0x4F28 ZB_DEPTHCLEARVALUE
0x4F58 ZB_ZPASS_DATA
0x4DF4 US_ALU_CONST_G_31
0x4DF8 US_ALU_CONST_B_31
0x4DFC US_ALU_CONST_A_31
-0x4E04 RB3D_BLENDCNTL_R3
0x4E08 RB3D_ABLENDCNTL_R3
-0x4E0C RB3D_COLOR_CHANNEL_MASK
0x4E10 RB3D_CONSTANT_COLOR
0x4E14 RB3D_COLOR_CLEAR_VALUE
0x4E18 RB3D_ROPCNTL_R3
0x4E74 RB3D_CMASK_WRINDEX
0x4E78 RB3D_CMASK_DWORD
0x4E7C RB3D_CMASK_RDINDEX
-0x4E80 RB3D_AARESOLVE_OFFSET
-0x4E84 RB3D_AARESOLVE_PITCH
-0x4E88 RB3D_AARESOLVE_CTL
0x4EA0 RB3D_DISCARD_SRC_PIXEL_LTE_THRESHOLD
0x4EA4 RB3D_DISCARD_SRC_PIXEL_GTE_THRESHOLD
0x4F04 ZB_ZSTENCILCNTL
0x4F08 ZB_STENCILREFMASK
0x4F14 ZB_ZTOP
0x4F18 ZB_ZCACHE_CTLSTAT
+0x4F28 ZB_DEPTHCLEARVALUE
0x4F58 ZB_ZPASS_DATA
0x401C GB_SELECT
0x4020 GB_AA_CONFIG
0x4024 GB_FIFO_SIZE
-0x4028 GB_Z_PEQ_CONFIG
0x4100 TX_INVALTAGS
0x4114 SU_TEX_WRAP_PS3
0x4118 PS3_ENABLE
0x4DF4 US_ALU_CONST_G_31
0x4DF8 US_ALU_CONST_B_31
0x4DFC US_ALU_CONST_A_31
-0x4E04 RB3D_BLENDCNTL_R3
0x4E08 RB3D_ABLENDCNTL_R3
-0x4E0C RB3D_COLOR_CHANNEL_MASK
0x4E10 RB3D_CONSTANT_COLOR
0x4E14 RB3D_COLOR_CLEAR_VALUE
0x4E18 RB3D_ROPCNTL_R3
0x4E74 RB3D_CMASK_WRINDEX
0x4E78 RB3D_CMASK_DWORD
0x4E7C RB3D_CMASK_RDINDEX
-0x4E80 RB3D_AARESOLVE_OFFSET
-0x4E84 RB3D_AARESOLVE_PITCH
-0x4E88 RB3D_AARESOLVE_CTL
0x4EA0 RB3D_DISCARD_SRC_PIXEL_LTE_THRESHOLD
0x4EA4 RB3D_DISCARD_SRC_PIXEL_GTE_THRESHOLD
0x4EF8 RB3D_CONSTANT_COLOR_AR
0x4F14 ZB_ZTOP
0x4F18 ZB_ZCACHE_CTLSTAT
0x4F58 ZB_ZPASS_DATA
+0x4F28 ZB_DEPTHCLEARVALUE
0x4FD4 ZB_STENCILREFMASK_BF
rdev->mc.real_vram_size = RREG32(RADEON_CONFIG_MEMSIZE);
rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
rdev->mc.visible_vram_size = rdev->mc.aper_size;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
base = RREG32_MC(R_000004_MC_FB_LOCATION);
base = G_000004_MC_FB_START(base) << 16;
switch (crev) {
case 1:
tmp.full = dfixed_const(100);
- rdev->pm.igp_sideport_mclk.full = dfixed_const(info->info.ulBootUpMemoryClock);
+ rdev->pm.igp_sideport_mclk.full = dfixed_const(le32_to_cpu(info->info.ulBootUpMemoryClock));
rdev->pm.igp_sideport_mclk.full = dfixed_div(rdev->pm.igp_sideport_mclk, tmp);
- if (info->info.usK8MemoryClock)
+ if (le16_to_cpu(info->info.usK8MemoryClock))
rdev->pm.igp_system_mclk.full = dfixed_const(le16_to_cpu(info->info.usK8MemoryClock));
else if (rdev->clock.default_mclk) {
rdev->pm.igp_system_mclk.full = dfixed_const(rdev->clock.default_mclk);
break;
case 2:
tmp.full = dfixed_const(100);
- rdev->pm.igp_sideport_mclk.full = dfixed_const(info->info_v2.ulBootUpSidePortClock);
+ rdev->pm.igp_sideport_mclk.full = dfixed_const(le32_to_cpu(info->info_v2.ulBootUpSidePortClock));
rdev->pm.igp_sideport_mclk.full = dfixed_div(rdev->pm.igp_sideport_mclk, tmp);
- if (info->info_v2.ulBootUpUMAClock)
- rdev->pm.igp_system_mclk.full = dfixed_const(info->info_v2.ulBootUpUMAClock);
+ if (le32_to_cpu(info->info_v2.ulBootUpUMAClock))
+ rdev->pm.igp_system_mclk.full = dfixed_const(le32_to_cpu(info->info_v2.ulBootUpUMAClock));
else if (rdev->clock.default_mclk)
rdev->pm.igp_system_mclk.full = dfixed_const(rdev->clock.default_mclk);
else
rdev->pm.igp_system_mclk.full = dfixed_const(66700);
rdev->pm.igp_system_mclk.full = dfixed_div(rdev->pm.igp_system_mclk, tmp);
- rdev->pm.igp_ht_link_clk.full = dfixed_const(info->info_v2.ulHTLinkFreq);
+ rdev->pm.igp_ht_link_clk.full = dfixed_const(le32_to_cpu(info->info_v2.ulHTLinkFreq));
rdev->pm.igp_ht_link_clk.full = dfixed_div(rdev->pm.igp_ht_link_clk, tmp);
rdev->pm.igp_ht_link_width.full = dfixed_const(le16_to_cpu(info->info_v2.usMinHTLinkWidth));
break;
rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
rdev->mc.visible_vram_size = rdev->mc.aper_size;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
base = RREG32_MC(R_000100_MCCFG_FB_LOCATION);
base = G_000100_MC_FB_START(base) << 16;
rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
*/
void r700_cp_stop(struct radeon_device *rdev)
{
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
WREG32(CP_ME_CNTL, (CP_ME_HALT | CP_PFP_HALT));
WREG32(SCRATCH_UMSK, 0);
}
return -EINVAL;
r700_cp_stop(rdev);
- WREG32(CP_RB_CNTL, RB_NO_UPDATE | (15 << 8) | (3 << 0));
+ WREG32(CP_RB_CNTL,
+#ifdef __BIG_ENDIAN
+ BUF_SWAP_32BIT |
+#endif
+ RB_NO_UPDATE | RB_BLKSZ(15) | RB_BUFSZ(3));
/* Reset cp */
WREG32(GRBM_SOFT_RESET, SOFT_RESET_CP);
rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE);
rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE);
rdev->mc.visible_vram_size = rdev->mc.aper_size;
- rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
r700_vram_gtt_location(rdev, &rdev->mc);
radeon_update_bandwidth_info(rdev);
#define ROQ_IB1_START(x) ((x) << 0)
#define ROQ_IB2_START(x) ((x) << 8)
#define CP_RB_CNTL 0xC104
-#define RB_BUFSZ(x) ((x)<<0)
-#define RB_BLKSZ(x) ((x)<<8)
-#define RB_NO_UPDATE (1<<27)
-#define RB_RPTR_WR_ENA (1<<31)
+#define RB_BUFSZ(x) ((x) << 0)
+#define RB_BLKSZ(x) ((x) << 8)
+#define RB_NO_UPDATE (1 << 27)
+#define RB_RPTR_WR_ENA (1 << 31)
#define BUF_SWAP_32BIT (2 << 16)
#define CP_RB_RPTR 0x8700
#define CP_RB_RPTR_ADDR 0xC10C
will be called k8temp.
config SENSORS_K10TEMP
- tristate "AMD Phenom/Sempron/Turion/Opteron temperature sensor"
+ tristate "AMD Family 10h/11h/12h/14h temperature sensor"
depends on X86 && PCI
help
If you say yes here you get support for the temperature
sensor(s) inside your CPU. Supported are later revisions of
- the AMD Family 10h and all revisions of the AMD Family 11h
- microarchitectures.
+ the AMD Family 10h and all revisions of the AMD Family 11h,
+ 12h (Llano), and 14h (Brazos) microarchitectures.
This driver can also be built as a module. If so, the module
will be called k10temp.
called jz4740-hwmon.
config SENSORS_JC42
- tristate "JEDEC JC42.4 compliant temperature sensors"
+ tristate "JEDEC JC42.4 compliant memory module temperature sensors"
depends on I2C
help
- If you say yes here you get support for Jedec JC42.4 compliant
- temperature sensors. Support will include, but not be limited to,
- ADT7408, CAT34TS02,, CAT6095, MAX6604, MCP9805, MCP98242, MCP98243,
- MCP9843, SE97, SE98, STTS424, TSE2002B3, and TS3000B3.
+ If you say yes here, you get support for JEDEC JC42.4 compliant
+ temperature sensors, which are used on many DDR3 memory modules for
+ mobile devices and servers. Support will include, but not be limited
+ to, ADT7408, CAT34TS02, CAT6095, MAX6604, MCP9805, MCP98242, MCP98243,
+ MCP9843, SE97, SE98, STTS424(E), TSE2002B3, and TS3000B3.
This driver can also be built as a module. If so, the module
will be called jc42.
help
If you say yes here you get support for National Semiconductor LM85
sensor chips and clones: ADM1027, ADT7463, ADT7468, EMC6D100,
- EMC6D101 and EMC6D102.
+ EMC6D101, EMC6D102, and EMC6D103.
This driver can also be built as a module. If so, the module
will be called lm85.
{ "ad7414", 0 },
{}
};
+MODULE_DEVICE_TABLE(i2c, ad7414_id);
static struct i2c_driver ad7414_driver = {
.driver = {
{ "adt7411", 0 },
{ }
};
+MODULE_DEVICE_TABLE(i2c, adt7411_id);
static struct i2c_driver adt7411_driver = {
.driver = {
}
static const unsigned short emc1403_address_list[] = {
- 0x18, 0x2a, 0x4c, 0x4d, I2C_CLIENT_END
+ 0x18, 0x29, 0x4c, 0x4d, I2C_CLIENT_END
};
static const struct i2c_device_id emc1403_idtable[] = {
#define SIO_F71858FG_LD_HWM 0x02 /* Hardware monitor logical device */
#define SIO_F71882FG_LD_HWM 0x04 /* Hardware monitor logical device */
#define SIO_UNLOCK_KEY 0x87 /* Key to enable Super-I/O */
-#define SIO_LOCK_KEY 0xAA /* Key to diasble Super-I/O */
+#define SIO_LOCK_KEY 0xAA /* Key to disable Super-I/O */
#define SIO_REG_LDSEL 0x07 /* Logical device select */
#define SIO_REG_DEVID 0x20 /* Device ID (2 bytes) */
int nr_fans = (data->type == f71882fg) ? 4 : 3;
u8 start_reg = f71882fg_read8(data, F71882FG_REG_START);
- platform_set_drvdata(pdev, NULL);
if (data->hwmon_dev)
hwmon_device_unregister(data->hwmon_dev);
}
}
+ platform_set_drvdata(pdev, NULL);
kfree(data);
return 0;
/* Configuration register defines */
#define JC42_CFG_CRIT_ONLY (1 << 2)
+#define JC42_CFG_TCRIT_LOCK (1 << 6)
+#define JC42_CFG_EVENT_LOCK (1 << 7)
#define JC42_CFG_SHUTDOWN (1 << 8)
#define JC42_CFG_HYST_SHIFT 9
#define JC42_CFG_HYST_MASK 0x03
{
struct i2c_client *client = to_i2c_client(dev);
struct jc42_data *data = i2c_get_clientdata(client);
- long val;
+ unsigned long val;
int diff, hyst;
int err;
int ret = count;
static DEVICE_ATTR(temp1_input, S_IRUGO,
show_temp_input, NULL);
-static DEVICE_ATTR(temp1_crit, S_IWUSR | S_IRUGO,
+static DEVICE_ATTR(temp1_crit, S_IRUGO,
show_temp_crit, set_temp_crit);
-static DEVICE_ATTR(temp1_min, S_IWUSR | S_IRUGO,
+static DEVICE_ATTR(temp1_min, S_IRUGO,
show_temp_min, set_temp_min);
-static DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO,
+static DEVICE_ATTR(temp1_max, S_IRUGO,
show_temp_max, set_temp_max);
-static DEVICE_ATTR(temp1_crit_hyst, S_IWUSR | S_IRUGO,
+static DEVICE_ATTR(temp1_crit_hyst, S_IRUGO,
show_temp_crit_hyst, set_temp_crit_hyst);
static DEVICE_ATTR(temp1_max_hyst, S_IRUGO,
show_temp_max_hyst, NULL);
NULL
};
+static mode_t jc42_attribute_mode(struct kobject *kobj,
+ struct attribute *attr, int index)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct i2c_client *client = to_i2c_client(dev);
+ struct jc42_data *data = i2c_get_clientdata(client);
+ unsigned int config = data->config;
+ bool readonly;
+
+ if (attr == &dev_attr_temp1_crit.attr)
+ readonly = config & JC42_CFG_TCRIT_LOCK;
+ else if (attr == &dev_attr_temp1_min.attr ||
+ attr == &dev_attr_temp1_max.attr)
+ readonly = config & JC42_CFG_EVENT_LOCK;
+ else if (attr == &dev_attr_temp1_crit_hyst.attr)
+ readonly = config & (JC42_CFG_EVENT_LOCK | JC42_CFG_TCRIT_LOCK);
+ else
+ readonly = true;
+
+ return S_IRUGO | (readonly ? 0 : S_IWUSR);
+}
+
static const struct attribute_group jc42_group = {
.attrs = jc42_attributes,
+ .is_visible = jc42_attribute_mode,
};
/* Return 0 if detection is successful, -ENODEV otherwise */
/*
- * k10temp.c - AMD Family 10h/11h processor hardware monitoring
+ * k10temp.c - AMD Family 10h/11h/12h/14h processor hardware monitoring
*
* Copyright (c) 2009 Clemens Ladisch <clemens@ladisch.de>
*
#include <linux/pci.h>
#include <asm/processor.h>
-MODULE_DESCRIPTION("AMD Family 10h/11h CPU core temperature monitor");
+MODULE_DESCRIPTION("AMD Family 10h/11h/12h/14h CPU core temperature monitor");
MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
MODULE_LICENSE("GPL");
static const struct pci_device_id k10temp_id_table[] = {
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) },
+ { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
{}
};
MODULE_DEVICE_TABLE(pci, k10temp_id_table);
* value, it uses signed 8-bit values with LSB = 1 degree Celsius.
* For remote temperature, low and high limits, it uses signed 11-bit values
* with LSB = 0.125 degree Celsius, left-justified in 16-bit registers.
+ * For LM64 the actual remote diode temperature is 16 degree Celsius higher
+ * than the register reading. Remote temperature setpoints have to be
+ * adapted accordingly.
*/
#define FAN_FROM_REG(reg) ((reg) == 0xFFFC || (reg) == 0 ? 0 : \
struct mutex update_lock;
char valid; /* zero until following fields are valid */
unsigned long last_updated; /* in jiffies */
+ int kind;
+ int temp2_offset;
/* registers values */
u8 config, config_fan;
return sprintf(buf, "%d\n", data->config_fan & 0x20 ? 1 : 2);
}
-static ssize_t show_temp8(struct device *dev, struct device_attribute *devattr,
- char *buf)
+/*
+ * There are 8bit registers for both local(temp1) and remote(temp2) sensor.
+ * For remote sensor registers temp2_offset has to be considered,
+ * for local sensor it must not.
+ * So we need separate 8bit accessors for local and remote sensor.
+ */
+static ssize_t show_local_temp8(struct device *dev,
+ struct device_attribute *devattr,
+ char *buf)
{
struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
struct lm63_data *data = lm63_update_device(dev);
return sprintf(buf, "%d\n", TEMP8_FROM_REG(data->temp8[attr->index]));
}
-static ssize_t set_temp8(struct device *dev, struct device_attribute *dummy,
- const char *buf, size_t count)
+static ssize_t show_remote_temp8(struct device *dev,
+ struct device_attribute *devattr,
+ char *buf)
+{
+ struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+ struct lm63_data *data = lm63_update_device(dev);
+ return sprintf(buf, "%d\n", TEMP8_FROM_REG(data->temp8[attr->index])
+ + data->temp2_offset);
+}
+
+static ssize_t set_local_temp8(struct device *dev,
+ struct device_attribute *dummy,
+ const char *buf, size_t count)
{
struct i2c_client *client = to_i2c_client(dev);
struct lm63_data *data = i2c_get_clientdata(client);
{
struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
struct lm63_data *data = lm63_update_device(dev);
- return sprintf(buf, "%d\n", TEMP11_FROM_REG(data->temp11[attr->index]));
+ return sprintf(buf, "%d\n", TEMP11_FROM_REG(data->temp11[attr->index])
+ + data->temp2_offset);
}
static ssize_t set_temp11(struct device *dev, struct device_attribute *devattr,
int nr = attr->index;
mutex_lock(&data->update_lock);
- data->temp11[nr] = TEMP11_TO_REG(val);
+ data->temp11[nr] = TEMP11_TO_REG(val - data->temp2_offset);
i2c_smbus_write_byte_data(client, reg[(nr - 1) * 2],
data->temp11[nr] >> 8);
i2c_smbus_write_byte_data(client, reg[(nr - 1) * 2 + 1],
{
struct lm63_data *data = lm63_update_device(dev);
return sprintf(buf, "%d\n", TEMP8_FROM_REG(data->temp8[2])
+ + data->temp2_offset
- TEMP8_FROM_REG(data->temp2_crit_hyst));
}
long hyst;
mutex_lock(&data->update_lock);
- hyst = TEMP8_FROM_REG(data->temp8[2]) - val;
+ hyst = TEMP8_FROM_REG(data->temp8[2]) + data->temp2_offset - val;
i2c_smbus_write_byte_data(client, LM63_REG_REMOTE_TCRIT_HYST,
HYST_TO_REG(hyst));
mutex_unlock(&data->update_lock);
static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm1, set_pwm1);
static DEVICE_ATTR(pwm1_enable, S_IRUGO, show_pwm1_enable, NULL);
-static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp8, NULL, 0);
-static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp8,
- set_temp8, 1);
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_local_temp8, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_local_temp8,
+ set_local_temp8, 1);
static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, show_temp11, NULL, 0);
static SENSOR_DEVICE_ATTR(temp2_min, S_IWUSR | S_IRUGO, show_temp11,
set_temp11, 1);
static SENSOR_DEVICE_ATTR(temp2_max, S_IWUSR | S_IRUGO, show_temp11,
set_temp11, 2);
-static SENSOR_DEVICE_ATTR(temp2_crit, S_IRUGO, show_temp8, NULL, 2);
+/*
+ * On LM63, temp2_crit can be set only once, which should be job
+ * of the bootloader.
+ */
+static SENSOR_DEVICE_ATTR(temp2_crit, S_IRUGO, show_remote_temp8,
+ NULL, 2);
static DEVICE_ATTR(temp2_crit_hyst, S_IWUSR | S_IRUGO, show_temp2_crit_hyst,
set_temp2_crit_hyst);
data->valid = 0;
mutex_init(&data->update_lock);
- /* Initialize the LM63 chip */
+ /* Set the device type */
+ data->kind = id->driver_data;
+ if (data->kind == lm64)
+ data->temp2_offset = 16000;
+
+ /* Initialize chip */
lm63_init_client(new_client);
/* Register sysfs hooks */
enum chips {
any_chip, lm85b, lm85c,
adm1027, adt7463, adt7468,
- emc6d100, emc6d102
+ emc6d100, emc6d102, emc6d103
};
/* The LM85 registers */
#define LM85_VERSTEP_EMC6D100_A0 0x60
#define LM85_VERSTEP_EMC6D100_A1 0x61
#define LM85_VERSTEP_EMC6D102 0x65
+#define LM85_VERSTEP_EMC6D103_A0 0x68
+#define LM85_VERSTEP_EMC6D103_A1 0x69
+#define LM85_VERSTEP_EMC6D103S 0x6A /* Also known as EMC6D103:A2 */
#define LM85_REG_CONFIG 0x40
{ "emc6d100", emc6d100 },
{ "emc6d101", emc6d100 },
{ "emc6d102", emc6d102 },
+ { "emc6d103", emc6d103 },
{ }
};
MODULE_DEVICE_TABLE(i2c, lm85_id);
case LM85_VERSTEP_EMC6D102:
type_name = "emc6d102";
break;
+ case LM85_VERSTEP_EMC6D103_A0:
+ case LM85_VERSTEP_EMC6D103_A1:
+ type_name = "emc6d103";
+ break;
+ /*
+ * Registers apparently missing in EMC6D103S/EMC6D103:A2
+ * compared to EMC6D103:A0, EMC6D103:A1, and EMC6D102
+ * (according to the data sheets), but used unconditionally
+ * in the driver: 62[5:7], 6D[0:7], and 6E[0:7].
+ * So skip EMC6D103S for now.
+ case LM85_VERSTEP_EMC6D103S:
+ type_name = "emc6d103s";
+ break;
+ */
}
} else {
dev_dbg(&adapter->dev,
case adt7468:
case emc6d100:
case emc6d102:
+ case emc6d103:
data->freq_map = adm1027_freq_map;
break;
default:
/* More alarm bits */
data->alarms |= lm85_read_value(client,
EMC6D100_REG_ALARM3) << 16;
- } else if (data->type == emc6d102) {
+ } else if (data->type == emc6d102 || data->type == emc6d103) {
/* Have to read LSB bits after the MSB ones because
the reading of the MSB bits has frozen the
LSBs (backward from the ADM1027).
#include <linux/pci.h>
#include <linux/mutex.h>
#include <linux/ktime.h>
+#include <linux/slab.h>
#define PCH_EVENT_SET 0 /* I2C Interrupt Event Set Status */
#define PCH_EVENT_NONE 1 /* I2C Interrupt Event Clear Status */
static int ocores_i2c_of_probe(struct platform_device* pdev,
struct ocores_i2c* i2c)
{
- __be32* val;
+ const __be32* val;
val = of_get_property(pdev->dev.of_node, "regstep", NULL);
if (!val) {
* REVISIT: Some wkup sources might not be needed.
*/
dev->westate = OMAP_I2C_WE_ALL;
- if (dev->rev < OMAP_I2C_REV_ON_4430)
- omap_i2c_write_reg(dev, OMAP_I2C_WE_REG,
- dev->westate);
+ omap_i2c_write_reg(dev, OMAP_I2C_WE_REG, dev->westate);
}
}
omap_i2c_write_reg(dev, OMAP_I2C_CON_REG, 0);
dev_err(dev->dev, "Arbitration lost\n");
err |= OMAP_I2C_STAT_AL;
}
+ /*
+ * ProDB0017052: Clear ARDY bit twice
+ */
if (stat & (OMAP_I2C_STAT_ARDY | OMAP_I2C_STAT_NACK |
OMAP_I2C_STAT_AL)) {
omap_i2c_ack_stat(dev, stat &
(OMAP_I2C_STAT_RRDY | OMAP_I2C_STAT_RDR |
- OMAP_I2C_STAT_XRDY | OMAP_I2C_STAT_XDR));
+ OMAP_I2C_STAT_XRDY | OMAP_I2C_STAT_XDR |
+ OMAP_I2C_STAT_ARDY));
omap_i2c_complete_cmd(dev, err);
return IRQ_HANDLED;
}
return 0;
}
+#ifdef CONFIG_SUSPEND
+static int omap_i2c_suspend(struct device *dev)
+{
+ if (!pm_runtime_suspended(dev))
+ if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend)
+ dev->bus->pm->runtime_suspend(dev);
+
+ return 0;
+}
+
+static int omap_i2c_resume(struct device *dev)
+{
+ if (!pm_runtime_suspended(dev))
+ if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume)
+ dev->bus->pm->runtime_resume(dev);
+
+ return 0;
+}
+
+static struct dev_pm_ops omap_i2c_pm_ops = {
+ .suspend = omap_i2c_suspend,
+ .resume = omap_i2c_resume,
+};
+#define OMAP_I2C_PM_OPS (&omap_i2c_pm_ops)
+#else
+#define OMAP_I2C_PM_OPS NULL
+#endif
+
static struct platform_driver omap_i2c_driver = {
.probe = omap_i2c_probe,
.remove = omap_i2c_remove,
.driver = {
.name = "omap_i2c",
.owner = THIS_MODULE,
+ .pm = OMAP_I2C_PM_OPS,
},
};
adap->owner = THIS_MODULE;
/* DDC class but actually often used for more generic I2C */
adap->class = I2C_CLASS_DDC;
- strncpy(adap->name, "ST Microelectronics DDC I2C adapter",
+ strlcpy(adap->name, "ST Microelectronics DDC I2C adapter",
sizeof(adap->name));
adap->nr = bus_nr;
adap->algo = &stu300_algo;
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <asm/mwait.h>
+#include <asm/msr.h>
#define INTEL_IDLE_VERSION "0.4"
#define PREFIX "intel_idle: "
static struct cpuidle_state *cpuidle_state_table;
+/*
+ * Hardware C-state auto-demotion may not always be optimal.
+ * Indicate which enable bits to clear here.
+ */
+static unsigned long long auto_demotion_disable_flags;
+
/*
* Set this flag for states where the HW flushes the TLB for us
* and so we don't need cross-calls to keep it consistent.
.notifier_call = setup_broadcast_cpuhp_notify,
};
+static void auto_demotion_disable(void *dummy)
+{
+ unsigned long long msr_bits;
+
+ rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
+ msr_bits &= ~auto_demotion_disable_flags;
+ wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
+}
+
/*
* intel_idle_probe()
*/
case 0x25: /* Westmere */
case 0x2C: /* Westmere */
cpuidle_state_table = nehalem_cstates;
+ auto_demotion_disable_flags =
+ (NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE);
break;
case 0x1C: /* 28 - Atom Processor */
+ cpuidle_state_table = atom_cstates;
+ break;
+
case 0x26: /* 38 - Lincroft Atom Processor */
cpuidle_state_table = atom_cstates;
+ auto_demotion_disable_flags = ATM_LNC_C6_AUTO_DEMOTE;
break;
case 0x2A: /* SNB */
return -EIO;
}
}
+ if (auto_demotion_disable_flags)
+ smp_call_function(auto_demotion_disable, NULL, 1);
return 0;
}
netif_carrier_on(nesvnic->netdev);
spin_lock(&nesvnic->port_ibevent_lock);
- if (nesdev->iw_status == 0) {
- nesdev->iw_status = 1;
- nes_port_ibevent(nesvnic);
+ if (nesvnic->of_device_registered) {
+ if (nesdev->iw_status == 0) {
+ nesdev->iw_status = 1;
+ nes_port_ibevent(nesvnic);
+ }
}
spin_unlock(&nesvnic->port_ibevent_lock);
}
netif_carrier_off(nesvnic->netdev);
spin_lock(&nesvnic->port_ibevent_lock);
- if (nesdev->iw_status == 1) {
- nesdev->iw_status = 0;
- nes_port_ibevent(nesvnic);
+ if (nesvnic->of_device_registered) {
+ if (nesdev->iw_status == 1) {
+ nesdev->iw_status = 0;
+ nes_port_ibevent(nesvnic);
+ }
}
spin_unlock(&nesvnic->port_ibevent_lock);
}
netif_carrier_on(nesvnic->netdev);
spin_lock(&nesvnic->port_ibevent_lock);
- if (nesdev->iw_status == 0) {
- nesdev->iw_status = 1;
- nes_port_ibevent(nesvnic);
+ if (nesvnic->of_device_registered) {
+ if (nesdev->iw_status == 0) {
+ nesdev->iw_status = 1;
+ nes_port_ibevent(nesvnic);
+ }
}
spin_unlock(&nesvnic->port_ibevent_lock);
}
netif_carrier_off(nesvnic->netdev);
spin_lock(&nesvnic->port_ibevent_lock);
- if (nesdev->iw_status == 1) {
- nesdev->iw_status = 0;
- nes_port_ibevent(nesvnic);
+ if (nesvnic->of_device_registered) {
+ if (nesdev->iw_status == 1) {
+ nesdev->iw_status = 0;
+ nes_port_ibevent(nesvnic);
+ }
}
spin_unlock(&nesvnic->port_ibevent_lock);
}
* there are still requests that haven't been acked.
*/
if ((psn & IB_BTH_REQ_ACK) && qp->s_acked != qp->s_tail &&
- !(qp->s_flags & (QIB_S_TIMER | QIB_S_WAIT_RNR | QIB_S_WAIT_PSN)))
+ !(qp->s_flags & (QIB_S_TIMER | QIB_S_WAIT_RNR | QIB_S_WAIT_PSN)) &&
+ (ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK))
start_timer(qp);
while (qp->s_last != qp->s_acked) {
}
spin_lock_irqsave(&qp->s_lock, flags);
+ if (!(ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK))
+ goto ack_done;
/* Ignore invalid responses. */
if (qib_cmp24(psn, qp->s_next_psn) >= 0)
event->owner = owner;
list_add_tail(&event->node, &gameport_event_list);
- schedule_work(&gameport_event_work);
+ queue_work(system_long_wq, &gameport_event_work);
out:
spin_unlock_irqrestore(&gameport_event_lock, flags);
* dev->event_lock held and interrupts disabled.
*/
static void input_pass_event(struct input_dev *dev,
- struct input_handler *src_handler,
unsigned int type, unsigned int code, int value)
{
struct input_handler *handler;
continue;
handler = handle->handler;
-
- /*
- * If this is the handler that injected this
- * particular event we want to skip it to avoid
- * filters firing again and again.
- */
- if (handler == src_handler)
- continue;
-
if (!handler->filter) {
if (filtered)
break;
if (test_bit(dev->repeat_key, dev->key) &&
is_event_supported(dev->repeat_key, dev->keybit, KEY_MAX)) {
- input_pass_event(dev, NULL, EV_KEY, dev->repeat_key, 2);
+ input_pass_event(dev, EV_KEY, dev->repeat_key, 2);
if (dev->sync) {
/*
* Otherwise assume that the driver will send
* SYN_REPORT once it's done.
*/
- input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1);
+ input_pass_event(dev, EV_SYN, SYN_REPORT, 1);
}
if (dev->rep[REP_PERIOD])
#define INPUT_PASS_TO_ALL (INPUT_PASS_TO_HANDLERS | INPUT_PASS_TO_DEVICE)
static int input_handle_abs_event(struct input_dev *dev,
- struct input_handler *src_handler,
unsigned int code, int *pval)
{
bool is_mt_event;
/* Flush pending "slot" event */
if (is_mt_event && dev->slot != input_abs_get_val(dev, ABS_MT_SLOT)) {
input_abs_set_val(dev, ABS_MT_SLOT, dev->slot);
- input_pass_event(dev, src_handler,
- EV_ABS, ABS_MT_SLOT, dev->slot);
+ input_pass_event(dev, EV_ABS, ABS_MT_SLOT, dev->slot);
}
return INPUT_PASS_TO_HANDLERS;
}
static void input_handle_event(struct input_dev *dev,
- struct input_handler *src_handler,
unsigned int type, unsigned int code, int value)
{
int disposition = INPUT_IGNORE_EVENT;
case EV_ABS:
if (is_event_supported(code, dev->absbit, ABS_MAX))
- disposition = input_handle_abs_event(dev, src_handler,
- code, &value);
+ disposition = input_handle_abs_event(dev, code, &value);
break;
dev->event(dev, type, code, value);
if (disposition & INPUT_PASS_TO_HANDLERS)
- input_pass_event(dev, src_handler, type, code, value);
+ input_pass_event(dev, type, code, value);
}
/**
spin_lock_irqsave(&dev->event_lock, flags);
add_input_randomness(type, code, value);
- input_handle_event(dev, NULL, type, code, value);
+ input_handle_event(dev, type, code, value);
spin_unlock_irqrestore(&dev->event_lock, flags);
}
}
rcu_read_lock();
grab = rcu_dereference(dev->grab);
if (!grab || grab == handle)
- input_handle_event(dev, handle->handler,
- type, code, value);
+ input_handle_event(dev, type, code, value);
rcu_read_unlock();
spin_unlock_irqrestore(&dev->event_lock, flags);
for (code = 0; code <= KEY_MAX; code++) {
if (is_event_supported(code, dev->keybit, KEY_MAX) &&
__test_and_clear_bit(code, dev->key)) {
- input_pass_event(dev, NULL, EV_KEY, code, 0);
+ input_pass_event(dev, EV_KEY, code, 0);
}
}
- input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1);
+ input_pass_event(dev, EV_SYN, SYN_REPORT, 1);
}
}
!is_event_supported(old_keycode, dev->keybit, KEY_MAX) &&
__test_and_clear_bit(old_keycode, dev->key)) {
- input_pass_event(dev, NULL, EV_KEY, old_keycode, 0);
+ input_pass_event(dev, EV_KEY, old_keycode, 0);
if (dev->sync)
- input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1);
+ input_pass_event(dev, EV_SYN, SYN_REPORT, 1);
}
out:
spinlock_t lock;
unsigned int repoll_dly;
unsigned long cp_dly_jiffies;
+ bool use_fn_map;
const struct tegra_kbc_platform_data *pdata;
- unsigned short keycode[KBC_MAX_KEY];
+ unsigned short keycode[KBC_MAX_KEY * 2];
unsigned short current_keys[KBC_MAX_KPENT];
unsigned int num_pressed_keys;
struct timer_list timer;
KEY(15, 5, KEY_F2),
KEY(15, 6, KEY_CAPSLOCK),
KEY(15, 7, KEY_F6),
+
+ /* Software Handled Function Keys */
+ KEY(20, 0, KEY_KP7),
+
+ KEY(21, 0, KEY_KP9),
+ KEY(21, 1, KEY_KP8),
+ KEY(21, 2, KEY_KP4),
+ KEY(21, 4, KEY_KP1),
+
+ KEY(22, 1, KEY_KPSLASH),
+ KEY(22, 2, KEY_KP6),
+ KEY(22, 3, KEY_KP5),
+ KEY(22, 4, KEY_KP3),
+ KEY(22, 5, KEY_KP2),
+ KEY(22, 7, KEY_KP0),
+
+ KEY(27, 1, KEY_KPASTERISK),
+ KEY(27, 3, KEY_KPMINUS),
+ KEY(27, 4, KEY_KPPLUS),
+ KEY(27, 5, KEY_KPDOT),
+
+ KEY(28, 5, KEY_VOLUMEUP),
+
+ KEY(29, 3, KEY_HOME),
+ KEY(29, 4, KEY_END),
+ KEY(29, 5, KEY_BRIGHTNESSDOWN),
+ KEY(29, 6, KEY_VOLUMEDOWN),
+ KEY(29, 7, KEY_BRIGHTNESSUP),
+
+ KEY(30, 0, KEY_NUMLOCK),
+ KEY(30, 1, KEY_SCROLLLOCK),
+ KEY(30, 2, KEY_MUTE),
+
+ KEY(31, 4, KEY_HELP),
};
static const struct matrix_keymap_data tegra_kbc_default_keymap_data = {
unsigned int i;
unsigned int num_down = 0;
unsigned long flags;
+ bool fn_keypress = false;
spin_lock_irqsave(&kbc->lock, flags);
for (i = 0; i < KBC_MAX_KPENT; i++) {
MATRIX_SCAN_CODE(row, col, KBC_ROW_SHIFT);
scancodes[num_down] = scancode;
- keycodes[num_down++] = kbc->keycode[scancode];
+ keycodes[num_down] = kbc->keycode[scancode];
+ /* If driver uses Fn map, do not report the Fn key. */
+ if ((keycodes[num_down] == KEY_FN) && kbc->use_fn_map)
+ fn_keypress = true;
+ else
+ num_down++;
}
val >>= 8;
}
+
+ /*
+ * If the platform uses Fn keymaps, translate keys on a Fn keypress.
+ * Function keycodes are KBC_MAX_KEY apart from the plain keycodes.
+ */
+ if (fn_keypress) {
+ for (i = 0; i < num_down; i++) {
+ scancodes[i] += KBC_MAX_KEY;
+ keycodes[i] = kbc->keycode[scancodes[i]];
+ }
+ }
+
spin_unlock_irqrestore(&kbc->lock, flags);
tegra_kbc_report_released_keys(kbc->idev,
input_dev->keycode = kbc->keycode;
input_dev->keycodesize = sizeof(kbc->keycode[0]);
- input_dev->keycodemax = ARRAY_SIZE(kbc->keycode);
+ input_dev->keycodemax = KBC_MAX_KEY;
+ if (pdata->use_fn_map)
+ input_dev->keycodemax *= 2;
+ kbc->use_fn_map = pdata->use_fn_map;
keymap_data = pdata->keymap_data ?: &tegra_kbc_default_keymap_data;
matrix_keypad_build_keymap(keymap_data, KBC_ROW_SHIFT,
input_dev->keycode, input_dev->keybit);
/* request the IRQs */
err = request_irq(encoder->irq_a, &rotary_encoder_irq,
- IORESOURCE_IRQ_HIGHEDGE | IORESOURCE_IRQ_LOWEDGE,
+ IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
DRV_NAME, encoder);
if (err) {
dev_err(&pdev->dev, "unable to request IRQ %d\n",
}
err = request_irq(encoder->irq_b, &rotary_encoder_irq,
- IORESOURCE_IRQ_HIGHEDGE | IORESOURCE_IRQ_LOWEDGE,
+ IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
DRV_NAME, encoder);
if (err) {
dev_err(&pdev->dev, "unable to request IRQ %d\n",
#define SYN_EXT_CAP_REQUESTS(c) (((c) & 0x700000) >> 20)
#define SYN_CAP_MULTI_BUTTON_NO(ec) (((ec) & 0x00f000) >> 12)
#define SYN_CAP_PRODUCT_ID(ec) (((ec) & 0xff0000) >> 16)
+
+/*
+ * The following describes response for the 0x0c query.
+ *
+ * byte mask name meaning
+ * ---- ---- ------- ------------
+ * 1 0x01 adjustable threshold capacitive button sensitivity
+ * can be adjusted
+ * 1 0x02 report max query 0x0d gives max coord reported
+ * 1 0x04 clearpad sensor is ClearPad product
+ * 1 0x08 advanced gesture not particularly meaningful
+ * 1 0x10 clickpad bit 0 1-button ClickPad
+ * 1 0x60 multifinger mode identifies firmware finger counting
+ * (not reporting!) algorithm.
+ * Not particularly meaningful
+ * 1 0x80 covered pad W clipped to 14, 15 == pad mostly covered
+ * 2 0x01 clickpad bit 1 2-button ClickPad
+ * 2 0x02 deluxe LED controls touchpad support LED commands
+ * ala multimedia control bar
+ * 2 0x04 reduced filtering firmware does less filtering on
+ * position data, driver should watch
+ * for noise.
+ */
#define SYN_CAP_CLICKPAD(ex0c) ((ex0c) & 0x100000) /* 1-button ClickPad */
#define SYN_CAP_CLICKPAD2BTN(ex0c) ((ex0c) & 0x000100) /* 2-button ClickPad */
#define SYN_CAP_MAX_DIMENSIONS(ex0c) ((ex0c) & 0x020000)
kfree(event);
}
-static void serio_remove_duplicate_events(struct serio_event *event)
+static void serio_remove_duplicate_events(void *object,
+ enum serio_event_type type)
{
struct serio_event *e, *next;
unsigned long flags;
spin_lock_irqsave(&serio_event_lock, flags);
list_for_each_entry_safe(e, next, &serio_event_list, node) {
- if (event->object == e->object) {
+ if (object == e->object) {
/*
* If this event is of different type we should not
* look further - we only suppress duplicate events
* that were sent back-to-back.
*/
- if (event->type != e->type)
+ if (type != e->type)
break;
list_del_init(&e->node);
break;
}
- serio_remove_duplicate_events(event);
+ serio_remove_duplicate_events(event->object, event->type);
serio_free_event(event);
}
event->owner = owner;
list_add_tail(&event->node, &serio_event_list);
- schedule_work(&serio_event_work);
+ queue_work(system_long_wq, &serio_event_work);
out:
spin_unlock_irqrestore(&serio_event_lock, flags);
} else if (!strncmp(buf, "rescan", count)) {
serio_disconnect_port(serio);
serio_find_driver(serio);
+ serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT);
} else if ((drv = driver_find(buf, &serio_bus)) != NULL) {
serio_disconnect_port(serio);
error = serio_bind_driver(serio, to_serio_driver(drv));
put_driver(drv);
+ serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT);
} else {
error = -EINVAL;
}
/* Retrieve the physical and logical size for OEM devices */
error = wacom_retrieve_hid_descriptor(intf, features);
if (error)
- goto fail2;
+ goto fail3;
wacom_setup_device_quirks(features);
struct ads7846_platform_data *pdata = spi->dev.platform_data;
int err;
- /* REVISIT when the irq can be triggered active-low, or if for some
+ /*
+ * REVISIT when the irq can be triggered active-low, or if for some
* reason the touchscreen isn't hooked up, we don't need to access
* the pendown state.
*/
- if (!pdata->get_pendown_state && !gpio_is_valid(pdata->gpio_pendown)) {
- dev_err(&spi->dev, "no get_pendown_state nor gpio_pendown?\n");
- return -EINVAL;
- }
if (pdata->get_pendown_state) {
ts->get_pendown_state = pdata->get_pendown_state;
- return 0;
- }
+ } else if (gpio_is_valid(pdata->gpio_pendown)) {
- err = gpio_request(pdata->gpio_pendown, "ads7846_pendown");
- if (err) {
- dev_err(&spi->dev, "failed to request pendown GPIO%d\n",
- pdata->gpio_pendown);
- return err;
- }
+ err = gpio_request(pdata->gpio_pendown, "ads7846_pendown");
+ if (err) {
+ dev_err(&spi->dev, "failed to request pendown GPIO%d\n",
+ pdata->gpio_pendown);
+ return err;
+ }
- ts->gpio_pendown = pdata->gpio_pendown;
+ ts->gpio_pendown = pdata->gpio_pendown;
+
+ } else {
+ dev_err(&spi->dev, "no get_pendown_state nor gpio_pendown?\n");
+ return -EINVAL;
+ }
return 0;
}
err_put_regulator:
regulator_put(ts->reg);
err_free_gpio:
- if (ts->gpio_pendown != -1)
+ if (!ts->get_pendown_state)
gpio_free(ts->gpio_pendown);
err_cleanup_filter:
if (ts->filter_cleanup)
regulator_disable(ts->reg);
regulator_put(ts->reg);
- if (ts->gpio_pendown != -1)
+ if (!ts->get_pendown_state) {
+ /*
+ * If we are not using specialized pendown method we must
+ * have been relying on gpio we set up ourselves.
+ */
gpio_free(ts->gpio_pendown);
+ }
if (ts->filter_cleanup)
ts->filter_cleanup(ts->filter_data);
#define W8001_PKTLEN_TPCCTL 11 /* control packet */
#define W8001_PKTLEN_TOUCH2FG 13
+/* resolution in points/mm */
+#define W8001_PEN_RESOLUTION 100
+#define W8001_TOUCH_RESOLUTION 10
+
struct w8001_coord {
u8 rdy;
u8 tsw;
query->y = 1024;
if (query->panel_res)
query->x = query->y = (1 << query->panel_res);
- query->panel_res = 10;
+ query->panel_res = W8001_TOUCH_RESOLUTION;
}
}
input_set_abs_params(dev, ABS_X, 0, coord.x, 0, 0);
input_set_abs_params(dev, ABS_Y, 0, coord.y, 0, 0);
+ input_abs_set_res(dev, ABS_X, W8001_PEN_RESOLUTION);
+ input_abs_set_res(dev, ABS_Y, W8001_PEN_RESOLUTION);
input_set_abs_params(dev, ABS_PRESSURE, 0, coord.pen_pressure, 0, 0);
if (coord.tilt_x && coord.tilt_y) {
input_set_abs_params(dev, ABS_TILT_X, 0, coord.tilt_x, 0, 0);
w8001->max_touch_x = touch.x;
w8001->max_touch_y = touch.y;
- /* scale to pen maximum */
if (w8001->max_pen_x && w8001->max_pen_y) {
+ /* if pen is supported scale to pen maximum */
touch.x = w8001->max_pen_x;
touch.y = w8001->max_pen_y;
+ touch.panel_res = W8001_PEN_RESOLUTION;
}
input_set_abs_params(dev, ABS_X, 0, touch.x, 0, 0);
input_set_abs_params(dev, ABS_Y, 0, touch.y, 0, 0);
+ input_abs_set_res(dev, ABS_X, touch.panel_res);
+ input_abs_set_res(dev, ABS_Y, touch.panel_res);
switch (touch.sensor_id) {
case 0:
stream interface.
If synchronous service was requested, then function
does return amount of data written to stream.
- 'final' does indicate that pice of data to be written is
+ 'final' does indicate that piece of data to be written is
final part of frame (necessary only by structured datatransfer)
return 0 if zero lengh packet was written
return -1 if stream is full
l2_pull_iqueue(struct FsmInst *fi, int event, void *arg)
{
struct PStack *st = fi->userdata;
- struct sk_buff *skb, *oskb;
+ struct sk_buff *skb;
struct Layer2 *l2 = &st->l2;
u_char header[MAX_HEADER_LEN];
- int i;
+ int i, hdr_space_needed;
int unsigned p1;
u_long flags;
if (!skb)
return;
+ hdr_space_needed = l2headersize(l2, 0);
+ if (hdr_space_needed > skb_headroom(skb)) {
+ struct sk_buff *orig_skb = skb;
+
+ skb = skb_realloc_headroom(skb, hdr_space_needed);
+ if (!skb) {
+ dev_kfree_skb(orig_skb);
+ return;
+ }
+ }
spin_lock_irqsave(&l2->lock, flags);
if(test_bit(FLG_MOD128, &l2->flag))
p1 = (l2->vs - l2->va) % 128;
l2->vs = (l2->vs + 1) % 8;
}
spin_unlock_irqrestore(&l2->lock, flags);
- p1 = skb->data - skb->head;
- if (p1 >= i)
- memcpy(skb_push(skb, i), header, i);
- else {
- printk(KERN_WARNING
- "isdl2 pull_iqueue skb header(%d/%d) too short\n", i, p1);
- oskb = skb;
- skb = alloc_skb(oskb->len + i, GFP_ATOMIC);
- memcpy(skb_put(skb, i), header, i);
- skb_copy_from_linear_data(oskb,
- skb_put(skb, oskb->len), oskb->len);
- dev_kfree_skb(oskb);
- }
+ memcpy(skb_push(skb, i), header, i);
st->l2.l2l1(st, PH_PULL | INDICATION, skb);
test_and_clear_bit(FLG_ACK_PEND, &st->l2.flag);
if (!test_and_set_bit(FLG_T200_RUN, &st->l2.flag)) {
/*************************/
/* im/exported functions */
/*************************/
-extern char *hysdn_getrev(const char *);
/* hysdn_procconf.c */
extern int hysdn_procconf_init(void); /* init proc config filesys */
/* hysdn_net.c */
extern unsigned int hynet_enable;
-extern char *hysdn_net_revision;
extern int hysdn_net_create(hysdn_card *); /* create a new net device */
extern int hysdn_net_release(hysdn_card *); /* delete the device */
extern char *hysdn_net_getname(hysdn_card *); /* get name of net interface */
MODULE_AUTHOR("Werner Cornelius");
MODULE_LICENSE("GPL");
-static char *hysdn_init_revision = "$Revision: 1.6.6.6 $";
static int cardmax; /* number of found cards */
hysdn_card *card_root = NULL; /* pointer to first card */
static hysdn_card *card_last = NULL; /* pointer to first card */
/* Additionally newer versions may be activated without rebooting. */
/****************************************************************************/
-/******************************************************/
-/* extract revision number from string for log output */
-/******************************************************/
-char *
-hysdn_getrev(const char *revision)
-{
- char *rev;
- char *p;
-
- if ((p = strchr(revision, ':'))) {
- rev = p + 2;
- p = strchr(rev, '$');
- *--p = 0;
- } else
- rev = "???";
- return rev;
-}
-
-
/****************************************************************************/
/* init_module is called once when the module is loaded to do all necessary */
/* things like autodetect... */
static int __init
hysdn_init(void)
{
- char tmp[50];
int rc;
- strcpy(tmp, hysdn_init_revision);
- printk(KERN_NOTICE "HYSDN: module Rev: %s loaded\n", hysdn_getrev(tmp));
- strcpy(tmp, hysdn_net_revision);
- printk(KERN_NOTICE "HYSDN: network interface Rev: %s \n", hysdn_getrev(tmp));
+ printk(KERN_NOTICE "HYSDN: module loaded\n");
rc = pci_register_driver(&hysdn_pci_driver);
if (rc)
unsigned int hynet_enable = 0xffffffff;
module_param(hynet_enable, uint, 0);
-/* store the actual version for log reporting */
-char *hysdn_net_revision = "$Revision: 1.8.6.4 $";
-
#define MAX_SKB_BUFFERS 20 /* number of buffers for keeping TX-data */
/****************************************************************************/
#include "hysdn_defs.h"
static DEFINE_MUTEX(hysdn_conf_mutex);
-static char *hysdn_procconf_revision = "$Revision: 1.8.6.4 $";
#define INFO_OUT_LEN 80 /* length of info line including lf */
card = card->next; /* next entry */
}
- printk(KERN_NOTICE "HYSDN: procfs Rev. %s initialised\n", hysdn_getrev(hysdn_procconf_revision));
+ printk(KERN_NOTICE "HYSDN: procfs initialised\n");
return (0);
} /* hysdn_procconf_init */
if (md_check_no_bitmap(mddev))
return -EINVAL;
- mddev->queue->queue_lock = &mddev->queue->__queue_lock;
conf = linear_conf(mddev, mddev->raid_disks);
if (!conf)
mddev_t *mddev = q->queuedata;
int rv;
int cpu;
+ unsigned int sectors;
if (mddev == NULL || mddev->pers == NULL
|| !mddev->ready) {
atomic_inc(&mddev->active_io);
rcu_read_unlock();
+ /*
+ * save the sectors now since our bio can
+ * go away inside make_request
+ */
+ sectors = bio_sectors(bio);
rv = mddev->pers->make_request(mddev, bio);
cpu = part_stat_lock();
part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
- part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
- bio_sectors(bio));
+ part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
part_stat_unlock();
if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
{
mddev_t *mddev, *new = NULL;
+ if (unit && MAJOR(unit) != MD_MAJOR)
+ unit &= ~((1<<MdpMinorShift)-1);
+
retry:
spin_lock(&all_mddevs_lock);
__bdevname(dev, b));
return PTR_ERR(bdev);
}
- if (!shared)
- set_bit(AllReserved, &rdev->flags);
rdev->bdev = bdev;
return err;
}
if (rdev->raid_disk != -1)
return -EBUSY;
+ if (test_bit(MD_RECOVERY_RUNNING, &rdev->mddev->recovery))
+ return -EBUSY;
+
if (rdev->mddev->pers->hot_add_disk == NULL)
return -EINVAL;
mddev_lock(mddev);
list_for_each_entry(rdev2, &mddev->disks, same_set)
- if (test_bit(AllReserved, &rdev2->flags) ||
- (rdev->bdev == rdev2->bdev &&
- rdev != rdev2 &&
- overlaps(rdev->data_offset, rdev->sectors,
- rdev2->data_offset,
- rdev2->sectors))) {
+ if (rdev->bdev == rdev2->bdev &&
+ rdev != rdev2 &&
+ overlaps(rdev->data_offset, rdev->sectors,
+ rdev2->data_offset,
+ rdev2->sectors)) {
overlap = 1;
break;
}
}
mddev->array_sectors = sectors;
- set_capacity(mddev->gendisk, mddev->array_sectors);
- if (mddev->pers)
+ if (mddev->pers) {
+ set_capacity(mddev->gendisk, mddev->array_sectors);
revalidate_disk(mddev->gendisk);
-
+ }
return len;
}
}
set_capacity(mddev->gendisk, mddev->array_sectors);
revalidate_disk(mddev->gendisk);
+ mddev->changed = 1;
kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
out:
return err;
mddev->sync_speed_min = mddev->sync_speed_max = 0;
mddev->recovery = 0;
mddev->in_sync = 0;
+ mddev->changed = 0;
mddev->degraded = 0;
mddev->safemode = 0;
mddev->bitmap_info.offset = 0;
set_capacity(disk, 0);
mutex_unlock(&mddev->open_mutex);
+ mddev->changed = 1;
revalidate_disk(disk);
if (mddev->ro)
mddev->delta_disks = raid_disks - mddev->raid_disks;
rv = mddev->pers->check_reshape(mddev);
+ if (rv < 0)
+ mddev->delta_disks = 0;
return rv;
}
atomic_inc(&mddev->openers);
mutex_unlock(&mddev->open_mutex);
- check_disk_size_change(mddev->gendisk, bdev);
+ check_disk_change(bdev);
out:
return err;
}
return 0;
}
+
+static int md_media_changed(struct gendisk *disk)
+{
+ mddev_t *mddev = disk->private_data;
+
+ return mddev->changed;
+}
+
+static int md_revalidate(struct gendisk *disk)
+{
+ mddev_t *mddev = disk->private_data;
+
+ mddev->changed = 0;
+ return 0;
+}
static const struct block_device_operations md_fops =
{
.owner = THIS_MODULE,
.compat_ioctl = md_compat_ioctl,
#endif
.getgeo = md_getgeo,
+ .media_changed = md_media_changed,
+ .revalidate_disk= md_revalidate,
};
static int md_thread(void * arg)
} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
mddev->resync_min = mddev->curr_resync_completed;
mddev->curr_resync = 0;
- if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
- mddev->curr_resync_completed = 0;
- sysfs_notify(&mddev->kobj, NULL, "sync_completed");
wake_up(&resync_wait);
set_bit(MD_RECOVERY_DONE, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
}
- if (mddev->degraded && ! mddev->ro && !mddev->recovery_disabled) {
+ if (mddev->degraded && !mddev->recovery_disabled) {
list_for_each_entry(rdev, &mddev->disks, same_set) {
if (rdev->raid_disk >= 0 &&
!test_bit(In_sync, &rdev->flags) &&
/* Only thing we do on a ro array is remove
* failed devices.
*/
- remove_and_add_spares(mddev);
+ mdk_rdev_t *rdev;
+ list_for_each_entry(rdev, &mddev->disks, same_set)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Blocked, &rdev->flags) &&
+ test_bit(Faulty, &rdev->flags) &&
+ atomic_read(&rdev->nr_pending)==0) {
+ if (mddev->pers->hot_remove_disk(
+ mddev, rdev->raid_disk)==0) {
+ char nm[20];
+ sprintf(nm,"rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ rdev->raid_disk = -1;
+ }
+ }
clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
goto unlock;
}
#define Faulty 1 /* device is known to have a fault */
#define In_sync 2 /* device is in_sync with rest of array */
#define WriteMostly 4 /* Avoid reading if at all possible */
-#define AllReserved 6 /* If whole device is reserved for
- * one array */
#define AutoDetected 7 /* added by auto-detect */
#define Blocked 8 /* An error occured on an externally
* managed array, don't allow writes
atomic_t active; /* general refcount */
atomic_t openers; /* number of active opens */
+ int changed; /* True if we might need to
+ * reread partition info */
int degraded; /* whether md should consider
* adding a spare
*/
* bookkeeping area. [whatever we allocate in multipath_run(),
* should be freed in multipath_stop()]
*/
- mddev->queue->queue_lock = &mddev->queue->__queue_lock;
conf = kzalloc(sizeof(multipath_conf_t), GFP_KERNEL);
mddev->private = conf;
rdev1->new_raid_disk = j;
}
+ if (mddev->level == 1) {
+ /* taiking over a raid1 array-
+ * we have only one active disk
+ */
+ j = 0;
+ rdev1->new_raid_disk = j;
+ }
+
if (j < 0 || j >= mddev->raid_disks) {
printk(KERN_ERR "md/raid0:%s: bad disk number %d - "
"aborting!\n", mdname(mddev), j);
if (md_check_no_bitmap(mddev))
return -EINVAL;
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
- mddev->queue->queue_lock = &mddev->queue->__queue_lock;
/* if private is not null, we are here after takeover */
if (mddev->private == NULL) {
return priv_conf;
}
+static void *raid0_takeover_raid1(mddev_t *mddev)
+{
+ raid0_conf_t *priv_conf;
+
+ /* Check layout:
+ * - (N - 1) mirror drives must be already faulty
+ */
+ if ((mddev->raid_disks - 1) != mddev->degraded) {
+ printk(KERN_ERR "md/raid0:%s: (N - 1) mirrors drives must be already faulty!\n",
+ mdname(mddev));
+ return ERR_PTR(-EINVAL);
+ }
+
+ /* Set new parameters */
+ mddev->new_level = 0;
+ mddev->new_layout = 0;
+ mddev->new_chunk_sectors = 128; /* by default set chunk size to 64k */
+ mddev->delta_disks = 1 - mddev->raid_disks;
+ mddev->raid_disks = 1;
+ /* make sure it will be not marked as dirty */
+ mddev->recovery_cp = MaxSector;
+
+ create_strip_zones(mddev, &priv_conf);
+ return priv_conf;
+}
+
static void *raid0_takeover(mddev_t *mddev)
{
/* raid0 can take over:
* raid4 - if all data disks are active.
* raid5 - providing it is Raid4 layout and one disk is faulty
* raid10 - assuming we have all necessary active disks
+ * raid1 - with (N -1) mirror drives faulty
*/
if (mddev->level == 4)
return raid0_takeover_raid45(mddev);
if (mddev->level == 10)
return raid0_takeover_raid10(mddev);
+ if (mddev->level == 1)
+ return raid0_takeover_raid1(mddev);
+
+ printk(KERN_ERR "Takeover from raid%i to raid0 not supported\n",
+ mddev->level);
+
return ERR_PTR(-EINVAL);
}
if (conf->pending_bio_list.head) {
struct bio *bio;
bio = bio_list_get(&conf->pending_bio_list);
+ /* Only take the spinlock to quiet a warning */
+ spin_lock(conf->mddev->queue->queue_lock);
blk_remove_plug(conf->mddev->queue);
+ spin_unlock(conf->mddev->queue->queue_lock);
spin_unlock_irq(&conf->device_lock);
/* flush any pending bitmap writes to
* disk before proceeding w/ I/O */
atomic_inc(&r1_bio->remaining);
spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
- blk_plug_device(mddev->queue);
+ blk_plug_device_unlocked(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
r1_bio_write_done(r1_bio, bio->bi_vcnt, behind_pages, behind_pages != NULL);
if (IS_ERR(conf))
return PTR_ERR(conf);
- mddev->queue->queue_lock = &conf->device_lock;
list_for_each_entry(rdev, &mddev->disks, same_set) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
if (conf->pending_bio_list.head) {
struct bio *bio;
bio = bio_list_get(&conf->pending_bio_list);
+ /* Spinlock only taken to quiet a warning */
+ spin_lock(conf->mddev->queue->queue_lock);
blk_remove_plug(conf->mddev->queue);
+ spin_unlock(conf->mddev->queue->queue_lock);
spin_unlock_irq(&conf->device_lock);
/* flush any pending bitmap writes to disk
* before proceeding w/ I/O */
atomic_inc(&r10_bio->remaining);
spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
- blk_plug_device(mddev->queue);
+ blk_plug_device_unlocked(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
if (!conf)
goto out;
- mddev->queue->queue_lock = &conf->device_lock;
-
mddev->thread = conf->thread;
conf->thread = NULL;
mddev->recovery_cp = MaxSector;
conf = setup_conf(mddev);
- if (!IS_ERR(conf))
+ if (!IS_ERR(conf)) {
list_for_each_entry(rdev, &mddev->disks, same_set)
if (rdev->raid_disk >= 0)
rdev->new_raid_disk = rdev->raid_disk * 2;
-
+ conf->barrier = 1;
+ }
+
return conf;
}
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = raid5_congested;
- mddev->queue->queue_lock = &conf->device_lock;
mddev->queue->unplug_fn = raid5_unplug_queue;
chunk_size = mddev->chunk_sectors << 9;
raid5_conf_t *conf = mddev->private;
mdk_rdev_t *rdev;
int spares = 0;
- int added_devices = 0;
unsigned long flags;
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -ENOSPC;
list_for_each_entry(rdev, &mddev->disks, same_set)
- if ((rdev->raid_disk < 0 || rdev->raid_disk >= conf->raid_disks)
- && !test_bit(Faulty, &rdev->flags))
+ if (!test_bit(In_sync, &rdev->flags)
+ && !test_bit(Faulty, &rdev->flags))
spares++;
if (spares - mddev->degraded < mddev->delta_disks - conf->max_degraded)
* to correctly record the "partially reconstructed" state of
* such devices during the reshape and confusion could result.
*/
- if (mddev->delta_disks >= 0)
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (rdev->raid_disk < 0 &&
- !test_bit(Faulty, &rdev->flags)) {
- if (raid5_add_disk(mddev, rdev) == 0) {
- char nm[20];
- if (rdev->raid_disk >= conf->previous_raid_disks) {
- set_bit(In_sync, &rdev->flags);
- added_devices++;
- } else
- rdev->recovery_offset = 0;
- sprintf(nm, "rd%d", rdev->raid_disk);
- if (sysfs_create_link(&mddev->kobj,
- &rdev->kobj, nm))
- /* Failure here is OK */;
- } else
- break;
- } else if (rdev->raid_disk >= conf->previous_raid_disks
- && !test_bit(Faulty, &rdev->flags)) {
- /* This is a spare that was manually added */
- set_bit(In_sync, &rdev->flags);
- added_devices++;
- }
+ if (mddev->delta_disks >= 0) {
+ int added_devices = 0;
+ list_for_each_entry(rdev, &mddev->disks, same_set)
+ if (rdev->raid_disk < 0 &&
+ !test_bit(Faulty, &rdev->flags)) {
+ if (raid5_add_disk(mddev, rdev) == 0) {
+ char nm[20];
+ if (rdev->raid_disk
+ >= conf->previous_raid_disks) {
+ set_bit(In_sync, &rdev->flags);
+ added_devices++;
+ } else
+ rdev->recovery_offset = 0;
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ if (sysfs_create_link(&mddev->kobj,
+ &rdev->kobj, nm))
+ /* Failure here is OK */;
+ }
+ } else if (rdev->raid_disk >= conf->previous_raid_disks
+ && !test_bit(Faulty, &rdev->flags)) {
+ /* This is a spare that was manually added */
+ set_bit(In_sync, &rdev->flags);
+ added_devices++;
+ }
- /* When a reshape changes the number of devices, ->degraded
- * is measured against the larger of the pre and post number of
- * devices.*/
- if (mddev->delta_disks > 0) {
+ /* When a reshape changes the number of devices,
+ * ->degraded is measured against the larger of the
+ * pre and post number of devices.
+ */
spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded += (conf->raid_disks - conf->previous_raid_disks)
- added_devices;
#define TDA8290_ID 0x89
u8 reg = 0x1f, id;
struct i2c_msg msg_read[] = {
- { .addr = 0x4b, .flags = 0, .len = 1, .buf = ® },
- { .addr = 0x4b, .flags = I2C_M_RD, .len = 1, .buf = &id },
+ { .addr = i2c_props->addr, .flags = 0, .len = 1, .buf = ® },
+ { .addr = i2c_props->addr, .flags = I2C_M_RD, .len = 1, .buf = &id },
};
/* detect tda8290 */
if (i2c_transfer(i2c_props->adap, msg_read, 2) != 2) {
- printk(KERN_WARNING "%s: tda8290 couldn't read register 0x%02x\n",
+ printk(KERN_WARNING "%s: couldn't read register 0x%02x\n",
__func__, reg);
return -ENODEV;
}
#define TDA8295C2_ID 0x8b
u8 reg = 0x2f, id;
struct i2c_msg msg_read[] = {
- { .addr = 0x4b, .flags = 0, .len = 1, .buf = ® },
- { .addr = 0x4b, .flags = I2C_M_RD, .len = 1, .buf = &id },
+ { .addr = i2c_props->addr, .flags = 0, .len = 1, .buf = ® },
+ { .addr = i2c_props->addr, .flags = I2C_M_RD, .len = 1, .buf = &id },
};
- /* detect tda8290 */
+ /* detect tda8295 */
if (i2c_transfer(i2c_props->adap, msg_read, 2) != 2) {
- printk(KERN_WARNING "%s: tda8290 couldn't read register 0x%02x\n",
+ printk(KERN_WARNING "%s: couldn't read register 0x%02x\n",
__func__, reg);
return -ENODEV;
}
return 0;
}
+static int stk7700p_pid_filter(struct dvb_usb_adapter *adapter, int index,
+ u16 pid, int onoff)
+{
+ struct dib0700_state *st = adapter->dev->priv;
+ if (st->is_dib7000pc)
+ return dib7000p_pid_filter(adapter->fe, index, pid, onoff);
+ return dib7000m_pid_filter(adapter->fe, index, pid, onoff);
+}
+
+static int stk7700p_pid_filter_ctrl(struct dvb_usb_adapter *adapter, int onoff)
+{
+ struct dib0700_state *st = adapter->dev->priv;
+ if (st->is_dib7000pc)
+ return dib7000p_pid_filter_ctrl(adapter->fe, onoff);
+ return dib7000m_pid_filter_ctrl(adapter->fe, onoff);
+}
+
static int stk70x0p_pid_filter(struct dvb_usb_adapter *adapter, int index, u16 pid, int onoff)
{
return dib7000p_pid_filter(adapter->fe, index, pid, onoff);
{
.caps = DVB_USB_ADAP_HAS_PID_FILTER | DVB_USB_ADAP_PID_FILTER_CAN_BE_TURNED_OFF,
.pid_filter_count = 32,
- .pid_filter = stk70x0p_pid_filter,
- .pid_filter_ctrl = stk70x0p_pid_filter_ctrl,
+ .pid_filter = stk7700p_pid_filter,
+ .pid_filter_ctrl = stk7700p_pid_filter_ctrl,
.frontend_attach = stk7700p_frontend_attach,
.tuner_attach = stk7700p_tuner_attach,
}
/* Default firmware for LME2510C */
-const char lme_firmware[50] = "dvb-usb-lme2510c-s7395.fw";
+char lme_firmware[50] = "dvb-usb-lme2510c-s7395.fw";
static void lme_coldreset(struct usb_device *dev)
{
.caps = DVB_USB_IS_AN_I2C_ADAPTER,
.usb_ctrl = DEVICE_SPECIFIC,
.download_firmware = lme2510_download_firmware,
- .firmware = lme_firmware,
+ .firmware = (const char *)&lme_firmware,
.size_of_priv = sizeof(struct lme2510_state),
.num_adapters = 1,
.adapter = {
MODULE_AUTHOR("Malcolm Priestley <tvboxspy@gmail.com>");
MODULE_DESCRIPTION("LME2510(C) DVB-S USB2.0");
-MODULE_VERSION("1.74");
+MODULE_VERSION("1.75");
MODULE_LICENSE("GPL");
}
EXPORT_SYMBOL(dib7000m_get_i2c_master);
+int dib7000m_pid_filter_ctrl(struct dvb_frontend *fe, u8 onoff)
+{
+ struct dib7000m_state *state = fe->demodulator_priv;
+ u16 val = dib7000m_read_word(state, 294 + state->reg_offs) & 0xffef;
+ val |= (onoff & 0x1) << 4;
+ dprintk("PID filter enabled %d", onoff);
+ return dib7000m_write_word(state, 294 + state->reg_offs, val);
+}
+EXPORT_SYMBOL(dib7000m_pid_filter_ctrl);
+
+int dib7000m_pid_filter(struct dvb_frontend *fe, u8 id, u16 pid, u8 onoff)
+{
+ struct dib7000m_state *state = fe->demodulator_priv;
+ dprintk("PID filter: index %x, PID %d, OnOff %d", id, pid, onoff);
+ return dib7000m_write_word(state, 300 + state->reg_offs + id,
+ onoff ? (1 << 13) | pid : 0);
+}
+EXPORT_SYMBOL(dib7000m_pid_filter);
+
#if 0
/* used with some prototype boards */
int dib7000m_i2c_enumeration(struct i2c_adapter *i2c, int no_of_demods,
extern struct i2c_adapter *dib7000m_get_i2c_master(struct dvb_frontend *,
enum dibx000_i2c_interface,
int);
+extern int dib7000m_pid_filter(struct dvb_frontend *, u8 id, u16 pid, u8 onoff);
+extern int dib7000m_pid_filter_ctrl(struct dvb_frontend *fe, u8 onoff);
#else
static inline
struct dvb_frontend *dib7000m_attach(struct i2c_adapter *i2c_adap,
printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
return NULL;
}
+static inline int dib7000m_pid_filter(struct dvb_frontend *fe, u8 id,
+ u16 pid, u8 onoff)
+{
+ printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
+ return -ENODEV;
+}
+
+static inline int dib7000m_pid_filter_ctrl(struct dvb_frontend *fe,
+ uint8_t onoff)
+{
+ printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
+ return -ENODEV;
+}
#endif
/* TODO
#include <linux/moduleparam.h>
#include <linux/kernel.h>
#include <asm/io.h>
-#include <asm/pgtable.h>
#include <asm/page.h>
#include <linux/kmod.h>
#include <linux/vmalloc.h>
{
ktime_t now;
s64 delta; /* ns */
- struct ir_raw_event ev;
+ DEFINE_IR_RAW_EVENT(ev);
int rc = 0;
if (!dev->raw)
* being called for the first time, note that delta can't
* possibly be negative.
*/
- ev.duration = 0;
if (delta > IR_MAX_DURATION || !dev->raw->last_type)
type |= IR_START_EVENT;
else
MCE_GEN2_TX_INV,
POLARIS_EVK,
CX_HYBRID_TV,
+ MULTIFUNCTION,
};
struct mceusb_model {
u32 mce_gen2:1;
u32 mce_gen3:1;
u32 tx_mask_normal:1;
- u32 is_polaris:1;
u32 no_tx:1;
+ int ir_intfnum;
+
const char *rc_map; /* Allow specify a per-board map */
const char *name; /* per-board name */
};
.tx_mask_normal = 1,
},
[POLARIS_EVK] = {
- .is_polaris = 1,
/*
* In fact, the EVK is shipped without
* remotes, but we should have something handy,
.name = "Conexant Hybrid TV (cx231xx) MCE IR",
},
[CX_HYBRID_TV] = {
- .is_polaris = 1,
.no_tx = 1, /* tx isn't wired up at all */
.name = "Conexant Hybrid TV (cx231xx) MCE IR",
},
+ [MULTIFUNCTION] = {
+ .mce_gen2 = 1,
+ .ir_intfnum = 2,
+ },
};
static struct usb_device_id mceusb_dev_table[] = {
{ USB_DEVICE(VENDOR_PHILIPS, 0x206c) },
/* Philips/Spinel plus IR transceiver for ASUS */
{ USB_DEVICE(VENDOR_PHILIPS, 0x2088) },
- /* Realtek MCE IR Receiver */
- { USB_DEVICE(VENDOR_REALTEK, 0x0161) },
+ /* Realtek MCE IR Receiver and card reader */
+ { USB_DEVICE(VENDOR_REALTEK, 0x0161),
+ .driver_info = MULTIFUNCTION },
/* SMK/Toshiba G83C0004D410 */
{ USB_DEVICE(VENDOR_SMK, 0x031d),
.driver_info = MCE_GEN2_TX_INV },
bool is_gen3;
bool is_microsoft_gen1;
bool tx_mask_normal;
- bool is_polaris;
+ int ir_intfnum;
dev_dbg(&intf->dev, "%s called\n", __func__);
is_gen3 = mceusb_model[model].mce_gen3;
is_microsoft_gen1 = mceusb_model[model].mce_gen1;
tx_mask_normal = mceusb_model[model].tx_mask_normal;
- is_polaris = mceusb_model[model].is_polaris;
+ ir_intfnum = mceusb_model[model].ir_intfnum;
- if (is_polaris) {
- /* Interface 0 is IR */
- if (idesc->desc.bInterfaceNumber)
- return -ENODEV;
- }
+ /* There are multi-function devices with non-IR interfaces */
+ if (idesc->desc.bInterfaceNumber != ir_intfnum)
+ return -ENODEV;
/* step through the endpoints to find first bulk in and out endpoint */
for (i = 0; i < idesc->desc.bNumEndpoints; ++i) {
static void nvt_cir_wake_regs_init(struct nvt_dev *nvt)
{
- /* set number of bytes needed for wake key comparison (default 67) */
- nvt_cir_wake_reg_write(nvt, CIR_WAKE_FIFO_LEN, CIR_WAKE_FIFO_CMP_DEEP);
+ /* set number of bytes needed for wake from s3 (default 65) */
+ nvt_cir_wake_reg_write(nvt, CIR_WAKE_FIFO_CMP_BYTES,
+ CIR_WAKE_FIFO_CMP_DEEP);
/* set tolerance/variance allowed per byte during wake compare */
nvt_cir_wake_reg_write(nvt, CIR_WAKE_CMP_TOLERANCE,
#define CIR_WAKE_IRFIFOSTS_RX_EMPTY 0x20
#define CIR_WAKE_IRFIFOSTS_RX_FULL 0x10
-/* CIR Wake FIFO buffer is 67 bytes long */
-#define CIR_WAKE_FIFO_LEN 67
+/*
+ * The CIR Wake FIFO buffer is 67 bytes long, but the stock remote wakes
+ * the system comparing only 65 bytes (fails with this set to 67)
+ */
+#define CIR_WAKE_FIFO_CMP_BYTES 65
/* CIR Wake byte comparison tolerance */
#define CIR_WAKE_CMP_TOLERANCE 5
count++;
} else {
for (i = 0; i < ARRAY_SIZE(proto_names); i++) {
- if (!strncasecmp(tmp, proto_names[i].name, strlen(proto_names[i].name))) {
+ if (!strcasecmp(tmp, proto_names[i].name)) {
tmp += strlen(proto_names[i].name);
mask = proto_names[i].type;
break;
if (rc < 0)
return rc;
- return videobuf_reqbufs(&fh->vb_vidq, rb);
+ if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+ rc = videobuf_reqbufs(&fh->vb_vidq, rb);
+ else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE)
+ rc = videobuf_reqbufs(&fh->vb_vbiq, rb);
+
+ return rc;
}
static int vidioc_querybuf(struct file *file, void *priv,
if (rc < 0)
return rc;
- return videobuf_querybuf(&fh->vb_vidq, b);
+ if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+ rc = videobuf_querybuf(&fh->vb_vidq, b);
+ else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE)
+ rc = videobuf_querybuf(&fh->vb_vbiq, b);
+
+ return rc;
}
static int vidioc_qbuf(struct file *file, void *priv, struct v4l2_buffer *b)
if (rc < 0)
return rc;
- return videobuf_qbuf(&fh->vb_vidq, b);
+ if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+ rc = videobuf_qbuf(&fh->vb_vidq, b);
+ else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE)
+ rc = videobuf_qbuf(&fh->vb_vbiq, b);
+
+ return rc;
}
static int vidioc_dqbuf(struct file *file, void *priv, struct v4l2_buffer *b)
dev->greenscreen_detected = 0;
}
- return videobuf_dqbuf(&fh->vb_vidq, b, file->f_flags & O_NONBLOCK);
+ if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+ rc = videobuf_dqbuf(&fh->vb_vidq, b, file->f_flags & O_NONBLOCK);
+ else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE)
+ rc = videobuf_dqbuf(&fh->vb_vbiq, b, file->f_flags & O_NONBLOCK);
+
+ return rc;
}
static struct v4l2_file_operations au0828_v4l_fops = {
.i2c = &cx18_i2c_std,
};
+static const struct cx18_card cx18_card_hvr1600_s5h1411 = {
+ .type = CX18_CARD_HVR_1600_S5H1411,
+ .name = "Hauppauge HVR-1600",
+ .comment = "Simultaneous Digital and Analog TV capture supported\n",
+ .v4l2_capabilities = CX18_CAP_ENCODER,
+ .hw_audio_ctrl = CX18_HW_418_AV,
+ .hw_muxer = CX18_HW_CS5345,
+ .hw_all = CX18_HW_TVEEPROM | CX18_HW_418_AV | CX18_HW_TUNER |
+ CX18_HW_CS5345 | CX18_HW_DVB | CX18_HW_GPIO_RESET_CTRL |
+ CX18_HW_Z8F0811_IR_HAUP,
+ .video_inputs = {
+ { CX18_CARD_INPUT_VID_TUNER, 0, CX18_AV_COMPOSITE7 },
+ { CX18_CARD_INPUT_SVIDEO1, 1, CX18_AV_SVIDEO1 },
+ { CX18_CARD_INPUT_COMPOSITE1, 1, CX18_AV_COMPOSITE3 },
+ { CX18_CARD_INPUT_SVIDEO2, 2, CX18_AV_SVIDEO2 },
+ { CX18_CARD_INPUT_COMPOSITE2, 2, CX18_AV_COMPOSITE4 },
+ },
+ .audio_inputs = {
+ { CX18_CARD_INPUT_AUD_TUNER,
+ CX18_AV_AUDIO8, CS5345_IN_1 | CS5345_MCLK_1_5 },
+ { CX18_CARD_INPUT_LINE_IN1,
+ CX18_AV_AUDIO_SERIAL1, CS5345_IN_2 },
+ { CX18_CARD_INPUT_LINE_IN2,
+ CX18_AV_AUDIO_SERIAL1, CS5345_IN_3 },
+ },
+ .radio_input = { CX18_CARD_INPUT_AUD_TUNER,
+ CX18_AV_AUDIO_SERIAL1, CS5345_IN_4 },
+ .ddr = {
+ /* ESMT M13S128324A-5B memory */
+ .chip_config = 0x003,
+ .refresh = 0x30c,
+ .timing1 = 0x44220e82,
+ .timing2 = 0x08,
+ .tune_lane = 0,
+ .initial_emrs = 0,
+ },
+ .gpio_init.initial_value = 0x3001,
+ .gpio_init.direction = 0x3001,
+ .gpio_i2c_slave_reset = {
+ .active_lo_mask = 0x3001,
+ .msecs_asserted = 10,
+ .msecs_recovery = 40,
+ .ir_reset_mask = 0x0001,
+ },
+ .i2c = &cx18_i2c_std,
+};
+
static const struct cx18_card cx18_card_hvr1600_samsung = {
.type = CX18_CARD_HVR_1600_SAMSUNG,
.name = "Hauppauge HVR-1600 (Preproduction)",
&cx18_card_toshiba_qosmio_dvbt,
&cx18_card_leadtek_pvr2100,
&cx18_card_leadtek_dvr3100h,
- &cx18_card_gotview_dvd3
+ &cx18_card_gotview_dvd3,
+ &cx18_card_hvr1600_s5h1411
};
const struct cx18_card *cx18_get_card(u16 index)
"\t\t\t 7 = Leadtek WinFast PVR2100\n"
"\t\t\t 8 = Leadtek WinFast DVR3100 H\n"
"\t\t\t 9 = GoTView PCI DVD3 Hybrid\n"
+ "\t\t\t 10 = Hauppauge HVR 1600 (S5H1411)\n"
"\t\t\t 0 = Autodetect (default)\n"
"\t\t\t-1 = Ignore this card\n\t\t");
MODULE_PARM_DESC(pal, "Set PAL standard: B, G, H, D, K, I, M, N, Nc, 60");
switch (cx->card->type) {
case CX18_CARD_HVR_1600_ESMT:
case CX18_CARD_HVR_1600_SAMSUNG:
+ case CX18_CARD_HVR_1600_S5H1411:
tveeprom_hauppauge_analog(&c, tv, eedata);
break;
case CX18_CARD_YUAN_MPC718:
from the model number. Use the cardtype module option if you
have one of these preproduction models. */
switch (tv.model) {
- case 74000 ... 74999:
+ case 74301: /* Retail models */
+ case 74321:
+ case 74351: /* OEM models */
+ case 74361:
+ /* Digital side is s5h1411/tda18271 */
+ cx->card = cx18_get_card(CX18_CARD_HVR_1600_S5H1411);
+ break;
+ case 74021: /* Retail models */
+ case 74031:
+ case 74041:
+ case 74141:
+ case 74541: /* OEM models */
+ case 74551:
+ case 74591:
+ case 74651:
+ case 74691:
+ case 74751:
+ case 74891:
+ /* Digital side is s5h1409/mxl5005s */
cx->card = cx18_get_card(CX18_CARD_HVR_1600_ESMT);
break;
case 0x718:
CX18_ERR("Invalid EEPROM\n");
return;
default:
- CX18_ERR("Unknown model %d, defaulting to HVR-1600\n", tv.model);
+ CX18_ERR("Unknown model %d, defaulting to original HVR-1600 "
+ "(cardtype=1)\n", tv.model);
cx->card = cx18_get_card(CX18_CARD_HVR_1600_ESMT);
break;
}
#define CX18_CARD_LEADTEK_PVR2100 6 /* Leadtek WinFast PVR2100 */
#define CX18_CARD_LEADTEK_DVR3100H 7 /* Leadtek WinFast DVR3100 H */
#define CX18_CARD_GOTVIEW_PCI_DVD3 8 /* GoTView PCI DVD3 Hybrid */
-#define CX18_CARD_LAST 8
+#define CX18_CARD_HVR_1600_S5H1411 9 /* Hauppauge HVR 1600 s5h1411/tda18271*/
+#define CX18_CARD_LAST 9
#define CX18_ENC_STREAM_TYPE_MPG 0
#define CX18_ENC_STREAM_TYPE_TS 1
#include "cx18-gpio.h"
#include "s5h1409.h"
#include "mxl5005s.h"
+#include "s5h1411.h"
+#include "tda18271.h"
#include "zl10353.h"
#include <linux/firmware.h>
.hvr1600_opt = S5H1409_HVR1600_OPTIMIZE
};
+/*
+ * CX18_CARD_HVR_1600_S5H1411
+ */
+static struct s5h1411_config hcw_s5h1411_config = {
+ .output_mode = S5H1411_SERIAL_OUTPUT,
+ .gpio = S5H1411_GPIO_OFF,
+ .vsb_if = S5H1411_IF_44000,
+ .qam_if = S5H1411_IF_4000,
+ .inversion = S5H1411_INVERSION_ON,
+ .status_mode = S5H1411_DEMODLOCKING,
+ .mpeg_timing = S5H1411_MPEGTIMING_CONTINOUS_NONINVERTING_CLOCK,
+};
+
+static struct tda18271_std_map hauppauge_tda18271_std_map = {
+ .atsc_6 = { .if_freq = 5380, .agc_mode = 3, .std = 3,
+ .if_lvl = 6, .rfagc_top = 0x37 },
+ .qam_6 = { .if_freq = 4000, .agc_mode = 3, .std = 0,
+ .if_lvl = 6, .rfagc_top = 0x37 },
+};
+
+static struct tda18271_config hauppauge_tda18271_config = {
+ .std_map = &hauppauge_tda18271_std_map,
+ .gate = TDA18271_GATE_DIGITAL,
+ .output_opt = TDA18271_OUTPUT_LT_OFF,
+};
+
/*
* CX18_CARD_LEADTEK_DVR3100H
*/
switch (cx->card->type) {
case CX18_CARD_HVR_1600_ESMT:
case CX18_CARD_HVR_1600_SAMSUNG:
+ case CX18_CARD_HVR_1600_S5H1411:
v = cx18_read_reg(cx, CX18_REG_DMUX_NUM_PORT_0_CONTROL);
v |= 0x00400000; /* Serial Mode */
v |= 0x00002000; /* Data Length - Byte */
ret = 0;
}
break;
+ case CX18_CARD_HVR_1600_S5H1411:
+ dvb->fe = dvb_attach(s5h1411_attach,
+ &hcw_s5h1411_config,
+ &cx->i2c_adap[0]);
+ if (dvb->fe != NULL)
+ dvb_attach(tda18271_attach, dvb->fe,
+ 0x60, &cx->i2c_adap[0],
+ &hauppauge_tda18271_config);
+ break;
case CX18_CARD_LEADTEK_DVR3100H:
dvb->fe = dvb_attach(zl10353_attach,
&leadtek_dvr3100h_demod,
if (!i2c_wait_done(i2c_adap))
goto eio;
- if (!i2c_slave_did_ack(i2c_adap)) {
- retval = -ENXIO;
- goto err;
- }
if (i2c_debug) {
printk(" <W %02x %02x", msg->addr << 1, msg->buf[0]);
if (!(ctrl & I2C_NOSTOP))
eio:
retval = -EIO;
- err:
if (i2c_debug)
printk(KERN_ERR " ERR: %d\n", retval);
return retval;
if (!i2c_wait_done(i2c_adap))
goto eio;
- if (cnt == 0 && !i2c_slave_did_ack(i2c_adap)) {
- retval = -ENXIO;
- goto err;
- }
msg->buf[cnt] = cx_read(bus->reg_rdata) & 0xff;
if (i2c_debug) {
dprintk(1, " %02x", msg->buf[cnt]);
eio:
retval = -EIO;
- err:
if (i2c_debug)
printk(KERN_ERR " ERR: %d\n", retval);
return retval;
kfree(state);
return err;
}
- v4l2_ctrl_cluster(2, &state->volume);
+ if (!is_cx2583x(state))
+ v4l2_ctrl_cluster(2, &state->volume);
v4l2_ctrl_handler_setup(&state->hdl);
if (client->dev.platform_data) {
static void ivtv_irq_dma_err(struct ivtv *itv)
{
u32 data[CX2341X_MBOX_MAX_DATA];
+ u32 status;
del_timer(&itv->dma_timer);
+
ivtv_api_get_data(&itv->enc_mbox, IVTV_MBOX_DMA_END, 2, data);
+ status = read_reg(IVTV_REG_DMASTATUS);
IVTV_DEBUG_WARN("DMA ERROR %08x %08x %08x %d\n", data[0], data[1],
- read_reg(IVTV_REG_DMASTATUS), itv->cur_dma_stream);
- write_reg(read_reg(IVTV_REG_DMASTATUS) & 3, IVTV_REG_DMASTATUS);
+ status, itv->cur_dma_stream);
+ /*
+ * We do *not* write back to the IVTV_REG_DMASTATUS register to
+ * clear the error status, if either the encoder write (0x02) or
+ * decoder read (0x01) bus master DMA operation do not indicate
+ * completed. We can race with the DMA engine, which may have
+ * transitioned to completed status *after* we read the register.
+ * Setting a IVTV_REG_DMASTATUS flag back to "busy" status, after the
+ * DMA engine has completed, will cause the DMA engine to stop working.
+ */
+ status &= 0x3;
+ if (status == 0x3)
+ write_reg(status, IVTV_REG_DMASTATUS);
+
if (!test_bit(IVTV_F_I_UDMA, &itv->i_flags) &&
itv->cur_dma_stream >= 0 && itv->cur_dma_stream < IVTV_MAX_STREAMS) {
struct ivtv_stream *s = &itv->streams[itv->cur_dma_stream];
- /* retry */
- if (s->type >= IVTV_DEC_STREAM_TYPE_MPG)
+ if (s->type >= IVTV_DEC_STREAM_TYPE_MPG) {
+ /* retry */
+ /*
+ * FIXME - handle cases of DMA error similar to
+ * encoder below, except conditioned on status & 0x1
+ */
ivtv_dma_dec_start(s);
- else
- ivtv_dma_enc_start(s);
- return;
+ return;
+ } else {
+ if ((status & 0x2) == 0) {
+ /*
+ * CX2341x Bus Master DMA write is ongoing.
+ * Reset the timer and let it complete.
+ */
+ itv->dma_timer.expires =
+ jiffies + msecs_to_jiffies(600);
+ add_timer(&itv->dma_timer);
+ return;
+ }
+
+ if (itv->dma_retries < 3) {
+ /*
+ * CX2341x Bus Master DMA write has ended.
+ * Retry the write, starting with the first
+ * xfer segment. Just retrying the current
+ * segment is not sufficient.
+ */
+ s->sg_processed = 0;
+ itv->dma_retries++;
+ ivtv_dma_enc_start_xfer(s);
+ return;
+ }
+ /* Too many retries, give up on this one */
+ }
+
}
if (test_bit(IVTV_F_I_UDMA, &itv->i_flags)) {
ivtv_udma_start(itv);
v4l2_m2m_release(dev->m2m_dev);
del_timer_sync(&dev->timer);
video_unregister_device(dev->vfd);
- video_device_release(dev->vfd);
v4l2_device_unregister(&dev->v4l2_dev);
kfree(dev);
#include <linux/usb.h>
#define S2255_MAJOR_VERSION 1
-#define S2255_MINOR_VERSION 20
+#define S2255_MINOR_VERSION 21
#define S2255_RELEASE 0
#define S2255_VERSION KERNEL_VERSION(S2255_MAJOR_VERSION, \
S2255_MINOR_VERSION, \
};
/* current cypress EEPROM firmware version */
-#define S2255_CUR_USB_FWVER ((3 << 8) | 6)
+#define S2255_CUR_USB_FWVER ((3 << 8) | 11)
/* current DSP FW version */
-#define S2255_CUR_DSP_FWVER 8
+#define S2255_CUR_DSP_FWVER 10102
/* Need DSP version 5+ for video status feature */
#define S2255_MIN_DSP_STATUS 5
#define S2255_MIN_DSP_COLORFILTER 8
static void s2255_reset_dsppower(struct s2255_dev *dev)
{
- s2255_vendor_req(dev, 0x40, 0x0b0b, 0x0b0b, NULL, 0, 1);
+ s2255_vendor_req(dev, 0x40, 0x0b0b, 0x0b01, NULL, 0, 1);
msleep(10);
s2255_vendor_req(dev, 0x50, 0x0000, 0x0000, NULL, 0, 1);
+ msleep(600);
+ s2255_vendor_req(dev, 0x10, 0x0000, 0x0000, NULL, 0, 1);
return;
}
{
int rc;
- workqueue = create_freezeable_workqueue("kmemstick");
+ workqueue = create_freezable_workqueue("kmemstick");
if (!workqueue)
return -ENOMEM;
#define COPYRIGHT "Copyright (c) 1999-2008 " MODULEAUTHOR
#endif
-#define MPT_LINUX_VERSION_COMMON "3.04.17"
-#define MPT_LINUX_PACKAGE_NAME "@(#)mptlinux-3.04.17"
+#define MPT_LINUX_VERSION_COMMON "3.04.18"
+#define MPT_LINUX_PACKAGE_NAME "@(#)mptlinux-3.04.18"
#define WHAT_MAGIC_STRING "@" "(" "#" ")"
#define show_mptmod_ver(s,ver) \
return 1;
}
+static int
+mptctl_release(struct inode *inode, struct file *filep)
+{
+ fasync_helper(-1, filep, 0, &async_queue);
+ return 0;
+}
+
static int
mptctl_fasync(int fd, struct file *filep, int mode)
{
.llseek = no_llseek,
.fasync = mptctl_fasync,
.unlocked_ioctl = mptctl_ioctl,
+ .release = mptctl_release,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_mpctl_ioctl,
#endif
}
out:
- printk(MYIOC_s_INFO_FMT "task abort: %s (sc=%p)\n",
- ioc->name, ((retval == SUCCESS) ? "SUCCESS" : "FAILED"), SCpnt);
+ printk(MYIOC_s_INFO_FMT "task abort: %s (rv=%04x) (sc=%p) (sn=%ld)\n",
+ ioc->name, ((retval == SUCCESS) ? "SUCCESS" : "FAILED"), retval,
+ SCpnt, SCpnt->serial_number);
return retval;
}
vdevice = SCpnt->device->hostdata;
if (!vdevice || !vdevice->vtarget) {
- retval = SUCCESS;
+ retval = 0;
goto out;
}
unsigned long flags;
struct asic3 *asic;
- desc->chip->ack(irq);
+ desc->irq_data.chip->irq_ack(&desc->irq_data);
- asic = desc->handler_data;
+ asic = get_irq_data(irq);
for (iter = 0 ; iter < MAX_ASIC_ISR_LOOPS; iter++) {
u32 status;
/* Voice codec interface client */
cell = &davinci_vc->cells[DAVINCI_VC_VCIF_CELL];
- cell->name = "davinci_vcif";
+ cell->name = "davinci-vcif";
cell->driver_data = davinci_vc;
/* Voice codec CQ93VC client */
cell = &davinci_vc->cells[DAVINCI_VC_CQ93VC_CELL];
- cell->name = "cq93vc";
+ cell->name = "cq93vc-codec";
cell->driver_data = davinci_vc;
ret = mfd_add_devices(&pdev->dev, pdev->id, davinci_vc->cells,
static inline int __tps6586x_writes(struct i2c_client *client, int reg,
int len, uint8_t *val)
{
- int ret;
+ int ret, i;
- ret = i2c_smbus_write_i2c_block_data(client, reg, len, val);
- if (ret < 0) {
- dev_err(&client->dev, "failed writings to 0x%02x\n", reg);
- return ret;
+ for (i = 0; i < len; i++) {
+ ret = __tps6586x_write(client, reg + i, *(val + i));
+ if (ret < 0)
+ return ret;
}
return 0;
idev->close = ucb1x00_ts_close;
__set_bit(EV_ABS, idev->evbit);
- __set_bit(ABS_X, idev->absbit);
- __set_bit(ABS_Y, idev->absbit);
- __set_bit(ABS_PRESSURE, idev->absbit);
input_set_drvdata(idev, ts);
+ ucb1x00_adc_enable(ts->ucb);
+ ts->x_res = ucb1x00_ts_read_xres(ts);
+ ts->y_res = ucb1x00_ts_read_yres(ts);
+ ucb1x00_adc_disable(ts->ucb);
+
+ input_set_abs_params(idev, ABS_X, 0, ts->x_res, 0, 0);
+ input_set_abs_params(idev, ABS_Y, 0, ts->y_res, 0, 0);
+ input_set_abs_params(idev, ABS_PRESSURE, 0, 0, 0, 0);
+
err = input_register_device(idev);
if (err)
goto fail;
struct wm8994 *wm8994 = dev_get_drvdata(dev);
int ret;
+ /* Don't actually go through with the suspend if the CODEC is
+ * still active (eg, for audio passthrough from CP. */
+ ret = wm8994_reg_read(wm8994, WM8994_POWER_MANAGEMENT_1);
+ if (ret < 0) {
+ dev_err(dev, "Failed to read power status: %d\n", ret);
+ } else if (ret & WM8994_VMID_SEL_MASK) {
+ dev_dbg(dev, "CODEC still active, ignoring suspend\n");
+ return 0;
+ }
+
/* GPIO configuration state is saved here since we may be configuring
* the GPIO alternate functions even if we're not using the gpiolib
* driver for them.
if (ret < 0)
dev_err(dev, "Failed to save LDO registers: %d\n", ret);
+ wm8994->suspended = true;
+
ret = regulator_bulk_disable(wm8994->num_supplies,
wm8994->supplies);
if (ret != 0) {
struct wm8994 *wm8994 = dev_get_drvdata(dev);
int ret;
+ /* We may have lied to the PM core about suspending */
+ if (!wm8994->suspended)
+ return 0;
+
ret = regulator_bulk_enable(wm8994->num_supplies,
wm8994->supplies);
if (ret != 0) {
if (ret < 0)
dev_err(dev, "Failed to restore GPIO registers: %d\n", ret);
+ wm8994->suspended = false;
+
return 0;
}
#endif
{ "bmp085", 0 },
{ }
};
+MODULE_DEVICE_TABLE(i2c, bmp085_id);
static struct i2c_driver bmp085_driver = {
.driver = {
{
int rc;
- workqueue = create_freezeable_workqueue("tifm");
+ workqueue = create_freezable_workqueue("tifm");
if (!workqueue)
return -ENOMEM;
if (x86_hyper != &x86_hyper_vmware)
return -ENODEV;
- vmballoon_wq = create_freezeable_workqueue("vmmemctl");
+ vmballoon_wq = create_freezable_workqueue("vmmemctl");
if (!vmballoon_wq) {
pr_err("failed to create workqueue\n");
return -ENOMEM;
* still present
*/
if (host->bus_ops && host->bus_ops->detect && !host->bus_dead
- && mmc_card_is_removable(host))
+ && !(host->caps & MMC_CAP_NONREMOVABLE))
host->bus_ops->detect(host);
/*
*/
mmc_release_host(host);
err = mmc_add_card(host->card);
- mmc_claim_host(host);
if (err)
goto remove_added;
goto remove_added;
}
+ mmc_claim_host(host);
return 0;
remove_added:
/* Remove without lock if the device has been added. */
- mmc_release_host(host);
mmc_sdio_remove(host);
mmc_claim_host(host);
remove:
sleep_time = chip_op_time / 2;
for (;;) {
+ if (chip->state != chip_state) {
+ /* Someone's suspended the operation: sleep */
+ DECLARE_WAITQUEUE(wait, current);
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ add_wait_queue(&chip->wq, &wait);
+ mutex_unlock(&chip->mutex);
+ schedule();
+ remove_wait_queue(&chip->wq, &wait);
+ mutex_lock(&chip->mutex);
+ continue;
+ }
+
status = map_read(map, cmd_adr);
if (map_word_andequal(map, status, status_OK, status_OK))
break;
+ if (chip->erase_suspended && chip_state == FL_ERASING) {
+ /* Erase suspend occured while sleep: reset timeout */
+ timeo = reset_timeo;
+ chip->erase_suspended = 0;
+ }
+ if (chip->write_suspended && chip_state == FL_WRITING) {
+ /* Write suspend occured while sleep: reset timeout */
+ timeo = reset_timeo;
+ chip->write_suspended = 0;
+ }
if (!timeo) {
map_write(map, CMD(0x70), cmd_adr);
chip->state = FL_STATUS;
timeo--;
}
mutex_lock(&chip->mutex);
-
- while (chip->state != chip_state) {
- /* Someone's suspended the operation: sleep */
- DECLARE_WAITQUEUE(wait, current);
- set_current_state(TASK_UNINTERRUPTIBLE);
- add_wait_queue(&chip->wq, &wait);
- mutex_unlock(&chip->mutex);
- schedule();
- remove_wait_queue(&chip->wq, &wait);
- mutex_lock(&chip->mutex);
- }
- if (chip->erase_suspended && chip_state == FL_ERASING) {
- /* Erase suspend occured while sleep: reset timeout */
- timeo = reset_timeo;
- chip->erase_suspended = 0;
- }
- if (chip->write_suspended && chip_state == FL_WRITING) {
- /* Write suspend occured while sleep: reset timeout */
- timeo = reset_timeo;
- chip->write_suspended = 0;
- }
}
/* Done and happy. */
}
-static int cfi_jedec_setup(struct cfi_private *p_cfi, int index)
+static int cfi_jedec_setup(struct map_info *map, struct cfi_private *cfi, int index)
{
int i,num_erase_regions;
uint8_t uaddr;
- if (! (jedec_table[index].devtypes & p_cfi->device_type)) {
+ if (!(jedec_table[index].devtypes & cfi->device_type)) {
DEBUG(MTD_DEBUG_LEVEL1, "Rejecting potential %s with incompatible %d-bit device type\n",
- jedec_table[index].name, 4 * (1<<p_cfi->device_type));
+ jedec_table[index].name, 4 * (1<<cfi->device_type));
return 0;
}
num_erase_regions = jedec_table[index].nr_regions;
- p_cfi->cfiq = kmalloc(sizeof(struct cfi_ident) + num_erase_regions * 4, GFP_KERNEL);
- if (!p_cfi->cfiq) {
+ cfi->cfiq = kmalloc(sizeof(struct cfi_ident) + num_erase_regions * 4, GFP_KERNEL);
+ if (!cfi->cfiq) {
//xx printk(KERN_WARNING "%s: kmalloc failed for CFI ident structure\n", map->name);
return 0;
}
- memset(p_cfi->cfiq,0,sizeof(struct cfi_ident));
+ memset(cfi->cfiq, 0, sizeof(struct cfi_ident));
- p_cfi->cfiq->P_ID = jedec_table[index].cmd_set;
- p_cfi->cfiq->NumEraseRegions = jedec_table[index].nr_regions;
- p_cfi->cfiq->DevSize = jedec_table[index].dev_size;
- p_cfi->cfi_mode = CFI_MODE_JEDEC;
+ cfi->cfiq->P_ID = jedec_table[index].cmd_set;
+ cfi->cfiq->NumEraseRegions = jedec_table[index].nr_regions;
+ cfi->cfiq->DevSize = jedec_table[index].dev_size;
+ cfi->cfi_mode = CFI_MODE_JEDEC;
+ cfi->sector_erase_cmd = CMD(0x30);
for (i=0; i<num_erase_regions; i++){
- p_cfi->cfiq->EraseRegionInfo[i] = jedec_table[index].regions[i];
+ cfi->cfiq->EraseRegionInfo[i] = jedec_table[index].regions[i];
}
- p_cfi->cmdset_priv = NULL;
+ cfi->cmdset_priv = NULL;
/* This may be redundant for some cases, but it doesn't hurt */
- p_cfi->mfr = jedec_table[index].mfr_id;
- p_cfi->id = jedec_table[index].dev_id;
+ cfi->mfr = jedec_table[index].mfr_id;
+ cfi->id = jedec_table[index].dev_id;
uaddr = jedec_table[index].uaddr;
our brains explode when we see the datasheets talking about address
lines numbered from A-1 to A18. The CFI table has unlock addresses
in device-words according to the mode the device is connected in */
- p_cfi->addr_unlock1 = unlock_addrs[uaddr].addr1 / p_cfi->device_type;
- p_cfi->addr_unlock2 = unlock_addrs[uaddr].addr2 / p_cfi->device_type;
+ cfi->addr_unlock1 = unlock_addrs[uaddr].addr1 / cfi->device_type;
+ cfi->addr_unlock2 = unlock_addrs[uaddr].addr2 / cfi->device_type;
return 1; /* ok */
}
"MTD %s(): matched device 0x%x,0x%x unlock_addrs: 0x%.4x 0x%.4x\n",
__func__, cfi->mfr, cfi->id,
cfi->addr_unlock1, cfi->addr_unlock2 );
- if (!cfi_jedec_setup(cfi, i))
+ if (!cfi_jedec_setup(map, cfi, i))
return 0;
goto ok_out;
}
printk(KERN_ERR MOD_NAME
" %s(): Unable to register resource %pR - kernel bug?\n",
__func__, &window->rsrc);
+ return -EBUSY;
}
error2:
list_del(&new->list);
error1:
- kfree(new);
return ret;
}
module_init(omap_nand_init);
module_exit(omap_nand_exit);
-MODULE_ALIAS(DRIVER_NAME);
+MODULE_ALIAS("platform:" DRIVER_NAME);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Glue layer for NAND flash on TI OMAP boards");
init_completion(&dev->dma_done);
- dev->card_workqueue = create_freezeable_workqueue(DRV_NAME);
+ dev->card_workqueue = create_freezable_workqueue(DRV_NAME);
if (!dev->card_workqueue)
goto error9;
.remove = __devexit_p(generic_onenand_remove),
};
-MODULE_ALIAS(DRIVER_NAME);
+MODULE_ALIAS("platform:" DRIVER_NAME);
static int __init generic_onenand_init(void)
{
module_init(omap2_onenand_init);
module_exit(omap2_onenand_exit);
-MODULE_ALIAS(DRIVER_NAME);
+MODULE_ALIAS("platform:" DRIVER_NAME);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jarkko Lavinen <jarkko.lavinen@nokia.com>");
MODULE_DESCRIPTION("Glue layer for OneNAND flash on OMAP2 / OMAP3");
static __init int sm_module_init(void)
{
int error = 0;
- cache_flush_workqueue = create_freezeable_workqueue("smflush");
+ cache_flush_workqueue = create_freezable_workqueue("smflush");
if (IS_ERR(cache_flush_workqueue))
return PTR_ERR(cache_flush_workqueue);
int csr0, boguscnt;
int handled = 0;
- if (dev == NULL) {
- printk(KERN_WARNING "ariadne_interrupt(): irq for unknown device.\n");
- return IRQ_NONE;
- }
-
lance->RAP = CSR0; /* PCnet-ISA Controller Status */
if (!(lance->RDP & INTR)) /* Check if any interrupt has been */
spin_lock_bh(&adapter->mcc_lock);
wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err;
+ }
req = nonemb_cmd->va;
sge = nonembedded_sgl(wrb);
status = be_mcc_notify_wait(adapter);
+err:
spin_unlock_bh(&adapter->mcc_lock);
return status;
}
* (you will need to reboot afterwards) */
/* #define BNX2X_STOP_ON_ERROR */
-#define DRV_MODULE_VERSION "1.62.00-5"
+#define DRV_MODULE_VERSION "1.62.00-6"
#define DRV_MODULE_RELDATE "2011/01/30"
#define BNX2X_BC_VER 0x040200
/* DCBX Negotation results */
struct dcbx_features dcbx_local_feat;
u32 dcbx_error;
+ u32 pending_max;
};
/**
#define BNX2X_BTR 4
#define MAX_SPQ_PENDING 8
-
-/* CMNG constants
- derived from lab experiments, and not from system spec calculations !!! */
-#define DEF_MIN_RATE 100
-/* resolution of the rate shaping timer - 100 usec */
-#define RS_PERIODIC_TIMEOUT_USEC 100
-/* resolution of fairness algorithm in usecs -
- coefficient for calculating the actual t fair */
-#define T_FAIR_COEF 10000000
+/* CMNG constants, as derived from system spec calculations */
+/* default MIN rate in case VNIC min rate is configured to zero - 100Mbps */
+#define DEF_MIN_RATE 100
+/* resolution of the rate shaping timer - 400 usec */
+#define RS_PERIODIC_TIMEOUT_USEC 400
/* number of bytes in single QM arbitration cycle -
- coefficient for calculating the fairness timer */
-#define QM_ARB_BYTES 40000
-#define FAIR_MEM 2
+ * coefficient for calculating the fairness timer */
+#define QM_ARB_BYTES 160000
+/* resolution of Min algorithm 1:100 */
+#define MIN_RES 100
+/* how many bytes above threshold for the minimal credit of Min algorithm*/
+#define MIN_ABOVE_THRESH 32768
+/* Fairness algorithm integration time coefficient -
+ * for calculating the actual Tfair */
+#define T_FAIR_COEF ((MIN_ABOVE_THRESH + QM_ARB_BYTES) * 8 * MIN_RES)
+/* Memory of fairness algorithm . 2 cycles */
+#define FAIR_MEM 2
#define ATTN_NIG_FOR_FUNC (1L << 8)
#endif
}
+/* Timestamp option length allowed for TPA aggregation:
+ *
+ * nop nop kind length echo val
+ */
+#define TPA_TSTAMP_OPT_LEN 12
+/**
+ * Calculate the approximate value of the MSS for this
+ * aggregation using the first packet of it.
+ *
+ * @param bp
+ * @param parsing_flags Parsing flags from the START CQE
+ * @param len_on_bd Total length of the first packet for the
+ * aggregation.
+ */
+static inline u16 bnx2x_set_lro_mss(struct bnx2x *bp, u16 parsing_flags,
+ u16 len_on_bd)
+{
+ /* TPA arrgregation won't have an IP options and TCP options
+ * other than timestamp.
+ */
+ u16 hdrs_len = ETH_HLEN + sizeof(struct iphdr) + sizeof(struct tcphdr);
+
+
+ /* Check if there was a TCP timestamp, if there is it's will
+ * always be 12 bytes length: nop nop kind length echo val.
+ *
+ * Otherwise FW would close the aggregation.
+ */
+ if (parsing_flags & PARSING_FLAGS_TIME_STAMP_EXIST_FLAG)
+ hdrs_len += TPA_TSTAMP_OPT_LEN;
+
+ return len_on_bd - hdrs_len;
+}
+
static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp,
struct sk_buff *skb,
struct eth_fast_path_rx_cqe *fp_cqe,
- u16 cqe_idx)
+ u16 cqe_idx, u16 parsing_flags)
{
struct sw_rx_page *rx_pg, old_rx_pg;
u16 len_on_bd = le16_to_cpu(fp_cqe->len_on_bd);
/* This is needed in order to enable forwarding support */
if (frag_size)
- skb_shinfo(skb)->gso_size = min((u32)SGE_PAGE_SIZE,
- max(frag_size, (u32)len_on_bd));
+ skb_shinfo(skb)->gso_size = bnx2x_set_lro_mss(bp, parsing_flags,
+ len_on_bd);
#ifdef BNX2X_STOP_ON_ERROR
if (pages > min_t(u32, 8, MAX_SKB_FRAGS)*SGE_PAGE_SIZE*PAGES_PER_SGE) {
if (likely(new_skb)) {
/* fix ip xsum and give it to the stack */
/* (no need to map the new skb) */
+ u16 parsing_flags =
+ le16_to_cpu(cqe->fast_path_cqe.pars_flags.flags);
prefetch(skb);
prefetch(((char *)(skb)) + L1_CACHE_BYTES);
}
if (!bnx2x_fill_frag_skb(bp, fp, skb,
- &cqe->fast_path_cqe, cqe_idx)) {
- if ((le16_to_cpu(cqe->fast_path_cqe.
- pars_flags.flags) & PARSING_FLAGS_VLAN))
+ &cqe->fast_path_cqe, cqe_idx,
+ parsing_flags)) {
+ if (parsing_flags & PARSING_FLAGS_VLAN)
__vlan_hwaccel_put_tag(skb,
le16_to_cpu(cqe->fast_path_cqe.
vlan_tag));
{
u16 line_speed = bp->link_vars.line_speed;
if (IS_MF(bp)) {
- u16 maxCfg = (bp->mf_config[BP_VN(bp)] &
- FUNC_MF_CFG_MAX_BW_MASK) >>
- FUNC_MF_CFG_MAX_BW_SHIFT;
- /* Calculate the current MAX line speed limit for the DCC
- * capable devices
+ u16 maxCfg = bnx2x_extract_max_cfg(bp,
+ bp->mf_config[BP_VN(bp)]);
+
+ /* Calculate the current MAX line speed limit for the MF
+ * devices
*/
- if (IS_MF_SD(bp)) {
+ if (IS_MF_SI(bp))
+ line_speed = (line_speed * maxCfg) / 100;
+ else { /* SD mode */
u16 vn_max_rate = maxCfg * 100;
if (vn_max_rate < line_speed)
line_speed = vn_max_rate;
- } else /* IS_MF_SI(bp)) */
- line_speed = (line_speed * maxCfg) / 100;
+ }
}
return line_speed;
bnx2x_free_rx_skbs(bp);
}
+void bnx2x_update_max_mf_config(struct bnx2x *bp, u32 value)
+{
+ /* load old values */
+ u32 mf_cfg = bp->mf_config[BP_VN(bp)];
+
+ if (value != bnx2x_extract_max_cfg(bp, mf_cfg)) {
+ /* leave all but MAX value */
+ mf_cfg &= ~FUNC_MF_CFG_MAX_BW_MASK;
+
+ /* set new MAX value */
+ mf_cfg |= (value << FUNC_MF_CFG_MAX_BW_SHIFT)
+ & FUNC_MF_CFG_MAX_BW_MASK;
+
+ bnx2x_fw_command(bp, DRV_MSG_CODE_SET_MF_BW, mf_cfg);
+ }
+}
+
static void bnx2x_free_msix_irqs(struct bnx2x *bp)
{
int i, offset = 1;
bnx2x_set_eth_mac(bp, 1);
+ if (bp->pending_max) {
+ bnx2x_update_max_mf_config(bp, bp->pending_max);
+ bp->pending_max = 0;
+ }
+
if (bp->port.pmf)
bnx2x_initial_phy_init(bp, load_mode);
*/
int bnx2x_set_power_state(struct bnx2x *bp, pci_power_t state);
+/**
+ * Updates MAX part of MF configuration in HW
+ * (if required)
+ *
+ * @param bp
+ * @param value
+ */
+void bnx2x_update_max_mf_config(struct bnx2x *bp, u32 value);
+
/* dev_close main block */
int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode);
void bnx2x_acquire_phy_lock(struct bnx2x *bp);
void bnx2x_release_phy_lock(struct bnx2x *bp);
+/**
+ * Extracts MAX BW part from MF configuration.
+ *
+ * @param bp
+ * @param mf_cfg
+ *
+ * @return u16
+ */
+static inline u16 bnx2x_extract_max_cfg(struct bnx2x *bp, u32 mf_cfg)
+{
+ u16 max_cfg = (mf_cfg & FUNC_MF_CFG_MAX_BW_MASK) >>
+ FUNC_MF_CFG_MAX_BW_SHIFT;
+ if (!max_cfg) {
+ BNX2X_ERR("Illegal configuration detected for Max BW - "
+ "using 100 instead\n");
+ max_cfg = 100;
+ }
+ return max_cfg;
+}
+
#endif /* BNX2X_CMN_H */
speed |= (cmd->speed_hi << 16);
if (IS_MF_SI(bp)) {
- u32 param = 0;
+ u32 part;
u32 line_speed = bp->link_vars.line_speed;
/* use 10G if no link detected */
REQ_BC_VER_4_SET_MF_BW);
return -EINVAL;
}
- if (line_speed < speed) {
- BNX2X_DEV_INFO("New speed should be less or equal "
- "to actual line speed\n");
+
+ part = (speed * 100) / line_speed;
+
+ if (line_speed < speed || !part) {
+ BNX2X_DEV_INFO("Speed setting should be in a range "
+ "from 1%% to 100%% "
+ "of actual line speed\n");
return -EINVAL;
}
- /* load old values */
- param = bp->mf_config[BP_VN(bp)];
-
- /* leave only MIN value */
- param &= FUNC_MF_CFG_MIN_BW_MASK;
- /* set new MAX value */
- param |= (((speed * 100) / line_speed)
- << FUNC_MF_CFG_MAX_BW_SHIFT)
- & FUNC_MF_CFG_MAX_BW_MASK;
+ if (bp->state != BNX2X_STATE_OPEN)
+ /* store value for following "load" */
+ bp->pending_max = part;
+ else
+ bnx2x_update_max_mf_config(bp, part);
- bnx2x_fw_command(bp, DRV_MSG_CODE_SET_MF_BW, param);
return 0;
}
{ 0x100, 0x350 }, /* manuf_info */
{ 0x450, 0xf0 }, /* feature_info */
{ 0x640, 0x64 }, /* upgrade_key_info */
- { 0x6a4, 0x64 },
{ 0x708, 0x70 }, /* manuf_key_info */
- { 0x778, 0x70 },
{ 0, 0 }
};
__be32 buf[0x350 / 4];
buf[4] = 1;
etest->flags |= ETH_TEST_FL_FAILED;
}
- if (bp->port.pmf)
- if (bnx2x_link_test(bp, is_serdes) != 0) {
- buf[5] = 1;
- etest->flags |= ETH_TEST_FL_FAILED;
- }
+
+ if (bnx2x_link_test(bp, is_serdes) != 0) {
+ buf[5] = 1;
+ etest->flags |= ETH_TEST_FL_FAILED;
+ }
#ifdef BNX2X_EXTRA_DEBUG
bnx2x_panic_dump(bp);
/* Block IGU, MISC, PXP and PXP2 parity errors as long as we don't
* want to handle "system kill" flow at the moment.
*/
- BLOCK_PRTY_INFO(PXP, 0x3ffffff, 0x3ffffff, 0x3ffffff, 0x3ffffff),
+ BLOCK_PRTY_INFO(PXP, 0x7ffffff, 0x3ffffff, 0x3ffffff, 0x7ffffff),
BLOCK_PRTY_INFO_0(PXP2, 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff),
BLOCK_PRTY_INFO_1(PXP2, 0x7ff, 0x7f, 0x7f, 0x7ff),
BLOCK_PRTY_INFO(HC, 0x7, 0x7, 0x7, 0),
vn_max_rate = 0;
} else {
+ u32 maxCfg = bnx2x_extract_max_cfg(bp, vn_cfg);
+
vn_min_rate = ((vn_cfg & FUNC_MF_CFG_MIN_BW_MASK) >>
FUNC_MF_CFG_MIN_BW_SHIFT) * 100;
- /* If min rate is zero - set it to 1 */
+ /* If fairness is enabled (not all min rates are zeroes) and
+ if current min rate is zero - set it to 1.
+ This is a requirement of the algorithm. */
if (bp->vn_weight_sum && (vn_min_rate == 0))
vn_min_rate = DEF_MIN_RATE;
- vn_max_rate = ((vn_cfg & FUNC_MF_CFG_MAX_BW_MASK) >>
- FUNC_MF_CFG_MAX_BW_SHIFT) * 100;
+
+ if (IS_MF_SI(bp))
+ /* maxCfg in percents of linkspeed */
+ vn_max_rate = (bp->link_vars.line_speed * maxCfg) / 100;
+ else
+ /* maxCfg is absolute in 100Mb units */
+ vn_max_rate = maxCfg * 100;
}
DP(NETIF_MSG_IFUP,
m_fair_vn.vn_credit_delta =
max_t(u32, (vn_min_rate * (T_FAIR_COEF /
(8 * bp->vn_weight_sum))),
- (bp->cmng.fair_vars.fair_threshold * 2));
+ (bp->cmng.fair_vars.fair_threshold +
+ MIN_ABOVE_THRESH));
DP(NETIF_MSG_IFUP, "m_fair_vn.vn_credit_delta %d\n",
m_fair_vn.vn_credit_delta);
}
bnx2x_calc_vn_weight_sum(bp);
/* calculate and set min-max rate for each vn */
- for (vn = VN_0; vn < E1HVN_MAX; vn++)
- bnx2x_init_vn_minmax(bp, vn);
+ if (bp->port.pmf)
+ for (vn = VN_0; vn < E1HVN_MAX; vn++)
+ bnx2x_init_vn_minmax(bp, vn);
/* always enable rate shaping and fairness */
bp->cmng.flags.cmng_enables |=
bnx2x_stats_handle(bp, STATS_EVENT_LINK_UP);
}
- /* indicate link status only if link status actually changed */
- if (prev_link_status != bp->link_vars.link_status)
- bnx2x_link_report(bp);
-
- if (IS_MF(bp))
- bnx2x_link_sync_notify(bp);
-
if (bp->link_vars.link_up && bp->link_vars.line_speed) {
int cmng_fns = bnx2x_get_cmng_fns_mode(bp);
DP(NETIF_MSG_IFUP,
"single function mode without fairness\n");
}
+
+ if (IS_MF(bp))
+ bnx2x_link_sync_notify(bp);
+
+ /* indicate link status only if link status actually changed */
+ if (prev_link_status != bp->link_vars.link_status)
+ bnx2x_link_report(bp);
}
void bnx2x__link_status_update(struct bnx2x *bp)
def_q_filters |= BNX2X_ACCEPT_UNICAST | BNX2X_ACCEPT_BROADCAST |
BNX2X_ACCEPT_MULTICAST;
#ifdef BCM_CNIC
- cl_id = bnx2x_fcoe(bp, cl_id);
- bnx2x_rxq_set_mac_filters(bp, cl_id, BNX2X_ACCEPT_UNICAST |
- BNX2X_ACCEPT_MULTICAST);
+ if (!NO_FCOE(bp)) {
+ cl_id = bnx2x_fcoe(bp, cl_id);
+ bnx2x_rxq_set_mac_filters(bp, cl_id,
+ BNX2X_ACCEPT_UNICAST |
+ BNX2X_ACCEPT_MULTICAST);
+ }
#endif
break;
def_q_filters |= BNX2X_ACCEPT_UNICAST | BNX2X_ACCEPT_BROADCAST |
BNX2X_ACCEPT_ALL_MULTICAST;
#ifdef BCM_CNIC
- cl_id = bnx2x_fcoe(bp, cl_id);
- bnx2x_rxq_set_mac_filters(bp, cl_id, BNX2X_ACCEPT_UNICAST |
- BNX2X_ACCEPT_MULTICAST);
+ /*
+ * Prevent duplication of multicast packets by configuring FCoE
+ * L2 Client to receive only matched unicast frames.
+ */
+ if (!NO_FCOE(bp)) {
+ cl_id = bnx2x_fcoe(bp, cl_id);
+ bnx2x_rxq_set_mac_filters(bp, cl_id,
+ BNX2X_ACCEPT_UNICAST);
+ }
#endif
break;
case BNX2X_RX_MODE_PROMISC:
def_q_filters |= BNX2X_PROMISCUOUS_MODE;
#ifdef BCM_CNIC
- cl_id = bnx2x_fcoe(bp, cl_id);
- bnx2x_rxq_set_mac_filters(bp, cl_id, BNX2X_ACCEPT_UNICAST |
- BNX2X_ACCEPT_MULTICAST);
+ /*
+ * Prevent packets duplication by configuring DROP_ALL for FCoE
+ * L2 Client.
+ */
+ if (!NO_FCOE(bp)) {
+ cl_id = bnx2x_fcoe(bp, cl_id);
+ bnx2x_rxq_set_mac_filters(bp, cl_id, BNX2X_ACCEPT_NONE);
+ }
#endif
/* pass management unicast packets as well */
llh_mask |= NIG_LLH0_BRB1_DRV_MASK_REG_LLH0_BRB1_DRV_MASK_UNCST;
if (unlikely(bp->panic))
return;
+ bnx2x_stats_stm[bp->stats_state][event].action(bp);
+
/* Protect a state change flow */
spin_lock_bh(&bp->stats_lock);
state = bp->stats_state;
bp->stats_state = bnx2x_stats_stm[state][event].next_state;
spin_unlock_bh(&bp->stats_lock);
- bnx2x_stats_stm[state][event].action(bp);
-
if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp))
DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n",
state, event, bp->stats_state);
}
/**
- * __get_rx_machine_lock - lock the port's RX machine
+ * __get_state_machine_lock - lock the port's state machines
* @port: the port we're looking at
*
*/
-static inline void __get_rx_machine_lock(struct port *port)
+static inline void __get_state_machine_lock(struct port *port)
{
- spin_lock_bh(&(SLAVE_AD_INFO(port->slave).rx_machine_lock));
+ spin_lock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock));
}
/**
- * __release_rx_machine_lock - unlock the port's RX machine
+ * __release_state_machine_lock - unlock the port's state machines
* @port: the port we're looking at
*
*/
-static inline void __release_rx_machine_lock(struct port *port)
+static inline void __release_state_machine_lock(struct port *port)
{
- spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).rx_machine_lock));
+ spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock));
}
/**
}
/**
- * __initialize_port_locks - initialize a port's RX machine spinlock
+ * __initialize_port_locks - initialize a port's STATE machine spinlock
* @port: the port we're looking at
*
*/
static inline void __initialize_port_locks(struct port *port)
{
// make sure it isn't called twice
- spin_lock_init(&(SLAVE_AD_INFO(port->slave).rx_machine_lock));
+ spin_lock_init(&(SLAVE_AD_INFO(port->slave).state_machine_lock));
}
//conversions
{
rx_states_t last_state;
- // Lock to prevent 2 instances of this function to run simultaneously(rx interrupt and periodic machine callback)
- __get_rx_machine_lock(port);
-
// keep current State Machine state to compare later if it was changed
last_state = port->sm_rx_state;
pr_err("%s: An illegal loopback occurred on adapter (%s).\n"
"Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n",
port->slave->dev->master->name, port->slave->dev->name);
- __release_rx_machine_lock(port);
return;
}
__update_selected(lacpdu, port);
break;
}
}
- __release_rx_machine_lock(port);
}
/**
goto re_arm;
}
+ /* Lock around state machines to protect data accessed
+ * by all (e.g., port->sm_vars). ad_rx_machine may run
+ * concurrently due to incoming LACPDU.
+ */
+ __get_state_machine_lock(port);
+
ad_rx_machine(NULL, port);
ad_periodic_machine(port);
ad_port_selection_logic(port);
// turn off the BEGIN bit, since we already handled it
if (port->sm_vars & AD_PORT_BEGIN)
port->sm_vars &= ~AD_PORT_BEGIN;
+
+ __release_state_machine_lock(port);
}
re_arm:
case AD_TYPE_LACPDU:
pr_debug("Received LACPDU on port %d\n",
port->actor_port_number);
+ /* Protect against concurrent state machines */
+ __get_state_machine_lock(port);
ad_rx_machine(lacpdu, port);
+ __release_state_machine_lock(port);
break;
case AD_TYPE_MARKER:
struct ad_slave_info {
struct aggregator aggregator; // 802.3ad aggregator structure
struct port port; // 802.3ad port structure
- spinlock_t rx_machine_lock; // To avoid race condition between callback and receive interrupt
+ spinlock_t state_machine_lock; /* mutex state machines vs.
+ incoming LACPDU */
u16 id;
};
goto open_unlock;
}
- priv->wq = create_freezeable_workqueue("mcp251x_wq");
+ priv->wq = create_freezable_workqueue("mcp251x_wq");
INIT_WORK(&priv->tx_work, mcp251x_tx_work_handler);
INIT_WORK(&priv->restart_work, mcp251x_restart_work_handler);
config CAN_MSCAN
- depends on CAN_DEV && (PPC || M68K || M68KNOMMU)
+ depends on CAN_DEV && (PPC || M68K)
tristate "Support for Freescale MSCAN based chips"
---help---
The Motorola Scalable Controller Area Network (MSCAN) definition
static struct can_bittiming_const pch_can_bittiming_const = {
.name = KBUILD_MODNAME,
- .tseg1_min = 1,
+ .tseg1_min = 2,
.tseg1_max = 16,
.tseg2_min = 1,
.tseg2_max = 8,
struct pch_can_priv *priv = netdev_priv(ndev);
unregister_candev(priv->ndev);
- pci_iounmap(pdev, priv->regs);
if (priv->use_msi)
pci_disable_msi(priv->dev);
pci_release_regions(pdev);
pci_disable_device(pdev);
pci_set_drvdata(pdev, NULL);
pch_can_reset(priv);
+ pci_iounmap(pdev, priv->regs);
free_candev(priv->ndev);
}
priv->use_msi = 0;
} else {
netdev_err(ndev, "PCH CAN opened with MSI\n");
+ pci_set_master(pdev);
priv->use_msi = 1;
}
config CAN_SOFTING_CS
tristate "Softing Gmbh CAN pcmcia cards"
depends on PCMCIA
- select CAN_SOFTING
+ depends on CAN_SOFTING
---help---
Support for PCMCIA cards from Softing Gmbh & some cards
from Vector Gmbh.
#include <linux/module.h>
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <pcmcia/cistpl.h>
#include <pcmcia/ds.h>
};
static const struct can_bittiming_const softing_btr_const = {
+ .name = "softing",
.tseg1_min = 1,
.tseg1_max = 16,
.tseg2_min = 1,
u32 status_idx = (u16) *cp->kcq1.status_idx_ptr;
int kcqe_cnt;
+ /* status block index must be read before reading other fields */
+ rmb();
cp->kwq_con_idx = *cp->kwq_con_idx_ptr;
while ((kcqe_cnt = cnic_get_kcqes(dev, &cp->kcq1))) {
barrier();
if (status_idx != *cp->kcq1.status_idx_ptr) {
status_idx = (u16) *cp->kcq1.status_idx_ptr;
+ /* status block index must be read first */
+ rmb();
cp->kwq_con_idx = *cp->kwq_con_idx_ptr;
} else
break;
u32 last_status = *info->status_idx_ptr;
int kcqe_cnt;
+ /* status block index must be read before reading the KCQ */
+ rmb();
while ((kcqe_cnt = cnic_get_kcqes(dev, info))) {
service_kcqes(dev, kcqe_cnt);
break;
last_status = *info->status_idx_ptr;
+ /* status block index must be read before reading the KCQ */
+ rmb();
}
return last_status;
}
{
struct cnic_dev *dev = (struct cnic_dev *) data;
struct cnic_local *cp = dev->cnic_priv;
- u32 status_idx;
+ u32 status_idx, new_status_idx;
if (unlikely(!test_bit(CNIC_F_CNIC_UP, &dev->flags)))
return;
- status_idx = cnic_service_bnx2x_kcq(dev, &cp->kcq1);
+ while (1) {
+ status_idx = cnic_service_bnx2x_kcq(dev, &cp->kcq1);
- CNIC_WR16(dev, cp->kcq1.io_addr, cp->kcq1.sw_prod_idx + MAX_KCQ_IDX);
+ CNIC_WR16(dev, cp->kcq1.io_addr,
+ cp->kcq1.sw_prod_idx + MAX_KCQ_IDX);
- if (BNX2X_CHIP_IS_E2(cp->chip_id)) {
- status_idx = cnic_service_bnx2x_kcq(dev, &cp->kcq2);
+ if (!BNX2X_CHIP_IS_E2(cp->chip_id)) {
+ cnic_ack_bnx2x_int(dev, cp->bnx2x_igu_sb_id, USTORM_ID,
+ status_idx, IGU_INT_ENABLE, 1);
+ break;
+ }
+
+ new_status_idx = cnic_service_bnx2x_kcq(dev, &cp->kcq2);
+
+ if (new_status_idx != status_idx)
+ continue;
CNIC_WR16(dev, cp->kcq2.io_addr, cp->kcq2.sw_prod_idx +
MAX_KCQ_IDX);
cnic_ack_igu_sb(dev, cp->bnx2x_igu_sb_id, IGU_SEG_ACCESS_DEF,
status_idx, IGU_INT_ENABLE, 1);
- } else {
- cnic_ack_bnx2x_int(dev, cp->bnx2x_igu_sb_id, USTORM_ID,
- status_idx, IGU_INT_ENABLE, 1);
+
+ break;
}
}
{
int i;
- BUG_ON(adapter->debugfs_root == NULL);
+ BUG_ON(IS_ERR_OR_NULL(adapter->debugfs_root));
/*
* Debugfs support is best effort.
*/
static void cleanup_debugfs(struct adapter *adapter)
{
- BUG_ON(adapter->debugfs_root == NULL);
+ BUG_ON(IS_ERR_OR_NULL(adapter->debugfs_root));
/*
* Unlike our sister routine cleanup_proc(), we don't need to remove
struct port_info *pi;
struct net_device *netdev;
- /*
- * Vet our module parameters.
- */
- if (msi != MSI_MSIX && msi != MSI_MSI) {
- dev_err(&pdev->dev, "bad module parameter msi=%d; must be %d"
- " (MSI-X or MSI) or %d (MSI)\n", msi, MSI_MSIX,
- MSI_MSI);
- err = -EINVAL;
- goto err_out;
- }
-
/*
* Print our driver banner the first time we're called to initialize a
* device.
/*
* Set up our debugfs entries.
*/
- if (cxgb4vf_debugfs_root) {
+ if (!IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) {
adapter->debugfs_root =
debugfs_create_dir(pci_name(pdev),
cxgb4vf_debugfs_root);
- if (adapter->debugfs_root == NULL)
+ if (IS_ERR_OR_NULL(adapter->debugfs_root))
dev_warn(&pdev->dev, "could not create debugfs"
" directory");
else
*/
err_free_debugfs:
- if (adapter->debugfs_root) {
+ if (!IS_ERR_OR_NULL(adapter->debugfs_root)) {
cleanup_debugfs(adapter);
debugfs_remove_recursive(adapter->debugfs_root);
}
err_disable_device:
pci_disable_device(pdev);
-err_out:
return err;
}
/*
* Tear down our debugfs entries.
*/
- if (adapter->debugfs_root) {
+ if (!IS_ERR_OR_NULL(adapter->debugfs_root)) {
cleanup_debugfs(adapter);
debugfs_remove_recursive(adapter->debugfs_root);
}
pci_release_regions(pdev);
}
+/*
+ * "Shutdown" quiesce the device, stopping Ingress Packet and Interrupt
+ * delivery.
+ */
+static void __devexit cxgb4vf_pci_shutdown(struct pci_dev *pdev)
+{
+ struct adapter *adapter;
+ int pidx;
+
+ adapter = pci_get_drvdata(pdev);
+ if (!adapter)
+ return;
+
+ /*
+ * Disable all Virtual Interfaces. This will shut down the
+ * delivery of all ingress packets into the chip for these
+ * Virtual Interfaces.
+ */
+ for_each_port(adapter, pidx) {
+ struct net_device *netdev;
+ struct port_info *pi;
+
+ if (!test_bit(pidx, &adapter->registered_device_map))
+ continue;
+
+ netdev = adapter->port[pidx];
+ if (!netdev)
+ continue;
+
+ pi = netdev_priv(netdev);
+ t4vf_enable_vi(adapter, pi->viid, false, false);
+ }
+
+ /*
+ * Free up all Queues which will prevent further DMA and
+ * Interrupts allowing various internal pathways to drain.
+ */
+ t4vf_free_sge_resources(adapter);
+}
+
/*
* PCI Device registration data structures.
*/
.id_table = cxgb4vf_pci_tbl,
.probe = cxgb4vf_pci_probe,
.remove = __devexit_p(cxgb4vf_pci_remove),
+ .shutdown = __devexit_p(cxgb4vf_pci_shutdown),
};
/*
{
int ret;
+ /*
+ * Vet our module parameters.
+ */
+ if (msi != MSI_MSIX && msi != MSI_MSI) {
+ printk(KERN_WARNING KBUILD_MODNAME
+ ": bad module parameter msi=%d; must be %d"
+ " (MSI-X or MSI) or %d (MSI)\n",
+ msi, MSI_MSIX, MSI_MSI);
+ return -EINVAL;
+ }
+
/* Debugfs support is optional, just warn if this fails */
cxgb4vf_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL);
- if (!cxgb4vf_debugfs_root)
+ if (IS_ERR_OR_NULL(cxgb4vf_debugfs_root))
printk(KERN_WARNING KBUILD_MODNAME ": could not create"
" debugfs entry, continuing\n");
ret = pci_register_driver(&cxgb4vf_driver);
- if (ret < 0)
+ if (ret < 0 && !IS_ERR_OR_NULL(cxgb4vf_debugfs_root))
debugfs_remove(cxgb4vf_debugfs_root);
return ret;
}
delay_idx = 0;
ms = delay[0];
- for (i = 0; i < 500; i += ms) {
+ for (i = 0; i < FW_CMD_MAX_TIMEOUT; i += ms) {
if (sleep_ok) {
ms = delay[delay_idx];
if (delay_idx < ARRAY_SIZE(delay) - 1)
int ret;
/* free and bail if we are shutting down */
- if (unlikely(!netif_running(ndev))) {
+ if (unlikely(!netif_running(ndev) || !netif_carrier_ok(ndev))) {
dev_kfree_skb_any(skb);
return;
}
/* Checksum mode */
dm9000_set_rx_csum_unlocked(dev, db->rx_csum);
- /* GPIO0 on pre-activate PHY */
- iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */
iow(db, DM9000_GPCR, GPCR_GEP_CNTL); /* Let GPIO0 output */
- iow(db, DM9000_GPR, 0); /* Enable PHY */
ncr = (db->flags & DM9000_PLATF_EXT_PHY) ? NCR_EXT_PHY : 0;
unsigned long flags;
/* Save previous register address */
- reg_save = readb(db->io_addr);
spin_lock_irqsave(&db->lock, flags);
+ reg_save = readb(db->io_addr);
netif_stop_queue(dev);
dm9000_reset(db);
if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
return -EAGAIN;
+ /* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */
+ iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */
+ mdelay(1); /* delay needs by DM9000B */
+
/* Initialize DM9000 board */
dm9000_reset(db);
dm9000_init_dm9000(dev);
for (i = 0; i < PHY_MAX_ADDR; i++)
bp->mii_bus->irq[i] = PHY_POLL;
- platform_set_drvdata(bp->dev, bp->mii_bus);
-
if (mdiobus_register(bp->mii_bus)) {
err = -ENXIO;
goto err_out_free_mdio_irq;
bp = netdev_priv(dev);
bp->dev = dev;
+ platform_set_drvdata(pdev, dev);
SET_NETDEV_DEV(dev, &pdev->dev);
spin_lock_init(&bp->lock);
case M88E1000_I_PHY_ID:
case M88E1011_I_PHY_ID:
case M88E1111_I_PHY_ID:
+ case M88E1118_E_PHY_ID:
hw->phy_type = e1000_phy_m88;
break;
case IGP01E1000_I_PHY_ID:
break;
case e1000_ce4100:
if ((hw->phy_id == RTL8211B_PHY_ID) ||
- (hw->phy_id == RTL8201N_PHY_ID))
+ (hw->phy_id == RTL8201N_PHY_ID) ||
+ (hw->phy_id == M88E1118_E_PHY_ID))
match = true;
break;
case e1000_82541:
#define M88E1000_14_PHY_ID M88E1000_E_PHY_ID
#define M88E1011_I_REV_4 0x04
#define M88E1111_I_PHY_ID 0x01410CC0
+#define M88E1118_E_PHY_ID 0x01410E40
#define L1LXT971A_PHY_ID 0x001378E0
#define RTL8211B_PHY_ID 0x001CC910
#define GBE_CONFIG_RAM_BASE \
((unsigned int)(CONFIG_RAM_BASE + GBE_CONFIG_OFFSET))
-#define GBE_CONFIG_BASE_VIRT phys_to_virt(GBE_CONFIG_RAM_BASE)
+#define GBE_CONFIG_BASE_VIRT \
+ ((void __iomem *)phys_to_virt(GBE_CONFIG_RAM_BASE))
#define GBE_CONFIG_FLASH_WRITE(base, offset, count, data) \
(iowrite16_rep(base + offset, data, count))
u16 phy_status, phy_1000t_status, phy_ext_status;
u16 pci_status;
+ if (test_bit(__E1000_DOWN, &adapter->state))
+ return;
+
e1e_rphy(hw, PHY_STATUS, &phy_status);
e1e_rphy(hw, PHY_1000T_STATUS, &phy_1000t_status);
e1e_rphy(hw, PHY_EXT_STATUS, &phy_ext_status);
struct e1000_adapter *adapter = container_of(work,
struct e1000_adapter, downshift_task);
+ if (test_bit(__E1000_DOWN, &adapter->state))
+ return;
+
e1000e_gig_downshift_workaround_ich8lan(&adapter->hw);
}
return 0;
}
+static void e1000e_flush_descriptors(struct e1000_adapter *adapter)
+{
+ struct e1000_hw *hw = &adapter->hw;
+
+ if (!(adapter->flags2 & FLAG2_DMA_BURST))
+ return;
+
+ /* flush pending descriptor writebacks to memory */
+ ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
+ ew32(RDTR, adapter->rx_int_delay | E1000_RDTR_FPD);
+
+ /* execute the writes immediately */
+ e1e_flush();
+}
+
void e1000e_down(struct e1000_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
if (!pci_channel_offline(adapter->pdev))
e1000e_reset(adapter);
+
+ e1000e_flush_descriptors(adapter);
+
e1000_clean_tx_ring(adapter);
e1000_clean_rx_ring(adapter);
{
struct e1000_adapter *adapter = container_of(work,
struct e1000_adapter, update_phy_task);
+
+ if (test_bit(__E1000_DOWN, &adapter->state))
+ return;
+
e1000_get_phy_info(&adapter->hw);
}
static void e1000_update_phy_info(unsigned long data)
{
struct e1000_adapter *adapter = (struct e1000_adapter *) data;
+
+ if (test_bit(__E1000_DOWN, &adapter->state))
+ return;
+
schedule_work(&adapter->update_phy_task);
}
u32 link, tctl;
int tx_pending = 0;
+ if (test_bit(__E1000_DOWN, &adapter->state))
+ return;
+
link = e1000e_has_link(adapter);
if ((netif_carrier_ok(netdev)) && link) {
/* Cancel scheduled suspend requests. */
* to get done, so reset controller to flush Tx.
* (Do the reset outside of interrupt context).
*/
- adapter->tx_timeout_count++;
schedule_work(&adapter->reset_task);
/* return immediately since reset is imminent */
return;
else
ew32(ICS, E1000_ICS_RXDMT0);
+ /* flush pending descriptors to memory before detecting Tx hang */
+ e1000e_flush_descriptors(adapter);
+
/* Force detection of hung controller every watchdog period */
adapter->detect_tx_hung = 1;
- /* flush partial descriptors to memory before detecting Tx hang */
- if (adapter->flags2 & FLAG2_DMA_BURST) {
- ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
- ew32(RDTR, adapter->rx_int_delay | E1000_RDTR_FPD);
- /*
- * no need to flush the writes because the timeout code does
- * an er32 first thing
- */
- }
-
/*
* With 82571 controllers, LAA may be overwritten due to controller
* reset from the other port. Set the appropriate LAA in RAR[0]
struct e1000_adapter *adapter;
adapter = container_of(work, struct e1000_adapter, reset_task);
+ /* don't run the task if already down */
+ if (test_bit(__E1000_DOWN, &adapter->state))
+ return;
+
if (!((adapter->flags & FLAG_RX_NEEDS_RESTART) &&
(adapter->flags & FLAG_RX_RESTART_NOW))) {
e1000e_dump(adapter);
/* APME bit in EEPROM is mapped to WUC.APME */
eeprom_data = er32(WUC);
eeprom_apme_mask = E1000_WUC_APME;
- if (eeprom_data & E1000_WUC_PHY_WAKE)
+ if ((hw->mac.type > e1000_ich10lan) &&
+ (eeprom_data & E1000_WUC_PHY_WAKE))
adapter->flags2 |= FLAG2_HAS_PHY_WAKEUP;
} else if (adapter->flags & FLAG_APME_IN_CTRL3) {
if (adapter->flags & FLAG_APME_CHECK_PORT_B &&
}, {
.name = "imx28-fec",
.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME,
- }
+ },
+ { }
};
static unsigned char macaddr[ETH_ALEN];
goto out_error;
}
+ netif_carrier_off(dev);
+
dev_info(&pci_dev->dev, "ifname %s, PHY OUI 0x%x @ %d, addr %pM\n",
dev->name, np->phy_oui, np->phyaddr, dev->dev_addr);
* The parameter rar_count will usually be hw->mac.rar_entry_count
* unless there are workarounds that change this.
**/
-void e1000_update_mc_addr_list_vf(struct e1000_hw *hw,
+static void e1000_update_mc_addr_list_vf(struct e1000_hw *hw,
u8 *mc_addr_list, u32 mc_addr_count,
u32 rar_used_count, u32 rar_count)
{
hw_dbg(hw, " New MAC Addr =%pM\n", hw->mac.addr);
hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV);
+
+ /* clear VMDq pool/queue selection for RAR 0 */
+ hw->mac.ops.clear_vmdq(hw, 0, IXGBE_CLEAR_VMDQ_ALL);
}
hw->addr_ctrl.overflow_promisc = 0;
struct scatterlist *sg;
unsigned int i, j, dmacount;
unsigned int len;
- static const unsigned int bufflen = 4096;
+ static const unsigned int bufflen = IXGBE_FCBUFF_MIN;
unsigned int firstoff = 0;
unsigned int lastsize;
unsigned int thisoff = 0;
unsigned int thislen = 0;
u32 fcbuff, fcdmarw, fcfltrw;
- dma_addr_t addr;
+ dma_addr_t addr = 0;
if (!netdev || !sgl)
return 0;
/* only the last buffer may have non-full bufflen */
lastsize = thisoff + thislen;
+ /*
+ * lastsize can not be buffer len.
+ * If it is then adding another buffer with lastsize = 1.
+ */
+ if (lastsize == bufflen) {
+ if (j >= IXGBE_BUFFCNT_MAX) {
+ e_err(drv, "xid=%x:%d,%d,%d:addr=%llx "
+ "not enough user buffers. We need an extra "
+ "buffer because lastsize is bufflen.\n",
+ xid, i, j, dmacount, (u64)addr);
+ goto out_noddp_free;
+ }
+
+ ddp->udl[j] = (u64)(fcoe->extra_ddp_buffer_dma);
+ j++;
+ lastsize = 1;
+ }
+
fcbuff = (IXGBE_FCBUFF_4KB << IXGBE_FCBUFF_BUFFSIZE_SHIFT);
fcbuff |= ((j & 0xff) << IXGBE_FCBUFF_BUFFCNT_SHIFT);
fcbuff |= (firstoff << IXGBE_FCBUFF_OFFSET_SHIFT);
e_err(drv, "failed to allocated FCoE DDP pool\n");
spin_lock_init(&fcoe->lock);
+
+ /* Extra buffer to be shared by all DDPs for HW work around */
+ fcoe->extra_ddp_buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_ATOMIC);
+ if (fcoe->extra_ddp_buffer == NULL) {
+ e_err(drv, "failed to allocated extra DDP buffer\n");
+ goto out_extra_ddp_buffer_alloc;
+ }
+
+ fcoe->extra_ddp_buffer_dma =
+ dma_map_single(&adapter->pdev->dev,
+ fcoe->extra_ddp_buffer,
+ IXGBE_FCBUFF_MIN,
+ DMA_FROM_DEVICE);
+ if (dma_mapping_error(&adapter->pdev->dev,
+ fcoe->extra_ddp_buffer_dma)) {
+ e_err(drv, "failed to map extra DDP buffer\n");
+ goto out_extra_ddp_buffer_dma;
+ }
}
/* Enable L2 eth type filter for FCoE */
}
}
#endif
+
+ return;
+
+out_extra_ddp_buffer_dma:
+ kfree(fcoe->extra_ddp_buffer);
+out_extra_ddp_buffer_alloc:
+ pci_pool_destroy(fcoe->pool);
+ fcoe->pool = NULL;
}
/**
if (fcoe->pool) {
for (i = 0; i < IXGBE_FCOE_DDP_MAX; i++)
ixgbe_fcoe_ddp_put(adapter->netdev, i);
+ dma_unmap_single(&adapter->pdev->dev,
+ fcoe->extra_ddp_buffer_dma,
+ IXGBE_FCBUFF_MIN,
+ DMA_FROM_DEVICE);
+ kfree(fcoe->extra_ddp_buffer);
pci_pool_destroy(fcoe->pool);
fcoe->pool = NULL;
}
spinlock_t lock;
struct pci_pool *pool;
struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX];
+ unsigned char *extra_ddp_buffer;
+ dma_addr_t extra_ddp_buffer_dma;
};
#endif /* _IXGBE_FCOE_H */
static const char ixgbe_driver_string[] =
"Intel(R) 10 Gigabit PCI Express Network Driver";
-#define DRV_VERSION "3.0.12-k2"
+#define DRV_VERSION "3.2.9-k2"
const char ixgbe_driver_version[] = DRV_VERSION;
static char ixgbe_copyright[] = "Copyright (c) 1999-2010 Intel Corporation.";
u32 mhadd, hlreg0;
/* Decide whether to use packet split mode or not */
+ /* On by default */
+ adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
+
/* Do not use packet split if we're in SR-IOV Mode */
- if (!adapter->num_vfs)
- adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
+ if (adapter->num_vfs)
+ adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
+
+ /* Disable packet split due to 82599 erratum #45 */
+ if (hw->mac.type == ixgbe_mac_82599EB)
+ adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
/* Set the RX buffer length according to the mode */
if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
* We need to try and force an autonegotiation
* session, then bring up link.
*/
- hw->mac.ops.setup_sfp(hw);
+ if (hw->mac.ops.setup_sfp)
+ hw->mac.ops.setup_sfp(hw);
if (!(adapter->flags & IXGBE_FLAG_IN_SFP_LINK_TASK))
schedule_work(&adapter->multispeed_fiber_task);
} else {
{
int q_idx, num_q_vectors;
struct ixgbe_q_vector *q_vector;
- int napi_vectors;
int (*poll)(struct napi_struct *, int);
if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
- napi_vectors = adapter->num_rx_queues;
poll = &ixgbe_clean_rxtx_many;
} else {
num_q_vectors = 1;
- napi_vectors = 1;
poll = &ixgbe_poll;
}
unregister_netdev(adapter->netdev);
return;
}
- hw->mac.ops.setup_sfp(hw);
+ if (hw->mac.ops.setup_sfp)
+ hw->mac.ops.setup_sfp(hw);
if (!(adapter->flags & IXGBE_FLAG_IN_SFP_LINK_TASK))
/* This will also work for DA Twinax connections */
return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add);
}
-
static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe)
{
u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
vmolr |= (IXGBE_VMOLR_ROMPE |
- IXGBE_VMOLR_ROPE |
IXGBE_VMOLR_BAM);
if (aupe)
vmolr |= IXGBE_VMOLR_AUPE;
}
ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL);
- IXGBE_WRITE_REG(hw, IXGBE_CTRL, (ctrl | IXGBE_CTRL_RST));
+ IXGBE_WRITE_REG(hw, IXGBE_CTRL, (ctrl | reset_bit));
IXGBE_WRITE_FLUSH(hw);
/* Poll for reset bit to self-clear indicating reset is complete */
for (i = 0; i < 10; i++) {
udelay(1);
ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL);
- if (!(ctrl & IXGBE_CTRL_RST))
+ if (!(ctrl & reset_bit))
break;
}
- if (ctrl & IXGBE_CTRL_RST) {
+ if (ctrl & reset_bit) {
status = IXGBE_ERR_RESET_FAILED;
hw_dbg(hw, "Reset polling failed to complete.\n");
}
for (i = 0; i < PHY_MAX_ADDR; i++)
bp->mii_bus->irq[i] = PHY_POLL;
- platform_set_drvdata(bp->dev, bp->mii_bus);
+ dev_set_drvdata(&bp->dev->dev, bp->mii_bus);
if (mdiobus_register(bp->mii_bus))
goto err_out_free_mdio_irq;
vnet_hdr_len = q->vnet_hdr_sz;
err = -EINVAL;
- if ((len -= vnet_hdr_len) < 0)
+ if (len < vnet_hdr_len)
goto err;
+ len -= vnet_hdr_len;
err = memcpy_fromiovecend((void *)&vnet_hdr, iv, 0,
sizeof(vnet_hdr));
struct pch_gbe_regs_mac_adr mac_adr[16];
u32 ADDR_MASK;
u32 MIIM;
- u32 reserve2;
+ u32 MAC_ADDR_LOAD;
u32 RGMII_ST;
u32 RGMII_CTRL;
u32 reserve3[3];
#define PCH_GBE_SHORT_PKT 64
#define DSC_INIT16 0xC000
#define PCH_GBE_DMA_ALIGN 0
+#define PCH_GBE_DMA_PADDING 2
#define PCH_GBE_WATCHDOG_PERIOD (1 * HZ) /* watchdog time */
#define PCH_GBE_COPYBREAK_DEFAULT 256
#define PCH_GBE_PCI_BAR 1
static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg);
static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg,
int data);
+
+inline void pch_gbe_mac_load_mac_addr(struct pch_gbe_hw *hw)
+{
+ iowrite32(0x01, &hw->reg->MAC_ADDR_LOAD);
+}
+
/**
* pch_gbe_mac_read_mac_addr - Read MAC address
* @hw: Pointer to the HW structure
struct pch_gbe_adapter *adapter;
adapter = container_of(work, struct pch_gbe_adapter, reset_task);
+ rtnl_lock();
pch_gbe_reinit_locked(adapter);
+ rtnl_unlock();
}
/**
*/
void pch_gbe_reinit_locked(struct pch_gbe_adapter *adapter)
{
- struct net_device *netdev = adapter->netdev;
-
- rtnl_lock();
- if (netif_running(netdev)) {
- pch_gbe_down(adapter);
- pch_gbe_up(adapter);
- }
- rtnl_unlock();
+ pch_gbe_down(adapter);
+ pch_gbe_up(adapter);
}
/**
struct pch_gbe_buffer *buffer_info;
struct pch_gbe_rx_desc *rx_desc;
u32 length;
- unsigned char tmp_packet[ETH_HLEN];
unsigned int i;
unsigned int cleaned_count = 0;
bool cleaned = false;
- struct sk_buff *skb;
+ struct sk_buff *skb, *new_skb;
u8 dma_status;
u16 gbec_status;
u32 tcp_ip_status;
- u8 skb_copy_flag = 0;
- u8 skb_padding_flag = 0;
i = rx_ring->next_to_clean;
pr_err("Receive CRC Error\n");
} else {
/* get receive length */
- /* length convert[-3], padding[-2] */
- length = (rx_desc->rx_words_eob) - 3 - 2;
+ /* length convert[-3] */
+ length = (rx_desc->rx_words_eob) - 3;
/* Decide the data conversion method */
if (!adapter->rx_csum) {
/* [Header:14][payload] */
- skb_padding_flag = 0;
- skb_copy_flag = 1;
+ if (NET_IP_ALIGN) {
+ /* Because alignment differs,
+ * the new_skb is newly allocated,
+ * and data is copied to new_skb.*/
+ new_skb = netdev_alloc_skb(netdev,
+ length + NET_IP_ALIGN);
+ if (!new_skb) {
+ /* dorrop error */
+ pr_err("New skb allocation "
+ "Error\n");
+ goto dorrop;
+ }
+ skb_reserve(new_skb, NET_IP_ALIGN);
+ memcpy(new_skb->data, skb->data,
+ length);
+ skb = new_skb;
+ } else {
+ /* DMA buffer is used as SKB as it is.*/
+ buffer_info->skb = NULL;
+ }
} else {
/* [Header:14][padding:2][payload] */
- skb_padding_flag = 1;
- if (length < copybreak)
- skb_copy_flag = 1;
- else
- skb_copy_flag = 0;
- }
-
- /* Data conversion */
- if (skb_copy_flag) { /* recycle skb */
- struct sk_buff *new_skb;
- new_skb =
- netdev_alloc_skb(netdev,
- length + NET_IP_ALIGN);
- if (new_skb) {
- if (!skb_padding_flag) {
- skb_reserve(new_skb,
- NET_IP_ALIGN);
+ /* The length includes padding length */
+ length = length - PCH_GBE_DMA_PADDING;
+ if ((length < copybreak) ||
+ (NET_IP_ALIGN != PCH_GBE_DMA_PADDING)) {
+ /* Because alignment differs,
+ * the new_skb is newly allocated,
+ * and data is copied to new_skb.
+ * Padding data is deleted
+ * at the time of a copy.*/
+ new_skb = netdev_alloc_skb(netdev,
+ length + NET_IP_ALIGN);
+ if (!new_skb) {
+ /* dorrop error */
+ pr_err("New skb allocation "
+ "Error\n");
+ goto dorrop;
}
+ skb_reserve(new_skb, NET_IP_ALIGN);
memcpy(new_skb->data, skb->data,
- length);
- /* save the skb
- * in buffer_info as good */
+ ETH_HLEN);
+ memcpy(&new_skb->data[ETH_HLEN],
+ &skb->data[ETH_HLEN +
+ PCH_GBE_DMA_PADDING],
+ length - ETH_HLEN);
skb = new_skb;
- } else if (!skb_padding_flag) {
- /* dorrop error */
- pr_err("New skb allocation Error\n");
- goto dorrop;
+ } else {
+ /* Padding data is deleted
+ * by moving header data.*/
+ memmove(&skb->data[PCH_GBE_DMA_PADDING],
+ &skb->data[0], ETH_HLEN);
+ skb_reserve(skb, NET_IP_ALIGN);
+ buffer_info->skb = NULL;
}
- } else {
- buffer_info->skb = NULL;
}
- if (skb_padding_flag) {
- memcpy(&tmp_packet[0], &skb->data[0], ETH_HLEN);
- memcpy(&skb->data[NET_IP_ALIGN], &tmp_packet[0],
- ETH_HLEN);
- skb_reserve(skb, NET_IP_ALIGN);
-
- }
-
+ /* The length includes FCS length */
+ length = length - ETH_FCS_LEN;
/* update status of driver */
adapter->stats.rx_bytes += length;
adapter->stats.rx_packets++;
netdev->features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_GRO;
pch_gbe_set_ethtool_ops(netdev);
+ pch_gbe_mac_load_mac_addr(&adapter->hw);
pch_gbe_mac_reset_hw(&adapter->hw);
/* setup the private structure */
PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0105, 0x0e0a),
PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0032, 0x0e01),
PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0032, 0x0a05),
+ PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0032, 0x0b05),
PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0032, 0x1101),
PCMCIA_DEVICE_NULL,
};
#include <asm/processor.h>
#define DRV_NAME "r6040"
-#define DRV_VERSION "0.26"
-#define DRV_RELDATE "30May2010"
+#define DRV_VERSION "0.27"
+#define DRV_RELDATE "23Feb2011"
/* PHY CHIP Address */
#define PHY1_ADDR 1 /* For MAC1 */
/* MAC registers */
#define MCR0 0x00 /* Control register 0 */
+#define MCR0_PROMISC 0x0020 /* Promiscuous mode */
+#define MCR0_HASH_EN 0x0100 /* Enable multicast hash table function */
#define MCR1 0x04 /* Control register 1 */
#define MAC_RST 0x0001 /* Reset the MAC */
#define MBCR 0x08 /* Bus control */
{
struct r6040_private *lp = netdev_priv(dev);
void __iomem *ioaddr = lp->base;
- u16 *adrp;
- u16 reg;
unsigned long flags;
struct netdev_hw_addr *ha;
int i;
+ u16 *adrp;
+ u16 hash_table[4] = { 0 };
+
+ spin_lock_irqsave(&lp->lock, flags);
- /* MAC Address */
+ /* Keep our MAC Address */
adrp = (u16 *)dev->dev_addr;
iowrite16(adrp[0], ioaddr + MID_0L);
iowrite16(adrp[1], ioaddr + MID_0M);
iowrite16(adrp[2], ioaddr + MID_0H);
- /* Promiscous Mode */
- spin_lock_irqsave(&lp->lock, flags);
-
/* Clear AMCP & PROM bits */
- reg = ioread16(ioaddr) & ~0x0120;
- if (dev->flags & IFF_PROMISC) {
- reg |= 0x0020;
- lp->mcr0 |= 0x0020;
- }
- /* Too many multicast addresses
- * accept all traffic */
- else if ((netdev_mc_count(dev) > MCAST_MAX) ||
- (dev->flags & IFF_ALLMULTI))
- reg |= 0x0020;
+ lp->mcr0 = ioread16(ioaddr + MCR0) & ~(MCR0_PROMISC | MCR0_HASH_EN);
- iowrite16(reg, ioaddr);
- spin_unlock_irqrestore(&lp->lock, flags);
+ /* Promiscuous mode */
+ if (dev->flags & IFF_PROMISC)
+ lp->mcr0 |= MCR0_PROMISC;
- /* Build the hash table */
- if (netdev_mc_count(dev) > MCAST_MAX) {
- u16 hash_table[4];
- u32 crc;
+ /* Enable multicast hash table function to
+ * receive all multicast packets. */
+ else if (dev->flags & IFF_ALLMULTI) {
+ lp->mcr0 |= MCR0_HASH_EN;
- for (i = 0; i < 4; i++)
- hash_table[i] = 0;
+ for (i = 0; i < MCAST_MAX ; i++) {
+ iowrite16(0, ioaddr + MID_1L + 8 * i);
+ iowrite16(0, ioaddr + MID_1M + 8 * i);
+ iowrite16(0, ioaddr + MID_1H + 8 * i);
+ }
+ for (i = 0; i < 4; i++)
+ hash_table[i] = 0xffff;
+ }
+ /* Use internal multicast address registers if the number of
+ * multicast addresses is not greater than MCAST_MAX. */
+ else if (netdev_mc_count(dev) <= MCAST_MAX) {
+ i = 0;
netdev_for_each_mc_addr(ha, dev) {
- char *addrs = ha->addr;
+ u16 *adrp = (u16 *) ha->addr;
+ iowrite16(adrp[0], ioaddr + MID_1L + 8 * i);
+ iowrite16(adrp[1], ioaddr + MID_1M + 8 * i);
+ iowrite16(adrp[2], ioaddr + MID_1H + 8 * i);
+ i++;
+ }
+ while (i < MCAST_MAX) {
+ iowrite16(0, ioaddr + MID_1L + 8 * i);
+ iowrite16(0, ioaddr + MID_1M + 8 * i);
+ iowrite16(0, ioaddr + MID_1H + 8 * i);
+ i++;
+ }
+ }
+ /* Otherwise, Enable multicast hash table function. */
+ else {
+ u32 crc;
- if (!(*addrs & 1))
- continue;
+ lp->mcr0 |= MCR0_HASH_EN;
+
+ for (i = 0; i < MCAST_MAX ; i++) {
+ iowrite16(0, ioaddr + MID_1L + 8 * i);
+ iowrite16(0, ioaddr + MID_1M + 8 * i);
+ iowrite16(0, ioaddr + MID_1H + 8 * i);
+ }
- crc = ether_crc_le(6, addrs);
+ /* Build multicast hash table */
+ netdev_for_each_mc_addr(ha, dev) {
+ u8 *addrs = ha->addr;
+
+ crc = ether_crc(ETH_ALEN, addrs);
crc >>= 26;
- hash_table[crc >> 4] |= 1 << (15 - (crc & 0xf));
+ hash_table[crc >> 4] |= 1 << (crc & 0xf);
}
- /* Fill the MAC hash tables with their values */
+ }
+
+ iowrite16(lp->mcr0, ioaddr + MCR0);
+
+ /* Fill the MAC hash tables with their values */
+ if (lp->mcr0 && MCR0_HASH_EN) {
iowrite16(hash_table[0], ioaddr + MAR0);
iowrite16(hash_table[1], ioaddr + MAR1);
iowrite16(hash_table[2], ioaddr + MAR2);
iowrite16(hash_table[3], ioaddr + MAR3);
}
- /* Multicast Address 1~4 case */
- i = 0;
- netdev_for_each_mc_addr(ha, dev) {
- if (i >= MCAST_MAX)
- break;
- adrp = (u16 *) ha->addr;
- iowrite16(adrp[0], ioaddr + MID_1L + 8 * i);
- iowrite16(adrp[1], ioaddr + MID_1M + 8 * i);
- iowrite16(adrp[2], ioaddr + MID_1H + 8 * i);
- i++;
- }
- while (i < MCAST_MAX) {
- iowrite16(0xffff, ioaddr + MID_1L + 8 * i);
- iowrite16(0xffff, ioaddr + MID_1M + 8 * i);
- iowrite16(0xffff, ioaddr + MID_1H + 8 * i);
- i++;
- }
+
+ spin_unlock_irqrestore(&lp->lock, flags);
}
static void netdev_get_drvinfo(struct net_device *dev,
#include <linux/dma-mapping.h>
#include <linux/pm_runtime.h>
#include <linux/firmware.h>
+#include <linux/pci-aspm.h>
#include <asm/system.h>
#include <asm/io.h>
}
}
-static void rtl8168_oob_notify(void __iomem *ioaddr, u8 cmd)
+static void rtl8168_oob_notify(struct rtl8169_private *tp, u8 cmd)
{
+ void __iomem *ioaddr = tp->mmio_addr;
int i;
RTL_W8(ERIDR, cmd);
break;
}
- ocp_write(ioaddr, 0x1, 0x30, 0x00000001);
+ ocp_write(tp, 0x1, 0x30, 0x00000001);
}
#define OOB_CMD_RESET 0x00
{
void __iomem *ioaddr = tp->mmio_addr;
- if (tp->mac_version == RTL_GIGA_MAC_VER_27)
+ if (((tp->mac_version == RTL_GIGA_MAC_VER_27) ||
+ (tp->mac_version == RTL_GIGA_MAC_VER_28)) &&
+ (ocp_read(tp, 0x0f, 0x0010) & 0x00008000)) {
return;
+ }
if (((tp->mac_version == RTL_GIGA_MAC_VER_23) ||
(tp->mac_version == RTL_GIGA_MAC_VER_24)) &&
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_25:
case RTL_GIGA_MAC_VER_26:
+ case RTL_GIGA_MAC_VER_27:
+ case RTL_GIGA_MAC_VER_28:
RTL_W8(PMCH, RTL_R8(PMCH) & ~0x80);
break;
}
{
void __iomem *ioaddr = tp->mmio_addr;
- if (tp->mac_version == RTL_GIGA_MAC_VER_27)
+ if (((tp->mac_version == RTL_GIGA_MAC_VER_27) ||
+ (tp->mac_version == RTL_GIGA_MAC_VER_28)) &&
+ (ocp_read(tp, 0x0f, 0x0010) & 0x00008000)) {
return;
+ }
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_25:
case RTL_GIGA_MAC_VER_26:
+ case RTL_GIGA_MAC_VER_27:
+ case RTL_GIGA_MAC_VER_28:
RTL_W8(PMCH, RTL_R8(PMCH) | 0x80);
break;
}
mii->reg_num_mask = 0x1f;
mii->supports_gmii = !!(cfg->features & RTL_FEATURE_GMII);
+ /* disable ASPM completely as that cause random device stop working
+ * problems as well as full system hangs for some PCIe devices users */
+ pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
+ PCIE_LINK_STATE_CLKPM);
+
/* enable device (incl. PCI PM wakeup and hotplug setup) */
rc = pci_enable_device(pdev);
if (rc < 0) {
goto err_out_mwi_2;
}
- tp->cp_cmd = PCIMulRW | RxChkSum;
+ tp->cp_cmd = RxChkSum;
if ((sizeof(dma_addr_t) > 4) &&
!pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) && use_dac) {
if (pci_dev_run_wake(pdev))
pm_runtime_put_noidle(&pdev->dev);
+ netif_carrier_off(dev);
+
out:
return rc;
/* Disable interrupts */
rtl8169_irq_mask_and_ack(ioaddr);
- if (tp->mac_version == RTL_GIGA_MAC_VER_28) {
+ if (tp->mac_version == RTL_GIGA_MAC_VER_27 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_28) {
while (RTL_R8(TxPoll) & NPQ)
udelay(20);
Cxpl_dbg_sel | \
ASF | \
PktCntrDisable | \
- PCIDAC | \
- PCIMulRW)
+ Mac_dbgo_sel)
static void rtl_hw_start_8102e_1(void __iomem *ioaddr, struct pci_dev *pdev)
{
if ((cfg1 & LEDS0) && (cfg1 & LEDS1))
RTL_W8(Config1, cfg1 & ~LEDS0);
- RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R810X_CPCMD_QUIRK_MASK);
-
rtl_ephy_init(ioaddr, e_info_8102e_1, ARRAY_SIZE(e_info_8102e_1));
}
RTL_W8(Config1, MEMMAP | IOMAP | VPD | PMEnable);
RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en);
-
- RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R810X_CPCMD_QUIRK_MASK);
}
static void rtl_hw_start_8102e_3(void __iomem *ioaddr, struct pci_dev *pdev)
}
}
+ RTL_W8(Cfg9346, Cfg9346_Unlock);
+
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_07:
rtl_hw_start_8102e_1(ioaddr, pdev);
break;
}
- RTL_W8(Cfg9346, Cfg9346_Unlock);
+ RTL_W8(Cfg9346, Cfg9346_Lock);
RTL_W8(MaxTxPacketSize, TxPacketMax);
rtl_set_rx_max_size(ioaddr, rx_buf_sz);
- tp->cp_cmd |= rtl_rw_cpluscmd(ioaddr) | PCIMulRW;
-
+ tp->cp_cmd &= ~R810X_CPCMD_QUIRK_MASK;
RTL_W16(CPlusCmd, tp->cp_cmd);
RTL_W16(IntrMitigate, 0x0000);
RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb);
rtl_set_rx_tx_config_registers(tp);
- RTL_W8(Cfg9346, Cfg9346_Lock);
-
RTL_R8(IntrMask);
rtl_set_rx_mode(dev);
- RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb);
-
RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xf000);
RTL_W16(IntrMask, tp->intr_event);
struct ethtool_test *test, u64 *data)
{
struct efx_nic *efx = netdev_priv(net_dev);
- struct efx_self_tests efx_tests;
+ struct efx_self_tests *efx_tests;
int already_up;
- int rc;
+ int rc = -ENOMEM;
+
+ efx_tests = kzalloc(sizeof(*efx_tests), GFP_KERNEL);
+ if (!efx_tests)
+ goto fail;
+
ASSERT_RTNL();
if (efx->state != STATE_RUNNING) {
if (rc) {
netif_err(efx, drv, efx->net_dev,
"failed opening device.\n");
- goto fail2;
+ goto fail1;
}
}
- memset(&efx_tests, 0, sizeof(efx_tests));
-
- rc = efx_selftest(efx, &efx_tests, test->flags);
+ rc = efx_selftest(efx, efx_tests, test->flags);
if (!already_up)
dev_close(efx->net_dev);
rc == 0 ? "passed" : "failed",
(test->flags & ETH_TEST_FL_OFFLINE) ? "off" : "on");
- fail2:
- fail1:
+fail1:
/* Fill ethtool results structures */
- efx_ethtool_fill_self_tests(efx, &efx_tests, NULL, data);
+ efx_ethtool_fill_self_tests(efx, efx_tests, NULL, data);
+ kfree(efx_tests);
+fail:
if (rc)
test->flags |= ETH_TEST_FL_FAILED;
}
"cur_rx:%4.4d, dirty_rx:%4.4d\n",
net_dev->name, sis_priv->cur_rx,
sis_priv->dirty_rx);
+ dev_kfree_skb(skb);
break;
}
memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port*8, ETH_ALEN);
memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
- /* device is off until link detection */
- netif_carrier_off(dev);
-
return dev;
}
smsc911x_reg_write(pdata, HW_CFG, 0x00050000);
smsc911x_reg_write(pdata, AFC_CFG, 0x006E3740);
+ /* Increase the legal frame size of VLAN tagged frames to 1522 bytes */
+ spin_lock_irq(&pdata->mac_lock);
+ smsc911x_mac_write(pdata, VLAN1, ETH_P_8021Q);
+ spin_unlock_irq(&pdata->mac_lock);
+
/* Make sure EEPROM has finished loading before setting GPIO_CFG */
timeout = 50;
while ((smsc911x_reg_read(pdata, E2P_CMD) & E2P_CMD_EPC_BUSY_) &&
priv->hw = device;
- if (device_can_wakeup(priv->device))
+ if (device_can_wakeup(priv->device)) {
priv->wolopts = WAKE_MAGIC; /* Magic Frame as default */
+ enable_irq_wake(dev->irq);
+ }
return 0;
}
if (tp->phy_flags & TG3_PHYFLG_PHY_SERDES)
break; /* We have no PHY */
- if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)
+ if ((tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) ||
+ ((tp->tg3_flags & TG3_FLAG_ENABLE_ASF) &&
+ !netif_running(dev)))
return -EAGAIN;
spin_lock_bh(&tp->lock);
if (tp->phy_flags & TG3_PHYFLG_PHY_SERDES)
break; /* We have no PHY */
- if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)
+ if ((tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) ||
+ ((tp->tg3_flags & TG3_FLAG_ENABLE_ASF) &&
+ !netif_running(dev)))
return -EAGAIN;
spin_lock_bh(&tp->lock);
/*
* cdc_ncm.c
*
- * Copyright (C) ST-Ericsson 2010
+ * Copyright (C) ST-Ericsson 2010-2011
* Contact: Alexey Orishko <alexey.orishko@stericsson.com>
* Original author: Hans Petter Selasky <hans.petter.selasky@stericsson.com>
*
#include <linux/usb/usbnet.h>
#include <linux/usb/cdc.h>
-#define DRIVER_VERSION "17-Jan-2011"
+#define DRIVER_VERSION "7-Feb-2011"
/* CDC NCM subclass 3.2.1 */
#define USB_CDC_NCM_NDP16_LENGTH_MIN 0x10
*/
#define CDC_NCM_DPT_DATAGRAMS_MAX 32
+/* Maximum amount of IN datagrams in NTB */
+#define CDC_NCM_DPT_DATAGRAMS_IN_MAX 0 /* unlimited */
+
/* Restart the timer, if amount of datagrams is less than given value */
#define CDC_NCM_RESTART_TIMER_DATAGRAM_CNT 3
(sizeof(struct usb_cdc_ncm_nth16) + sizeof(struct usb_cdc_ncm_ndp16) + \
(CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16))
-struct connection_speed_change {
- __le32 USBitRate; /* holds 3GPP downlink value, bits per second */
- __le32 DSBitRate; /* holds 3GPP uplink value, bits per second */
-} __attribute__ ((packed));
-
struct cdc_ncm_data {
struct usb_cdc_ncm_nth16 nth16;
struct usb_cdc_ncm_ndp16 ndp16;
{
struct usb_cdc_notification req;
u32 val;
- __le16 max_datagram_size;
u8 flags;
u8 iface_no;
int err;
+ u16 ntb_fmt_supported;
iface_no = ctx->control->cur_altsetting->desc.bInterfaceNumber;
ctx->tx_remainder = le16_to_cpu(ctx->ncm_parm.wNdpOutPayloadRemainder);
ctx->tx_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutDivisor);
ctx->tx_ndp_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutAlignment);
+ /* devices prior to NCM Errata shall set this field to zero */
+ ctx->tx_max_datagrams = le16_to_cpu(ctx->ncm_parm.wNtbOutMaxDatagrams);
+ ntb_fmt_supported = le16_to_cpu(ctx->ncm_parm.bmNtbFormatsSupported);
if (ctx->func_desc != NULL)
flags = ctx->func_desc->bmNetworkCapabilities;
pr_debug("dwNtbInMaxSize=%u dwNtbOutMaxSize=%u "
"wNdpOutPayloadRemainder=%u wNdpOutDivisor=%u "
- "wNdpOutAlignment=%u flags=0x%x\n",
+ "wNdpOutAlignment=%u wNtbOutMaxDatagrams=%u flags=0x%x\n",
ctx->rx_max, ctx->tx_max, ctx->tx_remainder, ctx->tx_modulus,
- ctx->tx_ndp_modulus, flags);
+ ctx->tx_ndp_modulus, ctx->tx_max_datagrams, flags);
- /* max count of tx datagrams without terminating NULL entry */
- ctx->tx_max_datagrams = CDC_NCM_DPT_DATAGRAMS_MAX;
+ /* max count of tx datagrams */
+ if ((ctx->tx_max_datagrams == 0) ||
+ (ctx->tx_max_datagrams > CDC_NCM_DPT_DATAGRAMS_MAX))
+ ctx->tx_max_datagrams = CDC_NCM_DPT_DATAGRAMS_MAX;
/* verify maximum size of received NTB in bytes */
- if ((ctx->rx_max <
- (CDC_NCM_MIN_HDR_SIZE + CDC_NCM_MIN_DATAGRAM_SIZE)) ||
- (ctx->rx_max > CDC_NCM_NTB_MAX_SIZE_RX)) {
+ if (ctx->rx_max < USB_CDC_NCM_NTB_MIN_IN_SIZE) {
+ pr_debug("Using min receive length=%d\n",
+ USB_CDC_NCM_NTB_MIN_IN_SIZE);
+ ctx->rx_max = USB_CDC_NCM_NTB_MIN_IN_SIZE;
+ }
+
+ if (ctx->rx_max > CDC_NCM_NTB_MAX_SIZE_RX) {
pr_debug("Using default maximum receive length=%d\n",
CDC_NCM_NTB_MAX_SIZE_RX);
ctx->rx_max = CDC_NCM_NTB_MAX_SIZE_RX;
}
+ /* inform device about NTB input size changes */
+ if (ctx->rx_max != le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize)) {
+ req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT |
+ USB_RECIP_INTERFACE;
+ req.bNotificationType = USB_CDC_SET_NTB_INPUT_SIZE;
+ req.wValue = 0;
+ req.wIndex = cpu_to_le16(iface_no);
+
+ if (flags & USB_CDC_NCM_NCAP_NTB_INPUT_SIZE) {
+ struct usb_cdc_ncm_ndp_input_size ndp_in_sz;
+
+ req.wLength = 8;
+ ndp_in_sz.dwNtbInMaxSize = cpu_to_le32(ctx->rx_max);
+ ndp_in_sz.wNtbInMaxDatagrams =
+ cpu_to_le16(CDC_NCM_DPT_DATAGRAMS_MAX);
+ ndp_in_sz.wReserved = 0;
+ err = cdc_ncm_do_request(ctx, &req, &ndp_in_sz, 0, NULL,
+ 1000);
+ } else {
+ __le32 dwNtbInMaxSize = cpu_to_le32(ctx->rx_max);
+
+ req.wLength = 4;
+ err = cdc_ncm_do_request(ctx, &req, &dwNtbInMaxSize, 0,
+ NULL, 1000);
+ }
+
+ if (err)
+ pr_debug("Setting NTB Input Size failed\n");
+ }
+
/* verify maximum size of transmitted NTB in bytes */
if ((ctx->tx_max <
(CDC_NCM_MIN_HDR_SIZE + CDC_NCM_MIN_DATAGRAM_SIZE)) ||
/* additional configuration */
/* set CRC Mode */
- req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE;
- req.bNotificationType = USB_CDC_SET_CRC_MODE;
- req.wValue = cpu_to_le16(USB_CDC_NCM_CRC_NOT_APPENDED);
- req.wIndex = cpu_to_le16(iface_no);
- req.wLength = 0;
-
- err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000);
- if (err)
- pr_debug("Setting CRC mode off failed\n");
+ if (flags & USB_CDC_NCM_NCAP_CRC_MODE) {
+ req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT |
+ USB_RECIP_INTERFACE;
+ req.bNotificationType = USB_CDC_SET_CRC_MODE;
+ req.wValue = cpu_to_le16(USB_CDC_NCM_CRC_NOT_APPENDED);
+ req.wIndex = cpu_to_le16(iface_no);
+ req.wLength = 0;
+
+ err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000);
+ if (err)
+ pr_debug("Setting CRC mode off failed\n");
+ }
- /* set NTB format */
- req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE;
- req.bNotificationType = USB_CDC_SET_NTB_FORMAT;
- req.wValue = cpu_to_le16(USB_CDC_NCM_NTB16_FORMAT);
- req.wIndex = cpu_to_le16(iface_no);
- req.wLength = 0;
+ /* set NTB format, if both formats are supported */
+ if (ntb_fmt_supported & USB_CDC_NCM_NTH32_SIGN) {
+ req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT |
+ USB_RECIP_INTERFACE;
+ req.bNotificationType = USB_CDC_SET_NTB_FORMAT;
+ req.wValue = cpu_to_le16(USB_CDC_NCM_NTB16_FORMAT);
+ req.wIndex = cpu_to_le16(iface_no);
+ req.wLength = 0;
+
+ err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000);
+ if (err)
+ pr_debug("Setting NTB format to 16-bit failed\n");
+ }
- err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000);
- if (err)
- pr_debug("Setting NTB format to 16-bit failed\n");
+ ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE;
/* set Max Datagram Size (MTU) */
- req.bmRequestType = USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE;
- req.bNotificationType = USB_CDC_GET_MAX_DATAGRAM_SIZE;
- req.wValue = 0;
- req.wIndex = cpu_to_le16(iface_no);
- req.wLength = cpu_to_le16(2);
+ if (flags & USB_CDC_NCM_NCAP_MAX_DATAGRAM_SIZE) {
+ __le16 max_datagram_size;
+ u16 eth_max_sz = le16_to_cpu(ctx->ether_desc->wMaxSegmentSize);
+
+ req.bmRequestType = USB_TYPE_CLASS | USB_DIR_IN |
+ USB_RECIP_INTERFACE;
+ req.bNotificationType = USB_CDC_GET_MAX_DATAGRAM_SIZE;
+ req.wValue = 0;
+ req.wIndex = cpu_to_le16(iface_no);
+ req.wLength = cpu_to_le16(2);
+
+ err = cdc_ncm_do_request(ctx, &req, &max_datagram_size, 0, NULL,
+ 1000);
+ if (err) {
+ pr_debug("GET_MAX_DATAGRAM_SIZE failed, use size=%u\n",
+ CDC_NCM_MIN_DATAGRAM_SIZE);
+ } else {
+ ctx->max_datagram_size = le16_to_cpu(max_datagram_size);
+ /* Check Eth descriptor value */
+ if (eth_max_sz < CDC_NCM_MAX_DATAGRAM_SIZE) {
+ if (ctx->max_datagram_size > eth_max_sz)
+ ctx->max_datagram_size = eth_max_sz;
+ } else {
+ if (ctx->max_datagram_size >
+ CDC_NCM_MAX_DATAGRAM_SIZE)
+ ctx->max_datagram_size =
+ CDC_NCM_MAX_DATAGRAM_SIZE;
+ }
- err = cdc_ncm_do_request(ctx, &req, &max_datagram_size, 0, NULL, 1000);
- if (err) {
- pr_debug(" GET_MAX_DATAGRAM_SIZE failed, using size=%u\n",
- CDC_NCM_MIN_DATAGRAM_SIZE);
- /* use default */
- ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE;
- } else {
- ctx->max_datagram_size = le16_to_cpu(max_datagram_size);
+ if (ctx->max_datagram_size < CDC_NCM_MIN_DATAGRAM_SIZE)
+ ctx->max_datagram_size =
+ CDC_NCM_MIN_DATAGRAM_SIZE;
+
+ /* if value changed, update device */
+ req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT |
+ USB_RECIP_INTERFACE;
+ req.bNotificationType = USB_CDC_SET_MAX_DATAGRAM_SIZE;
+ req.wValue = 0;
+ req.wIndex = cpu_to_le16(iface_no);
+ req.wLength = 2;
+ max_datagram_size = cpu_to_le16(ctx->max_datagram_size);
+
+ err = cdc_ncm_do_request(ctx, &req, &max_datagram_size,
+ 0, NULL, 1000);
+ if (err)
+ pr_debug("SET_MAX_DATAGRAM_SIZE failed\n");
+ }
- if (ctx->max_datagram_size < CDC_NCM_MIN_DATAGRAM_SIZE)
- ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE;
- else if (ctx->max_datagram_size > CDC_NCM_MAX_DATAGRAM_SIZE)
- ctx->max_datagram_size = CDC_NCM_MAX_DATAGRAM_SIZE;
}
if (ctx->netdev->mtu != (ctx->max_datagram_size - ETH_HLEN))
ctx->ether_desc =
(const struct usb_cdc_ether_desc *)buf;
-
dev->hard_mtu =
le16_to_cpu(ctx->ether_desc->wMaxSegmentSize);
- if (dev->hard_mtu <
- (CDC_NCM_MIN_DATAGRAM_SIZE - ETH_HLEN))
- dev->hard_mtu =
- CDC_NCM_MIN_DATAGRAM_SIZE - ETH_HLEN;
-
- else if (dev->hard_mtu >
- (CDC_NCM_MAX_DATAGRAM_SIZE - ETH_HLEN))
- dev->hard_mtu =
- CDC_NCM_MAX_DATAGRAM_SIZE - ETH_HLEN;
+ if (dev->hard_mtu < CDC_NCM_MIN_DATAGRAM_SIZE)
+ dev->hard_mtu = CDC_NCM_MIN_DATAGRAM_SIZE;
+ else if (dev->hard_mtu > CDC_NCM_MAX_DATAGRAM_SIZE)
+ dev->hard_mtu = CDC_NCM_MAX_DATAGRAM_SIZE;
break;
case USB_CDC_NCM_TYPE:
u32 offset;
u32 last_offset;
u16 n = 0;
- u8 timeout = 0;
+ u8 ready2send = 0;
/* if there is a remaining skb, it gets priority */
if (skb != NULL)
swap(skb, ctx->tx_rem_skb);
else
- timeout = 1;
+ ready2send = 1;
/*
* +----------------+
for (; n < ctx->tx_max_datagrams; n++) {
/* check if end of transmit buffer is reached */
- if (offset >= ctx->tx_max)
+ if (offset >= ctx->tx_max) {
+ ready2send = 1;
break;
-
+ }
/* compute maximum buffer size */
rem = ctx->tx_max - offset;
}
ctx->tx_rem_skb = skb;
skb = NULL;
-
- /* loop one more time */
- timeout = 1;
+ ready2send = 1;
}
break;
}
ctx->tx_curr_last_offset = last_offset;
goto exit_no_skb;
- } else if ((n < ctx->tx_max_datagrams) && (timeout == 0)) {
+ } else if ((n < ctx->tx_max_datagrams) && (ready2send == 0)) {
/* wait for more frames */
/* push variables */
ctx->tx_curr_skb = skb_out;
cpu_to_le16(sizeof(ctx->tx_ncm.nth16));
ctx->tx_ncm.nth16.wSequence = cpu_to_le16(ctx->tx_seq);
ctx->tx_ncm.nth16.wBlockLength = cpu_to_le16(last_offset);
- ctx->tx_ncm.nth16.wFpIndex = ALIGN(sizeof(struct usb_cdc_ncm_nth16),
+ ctx->tx_ncm.nth16.wNdpIndex = ALIGN(sizeof(struct usb_cdc_ncm_nth16),
ctx->tx_ndp_modulus);
memcpy(skb_out->data, &(ctx->tx_ncm.nth16), sizeof(ctx->tx_ncm.nth16));
rem = sizeof(ctx->tx_ncm.ndp16) + ((ctx->tx_curr_frame_num + 1) *
sizeof(struct usb_cdc_ncm_dpe16));
ctx->tx_ncm.ndp16.wLength = cpu_to_le16(rem);
- ctx->tx_ncm.ndp16.wNextFpIndex = 0; /* reserved */
+ ctx->tx_ncm.ndp16.wNextNdpIndex = 0; /* reserved */
- memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wFpIndex,
+ memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wNdpIndex,
&(ctx->tx_ncm.ndp16),
sizeof(ctx->tx_ncm.ndp16));
- memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wFpIndex +
+ memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wNdpIndex +
sizeof(ctx->tx_ncm.ndp16),
&(ctx->tx_ncm.dpe16),
(ctx->tx_curr_frame_num + 1) *
goto error;
}
- temp = le16_to_cpu(ctx->rx_ncm.nth16.wFpIndex);
+ temp = le16_to_cpu(ctx->rx_ncm.nth16.wNdpIndex);
if ((temp + sizeof(ctx->rx_ncm.ndp16)) > actlen) {
pr_debug("invalid DPT16 index\n");
goto error;
static void
cdc_ncm_speed_change(struct cdc_ncm_ctx *ctx,
- struct connection_speed_change *data)
+ struct usb_cdc_speed_change *data)
{
- uint32_t rx_speed = le32_to_cpu(data->USBitRate);
- uint32_t tx_speed = le32_to_cpu(data->DSBitRate);
+ uint32_t rx_speed = le32_to_cpu(data->DLBitRRate);
+ uint32_t tx_speed = le32_to_cpu(data->ULBitRate);
/*
* Currently the USB-NET API does not support reporting the actual
/* test for split data in 8-byte chunks */
if (test_and_clear_bit(EVENT_STS_SPLIT, &dev->flags)) {
cdc_ncm_speed_change(ctx,
- (struct connection_speed_change *)urb->transfer_buffer);
+ (struct usb_cdc_speed_change *)urb->transfer_buffer);
return;
}
break;
case USB_CDC_NOTIFY_SPEED_CHANGE:
- if (urb->actual_length <
- (sizeof(*event) + sizeof(struct connection_speed_change)))
+ if (urb->actual_length < (sizeof(*event) +
+ sizeof(struct usb_cdc_speed_change)))
set_bit(EVENT_STS_SPLIT, &dev->flags);
else
cdc_ncm_speed_change(ctx,
- (struct connection_speed_change *) &event[1]);
+ (struct usb_cdc_speed_change *) &event[1]);
break;
default:
USB_DEVICE(0x0fe6, 0x8101), /* DM9601 USB to Fast Ethernet Adapter */
.driver_info = (unsigned long)&dm9601_info,
},
+ {
+ USB_DEVICE(0x0fe6, 0x9700), /* DM9601 USB to Fast Ethernet Adapter */
+ .driver_info = (unsigned long)&dm9601_info,
+ },
{
USB_DEVICE(0x0a46, 0x9000), /* DM9000E */
.driver_info = (unsigned long)&dm9601_info,
static void hso_free_tiomget(struct hso_serial *serial)
{
- struct hso_tiocmget *tiocmget = serial->tiocmget;
+ struct hso_tiocmget *tiocmget;
+ if (!serial)
+ return;
+ tiocmget = serial->tiocmget;
if (tiocmget) {
- if (tiocmget->urb) {
- usb_free_urb(tiocmget->urb);
- tiocmget->urb = NULL;
- }
+ usb_free_urb(tiocmget->urb);
+ tiocmget->urb = NULL;
serial->tiocmget = NULL;
kfree(tiocmget);
-
}
}
if (urb != NULL) {
clear_bit (EVENT_RX_MEMORY, &dev->flags);
status = usb_autopm_get_interface(dev->intf);
- if (status < 0)
+ if (status < 0) {
+ usb_free_urb(urb);
goto fail_lowmem;
+ }
if (rx_submit (dev, urb, GFP_KERNEL) == -ENOLINK)
resched = 0;
usb_autopm_put_interface(dev->intf);
}
}
+static void virtnet_napi_enable(struct virtnet_info *vi)
+{
+ napi_enable(&vi->napi);
+
+ /* If all buffers were filled by other side before we napi_enabled, we
+ * won't get another interrupt, so process any outstanding packets
+ * now. virtnet_poll wants re-enable the queue, so we disable here.
+ * We synchronize against interrupts via NAPI_STATE_SCHED */
+ if (napi_schedule_prep(&vi->napi)) {
+ virtqueue_disable_cb(vi->rvq);
+ __napi_schedule(&vi->napi);
+ }
+}
+
static void refill_work(struct work_struct *work)
{
struct virtnet_info *vi;
vi = container_of(work, struct virtnet_info, refill.work);
napi_disable(&vi->napi);
still_empty = !try_fill_recv(vi, GFP_KERNEL);
- napi_enable(&vi->napi);
+ virtnet_napi_enable(vi);
/* In theory, this can happen: if we don't get any buffers in
* we will *never* try to fill again. */
{
struct virtnet_info *vi = netdev_priv(dev);
- napi_enable(&vi->napi);
-
- /* If all buffers were filled by other side before we napi_enabled, we
- * won't get another interrupt, so process any outstanding packets
- * now. virtnet_poll wants re-enable the queue, so we disable here.
- * We synchronize against interrupts via NAPI_STATE_SCHED */
- if (napi_schedule_prep(&vi->napi)) {
- virtqueue_disable_cb(vi->rvq);
- __napi_schedule(&vi->napi);
- }
+ virtnet_napi_enable(vi);
return 0;
}
return 0;
}
+/*
+ * Wait for synth to settle
+ */
+static void ath5k_hw_wait_for_synth(struct ath5k_hw *ah,
+ struct ieee80211_channel *channel)
+{
+ /*
+ * On 5211+ read activation -> rx delay
+ * and use it (100ns steps).
+ */
+ if (ah->ah_version != AR5K_AR5210) {
+ u32 delay;
+ delay = ath5k_hw_reg_read(ah, AR5K_PHY_RX_DELAY) &
+ AR5K_PHY_RX_DELAY_M;
+ delay = (channel->hw_value & CHANNEL_CCK) ?
+ ((delay << 2) / 22) : (delay / 10);
+ if (ah->ah_bwmode == AR5K_BWMODE_10MHZ)
+ delay = delay << 1;
+ if (ah->ah_bwmode == AR5K_BWMODE_5MHZ)
+ delay = delay << 2;
+ /* XXX: /2 on turbo ? Let's be safe
+ * for now */
+ udelay(100 + delay);
+ } else {
+ mdelay(1);
+ }
+}
+
/**********************\
* RF Gain optimization *
case AR5K_RF5111:
ret = ath5k_hw_rf5111_channel(ah, channel);
break;
+ case AR5K_RF2317:
case AR5K_RF2425:
ret = ath5k_hw_rf2425_channel(ah, channel);
break;
/* Failed */
if (i >= 100)
return -EIO;
+
+ /* Set channel and wait for synth */
+ ret = ath5k_hw_channel(ah, channel);
+ if (ret)
+ return ret;
+
+ ath5k_hw_wait_for_synth(ah, channel);
}
/*
if (ret)
return ret;
+ /* Write OFDM timings on 5212*/
+ if (ah->ah_version == AR5K_AR5212 &&
+ channel->hw_value & CHANNEL_OFDM) {
+
+ ret = ath5k_hw_write_ofdm_timings(ah, channel);
+ if (ret)
+ return ret;
+
+ /* Spur info is available only from EEPROM versions
+ * greater than 5.3, but the EEPROM routines will use
+ * static values for older versions */
+ if (ah->ah_mac_srev >= AR5K_SREV_AR5424)
+ ath5k_hw_set_spur_mitigation_filter(ah,
+ channel);
+ }
+
+ /* If we used fast channel switching
+ * we are done, release RF bus and
+ * fire up NF calibration.
+ *
+ * Note: Only NF calibration due to
+ * channel change, not AGC calibration
+ * since AGC is still running !
+ */
+ if (fast) {
+ /*
+ * Release RF Bus grant
+ */
+ AR5K_REG_DISABLE_BITS(ah, AR5K_PHY_RFBUS_REQ,
+ AR5K_PHY_RFBUS_REQ_REQUEST);
+
+ /*
+ * Start NF calibration
+ */
+ AR5K_REG_ENABLE_BITS(ah, AR5K_PHY_AGCCTL,
+ AR5K_PHY_AGCCTL_NF);
+
+ return ret;
+ }
+
/*
* For 5210 we do all initialization using
* initvals, so we don't have to modify
* any settings (5210 also only supports
* a/aturbo modes)
*/
- if ((ah->ah_version != AR5K_AR5210) && !fast) {
+ if (ah->ah_version != AR5K_AR5210) {
/*
* Write initial RF gain settings
if (ret)
return ret;
- /* Write OFDM timings on 5212*/
- if (ah->ah_version == AR5K_AR5212 &&
- channel->hw_value & CHANNEL_OFDM) {
-
- ret = ath5k_hw_write_ofdm_timings(ah, channel);
- if (ret)
- return ret;
-
- /* Spur info is available only from EEPROM versions
- * greater than 5.3, but the EEPROM routines will use
- * static values for older versions */
- if (ah->ah_mac_srev >= AR5K_SREV_AR5424)
- ath5k_hw_set_spur_mitigation_filter(ah,
- channel);
- }
-
/*Enable/disable 802.11b mode on 5111
(enable 2111 frequency converter + CCK)*/
if (ah->ah_radio == AR5K_RF5111) {
*/
ath5k_hw_reg_write(ah, AR5K_PHY_ACT_ENABLE, AR5K_PHY_ACT);
+ ath5k_hw_wait_for_synth(ah, channel);
+
/*
- * On 5211+ read activation -> rx delay
- * and use it.
+ * Perform ADC test to see if baseband is ready
+ * Set tx hold and check adc test register
*/
- if (ah->ah_version != AR5K_AR5210) {
- u32 delay;
- delay = ath5k_hw_reg_read(ah, AR5K_PHY_RX_DELAY) &
- AR5K_PHY_RX_DELAY_M;
- delay = (channel->hw_value & CHANNEL_CCK) ?
- ((delay << 2) / 22) : (delay / 10);
- if (ah->ah_bwmode == AR5K_BWMODE_10MHZ)
- delay = delay << 1;
- if (ah->ah_bwmode == AR5K_BWMODE_5MHZ)
- delay = delay << 2;
- /* XXX: /2 on turbo ? Let's be safe
- * for now */
- udelay(100 + delay);
- } else {
- mdelay(1);
- }
-
- if (fast)
- /*
- * Release RF Bus grant
- */
- AR5K_REG_DISABLE_BITS(ah, AR5K_PHY_RFBUS_REQ,
- AR5K_PHY_RFBUS_REQ_REQUEST);
- else {
- /*
- * Perform ADC test to see if baseband is ready
- * Set tx hold and check adc test register
- */
- phy_tst1 = ath5k_hw_reg_read(ah, AR5K_PHY_TST1);
- ath5k_hw_reg_write(ah, AR5K_PHY_TST1_TXHOLD, AR5K_PHY_TST1);
- for (i = 0; i <= 20; i++) {
- if (!(ath5k_hw_reg_read(ah, AR5K_PHY_ADC_TEST) & 0x10))
- break;
- udelay(200);
- }
- ath5k_hw_reg_write(ah, phy_tst1, AR5K_PHY_TST1);
+ phy_tst1 = ath5k_hw_reg_read(ah, AR5K_PHY_TST1);
+ ath5k_hw_reg_write(ah, AR5K_PHY_TST1_TXHOLD, AR5K_PHY_TST1);
+ for (i = 0; i <= 20; i++) {
+ if (!(ath5k_hw_reg_read(ah, AR5K_PHY_ADC_TEST) & 0x10))
+ break;
+ udelay(200);
}
+ ath5k_hw_reg_write(ah, phy_tst1, AR5K_PHY_TST1);
/*
* Start automatic gain control calibration
#include <linux/device.h>
#include <linux/leds.h>
#include <linux/completion.h>
-#include <linux/pm_qos_params.h>
#include "debug.h"
#include "common.h"
#define A_MAX(a, b) ((a) > (b) ? (a) : (b))
-#define ATH9K_PM_QOS_DEFAULT_VALUE 55
-
#define TSF_TO_TU(_h,_l) \
((((u32)(_h)) << 22) | (((u32)(_l)) >> 10))
struct ath_buf_state {
u8 bf_type;
u8 bfs_paprd;
+ unsigned long bfs_paprd_timestamp;
enum ath9k_internal_frame_type bfs_ftype;
};
struct work_struct paprd_work;
struct work_struct hw_check_work;
struct completion paprd_complete;
- bool paprd_pending;
u32 intrstatus;
u32 sc_flags; /* SC_OP_* */
struct ath_descdma txsdma;
struct ath_ant_comb ant_comb;
-
- struct pm_qos_request_list pm_qos_req;
};
struct ath_wiphy {
extern struct ieee80211_ops ath9k_ops;
extern int ath9k_modparam_nohwcrypt;
extern int led_blink;
-extern int ath9k_pm_qos_value;
extern bool is_ath9k_unloaded;
irqreturn_t ath_isr(int irq, void *dev);
struct tx_buf *tx_buf = NULL;
struct sk_buff *nskb = NULL;
int ret = 0, i;
- u16 *hdr, tx_skb_cnt = 0;
+ u16 tx_skb_cnt = 0;
u8 *buf;
+ __le16 *hdr;
if (hif_dev->tx.tx_skb_cnt == 0)
return 0;
buf = tx_buf->buf;
buf += tx_buf->offset;
- hdr = (u16 *)buf;
- *hdr++ = nskb->len;
- *hdr++ = ATH_USB_TX_STREAM_MODE_TAG;
+ hdr = (__le16 *)buf;
+ *hdr++ = cpu_to_le16(nskb->len);
+ *hdr++ = cpu_to_le16(ATH_USB_TX_STREAM_MODE_TAG);
buf += 4;
memcpy(buf, nskb->data, nskb->len);
tx_buf->len = nskb->len + 4;
module_param_named(btcoex_enable, ath9k_btcoex_enable, int, 0444);
MODULE_PARM_DESC(btcoex_enable, "Enable wifi-BT coexistence");
-int ath9k_pm_qos_value = ATH9K_PM_QOS_DEFAULT_VALUE;
-module_param_named(pmqos, ath9k_pm_qos_value, int, S_IRUSR | S_IRGRP | S_IROTH);
-MODULE_PARM_DESC(pmqos, "User specified PM-QOS value");
-
bool is_ath9k_unloaded;
/* We use the hw_value as an index into our private channel structure */
ath_init_leds(sc);
ath_start_rfkill_poll(sc);
- pm_qos_add_request(&sc->pm_qos_req, PM_QOS_CPU_DMA_LATENCY,
- PM_QOS_DEFAULT_VALUE);
-
return 0;
error_world:
}
ieee80211_unregister_hw(hw);
- pm_qos_remove_request(&sc->pm_qos_req);
ath_rx_cleanup(sc);
ath_tx_cleanup(sc);
ath9k_deinit_softc(sc);
struct ath_common *common = ath9k_hw_common(ah);
if (!(ints & ATH9K_INT_GLOBAL))
- ath9k_hw_enable_interrupts(ah);
+ ath9k_hw_disable_interrupts(ah);
ath_dbg(common, ATH_DBG_INTERRUPT, "0x%x => 0x%x\n", omask, ints);
REG_CLR_BIT(ah, AR_IMR_S5, AR_IMR_S5_TIM_TIMER);
}
- ath9k_hw_enable_interrupts(ah);
+ if (ints & ATH9K_INT_GLOBAL)
+ ath9k_hw_enable_interrupts(ah);
return;
}
tx_info->control.rates[1].idx = -1;
init_completion(&sc->paprd_complete);
- sc->paprd_pending = true;
txctl.paprd = BIT(chain);
if (ath_tx_start(hw, skb, &txctl) != 0) {
time_left = wait_for_completion_timeout(&sc->paprd_complete,
msecs_to_jiffies(ATH_PAPRD_TIMEOUT));
- sc->paprd_pending = false;
if (!time_left)
ath_dbg(ath9k_hw_common(sc->sc_ah), ATH_DBG_CALIBRATE,
ath9k_btcoex_timer_resume(sc);
}
- /* User has the option to provide pm-qos value as a module
- * parameter rather than using the default value of
- * 'ATH9K_PM_QOS_DEFAULT_VALUE'.
- */
- pm_qos_update_request(&sc->pm_qos_req, ath9k_pm_qos_value);
-
if (ah->caps.pcie_lcr_extsync_en && common->bus_ops->extn_synch_en)
common->bus_ops->extn_synch_en(common);
sc->sc_flags |= SC_OP_INVALID;
- pm_qos_update_request(&sc->pm_qos_req, PM_QOS_DEFAULT_VALUE);
-
mutex_unlock(&sc->mutex);
ath_dbg(common, ATH_DBG_CONFIG, "Driver halt\n");
ar9003_hw_set_paprd_txdesc(sc->sc_ah, bf->bf_desc,
bf->bf_state.bfs_paprd);
+ if (txctl->paprd)
+ bf->bf_state.bfs_paprd_timestamp = jiffies;
+
ath_tx_send_normal(sc, txctl->txq, tid, &bf_head);
}
bf->bf_buf_addr = 0;
if (bf->bf_state.bfs_paprd) {
- if (!sc->paprd_pending)
+ if (time_after(jiffies,
+ bf->bf_state.bfs_paprd_timestamp +
+ msecs_to_jiffies(ATH_PAPRD_TIMEOUT)))
dev_kfree_skb_any(skb);
else
complete(&sc->paprd_complete);
cam = ieee80211_check_tim(tim_ie, tim_len, ar->common.curaid);
/* 2. Maybe the AP wants to send multicast/broadcast data? */
- cam = !!(tim_ie->bitmap_ctrl & 0x01);
+ cam |= !!(tim_ie->bitmap_ctrl & 0x01);
if (!cam) {
/* back to low-power land. */
{ USB_DEVICE(0x057c, 0x8402) },
/* Qwest/Actiontec 802AIN Wireless N USB Network Adapter */
{ USB_DEVICE(0x1668, 0x1200) },
+ /* Airlive X.USB a/b/g/n */
+ { USB_DEVICE(0x1b75, 0x9170) },
/* terminate */
{}
}
#endif
-/**
- * iwl3945_good_plcp_health - checks for plcp error.
- *
- * When the plcp error is exceeding the thresholds, reset the radio
- * to improve the throughput.
- */
-static bool iwl3945_good_plcp_health(struct iwl_priv *priv,
- struct iwl_rx_packet *pkt)
-{
- bool rc = true;
- struct iwl3945_notif_statistics current_stat;
- int combined_plcp_delta;
- unsigned int plcp_msec;
- unsigned long plcp_received_jiffies;
-
- if (priv->cfg->base_params->plcp_delta_threshold ==
- IWL_MAX_PLCP_ERR_THRESHOLD_DISABLE) {
- IWL_DEBUG_RADIO(priv, "plcp_err check disabled\n");
- return rc;
- }
- memcpy(¤t_stat, pkt->u.raw, sizeof(struct
- iwl3945_notif_statistics));
- /*
- * check for plcp_err and trigger radio reset if it exceeds
- * the plcp error threshold plcp_delta.
- */
- plcp_received_jiffies = jiffies;
- plcp_msec = jiffies_to_msecs((long) plcp_received_jiffies -
- (long) priv->plcp_jiffies);
- priv->plcp_jiffies = plcp_received_jiffies;
- /*
- * check to make sure plcp_msec is not 0 to prevent division
- * by zero.
- */
- if (plcp_msec) {
- combined_plcp_delta =
- (le32_to_cpu(current_stat.rx.ofdm.plcp_err) -
- le32_to_cpu(priv->_3945.statistics.rx.ofdm.plcp_err));
-
- if ((combined_plcp_delta > 0) &&
- ((combined_plcp_delta * 100) / plcp_msec) >
- priv->cfg->base_params->plcp_delta_threshold) {
- /*
- * if plcp_err exceed the threshold, the following
- * data is printed in csv format:
- * Text: plcp_err exceeded %d,
- * Received ofdm.plcp_err,
- * Current ofdm.plcp_err,
- * combined_plcp_delta,
- * plcp_msec
- */
- IWL_DEBUG_RADIO(priv, "plcp_err exceeded %u, "
- "%u, %d, %u mSecs\n",
- priv->cfg->base_params->plcp_delta_threshold,
- le32_to_cpu(current_stat.rx.ofdm.plcp_err),
- combined_plcp_delta, plcp_msec);
- /*
- * Reset the RF radio due to the high plcp
- * error rate
- */
- rc = false;
- }
- }
- return rc;
-}
-
void iwl3945_hw_rx_statistics(struct iwl_priv *priv,
struct iwl_rx_mem_buffer *rxb)
{
.isr_ops = {
.isr = iwl_isr_legacy,
},
- .check_plcp_health = iwl3945_good_plcp_health,
.debugfs_ops = {
.rx_stats_read = iwl3945_ucode_rx_stats_read,
#include "iwl-agn-debugfs.h"
/* Highest firmware API version supported */
-#define IWL5000_UCODE_API_MAX 2
+#define IWL5000_UCODE_API_MAX 5
#define IWL5150_UCODE_API_MAX 2
/* Lowest firmware API version supported */
.fw_name_pre = IWL6050_FW_PRE, \
.ucode_api_max = IWL6050_UCODE_API_MAX, \
.ucode_api_min = IWL6050_UCODE_API_MIN, \
+ .valid_tx_ant = ANT_AB, /* .cfg overwrite */ \
+ .valid_rx_ant = ANT_AB, /* .cfg overwrite */ \
.ops = &iwl6050_ops, \
.eeprom_ver = EEPROM_6050_EEPROM_VERSION, \
.eeprom_calib_ver = EEPROM_6050_TX_POWER_VERSION, \
/* only Re-enable if disabled by irq */
if (test_bit(STATUS_INT_ENABLED, &priv->status))
iwl_enable_interrupts(priv);
+ /* Re-enable RF_KILL if it occurred */
+ else if (handled & CSR_INT_BIT_RF_KILL)
+ iwl_enable_rfkill_int(priv);
#ifdef CONFIG_IWLWIFI_DEBUG
if (iwl_get_debug_level(priv) & (IWL_DL_ISR)) {
/* only Re-enable if disabled by irq */
if (test_bit(STATUS_INT_ENABLED, &priv->status))
iwl_enable_interrupts(priv);
+ /* Re-enable RF_KILL if it occurred */
+ else if (handled & CSR_INT_BIT_RF_KILL)
+ iwl_enable_rfkill_int(priv);
}
/* the threshold ratio of actual_ack_cnt to expected_ack_cnt in percent */
while (i != idx) {
u16 len;
struct sk_buff *skb;
+ dma_addr_t dma_addr;
desc = &ring[i];
len = le16_to_cpu(desc->len);
skb = rx_buf[i];
len = priv->common.rx_mtu;
}
+ dma_addr = le32_to_cpu(desc->host_addr);
+ pci_dma_sync_single_for_cpu(priv->pdev, dma_addr,
+ priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE);
skb_put(skb, len);
if (p54_rx(dev, skb)) {
- pci_unmap_single(priv->pdev,
- le32_to_cpu(desc->host_addr),
- priv->common.rx_mtu + 32,
- PCI_DMA_FROMDEVICE);
+ pci_unmap_single(priv->pdev, dma_addr,
+ priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE);
rx_buf[i] = NULL;
- desc->host_addr = 0;
+ desc->host_addr = cpu_to_le32(0);
} else {
skb_trim(skb, 0);
+ pci_dma_sync_single_for_device(priv->pdev, dma_addr,
+ priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE);
desc->len = cpu_to_le16(priv->common.rx_mtu + 32);
}
{USB_DEVICE(0x1413, 0x5400)}, /* Telsey 802.11g USB2.0 Adapter */
{USB_DEVICE(0x1435, 0x0427)}, /* Inventel UR054G */
{USB_DEVICE(0x1668, 0x1050)}, /* Actiontec 802UIG-1 */
+ {USB_DEVICE(0x1740, 0x1000)}, /* Senao NUB-350 */
{USB_DEVICE(0x2001, 0x3704)}, /* DLink DWL-G122 rev A2 */
{USB_DEVICE(0x2001, 0x3705)}, /* D-Link DWL-G120 rev C1 */
{USB_DEVICE(0x413c, 0x5513)}, /* Dell WLA3310 USB Wireless Adapter */
__le32 mode;
int ret;
+ if (priv->device_type != RNDIS_BCM4320B)
+ return -ENOTSUPP;
+
netdev_dbg(usbdev->net, "%s(): %s, %d\n", __func__,
enabled ? "enabled" : "disabled",
timeout);
*/
rxdesc->flags |= RX_FLAG_IV_STRIPPED;
+ /*
+ * The hardware has already checked the Michael Mic and has
+ * stripped it from the frame. Signal this to mac80211.
+ */
+ rxdesc->flags |= RX_FLAG_MMIC_STRIPPED;
+
if (rxdesc->cipher_status == RX_CRYPTO_SUCCESS)
rxdesc->flags |= RX_FLAG_DECRYPTED;
else if (rxdesc->cipher_status == RX_CRYPTO_FAIL_MIC)
{ PCI_DEVICE(0x1814, 0x3390), PCI_DEVICE_DATA(&rt2800pci_ops) },
#endif
#ifdef CONFIG_RT2800PCI_RT35XX
+ { PCI_DEVICE(0x1432, 0x7711), PCI_DEVICE_DATA(&rt2800pci_ops) },
+ { PCI_DEVICE(0x1432, 0x7722), PCI_DEVICE_DATA(&rt2800pci_ops) },
{ PCI_DEVICE(0x1814, 0x3060), PCI_DEVICE_DATA(&rt2800pci_ops) },
{ PCI_DEVICE(0x1814, 0x3062), PCI_DEVICE_DATA(&rt2800pci_ops) },
{ PCI_DEVICE(0x1814, 0x3562), PCI_DEVICE_DATA(&rt2800pci_ops) },
*/
rxdesc->flags |= RX_FLAG_IV_STRIPPED;
+ /*
+ * The hardware has already checked the Michael Mic and has
+ * stripped it from the frame. Signal this to mac80211.
+ */
+ rxdesc->flags |= RX_FLAG_MMIC_STRIPPED;
+
if (rxdesc->cipher_status == RX_CRYPTO_SUCCESS)
rxdesc->flags |= RX_FLAG_DECRYPTED;
else if (rxdesc->cipher_status == RX_CRYPTO_FAIL_MIC)
if (changed & BSS_CHANGED_BEACON) {
beacon = ieee80211_beacon_get(hw, vif);
+ if (!beacon)
+ goto out_sleep;
+
ret = wl1251_cmd_template_set(wl, CMD_BEACON, beacon->data,
beacon->len);
#
menuconfig NFC_DEVICES
- bool "NFC devices"
+ bool "Near Field Communication (NFC) devices"
default n
---help---
You'll have to say Y if your computer contains an NFC device that
struct pn544_info {
struct miscdevice miscdev;
struct i2c_client *i2c_dev;
- struct regulator_bulk_data regs[2];
+ struct regulator_bulk_data regs[3];
enum pn544_state state;
wait_queue_head_t read_wait;
static const char reg_vdd_io[] = "Vdd_IO";
static const char reg_vbat[] = "VBat";
+static const char reg_vsim[] = "VSim";
/* sysfs interface */
static ssize_t pn544_test(struct device *dev,
info->regs[0].supply = reg_vdd_io;
info->regs[1].supply = reg_vbat;
+ info->regs[2].supply = reg_vsim;
r = regulator_bulk_get(&client->dev, ARRAY_SIZE(info->regs),
info->regs);
if (r < 0)
(p)->unique_id = of_pdt_unique_id++; \
} while (0)
-static inline const char *of_pdt_node_name(struct device_node *dp)
+static char * __init of_pdt_build_full_name(struct device_node *dp)
{
- return dp->path_component_name;
+ int len, ourlen, plen;
+ char *n;
+
+ dp->path_component_name = build_path_component(dp);
+
+ plen = strlen(dp->parent->full_name);
+ ourlen = strlen(dp->path_component_name);
+ len = ourlen + plen + 2;
+
+ n = prom_early_alloc(len);
+ strcpy(n, dp->parent->full_name);
+ if (!of_node_is_root(dp->parent)) {
+ strcpy(n + plen, "/");
+ plen++;
+ }
+ strcpy(n + plen, dp->path_component_name);
+
+ return n;
}
-#else
+#else /* CONFIG_SPARC */
static inline void of_pdt_incr_unique_id(void *p) { }
static inline void irq_trans_init(struct device_node *dp) { }
-static inline const char *of_pdt_node_name(struct device_node *dp)
+static char * __init of_pdt_build_full_name(struct device_node *dp)
{
- return dp->name;
+ static int failsafe_id = 0; /* for generating unique names on failure */
+ char *buf;
+ int len;
+
+ if (of_pdt_prom_ops->pkg2path(dp->phandle, NULL, 0, &len))
+ goto failsafe;
+
+ buf = prom_early_alloc(len + 1);
+ if (of_pdt_prom_ops->pkg2path(dp->phandle, buf, len, &len))
+ goto failsafe;
+ return buf;
+
+ failsafe:
+ buf = prom_early_alloc(strlen(dp->parent->full_name) +
+ strlen(dp->name) + 16);
+ sprintf(buf, "%s/%s@unknown%i",
+ of_node_is_root(dp->parent) ? "" : dp->parent->full_name,
+ dp->name, failsafe_id++);
+ pr_err("%s: pkg2path failed; assigning %s\n", __func__, buf);
+ return buf;
}
#endif /* !CONFIG_SPARC */
return buf;
}
-static char * __init of_pdt_try_pkg2path(phandle node)
-{
- char *res, *buf = NULL;
- int len;
-
- if (!of_pdt_prom_ops->pkg2path)
- return NULL;
-
- if (of_pdt_prom_ops->pkg2path(node, buf, 0, &len))
- return NULL;
- buf = prom_early_alloc(len + 1);
- if (of_pdt_prom_ops->pkg2path(node, buf, len, &len)) {
- pr_err("%s: package-to-path failed\n", __func__);
- return NULL;
- }
-
- res = strrchr(buf, '/');
- if (!res) {
- pr_err("%s: couldn't find / in %s\n", __func__, buf);
- return NULL;
- }
- return res+1;
-}
-
-/*
- * When fetching the node's name, first try using package-to-path; if
- * that fails (either because the arch hasn't supplied a PROM callback,
- * or some other random failure), fall back to just looking at the node's
- * 'name' property.
- */
-static char * __init of_pdt_build_name(phandle node)
-{
- char *buf;
-
- buf = of_pdt_try_pkg2path(node);
- if (!buf)
- buf = of_pdt_get_one_property(node, "name");
-
- return buf;
-}
-
static struct device_node * __init of_pdt_create_node(phandle node,
struct device_node *parent)
{
kref_init(&dp->kref);
- dp->name = of_pdt_build_name(node);
+ dp->name = of_pdt_get_one_property(node, "name");
dp->type = of_pdt_get_one_property(node, "device_type");
dp->phandle = node;
return dp;
}
-static char * __init of_pdt_build_full_name(struct device_node *dp)
-{
- int len, ourlen, plen;
- char *n;
-
- plen = strlen(dp->parent->full_name);
- ourlen = strlen(of_pdt_node_name(dp));
- len = ourlen + plen + 2;
-
- n = prom_early_alloc(len);
- strcpy(n, dp->parent->full_name);
- if (!of_node_is_root(dp->parent)) {
- strcpy(n + plen, "/");
- plen++;
- }
- strcpy(n + plen, of_pdt_node_name(dp));
-
- return n;
-}
-
static struct device_node * __init of_pdt_build_tree(struct device_node *parent,
phandle node,
struct device_node ***nextp)
*(*nextp) = dp;
*nextp = &dp->allnext;
-#if defined(CONFIG_SPARC)
- dp->path_component_name = build_path_component(dp);
-#endif
dp->full_name = of_pdt_build_full_name(dp);
dp->child = of_pdt_build_tree(dp,
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/capability.h>
+#include <linux/security.h>
#include <linux/pci-aspm.h>
#include <linux/slab.h>
#include "pci.h"
u8 *data = (u8*) buf;
/* Several chips lock up trying to read undefined config space */
- if (cap_raised(filp->f_cred->cap_effective, CAP_SYS_ADMIN)) {
+ if (security_capable(filp->f_cred, CAP_SYS_ADMIN) == 0) {
size = dev->cfg_size;
} else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) {
size = 128;
#ifdef CONFIG_PCI_MSI
static int pci_frontend_enable_msix(struct pci_dev *dev,
- int **vector, int nvec)
+ int vector[], int nvec)
{
int err;
int i;
if (likely(!err)) {
if (likely(!op.value)) {
/* we get the result */
- for (i = 0; i < nvec; i++)
- *(*vector+i) = op.msix_entries[i].vector;
- return 0;
+ for (i = 0; i < nvec; i++) {
+ if (op.msix_entries[i].vector <= 0) {
+ dev_warn(&dev->dev, "MSI-X entry %d is invalid: %d!\n",
+ i, op.msix_entries[i].vector);
+ err = -EINVAL;
+ vector[i] = -1;
+ continue;
+ }
+ vector[i] = op.msix_entries[i].vector;
+ }
} else {
printk(KERN_DEBUG "enable msix get value %x\n",
op.value);
- return op.value;
}
} else {
dev_err(&dev->dev, "enable msix get err %x\n", err);
- return err;
}
+ return err;
}
static void pci_frontend_disable_msix(struct pci_dev *dev)
dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
}
-static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
+static int pci_frontend_enable_msi(struct pci_dev *dev, int vector[])
{
int err;
struct xen_pci_op op = {
err = do_pci_op(pdev, &op);
if (likely(!err)) {
- *(*vector) = op.value;
+ vector[0] = op.value;
+ if (op.value <= 0) {
+ dev_warn(&dev->dev, "MSI entry is invalid: %d!\n",
+ op.value);
+ err = -EINVAL;
+ vector[0] = -1;
+ }
} else {
dev_err(&dev->dev, "pci frontend enable msi failed for dev "
"%x:%x\n", op.bus, op.devfn);
pcifront_free_roots(pdev);
- /*For PCIE_AER error handling job*/
- flush_scheduled_work();
+ cancel_work_sync(&pdev->op_work);
if (pdev->irq >= 0)
unbind_from_irqhandler(pdev->irq, pdev);
flags |= CONF_ENABLE_IOCARD;
if (flags & CONF_ENABLE_IOCARD)
s->socket.flags |= SS_IOCARD;
+ if (flags & CONF_ENABLE_ZVCARD)
+ s->socket.flags |= SS_ZVCARD | SS_IOCARD;
if (flags & CONF_ENABLE_SPKR) {
s->socket.flags |= SS_SPKR_ENA;
status = CCSR_AUDIO_ENA;
}
#endif
-static void pxa2xx_configure_sockets(struct device *dev)
+void pxa2xx_configure_sockets(struct device *dev)
{
struct pcmcia_low_level *ops = dev->platform_data;
/*
int pxa2xx_drv_pcmcia_add_one(struct soc_pcmcia_socket *skt);
void pxa2xx_drv_pcmcia_ops(struct pcmcia_low_level *ops);
+void pxa2xx_configure_sockets(struct device *dev);
{
int ret;
+ if (!machine_is_colibri() && !machine_is_colibri320())
+ return -ENODEV;
+
colibri_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1);
if (!colibri_pcmcia_device)
return -ENOMEM;
lubbock_set_misc_wr((1 << 15) | (1 << 14), 0);
pxa2xx_drv_pcmcia_ops(&lubbock_pcmcia_ops);
+ pxa2xx_configure_sockets(&sadev->dev);
ret = sa1111_pcmcia_add(sadev, &lubbock_pcmcia_ops,
pxa2xx_drv_pcmcia_add_one);
}
config IDEAPAD_LAPTOP
tristate "Lenovo IdeaPad Laptop Extras"
depends on ACPI
- depends on RFKILL
+ depends on RFKILL && INPUT
select INPUT_SPARSEKMAP
help
This is a driver for the rfkill switches on Lenovo IdeaPad netbooks.
*/
#define AMW0_GUID1 "67C3371D-95A3-4C37-BB61-DD47B491DAAB"
#define AMW0_GUID2 "431F16ED-0C2B-444C-B267-27DEB140CF9C"
-#define WMID_GUID1 "6AF4F258-B401-42fd-BE91-3D4AC2D7C0D3"
+#define WMID_GUID1 "6AF4F258-B401-42FD-BE91-3D4AC2D7C0D3"
#define WMID_GUID2 "95764E09-FB56-4e83-B31A-37761F60994A"
#define WMID_GUID3 "61EF69EA-865C-4BC3-A502-A0DEBA0CB531"
return -EINVAL;
return count;
}
-static DEVICE_ATTR(threeg, S_IWUGO | S_IRUGO | S_IWUSR, show_bool_threeg,
+static DEVICE_ATTR(threeg, S_IRUGO | S_IWUSR, show_bool_threeg,
set_bool_threeg);
static ssize_t show_interface(struct device *dev, struct device_attribute *attr,
struct proc_dir_entry *proc;
mode_t mode;
- /*
- * If parameter uid or gid is not changed, keep the default setting for
- * our proc entries (-rw-rw-rw-) else, it means we care about security,
- * and then set to -rw-rw----
- */
-
if ((asus_uid == 0) && (asus_gid == 0)) {
- mode = S_IFREG | S_IRUGO | S_IWUGO;
+ mode = S_IFREG | S_IRUGO | S_IWUSR | S_IWGRP;
} else {
mode = S_IFREG | S_IRUSR | S_IRGRP | S_IWUSR | S_IWGRP;
printk(KERN_WARNING " asus_uid and asus_gid parameters are "
dell_send_request(buffer, 17, 11);
/* If the hardware switch controls this radio, and the hardware
- switch is disabled, don't allow changing the software state */
+ switch is disabled, don't allow changing the software state.
+ If the hardware switch is reported as not supported, always
+ fire the SMI to toggle the killswitch. */
if ((hwswitch_state & BIT(hwswitch_bit)) &&
- !(buffer->output[1] & BIT(16))) {
+ !(buffer->output[1] & BIT(16)) &&
+ (buffer->output[1] & BIT(0))) {
ret = -EINVAL;
goto out;
}
static void dell_update_rfkill(struct work_struct *ignored)
{
+ int status;
+
+ get_buffer();
+ dell_send_request(buffer, 17, 11);
+ status = buffer->output[1];
+ release_buffer();
+
+ /* if hardware rfkill is not supported, set it explicitly */
+ if (!(status & BIT(0))) {
+ if (wifi_rfkill)
+ dell_rfkill_set((void *)1, !((status & BIT(17)) >> 17));
+ if (bluetooth_rfkill)
+ dell_rfkill_set((void *)2, !((status & BIT(18)) >> 18));
+ if (wwan_rfkill)
+ dell_rfkill_set((void *)3, !((status & BIT(19)) >> 19));
+ }
+
if (wifi_rfkill)
dell_rfkill_query(wifi_rfkill, (void *)1);
if (bluetooth_rfkill)
#define GPOSW_DOU 0x08
#define GPOSW_RDRV 0x30
+#define GPIO_UPDATE_TYPE 0x80000000
#define NUM_GPIO 24
-struct pmic_gpio_irq {
- spinlock_t lock;
- u32 trigger[NUM_GPIO];
- u32 dirty;
- struct work_struct work;
-};
-
-
struct pmic_gpio {
+ struct mutex buslock;
struct gpio_chip chip;
- struct pmic_gpio_irq irqtypes;
void *gpiointr;
int irq;
unsigned irq_base;
+ unsigned int update_type;
+ u32 trigger_type;
};
-static void pmic_program_irqtype(int gpio, int type)
-{
- if (type & IRQ_TYPE_EDGE_RISING)
- intel_scu_ipc_update_register(GPIO0 + gpio, 0x20, 0x20);
- else
- intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x20);
-
- if (type & IRQ_TYPE_EDGE_FALLING)
- intel_scu_ipc_update_register(GPIO0 + gpio, 0x10, 0x10);
- else
- intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x10);
-};
-
-static void pmic_irqtype_work(struct work_struct *work)
-{
- struct pmic_gpio_irq *t =
- container_of(work, struct pmic_gpio_irq, work);
- unsigned long flags;
- int i;
- u16 type;
-
- spin_lock_irqsave(&t->lock, flags);
- /* As we drop the lock, we may need multiple scans if we race the
- pmic_irq_type function */
- while (t->dirty) {
- /*
- * For each pin that has the dirty bit set send an IPC
- * message to configure the hardware via the PMIC
- */
- for (i = 0; i < NUM_GPIO; i++) {
- if (!(t->dirty & (1 << i)))
- continue;
- t->dirty &= ~(1 << i);
- /* We can't trust the array entry or dirty
- once the lock is dropped */
- type = t->trigger[i];
- spin_unlock_irqrestore(&t->lock, flags);
- pmic_program_irqtype(i, type);
- spin_lock_irqsave(&t->lock, flags);
- }
- }
- spin_unlock_irqrestore(&t->lock, flags);
-}
-
static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
{
if (offset > 8) {
1 << (offset - 16));
}
-static int pmic_irq_type(unsigned irq, unsigned type)
+/*
+ * This is called from genirq with pg->buslock locked and
+ * irq_desc->lock held. We can not access the scu bus here, so we
+ * store the change and update in the bus_sync_unlock() function below
+ */
+static int pmic_irq_type(struct irq_data *data, unsigned type)
{
- struct pmic_gpio *pg = get_irq_chip_data(irq);
- u32 gpio = irq - pg->irq_base;
- unsigned long flags;
+ struct pmic_gpio *pg = irq_data_get_irq_chip_data(data);
+ u32 gpio = data->irq - pg->irq_base;
if (gpio >= pg->chip.ngpio)
return -EINVAL;
- spin_lock_irqsave(&pg->irqtypes.lock, flags);
- pg->irqtypes.trigger[gpio] = type;
- pg->irqtypes.dirty |= (1 << gpio);
- spin_unlock_irqrestore(&pg->irqtypes.lock, flags);
- schedule_work(&pg->irqtypes.work);
+ pg->trigger_type = type;
+ pg->update_type = gpio | GPIO_UPDATE_TYPE;
return 0;
}
-
-
static int pmic_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
{
struct pmic_gpio *pg = container_of(chip, struct pmic_gpio, chip);
}
/* the gpiointr register is read-clear, so just do nothing. */
-static void pmic_irq_unmask(unsigned irq)
-{
-};
+static void pmic_irq_unmask(struct irq_data *data) { }
-static void pmic_irq_mask(unsigned irq)
-{
-};
+static void pmic_irq_mask(struct irq_data *data) { }
static struct irq_chip pmic_irqchip = {
.name = "PMIC-GPIO",
- .mask = pmic_irq_mask,
- .unmask = pmic_irq_unmask,
- .set_type = pmic_irq_type,
+ .irq_mask = pmic_irq_mask,
+ .irq_unmask = pmic_irq_unmask,
+ .irq_set_type = pmic_irq_type,
};
-static void pmic_irq_handler(unsigned irq, struct irq_desc *desc)
+static irqreturn_t pmic_irq_handler(int irq, void *data)
{
- struct pmic_gpio *pg = (struct pmic_gpio *)get_irq_data(irq);
+ struct pmic_gpio *pg = data;
u8 intsts = *((u8 *)pg->gpiointr + 4);
int gpio;
+ irqreturn_t ret = IRQ_NONE;
for (gpio = 0; gpio < 8; gpio++) {
if (intsts & (1 << gpio)) {
pr_debug("pmic pin %d triggered\n", gpio);
generic_handle_irq(pg->irq_base + gpio);
+ ret = IRQ_HANDLED;
}
}
-
- if (desc->chip->irq_eoi)
- desc->chip->irq_eoi(irq_get_irq_data(irq));
- else
- dev_warn(pg->chip.dev, "missing EOI handler for irq %d\n", irq);
+ return ret;
}
static int __devinit platform_pmic_gpio_probe(struct platform_device *pdev)
pg->chip.can_sleep = 1;
pg->chip.dev = dev;
- INIT_WORK(&pg->irqtypes.work, pmic_irqtype_work);
- spin_lock_init(&pg->irqtypes.lock);
+ mutex_init(&pg->buslock);
pg->chip.dev = dev;
retval = gpiochip_add(&pg->chip);
printk(KERN_ERR "%s: Can not add pmic gpio chip.\n", __func__);
goto err;
}
- set_irq_data(pg->irq, pg);
- set_irq_chained_handler(pg->irq, pmic_irq_handler);
+
+ retval = request_irq(pg->irq, pmic_irq_handler, 0, "pmic", pg);
+ if (retval) {
+ printk(KERN_WARNING "pmic: Interrupt request failed\n");
+ goto err;
+ }
+
for (i = 0; i < 8; i++) {
set_irq_chip_and_handler_name(i + pg->irq_base, &pmic_irqchip,
handle_simple_irq, "demux");
return -EINVAL; \
return count; \
} \
-static DEVICE_ATTR(value, S_IWUGO | S_IRUGO | S_IWUSR, \
+static DEVICE_ATTR(value, S_IRUGO | S_IWUSR, \
show_bool_##value, set_bool_##value);
show_set_bool(wireless, TC1100_INSTANCE_WIRELESS);
if (keycode != KEY_RESERVED) {
mutex_lock(&tpacpi_inputdev_send_mutex);
+ input_event(tpacpi_inputdev, EV_MSC, MSC_SCAN, scancode);
input_report_key(tpacpi_inputdev, keycode, 1);
- if (keycode == KEY_UNKNOWN)
- input_event(tpacpi_inputdev, EV_MSC, MSC_SCAN,
- scancode);
input_sync(tpacpi_inputdev);
+ input_event(tpacpi_inputdev, EV_MSC, MSC_SCAN, scancode);
input_report_key(tpacpi_inputdev, keycode, 0);
- if (keycode == KEY_UNKNOWN)
- input_event(tpacpi_inputdev, EV_MSC, MSC_SCAN,
- scancode);
input_sync(tpacpi_inputdev);
mutex_unlock(&tpacpi_inputdev_send_mutex);
config PPS_GENERATOR_PARPORT
tristate "Parallel port PPS signal generator"
- depends on PARPORT
+ depends on PARPORT && BROKEN
help
If you say yes here you get support for a PPS signal generator which
utilizes STROBE pin of a parallel port to send PPS signals. It uses
{
unsigned long flags;
int captured = 0;
- struct pps_ktime ts_real;
+ struct pps_ktime ts_real = { .sec = 0, .nsec = 0, .flags = 0 };
/* check event type */
BUG_ON((event & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR)) == 0);
/* Several chips lock up trying to read undefined config space */
if (capable(CAP_SYS_ADMIN))
- size = 0x200000;
+ size = RIO_MAINT_SPACE_SZ;
- if (off > size)
+ if (off >= size)
return 0;
if (off + count > size) {
size -= off;
loff_t init_off = off;
u8 *data = (u8 *) buf;
- if (off > 0x200000)
+ if (off >= RIO_MAINT_SPACE_SZ)
return 0;
- if (off + count > 0x200000) {
- size = 0x200000 - off;
+ if (off + count > RIO_MAINT_SPACE_SZ) {
+ size = RIO_MAINT_SPACE_SZ - off;
count = size;
}
.name = "config",
.mode = S_IRUGO | S_IWUSR,
},
- .size = 0x200000,
+ .size = RIO_MAINT_SPACE_SZ,
.read = rio_read_config,
.write = rio_write_config,
};
dev_dbg(rdev_get_dev(rdev), "%s id: %d val: %d\n", __func__, id, val);
- BUG_ON(val < 0 || val > mc13xxx_regulators[id].desc.n_voltages);
+ BUG_ON(val > mc13xxx_regulators[id].desc.n_voltages);
return mc13xxx_regulators[id].voltages[val];
}
return REGULATOR_MODE_IDLE;
default:
BUG();
+ return -EINVAL;
}
}
If unsure, say Y.
+config RTC_INTF_DEV_UIE_EMUL
+ bool "RTC UIE emulation on dev interface"
+ depends on RTC_INTF_DEV
+ help
+ Provides an emulation for RTC_UIE if the underlying rtc chip
+ driver does not expose RTC_UIE ioctls. Those requests generate
+ once-per-second update interrupts, used for synchronization.
+
+ The emulation code will read the time from the hardware
+ clock several times per second, please enable this option
+ only if you know that you really need it.
+
config RTC_DRV_TEST
tristate "Test driver/device"
help
struct module *owner)
{
struct rtc_device *rtc;
+ struct rtc_wkalrm alrm;
int id, err;
if (idr_pre_get(&rtc_idr, GFP_KERNEL) == 0) {
rtc->pie_timer.function = rtc_pie_update_irq;
rtc->pie_enabled = 0;
+ /* Check to see if there is an ALARM already set in hw */
+ err = __rtc_read_alarm(rtc, &alrm);
+
+ if (!err && !rtc_valid_tm(&alrm.time))
+ rtc_set_alarm(rtc, &alrm);
+
strlcpy(rtc->name, name, RTC_DEVICE_NAME_SIZE);
dev_set_name(&rtc->dev, "rtc%d", id);
}
EXPORT_SYMBOL_GPL(rtc_set_mmss);
+static int rtc_read_alarm_internal(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+{
+ int err;
+
+ err = mutex_lock_interruptible(&rtc->ops_lock);
+ if (err)
+ return err;
+
+ if (rtc->ops == NULL)
+ err = -ENODEV;
+ else if (!rtc->ops->read_alarm)
+ err = -EINVAL;
+ else {
+ memset(alarm, 0, sizeof(struct rtc_wkalrm));
+ err = rtc->ops->read_alarm(rtc->dev.parent, alarm);
+ }
+
+ mutex_unlock(&rtc->ops_lock);
+ return err;
+}
+
+int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+{
+ int err;
+ struct rtc_time before, now;
+ int first_time = 1;
+ unsigned long t_now, t_alm;
+ enum { none, day, month, year } missing = none;
+ unsigned days;
+
+ /* The lower level RTC driver may return -1 in some fields,
+ * creating invalid alarm->time values, for reasons like:
+ *
+ * - The hardware may not be capable of filling them in;
+ * many alarms match only on time-of-day fields, not
+ * day/month/year calendar data.
+ *
+ * - Some hardware uses illegal values as "wildcard" match
+ * values, which non-Linux firmware (like a BIOS) may try
+ * to set up as e.g. "alarm 15 minutes after each hour".
+ * Linux uses only oneshot alarms.
+ *
+ * When we see that here, we deal with it by using values from
+ * a current RTC timestamp for any missing (-1) values. The
+ * RTC driver prevents "periodic alarm" modes.
+ *
+ * But this can be racey, because some fields of the RTC timestamp
+ * may have wrapped in the interval since we read the RTC alarm,
+ * which would lead to us inserting inconsistent values in place
+ * of the -1 fields.
+ *
+ * Reading the alarm and timestamp in the reverse sequence
+ * would have the same race condition, and not solve the issue.
+ *
+ * So, we must first read the RTC timestamp,
+ * then read the RTC alarm value,
+ * and then read a second RTC timestamp.
+ *
+ * If any fields of the second timestamp have changed
+ * when compared with the first timestamp, then we know
+ * our timestamp may be inconsistent with that used by
+ * the low-level rtc_read_alarm_internal() function.
+ *
+ * So, when the two timestamps disagree, we just loop and do
+ * the process again to get a fully consistent set of values.
+ *
+ * This could all instead be done in the lower level driver,
+ * but since more than one lower level RTC implementation needs it,
+ * then it's probably best best to do it here instead of there..
+ */
+
+ /* Get the "before" timestamp */
+ err = rtc_read_time(rtc, &before);
+ if (err < 0)
+ return err;
+ do {
+ if (!first_time)
+ memcpy(&before, &now, sizeof(struct rtc_time));
+ first_time = 0;
+
+ /* get the RTC alarm values, which may be incomplete */
+ err = rtc_read_alarm_internal(rtc, alarm);
+ if (err)
+ return err;
+
+ /* full-function RTCs won't have such missing fields */
+ if (rtc_valid_tm(&alarm->time) == 0)
+ return 0;
+
+ /* get the "after" timestamp, to detect wrapped fields */
+ err = rtc_read_time(rtc, &now);
+ if (err < 0)
+ return err;
+
+ /* note that tm_sec is a "don't care" value here: */
+ } while ( before.tm_min != now.tm_min
+ || before.tm_hour != now.tm_hour
+ || before.tm_mon != now.tm_mon
+ || before.tm_year != now.tm_year);
+
+ /* Fill in the missing alarm fields using the timestamp; we
+ * know there's at least one since alarm->time is invalid.
+ */
+ if (alarm->time.tm_sec == -1)
+ alarm->time.tm_sec = now.tm_sec;
+ if (alarm->time.tm_min == -1)
+ alarm->time.tm_min = now.tm_min;
+ if (alarm->time.tm_hour == -1)
+ alarm->time.tm_hour = now.tm_hour;
+
+ /* For simplicity, only support date rollover for now */
+ if (alarm->time.tm_mday == -1) {
+ alarm->time.tm_mday = now.tm_mday;
+ missing = day;
+ }
+ if (alarm->time.tm_mon == -1) {
+ alarm->time.tm_mon = now.tm_mon;
+ if (missing == none)
+ missing = month;
+ }
+ if (alarm->time.tm_year == -1) {
+ alarm->time.tm_year = now.tm_year;
+ if (missing == none)
+ missing = year;
+ }
+
+ /* with luck, no rollover is needed */
+ rtc_tm_to_time(&now, &t_now);
+ rtc_tm_to_time(&alarm->time, &t_alm);
+ if (t_now < t_alm)
+ goto done;
+
+ switch (missing) {
+
+ /* 24 hour rollover ... if it's now 10am Monday, an alarm that
+ * that will trigger at 5am will do so at 5am Tuesday, which
+ * could also be in the next month or year. This is a common
+ * case, especially for PCs.
+ */
+ case day:
+ dev_dbg(&rtc->dev, "alarm rollover: %s\n", "day");
+ t_alm += 24 * 60 * 60;
+ rtc_time_to_tm(t_alm, &alarm->time);
+ break;
+
+ /* Month rollover ... if it's the 31th, an alarm on the 3rd will
+ * be next month. An alarm matching on the 30th, 29th, or 28th
+ * may end up in the month after that! Many newer PCs support
+ * this type of alarm.
+ */
+ case month:
+ dev_dbg(&rtc->dev, "alarm rollover: %s\n", "month");
+ do {
+ if (alarm->time.tm_mon < 11)
+ alarm->time.tm_mon++;
+ else {
+ alarm->time.tm_mon = 0;
+ alarm->time.tm_year++;
+ }
+ days = rtc_month_days(alarm->time.tm_mon,
+ alarm->time.tm_year);
+ } while (days < alarm->time.tm_mday);
+ break;
+
+ /* Year rollover ... easy except for leap years! */
+ case year:
+ dev_dbg(&rtc->dev, "alarm rollover: %s\n", "year");
+ do {
+ alarm->time.tm_year++;
+ } while (rtc_valid_tm(&alarm->time) != 0);
+ break;
+
+ default:
+ dev_warn(&rtc->dev, "alarm rollover not handled\n");
+ }
+
+done:
+ return 0;
+}
+
int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
{
int err;
}
if (err)
- return err;
-
- if (!rtc->ops)
+ /* nothing */;
+ else if (!rtc->ops)
err = -ENODEV;
else if (!rtc->ops->alarm_irq_enable)
err = -EINVAL;
if (err)
return err;
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+ if (enabled == 0 && rtc->uie_irq_active) {
+ mutex_unlock(&rtc->ops_lock);
+ return rtc_dev_update_irq_enable_emul(rtc, 0);
+ }
+#endif
/* make sure we're changing state */
if (rtc->uie_rtctimer.enabled == enabled)
goto out;
out:
mutex_unlock(&rtc->ops_lock);
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+ /*
+ * Enable emulation if the driver did not provide
+ * the update_irq_enable function pointer or if returned
+ * -EINVAL to signal that it has been configured without
+ * interrupts or that are not available at the moment.
+ */
+ if (err == -EINVAL)
+ err = rtc_dev_update_irq_enable_emul(rtc, enabled);
+#endif
return err;
}
*
* Triggers the registered irq_task function callback.
*/
-static void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode)
+void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode)
{
unsigned long flags;
return ret;
}
-static int at32_rtc_ioctl(struct device *dev, unsigned int cmd,
- unsigned long arg)
+static int at32_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct rtc_at32ap700x *rtc = dev_get_drvdata(dev);
int ret = 0;
spin_lock_irq(&rtc->lock);
- switch (cmd) {
- case RTC_AIE_ON:
+ if(enabled) {
if (rtc_readl(rtc, VAL) > rtc->alarm_time) {
ret = -EINVAL;
- break;
+ goto out;
}
rtc_writel(rtc, CTRL, rtc_readl(rtc, CTRL)
| RTC_BIT(CTRL_TOPEN));
rtc_writel(rtc, ICR, RTC_BIT(ICR_TOPI));
rtc_writel(rtc, IER, RTC_BIT(IER_TOPI));
- break;
- case RTC_AIE_OFF:
+ } else {
rtc_writel(rtc, CTRL, rtc_readl(rtc, CTRL)
& ~RTC_BIT(CTRL_TOPEN));
rtc_writel(rtc, IDR, RTC_BIT(IDR_TOPI));
rtc_writel(rtc, ICR, RTC_BIT(ICR_TOPI));
- break;
- default:
- ret = -ENOIOCTLCMD;
- break;
}
-
+out:
spin_unlock_irq(&rtc->lock);
return ret;
}
static struct rtc_class_ops at32_rtc_ops = {
- .ioctl = at32_rtc_ioctl,
.read_time = at32_rtc_readtime,
.set_time = at32_rtc_settime,
.read_alarm = at32_rtc_readalarm,
.set_alarm = at32_rtc_setalarm,
+ .alarm_irq_enable = at32_rtc_alarm_irq_enable,
};
static int __init at32_rtc_probe(struct platform_device *pdev)
return 0;
}
-/*
- * Handle commands from user-space
- */
-static int at91_rtc_ioctl(struct device *dev, unsigned int cmd,
- unsigned long arg)
+static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
- int ret = 0;
+ pr_debug("%s(): cmd=%08x\n", __func__, enabled);
- pr_debug("%s(): cmd=%08x, arg=%08lx.\n", __func__, cmd, arg);
-
- /* important: scrub old status before enabling IRQs */
- switch (cmd) {
- case RTC_AIE_OFF: /* alarm off */
- at91_sys_write(AT91_RTC_IDR, AT91_RTC_ALARM);
- break;
- case RTC_AIE_ON: /* alarm on */
+ if (enabled) {
at91_sys_write(AT91_RTC_SCCR, AT91_RTC_ALARM);
at91_sys_write(AT91_RTC_IER, AT91_RTC_ALARM);
- break;
- case RTC_UIE_OFF: /* update off */
- at91_sys_write(AT91_RTC_IDR, AT91_RTC_SECEV);
- break;
- case RTC_UIE_ON: /* update on */
- at91_sys_write(AT91_RTC_SCCR, AT91_RTC_SECEV);
- at91_sys_write(AT91_RTC_IER, AT91_RTC_SECEV);
- break;
- default:
- ret = -ENOIOCTLCMD;
- break;
- }
+ } else
+ at91_sys_write(AT91_RTC_IDR, AT91_RTC_ALARM);
- return ret;
+ return 0;
}
-
/*
* Provide additional RTC information in /proc/driver/rtc
*/
}
static const struct rtc_class_ops at91_rtc_ops = {
- .ioctl = at91_rtc_ioctl,
.read_time = at91_rtc_readtime,
.set_time = at91_rtc_settime,
.read_alarm = at91_rtc_readalarm,
.set_alarm = at91_rtc_setalarm,
.proc = at91_rtc_proc,
+ .alarm_irq_enable = at91_rtc_alarm_irq_enable,
};
/*
return 0;
}
-/*
- * Handle commands from user-space
- */
-static int at91_rtc_ioctl(struct device *dev, unsigned int cmd,
- unsigned long arg)
+static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct sam9_rtc *rtc = dev_get_drvdata(dev);
- int ret = 0;
u32 mr = rtt_readl(rtc, MR);
- dev_dbg(dev, "ioctl: cmd=%08x, arg=%08lx, mr %08x\n", cmd, arg, mr);
-
- switch (cmd) {
- case RTC_AIE_OFF: /* alarm off */
- rtt_writel(rtc, MR, mr & ~AT91_RTT_ALMIEN);
- break;
- case RTC_AIE_ON: /* alarm on */
+ dev_dbg(dev, "alarm_irq_enable: enabled=%08x, mr %08x\n", enabled, mr);
+ if (enabled)
rtt_writel(rtc, MR, mr | AT91_RTT_ALMIEN);
- break;
- case RTC_UIE_OFF: /* update off */
- rtt_writel(rtc, MR, mr & ~AT91_RTT_RTTINCIEN);
- break;
- case RTC_UIE_ON: /* update on */
- rtt_writel(rtc, MR, mr | AT91_RTT_RTTINCIEN);
- break;
- default:
- ret = -ENOIOCTLCMD;
- break;
- }
-
- return ret;
+ else
+ rtt_writel(rtc, MR, mr & ~AT91_RTT_ALMIEN);
+ return 0;
}
/*
}
static const struct rtc_class_ops at91_rtc_ops = {
- .ioctl = at91_rtc_ioctl,
.read_time = at91_rtc_readtime,
.set_time = at91_rtc_settime,
.read_alarm = at91_rtc_readalarm,
.set_alarm = at91_rtc_setalarm,
.proc = at91_rtc_proc,
+ .alarm_irq_enable = at91_rtc_alarm_irq_enable,
};
/*
*/
bfin_rtc_int_set(rtc->rtc_alarm.tm_yday == -1 ? RTC_ISTAT_ALARM : RTC_ISTAT_ALARM_DAY);
}
-static int bfin_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+
+static int bfin_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct bfin_rtc *rtc = dev_get_drvdata(dev);
- int ret = 0;
dev_dbg_stamp(dev);
-
- bfin_rtc_sync_pending(dev);
-
- switch (cmd) {
- case RTC_UIE_ON:
- dev_dbg_stamp(dev);
- bfin_rtc_int_set(RTC_ISTAT_SEC);
- break;
- case RTC_UIE_OFF:
- dev_dbg_stamp(dev);
- bfin_rtc_int_clear(~RTC_ISTAT_SEC);
- break;
-
- case RTC_AIE_ON:
- dev_dbg_stamp(dev);
+ if (enabled)
bfin_rtc_int_set_alarm(rtc);
- break;
- case RTC_AIE_OFF:
- dev_dbg_stamp(dev);
+ else
bfin_rtc_int_clear(~(RTC_ISTAT_ALARM | RTC_ISTAT_ALARM_DAY));
- break;
-
- default:
- dev_dbg_stamp(dev);
- ret = -ENOIOCTLCMD;
- }
-
- return ret;
}
static int bfin_rtc_read_time(struct device *dev, struct rtc_time *tm)
}
static struct rtc_class_ops bfin_rtc_ops = {
- .ioctl = bfin_rtc_ioctl,
.read_time = bfin_rtc_read_time,
.set_time = bfin_rtc_set_time,
.read_alarm = bfin_rtc_read_alarm,
.set_alarm = bfin_rtc_set_alarm,
.proc = bfin_rtc_proc,
+ .alarm_irq_enable = bfin_rtc_alarm_irq_enable,
};
static int __devinit bfin_rtc_probe(struct platform_device *pdev)
return 0;
}
-static int cmos_irq_set_freq(struct device *dev, int freq)
-{
- struct cmos_rtc *cmos = dev_get_drvdata(dev);
- int f;
- unsigned long flags;
-
- if (!is_valid_irq(cmos->irq))
- return -ENXIO;
-
- if (!is_power_of_2(freq))
- return -EINVAL;
- /* 0 = no irqs; 1 = 2^15 Hz ... 15 = 2^0 Hz */
- f = ffs(freq);
- if (f-- > 16)
- return -EINVAL;
- f = 16 - f;
-
- spin_lock_irqsave(&rtc_lock, flags);
- hpet_set_periodic_freq(freq);
- CMOS_WRITE(RTC_REF_CLCK_32KHZ | f, RTC_FREQ_SELECT);
- spin_unlock_irqrestore(&rtc_lock, flags);
-
- return 0;
-}
-
-static int cmos_irq_set_state(struct device *dev, int enabled)
-{
- struct cmos_rtc *cmos = dev_get_drvdata(dev);
- unsigned long flags;
-
- if (!is_valid_irq(cmos->irq))
- return -ENXIO;
-
- spin_lock_irqsave(&rtc_lock, flags);
-
- if (enabled)
- cmos_irq_enable(cmos, RTC_PIE);
- else
- cmos_irq_disable(cmos, RTC_PIE);
-
- spin_unlock_irqrestore(&rtc_lock, flags);
- return 0;
-}
-
static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct cmos_rtc *cmos = dev_get_drvdata(dev);
return 0;
}
-static int cmos_update_irq_enable(struct device *dev, unsigned int enabled)
-{
- struct cmos_rtc *cmos = dev_get_drvdata(dev);
- unsigned long flags;
-
- if (!is_valid_irq(cmos->irq))
- return -EINVAL;
-
- spin_lock_irqsave(&rtc_lock, flags);
-
- if (enabled)
- cmos_irq_enable(cmos, RTC_UIE);
- else
- cmos_irq_disable(cmos, RTC_UIE);
-
- spin_unlock_irqrestore(&rtc_lock, flags);
- return 0;
-}
-
#if defined(CONFIG_RTC_INTF_PROC) || defined(CONFIG_RTC_INTF_PROC_MODULE)
static int cmos_procfs(struct device *dev, struct seq_file *seq)
.read_alarm = cmos_read_alarm,
.set_alarm = cmos_set_alarm,
.proc = cmos_procfs,
- .irq_set_freq = cmos_irq_set_freq,
- .irq_set_state = cmos_irq_set_state,
.alarm_irq_enable = cmos_alarm_irq_enable,
- .update_irq_enable = cmos_update_irq_enable,
};
/*----------------------------------------------------------------*/
case RTC_WIE_OFF:
rtc_ctrl &= ~PRTCSS_RTC_CTRL_WEN;
break;
- case RTC_UIE_OFF:
- case RTC_UIE_ON:
- ret = -ENOTTY;
- break;
default:
ret = -ENOIOCTLCMD;
}
return 0;
}
-static int davinci_rtc_irq_set_state(struct device *dev, int enabled)
-{
- struct davinci_rtc *davinci_rtc = dev_get_drvdata(dev);
- unsigned long flags;
- u8 rtc_ctrl;
-
- spin_lock_irqsave(&davinci_rtc_lock, flags);
-
- rtc_ctrl = rtcss_read(davinci_rtc, PRTCSS_RTC_CTRL);
-
- if (enabled) {
- while (rtcss_read(davinci_rtc, PRTCSS_RTC_CTRL)
- & PRTCSS_RTC_CTRL_WDTBUS)
- cpu_relax();
-
- rtc_ctrl |= PRTCSS_RTC_CTRL_TE;
- rtcss_write(davinci_rtc, rtc_ctrl, PRTCSS_RTC_CTRL);
-
- rtcss_write(davinci_rtc, 0x0, PRTCSS_RTC_CLKC_CNT);
-
- rtc_ctrl |= PRTCSS_RTC_CTRL_TIEN |
- PRTCSS_RTC_CTRL_TMMD |
- PRTCSS_RTC_CTRL_TMRFLG;
- } else
- rtc_ctrl &= ~PRTCSS_RTC_CTRL_TIEN;
-
- rtcss_write(davinci_rtc, rtc_ctrl, PRTCSS_RTC_CTRL);
-
- spin_unlock_irqrestore(&davinci_rtc_lock, flags);
-
- return 0;
-}
-
-static int davinci_rtc_irq_set_freq(struct device *dev, int freq)
-{
- struct davinci_rtc *davinci_rtc = dev_get_drvdata(dev);
- unsigned long flags;
- u16 tmr_counter = (0x8000 >> (ffs(freq) - 1));
-
- spin_lock_irqsave(&davinci_rtc_lock, flags);
-
- rtcss_write(davinci_rtc, tmr_counter & 0xFF, PRTCSS_RTC_TMR0);
- rtcss_write(davinci_rtc, (tmr_counter & 0xFF00) >> 8, PRTCSS_RTC_TMR1);
-
- spin_unlock_irqrestore(&davinci_rtc_lock, flags);
-
- return 0;
-}
-
static struct rtc_class_ops davinci_rtc_ops = {
.ioctl = davinci_rtc_ioctl,
.read_time = davinci_rtc_read_time,
.alarm_irq_enable = davinci_rtc_alarm_irq_enable,
.read_alarm = davinci_rtc_read_alarm,
.set_alarm = davinci_rtc_set_alarm,
- .irq_set_state = davinci_rtc_irq_set_state,
- .irq_set_freq = davinci_rtc_irq_set_freq,
};
static int __init davinci_rtc_probe(struct platform_device *pdev)
return err;
}
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+/*
+ * Routine to poll RTC seconds field for change as often as possible,
+ * after first RTC_UIE use timer to reduce polling
+ */
+static void rtc_uie_task(struct work_struct *work)
+{
+ struct rtc_device *rtc =
+ container_of(work, struct rtc_device, uie_task);
+ struct rtc_time tm;
+ int num = 0;
+ int err;
+
+ err = rtc_read_time(rtc, &tm);
+
+ spin_lock_irq(&rtc->irq_lock);
+ if (rtc->stop_uie_polling || err) {
+ rtc->uie_task_active = 0;
+ } else if (rtc->oldsecs != tm.tm_sec) {
+ num = (tm.tm_sec + 60 - rtc->oldsecs) % 60;
+ rtc->oldsecs = tm.tm_sec;
+ rtc->uie_timer.expires = jiffies + HZ - (HZ/10);
+ rtc->uie_timer_active = 1;
+ rtc->uie_task_active = 0;
+ add_timer(&rtc->uie_timer);
+ } else if (schedule_work(&rtc->uie_task) == 0) {
+ rtc->uie_task_active = 0;
+ }
+ spin_unlock_irq(&rtc->irq_lock);
+ if (num)
+ rtc_handle_legacy_irq(rtc, num, RTC_UF);
+}
+static void rtc_uie_timer(unsigned long data)
+{
+ struct rtc_device *rtc = (struct rtc_device *)data;
+ unsigned long flags;
+
+ spin_lock_irqsave(&rtc->irq_lock, flags);
+ rtc->uie_timer_active = 0;
+ rtc->uie_task_active = 1;
+ if ((schedule_work(&rtc->uie_task) == 0))
+ rtc->uie_task_active = 0;
+ spin_unlock_irqrestore(&rtc->irq_lock, flags);
+}
+
+static int clear_uie(struct rtc_device *rtc)
+{
+ spin_lock_irq(&rtc->irq_lock);
+ if (rtc->uie_irq_active) {
+ rtc->stop_uie_polling = 1;
+ if (rtc->uie_timer_active) {
+ spin_unlock_irq(&rtc->irq_lock);
+ del_timer_sync(&rtc->uie_timer);
+ spin_lock_irq(&rtc->irq_lock);
+ rtc->uie_timer_active = 0;
+ }
+ if (rtc->uie_task_active) {
+ spin_unlock_irq(&rtc->irq_lock);
+ flush_scheduled_work();
+ spin_lock_irq(&rtc->irq_lock);
+ }
+ rtc->uie_irq_active = 0;
+ }
+ spin_unlock_irq(&rtc->irq_lock);
+ return 0;
+}
+
+static int set_uie(struct rtc_device *rtc)
+{
+ struct rtc_time tm;
+ int err;
+
+ err = rtc_read_time(rtc, &tm);
+ if (err)
+ return err;
+ spin_lock_irq(&rtc->irq_lock);
+ if (!rtc->uie_irq_active) {
+ rtc->uie_irq_active = 1;
+ rtc->stop_uie_polling = 0;
+ rtc->oldsecs = tm.tm_sec;
+ rtc->uie_task_active = 1;
+ if (schedule_work(&rtc->uie_task) == 0)
+ rtc->uie_task_active = 0;
+ }
+ rtc->irq_data = 0;
+ spin_unlock_irq(&rtc->irq_lock);
+ return 0;
+}
+
+int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc, unsigned int enabled)
+{
+ if (enabled)
+ return set_uie(rtc);
+ else
+ return clear_uie(rtc);
+}
+EXPORT_SYMBOL(rtc_dev_update_irq_enable_emul);
+
+#endif /* CONFIG_RTC_INTF_DEV_UIE_EMUL */
static ssize_t
rtc_dev_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
if (err)
goto done;
- /* try the driver's ioctl interface */
- if (ops->ioctl) {
- err = ops->ioctl(rtc->dev.parent, cmd, arg);
- if (err != -ENOIOCTLCMD) {
- mutex_unlock(&rtc->ops_lock);
- return err;
- }
- }
-
- /* if the driver does not provide the ioctl interface
- * or if that particular ioctl was not implemented
- * (-ENOIOCTLCMD), we will try to emulate here.
- *
+ /*
* Drivers *SHOULD NOT* provide ioctl implementations
* for these requests. Instead, provide methods to
* support the following code, so that the RTC's main
return err;
default:
- err = -ENOTTY;
+ /* Finally try the driver's ioctl interface */
+ if (ops->ioctl) {
+ err = ops->ioctl(rtc->dev.parent, cmd, arg);
+ if (err == -ENOIOCTLCMD)
+ err = -ENOTTY;
+ }
break;
}
rtc->dev.devt = MKDEV(MAJOR(rtc_devt), rtc->id);
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+ INIT_WORK(&rtc->uie_task, rtc_uie_task);
+ setup_timer(&rtc->uie_timer, rtc_uie_timer, (unsigned long)rtc);
+#endif
+
cdev_init(&rtc->char_dev, &rtc_dev_fops);
rtc->char_dev.owner = rtc->owner;
}
__raw_writel(data, &priv->rtcregs[reg]);
}
+
+static int ds1286_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+ struct ds1286_priv *priv = dev_get_drvdata(dev);
+ unsigned long flags;
+ unsigned char val;
+
+ /* Allow or mask alarm interrupts */
+ spin_lock_irqsave(&priv->lock, flags);
+ val = ds1286_rtc_read(priv, RTC_CMD);
+ if (enabled)
+ val &= ~RTC_TDM;
+ else
+ val |= RTC_TDM;
+ ds1286_rtc_write(priv, val, RTC_CMD);
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+ return 0;
+}
+
#ifdef CONFIG_RTC_INTF_DEV
static int ds1286_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
unsigned char val;
switch (cmd) {
- case RTC_AIE_OFF:
- /* Mask alarm int. enab. bit */
- spin_lock_irqsave(&priv->lock, flags);
- val = ds1286_rtc_read(priv, RTC_CMD);
- val |= RTC_TDM;
- ds1286_rtc_write(priv, val, RTC_CMD);
- spin_unlock_irqrestore(&priv->lock, flags);
- break;
- case RTC_AIE_ON:
- /* Allow alarm interrupts. */
- spin_lock_irqsave(&priv->lock, flags);
- val = ds1286_rtc_read(priv, RTC_CMD);
- val &= ~RTC_TDM;
- ds1286_rtc_write(priv, val, RTC_CMD);
- spin_unlock_irqrestore(&priv->lock, flags);
- break;
case RTC_WIE_OFF:
/* Mask watchdog int. enab. bit */
spin_lock_irqsave(&priv->lock, flags);
}
static const struct rtc_class_ops ds1286_ops = {
- .ioctl = ds1286_ioctl,
- .proc = ds1286_proc,
+ .ioctl = ds1286_ioctl,
+ .proc = ds1286_proc,
.read_time = ds1286_read_time,
.set_time = ds1286_set_time,
.read_alarm = ds1286_read_alarm,
.set_alarm = ds1286_set_alarm,
+ .alarm_irq_enable = ds1286_alarm_irq_enable,
};
static int __devinit ds1286_probe(struct platform_device *pdev)
* Interface to RTC framework
*/
-#ifdef CONFIG_RTC_INTF_DEV
-
-/*
- * Context: caller holds rtc->ops_lock (to protect ds1305->ctrl)
- */
-static int ds1305_ioctl(struct device *dev, unsigned cmd, unsigned long arg)
+static int ds1305_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct ds1305 *ds1305 = dev_get_drvdata(dev);
u8 buf[2];
- int status = -ENOIOCTLCMD;
+ long err = -EINVAL;
buf[0] = DS1305_WRITE | DS1305_CONTROL;
buf[1] = ds1305->ctrl[0];
- switch (cmd) {
- case RTC_AIE_OFF:
- status = 0;
- if (!(buf[1] & DS1305_AEI0))
- goto done;
- buf[1] &= ~DS1305_AEI0;
- break;
-
- case RTC_AIE_ON:
- status = 0;
+ if (enabled) {
if (ds1305->ctrl[0] & DS1305_AEI0)
goto done;
buf[1] |= DS1305_AEI0;
- break;
- }
- if (status == 0) {
- status = spi_write_then_read(ds1305->spi, buf, sizeof buf,
- NULL, 0);
- if (status >= 0)
- ds1305->ctrl[0] = buf[1];
+ } else {
+ if (!(buf[1] & DS1305_AEI0))
+ goto done;
+ buf[1] &= ~DS1305_AEI0;
}
-
+ err = spi_write_then_read(ds1305->spi, buf, sizeof buf, NULL, 0);
+ if (err >= 0)
+ ds1305->ctrl[0] = buf[1];
done:
- return status;
+ return err;
+
}
-#else
-#define ds1305_ioctl NULL
-#endif
/*
* Get/set of date and time is pretty normal.
#endif
static const struct rtc_class_ops ds1305_ops = {
- .ioctl = ds1305_ioctl,
.read_time = ds1305_get_time,
.set_time = ds1305_set_time,
.read_alarm = ds1305_get_alarm,
.set_alarm = ds1305_set_alarm,
.proc = ds1305_proc,
+ .alarm_irq_enable = ds1305_alarm_irq_enable,
};
static void ds1305_work(struct work_struct *work)
return 0;
}
-static int ds1307_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+static int ds1307_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct i2c_client *client = to_i2c_client(dev);
struct ds1307 *ds1307 = i2c_get_clientdata(client);
int ret;
- switch (cmd) {
- case RTC_AIE_OFF:
- if (!test_bit(HAS_ALARM, &ds1307->flags))
- return -ENOTTY;
-
- ret = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL);
- if (ret < 0)
- return ret;
-
- ret &= ~DS1337_BIT_A1IE;
-
- ret = i2c_smbus_write_byte_data(client,
- DS1337_REG_CONTROL, ret);
- if (ret < 0)
- return ret;
-
- break;
-
- case RTC_AIE_ON:
- if (!test_bit(HAS_ALARM, &ds1307->flags))
- return -ENOTTY;
+ if (!test_bit(HAS_ALARM, &ds1307->flags))
+ return -ENOTTY;
- ret = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL);
- if (ret < 0)
- return ret;
+ ret = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL);
+ if (ret < 0)
+ return ret;
+ if (enabled)
ret |= DS1337_BIT_A1IE;
+ else
+ ret &= ~DS1337_BIT_A1IE;
- ret = i2c_smbus_write_byte_data(client,
- DS1337_REG_CONTROL, ret);
- if (ret < 0)
- return ret;
-
- break;
-
- default:
- return -ENOIOCTLCMD;
- }
+ ret = i2c_smbus_write_byte_data(client, DS1337_REG_CONTROL, ret);
+ if (ret < 0)
+ return ret;
return 0;
}
.set_time = ds1307_set_time,
.read_alarm = ds1337_read_alarm,
.set_alarm = ds1337_set_alarm,
- .ioctl = ds1307_ioctl,
+ .alarm_irq_enable = ds1307_alarm_irq_enable,
};
/*----------------------------------------------------------------------*/
mutex_unlock(&ds1374->mutex);
}
-static int ds1374_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+static int ds1374_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct i2c_client *client = to_i2c_client(dev);
struct ds1374 *ds1374 = i2c_get_clientdata(client);
- int ret = -ENOIOCTLCMD;
+ int ret;
mutex_lock(&ds1374->mutex);
- switch (cmd) {
- case RTC_AIE_OFF:
- ret = i2c_smbus_read_byte_data(client, DS1374_REG_CR);
- if (ret < 0)
- goto out;
-
- ret &= ~DS1374_REG_CR_WACE;
-
- ret = i2c_smbus_write_byte_data(client, DS1374_REG_CR, ret);
- if (ret < 0)
- goto out;
-
- break;
-
- case RTC_AIE_ON:
- ret = i2c_smbus_read_byte_data(client, DS1374_REG_CR);
- if (ret < 0)
- goto out;
+ ret = i2c_smbus_read_byte_data(client, DS1374_REG_CR);
+ if (ret < 0)
+ goto out;
+ if (enabled) {
ret |= DS1374_REG_CR_WACE | DS1374_REG_CR_AIE;
ret &= ~DS1374_REG_CR_WDALM;
-
- ret = i2c_smbus_write_byte_data(client, DS1374_REG_CR, ret);
- if (ret < 0)
- goto out;
-
- break;
+ } else {
+ ret &= ~DS1374_REG_CR_WACE;
}
+ ret = i2c_smbus_write_byte_data(client, DS1374_REG_CR, ret);
out:
mutex_unlock(&ds1374->mutex);
.set_time = ds1374_set_time,
.read_alarm = ds1374_read_alarm,
.set_alarm = ds1374_set_alarm,
- .ioctl = ds1374_ioctl,
+ .alarm_irq_enable = ds1374_alarm_irq_enable,
};
static int ds1374_probe(struct i2c_client *client,
return 0;
}
-static int ds1511_rtc_update_irq_enable(struct device *dev,
- unsigned int enabled)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
-
- if (pdata->irq <= 0)
- return -EINVAL;
- if (enabled)
- pdata->irqen |= RTC_UF;
- else
- pdata->irqen &= ~RTC_UF;
- ds1511_rtc_update_alarm(pdata);
- return 0;
-}
-
static const struct rtc_class_ops ds1511_rtc_ops = {
.read_time = ds1511_rtc_read_time,
.set_time = ds1511_rtc_set_time,
.read_alarm = ds1511_rtc_read_alarm,
.set_alarm = ds1511_rtc_set_alarm,
.alarm_irq_enable = ds1511_rtc_alarm_irq_enable,
- .update_irq_enable = ds1511_rtc_update_irq_enable,
};
static ssize_t
return 0;
}
-static int ds1553_rtc_update_irq_enable(struct device *dev,
- unsigned int enabled)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
-
- if (pdata->irq <= 0)
- return -EINVAL;
- if (enabled)
- pdata->irqen |= RTC_UF;
- else
- pdata->irqen &= ~RTC_UF;
- ds1553_rtc_update_alarm(pdata);
- return 0;
-}
-
static const struct rtc_class_ops ds1553_rtc_ops = {
.read_time = ds1553_rtc_read_time,
.set_time = ds1553_rtc_set_time,
.read_alarm = ds1553_rtc_read_alarm,
.set_alarm = ds1553_rtc_set_alarm,
.alarm_irq_enable = ds1553_rtc_alarm_irq_enable,
- .update_irq_enable = ds1553_rtc_update_irq_enable,
};
static ssize_t ds1553_nvram_read(struct file *filp, struct kobject *kobj,
/*
* RTC client/driver for the Maxim/Dallas DS3232 Real-Time Clock over I2C
*
- * Copyright (C) 2009-2010 Freescale Semiconductor.
+ * Copyright (C) 2009-2011 Freescale Semiconductor.
* Author: Jack Lan <jack.lan@freescale.com>
*
* This program is free software; you can redistribute it and/or modify it
time->tm_hour = bcd2bin(hour);
}
- time->tm_wday = bcd2bin(week);
+ /* Day of the week in linux range is 0~6 while 1~7 in RTC chip */
+ time->tm_wday = bcd2bin(week) - 1;
time->tm_mday = bcd2bin(day);
- time->tm_mon = bcd2bin(month & 0x7F);
+ /* linux tm_mon range:0~11, while month range is 1~12 in RTC chip */
+ time->tm_mon = bcd2bin(month & 0x7F) - 1;
if (century)
add_century = 100;
buf[0] = bin2bcd(time->tm_sec);
buf[1] = bin2bcd(time->tm_min);
buf[2] = bin2bcd(time->tm_hour);
- buf[3] = bin2bcd(time->tm_wday); /* Day of the week */
+ /* Day of the week in linux range is 0~6 while 1~7 in RTC chip */
+ buf[3] = bin2bcd(time->tm_wday + 1);
buf[4] = bin2bcd(time->tm_mday); /* Date */
- buf[5] = bin2bcd(time->tm_mon);
+ /* linux tm_mon range:0~11, while month range is 1~12 in RTC chip */
+ buf[5] = bin2bcd(time->tm_mon + 1);
if (time->tm_year >= 100) {
buf[5] |= 0x80;
buf[6] = bin2bcd(time->tm_year - 100);
return 0;
}
-static int ds3232_update_irq_enable(struct device *dev, unsigned int enabled)
-{
- struct i2c_client *client = to_i2c_client(dev);
- struct ds3232 *ds3232 = i2c_get_clientdata(client);
-
- if (client->irq <= 0)
- return -EINVAL;
-
- if (enabled)
- ds3232->rtc->irq_data |= RTC_UF;
- else
- ds3232->rtc->irq_data &= ~RTC_UF;
-
- ds3232_update_alarm(client);
- return 0;
-}
-
static irqreturn_t ds3232_irq(int irq, void *dev_id)
{
struct i2c_client *client = dev_id;
.read_alarm = ds3232_read_alarm,
.set_alarm = ds3232_set_alarm,
.alarm_irq_enable = ds3232_alarm_irq_enable,
- .update_irq_enable = ds3232_update_irq_enable,
};
static int __devinit ds3232_probe(struct i2c_client *client,
return ret;
}
-static int jz4740_rtc_update_irq_enable(struct device *dev, unsigned int enable)
-{
- struct jz4740_rtc *rtc = dev_get_drvdata(dev);
- return jz4740_rtc_ctrl_set_bits(rtc, JZ_RTC_CTRL_1HZ_IRQ, enable);
-}
-
static int jz4740_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
{
struct jz4740_rtc *rtc = dev_get_drvdata(dev);
.set_mmss = jz4740_rtc_set_mmss,
.read_alarm = jz4740_rtc_read_alarm,
.set_alarm = jz4740_rtc_set_alarm,
- .update_irq_enable = jz4740_rtc_update_irq_enable,
.alarm_irq_enable = jz4740_rtc_alarm_irq_enable,
};
return m41t80_set_datetime(to_i2c_client(dev), tm);
}
-#if defined(CONFIG_RTC_INTF_DEV) || defined(CONFIG_RTC_INTF_DEV_MODULE)
-static int
-m41t80_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+static int m41t80_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct i2c_client *client = to_i2c_client(dev);
int rc;
- switch (cmd) {
- case RTC_AIE_OFF:
- case RTC_AIE_ON:
- break;
- default:
- return -ENOIOCTLCMD;
- }
-
rc = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_MON);
if (rc < 0)
goto err;
- switch (cmd) {
- case RTC_AIE_OFF:
- rc &= ~M41T80_ALMON_AFE;
- break;
- case RTC_AIE_ON:
+
+ if (enabled)
rc |= M41T80_ALMON_AFE;
- break;
- }
+ else
+ rc &= ~M41T80_ALMON_AFE;
+
if (i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON, rc) < 0)
goto err;
+
return 0;
err:
return -EIO;
}
-#else
-#define m41t80_rtc_ioctl NULL
-#endif
static int m41t80_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *t)
{
.read_alarm = m41t80_rtc_read_alarm,
.set_alarm = m41t80_rtc_set_alarm,
.proc = m41t80_rtc_proc,
- .ioctl = m41t80_rtc_ioctl,
+ .alarm_irq_enable = m41t80_rtc_alarm_irq_enable,
};
#if defined(CONFIG_RTC_INTF_SYSFS) || defined(CONFIG_RTC_INTF_SYSFS_MODULE)
/*
* Handle commands from user-space
*/
-static int m48t59_rtc_ioctl(struct device *dev, unsigned int cmd,
- unsigned long arg)
+static int m48t59_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct platform_device *pdev = to_platform_device(dev);
struct m48t59_plat_data *pdata = pdev->dev.platform_data;
struct m48t59_private *m48t59 = platform_get_drvdata(pdev);
unsigned long flags;
- int ret = 0;
spin_lock_irqsave(&m48t59->lock, flags);
- switch (cmd) {
- case RTC_AIE_OFF: /* alarm interrupt off */
- M48T59_WRITE(0x00, M48T59_INTR);
- break;
- case RTC_AIE_ON: /* alarm interrupt on */
+ if (enabled)
M48T59_WRITE(M48T59_INTR_AFE, M48T59_INTR);
- break;
- default:
- ret = -ENOIOCTLCMD;
- break;
- }
+ else
+ M48T59_WRITE(0x00, M48T59_INTR);
spin_unlock_irqrestore(&m48t59->lock, flags);
- return ret;
+ return 0;
}
static int m48t59_rtc_proc(struct device *dev, struct seq_file *seq)
}
static const struct rtc_class_ops m48t59_rtc_ops = {
- .ioctl = m48t59_rtc_ioctl,
.read_time = m48t59_rtc_read_time,
.set_time = m48t59_rtc_set_time,
.read_alarm = m48t59_rtc_readalarm,
.set_alarm = m48t59_rtc_setalarm,
.proc = m48t59_rtc_proc,
+ .alarm_irq_enable = m48t59_rtc_alarm_irq_enable,
};
static const struct rtc_class_ops m48t02_rtc_ops = {
return IRQ_HANDLED;
}
-static int mc13xxx_rtc_update_irq_enable(struct device *dev,
- unsigned int enabled)
-{
- return mc13xxx_rtc_irq_enable(dev, enabled, MC13XXX_IRQ_1HZ);
-}
-
static int mc13xxx_rtc_alarm_irq_enable(struct device *dev,
unsigned int enabled)
{
.read_alarm = mc13xxx_rtc_read_alarm,
.set_alarm = mc13xxx_rtc_set_alarm,
.alarm_irq_enable = mc13xxx_rtc_alarm_irq_enable,
- .update_irq_enable = mc13xxx_rtc_update_irq_enable,
};
static irqreturn_t mc13xxx_rtc_reset_handler(int irq, void *dev)
return 0;
}
-static int mpc5121_rtc_update_irq_enable(struct device *dev,
- unsigned int enabled)
-{
- struct mpc5121_rtc_data *rtc = dev_get_drvdata(dev);
- struct mpc5121_rtc_regs __iomem *regs = rtc->regs;
- int val;
-
- val = in_8(®s->int_enable);
-
- if (enabled)
- val = (val & ~0x8) | 0x1;
- else
- val &= ~0x1;
-
- out_8(®s->int_enable, val);
-
- return 0;
-}
-
static const struct rtc_class_ops mpc5121_rtc_ops = {
.read_time = mpc5121_rtc_read_time,
.set_time = mpc5121_rtc_set_time,
.read_alarm = mpc5121_rtc_read_alarm,
.set_alarm = mpc5121_rtc_set_alarm,
.alarm_irq_enable = mpc5121_rtc_alarm_irq_enable,
- .update_irq_enable = mpc5121_rtc_update_irq_enable,
};
static int __devinit mpc5121_rtc_probe(struct platform_device *op,
return 0;
}
-static int mrst_irq_set_state(struct device *dev, int enabled)
+/* Currently, the vRTC doesn't support UIE ON/OFF */
+static int mrst_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct mrst_rtc *mrst = dev_get_drvdata(dev);
unsigned long flags;
- if (!mrst->irq)
- return -ENXIO;
-
spin_lock_irqsave(&rtc_lock, flags);
-
if (enabled)
- mrst_irq_enable(mrst, RTC_PIE);
+ mrst_irq_enable(mrst, RTC_AIE);
else
- mrst_irq_disable(mrst, RTC_PIE);
-
- spin_unlock_irqrestore(&rtc_lock, flags);
- return 0;
-}
-
-#if defined(CONFIG_RTC_INTF_DEV) || defined(CONFIG_RTC_INTF_DEV_MODULE)
-
-/* Currently, the vRTC doesn't support UIE ON/OFF */
-static int
-mrst_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
-{
- struct mrst_rtc *mrst = dev_get_drvdata(dev);
- unsigned long flags;
-
- switch (cmd) {
- case RTC_AIE_OFF:
- case RTC_AIE_ON:
- if (!mrst->irq)
- return -EINVAL;
- break;
- default:
- /* PIE ON/OFF is handled by mrst_irq_set_state() */
- return -ENOIOCTLCMD;
- }
-
- spin_lock_irqsave(&rtc_lock, flags);
- switch (cmd) {
- case RTC_AIE_OFF: /* alarm off */
mrst_irq_disable(mrst, RTC_AIE);
- break;
- case RTC_AIE_ON: /* alarm on */
- mrst_irq_enable(mrst, RTC_AIE);
- break;
- }
spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
-#else
-#define mrst_rtc_ioctl NULL
-#endif
#if defined(CONFIG_RTC_INTF_PROC) || defined(CONFIG_RTC_INTF_PROC_MODULE)
#endif
static const struct rtc_class_ops mrst_rtc_ops = {
- .ioctl = mrst_rtc_ioctl,
.read_time = mrst_read_time,
.set_time = mrst_set_time,
.read_alarm = mrst_read_alarm,
.set_alarm = mrst_set_alarm,
.proc = mrst_procfs,
- .irq_set_state = mrst_irq_set_state,
+ .alarm_irq_enable = mrst_rtc_alarm_irq_enable,
};
static struct mrst_rtc mrst_rtc;
static inline void msm6242_write(struct msm6242_priv *priv, unsigned int val,
unsigned int reg)
{
- return __raw_writel(val, &priv->regs[reg]);
+ __raw_writel(val, &priv->regs[reg]);
}
static inline void msm6242_set(struct msm6242_priv *priv, unsigned int val,
return 0;
}
-static int mv_rtc_ioctl(struct device *dev, unsigned int cmd,
- unsigned long arg)
+static int mv_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct platform_device *pdev = to_platform_device(dev);
struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
void __iomem *ioaddr = pdata->ioaddr;
if (pdata->irq < 0)
- return -ENOIOCTLCMD; /* fall back into rtc-dev's emulation */
- switch (cmd) {
- case RTC_AIE_OFF:
- writel(0, ioaddr + RTC_ALARM_INTERRUPT_MASK_REG_OFFS);
- break;
- case RTC_AIE_ON:
+ return -EINVAL; /* fall back into rtc-dev's emulation */
+
+ if (enabled)
writel(1, ioaddr + RTC_ALARM_INTERRUPT_MASK_REG_OFFS);
- break;
- default:
- return -ENOIOCTLCMD;
- }
+ else
+ writel(0, ioaddr + RTC_ALARM_INTERRUPT_MASK_REG_OFFS);
return 0;
}
.set_time = mv_rtc_set_time,
.read_alarm = mv_rtc_read_alarm,
.set_alarm = mv_rtc_set_alarm,
- .ioctl = mv_rtc_ioctl,
+ .alarm_irq_enable = mv_rtc_alarm_irq_enable,
};
static int __devinit mv_rtc_probe(struct platform_device *pdev)
return 0;
}
-static int mxc_rtc_update_irq_enable(struct device *dev, unsigned int enabled)
-{
- mxc_rtc_irq_enable(dev, RTC_1HZ_BIT, enabled);
- return 0;
-}
-
/*
* This function reads the current RTC time into tm in Gregorian date.
*/
.read_alarm = mxc_rtc_read_alarm,
.set_alarm = mxc_rtc_set_alarm,
.alarm_irq_enable = mxc_rtc_alarm_irq_enable,
- .update_irq_enable = mxc_rtc_update_irq_enable,
};
static int __init mxc_rtc_probe(struct platform_device *pdev)
gettm->bcd_hour = bin2bcd(settm->tm_hour) << 16;
}
-static int nuc900_update_irq_enable(struct device *dev, unsigned int enabled)
-{
- struct nuc900_rtc *rtc = dev_get_drvdata(dev);
-
- if (enabled)
- __raw_writel(__raw_readl(rtc->rtc_reg + REG_RTC_RIER)|
- (TICKINTENB), rtc->rtc_reg + REG_RTC_RIER);
- else
- __raw_writel(__raw_readl(rtc->rtc_reg + REG_RTC_RIER)&
- (~TICKINTENB), rtc->rtc_reg + REG_RTC_RIER);
-
- return 0;
-}
-
static int nuc900_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct nuc900_rtc *rtc = dev_get_drvdata(dev);
.read_alarm = nuc900_rtc_read_alarm,
.set_alarm = nuc900_rtc_set_alarm,
.alarm_irq_enable = nuc900_alarm_irq_enable,
- .update_irq_enable = nuc900_update_irq_enable,
};
static int __devinit nuc900_rtc_probe(struct platform_device *pdev)
return IRQ_HANDLED;
}
-#ifdef CONFIG_RTC_INTF_DEV
-
-static int
-omap_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+static int omap_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
u8 reg;
- switch (cmd) {
- case RTC_AIE_OFF:
- case RTC_AIE_ON:
- case RTC_UIE_OFF:
- case RTC_UIE_ON:
- break;
- default:
- return -ENOIOCTLCMD;
- }
-
local_irq_disable();
rtc_wait_not_busy();
reg = rtc_read(OMAP_RTC_INTERRUPTS_REG);
- switch (cmd) {
- /* AIE = Alarm Interrupt Enable */
- case RTC_AIE_OFF:
- reg &= ~OMAP_RTC_INTERRUPTS_IT_ALARM;
- break;
- case RTC_AIE_ON:
+ if (enabled)
reg |= OMAP_RTC_INTERRUPTS_IT_ALARM;
- break;
- /* UIE = Update Interrupt Enable (1/second) */
- case RTC_UIE_OFF:
- reg &= ~OMAP_RTC_INTERRUPTS_IT_TIMER;
- break;
- case RTC_UIE_ON:
- reg |= OMAP_RTC_INTERRUPTS_IT_TIMER;
- break;
- }
+ else
+ reg &= ~OMAP_RTC_INTERRUPTS_IT_ALARM;
rtc_wait_not_busy();
rtc_write(reg, OMAP_RTC_INTERRUPTS_REG);
local_irq_enable();
return 0;
}
-#else
-#define omap_rtc_ioctl NULL
-#endif
-
/* this hardware doesn't support "don't care" alarm fields */
static int tm2bcd(struct rtc_time *tm)
{
}
static struct rtc_class_ops omap_rtc_ops = {
- .ioctl = omap_rtc_ioctl,
.read_time = omap_rtc_read_time,
.set_time = omap_rtc_set_time,
.read_alarm = omap_rtc_read_alarm,
.set_alarm = omap_rtc_set_alarm,
+ .alarm_irq_enable = omap_rtc_alarm_irq_enable,
};
static int omap_rtc_alarm;
return pcap_rtc_irq_enable(dev, PCAP_IRQ_TODA, en);
}
-static int pcap_rtc_update_irq_enable(struct device *dev, unsigned int en)
-{
- return pcap_rtc_irq_enable(dev, PCAP_IRQ_1HZ, en);
-}
-
static const struct rtc_class_ops pcap_rtc_ops = {
.read_time = pcap_rtc_read_time,
.read_alarm = pcap_rtc_read_alarm,
.set_alarm = pcap_rtc_set_alarm,
.set_mmss = pcap_rtc_set_mmss,
.alarm_irq_enable = pcap_rtc_alarm_irq_enable,
- .update_irq_enable = pcap_rtc_update_irq_enable,
};
static int __devinit pcap_rtc_probe(struct platform_device *pdev)
return 0;
}
-static int
-pcf50633_rtc_update_irq_enable(struct device *dev, unsigned int enabled)
-{
- struct pcf50633_rtc *rtc = dev_get_drvdata(dev);
- int err;
-
- if (enabled)
- err = pcf50633_irq_unmask(rtc->pcf, PCF50633_IRQ_SECOND);
- else
- err = pcf50633_irq_mask(rtc->pcf, PCF50633_IRQ_SECOND);
-
- if (err < 0)
- return err;
-
- rtc->second_enabled = enabled;
-
- return 0;
-}
-
static int pcf50633_rtc_read_time(struct device *dev, struct rtc_time *tm)
{
struct pcf50633_rtc *rtc;
.set_time = pcf50633_rtc_set_time,
.read_alarm = pcf50633_rtc_read_alarm,
.set_alarm = pcf50633_rtc_set_alarm,
- .alarm_irq_enable = pcf50633_rtc_alarm_irq_enable,
- .update_irq_enable = pcf50633_rtc_update_irq_enable,
+ .alarm_irq_enable = pcf50633_rtc_alarm_irq_enable,
};
static void pcf50633_rtc_irq(int irq, void *data)
return IRQ_HANDLED;
}
-static int pl030_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
-{
- return -ENOIOCTLCMD;
-}
-
static int pl030_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
{
struct pl030_rtc *rtc = dev_get_drvdata(dev);
}
static const struct rtc_class_ops pl030_ops = {
- .ioctl = pl030_ioctl,
.read_time = pl030_read_time,
.set_time = pl030_set_time,
.read_alarm = pl030_read_alarm,
return ret;
}
-/* Periodic interrupt is only available in ST variants. */
-static int pl031_irq_set_state(struct device *dev, int enabled)
-{
- struct pl031_local *ldata = dev_get_drvdata(dev);
-
- if (enabled == 1) {
- /* Clear any pending timer interrupt. */
- writel(RTC_BIT_PI, ldata->base + RTC_ICR);
-
- writel(readl(ldata->base + RTC_IMSC) | RTC_BIT_PI,
- ldata->base + RTC_IMSC);
-
- /* Now start the timer */
- writel(readl(ldata->base + RTC_TCR) | RTC_TCR_EN,
- ldata->base + RTC_TCR);
-
- } else {
- writel(readl(ldata->base + RTC_IMSC) & (~RTC_BIT_PI),
- ldata->base + RTC_IMSC);
-
- /* Also stop the timer */
- writel(readl(ldata->base + RTC_TCR) & (~RTC_TCR_EN),
- ldata->base + RTC_TCR);
- }
- /* Wait at least 1 RTC32 clock cycle to ensure next access
- * to RTC_TCR will succeed.
- */
- udelay(40);
-
- return 0;
-}
-
-static int pl031_irq_set_freq(struct device *dev, int freq)
-{
- struct pl031_local *ldata = dev_get_drvdata(dev);
-
- /* Cant set timer if it is already enabled */
- if (readl(ldata->base + RTC_TCR) & RTC_TCR_EN) {
- dev_err(dev, "can't change frequency while timer enabled\n");
- return -EINVAL;
- }
-
- /* If self start bit in RTC_TCR is set timer will start here,
- * but we never set that bit. Instead we start the timer when
- * set_state is called with enabled == 1.
- */
- writel(RTC_TIMER_FREQ / freq, ldata->base + RTC_TLR);
-
- return 0;
-}
-
static int pl031_remove(struct amba_device *adev)
{
struct pl031_local *ldata = dev_get_drvdata(&adev->dev);
.read_alarm = pl031_read_alarm,
.set_alarm = pl031_set_alarm,
.alarm_irq_enable = pl031_alarm_irq_enable,
- .irq_set_state = pl031_irq_set_state,
- .irq_set_freq = pl031_irq_set_freq,
};
/* And the second ST derivative */
.read_alarm = pl031_stv2_read_alarm,
.set_alarm = pl031_stv2_set_alarm,
.alarm_irq_enable = pl031_alarm_irq_enable,
- .irq_set_state = pl031_irq_set_state,
- .irq_set_freq = pl031_irq_set_freq,
};
static struct amba_id pl031_ids[] = {
alrm.enabled ? "yes" : "no");
seq_printf(seq, "alrm_pending\t: %s\n",
alrm.pending ? "yes" : "no");
+ seq_printf(seq, "update IRQ enabled\t: %s\n",
+ (rtc->uie_rtctimer.enabled) ? "yes" : "no");
+ seq_printf(seq, "periodic IRQ enabled\t: %s\n",
+ (rtc->pie_enabled) ? "yes" : "no");
+ seq_printf(seq, "periodic IRQ frequency\t: %d\n",
+ rtc->irq_freq);
+ seq_printf(seq, "max user IRQ frequency\t: %d\n",
+ rtc->max_user_freq);
}
seq_printf(seq, "24hr\t\t: yes\n");
static int rtc_proc_open(struct inode *inode, struct file *file)
{
+ int ret;
struct rtc_device *rtc = PDE(inode)->data;
if (!try_module_get(THIS_MODULE))
return -ENODEV;
- return single_open(file, rtc_proc_show, rtc);
+ ret = single_open(file, rtc_proc_show, rtc);
+ if (ret)
+ module_put(THIS_MODULE);
+ return ret;
}
static int rtc_proc_release(struct inode *inode, struct file *file)
free_irq(pxa_rtc->irq_1Hz, dev);
}
-static int pxa_periodic_irq_set_freq(struct device *dev, int freq)
-{
- struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
- int period_ms;
-
- if (freq < 1 || freq > MAXFREQ_PERIODIC)
- return -EINVAL;
-
- period_ms = 1000 / freq;
- rtc_writel(pxa_rtc, PIAR, period_ms);
-
- return 0;
-}
-
-static int pxa_periodic_irq_set_state(struct device *dev, int enabled)
-{
- struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
-
- if (enabled)
- rtsr_set_bits(pxa_rtc, RTSR_PIALE | RTSR_PICE);
- else
- rtsr_clear_bits(pxa_rtc, RTSR_PIALE | RTSR_PICE);
-
- return 0;
-}
-
static int pxa_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
return 0;
}
-static int pxa_update_irq_enable(struct device *dev, unsigned int enabled)
-{
- struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
-
- spin_lock_irq(&pxa_rtc->lock);
-
- if (enabled)
- rtsr_set_bits(pxa_rtc, RTSR_HZE);
- else
- rtsr_clear_bits(pxa_rtc, RTSR_HZE);
-
- spin_unlock_irq(&pxa_rtc->lock);
- return 0;
-}
-
static int pxa_rtc_read_time(struct device *dev, struct rtc_time *tm)
{
struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
.read_alarm = pxa_rtc_read_alarm,
.set_alarm = pxa_rtc_set_alarm,
.alarm_irq_enable = pxa_alarm_irq_enable,
- .update_irq_enable = pxa_update_irq_enable,
.proc = pxa_rtc_proc,
- .irq_set_state = pxa_periodic_irq_set_state,
- .irq_set_freq = pxa_periodic_irq_set_freq,
};
static int __init pxa_rtc_probe(struct platform_device *pdev)
static inline void rp5c01_write(struct rp5c01_priv *priv, unsigned int val,
unsigned int reg)
{
- return __raw_writel(val, &priv->regs[reg]);
+ __raw_writel(val, &priv->regs[reg]);
}
static void rp5c01_lock(struct rp5c01_priv *priv)
return rs5c372_set_datetime(to_i2c_client(dev), tm);
}
-#if defined(CONFIG_RTC_INTF_DEV) || defined(CONFIG_RTC_INTF_DEV_MODULE)
-static int
-rs5c_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+static int rs5c_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct i2c_client *client = to_i2c_client(dev);
struct rs5c372 *rs5c = i2c_get_clientdata(client);
int status, addr;
buf = rs5c->regs[RS5C_REG_CTRL1];
- switch (cmd) {
- case RTC_UIE_OFF:
- case RTC_UIE_ON:
- /* some 327a modes use a different IRQ pin for 1Hz irqs */
- if (rs5c->type == rtc_rs5c372a
- && (buf & RS5C372A_CTRL1_SL1))
- return -ENOIOCTLCMD;
- case RTC_AIE_OFF:
- case RTC_AIE_ON:
- /* these irq management calls only make sense for chips
- * which are wired up to an IRQ.
- */
- if (!rs5c->has_irq)
- return -ENOIOCTLCMD;
- break;
- default:
- return -ENOIOCTLCMD;
- }
+
+ if (!rs5c->has_irq)
+ return -EINVAL;
status = rs5c_get_regs(rs5c);
if (status < 0)
return status;
addr = RS5C_ADDR(RS5C_REG_CTRL1);
- switch (cmd) {
- case RTC_AIE_OFF: /* alarm off */
- buf &= ~RS5C_CTRL1_AALE;
- break;
- case RTC_AIE_ON: /* alarm on */
+ if (enabled)
buf |= RS5C_CTRL1_AALE;
- break;
- case RTC_UIE_OFF: /* update off */
- buf &= ~RS5C_CTRL1_CT_MASK;
- break;
- case RTC_UIE_ON: /* update on */
- buf &= ~RS5C_CTRL1_CT_MASK;
- buf |= RS5C_CTRL1_CT4;
- break;
- }
+ else
+ buf &= ~RS5C_CTRL1_AALE;
if (i2c_smbus_write_byte_data(client, addr, buf) < 0) {
printk(KERN_WARNING "%s: can't update alarm\n",
return status;
}
-#else
-#define rs5c_rtc_ioctl NULL
-#endif
-
/* NOTE: Since RTC_WKALM_{RD,SET} were originally defined for EFI,
* which only exposes a polled programming interface; and since
static const struct rtc_class_ops rs5c372_rtc_ops = {
.proc = rs5c372_rtc_proc,
- .ioctl = rs5c_rtc_ioctl,
.read_time = rs5c372_rtc_read_time,
.set_time = rs5c372_rtc_set_time,
.read_alarm = rs5c_read_alarm,
.set_alarm = rs5c_set_alarm,
+ .alarm_irq_enable = rs5c_rtc_alarm_irq_enable,
};
#if defined(CONFIG_RTC_INTF_SYSFS) || defined(CONFIG_RTC_INTF_SYSFS_MODULE)
return 0;
}
-static int rx8025_irq_set_state(struct device *dev, int enabled)
-{
- struct i2c_client *client = to_i2c_client(dev);
- struct rx8025_data *rx8025 = i2c_get_clientdata(client);
- int ctrl1;
- int err;
-
- if (client->irq <= 0)
- return -ENXIO;
-
- ctrl1 = rx8025->ctrl1 & ~RX8025_BIT_CTRL1_CT;
- if (enabled)
- ctrl1 |= RX8025_BIT_CTRL1_CT_1HZ;
- if (ctrl1 != rx8025->ctrl1) {
- rx8025->ctrl1 = ctrl1;
- err = rx8025_write_reg(rx8025->client, RX8025_REG_CTRL1,
- rx8025->ctrl1);
- if (err)
- return err;
- }
-
- return 0;
-}
-
static struct rtc_class_ops rx8025_rtc_ops = {
.read_time = rx8025_get_time,
.set_time = rx8025_set_time,
.read_alarm = rx8025_read_alarm,
.set_alarm = rx8025_set_alarm,
.alarm_irq_enable = rx8025_alarm_irq_enable,
- .irq_set_state = rx8025_irq_set_state,
};
/*
}
/* Update control registers */
-static void s3c_rtc_setaie(int to)
+static int s3c_rtc_setaie(struct device *dev, unsigned int enabled)
{
unsigned int tmp;
- pr_debug("%s: aie=%d\n", __func__, to);
+ pr_debug("%s: aie=%d\n", __func__, enabled);
tmp = readb(s3c_rtc_base + S3C2410_RTCALM) & ~S3C2410_RTCALM_ALMEN;
- if (to)
+ if (enabled)
tmp |= S3C2410_RTCALM_ALMEN;
writeb(tmp, s3c_rtc_base + S3C2410_RTCALM);
-}
-
-static int s3c_rtc_setpie(struct device *dev, int enabled)
-{
- unsigned int tmp;
-
- pr_debug("%s: pie=%d\n", __func__, enabled);
-
- spin_lock_irq(&s3c_rtc_pie_lock);
-
- if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
- tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
- tmp &= ~S3C64XX_RTCCON_TICEN;
-
- if (enabled)
- tmp |= S3C64XX_RTCCON_TICEN;
-
- writew(tmp, s3c_rtc_base + S3C2410_RTCCON);
- } else {
- tmp = readb(s3c_rtc_base + S3C2410_TICNT);
- tmp &= ~S3C2410_TICNT_ENABLE;
-
- if (enabled)
- tmp |= S3C2410_TICNT_ENABLE;
-
- writeb(tmp, s3c_rtc_base + S3C2410_TICNT);
- }
-
- spin_unlock_irq(&s3c_rtc_pie_lock);
return 0;
}
writeb(alrm_en, base + S3C2410_RTCALM);
- s3c_rtc_setaie(alrm->enabled);
+ s3c_rtc_setaie(dev, alrm->enabled);
return 0;
}
.set_time = s3c_rtc_settime,
.read_alarm = s3c_rtc_getalarm,
.set_alarm = s3c_rtc_setalarm,
- .irq_set_freq = s3c_rtc_setfreq,
- .irq_set_state = s3c_rtc_setpie,
.proc = s3c_rtc_proc,
.alarm_irq_enable = s3c_rtc_setaie,
};
rtc_device_unregister(rtc);
s3c_rtc_setpie(&dev->dev, 0);
- s3c_rtc_setaie(0);
+ s3c_rtc_setaie(&dev->dev, 0);
clk_disable(rtc_clk);
clk_put(rtc_clk);
#define RTC_DEF_TRIM 0
static const unsigned long RTC_FREQ = 1024;
-static unsigned long timer_freq;
static struct rtc_time rtc_alarm;
static DEFINE_SPINLOCK(sa1100_rtc_lock);
return IRQ_HANDLED;
}
-static int sa1100_irq_set_freq(struct device *dev, int freq)
-{
- if (freq < 1 || freq > timer_freq) {
- return -EINVAL;
- } else {
- struct rtc_device *rtc = (struct rtc_device *)dev;
-
- rtc->irq_freq = freq;
-
- return 0;
- }
-}
-
-static int rtc_timer1_count;
-
-static int sa1100_irq_set_state(struct device *dev, int enabled)
-{
- spin_lock_irq(&sa1100_rtc_lock);
- if (enabled) {
- struct rtc_device *rtc = (struct rtc_device *)dev;
-
- OSMR1 = timer_freq / rtc->irq_freq + OSCR;
- OIER |= OIER_E1;
- rtc_timer1_count = 1;
- } else {
- OIER &= ~OIER_E1;
- }
- spin_unlock_irq(&sa1100_rtc_lock);
-
- return 0;
-}
-
-static inline int sa1100_timer1_retrigger(struct rtc_device *rtc)
-{
- unsigned long diff;
- unsigned long period = timer_freq / rtc->irq_freq;
-
- spin_lock_irq(&sa1100_rtc_lock);
-
- do {
- OSMR1 += period;
- diff = OSMR1 - OSCR;
- /* If OSCR > OSMR1, diff is a very large number (unsigned
- * math). This means we have a lost interrupt. */
- } while (diff > period);
- OIER |= OIER_E1;
-
- spin_unlock_irq(&sa1100_rtc_lock);
-
- return 0;
-}
-
-static irqreturn_t timer1_interrupt(int irq, void *dev_id)
-{
- struct platform_device *pdev = to_platform_device(dev_id);
- struct rtc_device *rtc = platform_get_drvdata(pdev);
-
- /*
- * If we match for the first time, rtc_timer1_count will be 1.
- * Otherwise, we wrapped around (very unlikely but
- * still possible) so compute the amount of missed periods.
- * The match reg is updated only when the data is actually retrieved
- * to avoid unnecessary interrupts.
- */
- OSSR = OSSR_M1; /* clear match on timer1 */
-
- rtc_update_irq(rtc, rtc_timer1_count, RTC_PF | RTC_IRQF);
-
- if (rtc_timer1_count == 1)
- rtc_timer1_count =
- (rtc->irq_freq * ((1 << 30) / (timer_freq >> 2)));
-
- /* retrigger. */
- sa1100_timer1_retrigger(rtc);
-
- return IRQ_HANDLED;
-}
-
-static int sa1100_rtc_read_callback(struct device *dev, int data)
-{
- if (data & RTC_PF) {
- struct rtc_device *rtc = (struct rtc_device *)dev;
-
- /* interpolate missed periods and set match for the next */
- unsigned long period = timer_freq / rtc->irq_freq;
- unsigned long oscr = OSCR;
- unsigned long osmr1 = OSMR1;
- unsigned long missed = (oscr - osmr1)/period;
- data += missed << 8;
- OSSR = OSSR_M1; /* clear match on timer 1 */
- OSMR1 = osmr1 + (missed + 1)*period;
- /* Ensure we didn't miss another match in the mean time.
- * Here we compare (match - OSCR) 8 instead of 0 --
- * see comment in pxa_timer_interrupt() for explanation.
- */
- while ((signed long)((osmr1 = OSMR1) - OSCR) <= 8) {
- data += 0x100;
- OSSR = OSSR_M1; /* clear match on timer 1 */
- OSMR1 = osmr1 + period;
- }
- }
- return data;
-}
-
static int sa1100_rtc_open(struct device *dev)
{
int ret;
- struct rtc_device *rtc = (struct rtc_device *)dev;
+ struct platform_device *plat_dev = to_platform_device(dev);
+ struct rtc_device *rtc = platform_get_drvdata(plat_dev);
ret = request_irq(IRQ_RTC1Hz, sa1100_rtc_interrupt, IRQF_DISABLED,
"rtc 1Hz", dev);
dev_err(dev, "IRQ %d already in use.\n", IRQ_RTCAlrm);
goto fail_ai;
}
- ret = request_irq(IRQ_OST1, timer1_interrupt, IRQF_DISABLED,
- "rtc timer", dev);
- if (ret) {
- dev_err(dev, "IRQ %d already in use.\n", IRQ_OST1);
- goto fail_pi;
- }
rtc->max_user_freq = RTC_FREQ;
- sa1100_irq_set_freq(dev, RTC_FREQ);
+ rtc_irq_set_freq(rtc, NULL, RTC_FREQ);
return 0;
- fail_pi:
- free_irq(IRQ_RTCAlrm, dev);
fail_ai:
free_irq(IRQ_RTC1Hz, dev);
fail_ui:
OSSR = OSSR_M1;
spin_unlock_irq(&sa1100_rtc_lock);
- free_irq(IRQ_OST1, dev);
free_irq(IRQ_RTCAlrm, dev);
free_irq(IRQ_RTC1Hz, dev);
}
-
-static int sa1100_rtc_ioctl(struct device *dev, unsigned int cmd,
- unsigned long arg)
+static int sa1100_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
- switch (cmd) {
- case RTC_AIE_OFF:
- spin_lock_irq(&sa1100_rtc_lock);
- RTSR &= ~RTSR_ALE;
- spin_unlock_irq(&sa1100_rtc_lock);
- return 0;
- case RTC_AIE_ON:
- spin_lock_irq(&sa1100_rtc_lock);
+ spin_lock_irq(&sa1100_rtc_lock);
+ if (enabled)
RTSR |= RTSR_ALE;
- spin_unlock_irq(&sa1100_rtc_lock);
- return 0;
- case RTC_UIE_OFF:
- spin_lock_irq(&sa1100_rtc_lock);
- RTSR &= ~RTSR_HZE;
- spin_unlock_irq(&sa1100_rtc_lock);
- return 0;
- case RTC_UIE_ON:
- spin_lock_irq(&sa1100_rtc_lock);
- RTSR |= RTSR_HZE;
- spin_unlock_irq(&sa1100_rtc_lock);
- return 0;
- }
- return -ENOIOCTLCMD;
+ else
+ RTSR &= ~RTSR_ALE;
+ spin_unlock_irq(&sa1100_rtc_lock);
+ return 0;
}
static int sa1100_rtc_read_time(struct device *dev, struct rtc_time *tm)
static int sa1100_rtc_proc(struct device *dev, struct seq_file *seq)
{
- struct rtc_device *rtc = (struct rtc_device *)dev;
-
- seq_printf(seq, "trim/divider\t: 0x%08x\n", (u32) RTTR);
- seq_printf(seq, "update_IRQ\t: %s\n",
- (RTSR & RTSR_HZE) ? "yes" : "no");
- seq_printf(seq, "periodic_IRQ\t: %s\n",
- (OIER & OIER_E1) ? "yes" : "no");
- seq_printf(seq, "periodic_freq\t: %d\n", rtc->irq_freq);
- seq_printf(seq, "RTSR\t\t: 0x%08x\n", (u32)RTSR);
+ seq_printf(seq, "trim/divider\t\t: 0x%08x\n", (u32) RTTR);
+ seq_printf(seq, "RTSR\t\t\t: 0x%08x\n", (u32)RTSR);
return 0;
}
static const struct rtc_class_ops sa1100_rtc_ops = {
.open = sa1100_rtc_open,
- .read_callback = sa1100_rtc_read_callback,
.release = sa1100_rtc_release,
- .ioctl = sa1100_rtc_ioctl,
.read_time = sa1100_rtc_read_time,
.set_time = sa1100_rtc_set_time,
.read_alarm = sa1100_rtc_read_alarm,
.set_alarm = sa1100_rtc_set_alarm,
.proc = sa1100_rtc_proc,
- .irq_set_freq = sa1100_irq_set_freq,
- .irq_set_state = sa1100_irq_set_state,
+ .alarm_irq_enable = sa1100_rtc_alarm_irq_enable,
};
static int sa1100_rtc_probe(struct platform_device *pdev)
{
struct rtc_device *rtc;
- timer_freq = get_clock_tick_rate();
-
/*
* According to the manual we should be able to let RTTR be zero
* and then a default diviser for a 32.768KHz clock is used.
platform_set_drvdata(pdev, rtc);
- /* Set the irq_freq */
- /*TODO: Find out who is messing with this value after we initialize
- * it here.*/
- rtc->irq_freq = RTC_FREQ;
-
/* Fix for a nasty initialization problem the in SA11xx RTSR register.
* See also the comments in sa1100_rtc_interrupt().
*
spin_unlock_irq(&rtc->lock);
}
-static int sh_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+static int sh_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
- struct sh_rtc *rtc = dev_get_drvdata(dev);
- unsigned int ret = 0;
-
- switch (cmd) {
- case RTC_AIE_OFF:
- case RTC_AIE_ON:
- sh_rtc_setaie(dev, cmd == RTC_AIE_ON);
- break;
- case RTC_UIE_OFF:
- rtc->periodic_freq &= ~PF_OXS;
- sh_rtc_setcie(dev, 0);
- break;
- case RTC_UIE_ON:
- rtc->periodic_freq |= PF_OXS;
- sh_rtc_setcie(dev, 1);
- break;
- default:
- ret = -ENOIOCTLCMD;
- }
-
- return ret;
+ sh_rtc_setaie(dev, enabled);
+ return 0;
}
static int sh_rtc_read_time(struct device *dev, struct rtc_time *tm)
}
static struct rtc_class_ops sh_rtc_ops = {
- .ioctl = sh_rtc_ioctl,
.read_time = sh_rtc_read_time,
.set_time = sh_rtc_set_time,
.read_alarm = sh_rtc_read_alarm,
.set_alarm = sh_rtc_set_alarm,
- .irq_set_state = sh_rtc_irq_set_state,
- .irq_set_freq = sh_rtc_irq_set_freq,
.proc = sh_rtc_proc,
+ .alarm_irq_enable = sh_rtc_alarm_irq_enable,
};
static int __init sh_rtc_probe(struct platform_device *pdev)
return 0;
}
-static int stmp3xxx_update_irq_enable(struct device *dev, unsigned int enabled)
-{
- struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
-
- if (enabled)
- stmp3xxx_setl(BM_RTC_CTRL_ONEMSEC_IRQ_EN,
- rtc_data->io + HW_RTC_CTRL);
- else
- stmp3xxx_clearl(BM_RTC_CTRL_ONEMSEC_IRQ_EN,
- rtc_data->io + HW_RTC_CTRL);
- return 0;
-}
-
static int stmp3xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
{
struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
static struct rtc_class_ops stmp3xxx_rtc_ops = {
.alarm_irq_enable =
stmp3xxx_alarm_irq_enable,
- .update_irq_enable =
- stmp3xxx_update_irq_enable,
.read_time = stmp3xxx_rtc_gettime,
.set_mmss = stmp3xxx_rtc_set_mmss,
.read_alarm = stmp3xxx_rtc_read_alarm,
return 0;
}
-static int test_rtc_ioctl(struct device *dev, unsigned int cmd,
- unsigned long arg)
+static int test_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
{
- /* We do support interrupts, they're generated
- * using the sysfs interface.
- */
- switch (cmd) {
- case RTC_PIE_ON:
- case RTC_PIE_OFF:
- case RTC_UIE_ON:
- case RTC_UIE_OFF:
- case RTC_AIE_ON:
- case RTC_AIE_OFF:
- return 0;
-
- default:
- return -ENOIOCTLCMD;
- }
+ return 0;
}
static const struct rtc_class_ops test_rtc_ops = {
.read_alarm = test_rtc_read_alarm,
.set_alarm = test_rtc_set_alarm,
.set_mmss = test_rtc_set_mmss,
- .ioctl = test_rtc_ioctl,
+ .alarm_irq_enable = test_rtc_alarm_irq_enable,
};
static ssize_t test_irq_show(struct device *dev,
struct rtc_device *rtc = platform_get_drvdata(plat_dev);
retval = count;
- if (strncmp(buf, "tick", 4) == 0)
+ if (strncmp(buf, "tick", 4) == 0 && rtc->pie_enabled)
rtc_update_irq(rtc, 1, RTC_PF | RTC_IRQF);
- else if (strncmp(buf, "alarm", 5) == 0)
- rtc_update_irq(rtc, 1, RTC_AF | RTC_IRQF);
- else if (strncmp(buf, "update", 6) == 0)
+ else if (strncmp(buf, "alarm", 5) == 0) {
+ struct rtc_wkalrm alrm;
+ int err = rtc_read_alarm(rtc, &alrm);
+
+ if (!err && alrm.enabled)
+ rtc_update_irq(rtc, 1, RTC_AF | RTC_IRQF);
+
+ } else if (strncmp(buf, "update", 6) == 0 && rtc->uie_rtctimer.enabled)
rtc_update_irq(rtc, 1, RTC_UF | RTC_IRQF);
else
retval = -EINVAL;
return ret;
}
-static int twl_rtc_update_irq_enable(struct device *dev, unsigned enabled)
-{
- int ret;
-
- if (enabled)
- ret = set_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
- else
- ret = mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
-
- return ret;
-}
-
/*
* Gets current TWL RTC time and date parameters.
*
.read_alarm = twl_rtc_read_alarm,
.set_alarm = twl_rtc_set_alarm,
.alarm_irq_enable = twl_rtc_alarm_irq_enable,
- .update_irq_enable = twl_rtc_update_irq_enable,
};
/*----------------------------------------------------------------------*/
return 0;
}
-static int vr41xx_rtc_irq_set_freq(struct device *dev, int freq)
-{
- u64 count;
-
- if (!is_power_of_2(freq))
- return -EINVAL;
- count = RTC_FREQUENCY;
- do_div(count, freq);
-
- spin_lock_irq(&rtc_lock);
-
- periodic_count = count;
- rtc1_write(RTCL1LREG, periodic_count);
- rtc1_write(RTCL1HREG, periodic_count >> 16);
-
- spin_unlock_irq(&rtc_lock);
-
- return 0;
-}
-
-static int vr41xx_rtc_irq_set_state(struct device *dev, int enabled)
-{
- if (enabled)
- enable_irq(pie_irq);
- else
- disable_irq(pie_irq);
-
- return 0;
-}
-
static int vr41xx_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
- case RTC_AIE_ON:
- spin_lock_irq(&rtc_lock);
-
- if (!alarm_enabled) {
- enable_irq(aie_irq);
- alarm_enabled = 1;
- }
-
- spin_unlock_irq(&rtc_lock);
- break;
- case RTC_AIE_OFF:
- spin_lock_irq(&rtc_lock);
-
- if (alarm_enabled) {
- disable_irq(aie_irq);
- alarm_enabled = 0;
- }
-
- spin_unlock_irq(&rtc_lock);
- break;
case RTC_EPOCH_READ:
return put_user(epoch, (unsigned long __user *)arg);
case RTC_EPOCH_SET:
return 0;
}
+static int vr41xx_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+ spin_lock_irq(&rtc_lock);
+ if (enabled) {
+ if (!alarm_enabled) {
+ enable_irq(aie_irq);
+ alarm_enabled = 1;
+ }
+ } else {
+ if (alarm_enabled) {
+ disable_irq(aie_irq);
+ alarm_enabled = 0;
+ }
+ }
+ spin_unlock_irq(&rtc_lock);
+ return 0;
+}
+
static irqreturn_t elapsedtime_interrupt(int irq, void *dev_id)
{
struct platform_device *pdev = (struct platform_device *)dev_id;
.set_time = vr41xx_rtc_set_time,
.read_alarm = vr41xx_rtc_read_alarm,
.set_alarm = vr41xx_rtc_set_alarm,
- .irq_set_freq = vr41xx_rtc_irq_set_freq,
- .irq_set_state = vr41xx_rtc_irq_set_state,
};
static int __devinit rtc_probe(struct platform_device *pdev)
return wm831x_rtc_stop_alarm(wm831x_rtc);
}
-static int wm831x_rtc_update_irq_enable(struct device *dev,
- unsigned int enabled)
-{
- struct wm831x_rtc *wm831x_rtc = dev_get_drvdata(dev);
- int val;
-
- if (enabled)
- val = 1 << WM831X_RTC_PINT_FREQ_SHIFT;
- else
- val = 0;
-
- return wm831x_set_bits(wm831x_rtc->wm831x, WM831X_RTC_CONTROL,
- WM831X_RTC_PINT_FREQ_MASK, val);
-}
-
static irqreturn_t wm831x_alm_irq(int irq, void *data)
{
struct wm831x_rtc *wm831x_rtc = data;
.read_alarm = wm831x_rtc_readalarm,
.set_alarm = wm831x_rtc_setalarm,
.alarm_irq_enable = wm831x_rtc_alarm_irq_enable,
- .update_irq_enable = wm831x_rtc_update_irq_enable,
};
#ifdef CONFIG_PM
return ret;
}
-static int wm8350_rtc_update_irq_enable(struct device *dev,
- unsigned int enabled)
-{
- struct wm8350 *wm8350 = dev_get_drvdata(dev);
-
- /* Suppress duplicate changes since genirq nests enable and
- * disable calls. */
- if (enabled == wm8350->rtc.update_enabled)
- return 0;
-
- if (enabled)
- wm8350_unmask_irq(wm8350, WM8350_IRQ_RTC_SEC);
- else
- wm8350_mask_irq(wm8350, WM8350_IRQ_RTC_SEC);
-
- wm8350->rtc.update_enabled = enabled;
-
- return 0;
-}
-
static irqreturn_t wm8350_rtc_alarm_handler(int irq, void *data)
{
struct wm8350 *wm8350 = data;
.read_alarm = wm8350_rtc_readalarm,
.set_alarm = wm8350_rtc_setalarm,
.alarm_irq_enable = wm8350_rtc_alarm_irq_enable,
- .update_irq_enable = wm8350_rtc_update_irq_enable,
};
#ifdef CONFIG_PM
static struct ccw_device_id dasd_eckd_ids[] = {
{ CCW_DEVICE_DEVTYPE (0x3990, 0, 0x3390, 0), .driver_info = 0x1},
{ CCW_DEVICE_DEVTYPE (0x2105, 0, 0x3390, 0), .driver_info = 0x2},
- { CCW_DEVICE_DEVTYPE (0x3880, 0, 0x3390, 0), .driver_info = 0x3},
+ { CCW_DEVICE_DEVTYPE (0x3880, 0, 0x3380, 0), .driver_info = 0x3},
{ CCW_DEVICE_DEVTYPE (0x3990, 0, 0x3380, 0), .driver_info = 0x4},
{ CCW_DEVICE_DEVTYPE (0x2105, 0, 0x3380, 0), .driver_info = 0x5},
{ CCW_DEVICE_DEVTYPE (0x9343, 0, 0x9345, 0), .driver_info = 0x6},
/*
* Parameter parsing functions.
*/
-static int __initdata devs = XPRAM_DEVS;
-static char __initdata *sizes[XPRAM_MAX_DEVS];
+static int devs = XPRAM_DEVS;
+static char *sizes[XPRAM_MAX_DEVS];
module_param(devs, int, 0);
module_param_array(sizes, charp, NULL, 0);
unsigned int cmd, unsigned long arg)
{
void __user *argp;
- int ct, perm;
+ unsigned int ct;
+ int perm;
argp = (void __user *)arg;
return rc;
}
+static inline void
+tape_do_io_async_free(struct tape_device *device, struct tape_request *request)
+{
+ request->callback = (void *) tape_free_request;
+ request->callback_data = NULL;
+ tape_do_io_async(device, request);
+}
+
extern int tape_oper_handler(int irq, int status);
extern void tape_noper_handler(int irq, int status);
extern int tape_open(struct tape_device *);
* Medium sense for 34xx tapes. There is no 'real' medium sense call.
* So we just do a normal sense.
*/
-static int
-tape_34xx_medium_sense(struct tape_device *device)
+static void __tape_34xx_medium_sense(struct tape_request *request)
{
- struct tape_request *request;
- unsigned char *sense;
- int rc;
-
- request = tape_alloc_request(1, 32);
- if (IS_ERR(request)) {
- DBF_EXCEPTION(6, "MSEN fail\n");
- return PTR_ERR(request);
- }
-
- request->op = TO_MSEN;
- tape_ccw_end(request->cpaddr, SENSE, 32, request->cpdata);
+ struct tape_device *device = request->device;
+ unsigned char *sense;
- rc = tape_do_io_interruptible(device, request);
if (request->rc == 0) {
sense = request->cpdata;
device->tape_generic_status |= GMT_WR_PROT(~0);
else
device->tape_generic_status &= ~GMT_WR_PROT(~0);
- } else {
+ } else
DBF_EVENT(4, "tape_34xx: medium sense failed with rc=%d\n",
request->rc);
- }
tape_free_request(request);
+}
+
+static int tape_34xx_medium_sense(struct tape_device *device)
+{
+ struct tape_request *request;
+ int rc;
+
+ request = tape_alloc_request(1, 32);
+ if (IS_ERR(request)) {
+ DBF_EXCEPTION(6, "MSEN fail\n");
+ return PTR_ERR(request);
+ }
+ request->op = TO_MSEN;
+ tape_ccw_end(request->cpaddr, SENSE, 32, request->cpdata);
+ rc = tape_do_io_interruptible(device, request);
+ __tape_34xx_medium_sense(request);
return rc;
}
+static void tape_34xx_medium_sense_async(struct tape_device *device)
+{
+ struct tape_request *request;
+
+ request = tape_alloc_request(1, 32);
+ if (IS_ERR(request)) {
+ DBF_EXCEPTION(6, "MSEN fail\n");
+ return;
+ }
+
+ request->op = TO_MSEN;
+ tape_ccw_end(request->cpaddr, SENSE, 32, request->cpdata);
+ request->callback = (void *) __tape_34xx_medium_sense;
+ request->callback_data = NULL;
+ tape_do_io_async(device, request);
+}
+
struct tape_34xx_work {
struct tape_device *device;
enum tape_op op;
* is inserted but cannot call tape_do_io* from an interrupt context.
* Maybe that's useful for other actions we want to start from the
* interrupt handler.
+ * Note: the work handler is called by the system work queue. The tape
+ * commands started by the handler need to be asynchrounous, otherwise
+ * a deadlock can occur e.g. in case of a deferred cc=1 (see __tape_do_irq).
*/
static void
tape_34xx_work_handler(struct work_struct *work)
switch(p->op) {
case TO_MSEN:
- tape_34xx_medium_sense(device);
+ tape_34xx_medium_sense_async(device);
break;
default:
DBF_EVENT(3, "T34XX: internal error: unknown work\n");
/*
* Enable encryption
*/
-static int tape_3592_enable_crypt(struct tape_device *device)
+static struct tape_request *__tape_3592_enable_crypt(struct tape_device *device)
{
struct tape_request *request;
char *data;
DBF_EVENT(6, "tape_3592_enable_crypt\n");
if (!crypt_supported(device))
- return -ENOSYS;
+ return ERR_PTR(-ENOSYS);
request = tape_alloc_request(2, 72);
if (IS_ERR(request))
- return PTR_ERR(request);
+ return request;
data = request->cpdata;
memset(data,0,72);
request->op = TO_CRYPT_ON;
tape_ccw_cc(request->cpaddr, MODE_SET_CB, 36, data);
tape_ccw_end(request->cpaddr + 1, MODE_SET_CB, 36, data + 36);
+ return request;
+}
+
+static int tape_3592_enable_crypt(struct tape_device *device)
+{
+ struct tape_request *request;
+
+ request = __tape_3592_enable_crypt(device);
+ if (IS_ERR(request))
+ return PTR_ERR(request);
return tape_do_io_free(device, request);
}
+static void tape_3592_enable_crypt_async(struct tape_device *device)
+{
+ struct tape_request *request;
+
+ request = __tape_3592_enable_crypt(device);
+ if (!IS_ERR(request))
+ tape_do_io_async_free(device, request);
+}
+
/*
* Disable encryption
*/
-static int tape_3592_disable_crypt(struct tape_device *device)
+static struct tape_request *__tape_3592_disable_crypt(struct tape_device *device)
{
struct tape_request *request;
char *data;
DBF_EVENT(6, "tape_3592_disable_crypt\n");
if (!crypt_supported(device))
- return -ENOSYS;
+ return ERR_PTR(-ENOSYS);
request = tape_alloc_request(2, 72);
if (IS_ERR(request))
- return PTR_ERR(request);
+ return request;
data = request->cpdata;
memset(data,0,72);
tape_ccw_cc(request->cpaddr, MODE_SET_CB, 36, data);
tape_ccw_end(request->cpaddr + 1, MODE_SET_CB, 36, data + 36);
+ return request;
+}
+
+static int tape_3592_disable_crypt(struct tape_device *device)
+{
+ struct tape_request *request;
+
+ request = __tape_3592_disable_crypt(device);
+ if (IS_ERR(request))
+ return PTR_ERR(request);
return tape_do_io_free(device, request);
}
+static void tape_3592_disable_crypt_async(struct tape_device *device)
+{
+ struct tape_request *request;
+
+ request = __tape_3592_disable_crypt(device);
+ if (!IS_ERR(request))
+ tape_do_io_async_free(device, request);
+}
+
/*
* IOCTL: Set encryption status
*/
/*
* SENSE Medium: Get Sense data about medium state
*/
-static int
-tape_3590_sense_medium(struct tape_device *device)
+static int tape_3590_sense_medium(struct tape_device *device)
{
struct tape_request *request;
return tape_do_io_free(device, request);
}
+static void tape_3590_sense_medium_async(struct tape_device *device)
+{
+ struct tape_request *request;
+
+ request = tape_alloc_request(1, 128);
+ if (IS_ERR(request))
+ return;
+ request->op = TO_MSEN;
+ tape_ccw_end(request->cpaddr, MEDIUM_SENSE, 128, request->cpdata);
+ tape_do_io_async_free(device, request);
+}
+
/*
* MTTELL: Tell block. Return the number of block relative to current file.
*/
* 2. The attention msg is written to the "read subsystem data" buffer.
* In this case we probably should print it to the console.
*/
-static int
-tape_3590_read_attmsg(struct tape_device *device)
+static void tape_3590_read_attmsg_async(struct tape_device *device)
{
struct tape_request *request;
char *buf;
request = tape_alloc_request(3, 4096);
if (IS_ERR(request))
- return PTR_ERR(request);
+ return;
request->op = TO_READ_ATTMSG;
buf = request->cpdata;
buf[0] = PREP_RD_SS_DATA;
tape_ccw_cc(request->cpaddr, PERFORM_SS_FUNC, 12, buf);
tape_ccw_cc(request->cpaddr + 1, READ_SS_DATA, 4096 - 12, buf + 12);
tape_ccw_end(request->cpaddr + 2, NOP, 0, NULL);
- return tape_do_io_free(device, request);
+ tape_do_io_async_free(device, request);
}
/*
* These functions are used to schedule follow-up actions from within an
* interrupt context (like unsolicited interrupts).
+ * Note: the work handler is called by the system work queue. The tape
+ * commands started by the handler need to be asynchrounous, otherwise
+ * a deadlock can occur e.g. in case of a deferred cc=1 (see __tape_do_irq).
*/
struct work_handler_data {
struct tape_device *device;
switch (p->op) {
case TO_MSEN:
- tape_3590_sense_medium(p->device);
+ tape_3590_sense_medium_async(p->device);
break;
case TO_READ_ATTMSG:
- tape_3590_read_attmsg(p->device);
+ tape_3590_read_attmsg_async(p->device);
break;
case TO_CRYPT_ON:
- tape_3592_enable_crypt(p->device);
+ tape_3592_enable_crypt_async(p->device);
break;
case TO_CRYPT_OFF:
- tape_3592_disable_crypt(p->device);
+ tape_3592_disable_crypt_async(p->device);
break;
default:
DBF_EVENT(3, "T3590: work handler undefined for "
{
struct Scsi_Host *host = rport_to_shost(rport);
fc_port_t *fcport = *(fc_port_t **)rport->dd_data;
+ unsigned long flags;
if (!fcport)
return;
* Transport has effectively 'deleted' the rport, clear
* all local references.
*/
- spin_lock_irq(host->host_lock);
+ spin_lock_irqsave(host->host_lock, flags);
fcport->rport = fcport->drport = NULL;
*((fc_port_t **)rport->dd_data) = NULL;
- spin_unlock_irq(host->host_lock);
+ spin_unlock_irqrestore(host->host_lock, flags);
if (test_bit(ABORT_ISP_ACTIVE, &fcport->vha->dpc_flags))
return;
{
fc_port_t *fcport = data;
struct fc_rport *rport;
+ unsigned long flags;
- spin_lock_irq(fcport->vha->host->host_lock);
+ spin_lock_irqsave(fcport->vha->host->host_lock, flags);
rport = fcport->drport ? fcport->drport: fcport->rport;
fcport->drport = NULL;
- spin_unlock_irq(fcport->vha->host->host_lock);
+ spin_unlock_irqrestore(fcport->vha->host->host_lock, flags);
if (rport)
fc_remote_port_delete(rport);
}
struct fc_rport_identifiers rport_ids;
struct fc_rport *rport;
struct qla_hw_data *ha = vha->hw;
+ unsigned long flags;
qla2x00_rport_del(fcport);
"Unable to allocate fc remote port!\n");
return;
}
- spin_lock_irq(fcport->vha->host->host_lock);
+ spin_lock_irqsave(fcport->vha->host->host_lock, flags);
*((fc_port_t **)rport->dd_data) = fcport;
- spin_unlock_irq(fcport->vha->host->host_lock);
+ spin_unlock_irqrestore(fcport->vha->host->host_lock, flags);
rport->supported_classes = fcport->supported_classes;
}
if (atomic_read(&fcport->state) != FCS_ONLINE) {
if (atomic_read(&fcport->state) == FCS_DEVICE_DEAD ||
- atomic_read(&fcport->state) == FCS_DEVICE_LOST ||
atomic_read(&base_vha->loop_state) == LOOP_DEAD) {
cmd->result = DID_NO_CONNECT << 16;
goto qc24_fail_command;
{
struct fc_rport *rport;
scsi_qla_host_t *base_vha;
+ unsigned long flags;
if (!fcport->rport)
return;
rport = fcport->rport;
if (defer) {
base_vha = pci_get_drvdata(vha->hw->pdev);
- spin_lock_irq(vha->host->host_lock);
+ spin_lock_irqsave(vha->host->host_lock, flags);
fcport->drport = rport;
- spin_unlock_irq(vha->host->host_lock);
+ spin_unlock_irqrestore(vha->host->host_lock, flags);
set_bit(FCPORT_UPDATE_NEEDED, &base_vha->dpc_flags);
qla2xxx_wake_dpc(base_vha);
} else
set_user_nice(current, -20);
+ set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
DEBUG3(printk("qla2x00: DPC handler sleeping\n"));
- set_current_state(TASK_INTERRUPTIBLE);
schedule();
__set_current_state(TASK_RUNNING);
qla2x00_do_dpc_all_vps(base_vha);
ha->dpc_active = 0;
+ set_current_state(TASK_INTERRUPTIBLE);
} /* End of while(1) */
+ __set_current_state(TASK_RUNNING);
DEBUG(printk("scsi(%ld): DPC handler exiting\n", base_vha->host_no));
unsigned long long lba, unsigned int num, int write)
{
int ret;
- unsigned int block, rest = 0;
+ unsigned long long block, rest = 0;
int (*func)(struct scsi_cmnd *, unsigned char *, int);
func = write ? fetch_to_dev_buffer : fill_from_dev_buffer;
&sdev->request_queue->queue_flags);
if (flagset)
queue_flag_set(QUEUE_FLAG_REENTER, sdev->request_queue);
- __blk_run_queue(sdev->request_queue);
+ __blk_run_queue(sdev->request_queue, false);
if (flagset)
queue_flag_clear(QUEUE_FLAG_REENTER, sdev->request_queue);
spin_unlock(sdev->request_queue->queue_lock);
!test_bit(QUEUE_FLAG_REENTER, &rport->rqst_q->queue_flags);
if (flagset)
queue_flag_set(QUEUE_FLAG_REENTER, rport->rqst_q);
- __blk_run_queue(rport->rqst_q);
+ __blk_run_queue(rport->rqst_q, false);
if (flagset)
queue_flag_clear(QUEUE_FLAG_REENTER, rport->rqst_q);
spin_unlock_irqrestore(rport->rqst_q->queue_lock, flags);
#include <linux/of_device.h>
#include <linux/spi/pxa2xx_spi.h>
-struct awesome_struct {
+struct ce4100_info {
struct ssp_device ssp;
- struct platform_device spi_pdev;
- struct pxa2xx_spi_master spi_pdata;
+ struct platform_device *spi_pdev;
};
static DEFINE_MUTEX(ssp_lock);
}
EXPORT_SYMBOL_GPL(pxa_ssp_free);
-static void plat_dev_release(struct device *dev)
-{
- struct awesome_struct *as = container_of(dev,
- struct awesome_struct, spi_pdev.dev);
-
- of_device_node_put(&as->spi_pdev.dev);
-}
-
static int __devinit ce4100_spi_probe(struct pci_dev *dev,
const struct pci_device_id *ent)
{
int ret;
resource_size_t phys_beg;
resource_size_t phys_len;
- struct awesome_struct *spi_info;
+ struct ce4100_info *spi_info;
struct platform_device *pdev;
- struct pxa2xx_spi_master *spi_pdata;
+ struct pxa2xx_spi_master spi_pdata;
struct ssp_device *ssp;
ret = pci_enable_device(dev);
return ret;
}
+ pdev = platform_device_alloc("pxa2xx-spi", dev->devfn);
spi_info = kzalloc(sizeof(*spi_info), GFP_KERNEL);
- if (!spi_info) {
+ if (!pdev || !spi_info ) {
ret = -ENOMEM;
- goto err_kz;
+ goto err_nomem;
}
- ssp = &spi_info->ssp;
- pdev = &spi_info->spi_pdev;
- spi_pdata = &spi_info->spi_pdata;
+ memset(&spi_pdata, 0, sizeof(spi_pdata));
+ spi_pdata.num_chipselect = dev->devfn;
- pdev->name = "pxa2xx-spi";
- pdev->id = dev->devfn;
- pdev->dev.parent = &dev->dev;
- pdev->dev.platform_data = &spi_info->spi_pdata;
+ ret = platform_device_add_data(pdev, &spi_pdata, sizeof(spi_pdata));
+ if (ret)
+ goto err_nomem;
+ pdev->dev.parent = &dev->dev;
#ifdef CONFIG_OF
pdev->dev.of_node = dev->dev.of_node;
#endif
- pdev->dev.release = plat_dev_release;
-
- spi_pdata->num_chipselect = dev->devfn;
-
+ ssp = &spi_info->ssp;
ssp->phys_base = pci_resource_start(dev, 0);
ssp->mmio_base = ioremap(phys_beg, phys_len);
if (!ssp->mmio_base) {
dev_err(&pdev->dev, "failed to ioremap() registers\n");
ret = -EIO;
- goto err_remap;
+ goto err_nomem;
}
ssp->irq = dev->irq;
ssp->port_id = pdev->id;
pci_set_drvdata(dev, spi_info);
- ret = platform_device_register(pdev);
+ ret = platform_device_add(pdev);
if (ret)
goto err_dev_add;
mutex_unlock(&ssp_lock);
iounmap(ssp->mmio_base);
-err_remap:
- kfree(spi_info);
-
-err_kz:
+err_nomem:
release_mem_region(phys_beg, phys_len);
-
+ platform_device_put(pdev);
+ kfree(spi_info);
return ret;
}
static void __devexit ce4100_spi_remove(struct pci_dev *dev)
{
- struct awesome_struct *spi_info;
- struct platform_device *pdev;
+ struct ce4100_info *spi_info;
struct ssp_device *ssp;
spi_info = pci_get_drvdata(dev);
-
ssp = &spi_info->ssp;
- pdev = &spi_info->spi_pdev;
-
- platform_device_unregister(pdev);
+ platform_device_unregister(spi_info->spi_pdev);
iounmap(ssp->mmio_base);
release_mem_region(pci_resource_start(dev, 0),
}
static struct pci_device_id ce4100_spi_devices[] __devinitdata = {
-
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2e6a) },
{ },
};
bytes_done = 0;
while (bytes_done < t->len) {
+ void *rx_buf = t->rx_buf ? t->rx_buf + bytes_done : NULL;
+ const void *tx_buf = t->tx_buf ? t->tx_buf + bytes_done : NULL;
n = sh_msiof_spi_txrx_once(p, tx_fifo, rx_fifo,
- t->tx_buf + bytes_done,
- t->rx_buf + bytes_done,
+ tx_buf,
+ rx_buf,
words, bits);
if (n < 0)
break;
/* Fetch the vendor specific tuples. */
res = pcmcia_loop_tuple(bus->host_pcmcia, SSB_PCMCIA_CIS,
- ssb_pcmcia_do_get_invariants, sprom);
+ ssb_pcmcia_do_get_invariants, iv);
if ((res == 0) || (res == -ENOSPC))
return 0;
switch (type) {
case NL80211_CHAN_HT20:
case NL80211_CHAN_NO_HT:
- WL_LOCK(wl);
err = wlc_set(wl->wlc, WLC_SET_CHANNEL, chan->hw_value);
- WL_UNLOCK(wl);
break;
case NL80211_CHAN_HT40MINUS:
case NL80211_CHAN_HT40PLUS:
int err = 0;
int new_int;
+ WL_LOCK(wl);
if (changed & IEEE80211_CONF_CHANGE_LISTEN_INTERVAL) {
WL_NONE("%s: Setting listen interval to %d\n",
__func__, conf->listen_interval);
}
config_out:
+ WL_UNLOCK(wl);
return err;
}
static void wl_ops_sw_scan_start(struct ieee80211_hw *hw)
{
+ struct wl_info *wl = hw->priv;
WL_NONE("Scan Start\n");
+ WL_LOCK(wl);
+ wlc_scan_start(wl->wlc);
+ WL_UNLOCK(wl);
return;
}
static void wl_ops_sw_scan_complete(struct ieee80211_hw *hw)
{
+ struct wl_info *wl = hw->priv;
WL_NONE("Scan Complete\n");
+ WL_LOCK(wl);
+ wlc_scan_stop(wl->wlc);
+ WL_UNLOCK(wl);
return;
}
kfree(qi);
}
+
+/*
+ * Flag 'scan in progress' to withold dynamic phy calibration
+ */
+void wlc_scan_start(struct wlc_info *wlc)
+{
+ wlc_phy_hold_upd(wlc->band->pi, PHY_HOLD_FOR_SCAN, true);
+}
+
+void wlc_scan_stop(struct wlc_info *wlc)
+{
+ wlc_phy_hold_upd(wlc->band->pi, PHY_HOLD_FOR_SCAN, false);
+}
extern u16 wlc_rate_shm_offset(struct wlc_info *wlc, u8 rate);
extern u32 wlc_get_rspec_history(struct wlc_bsscfg *cfg);
extern u32 wlc_get_current_highest_rate(struct wlc_bsscfg *cfg);
+extern void wlc_scan_start(struct wlc_info *wlc);
+extern void wlc_scan_stop(struct wlc_info *wlc);
static inline int wlc_iovar_getuint(struct wlc_info *wlc, const char *name,
uint *arg)
config COMEDI_NI_ATMIO
tristate "NI AT-MIO E series ISA-PNP card support"
depends on ISAPNP && COMEDI_NI_TIO && COMEDI_NI_COMMON
+ select COMEDI_8255
default N
---help---
Enable support for National Instruments AT-MIO E series cards
config COMEDI_NI_PCIMIO
tristate "NI PCI-MIO-E series and M series support"
depends on COMEDI_NI_TIO && COMEDI_NI_COMMON
+ select COMEDI_8255
+ select COMEDI_FC
default N
---help---
Enable support for National Instruments PCI-MIO-E series and M series
config COMEDI_NI_MIO_CS
tristate "NI DAQCard E series PCMCIA support"
depends on COMEDI_NI_TIO && COMEDI_NI_COMMON
+ select COMEDI_8255
select COMEDI_FC
default N
---help---
config COMEDI_NI_TIO
tristate "NI general purpose counter support"
depends on COMEDI_MITE
- select COMEDI_8255
default N
---help---
Enable support for National Instruments general purpose counters.
#define PCI_DAQ_SIZE 4096
#define PCI_DAQ_SIZE_660X 8192
-MODULE_LICENSE("GPL");
-
struct mite_struct *mite_devices;
EXPORT_SYMBOL(mite_devices);
module_init(driver_ni6527_init_module);
module_exit(driver_ni6527_cleanup_module);
+
+MODULE_AUTHOR("Comedi http://www.comedi.org");
+MODULE_DESCRIPTION("Comedi low-level driver");
+MODULE_LICENSE("GPL");
module_init(driver_ni_65xx_init_module);
module_exit(driver_ni_65xx_cleanup_module);
+
+MODULE_AUTHOR("Comedi http://www.comedi.org");
+MODULE_DESCRIPTION("Comedi low-level driver");
+MODULE_LICENSE("GPL");
};
return 0;
}
+
+MODULE_AUTHOR("Comedi http://www.comedi.org");
+MODULE_DESCRIPTION("Comedi low-level driver");
+MODULE_LICENSE("GPL");
mite_list_devices();
return -EIO;
}
+
+MODULE_AUTHOR("Comedi http://www.comedi.org");
+MODULE_DESCRIPTION("Comedi low-level driver");
+MODULE_LICENSE("GPL");
module_init(driver_pcidio_init_module);
module_exit(driver_pcidio_cleanup_module);
+
+MODULE_AUTHOR("Comedi http://www.comedi.org");
+MODULE_DESCRIPTION("Comedi low-level driver");
+MODULE_LICENSE("GPL");
return 0;
}
+
+MODULE_AUTHOR("Comedi http://www.comedi.org");
+MODULE_DESCRIPTION("Comedi low-level driver");
+MODULE_LICENSE("GPL");
if (status == 1) {
netif_carrier_on(net);
netif_wake_queue(net);
+ netif_notify_peers(net);
} else {
netif_carrier_off(net);
netif_stop_queue(net);
sc_access[3].reg_addr = 0x109;
sc_access[3].mask = MASK6;
sc_access[3].value = 0x00;
- num_val = 4;
+ sc_access[4].reg_addr = 0x104;
+ sc_access[4].value = 0x3C;
+ sc_access[4].mask = 0xff;
+ num_val = 5;
break;
default:
return -EINVAL;
if (zram_test_flag(zram, index, ZRAM_ZERO)) {
handle_zero_page(page);
+ index++;
continue;
}
pr_debug("Read before write: sector=%lu, size=%u",
(ulong)(bio->bi_sector), bio->bi_size);
/* Do nothing */
+ index++;
continue;
}
/* Page is stored uncompressed since it's incompressible */
if (unlikely(zram_test_flag(zram, index, ZRAM_UNCOMPRESSED))) {
handle_uncompressed_page(zram, page, index);
+ index++;
continue;
}
mutex_unlock(&zram->lock);
zram_stat_inc(&zram->stats.pages_zero);
zram_set_flag(zram, index, ZRAM_ZERO);
+ index++;
continue;
}
target_core_transport.o \
target_core_cdb.o \
target_core_ua.o \
- target_core_rd.o \
- target_core_mib.o
+ target_core_rd.o
obj-$(CONFIG_TARGET_CORE) += target_core_mod.o
#include <linux/parser.h>
#include <linux/syscalls.h>
#include <linux/configfs.h>
-#include <linux/proc_fs.h>
#include <target/target_core_base.h>
#include <target/target_core_device.h>
{
struct se_subsystem_dev *se_dev = container_of(to_config_group(item),
struct se_subsystem_dev, se_dev_group);
- struct config_group *dev_cg;
-
- if (!(se_dev))
- return;
+ struct se_hba *hba = item_to_hba(&se_dev->se_dev_hba->hba_group.cg_item);
+ struct se_subsystem_api *t = hba->transport;
+ struct config_group *dev_cg = &se_dev->se_dev_group;
- dev_cg = &se_dev->se_dev_group;
kfree(dev_cg->default_groups);
+ /*
+ * This pointer will set when the storage is enabled with:
+ *`echo 1 > $CONFIGFS/core/$HBA/$DEV/dev_enable`
+ */
+ if (se_dev->se_dev_ptr) {
+ printk(KERN_INFO "Target_Core_ConfigFS: Calling se_free_"
+ "virtual_device() for se_dev_ptr: %p\n",
+ se_dev->se_dev_ptr);
+
+ se_free_virtual_device(se_dev->se_dev_ptr, hba);
+ } else {
+ /*
+ * Release struct se_subsystem_dev->se_dev_su_ptr..
+ */
+ printk(KERN_INFO "Target_Core_ConfigFS: Calling t->free_"
+ "device() for se_dev_su_ptr: %p\n",
+ se_dev->se_dev_su_ptr);
+
+ t->free_device(se_dev->se_dev_su_ptr);
+ }
+
+ printk(KERN_INFO "Target_Core_ConfigFS: Deallocating se_subsystem"
+ "_dev_t: %p\n", se_dev);
+ kfree(se_dev);
}
static ssize_t target_core_dev_show(struct config_item *item,
NULL,
};
+static void target_core_alua_lu_gp_release(struct config_item *item)
+{
+ struct t10_alua_lu_gp *lu_gp = container_of(to_config_group(item),
+ struct t10_alua_lu_gp, lu_gp_group);
+
+ core_alua_free_lu_gp(lu_gp);
+}
+
static struct configfs_item_operations target_core_alua_lu_gp_ops = {
+ .release = target_core_alua_lu_gp_release,
.show_attribute = target_core_alua_lu_gp_attr_show,
.store_attribute = target_core_alua_lu_gp_attr_store,
};
printk(KERN_INFO "Target_Core_ConfigFS: Releasing ALUA Logical Unit"
" Group: core/alua/lu_gps/%s, ID: %hu\n",
config_item_name(item), lu_gp->lu_gp_id);
-
+ /*
+ * core_alua_free_lu_gp() is called from target_core_alua_lu_gp_ops->release()
+ * -> target_core_alua_lu_gp_release()
+ */
config_item_put(item);
- core_alua_free_lu_gp(lu_gp);
}
static struct configfs_group_operations target_core_alua_lu_gps_group_ops = {
NULL,
};
+static void target_core_alua_tg_pt_gp_release(struct config_item *item)
+{
+ struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(to_config_group(item),
+ struct t10_alua_tg_pt_gp, tg_pt_gp_group);
+
+ core_alua_free_tg_pt_gp(tg_pt_gp);
+}
+
static struct configfs_item_operations target_core_alua_tg_pt_gp_ops = {
+ .release = target_core_alua_tg_pt_gp_release,
.show_attribute = target_core_alua_tg_pt_gp_attr_show,
.store_attribute = target_core_alua_tg_pt_gp_attr_store,
};
printk(KERN_INFO "Target_Core_ConfigFS: Releasing ALUA Target Port"
" Group: alua/tg_pt_gps/%s, ID: %hu\n",
config_item_name(item), tg_pt_gp->tg_pt_gp_id);
-
+ /*
+ * core_alua_free_tg_pt_gp() is called from target_core_alua_tg_pt_gp_ops->release()
+ * -> target_core_alua_tg_pt_gp_release().
+ */
config_item_put(item);
- core_alua_free_tg_pt_gp(tg_pt_gp);
}
static struct configfs_group_operations target_core_alua_tg_pt_gps_group_ops = {
struct se_subsystem_api *t;
struct config_item *df_item;
struct config_group *dev_cg, *tg_pt_gp_cg;
- int i, ret;
+ int i;
hba = item_to_hba(&se_dev->se_dev_hba->hba_group.cg_item);
- if (mutex_lock_interruptible(&hba->hba_access_mutex))
- goto out;
-
+ mutex_lock(&hba->hba_access_mutex);
t = hba->transport;
spin_lock(&se_global->g_device_lock);
config_item_put(df_item);
}
kfree(tg_pt_gp_cg->default_groups);
- core_alua_free_tg_pt_gp(T10_ALUA(se_dev)->default_tg_pt_gp);
+ /*
+ * core_alua_free_tg_pt_gp() is called from ->default_tg_pt_gp
+ * directly from target_core_alua_tg_pt_gp_release().
+ */
T10_ALUA(se_dev)->default_tg_pt_gp = NULL;
dev_cg = &se_dev->se_dev_group;
dev_cg->default_groups[i] = NULL;
config_item_put(df_item);
}
-
- config_item_put(item);
/*
- * This pointer will set when the storage is enabled with:
- * `echo 1 > $CONFIGFS/core/$HBA/$DEV/dev_enable`
+ * The releasing of se_dev and associated se_dev->se_dev_ptr is done
+ * from target_core_dev_item_ops->release() ->target_core_dev_release().
*/
- if (se_dev->se_dev_ptr) {
- printk(KERN_INFO "Target_Core_ConfigFS: Calling se_free_"
- "virtual_device() for se_dev_ptr: %p\n",
- se_dev->se_dev_ptr);
-
- ret = se_free_virtual_device(se_dev->se_dev_ptr, hba);
- if (ret < 0)
- goto hba_out;
- } else {
- /*
- * Release struct se_subsystem_dev->se_dev_su_ptr..
- */
- printk(KERN_INFO "Target_Core_ConfigFS: Calling t->free_"
- "device() for se_dev_su_ptr: %p\n",
- se_dev->se_dev_su_ptr);
-
- t->free_device(se_dev->se_dev_su_ptr);
- }
-
- printk(KERN_INFO "Target_Core_ConfigFS: Deallocating se_subsystem"
- "_dev_t: %p\n", se_dev);
-
-hba_out:
+ config_item_put(item);
mutex_unlock(&hba->hba_access_mutex);
-out:
- kfree(se_dev);
}
static struct configfs_group_operations target_core_hba_group_ops = {
CONFIGFS_EATTR_OPS(target_core_hba, se_hba, hba_group);
+static void target_core_hba_release(struct config_item *item)
+{
+ struct se_hba *hba = container_of(to_config_group(item),
+ struct se_hba, hba_group);
+ core_delete_hba(hba);
+}
+
static struct configfs_attribute *target_core_hba_attrs[] = {
&target_core_hba_hba_info.attr,
&target_core_hba_hba_mode.attr,
};
static struct configfs_item_operations target_core_hba_item_ops = {
+ .release = target_core_hba_release,
.show_attribute = target_core_hba_attr_show,
.store_attribute = target_core_hba_attr_store,
};
struct config_group *group,
struct config_item *item)
{
- struct se_hba *hba = item_to_hba(item);
-
+ /*
+ * core_delete_hba() is called from target_core_hba_item_ops->release()
+ * -> target_core_hba_release()
+ */
config_item_put(item);
- core_delete_hba(hba);
}
static struct configfs_group_operations target_core_group_ops = {
struct config_group *target_cg, *hba_cg = NULL, *alua_cg = NULL;
struct config_group *lu_gp_cg = NULL;
struct configfs_subsystem *subsys;
- struct proc_dir_entry *scsi_target_proc = NULL;
struct t10_alua_lu_gp *lu_gp;
int ret;
if (core_dev_setup_virtual_lun0() < 0)
goto out;
- scsi_target_proc = proc_mkdir("scsi_target", 0);
- if (!(scsi_target_proc)) {
- printk(KERN_ERR "proc_mkdir(scsi_target, 0) failed\n");
- goto out;
- }
- ret = init_scsi_target_mib();
- if (ret < 0)
- goto out;
-
return 0;
out:
configfs_unregister_subsystem(subsys);
- if (scsi_target_proc)
- remove_proc_entry("scsi_target", 0);
core_dev_release_virtual_lun0();
rd_module_exit();
out_global:
config_item_put(item);
}
kfree(lu_gp_cg->default_groups);
- core_alua_free_lu_gp(se_global->default_lu_gp);
- se_global->default_lu_gp = NULL;
+ lu_gp_cg->default_groups = NULL;
alua_cg = &se_global->alua_group;
for (i = 0; alua_cg->default_groups[i]; i++) {
config_item_put(item);
}
kfree(alua_cg->default_groups);
+ alua_cg->default_groups = NULL;
hba_cg = &se_global->target_core_hbagroup;
for (i = 0; hba_cg->default_groups[i]; i++) {
config_item_put(item);
}
kfree(hba_cg->default_groups);
-
- for (i = 0; subsys->su_group.default_groups[i]; i++) {
- item = &subsys->su_group.default_groups[i]->cg_item;
- subsys->su_group.default_groups[i] = NULL;
- config_item_put(item);
- }
+ hba_cg->default_groups = NULL;
+ /*
+ * 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(subsys);
+ core_alua_free_lu_gp(se_global->default_lu_gp);
+ se_global->default_lu_gp = NULL;
+
printk(KERN_INFO "TARGET_CORE[0]: Released ConfigFS Fabric"
" Infrastructure\n");
- remove_scsi_target_mib();
- remove_proc_entry("scsi_target", 0);
core_dev_release_virtual_lun0();
rd_module_exit();
release_se_global();
/*
* deve->se_lun_acl will be NULL for demo-mode created LUNs
* that have not been explictly concerted to MappedLUNs ->
- * struct se_lun_acl.
+ * struct se_lun_acl, but we remove deve->alua_port_list from
+ * port->sep_alua_list. This also means that active UAs and
+ * NodeACL context specific PR metadata for demo-mode
+ * MappedLUN *deve will be released below..
*/
- if (!(deve->se_lun_acl))
- return 0;
-
spin_lock_bh(&port->sep_alua_lock);
list_del(&deve->alua_port_list);
spin_unlock_bh(&port->sep_alua_lock);
printk(KERN_ERR "struct se_dev_entry->se_lun_acl"
" already set for demo mode -> explict"
" LUN ACL transition\n");
+ spin_unlock_irq(&nacl->device_list_lock);
return -1;
}
if (deve->se_lun != lun) {
printk(KERN_ERR "struct se_dev_entry->se_lun does"
" match passed struct se_lun for demo mode"
" -> explict LUN ACL transition\n");
+ spin_unlock_irq(&nacl->device_list_lock);
return -1;
}
deve->se_lun_acl = lun_acl;
}
}
spin_unlock(&hba->device_lock);
-
- while (atomic_read(&hba->dev_mib_access_count))
- cpu_relax();
}
int se_dev_check_online(struct se_device *dev)
CONFIGFS_EATTR_OPS(target_fabric_mappedlun, se_lun_acl, se_lun_group);
+static void target_fabric_mappedlun_release(struct config_item *item)
+{
+ struct se_lun_acl *lacl = container_of(to_config_group(item),
+ struct se_lun_acl, se_lun_group);
+ struct se_portal_group *se_tpg = lacl->se_lun_nacl->se_tpg;
+
+ core_dev_free_initiator_node_lun_acl(se_tpg, lacl);
+}
+
static struct configfs_attribute *target_fabric_mappedlun_attrs[] = {
&target_fabric_mappedlun_write_protect.attr,
NULL,
};
static struct configfs_item_operations target_fabric_mappedlun_item_ops = {
+ .release = target_fabric_mappedlun_release,
.show_attribute = target_fabric_mappedlun_attr_show,
.store_attribute = target_fabric_mappedlun_attr_store,
.allow_link = target_fabric_mappedlun_link,
struct config_group *group,
struct config_item *item)
{
- struct se_lun_acl *lacl = container_of(to_config_group(item),
- struct se_lun_acl, se_lun_group);
- struct se_portal_group *se_tpg = lacl->se_lun_nacl->se_tpg;
-
config_item_put(item);
- core_dev_free_initiator_node_lun_acl(se_tpg, lacl);
+}
+
+static void target_fabric_nacl_base_release(struct config_item *item)
+{
+ struct se_node_acl *se_nacl = container_of(to_config_group(item),
+ struct se_node_acl, acl_group);
+ struct se_portal_group *se_tpg = se_nacl->se_tpg;
+ struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
+
+ tf->tf_ops.fabric_drop_nodeacl(se_nacl);
}
static struct configfs_item_operations target_fabric_nacl_base_item_ops = {
+ .release = target_fabric_nacl_base_release,
.show_attribute = target_fabric_nacl_base_attr_show,
.store_attribute = target_fabric_nacl_base_attr_store,
};
struct config_group *group,
struct config_item *item)
{
- struct se_portal_group *se_tpg = container_of(group,
- struct se_portal_group, tpg_acl_group);
- struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
struct se_node_acl *se_nacl = container_of(to_config_group(item),
struct se_node_acl, acl_group);
struct config_item *df_item;
nacl_cg->default_groups[i] = NULL;
config_item_put(df_item);
}
-
+ /*
+ * struct se_node_acl free is done in target_fabric_nacl_base_release()
+ */
config_item_put(item);
- tf->tf_ops.fabric_drop_nodeacl(se_nacl);
}
static struct configfs_group_operations target_fabric_nacl_group_ops = {
CONFIGFS_EATTR_OPS(target_fabric_np_base, se_tpg_np, tpg_np_group);
+static void target_fabric_np_base_release(struct config_item *item)
+{
+ struct se_tpg_np *se_tpg_np = container_of(to_config_group(item),
+ struct se_tpg_np, tpg_np_group);
+ struct se_portal_group *se_tpg = se_tpg_np->tpg_np_parent;
+ struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
+
+ tf->tf_ops.fabric_drop_np(se_tpg_np);
+}
+
static struct configfs_item_operations target_fabric_np_base_item_ops = {
+ .release = target_fabric_np_base_release,
.show_attribute = target_fabric_np_base_attr_show,
.store_attribute = target_fabric_np_base_attr_store,
};
if (!(se_tpg_np) || IS_ERR(se_tpg_np))
return ERR_PTR(-EINVAL);
+ se_tpg_np->tpg_np_parent = se_tpg;
config_group_init_type_name(&se_tpg_np->tpg_np_group, name,
&TF_CIT_TMPL(tf)->tfc_tpg_np_base_cit);
struct config_group *group,
struct config_item *item)
{
- struct se_portal_group *se_tpg = container_of(group,
- struct se_portal_group, tpg_np_group);
- struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
- struct se_tpg_np *se_tpg_np = container_of(to_config_group(item),
- struct se_tpg_np, tpg_np_group);
-
+ /*
+ * struct se_tpg_np is released via target_fabric_np_base_release()
+ */
config_item_put(item);
- tf->tf_ops.fabric_drop_np(se_tpg_np);
}
static struct configfs_group_operations target_fabric_np_group_ops = {
*/
CONFIGFS_EATTR_OPS(target_fabric_tpg, se_portal_group, tpg_group);
+static void target_fabric_tpg_release(struct config_item *item)
+{
+ struct se_portal_group *se_tpg = container_of(to_config_group(item),
+ struct se_portal_group, tpg_group);
+ struct se_wwn *wwn = se_tpg->se_tpg_wwn;
+ struct target_fabric_configfs *tf = wwn->wwn_tf;
+
+ tf->tf_ops.fabric_drop_tpg(se_tpg);
+}
+
static struct configfs_item_operations target_fabric_tpg_base_item_ops = {
+ .release = target_fabric_tpg_release,
.show_attribute = target_fabric_tpg_attr_show,
.store_attribute = target_fabric_tpg_attr_store,
};
struct config_group *group,
struct config_item *item)
{
- struct se_wwn *wwn = container_of(group, struct se_wwn, wwn_group);
- struct target_fabric_configfs *tf = wwn->wwn_tf;
struct se_portal_group *se_tpg = container_of(to_config_group(item),
struct se_portal_group, tpg_group);
struct config_group *tpg_cg = &se_tpg->tpg_group;
}
config_item_put(item);
- tf->tf_ops.fabric_drop_tpg(se_tpg);
}
+static void target_fabric_release_wwn(struct config_item *item)
+{
+ struct se_wwn *wwn = container_of(to_config_group(item),
+ struct se_wwn, wwn_group);
+ struct target_fabric_configfs *tf = wwn->wwn_tf;
+
+ tf->tf_ops.fabric_drop_wwn(wwn);
+}
+
+static struct configfs_item_operations target_fabric_tpg_item_ops = {
+ .release = target_fabric_release_wwn,
+};
+
static struct configfs_group_operations target_fabric_tpg_group_ops = {
.make_group = target_fabric_make_tpg,
.drop_item = target_fabric_drop_tpg,
};
-TF_CIT_SETUP(tpg, NULL, &target_fabric_tpg_group_ops, NULL);
+TF_CIT_SETUP(tpg, &target_fabric_tpg_item_ops, &target_fabric_tpg_group_ops,
+ NULL);
/* End of tfc_tpg_cit */
struct config_group *group,
struct config_item *item)
{
- struct target_fabric_configfs *tf = container_of(group,
- struct target_fabric_configfs, tf_group);
- struct se_wwn *wwn = container_of(to_config_group(item),
- struct se_wwn, wwn_group);
-
config_item_put(item);
- tf->tf_ops.fabric_drop_wwn(wwn);
}
static struct configfs_group_operations target_fabric_wwn_group_ops = {
bd = blkdev_get_by_path(ib_dev->ibd_udev_path,
FMODE_WRITE|FMODE_READ|FMODE_EXCL, ib_dev);
- if (!(bd))
+ if (IS_ERR(bd))
goto failed;
/*
* Setup the local scope queue_limits from struct request_queue->limits
{
struct iblock_dev *ib_dev = p;
- blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
- bioset_free(ib_dev->ibd_bio_set);
+ if (ib_dev->ibd_bd != NULL)
+ blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
+ if (ib_dev->ibd_bio_set != NULL)
+ bioset_free(ib_dev->ibd_bio_set);
kfree(ib_dev);
}
+++ /dev/null
-/*******************************************************************************
- * Filename: target_core_mib.c
- *
- * Copyright (c) 2006-2007 SBE, Inc. All Rights Reserved.
- * Copyright (c) 2007-2010 Rising Tide Systems
- * Copyright (c) 2008-2010 Linux-iSCSI.org
- *
- * Nicholas A. Bellinger <nab@linux-iscsi.org>
- *
- * 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- ******************************************************************************/
-
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/timer.h>
-#include <linux/string.h>
-#include <linux/version.h>
-#include <generated/utsrelease.h>
-#include <linux/utsname.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/blkdev.h>
-#include <scsi/scsi.h>
-#include <scsi/scsi_device.h>
-#include <scsi/scsi_host.h>
-
-#include <target/target_core_base.h>
-#include <target/target_core_transport.h>
-#include <target/target_core_fabric_ops.h>
-#include <target/target_core_configfs.h>
-
-#include "target_core_hba.h"
-#include "target_core_mib.h"
-
-/* SCSI mib table index */
-static struct scsi_index_table scsi_index_table;
-
-#ifndef INITIAL_JIFFIES
-#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ))
-#endif
-
-/* SCSI Instance Table */
-#define SCSI_INST_SW_INDEX 1
-#define SCSI_TRANSPORT_INDEX 1
-
-#define NONE "None"
-#define ISPRINT(a) ((a >= ' ') && (a <= '~'))
-
-static inline int list_is_first(const struct list_head *list,
- const struct list_head *head)
-{
- return list->prev == head;
-}
-
-static void *locate_hba_start(
- struct seq_file *seq,
- loff_t *pos)
-{
- spin_lock(&se_global->g_device_lock);
- return seq_list_start(&se_global->g_se_dev_list, *pos);
-}
-
-static void *locate_hba_next(
- struct seq_file *seq,
- void *v,
- loff_t *pos)
-{
- return seq_list_next(v, &se_global->g_se_dev_list, pos);
-}
-
-static void locate_hba_stop(struct seq_file *seq, void *v)
-{
- spin_unlock(&se_global->g_device_lock);
-}
-
-/****************************************************************************
- * SCSI MIB Tables
- ****************************************************************************/
-
-/*
- * SCSI Instance Table
- */
-static void *scsi_inst_seq_start(
- struct seq_file *seq,
- loff_t *pos)
-{
- spin_lock(&se_global->hba_lock);
- return seq_list_start(&se_global->g_hba_list, *pos);
-}
-
-static void *scsi_inst_seq_next(
- struct seq_file *seq,
- void *v,
- loff_t *pos)
-{
- return seq_list_next(v, &se_global->g_hba_list, pos);
-}
-
-static void scsi_inst_seq_stop(struct seq_file *seq, void *v)
-{
- spin_unlock(&se_global->hba_lock);
-}
-
-static int scsi_inst_seq_show(struct seq_file *seq, void *v)
-{
- struct se_hba *hba = list_entry(v, struct se_hba, hba_list);
-
- if (list_is_first(&hba->hba_list, &se_global->g_hba_list))
- seq_puts(seq, "inst sw_indx\n");
-
- seq_printf(seq, "%u %u\n", hba->hba_index, SCSI_INST_SW_INDEX);
- seq_printf(seq, "plugin: %s version: %s\n",
- hba->transport->name, TARGET_CORE_VERSION);
-
- return 0;
-}
-
-static const struct seq_operations scsi_inst_seq_ops = {
- .start = scsi_inst_seq_start,
- .next = scsi_inst_seq_next,
- .stop = scsi_inst_seq_stop,
- .show = scsi_inst_seq_show
-};
-
-static int scsi_inst_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_inst_seq_ops);
-}
-
-static const struct file_operations scsi_inst_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_inst_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
- * SCSI Device Table
- */
-static void *scsi_dev_seq_start(struct seq_file *seq, loff_t *pos)
-{
- return locate_hba_start(seq, pos);
-}
-
-static void *scsi_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
- return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_dev_seq_stop(struct seq_file *seq, void *v)
-{
- locate_hba_stop(seq, v);
-}
-
-static int scsi_dev_seq_show(struct seq_file *seq, void *v)
-{
- struct se_hba *hba;
- struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
- g_se_dev_list);
- struct se_device *dev = se_dev->se_dev_ptr;
- char str[28];
- int k;
-
- if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
- seq_puts(seq, "inst indx role ports\n");
-
- if (!(dev))
- return 0;
-
- hba = dev->se_hba;
- if (!(hba)) {
- /* Log error ? */
- return 0;
- }
-
- seq_printf(seq, "%u %u %s %u\n", hba->hba_index,
- dev->dev_index, "Target", dev->dev_port_count);
-
- memcpy(&str[0], (void *)DEV_T10_WWN(dev), 28);
-
- /* vendor */
- for (k = 0; k < 8; k++)
- str[k] = ISPRINT(DEV_T10_WWN(dev)->vendor[k]) ?
- DEV_T10_WWN(dev)->vendor[k] : 0x20;
- str[k] = 0x20;
-
- /* model */
- for (k = 0; k < 16; k++)
- str[k+9] = ISPRINT(DEV_T10_WWN(dev)->model[k]) ?
- DEV_T10_WWN(dev)->model[k] : 0x20;
- str[k + 9] = 0;
-
- seq_printf(seq, "dev_alias: %s\n", str);
-
- return 0;
-}
-
-static const struct seq_operations scsi_dev_seq_ops = {
- .start = scsi_dev_seq_start,
- .next = scsi_dev_seq_next,
- .stop = scsi_dev_seq_stop,
- .show = scsi_dev_seq_show
-};
-
-static int scsi_dev_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_dev_seq_ops);
-}
-
-static const struct file_operations scsi_dev_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_dev_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
- * SCSI Port Table
- */
-static void *scsi_port_seq_start(struct seq_file *seq, loff_t *pos)
-{
- return locate_hba_start(seq, pos);
-}
-
-static void *scsi_port_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
- return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_port_seq_stop(struct seq_file *seq, void *v)
-{
- locate_hba_stop(seq, v);
-}
-
-static int scsi_port_seq_show(struct seq_file *seq, void *v)
-{
- struct se_hba *hba;
- struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
- g_se_dev_list);
- struct se_device *dev = se_dev->se_dev_ptr;
- struct se_port *sep, *sep_tmp;
-
- if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
- seq_puts(seq, "inst device indx role busy_count\n");
-
- if (!(dev))
- return 0;
-
- hba = dev->se_hba;
- if (!(hba)) {
- /* Log error ? */
- return 0;
- }
-
- /* FIXME: scsiPortBusyStatuses count */
- spin_lock(&dev->se_port_lock);
- list_for_each_entry_safe(sep, sep_tmp, &dev->dev_sep_list, sep_list) {
- seq_printf(seq, "%u %u %u %s%u %u\n", hba->hba_index,
- dev->dev_index, sep->sep_index, "Device",
- dev->dev_index, 0);
- }
- spin_unlock(&dev->se_port_lock);
-
- return 0;
-}
-
-static const struct seq_operations scsi_port_seq_ops = {
- .start = scsi_port_seq_start,
- .next = scsi_port_seq_next,
- .stop = scsi_port_seq_stop,
- .show = scsi_port_seq_show
-};
-
-static int scsi_port_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_port_seq_ops);
-}
-
-static const struct file_operations scsi_port_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_port_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
- * SCSI Transport Table
- */
-static void *scsi_transport_seq_start(struct seq_file *seq, loff_t *pos)
-{
- return locate_hba_start(seq, pos);
-}
-
-static void *scsi_transport_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
- return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_transport_seq_stop(struct seq_file *seq, void *v)
-{
- locate_hba_stop(seq, v);
-}
-
-static int scsi_transport_seq_show(struct seq_file *seq, void *v)
-{
- struct se_hba *hba;
- struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
- g_se_dev_list);
- struct se_device *dev = se_dev->se_dev_ptr;
- struct se_port *se, *se_tmp;
- struct se_portal_group *tpg;
- struct t10_wwn *wwn;
- char buf[64];
-
- if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
- seq_puts(seq, "inst device indx dev_name\n");
-
- if (!(dev))
- return 0;
-
- hba = dev->se_hba;
- if (!(hba)) {
- /* Log error ? */
- return 0;
- }
-
- wwn = DEV_T10_WWN(dev);
-
- spin_lock(&dev->se_port_lock);
- list_for_each_entry_safe(se, se_tmp, &dev->dev_sep_list, sep_list) {
- tpg = se->sep_tpg;
- sprintf(buf, "scsiTransport%s",
- TPG_TFO(tpg)->get_fabric_name());
-
- seq_printf(seq, "%u %s %u %s+%s\n",
- hba->hba_index, /* scsiTransportIndex */
- buf, /* scsiTransportType */
- (TPG_TFO(tpg)->tpg_get_inst_index != NULL) ?
- TPG_TFO(tpg)->tpg_get_inst_index(tpg) :
- 0,
- TPG_TFO(tpg)->tpg_get_wwn(tpg),
- (strlen(wwn->unit_serial)) ?
- /* scsiTransportDevName */
- wwn->unit_serial : wwn->vendor);
- }
- spin_unlock(&dev->se_port_lock);
-
- return 0;
-}
-
-static const struct seq_operations scsi_transport_seq_ops = {
- .start = scsi_transport_seq_start,
- .next = scsi_transport_seq_next,
- .stop = scsi_transport_seq_stop,
- .show = scsi_transport_seq_show
-};
-
-static int scsi_transport_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_transport_seq_ops);
-}
-
-static const struct file_operations scsi_transport_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_transport_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
- * SCSI Target Device Table
- */
-static void *scsi_tgt_dev_seq_start(struct seq_file *seq, loff_t *pos)
-{
- return locate_hba_start(seq, pos);
-}
-
-static void *scsi_tgt_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
- return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_tgt_dev_seq_stop(struct seq_file *seq, void *v)
-{
- locate_hba_stop(seq, v);
-}
-
-
-#define LU_COUNT 1 /* for now */
-static int scsi_tgt_dev_seq_show(struct seq_file *seq, void *v)
-{
- struct se_hba *hba;
- struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
- g_se_dev_list);
- struct se_device *dev = se_dev->se_dev_ptr;
- int non_accessible_lus = 0;
- char status[16];
-
- if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
- seq_puts(seq, "inst indx num_LUs status non_access_LUs"
- " resets\n");
-
- if (!(dev))
- return 0;
-
- hba = dev->se_hba;
- if (!(hba)) {
- /* Log error ? */
- return 0;
- }
-
- switch (dev->dev_status) {
- case TRANSPORT_DEVICE_ACTIVATED:
- strcpy(status, "activated");
- break;
- case TRANSPORT_DEVICE_DEACTIVATED:
- strcpy(status, "deactivated");
- non_accessible_lus = 1;
- break;
- case TRANSPORT_DEVICE_SHUTDOWN:
- strcpy(status, "shutdown");
- non_accessible_lus = 1;
- break;
- case TRANSPORT_DEVICE_OFFLINE_ACTIVATED:
- case TRANSPORT_DEVICE_OFFLINE_DEACTIVATED:
- strcpy(status, "offline");
- non_accessible_lus = 1;
- break;
- default:
- sprintf(status, "unknown(%d)", dev->dev_status);
- non_accessible_lus = 1;
- }
-
- seq_printf(seq, "%u %u %u %s %u %u\n",
- hba->hba_index, dev->dev_index, LU_COUNT,
- status, non_accessible_lus, dev->num_resets);
-
- return 0;
-}
-
-static const struct seq_operations scsi_tgt_dev_seq_ops = {
- .start = scsi_tgt_dev_seq_start,
- .next = scsi_tgt_dev_seq_next,
- .stop = scsi_tgt_dev_seq_stop,
- .show = scsi_tgt_dev_seq_show
-};
-
-static int scsi_tgt_dev_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_tgt_dev_seq_ops);
-}
-
-static const struct file_operations scsi_tgt_dev_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_tgt_dev_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
- * SCSI Target Port Table
- */
-static void *scsi_tgt_port_seq_start(struct seq_file *seq, loff_t *pos)
-{
- return locate_hba_start(seq, pos);
-}
-
-static void *scsi_tgt_port_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
- return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_tgt_port_seq_stop(struct seq_file *seq, void *v)
-{
- locate_hba_stop(seq, v);
-}
-
-static int scsi_tgt_port_seq_show(struct seq_file *seq, void *v)
-{
- struct se_hba *hba;
- struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
- g_se_dev_list);
- struct se_device *dev = se_dev->se_dev_ptr;
- struct se_port *sep, *sep_tmp;
- struct se_portal_group *tpg;
- u32 rx_mbytes, tx_mbytes;
- unsigned long long num_cmds;
- char buf[64];
-
- if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
- seq_puts(seq, "inst device indx name port_index in_cmds"
- " write_mbytes read_mbytes hs_in_cmds\n");
-
- if (!(dev))
- return 0;
-
- hba = dev->se_hba;
- if (!(hba)) {
- /* Log error ? */
- return 0;
- }
-
- spin_lock(&dev->se_port_lock);
- list_for_each_entry_safe(sep, sep_tmp, &dev->dev_sep_list, sep_list) {
- tpg = sep->sep_tpg;
- sprintf(buf, "%sPort#",
- TPG_TFO(tpg)->get_fabric_name());
-
- seq_printf(seq, "%u %u %u %s%d %s%s%d ",
- hba->hba_index,
- dev->dev_index,
- sep->sep_index,
- buf, sep->sep_index,
- TPG_TFO(tpg)->tpg_get_wwn(tpg), "+t+",
- TPG_TFO(tpg)->tpg_get_tag(tpg));
-
- spin_lock(&sep->sep_lun->lun_sep_lock);
- num_cmds = sep->sep_stats.cmd_pdus;
- rx_mbytes = (sep->sep_stats.rx_data_octets >> 20);
- tx_mbytes = (sep->sep_stats.tx_data_octets >> 20);
- spin_unlock(&sep->sep_lun->lun_sep_lock);
-
- seq_printf(seq, "%llu %u %u %u\n", num_cmds,
- rx_mbytes, tx_mbytes, 0);
- }
- spin_unlock(&dev->se_port_lock);
-
- return 0;
-}
-
-static const struct seq_operations scsi_tgt_port_seq_ops = {
- .start = scsi_tgt_port_seq_start,
- .next = scsi_tgt_port_seq_next,
- .stop = scsi_tgt_port_seq_stop,
- .show = scsi_tgt_port_seq_show
-};
-
-static int scsi_tgt_port_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_tgt_port_seq_ops);
-}
-
-static const struct file_operations scsi_tgt_port_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_tgt_port_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
- * SCSI Authorized Initiator Table:
- * It contains the SCSI Initiators authorized to be attached to one of the
- * local Target ports.
- * Iterates through all active TPGs and extracts the info from the ACLs
- */
-static void *scsi_auth_intr_seq_start(struct seq_file *seq, loff_t *pos)
-{
- spin_lock_bh(&se_global->se_tpg_lock);
- return seq_list_start(&se_global->g_se_tpg_list, *pos);
-}
-
-static void *scsi_auth_intr_seq_next(struct seq_file *seq, void *v,
- loff_t *pos)
-{
- return seq_list_next(v, &se_global->g_se_tpg_list, pos);
-}
-
-static void scsi_auth_intr_seq_stop(struct seq_file *seq, void *v)
-{
- spin_unlock_bh(&se_global->se_tpg_lock);
-}
-
-static int scsi_auth_intr_seq_show(struct seq_file *seq, void *v)
-{
- struct se_portal_group *se_tpg = list_entry(v, struct se_portal_group,
- se_tpg_list);
- struct se_dev_entry *deve;
- struct se_lun *lun;
- struct se_node_acl *se_nacl;
- int j;
-
- if (list_is_first(&se_tpg->se_tpg_list,
- &se_global->g_se_tpg_list))
- seq_puts(seq, "inst dev port indx dev_or_port intr_name "
- "map_indx att_count num_cmds read_mbytes "
- "write_mbytes hs_num_cmds creation_time row_status\n");
-
- if (!(se_tpg))
- return 0;
-
- spin_lock(&se_tpg->acl_node_lock);
- list_for_each_entry(se_nacl, &se_tpg->acl_node_list, acl_list) {
-
- atomic_inc(&se_nacl->mib_ref_count);
- smp_mb__after_atomic_inc();
- spin_unlock(&se_tpg->acl_node_lock);
-
- spin_lock_irq(&se_nacl->device_list_lock);
- for (j = 0; j < TRANSPORT_MAX_LUNS_PER_TPG; j++) {
- deve = &se_nacl->device_list[j];
- if (!(deve->lun_flags &
- TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) ||
- (!deve->se_lun))
- continue;
- lun = deve->se_lun;
- if (!lun->lun_se_dev)
- continue;
-
- seq_printf(seq, "%u %u %u %u %u %s %u %u %u %u %u %u"
- " %u %s\n",
- /* scsiInstIndex */
- (TPG_TFO(se_tpg)->tpg_get_inst_index != NULL) ?
- TPG_TFO(se_tpg)->tpg_get_inst_index(se_tpg) :
- 0,
- /* scsiDeviceIndex */
- lun->lun_se_dev->dev_index,
- /* scsiAuthIntrTgtPortIndex */
- TPG_TFO(se_tpg)->tpg_get_tag(se_tpg),
- /* scsiAuthIntrIndex */
- se_nacl->acl_index,
- /* scsiAuthIntrDevOrPort */
- 1,
- /* scsiAuthIntrName */
- se_nacl->initiatorname[0] ?
- se_nacl->initiatorname : NONE,
- /* FIXME: scsiAuthIntrLunMapIndex */
- 0,
- /* scsiAuthIntrAttachedTimes */
- deve->attach_count,
- /* scsiAuthIntrOutCommands */
- deve->total_cmds,
- /* scsiAuthIntrReadMegaBytes */
- (u32)(deve->read_bytes >> 20),
- /* scsiAuthIntrWrittenMegaBytes */
- (u32)(deve->write_bytes >> 20),
- /* FIXME: scsiAuthIntrHSOutCommands */
- 0,
- /* scsiAuthIntrLastCreation */
- (u32)(((u32)deve->creation_time -
- INITIAL_JIFFIES) * 100 / HZ),
- /* FIXME: scsiAuthIntrRowStatus */
- "Ready");
- }
- spin_unlock_irq(&se_nacl->device_list_lock);
-
- spin_lock(&se_tpg->acl_node_lock);
- atomic_dec(&se_nacl->mib_ref_count);
- smp_mb__after_atomic_dec();
- }
- spin_unlock(&se_tpg->acl_node_lock);
-
- return 0;
-}
-
-static const struct seq_operations scsi_auth_intr_seq_ops = {
- .start = scsi_auth_intr_seq_start,
- .next = scsi_auth_intr_seq_next,
- .stop = scsi_auth_intr_seq_stop,
- .show = scsi_auth_intr_seq_show
-};
-
-static int scsi_auth_intr_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_auth_intr_seq_ops);
-}
-
-static const struct file_operations scsi_auth_intr_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_auth_intr_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
- * SCSI Attached Initiator Port Table:
- * It lists the SCSI Initiators attached to one of the local Target ports.
- * Iterates through all active TPGs and use active sessions from each TPG
- * to list the info fo this table.
- */
-static void *scsi_att_intr_port_seq_start(struct seq_file *seq, loff_t *pos)
-{
- spin_lock_bh(&se_global->se_tpg_lock);
- return seq_list_start(&se_global->g_se_tpg_list, *pos);
-}
-
-static void *scsi_att_intr_port_seq_next(struct seq_file *seq, void *v,
- loff_t *pos)
-{
- return seq_list_next(v, &se_global->g_se_tpg_list, pos);
-}
-
-static void scsi_att_intr_port_seq_stop(struct seq_file *seq, void *v)
-{
- spin_unlock_bh(&se_global->se_tpg_lock);
-}
-
-static int scsi_att_intr_port_seq_show(struct seq_file *seq, void *v)
-{
- struct se_portal_group *se_tpg = list_entry(v, struct se_portal_group,
- se_tpg_list);
- struct se_dev_entry *deve;
- struct se_lun *lun;
- struct se_node_acl *se_nacl;
- struct se_session *se_sess;
- unsigned char buf[64];
- int j;
-
- if (list_is_first(&se_tpg->se_tpg_list,
- &se_global->g_se_tpg_list))
- seq_puts(seq, "inst dev port indx port_auth_indx port_name"
- " port_ident\n");
-
- if (!(se_tpg))
- return 0;
-
- spin_lock(&se_tpg->session_lock);
- list_for_each_entry(se_sess, &se_tpg->tpg_sess_list, sess_list) {
- if ((TPG_TFO(se_tpg)->sess_logged_in(se_sess)) ||
- (!se_sess->se_node_acl) ||
- (!se_sess->se_node_acl->device_list))
- continue;
-
- atomic_inc(&se_sess->mib_ref_count);
- smp_mb__after_atomic_inc();
- se_nacl = se_sess->se_node_acl;
- atomic_inc(&se_nacl->mib_ref_count);
- smp_mb__after_atomic_inc();
- spin_unlock(&se_tpg->session_lock);
-
- spin_lock_irq(&se_nacl->device_list_lock);
- for (j = 0; j < TRANSPORT_MAX_LUNS_PER_TPG; j++) {
- deve = &se_nacl->device_list[j];
- if (!(deve->lun_flags &
- TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) ||
- (!deve->se_lun))
- continue;
-
- lun = deve->se_lun;
- if (!lun->lun_se_dev)
- continue;
-
- memset(buf, 0, 64);
- if (TPG_TFO(se_tpg)->sess_get_initiator_sid != NULL)
- TPG_TFO(se_tpg)->sess_get_initiator_sid(
- se_sess, (unsigned char *)&buf[0], 64);
-
- seq_printf(seq, "%u %u %u %u %u %s+i+%s\n",
- /* scsiInstIndex */
- (TPG_TFO(se_tpg)->tpg_get_inst_index != NULL) ?
- TPG_TFO(se_tpg)->tpg_get_inst_index(se_tpg) :
- 0,
- /* scsiDeviceIndex */
- lun->lun_se_dev->dev_index,
- /* scsiPortIndex */
- TPG_TFO(se_tpg)->tpg_get_tag(se_tpg),
- /* scsiAttIntrPortIndex */
- (TPG_TFO(se_tpg)->sess_get_index != NULL) ?
- TPG_TFO(se_tpg)->sess_get_index(se_sess) :
- 0,
- /* scsiAttIntrPortAuthIntrIdx */
- se_nacl->acl_index,
- /* scsiAttIntrPortName */
- se_nacl->initiatorname[0] ?
- se_nacl->initiatorname : NONE,
- /* scsiAttIntrPortIdentifier */
- buf);
- }
- spin_unlock_irq(&se_nacl->device_list_lock);
-
- spin_lock(&se_tpg->session_lock);
- atomic_dec(&se_nacl->mib_ref_count);
- smp_mb__after_atomic_dec();
- atomic_dec(&se_sess->mib_ref_count);
- smp_mb__after_atomic_dec();
- }
- spin_unlock(&se_tpg->session_lock);
-
- return 0;
-}
-
-static const struct seq_operations scsi_att_intr_port_seq_ops = {
- .start = scsi_att_intr_port_seq_start,
- .next = scsi_att_intr_port_seq_next,
- .stop = scsi_att_intr_port_seq_stop,
- .show = scsi_att_intr_port_seq_show
-};
-
-static int scsi_att_intr_port_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_att_intr_port_seq_ops);
-}
-
-static const struct file_operations scsi_att_intr_port_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_att_intr_port_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
- * SCSI Logical Unit Table
- */
-static void *scsi_lu_seq_start(struct seq_file *seq, loff_t *pos)
-{
- return locate_hba_start(seq, pos);
-}
-
-static void *scsi_lu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
- return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_lu_seq_stop(struct seq_file *seq, void *v)
-{
- locate_hba_stop(seq, v);
-}
-
-#define SCSI_LU_INDEX 1
-static int scsi_lu_seq_show(struct seq_file *seq, void *v)
-{
- struct se_hba *hba;
- struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
- g_se_dev_list);
- struct se_device *dev = se_dev->se_dev_ptr;
- int j;
- char str[28];
-
- if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
- seq_puts(seq, "inst dev indx LUN lu_name vend prod rev"
- " dev_type status state-bit num_cmds read_mbytes"
- " write_mbytes resets full_stat hs_num_cmds creation_time\n");
-
- if (!(dev))
- return 0;
-
- hba = dev->se_hba;
- if (!(hba)) {
- /* Log error ? */
- return 0;
- }
-
- /* Fix LU state, if we can read it from the device */
- seq_printf(seq, "%u %u %u %llu %s", hba->hba_index,
- dev->dev_index, SCSI_LU_INDEX,
- (unsigned long long)0, /* FIXME: scsiLuDefaultLun */
- (strlen(DEV_T10_WWN(dev)->unit_serial)) ?
- /* scsiLuWwnName */
- (char *)&DEV_T10_WWN(dev)->unit_serial[0] :
- "None");
-
- memcpy(&str[0], (void *)DEV_T10_WWN(dev), 28);
- /* scsiLuVendorId */
- for (j = 0; j < 8; j++)
- str[j] = ISPRINT(DEV_T10_WWN(dev)->vendor[j]) ?
- DEV_T10_WWN(dev)->vendor[j] : 0x20;
- str[8] = 0;
- seq_printf(seq, " %s", str);
-
- /* scsiLuProductId */
- for (j = 0; j < 16; j++)
- str[j] = ISPRINT(DEV_T10_WWN(dev)->model[j]) ?
- DEV_T10_WWN(dev)->model[j] : 0x20;
- str[16] = 0;
- seq_printf(seq, " %s", str);
-
- /* scsiLuRevisionId */
- for (j = 0; j < 4; j++)
- str[j] = ISPRINT(DEV_T10_WWN(dev)->revision[j]) ?
- DEV_T10_WWN(dev)->revision[j] : 0x20;
- str[4] = 0;
- seq_printf(seq, " %s", str);
-
- seq_printf(seq, " %u %s %s %llu %u %u %u %u %u %u\n",
- /* scsiLuPeripheralType */
- TRANSPORT(dev)->get_device_type(dev),
- (dev->dev_status == TRANSPORT_DEVICE_ACTIVATED) ?
- "available" : "notavailable", /* scsiLuStatus */
- "exposed", /* scsiLuState */
- (unsigned long long)dev->num_cmds,
- /* scsiLuReadMegaBytes */
- (u32)(dev->read_bytes >> 20),
- /* scsiLuWrittenMegaBytes */
- (u32)(dev->write_bytes >> 20),
- dev->num_resets, /* scsiLuInResets */
- 0, /* scsiLuOutTaskSetFullStatus */
- 0, /* scsiLuHSInCommands */
- (u32)(((u32)dev->creation_time - INITIAL_JIFFIES) *
- 100 / HZ));
-
- return 0;
-}
-
-static const struct seq_operations scsi_lu_seq_ops = {
- .start = scsi_lu_seq_start,
- .next = scsi_lu_seq_next,
- .stop = scsi_lu_seq_stop,
- .show = scsi_lu_seq_show
-};
-
-static int scsi_lu_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scsi_lu_seq_ops);
-}
-
-static const struct file_operations scsi_lu_seq_fops = {
- .owner = THIS_MODULE,
- .open = scsi_lu_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/****************************************************************************/
-
-/*
- * Remove proc fs entries
- */
-void remove_scsi_target_mib(void)
-{
- remove_proc_entry("scsi_target/mib/scsi_inst", NULL);
- remove_proc_entry("scsi_target/mib/scsi_dev", NULL);
- remove_proc_entry("scsi_target/mib/scsi_port", NULL);
- remove_proc_entry("scsi_target/mib/scsi_transport", NULL);
- remove_proc_entry("scsi_target/mib/scsi_tgt_dev", NULL);
- remove_proc_entry("scsi_target/mib/scsi_tgt_port", NULL);
- remove_proc_entry("scsi_target/mib/scsi_auth_intr", NULL);
- remove_proc_entry("scsi_target/mib/scsi_att_intr_port", NULL);
- remove_proc_entry("scsi_target/mib/scsi_lu", NULL);
- remove_proc_entry("scsi_target/mib", NULL);
-}
-
-/*
- * Create proc fs entries for the mib tables
- */
-int init_scsi_target_mib(void)
-{
- struct proc_dir_entry *dir_entry;
- struct proc_dir_entry *scsi_inst_entry;
- struct proc_dir_entry *scsi_dev_entry;
- struct proc_dir_entry *scsi_port_entry;
- struct proc_dir_entry *scsi_transport_entry;
- struct proc_dir_entry *scsi_tgt_dev_entry;
- struct proc_dir_entry *scsi_tgt_port_entry;
- struct proc_dir_entry *scsi_auth_intr_entry;
- struct proc_dir_entry *scsi_att_intr_port_entry;
- struct proc_dir_entry *scsi_lu_entry;
-
- dir_entry = proc_mkdir("scsi_target/mib", NULL);
- if (!(dir_entry)) {
- printk(KERN_ERR "proc_mkdir() failed.\n");
- return -1;
- }
-
- scsi_inst_entry =
- create_proc_entry("scsi_target/mib/scsi_inst", 0, NULL);
- if (scsi_inst_entry)
- scsi_inst_entry->proc_fops = &scsi_inst_seq_fops;
- else
- goto error;
-
- scsi_dev_entry =
- create_proc_entry("scsi_target/mib/scsi_dev", 0, NULL);
- if (scsi_dev_entry)
- scsi_dev_entry->proc_fops = &scsi_dev_seq_fops;
- else
- goto error;
-
- scsi_port_entry =
- create_proc_entry("scsi_target/mib/scsi_port", 0, NULL);
- if (scsi_port_entry)
- scsi_port_entry->proc_fops = &scsi_port_seq_fops;
- else
- goto error;
-
- scsi_transport_entry =
- create_proc_entry("scsi_target/mib/scsi_transport", 0, NULL);
- if (scsi_transport_entry)
- scsi_transport_entry->proc_fops = &scsi_transport_seq_fops;
- else
- goto error;
-
- scsi_tgt_dev_entry =
- create_proc_entry("scsi_target/mib/scsi_tgt_dev", 0, NULL);
- if (scsi_tgt_dev_entry)
- scsi_tgt_dev_entry->proc_fops = &scsi_tgt_dev_seq_fops;
- else
- goto error;
-
- scsi_tgt_port_entry =
- create_proc_entry("scsi_target/mib/scsi_tgt_port", 0, NULL);
- if (scsi_tgt_port_entry)
- scsi_tgt_port_entry->proc_fops = &scsi_tgt_port_seq_fops;
- else
- goto error;
-
- scsi_auth_intr_entry =
- create_proc_entry("scsi_target/mib/scsi_auth_intr", 0, NULL);
- if (scsi_auth_intr_entry)
- scsi_auth_intr_entry->proc_fops = &scsi_auth_intr_seq_fops;
- else
- goto error;
-
- scsi_att_intr_port_entry =
- create_proc_entry("scsi_target/mib/scsi_att_intr_port", 0, NULL);
- if (scsi_att_intr_port_entry)
- scsi_att_intr_port_entry->proc_fops =
- &scsi_att_intr_port_seq_fops;
- else
- goto error;
-
- scsi_lu_entry = create_proc_entry("scsi_target/mib/scsi_lu", 0, NULL);
- if (scsi_lu_entry)
- scsi_lu_entry->proc_fops = &scsi_lu_seq_fops;
- else
- goto error;
-
- return 0;
-
-error:
- printk(KERN_ERR "create_proc_entry() failed.\n");
- remove_scsi_target_mib();
- return -1;
-}
-
-/*
- * Initialize the index table for allocating unique row indexes to various mib
- * tables
- */
-void init_scsi_index_table(void)
-{
- memset(&scsi_index_table, 0, sizeof(struct scsi_index_table));
- spin_lock_init(&scsi_index_table.lock);
-}
-
-/*
- * Allocate a new row index for the entry type specified
- */
-u32 scsi_get_new_index(scsi_index_t type)
-{
- u32 new_index;
-
- if ((type < 0) || (type >= SCSI_INDEX_TYPE_MAX)) {
- printk(KERN_ERR "Invalid index type %d\n", type);
- return -1;
- }
-
- spin_lock(&scsi_index_table.lock);
- new_index = ++scsi_index_table.scsi_mib_index[type];
- if (new_index == 0)
- new_index = ++scsi_index_table.scsi_mib_index[type];
- spin_unlock(&scsi_index_table.lock);
-
- return new_index;
-}
-EXPORT_SYMBOL(scsi_get_new_index);
+++ /dev/null
-#ifndef TARGET_CORE_MIB_H
-#define TARGET_CORE_MIB_H
-
-typedef enum {
- SCSI_INST_INDEX,
- SCSI_DEVICE_INDEX,
- SCSI_AUTH_INTR_INDEX,
- SCSI_INDEX_TYPE_MAX
-} scsi_index_t;
-
-struct scsi_index_table {
- spinlock_t lock;
- u32 scsi_mib_index[SCSI_INDEX_TYPE_MAX];
-} ____cacheline_aligned;
-
-/* SCSI Port stats */
-struct scsi_port_stats {
- u64 cmd_pdus;
- u64 tx_data_octets;
- u64 rx_data_octets;
-} ____cacheline_aligned;
-
-extern int init_scsi_target_mib(void);
-extern void remove_scsi_target_mib(void);
-extern void init_scsi_index_table(void);
-extern u32 scsi_get_new_index(scsi_index_t);
-
-#endif /*** TARGET_CORE_MIB_H ***/
*/
bd = blkdev_get_by_path(se_dev->se_dev_udev_path,
FMODE_WRITE|FMODE_READ|FMODE_EXCL, pdv);
- if (!(bd)) {
- printk("pSCSI: blkdev_get_by_path() failed\n");
+ if (IS_ERR(bd)) {
+ printk(KERN_ERR "pSCSI: blkdev_get_by_path() failed\n");
scsi_device_put(sd);
return NULL;
}
atomic_set(&task->task_active, 0);
atomic_set(&task->task_stop, 0);
+ } else {
+ if (atomic_read(&task->task_execute_queue) != 0)
+ transport_remove_task_from_execute_queue(task, dev);
}
__transport_stop_task_timer(task, &flags);
DEBUG_LR("LUN_RESET: got t_transport_active = 1 for"
" task: %p, t_fe_count: %d dev: %p\n", task,
fe_count, dev);
+ atomic_set(&T_TASK(cmd)->t_transport_aborted, 1);
spin_unlock_irqrestore(&T_TASK(cmd)->t_state_lock,
flags);
core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count);
}
DEBUG_LR("LUN_RESET: Got t_transport_active = 0 for task: %p,"
" t_fe_count: %d dev: %p\n", task, fe_count, dev);
+ atomic_set(&T_TASK(cmd)->t_transport_aborted, 1);
spin_unlock_irqrestore(&T_TASK(cmd)->t_state_lock, flags);
core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count);
spin_lock_init(&acl->device_list_lock);
spin_lock_init(&acl->nacl_sess_lock);
atomic_set(&acl->acl_pr_ref_count, 0);
- atomic_set(&acl->mib_ref_count, 0);
acl->queue_depth = TPG_TFO(tpg)->tpg_get_default_depth(tpg);
snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname);
acl->se_tpg = tpg;
cpu_relax();
}
-void core_tpg_wait_for_mib_ref(struct se_node_acl *nacl)
-{
- while (atomic_read(&nacl->mib_ref_count) != 0)
- cpu_relax();
-}
-
void core_tpg_clear_object_luns(struct se_portal_group *tpg)
{
int i, ret;
spin_unlock_bh(&tpg->session_lock);
core_tpg_wait_for_nacl_pr_ref(acl);
- core_tpg_wait_for_mib_ref(acl);
core_clear_initiator_node_from_tpg(acl, tpg);
core_free_device_list_for_node(acl, tpg);
int core_tpg_deregister(struct se_portal_group *se_tpg)
{
+ struct se_node_acl *nacl, *nacl_tmp;
+
printk(KERN_INFO "TARGET_CORE[%s]: Deallocating %s struct se_portal_group"
" for endpoint: %s Portal Tag %u\n",
(se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL) ?
while (atomic_read(&se_tpg->tpg_pr_ref_count) != 0)
cpu_relax();
+ /*
+ * Release any remaining demo-mode generated se_node_acl that have
+ * not been released because of TFO->tpg_check_demo_mode_cache() == 1
+ * in transport_deregister_session().
+ */
+ spin_lock_bh(&se_tpg->acl_node_lock);
+ list_for_each_entry_safe(nacl, nacl_tmp, &se_tpg->acl_node_list,
+ acl_list) {
+ list_del(&nacl->acl_list);
+ se_tpg->num_node_acls--;
+ spin_unlock_bh(&se_tpg->acl_node_lock);
+
+ core_tpg_wait_for_nacl_pr_ref(nacl);
+ core_free_device_list_for_node(nacl, se_tpg);
+ TPG_TFO(se_tpg)->tpg_release_fabric_acl(se_tpg, nacl);
+
+ spin_lock_bh(&se_tpg->acl_node_lock);
+ }
+ spin_unlock_bh(&se_tpg->acl_node_lock);
if (se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL)
core_tpg_release_virtual_lun0(se_tpg);
se_global = NULL;
}
+/* SCSI statistics table index */
+static struct scsi_index_table scsi_index_table;
+
+/*
+ * Initialize the index table for allocating unique row indexes to various mib
+ * tables.
+ */
+void init_scsi_index_table(void)
+{
+ memset(&scsi_index_table, 0, sizeof(struct scsi_index_table));
+ spin_lock_init(&scsi_index_table.lock);
+}
+
+/*
+ * Allocate a new row index for the entry type specified
+ */
+u32 scsi_get_new_index(scsi_index_t type)
+{
+ u32 new_index;
+
+ if ((type < 0) || (type >= SCSI_INDEX_TYPE_MAX)) {
+ printk(KERN_ERR "Invalid index type %d\n", type);
+ return -EINVAL;
+ }
+
+ spin_lock(&scsi_index_table.lock);
+ new_index = ++scsi_index_table.scsi_mib_index[type];
+ if (new_index == 0)
+ new_index = ++scsi_index_table.scsi_mib_index[type];
+ spin_unlock(&scsi_index_table.lock);
+
+ return new_index;
+}
+
void transport_init_queue_obj(struct se_queue_obj *qobj)
{
atomic_set(&qobj->queue_cnt, 0);
}
INIT_LIST_HEAD(&se_sess->sess_list);
INIT_LIST_HEAD(&se_sess->sess_acl_list);
- atomic_set(&se_sess->mib_ref_count, 0);
return se_sess;
}
transport_free_session(se_sess);
return;
}
- /*
- * Wait for possible reference in drivers/target/target_core_mib.c:
- * scsi_att_intr_port_seq_show()
- */
- while (atomic_read(&se_sess->mib_ref_count) != 0)
- cpu_relax();
spin_lock_bh(&se_tpg->session_lock);
list_del(&se_sess->sess_list);
spin_unlock_bh(&se_tpg->acl_node_lock);
core_tpg_wait_for_nacl_pr_ref(se_nacl);
- core_tpg_wait_for_mib_ref(se_nacl);
core_free_device_list_for_node(se_nacl, se_tpg);
TPG_TFO(se_tpg)->tpg_release_fabric_acl(se_tpg,
se_nacl);
*
*
*/
-static void transport_remove_task_from_execute_queue(
+void transport_remove_task_from_execute_queue(
struct se_task *task,
struct se_device *dev)
{
return ret;
}
+
+ BUG_ON(list_empty(se_mem_list));
/*
* This is the normal path for all normal non BIDI and BIDI-COMMAND
* WRITE payloads.. If we need to do BIDI READ passthrough for
struct se_mem *se_mem = NULL, *se_mem_lout = NULL;
u32 se_mem_cnt = 0, task_offset = 0;
- BUG_ON(list_empty(cmd->t_task->t_mem_list));
+ if (!list_empty(T_TASK(cmd)->t_mem_list))
+ se_mem = list_entry(T_TASK(cmd)->t_mem_list->next,
+ struct se_mem, se_list);
ret = transport_do_se_mem_map(dev, task,
cmd->t_task->t_mem_list, NULL, se_mem,
atomic_set(&T_TASK(cmd)->transport_lun_stop, 0);
}
- if (!atomic_read(&T_TASK(cmd)->t_transport_active))
+ if (!atomic_read(&T_TASK(cmd)->t_transport_active) ||
+ atomic_read(&T_TASK(cmd)->t_transport_aborted))
goto remove;
atomic_set(&T_TASK(cmd)->t_transport_stop, 1);
atomic_set(&task->task_active, 0);
atomic_set(&task->task_stop, 0);
+ } else {
+ if (atomic_read(&task->task_execute_queue) != 0)
+ transport_remove_task_from_execute_queue(task, dev);
}
__transport_stop_task_timer(task, &flags);
menuconfig THERMAL
tristate "Generic Thermal sysfs driver"
- depends on NET
help
Generic Thermal Sysfs driver offers a generic mechanism for
thermal management. Usually it's made up of one or more thermal
static unsigned int thermal_event_seqnum;
-static struct genl_family thermal_event_genl_family = {
- .id = GENL_ID_GENERATE,
- .name = THERMAL_GENL_FAMILY_NAME,
- .version = THERMAL_GENL_VERSION,
- .maxattr = THERMAL_GENL_ATTR_MAX,
-};
-
-static struct genl_multicast_group thermal_event_mcgrp = {
- .name = THERMAL_GENL_MCAST_GROUP_NAME,
-};
-
-static int genetlink_init(void);
-static void genetlink_exit(void);
-
static int get_idr(struct idr *idr, struct mutex *lock, int *id)
{
int err;
EXPORT_SYMBOL(thermal_zone_device_unregister);
+#ifdef CONFIG_NET
+static struct genl_family thermal_event_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .name = THERMAL_GENL_FAMILY_NAME,
+ .version = THERMAL_GENL_VERSION,
+ .maxattr = THERMAL_GENL_ATTR_MAX,
+};
+
+static struct genl_multicast_group thermal_event_mcgrp = {
+ .name = THERMAL_GENL_MCAST_GROUP_NAME,
+};
+
int generate_netlink_event(u32 orig, enum events event)
{
struct sk_buff *skb;
return result;
}
+static void genetlink_exit(void)
+{
+ genl_unregister_family(&thermal_event_genl_family);
+}
+#else /* !CONFIG_NET */
+static inline int genetlink_init(void) { return 0; }
+static inline void genetlink_exit(void) {}
+#endif /* !CONFIG_NET */
+
static int __init thermal_init(void)
{
int result = 0;
return result;
}
-static void genetlink_exit(void)
-{
- genl_unregister_family(&thermal_event_genl_family);
-}
-
static void __exit thermal_exit(void)
{
class_unregister(&thermal_class);
obj-$(CONFIG_HVC_IUCV) += hvc_iucv.o
obj-$(CONFIG_HVC_UDBG) += hvc_udbg.o
obj-$(CONFIG_HVCS) += hvcs.o
-obj-$(CONFIG_VIRTIO_CONSOLE) += virtio_console.o
+++ /dev/null
-/*
- * Copyright (C) 2006, 2007, 2009 Rusty Russell, IBM Corporation
- * Copyright (C) 2009, 2010 Red Hat, Inc.
- *
- * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-#include <linux/cdev.h>
-#include <linux/debugfs.h>
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/poll.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/virtio.h>
-#include <linux/virtio_console.h>
-#include <linux/wait.h>
-#include <linux/workqueue.h>
-#include "hvc_console.h"
-
-/*
- * This is a global struct for storing common data for all the devices
- * this driver handles.
- *
- * Mainly, it has a linked list for all the consoles in one place so
- * that callbacks from hvc for get_chars(), put_chars() work properly
- * across multiple devices and multiple ports per device.
- */
-struct ports_driver_data {
- /* Used for registering chardevs */
- struct class *class;
-
- /* Used for exporting per-port information to debugfs */
- struct dentry *debugfs_dir;
-
- /* List of all the devices we're handling */
- struct list_head portdevs;
-
- /* Number of devices this driver is handling */
- unsigned int index;
-
- /*
- * This is used to keep track of the number of hvc consoles
- * spawned by this driver. This number is given as the first
- * argument to hvc_alloc(). To correctly map an initial
- * console spawned via hvc_instantiate to the console being
- * hooked up via hvc_alloc, we need to pass the same vtermno.
- *
- * We also just assume the first console being initialised was
- * the first one that got used as the initial console.
- */
- unsigned int next_vtermno;
-
- /* All the console devices handled by this driver */
- struct list_head consoles;
-};
-static struct ports_driver_data pdrvdata;
-
-DEFINE_SPINLOCK(pdrvdata_lock);
-
-/* This struct holds information that's relevant only for console ports */
-struct console {
- /* We'll place all consoles in a list in the pdrvdata struct */
- struct list_head list;
-
- /* The hvc device associated with this console port */
- struct hvc_struct *hvc;
-
- /* The size of the console */
- struct winsize ws;
-
- /*
- * This number identifies the number that we used to register
- * with hvc in hvc_instantiate() and hvc_alloc(); this is the
- * number passed on by the hvc callbacks to us to
- * differentiate between the other console ports handled by
- * this driver
- */
- u32 vtermno;
-};
-
-struct port_buffer {
- char *buf;
-
- /* size of the buffer in *buf above */
- size_t size;
-
- /* used length of the buffer */
- size_t len;
- /* offset in the buf from which to consume data */
- size_t offset;
-};
-
-/*
- * This is a per-device struct that stores data common to all the
- * ports for that device (vdev->priv).
- */
-struct ports_device {
- /* Next portdev in the list, head is in the pdrvdata struct */
- struct list_head list;
-
- /*
- * Workqueue handlers where we process deferred work after
- * notification
- */
- struct work_struct control_work;
-
- struct list_head ports;
-
- /* To protect the list of ports */
- spinlock_t ports_lock;
-
- /* To protect the vq operations for the control channel */
- spinlock_t cvq_lock;
-
- /* The current config space is stored here */
- struct virtio_console_config config;
-
- /* The virtio device we're associated with */
- struct virtio_device *vdev;
-
- /*
- * A couple of virtqueues for the control channel: one for
- * guest->host transfers, one for host->guest transfers
- */
- struct virtqueue *c_ivq, *c_ovq;
-
- /* Array of per-port IO virtqueues */
- struct virtqueue **in_vqs, **out_vqs;
-
- /* Used for numbering devices for sysfs and debugfs */
- unsigned int drv_index;
-
- /* Major number for this device. Ports will be created as minors. */
- int chr_major;
-};
-
-/* This struct holds the per-port data */
-struct port {
- /* Next port in the list, head is in the ports_device */
- struct list_head list;
-
- /* Pointer to the parent virtio_console device */
- struct ports_device *portdev;
-
- /* The current buffer from which data has to be fed to readers */
- struct port_buffer *inbuf;
-
- /*
- * To protect the operations on the in_vq associated with this
- * port. Has to be a spinlock because it can be called from
- * interrupt context (get_char()).
- */
- spinlock_t inbuf_lock;
-
- /* Protect the operations on the out_vq. */
- spinlock_t outvq_lock;
-
- /* The IO vqs for this port */
- struct virtqueue *in_vq, *out_vq;
-
- /* File in the debugfs directory that exposes this port's information */
- struct dentry *debugfs_file;
-
- /*
- * The entries in this struct will be valid if this port is
- * hooked up to an hvc console
- */
- struct console cons;
-
- /* Each port associates with a separate char device */
- struct cdev *cdev;
- struct device *dev;
-
- /* Reference-counting to handle port hot-unplugs and file operations */
- struct kref kref;
-
- /* A waitqueue for poll() or blocking read operations */
- wait_queue_head_t waitqueue;
-
- /* The 'name' of the port that we expose via sysfs properties */
- char *name;
-
- /* We can notify apps of host connect / disconnect events via SIGIO */
- struct fasync_struct *async_queue;
-
- /* The 'id' to identify the port with the Host */
- u32 id;
-
- bool outvq_full;
-
- /* Is the host device open */
- bool host_connected;
-
- /* We should allow only one process to open a port */
- bool guest_connected;
-};
-
-/* This is the very early arch-specified put chars function. */
-static int (*early_put_chars)(u32, const char *, int);
-
-static struct port *find_port_by_vtermno(u32 vtermno)
-{
- struct port *port;
- struct console *cons;
- unsigned long flags;
-
- spin_lock_irqsave(&pdrvdata_lock, flags);
- list_for_each_entry(cons, &pdrvdata.consoles, list) {
- if (cons->vtermno == vtermno) {
- port = container_of(cons, struct port, cons);
- goto out;
- }
- }
- port = NULL;
-out:
- spin_unlock_irqrestore(&pdrvdata_lock, flags);
- return port;
-}
-
-static struct port *find_port_by_devt_in_portdev(struct ports_device *portdev,
- dev_t dev)
-{
- struct port *port;
- unsigned long flags;
-
- spin_lock_irqsave(&portdev->ports_lock, flags);
- list_for_each_entry(port, &portdev->ports, list)
- if (port->cdev->dev == dev)
- goto out;
- port = NULL;
-out:
- spin_unlock_irqrestore(&portdev->ports_lock, flags);
-
- return port;
-}
-
-static struct port *find_port_by_devt(dev_t dev)
-{
- struct ports_device *portdev;
- struct port *port;
- unsigned long flags;
-
- spin_lock_irqsave(&pdrvdata_lock, flags);
- list_for_each_entry(portdev, &pdrvdata.portdevs, list) {
- port = find_port_by_devt_in_portdev(portdev, dev);
- if (port)
- goto out;
- }
- port = NULL;
-out:
- spin_unlock_irqrestore(&pdrvdata_lock, flags);
- return port;
-}
-
-static struct port *find_port_by_id(struct ports_device *portdev, u32 id)
-{
- struct port *port;
- unsigned long flags;
-
- spin_lock_irqsave(&portdev->ports_lock, flags);
- list_for_each_entry(port, &portdev->ports, list)
- if (port->id == id)
- goto out;
- port = NULL;
-out:
- spin_unlock_irqrestore(&portdev->ports_lock, flags);
-
- return port;
-}
-
-static struct port *find_port_by_vq(struct ports_device *portdev,
- struct virtqueue *vq)
-{
- struct port *port;
- unsigned long flags;
-
- spin_lock_irqsave(&portdev->ports_lock, flags);
- list_for_each_entry(port, &portdev->ports, list)
- if (port->in_vq == vq || port->out_vq == vq)
- goto out;
- port = NULL;
-out:
- spin_unlock_irqrestore(&portdev->ports_lock, flags);
- return port;
-}
-
-static bool is_console_port(struct port *port)
-{
- if (port->cons.hvc)
- return true;
- return false;
-}
-
-static inline bool use_multiport(struct ports_device *portdev)
-{
- /*
- * This condition can be true when put_chars is called from
- * early_init
- */
- if (!portdev->vdev)
- return 0;
- return portdev->vdev->features[0] & (1 << VIRTIO_CONSOLE_F_MULTIPORT);
-}
-
-static void free_buf(struct port_buffer *buf)
-{
- kfree(buf->buf);
- kfree(buf);
-}
-
-static struct port_buffer *alloc_buf(size_t buf_size)
-{
- struct port_buffer *buf;
-
- buf = kmalloc(sizeof(*buf), GFP_KERNEL);
- if (!buf)
- goto fail;
- buf->buf = kzalloc(buf_size, GFP_KERNEL);
- if (!buf->buf)
- goto free_buf;
- buf->len = 0;
- buf->offset = 0;
- buf->size = buf_size;
- return buf;
-
-free_buf:
- kfree(buf);
-fail:
- return NULL;
-}
-
-/* Callers should take appropriate locks */
-static void *get_inbuf(struct port *port)
-{
- struct port_buffer *buf;
- struct virtqueue *vq;
- unsigned int len;
-
- vq = port->in_vq;
- buf = virtqueue_get_buf(vq, &len);
- if (buf) {
- buf->len = len;
- buf->offset = 0;
- }
- return buf;
-}
-
-/*
- * Create a scatter-gather list representing our input buffer and put
- * it in the queue.
- *
- * Callers should take appropriate locks.
- */
-static int add_inbuf(struct virtqueue *vq, struct port_buffer *buf)
-{
- struct scatterlist sg[1];
- int ret;
-
- sg_init_one(sg, buf->buf, buf->size);
-
- ret = virtqueue_add_buf(vq, sg, 0, 1, buf);
- virtqueue_kick(vq);
- return ret;
-}
-
-/* Discard any unread data this port has. Callers lockers. */
-static void discard_port_data(struct port *port)
-{
- struct port_buffer *buf;
- struct virtqueue *vq;
- unsigned int len;
- int ret;
-
- vq = port->in_vq;
- if (port->inbuf)
- buf = port->inbuf;
- else
- buf = virtqueue_get_buf(vq, &len);
-
- ret = 0;
- while (buf) {
- if (add_inbuf(vq, buf) < 0) {
- ret++;
- free_buf(buf);
- }
- buf = virtqueue_get_buf(vq, &len);
- }
- port->inbuf = NULL;
- if (ret)
- dev_warn(port->dev, "Errors adding %d buffers back to vq\n",
- ret);
-}
-
-static bool port_has_data(struct port *port)
-{
- unsigned long flags;
- bool ret;
-
- spin_lock_irqsave(&port->inbuf_lock, flags);
- if (port->inbuf) {
- ret = true;
- goto out;
- }
- port->inbuf = get_inbuf(port);
- if (port->inbuf) {
- ret = true;
- goto out;
- }
- ret = false;
-out:
- spin_unlock_irqrestore(&port->inbuf_lock, flags);
- return ret;
-}
-
-static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
- unsigned int event, unsigned int value)
-{
- struct scatterlist sg[1];
- struct virtio_console_control cpkt;
- struct virtqueue *vq;
- unsigned int len;
-
- if (!use_multiport(portdev))
- return 0;
-
- cpkt.id = port_id;
- cpkt.event = event;
- cpkt.value = value;
-
- vq = portdev->c_ovq;
-
- sg_init_one(sg, &cpkt, sizeof(cpkt));
- if (virtqueue_add_buf(vq, sg, 1, 0, &cpkt) >= 0) {
- virtqueue_kick(vq);
- while (!virtqueue_get_buf(vq, &len))
- cpu_relax();
- }
- return 0;
-}
-
-static ssize_t send_control_msg(struct port *port, unsigned int event,
- unsigned int value)
-{
- /* Did the port get unplugged before userspace closed it? */
- if (port->portdev)
- return __send_control_msg(port->portdev, port->id, event, value);
- return 0;
-}
-
-/* Callers must take the port->outvq_lock */
-static void reclaim_consumed_buffers(struct port *port)
-{
- void *buf;
- unsigned int len;
-
- while ((buf = virtqueue_get_buf(port->out_vq, &len))) {
- kfree(buf);
- port->outvq_full = false;
- }
-}
-
-static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count,
- bool nonblock)
-{
- struct scatterlist sg[1];
- struct virtqueue *out_vq;
- ssize_t ret;
- unsigned long flags;
- unsigned int len;
-
- out_vq = port->out_vq;
-
- spin_lock_irqsave(&port->outvq_lock, flags);
-
- reclaim_consumed_buffers(port);
-
- sg_init_one(sg, in_buf, in_count);
- ret = virtqueue_add_buf(out_vq, sg, 1, 0, in_buf);
-
- /* Tell Host to go! */
- virtqueue_kick(out_vq);
-
- if (ret < 0) {
- in_count = 0;
- goto done;
- }
-
- if (ret == 0)
- port->outvq_full = true;
-
- if (nonblock)
- goto done;
-
- /*
- * Wait till the host acknowledges it pushed out the data we
- * sent. This is done for data from the hvc_console; the tty
- * operations are performed with spinlocks held so we can't
- * sleep here. An alternative would be to copy the data to a
- * buffer and relax the spinning requirement. The downside is
- * we need to kmalloc a GFP_ATOMIC buffer each time the
- * console driver writes something out.
- */
- while (!virtqueue_get_buf(out_vq, &len))
- cpu_relax();
-done:
- spin_unlock_irqrestore(&port->outvq_lock, flags);
- /*
- * We're expected to return the amount of data we wrote -- all
- * of it
- */
- return in_count;
-}
-
-/*
- * Give out the data that's requested from the buffer that we have
- * queued up.
- */
-static ssize_t fill_readbuf(struct port *port, char *out_buf, size_t out_count,
- bool to_user)
-{
- struct port_buffer *buf;
- unsigned long flags;
-
- if (!out_count || !port_has_data(port))
- return 0;
-
- buf = port->inbuf;
- out_count = min(out_count, buf->len - buf->offset);
-
- if (to_user) {
- ssize_t ret;
-
- ret = copy_to_user(out_buf, buf->buf + buf->offset, out_count);
- if (ret)
- return -EFAULT;
- } else {
- memcpy(out_buf, buf->buf + buf->offset, out_count);
- }
-
- buf->offset += out_count;
-
- if (buf->offset == buf->len) {
- /*
- * We're done using all the data in this buffer.
- * Re-queue so that the Host can send us more data.
- */
- spin_lock_irqsave(&port->inbuf_lock, flags);
- port->inbuf = NULL;
-
- if (add_inbuf(port->in_vq, buf) < 0)
- dev_warn(port->dev, "failed add_buf\n");
-
- spin_unlock_irqrestore(&port->inbuf_lock, flags);
- }
- /* Return the number of bytes actually copied */
- return out_count;
-}
-
-/* The condition that must be true for polling to end */
-static bool will_read_block(struct port *port)
-{
- if (!port->guest_connected) {
- /* Port got hot-unplugged. Let's exit. */
- return false;
- }
- return !port_has_data(port) && port->host_connected;
-}
-
-static bool will_write_block(struct port *port)
-{
- bool ret;
-
- if (!port->guest_connected) {
- /* Port got hot-unplugged. Let's exit. */
- return false;
- }
- if (!port->host_connected)
- return true;
-
- spin_lock_irq(&port->outvq_lock);
- /*
- * Check if the Host has consumed any buffers since we last
- * sent data (this is only applicable for nonblocking ports).
- */
- reclaim_consumed_buffers(port);
- ret = port->outvq_full;
- spin_unlock_irq(&port->outvq_lock);
-
- return ret;
-}
-
-static ssize_t port_fops_read(struct file *filp, char __user *ubuf,
- size_t count, loff_t *offp)
-{
- struct port *port;
- ssize_t ret;
-
- port = filp->private_data;
-
- if (!port_has_data(port)) {
- /*
- * If nothing's connected on the host just return 0 in
- * case of list_empty; this tells the userspace app
- * that there's no connection
- */
- if (!port->host_connected)
- return 0;
- if (filp->f_flags & O_NONBLOCK)
- return -EAGAIN;
-
- ret = wait_event_interruptible(port->waitqueue,
- !will_read_block(port));
- if (ret < 0)
- return ret;
- }
- /* Port got hot-unplugged. */
- if (!port->guest_connected)
- return -ENODEV;
- /*
- * We could've received a disconnection message while we were
- * waiting for more data.
- *
- * This check is not clubbed in the if() statement above as we
- * might receive some data as well as the host could get
- * disconnected after we got woken up from our wait. So we
- * really want to give off whatever data we have and only then
- * check for host_connected.
- */
- if (!port_has_data(port) && !port->host_connected)
- return 0;
-
- return fill_readbuf(port, ubuf, count, true);
-}
-
-static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
- size_t count, loff_t *offp)
-{
- struct port *port;
- char *buf;
- ssize_t ret;
- bool nonblock;
-
- /* Userspace could be out to fool us */
- if (!count)
- return 0;
-
- port = filp->private_data;
-
- nonblock = filp->f_flags & O_NONBLOCK;
-
- if (will_write_block(port)) {
- if (nonblock)
- return -EAGAIN;
-
- ret = wait_event_interruptible(port->waitqueue,
- !will_write_block(port));
- if (ret < 0)
- return ret;
- }
- /* Port got hot-unplugged. */
- if (!port->guest_connected)
- return -ENODEV;
-
- count = min((size_t)(32 * 1024), count);
-
- buf = kmalloc(count, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- ret = copy_from_user(buf, ubuf, count);
- if (ret) {
- ret = -EFAULT;
- goto free_buf;
- }
-
- /*
- * We now ask send_buf() to not spin for generic ports -- we
- * can re-use the same code path that non-blocking file
- * descriptors take for blocking file descriptors since the
- * wait is already done and we're certain the write will go
- * through to the host.
- */
- nonblock = true;
- ret = send_buf(port, buf, count, nonblock);
-
- if (nonblock && ret > 0)
- goto out;
-
-free_buf:
- kfree(buf);
-out:
- return ret;
-}
-
-static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
-{
- struct port *port;
- unsigned int ret;
-
- port = filp->private_data;
- poll_wait(filp, &port->waitqueue, wait);
-
- if (!port->guest_connected) {
- /* Port got unplugged */
- return POLLHUP;
- }
- ret = 0;
- if (!will_read_block(port))
- ret |= POLLIN | POLLRDNORM;
- if (!will_write_block(port))
- ret |= POLLOUT;
- if (!port->host_connected)
- ret |= POLLHUP;
-
- return ret;
-}
-
-static void remove_port(struct kref *kref);
-
-static int port_fops_release(struct inode *inode, struct file *filp)
-{
- struct port *port;
-
- port = filp->private_data;
-
- /* Notify host of port being closed */
- send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 0);
-
- spin_lock_irq(&port->inbuf_lock);
- port->guest_connected = false;
-
- discard_port_data(port);
-
- spin_unlock_irq(&port->inbuf_lock);
-
- spin_lock_irq(&port->outvq_lock);
- reclaim_consumed_buffers(port);
- spin_unlock_irq(&port->outvq_lock);
-
- /*
- * Locks aren't necessary here as a port can't be opened after
- * unplug, and if a port isn't unplugged, a kref would already
- * exist for the port. Plus, taking ports_lock here would
- * create a dependency on other locks taken by functions
- * inside remove_port if we're the last holder of the port,
- * creating many problems.
- */
- kref_put(&port->kref, remove_port);
-
- return 0;
-}
-
-static int port_fops_open(struct inode *inode, struct file *filp)
-{
- struct cdev *cdev = inode->i_cdev;
- struct port *port;
- int ret;
-
- port = find_port_by_devt(cdev->dev);
- filp->private_data = port;
-
- /* Prevent against a port getting hot-unplugged at the same time */
- spin_lock_irq(&port->portdev->ports_lock);
- kref_get(&port->kref);
- spin_unlock_irq(&port->portdev->ports_lock);
-
- /*
- * Don't allow opening of console port devices -- that's done
- * via /dev/hvc
- */
- if (is_console_port(port)) {
- ret = -ENXIO;
- goto out;
- }
-
- /* Allow only one process to open a particular port at a time */
- spin_lock_irq(&port->inbuf_lock);
- if (port->guest_connected) {
- spin_unlock_irq(&port->inbuf_lock);
- ret = -EMFILE;
- goto out;
- }
-
- port->guest_connected = true;
- spin_unlock_irq(&port->inbuf_lock);
-
- spin_lock_irq(&port->outvq_lock);
- /*
- * There might be a chance that we missed reclaiming a few
- * buffers in the window of the port getting previously closed
- * and opening now.
- */
- reclaim_consumed_buffers(port);
- spin_unlock_irq(&port->outvq_lock);
-
- nonseekable_open(inode, filp);
-
- /* Notify host of port being opened */
- send_control_msg(filp->private_data, VIRTIO_CONSOLE_PORT_OPEN, 1);
-
- return 0;
-out:
- kref_put(&port->kref, remove_port);
- return ret;
-}
-
-static int port_fops_fasync(int fd, struct file *filp, int mode)
-{
- struct port *port;
-
- port = filp->private_data;
- return fasync_helper(fd, filp, mode, &port->async_queue);
-}
-
-/*
- * The file operations that we support: programs in the guest can open
- * a console device, read from it, write to it, poll for data and
- * close it. The devices are at
- * /dev/vport<device number>p<port number>
- */
-static const struct file_operations port_fops = {
- .owner = THIS_MODULE,
- .open = port_fops_open,
- .read = port_fops_read,
- .write = port_fops_write,
- .poll = port_fops_poll,
- .release = port_fops_release,
- .fasync = port_fops_fasync,
- .llseek = no_llseek,
-};
-
-/*
- * The put_chars() callback is pretty straightforward.
- *
- * We turn the characters into a scatter-gather list, add it to the
- * output queue and then kick the Host. Then we sit here waiting for
- * it to finish: inefficient in theory, but in practice
- * implementations will do it immediately (lguest's Launcher does).
- */
-static int put_chars(u32 vtermno, const char *buf, int count)
-{
- struct port *port;
-
- if (unlikely(early_put_chars))
- return early_put_chars(vtermno, buf, count);
-
- port = find_port_by_vtermno(vtermno);
- if (!port)
- return -EPIPE;
-
- return send_buf(port, (void *)buf, count, false);
-}
-
-/*
- * get_chars() is the callback from the hvc_console infrastructure
- * when an interrupt is received.
- *
- * We call out to fill_readbuf that gets us the required data from the
- * buffers that are queued up.
- */
-static int get_chars(u32 vtermno, char *buf, int count)
-{
- struct port *port;
-
- /* If we've not set up the port yet, we have no input to give. */
- if (unlikely(early_put_chars))
- return 0;
-
- port = find_port_by_vtermno(vtermno);
- if (!port)
- return -EPIPE;
-
- /* If we don't have an input queue yet, we can't get input. */
- BUG_ON(!port->in_vq);
-
- return fill_readbuf(port, buf, count, false);
-}
-
-static void resize_console(struct port *port)
-{
- struct virtio_device *vdev;
-
- /* The port could have been hot-unplugged */
- if (!port || !is_console_port(port))
- return;
-
- vdev = port->portdev->vdev;
- if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_SIZE))
- hvc_resize(port->cons.hvc, port->cons.ws);
-}
-
-/* We set the configuration at this point, since we now have a tty */
-static int notifier_add_vio(struct hvc_struct *hp, int data)
-{
- struct port *port;
-
- port = find_port_by_vtermno(hp->vtermno);
- if (!port)
- return -EINVAL;
-
- hp->irq_requested = 1;
- resize_console(port);
-
- return 0;
-}
-
-static void notifier_del_vio(struct hvc_struct *hp, int data)
-{
- hp->irq_requested = 0;
-}
-
-/* The operations for console ports. */
-static const struct hv_ops hv_ops = {
- .get_chars = get_chars,
- .put_chars = put_chars,
- .notifier_add = notifier_add_vio,
- .notifier_del = notifier_del_vio,
- .notifier_hangup = notifier_del_vio,
-};
-
-/*
- * Console drivers are initialized very early so boot messages can go
- * out, so we do things slightly differently from the generic virtio
- * initialization of the net and block drivers.
- *
- * At this stage, the console is output-only. It's too early to set
- * up a virtqueue, so we let the drivers do some boutique early-output
- * thing.
- */
-int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int))
-{
- early_put_chars = put_chars;
- return hvc_instantiate(0, 0, &hv_ops);
-}
-
-int init_port_console(struct port *port)
-{
- int ret;
-
- /*
- * The Host's telling us this port is a console port. Hook it
- * up with an hvc console.
- *
- * To set up and manage our virtual console, we call
- * hvc_alloc().
- *
- * The first argument of hvc_alloc() is the virtual console
- * number. The second argument is the parameter for the
- * notification mechanism (like irq number). We currently
- * leave this as zero, virtqueues have implicit notifications.
- *
- * The third argument is a "struct hv_ops" containing the
- * put_chars() get_chars(), notifier_add() and notifier_del()
- * pointers. The final argument is the output buffer size: we
- * can do any size, so we put PAGE_SIZE here.
- */
- port->cons.vtermno = pdrvdata.next_vtermno;
-
- port->cons.hvc = hvc_alloc(port->cons.vtermno, 0, &hv_ops, PAGE_SIZE);
- if (IS_ERR(port->cons.hvc)) {
- ret = PTR_ERR(port->cons.hvc);
- dev_err(port->dev,
- "error %d allocating hvc for port\n", ret);
- port->cons.hvc = NULL;
- return ret;
- }
- spin_lock_irq(&pdrvdata_lock);
- pdrvdata.next_vtermno++;
- list_add_tail(&port->cons.list, &pdrvdata.consoles);
- spin_unlock_irq(&pdrvdata_lock);
- port->guest_connected = true;
-
- /*
- * Start using the new console output if this is the first
- * console to come up.
- */
- if (early_put_chars)
- early_put_chars = NULL;
-
- /* Notify host of port being opened */
- send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 1);
-
- return 0;
-}
-
-static ssize_t show_port_name(struct device *dev,
- struct device_attribute *attr, char *buffer)
-{
- struct port *port;
-
- port = dev_get_drvdata(dev);
-
- return sprintf(buffer, "%s\n", port->name);
-}
-
-static DEVICE_ATTR(name, S_IRUGO, show_port_name, NULL);
-
-static struct attribute *port_sysfs_entries[] = {
- &dev_attr_name.attr,
- NULL
-};
-
-static struct attribute_group port_attribute_group = {
- .name = NULL, /* put in device directory */
- .attrs = port_sysfs_entries,
-};
-
-static int debugfs_open(struct inode *inode, struct file *filp)
-{
- filp->private_data = inode->i_private;
- return 0;
-}
-
-static ssize_t debugfs_read(struct file *filp, char __user *ubuf,
- size_t count, loff_t *offp)
-{
- struct port *port;
- char *buf;
- ssize_t ret, out_offset, out_count;
-
- out_count = 1024;
- buf = kmalloc(out_count, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- port = filp->private_data;
- out_offset = 0;
- out_offset += snprintf(buf + out_offset, out_count,
- "name: %s\n", port->name ? port->name : "");
- out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "guest_connected: %d\n", port->guest_connected);
- out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "host_connected: %d\n", port->host_connected);
- out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "outvq_full: %d\n", port->outvq_full);
- out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "is_console: %s\n",
- is_console_port(port) ? "yes" : "no");
- out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "console_vtermno: %u\n", port->cons.vtermno);
-
- ret = simple_read_from_buffer(ubuf, count, offp, buf, out_offset);
- kfree(buf);
- return ret;
-}
-
-static const struct file_operations port_debugfs_ops = {
- .owner = THIS_MODULE,
- .open = debugfs_open,
- .read = debugfs_read,
-};
-
-static void set_console_size(struct port *port, u16 rows, u16 cols)
-{
- if (!port || !is_console_port(port))
- return;
-
- port->cons.ws.ws_row = rows;
- port->cons.ws.ws_col = cols;
-}
-
-static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
-{
- struct port_buffer *buf;
- unsigned int nr_added_bufs;
- int ret;
-
- nr_added_bufs = 0;
- do {
- buf = alloc_buf(PAGE_SIZE);
- if (!buf)
- break;
-
- spin_lock_irq(lock);
- ret = add_inbuf(vq, buf);
- if (ret < 0) {
- spin_unlock_irq(lock);
- free_buf(buf);
- break;
- }
- nr_added_bufs++;
- spin_unlock_irq(lock);
- } while (ret > 0);
-
- return nr_added_bufs;
-}
-
-static void send_sigio_to_port(struct port *port)
-{
- if (port->async_queue && port->guest_connected)
- kill_fasync(&port->async_queue, SIGIO, POLL_OUT);
-}
-
-static int add_port(struct ports_device *portdev, u32 id)
-{
- char debugfs_name[16];
- struct port *port;
- struct port_buffer *buf;
- dev_t devt;
- unsigned int nr_added_bufs;
- int err;
-
- port = kmalloc(sizeof(*port), GFP_KERNEL);
- if (!port) {
- err = -ENOMEM;
- goto fail;
- }
- kref_init(&port->kref);
-
- port->portdev = portdev;
- port->id = id;
-
- port->name = NULL;
- port->inbuf = NULL;
- port->cons.hvc = NULL;
- port->async_queue = NULL;
-
- port->cons.ws.ws_row = port->cons.ws.ws_col = 0;
-
- port->host_connected = port->guest_connected = false;
-
- port->outvq_full = false;
-
- port->in_vq = portdev->in_vqs[port->id];
- port->out_vq = portdev->out_vqs[port->id];
-
- port->cdev = cdev_alloc();
- if (!port->cdev) {
- dev_err(&port->portdev->vdev->dev, "Error allocating cdev\n");
- err = -ENOMEM;
- goto free_port;
- }
- port->cdev->ops = &port_fops;
-
- devt = MKDEV(portdev->chr_major, id);
- err = cdev_add(port->cdev, devt, 1);
- if (err < 0) {
- dev_err(&port->portdev->vdev->dev,
- "Error %d adding cdev for port %u\n", err, id);
- goto free_cdev;
- }
- port->dev = device_create(pdrvdata.class, &port->portdev->vdev->dev,
- devt, port, "vport%up%u",
- port->portdev->drv_index, id);
- if (IS_ERR(port->dev)) {
- err = PTR_ERR(port->dev);
- dev_err(&port->portdev->vdev->dev,
- "Error %d creating device for port %u\n",
- err, id);
- goto free_cdev;
- }
-
- spin_lock_init(&port->inbuf_lock);
- spin_lock_init(&port->outvq_lock);
- init_waitqueue_head(&port->waitqueue);
-
- /* Fill the in_vq with buffers so the host can send us data. */
- nr_added_bufs = fill_queue(port->in_vq, &port->inbuf_lock);
- if (!nr_added_bufs) {
- dev_err(port->dev, "Error allocating inbufs\n");
- err = -ENOMEM;
- goto free_device;
- }
-
- /*
- * If we're not using multiport support, this has to be a console port
- */
- if (!use_multiport(port->portdev)) {
- err = init_port_console(port);
- if (err)
- goto free_inbufs;
- }
-
- spin_lock_irq(&portdev->ports_lock);
- list_add_tail(&port->list, &port->portdev->ports);
- spin_unlock_irq(&portdev->ports_lock);
-
- /*
- * Tell the Host we're set so that it can send us various
- * configuration parameters for this port (eg, port name,
- * caching, whether this is a console port, etc.)
- */
- send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1);
-
- if (pdrvdata.debugfs_dir) {
- /*
- * Finally, create the debugfs file that we can use to
- * inspect a port's state at any time
- */
- sprintf(debugfs_name, "vport%up%u",
- port->portdev->drv_index, id);
- port->debugfs_file = debugfs_create_file(debugfs_name, 0444,
- pdrvdata.debugfs_dir,
- port,
- &port_debugfs_ops);
- }
- return 0;
-
-free_inbufs:
- while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
- free_buf(buf);
-free_device:
- device_destroy(pdrvdata.class, port->dev->devt);
-free_cdev:
- cdev_del(port->cdev);
-free_port:
- kfree(port);
-fail:
- /* The host might want to notify management sw about port add failure */
- __send_control_msg(portdev, id, VIRTIO_CONSOLE_PORT_READY, 0);
- return err;
-}
-
-/* No users remain, remove all port-specific data. */
-static void remove_port(struct kref *kref)
-{
- struct port *port;
-
- port = container_of(kref, struct port, kref);
-
- sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
- device_destroy(pdrvdata.class, port->dev->devt);
- cdev_del(port->cdev);
-
- kfree(port->name);
-
- debugfs_remove(port->debugfs_file);
-
- kfree(port);
-}
-
-/*
- * Port got unplugged. Remove port from portdev's list and drop the
- * kref reference. If no userspace has this port opened, it will
- * result in immediate removal the port.
- */
-static void unplug_port(struct port *port)
-{
- struct port_buffer *buf;
-
- spin_lock_irq(&port->portdev->ports_lock);
- list_del(&port->list);
- spin_unlock_irq(&port->portdev->ports_lock);
-
- if (port->guest_connected) {
- port->guest_connected = false;
- port->host_connected = false;
- wake_up_interruptible(&port->waitqueue);
-
- /* Let the app know the port is going down. */
- send_sigio_to_port(port);
- }
-
- if (is_console_port(port)) {
- spin_lock_irq(&pdrvdata_lock);
- list_del(&port->cons.list);
- spin_unlock_irq(&pdrvdata_lock);
-#if 0
- /*
- * hvc_remove() not called as removing one hvc port
- * results in other hvc ports getting frozen.
- *
- * Once this is resolved in hvc, this functionality
- * will be enabled. Till that is done, the -EPIPE
- * return from get_chars() above will help
- * hvc_console.c to clean up on ports we remove here.
- */
- hvc_remove(port->cons.hvc);
-#endif
- }
-
- /* Remove unused data this port might have received. */
- discard_port_data(port);
-
- reclaim_consumed_buffers(port);
-
- /* Remove buffers we queued up for the Host to send us data in. */
- while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
- free_buf(buf);
-
- /*
- * We should just assume the device itself has gone off --
- * else a close on an open port later will try to send out a
- * control message.
- */
- port->portdev = NULL;
-
- /*
- * Locks around here are not necessary - a port can't be
- * opened after we removed the port struct from ports_list
- * above.
- */
- kref_put(&port->kref, remove_port);
-}
-
-/* Any private messages that the Host and Guest want to share */
-static void handle_control_message(struct ports_device *portdev,
- struct port_buffer *buf)
-{
- struct virtio_console_control *cpkt;
- struct port *port;
- size_t name_size;
- int err;
-
- cpkt = (struct virtio_console_control *)(buf->buf + buf->offset);
-
- port = find_port_by_id(portdev, cpkt->id);
- if (!port && cpkt->event != VIRTIO_CONSOLE_PORT_ADD) {
- /* No valid header at start of buffer. Drop it. */
- dev_dbg(&portdev->vdev->dev,
- "Invalid index %u in control packet\n", cpkt->id);
- return;
- }
-
- switch (cpkt->event) {
- case VIRTIO_CONSOLE_PORT_ADD:
- if (port) {
- dev_dbg(&portdev->vdev->dev,
- "Port %u already added\n", port->id);
- send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1);
- break;
- }
- if (cpkt->id >= portdev->config.max_nr_ports) {
- dev_warn(&portdev->vdev->dev,
- "Request for adding port with out-of-bound id %u, max. supported id: %u\n",
- cpkt->id, portdev->config.max_nr_ports - 1);
- break;
- }
- add_port(portdev, cpkt->id);
- break;
- case VIRTIO_CONSOLE_PORT_REMOVE:
- unplug_port(port);
- break;
- case VIRTIO_CONSOLE_CONSOLE_PORT:
- if (!cpkt->value)
- break;
- if (is_console_port(port))
- break;
-
- init_port_console(port);
- /*
- * Could remove the port here in case init fails - but
- * have to notify the host first.
- */
- break;
- case VIRTIO_CONSOLE_RESIZE: {
- struct {
- __u16 rows;
- __u16 cols;
- } size;
-
- if (!is_console_port(port))
- break;
-
- memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt),
- sizeof(size));
- set_console_size(port, size.rows, size.cols);
-
- port->cons.hvc->irq_requested = 1;
- resize_console(port);
- break;
- }
- case VIRTIO_CONSOLE_PORT_OPEN:
- port->host_connected = cpkt->value;
- wake_up_interruptible(&port->waitqueue);
- /*
- * If the host port got closed and the host had any
- * unconsumed buffers, we'll be able to reclaim them
- * now.
- */
- spin_lock_irq(&port->outvq_lock);
- reclaim_consumed_buffers(port);
- spin_unlock_irq(&port->outvq_lock);
-
- /*
- * If the guest is connected, it'll be interested in
- * knowing the host connection state changed.
- */
- send_sigio_to_port(port);
- break;
- case VIRTIO_CONSOLE_PORT_NAME:
- /*
- * Skip the size of the header and the cpkt to get the size
- * of the name that was sent
- */
- name_size = buf->len - buf->offset - sizeof(*cpkt) + 1;
-
- port->name = kmalloc(name_size, GFP_KERNEL);
- if (!port->name) {
- dev_err(port->dev,
- "Not enough space to store port name\n");
- break;
- }
- strncpy(port->name, buf->buf + buf->offset + sizeof(*cpkt),
- name_size - 1);
- port->name[name_size - 1] = 0;
-
- /*
- * Since we only have one sysfs attribute, 'name',
- * create it only if we have a name for the port.
- */
- err = sysfs_create_group(&port->dev->kobj,
- &port_attribute_group);
- if (err) {
- dev_err(port->dev,
- "Error %d creating sysfs device attributes\n",
- err);
- } else {
- /*
- * Generate a udev event so that appropriate
- * symlinks can be created based on udev
- * rules.
- */
- kobject_uevent(&port->dev->kobj, KOBJ_CHANGE);
- }
- break;
- }
-}
-
-static void control_work_handler(struct work_struct *work)
-{
- struct ports_device *portdev;
- struct virtqueue *vq;
- struct port_buffer *buf;
- unsigned int len;
-
- portdev = container_of(work, struct ports_device, control_work);
- vq = portdev->c_ivq;
-
- spin_lock(&portdev->cvq_lock);
- while ((buf = virtqueue_get_buf(vq, &len))) {
- spin_unlock(&portdev->cvq_lock);
-
- buf->len = len;
- buf->offset = 0;
-
- handle_control_message(portdev, buf);
-
- spin_lock(&portdev->cvq_lock);
- if (add_inbuf(portdev->c_ivq, buf) < 0) {
- dev_warn(&portdev->vdev->dev,
- "Error adding buffer to queue\n");
- free_buf(buf);
- }
- }
- spin_unlock(&portdev->cvq_lock);
-}
-
-static void in_intr(struct virtqueue *vq)
-{
- struct port *port;
- unsigned long flags;
-
- port = find_port_by_vq(vq->vdev->priv, vq);
- if (!port)
- return;
-
- spin_lock_irqsave(&port->inbuf_lock, flags);
- if (!port->inbuf)
- port->inbuf = get_inbuf(port);
-
- /*
- * Don't queue up data when port is closed. This condition
- * can be reached when a console port is not yet connected (no
- * tty is spawned) and the host sends out data to console
- * ports. For generic serial ports, the host won't
- * (shouldn't) send data till the guest is connected.
- */
- if (!port->guest_connected)
- discard_port_data(port);
-
- spin_unlock_irqrestore(&port->inbuf_lock, flags);
-
- wake_up_interruptible(&port->waitqueue);
-
- /* Send a SIGIO indicating new data in case the process asked for it */
- send_sigio_to_port(port);
-
- if (is_console_port(port) && hvc_poll(port->cons.hvc))
- hvc_kick();
-}
-
-static void control_intr(struct virtqueue *vq)
-{
- struct ports_device *portdev;
-
- portdev = vq->vdev->priv;
- schedule_work(&portdev->control_work);
-}
-
-static void config_intr(struct virtio_device *vdev)
-{
- struct ports_device *portdev;
-
- portdev = vdev->priv;
-
- if (!use_multiport(portdev)) {
- struct port *port;
- u16 rows, cols;
-
- vdev->config->get(vdev,
- offsetof(struct virtio_console_config, cols),
- &cols, sizeof(u16));
- vdev->config->get(vdev,
- offsetof(struct virtio_console_config, rows),
- &rows, sizeof(u16));
-
- port = find_port_by_id(portdev, 0);
- set_console_size(port, rows, cols);
-
- /*
- * We'll use this way of resizing only for legacy
- * support. For newer userspace
- * (VIRTIO_CONSOLE_F_MULTPORT+), use control messages
- * to indicate console size changes so that it can be
- * done per-port.
- */
- resize_console(port);
- }
-}
-
-static int init_vqs(struct ports_device *portdev)
-{
- vq_callback_t **io_callbacks;
- char **io_names;
- struct virtqueue **vqs;
- u32 i, j, nr_ports, nr_queues;
- int err;
-
- nr_ports = portdev->config.max_nr_ports;
- nr_queues = use_multiport(portdev) ? (nr_ports + 1) * 2 : 2;
-
- vqs = kmalloc(nr_queues * sizeof(struct virtqueue *), GFP_KERNEL);
- io_callbacks = kmalloc(nr_queues * sizeof(vq_callback_t *), GFP_KERNEL);
- io_names = kmalloc(nr_queues * sizeof(char *), GFP_KERNEL);
- portdev->in_vqs = kmalloc(nr_ports * sizeof(struct virtqueue *),
- GFP_KERNEL);
- portdev->out_vqs = kmalloc(nr_ports * sizeof(struct virtqueue *),
- GFP_KERNEL);
- if (!vqs || !io_callbacks || !io_names || !portdev->in_vqs ||
- !portdev->out_vqs) {
- err = -ENOMEM;
- goto free;
- }
-
- /*
- * For backward compat (newer host but older guest), the host
- * spawns a console port first and also inits the vqs for port
- * 0 before others.
- */
- j = 0;
- io_callbacks[j] = in_intr;
- io_callbacks[j + 1] = NULL;
- io_names[j] = "input";
- io_names[j + 1] = "output";
- j += 2;
-
- if (use_multiport(portdev)) {
- io_callbacks[j] = control_intr;
- io_callbacks[j + 1] = NULL;
- io_names[j] = "control-i";
- io_names[j + 1] = "control-o";
-
- for (i = 1; i < nr_ports; i++) {
- j += 2;
- io_callbacks[j] = in_intr;
- io_callbacks[j + 1] = NULL;
- io_names[j] = "input";
- io_names[j + 1] = "output";
- }
- }
- /* Find the queues. */
- err = portdev->vdev->config->find_vqs(portdev->vdev, nr_queues, vqs,
- io_callbacks,
- (const char **)io_names);
- if (err)
- goto free;
-
- j = 0;
- portdev->in_vqs[0] = vqs[0];
- portdev->out_vqs[0] = vqs[1];
- j += 2;
- if (use_multiport(portdev)) {
- portdev->c_ivq = vqs[j];
- portdev->c_ovq = vqs[j + 1];
-
- for (i = 1; i < nr_ports; i++) {
- j += 2;
- portdev->in_vqs[i] = vqs[j];
- portdev->out_vqs[i] = vqs[j + 1];
- }
- }
- kfree(io_names);
- kfree(io_callbacks);
- kfree(vqs);
-
- return 0;
-
-free:
- kfree(portdev->out_vqs);
- kfree(portdev->in_vqs);
- kfree(io_names);
- kfree(io_callbacks);
- kfree(vqs);
-
- return err;
-}
-
-static const struct file_operations portdev_fops = {
- .owner = THIS_MODULE,
-};
-
-/*
- * Once we're further in boot, we get probed like any other virtio
- * device.
- *
- * If the host also supports multiple console ports, we check the
- * config space to see how many ports the host has spawned. We
- * initialize each port found.
- */
-static int __devinit virtcons_probe(struct virtio_device *vdev)
-{
- struct ports_device *portdev;
- int err;
- bool multiport;
-
- portdev = kmalloc(sizeof(*portdev), GFP_KERNEL);
- if (!portdev) {
- err = -ENOMEM;
- goto fail;
- }
-
- /* Attach this portdev to this virtio_device, and vice-versa. */
- portdev->vdev = vdev;
- vdev->priv = portdev;
-
- spin_lock_irq(&pdrvdata_lock);
- portdev->drv_index = pdrvdata.index++;
- spin_unlock_irq(&pdrvdata_lock);
-
- portdev->chr_major = register_chrdev(0, "virtio-portsdev",
- &portdev_fops);
- if (portdev->chr_major < 0) {
- dev_err(&vdev->dev,
- "Error %d registering chrdev for device %u\n",
- portdev->chr_major, portdev->drv_index);
- err = portdev->chr_major;
- goto free;
- }
-
- multiport = false;
- portdev->config.max_nr_ports = 1;
- if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
- multiport = true;
- vdev->features[0] |= 1 << VIRTIO_CONSOLE_F_MULTIPORT;
-
- vdev->config->get(vdev, offsetof(struct virtio_console_config,
- max_nr_ports),
- &portdev->config.max_nr_ports,
- sizeof(portdev->config.max_nr_ports));
- }
-
- /* Let the Host know we support multiple ports.*/
- vdev->config->finalize_features(vdev);
-
- err = init_vqs(portdev);
- if (err < 0) {
- dev_err(&vdev->dev, "Error %d initializing vqs\n", err);
- goto free_chrdev;
- }
-
- spin_lock_init(&portdev->ports_lock);
- INIT_LIST_HEAD(&portdev->ports);
-
- if (multiport) {
- unsigned int nr_added_bufs;
-
- spin_lock_init(&portdev->cvq_lock);
- INIT_WORK(&portdev->control_work, &control_work_handler);
-
- nr_added_bufs = fill_queue(portdev->c_ivq, &portdev->cvq_lock);
- if (!nr_added_bufs) {
- dev_err(&vdev->dev,
- "Error allocating buffers for control queue\n");
- err = -ENOMEM;
- goto free_vqs;
- }
- } else {
- /*
- * For backward compatibility: Create a console port
- * if we're running on older host.
- */
- add_port(portdev, 0);
- }
-
- spin_lock_irq(&pdrvdata_lock);
- list_add_tail(&portdev->list, &pdrvdata.portdevs);
- spin_unlock_irq(&pdrvdata_lock);
-
- __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
- VIRTIO_CONSOLE_DEVICE_READY, 1);
- return 0;
-
-free_vqs:
- /* The host might want to notify mgmt sw about device add failure */
- __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
- VIRTIO_CONSOLE_DEVICE_READY, 0);
- vdev->config->del_vqs(vdev);
- kfree(portdev->in_vqs);
- kfree(portdev->out_vqs);
-free_chrdev:
- unregister_chrdev(portdev->chr_major, "virtio-portsdev");
-free:
- kfree(portdev);
-fail:
- return err;
-}
-
-static void virtcons_remove(struct virtio_device *vdev)
-{
- struct ports_device *portdev;
- struct port *port, *port2;
-
- portdev = vdev->priv;
-
- spin_lock_irq(&pdrvdata_lock);
- list_del(&portdev->list);
- spin_unlock_irq(&pdrvdata_lock);
-
- /* Disable interrupts for vqs */
- vdev->config->reset(vdev);
- /* Finish up work that's lined up */
- cancel_work_sync(&portdev->control_work);
-
- list_for_each_entry_safe(port, port2, &portdev->ports, list)
- unplug_port(port);
-
- unregister_chrdev(portdev->chr_major, "virtio-portsdev");
-
- /*
- * When yanking out a device, we immediately lose the
- * (device-side) queues. So there's no point in keeping the
- * guest side around till we drop our final reference. This
- * also means that any ports which are in an open state will
- * have to just stop using the port, as the vqs are going
- * away.
- */
- if (use_multiport(portdev)) {
- struct port_buffer *buf;
- unsigned int len;
-
- while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
- free_buf(buf);
-
- while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
- free_buf(buf);
- }
-
- vdev->config->del_vqs(vdev);
- kfree(portdev->in_vqs);
- kfree(portdev->out_vqs);
-
- kfree(portdev);
-}
-
-static struct virtio_device_id id_table[] = {
- { VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
- { 0 },
-};
-
-static unsigned int features[] = {
- VIRTIO_CONSOLE_F_SIZE,
- VIRTIO_CONSOLE_F_MULTIPORT,
-};
-
-static struct virtio_driver virtio_console = {
- .feature_table = features,
- .feature_table_size = ARRAY_SIZE(features),
- .driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
- .id_table = id_table,
- .probe = virtcons_probe,
- .remove = virtcons_remove,
- .config_changed = config_intr,
-};
-
-static int __init init(void)
-{
- int err;
-
- pdrvdata.class = class_create(THIS_MODULE, "virtio-ports");
- if (IS_ERR(pdrvdata.class)) {
- err = PTR_ERR(pdrvdata.class);
- pr_err("Error %d creating virtio-ports class\n", err);
- return err;
- }
-
- pdrvdata.debugfs_dir = debugfs_create_dir("virtio-ports", NULL);
- if (!pdrvdata.debugfs_dir) {
- pr_warning("Error %ld creating debugfs dir for virtio-ports\n",
- PTR_ERR(pdrvdata.debugfs_dir));
- }
- INIT_LIST_HEAD(&pdrvdata.consoles);
- INIT_LIST_HEAD(&pdrvdata.portdevs);
-
- return register_virtio_driver(&virtio_console);
-}
-
-static void __exit fini(void)
-{
- unregister_virtio_driver(&virtio_console);
-
- class_destroy(pdrvdata.class);
- if (pdrvdata.debugfs_dir)
- debugfs_remove_recursive(pdrvdata.debugfs_dir);
-}
-module_init(init);
-module_exit(fini);
-
-MODULE_DEVICE_TABLE(virtio, id_table);
-MODULE_DESCRIPTION("Virtio console driver");
-MODULE_LICENSE("GPL");
gsm->initiator = c->initiator;
gsm->mru = c->mru;
+ gsm->mtu = c->mtu;
gsm->encoding = c->encapsulation;
gsm->adaption = c->adaption;
gsm->n2 = c->n2;
static void receive_chars(struct m68k_serial *info, unsigned short rx)
{
- struct tty_struct *tty = info->port.tty;
+ struct tty_struct *tty = info->tty;
m68328_uart *uart = &uart_addr[info->line];
unsigned char ch, flag;
goto clear_and_return;
}
- if((info->xmit_cnt <= 0) || info->port.tty->stopped) {
+ if((info->xmit_cnt <= 0) || info->tty->stopped) {
/* That's peculiar... TX ints off */
uart->ustcnt &= ~USTCNT_TX_INTR_MASK;
goto clear_and_return;
struct m68k_serial *info = container_of(work, struct m68k_serial, tqueue);
struct tty_struct *tty;
- tty = info->port.tty;
+ tty = info->tty;
if (!tty)
return;
#if 0
struct m68k_serial *info = container_of(work, struct m68k_serial, tqueue_hangup);
struct tty_struct *tty;
- tty = info->port.tty;
+ tty = info->tty;
if (!tty)
return;
uart->ustcnt = USTCNT_UEN | USTCNT_RXEN | USTCNT_RX_INTR_MASK;
#endif
- if (info->port.tty)
- clear_bit(TTY_IO_ERROR, &info->port.tty->flags);
+ if (info->tty)
+ clear_bit(TTY_IO_ERROR, &info->tty->flags);
info->xmit_cnt = info->xmit_head = info->xmit_tail = 0;
/*
info->xmit_buf = 0;
}
- if (info->port.tty)
- set_bit(TTY_IO_ERROR, &info->port.tty->flags);
+ if (info->tty)
+ set_bit(TTY_IO_ERROR, &info->tty->flags);
info->flags &= ~S_INITIALIZED;
local_irq_restore(flags);
unsigned cflag;
int i;
- if (!info->port.tty || !info->port.tty->termios)
+ if (!info->tty || !info->tty->termios)
return;
- cflag = info->port.tty->termios->c_cflag;
+ cflag = info->tty->termios->c_cflag;
if (!(port = info->port))
return;
static int rs_ioctl(struct tty_struct *tty, struct file * file,
unsigned int cmd, unsigned long arg)
{
- int error;
struct m68k_serial * info = (struct m68k_serial *)tty->driver_data;
int retval;
tty_ldisc_flush(tty);
tty->closing = 0;
info->event = 0;
- info->port.tty = NULL;
+ info->tty = NULL;
#warning "This is not and has never been valid so fix it"
#if 0
if (tty->ldisc.num != ldiscs[N_TTY].num) {
info->event = 0;
info->count = 0;
info->flags &= ~S_NORMAL_ACTIVE;
- info->port.tty = NULL;
+ info->tty = NULL;
wake_up_interruptible(&info->open_wait);
}
info->count++;
tty->driver_data = info;
- info->port.tty = tty;
+ info->tty = tty;
/*
* Start up serial port
info = &m68k_soft[i];
info->magic = SERIAL_MAGIC;
info->port = (int) &uart_addr[i];
- info->port.tty = NULL;
+ info->tty = NULL;
info->irq = uart_irqs[i];
info->custom_divisor = 16;
info->close_delay = 50;
/* .read_proc = rs_360_read_proc, */
.tiocmget = rs_360_tiocmget,
.tiocmset = rs_360_tiocmset,
+ .get_icount = rs_360_get_icount,
};
static int __init rs_360_init(void)
{
struct bfin_serial_port *uart = dev_id;
- spin_lock(&uart->port.lock);
while (UART_GET_LSR(uart) & DR)
bfin_serial_rx_chars(uart);
- spin_unlock(&uart->port.lock);
return IRQ_HANDLED;
}
{
int x_pos, pos;
- dma_disable_irq(uart->tx_dma_channel);
- dma_disable_irq(uart->rx_dma_channel);
- spin_lock_bh(&uart->port.lock);
+ dma_disable_irq_nosync(uart->rx_dma_channel);
+ spin_lock_bh(&uart->rx_lock);
/* 2D DMA RX buffer ring is used. Because curr_y_count and
* curr_x_count can't be read as an atomic operation,
uart->rx_dma_buf.tail = uart->rx_dma_buf.head;
}
- spin_unlock_bh(&uart->port.lock);
- dma_enable_irq(uart->tx_dma_channel);
+ spin_unlock_bh(&uart->rx_lock);
dma_enable_irq(uart->rx_dma_channel);
mod_timer(&(uart->rx_dma_timer), jiffies + DMA_RX_FLUSH_JIFFIES);
unsigned short irqstat;
int x_pos, pos;
- spin_lock(&uart->port.lock);
+ spin_lock(&uart->rx_lock);
irqstat = get_dma_curr_irqstat(uart->rx_dma_channel);
clear_dma_irqstat(uart->rx_dma_channel);
uart->rx_dma_buf.tail = uart->rx_dma_buf.head;
}
- spin_unlock(&uart->port.lock);
+ spin_unlock(&uart->rx_lock);
return IRQ_HANDLED;
}
}
#ifdef CONFIG_SERIAL_BFIN_DMA
+ spin_lock_init(&uart->rx_lock);
uart->tx_done = 1;
uart->tx_count = 0;
s->rts = 0;
sprintf(b, "max3100-%d", s->minor);
- s->workqueue = create_freezeable_workqueue(b);
+ s->workqueue = create_freezable_workqueue(b);
if (!s->workqueue) {
dev_warn(&s->spi->dev, "cannot create workqueue\n");
return -EBUSY;
struct max3107_port *s = container_of(port, struct max3107_port, port);
/* Initialize work queue */
- s->workqueue = create_freezeable_workqueue("max3107");
+ s->workqueue = create_freezable_workqueue("max3107");
if (!s->workqueue) {
dev_err(&s->spi->dev, "Workqueue creation failed\n");
return -EBUSY;
PCMCIA_PFC_DEVICE_PROD_ID12(1, "Xircom", "CreditCard Ethernet+Modem II", 0x2e3ee845, 0xeca401bf),
PCMCIA_PFC_DEVICE_MANF_CARD(1, 0x0032, 0x0e01),
PCMCIA_PFC_DEVICE_MANF_CARD(1, 0x0032, 0x0a05),
+ PCMCIA_PFC_DEVICE_MANF_CARD(1, 0x0032, 0x0b05),
PCMCIA_PFC_DEVICE_MANF_CARD(1, 0x0032, 0x1101),
PCMCIA_MFC_DEVICE_MANF_CARD(0, 0x0104, 0x0070),
PCMCIA_MFC_DEVICE_MANF_CARD(1, 0x0101, 0x0562),
unsigned int alt_use;
bool active;
bool need_reinject;
+ bool reinjecting;
};
static void sysrq_reinject_alt_sysrq(struct work_struct *work)
unsigned int alt_code = sysrq->alt_use;
if (sysrq->need_reinject) {
+ /* we do not want the assignment to be reordered */
+ sysrq->reinjecting = true;
+ mb();
+
/* Simulate press and release of Alt + SysRq */
input_inject_event(handle, EV_KEY, alt_code, 1);
input_inject_event(handle, EV_KEY, KEY_SYSRQ, 1);
input_inject_event(handle, EV_KEY, KEY_SYSRQ, 0);
input_inject_event(handle, EV_KEY, alt_code, 0);
input_inject_event(handle, EV_SYN, SYN_REPORT, 1);
+
+ mb();
+ sysrq->reinjecting = false;
}
}
bool was_active = sysrq->active;
bool suppress;
+ /*
+ * Do not filter anything if we are in the process of re-injecting
+ * Alt+SysRq combination.
+ */
+ if (sysrq->reinjecting)
+ return false;
+
switch (type) {
case EV_SYN:
sysrq->alt_use = sysrq->alt;
/*
* If nothing else will be pressed we'll need
- * to * re-inject Alt-SysRq keysroke.
+ * to re-inject Alt-SysRq keysroke.
*/
sysrq->need_reinject = true;
}
{ NOKIA_PCSUITE_ACM_INFO(0x0154), }, /* Nokia 5800 XpressMusic */
{ NOKIA_PCSUITE_ACM_INFO(0x04ce), }, /* Nokia E90 */
{ NOKIA_PCSUITE_ACM_INFO(0x01d4), }, /* Nokia E55 */
+ { NOKIA_PCSUITE_ACM_INFO(0x0302), }, /* Nokia N8 */
{ SAMSUNG_PCSUITE_ACM_INFO(0x6651), }, /* Samsung GTi8510 (INNOV8) */
/* NOTE: non-Nokia COMM/ACM/0xff is likely MSFT RNDIS... NOT a modem! */
dev_dbg(&rhdev->dev, "usb %s%s\n",
(msg.event & PM_EVENT_AUTO ? "auto-" : ""), "resume");
- clear_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags);
if (!hcd->driver->bus_resume)
return -ENOENT;
if (hcd->state == HC_STATE_RUNNING)
hcd->state = HC_STATE_RESUMING;
status = hcd->driver->bus_resume(hcd);
+ clear_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags);
if (status == 0) {
/* TRSMRCY = 10 msec */
msleep(10);
mutex_lock(&usb_address0_mutex);
- if (!udev->config && oldspeed == USB_SPEED_SUPER) {
- /* Don't reset USB 3.0 devices during an initial setup */
- usb_set_device_state(udev, USB_STATE_DEFAULT);
- } else {
- /* Reset the device; full speed may morph to high speed */
- /* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */
- retval = hub_port_reset(hub, port1, udev, delay);
- if (retval < 0) /* error or disconnect */
- goto fail;
- /* success, speed is known */
- }
+ /* Reset the device; full speed may morph to high speed */
+ /* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */
+ retval = hub_port_reset(hub, port1, udev, delay);
+ if (retval < 0) /* error or disconnect */
+ goto fail;
+ /* success, speed is known */
+
retval = -ENODEV;
if (oldspeed != USB_SPEED_UNKNOWN && oldspeed != udev->speed) {
udev->ttport = hdev->ttport;
} else if (udev->speed != USB_SPEED_HIGH
&& hdev->speed == USB_SPEED_HIGH) {
+ if (!hub->tt.hub) {
+ dev_err(&udev->dev, "parent hub has no TT\n");
+ retval = -EINVAL;
+ goto fail;
+ }
udev->tt = &hub->tt;
udev->ttport = port1;
}
{ USB_DEVICE(0x04b4, 0x0526), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
+ /* Samsung Android phone modem - ID conflict with SPH-I500 */
+ { USB_DEVICE(0x04e8, 0x6601), .driver_info =
+ USB_QUIRK_CONFIG_INTF_STRINGS },
+
/* Roland SC-8820 */
{ USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME },
/* M-Systems Flash Disk Pioneers */
{ USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Keytouch QWERTY Panel keyboard */
+ { USB_DEVICE(0x0926, 0x3333), .driver_info =
+ USB_QUIRK_CONFIG_INTF_STRINGS },
+
/* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */
{ USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF },
ci13xxx_udc core.
This driver depends on OTG driver for PHY initialization,
clock management, powering up VBUS, and power management.
+ This driver is not supported on boards like trout which
+ has an external PHY.
Say "y" to link the driver statically, or "m" to build a
dynamically linked module called "ci13xxx_msm" and force all
#include <linux/usb/ch9.h>
#include <linux/usb/gadget.h>
+#include <linux/usb/composite.h>
#include "gadget_chips.h"
return ERR_PTR(-ENOMEM);
common->free_storage_on_release = 1;
} else {
- memset(common, 0, sizeof common);
+ memset(common, 0, sizeof *common);
common->free_storage_on_release = 0;
}
if (unlikely(!skb))
break;
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, 0,
- req->actual);
- page = NULL;
- if (req->actual < req->length) { /* Last fragment */
+ if (skb->len == 0) { /* First fragment */
skb->protocol = htons(ETH_P_PHONET);
skb_reset_mac_header(skb);
- pskb_pull(skb, 1);
+ /* Can't use pskb_pull() on page in IRQ */
+ memcpy(skb_put(skb, 1), page_address(page), 1);
+ }
+
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+ skb->len == 0, req->actual);
+ page = NULL;
+
+ if (req->actual < req->length) { /* Last fragment */
skb->dev = dev;
dev->stats.rx_packets++;
dev->stats.rx_bytes += skb->len;
break;
case R8A66597_BULK:
/* isochronous pipes may be used as bulk pipes */
- if (info->pipe > R8A66597_BASE_PIPENUM_BULK)
+ if (info->pipe >= R8A66597_BASE_PIPENUM_BULK)
bufnum = info->pipe - R8A66597_BASE_PIPENUM_BULK;
else
bufnum = info->pipe - R8A66597_BASE_PIPENUM_ISOC;
Qualcomm chipsets. Root Hub has inbuilt TT.
This driver depends on OTG driver for PHY initialization,
clock management, powering up VBUS, and power management.
+ This driver is not supported on boards like trout which
+ has an external PHY.
config USB_EHCI_HCD_PPC_OF
bool "EHCI support for PPC USB controller on OF platform bus"
* mark HW unaccessible. The PM and USB cores make sure that
* the root hub is either suspended or stopped.
*/
- spin_lock_irqsave(&ehci->lock, flags);
ehci_prepare_ports_for_controller_suspend(ehci, device_may_wakeup(dev));
+ spin_lock_irqsave(&ehci->lock, flags);
ehci_writel(ehci, 0, &ehci->regs->intr_enable);
(void)ehci_readl(ehci, &ehci->regs->intr_enable);
{
int port;
u32 temp;
+ unsigned long flags;
/* If remote wakeup is enabled for the root hub but disabled
* for the controller, we must adjust all the port wakeup flags
if (!ehci_to_hcd(ehci)->self.root_hub->do_remote_wakeup || do_wakeup)
return;
+ spin_lock_irqsave(&ehci->lock, flags);
+
/* clear phy low-power mode before changing wakeup flags */
if (ehci->has_hostpc) {
port = HCS_N_PORTS(ehci->hcs_params);
temp = ehci_readl(ehci, hostpc_reg);
ehci_writel(ehci, temp & ~HOSTPC_PHCD, hostpc_reg);
}
+ spin_unlock_irqrestore(&ehci->lock, flags);
msleep(5);
+ spin_lock_irqsave(&ehci->lock, flags);
}
port = HCS_N_PORTS(ehci->hcs_params);
/* Does the root hub have a port wakeup pending? */
if (!suspending && (ehci_readl(ehci, &ehci->regs->status) & STS_PCD))
usb_hcd_resume_root_hub(ehci_to_hcd(ehci));
+
+ spin_unlock_irqrestore(&ehci->lock, flags);
}
static int ehci_bus_suspend (struct usb_hcd *hcd)
hcd = usb_create_hcd(&ehci_omap_hc_driver, &pdev->dev,
dev_name(&pdev->dev));
if (!hcd) {
- dev_dbg(&pdev->dev, "failed to create hcd with err %d\n", ret);
+ dev_err(&pdev->dev, "failed to create hcd with err %d\n", ret);
ret = -ENOMEM;
goto err_create_hcd;
}
ret = omap_start_ehc(omap, hcd);
if (ret) {
- dev_dbg(&pdev->dev, "failed to start ehci\n");
+ dev_err(&pdev->dev, "failed to start ehci with err %d\n", ret);
goto err_start;
}
ret = usb_add_hcd(hcd, irq, IRQF_DISABLED | IRQF_SHARED);
if (ret) {
- dev_dbg(&pdev->dev, "failed to add hcd with err %d\n", ret);
+ dev_err(&pdev->dev, "failed to add hcd with err %d\n", ret);
goto err_add_hcd;
}
* mark HW unaccessible. The PM and USB cores make sure that
* the root hub is either suspended or stopped.
*/
- spin_lock_irqsave (&ehci->lock, flags);
ehci_prepare_ports_for_controller_suspend(ehci, do_wakeup);
+ spin_lock_irqsave (&ehci->lock, flags);
ehci_writel(ehci, 0, &ehci->regs->intr_enable);
(void)ehci_readl(ehci, &ehci->regs->intr_enable);
#include <linux/of.h>
#include <linux/of_platform.h>
+#include <linux/of_address.h>
/**
* ehci_xilinx_of_setup - Initialize the device for ehci_reset()
DBG("dev %d ep%d maxpacket %d\n",
udev->devnum, epnum, ep->maxpacket);
retval = -EINVAL;
+ kfree(ep);
goto fail;
}
}
}
-void xhci_print_ir_set(struct xhci_hcd *xhci, struct xhci_intr_reg *ir_set, int set_num)
+void xhci_print_ir_set(struct xhci_hcd *xhci, int set_num)
{
- void *addr;
+ struct xhci_intr_reg __iomem *ir_set = &xhci->run_regs->ir_set[set_num];
+ void __iomem *addr;
u32 temp;
u64 temp_64;
}
}
-void xhci_dbg_slot_ctx(struct xhci_hcd *xhci, struct xhci_container_ctx *ctx)
+static void xhci_dbg_slot_ctx(struct xhci_hcd *xhci, struct xhci_container_ctx *ctx)
{
/* Fields are 32 bits wide, DMA addresses are in bytes */
int field_size = 32 / 8;
dbg_rsvd64(xhci, (u64 *)slot_ctx, dma);
}
-void xhci_dbg_ep_ctx(struct xhci_hcd *xhci,
+static void xhci_dbg_ep_ctx(struct xhci_hcd *xhci,
struct xhci_container_ctx *ctx,
unsigned int last_ep)
{
/***************** Streams structures manipulation *************************/
-void xhci_free_stream_ctx(struct xhci_hcd *xhci,
+static void xhci_free_stream_ctx(struct xhci_hcd *xhci,
unsigned int num_stream_ctxs,
struct xhci_stream_ctx *stream_ctx, dma_addr_t dma)
{
* The stream context array must be a power of 2, and can be as small as
* 64 bytes or as large as 1MB.
*/
-struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci,
+static struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci,
unsigned int num_stream_ctxs, dma_addr_t *dma,
gfp_t mem_flags)
{
val &= DBOFF_MASK;
xhci_dbg(xhci, "// Doorbell array is located at offset 0x%x"
" from cap regs base addr\n", val);
- xhci->dba = (void *) xhci->cap_regs + val;
+ xhci->dba = (void __iomem *) xhci->cap_regs + val;
xhci_dbg_regs(xhci);
xhci_print_run_regs(xhci);
/* Set ir_set to interrupt register set 0 */
- xhci->ir_set = (void *) xhci->run_regs->ir_set;
+ xhci->ir_set = &xhci->run_regs->ir_set[0];
/*
* Event ring setup: Allocate a normal ring, but also setup
/* Set the event ring dequeue address */
xhci_set_hc_event_deq(xhci);
xhci_dbg(xhci, "Wrote ERST address to ir_set 0.\n");
- xhci_print_ir_set(xhci, xhci->ir_set, 0);
+ xhci_print_ir_set(xhci, 0);
/*
* XXX: Might need to set the Interrupter Moderation Register to
state->new_deq_seg = find_trb_seg(cur_td->start_seg,
dev->eps[ep_index].stopped_trb,
&state->new_cycle_state);
- if (!state->new_deq_seg)
- BUG();
+ if (!state->new_deq_seg) {
+ WARN_ON(1);
+ return;
+ }
+
/* Dig out the cycle state saved by the xHC during the stop ep cmd */
xhci_dbg(xhci, "Finding endpoint context\n");
ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index);
state->new_deq_seg = find_trb_seg(state->new_deq_seg,
state->new_deq_ptr,
&state->new_cycle_state);
- if (!state->new_deq_seg)
- BUG();
+ if (!state->new_deq_seg) {
+ WARN_ON(1);
+ return;
+ }
trb = &state->new_deq_ptr->generic;
if ((trb->field[3] & TRB_TYPE_BITMASK) == TRB_TYPE(TRB_LINK) &&
/* Scatter gather list entries may cross 64KB boundaries */
running_total = TRB_MAX_BUFF_SIZE -
- (sg_dma_address(sg) & ((1 << TRB_MAX_BUFF_SHIFT) - 1));
+ (sg_dma_address(sg) & (TRB_MAX_BUFF_SIZE - 1));
+ running_total &= TRB_MAX_BUFF_SIZE - 1;
if (running_total != 0)
num_trbs++;
/* How many more 64KB chunks to transfer, how many more TRBs? */
- while (running_total < sg_dma_len(sg)) {
+ while (running_total < sg_dma_len(sg) && running_total < temp) {
num_trbs++;
running_total += TRB_MAX_BUFF_SIZE;
}
static void check_trb_math(struct urb *urb, int num_trbs, int running_total)
{
if (num_trbs != 0)
- dev_dbg(&urb->dev->dev, "%s - ep %#x - Miscalculated number of "
+ dev_err(&urb->dev->dev, "%s - ep %#x - Miscalculated number of "
"TRBs, %d left\n", __func__,
urb->ep->desc.bEndpointAddress, num_trbs);
if (running_total != urb->transfer_buffer_length)
- dev_dbg(&urb->dev->dev, "%s - ep %#x - Miscalculated tx length, "
+ dev_err(&urb->dev->dev, "%s - ep %#x - Miscalculated tx length, "
"queued %#x (%d), asked for %#x (%d)\n",
__func__,
urb->ep->desc.bEndpointAddress,
sg = urb->sg;
addr = (u64) sg_dma_address(sg);
this_sg_len = sg_dma_len(sg);
- trb_buff_len = TRB_MAX_BUFF_SIZE -
- (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1));
+ trb_buff_len = TRB_MAX_BUFF_SIZE - (addr & (TRB_MAX_BUFF_SIZE - 1));
trb_buff_len = min_t(int, trb_buff_len, this_sg_len);
if (trb_buff_len > urb->transfer_buffer_length)
trb_buff_len = urb->transfer_buffer_length;
(unsigned int) (addr + TRB_MAX_BUFF_SIZE) & ~(TRB_MAX_BUFF_SIZE - 1),
(unsigned int) addr + trb_buff_len);
if (TRB_MAX_BUFF_SIZE -
- (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1)) < trb_buff_len) {
+ (addr & (TRB_MAX_BUFF_SIZE - 1)) < trb_buff_len) {
xhci_warn(xhci, "WARN: sg dma xfer crosses 64KB boundaries!\n");
xhci_dbg(xhci, "Next boundary at %#x, end dma = %#x\n",
(unsigned int) (addr + TRB_MAX_BUFF_SIZE) & ~(TRB_MAX_BUFF_SIZE - 1),
}
trb_buff_len = TRB_MAX_BUFF_SIZE -
- (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1));
+ (addr & (TRB_MAX_BUFF_SIZE - 1));
trb_buff_len = min_t(int, trb_buff_len, this_sg_len);
if (running_total + trb_buff_len > urb->transfer_buffer_length)
trb_buff_len =
num_trbs = 0;
/* How much data is (potentially) left before the 64KB boundary? */
running_total = TRB_MAX_BUFF_SIZE -
- (urb->transfer_dma & ((1 << TRB_MAX_BUFF_SHIFT) - 1));
+ (urb->transfer_dma & (TRB_MAX_BUFF_SIZE - 1));
+ running_total &= TRB_MAX_BUFF_SIZE - 1;
/* If there's some data on this 64KB chunk, or we have to send a
* zero-length transfer, we need at least one TRB
/* How much data is in the first TRB? */
addr = (u64) urb->transfer_dma;
trb_buff_len = TRB_MAX_BUFF_SIZE -
- (urb->transfer_dma & ((1 << TRB_MAX_BUFF_SHIFT) - 1));
- if (urb->transfer_buffer_length < trb_buff_len)
+ (urb->transfer_dma & (TRB_MAX_BUFF_SIZE - 1));
+ if (trb_buff_len > urb->transfer_buffer_length)
trb_buff_len = urb->transfer_buffer_length;
first_trb = true;
addr = (u64) (urb->transfer_dma + urb->iso_frame_desc[i].offset);
td_len = urb->iso_frame_desc[i].length;
- running_total = TRB_MAX_BUFF_SIZE -
- (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1));
+ running_total = TRB_MAX_BUFF_SIZE - (addr & (TRB_MAX_BUFF_SIZE - 1));
+ running_total &= TRB_MAX_BUFF_SIZE - 1;
if (running_total != 0)
num_trbs++;
/*
* Set the run bit and wait for the host to be running.
*/
-int xhci_start(struct xhci_hcd *xhci)
+static int xhci_start(struct xhci_hcd *xhci)
{
u32 temp;
int ret;
#ifdef CONFIG_USB_XHCI_HCD_DEBUGGING
-void xhci_event_ring_work(unsigned long arg)
+static void xhci_event_ring_work(unsigned long arg)
{
unsigned long flags;
int temp;
xhci->ir_set, (unsigned int) ER_IRQ_ENABLE(temp));
xhci_writel(xhci, ER_IRQ_ENABLE(temp),
&xhci->ir_set->irq_pending);
- xhci_print_ir_set(xhci, xhci->ir_set, 0);
+ xhci_print_ir_set(xhci, 0);
if (NUM_TEST_NOOPS > 0)
doorbell = xhci_setup_one_noop(xhci);
temp = xhci_readl(xhci, &xhci->ir_set->irq_pending);
xhci_writel(xhci, ER_IRQ_DISABLE(temp),
&xhci->ir_set->irq_pending);
- xhci_print_ir_set(xhci, xhci->ir_set, 0);
+ xhci_print_ir_set(xhci, 0);
xhci_dbg(xhci, "cleaning up memory\n");
xhci_mem_cleanup(xhci);
temp = xhci_readl(xhci, &xhci->ir_set->irq_pending);
xhci_writel(xhci, ER_IRQ_DISABLE(temp),
&xhci->ir_set->irq_pending);
- xhci_print_ir_set(xhci, xhci->ir_set, 0);
+ xhci_print_ir_set(xhci, 0);
xhci_dbg(xhci, "cleaning up memory\n");
xhci_mem_cleanup(xhci);
/* Returns 1 if the arguments are OK;
* returns 0 this is a root hub; returns -EINVAL for NULL pointers.
*/
-int xhci_check_args(struct usb_hcd *hcd, struct usb_device *udev,
+static int xhci_check_args(struct usb_hcd *hcd, struct usb_device *udev,
struct usb_host_endpoint *ep, int check_ep, bool check_virt_dev,
const char *func) {
struct xhci_hcd *xhci;
xhci_dbg_ctx(xhci, in_ctx, xhci_last_valid_endpoint(add_flags));
}
-void xhci_setup_input_ctx_for_quirk(struct xhci_hcd *xhci,
+static void xhci_setup_input_ctx_for_quirk(struct xhci_hcd *xhci,
unsigned int slot_id, unsigned int ep_index,
struct xhci_dequeue_state *deq_state)
{
}
/* xHCI debugging */
-void xhci_print_ir_set(struct xhci_hcd *xhci, struct xhci_intr_reg *ir_set, int set_num);
+void xhci_print_ir_set(struct xhci_hcd *xhci, int set_num);
void xhci_print_registers(struct xhci_hcd *xhci);
void xhci_dbg_regs(struct xhci_hcd *xhci);
void xhci_print_run_regs(struct xhci_hcd *xhci);
musb->xceiv->set_power = bfin_musb_set_power;
musb->isr = blackfin_interrupt;
+ musb->double_buffer_not_ok = true;
return 0;
}
static inline struct musb *dev_to_musb(struct device *dev)
{
-#ifdef CONFIG_USB_MUSB_HDRC_HCD
- /* usbcore insists dev->driver_data is a "struct hcd *" */
- return hcd_to_musb(dev_get_drvdata(dev));
-#else
return dev_get_drvdata(dev);
-#endif
}
/*-------------------------------------------------------------------------*/
INIT_LIST_HEAD(&musb->out_bulk);
hcd->uses_new_polling = 1;
+ hcd->has_tt = 1;
musb->vbuserr_retry = VBUSERR_RETRY_COUNT;
musb->a_wait_bcon = OTG_TIME_A_WAIT_BCON;
musb = kzalloc(sizeof *musb, GFP_KERNEL);
if (!musb)
return NULL;
- dev_set_drvdata(dev, musb);
#endif
-
+ dev_set_drvdata(dev, musb);
musb->mregs = mbase;
musb->ctrl_base = mbase;
musb->nIrq = -ENODEV;
void __iomem *base;
iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!iomem || irq == 0)
+ if (!iomem || irq <= 0)
return -ENODEV;
base = ioremap(iomem->start, resource_size(iomem));
struct usb_gadget_driver *gadget_driver; /* its driver */
#endif
+ /*
+ * FIXME: Remove this flag.
+ *
+ * This is only added to allow Blackfin to work
+ * with current driver. For some unknown reason
+ * Blackfin doesn't work with double buffering
+ * and that's enabled by default.
+ *
+ * We added this flag to forcefully disable double
+ * buffering until we get it working.
+ */
+ unsigned double_buffer_not_ok:1 __deprecated;
+
struct musb_hdrc_config *config;
#ifdef MUSB_CONFIG_PROC_FS
dma_addr_t dma_addr,
u32 length);
int (*channel_abort)(struct dma_channel *);
+ int (*is_compatible)(struct dma_channel *channel,
+ u16 maxpacket,
+ void *buf, u32 length);
};
/* called after channel_program(), may indicate a fault */
/* ----------------------------------------------------------------------- */
+#define is_buffer_mapped(req) (is_dma_capable() && \
+ (req->map_state != UN_MAPPED))
+
/* Maps the buffer to dma */
static inline void map_dma_buffer(struct musb_request *request,
- struct musb *musb)
+ struct musb *musb, struct musb_ep *musb_ep)
{
+ int compatible = true;
+ struct dma_controller *dma = musb->dma_controller;
+
+ request->map_state = UN_MAPPED;
+
+ if (!is_dma_capable() || !musb_ep->dma)
+ return;
+
+ /* Check if DMA engine can handle this request.
+ * DMA code must reject the USB request explicitly.
+ * Default behaviour is to map the request.
+ */
+ if (dma->is_compatible)
+ compatible = dma->is_compatible(musb_ep->dma,
+ musb_ep->packet_sz, request->request.buf,
+ request->request.length);
+ if (!compatible)
+ return;
+
if (request->request.dma == DMA_ADDR_INVALID) {
request->request.dma = dma_map_single(
musb->controller,
request->tx
? DMA_TO_DEVICE
: DMA_FROM_DEVICE);
- request->mapped = 1;
+ request->map_state = MUSB_MAPPED;
} else {
dma_sync_single_for_device(musb->controller,
request->request.dma,
request->tx
? DMA_TO_DEVICE
: DMA_FROM_DEVICE);
- request->mapped = 0;
+ request->map_state = PRE_MAPPED;
}
}
static inline void unmap_dma_buffer(struct musb_request *request,
struct musb *musb)
{
+ if (!is_buffer_mapped(request))
+ return;
+
if (request->request.dma == DMA_ADDR_INVALID) {
DBG(20, "not unmapping a never mapped buffer\n");
return;
}
- if (request->mapped) {
+ if (request->map_state == MUSB_MAPPED) {
dma_unmap_single(musb->controller,
request->request.dma,
request->request.length,
? DMA_TO_DEVICE
: DMA_FROM_DEVICE);
request->request.dma = DMA_ADDR_INVALID;
- request->mapped = 0;
- } else {
+ } else { /* PRE_MAPPED */
dma_sync_single_for_cpu(musb->controller,
request->request.dma,
request->request.length,
request->tx
? DMA_TO_DEVICE
: DMA_FROM_DEVICE);
-
}
+ request->map_state = UN_MAPPED;
}
/*
ep->busy = 1;
spin_unlock(&musb->lock);
- if (is_dma_capable() && ep->dma)
- unmap_dma_buffer(req, musb);
+ unmap_dma_buffer(req, musb);
if (request->status == 0)
DBG(5, "%s done request %p, %d/%d\n",
ep->end_point.name, request,
csr);
#ifndef CONFIG_MUSB_PIO_ONLY
- if (is_dma_capable() && musb_ep->dma) {
+ if (is_buffer_mapped(req)) {
struct dma_controller *c = musb->dma_controller;
size_t request_size;
* Unmap the dma buffer back to cpu if dma channel
* programming fails
*/
- if (is_dma_capable() && musb_ep->dma)
- unmap_dma_buffer(req, musb);
+ unmap_dma_buffer(req, musb);
musb_write_fifo(musb_ep->hw_ep, fifo_count,
(u8 *) (request->buf + request->actual));
return;
}
- if (is_cppi_enabled() && musb_ep->dma) {
+ if (is_cppi_enabled() && is_buffer_mapped(req)) {
struct dma_controller *c = musb->dma_controller;
struct dma_channel *channel = musb_ep->dma;
len = musb_readw(epio, MUSB_RXCOUNT);
if (request->actual < request->length) {
#ifdef CONFIG_USB_INVENTRA_DMA
- if (is_dma_capable() && musb_ep->dma) {
+ if (is_buffer_mapped(req)) {
struct dma_controller *c;
struct dma_channel *channel;
int use_dma = 0;
fifo_count = min_t(unsigned, len, fifo_count);
#ifdef CONFIG_USB_TUSB_OMAP_DMA
- if (tusb_dma_omap() && musb_ep->dma) {
+ if (tusb_dma_omap() && is_buffer_mapped(req)) {
struct dma_controller *c = musb->dma_controller;
struct dma_channel *channel = musb_ep->dma;
u32 dma_addr = request->dma + request->actual;
* programming fails. This buffer is mapped if the
* channel allocation is successful
*/
- if (is_dma_capable() && musb_ep->dma) {
+ if (is_buffer_mapped(req)) {
unmap_dma_buffer(req, musb);
/*
/* Set TXMAXP with the FIFO size of the endpoint
* to disable double buffering mode.
*/
- musb_writew(regs, MUSB_TXMAXP, musb_ep->packet_sz | (musb_ep->hb_mult << 11));
+ if (musb->double_buffer_not_ok)
+ musb_writew(regs, MUSB_TXMAXP, hw_ep->max_packet_sz_tx);
+ else
+ musb_writew(regs, MUSB_TXMAXP, musb_ep->packet_sz
+ | (musb_ep->hb_mult << 11));
csr = MUSB_TXCSR_MODE | MUSB_TXCSR_CLRDATATOG;
if (musb_readw(regs, MUSB_TXCSR)
/* Set RXMAXP with the FIFO size of the endpoint
* to disable double buffering mode.
*/
- musb_writew(regs, MUSB_RXMAXP, musb_ep->packet_sz | (musb_ep->hb_mult << 11));
+ if (musb->double_buffer_not_ok)
+ musb_writew(regs, MUSB_RXMAXP, hw_ep->max_packet_sz_tx);
+ else
+ musb_writew(regs, MUSB_RXMAXP, musb_ep->packet_sz
+ | (musb_ep->hb_mult << 11));
/* force shared fifo to OUT-only mode */
if (hw_ep->is_shared_fifo) {
request->epnum = musb_ep->current_epnum;
request->tx = musb_ep->is_in;
- if (is_dma_capable() && musb_ep->dma)
- map_dma_buffer(request, musb);
- else
- request->mapped = 0;
+ map_dma_buffer(request, musb, musb_ep);
spin_lock_irqsave(&musb->lock, lockflags);
#ifndef __MUSB_GADGET_H
#define __MUSB_GADGET_H
+enum buffer_map_state {
+ UN_MAPPED = 0,
+ PRE_MAPPED,
+ MUSB_MAPPED
+};
+
struct musb_request {
struct usb_request request;
struct musb_ep *ep;
struct musb *musb;
u8 tx; /* endpoint direction */
u8 epnum;
- u8 mapped;
+ enum buffer_map_state map_state;
};
static inline struct musb_request *to_musb_request(struct usb_request *req)
/* Set RXMAXP with the FIFO size of the endpoint
* to disable double buffer mode.
*/
- if (musb->hwvers < MUSB_HWVERS_2000)
+ if (musb->double_buffer_not_ok)
musb_writew(ep->regs, MUSB_RXMAXP, ep->max_packet_sz_rx);
else
musb_writew(ep->regs, MUSB_RXMAXP,
/* protocol/endpoint/interval/NAKlimit */
if (epnum) {
musb_writeb(epio, MUSB_TXTYPE, qh->type_reg);
- if (can_bulk_split(musb, qh->type))
+ if (musb->double_buffer_not_ok)
musb_writew(epio, MUSB_TXMAXP,
- packet_sz
- | ((hw_ep->max_packet_sz_tx /
- packet_sz) - 1) << 11);
+ hw_ep->max_packet_sz_tx);
else
musb_writew(epio, MUSB_TXMAXP,
- packet_sz);
+ qh->maxpacket |
+ ((qh->hb_mult - 1) << 11));
musb_writeb(epio, MUSB_TXINTERVAL, qh->intv_reg);
} else {
musb_writeb(epio, MUSB_NAKLIMIT0, qh->intv_reg);
{
musb_writew(mbase,
MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_ADDR_LOW),
- ((u16)((u32) dma_addr & 0xFFFF)));
+ dma_addr);
musb_writew(mbase,
MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_ADDR_HIGH),
- ((u16)(((u32) dma_addr >> 16) & 0xFFFF)));
+ (dma_addr >> 16));
}
static inline u32 musb_read_hsdma_count(void __iomem *mbase, u8 bchannel)
{
- return musb_readl(mbase,
+ u32 count = musb_readw(mbase,
MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT_HIGH));
+
+ count = count << 16;
+
+ count |= musb_readw(mbase,
+ MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT_LOW));
+
+ return count;
}
static inline void musb_write_hsdma_count(void __iomem *mbase,
u8 bchannel, u32 len)
{
- musb_writel(mbase,
+ musb_writew(mbase,
+ MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT_LOW),len);
+ musb_writew(mbase,
MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT_HIGH),
- len);
+ (len >> 16));
}
#endif /* CONFIG_BLACKFIN */
static int omap2430_musb_exit(struct musb *musb)
{
+ del_timer_sync(&musb_idle_timer);
omap2430_low_level_exit(musb);
otg_put_transceiver(musb->xceiv);
required after resetting the hardware and power management.
This driver is required even for peripheral only or host only
mode configurations.
+ This driver is not supported on boards like trout which
+ has an external PHY.
config AB8500_USB
tristate "AB8500 USB Transceiver Driver"
static int ftdi_jtag_probe(struct usb_serial *serial);
static int ftdi_mtxorb_hack_setup(struct usb_serial *serial);
static int ftdi_NDI_device_setup(struct usb_serial *serial);
+static int ftdi_stmclite_probe(struct usb_serial *serial);
static void ftdi_USB_UIRT_setup(struct ftdi_private *priv);
static void ftdi_HE_TIRA1_setup(struct ftdi_private *priv);
.port_probe = ftdi_HE_TIRA1_setup,
};
+static struct ftdi_sio_quirk ftdi_stmclite_quirk = {
+ .probe = ftdi_stmclite_probe,
+};
+
/*
* The 8U232AM has the same API as the sio except for:
* - it can support MUCH higher baudrates; up to:
{ USB_DEVICE(FTDI_VID, FTDI_OCEANIC_PID) },
{ USB_DEVICE(TTI_VID, TTI_QL355P_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_RM_CANVIEW_PID) },
+ { USB_DEVICE(ACTON_VID, ACTON_SPECTRAPRO_PID) },
{ USB_DEVICE(CONTEC_VID, CONTEC_COM1USBH_PID) },
{ USB_DEVICE(BANDB_VID, BANDB_USOTL4_PID) },
{ USB_DEVICE(BANDB_VID, BANDB_USTL4_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_DOTEC_PID) },
{ USB_DEVICE(QIHARDWARE_VID, MILKYMISTONE_JTAGSERIAL_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE(ST_VID, ST_STMCLT1030_PID),
+ .driver_info = (kernel_ulong_t)&ftdi_stmclite_quirk },
{ }, /* Optional parameter entry */
{ } /* Terminating entry */
};
return 0;
}
+/*
+ * First and second port on STMCLiteadaptors is reserved for JTAG interface
+ * and the forth port for pio
+ */
+static int ftdi_stmclite_probe(struct usb_serial *serial)
+{
+ struct usb_device *udev = serial->dev;
+ struct usb_interface *interface = serial->interface;
+
+ dbg("%s", __func__);
+
+ if (interface == udev->actconfig->interface[2])
+ return 0;
+
+ dev_info(&udev->dev, "Ignoring serial port reserved for JTAG\n");
+
+ return -ENODEV;
+}
+
/*
* The Matrix Orbital VK204-25-USB has an invalid IN endpoint.
* We have to correct it if we want to read from it.
#define RATOC_VENDOR_ID 0x0584
#define RATOC_PRODUCT_ID_USB60F 0xb020
+/*
+ * Acton Research Corp.
+ */
+#define ACTON_VID 0x0647 /* Vendor ID */
+#define ACTON_SPECTRAPRO_PID 0x0100
+
/*
* Contec products (http://www.contec.com)
* Submitted by Daniel Sangorrin
#define STB_PID 0x0001 /* Sensor Terminal Board */
#define WHT_PID 0x0004 /* Wireless Handheld Terminal */
+/*
+ * STMicroelectonics
+ */
+#define ST_VID 0x0483
+#define ST_STMCLT1030_PID 0x3747 /* ST Micro Connect Lite STMCLT1030 */
+
/*
* Papouch products (http://www.papouch.com/)
* Submitted by Folkert van Heusden
dbg("%s %d.%d.%d", fw_info, rec->data[0], rec->data[1], build);
- edge_serial->product_info.FirmwareMajorVersion = fw->data[0];
- edge_serial->product_info.FirmwareMinorVersion = fw->data[1];
+ edge_serial->product_info.FirmwareMajorVersion = rec->data[0];
+ edge_serial->product_info.FirmwareMinorVersion = rec->data[1];
edge_serial->product_info.FirmwareBuildNumber = cpu_to_le16(build);
for (rec = ihex_next_binrec(rec); rec;
{ USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless Direct IP modems */
.driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
},
+ { USB_DEVICE(0x0f3d, 0x68A3), /* Airprime/Sierra Wireless Direct IP modems */
+ .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
+ },
{ USB_DEVICE(0x413C, 0x08133) }, /* Dell Computer Corp. Wireless 5720 VZW Mobile Broadband (EVDO Rev-A) Minicard GPS Port */
{ }
static void __exit ti_exit(void)
{
+ usb_deregister(&ti_usb_driver);
usb_serial_deregister(&ti_1port_device);
usb_serial_deregister(&ti_2port_device);
- usb_deregister(&ti_usb_driver);
}
__func__, status, endpoint);
} else {
tty = tty_port_tty_get(&port->port);
- if (urb->actual_length) {
- tty_insert_flip_string(tty, data, urb->actual_length);
- tty_flip_buffer_push(tty);
- } else
- dbg("%s: empty read urb received", __func__);
- tty_kref_put(tty);
+ if (tty) {
+ if (urb->actual_length) {
+ tty_insert_flip_string(tty, data,
+ urb->actual_length);
+ tty_flip_buffer_push(tty);
+ } else
+ dbg("%s: empty read urb received", __func__);
+ tty_kref_put(tty);
+ }
/* Resubmit urb so we continue receiving */
if (status != -ESHUTDOWN) {
#include <linux/uaccess.h>
#include <linux/usb.h>
#include <linux/usb/serial.h>
+#include <linux/usb/cdc.h>
#include "visor.h"
/*
dbg("%s", __func__);
+ /*
+ * some Samsung Android phones in modem mode have the same ID
+ * as SPH-I500, but they are ACM devices, so dont bind to them
+ */
+ if (id->idVendor == SAMSUNG_VENDOR_ID &&
+ id->idProduct == SAMSUNG_SPH_I500_ID &&
+ serial->dev->descriptor.bDeviceClass == USB_CLASS_COMM &&
+ serial->dev->descriptor.bDeviceSubClass ==
+ USB_CDC_SUBCLASS_ACM)
+ return -ENODEV;
+
if (serial->dev->actconfig->desc.bConfigurationValue != 1) {
dev_err(&serial->dev->dev, "active config #%d != 1 ??\n",
serial->dev->actconfig->desc.bConfigurationValue);
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_IGNORE_RESIDUE ),
+/* Submitted by Nick Holloway */
+UNUSUAL_DEV( 0x0f88, 0x042e, 0x0100, 0x0100,
+ "VTech",
+ "Kidizoom",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_FIX_CAPACITY ),
+
/* Reported by Michael Stattmann <michael@stattmann.com> */
UNUSUAL_DEV( 0x0fce, 0xd008, 0x0000, 0x0000,
"Sony Ericsson",
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ),
+/* Reported by Jasper Mackenzie <scarletpimpernal@hotmail.com> */
+UNUSUAL_DEV( 0x1e74, 0x4621, 0x0000, 0x0000,
+ "Coby Electronics",
+ "MP3 Player",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ),
+
UNUSUAL_DEV( 0x2116, 0x0320, 0x0001, 0x0001,
"ST",
"2A",
lcd->spi = spi;
lcd->power = FB_BLANK_POWERDOWN;
lcd->buffer = kzalloc(8, GFP_KERNEL);
+ if (!lcd->buffer) {
+ ret = -ENOMEM;
+ goto out_free_lcd;
+ }
ld = lcd_device_register("ltv350qv", &spi->dev, lcd, <v_ops);
if (IS_ERR(ld)) {
ret = PTR_ERR(ld);
- goto out_free_lcd;
+ goto out_free_buffer;
}
lcd->ld = ld;
out_unregister:
lcd_device_unregister(ld);
+out_free_buffer:
+ kfree(lcd->buffer);
out_free_lcd:
kfree(lcd);
return ret;
ltv350qv_power(lcd, FB_BLANK_POWERDOWN);
lcd_device_unregister(lcd->ld);
+ kfree(lcd->buffer);
kfree(lcd);
return 0;
/* get interface & functional clock objects */
hdq_data->hdq_ick = clk_get(&pdev->dev, "ick");
- hdq_data->hdq_fck = clk_get(&pdev->dev, "fck");
+ if (IS_ERR(hdq_data->hdq_ick)) {
+ dev_dbg(&pdev->dev, "Can't get HDQ ick clock object\n");
+ ret = PTR_ERR(hdq_data->hdq_ick);
+ goto err_ick;
+ }
- if (IS_ERR(hdq_data->hdq_ick) || IS_ERR(hdq_data->hdq_fck)) {
- dev_dbg(&pdev->dev, "Can't get HDQ clock objects\n");
- if (IS_ERR(hdq_data->hdq_ick)) {
- ret = PTR_ERR(hdq_data->hdq_ick);
- goto err_clk;
- }
- if (IS_ERR(hdq_data->hdq_fck)) {
- ret = PTR_ERR(hdq_data->hdq_fck);
- clk_put(hdq_data->hdq_ick);
- goto err_clk;
- }
+ hdq_data->hdq_fck = clk_get(&pdev->dev, "fck");
+ if (IS_ERR(hdq_data->hdq_fck)) {
+ dev_dbg(&pdev->dev, "Can't get HDQ fck clock object\n");
+ ret = PTR_ERR(hdq_data->hdq_fck);
+ goto err_fck;
}
hdq_data->hdq_usecount = 0;
clk_disable(hdq_data->hdq_ick);
err_intfclk:
- clk_put(hdq_data->hdq_ick);
clk_put(hdq_data->hdq_fck);
-err_clk:
+err_fck:
+ clk_put(hdq_data->hdq_ick);
+
+err_ick:
iounmap(hdq_data->hdq_base);
err_ioremap:
# M68K Architecture
-config M548x_WATCHDOG
- tristate "MCF548x watchdog support"
+config M54xx_WATCHDOG
+ tristate "MCF54xx watchdog support"
depends on M548x
help
To compile this driver as a module, choose M here: the
- module will be called m548x_wdt.
+ module will be called m54xx_wdt.
# MIPS Architecture
# M32R Architecture
# M68K Architecture
-obj-$(CONFIG_M548x_WATCHDOG) += m548x_wdt.o
+obj-$(CONFIG_M54xx_WATCHDOG) += m54xx_wdt.o
# MIPS Architecture
obj-$(CONFIG_ATH79_WDT) += ath79_wdt.o
struct cpwd *p = dev_get_drvdata(&op->dev);
int i;
- for (i = 0; i < 4; i++) {
+ for (i = 0; i < WD_NUMDEVS; i++) {
misc_deregister(&p->devs[i].misc);
if (!p->enabled) {
return 0;
}
-static void __devexit hpwdt_exit_nmi_decoding(void)
+static void hpwdt_exit_nmi_decoding(void)
{
unregister_die_notifier(&die_notifier);
if (cru_rom_addr)
return 0;
}
-static void __devexit hpwdt_exit_nmi_decoding(void)
+static void hpwdt_exit_nmi_decoding(void)
{
}
#endif /* CONFIG_HPWDT_NMI_DECODING */
+++ /dev/null
-/*
- * drivers/watchdog/m548x_wdt.c
- *
- * Watchdog driver for ColdFire MCF548x processors
- * Copyright 2010 (c) Philippe De Muyter <phdm@macqel.be>
- *
- * Adapted from the IXP4xx watchdog driver, which carries these notices:
- *
- * Author: Deepak Saxena <dsaxena@plexity.net>
- *
- * Copyright 2004 (c) MontaVista, Software, Inc.
- * Based on sa1100 driver, Copyright (C) 2000 Oleg Drokin <green@crimea.edu>
- *
- * 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.
- */
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/miscdevice.h>
-#include <linux/watchdog.h>
-#include <linux/init.h>
-#include <linux/bitops.h>
-#include <linux/ioport.h>
-#include <linux/uaccess.h>
-
-#include <asm/coldfire.h>
-#include <asm/m548xsim.h>
-#include <asm/m548xgpt.h>
-
-static int nowayout = WATCHDOG_NOWAYOUT;
-static unsigned int heartbeat = 30; /* (secs) Default is 0.5 minute */
-static unsigned long wdt_status;
-
-#define WDT_IN_USE 0
-#define WDT_OK_TO_CLOSE 1
-
-static void wdt_enable(void)
-{
- unsigned int gms0;
-
- /* preserve GPIO usage, if any */
- gms0 = __raw_readl(MCF_MBAR + MCF_GPT_GMS0);
- if (gms0 & MCF_GPT_GMS_TMS_GPIO)
- gms0 &= (MCF_GPT_GMS_TMS_GPIO | MCF_GPT_GMS_GPIO_MASK
- | MCF_GPT_GMS_OD);
- else
- gms0 = MCF_GPT_GMS_TMS_GPIO | MCF_GPT_GMS_OD;
- __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0);
- __raw_writel(MCF_GPT_GCIR_PRE(heartbeat*(MCF_BUSCLK/0xffff)) |
- MCF_GPT_GCIR_CNT(0xffff), MCF_MBAR + MCF_GPT_GCIR0);
- gms0 |= MCF_GPT_GMS_OCPW(0xA5) | MCF_GPT_GMS_WDEN | MCF_GPT_GMS_CE;
- __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0);
-}
-
-static void wdt_disable(void)
-{
- unsigned int gms0;
-
- /* disable watchdog */
- gms0 = __raw_readl(MCF_MBAR + MCF_GPT_GMS0);
- gms0 &= ~(MCF_GPT_GMS_WDEN | MCF_GPT_GMS_CE);
- __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0);
-}
-
-static void wdt_keepalive(void)
-{
- unsigned int gms0;
-
- gms0 = __raw_readl(MCF_MBAR + MCF_GPT_GMS0);
- gms0 |= MCF_GPT_GMS_OCPW(0xA5);
- __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0);
-}
-
-static int m548x_wdt_open(struct inode *inode, struct file *file)
-{
- if (test_and_set_bit(WDT_IN_USE, &wdt_status))
- return -EBUSY;
-
- clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
- wdt_enable();
- return nonseekable_open(inode, file);
-}
-
-static ssize_t m548x_wdt_write(struct file *file, const char *data,
- size_t len, loff_t *ppos)
-{
- if (len) {
- if (!nowayout) {
- size_t i;
-
- clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
- for (i = 0; i != len; i++) {
- char c;
-
- if (get_user(c, data + i))
- return -EFAULT;
- if (c == 'V')
- set_bit(WDT_OK_TO_CLOSE, &wdt_status);
- }
- }
- wdt_keepalive();
- }
- return len;
-}
-
-static const struct watchdog_info ident = {
- .options = WDIOF_MAGICCLOSE | WDIOF_SETTIMEOUT |
- WDIOF_KEEPALIVEPING,
- .identity = "Coldfire M548x Watchdog",
-};
-
-static long m548x_wdt_ioctl(struct file *file, unsigned int cmd,
- unsigned long arg)
-{
- int ret = -ENOTTY;
- int time;
-
- switch (cmd) {
- case WDIOC_GETSUPPORT:
- ret = copy_to_user((struct watchdog_info *)arg, &ident,
- sizeof(ident)) ? -EFAULT : 0;
- break;
-
- case WDIOC_GETSTATUS:
- ret = put_user(0, (int *)arg);
- break;
-
- case WDIOC_GETBOOTSTATUS:
- ret = put_user(0, (int *)arg);
- break;
-
- case WDIOC_KEEPALIVE:
- wdt_keepalive();
- ret = 0;
- break;
-
- case WDIOC_SETTIMEOUT:
- ret = get_user(time, (int *)arg);
- if (ret)
- break;
-
- if (time <= 0 || time > 30) {
- ret = -EINVAL;
- break;
- }
-
- heartbeat = time;
- wdt_enable();
- /* Fall through */
-
- case WDIOC_GETTIMEOUT:
- ret = put_user(heartbeat, (int *)arg);
- break;
- }
- return ret;
-}
-
-static int m548x_wdt_release(struct inode *inode, struct file *file)
-{
- if (test_bit(WDT_OK_TO_CLOSE, &wdt_status))
- wdt_disable();
- else {
- printk(KERN_CRIT "WATCHDOG: Device closed unexpectedly - "
- "timer will not stop\n");
- wdt_keepalive();
- }
- clear_bit(WDT_IN_USE, &wdt_status);
- clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
-
- return 0;
-}
-
-
-static const struct file_operations m548x_wdt_fops = {
- .owner = THIS_MODULE,
- .llseek = no_llseek,
- .write = m548x_wdt_write,
- .unlocked_ioctl = m548x_wdt_ioctl,
- .open = m548x_wdt_open,
- .release = m548x_wdt_release,
-};
-
-static struct miscdevice m548x_wdt_miscdev = {
- .minor = WATCHDOG_MINOR,
- .name = "watchdog",
- .fops = &m548x_wdt_fops,
-};
-
-static int __init m548x_wdt_init(void)
-{
- if (!request_mem_region(MCF_MBAR + MCF_GPT_GCIR0, 4,
- "Coldfire M548x Watchdog")) {
- printk(KERN_WARNING
- "Coldfire M548x Watchdog : I/O region busy\n");
- return -EBUSY;
- }
- printk(KERN_INFO "ColdFire watchdog driver is loaded.\n");
-
- return misc_register(&m548x_wdt_miscdev);
-}
-
-static void __exit m548x_wdt_exit(void)
-{
- misc_deregister(&m548x_wdt_miscdev);
- release_mem_region(MCF_MBAR + MCF_GPT_GCIR0, 4);
-}
-
-module_init(m548x_wdt_init);
-module_exit(m548x_wdt_exit);
-
-MODULE_AUTHOR("Philippe De Muyter <phdm@macqel.be>");
-MODULE_DESCRIPTION("Coldfire M548x Watchdog");
-
-module_param(heartbeat, int, 0);
-MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds (default 30s)");
-
-module_param(nowayout, int, 0);
-MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
--- /dev/null
+/*
+ * drivers/watchdog/m54xx_wdt.c
+ *
+ * Watchdog driver for ColdFire MCF547x & MCF548x processors
+ * Copyright 2010 (c) Philippe De Muyter <phdm@macqel.be>
+ *
+ * Adapted from the IXP4xx watchdog driver, which carries these notices:
+ *
+ * Author: Deepak Saxena <dsaxena@plexity.net>
+ *
+ * Copyright 2004 (c) MontaVista, Software, Inc.
+ * Based on sa1100 driver, Copyright (C) 2000 Oleg Drokin <green@crimea.edu>
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/watchdog.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+#include <linux/ioport.h>
+#include <linux/uaccess.h>
+
+#include <asm/coldfire.h>
+#include <asm/m54xxsim.h>
+#include <asm/m54xxgpt.h>
+
+static int nowayout = WATCHDOG_NOWAYOUT;
+static unsigned int heartbeat = 30; /* (secs) Default is 0.5 minute */
+static unsigned long wdt_status;
+
+#define WDT_IN_USE 0
+#define WDT_OK_TO_CLOSE 1
+
+static void wdt_enable(void)
+{
+ unsigned int gms0;
+
+ /* preserve GPIO usage, if any */
+ gms0 = __raw_readl(MCF_MBAR + MCF_GPT_GMS0);
+ if (gms0 & MCF_GPT_GMS_TMS_GPIO)
+ gms0 &= (MCF_GPT_GMS_TMS_GPIO | MCF_GPT_GMS_GPIO_MASK
+ | MCF_GPT_GMS_OD);
+ else
+ gms0 = MCF_GPT_GMS_TMS_GPIO | MCF_GPT_GMS_OD;
+ __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0);
+ __raw_writel(MCF_GPT_GCIR_PRE(heartbeat*(MCF_BUSCLK/0xffff)) |
+ MCF_GPT_GCIR_CNT(0xffff), MCF_MBAR + MCF_GPT_GCIR0);
+ gms0 |= MCF_GPT_GMS_OCPW(0xA5) | MCF_GPT_GMS_WDEN | MCF_GPT_GMS_CE;
+ __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0);
+}
+
+static void wdt_disable(void)
+{
+ unsigned int gms0;
+
+ /* disable watchdog */
+ gms0 = __raw_readl(MCF_MBAR + MCF_GPT_GMS0);
+ gms0 &= ~(MCF_GPT_GMS_WDEN | MCF_GPT_GMS_CE);
+ __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0);
+}
+
+static void wdt_keepalive(void)
+{
+ unsigned int gms0;
+
+ gms0 = __raw_readl(MCF_MBAR + MCF_GPT_GMS0);
+ gms0 |= MCF_GPT_GMS_OCPW(0xA5);
+ __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0);
+}
+
+static int m54xx_wdt_open(struct inode *inode, struct file *file)
+{
+ if (test_and_set_bit(WDT_IN_USE, &wdt_status))
+ return -EBUSY;
+
+ clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
+ wdt_enable();
+ return nonseekable_open(inode, file);
+}
+
+static ssize_t m54xx_wdt_write(struct file *file, const char *data,
+ size_t len, loff_t *ppos)
+{
+ if (len) {
+ if (!nowayout) {
+ size_t i;
+
+ clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
+
+ for (i = 0; i != len; i++) {
+ char c;
+
+ if (get_user(c, data + i))
+ return -EFAULT;
+ if (c == 'V')
+ set_bit(WDT_OK_TO_CLOSE, &wdt_status);
+ }
+ }
+ wdt_keepalive();
+ }
+ return len;
+}
+
+static const struct watchdog_info ident = {
+ .options = WDIOF_MAGICCLOSE | WDIOF_SETTIMEOUT |
+ WDIOF_KEEPALIVEPING,
+ .identity = "Coldfire M54xx Watchdog",
+};
+
+static long m54xx_wdt_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ int ret = -ENOTTY;
+ int time;
+
+ switch (cmd) {
+ case WDIOC_GETSUPPORT:
+ ret = copy_to_user((struct watchdog_info *)arg, &ident,
+ sizeof(ident)) ? -EFAULT : 0;
+ break;
+
+ case WDIOC_GETSTATUS:
+ ret = put_user(0, (int *)arg);
+ break;
+
+ case WDIOC_GETBOOTSTATUS:
+ ret = put_user(0, (int *)arg);
+ break;
+
+ case WDIOC_KEEPALIVE:
+ wdt_keepalive();
+ ret = 0;
+ break;
+
+ case WDIOC_SETTIMEOUT:
+ ret = get_user(time, (int *)arg);
+ if (ret)
+ break;
+
+ if (time <= 0 || time > 30) {
+ ret = -EINVAL;
+ break;
+ }
+
+ heartbeat = time;
+ wdt_enable();
+ /* Fall through */
+
+ case WDIOC_GETTIMEOUT:
+ ret = put_user(heartbeat, (int *)arg);
+ break;
+ }
+ return ret;
+}
+
+static int m54xx_wdt_release(struct inode *inode, struct file *file)
+{
+ if (test_bit(WDT_OK_TO_CLOSE, &wdt_status))
+ wdt_disable();
+ else {
+ printk(KERN_CRIT "WATCHDOG: Device closed unexpectedly - "
+ "timer will not stop\n");
+ wdt_keepalive();
+ }
+ clear_bit(WDT_IN_USE, &wdt_status);
+ clear_bit(WDT_OK_TO_CLOSE, &wdt_status);
+
+ return 0;
+}
+
+
+static const struct file_operations m54xx_wdt_fops = {
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+ .write = m54xx_wdt_write,
+ .unlocked_ioctl = m54xx_wdt_ioctl,
+ .open = m54xx_wdt_open,
+ .release = m54xx_wdt_release,
+};
+
+static struct miscdevice m54xx_wdt_miscdev = {
+ .minor = WATCHDOG_MINOR,
+ .name = "watchdog",
+ .fops = &m54xx_wdt_fops,
+};
+
+static int __init m54xx_wdt_init(void)
+{
+ if (!request_mem_region(MCF_MBAR + MCF_GPT_GCIR0, 4,
+ "Coldfire M54xx Watchdog")) {
+ printk(KERN_WARNING
+ "Coldfire M54xx Watchdog : I/O region busy\n");
+ return -EBUSY;
+ }
+ printk(KERN_INFO "ColdFire watchdog driver is loaded.\n");
+
+ return misc_register(&m54xx_wdt_miscdev);
+}
+
+static void __exit m54xx_wdt_exit(void)
+{
+ misc_deregister(&m54xx_wdt_miscdev);
+ release_mem_region(MCF_MBAR + MCF_GPT_GCIR0, 4);
+}
+
+module_init(m54xx_wdt_init);
+module_exit(m54xx_wdt_exit);
+
+MODULE_AUTHOR("Philippe De Muyter <phdm@macqel.be>");
+MODULE_DESCRIPTION("Coldfire M54xx Watchdog");
+
+module_param(heartbeat, int, 0);
+MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds (default 30s)");
+
+module_param(nowayout, int, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started");
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
static int __init fitpc2_wdt_init(void)
{
int err;
+ const char *brd_name;
- if (!strstr(dmi_get_system_info(DMI_BOARD_NAME), "SBC-FITPC2"))
+ brd_name = dmi_get_system_info(DMI_BOARD_NAME);
+
+ if (!brd_name || !strstr(brd_name, "SBC-FITPC2"))
return -ENODEV;
- pr_info("%s found\n", dmi_get_system_info(DMI_BOARD_NAME));
+ pr_info("%s found\n", brd_name);
if (!request_region(COMMAND_PORT, 1, WATCHDOG_NAME)) {
pr_err("I/O address 0x%04x already in use\n", COMMAND_PORT);
sch311x_sio_outb(sio_config_port, 0x07, 0x0a);
/* Check if Logical Device Register is currently active */
- if (sch311x_sio_inb(sio_config_port, 0x30) && 0x01 == 0)
+ if ((sch311x_sio_inb(sio_config_port, 0x30) & 0x01) == 0)
printk(KERN_INFO PFX "Seems that LDN 0x0a is not active...\n");
/* Get the base address of the runtime registers */
outb_p(0x08, WDT_EFDR); /* select logical device 8 (GPIO2) */
outb_p(0x30, WDT_EFER); /* select CR30 */
c = inb_p(WDT_EFDR);
- outb_p(c || 0x01, WDT_EFDR); /* set bit 0 to activate GPIO2 */
+ outb_p(c | 0x01, WDT_EFDR); /* set bit 0 to activate GPIO2 */
return 0;
}
set_phys_to_machine(pfn, frame_list[i]);
/* Link back into the page tables if not highmem. */
- if (pfn < max_low_pfn) {
+ if (!xen_hvm_domain() && pfn < max_low_pfn) {
int ret;
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
scrub_page(page);
- if (!PageHighMem(page)) {
+ if (!xen_hvm_domain() && !PageHighMem(page)) {
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
__pte_ma(0), 0);
/* No more mappings: invalidate P2M and add to balloon. */
for (i = 0; i < nr_pages; i++) {
pfn = mfn_to_pfn(frame_list[i]);
- set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+ __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
balloon_append(pfn_to_page(pfn));
}
static int __init balloon_init(void)
{
- unsigned long pfn, extra_pfn_end;
+ unsigned long pfn, nr_pages, extra_pfn_end;
struct page *page;
- if (!xen_pv_domain())
+ if (!xen_domain())
return -ENODEV;
pr_info("xen_balloon: Initialising balloon driver.\n");
- balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn);
+ if (xen_pv_domain())
+ nr_pages = xen_start_info->nr_pages;
+ else
+ nr_pages = max_pfn;
+ balloon_stats.current_pages = min(nr_pages, max_pfn);
balloon_stats.target_pages = balloon_stats.current_pages;
balloon_stats.balloon_low = 0;
balloon_stats.balloon_high = 0;
static __initdata struct cpu_evtchn_s init_evtchn_mask = {
.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
};
-static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
+static struct cpu_evtchn_s __refdata *cpu_evtchn_mask_p = &init_evtchn_mask;
static inline unsigned long *cpu_evtchn_mask(int cpu)
{
BUG_ON(irq == -1);
#ifdef CONFIG_SMP
- cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu));
+ cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu));
#endif
clear_bit(chn, cpu_evtchn_mask(cpu_from_irq(irq)));
/* By default all event channels notify CPU#0. */
for_each_irq_desc(i, desc) {
- cpumask_copy(desc->affinity, cpumask_of(0));
+ cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
}
#endif
put_cpu();
}
-static int get_nr_hw_irqs(void)
+static int xen_allocate_irq_dynamic(void)
{
- int ret = 1;
+ int first = 0;
+ int irq;
#ifdef CONFIG_X86_IO_APIC
- ret = get_nr_irqs_gsi();
+ /*
+ * For an HVM guest or domain 0 which see "real" (emulated or
+ * actual repectively) GSIs we allocate dynamic IRQs
+ * e.g. those corresponding to event channels or MSIs
+ * etc. from the range above those "real" GSIs to avoid
+ * collisions.
+ */
+ if (xen_initial_domain() || xen_hvm_domain())
+ first = get_nr_irqs_gsi();
#endif
- return ret;
-}
+retry:
+ irq = irq_alloc_desc_from(first, -1);
-static int find_unbound_pirq(int type)
-{
- int rc, i;
- struct physdev_get_free_pirq op_get_free_pirq;
- op_get_free_pirq.type = type;
+ if (irq == -ENOMEM && first > NR_IRQS_LEGACY) {
+ printk(KERN_ERR "Out of dynamic IRQ space and eating into GSI space. You should increase nr_irqs\n");
+ first = max(NR_IRQS_LEGACY, first - NR_IRQS_LEGACY);
+ goto retry;
+ }
- rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
- if (!rc)
- return op_get_free_pirq.pirq;
+ if (irq < 0)
+ panic("No available IRQ to bind to: increase nr_irqs!\n");
- for (i = 0; i < nr_irqs; i++) {
- if (pirq_to_irq[i] < 0)
- return i;
- }
- return -1;
+ return irq;
}
-static int find_unbound_irq(void)
+static int xen_allocate_irq_gsi(unsigned gsi)
{
- struct irq_data *data;
- int irq, res;
- int bottom = get_nr_hw_irqs();
- int top = nr_irqs-1;
-
- if (bottom == nr_irqs)
- goto no_irqs;
+ int irq;
- /* This loop starts from the top of IRQ space and goes down.
- * We need this b/c if we have a PCI device in a Xen PV guest
- * we do not have an IO-APIC (though the backend might have them)
- * mapped in. To not have a collision of physical IRQs with the Xen
- * event channels start at the top of the IRQ space for virtual IRQs.
+ /*
+ * A PV guest has no concept of a GSI (since it has no ACPI
+ * nor access to/knowledge of the physical APICs). Therefore
+ * all IRQs are dynamically allocated from the entire IRQ
+ * space.
*/
- for (irq = top; irq > bottom; irq--) {
- data = irq_get_irq_data(irq);
- /* only 15->0 have init'd desc; handle irq > 16 */
- if (!data)
- break;
- if (data->chip == &no_irq_chip)
- break;
- if (data->chip != &xen_dynamic_chip)
- continue;
- if (irq_info[irq].type == IRQT_UNBOUND)
- return irq;
- }
-
- if (irq == bottom)
- goto no_irqs;
+ if (xen_pv_domain() && !xen_initial_domain())
+ return xen_allocate_irq_dynamic();
- res = irq_alloc_desc_at(irq, -1);
+ /* Legacy IRQ descriptors are already allocated by the arch. */
+ if (gsi < NR_IRQS_LEGACY)
+ return gsi;
- if (WARN_ON(res != irq))
- return -1;
+ irq = irq_alloc_desc_at(gsi, -1);
+ if (irq < 0)
+ panic("Unable to allocate to IRQ%d (%d)\n", gsi, irq);
return irq;
-
-no_irqs:
- panic("No available IRQ to bind to: increase nr_irqs!\n");
}
-static bool identity_mapped_irq(unsigned irq)
+static void xen_free_irq(unsigned irq)
{
- /* identity map all the hardware irqs */
- return irq < get_nr_hw_irqs();
+ /* Legacy IRQ descriptors are managed by the arch. */
+ if (irq < NR_IRQS_LEGACY)
+ return;
+
+ irq_free_desc(irq);
}
static void pirq_unmask_notify(int irq)
return desc && desc->action == NULL;
}
-static unsigned int startup_pirq(unsigned int irq)
+static unsigned int __startup_pirq(unsigned int irq)
{
struct evtchn_bind_pirq bind_pirq;
struct irq_info *info = info_for_irq(irq);
return 0;
}
-static void shutdown_pirq(unsigned int irq)
+static unsigned int startup_pirq(struct irq_data *data)
+{
+ return __startup_pirq(data->irq);
+}
+
+static void shutdown_pirq(struct irq_data *data)
{
struct evtchn_close close;
+ unsigned int irq = data->irq;
struct irq_info *info = info_for_irq(irq);
int evtchn = evtchn_from_irq(irq);
info->evtchn = 0;
}
-static void enable_pirq(unsigned int irq)
+static void enable_pirq(struct irq_data *data)
{
- startup_pirq(irq);
+ startup_pirq(data);
}
-static void disable_pirq(unsigned int irq)
+static void disable_pirq(struct irq_data *data)
{
}
-static void ack_pirq(unsigned int irq)
+static void ack_pirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
- move_native_irq(irq);
+ move_native_irq(data->irq);
if (VALID_EVTCHN(evtchn)) {
mask_evtchn(evtchn);
}
}
-static void end_pirq(unsigned int irq)
-{
- int evtchn = evtchn_from_irq(irq);
- struct irq_desc *desc = irq_to_desc(irq);
-
- if (WARN_ON(!desc))
- return;
-
- if ((desc->status & (IRQ_DISABLED|IRQ_PENDING)) ==
- (IRQ_DISABLED|IRQ_PENDING)) {
- shutdown_pirq(irq);
- } else if (VALID_EVTCHN(evtchn)) {
- unmask_evtchn(evtchn);
- pirq_unmask_notify(irq);
- }
-}
-
static int find_irq_by_gsi(unsigned gsi)
{
int irq;
goto out; /* XXX need refcount? */
}
- /* If we are a PV guest, we don't have GSIs (no ACPI passed). Therefore
- * we are using the !xen_initial_domain() to drop in the function.*/
- if (identity_mapped_irq(gsi) || (!xen_initial_domain() &&
- xen_pv_domain())) {
- irq = gsi;
- irq_alloc_desc_at(irq, -1);
- } else
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_gsi(gsi);
set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
handle_level_irq, name);
* this in the priv domain. */
if (xen_initial_domain() &&
HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
- irq_free_desc(irq);
+ xen_free_irq(irq);
irq = -ENOSPC;
goto out;
}
}
#ifdef CONFIG_PCI_MSI
-#include <linux/msi.h>
-#include "../pci/msi.h"
-
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc)
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
{
- spin_lock(&irq_mapping_update_lock);
-
- if (alloc & XEN_ALLOC_IRQ) {
- *irq = find_unbound_irq();
- if (*irq == -1)
- goto out;
- }
-
- if (alloc & XEN_ALLOC_PIRQ) {
- *pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI);
- if (*pirq == -1)
- goto out;
- }
+ int rc;
+ struct physdev_get_free_pirq op_get_free_pirq;
- set_irq_chip_and_handler_name(*irq, &xen_pirq_chip,
- handle_level_irq, name);
+ op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
+ rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
- irq_info[*irq] = mk_pirq_info(0, *pirq, 0, 0);
- pirq_to_irq[*pirq] = *irq;
+ WARN_ONCE(rc == -ENOSYS,
+ "hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n");
-out:
- spin_unlock(&irq_mapping_update_lock);
+ return rc ? -1 : op_get_free_pirq.pirq;
}
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+ int pirq, int vector, const char *name)
{
- int irq = -1;
- struct physdev_map_pirq map_irq;
- int rc;
- int pos;
- u32 table_offset, bir;
-
- memset(&map_irq, 0, sizeof(map_irq));
- map_irq.domid = DOMID_SELF;
- map_irq.type = MAP_PIRQ_TYPE_MSI;
- map_irq.index = -1;
- map_irq.pirq = -1;
- map_irq.bus = dev->bus->number;
- map_irq.devfn = dev->devfn;
-
- if (type == PCI_CAP_ID_MSIX) {
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-
- pci_read_config_dword(dev, msix_table_offset_reg(pos),
- &table_offset);
- bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
-
- map_irq.table_base = pci_resource_start(dev, bir);
- map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
- }
+ int irq, ret;
spin_lock(&irq_mapping_update_lock);
- irq = find_unbound_irq();
-
+ irq = xen_allocate_irq_dynamic();
if (irq == -1)
goto out;
- rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
- if (rc) {
- printk(KERN_WARNING "xen map irq failed %d\n", rc);
-
- irq_free_desc(irq);
-
- irq = -1;
- goto out;
- }
- irq_info[irq] = mk_pirq_info(0, map_irq.pirq, 0, map_irq.index);
-
set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
- handle_level_irq,
- (type == PCI_CAP_ID_MSIX) ? "msi-x":"msi");
+ handle_level_irq, name);
+ irq_info[irq] = mk_pirq_info(0, pirq, 0, vector);
+ pirq_to_irq[pirq] = irq;
+ ret = irq_set_msi_desc(irq, msidesc);
+ if (ret < 0)
+ goto error_irq;
out:
spin_unlock(&irq_mapping_update_lock);
return irq;
+error_irq:
+ spin_unlock(&irq_mapping_update_lock);
+ xen_free_irq(irq);
+ return -1;
}
#endif
printk(KERN_WARNING "unmap irq failed %d\n", rc);
goto out;
}
- pirq_to_irq[info->u.pirq.pirq] = -1;
}
+ pirq_to_irq[info->u.pirq.pirq] = -1;
+
irq_info[irq] = mk_unbound_info();
- irq_free_desc(irq);
+ xen_free_irq(irq);
out:
spin_unlock(&irq_mapping_update_lock);
irq = evtchn_to_irq[evtchn];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
handle_fasteoi_irq, "event");
irq = per_cpu(ipi_to_irq, cpu)[ipi];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
if (irq < 0)
goto out;
irq = per_cpu(virq_to_irq, cpu)[virq];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
handle_percpu_irq, "virq");
if (irq_info[irq].type != IRQT_UNBOUND) {
irq_info[irq] = mk_unbound_info();
- irq_free_desc(irq);
+ xen_free_irq(irq);
}
spin_unlock(&irq_mapping_update_lock);
if (irq < 0)
return irq;
- irqflags |= IRQF_NO_SUSPEND;
+ irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
if (retval != 0) {
unbind_from_irq(irq);
return 0;
}
-static int set_affinity_irq(unsigned irq, const struct cpumask *dest)
+static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
+ bool force)
{
unsigned tcpu = cpumask_first(dest);
- return rebind_irq_to_cpu(irq, tcpu);
+ return rebind_irq_to_cpu(data->irq, tcpu);
}
int resend_irq_on_evtchn(unsigned int irq)
return 1;
}
-static void enable_dynirq(unsigned int irq)
+static void enable_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
if (VALID_EVTCHN(evtchn))
unmask_evtchn(evtchn);
}
-static void disable_dynirq(unsigned int irq)
+static void disable_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
if (VALID_EVTCHN(evtchn))
mask_evtchn(evtchn);
}
-static void ack_dynirq(unsigned int irq)
+static void ack_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
- move_masked_irq(irq);
+ move_masked_irq(data->irq);
if (VALID_EVTCHN(evtchn))
unmask_evtchn(evtchn);
}
-static int retrigger_dynirq(unsigned int irq)
+static int retrigger_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
struct shared_info *sh = HYPERVISOR_shared_info;
int ret = 0;
printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
- startup_pirq(irq);
+ __startup_pirq(irq);
}
}
void xen_irq_resume(void)
{
unsigned int cpu, irq, evtchn;
- struct irq_desc *desc;
init_evtchn_cpu_bindings();
restore_cpu_ipis(cpu);
}
- /*
- * Unmask any IRQF_NO_SUSPEND IRQs which are enabled. These
- * are not handled by the IRQ core.
- */
- for_each_irq_desc(irq, desc) {
- if (!desc->action || !(desc->action->flags & IRQF_NO_SUSPEND))
- continue;
- if (desc->status & IRQ_DISABLED)
- continue;
-
- evtchn = evtchn_from_irq(irq);
- if (evtchn == -1)
- continue;
-
- unmask_evtchn(evtchn);
- }
-
restore_cpu_pirqs();
}
static struct irq_chip xen_dynamic_chip __read_mostly = {
- .name = "xen-dyn",
+ .name = "xen-dyn",
- .disable = disable_dynirq,
- .mask = disable_dynirq,
- .unmask = enable_dynirq,
+ .irq_disable = disable_dynirq,
+ .irq_mask = disable_dynirq,
+ .irq_unmask = enable_dynirq,
- .eoi = ack_dynirq,
- .set_affinity = set_affinity_irq,
- .retrigger = retrigger_dynirq,
+ .irq_eoi = ack_dynirq,
+ .irq_set_affinity = set_affinity_irq,
+ .irq_retrigger = retrigger_dynirq,
};
static struct irq_chip xen_pirq_chip __read_mostly = {
- .name = "xen-pirq",
+ .name = "xen-pirq",
- .startup = startup_pirq,
- .shutdown = shutdown_pirq,
+ .irq_startup = startup_pirq,
+ .irq_shutdown = shutdown_pirq,
- .enable = enable_pirq,
- .unmask = enable_pirq,
+ .irq_enable = enable_pirq,
+ .irq_unmask = enable_pirq,
- .disable = disable_pirq,
- .mask = disable_pirq,
+ .irq_disable = disable_pirq,
+ .irq_mask = disable_pirq,
- .ack = ack_pirq,
- .end = end_pirq,
+ .irq_ack = ack_pirq,
- .set_affinity = set_affinity_irq,
+ .irq_set_affinity = set_affinity_irq,
- .retrigger = retrigger_dynirq,
+ .irq_retrigger = retrigger_dynirq,
};
static struct irq_chip xen_percpu_chip __read_mostly = {
- .name = "xen-percpu",
+ .name = "xen-percpu",
- .disable = disable_dynirq,
- .mask = disable_dynirq,
- .unmask = enable_dynirq,
+ .irq_disable = disable_dynirq,
+ .irq_mask = disable_dynirq,
+ .irq_unmask = enable_dynirq,
- .ack = ack_dynirq,
+ .irq_ack = ack_dynirq,
};
int xen_set_callback_via(uint64_t via)
/* Ignore multiple shutdown requests. */
static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
-#ifdef CONFIG_PM_SLEEP
-static int xen_hvm_suspend(void *data)
-{
- struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
- int *cancelled = data;
-
- BUG_ON(!irqs_disabled());
-
- *cancelled = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
+struct suspend_info {
+ int cancelled;
+ unsigned long arg; /* extra hypercall argument */
+ void (*pre)(void);
+ void (*post)(int cancelled);
+};
- xen_hvm_post_suspend(*cancelled);
+static void xen_hvm_post_suspend(int cancelled)
+{
+ xen_arch_hvm_post_suspend(cancelled);
gnttab_resume();
+}
- if (!*cancelled) {
- xen_irq_resume();
- xen_console_resume();
- xen_timer_resume();
- }
+static void xen_pre_suspend(void)
+{
+ xen_mm_pin_all();
+ gnttab_suspend();
+ xen_arch_pre_suspend();
+}
- return 0;
+static void xen_post_suspend(int cancelled)
+{
+ xen_arch_post_suspend(cancelled);
+ gnttab_resume();
+ xen_mm_unpin_all();
}
+#ifdef CONFIG_PM_SLEEP
static int xen_suspend(void *data)
{
+ struct suspend_info *si = data;
int err;
- int *cancelled = data;
BUG_ON(!irqs_disabled());
return err;
}
- xen_mm_pin_all();
- gnttab_suspend();
- xen_pre_suspend();
+ if (si->pre)
+ si->pre();
/*
* This hypercall returns 1 if suspend was cancelled
* or the domain was merely checkpointed, and 0 if it
* is resuming in a new domain.
*/
- *cancelled = HYPERVISOR_suspend(virt_to_mfn(xen_start_info));
+ si->cancelled = HYPERVISOR_suspend(si->arg);
- xen_post_suspend(*cancelled);
- gnttab_resume();
- xen_mm_unpin_all();
+ if (si->post)
+ si->post(si->cancelled);
- if (!*cancelled) {
+ if (!si->cancelled) {
xen_irq_resume();
xen_console_resume();
xen_timer_resume();
static void do_suspend(void)
{
int err;
- int cancelled = 1;
+ struct suspend_info si;
shutting_down = SHUTDOWN_SUSPEND;
goto out_resume;
}
- if (xen_hvm_domain())
- err = stop_machine(xen_hvm_suspend, &cancelled, cpumask_of(0));
- else
- err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
+ si.cancelled = 1;
+
+ if (xen_hvm_domain()) {
+ si.arg = 0UL;
+ si.pre = NULL;
+ si.post = &xen_hvm_post_suspend;
+ } else {
+ si.arg = virt_to_mfn(xen_start_info);
+ si.pre = &xen_pre_suspend;
+ si.post = &xen_post_suspend;
+ }
+
+ err = stop_machine(xen_suspend, &si, cpumask_of(0));
dpm_resume_noirq(PMSG_RESUME);
if (err) {
printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
- cancelled = 1;
+ si.cancelled = 1;
}
out_resume:
- if (!cancelled) {
+ if (!si.cancelled) {
xen_arch_resume();
xs_resume();
} else
}
#endif /* CONFIG_PM_SLEEP */
+struct shutdown_handler {
+ const char *command;
+ void (*cb)(void);
+};
+
+static void do_poweroff(void)
+{
+ shutting_down = SHUTDOWN_POWEROFF;
+ orderly_poweroff(false);
+}
+
+static void do_reboot(void)
+{
+ shutting_down = SHUTDOWN_POWEROFF; /* ? */
+ ctrl_alt_del();
+}
+
static void shutdown_handler(struct xenbus_watch *watch,
const char **vec, unsigned int len)
{
char *str;
struct xenbus_transaction xbt;
int err;
+ static struct shutdown_handler handlers[] = {
+ { "poweroff", do_poweroff },
+ { "halt", do_poweroff },
+ { "reboot", do_reboot },
+#ifdef CONFIG_PM_SLEEP
+ { "suspend", do_suspend },
+#endif
+ {NULL, NULL},
+ };
+ static struct shutdown_handler *handler;
if (shutting_down != SHUTDOWN_INVALID)
return;
return;
}
- xenbus_write(xbt, "control", "shutdown", "");
+ for (handler = &handlers[0]; handler->command; handler++) {
+ if (strcmp(str, handler->command) == 0)
+ break;
+ }
+
+ /* Only acknowledge commands which we are prepared to handle. */
+ if (handler->cb)
+ xenbus_write(xbt, "control", "shutdown", "");
err = xenbus_transaction_end(xbt, 0);
if (err == -EAGAIN) {
goto again;
}
- if (strcmp(str, "poweroff") == 0 ||
- strcmp(str, "halt") == 0) {
- shutting_down = SHUTDOWN_POWEROFF;
- orderly_poweroff(false);
- } else if (strcmp(str, "reboot") == 0) {
- shutting_down = SHUTDOWN_POWEROFF; /* ? */
- ctrl_alt_del();
-#ifdef CONFIG_PM_SLEEP
- } else if (strcmp(str, "suspend") == 0) {
- do_suspend();
-#endif
+ if (handler->cb) {
+ handler->cb();
} else {
printk(KERN_INFO "Ignoring shutdown request: %s\n", str);
shutting_down = SHUTDOWN_INVALID;
return NOTIFY_DONE;
}
-static int __init __setup_shutdown_event(void)
-{
- /* Delay initialization in the PV on HVM case */
- if (xen_hvm_domain())
- return 0;
-
- if (!xen_pv_domain())
- return -ENODEV;
-
- return xen_setup_shutdown_event();
-}
-
int xen_setup_shutdown_event(void)
{
static struct notifier_block xenstore_notifier = {
.notifier_call = shutdown_event
};
+
+ if (!xen_domain())
+ return -ENODEV;
register_xenstore_notifier(&xenstore_notifier);
return 0;
}
EXPORT_SYMBOL_GPL(xen_setup_shutdown_event);
-subsys_initcall(__setup_shutdown_event);
+subsys_initcall(xen_setup_shutdown_event);
if (ret)
goto out;
xenbus_probe(NULL);
- ret = xen_setup_shutdown_event();
- if (ret)
- goto out;
return 0;
out:
def_bool n
config EXPORTFS
- tristate
+ bool
config FILE_LOCKING
bool "Enable POSIX file locking API" if EXPERT
obj-$(CONFIG_NFS_COMMON) += nfs_common/
obj-$(CONFIG_GENERIC_ACL) += generic_acl.o
+obj-$(CONFIG_FHANDLE) += fhandle.o
+
obj-y += quota/
obj-$(CONFIG_PROC_FS) += proc/
candidate->first = candidate->last = index;
candidate->offset_first = from;
candidate->to_last = to;
+ INIT_LIST_HEAD(&candidate->link);
candidate->usage = 1;
candidate->state = AFS_WBACK_PENDING;
init_waitqueue_head(&candidate->waitq);
call_rcu(&ctx->rcu_head, ctx_rcu_free);
}
-#define get_ioctx(kioctx) do { \
- BUG_ON(atomic_read(&(kioctx)->users) <= 0); \
- atomic_inc(&(kioctx)->users); \
-} while (0)
-#define put_ioctx(kioctx) do { \
- BUG_ON(atomic_read(&(kioctx)->users) <= 0); \
- if (unlikely(atomic_dec_and_test(&(kioctx)->users))) \
- __put_ioctx(kioctx); \
-} while (0)
+static inline void get_ioctx(struct kioctx *kioctx)
+{
+ BUG_ON(atomic_read(&kioctx->users) <= 0);
+ atomic_inc(&kioctx->users);
+}
+
+static inline int try_get_ioctx(struct kioctx *kioctx)
+{
+ return atomic_inc_not_zero(&kioctx->users);
+}
+
+static inline void put_ioctx(struct kioctx *kioctx)
+{
+ BUG_ON(atomic_read(&kioctx->users) <= 0);
+ if (unlikely(atomic_dec_and_test(&kioctx->users)))
+ __put_ioctx(kioctx);
+}
/* ioctx_alloc
* Allocates and initializes an ioctx. Returns an ERR_PTR if it failed.
rcu_read_lock();
hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) {
- if (ctx->user_id == ctx_id && !ctx->dead) {
- get_ioctx(ctx);
+ /*
+ * RCU protects us against accessing freed memory but
+ * we have to be careful not to get a reference when the
+ * reference count already dropped to 0 (ctx->dead test
+ * is unreliable because of races).
+ */
+ if (ctx->user_id == ctx_id && !ctx->dead && try_get_ioctx(ctx)){
ret = ctx;
break;
}
goto out_put_req;
spin_lock_irq(&ctx->ctx_lock);
+ /*
+ * We could have raced with io_destroy() and are currently holding a
+ * reference to ctx which should be destroyed. We cannot submit IO
+ * since ctx gets freed as soon as io_submit() puts its reference. The
+ * check here is reliable: io_destroy() sets ctx->dead before waiting
+ * for outstanding IO and the barrier between these two is realized by
+ * unlock of mm->ioctx_lock and lock of ctx->ctx_lock. Analogously we
+ * increment ctx->reqs_active before checking for ctx->dead and the
+ * barrier is realized by unlock and lock of ctx->ctx_lock. Thus if we
+ * don't see ctx->dead set here, io_destroy() waits for our IO to
+ * finish.
+ */
+ if (ctx->dead) {
+ spin_unlock_irq(&ctx->ctx_lock);
+ ret = -EINVAL;
+ goto out_put_req;
+ }
aio_run_iocb(req);
if (!list_empty(&ctx->run_list)) {
/* drain the run list */
ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
if (ret)
goto out_del;
+ /*
+ * bdev could be deleted beneath us which would implicitly destroy
+ * the holder directory. Hold on to it.
+ */
+ kobject_get(bdev->bd_part->holder_dir);
list_add(&holder->list, &bdev->bd_holder_disks);
goto out_unlock;
del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
del_symlink(bdev->bd_part->holder_dir,
&disk_to_dev(disk)->kobj);
+ kobject_put(bdev->bd_part->holder_dir);
list_del_init(&holder->list);
kfree(holder);
}
* flush_disk - invalidates all buffer-cache entries on a disk
*
* @bdev: struct block device to be flushed
+ * @kill_dirty: flag to guide handling of dirty inodes
*
* Invalidates all buffer-cache entries on a disk. It should be called
* when a disk has been changed -- either by a media change or online
* resize.
*/
-static void flush_disk(struct block_device *bdev)
+static void flush_disk(struct block_device *bdev, bool kill_dirty)
{
- if (__invalidate_device(bdev)) {
+ if (__invalidate_device(bdev, kill_dirty)) {
char name[BDEVNAME_SIZE] = "";
if (bdev->bd_disk)
"%s: detected capacity change from %lld to %lld\n",
name, bdev_size, disk_size);
i_size_write(bdev->bd_inode, disk_size);
- flush_disk(bdev);
+ flush_disk(bdev, false);
}
}
EXPORT_SYMBOL(check_disk_size_change);
if (!(events & DISK_EVENT_MEDIA_CHANGE))
return 0;
- flush_disk(bdev);
+ flush_disk(bdev, true);
if (bdops->revalidate_disk)
bdops->revalidate_disk(bdev->bd_disk);
return 1;
res = __blkdev_get(bdev, mode, 0);
- /* __blkdev_get() may alter read only status, check it afterwards */
- if (!res && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
- __blkdev_put(bdev, mode, 0);
- res = -EACCES;
- }
-
if (whole) {
/* finish claiming */
mutex_lock(&bdev->bd_mutex);
if (err)
return ERR_PTR(err);
+ if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+ blkdev_put(bdev, mode);
+ return ERR_PTR(-EACCES);
+ }
+
return bdev;
}
EXPORT_SYMBOL(blkdev_get_by_path);
}
EXPORT_SYMBOL(lookup_bdev);
-int __invalidate_device(struct block_device *bdev)
+int __invalidate_device(struct block_device *bdev, bool kill_dirty)
{
struct super_block *sb = get_super(bdev);
int res = 0;
* hold).
*/
shrink_dcache_sb(sb);
- res = invalidate_inodes(sb);
+ res = invalidate_inodes(sb, kill_dirty);
drop_super(sb);
}
invalidate_bdev(bdev);
u64 disk_total; /* total bytes on disk, takes mirrors into
account */
+ /*
+ * we bump reservation progress every time we decrement
+ * bytes_reserved. This way people waiting for reservations
+ * know something good has happened and they can check
+ * for progress. The number here isn't to be trusted, it
+ * just shows reclaim activity
+ */
+ unsigned long reservation_progress;
+
int full; /* indicates that we cannot allocate any more
chunks for this space */
int force_alloc; /* set if we need to force a chunk alloc for
#define BTRFS_MOUNT_SPACE_CACHE (1 << 12)
#define BTRFS_MOUNT_CLEAR_CACHE (1 << 13)
#define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14)
+#define BTRFS_MOUNT_ENOSPC_DEBUG (1 << 15)
#define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt)
#define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt)
u64 start, u64 end);
int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
u64 num_bytes);
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 type);
/* ctree.c */
int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
tree = &BTRFS_I(page->mapping->host)->io_tree;
- if (page->private == EXTENT_PAGE_PRIVATE)
+ if (page->private == EXTENT_PAGE_PRIVATE) {
+ WARN_ON(1);
goto out;
- if (!page->private)
+ }
+ if (!page->private) {
+ WARN_ON(1);
goto out;
+ }
len = page->private >> 2;
WARN_ON(len == 0);
int len = *max_len;
int type;
- if ((len < BTRFS_FID_SIZE_NON_CONNECTABLE) ||
- (connectable && len < BTRFS_FID_SIZE_CONNECTABLE))
+ if (connectable && (len < BTRFS_FID_SIZE_CONNECTABLE)) {
+ *max_len = BTRFS_FID_SIZE_CONNECTABLE;
return 255;
+ } else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) {
+ *max_len = BTRFS_FID_SIZE_NON_CONNECTABLE;
+ return 255;
+ }
len = BTRFS_FID_SIZE_NON_CONNECTABLE;
type = FILEID_BTRFS_WITHOUT_PARENT;
u64 max_reclaim;
u64 reclaimed = 0;
long time_left;
- int pause = 1;
int nr_pages = (2 * 1024 * 1024) >> PAGE_CACHE_SHIFT;
int loops = 0;
+ unsigned long progress;
block_rsv = &root->fs_info->delalloc_block_rsv;
space_info = block_rsv->space_info;
smp_mb();
reserved = space_info->bytes_reserved;
+ progress = space_info->reservation_progress;
if (reserved == 0)
return 0;
writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages);
spin_lock(&space_info->lock);
- if (reserved > space_info->bytes_reserved) {
- loops = 0;
+ if (reserved > space_info->bytes_reserved)
reclaimed += reserved - space_info->bytes_reserved;
- } else {
- loops++;
- }
reserved = space_info->bytes_reserved;
spin_unlock(&space_info->lock);
+ loops++;
+
if (reserved == 0 || reclaimed >= max_reclaim)
break;
if (trans && trans->transaction->blocked)
return -EAGAIN;
- __set_current_state(TASK_INTERRUPTIBLE);
- time_left = schedule_timeout(pause);
+ time_left = schedule_timeout_interruptible(1);
/* We were interrupted, exit */
if (time_left)
break;
- pause <<= 1;
- if (pause > HZ / 10)
- pause = HZ / 10;
+ /* we've kicked the IO a few times, if anything has been freed,
+ * exit. There is no sense in looping here for a long time
+ * when we really need to commit the transaction, or there are
+ * just too many writers without enough free space
+ */
+
+ if (loops > 3) {
+ smp_mb();
+ if (progress != space_info->reservation_progress)
+ break;
+ }
}
return reclaimed >= to_reclaim;
if (num_bytes) {
spin_lock(&space_info->lock);
space_info->bytes_reserved -= num_bytes;
+ space_info->reservation_progress++;
spin_unlock(&space_info->lock);
}
}
if (block_rsv->reserved >= block_rsv->size) {
num_bytes = block_rsv->reserved - block_rsv->size;
sinfo->bytes_reserved -= num_bytes;
+ sinfo->reservation_progress++;
block_rsv->reserved = block_rsv->size;
block_rsv->full = 1;
}
to_reserve = 0;
}
spin_unlock(&BTRFS_I(inode)->accounting_lock);
-
to_reserve += calc_csum_metadata_size(inode, num_bytes);
ret = reserve_metadata_bytes(NULL, root, block_rsv, to_reserve, 1);
if (ret)
btrfs_set_block_group_used(&cache->item, old_val);
cache->reserved -= num_bytes;
cache->space_info->bytes_reserved -= num_bytes;
+ cache->space_info->reservation_progress++;
cache->space_info->bytes_used += num_bytes;
cache->space_info->disk_used += num_bytes * factor;
spin_unlock(&cache->lock);
if (reserved) {
cache->reserved -= num_bytes;
cache->space_info->bytes_reserved -= num_bytes;
+ cache->space_info->reservation_progress++;
}
spin_unlock(&cache->lock);
spin_unlock(&cache->space_info->lock);
space_info->bytes_readonly += num_bytes;
cache->reserved -= num_bytes;
space_info->bytes_reserved -= num_bytes;
+ space_info->reservation_progress++;
}
spin_unlock(&cache->lock);
spin_unlock(&space_info->lock);
if (ret) {
spin_lock(&cache->space_info->lock);
cache->space_info->bytes_reserved -= buf->len;
+ cache->space_info->reservation_progress++;
spin_unlock(&cache->space_info->lock);
}
goto out;
num_bytes, data, 1);
goto again;
}
- if (ret == -ENOSPC) {
+ if (ret == -ENOSPC && btrfs_test_opt(root, ENOSPC_DEBUG)) {
struct btrfs_space_info *sinfo;
sinfo = __find_space_info(root->fs_info, data);
u64 end = start + extent_key->offset - 1;
em = alloc_extent_map(GFP_NOFS);
- BUG_ON(!em || IS_ERR(em));
+ BUG_ON(!em);
em->start = start;
em->len = extent_key->offset;
return ret;
}
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 type)
+{
+ u64 alloc_flags = get_alloc_profile(root, type);
+ return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+}
+
/*
* helper to account the unused space of all the readonly block group in the
* list. takes mirrors into account.
*/
u64 count_range_bits(struct extent_io_tree *tree,
u64 *start, u64 search_end, u64 max_bytes,
- unsigned long bits)
+ unsigned long bits, int contig)
{
struct rb_node *node;
struct extent_state *state;
u64 cur_start = *start;
u64 total_bytes = 0;
+ u64 last = 0;
int found = 0;
if (search_end <= cur_start) {
state = rb_entry(node, struct extent_state, rb_node);
if (state->start > search_end)
break;
- if (state->end >= cur_start && (state->state & bits)) {
+ if (contig && found && state->start > last + 1)
+ break;
+ if (state->end >= cur_start && (state->state & bits) == bits) {
total_bytes += min(search_end, state->end) + 1 -
max(cur_start, state->start);
if (total_bytes >= max_bytes)
*start = state->start;
found = 1;
}
+ last = state->end;
+ } else if (contig && found) {
+ break;
}
node = rb_next(node);
if (!node)
static void set_page_extent_head(struct page *page, unsigned long len)
{
+ WARN_ON(!PagePrivate(page));
set_page_private(page, EXTENT_PAGE_PRIVATE_FIRST_PAGE | len << 2);
}
* at this point we can safely clear everything except the
* locked bit and the nodatasum bit
*/
- clear_extent_bit(tree, start, end,
+ ret = clear_extent_bit(tree, start, end,
~(EXTENT_LOCKED | EXTENT_NODATASUM),
0, 0, NULL, mask);
+
+ /* if clear_extent_bit failed for enomem reasons,
+ * we can't allow the release to continue.
+ */
+ if (ret < 0)
+ ret = 0;
+ else
+ ret = 1;
}
return ret;
}
return sector;
}
+/*
+ * helper function for fiemap, which doesn't want to see any holes.
+ * This maps until we find something past 'last'
+ */
+static struct extent_map *get_extent_skip_holes(struct inode *inode,
+ u64 offset,
+ u64 last,
+ get_extent_t *get_extent)
+{
+ u64 sectorsize = BTRFS_I(inode)->root->sectorsize;
+ struct extent_map *em;
+ u64 len;
+
+ if (offset >= last)
+ return NULL;
+
+ while(1) {
+ len = last - offset;
+ if (len == 0)
+ break;
+ len = (len + sectorsize - 1) & ~(sectorsize - 1);
+ em = get_extent(inode, NULL, 0, offset, len, 0);
+ if (!em || IS_ERR(em))
+ return em;
+
+ /* if this isn't a hole return it */
+ if (!test_bit(EXTENT_FLAG_VACANCY, &em->flags) &&
+ em->block_start != EXTENT_MAP_HOLE) {
+ return em;
+ }
+
+ /* this is a hole, advance to the next extent */
+ offset = extent_map_end(em);
+ free_extent_map(em);
+ if (offset >= last)
+ break;
+ }
+ return NULL;
+}
+
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len, get_extent_t *get_extent)
{
u32 flags = 0;
u32 found_type;
u64 last;
+ u64 last_for_get_extent = 0;
u64 disko = 0;
+ u64 isize = i_size_read(inode);
struct btrfs_key found_key;
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
struct btrfs_path *path;
struct btrfs_file_extent_item *item;
int end = 0;
- u64 em_start = 0, em_len = 0;
+ u64 em_start = 0;
+ u64 em_len = 0;
+ u64 em_end = 0;
unsigned long emflags;
- int hole = 0;
if (len == 0)
return -EINVAL;
return -ENOMEM;
path->leave_spinning = 1;
+ /*
+ * lookup the last file extent. We're not using i_size here
+ * because there might be preallocation past i_size
+ */
ret = btrfs_lookup_file_extent(NULL, BTRFS_I(inode)->root,
path, inode->i_ino, -1, 0);
if (ret < 0) {
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
- /* No extents, just return */
+ /* No extents, but there might be delalloc bits */
if (found_key.objectid != inode->i_ino ||
found_type != BTRFS_EXTENT_DATA_KEY) {
- btrfs_free_path(path);
- return 0;
+ /* have to trust i_size as the end */
+ last = (u64)-1;
+ last_for_get_extent = isize;
+ } else {
+ /*
+ * remember the start of the last extent. There are a
+ * bunch of different factors that go into the length of the
+ * extent, so its much less complex to remember where it started
+ */
+ last = found_key.offset;
+ last_for_get_extent = last + 1;
}
- last = found_key.offset;
btrfs_free_path(path);
+ /*
+ * we might have some extents allocated but more delalloc past those
+ * extents. so, we trust isize unless the start of the last extent is
+ * beyond isize
+ */
+ if (last < isize) {
+ last = (u64)-1;
+ last_for_get_extent = isize;
+ }
+
lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0,
&cached_state, GFP_NOFS);
- em = get_extent(inode, NULL, 0, off, max - off, 0);
+
+ em = get_extent_skip_holes(inode, off, last_for_get_extent,
+ get_extent);
if (!em)
goto out;
if (IS_ERR(em)) {
}
while (!end) {
- hole = 0;
- off = em->start + em->len;
- if (off >= max)
- end = 1;
+ u64 offset_in_extent;
- if (em->block_start == EXTENT_MAP_HOLE) {
- hole = 1;
- goto next;
- }
+ /* break if the extent we found is outside the range */
+ if (em->start >= max || extent_map_end(em) < off)
+ break;
- em_start = em->start;
- em_len = em->len;
+ /*
+ * get_extent may return an extent that starts before our
+ * requested range. We have to make sure the ranges
+ * we return to fiemap always move forward and don't
+ * overlap, so adjust the offsets here
+ */
+ em_start = max(em->start, off);
+ /*
+ * record the offset from the start of the extent
+ * for adjusting the disk offset below
+ */
+ offset_in_extent = em_start - em->start;
+ em_end = extent_map_end(em);
+ em_len = em_end - em_start;
+ emflags = em->flags;
disko = 0;
flags = 0;
+ /*
+ * bump off for our next call to get_extent
+ */
+ off = extent_map_end(em);
+ if (off >= max)
+ end = 1;
+
if (em->block_start == EXTENT_MAP_LAST_BYTE) {
end = 1;
flags |= FIEMAP_EXTENT_LAST;
flags |= (FIEMAP_EXTENT_DELALLOC |
FIEMAP_EXTENT_UNKNOWN);
} else {
- disko = em->block_start;
+ disko = em->block_start + offset_in_extent;
}
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
flags |= FIEMAP_EXTENT_ENCODED;
-next:
- emflags = em->flags;
free_extent_map(em);
em = NULL;
- if (!end) {
- em = get_extent(inode, NULL, 0, off, max - off, 0);
- if (!em)
- goto out;
- if (IS_ERR(em)) {
- ret = PTR_ERR(em);
- goto out;
- }
- emflags = em->flags;
- }
-
- if (test_bit(EXTENT_FLAG_VACANCY, &emflags)) {
+ if ((em_start >= last) || em_len == (u64)-1 ||
+ (last == (u64)-1 && isize <= em_end)) {
flags |= FIEMAP_EXTENT_LAST;
end = 1;
}
- if (em_start == last) {
+ /* now scan forward to see if this is really the last extent. */
+ em = get_extent_skip_holes(inode, off, last_for_get_extent,
+ get_extent);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ goto out;
+ }
+ if (!em) {
flags |= FIEMAP_EXTENT_LAST;
end = 1;
}
-
- if (!hole) {
- ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
- em_len, flags);
- if (ret)
- goto out_free;
- }
+ ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
+ em_len, flags);
+ if (ret)
+ goto out_free;
}
out_free:
free_extent_map(em);
}
if (!PageUptodate(p))
uptodate = 0;
- unlock_page(p);
+
+ /*
+ * see below about how we avoid a nasty race with release page
+ * and why we unlock later
+ */
+ if (i != 0)
+ unlock_page(p);
}
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
atomic_inc(&eb->refs);
spin_unlock(&tree->buffer_lock);
radix_tree_preload_end();
+
+ /*
+ * there is a race where release page may have
+ * tried to find this extent buffer in the radix
+ * but failed. It will tell the VM it is safe to
+ * reclaim the, and it will clear the page private bit.
+ * We must make sure to set the page private bit properly
+ * after the extent buffer is in the radix tree so
+ * it doesn't get lost
+ */
+ set_page_extent_mapped(eb->first_page);
+ set_page_extent_head(eb->first_page, eb->len);
+ if (!page0)
+ unlock_page(eb->first_page);
return eb;
free_eb:
+ if (eb->first_page && !page0)
+ unlock_page(eb->first_page);
+
if (!atomic_dec_and_test(&eb->refs))
return exists;
btrfs_release_extent_buffer(eb);
continue;
lock_page(page);
+ WARN_ON(!PagePrivate(page));
+
+ set_page_extent_mapped(page);
if (i == 0)
set_page_extent_head(page, eb->len);
- else
- set_page_private(page, EXTENT_PAGE_PRIVATE);
clear_page_dirty_for_io(page);
spin_lock_irq(&page->mapping->tree_lock);
for (i = start_i; i < num_pages; i++) {
page = extent_buffer_page(eb, i);
+
+ WARN_ON(!PagePrivate(page));
+
+ set_page_extent_mapped(page);
+ if (i == 0)
+ set_page_extent_head(page, eb->len);
+
if (inc_all_pages)
page_cache_get(page);
if (!PageUptodate(page)) {
u64 count_range_bits(struct extent_io_tree *tree,
u64 *start, u64 search_end,
- u64 max_bytes, unsigned long bits);
+ u64 max_bytes, unsigned long bits, int contig);
void free_extent_state(struct extent_state *state);
int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
{
struct extent_map *em;
em = kmem_cache_alloc(extent_map_cache, mask);
- if (!em || IS_ERR(em))
- return em;
+ if (!em)
+ return NULL;
em->in_tree = 0;
em->flags = 0;
em->compress_type = BTRFS_COMPRESS_NONE;
/* Flush processor's dcache for this page */
flush_dcache_page(page);
+
+ /*
+ * if we get a partial write, we can end up with
+ * partially up to date pages. These add
+ * a lot of complexity, so make sure they don't
+ * happen by forcing this copy to be retried.
+ *
+ * The rest of the btrfs_file_write code will fall
+ * back to page at a time copies after we return 0.
+ */
+ if (!PageUptodate(page) && copied < count)
+ copied = 0;
+
iov_iter_advance(i, copied);
write_bytes -= copied;
total_copied += copied;
split = alloc_extent_map(GFP_NOFS);
if (!split2)
split2 = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!split || !split2);
write_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
return 0;
}
+/*
+ * on error we return an unlocked page and the error value
+ * on success we return a locked page and 0
+ */
+static int prepare_uptodate_page(struct page *page, u64 pos)
+{
+ int ret = 0;
+
+ if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) {
+ ret = btrfs_readpage(NULL, page);
+ if (ret)
+ return ret;
+ lock_page(page);
+ if (!PageUptodate(page)) {
+ unlock_page(page);
+ return -EIO;
+ }
+ }
+ return 0;
+}
+
/*
* this gets pages into the page cache and locks them down, it also properly
* waits for data=ordered extents to finish before allowing the pages to be
unsigned long index = pos >> PAGE_CACHE_SHIFT;
struct inode *inode = fdentry(file)->d_inode;
int err = 0;
+ int faili = 0;
u64 start_pos;
u64 last_pos;
for (i = 0; i < num_pages; i++) {
pages[i] = grab_cache_page(inode->i_mapping, index + i);
if (!pages[i]) {
- int c;
- for (c = i - 1; c >= 0; c--) {
- unlock_page(pages[c]);
- page_cache_release(pages[c]);
- }
- return -ENOMEM;
+ faili = i - 1;
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ if (i == 0)
+ err = prepare_uptodate_page(pages[i], pos);
+ if (i == num_pages - 1)
+ err = prepare_uptodate_page(pages[i],
+ pos + write_bytes);
+ if (err) {
+ page_cache_release(pages[i]);
+ faili = i - 1;
+ goto fail;
}
wait_on_page_writeback(pages[i]);
}
+ err = 0;
if (start_pos < inode->i_size) {
struct btrfs_ordered_extent *ordered;
lock_extent_bits(&BTRFS_I(inode)->io_tree,
WARN_ON(!PageLocked(pages[i]));
}
return 0;
+fail:
+ while (faili >= 0) {
+ unlock_page(pages[faili]);
+ page_cache_release(pages[faili]);
+ faili--;
+ }
+ return err;
+
}
static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
struct file *file = iocb->ki_filp;
struct inode *inode = fdentry(file)->d_inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct page *pinned[2];
struct page **pages = NULL;
struct iov_iter i;
loff_t *ppos = &iocb->ki_pos;
will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
(file->f_flags & O_DIRECT));
- pinned[0] = NULL;
- pinned[1] = NULL;
-
start_pos = pos;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
first_index = pos >> PAGE_CACHE_SHIFT;
last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT;
- /*
- * there are lots of better ways to do this, but this code
- * makes sure the first and last page in the file range are
- * up to date and ready for cow
- */
- if ((pos & (PAGE_CACHE_SIZE - 1))) {
- pinned[0] = grab_cache_page(inode->i_mapping, first_index);
- if (!PageUptodate(pinned[0])) {
- ret = btrfs_readpage(NULL, pinned[0]);
- BUG_ON(ret);
- wait_on_page_locked(pinned[0]);
- } else {
- unlock_page(pinned[0]);
- }
- }
- if ((pos + iov_iter_count(&i)) & (PAGE_CACHE_SIZE - 1)) {
- pinned[1] = grab_cache_page(inode->i_mapping, last_index);
- if (!PageUptodate(pinned[1])) {
- ret = btrfs_readpage(NULL, pinned[1]);
- BUG_ON(ret);
- wait_on_page_locked(pinned[1]);
- } else {
- unlock_page(pinned[1]);
- }
- }
-
while (iov_iter_count(&i) > 0) {
size_t offset = pos & (PAGE_CACHE_SIZE - 1);
size_t write_bytes = min(iov_iter_count(&i),
copied = btrfs_copy_from_user(pos, num_pages,
write_bytes, pages, &i);
- dirty_pages = (copied + offset + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT;
+
+ /*
+ * if we have trouble faulting in the pages, fall
+ * back to one page at a time
+ */
+ if (copied < write_bytes)
+ nrptrs = 1;
+
+ if (copied == 0)
+ dirty_pages = 0;
+ else
+ dirty_pages = (copied + offset +
+ PAGE_CACHE_SIZE - 1) >>
+ PAGE_CACHE_SHIFT;
if (num_pages > dirty_pages) {
if (copied > 0)
err = ret;
kfree(pages);
- if (pinned[0])
- page_cache_release(pinned[0]);
- if (pinned[1])
- page_cache_release(pinned[1]);
*ppos = pos;
/*
async_extent->ram_size - 1, 0);
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = async_extent->start;
em->len = async_extent->ram_size;
em->orig_start = em->start;
BUG_ON(ret);
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = start;
em->orig_start = em->start;
ram_size = ins.offset;
struct extent_map_tree *em_tree;
em_tree = &BTRFS_I(inode)->extent_tree;
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = cur_offset;
em->orig_start = em->start;
em->len = num_bytes;
private = 0;
if (count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private,
- (u64)-1, 1, EXTENT_DIRTY)) {
+ (u64)-1, 1, EXTENT_DIRTY, 0)) {
ret = get_state_private(&BTRFS_I(inode)->io_failure_tree,
start, &private_failure);
if (ret == 0) {
int err;
int drop_inode = 0;
- if (inode->i_nlink == 0)
- return -ENOENT;
-
/* do not allow sys_link's with other subvols of the same device */
if (root->objectid != BTRFS_I(inode)->root->objectid)
return -EPERM;
goto fail;
/*
- * 1 item for inode ref
+ * 2 items for inode and inode ref
* 2 items for dir items
+ * 1 item for parent inode
*/
- trans = btrfs_start_transaction(root, 3);
+ trans = btrfs_start_transaction(root, 5);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto fail;
return em;
}
+struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
+ size_t pg_offset, u64 start, u64 len,
+ int create)
+{
+ struct extent_map *em;
+ struct extent_map *hole_em = NULL;
+ u64 range_start = start;
+ u64 end;
+ u64 found;
+ u64 found_end;
+ int err = 0;
+
+ em = btrfs_get_extent(inode, page, pg_offset, start, len, create);
+ if (IS_ERR(em))
+ return em;
+ if (em) {
+ /*
+ * if our em maps to a hole, there might
+ * actually be delalloc bytes behind it
+ */
+ if (em->block_start != EXTENT_MAP_HOLE)
+ return em;
+ else
+ hole_em = em;
+ }
+
+ /* check to see if we've wrapped (len == -1 or similar) */
+ end = start + len;
+ if (end < start)
+ end = (u64)-1;
+ else
+ end -= 1;
+
+ em = NULL;
+
+ /* ok, we didn't find anything, lets look for delalloc */
+ found = count_range_bits(&BTRFS_I(inode)->io_tree, &range_start,
+ end, len, EXTENT_DELALLOC, 1);
+ found_end = range_start + found;
+ if (found_end < range_start)
+ found_end = (u64)-1;
+
+ /*
+ * we didn't find anything useful, return
+ * the original results from get_extent()
+ */
+ if (range_start > end || found_end <= start) {
+ em = hole_em;
+ hole_em = NULL;
+ goto out;
+ }
+
+ /* adjust the range_start to make sure it doesn't
+ * go backwards from the start they passed in
+ */
+ range_start = max(start,range_start);
+ found = found_end - range_start;
+
+ if (found > 0) {
+ u64 hole_start = start;
+ u64 hole_len = len;
+
+ em = alloc_extent_map(GFP_NOFS);
+ if (!em) {
+ err = -ENOMEM;
+ goto out;
+ }
+ /*
+ * when btrfs_get_extent can't find anything it
+ * returns one huge hole
+ *
+ * make sure what it found really fits our range, and
+ * adjust to make sure it is based on the start from
+ * the caller
+ */
+ if (hole_em) {
+ u64 calc_end = extent_map_end(hole_em);
+
+ if (calc_end <= start || (hole_em->start > end)) {
+ free_extent_map(hole_em);
+ hole_em = NULL;
+ } else {
+ hole_start = max(hole_em->start, start);
+ hole_len = calc_end - hole_start;
+ }
+ }
+ em->bdev = NULL;
+ if (hole_em && range_start > hole_start) {
+ /* our hole starts before our delalloc, so we
+ * have to return just the parts of the hole
+ * that go until the delalloc starts
+ */
+ em->len = min(hole_len,
+ range_start - hole_start);
+ em->start = hole_start;
+ em->orig_start = hole_start;
+ /*
+ * don't adjust block start at all,
+ * it is fixed at EXTENT_MAP_HOLE
+ */
+ em->block_start = hole_em->block_start;
+ em->block_len = hole_len;
+ } else {
+ em->start = range_start;
+ em->len = found;
+ em->orig_start = range_start;
+ em->block_start = EXTENT_MAP_DELALLOC;
+ em->block_len = found;
+ }
+ } else if (hole_em) {
+ return hole_em;
+ }
+out:
+
+ free_extent_map(hole_em);
+ if (err) {
+ free_extent_map(em);
+ return ERR_PTR(err);
+ }
+ return em;
+}
+
static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
u64 start, u64 len)
{
if (!skip_sum) {
dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS);
if (!dip->csums) {
+ kfree(dip);
ret = -ENOMEM;
goto free_ordered;
}
static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
- return extent_fiemap(inode, fieinfo, start, len, btrfs_get_extent);
+ return extent_fiemap(inode, fieinfo, start, len, btrfs_get_extent_fiemap);
}
int btrfs_readpage(struct file *file, struct page *page)
if (copy_from_user(&flags, arg, sizeof(flags)))
return -EFAULT;
- if (flags & ~BTRFS_SUBVOL_CREATE_ASYNC)
+ if (flags & BTRFS_SUBVOL_CREATE_ASYNC)
return -EINVAL;
if (flags & ~BTRFS_SUBVOL_RDONLY)
return -EOPNOTSUPP;
+ if (!is_owner_or_cap(inode))
+ return -EACCES;
+
down_write(&root->fs_info->subvol_sem);
/* nothing to do */
goto out_reset;
}
- ret = btrfs_update_root(trans, root,
+ ret = btrfs_update_root(trans, root->fs_info->tree_root,
&root->root_key, &root->root_item);
btrfs_commit_transaction(trans, root);
int num_types = 4;
int alloc_size;
int ret = 0;
- int slot_count = 0;
+ u64 slot_count = 0;
int i, c;
if (copy_from_user(&space_args,
goto out;
}
- slot_count = min_t(int, space_args.space_slots, slot_count);
+ slot_count = min_t(u64, space_args.space_slots, slot_count);
alloc_size = sizeof(*dest) * slot_count;
for (i = 0; i < num_types; i++) {
struct btrfs_space_info *tmp;
+ if (!slot_count)
+ break;
+
info = NULL;
rcu_read_lock();
list_for_each_entry_rcu(tmp, &root->fs_info->space_info,
memcpy(dest, &space, sizeof(space));
dest++;
space_args.total_spaces++;
+ slot_count--;
}
+ if (!slot_count)
+ break;
}
up_read(&info->groups_sem);
}
unsigned long tot_out;
unsigned long tot_len;
char *buf;
+ bool may_late_unmap, need_unmap;
data_in = kmap(pages_in[0]);
tot_len = read_compress_length(data_in);
tot_in += in_len;
working_bytes = in_len;
+ may_late_unmap = need_unmap = false;
/* fast path: avoid using the working buffer */
if (in_page_bytes_left >= in_len) {
buf = data_in + in_offset;
bytes = in_len;
+ may_late_unmap = true;
goto cont;
}
if (working_bytes == 0 && tot_in >= tot_len)
break;
- kunmap(pages_in[page_in_index]);
- page_in_index++;
- if (page_in_index >= total_pages_in) {
+ if (page_in_index + 1 >= total_pages_in) {
ret = -1;
- data_in = NULL;
goto done;
}
- data_in = kmap(pages_in[page_in_index]);
+
+ if (may_late_unmap)
+ need_unmap = true;
+ else
+ kunmap(pages_in[page_in_index]);
+
+ data_in = kmap(pages_in[++page_in_index]);
in_page_bytes_left = PAGE_CACHE_SIZE;
in_offset = 0;
out_len = lzo1x_worst_compress(PAGE_CACHE_SIZE);
ret = lzo1x_decompress_safe(buf, in_len, workspace->buf,
&out_len);
+ if (need_unmap)
+ kunmap(pages_in[page_in_index - 1]);
if (ret != LZO_E_OK) {
printk(KERN_WARNING "btrfs decompress failed\n");
ret = -1;
break;
}
done:
- if (data_in)
- kunmap(pages_in[page_in_index]);
+ kunmap(pages_in[page_in_index]);
return ret;
}
new_node->bytenr = dest->node->start;
new_node->level = node->level;
new_node->lowest = node->lowest;
+ new_node->checked = 1;
new_node->root = dest;
if (!node->lowest) {
u32 item_size;
int ret;
int err = 0;
+ int progress = 0;
path = btrfs_alloc_path();
if (!path)
}
while (1) {
+ progress++;
trans = btrfs_start_transaction(rc->extent_root, 0);
BUG_ON(IS_ERR(trans));
-
+restart:
if (update_backref_cache(trans, &rc->backref_cache)) {
btrfs_end_transaction(trans, rc->extent_root);
continue;
}
}
}
+ if (trans && progress && err == -ENOSPC) {
+ ret = btrfs_force_chunk_alloc(trans, rc->extent_root,
+ rc->block_group->flags);
+ if (ret == 0) {
+ err = 0;
+ progress = 0;
+ goto restart;
+ }
+ }
btrfs_release_path(rc->extent_root, path);
clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY,
Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress,
Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
- Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, Opt_err,
+ Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
+ Opt_enospc_debug, Opt_err,
};
static match_table_t tokens = {
{Opt_space_cache, "space_cache"},
{Opt_clear_cache, "clear_cache"},
{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
+ {Opt_enospc_debug, "enospc_debug"},
{Opt_err, NULL},
};
case Opt_user_subvol_rm_allowed:
btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED);
break;
+ case Opt_enospc_debug:
+ btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
+ break;
case Opt_err:
printk(KERN_INFO "btrfs: unrecognized mount option "
"'%s'\n", p);
ret = btrfs_shrink_device(device, 0);
if (ret)
- goto error_brelse;
+ goto error_undo;
ret = btrfs_rm_dev_item(root->fs_info->chunk_root, device);
if (ret)
- goto error_brelse;
+ goto error_undo;
device->in_fs_metadata = 0;
mutex_unlock(&root->fs_info->volume_mutex);
mutex_unlock(&uuid_mutex);
return ret;
+error_undo:
+ if (device->writeable) {
+ list_add(&device->dev_alloc_list,
+ &root->fs_info->fs_devices->alloc_list);
+ root->fs_info->fs_devices->rw_devices++;
+ }
+ goto error_brelse;
}
/*
ret = find_next_devid(root, &device->devid);
if (ret) {
+ kfree(device->name);
kfree(device);
goto error;
}
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
+ kfree(device->name);
kfree(device);
ret = PTR_ERR(trans);
goto error;
device->dev_root = root->fs_info->dev_root;
device->bdev = bdev;
device->in_fs_metadata = 1;
- device->mode = 0;
+ device->mode = FMODE_EXCL;
set_blocksize(device->bdev, 4096);
if (seeding_dev) {
spin_lock(&inode->i_lock);
if (ci->i_release_count == fi->dir_release_count) {
dout(" marking %p complete\n", inode);
- ci->i_ceph_flags |= CEPH_I_COMPLETE;
+ /* ci->i_ceph_flags |= CEPH_I_COMPLETE; */
ci->i_max_offset = filp->f_pos;
}
spin_unlock(&inode->i_lock);
/* .snap dir? */
if (err == -ENOENT &&
+ ceph_snap(parent) == CEPH_NOSNAP &&
strcmp(dentry->d_name.name,
fsc->mount_options->snapdir_name) == 0) {
struct inode *inode = ceph_get_snapdir(parent);
{
struct inode *dir;
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
dir = dentry->d_parent->d_inode;
static void ceph_dentry_release(struct dentry *dentry)
{
struct ceph_dentry_info *di = ceph_dentry(dentry);
- struct inode *parent_inode = NULL;
- u64 snapid = CEPH_NOSNAP;
- if (!IS_ROOT(dentry)) {
- parent_inode = dentry->d_parent->d_inode;
- if (parent_inode)
- snapid = ceph_snap(parent_inode);
- }
- dout("dentry_release %p parent %p\n", dentry, parent_inode);
- if (parent_inode && snapid != CEPH_SNAPDIR) {
- struct ceph_inode_info *ci = ceph_inode(parent_inode);
-
- spin_lock(&parent_inode->i_lock);
- if (ci->i_shared_gen == di->lease_shared_gen ||
- snapid <= CEPH_MAXSNAP) {
- dout(" clearing %p complete (d_release)\n",
- parent_inode);
- ci->i_ceph_flags &= ~CEPH_I_COMPLETE;
- ci->i_release_count++;
- }
- spin_unlock(&parent_inode->i_lock);
- }
+ dout("dentry_release %p\n", dentry);
if (di) {
ceph_dentry_lru_del(dentry);
if (di->lease_session)
(issued & CEPH_CAP_FILE_EXCL) == 0 &&
(ci->i_ceph_flags & CEPH_I_COMPLETE) == 0) {
dout(" marking %p complete (empty)\n", inode);
- ci->i_ceph_flags |= CEPH_I_COMPLETE;
+ /* ci->i_ceph_flags |= CEPH_I_COMPLETE; */
ci->i_max_offset = 2;
}
break;
if (lastinode)
iput(lastinode);
- dout("queue_realm_cap_snaps %p %llx children\n", realm, realm->ino);
- list_for_each_entry(child, &realm->children, child_item)
- queue_realm_cap_snaps(child);
+ list_for_each_entry(child, &realm->children, child_item) {
+ dout("queue_realm_cap_snaps %p %llx queue child %p %llx\n",
+ realm, realm->ino, child, child->ino);
+ list_del_init(&child->dirty_item);
+ list_add(&child->dirty_item, &realm->dirty_item);
+ }
+ list_del_init(&realm->dirty_item);
dout("queue_realm_cap_snaps %p %llx done\n", realm, realm->ino);
}
* queue cap snaps _after_ we've built the new snap contexts,
* so that i_head_snapc can be set appropriately.
*/
- list_for_each_entry(realm, &dirty_realms, dirty_item) {
+ while (!list_empty(&dirty_realms)) {
+ realm = list_first_entry(&dirty_realms, struct ceph_snap_realm,
+ dirty_item);
queue_realm_cap_snaps(realm);
}
extern const struct export_operations cifs_export_ops;
#endif /* EXPERIMENTAL */
-#define CIFS_VERSION "1.70"
+#define CIFS_VERSION "1.71"
#endif /* _CIFSFS_H */
/* multiplexed reads or writes */
unsigned int maxBuf; /* maxBuf specifies the maximum */
/* message size the server can send or receive for non-raw SMBs */
+ /* maxBuf is returned by SMB NegotiateProtocol so maxBuf is only 0 */
+ /* when socket is setup (and during reconnect) before NegProt sent */
unsigned int max_rw; /* maxRw specifies the maximum */
/* message size the server can send or receive for */
/* SMB_COM_WRITE_RAW or SMB_COM_READ_RAW. */
#define MID_REQUEST_SUBMITTED 2
#define MID_RESPONSE_RECEIVED 4
#define MID_RETRY_NEEDED 8 /* session closed while this request out */
-#define MID_NO_RESP_NEEDED 0x10
+#define MID_RESPONSE_MALFORMED 0x10
/* Types of response buffer returned from SendReceive2 */
#define CIFS_NO_BUFFER 0 /* Response buffer not returned */
struct TCP_Server_Info, echo.work);
/*
- * We cannot send an echo until the NEGOTIATE_PROTOCOL request is done.
- * Also, no need to ping if we got a response recently
+ * We cannot send an echo until the NEGOTIATE_PROTOCOL request is
+ * done, which is indicated by maxBuf != 0. Also, no need to ping if
+ * we got a response recently
*/
- if (server->tcpStatus != CifsGood ||
+ if (server->maxBuf == 0 ||
time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
goto requeue_echo;
total_read += 4; /* account for rfc1002 hdr */
dump_smb(smb_buffer, total_read);
- if (checkSMB(smb_buffer, smb_buffer->Mid, total_read)) {
+
+ /*
+ * We know that we received enough to get to the MID as we
+ * checked the pdu_length earlier. Now check to see
+ * if the rest of the header is OK. We borrow the length
+ * var for the rest of the loop to avoid a new stack var.
+ *
+ * 48 bytes is enough to display the header and a little bit
+ * into the payload for debugging purposes.
+ */
+ length = checkSMB(smb_buffer, smb_buffer->Mid, total_read);
+ if (length != 0)
cifs_dump_mem("Bad SMB: ", smb_buffer,
- total_read < 48 ? total_read : 48);
- continue;
- }
+ min_t(unsigned int, total_read, 48));
mid_entry = NULL;
server->lstrp = jiffies;
if ((mid_entry->mid == smb_buffer->Mid) &&
(mid_entry->midState == MID_REQUEST_SUBMITTED) &&
(mid_entry->command == smb_buffer->Command)) {
- if (check2ndT2(smb_buffer,server->maxBuf) > 0) {
+ if (length == 0 &&
+ check2ndT2(smb_buffer, server->maxBuf) > 0) {
/* We have a multipart transact2 resp */
isMultiRsp = true;
if (mid_entry->resp_buf) {
mid_entry->resp_buf = smb_buffer;
mid_entry->largeBuf = isLargeBuf;
multi_t2_fnd:
- mid_entry->midState = MID_RESPONSE_RECEIVED;
+ if (length == 0)
+ mid_entry->midState =
+ MID_RESPONSE_RECEIVED;
+ else
+ mid_entry->midState =
+ MID_RESPONSE_MALFORMED;
#ifdef CONFIG_CIFS_STATS2
mid_entry->when_received = jiffies;
#endif
else
smallbuf = NULL;
}
+ } else if (length != 0) {
+ /* response sanity checks failed */
+ continue;
} else if (!is_valid_oplock_break(smb_buffer, server) &&
!isMultiRsp) {
cERROR(1, "No task to wake, unknown frame received! "
{
int rc, alen, slen;
const char *pct;
- char *endp, scope_id[13];
+ char scope_id[13];
struct sockaddr_in *s4 = (struct sockaddr_in *) dst;
struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) dst;
memcpy(scope_id, pct + 1, slen);
scope_id[slen] = '\0';
- s6->sin6_scope_id = (u32) simple_strtoul(pct, &endp, 0);
- if (endp != scope_id + slen)
- return 0;
+ rc = strict_strtoul(scope_id, 0,
+ (unsigned long *)&s6->sin6_scope_id);
+ rc = (rc == 0) ? 1 : 0;
}
return rc;
if (type == LANMAN) {
#ifdef CONFIG_CIFS_WEAK_PW_HASH
- char lnm_session_key[CIFS_SESS_KEY_SIZE];
+ char lnm_session_key[CIFS_AUTH_RESP_SIZE];
pSMB->req.hdr.Flags2 &= ~SMBFLG2_UNICODE;
/* no capabilities flags in old lanman negotiation */
- pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_SESS_KEY_SIZE);
+ pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE);
/* Calculate hash with password and copy into bcc_ptr.
* Encryption Key (stored as in cryptkey) gets used if the
true : false, lnm_session_key);
ses->flags |= CIFS_SES_LANMAN;
- memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_SESS_KEY_SIZE);
- bcc_ptr += CIFS_SESS_KEY_SIZE;
+ memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
+ bcc_ptr += CIFS_AUTH_RESP_SIZE;
/* can not sign if LANMAN negotiated so no need
to calculate signing key? but what if server
case MID_RETRY_NEEDED:
rc = -EAGAIN;
break;
+ case MID_RESPONSE_MALFORMED:
+ rc = -EIO;
+ break;
default:
cERROR(1, "%s: invalid mid state mid=%d state=%d", __func__,
mid->mid, mid->midState);
*/
asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf)
{
- struct path path;
- int error;
-
- error = user_path(pathname, &path);
- if (!error) {
- struct kstatfs tmp;
- error = vfs_statfs(&path, &tmp);
- if (!error)
- error = put_compat_statfs(buf, &tmp);
- path_put(&path);
- }
+ struct kstatfs tmp;
+ int error = user_statfs(pathname, &tmp);
+ if (!error)
+ error = put_compat_statfs(buf, &tmp);
return error;
}
asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf)
{
- struct file * file;
struct kstatfs tmp;
- int error;
-
- error = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
- error = vfs_statfs(&file->f_path, &tmp);
+ int error = fd_statfs(fd, &tmp);
if (!error)
error = put_compat_statfs(buf, &tmp);
- fput(file);
-out:
return error;
}
asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf)
{
- struct path path;
+ struct kstatfs tmp;
int error;
if (sz != sizeof(*buf))
return -EINVAL;
- error = user_path(pathname, &path);
- if (!error) {
- struct kstatfs tmp;
- error = vfs_statfs(&path, &tmp);
- if (!error)
- error = put_compat_statfs64(buf, &tmp);
- path_put(&path);
- }
+ error = user_statfs(pathname, &tmp);
+ if (!error)
+ error = put_compat_statfs64(buf, &tmp);
return error;
}
asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf)
{
- struct file * file;
struct kstatfs tmp;
int error;
if (sz != sizeof(*buf))
return -EINVAL;
- error = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
- error = vfs_statfs(&file->f_path, &tmp);
+ error = fd_statfs(fd, &tmp);
if (!error)
error = put_compat_statfs64(buf, &tmp);
- fput(file);
-out:
return error;
}
file = fget_light(fd, &fput_needed);
if (!file)
return -EBADF;
- ret = compat_readv(file, vec, vlen, &pos);
+ ret = -ESPIPE;
+ if (file->f_mode & FMODE_PREAD)
+ ret = compat_readv(file, vec, vlen, &pos);
fput_light(file, fput_needed);
return ret;
}
file = fget_light(fd, &fput_needed);
if (!file)
return -EBADF;
- ret = compat_writev(file, vec, vlen, &pos);
+ ret = -ESPIPE;
+ if (file->f_mode & FMODE_PWRITE)
+ ret = compat_writev(file, vec, vlen, &pos);
fput_light(file, fput_needed);
return ret;
}
}
#endif /* CONFIG_TIMERFD */
+
+#ifdef CONFIG_FHANDLE
+/*
+ * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
+ * doesn't set the O_LARGEFILE flag.
+ */
+asmlinkage long
+compat_sys_open_by_handle_at(int mountdirfd,
+ struct file_handle __user *handle, int flags)
+{
+ return do_handle_open(mountdirfd, handle, flags);
+}
+#endif
__releases(parent->d_lock)
__releases(dentry->d_inode->i_lock)
{
- dentry->d_parent = NULL;
list_del(&dentry->d_u.d_child);
+ /*
+ * Inform try_to_ascend() that we are no longer attached to the
+ * dentry tree
+ */
+ dentry->d_flags |= DCACHE_DISCONNECTED;
if (parent)
spin_unlock(&parent->d_lock);
dentry_iput(dentry);
}
}
+/*
+ * This tries to ascend one level of parenthood, but
+ * we can race with renaming, so we need to re-check
+ * the parenthood after dropping the lock and check
+ * that the sequence number still matches.
+ */
+static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq)
+{
+ struct dentry *new = old->d_parent;
+
+ rcu_read_lock();
+ spin_unlock(&old->d_lock);
+ spin_lock(&new->d_lock);
+
+ /*
+ * might go back up the wrong parent if we have had a rename
+ * or deletion
+ */
+ if (new != old->d_parent ||
+ (old->d_flags & DCACHE_DISCONNECTED) ||
+ (!locked && read_seqretry(&rename_lock, seq))) {
+ spin_unlock(&new->d_lock);
+ new = NULL;
+ }
+ rcu_read_unlock();
+ return new;
+}
+
+
/*
* Search for at least 1 mount point in the dentry's subdirs.
* We descend to the next level whenever the d_subdirs
* All done at this level ... ascend and resume the search.
*/
if (this_parent != parent) {
- struct dentry *tmp;
- struct dentry *child;
-
- tmp = this_parent->d_parent;
- rcu_read_lock();
- spin_unlock(&this_parent->d_lock);
- child = this_parent;
- this_parent = tmp;
- spin_lock(&this_parent->d_lock);
- /* might go back up the wrong parent if we have had a rename
- * or deletion */
- if (this_parent != child->d_parent ||
- (!locked && read_seqretry(&rename_lock, seq))) {
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
+ struct dentry *child = this_parent;
+ this_parent = try_to_ascend(this_parent, locked, seq);
+ if (!this_parent)
goto rename_retry;
- }
- rcu_read_unlock();
next = child->d_u.d_child.next;
goto resume;
}
* All done at this level ... ascend and resume the search.
*/
if (this_parent != parent) {
- struct dentry *tmp;
- struct dentry *child;
-
- tmp = this_parent->d_parent;
- rcu_read_lock();
- spin_unlock(&this_parent->d_lock);
- child = this_parent;
- this_parent = tmp;
- spin_lock(&this_parent->d_lock);
- /* might go back up the wrong parent if we have had a rename
- * or deletion */
- if (this_parent != child->d_parent ||
- (!locked && read_seqretry(&rename_lock, seq))) {
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
+ struct dentry *child = this_parent;
+ this_parent = try_to_ascend(this_parent, locked, seq);
+ if (!this_parent)
goto rename_retry;
- }
- rcu_read_unlock();
next = child->d_u.d_child.next;
goto resume;
}
}
EXPORT_SYMBOL(d_alloc_root);
+static struct dentry * __d_find_any_alias(struct inode *inode)
+{
+ struct dentry *alias;
+
+ if (list_empty(&inode->i_dentry))
+ return NULL;
+ alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias);
+ __dget(alias);
+ return alias;
+}
+
+static struct dentry * d_find_any_alias(struct inode *inode)
+{
+ struct dentry *de;
+
+ spin_lock(&inode->i_lock);
+ de = __d_find_any_alias(inode);
+ spin_unlock(&inode->i_lock);
+ return de;
+}
+
+
/**
* d_obtain_alias - find or allocate a dentry for a given inode
* @inode: inode to allocate the dentry for
if (IS_ERR(inode))
return ERR_CAST(inode);
- res = d_find_alias(inode);
+ res = d_find_any_alias(inode);
if (res)
goto out_iput;
spin_lock(&inode->i_lock);
- res = __d_find_alias(inode, 0);
+ res = __d_find_any_alias(inode);
if (res) {
spin_unlock(&inode->i_lock);
dput(tmp);
spin_unlock(&dentry->d_lock);
}
if (this_parent != root) {
- struct dentry *tmp;
- struct dentry *child;
-
- tmp = this_parent->d_parent;
+ struct dentry *child = this_parent;
if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
this_parent->d_flags |= DCACHE_GENOCIDE;
this_parent->d_count--;
}
- rcu_read_lock();
- spin_unlock(&this_parent->d_lock);
- child = this_parent;
- this_parent = tmp;
- spin_lock(&this_parent->d_lock);
- /* might go back up the wrong parent if we have had a rename
- * or deletion */
- if (this_parent != child->d_parent ||
- (!locked && read_seqretry(&rename_lock, seq))) {
- spin_unlock(&this_parent->d_lock);
- rcu_read_unlock();
+ this_parent = try_to_ascend(this_parent, locked, seq);
+ if (!this_parent)
goto rename_retry;
- }
- rcu_read_unlock();
next = child->d_u.d_child.next;
goto resume;
}
static int work_start(void)
{
- recv_workqueue = alloc_workqueue("dlm_recv", WQ_MEM_RECLAIM |
- WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+ recv_workqueue = create_singlethread_workqueue("dlm_recv");
if (!recv_workqueue) {
log_print("can't start dlm_recv");
return -ENOMEM;
}
- send_workqueue = alloc_workqueue("dlm_send", WQ_MEM_RECLAIM |
- WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+ send_workqueue = create_singlethread_workqueue("dlm_send");
if (!send_workqueue) {
log_print("can't start dlm_send");
destroy_workqueue(recv_workqueue);
{
struct dentry *lower_dentry;
struct vfsmount *lower_mnt;
- struct dentry *dentry_save;
- struct vfsmount *vfsmount_save;
+ struct dentry *dentry_save = NULL;
+ struct vfsmount *vfsmount_save = NULL;
int rc = 1;
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
goto out;
- dentry_save = nd->path.dentry;
- vfsmount_save = nd->path.mnt;
- nd->path.dentry = lower_dentry;
- nd->path.mnt = lower_mnt;
+ if (nd) {
+ dentry_save = nd->path.dentry;
+ vfsmount_save = nd->path.mnt;
+ nd->path.dentry = lower_dentry;
+ nd->path.mnt = lower_mnt;
+ }
rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd);
- nd->path.dentry = dentry_save;
- nd->path.mnt = vfsmount_save;
+ if (nd) {
+ nd->path.dentry = dentry_save;
+ nd->path.mnt = vfsmount_save;
+ }
if (dentry->d_inode) {
struct inode *lower_inode =
ecryptfs_inode_to_lower(dentry->d_inode);
u32 flags);
int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
struct dentry *lower_dentry,
- struct inode *ecryptfs_dir_inode,
- struct nameidata *ecryptfs_nd);
+ struct inode *ecryptfs_dir_inode);
int ecryptfs_decode_and_decrypt_filename(char **decrypted_name,
size_t *decrypted_name_size,
struct dentry *ecryptfs_dentry,
const struct file_operations ecryptfs_dir_fops = {
.readdir = ecryptfs_readdir,
+ .read = generic_read_dir,
.unlocked_ioctl = ecryptfs_unlocked_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ecryptfs_compat_ioctl,
unsigned int flags_save;
int rc;
- dentry_save = nd->path.dentry;
- vfsmount_save = nd->path.mnt;
- flags_save = nd->flags;
- nd->path.dentry = lower_dentry;
- nd->path.mnt = lower_mnt;
- nd->flags &= ~LOOKUP_OPEN;
+ if (nd) {
+ dentry_save = nd->path.dentry;
+ vfsmount_save = nd->path.mnt;
+ flags_save = nd->flags;
+ nd->path.dentry = lower_dentry;
+ nd->path.mnt = lower_mnt;
+ nd->flags &= ~LOOKUP_OPEN;
+ }
rc = vfs_create(lower_dir_inode, lower_dentry, mode, nd);
- nd->path.dentry = dentry_save;
- nd->path.mnt = vfsmount_save;
- nd->flags = flags_save;
+ if (nd) {
+ nd->path.dentry = dentry_save;
+ nd->path.mnt = vfsmount_save;
+ nd->flags = flags_save;
+ }
return rc;
}
*/
int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
struct dentry *lower_dentry,
- struct inode *ecryptfs_dir_inode,
- struct nameidata *ecryptfs_nd)
+ struct inode *ecryptfs_dir_inode)
{
struct dentry *lower_dir_dentry;
struct vfsmount *lower_mnt;
goto out;
if (special_file(lower_inode->i_mode))
goto out;
- if (!ecryptfs_nd)
- goto out;
/* Released in this function */
page_virt = kmem_cache_zalloc(ecryptfs_header_cache_2, GFP_USER);
if (!page_virt) {
return rc;
}
-/**
- * ecryptfs_new_lower_dentry
- * @name: The name of the new dentry.
- * @lower_dir_dentry: Parent directory of the new dentry.
- * @nd: nameidata from last lookup.
- *
- * Create a new dentry or get it from lower parent dir.
- */
-static struct dentry *
-ecryptfs_new_lower_dentry(struct qstr *name, struct dentry *lower_dir_dentry,
- struct nameidata *nd)
-{
- struct dentry *new_dentry;
- struct dentry *tmp;
- struct inode *lower_dir_inode;
-
- lower_dir_inode = lower_dir_dentry->d_inode;
-
- tmp = d_alloc(lower_dir_dentry, name);
- if (!tmp)
- return ERR_PTR(-ENOMEM);
-
- mutex_lock(&lower_dir_inode->i_mutex);
- new_dentry = lower_dir_inode->i_op->lookup(lower_dir_inode, tmp, nd);
- mutex_unlock(&lower_dir_inode->i_mutex);
-
- if (!new_dentry)
- new_dentry = tmp;
- else
- dput(tmp);
-
- return new_dentry;
-}
-
-
-/**
- * ecryptfs_lookup_one_lower
- * @ecryptfs_dentry: The eCryptfs dentry that we are looking up
- * @lower_dir_dentry: lower parent directory
- * @name: lower file name
- *
- * Get the lower dentry from vfs. If lower dentry does not exist yet,
- * create it.
- */
-static struct dentry *
-ecryptfs_lookup_one_lower(struct dentry *ecryptfs_dentry,
- struct dentry *lower_dir_dentry, struct qstr *name)
-{
- struct nameidata nd;
- struct vfsmount *lower_mnt;
- int err;
-
- lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(
- ecryptfs_dentry->d_parent));
- err = vfs_path_lookup(lower_dir_dentry, lower_mnt, name->name , 0, &nd);
- mntput(lower_mnt);
-
- if (!err) {
- /* we dont need the mount */
- mntput(nd.path.mnt);
- return nd.path.dentry;
- }
- if (err != -ENOENT)
- return ERR_PTR(err);
-
- /* create a new lower dentry */
- return ecryptfs_new_lower_dentry(name, lower_dir_dentry, &nd);
-}
-
/**
* ecryptfs_lookup
* @ecryptfs_dir_inode: The eCryptfs directory inode
size_t encrypted_and_encoded_name_size;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL;
struct dentry *lower_dir_dentry, *lower_dentry;
- struct qstr lower_name;
int rc = 0;
if ((ecryptfs_dentry->d_name.len == 1
goto out_d_drop;
}
lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
- lower_name.name = ecryptfs_dentry->d_name.name;
- lower_name.len = ecryptfs_dentry->d_name.len;
- lower_name.hash = ecryptfs_dentry->d_name.hash;
- if (lower_dir_dentry->d_op && lower_dir_dentry->d_op->d_hash) {
- rc = lower_dir_dentry->d_op->d_hash(lower_dir_dentry,
- lower_dir_dentry->d_inode, &lower_name);
- if (rc < 0)
- goto out_d_drop;
- }
- lower_dentry = ecryptfs_lookup_one_lower(ecryptfs_dentry,
- lower_dir_dentry, &lower_name);
+ mutex_lock(&lower_dir_dentry->d_inode->i_mutex);
+ lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name,
+ lower_dir_dentry,
+ ecryptfs_dentry->d_name.len);
+ mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
if (IS_ERR(lower_dentry)) {
rc = PTR_ERR(lower_dentry);
- ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_lower() returned "
+ ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
"[%d] on lower_dentry = [%s]\n", __func__, rc,
encrypted_and_encoded_name);
goto out_d_drop;
"filename; rc = [%d]\n", __func__, rc);
goto out_d_drop;
}
- lower_name.name = encrypted_and_encoded_name;
- lower_name.len = encrypted_and_encoded_name_size;
- lower_name.hash = full_name_hash(lower_name.name, lower_name.len);
- if (lower_dir_dentry->d_op && lower_dir_dentry->d_op->d_hash) {
- rc = lower_dir_dentry->d_op->d_hash(lower_dir_dentry,
- lower_dir_dentry->d_inode, &lower_name);
- if (rc < 0)
- goto out_d_drop;
- }
- lower_dentry = ecryptfs_lookup_one_lower(ecryptfs_dentry,
- lower_dir_dentry, &lower_name);
+ mutex_lock(&lower_dir_dentry->d_inode->i_mutex);
+ lower_dentry = lookup_one_len(encrypted_and_encoded_name,
+ lower_dir_dentry,
+ encrypted_and_encoded_name_size);
+ mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
if (IS_ERR(lower_dentry)) {
rc = PTR_ERR(lower_dentry);
- ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_lower() returned "
+ ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
"[%d] on lower_dentry = [%s]\n", __func__, rc,
encrypted_and_encoded_name);
goto out_d_drop;
}
lookup_and_interpose:
rc = ecryptfs_lookup_and_interpose_lower(ecryptfs_dentry, lower_dentry,
- ecryptfs_dir_inode,
- ecryptfs_nd);
+ ecryptfs_dir_inode);
goto out;
out_d_drop:
d_drop(ecryptfs_dentry);
rc = vfs_getattr(ecryptfs_dentry_to_lower_mnt(dentry),
ecryptfs_dentry_to_lower(dentry), &lower_stat);
if (!rc) {
+ fsstack_copy_attr_all(dentry->d_inode,
+ ecryptfs_inode_to_lower(dentry->d_inode));
generic_fillattr(dentry->d_inode, stat);
stat->blocks = lower_stat.blocks;
}
* @ctx: [in] Pointer to eventfd context.
*
* The eventfd context reference must have been previously acquired either
- * with eventfd_ctx_get() or eventfd_ctx_fdget()).
+ * with eventfd_ctx_get() or eventfd_ctx_fdget().
*/
void eventfd_ctx_put(struct eventfd_ctx *ctx)
{
* eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
* @ctx: [in] Pointer to eventfd context.
* @wait: [in] Wait queue to be removed.
- * @cnt: [out] Pointer to the 64bit conter value.
+ * @cnt: [out] Pointer to the 64-bit counter value.
*
- * Returns zero if successful, or the following error codes:
+ * Returns %0 if successful, or the following error codes:
*
* -EAGAIN : The operation would have blocked.
*
* eventfd_ctx_read - Reads the eventfd counter or wait if it is zero.
* @ctx: [in] Pointer to eventfd context.
* @no_wait: [in] Different from zero if the operation should not block.
- * @cnt: [out] Pointer to the 64bit conter value.
+ * @cnt: [out] Pointer to the 64-bit counter value.
*
- * Returns zero if successful, or the following error codes:
+ * Returns %0 if successful, or the following error codes:
*
- * -EAGAIN : The operation would have blocked but @no_wait was nonzero.
+ * -EAGAIN : The operation would have blocked but @no_wait was non-zero.
* -ERESTARTSYS : A signal interrupted the wait operation.
*
* If @no_wait is zero, the function might sleep until the eventfd internal
* cleanup path and it is also acquired by eventpoll_release_file()
* if a file has been pushed inside an epoll set and it is then
* close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL).
+ * It is also acquired when inserting an epoll fd onto another epoll
+ * fd. We do this so that we walk the epoll tree and ensure that this
+ * insertion does not create a cycle of epoll file descriptors, which
+ * could lead to deadlock. We need a global mutex to prevent two
+ * simultaneous inserts (A into B and B into A) from racing and
+ * constructing a cycle without either insert observing that it is
+ * going to.
* It is possible to drop the "ep->mtx" and to use the global
* mutex "epmutex" (together with "ep->lock") to have it working,
* but having "ep->mtx" will make the interface more scalable.
*/
static DEFINE_MUTEX(epmutex);
+/* Used to check for epoll file descriptor inclusion loops */
+static struct nested_calls poll_loop_ncalls;
+
/* Used for safe wake up implementation */
static struct nested_calls poll_safewake_ncalls;
return res;
}
+/**
+ * ep_loop_check_proc - Callback function to be passed to the @ep_call_nested()
+ * API, to verify that adding an epoll file inside another
+ * epoll structure, does not violate the constraints, in
+ * terms of closed loops, or too deep chains (which can
+ * result in excessive stack usage).
+ *
+ * @priv: Pointer to the epoll file to be currently checked.
+ * @cookie: Original cookie for this call. This is the top-of-the-chain epoll
+ * data structure pointer.
+ * @call_nests: Current dept of the @ep_call_nested() call stack.
+ *
+ * Returns: Returns zero if adding the epoll @file inside current epoll
+ * structure @ep does not violate the constraints, or -1 otherwise.
+ */
+static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
+{
+ int error = 0;
+ struct file *file = priv;
+ struct eventpoll *ep = file->private_data;
+ struct rb_node *rbp;
+ struct epitem *epi;
+
+ mutex_lock(&ep->mtx);
+ for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+ epi = rb_entry(rbp, struct epitem, rbn);
+ if (unlikely(is_file_epoll(epi->ffd.file))) {
+ error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+ ep_loop_check_proc, epi->ffd.file,
+ epi->ffd.file->private_data, current);
+ if (error != 0)
+ break;
+ }
+ }
+ mutex_unlock(&ep->mtx);
+
+ return error;
+}
+
+/**
+ * ep_loop_check - Performs a check to verify that adding an epoll file (@file)
+ * another epoll file (represented by @ep) does not create
+ * closed loops or too deep chains.
+ *
+ * @ep: Pointer to the epoll private data structure.
+ * @file: Pointer to the epoll file to be checked.
+ *
+ * Returns: Returns zero if adding the epoll @file inside current epoll
+ * structure @ep does not violate the constraints, or -1 otherwise.
+ */
+static int ep_loop_check(struct eventpoll *ep, struct file *file)
+{
+ return ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+ ep_loop_check_proc, file, ep, current);
+}
+
/*
* Open an eventpoll file descriptor.
*/
struct epoll_event __user *, event)
{
int error;
+ int did_lock_epmutex = 0;
struct file *file, *tfile;
struct eventpoll *ep;
struct epitem *epi;
*/
ep = file->private_data;
+ /*
+ * When we insert an epoll file descriptor, inside another epoll file
+ * descriptor, there is the change of creating closed loops, which are
+ * better be handled here, than in more critical paths.
+ *
+ * We hold epmutex across the loop check and the insert in this case, in
+ * order to prevent two separate inserts from racing and each doing the
+ * insert "at the same time" such that ep_loop_check passes on both
+ * before either one does the insert, thereby creating a cycle.
+ */
+ if (unlikely(is_file_epoll(tfile) && op == EPOLL_CTL_ADD)) {
+ mutex_lock(&epmutex);
+ did_lock_epmutex = 1;
+ error = -ELOOP;
+ if (ep_loop_check(ep, tfile) != 0)
+ goto error_tgt_fput;
+ }
+
+
mutex_lock(&ep->mtx);
/*
mutex_unlock(&ep->mtx);
error_tgt_fput:
+ if (unlikely(did_lock_epmutex))
+ mutex_unlock(&epmutex);
+
fput(tfile);
error_fput:
fput(file);
EP_ITEM_COST;
BUG_ON(max_user_watches < 0);
+ /*
+ * Initialize the structure used to perform epoll file descriptor
+ * inclusion loops checks.
+ */
+ ep_nested_calls_init(&poll_loop_ncalls);
+
/* Initialize the structure used to perform safe poll wait head wake ups */
ep_nested_calls_init(&poll_safewake_ncalls);
struct file *file;
char *tmp = getname(library);
int error = PTR_ERR(tmp);
+ static const struct open_flags uselib_flags = {
+ .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+ .acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
+ .intent = LOOKUP_OPEN
+ };
if (IS_ERR(tmp))
goto out;
- file = do_filp_open(AT_FDCWD, tmp,
- O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
- MAY_READ | MAY_EXEC | MAY_OPEN);
+ file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW);
putname(tmp);
error = PTR_ERR(file);
if (IS_ERR(file))
{
struct file *file;
int err;
+ static const struct open_flags open_exec_flags = {
+ .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+ .acc_mode = MAY_EXEC | MAY_OPEN,
+ .intent = LOOKUP_OPEN
+ };
- file = do_filp_open(AT_FDCWD, name,
- O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
- MAY_EXEC | MAY_OPEN);
+ file = do_filp_open(AT_FDCWD, name, &open_exec_flags, LOOKUP_FOLLOW);
if (IS_ERR(file))
goto out;
new_de = exofs_find_entry(new_dir, new_dentry, &new_page);
if (!new_de)
goto out_dir;
- inode_inc_link_count(old_inode);
err = exofs_set_link(new_dir, new_de, new_page, old_inode);
new_inode->i_ctime = CURRENT_TIME;
if (dir_de)
if (new_dir->i_nlink >= EXOFS_LINK_MAX)
goto out_dir;
}
- inode_inc_link_count(old_inode);
err = exofs_add_link(new_dentry, old_inode);
- if (err) {
- inode_dec_link_count(old_inode);
+ if (err)
goto out_dir;
- }
if (dir_de)
inode_inc_link_count(new_dir);
}
old_inode->i_ctime = CURRENT_TIME;
exofs_delete_entry(old_de, old_page);
- inode_dec_link_count(old_inode);
+ mark_inode_dirty(old_inode);
if (dir_de) {
err = exofs_set_link(old_inode, dir_de, dir_page, new_dir);
struct inode * inode = dentry->d_inode;
int len = *max_len;
int type = FILEID_INO32_GEN;
-
- if (len < 2 || (connectable && len < 4))
+
+ if (connectable && (len < 4)) {
+ *max_len = 4;
+ return 255;
+ } else if (len < 2) {
+ *max_len = 2;
return 255;
+ }
len = 2;
fid->i32.ino = inode->i_ino;
/*
* Try to get any dentry for the given file handle from the filesystem.
*/
+ if (!nop || !nop->fh_to_dentry)
+ return ERR_PTR(-ESTALE);
result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
if (!result)
result = ERR_PTR(-ESTALE);
new_de = ext2_find_entry (new_dir, &new_dentry->d_name, &new_page);
if (!new_de)
goto out_dir;
- inode_inc_link_count(old_inode);
ext2_set_link(new_dir, new_de, new_page, old_inode, 1);
new_inode->i_ctime = CURRENT_TIME_SEC;
if (dir_de)
if (new_dir->i_nlink >= EXT2_LINK_MAX)
goto out_dir;
}
- inode_inc_link_count(old_inode);
err = ext2_add_link(new_dentry, old_inode);
- if (err) {
- inode_dec_link_count(old_inode);
+ if (err)
goto out_dir;
- }
if (dir_de)
inode_inc_link_count(new_dir);
}
/*
* Like most other Unix systems, set the ctime for inodes on a
* rename.
- * inode_dec_link_count() will mark the inode dirty.
*/
old_inode->i_ctime = CURRENT_TIME_SEC;
+ mark_inode_dirty(old_inode);
ext2_delete_entry (old_de, old_page);
- inode_dec_link_count(old_inode);
if (dir_de) {
if (old_dir != new_dir)
dquot_initialize(dir);
- /*
- * Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing
- * otherwise has the potential to corrupt the orphan inode list.
- */
- if (inode->i_nlink == 0)
- return -ENOENT;
-
retry:
handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT3_INDEX_EXTRA_TRANS_BLOCKS);
sb->s_qcop = &ext3_qctl_operations;
sb->dq_op = &ext3_quota_operations;
#endif
+ memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
mutex_init(&sbi->s_orphan_lock);
mutex_init(&sbi->s_resize_lock);
atomic_t i_ioend_count; /* Number of outstanding io_end structs */
/* current io_end structure for async DIO write*/
ext4_io_end_t *cur_aio_dio;
+ atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
spinlock_t i_block_reservation_lock;
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
+/* For ioend & aio unwritten conversion wait queues */
+#define EXT4_WQ_HASH_SZ 37
+#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\
+ EXT4_WQ_HASH_SZ])
+#define ext4_aio_mutex(v) (&ext4__aio_mutex[((unsigned long)(v)) %\
+ EXT4_WQ_HASH_SZ])
+extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
* that this IO needs to convertion to written when IO is
* completed
*/
- if (io)
+ if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
io->flag = EXT4_IO_END_UNWRITTEN;
- else
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ } else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
* that we need to perform convertion when IO is done.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
- if (io)
+ if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
io->flag = EXT4_IO_END_UNWRITTEN;
- else
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ } else
ext4_set_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN);
}
return 0;
}
+static void ext4_aiodio_wait(struct inode *inode)
+{
+ wait_queue_head_t *wq = ext4_ioend_wq(inode);
+
+ wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
+}
+
+/*
+ * This tests whether the IO in question is block-aligned or not.
+ * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
+ * are converted to written only after the IO is complete. Until they are
+ * mapped, these blocks appear as holes, so dio_zero_block() will assume that
+ * it needs to zero out portions of the start and/or end block. If 2 AIO
+ * threads are at work on the same unwritten block, they must be synchronized
+ * or one thread will zero the other's data, causing corruption.
+ */
+static int
+ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct super_block *sb = inode->i_sb;
+ int blockmask = sb->s_blocksize - 1;
+ size_t count = iov_length(iov, nr_segs);
+ loff_t final_size = pos + count;
+
+ if (pos >= inode->i_size)
+ return 0;
+
+ if ((pos & blockmask) || (final_size & blockmask))
+ return 1;
+
+ return 0;
+}
+
static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+ int unaligned_aio = 0;
+ int ret;
/*
* If we have encountered a bitmap-format file, the size limit
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
+ } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
+ !is_sync_kiocb(iocb))) {
+ unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
}
- return generic_file_aio_write(iocb, iov, nr_segs, pos);
+ /* Unaligned direct AIO must be serialized; see comment above */
+ if (unaligned_aio) {
+ static unsigned long unaligned_warn_time;
+
+ /* Warn about this once per day */
+ if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
+ ext4_msg(inode->i_sb, KERN_WARNING,
+ "Unaligned AIO/DIO on inode %ld by %s; "
+ "performance will be poor.",
+ inode->i_ino, current->comm);
+ mutex_lock(ext4_aio_mutex(inode));
+ ext4_aiodio_wait(inode);
+ }
+
+ ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+ if (unaligned_aio)
+ mutex_unlock(ext4_aio_mutex(inode));
+
+ return ret;
}
static const struct vm_operations_struct ext4_file_vm_ops = {
/* We create slab caches for groupinfo data structures based on the
* superblock block size. There will be one per mounted filesystem for
* each unique s_blocksize_bits */
-#define NR_GRPINFO_CACHES \
- (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE + 1)
+#define NR_GRPINFO_CACHES 8
static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES];
+static const char *ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = {
+ "ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k",
+ "ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k",
+ "ext4_groupinfo_64k", "ext4_groupinfo_128k"
+};
+
static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t group);
static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
return -ENOMEM;
}
+static void ext4_groupinfo_destroy_slabs(void)
+{
+ int i;
+
+ for (i = 0; i < NR_GRPINFO_CACHES; i++) {
+ if (ext4_groupinfo_caches[i])
+ kmem_cache_destroy(ext4_groupinfo_caches[i]);
+ ext4_groupinfo_caches[i] = NULL;
+ }
+}
+
+static int ext4_groupinfo_create_slab(size_t size)
+{
+ static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex);
+ int slab_size;
+ int blocksize_bits = order_base_2(size);
+ int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
+ struct kmem_cache *cachep;
+
+ if (cache_index >= NR_GRPINFO_CACHES)
+ return -EINVAL;
+
+ if (unlikely(cache_index < 0))
+ cache_index = 0;
+
+ mutex_lock(&ext4_grpinfo_slab_create_mutex);
+ if (ext4_groupinfo_caches[cache_index]) {
+ mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+ return 0; /* Already created */
+ }
+
+ slab_size = offsetof(struct ext4_group_info,
+ bb_counters[blocksize_bits + 2]);
+
+ cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index],
+ slab_size, 0, SLAB_RECLAIM_ACCOUNT,
+ NULL);
+
+ mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+ if (!cachep) {
+ printk(KERN_EMERG "EXT4: no memory for groupinfo slab cache\n");
+ return -ENOMEM;
+ }
+
+ ext4_groupinfo_caches[cache_index] = cachep;
+
+ return 0;
+}
+
int ext4_mb_init(struct super_block *sb, int needs_recovery)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned offset;
unsigned max;
int ret;
- int cache_index;
- struct kmem_cache *cachep;
- char *namep = NULL;
i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets);
goto out;
}
- cache_index = sb->s_blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
- cachep = ext4_groupinfo_caches[cache_index];
- if (!cachep) {
- char name[32];
- int len = offsetof(struct ext4_group_info,
- bb_counters[sb->s_blocksize_bits + 2]);
-
- sprintf(name, "ext4_groupinfo_%d", sb->s_blocksize_bits);
- namep = kstrdup(name, GFP_KERNEL);
- if (!namep) {
- ret = -ENOMEM;
- goto out;
- }
-
- /* Need to free the kmem_cache_name() when we
- * destroy the slab */
- cachep = kmem_cache_create(namep, len, 0,
- SLAB_RECLAIM_ACCOUNT, NULL);
- if (!cachep) {
- ret = -ENOMEM;
- goto out;
- }
- ext4_groupinfo_caches[cache_index] = cachep;
- }
+ ret = ext4_groupinfo_create_slab(sb->s_blocksize);
+ if (ret < 0)
+ goto out;
/* order 0 is regular bitmap */
sbi->s_mb_maxs[0] = sb->s_blocksize << 3;
if (ret) {
kfree(sbi->s_mb_offsets);
kfree(sbi->s_mb_maxs);
- kfree(namep);
}
return ret;
}
void ext4_exit_mballoc(void)
{
- int i;
/*
* Wait for completion of call_rcu()'s on ext4_pspace_cachep
* before destroying the slab cache.
kmem_cache_destroy(ext4_pspace_cachep);
kmem_cache_destroy(ext4_ac_cachep);
kmem_cache_destroy(ext4_free_ext_cachep);
-
- for (i = 0; i < NR_GRPINFO_CACHES; i++) {
- struct kmem_cache *cachep = ext4_groupinfo_caches[i];
- if (cachep) {
- char *name = (char *)kmem_cache_name(cachep);
- kmem_cache_destroy(cachep);
- kfree(name);
- }
- }
+ ext4_groupinfo_destroy_slabs();
ext4_remove_debugfs_entry();
}
dquot_initialize(dir);
- /*
- * Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing
- * otherwise has the potential to corrupt the orphan inode list.
- */
- if (inode->i_nlink == 0)
- return -ENOENT;
-
retry:
handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS);
static struct kmem_cache *io_page_cachep, *io_end_cachep;
-#define WQ_HASH_SZ 37
-#define to_ioend_wq(v) (&ioend_wq[((unsigned long)v) % WQ_HASH_SZ])
-static wait_queue_head_t ioend_wq[WQ_HASH_SZ];
-
int __init ext4_init_pageio(void)
{
- int i;
-
io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT);
if (io_page_cachep == NULL)
return -ENOMEM;
kmem_cache_destroy(io_page_cachep);
return -ENOMEM;
}
- for (i = 0; i < WQ_HASH_SZ; i++)
- init_waitqueue_head(&ioend_wq[i]);
-
return 0;
}
void ext4_ioend_wait(struct inode *inode)
{
- wait_queue_head_t *wq = to_ioend_wq(inode);
+ wait_queue_head_t *wq = ext4_ioend_wq(inode);
wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
}
for (i = 0; i < io->num_io_pages; i++)
put_io_page(io->pages[i]);
io->num_io_pages = 0;
- wq = to_ioend_wq(io->inode);
+ wq = ext4_ioend_wq(io->inode);
if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
waitqueue_active(wq))
wake_up_all(wq);
struct inode *inode = io->inode;
loff_t offset = io->offset;
ssize_t size = io->size;
+ wait_queue_head_t *wq;
int ret = 0;
ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
if (io->iocb)
aio_complete(io->iocb, io->result, 0);
/* clear the DIO AIO unwritten flag */
- io->flag &= ~EXT4_IO_END_UNWRITTEN;
+ if (io->flag & EXT4_IO_END_UNWRITTEN) {
+ io->flag &= ~EXT4_IO_END_UNWRITTEN;
+ /* Wake up anyone waiting on unwritten extent conversion */
+ wq = ext4_ioend_wq(io->inode);
+ if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
+ waitqueue_active(wq)) {
+ wake_up_all(wq);
+ }
+ }
+
return ret;
}
struct inode *inode;
unsigned long flags;
int i;
+ sector_t bi_sector = bio->bi_sector;
BUG_ON(!io_end);
bio->bi_private = NULL;
if (error)
SetPageError(page);
BUG_ON(!head);
- if (head->b_size == PAGE_CACHE_SIZE)
- clear_buffer_dirty(head);
- else {
+ if (head->b_size != PAGE_CACHE_SIZE) {
loff_t offset;
loff_t io_end_offset = io_end->offset + io_end->size;
if (error)
buffer_io_error(bh);
- clear_buffer_dirty(bh);
}
if (buffer_delay(bh))
partial_write = 1;
(unsigned long long) io_end->offset,
(long) io_end->size,
(unsigned long long)
- bio->bi_sector >> (inode->i_blkbits - 9));
+ bi_sector >> (inode->i_blkbits - 9));
}
/* Add the io_end to per-inode completed io list*/
blocksize = 1 << inode->i_blkbits;
+ BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
set_page_writeback(page);
ClearPageError(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
+
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
+ clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
const char *dev_name, void *data);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
+static void ext4_clear_request_list(void);
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext3_fs_type = {
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
atomic_set(&ei->i_ioend_count, 0);
+ atomic_set(&ei->i_aiodio_unwritten, 0);
return &ei->vfs_inode;
}
mutex_unlock(&ext4_li_info->li_list_mtx);
}
+static struct task_struct *ext4_lazyinit_task;
+
/*
* This is the function where ext4lazyinit thread lives. It walks
* through the request list searching for next scheduled filesystem.
if (time_before(jiffies, next_wakeup))
schedule();
finish_wait(&eli->li_wait_daemon, &wait);
+ if (kthread_should_stop()) {
+ ext4_clear_request_list();
+ goto exit_thread;
+ }
}
exit_thread:
wake_up(&eli->li_wait_task);
kfree(ext4_li_info);
+ ext4_lazyinit_task = NULL;
ext4_li_info = NULL;
mutex_unlock(&ext4_li_mtx);
static int ext4_run_lazyinit_thread(void)
{
- struct task_struct *t;
-
- t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
- if (IS_ERR(t)) {
- int err = PTR_ERR(t);
+ ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread,
+ ext4_li_info, "ext4lazyinit");
+ if (IS_ERR(ext4_lazyinit_task)) {
+ int err = PTR_ERR(ext4_lazyinit_task);
ext4_clear_request_list();
del_timer_sync(&ext4_li_info->li_timer);
kfree(ext4_li_info);
* If thread exited earlier
* there's nothing to be done.
*/
- if (!ext4_li_info)
+ if (!ext4_li_info || !ext4_lazyinit_task)
return;
- ext4_clear_request_list();
-
- while (ext4_li_info->li_task) {
- wake_up(&ext4_li_info->li_wait_daemon);
- wait_event(ext4_li_info->li_wait_task,
- ext4_li_info->li_task == NULL);
- }
+ kthread_stop(ext4_lazyinit_task);
}
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sb->s_qcop = &ext4_qctl_operations;
sb->dq_op = &ext4_quota_operations;
#endif
+ memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
mutex_init(&sbi->s_orphan_lock);
mutex_init(&sbi->s_resize_lock);
.fs_flags = FS_REQUIRES_DEV,
};
-int __init ext4_init_feat_adverts(void)
+static int __init ext4_init_feat_adverts(void)
{
struct ext4_features *ef;
int ret = -ENOMEM;
return ret;
}
+static void ext4_exit_feat_adverts(void)
+{
+ kobject_put(&ext4_feat->f_kobj);
+ wait_for_completion(&ext4_feat->f_kobj_unregister);
+ kfree(ext4_feat);
+}
+
+/* Shared across all ext4 file systems */
+wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
static int __init ext4_init_fs(void)
{
- int err;
+ int i, err;
ext4_check_flag_values();
+
+ for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
+ mutex_init(&ext4__aio_mutex[i]);
+ init_waitqueue_head(&ext4__ioend_wq[i]);
+ }
+
err = ext4_init_pageio();
if (err)
return err;
err = ext4_init_system_zone();
if (err)
- goto out5;
+ goto out7;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
- goto out4;
+ goto out6;
ext4_proc_root = proc_mkdir("fs/ext4", NULL);
+ if (!ext4_proc_root)
+ goto out5;
err = ext4_init_feat_adverts();
+ if (err)
+ goto out4;
err = ext4_init_mballoc();
if (err)
out2:
ext4_exit_mballoc();
out3:
- kfree(ext4_feat);
+ ext4_exit_feat_adverts();
+out4:
remove_proc_entry("fs/ext4", NULL);
+out5:
kset_unregister(ext4_kset);
-out4:
+out6:
ext4_exit_system_zone();
-out5:
+out7:
ext4_exit_pageio();
return err;
}
destroy_inodecache();
ext4_exit_xattr();
ext4_exit_mballoc();
+ ext4_exit_feat_adverts();
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
ext4_exit_system_zone();
struct inode *inode = de->d_inode;
u32 ipos_h, ipos_m, ipos_l;
- if (len < 5)
+ if (len < 5) {
+ *lenp = 5;
return 255; /* no room */
+ }
ipos_h = MSDOS_I(inode)->i_pos >> 8;
ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24;
static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
{
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
/* This is not negative dentry. Always valid. */
static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
{
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
/*
SYSCALL_DEFINE1(dup, unsigned int, fildes)
{
int ret = -EBADF;
- struct file *file = fget(fildes);
+ struct file *file = fget_raw(fildes);
if (file) {
ret = get_unused_fd();
return err;
}
+static int check_fcntl_cmd(unsigned cmd)
+{
+ switch (cmd) {
+ case F_DUPFD:
+ case F_DUPFD_CLOEXEC:
+ case F_GETFD:
+ case F_SETFD:
+ case F_GETFL:
+ return 1;
+ }
+ return 0;
+}
+
SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
struct file *filp;
long err = -EBADF;
- filp = fget(fd);
+ filp = fget_raw(fd);
if (!filp)
goto out;
+ if (unlikely(filp->f_mode & FMODE_PATH)) {
+ if (!check_fcntl_cmd(cmd)) {
+ fput(filp);
+ goto out;
+ }
+ }
+
err = security_file_fcntl(filp, cmd, arg);
if (err) {
fput(filp);
long err;
err = -EBADF;
- filp = fget(fd);
+ filp = fget_raw(fd);
if (!filp)
goto out;
+ if (unlikely(filp->f_mode & FMODE_PATH)) {
+ if (!check_fcntl_cmd(cmd)) {
+ fput(filp);
+ goto out;
+ }
+ }
+
err = security_file_fcntl(filp, cmd, arg);
if (err) {
fput(filp);
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
- BUILD_BUG_ON(18 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+ BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
O_RDONLY | O_WRONLY | O_RDWR |
O_CREAT | O_EXCL | O_NOCTTY |
O_TRUNC | O_APPEND | /* O_NONBLOCK | */
__O_SYNC | O_DSYNC | FASYNC |
O_DIRECT | O_LARGEFILE | O_DIRECTORY |
O_NOFOLLOW | O_NOATIME | O_CLOEXEC |
- __FMODE_EXEC
+ __FMODE_EXEC | O_PATH
));
fasync_cache = kmem_cache_create("fasync_cache",
--- /dev/null
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/exportfs.h>
+#include <linux/fs_struct.h>
+#include <linux/fsnotify.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+static long do_sys_name_to_handle(struct path *path,
+ struct file_handle __user *ufh,
+ int __user *mnt_id)
+{
+ long retval;
+ struct file_handle f_handle;
+ int handle_dwords, handle_bytes;
+ struct file_handle *handle = NULL;
+
+ /*
+ * We need t make sure wether the file system
+ * support decoding of the file handle
+ */
+ if (!path->mnt->mnt_sb->s_export_op ||
+ !path->mnt->mnt_sb->s_export_op->fh_to_dentry)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
+ return -EFAULT;
+
+ if (f_handle.handle_bytes > MAX_HANDLE_SZ)
+ return -EINVAL;
+
+ handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+ GFP_KERNEL);
+ if (!handle)
+ return -ENOMEM;
+
+ /* convert handle size to multiple of sizeof(u32) */
+ handle_dwords = f_handle.handle_bytes >> 2;
+
+ /* we ask for a non connected handle */
+ retval = exportfs_encode_fh(path->dentry,
+ (struct fid *)handle->f_handle,
+ &handle_dwords, 0);
+ handle->handle_type = retval;
+ /* convert handle size to bytes */
+ handle_bytes = handle_dwords * sizeof(u32);
+ handle->handle_bytes = handle_bytes;
+ if ((handle->handle_bytes > f_handle.handle_bytes) ||
+ (retval == 255) || (retval == -ENOSPC)) {
+ /* As per old exportfs_encode_fh documentation
+ * we could return ENOSPC to indicate overflow
+ * But file system returned 255 always. So handle
+ * both the values
+ */
+ /*
+ * set the handle size to zero so we copy only
+ * non variable part of the file_handle
+ */
+ handle_bytes = 0;
+ retval = -EOVERFLOW;
+ } else
+ retval = 0;
+ /* copy the mount id */
+ if (copy_to_user(mnt_id, &path->mnt->mnt_id, sizeof(*mnt_id)) ||
+ copy_to_user(ufh, handle,
+ sizeof(struct file_handle) + handle_bytes))
+ retval = -EFAULT;
+ kfree(handle);
+ return retval;
+}
+
+/**
+ * sys_name_to_handle_at: convert name to handle
+ * @dfd: directory relative to which name is interpreted if not absolute
+ * @name: name that should be converted to handle.
+ * @handle: resulting file handle
+ * @mnt_id: mount id of the file system containing the file
+ * @flag: flag value to indicate whether to follow symlink or not
+ *
+ * @handle->handle_size indicate the space available to store the
+ * variable part of the file handle in bytes. If there is not
+ * enough space, the field is updated to return the minimum
+ * value required.
+ */
+SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
+ struct file_handle __user *, handle, int __user *, mnt_id,
+ int, flag)
+{
+ struct path path;
+ int lookup_flags;
+ int err;
+
+ if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
+ return -EINVAL;
+
+ lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
+ if (flag & AT_EMPTY_PATH)
+ lookup_flags |= LOOKUP_EMPTY;
+ err = user_path_at(dfd, name, lookup_flags, &path);
+ if (!err) {
+ err = do_sys_name_to_handle(&path, handle, mnt_id);
+ path_put(&path);
+ }
+ return err;
+}
+
+static struct vfsmount *get_vfsmount_from_fd(int fd)
+{
+ struct path path;
+
+ if (fd == AT_FDCWD) {
+ struct fs_struct *fs = current->fs;
+ spin_lock(&fs->lock);
+ path = fs->pwd;
+ mntget(path.mnt);
+ spin_unlock(&fs->lock);
+ } else {
+ int fput_needed;
+ struct file *file = fget_light(fd, &fput_needed);
+ if (!file)
+ return ERR_PTR(-EBADF);
+ path = file->f_path;
+ mntget(path.mnt);
+ fput_light(file, fput_needed);
+ }
+ return path.mnt;
+}
+
+static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
+{
+ return 1;
+}
+
+static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
+ struct path *path)
+{
+ int retval = 0;
+ int handle_dwords;
+
+ path->mnt = get_vfsmount_from_fd(mountdirfd);
+ if (IS_ERR(path->mnt)) {
+ retval = PTR_ERR(path->mnt);
+ goto out_err;
+ }
+ /* change the handle size to multiple of sizeof(u32) */
+ handle_dwords = handle->handle_bytes >> 2;
+ path->dentry = exportfs_decode_fh(path->mnt,
+ (struct fid *)handle->f_handle,
+ handle_dwords, handle->handle_type,
+ vfs_dentry_acceptable, NULL);
+ if (IS_ERR(path->dentry)) {
+ retval = PTR_ERR(path->dentry);
+ goto out_mnt;
+ }
+ return 0;
+out_mnt:
+ mntput(path->mnt);
+out_err:
+ return retval;
+}
+
+static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
+ struct path *path)
+{
+ int retval = 0;
+ struct file_handle f_handle;
+ struct file_handle *handle = NULL;
+
+ /*
+ * With handle we don't look at the execute bit on the
+ * the directory. Ideally we would like CAP_DAC_SEARCH.
+ * But we don't have that
+ */
+ if (!capable(CAP_DAC_READ_SEARCH)) {
+ retval = -EPERM;
+ goto out_err;
+ }
+ if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
+ retval = -EFAULT;
+ goto out_err;
+ }
+ if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
+ (f_handle.handle_bytes == 0)) {
+ retval = -EINVAL;
+ goto out_err;
+ }
+ handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+ GFP_KERNEL);
+ if (!handle) {
+ retval = -ENOMEM;
+ goto out_err;
+ }
+ /* copy the full handle */
+ if (copy_from_user(handle, ufh,
+ sizeof(struct file_handle) +
+ f_handle.handle_bytes)) {
+ retval = -EFAULT;
+ goto out_handle;
+ }
+
+ retval = do_handle_to_path(mountdirfd, handle, path);
+
+out_handle:
+ kfree(handle);
+out_err:
+ return retval;
+}
+
+long do_handle_open(int mountdirfd,
+ struct file_handle __user *ufh, int open_flag)
+{
+ long retval = 0;
+ struct path path;
+ struct file *file;
+ int fd;
+
+ retval = handle_to_path(mountdirfd, ufh, &path);
+ if (retval)
+ return retval;
+
+ fd = get_unused_fd_flags(open_flag);
+ if (fd < 0) {
+ path_put(&path);
+ return fd;
+ }
+ file = file_open_root(path.dentry, path.mnt, "", open_flag);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ retval = PTR_ERR(file);
+ } else {
+ retval = fd;
+ fsnotify_open(file);
+ fd_install(fd, file);
+ }
+ path_put(&path);
+ return retval;
+}
+
+/**
+ * sys_open_by_handle_at: Open the file handle
+ * @mountdirfd: directory file descriptor
+ * @handle: file handle to be opened
+ * @flag: open flags.
+ *
+ * @mountdirfd indicate the directory file descriptor
+ * of the mount point. file handle is decoded relative
+ * to the vfsmount pointed by the @mountdirfd. @flags
+ * value is same as the open(2) flags.
+ */
+SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
+ struct file_handle __user *, handle,
+ int, flags)
+{
+ long ret;
+
+ if (force_o_largefile())
+ flags |= O_LARGEFILE;
+
+ ret = do_handle_open(mountdirfd, handle, flags);
+ return ret;
+}
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
- if (!atomic_long_inc_not_zero(&file->f_count)) {
- /* File object ref couldn't be taken */
- rcu_read_unlock();
- return NULL;
- }
+ /* File object ref couldn't be taken */
+ if (file->f_mode & FMODE_PATH ||
+ !atomic_long_inc_not_zero(&file->f_count))
+ file = NULL;
}
rcu_read_unlock();
EXPORT_SYMBOL(fget);
+struct file *fget_raw(unsigned int fd)
+{
+ struct file *file;
+ struct files_struct *files = current->files;
+
+ rcu_read_lock();
+ file = fcheck_files(files, fd);
+ if (file) {
+ /* File object ref couldn't be taken */
+ if (!atomic_long_inc_not_zero(&file->f_count))
+ file = NULL;
+ }
+ rcu_read_unlock();
+
+ return file;
+}
+
+EXPORT_SYMBOL(fget_raw);
+
/*
* Lightweight file lookup - no refcnt increment if fd table isn't shared.
*
struct file *file;
struct files_struct *files = current->files;
+ *fput_needed = 0;
+ if (atomic_read(&files->count) == 1) {
+ file = fcheck_files(files, fd);
+ if (file && (file->f_mode & FMODE_PATH))
+ file = NULL;
+ } else {
+ rcu_read_lock();
+ file = fcheck_files(files, fd);
+ if (file) {
+ if (!(file->f_mode & FMODE_PATH) &&
+ atomic_long_inc_not_zero(&file->f_count))
+ *fput_needed = 1;
+ else
+ /* Didn't get the reference, someone's freed */
+ file = NULL;
+ }
+ rcu_read_unlock();
+ }
+
+ return file;
+}
+
+struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+{
+ struct file *file;
+ struct files_struct *files = current->files;
+
*fput_needed = 0;
if (atomic_read(&files->count) == 1) {
file = fcheck_files(files, fd);
{
struct inode *inode;
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
inode = entry->d_inode;
if (err)
return err;
- if ((attr->ia_valid & ATTR_OPEN) && fc->atomic_o_trunc)
- return 0;
+ if (attr->ia_valid & ATTR_OPEN) {
+ if (fc->atomic_o_trunc)
+ return 0;
+ file = NULL;
+ }
if (attr->ia_valid & ATTR_SIZE)
is_truncate = true;
return ff;
}
+static void fuse_release_async(struct work_struct *work)
+{
+ struct fuse_req *req;
+ struct fuse_conn *fc;
+ struct path path;
+
+ req = container_of(work, struct fuse_req, misc.release.work);
+ path = req->misc.release.path;
+ fc = get_fuse_conn(path.dentry->d_inode);
+
+ fuse_put_request(fc, req);
+ path_put(&path);
+}
+
static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req)
{
- path_put(&req->misc.release.path);
+ if (fc->destroy_req) {
+ /*
+ * If this is a fuseblk mount, then it's possible that
+ * releasing the path will result in releasing the
+ * super block and sending the DESTROY request. If
+ * the server is single threaded, this would hang.
+ * For this reason do the path_put() in a separate
+ * thread.
+ */
+ atomic_inc(&req->count);
+ INIT_WORK(&req->misc.release.work, fuse_release_async);
+ schedule_work(&req->misc.release.work);
+ } else {
+ path_put(&req->misc.release.path);
+ }
}
-static void fuse_file_put(struct fuse_file *ff)
+static void fuse_file_put(struct fuse_file *ff, bool sync)
{
if (atomic_dec_and_test(&ff->count)) {
struct fuse_req *req = ff->reserved_req;
- req->end = fuse_release_end;
- fuse_request_send_background(ff->fc, req);
+ if (sync) {
+ fuse_request_send(ff->fc, req);
+ path_put(&req->misc.release.path);
+ fuse_put_request(ff->fc, req);
+ } else {
+ req->end = fuse_release_end;
+ fuse_request_send_background(ff->fc, req);
+ }
kfree(ff);
}
}
* Normally this will send the RELEASE request, however if
* some asynchronous READ or WRITE requests are outstanding,
* the sending will be delayed.
+ *
+ * Make the release synchronous if this is a fuseblk mount,
+ * synchronous RELEASE is allowed (and desirable) in this case
+ * because the server can be trusted not to screw up.
*/
- fuse_file_put(ff);
+ fuse_file_put(ff, ff->fc->destroy_req != NULL);
}
static int fuse_open(struct inode *inode, struct file *file)
page_cache_release(page);
}
if (req->ff)
- fuse_file_put(req->ff);
+ fuse_file_put(req->ff, false);
}
static void fuse_send_readpages(struct fuse_req *req, struct file *file)
static void fuse_writepage_free(struct fuse_conn *fc, struct fuse_req *req)
{
__free_page(req->pages[0]);
- fuse_file_put(req->ff);
+ fuse_file_put(req->ff, false);
}
static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/poll.h>
+#include <linux/workqueue.h>
/** Max number of pages that can be used in a single read request */
#define FUSE_MAX_PAGES_PER_REQ 32
/** Data for asynchronous requests */
union {
struct {
- struct fuse_release_in in;
+ union {
+ struct fuse_release_in in;
+ struct work_struct work;
+ };
struct path path;
} release;
struct fuse_init_in init_in;
u64 nodeid;
u32 generation;
- if (*max_len < len)
+ if (*max_len < len) {
+ *max_len = len;
return 255;
+ }
nodeid = get_fuse_inode(inode)->nodeid;
generation = inode->i_generation;
int error;
int had_lock = 0;
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
struct super_block *sb = inode->i_sb;
struct gfs2_inode *ip = GFS2_I(inode);
- if (*len < GFS2_SMALL_FH_SIZE ||
- (connectable && *len < GFS2_LARGE_FH_SIZE))
+ if (connectable && (*len < GFS2_LARGE_FH_SIZE)) {
+ *len = GFS2_LARGE_FH_SIZE;
return 255;
+ } else if (*len < GFS2_SMALL_FH_SIZE) {
+ *len = GFS2_SMALL_FH_SIZE;
+ return 255;
+ }
fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
#endif
glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
- WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+ WQ_HIGHPRI | WQ_FREEZABLE, 0);
if (IS_ERR(glock_workqueue))
return PTR_ERR(glock_workqueue);
gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
- WQ_MEM_RECLAIM | WQ_FREEZEABLE,
+ WQ_MEM_RECLAIM | WQ_FREEZABLE,
0);
if (IS_ERR(gfs2_delete_workqueue)) {
destroy_workqueue(glock_workqueue);
struct address_space *mapping = (struct address_space *)(gl + 1);
gfs2_init_glock_once(gl);
- memset(mapping, 0, sizeof(*mapping));
- INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
- spin_lock_init(&mapping->tree_lock);
- spin_lock_init(&mapping->i_mmap_lock);
- INIT_LIST_HEAD(&mapping->private_list);
- spin_lock_init(&mapping->private_lock);
- INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
- INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
+ address_space_init_once(mapping);
}
/**
error = -ENOMEM;
gfs_recovery_wq = alloc_workqueue("gfs_recovery",
- WQ_MEM_RECLAIM | WQ_FREEZEABLE, 0);
+ WQ_MEM_RECLAIM | WQ_FREEZABLE, 0);
if (!gfs_recovery_wq)
goto fail_wq;
}
/*
- * hfs_unlink()
+ * hfs_remove()
*
- * This is the unlink() entry in the inode_operations structure for
- * regular HFS directories. The purpose is to delete an existing
- * file, given the inode for the parent directory and the name
- * (and its length) of the existing file.
- */
-static int hfs_unlink(struct inode *dir, struct dentry *dentry)
-{
- struct inode *inode;
- int res;
-
- inode = dentry->d_inode;
- res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name);
- if (res)
- return res;
-
- drop_nlink(inode);
- hfs_delete_inode(inode);
- inode->i_ctime = CURRENT_TIME_SEC;
- mark_inode_dirty(inode);
-
- return res;
-}
-
-/*
- * hfs_rmdir()
+ * This serves as both unlink() and rmdir() in the inode_operations
+ * structure for regular HFS directories. The purpose is to delete
+ * an existing child, given the inode for the parent directory and
+ * the name (and its length) of the existing directory.
*
- * This is the rmdir() entry in the inode_operations structure for
- * regular HFS directories. The purpose is to delete an existing
- * directory, given the inode for the parent directory and the name
- * (and its length) of the existing directory.
+ * HFS does not have hardlinks, so both rmdir and unlink set the
+ * link count to 0. The only difference is the emptiness check.
*/
-static int hfs_rmdir(struct inode *dir, struct dentry *dentry)
+static int hfs_remove(struct inode *dir, struct dentry *dentry)
{
- struct inode *inode;
+ struct inode *inode = dentry->d_inode;
int res;
- inode = dentry->d_inode;
- if (inode->i_size != 2)
+ if (S_ISDIR(inode->i_mode) && inode->i_size != 2)
return -ENOTEMPTY;
res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name);
if (res)
/* Unlink destination if it already exists */
if (new_dentry->d_inode) {
- res = hfs_unlink(new_dir, new_dentry);
+ res = hfs_remove(new_dir, new_dentry);
if (res)
return res;
}
const struct inode_operations hfs_dir_inode_operations = {
.create = hfs_create,
.lookup = hfs_lookup,
- .unlink = hfs_unlink,
+ .unlink = hfs_remove,
.mkdir = hfs_mkdir,
- .rmdir = hfs_rmdir,
+ .rmdir = hfs_remove,
.rename = hfs_rename,
.setattr = hfs_inode_setattr,
};
call_rcu(&inode->i_rcu, i_callback);
}
+void address_space_init_once(struct address_space *mapping)
+{
+ memset(mapping, 0, sizeof(*mapping));
+ INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
+ spin_lock_init(&mapping->tree_lock);
+ spin_lock_init(&mapping->i_mmap_lock);
+ INIT_LIST_HEAD(&mapping->private_list);
+ spin_lock_init(&mapping->private_lock);
+ INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
+ INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
+ mutex_init(&mapping->unmap_mutex);
+}
+EXPORT_SYMBOL(address_space_init_once);
+
/*
* These are initializations that only need to be done
* once, because the fields are idempotent across use
INIT_LIST_HEAD(&inode->i_devices);
INIT_LIST_HEAD(&inode->i_wb_list);
INIT_LIST_HEAD(&inode->i_lru);
- INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
- spin_lock_init(&inode->i_data.tree_lock);
- spin_lock_init(&inode->i_data.i_mmap_lock);
- INIT_LIST_HEAD(&inode->i_data.private_list);
- spin_lock_init(&inode->i_data.private_lock);
- INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap);
- INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear);
+ address_space_init_once(&inode->i_data);
i_size_ordered_init(inode);
#ifdef CONFIG_FSNOTIFY
INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
/**
* invalidate_inodes - attempt to free all inodes on a superblock
* @sb: superblock to operate on
+ * @kill_dirty: flag to guide handling of dirty inodes
*
* Attempts to free all inodes for a given superblock. If there were any
* busy inodes return a non-zero value, else zero.
+ * If @kill_dirty is set, discard dirty inodes too, otherwise treat
+ * them as busy.
*/
-int invalidate_inodes(struct super_block *sb)
+int invalidate_inodes(struct super_block *sb, bool kill_dirty)
{
int busy = 0;
struct inode *inode, *next;
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
continue;
+ if (inode->i_state & I_DIRTY && !kill_dirty) {
+ busy = 1;
+ continue;
+ }
if (atomic_read(&inode->i_count)) {
busy = 1;
continue;
struct nameidata;
extern struct file *nameidata_to_filp(struct nameidata *);
extern void release_open_intent(struct nameidata *);
+struct open_flags {
+ int open_flag;
+ int mode;
+ int acc_mode;
+ int intent;
+};
+extern struct file *do_filp_open(int dfd, const char *pathname,
+ const struct open_flags *op, int lookup_flags);
+extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
+ const char *, const struct open_flags *, int lookup_flags);
+
+extern long do_handle_open(int mountdirfd,
+ struct file_handle __user *ufh, int open_flag);
/*
* inode.c
*/
extern int get_nr_dirty_inodes(void);
extern void evict_inodes(struct super_block *);
-extern int invalidate_inodes(struct super_block *);
+extern int invalidate_inodes(struct super_block *, bool);
* offset of the inode and the upper 16 bits of fh32[1] to
* hold the offset of the parent.
*/
-
- if (len < 3 || (connectable && len < 5))
+ if (connectable && (len < 5)) {
+ *max_len = 5;
+ return 255;
+ } else if (len < 3) {
+ *max_len = 3;
return 255;
+ }
len = 3;
fh32[0] = ei->i_iget5_block;
}
/*
- * Called under j_state_lock. Returns true if a transaction commit was started.
+ * Called with j_state_lock locked for writing.
+ * Returns true if a transaction commit was started.
*/
int __jbd2_log_start_commit(journal_t *journal, tid_t target)
{
{
transaction_t *transaction = NULL;
tid_t tid;
+ int need_to_start = 0;
read_lock(&journal->j_state_lock);
if (journal->j_running_transaction && !current->journal_info) {
transaction = journal->j_running_transaction;
- __jbd2_log_start_commit(journal, transaction->t_tid);
+ if (!tid_geq(journal->j_commit_request, transaction->t_tid))
+ need_to_start = 1;
} else if (journal->j_committing_transaction)
transaction = journal->j_committing_transaction;
tid = transaction->t_tid;
read_unlock(&journal->j_state_lock);
+ if (need_to_start)
+ jbd2_log_start_commit(journal, tid);
jbd2_log_wait_commit(journal, tid);
return 1;
}
static int start_this_handle(journal_t *journal, handle_t *handle,
int gfp_mask)
{
- transaction_t *transaction;
- int needed;
- int nblocks = handle->h_buffer_credits;
- transaction_t *new_transaction = NULL;
+ transaction_t *transaction, *new_transaction = NULL;
+ tid_t tid;
+ int needed, need_to_start;
+ int nblocks = handle->h_buffer_credits;
if (nblocks > journal->j_max_transaction_buffers) {
printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
atomic_sub(nblocks, &transaction->t_outstanding_credits);
prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
TASK_UNINTERRUPTIBLE);
- __jbd2_log_start_commit(journal, transaction->t_tid);
+ tid = transaction->t_tid;
+ need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
+ if (need_to_start)
+ jbd2_log_start_commit(journal, tid);
schedule();
finish_wait(&journal->j_wait_transaction_locked, &wait);
goto repeat;
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
- int ret;
+ tid_t tid;
+ int need_to_start, ret;
/* If we've had an abort of any type, don't even think about
* actually doing the restart! */
spin_unlock(&transaction->t_handle_lock);
jbd_debug(2, "restarting handle %p\n", handle);
- __jbd2_log_start_commit(journal, transaction->t_tid);
+ tid = transaction->t_tid;
+ need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
+ if (need_to_start)
+ jbd2_log_start_commit(journal, tid);
lock_map_release(&handle->h_lockdep_map);
handle->h_buffer_credits = nblocks;
if (ip->i_nlink == JFS_LINK_MAX)
return -EMLINK;
- if (ip->i_nlink == 0)
- return -ENOENT;
-
dquot_initialize(dir);
tid = txBegin(ip->i_sb, 0);
static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd)
{
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
/*
* This is not negative dentry. Always valid.
new_de = minix_find_entry(new_dentry, &new_page);
if (!new_de)
goto out_dir;
- inode_inc_link_count(old_inode);
minix_set_link(new_de, new_page, old_inode);
new_inode->i_ctime = CURRENT_TIME_SEC;
if (dir_de)
if (new_dir->i_nlink >= info->s_link_max)
goto out_dir;
}
- inode_inc_link_count(old_inode);
err = minix_add_link(new_dentry, old_inode);
- if (err) {
- inode_dec_link_count(old_inode);
+ if (err)
goto out_dir;
- }
if (dir_de)
inode_inc_link_count(new_dir);
}
minix_delete_entry(old_de, old_page);
- inode_dec_link_count(old_inode);
+ mark_inode_dirty(old_inode);
if (dir_de) {
minix_set_link(dir_de, dir_page, new_dir);
return retval;
}
-char * getname(const char __user * filename)
+static char *getname_flags(const char __user * filename, int flags)
{
char *tmp, *result;
result = tmp;
if (retval < 0) {
- __putname(tmp);
- result = ERR_PTR(retval);
+ if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
+ __putname(tmp);
+ result = ERR_PTR(retval);
+ }
}
}
audit_getname(result);
return result;
}
+char *getname(const char __user * filename)
+{
+ return getname_flags(filename, 0);
+}
+
#ifdef CONFIG_AUDITSYSCALL
void putname(const char *name)
{
{
struct fs_struct *fs = current->fs;
struct dentry *dentry = nd->path.dentry;
+ int want_root = 0;
BUG_ON(!(nd->flags & LOOKUP_RCU));
- if (nd->root.mnt) {
+ if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+ want_root = 1;
spin_lock(&fs->lock);
if (nd->root.mnt != fs->root.mnt ||
nd->root.dentry != fs->root.dentry)
goto err;
BUG_ON(nd->inode != dentry->d_inode);
spin_unlock(&dentry->d_lock);
- if (nd->root.mnt) {
+ if (want_root) {
path_get(&nd->root);
spin_unlock(&fs->lock);
}
err:
spin_unlock(&dentry->d_lock);
err_root:
- if (nd->root.mnt)
+ if (want_root)
spin_unlock(&fs->lock);
return -ECHILD;
}
{
struct fs_struct *fs = current->fs;
struct dentry *parent = nd->path.dentry;
-
- /*
- * It can be possible to revalidate the dentry that we started
- * the path walk with. force_reval_path may also revalidate the
- * dentry already committed to the nameidata.
- */
- if (unlikely(parent == dentry))
- return nameidata_drop_rcu(nd);
+ int want_root = 0;
BUG_ON(!(nd->flags & LOOKUP_RCU));
- if (nd->root.mnt) {
+ if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+ want_root = 1;
spin_lock(&fs->lock);
if (nd->root.mnt != fs->root.mnt ||
nd->root.dentry != fs->root.dentry)
parent->d_count++;
spin_unlock(&dentry->d_lock);
spin_unlock(&parent->d_lock);
- if (nd->root.mnt) {
+ if (want_root) {
path_get(&nd->root);
spin_unlock(&fs->lock);
}
spin_unlock(&dentry->d_lock);
spin_unlock(&parent->d_lock);
err_root:
- if (nd->root.mnt)
+ if (want_root)
spin_unlock(&fs->lock);
return -ECHILD;
}
/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing. */
static inline int nameidata_dentry_drop_rcu_maybe(struct nameidata *nd, struct dentry *dentry)
{
- if (nd->flags & LOOKUP_RCU)
- return nameidata_dentry_drop_rcu(nd, dentry);
+ if (nd->flags & LOOKUP_RCU) {
+ if (unlikely(nameidata_dentry_drop_rcu(nd, dentry))) {
+ nd->flags &= ~LOOKUP_RCU;
+ if (!(nd->flags & LOOKUP_ROOT))
+ nd->root.mnt = NULL;
+ rcu_read_unlock();
+ br_read_unlock(vfsmount_lock);
+ return -ECHILD;
+ }
+ }
return 0;
}
BUG_ON(!(nd->flags & LOOKUP_RCU));
nd->flags &= ~LOOKUP_RCU;
- nd->root.mnt = NULL;
+ if (!(nd->flags & LOOKUP_ROOT))
+ nd->root.mnt = NULL;
spin_lock(&dentry->d_lock);
if (!__d_rcu_to_refcount(dentry, nd->seq))
goto err_unlock;
return -ECHILD;
}
-/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing. */
-static inline int nameidata_drop_rcu_last_maybe(struct nameidata *nd)
-{
- if (likely(nd->flags & LOOKUP_RCU))
- return nameidata_drop_rcu_last(nd);
- return 0;
-}
-
/**
* release_open_intent - free up open intent resources
* @nd: pointer to nameidata
*/
void release_open_intent(struct nameidata *nd)
{
- if (nd->intent.open.file->f_path.dentry == NULL)
- put_filp(nd->intent.open.file);
- else
- fput(nd->intent.open.file);
-}
-
-/*
- * Call d_revalidate and handle filesystems that request rcu-walk
- * to be dropped. This may be called and return in rcu-walk mode,
- * regardless of success or error. If -ECHILD is returned, the caller
- * must return -ECHILD back up the path walk stack so path walk may
- * be restarted in ref-walk mode.
- */
-static int d_revalidate(struct dentry *dentry, struct nameidata *nd)
-{
- int status;
+ struct file *file = nd->intent.open.file;
- status = dentry->d_op->d_revalidate(dentry, nd);
- if (status == -ECHILD) {
- if (nameidata_dentry_drop_rcu(nd, dentry))
- return status;
- status = dentry->d_op->d_revalidate(dentry, nd);
+ if (file && !IS_ERR(file)) {
+ if (file->f_path.dentry == NULL)
+ put_filp(file);
+ else
+ fput(file);
}
+}
- return status;
+static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+ return dentry->d_op->d_revalidate(dentry, nd);
}
-static inline struct dentry *
+static struct dentry *
do_revalidate(struct dentry *dentry, struct nameidata *nd)
{
- int status;
-
- status = d_revalidate(dentry, nd);
+ int status = d_revalidate(dentry, nd);
if (unlikely(status <= 0)) {
/*
* The dentry failed validation.
* to return a fail status.
*/
if (status < 0) {
- /* If we're in rcu-walk, we don't have a ref */
- if (!(nd->flags & LOOKUP_RCU))
- dput(dentry);
+ dput(dentry);
dentry = ERR_PTR(status);
-
- } else {
- /* Don't d_invalidate in rcu-walk mode */
- if (nameidata_dentry_drop_rcu_maybe(nd, dentry))
- return ERR_PTR(-ECHILD);
- if (!d_invalidate(dentry)) {
- dput(dentry);
- dentry = NULL;
- }
+ } else if (!d_invalidate(dentry)) {
+ dput(dentry);
+ dentry = NULL;
}
}
return dentry;
}
-static inline int need_reval_dot(struct dentry *dentry)
-{
- if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
- return 0;
-
- if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
- return 0;
-
- return 1;
-}
-
/*
- * force_reval_path - force revalidation of a dentry
+ * handle_reval_path - force revalidation of a dentry
*
* In some situations the path walking code will trust dentries without
* revalidating them. This causes problems for filesystems that depend on
* invalidate the dentry. It's up to the caller to handle putting references
* to the path if necessary.
*/
-static int
-force_reval_path(struct path *path, struct nameidata *nd)
+static inline int handle_reval_path(struct nameidata *nd)
{
+ struct dentry *dentry = nd->path.dentry;
int status;
- struct dentry *dentry = path->dentry;
- /*
- * only check on filesystems where it's possible for the dentry to
- * become stale.
- */
- if (!need_reval_dot(dentry))
+ if (likely(!(nd->flags & LOOKUP_JUMPED)))
+ return 0;
+
+ if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
return 0;
+ if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
+ return 0;
+
+ /* Note: we do not d_invalidate() */
status = d_revalidate(dentry, nd);
if (status > 0)
return 0;
- if (!status) {
- /* Don't d_invalidate in rcu-walk mode */
- if (nameidata_drop_rcu(nd))
- return -ECHILD;
- d_invalidate(dentry);
+ if (!status)
status = -ESTALE;
- }
+
return status;
}
path_put(&nd->path);
nd->path = nd->root;
path_get(&nd->root);
+ nd->flags |= LOOKUP_JUMPED;
}
nd->inode = nd->path.dentry->d_inode;
nd->path.dentry = path->dentry;
}
+static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
+{
+ struct inode *inode = link->dentry->d_inode;
+ if (!IS_ERR(cookie) && inode->i_op->put_link)
+ inode->i_op->put_link(link->dentry, nd, cookie);
+ path_put(link);
+}
+
static __always_inline int
-__do_follow_link(const struct path *link, struct nameidata *nd, void **p)
+follow_link(struct path *link, struct nameidata *nd, void **p)
{
int error;
struct dentry *dentry = link->dentry;
+ BUG_ON(nd->flags & LOOKUP_RCU);
+
+ if (unlikely(current->total_link_count >= 40)) {
+ *p = ERR_PTR(-ELOOP); /* no ->put_link(), please */
+ path_put_conditional(link, nd);
+ path_put(&nd->path);
+ return -ELOOP;
+ }
+ cond_resched();
+ current->total_link_count++;
+
touch_atime(link->mnt, dentry);
nd_set_link(nd, NULL);
if (link->mnt == nd->path.mnt)
mntget(link->mnt);
+ error = security_inode_follow_link(link->dentry, nd);
+ if (error) {
+ *p = ERR_PTR(error); /* no ->put_link(), please */
+ path_put(&nd->path);
+ return error;
+ }
+
nd->last_type = LAST_BIND;
*p = dentry->d_inode->i_op->follow_link(dentry, nd);
error = PTR_ERR(*p);
if (s)
error = __vfs_follow_link(nd, s);
else if (nd->last_type == LAST_BIND) {
- error = force_reval_path(&nd->path, nd);
- if (error)
+ nd->flags |= LOOKUP_JUMPED;
+ nd->inode = nd->path.dentry->d_inode;
+ if (nd->inode->i_op->follow_link) {
+ /* stepped on a _really_ weird one */
path_put(&nd->path);
+ error = -ELOOP;
+ }
}
}
return error;
}
-/*
- * 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 do_follow_link(struct path *path, struct nameidata *nd)
-{
- void *cookie;
- int err = -ELOOP;
- if (current->link_count >= MAX_NESTED_LINKS)
- goto loop;
- if (current->total_link_count >= 40)
- goto loop;
- BUG_ON(nd->depth >= MAX_NESTED_LINKS);
- cond_resched();
- err = security_inode_follow_link(path->dentry, nd);
- if (err)
- goto loop;
- current->link_count++;
- current->total_link_count++;
- nd->depth++;
- err = __do_follow_link(path, nd, &cookie);
- if (!IS_ERR(cookie) && path->dentry->d_inode->i_op->put_link)
- path->dentry->d_inode->i_op->put_link(path->dentry, nd, cookie);
- path_put(path);
- current->link_count--;
- nd->depth--;
- return err;
-loop:
- path_put_conditional(path, nd);
- path_put(&nd->path);
- return err;
-}
-
static int follow_up_rcu(struct path *path)
{
struct vfsmount *parent;
seq = read_seqcount_begin(&parent->d_seq);
if (read_seqcount_retry(&old->d_seq, nd->seq))
- return -ECHILD;
+ goto failed;
inode = parent->d_inode;
nd->path.dentry = parent;
nd->seq = seq;
}
__follow_mount_rcu(nd, &nd->path, &inode, true);
nd->inode = inode;
-
return 0;
+
+failed:
+ nd->flags &= ~LOOKUP_RCU;
+ if (!(nd->flags & LOOKUP_ROOT))
+ nd->root.mnt = NULL;
+ rcu_read_unlock();
+ br_read_unlock(vfsmount_lock);
+ return -ECHILD;
}
/*
{
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent = nd->path.dentry;
- struct inode *dir;
+ int need_reval = 1;
+ int status = 1;
int err;
- /*
- * See if the low-level filesystem might want
- * to use its own hash..
- */
- if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
- err = parent->d_op->d_hash(parent, nd->inode, name);
- if (err < 0)
- return err;
- }
-
/*
* Rename seqlock is not required here because in the off chance
* of a false negative due to a concurrent rename, we're going to
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
-
*inode = nd->inode;
dentry = __d_lookup_rcu(parent, name, &seq, inode);
- if (!dentry) {
- if (nameidata_drop_rcu(nd))
- return -ECHILD;
- goto need_lookup;
- }
+ if (!dentry)
+ goto unlazy;
+
/* Memory barrier in read_seqcount_begin of child is enough */
if (__read_seqcount_retry(&parent->d_seq, nd->seq))
return -ECHILD;
-
nd->seq = seq;
- if (dentry->d_flags & DCACHE_OP_REVALIDATE)
- goto need_revalidate;
-done2:
+
+ if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
+ status = d_revalidate(dentry, nd);
+ if (unlikely(status <= 0)) {
+ if (status != -ECHILD)
+ need_reval = 0;
+ goto unlazy;
+ }
+ }
path->mnt = mnt;
path->dentry = dentry;
if (likely(__follow_mount_rcu(nd, path, inode, false)))
return 0;
- if (nameidata_drop_rcu(nd))
- return -ECHILD;
- /* fallthru */
+unlazy:
+ if (dentry) {
+ if (nameidata_dentry_drop_rcu(nd, dentry))
+ return -ECHILD;
+ } else {
+ if (nameidata_drop_rcu(nd))
+ return -ECHILD;
+ }
+ } else {
+ dentry = __d_lookup(parent, name);
}
- dentry = __d_lookup(parent, name);
- if (!dentry)
- goto need_lookup;
-found:
- if (dentry->d_flags & DCACHE_OP_REVALIDATE)
- goto need_revalidate;
-done:
+
+retry:
+ if (unlikely(!dentry)) {
+ struct inode *dir = parent->d_inode;
+ BUG_ON(nd->inode != dir);
+
+ mutex_lock(&dir->i_mutex);
+ dentry = d_lookup(parent, name);
+ if (likely(!dentry)) {
+ dentry = d_alloc_and_lookup(parent, name, nd);
+ if (IS_ERR(dentry)) {
+ mutex_unlock(&dir->i_mutex);
+ return PTR_ERR(dentry);
+ }
+ /* known good */
+ need_reval = 0;
+ status = 1;
+ }
+ mutex_unlock(&dir->i_mutex);
+ }
+ if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
+ status = d_revalidate(dentry, nd);
+ if (unlikely(status <= 0)) {
+ if (status < 0) {
+ dput(dentry);
+ return status;
+ }
+ if (!d_invalidate(dentry)) {
+ dput(dentry);
+ dentry = NULL;
+ need_reval = 1;
+ goto retry;
+ }
+ }
+
path->mnt = mnt;
path->dentry = dentry;
err = follow_managed(path, nd->flags);
}
*inode = path->dentry->d_inode;
return 0;
+}
-need_lookup:
- dir = parent->d_inode;
- BUG_ON(nd->inode != dir);
+static inline int may_lookup(struct nameidata *nd)
+{
+ if (nd->flags & LOOKUP_RCU) {
+ int err = exec_permission(nd->inode, IPERM_FLAG_RCU);
+ if (err != -ECHILD)
+ return err;
+ if (nameidata_drop_rcu(nd))
+ return -ECHILD;
+ }
+ return exec_permission(nd->inode, 0);
+}
- mutex_lock(&dir->i_mutex);
- /*
- * First re-do the cached lookup just in case it was created
- * while we waited for the directory semaphore, or the first
- * lookup failed due to an unrelated rename.
- *
- * This could use version numbering or similar to avoid unnecessary
- * cache lookups, but then we'd have to do the first lookup in the
- * non-racy way. However in the common case here, everything should
- * be hot in cache, so would it be a big win?
- */
- dentry = d_lookup(parent, name);
- if (likely(!dentry)) {
- dentry = d_alloc_and_lookup(parent, name, nd);
- mutex_unlock(&dir->i_mutex);
- if (IS_ERR(dentry))
- goto fail;
- goto done;
+static inline int handle_dots(struct nameidata *nd, int type)
+{
+ if (type == LAST_DOTDOT) {
+ if (nd->flags & LOOKUP_RCU) {
+ if (follow_dotdot_rcu(nd))
+ return -ECHILD;
+ } else
+ follow_dotdot(nd);
+ }
+ return 0;
+}
+
+static void terminate_walk(struct nameidata *nd)
+{
+ 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();
+ br_read_unlock(vfsmount_lock);
}
+}
+
+static inline int walk_component(struct nameidata *nd, struct path *path,
+ struct qstr *name, int type, int follow)
+{
+ struct inode *inode;
+ int err;
/*
- * Uhhuh! Nasty case: the cache was re-populated while
- * we waited on the semaphore. Need to revalidate.
+ * "." and ".." are special - ".." especially so because it has
+ * to be able to know about the current root directory and
+ * parent relationships.
*/
- mutex_unlock(&dir->i_mutex);
- goto found;
+ if (unlikely(type != LAST_NORM))
+ return handle_dots(nd, type);
+ err = do_lookup(nd, name, path, &inode);
+ if (unlikely(err)) {
+ terminate_walk(nd);
+ return err;
+ }
+ if (!inode) {
+ path_to_nameidata(path, nd);
+ terminate_walk(nd);
+ return -ENOENT;
+ }
+ if (unlikely(inode->i_op->follow_link) && follow) {
+ if (nameidata_dentry_drop_rcu_maybe(nd, path->dentry))
+ return -ECHILD;
+ BUG_ON(inode != path->dentry->d_inode);
+ return 1;
+ }
+ path_to_nameidata(path, nd);
+ nd->inode = inode;
+ return 0;
+}
-need_revalidate:
- dentry = do_revalidate(dentry, nd);
- if (!dentry)
- goto need_lookup;
- if (IS_ERR(dentry))
- goto fail;
- if (nd->flags & LOOKUP_RCU)
- goto done2;
- goto done;
+/*
+ * 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;
-fail:
- return PTR_ERR(dentry);
+ BUG_ON(nd->depth >= MAX_NESTED_LINKS);
+ if (unlikely(current->link_count >= MAX_NESTED_LINKS)) {
+ path_put_conditional(path, nd);
+ path_put(&nd->path);
+ return -ELOOP;
+ }
+
+ nd->depth++;
+ current->link_count++;
+
+ do {
+ struct path link = *path;
+ void *cookie;
+
+ res = follow_link(&link, nd, &cookie);
+ if (!res)
+ res = walk_component(nd, path, &nd->last,
+ nd->last_type, LOOKUP_FOLLOW);
+ put_link(nd, &link, cookie);
+ } while (res > 0);
+
+ current->link_count--;
+ nd->depth--;
+ return res;
}
/*
while (*name=='/')
name++;
if (!*name)
- goto return_reval;
-
- if (nd->depth)
- lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE);
+ return 0;
/* At this point we know we have a real path component. */
for(;;) {
- struct inode *inode;
unsigned long hash;
struct qstr this;
unsigned int c;
+ int type;
nd->flags |= LOOKUP_CONTINUE;
- if (nd->flags & LOOKUP_RCU) {
- err = exec_permission(nd->inode, IPERM_FLAG_RCU);
- if (err == -ECHILD) {
- if (nameidata_drop_rcu(nd))
- return -ECHILD;
- goto exec_again;
- }
- } else {
-exec_again:
- err = exec_permission(nd->inode, 0);
- }
+
+ err = may_lookup(nd);
if (err)
break;
this.len = name - (const char *) this.name;
this.hash = end_name_hash(hash);
+ type = LAST_NORM;
+ if (this.name[0] == '.') switch (this.len) {
+ case 2:
+ if (this.name[1] == '.') {
+ type = LAST_DOTDOT;
+ nd->flags |= LOOKUP_JUMPED;
+ }
+ break;
+ case 1:
+ type = LAST_DOT;
+ }
+ if (likely(type == LAST_NORM)) {
+ struct dentry *parent = nd->path.dentry;
+ nd->flags &= ~LOOKUP_JUMPED;
+ if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
+ err = parent->d_op->d_hash(parent, nd->inode,
+ &this);
+ if (err < 0)
+ break;
+ }
+ }
+
/* remove trailing slashes? */
if (!c)
goto last_component;
while (*++name == '/');
if (!*name)
- goto last_with_slashes;
+ goto last_component;
- /*
- * "." and ".." are special - ".." especially so because it has
- * to be able to know about the current root directory and
- * parent relationships.
- */
- if (this.name[0] == '.') switch (this.len) {
- default:
- break;
- case 2:
- if (this.name[1] != '.')
- break;
- if (nd->flags & LOOKUP_RCU) {
- if (follow_dotdot_rcu(nd))
- return -ECHILD;
- } else
- follow_dotdot(nd);
- /* fallthrough */
- case 1:
- continue;
- }
- /* This does the actual lookups.. */
- err = do_lookup(nd, &this, &next, &inode);
- if (err)
- break;
- err = -ENOENT;
- if (!inode)
- goto out_dput;
+ err = walk_component(nd, &next, &this, type, LOOKUP_FOLLOW);
+ if (err < 0)
+ return err;
- if (inode->i_op->follow_link) {
- /* We commonly drop rcu-walk here */
- if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry))
- return -ECHILD;
- BUG_ON(inode != next.dentry->d_inode);
- err = do_follow_link(&next, nd);
+ if (err) {
+ err = nested_symlink(&next, nd);
if (err)
- goto return_err;
- nd->inode = nd->path.dentry->d_inode;
- err = -ENOENT;
- if (!nd->inode)
- break;
- } else {
- path_to_nameidata(&next, nd);
- nd->inode = inode;
+ return err;
}
err = -ENOTDIR;
if (!nd->inode->i_op->lookup)
continue;
/* here ends the main loop */
-last_with_slashes:
- lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
last_component:
/* Clear LOOKUP_CONTINUE iff it was previously unset */
nd->flags &= lookup_flags | ~LOOKUP_CONTINUE;
- if (lookup_flags & LOOKUP_PARENT)
- goto lookup_parent;
- if (this.name[0] == '.') switch (this.len) {
- default:
- break;
- case 2:
- if (this.name[1] != '.')
- break;
- if (nd->flags & LOOKUP_RCU) {
- if (follow_dotdot_rcu(nd))
- return -ECHILD;
- } else
- follow_dotdot(nd);
- /* fallthrough */
- case 1:
- goto return_reval;
- }
- err = do_lookup(nd, &this, &next, &inode);
- if (err)
- break;
- if (inode && unlikely(inode->i_op->follow_link) &&
- (lookup_flags & LOOKUP_FOLLOW)) {
- if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry))
- return -ECHILD;
- BUG_ON(inode != next.dentry->d_inode);
- err = do_follow_link(&next, nd);
- if (err)
- goto return_err;
- nd->inode = nd->path.dentry->d_inode;
- } else {
- path_to_nameidata(&next, nd);
- nd->inode = inode;
- }
- err = -ENOENT;
- if (!nd->inode)
- break;
- if (lookup_flags & LOOKUP_DIRECTORY) {
- err = -ENOTDIR;
- if (!nd->inode->i_op->lookup)
- break;
- }
- goto return_base;
-lookup_parent:
nd->last = this;
- nd->last_type = LAST_NORM;
- if (this.name[0] != '.')
- goto return_base;
- if (this.len == 1)
- nd->last_type = LAST_DOT;
- else if (this.len == 2 && this.name[1] == '.')
- nd->last_type = LAST_DOTDOT;
- else
- goto return_base;
-return_reval:
- /*
- * We bypassed the ordinary revalidation routines.
- * We may need to check the cached dentry for staleness.
- */
- if (need_reval_dot(nd->path.dentry)) {
- /* Note: we do not d_invalidate() */
- err = d_revalidate(nd->path.dentry, nd);
- if (!err)
- err = -ESTALE;
- if (err < 0)
- break;
- }
-return_base:
- if (nameidata_drop_rcu_last_maybe(nd))
- return -ECHILD;
+ nd->last_type = type;
return 0;
-out_dput:
- if (!(nd->flags & LOOKUP_RCU))
- path_put_conditional(&next, nd);
- break;
}
- if (!(nd->flags & LOOKUP_RCU))
- path_put(&nd->path);
-return_err:
+ terminate_walk(nd);
return err;
}
-static inline int path_walk_rcu(const char *name, struct nameidata *nd)
-{
- current->total_link_count = 0;
-
- return link_path_walk(name, nd);
-}
-
-static inline int path_walk_simple(const char *name, struct nameidata *nd)
-{
- current->total_link_count = 0;
-
- return link_path_walk(name, nd);
-}
-
-static int path_walk(const char *name, struct nameidata *nd)
-{
- struct path save = nd->path;
- int result;
-
- current->total_link_count = 0;
-
- /* make sure the stuff we saved doesn't go away */
- path_get(&save);
-
- result = link_path_walk(name, nd);
- if (result == -ESTALE) {
- /* nd->path had been dropped */
- current->total_link_count = 0;
- nd->path = save;
- path_get(&nd->path);
- nd->flags |= LOOKUP_REVAL;
- result = link_path_walk(name, nd);
- }
-
- path_put(&save);
-
- return result;
-}
-
-static void path_finish_rcu(struct nameidata *nd)
-{
- if (nd->flags & LOOKUP_RCU) {
- /* RCU dangling. Cancel it. */
- nd->flags &= ~LOOKUP_RCU;
- nd->root.mnt = NULL;
- rcu_read_unlock();
- br_read_unlock(vfsmount_lock);
- }
- if (nd->file)
- fput(nd->file);
-}
-
-static int path_init_rcu(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
+static int path_init(int dfd, const char *name, unsigned int flags,
+ struct nameidata *nd, struct file **fp)
{
int retval = 0;
int fput_needed;
struct file *file;
nd->last_type = LAST_ROOT; /* if there are only slashes... */
- nd->flags = flags | LOOKUP_RCU;
+ nd->flags = flags | LOOKUP_JUMPED;
nd->depth = 0;
+ if (flags & LOOKUP_ROOT) {
+ struct inode *inode = nd->root.dentry->d_inode;
+ if (*name) {
+ if (!inode->i_op->lookup)
+ return -ENOTDIR;
+ retval = inode_permission(inode, MAY_EXEC);
+ if (retval)
+ return retval;
+ }
+ nd->path = nd->root;
+ nd->inode = inode;
+ if (flags & LOOKUP_RCU) {
+ br_read_lock(vfsmount_lock);
+ rcu_read_lock();
+ nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+ } else {
+ path_get(&nd->path);
+ }
+ return 0;
+ }
+
nd->root.mnt = NULL;
- nd->file = NULL;
if (*name=='/') {
- struct fs_struct *fs = current->fs;
- unsigned seq;
-
- br_read_lock(vfsmount_lock);
- rcu_read_lock();
-
- do {
- seq = read_seqcount_begin(&fs->seq);
- nd->root = fs->root;
- nd->path = nd->root;
- nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
- } while (read_seqcount_retry(&fs->seq, seq));
-
+ if (flags & LOOKUP_RCU) {
+ br_read_lock(vfsmount_lock);
+ rcu_read_lock();
+ set_root_rcu(nd);
+ } else {
+ set_root(nd);
+ path_get(&nd->root);
+ }
+ nd->path = nd->root;
} else if (dfd == AT_FDCWD) {
- struct fs_struct *fs = current->fs;
- unsigned seq;
+ if (flags & LOOKUP_RCU) {
+ struct fs_struct *fs = current->fs;
+ unsigned seq;
- br_read_lock(vfsmount_lock);
- rcu_read_lock();
-
- do {
- seq = read_seqcount_begin(&fs->seq);
- nd->path = fs->pwd;
- nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
- } while (read_seqcount_retry(&fs->seq, seq));
+ br_read_lock(vfsmount_lock);
+ rcu_read_lock();
+ do {
+ seq = read_seqcount_begin(&fs->seq);
+ nd->path = fs->pwd;
+ nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+ } while (read_seqcount_retry(&fs->seq, seq));
+ } else {
+ get_fs_pwd(current->fs, &nd->path);
+ }
} else {
struct dentry *dentry;
- file = fget_light(dfd, &fput_needed);
+ file = fget_raw_light(dfd, &fput_needed);
retval = -EBADF;
if (!file)
goto out_fail;
dentry = file->f_path.dentry;
- retval = -ENOTDIR;
- if (!S_ISDIR(dentry->d_inode->i_mode))
- goto fput_fail;
+ if (*name) {
+ retval = -ENOTDIR;
+ if (!S_ISDIR(dentry->d_inode->i_mode))
+ goto fput_fail;
- retval = file_permission(file, MAY_EXEC);
- if (retval)
- goto fput_fail;
+ retval = file_permission(file, MAY_EXEC);
+ if (retval)
+ goto fput_fail;
+ }
nd->path = file->f_path;
- if (fput_needed)
- nd->file = file;
-
- nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
- br_read_lock(vfsmount_lock);
- rcu_read_lock();
+ if (flags & LOOKUP_RCU) {
+ if (fput_needed)
+ *fp = file;
+ nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+ br_read_lock(vfsmount_lock);
+ rcu_read_lock();
+ } else {
+ path_get(&file->f_path);
+ fput_light(file, fput_needed);
+ }
}
+
nd->inode = nd->path.dentry->d_inode;
return 0;
return retval;
}
-static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
+static inline int lookup_last(struct nameidata *nd, struct path *path)
{
- int retval = 0;
- int fput_needed;
- struct file *file;
-
- nd->last_type = LAST_ROOT; /* if there are only slashes... */
- nd->flags = flags;
- nd->depth = 0;
- nd->root.mnt = NULL;
-
- if (*name=='/') {
- set_root(nd);
- nd->path = nd->root;
- path_get(&nd->root);
- } else if (dfd == AT_FDCWD) {
- get_fs_pwd(current->fs, &nd->path);
- } else {
- struct dentry *dentry;
-
- file = fget_light(dfd, &fput_needed);
- retval = -EBADF;
- if (!file)
- goto out_fail;
-
- dentry = file->f_path.dentry;
-
- retval = -ENOTDIR;
- if (!S_ISDIR(dentry->d_inode->i_mode))
- goto fput_fail;
-
- retval = file_permission(file, MAY_EXEC);
- if (retval)
- goto fput_fail;
-
- nd->path = file->f_path;
- path_get(&file->f_path);
+ if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
+ nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
- fput_light(file, fput_needed);
- }
- nd->inode = nd->path.dentry->d_inode;
- return 0;
-
-fput_fail:
- fput_light(file, fput_needed);
-out_fail:
- return retval;
+ nd->flags &= ~LOOKUP_PARENT;
+ return walk_component(nd, path, &nd->last, nd->last_type,
+ nd->flags & LOOKUP_FOLLOW);
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
-static int do_path_lookup(int dfd, const char *name,
+static int path_lookupat(int dfd, const char *name,
unsigned int flags, struct nameidata *nd)
{
- int retval;
+ struct file *base = NULL;
+ struct path path;
+ int err;
/*
* Path walking is largely split up into 2 different synchronisation
* be handled by restarting a traditional ref-walk (which will always
* be able to complete).
*/
- retval = path_init_rcu(dfd, name, flags, nd);
- if (unlikely(retval))
- return retval;
- retval = path_walk_rcu(name, nd);
- path_finish_rcu(nd);
- if (nd->root.mnt) {
- path_put(&nd->root);
- nd->root.mnt = NULL;
+ err = path_init(dfd, name, flags | LOOKUP_PARENT, nd, &base);
+
+ if (unlikely(err))
+ return err;
+
+ current->total_link_count = 0;
+ err = link_path_walk(name, nd);
+
+ if (!err && !(flags & LOOKUP_PARENT)) {
+ err = lookup_last(nd, &path);
+ while (err > 0) {
+ void *cookie;
+ struct path link = path;
+ nd->flags |= LOOKUP_PARENT;
+ err = follow_link(&link, nd, &cookie);
+ if (!err)
+ err = lookup_last(nd, &path);
+ put_link(nd, &link, cookie);
+ }
}
- if (unlikely(retval == -ECHILD || retval == -ESTALE)) {
- /* slower, locked walk */
- if (retval == -ESTALE)
- flags |= LOOKUP_REVAL;
- retval = path_init(dfd, name, flags, nd);
- if (unlikely(retval))
- return retval;
- retval = path_walk(name, nd);
- if (nd->root.mnt) {
- path_put(&nd->root);
- nd->root.mnt = NULL;
+ if (nd->flags & LOOKUP_RCU) {
+ /* went all way through without dropping RCU */
+ BUG_ON(err);
+ if (nameidata_drop_rcu_last(nd))
+ err = -ECHILD;
+ }
+
+ if (!err)
+ err = handle_reval_path(nd);
+
+ if (!err && nd->flags & LOOKUP_DIRECTORY) {
+ if (!nd->inode->i_op->lookup) {
+ path_put(&nd->path);
+ return -ENOTDIR;
}
}
+ if (base)
+ fput(base);
+
+ if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+ path_put(&nd->root);
+ nd->root.mnt = NULL;
+ }
+ return err;
+}
+
+static int do_path_lookup(int dfd, const char *name,
+ unsigned int flags, struct nameidata *nd)
+{
+ int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
+ if (unlikely(retval == -ECHILD))
+ retval = path_lookupat(dfd, name, flags, nd);
+ if (unlikely(retval == -ESTALE))
+ retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);
+
if (likely(!retval)) {
if (unlikely(!audit_dummy_context())) {
if (nd->path.dentry && nd->inode)
audit_inode(name, nd->path.dentry);
}
}
-
return retval;
}
-int path_lookup(const char *name, unsigned int flags,
- struct nameidata *nd)
+int kern_path_parent(const char *name, struct nameidata *nd)
{
- return do_path_lookup(AT_FDCWD, name, flags, nd);
+ return do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, nd);
}
int kern_path(const char *name, unsigned int flags, struct path *path)
const char *name, unsigned int flags,
struct nameidata *nd)
{
- int retval;
-
- /* same as do_path_lookup */
- nd->last_type = LAST_ROOT;
- nd->flags = flags;
- nd->depth = 0;
-
- nd->path.dentry = dentry;
- nd->path.mnt = mnt;
- path_get(&nd->path);
- nd->root = nd->path;
- path_get(&nd->root);
- nd->inode = nd->path.dentry->d_inode;
-
- retval = path_walk(name, nd);
- if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
- nd->inode))
- audit_inode(name, nd->path.dentry);
-
- path_put(&nd->root);
- nd->root.mnt = NULL;
-
- return retval;
+ nd->root.dentry = dentry;
+ nd->root.mnt = mnt;
+ /* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */
+ return do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, nd);
}
static struct dentry *__lookup_hash(struct qstr *name,
if (err)
return ERR_PTR(err);
- /*
- * See if the low-level filesystem might want
- * to use its own hash..
- */
- if (base->d_flags & DCACHE_OP_HASH) {
- err = base->d_op->d_hash(base, inode, name);
- dentry = ERR_PTR(err);
- if (err < 0)
- goto out;
- }
-
/*
* Don't bother with __d_lookup: callers are for creat as
* well as unlink, so a lot of the time it would cost
if (!dentry)
dentry = d_alloc_and_lookup(base, name, nd);
-out:
+
return dentry;
}
return __lookup_hash(&nd->last, nd->path.dentry, nd);
}
-static int __lookup_one_len(const char *name, struct qstr *this,
- struct dentry *base, int len)
-{
- unsigned long hash;
- unsigned int c;
-
- this->name = name;
- this->len = len;
- if (!len)
- return -EACCES;
-
- hash = init_name_hash();
- while (len--) {
- c = *(const unsigned char *)name++;
- if (c == '/' || c == '\0')
- return -EACCES;
- hash = partial_name_hash(c, hash);
- }
- this->hash = end_name_hash(hash);
- return 0;
-}
-
/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
*/
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
- int err;
struct qstr this;
+ unsigned long hash;
+ unsigned int c;
WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
- err = __lookup_one_len(name, &this, base, len);
- if (err)
- return ERR_PTR(err);
+ this.name = name;
+ this.len = len;
+ if (!len)
+ return ERR_PTR(-EACCES);
+
+ hash = init_name_hash();
+ while (len--) {
+ c = *(const unsigned char *)name++;
+ if (c == '/' || c == '\0')
+ return ERR_PTR(-EACCES);
+ hash = partial_name_hash(c, hash);
+ }
+ this.hash = end_name_hash(hash);
+ /*
+ * See if the low-level filesystem might want
+ * to use its own hash..
+ */
+ if (base->d_flags & DCACHE_OP_HASH) {
+ int err = base->d_op->d_hash(base, base->d_inode, &this);
+ if (err < 0)
+ return ERR_PTR(err);
+ }
return __lookup_hash(&this, base, NULL);
}
struct path *path)
{
struct nameidata nd;
- char *tmp = getname(name);
+ char *tmp = getname_flags(name, flags);
int err = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
return error;
}
-int may_open(struct path *path, int acc_mode, int flag)
+static int may_open(struct path *path, int acc_mode, int flag)
{
struct dentry *dentry = path->dentry;
struct inode *inode = dentry->d_inode;
int error;
+ /* O_PATH? */
+ if (!acc_mode)
+ return 0;
+
if (!inode)
return -ENOENT;
return error;
}
-/*
- * Be careful about ever adding any more callers of this
- * function. Its flags must be in the namei format, not
- * what get passed to sys_open().
- */
-static int __open_namei_create(struct nameidata *nd, struct path *path,
- int open_flag, int mode)
-{
- int error;
- struct dentry *dir = nd->path.dentry;
-
- if (!IS_POSIXACL(dir->d_inode))
- mode &= ~current_umask();
- error = security_path_mknod(&nd->path, path->dentry, mode, 0);
- if (error)
- goto out_unlock;
- error = vfs_create(dir->d_inode, path->dentry, mode, nd);
-out_unlock:
- mutex_unlock(&dir->d_inode->i_mutex);
- dput(nd->path.dentry);
- nd->path.dentry = path->dentry;
-
- if (error)
- return error;
- /* Don't check for write permission, don't truncate */
- return may_open(&nd->path, 0, open_flag & ~O_TRUNC);
-}
-
/*
* Note that while the flag value (low two bits) for sys_open means:
* 00 - read-only
return flag;
}
-static int open_will_truncate(int flag, struct inode *inode)
-{
- /*
- * We'll never write to the fs underlying
- * a device file.
- */
- if (special_file(inode->i_mode))
- return 0;
- return (flag & O_TRUNC);
-}
-
-static struct file *finish_open(struct nameidata *nd,
- int open_flag, int acc_mode)
-{
- struct file *filp;
- int will_truncate;
- int error;
-
- will_truncate = open_will_truncate(open_flag, nd->path.dentry->d_inode);
- if (will_truncate) {
- error = mnt_want_write(nd->path.mnt);
- if (error)
- goto exit;
- }
- error = may_open(&nd->path, acc_mode, open_flag);
- if (error) {
- if (will_truncate)
- mnt_drop_write(nd->path.mnt);
- goto exit;
- }
- filp = nameidata_to_filp(nd);
- if (!IS_ERR(filp)) {
- error = ima_file_check(filp, acc_mode);
- if (error) {
- fput(filp);
- filp = ERR_PTR(error);
- }
- }
- if (!IS_ERR(filp)) {
- if (will_truncate) {
- error = handle_truncate(filp);
- if (error) {
- fput(filp);
- filp = ERR_PTR(error);
- }
- }
- }
- /*
- * It is now safe to drop the mnt write
- * because the filp has had a write taken
- * on its behalf.
- */
- if (will_truncate)
- mnt_drop_write(nd->path.mnt);
- path_put(&nd->path);
- return filp;
-
-exit:
- if (!IS_ERR(nd->intent.open.file))
- release_open_intent(nd);
- path_put(&nd->path);
- return ERR_PTR(error);
-}
-
/*
- * Handle O_CREAT case for do_filp_open
+ * Handle the last step of open()
*/
static struct file *do_last(struct nameidata *nd, struct path *path,
- int open_flag, int acc_mode,
- int mode, const char *pathname)
+ const struct open_flags *op, const char *pathname)
{
struct dentry *dir = nd->path.dentry;
+ struct dentry *dentry;
+ int open_flag = op->open_flag;
+ int will_truncate = open_flag & O_TRUNC;
+ int want_write = 0;
+ int acc_mode = op->acc_mode;
struct file *filp;
- int error = -EISDIR;
+ int error;
+
+ nd->flags &= ~LOOKUP_PARENT;
+ nd->flags |= op->intent;
switch (nd->last_type) {
case LAST_DOTDOT:
- follow_dotdot(nd);
- dir = nd->path.dentry;
case LAST_DOT:
- if (need_reval_dot(dir)) {
- int status = d_revalidate(nd->path.dentry, nd);
- if (!status)
- status = -ESTALE;
- if (status < 0) {
- error = status;
- goto exit;
- }
- }
+ error = handle_dots(nd, nd->last_type);
+ if (error)
+ return ERR_PTR(error);
/* fallthrough */
case LAST_ROOT:
- goto exit;
+ if (nd->flags & LOOKUP_RCU) {
+ if (nameidata_drop_rcu_last(nd))
+ return ERR_PTR(-ECHILD);
+ }
+ error = handle_reval_path(nd);
+ if (error)
+ goto exit;
+ audit_inode(pathname, nd->path.dentry);
+ if (open_flag & O_CREAT) {
+ error = -EISDIR;
+ goto exit;
+ }
+ goto ok;
case LAST_BIND:
+ /* can't be RCU mode here */
+ error = handle_reval_path(nd);
+ if (error)
+ goto exit;
audit_inode(pathname, dir);
goto ok;
}
+ if (!(open_flag & O_CREAT)) {
+ int symlink_ok = 0;
+ if (nd->last.name[nd->last.len])
+ nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+ if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
+ symlink_ok = 1;
+ /* we _can_ be in RCU mode here */
+ error = walk_component(nd, path, &nd->last, LAST_NORM,
+ !symlink_ok);
+ if (error < 0)
+ return ERR_PTR(error);
+ if (error) /* symlink */
+ return NULL;
+ /* sayonara */
+ if (nd->flags & LOOKUP_RCU) {
+ if (nameidata_drop_rcu_last(nd))
+ return ERR_PTR(-ECHILD);
+ }
+
+ error = -ENOTDIR;
+ if (nd->flags & LOOKUP_DIRECTORY) {
+ if (!nd->inode->i_op->lookup)
+ goto exit;
+ }
+ audit_inode(pathname, nd->path.dentry);
+ goto ok;
+ }
+
+ /* create side of things */
+
+ if (nd->flags & LOOKUP_RCU) {
+ if (nameidata_drop_rcu_last(nd))
+ return ERR_PTR(-ECHILD);
+ }
+
+ audit_inode(pathname, dir);
+ error = -EISDIR;
/* trailing slashes? */
if (nd->last.name[nd->last.len])
goto exit;
mutex_lock(&dir->d_inode->i_mutex);
- path->dentry = lookup_hash(nd);
- path->mnt = nd->path.mnt;
-
- error = PTR_ERR(path->dentry);
- if (IS_ERR(path->dentry)) {
+ dentry = lookup_hash(nd);
+ error = PTR_ERR(dentry);
+ if (IS_ERR(dentry)) {
mutex_unlock(&dir->d_inode->i_mutex);
goto exit;
}
- if (IS_ERR(nd->intent.open.file)) {
- error = PTR_ERR(nd->intent.open.file);
- goto exit_mutex_unlock;
- }
+ path->dentry = dentry;
+ path->mnt = nd->path.mnt;
/* Negative dentry, just create the file */
- if (!path->dentry->d_inode) {
+ if (!dentry->d_inode) {
+ int mode = op->mode;
+ if (!IS_POSIXACL(dir->d_inode))
+ mode &= ~current_umask();
/*
* This write is needed to ensure that a
- * ro->rw transition does not occur between
+ * rw->ro transition does not occur between
* the time when the file is created and when
* a permanent write count is taken through
* the 'struct file' in nameidata_to_filp().
error = mnt_want_write(nd->path.mnt);
if (error)
goto exit_mutex_unlock;
- error = __open_namei_create(nd, path, open_flag, mode);
- if (error) {
- mnt_drop_write(nd->path.mnt);
- goto exit;
- }
- filp = nameidata_to_filp(nd);
- mnt_drop_write(nd->path.mnt);
- path_put(&nd->path);
- if (!IS_ERR(filp)) {
- error = ima_file_check(filp, acc_mode);
- if (error) {
- fput(filp);
- filp = ERR_PTR(error);
- }
- }
- return filp;
+ want_write = 1;
+ /* Don't check for write permission, don't truncate */
+ open_flag &= ~O_TRUNC;
+ will_truncate = 0;
+ acc_mode = MAY_OPEN;
+ error = security_path_mknod(&nd->path, dentry, mode, 0);
+ if (error)
+ goto exit_mutex_unlock;
+ error = vfs_create(dir->d_inode, dentry, mode, nd);
+ if (error)
+ goto exit_mutex_unlock;
+ mutex_unlock(&dir->d_inode->i_mutex);
+ dput(nd->path.dentry);
+ nd->path.dentry = dentry;
+ goto common;
}
/*
if (S_ISDIR(nd->inode->i_mode))
goto exit;
ok:
- filp = finish_open(nd, open_flag, acc_mode);
+ if (!S_ISREG(nd->inode->i_mode))
+ will_truncate = 0;
+
+ if (will_truncate) {
+ error = mnt_want_write(nd->path.mnt);
+ if (error)
+ goto exit;
+ want_write = 1;
+ }
+common:
+ error = may_open(&nd->path, acc_mode, open_flag);
+ if (error)
+ goto exit;
+ filp = nameidata_to_filp(nd);
+ if (!IS_ERR(filp)) {
+ error = ima_file_check(filp, op->acc_mode);
+ if (error) {
+ fput(filp);
+ filp = ERR_PTR(error);
+ }
+ }
+ if (!IS_ERR(filp)) {
+ if (will_truncate) {
+ error = handle_truncate(filp);
+ if (error) {
+ fput(filp);
+ filp = ERR_PTR(error);
+ }
+ }
+ }
+out:
+ if (want_write)
+ mnt_drop_write(nd->path.mnt);
+ path_put(&nd->path);
return filp;
exit_mutex_unlock:
exit_dput:
path_put_conditional(path, nd);
exit:
- if (!IS_ERR(nd->intent.open.file))
- release_open_intent(nd);
- path_put(&nd->path);
- return ERR_PTR(error);
+ filp = ERR_PTR(error);
+ goto out;
}
-/*
- * Note that the low bits of the passed in "open_flag"
- * are not the same as in the local variable "flag". See
- * open_to_namei_flags() for more details.
- */
-struct file *do_filp_open(int dfd, const char *pathname,
- int open_flag, int mode, int acc_mode)
+static struct file *path_openat(int dfd, const char *pathname,
+ struct nameidata *nd, const struct open_flags *op, int flags)
{
+ struct file *base = NULL;
struct file *filp;
- struct nameidata nd;
- int error;
struct path path;
- int count = 0;
- int flag = open_to_namei_flags(open_flag);
- int flags;
-
- if (!(open_flag & O_CREAT))
- mode = 0;
-
- /* Must never be set by userspace */
- open_flag &= ~FMODE_NONOTIFY;
-
- /*
- * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
- * check for O_DSYNC if the need any syncing at all we enforce it's
- * always set instead of having to deal with possibly weird behaviour
- * for malicious applications setting only __O_SYNC.
- */
- if (open_flag & __O_SYNC)
- open_flag |= O_DSYNC;
-
- if (!acc_mode)
- acc_mode = MAY_OPEN | ACC_MODE(open_flag);
-
- /* O_TRUNC implies we need access checks for write permissions */
- if (open_flag & O_TRUNC)
- acc_mode |= MAY_WRITE;
-
- /* Allow the LSM permission hook to distinguish append
- access from general write access. */
- if (open_flag & O_APPEND)
- acc_mode |= MAY_APPEND;
-
- flags = LOOKUP_OPEN;
- if (open_flag & O_CREAT) {
- flags |= LOOKUP_CREATE;
- if (open_flag & O_EXCL)
- flags |= LOOKUP_EXCL;
- }
- if (open_flag & O_DIRECTORY)
- flags |= LOOKUP_DIRECTORY;
- if (!(open_flag & O_NOFOLLOW))
- flags |= LOOKUP_FOLLOW;
+ int error;
filp = get_empty_filp();
if (!filp)
return ERR_PTR(-ENFILE);
- filp->f_flags = open_flag;
- nd.intent.open.file = filp;
- nd.intent.open.flags = flag;
- nd.intent.open.create_mode = mode;
+ filp->f_flags = op->open_flag;
+ nd->intent.open.file = filp;
+ nd->intent.open.flags = open_to_namei_flags(op->open_flag);
+ nd->intent.open.create_mode = op->mode;
- if (open_flag & O_CREAT)
- goto creat;
-
- /* !O_CREAT, simple open */
- error = do_path_lookup(dfd, pathname, flags, &nd);
+ error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base);
if (unlikely(error))
goto out_filp;
- error = -ELOOP;
- if (!(nd.flags & LOOKUP_FOLLOW)) {
- if (nd.inode->i_op->follow_link)
- goto out_path;
- }
- error = -ENOTDIR;
- if (nd.flags & LOOKUP_DIRECTORY) {
- if (!nd.inode->i_op->lookup)
- goto out_path;
- }
- audit_inode(pathname, nd.path.dentry);
- filp = finish_open(&nd, open_flag, acc_mode);
- return filp;
-creat:
- /* OK, have to create the file. Find the parent. */
- error = path_init_rcu(dfd, pathname,
- LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd);
- if (error)
- goto out_filp;
- error = path_walk_rcu(pathname, &nd);
- path_finish_rcu(&nd);
- if (unlikely(error == -ECHILD || error == -ESTALE)) {
- /* slower, locked walk */
- if (error == -ESTALE) {
-reval:
- flags |= LOOKUP_REVAL;
- }
- error = path_init(dfd, pathname,
- LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd);
- if (error)
- goto out_filp;
-
- error = path_walk_simple(pathname, &nd);
- }
+ current->total_link_count = 0;
+ error = link_path_walk(pathname, nd);
if (unlikely(error))
goto out_filp;
- if (unlikely(!audit_dummy_context()))
- audit_inode(pathname, nd.path.dentry);
- /*
- * We have the parent and last component.
- */
- nd.flags = flags;
- filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
+ filp = do_last(nd, &path, op, pathname);
while (unlikely(!filp)) { /* trailing symlink */
struct path link = path;
- struct inode *linki = link.dentry->d_inode;
void *cookie;
- error = -ELOOP;
- if (!(nd.flags & LOOKUP_FOLLOW))
- goto exit_dput;
- if (count++ == 32)
- goto exit_dput;
- /*
- * This is subtle. Instead of calling do_follow_link() we do
- * the thing by hands. The reason is that this way we have zero
- * link_count and path_walk() (called from ->follow_link)
- * honoring LOOKUP_PARENT. After that we have the parent and
- * last component, i.e. we are in the same situation as after
- * the first path_walk(). Well, almost - if the last component
- * is normal we get its copy stored in nd->last.name and we will
- * have to putname() it when we are done. Procfs-like symlinks
- * just set LAST_BIND.
- */
- nd.flags |= LOOKUP_PARENT;
- error = security_inode_follow_link(link.dentry, &nd);
- if (error)
- goto exit_dput;
- error = __do_follow_link(&link, &nd, &cookie);
- if (unlikely(error)) {
- if (!IS_ERR(cookie) && linki->i_op->put_link)
- linki->i_op->put_link(link.dentry, &nd, cookie);
- /* nd.path had been dropped */
- nd.path = link;
- goto out_path;
+ if (!(nd->flags & LOOKUP_FOLLOW)) {
+ path_put_conditional(&path, nd);
+ path_put(&nd->path);
+ filp = ERR_PTR(-ELOOP);
+ break;
}
- nd.flags &= ~LOOKUP_PARENT;
- filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
- if (linki->i_op->put_link)
- linki->i_op->put_link(link.dentry, &nd, cookie);
- path_put(&link);
+ nd->flags |= LOOKUP_PARENT;
+ nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
+ error = follow_link(&link, nd, &cookie);
+ if (unlikely(error))
+ filp = ERR_PTR(error);
+ else
+ filp = do_last(nd, &path, op, pathname);
+ put_link(nd, &link, cookie);
}
out:
- if (nd.root.mnt)
- path_put(&nd.root);
- if (filp == ERR_PTR(-ESTALE) && !(flags & LOOKUP_REVAL))
- goto reval;
+ if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT))
+ path_put(&nd->root);
+ if (base)
+ fput(base);
+ release_open_intent(nd);
return filp;
-exit_dput:
- path_put_conditional(&path, &nd);
-out_path:
- path_put(&nd.path);
out_filp:
- if (!IS_ERR(nd.intent.open.file))
- release_open_intent(&nd);
filp = ERR_PTR(error);
goto out;
}
-/**
- * filp_open - open file and return file pointer
- *
- * @filename: path to open
- * @flags: open flags as per the open(2) second argument
- * @mode: mode for the new file if O_CREAT is set, else ignored
- *
- * This is the helper to open a file from kernelspace if you really
- * have to. But in generally you should not do this, so please move
- * along, nothing to see here..
- */
-struct file *filp_open(const char *filename, int flags, int mode)
+struct file *do_filp_open(int dfd, const char *pathname,
+ const struct open_flags *op, int flags)
+{
+ struct nameidata nd;
+ struct file *filp;
+
+ filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_RCU);
+ if (unlikely(filp == ERR_PTR(-ECHILD)))
+ filp = path_openat(dfd, pathname, &nd, op, flags);
+ if (unlikely(filp == ERR_PTR(-ESTALE)))
+ filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_REVAL);
+ return filp;
+}
+
+struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+ const char *name, const struct open_flags *op, int flags)
{
- return do_filp_open(AT_FDCWD, filename, flags, mode, 0);
+ struct nameidata nd;
+ struct file *file;
+
+ nd.root.mnt = mnt;
+ nd.root.dentry = dentry;
+
+ flags |= LOOKUP_ROOT;
+
+ if (dentry->d_inode->i_op->follow_link && op->intent & LOOKUP_OPEN)
+ return ERR_PTR(-ELOOP);
+
+ file = path_openat(-1, name, &nd, op, flags | LOOKUP_RCU);
+ if (unlikely(file == ERR_PTR(-ECHILD)))
+ file = path_openat(-1, name, &nd, op, flags);
+ if (unlikely(file == ERR_PTR(-ESTALE)))
+ file = path_openat(-1, name, &nd, op, flags | LOOKUP_REVAL);
+ return file;
}
-EXPORT_SYMBOL(filp_open);
/**
* lookup_create - lookup a dentry, creating it if it doesn't exist
return error;
mutex_lock(&inode->i_mutex);
- error = dir->i_op->link(old_dentry, dir, new_dentry);
+ /* Make sure we don't allow creating hardlink to an unlinked file */
+ if (inode->i_nlink == 0)
+ error = -ENOENT;
+ else
+ error = dir->i_op->link(old_dentry, dir, new_dentry);
mutex_unlock(&inode->i_mutex);
if (!error)
fsnotify_link(dir, inode, new_dentry);
struct dentry *new_dentry;
struct nameidata nd;
struct path old_path;
+ int how = 0;
int error;
char *to;
- if ((flags & ~AT_SYMLINK_FOLLOW) != 0)
+ if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
return -EINVAL;
+ /*
+ * To use null names we require CAP_DAC_READ_SEARCH
+ * This ensures that not everyone will be able to create
+ * handlink using the passed filedescriptor.
+ */
+ if (flags & AT_EMPTY_PATH) {
+ if (!capable(CAP_DAC_READ_SEARCH))
+ return -ENOENT;
+ how = LOOKUP_EMPTY;
+ }
+
+ if (flags & AT_SYMLINK_FOLLOW)
+ how |= LOOKUP_FOLLOW;
- error = user_path_at(olddfd, oldname,
- flags & AT_SYMLINK_FOLLOW ? LOOKUP_FOLLOW : 0,
- &old_path);
+ error = user_path_at(olddfd, oldname, how, &old_path);
if (error)
return error;
EXPORT_SYMBOL(__page_symlink);
EXPORT_SYMBOL(page_symlink);
EXPORT_SYMBOL(page_symlink_inode_operations);
-EXPORT_SYMBOL(path_lookup);
+EXPORT_SYMBOL(kern_path_parent);
EXPORT_SYMBOL(kern_path);
EXPORT_SYMBOL(vfs_path_lookup);
EXPORT_SYMBOL(inode_permission);
.show = show_vfsmnt
};
+static int uuid_is_nil(u8 *uuid)
+{
+ int i;
+ u8 *cp = (u8 *)uuid;
+
+ for (i = 0; i < 16; i++) {
+ if (*cp++)
+ return 0;
+ }
+ return 1;
+}
+
static int show_mountinfo(struct seq_file *m, void *v)
{
struct proc_mounts *p = m->private;
if (IS_MNT_UNBINDABLE(mnt))
seq_puts(m, " unbindable");
+ if (!uuid_is_nil(mnt->mnt_sb->s_uuid))
+ /* print the uuid */
+ seq_printf(m, " uuid:%pU", mnt->mnt_sb->s_uuid);
+
/* Filesystem specific data */
seq_puts(m, " - ");
show_type(m, sb);
*/
br_write_lock(vfsmount_lock);
if (mnt_get_count(mnt) != 2) {
- br_write_lock(vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
return -EBUSY;
}
br_write_unlock(vfsmount_lock);
#include <linux/inet.h>
#include <linux/nfs_xdr.h>
#include <linux/slab.h>
+#include <linux/compat.h>
#include <asm/system.h>
#include <asm/uaccess.h>
*/
u64 nfs_compat_user_ino64(u64 fileid)
{
- int ino;
+#ifdef CONFIG_COMPAT
+ compat_ulong_t ino;
+#else
+ unsigned long ino;
+#endif
if (enable_ino64)
return fileid;
#if defined(CONFIG_NFS_V4_1)
struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
+extern void nfs4_schedule_session_recovery(struct nfs4_session *);
+#else
+static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
+{
+}
#endif /* CONFIG_NFS_V4_1 */
extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
extern void nfs4_close_state(struct path *, struct nfs4_state *, fmode_t);
extern void nfs4_close_sync(struct path *, struct nfs4_state *, fmode_t);
extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
-extern void nfs4_schedule_state_recovery(struct nfs_client *);
+extern void nfs4_schedule_lease_recovery(struct nfs_client *);
extern void nfs4_schedule_state_manager(struct nfs_client *);
-extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state);
-extern int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state);
+extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
extern void nfs41_handle_recall_slot(struct nfs_client *clp);
extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
goto out_err;
}
buf = kmalloc(rlen + 1, GFP_KERNEL);
+ if (!buf) {
+ dprintk("%s: Not enough memory\n", __func__);
+ goto out_err;
+ }
buf[rlen] = '\0';
memcpy(buf, r_addr, rlen);
case -NFS4ERR_OPENMODE:
if (state == NULL)
break;
- nfs4_state_mark_reclaim_nograce(clp, state);
- goto do_state_recovery;
+ nfs4_schedule_stateid_recovery(server, state);
+ goto wait_on_recovery;
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_EXPIRED:
- goto do_state_recovery;
+ nfs4_schedule_lease_recovery(clp);
+ goto wait_on_recovery;
#if defined(CONFIG_NFS_V4_1)
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
case -NFS4ERR_SEQ_MISORDERED:
dprintk("%s ERROR: %d Reset session\n", __func__,
errorcode);
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_session_recovery(clp->cl_session);
exception->retry = 1;
break;
#endif /* defined(CONFIG_NFS_V4_1) */
}
/* We failed to handle the error */
return nfs4_map_errors(ret);
-do_state_recovery:
- nfs4_schedule_state_recovery(clp);
+wait_on_recovery:
ret = nfs4_wait_clnt_recover(clp);
if (ret == 0)
exception->retry = 1;
clp = res->sr_session->clp;
do_renew_lease(clp, timestamp);
/* Check sequence flags */
- if (atomic_read(&clp->cl_count) > 1)
- nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
+ if (res->sr_status_flags != 0)
+ nfs4_schedule_lease_recovery(clp);
break;
case -NFS4ERR_DELAY:
/* The server detected a resend of the RPC call and
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_DEADSESSION:
- nfs4_schedule_state_recovery(
- server->nfs_client);
+ nfs4_schedule_session_recovery(server->nfs_client->cl_session);
goto out;
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_EXPIRED:
/* Don't recall a delegation if it was lost */
- nfs4_schedule_state_recovery(server->nfs_client);
+ nfs4_schedule_lease_recovery(server->nfs_client);
goto out;
case -ERESTARTSYS:
/*
*/
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
- nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+ nfs4_schedule_stateid_recovery(server, state);
case -EKEYEXPIRED:
/*
* User RPCSEC_GSS context has expired.
if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
!test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state))
break;
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_state_manager(clp);
ret = -EIO;
}
return ret;
if (task->tk_status < 0) {
/* Unless we're shutting down, schedule state recovery! */
if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) != 0)
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_lease_recovery(clp);
return;
}
do_renew_lease(clp, timestamp);
}
}
+static int buf_to_pages_noslab(const void *buf, size_t buflen,
+ struct page **pages, unsigned int *pgbase)
+{
+ struct page *newpage, **spages;
+ int rc = 0;
+ size_t len;
+ spages = pages;
+
+ do {
+ len = min_t(size_t, PAGE_CACHE_SIZE, buflen);
+ newpage = alloc_page(GFP_KERNEL);
+
+ if (newpage == NULL)
+ goto unwind;
+ memcpy(page_address(newpage), buf, len);
+ buf += len;
+ buflen -= len;
+ *pages++ = newpage;
+ rc++;
+ } while (buflen != 0);
+
+ return rc;
+
+unwind:
+ for(; rc > 0; rc--)
+ __free_page(spages[rc-1]);
+ return -ENOMEM;
+}
+
struct nfs4_cached_acl {
int cached;
size_t len;
.rpc_argp = &arg,
.rpc_resp = &res,
};
- int ret;
+ int ret, i;
if (!nfs4_server_supports_acls(server))
return -EOPNOTSUPP;
+ i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
+ if (i < 0)
+ return i;
nfs_inode_return_delegation(inode);
- buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
ret = nfs4_call_sync(server, &msg, &arg, &res, 1);
+
+ /*
+ * Free each page after tx, so the only ref left is
+ * held by the network stack
+ */
+ for (; i > 0; i--)
+ put_page(pages[i-1]);
+
/*
* Acl update can result in inode attribute update.
* so mark the attribute cache invalid.
case -NFS4ERR_OPENMODE:
if (state == NULL)
break;
- nfs4_state_mark_reclaim_nograce(clp, state);
- goto do_state_recovery;
+ nfs4_schedule_stateid_recovery(server, state);
+ goto wait_on_recovery;
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_EXPIRED:
- goto do_state_recovery;
+ nfs4_schedule_lease_recovery(clp);
+ goto wait_on_recovery;
#if defined(CONFIG_NFS_V4_1)
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
case -NFS4ERR_SEQ_MISORDERED:
dprintk("%s ERROR %d, Reset session\n", __func__,
task->tk_status);
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_session_recovery(clp->cl_session);
task->tk_status = 0;
return -EAGAIN;
#endif /* CONFIG_NFS_V4_1 */
}
task->tk_status = nfs4_map_errors(task->tk_status);
return 0;
-do_state_recovery:
+wait_on_recovery:
rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
- nfs4_schedule_state_recovery(clp);
if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
task->tk_status = 0;
task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp,
data->arg.lock_seqid);
if (!IS_ERR(task))
- rpc_put_task(task);
+ rpc_put_task_async(task);
dprintk("%s: cancelling lock!\n", __func__);
} else
nfs_free_seqid(data->arg.lock_seqid);
static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_state *lsp, int new_lock_owner, int error)
{
- struct nfs_client *clp = server->nfs_client;
- struct nfs4_state *state = lsp->ls_state;
-
switch (error) {
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
- case -NFS4ERR_EXPIRED:
+ lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
if (new_lock_owner != 0 ||
(lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
- nfs4_state_mark_reclaim_nograce(clp, state);
- lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+ nfs4_schedule_stateid_recovery(server, lsp->ls_state);
break;
case -NFS4ERR_STALE_STATEID:
- if (new_lock_owner != 0 ||
- (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
- nfs4_state_mark_reclaim_reboot(clp, state);
lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+ case -NFS4ERR_EXPIRED:
+ nfs4_schedule_lease_recovery(server->nfs_client);
};
}
case -NFS4ERR_EXPIRED:
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
+ nfs4_schedule_lease_recovery(server->nfs_client);
+ goto out;
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_DEADSESSION:
- nfs4_schedule_state_recovery(server->nfs_client);
+ nfs4_schedule_session_recovery(server->nfs_client->cl_session);
goto out;
case -ERESTARTSYS:
/*
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
case -NFS4ERR_OPENMODE:
- nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+ nfs4_schedule_stateid_recovery(server, state);
err = 0;
goto out;
case -EKEYEXPIRED:
int status;
unsigned *ptr;
struct nfs4_session *session = clp->cl_session;
+ long timeout = 0;
+ int err;
dprintk("--> %s clp=%p session=%p\n", __func__, clp, session);
- status = _nfs4_proc_create_session(clp);
+ do {
+ status = _nfs4_proc_create_session(clp);
+ if (status == -NFS4ERR_DELAY) {
+ err = nfs4_delay(clp->cl_rpcclient, &timeout);
+ if (err)
+ status = err;
+ }
+ } while (status == -NFS4ERR_DELAY);
+
if (status)
goto out;
rpc_delay(task, NFS4_POLL_RETRY_MAX);
return -EAGAIN;
default:
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_lease_recovery(clp);
}
return 0;
}
if (IS_ERR(task))
ret = PTR_ERR(task);
else
- rpc_put_task(task);
+ rpc_put_task_async(task);
dprintk("<-- %s status=%d\n", __func__, ret);
return ret;
}
goto out;
}
ret = rpc_wait_for_completion_task(task);
- if (!ret)
+ if (!ret) {
+ struct nfs4_sequence_res *res = task->tk_msg.rpc_resp;
+
+ if (task->tk_status == 0)
+ nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
ret = task->tk_status;
+ }
rpc_put_task(task);
out:
dprintk("<-- %s status=%d\n", __func__, ret);
rpc_delay(task, NFS4_POLL_RETRY_MAX);
return -EAGAIN;
default:
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_lease_recovery(clp);
}
return 0;
}
status = PTR_ERR(task);
goto out;
}
+ status = nfs4_wait_for_completion_rpc_task(task);
+ if (status == 0)
+ status = task->tk_status;
rpc_put_task(task);
return 0;
out:
}
/*
- * Schedule a state recovery attempt
+ * Schedule a lease recovery attempt
*/
-void nfs4_schedule_state_recovery(struct nfs_client *clp)
+void nfs4_schedule_lease_recovery(struct nfs_client *clp)
{
if (!clp)
return;
nfs4_schedule_state_manager(clp);
}
-int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
+static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
{
set_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
return 1;
}
-int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
+static int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
{
set_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags);
clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
return 1;
}
+void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state)
+{
+ struct nfs_client *clp = server->nfs_client;
+
+ nfs4_state_mark_reclaim_nograce(clp, state);
+ nfs4_schedule_state_manager(clp);
+}
+
static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops)
{
struct inode *inode = state->inode;
}
#ifdef CONFIG_NFS_V4_1
+void nfs4_schedule_session_recovery(struct nfs4_session *session)
+{
+ nfs4_schedule_lease_recovery(session->clp);
+}
+
void nfs41_handle_recall_slot(struct nfs_client *clp)
{
set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_state_manager(clp);
}
static void nfs4_reset_all_state(struct nfs_client *clp)
if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
clp->cl_boot_time = CURRENT_TIME;
nfs4_state_start_reclaim_nograce(clp);
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_state_manager(clp);
}
}
{
if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
nfs4_state_start_reclaim_reboot(clp);
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_state_manager(clp);
}
}
{
nfs_expire_all_delegations(clp);
if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
- nfs4_schedule_state_recovery(clp);
+ nfs4_schedule_state_manager(clp);
}
void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12);
*p++ = cpu_to_be32(OP_CREATE_SESSION);
- p = xdr_encode_hyper(p, clp->cl_ex_clid);
+ p = xdr_encode_hyper(p, clp->cl_clientid);
*p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */
*p++ = cpu_to_be32(args->flags); /*flags */
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
goto out_overflow;
- xdr_decode_hyper(p, &clp->cl_ex_clid);
+ xdr_decode_hyper(p, &clp->cl_clientid);
p = xdr_inline_decode(xdr, 12);
if (unlikely(!p))
goto out_overflow;
/* Default path we try to mount. "%s" gets replaced by our IP address */
#define NFS_ROOT "/tftpboot/%s"
+/* Default NFSROOT mount options. */
+#define NFS_DEF_OPTIONS "udp"
+
/* Parameters passed from the kernel command line */
static char nfs_root_parms[256] __initdata = "";
/* Text-based mount options passed to super.c */
-static char nfs_root_options[256] __initdata = "";
+static char nfs_root_options[256] __initdata = NFS_DEF_OPTIONS;
/* Address of NFS server */
static __be32 servaddr __initdata = htonl(INADDR_NONE);
}
static int __init root_nfs_cat(char *dest, const char *src,
- const size_t destlen)
+ const size_t destlen)
{
+ size_t len = strlen(dest);
+
+ if (len && dest[len - 1] != ',')
+ if (strlcat(dest, ",", destlen) > destlen)
+ return -1;
+
if (strlcat(dest, src, destlen) > destlen)
return -1;
return 0;
if (root_nfs_cat(nfs_root_options, incoming,
sizeof(nfs_root_options)))
return -1;
-
- /*
- * Possibly prepare for more options to be appended
- */
- if (nfs_root_options[0] != '\0' &&
- nfs_root_options[strlen(nfs_root_options)] != ',')
- if (root_nfs_cat(nfs_root_options, ",",
- sizeof(nfs_root_options)))
- return -1;
-
return 0;
}
*/
static int __init root_nfs_data(char *cmdline)
{
- char addr_option[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1];
+ char mand_options[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1];
int len, retval = -1;
char *tmp = NULL;
const size_t tmplen = sizeof(nfs_export_path);
* Append mandatory options for nfsroot so they override
* what has come before
*/
- snprintf(addr_option, sizeof(addr_option), "nolock,addr=%pI4",
+ snprintf(mand_options, sizeof(mand_options), "nolock,addr=%pI4",
&servaddr);
- if (root_nfs_cat(nfs_root_options, addr_option,
+ if (root_nfs_cat(nfs_root_options, mand_options,
sizeof(nfs_root_options)))
goto out_optionstoolong;
task_setup_data.rpc_client = NFS_CLIENT(dir);
task = rpc_run_task(&task_setup_data);
if (!IS_ERR(task))
- rpc_put_task(task);
+ rpc_put_task_async(task);
return 1;
}
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
+ if (how & FLUSH_SYNC)
+ rpc_wait_for_completion_task(task);
rpc_put_task(task);
return 0;
}
static struct file *do_open(char *name, int flags)
{
- struct nameidata nd;
struct vfsmount *mnt;
- int error;
+ struct file *file;
mnt = do_kern_mount("nfsd", 0, "nfsd", NULL);
if (IS_ERR(mnt))
return (struct file *)mnt;
- error = vfs_path_lookup(mnt->mnt_root, mnt, name, 0, &nd);
- mntput(mnt); /* drop do_kern_mount reference */
- if (error)
- return ERR_PTR(error);
-
- if (flags == O_RDWR)
- error = may_open(&nd.path, MAY_READ|MAY_WRITE, flags);
- else
- error = may_open(&nd.path, MAY_WRITE, flags);
+ file = file_open_root(mnt->mnt_root, mnt, name, flags);
- if (!error)
- return dentry_open(nd.path.dentry, nd.path.mnt, flags,
- current_cred());
-
- path_put(&nd.path);
- return ERR_PTR(error);
+ mntput(mnt); /* drop do_kern_mount reference */
+ return file;
}
static struct {
* If the server returns different values for sessionID, slotID or
* sequence number, the server is looney tunes.
*/
- p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4);
+ p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4 + 4 + 4);
if (unlikely(p == NULL))
goto out_overflow;
memcpy(id.data, p, NFS4_MAX_SESSIONID_LEN);
out:
return status;
out_default:
- return nfs_cb_stat_to_errno(status);
+ return nfs_cb_stat_to_errno(nfserr);
}
/*
if (unlikely(status))
goto out;
if (unlikely(nfserr != NFS4_OK))
- goto out_default;
+ status = nfs_cb_stat_to_errno(nfserr);
out:
return status;
-out_default:
- return nfs_cb_stat_to_errno(status);
}
/*
dp->dl_client = clp;
get_nfs4_file(fp);
dp->dl_file = fp;
- dp->dl_vfs_file = find_readable_file(fp);
- get_file(dp->dl_vfs_file);
- dp->dl_flock = NULL;
dp->dl_type = type;
dp->dl_stateid.si_boot = boot_time;
dp->dl_stateid.si_stateownerid = current_delegid++;
fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle);
dp->dl_time = 0;
atomic_set(&dp->dl_count, 1);
- list_add(&dp->dl_perfile, &fp->fi_delegations);
- list_add(&dp->dl_perclnt, &clp->cl_delegations);
INIT_WORK(&dp->dl_recall.cb_work, nfsd4_do_callback_rpc);
return dp;
}
if (atomic_dec_and_test(&dp->dl_count)) {
dprintk("NFSD: freeing dp %p\n",dp);
put_nfs4_file(dp->dl_file);
- fput(dp->dl_vfs_file);
kmem_cache_free(deleg_slab, dp);
num_delegations--;
}
}
-/* Remove the associated file_lock first, then remove the delegation.
- * lease_modify() is called to remove the FS_LEASE file_lock from
- * the i_flock list, eventually calling nfsd's lock_manager
- * fl_release_callback.
- */
-static void
-nfs4_close_delegation(struct nfs4_delegation *dp)
+static void nfs4_put_deleg_lease(struct nfs4_file *fp)
{
- dprintk("NFSD: close_delegation dp %p\n",dp);
- /* XXX: do we even need this check?: */
- if (dp->dl_flock)
- vfs_setlease(dp->dl_vfs_file, F_UNLCK, &dp->dl_flock);
+ if (atomic_dec_and_test(&fp->fi_delegees)) {
+ vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease);
+ fp->fi_lease = NULL;
+ fp->fi_deleg_file = NULL;
+ }
}
/* Called under the state lock. */
static void
unhash_delegation(struct nfs4_delegation *dp)
{
- list_del_init(&dp->dl_perfile);
list_del_init(&dp->dl_perclnt);
spin_lock(&recall_lock);
+ list_del_init(&dp->dl_perfile);
list_del_init(&dp->dl_recall_lru);
spin_unlock(&recall_lock);
- nfs4_close_delegation(dp);
+ nfs4_put_deleg_lease(dp->dl_file);
nfs4_put_delegation(dp);
}
spin_lock(&recall_lock);
while (!list_empty(&clp->cl_delegations)) {
dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
- dprintk("NFSD: expire client. dp %p, fp %p\n", dp,
- dp->dl_flock);
list_del_init(&dp->dl_perclnt);
list_move(&dp->dl_recall_lru, &reaplist);
}
fp->fi_inode = igrab(ino);
fp->fi_id = current_fileid++;
fp->fi_had_conflict = false;
+ fp->fi_lease = NULL;
memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
memset(fp->fi_access, 0, sizeof(fp->fi_access));
spin_lock(&recall_lock);
nfs4_file_put_access(fp, O_RDONLY);
}
-/*
- * Spawn a thread to perform a recall on the delegation represented
- * by the lease (file_lock)
- *
- * Called from break_lease() with lock_flocks() held.
- * Note: we assume break_lease will only call this *once* for any given
- * lease.
- */
-static
-void nfsd_break_deleg_cb(struct file_lock *fl)
+static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
{
- struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
-
- dprintk("NFSD nfsd_break_deleg_cb: dp %p fl %p\n",dp,fl);
- if (!dp)
- return;
-
/* We're assuming the state code never drops its reference
* without first removing the lease. Since we're in this lease
* callback (and since the lease code is serialized by the kernel
* it's safe to take a reference: */
atomic_inc(&dp->dl_count);
- spin_lock(&recall_lock);
list_add_tail(&dp->dl_recall_lru, &del_recall_lru);
- spin_unlock(&recall_lock);
/* only place dl_time is set. protected by lock_flocks*/
dp->dl_time = get_seconds();
+ nfsd4_cb_recall(dp);
+}
+
+/* Called from break_lease() with lock_flocks() held. */
+static void nfsd_break_deleg_cb(struct file_lock *fl)
+{
+ struct nfs4_file *fp = (struct nfs4_file *)fl->fl_owner;
+ struct nfs4_delegation *dp;
+
+ BUG_ON(!fp);
+ /* We assume break_lease is only called once per lease: */
+ BUG_ON(fp->fi_had_conflict);
/*
* We don't want the locks code to timeout the lease for us;
- * we'll remove it ourself if the delegation isn't returned
- * in time.
+ * we'll remove it ourself if a delegation isn't returned
+ * in time:
*/
fl->fl_break_time = 0;
- dp->dl_file->fi_had_conflict = true;
- nfsd4_cb_recall(dp);
+ spin_lock(&recall_lock);
+ fp->fi_had_conflict = true;
+ list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
+ nfsd_break_one_deleg(dp);
+ spin_unlock(&recall_lock);
}
static
{
struct nfs4_delegation *dp;
- list_for_each_entry(dp, &fp->fi_delegations, dl_perfile) {
- if (dp->dl_stateid.si_stateownerid == stid->si_stateownerid)
+ spin_lock(&recall_lock);
+ list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
+ if (dp->dl_stateid.si_stateownerid == stid->si_stateownerid) {
+ spin_unlock(&recall_lock);
return dp;
- }
+ }
+ spin_unlock(&recall_lock);
return NULL;
}
return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
}
+static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, int flag)
+{
+ struct file_lock *fl;
+
+ fl = locks_alloc_lock();
+ if (!fl)
+ return NULL;
+ locks_init_lock(fl);
+ fl->fl_lmops = &nfsd_lease_mng_ops;
+ fl->fl_flags = FL_LEASE;
+ fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
+ fl->fl_end = OFFSET_MAX;
+ fl->fl_owner = (fl_owner_t)(dp->dl_file);
+ fl->fl_pid = current->tgid;
+ return fl;
+}
+
+static int nfs4_setlease(struct nfs4_delegation *dp, int flag)
+{
+ struct nfs4_file *fp = dp->dl_file;
+ struct file_lock *fl;
+ int status;
+
+ fl = nfs4_alloc_init_lease(dp, flag);
+ if (!fl)
+ return -ENOMEM;
+ fl->fl_file = find_readable_file(fp);
+ list_add(&dp->dl_perclnt, &dp->dl_client->cl_delegations);
+ status = vfs_setlease(fl->fl_file, fl->fl_type, &fl);
+ if (status) {
+ list_del_init(&dp->dl_perclnt);
+ locks_free_lock(fl);
+ return -ENOMEM;
+ }
+ fp->fi_lease = fl;
+ fp->fi_deleg_file = fl->fl_file;
+ get_file(fp->fi_deleg_file);
+ atomic_set(&fp->fi_delegees, 1);
+ list_add(&dp->dl_perfile, &fp->fi_delegations);
+ return 0;
+}
+
+static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag)
+{
+ struct nfs4_file *fp = dp->dl_file;
+
+ if (!fp->fi_lease)
+ return nfs4_setlease(dp, flag);
+ spin_lock(&recall_lock);
+ if (fp->fi_had_conflict) {
+ spin_unlock(&recall_lock);
+ return -EAGAIN;
+ }
+ atomic_inc(&fp->fi_delegees);
+ list_add(&dp->dl_perfile, &fp->fi_delegations);
+ spin_unlock(&recall_lock);
+ list_add(&dp->dl_perclnt, &dp->dl_client->cl_delegations);
+ return 0;
+}
+
/*
* Attempt to hand out a delegation.
*/
struct nfs4_delegation *dp;
struct nfs4_stateowner *sop = stp->st_stateowner;
int cb_up;
- struct file_lock *fl;
int status, flag = 0;
cb_up = nfsd4_cb_channel_good(sop->so_client);
}
dp = alloc_init_deleg(sop->so_client, stp, fh, flag);
- if (dp == NULL) {
- flag = NFS4_OPEN_DELEGATE_NONE;
- goto out;
- }
- status = -ENOMEM;
- fl = locks_alloc_lock();
- if (!fl)
- goto out;
- locks_init_lock(fl);
- fl->fl_lmops = &nfsd_lease_mng_ops;
- fl->fl_flags = FL_LEASE;
- fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
- fl->fl_end = OFFSET_MAX;
- fl->fl_owner = (fl_owner_t)dp;
- fl->fl_file = find_readable_file(stp->st_file);
- BUG_ON(!fl->fl_file);
- fl->fl_pid = current->tgid;
- dp->dl_flock = fl;
-
- /* vfs_setlease checks to see if delegation should be handed out.
- * the lock_manager callback fl_change is used
- */
- if ((status = vfs_setlease(fl->fl_file, fl->fl_type, &fl))) {
- dprintk("NFSD: setlease failed [%d], no delegation\n", status);
- dp->dl_flock = NULL;
- locks_free_lock(fl);
- unhash_delegation(dp);
- flag = NFS4_OPEN_DELEGATE_NONE;
- goto out;
- }
+ if (dp == NULL)
+ goto out_no_deleg;
+ status = nfs4_set_delegation(dp, flag);
+ if (status)
+ goto out_free;
memcpy(&open->op_delegate_stateid, &dp->dl_stateid, sizeof(dp->dl_stateid));
&& open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
dprintk("NFSD: WARNING: refusing delegation reclaim\n");
open->op_delegate_type = flag;
+ return;
+out_free:
+ nfs4_put_delegation(dp);
+out_no_deleg:
+ flag = NFS4_OPEN_DELEGATE_NONE;
+ goto out;
}
/*
test_val = u;
break;
}
- dprintk("NFSD: purging unused delegation dp %p, fp %p\n",
- dp, dp->dl_flock);
list_move(&dp->dl_recall_lru, &reaplist);
}
spin_unlock(&recall_lock);
goto out;
renew_client(dp->dl_client);
if (filpp) {
- *filpp = find_readable_file(dp->dl_file);
+ *filpp = dp->dl_file->fi_deleg_file;
BUG_ON(!*filpp);
}
} else { /* open or lock stateid */
READ_BUF(dummy32);
len += (XDR_QUADLEN(dummy32) << 2);
READMEM(buf, dummy32);
- if ((host_err = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid)))
- goto out_nfserr;
+ if ((status = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid)))
+ return status;
iattr->ia_valid |= ATTR_UID;
}
if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) {
READ_BUF(dummy32);
len += (XDR_QUADLEN(dummy32) << 2);
READMEM(buf, dummy32);
- if ((host_err = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid)))
- goto out_nfserr;
+ if ((status = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid)))
+ return status;
iattr->ia_valid |= ATTR_GID;
}
if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
u32 dummy;
char *machine_name;
- int i;
+ int i, j;
int nr_secflavs;
READ_BUF(16);
READ_BUF(4);
READ32(dummy);
READ_BUF(dummy * 4);
- for (i = 0; i < dummy; ++i)
+ for (j = 0; j < dummy; ++j)
READ32(dummy);
break;
case RPC_AUTH_GSS:
atomic_t dl_count; /* ref count */
struct nfs4_client *dl_client;
struct nfs4_file *dl_file;
- struct file *dl_vfs_file;
- struct file_lock *dl_flock;
u32 dl_type;
time_t dl_time;
/* For recall: */
*/
atomic_t fi_readers;
atomic_t fi_writers;
+ struct file *fi_deleg_file;
+ struct file_lock *fi_lease;
+ atomic_t fi_delegees;
struct inode *fi_inode;
u32 fi_id; /* used with stateowner->so_id
* for stateid_hashtbl hash */
if (ra->p_count == 0)
frap = rap;
}
- depth = nfsdstats.ra_size*11/10;
+ depth = nfsdstats.ra_size;
if (!frap) {
spin_unlock(&rab->pb_lock);
return NULL;
goto out_dput_new;
host_err = nfsd_break_lease(odentry->d_inode);
+ if (host_err)
+ goto out_drop_write;
+ if (ndentry->d_inode) {
+ host_err = nfsd_break_lease(ndentry->d_inode);
+ if (host_err)
+ goto out_drop_write;
+ }
if (host_err)
goto out_drop_write;
host_err = vfs_rename(fdir, odentry, tdir, ndentry);
host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
if (host_err)
- goto out_nfserr;
+ goto out_put;
host_err = nfsd_break_lease(rdentry->d_inode);
if (host_err)
- goto out_put;
+ goto out_drop_write;
if (type != S_IFDIR)
host_err = vfs_unlink(dirp, rdentry);
else
host_err = vfs_rmdir(dirp, rdentry);
-out_put:
- dput(rdentry);
-
if (!host_err)
host_err = commit_metadata(fhp);
-
+out_drop_write:
mnt_drop_write(fhp->fh_export->ex_path.mnt);
+out_put:
+ dput(rdentry);
+
out_nfserr:
err = nfserrno(host_err);
out:
#include "btnode.h"
-void nilfs_btnode_cache_init_once(struct address_space *btnc)
-{
- nilfs_mapping_init_once(btnc);
-}
-
static const struct address_space_operations def_btnode_aops = {
.sync_page = block_sync_page,
};
struct buffer_head *newbh;
};
-void nilfs_btnode_cache_init_once(struct address_space *);
void nilfs_btnode_cache_init(struct address_space *, struct backing_dev_info *);
void nilfs_btnode_cache_clear(struct address_space *);
struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc,
struct backing_dev_info *bdi = inode->i_sb->s_bdi;
INIT_LIST_HEAD(&shadow->frozen_buffers);
- nilfs_mapping_init_once(&shadow->frozen_data);
+ address_space_init_once(&shadow->frozen_data);
nilfs_mapping_init(&shadow->frozen_data, bdi, &shadow_map_aops);
- nilfs_mapping_init_once(&shadow->frozen_btnodes);
+ address_space_init_once(&shadow->frozen_btnodes);
nilfs_mapping_init(&shadow->frozen_btnodes, bdi, &shadow_map_aops);
mi->mi_shadow = shadow;
return 0;
new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_page);
if (!new_de)
goto out_dir;
- inc_nlink(old_inode);
nilfs_set_link(new_dir, new_de, new_page, old_inode);
nilfs_mark_inode_dirty(new_dir);
new_inode->i_ctime = CURRENT_TIME;
if (new_dir->i_nlink >= NILFS_LINK_MAX)
goto out_dir;
}
- inc_nlink(old_inode);
err = nilfs_add_link(new_dentry, old_inode);
- if (err) {
- drop_nlink(old_inode);
- nilfs_mark_inode_dirty(old_inode);
+ if (err)
goto out_dir;
- }
if (dir_de) {
inc_nlink(new_dir);
nilfs_mark_inode_dirty(new_dir);
old_inode->i_ctime = CURRENT_TIME;
nilfs_delete_entry(old_de, old_page);
- drop_nlink(old_inode);
if (dir_de) {
nilfs_set_link(old_inode, dir_de, dir_page, new_dir);
return nc;
}
-void nilfs_mapping_init_once(struct address_space *mapping)
-{
- memset(mapping, 0, sizeof(*mapping));
- INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
- spin_lock_init(&mapping->tree_lock);
- INIT_LIST_HEAD(&mapping->private_list);
- spin_lock_init(&mapping->private_lock);
-
- spin_lock_init(&mapping->i_mmap_lock);
- INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
- INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
-}
-
void nilfs_mapping_init(struct address_space *mapping,
struct backing_dev_info *bdi,
const struct address_space_operations *aops)
int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
void nilfs_copy_back_pages(struct address_space *, struct address_space *);
void nilfs_clear_dirty_pages(struct address_space *);
-void nilfs_mapping_init_once(struct address_space *mapping);
void nilfs_mapping_init(struct address_space *mapping,
struct backing_dev_info *bdi,
const struct address_space_operations *aops);
nilfs_segctor_map_segsum_entry(
sci, &sci->sc_binfo_ptr, sizeof(struct nilfs_finfo));
- if (inode->i_sb && !test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags))
+ if (NILFS_I(inode)->i_root &&
+ !test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags))
set_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags);
/* skip finfo */
}
#ifdef CONFIG_NILFS_XATTR
init_rwsem(&ii->xattr_sem);
#endif
- nilfs_btnode_cache_init_once(&ii->i_btnode_cache);
+ address_space_init_once(&ii->i_btnode_cache);
ii->i_bmap = &ii->i_bmap_data;
inode_init_once(&ii->vfs_inode);
}
int ret = 0; /* if all else fails, just return false */
struct ocfs2_super *osb;
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
dentry->d_name.len, dentry->d_name.name,
fh, len, connectable);
- if (len < 3 || (connectable && len < 6)) {
- mlog(ML_ERROR, "fh buffer is too small for encoding\n");
+ if (connectable && (len < 6)) {
+ *max_len = 6;
+ type = 255;
+ goto bail;
+ } else if (len < 3) {
+ *max_len = 3;
type = 255;
goto bail;
}
ocfs2_quota_trans_credits(sb);
}
-/* data block for new dir/symlink, 2 for bitmap updates (bitmap fe +
- * bitmap block for the new bit) dx_root update for free list */
-#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + 2 + 1)
+/* data block for new dir/symlink, allocation of directory block, dx_root
+ * update for free list */
+#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + OCFS2_SUBALLOC_ALLOC + 1)
static inline int ocfs2_add_dir_index_credits(struct super_block *sb)
{
u32 num_clusters, unsigned int e_flags)
{
int ret, delete, index, credits = 0;
- u32 new_bit, new_len;
+ u32 new_bit, new_len, orig_num_clusters;
unsigned int set_len;
struct ocfs2_super *osb = OCFS2_SB(sb);
handle_t *handle;
goto out;
}
+ orig_num_clusters = num_clusters;
+
while (num_clusters) {
ret = ocfs2_get_refcount_rec(ref_ci, context->ref_root_bh,
p_cluster, num_clusters,
* in write-back mode.
*/
if (context->get_clusters == ocfs2_di_get_clusters) {
- ret = ocfs2_cow_sync_writeback(sb, context, cpos, num_clusters);
+ ret = ocfs2_cow_sync_writeback(sb, context, cpos,
+ orig_num_clusters);
if (ret)
mlog_errno(ret);
}
if (IS_ERR(s))
return PTR_ERR(s);
- error = path_lookup(s, LOOKUP_PARENT, nd);
+ error = kern_path_parent(s, nd);
if (error)
putname(s);
else
struct mount_options *mopt,
int is_remount)
{
- int status;
+ int status, user_stack = 0;
char *p;
u32 tmp;
memcpy(mopt->cluster_stack, args[0].from,
OCFS2_STACK_LABEL_LEN);
mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
+ /*
+ * Open code the memcmp here as we don't have
+ * an osb to pass to
+ * ocfs2_userspace_stack().
+ */
+ if (memcmp(mopt->cluster_stack,
+ OCFS2_CLASSIC_CLUSTER_STACK,
+ OCFS2_STACK_LABEL_LEN))
+ user_stack = 1;
break;
case Opt_inode64:
mopt->mount_opt |= OCFS2_MOUNT_INODE64;
}
}
- /* Ensure only one heartbeat mode */
- tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
- OCFS2_MOUNT_HB_NONE);
- if (hweight32(tmp) != 1) {
- mlog(ML_ERROR, "Invalid heartbeat mount options\n");
- status = 0;
- goto bail;
+ if (user_stack == 0) {
+ /* Ensure only one heartbeat mode */
+ tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL |
+ OCFS2_MOUNT_HB_GLOBAL |
+ OCFS2_MOUNT_HB_NONE);
+ if (hweight32(tmp) != 1) {
+ mlog(ML_ERROR, "Invalid heartbeat mount options\n");
+ status = 0;
+ goto bail;
+ }
}
status = 1;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
+
+ /* It's not possible punch hole on append only file */
+ if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode))
+ return -EPERM;
+
+ if (IS_IMMUTABLE(inode))
+ return -EPERM;
+
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
{
struct path path;
int error = -EINVAL;
- int follow;
+ int lookup_flags;
- if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+ if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
goto out;
- follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
- error = user_path_at(dfd, filename, follow, &path);
+ lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+ if (flag & AT_EMPTY_PATH)
+ lookup_flags |= LOOKUP_EMPTY;
+ error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
goto out;
error = mnt_want_write(path.mnt);
int (*open)(struct inode *, struct file *),
const struct cred *cred)
{
+ static const struct file_operations empty_fops = {};
struct inode *inode;
int error;
f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
+
+ if (unlikely(f->f_flags & O_PATH))
+ f->f_mode = FMODE_PATH;
+
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
error = __get_file_write_access(inode, mnt);
f->f_path.dentry = dentry;
f->f_path.mnt = mnt;
f->f_pos = 0;
- f->f_op = fops_get(inode->i_fop);
file_sb_list_add(f, inode->i_sb);
+ if (unlikely(f->f_mode & FMODE_PATH)) {
+ f->f_op = &empty_fops;
+ return f;
+ }
+
+ f->f_op = fops_get(inode->i_fop);
+
error = security_dentry_open(f, cred);
if (error)
goto cleanup_all;
/* Pick up the filp from the open intent */
filp = nd->intent.open.file;
+ nd->intent.open.file = NULL;
+
/* Has the filesystem initialised the file for us? */
if (filp->f_path.dentry == NULL) {
path_get(&nd->path);
EXPORT_SYMBOL(fd_install);
+static inline int build_open_flags(int flags, int mode, struct open_flags *op)
+{
+ int lookup_flags = 0;
+ int acc_mode;
+
+ if (!(flags & O_CREAT))
+ mode = 0;
+ op->mode = mode;
+
+ /* Must never be set by userspace */
+ flags &= ~FMODE_NONOTIFY;
+
+ /*
+ * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
+ * check for O_DSYNC if the need any syncing at all we enforce it's
+ * always set instead of having to deal with possibly weird behaviour
+ * for malicious applications setting only __O_SYNC.
+ */
+ if (flags & __O_SYNC)
+ flags |= O_DSYNC;
+
+ /*
+ * If we have O_PATH in the open flag. Then we
+ * cannot have anything other than the below set of flags
+ */
+ if (flags & O_PATH) {
+ flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
+ acc_mode = 0;
+ } else {
+ acc_mode = MAY_OPEN | ACC_MODE(flags);
+ }
+
+ op->open_flag = flags;
+
+ /* O_TRUNC implies we need access checks for write permissions */
+ if (flags & O_TRUNC)
+ acc_mode |= MAY_WRITE;
+
+ /* Allow the LSM permission hook to distinguish append
+ access from general write access. */
+ if (flags & O_APPEND)
+ acc_mode |= MAY_APPEND;
+
+ op->acc_mode = acc_mode;
+
+ op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
+
+ if (flags & O_CREAT) {
+ op->intent |= LOOKUP_CREATE;
+ if (flags & O_EXCL)
+ op->intent |= LOOKUP_EXCL;
+ }
+
+ if (flags & O_DIRECTORY)
+ lookup_flags |= LOOKUP_DIRECTORY;
+ if (!(flags & O_NOFOLLOW))
+ lookup_flags |= LOOKUP_FOLLOW;
+ return lookup_flags;
+}
+
+/**
+ * filp_open - open file and return file pointer
+ *
+ * @filename: path to open
+ * @flags: open flags as per the open(2) second argument
+ * @mode: mode for the new file if O_CREAT is set, else ignored
+ *
+ * This is the helper to open a file from kernelspace if you really
+ * have to. But in generally you should not do this, so please move
+ * along, nothing to see here..
+ */
+struct file *filp_open(const char *filename, int flags, int mode)
+{
+ struct open_flags op;
+ int lookup = build_open_flags(flags, mode, &op);
+ return do_filp_open(AT_FDCWD, filename, &op, lookup);
+}
+EXPORT_SYMBOL(filp_open);
+
+struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+ const char *filename, int flags)
+{
+ struct open_flags op;
+ int lookup = build_open_flags(flags, 0, &op);
+ if (flags & O_CREAT)
+ return ERR_PTR(-EINVAL);
+ if (!filename && (flags & O_DIRECTORY))
+ if (!dentry->d_inode->i_op->lookup)
+ return ERR_PTR(-ENOTDIR);
+ return do_file_open_root(dentry, mnt, filename, &op, lookup);
+}
+EXPORT_SYMBOL(file_open_root);
+
long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
{
+ struct open_flags op;
+ int lookup = build_open_flags(flags, mode, &op);
char *tmp = getname(filename);
int fd = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
fd = get_unused_fd_flags(flags);
if (fd >= 0) {
- struct file *f = do_filp_open(dfd, tmp, flags, mode, 0);
+ struct file *f = do_filp_open(dfd, tmp, &op, lookup);
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
if (filp->f_op && filp->f_op->flush)
retval = filp->f_op->flush(filp, id);
- dnotify_flush(filp, id);
- locks_remove_posix(filp, id);
+ if (likely(!(filp->f_mode & FMODE_PATH))) {
+ dnotify_flush(filp, id);
+ locks_remove_posix(filp, id);
+ }
fput(filp);
return retval;
}
}
vm->vblk_size = get_unaligned_be32(data + 0x08);
+ if (vm->vblk_size == 0) {
+ ldm_error ("Illegal VBLK size");
+ return false;
+ }
+
vm->vblk_offset = get_unaligned_be32(data + 0x0C);
vm->last_vblk_seq = get_unaligned_be32(data + 0x04);
int mac_partition(struct parsed_partitions *state)
{
- int slot = 1;
Sector sect;
unsigned char *data;
- int blk, blocks_in_map;
+ int slot, blocks_in_map;
unsigned secsize;
#ifdef CONFIG_PPC_PMAC
int found_root = 0;
put_dev_sector(sect);
return 0; /* not a MacOS disk */
}
- strlcat(state->pp_buf, " [mac]", PAGE_SIZE);
blocks_in_map = be32_to_cpu(part->map_count);
- for (blk = 1; blk <= blocks_in_map; ++blk) {
- int pos = blk * secsize;
+ if (blocks_in_map < 0 || blocks_in_map >= DISK_MAX_PARTS) {
+ put_dev_sector(sect);
+ return 0;
+ }
+ strlcat(state->pp_buf, " [mac]", PAGE_SIZE);
+ for (slot = 1; slot <= blocks_in_map; ++slot) {
+ int pos = slot * secsize;
put_dev_sector(sect);
data = read_part_sector(state, pos/512, §);
if (!data)
}
if (goodness > found_root_goodness) {
- found_root = blk;
+ found_root = slot;
found_root_goodness = goodness;
}
}
#endif /* CONFIG_PPC_PMAC */
-
- ++slot;
}
#ifdef CONFIG_PPC_PMAC
if (found_root_goodness)
#include "check.h"
#include "osf.h"
+#define MAX_OSF_PARTITIONS 8
+
int osf_partition(struct parsed_partitions *state)
{
int i;
int slot = 1;
+ unsigned int npartitions;
Sector sect;
unsigned char *data;
struct disklabel {
u8 p_fstype;
u8 p_frag;
__le16 p_cpg;
- } d_partitions[8];
+ } d_partitions[MAX_OSF_PARTITIONS];
} * label;
struct d_partition * partition;
put_dev_sector(sect);
return 0;
}
- for (i = 0 ; i < le16_to_cpu(label->d_npartitions); i++, partition++) {
+ npartitions = le16_to_cpu(label->d_npartitions);
+ if (npartitions > MAX_OSF_PARTITIONS) {
+ put_dev_sector(sect);
+ return 0;
+ }
+ for (i = 0 ; i < npartitions; i++, partition++) {
if (slot == state->limit)
break;
if (le32_to_cpu(partition->p_size))
task_cap(m, task);
task_cpus_allowed(m, task);
cpuset_task_status_allowed(m, task);
-#if defined(CONFIG_S390)
- task_show_regs(m, task);
-#endif
task_context_switch_counts(m, task);
return 0;
}
&proc_self_inode_operations, NULL, {}),
};
-/*
- * Exceptional case: normally we are not allowed to unhash a busy
- * directory. In this case, however, we can do it - no aliasing problems
- * due to the way we treat inodes.
- */
-static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd)
-{
- struct inode *inode;
- struct task_struct *task;
-
- if (nd->flags & LOOKUP_RCU)
- return -ECHILD;
-
- inode = dentry->d_inode;
- task = get_proc_task(inode);
- if (task) {
- put_task_struct(task);
- return 1;
- }
- d_drop(dentry);
- return 0;
-}
-
-static const struct dentry_operations proc_base_dentry_operations =
-{
- .d_revalidate = proc_base_revalidate,
- .d_delete = pid_delete_dentry,
-};
-
static struct dentry *proc_base_instantiate(struct inode *dir,
struct dentry *dentry, struct task_struct *task, const void *ptr)
{
if (p->fop)
inode->i_fop = p->fop;
ei->op = p->op;
- d_set_d_op(dentry, &proc_base_dentry_operations);
d_add(dentry, inode);
error = NULL;
out:
static void proc_evict_inode(struct inode *inode)
{
struct proc_dir_entry *de;
+ struct ctl_table_header *head;
truncate_inode_pages(&inode->i_data, 0);
end_writeback(inode);
de = PROC_I(inode)->pde;
if (de)
pde_put(de);
- if (PROC_I(inode)->sysctl)
- sysctl_head_put(PROC_I(inode)->sysctl);
+ head = PROC_I(inode)->sysctl;
+ if (head) {
+ rcu_assign_pointer(PROC_I(inode)->sysctl, NULL);
+ sysctl_head_put(head);
+ }
}
struct vfsmount *proc_mnt;
return;
root = of_find_node_by_path("/");
if (root == NULL) {
- printk(KERN_ERR "/proc/device-tree: can't find root\n");
+ pr_debug("/proc/device-tree: can't find root\n");
return;
}
proc_device_tree_add_node(root, proc_device_tree);
const struct dentry *dentry, const struct inode *inode,
unsigned int len, const char *str, const struct qstr *name)
{
+ struct ctl_table_header *head;
/* Although proc doesn't have negative dentries, rcu-walk means
* that inode here can be NULL */
+ /* AV: can it, indeed? */
if (!inode)
- return 0;
+ return 1;
if (name->len != len)
return 1;
if (memcmp(name->name, str, len))
return 1;
- return !sysctl_is_seen(PROC_I(inode)->sysctl);
+ head = rcu_dereference(PROC_I(inode)->sysctl);
+ return !head || !sysctl_is_seen(head);
}
static const struct dentry_operations proc_sys_dentry_operations = {
struct inode *inode = dentry->d_inode;
int maxlen = *lenp;
- if (maxlen < 3)
+ if (need_parent && (maxlen < 5)) {
+ *lenp = 5;
return 255;
+ } else if (maxlen < 3) {
+ *lenp = 3;
+ return 255;
+ }
data[0] = inode->i_ino;
data[1] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
EMPTY_DIR_SIZE_V1 : EMPTY_DIR_SIZE,
dentry, inode, &security);
if (retval) {
- dir->i_nlink--;
+ DEC_DIR_INODE_NLINK(dir)
goto out_failed;
}
reiserfs_write_unlock(dir->i_sb);
return -EMLINK;
}
- if (inode->i_nlink == 0) {
- reiserfs_write_unlock(dir->i_sb);
- return -ENOENT;
- }
/* inc before scheduling so reiserfs_unlink knows we are here */
inc_nlink(inode);
static int xattr_hide_revalidate(struct dentry *dentry, struct nameidata *nd)
{
- if (nd->flags & LOOKUP_RCU)
- return -ECHILD;
return -EPERM;
}
int error = -EINVAL;
int lookup_flags = 0;
- if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) != 0)
+ if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+ AT_EMPTY_PATH)) != 0)
goto out;
if (!(flag & AT_SYMLINK_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
if (flag & AT_NO_AUTOMOUNT)
lookup_flags |= LOOKUP_NO_AUTOMOUNT;
+ if (flag & AT_EMPTY_PATH)
+ lookup_flags |= LOOKUP_EMPTY;
error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
if (bufsiz <= 0)
return -EINVAL;
- error = user_path_at(dfd, pathname, 0, &path);
+ error = user_path_at(dfd, pathname, LOOKUP_EMPTY, &path);
if (!error) {
struct inode *inode = path.dentry->d_inode;
}
EXPORT_SYMBOL(vfs_statfs);
-static int do_statfs_native(struct path *path, struct statfs *buf)
+int user_statfs(const char __user *pathname, struct kstatfs *st)
{
- struct kstatfs st;
- int retval;
+ struct path path;
+ int error = user_path(pathname, &path);
+ if (!error) {
+ error = vfs_statfs(&path, st);
+ path_put(&path);
+ }
+ return error;
+}
- retval = vfs_statfs(path, &st);
- if (retval)
- return retval;
+int fd_statfs(int fd, struct kstatfs *st)
+{
+ struct file *file = fget(fd);
+ int error = -EBADF;
+ if (file) {
+ error = vfs_statfs(&file->f_path, st);
+ fput(file);
+ }
+ return error;
+}
- if (sizeof(*buf) == sizeof(st))
- memcpy(buf, &st, sizeof(st));
+static int do_statfs_native(struct kstatfs *st, struct statfs __user *p)
+{
+ struct statfs buf;
+
+ if (sizeof(buf) == sizeof(*st))
+ memcpy(&buf, st, sizeof(*st));
else {
- if (sizeof buf->f_blocks == 4) {
- if ((st.f_blocks | st.f_bfree | st.f_bavail |
- st.f_bsize | st.f_frsize) &
+ if (sizeof buf.f_blocks == 4) {
+ if ((st->f_blocks | st->f_bfree | st->f_bavail |
+ st->f_bsize | st->f_frsize) &
0xffffffff00000000ULL)
return -EOVERFLOW;
/*
* f_files and f_ffree may be -1; it's okay to stuff
* that into 32 bits
*/
- if (st.f_files != -1 &&
- (st.f_files & 0xffffffff00000000ULL))
+ if (st->f_files != -1 &&
+ (st->f_files & 0xffffffff00000000ULL))
return -EOVERFLOW;
- if (st.f_ffree != -1 &&
- (st.f_ffree & 0xffffffff00000000ULL))
+ if (st->f_ffree != -1 &&
+ (st->f_ffree & 0xffffffff00000000ULL))
return -EOVERFLOW;
}
- buf->f_type = st.f_type;
- buf->f_bsize = st.f_bsize;
- buf->f_blocks = st.f_blocks;
- buf->f_bfree = st.f_bfree;
- buf->f_bavail = st.f_bavail;
- buf->f_files = st.f_files;
- buf->f_ffree = st.f_ffree;
- buf->f_fsid = st.f_fsid;
- buf->f_namelen = st.f_namelen;
- buf->f_frsize = st.f_frsize;
- buf->f_flags = st.f_flags;
- memset(buf->f_spare, 0, sizeof(buf->f_spare));
+ buf.f_type = st->f_type;
+ buf.f_bsize = st->f_bsize;
+ buf.f_blocks = st->f_blocks;
+ buf.f_bfree = st->f_bfree;
+ buf.f_bavail = st->f_bavail;
+ buf.f_files = st->f_files;
+ buf.f_ffree = st->f_ffree;
+ buf.f_fsid = st->f_fsid;
+ buf.f_namelen = st->f_namelen;
+ buf.f_frsize = st->f_frsize;
+ buf.f_flags = st->f_flags;
+ memset(buf.f_spare, 0, sizeof(buf.f_spare));
}
+ if (copy_to_user(p, &buf, sizeof(buf)))
+ return -EFAULT;
return 0;
}
-static int do_statfs64(struct path *path, struct statfs64 *buf)
+static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p)
{
- struct kstatfs st;
- int retval;
-
- retval = vfs_statfs(path, &st);
- if (retval)
- return retval;
-
- if (sizeof(*buf) == sizeof(st))
- memcpy(buf, &st, sizeof(st));
+ struct statfs64 buf;
+ if (sizeof(buf) == sizeof(*st))
+ memcpy(&buf, st, sizeof(*st));
else {
- buf->f_type = st.f_type;
- buf->f_bsize = st.f_bsize;
- buf->f_blocks = st.f_blocks;
- buf->f_bfree = st.f_bfree;
- buf->f_bavail = st.f_bavail;
- buf->f_files = st.f_files;
- buf->f_ffree = st.f_ffree;
- buf->f_fsid = st.f_fsid;
- buf->f_namelen = st.f_namelen;
- buf->f_frsize = st.f_frsize;
- buf->f_flags = st.f_flags;
- memset(buf->f_spare, 0, sizeof(buf->f_spare));
+ buf.f_type = st->f_type;
+ buf.f_bsize = st->f_bsize;
+ buf.f_blocks = st->f_blocks;
+ buf.f_bfree = st->f_bfree;
+ buf.f_bavail = st->f_bavail;
+ buf.f_files = st->f_files;
+ buf.f_ffree = st->f_ffree;
+ buf.f_fsid = st->f_fsid;
+ buf.f_namelen = st->f_namelen;
+ buf.f_frsize = st->f_frsize;
+ buf.f_flags = st->f_flags;
+ memset(buf.f_spare, 0, sizeof(buf.f_spare));
}
+ if (copy_to_user(p, &buf, sizeof(buf)))
+ return -EFAULT;
return 0;
}
SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf)
{
- struct path path;
- int error;
-
- error = user_path(pathname, &path);
- if (!error) {
- struct statfs tmp;
- error = do_statfs_native(&path, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- path_put(&path);
- }
+ struct kstatfs st;
+ int error = user_statfs(pathname, &st);
+ if (!error)
+ error = do_statfs_native(&st, buf);
return error;
}
SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf)
{
- struct path path;
- long error;
-
+ struct kstatfs st;
+ int error;
if (sz != sizeof(*buf))
return -EINVAL;
- error = user_path(pathname, &path);
- if (!error) {
- struct statfs64 tmp;
- error = do_statfs64(&path, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- path_put(&path);
- }
+ error = user_statfs(pathname, &st);
+ if (!error)
+ error = do_statfs64(&st, buf);
return error;
}
SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf)
{
- struct file *file;
- struct statfs tmp;
- int error;
-
- error = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
- error = do_statfs_native(&file->f_path, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- fput(file);
-out:
+ struct kstatfs st;
+ int error = fd_statfs(fd, &st);
+ if (!error)
+ error = do_statfs_native(&st, buf);
return error;
}
SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf)
{
- struct file *file;
- struct statfs64 tmp;
+ struct kstatfs st;
int error;
if (sz != sizeof(*buf))
return -EINVAL;
- error = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
- error = do_statfs64(&file->f_path, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- fput(file);
-out:
+ error = fd_statfs(fd, &st);
+ if (!error)
+ error = do_statfs64(&st, buf);
return error;
}
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
fs->kill_sb(s);
+ /*
+ * We need to call rcu_barrier so all the delayed rcu free
+ * inodes are flushed before we release the fs module.
+ */
+ rcu_barrier();
put_filesystem(fs);
put_super(s);
} else {
new_de = sysv_find_entry(new_dentry, &new_page);
if (!new_de)
goto out_dir;
- inode_inc_link_count(old_inode);
sysv_set_link(new_de, new_page, old_inode);
new_inode->i_ctime = CURRENT_TIME_SEC;
if (dir_de)
if (new_dir->i_nlink >= SYSV_SB(new_dir->i_sb)->s_link_max)
goto out_dir;
}
- inode_inc_link_count(old_inode);
err = sysv_add_link(new_dentry, old_inode);
- if (err) {
- inode_dec_link_count(old_inode);
+ if (err)
goto out_dir;
- }
if (dir_de)
inode_inc_link_count(new_dir);
}
sysv_delete_entry(old_de, old_page);
- inode_dec_link_count(old_inode);
+ mark_inode_dirty(old_inode);
if (dir_de) {
sysv_set_link(dir_de, dir_page, new_dir);
ubifs_assert(mutex_is_locked(&dir->i_mutex));
ubifs_assert(mutex_is_locked(&inode->i_mutex));
- /*
- * Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing
- * otherwise has the potential to corrupt the orphan inode list.
- *
- * Indeed, consider a scenario when 'vfs_link(dirA/fileA)' and
- * 'vfs_unlink(dirA/fileA, dirB/fileB)' race. 'vfs_link()' does not
- * lock 'dirA->i_mutex', so this is possible. Both of the functions
- * lock 'fileA->i_mutex' though. Suppose 'vfs_unlink()' wins, and takes
- * 'fileA->i_mutex' mutex first. Suppose 'fileA->i_nlink' is 1. In this
- * case 'ubifs_unlink()' will drop the last reference, and put 'inodeA'
- * to the list of orphans. After this, 'vfs_link()' will link
- * 'dirB/fileB' to 'inodeA'. This is a problem because, for example,
- * the subsequent 'vfs_unlink(dirB/fileB)' will add the same inode
- * to the list of orphans.
- */
- if (inode->i_nlink == 0)
- return -ENOENT;
-
err = dbg_check_synced_i_size(inode);
if (err)
return err;
#include <linux/crc-itu-t.h>
#include <linux/exportfs.h>
+enum { UDF_MAX_LINKS = 0xffff };
+
static inline int udf_match(int len1, const unsigned char *name1, int len2,
const unsigned char *name2)
{
struct udf_inode_info *iinfo;
err = -EMLINK;
- if (dir->i_nlink >= (256 << sizeof(dir->i_nlink)) - 1)
+ if (dir->i_nlink >= UDF_MAX_LINKS)
goto out;
err = -EIO;
struct fileIdentDesc cfi, *fi;
int err;
- if (inode->i_nlink >= (256 << sizeof(inode->i_nlink)) - 1) {
+ if (inode->i_nlink >= UDF_MAX_LINKS)
return -EMLINK;
- }
fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
if (!fi) {
goto end_rename;
retval = -EMLINK;
- if (!new_inode &&
- new_dir->i_nlink >=
- (256 << sizeof(new_dir->i_nlink)) - 1)
+ if (!new_inode && new_dir->i_nlink >= UDF_MAX_LINKS)
goto end_rename;
}
if (!nfi) {
struct fid *fid = (struct fid *)fh;
int type = FILEID_UDF_WITHOUT_PARENT;
- if (len < 3 || (connectable && len < 5))
+ if (connectable && (len < 5)) {
+ *lenp = 5;
return 255;
+ } else if (len < 3) {
+ *lenp = 3;
+ return 255;
+ }
*lenp = 3;
fid->udf.block = location.logicalBlockNum;
new_de = ufs_find_entry(new_dir, &new_dentry->d_name, &new_page);
if (!new_de)
goto out_dir;
- inode_inc_link_count(old_inode);
ufs_set_link(new_dir, new_de, new_page, old_inode);
new_inode->i_ctime = CURRENT_TIME_SEC;
if (dir_de)
if (new_dir->i_nlink >= UFS_LINK_MAX)
goto out_dir;
}
- inode_inc_link_count(old_inode);
err = ufs_add_link(new_dentry, old_inode);
- if (err) {
- inode_dec_link_count(old_inode);
+ if (err)
goto out_dir;
- }
if (dir_de)
inode_inc_link_count(new_dir);
}
/*
* Like most other Unix systems, set the ctime for inodes on a
* rename.
- * inode_dec_link_count() will mark the inode dirty.
*/
old_inode->i_ctime = CURRENT_TIME_SEC;
ufs_delete_entry(old_dir, old_de, old_page);
- inode_dec_link_count(old_inode);
+ mark_inode_dirty(old_inode);
if (dir_de) {
ufs_set_link(old_inode, dir_de, dir_page, new_dir);
if (!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
+ if (!blk_queue_discard(q))
+ return -XFS_ERROR(EOPNOTSUPP);
if (copy_from_user(&range, urange, sizeof(range)))
return -XFS_ERROR(EFAULT);
* seven combinations work. The real answer is "don't use v2".
*/
len = xfs_fileid_length(fileid_type);
- if (*max_len < len)
+ if (*max_len < len) {
+ *max_len = len;
return 255;
+ }
*max_len = len;
switch (fileid_type) {
xfs_mount_t *mp,
void __user *arg)
{
- xfs_fsop_geom_v1_t fsgeo;
+ xfs_fsop_geom_t fsgeo;
int error;
- error = xfs_fs_geometry(mp, (xfs_fsop_geom_t *)&fsgeo, 3);
+ error = xfs_fs_geometry(mp, &fsgeo, 3);
if (error)
return -error;
- if (copy_to_user(arg, &fsgeo, sizeof(fsgeo)))
+ /*
+ * Caller should have passed an argument of type
+ * xfs_fsop_geom_v1_t. This is a proper subset of the
+ * xfs_fsop_geom_t that xfs_fs_geometry() fills in.
+ */
+ if (copy_to_user(arg, &fsgeo, sizeof(xfs_fsop_geom_v1_t)))
return -XFS_ERROR(EFAULT);
return 0;
}
xfs_fsop_geom_t *geo,
int new_version)
{
+
+ memset(geo, 0, sizeof(*geo));
+
geo->blocksize = mp->m_sb.sb_blocksize;
geo->rtextsize = mp->m_sb.sb_rextsize;
geo->agblocks = mp->m_sb.sb_agblocks;
#define cputime64_to_jiffies64(__ct) (__ct)
#define jiffies64_to_cputime64(__jif) (__jif)
#define cputime_to_cputime64(__ct) ((u64) __ct)
+#define cputime64_gt(__a, __b) ((__a) > (__b))
+
+#define nsecs_to_cputime64(__ct) nsecs_to_jiffies64(__ct)
/*
#define O_SYNC (__O_SYNC|O_DSYNC)
#endif
+#ifndef O_PATH
+#define O_PATH 010000000
+#endif
+
#ifndef O_NDELAY
#define O_NDELAY O_NONBLOCK
#endif
#include <asm/errno.h>
static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+ if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
pagefault_disable();
}
static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
return -ENOSYS;
}
#ifndef __ASSEMBLY__
#ifdef CONFIG_MMU
+#include <linux/mm_types.h>
+
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
extern char _end[];
extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
extern char __kprobes_text_start[], __kprobes_text_end[];
+extern char __entry_text_start[], __entry_text_end[];
extern char __initdata_begin[], __initdata_end[];
extern char __start_rodata[], __end_rodata[];
__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
#define __NR_fanotify_mark 263
__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at 264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at 265
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
#undef __NR_syscalls
-#define __NR_syscalls 264
+#define __NR_syscalls 266
/*
* All syscalls below here should go away really,
*(.kprobes.text) \
VMLINUX_SYMBOL(__kprobes_text_end) = .;
+#define ENTRY_TEXT \
+ ALIGN_FUNCTION(); \
+ VMLINUX_SYMBOL(__entry_text_start) = .; \
+ *(.entry.text) \
+ VMLINUX_SYMBOL(__entry_text_end) = .;
+
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
#define IRQENTRY_TEXT \
ALIGN_FUNCTION(); \
struct platform_device *platformdev; /**< Platform device struture */
struct drm_sg_mem *sg; /**< Scatter gather memory */
- int num_crtcs; /**< Number of CRTCs on this device */
+ unsigned int num_crtcs; /**< Number of CRTCs on this device */
void *dev_private; /**< device private data */
void *mm_private;
struct address_space *dev_mapping;
* structure of raw payloads passed to add_key() or instantiate key
*/
struct rxrpc_key_data_v1 {
- u32 kif_version; /* 1 */
u16 security_index;
u16 ticket_length;
u32 expiry; /* time_t */
extern void blk_stop_queue(struct request_queue *q);
extern void blk_sync_queue(struct request_queue *q);
extern void __blk_stop_queue(struct request_queue *q);
-extern void __blk_run_queue(struct request_queue *);
+extern void __blk_run_queue(struct request_queue *q, bool force_kblockd);
extern void blk_run_queue(struct request_queue *);
extern int blk_rq_map_user(struct request_queue *, struct request *,
struct rq_map_data *, void __user *, unsigned long,
struct work_struct;
int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
-int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay);
#ifdef CONFIG_BLK_CGROUP
/*
extern int blk_throtl_init(struct request_queue *q);
extern void blk_throtl_exit(struct request_queue *q);
extern int blk_throtl_bio(struct request_queue *q, struct bio **bio);
-extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay);
extern void throtl_shutdown_timer_wq(struct request_queue *q);
#else /* CONFIG_BLK_DEV_THROTTLING */
static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio)
static inline int blk_throtl_init(struct request_queue *q) { return 0; }
static inline int blk_throtl_exit(struct request_queue *q) { return 0; }
-static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {}
static inline void throtl_shutdown_timer_wq(struct request_queue *q) {}
#endif /* CONFIG_BLK_DEV_THROTTLING */
extern void blk_dump_cmd(char *buf, struct request *rq);
extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
-extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq);
#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
#define SOCK_CLOSED 11 /* socket state changed to closed */
#define OPENING 13 /* open connection w/ (possibly new) peer */
#define DEAD 14 /* dead, about to kfree */
+#define BACKOFF 15
/*
* A single connection with another host.
struct list_head out_queue;
struct list_head out_sent; /* sending or sent but unacked */
u64 out_seq; /* last message queued for send */
- bool out_keepalive_pending;
u64 in_seq, in_seq_acked; /* last message received, acked */
struct cgroup *old_cgrp, struct task_struct *tsk,
bool threadgroup);
void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
- void (*exit)(struct cgroup_subsys *ss, struct task_struct *task);
+ void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup *old_cgrp, struct task_struct *task);
int (*populate)(struct cgroup_subsys *ss,
struct cgroup *cgrp);
void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
/* Get id and depth of css */
unsigned short css_id(struct cgroup_subsys_state *css);
unsigned short css_depth(struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id);
#else /* !CONFIG_CGROUPS */
SUBSYS(blkio)
#endif
+#ifdef CONFIG_CGROUP_PERF
+SUBSYS(perf)
+#endif
+
/* */
*/
struct dcb_app {
__u8 selector;
- __u32 protocol;
__u8 priority;
+ __u16 protocol;
};
struct dcbmsg {
/**
* struct debug_obj_descr - object type specific debug description structure
+ *
* @name: name of the object typee
+ * @debug_hint: function returning address, which have associated
+ * kernel symbol, to allow identify the object
* @fixup_init: fixup function, which is called when the init check
* fails
* @fixup_activate: fixup function, which is called when the activate check
*/
struct debug_obj_descr {
const char *name;
-
+ void *(*debug_hint) (void *addr);
int (*fixup_init) (void *addr, enum debug_obj_state state);
int (*fixup_activate) (void *addr, enum debug_obj_state state);
int (*fixup_destroy) (void *addr, enum debug_obj_state state);
struct super_block;
struct vfsmount;
+/* limit the handle size to NFSv4 handle size now */
+#define MAX_HANDLE_SZ 128
+
/*
* The fileid_type identifies how the file within the filesystem is encoded.
* In theory this is freely set and parsed by the filesystem, but we try to
* set, the encode_fh() should store sufficient information so that a good
* attempt can be made to find not only the file but also it's place in the
* filesystem. This typically means storing a reference to de->d_parent in
- * the filehandle fragment. encode_fh() should return the number of bytes
- * stored or a negative error code such as %-ENOSPC
+ * the filehandle fragment. encode_fh() should return the fileid_type on
+ * success and on error returns 255 (if the space needed to encode fh is
+ * greater than @max_len*4 bytes). On error @max_len contains the minimum
+ * size(in 4 byte unit) needed to encode the file handle.
*
* fh_to_dentry:
* @fh_to_dentry is given a &struct super_block (@sb) and a file handle
unlinking file. */
#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */
#ifdef __KERNEL__
extern struct file *fget(unsigned int fd);
extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
extern void set_close_on_exec(unsigned int fd, int flag);
extern void put_filp(struct file *);
extern int alloc_fd(unsigned start, unsigned flags);
}
/*
- * Check if the task should be counted as freezeable by the freezer
+ * Check if the task should be counted as freezable by the freezer
*/
static inline int freezer_should_skip(struct task_struct *p)
{
/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000)
+/* File is opened with O_PATH; almost nothing can be done with it */
+#define FMODE_PATH ((__force fmode_t)0x4000)
+
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x1000000)
spinlock_t private_lock; /* for use by the address_space */
struct list_head private_list; /* ditto */
struct address_space *assoc_mapping; /* ditto */
+ struct mutex unmap_mutex; /* to protect unmapping */
} __attribute__((aligned(sizeof(long))));
/*
* On most architectures that alignment is already the case; but
#endif
};
+struct file_handle {
+ __u32 handle_bytes;
+ int handle_type;
+ /* file identifier */
+ unsigned char f_handle[0];
+};
+
#define get_file(x) atomic_long_inc(&(x)->f_count)
#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
#define file_count(x) atomic_long_read(&(x)->f_count)
wait_queue_head_t s_wait_unfrozen;
char s_id[32]; /* Informational name */
+ u8 s_uuid[16]; /* UUID */
void *s_fs_info; /* Filesystem private info */
fmode_t s_mode;
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
struct vfsmount *);
extern int vfs_statfs(struct path *, struct kstatfs *);
+extern int user_statfs(const char __user *, struct kstatfs *);
+extern int fd_statfs(int, struct kstatfs *);
extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
extern long do_sys_open(int dfd, const char __user *filename, int flags,
int mode);
extern struct file *filp_open(const char *, int, int);
+extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+ const char *, int);
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
const struct cred *);
extern int filp_close(struct file *, fl_owner_t id);
struct block_device *bdev);
extern int revalidate_disk(struct gendisk *);
extern int check_disk_change(struct block_device *);
-extern int __invalidate_device(struct block_device *);
+extern int __invalidate_device(struct block_device *, bool);
extern int invalidate_partition(struct gendisk *, int);
#endif
unsigned long invalidate_mapping_pages(struct address_space *mapping,
extern struct file *create_write_pipe(int flags);
extern void free_write_pipe(struct file *);
-extern struct file *do_filp_open(int dfd, const char *pathname,
- int open_flag, int mode, int acc_mode);
-extern int may_open(struct path *, int, int);
-
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
extern struct file * open_exec(const char *);
extern int inode_init_always(struct super_block *, struct inode *);
extern void inode_init_once(struct inode *);
+extern void address_space_init_once(struct address_space *mapping);
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
extern struct inode * igrab(struct inode *);
extern void ftrace_graph_init_task(struct task_struct *t);
extern void ftrace_graph_exit_task(struct task_struct *t);
+extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
static inline int task_curr_ret_stack(struct task_struct *t)
{
static inline void ftrace_graph_init_task(struct task_struct *t) { }
static inline void ftrace_graph_exit_task(struct task_struct *t) { }
+static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { }
static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
trace_func_graph_ent_t entryfunc)
unsigned char flags;
unsigned char preempt_count;
int pid;
- int lock_depth;
};
#define FTRACE_MAX_EVENT \
#define PERF_MAX_TRACE_SIZE 2048
-#define MAX_FILTER_PRED 32
#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */
extern void destroy_preds(struct ftrace_event_call *call);
return alloc_pages_current(gfp_mask, order);
}
extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
- struct vm_area_struct *vma, unsigned long addr);
+ struct vm_area_struct *vma, unsigned long addr,
+ int node);
#else
#define alloc_pages(gfp_mask, order) \
alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_pages_vma(gfp_mask, order, vma, addr) \
+#define alloc_pages_vma(gfp_mask, order, vma, addr, node) \
alloc_pages(gfp_mask, order)
#endif
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
-#define alloc_page_vma(gfp_mask, vma, addr) \
- alloc_pages_vma(gfp_mask, 0, vma, addr)
+#define alloc_page_vma(gfp_mask, vma, addr) \
+ alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
+#define alloc_page_vma_node(gfp_mask, vma, addr, node) \
+ alloc_pages_vma(gfp_mask, 0, vma, addr, node)
extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
extern unsigned long get_zeroed_page(gfp_t gfp_mask);
* 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)
- * 0x09 timer was migrated on CPU hotunplug
+ * 0x05 timer was migrated on CPU hotunplug
+ *
* The "callback function running and enqueued" status is only possible on
* SMP. It happens for example when a posix timer expired and the callback
* queued a signal. Between dropping the lock which protects the posix timer
* 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 bit in the above scenario.
+ * 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.
*
* All state transitions are protected by cpu_base->lock.
*/
#endif
};
-#define HRTIMER_MAX_CLOCK_BASES 2
+enum hrtimer_base_type {
+ HRTIMER_BASE_REALTIME,
+ HRTIMER_BASE_MONOTONIC,
+ HRTIMER_BASE_BOOTTIME,
+ HRTIMER_MAX_CLOCK_BASES,
+};
/*
* struct hrtimer_cpu_base - the per cpu clock bases
extern ktime_t ktime_get(void);
extern ktime_t ktime_get_real(void);
+extern ktime_t ktime_get_boottime(void);
DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
extern ktime_t hrtimer_get_next_event(void);
/*
- * A timer is active, when it is enqueued into the rbtree or the callback
- * function is running.
+ * 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)
{
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \
((__vma)->vm_flags & VM_HUGEPAGE))) && \
- !((__vma)->vm_flags & VM_NOHUGEPAGE))
+ !((__vma)->vm_flags & VM_NOHUGEPAGE) && \
+ !is_vma_temporary_stack(__vma))
#define transparent_hugepage_defrag(__vma) \
((transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)) || \
#include <linux/types.h>
#include <linux/input.h>
-#define MATRIX_MAX_ROWS 16
-#define MATRIX_MAX_COLS 16
+#define MATRIX_MAX_ROWS 32
+#define MATRIX_MAX_COLS 32
#define KEY(row, col, val) ((((row) & (MATRIX_MAX_ROWS - 1)) << 24) |\
(((col) & (MATRIX_MAX_COLS - 1)) << 16) |\
#include <linux/smp.h>
#include <linux/percpu.h>
#include <linux/hrtimer.h>
+#include <linux/kref.h>
+#include <linux/workqueue.h>
#include <asm/atomic.h>
#include <asm/ptrace.h>
* Used by threaded interrupts which need to keep the
* irq line disabled until the threaded handler has been run.
* IRQF_NO_SUSPEND - Do not disable this IRQ during suspend
- *
+ * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set
+ * IRQF_NO_THREAD - Interrupt cannot be threaded
*/
#define IRQF_DISABLED 0x00000020
#define IRQF_SAMPLE_RANDOM 0x00000040
#define IRQF_IRQPOLL 0x00001000
#define IRQF_ONESHOT 0x00002000
#define IRQF_NO_SUSPEND 0x00004000
+#define IRQF_FORCE_RESUME 0x00008000
+#define IRQF_NO_THREAD 0x00010000
-#define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND)
-
-/*
- * Bits used by threaded handlers:
- * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
- * IRQTF_DIED - handler thread died
- * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
- * IRQTF_AFFINITY - irq thread is requested to adjust affinity
- */
-enum {
- IRQTF_RUNTHREAD,
- IRQTF_DIED,
- IRQTF_WARNED,
- IRQTF_AFFINITY,
-};
+#define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
/*
* These values can be returned by request_any_context_irq() and
* @thread_fn: interupt handler function for threaded interrupts
* @thread: thread pointer for threaded interrupts
* @thread_flags: flags related to @thread
+ * @thread_mask: bitmask for keeping track of @thread activity
*/
struct irqaction {
irq_handler_t handler;
irq_handler_t thread_fn;
struct task_struct *thread;
unsigned long thread_flags;
+ unsigned long thread_mask;
const char *name;
struct proc_dir_entry *dir;
} ____cacheline_internodealigned_in_smp;
extern int irq_select_affinity(unsigned int irq);
extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
+
+/**
+ * struct irq_affinity_notify - context for notification of IRQ affinity changes
+ * @irq: Interrupt to which notification applies
+ * @kref: Reference count, for internal use
+ * @work: Work item, for internal use
+ * @notify: Function to be called on change. This will be
+ * called in process context.
+ * @release: Function to be called on release. This will be
+ * called in process context. Once registered, the
+ * structure must only be freed when this function is
+ * called or later.
+ */
+struct irq_affinity_notify {
+ unsigned int irq;
+ struct kref kref;
+ struct work_struct work;
+ void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
+ void (*release)(struct kref *ref);
+};
+
+extern int
+irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
+
+static inline void irq_run_affinity_notifiers(void)
+{
+ flush_scheduled_work();
+}
+
#else /* CONFIG_SMP */
static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
static inline int irq_select_affinity(unsigned int irq) { return 0; }
static inline int irq_set_affinity_hint(unsigned int irq,
- const struct cpumask *m)
+ const struct cpumask *m)
{
return -EINVAL;
}
}
/* IRQ wakeup (PM) control: */
-extern int set_irq_wake(unsigned int irq, unsigned int on);
+extern int irq_set_irq_wake(unsigned int irq, unsigned int on);
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+/* Please do not use: Use the replacement functions instead */
+static inline int set_irq_wake(unsigned int irq, unsigned int on)
+{
+ return irq_set_irq_wake(irq, on);
+}
+#endif
static inline int enable_irq_wake(unsigned int irq)
{
- return set_irq_wake(irq, 1);
+ return irq_set_irq_wake(irq, 1);
}
static inline int disable_irq_wake(unsigned int irq)
{
- return set_irq_wake(irq, 0);
+ return irq_set_irq_wake(irq, 0);
}
#else /* !CONFIG_GENERIC_HARDIRQS */
}
#endif /* CONFIG_GENERIC_HARDIRQS */
+
+#ifdef CONFIG_IRQ_FORCED_THREADING
+extern bool force_irqthreads;
+#else
+#define force_irqthreads (0)
+#endif
+
#ifndef __ARCH_SET_SOFTIRQ_PENDING
#define set_softirq_pending(x) (local_softirq_pending() = (x))
#define or_softirq_pending(x) (local_softirq_pending() |= (x))
*/
DECLARE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
+DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
+
+static inline struct task_struct *this_cpu_ksoftirqd(void)
+{
+ return this_cpu_read(ksoftirqd);
+}
+
/* Try to send a softirq to a remote cpu. If this cannot be done, the
* work will be queued to the local cpu.
*/
struct seq_file;
int show_interrupts(struct seq_file *p, void *v);
+int arch_show_interrupts(struct seq_file *p, int prec);
extern int early_irq_init(void);
extern int arch_probe_nr_irqs(void);
#include <asm/irq_regs.h>
struct irq_desc;
+struct irq_data;
typedef void (*irq_flow_handler_t)(unsigned int irq,
struct irq_desc *desc);
-
+typedef void (*irq_preflow_handler_t)(struct irq_data *data);
/*
* IRQ line status.
*
- * Bits 0-7 are reserved for the IRQF_* bits in linux/interrupt.h
+ * Bits 0-7 are the same as the IRQF_* bits in linux/interrupt.h
+ *
+ * IRQ_TYPE_NONE - default, unspecified type
+ * IRQ_TYPE_EDGE_RISING - rising edge triggered
+ * IRQ_TYPE_EDGE_FALLING - falling edge triggered
+ * IRQ_TYPE_EDGE_BOTH - rising and falling edge triggered
+ * IRQ_TYPE_LEVEL_HIGH - high level triggered
+ * IRQ_TYPE_LEVEL_LOW - low level triggered
+ * IRQ_TYPE_LEVEL_MASK - Mask to filter out the level bits
+ * IRQ_TYPE_SENSE_MASK - Mask for all the above bits
+ * IRQ_TYPE_PROBE - Special flag for probing in progress
+ *
+ * Bits which can be modified via irq_set/clear/modify_status_flags()
+ * IRQ_LEVEL - Interrupt is level type. Will be also
+ * updated in the code when the above trigger
+ * bits are modified via set_irq_type()
+ * IRQ_PER_CPU - Mark an interrupt PER_CPU. Will protect
+ * it from affinity setting
+ * IRQ_NOPROBE - Interrupt cannot be probed by autoprobing
+ * IRQ_NOREQUEST - Interrupt cannot be requested via
+ * request_irq()
+ * IRQ_NOAUTOEN - Interrupt is not automatically enabled in
+ * request/setup_irq()
+ * IRQ_NO_BALANCING - Interrupt cannot be balanced (affinity set)
+ * IRQ_MOVE_PCNTXT - Interrupt can be migrated from process context
+ * IRQ_NESTED_TRHEAD - Interrupt nests into another thread
+ *
+ * Deprecated bits. They are kept updated as long as
+ * CONFIG_GENERIC_HARDIRQS_NO_COMPAT is not set. Will go away soon. These bits
+ * are internal state of the core code and if you really need to acces
+ * them then talk to the genirq maintainer instead of hacking
+ * something weird.
*
- * IRQ types
*/
-#define IRQ_TYPE_NONE 0x00000000 /* Default, unspecified type */
-#define IRQ_TYPE_EDGE_RISING 0x00000001 /* Edge rising type */
-#define IRQ_TYPE_EDGE_FALLING 0x00000002 /* Edge falling type */
-#define IRQ_TYPE_EDGE_BOTH (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)
-#define IRQ_TYPE_LEVEL_HIGH 0x00000004 /* Level high type */
-#define IRQ_TYPE_LEVEL_LOW 0x00000008 /* Level low type */
-#define IRQ_TYPE_SENSE_MASK 0x0000000f /* Mask of the above */
-#define IRQ_TYPE_PROBE 0x00000010 /* Probing in progress */
-
-/* Internal flags */
-#define IRQ_INPROGRESS 0x00000100 /* IRQ handler active - do not enter! */
-#define IRQ_DISABLED 0x00000200 /* IRQ disabled - do not enter! */
-#define IRQ_PENDING 0x00000400 /* IRQ pending - replay on enable */
-#define IRQ_REPLAY 0x00000800 /* IRQ has been replayed but not acked yet */
-#define IRQ_AUTODETECT 0x00001000 /* IRQ is being autodetected */
-#define IRQ_WAITING 0x00002000 /* IRQ not yet seen - for autodetection */
-#define IRQ_LEVEL 0x00004000 /* IRQ level triggered */
-#define IRQ_MASKED 0x00008000 /* IRQ masked - shouldn't be seen again */
-#define IRQ_PER_CPU 0x00010000 /* IRQ is per CPU */
-#define IRQ_NOPROBE 0x00020000 /* IRQ is not valid for probing */
-#define IRQ_NOREQUEST 0x00040000 /* IRQ cannot be requested */
-#define IRQ_NOAUTOEN 0x00080000 /* IRQ will not be enabled on request irq */
-#define IRQ_WAKEUP 0x00100000 /* IRQ triggers system wakeup */
-#define IRQ_MOVE_PENDING 0x00200000 /* need to re-target IRQ destination */
-#define IRQ_NO_BALANCING 0x00400000 /* IRQ is excluded from balancing */
-#define IRQ_SPURIOUS_DISABLED 0x00800000 /* IRQ was disabled by the spurious trap */
-#define IRQ_MOVE_PCNTXT 0x01000000 /* IRQ migration from process context */
-#define IRQ_AFFINITY_SET 0x02000000 /* IRQ affinity was set from userspace*/
-#define IRQ_SUSPENDED 0x04000000 /* IRQ has gone through suspend sequence */
-#define IRQ_ONESHOT 0x08000000 /* IRQ is not unmasked after hardirq */
-#define IRQ_NESTED_THREAD 0x10000000 /* IRQ is nested into another, no own handler thread */
+enum {
+ IRQ_TYPE_NONE = 0x00000000,
+ IRQ_TYPE_EDGE_RISING = 0x00000001,
+ IRQ_TYPE_EDGE_FALLING = 0x00000002,
+ IRQ_TYPE_EDGE_BOTH = (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING),
+ IRQ_TYPE_LEVEL_HIGH = 0x00000004,
+ IRQ_TYPE_LEVEL_LOW = 0x00000008,
+ IRQ_TYPE_LEVEL_MASK = (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH),
+ IRQ_TYPE_SENSE_MASK = 0x0000000f,
+
+ IRQ_TYPE_PROBE = 0x00000010,
+
+ IRQ_LEVEL = (1 << 8),
+ IRQ_PER_CPU = (1 << 9),
+ IRQ_NOPROBE = (1 << 10),
+ IRQ_NOREQUEST = (1 << 11),
+ IRQ_NOAUTOEN = (1 << 12),
+ IRQ_NO_BALANCING = (1 << 13),
+ IRQ_MOVE_PCNTXT = (1 << 14),
+ IRQ_NESTED_THREAD = (1 << 15),
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+ IRQ_INPROGRESS = (1 << 16),
+ IRQ_REPLAY = (1 << 17),
+ IRQ_WAITING = (1 << 18),
+ IRQ_DISABLED = (1 << 19),
+ IRQ_PENDING = (1 << 20),
+ IRQ_MASKED = (1 << 21),
+ IRQ_MOVE_PENDING = (1 << 22),
+ IRQ_AFFINITY_SET = (1 << 23),
+ IRQ_WAKEUP = (1 << 24),
+#endif
+};
#define IRQF_MODIFY_MASK \
(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
- IRQ_PER_CPU)
+ IRQ_PER_CPU | IRQ_NESTED_THREAD)
-#ifdef CONFIG_IRQ_PER_CPU
-# define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
-# define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING)
-#else
-# define CHECK_IRQ_PER_CPU(var) 0
-# define IRQ_NO_BALANCING_MASK IRQ_NO_BALANCING
-#endif
+#define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING)
+
+static inline __deprecated bool CHECK_IRQ_PER_CPU(unsigned int status)
+{
+ return status & IRQ_PER_CPU;
+}
+
+/*
+ * Return value for chip->irq_set_affinity()
+ *
+ * IRQ_SET_MASK_OK - OK, core updates irq_data.affinity
+ * IRQ_SET_MASK_NOCPY - OK, chip did update irq_data.affinity
+ */
+enum {
+ IRQ_SET_MASK_OK = 0,
+ IRQ_SET_MASK_OK_NOCOPY,
+};
struct msi_desc;
* struct irq_data - per irq and irq chip data passed down to chip functions
* @irq: interrupt number
* @node: node index useful for balancing
+ * @state_use_accessor: status information for irq chip functions.
+ * Use accessor functions to deal with it
* @chip: low level interrupt hardware access
* @handler_data: per-IRQ data for the irq_chip methods
* @chip_data: platform-specific per-chip private data for the chip
struct irq_data {
unsigned int irq;
unsigned int node;
+ unsigned int state_use_accessors;
struct irq_chip *chip;
void *handler_data;
void *chip_data;
#endif
};
+/*
+ * Bit masks for irq_data.state
+ *
+ * IRQD_TRIGGER_MASK - Mask for the trigger type bits
+ * IRQD_SETAFFINITY_PENDING - Affinity setting is pending
+ * IRQD_NO_BALANCING - Balancing disabled for this IRQ
+ * IRQD_PER_CPU - Interrupt is per cpu
+ * IRQD_AFFINITY_SET - Interrupt affinity was set
+ * IRQD_LEVEL - Interrupt is level triggered
+ * IRQD_WAKEUP_STATE - Interrupt is configured for wakeup
+ * from suspend
+ * IRDQ_MOVE_PCNTXT - Interrupt can be moved in process
+ * context
+ */
+enum {
+ IRQD_TRIGGER_MASK = 0xf,
+ IRQD_SETAFFINITY_PENDING = (1 << 8),
+ IRQD_NO_BALANCING = (1 << 10),
+ IRQD_PER_CPU = (1 << 11),
+ IRQD_AFFINITY_SET = (1 << 12),
+ IRQD_LEVEL = (1 << 13),
+ IRQD_WAKEUP_STATE = (1 << 14),
+ IRQD_MOVE_PCNTXT = (1 << 15),
+};
+
+static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
+{
+ return d->state_use_accessors & IRQD_SETAFFINITY_PENDING;
+}
+
+static inline bool irqd_is_per_cpu(struct irq_data *d)
+{
+ return d->state_use_accessors & IRQD_PER_CPU;
+}
+
+static inline bool irqd_can_balance(struct irq_data *d)
+{
+ return !(d->state_use_accessors & (IRQD_PER_CPU | IRQD_NO_BALANCING));
+}
+
+static inline bool irqd_affinity_was_set(struct irq_data *d)
+{
+ return d->state_use_accessors & IRQD_AFFINITY_SET;
+}
+
+static inline u32 irqd_get_trigger_type(struct irq_data *d)
+{
+ return d->state_use_accessors & IRQD_TRIGGER_MASK;
+}
+
+/*
+ * Must only be called inside irq_chip.irq_set_type() functions.
+ */
+static inline void irqd_set_trigger_type(struct irq_data *d, u32 type)
+{
+ d->state_use_accessors &= ~IRQD_TRIGGER_MASK;
+ d->state_use_accessors |= type & IRQD_TRIGGER_MASK;
+}
+
+static inline bool irqd_is_level_type(struct irq_data *d)
+{
+ return d->state_use_accessors & IRQD_LEVEL;
+}
+
+static inline bool irqd_is_wakeup_set(struct irq_data *d)
+{
+ return d->state_use_accessors & IRQD_WAKEUP_STATE;
+}
+
+static inline bool irqd_can_move_in_process_context(struct irq_data *d)
+{
+ return d->state_use_accessors & IRQD_MOVE_PCNTXT;
+}
+
/**
* struct irq_chip - hardware interrupt chip descriptor
*
* @irq_set_wake: enable/disable power-management wake-on of an IRQ
* @irq_bus_lock: function to lock access to slow bus (i2c) chips
* @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
+ * @flags: chip specific flags
*
* @release: release function solely used by UML
*/
void (*irq_bus_lock)(struct irq_data *data);
void (*irq_bus_sync_unlock)(struct irq_data *data);
+ unsigned long flags;
+
/* Currently used only by UML, might disappear one day.*/
#ifdef CONFIG_IRQ_RELEASE_METHOD
void (*release)(unsigned int irq, void *dev_id);
#endif
};
+/*
+ * irq_chip specific flags
+ *
+ * IRQCHIP_SET_TYPE_MASKED: Mask before calling chip.irq_set_type()
+ * IRQCHIP_EOI_IF_HANDLED: Only issue irq_eoi() when irq was handled
+ * IRQCHIP_MASK_ON_SUSPEND: Mask non wake irqs in the suspend path
+ */
+enum {
+ IRQCHIP_SET_TYPE_MASKED = (1 << 0),
+ IRQCHIP_EOI_IF_HANDLED = (1 << 1),
+ IRQCHIP_MASK_ON_SUSPEND = (1 << 2),
+};
+
/* This include will go away once we isolated irq_desc usage to core code */
#include <linux/irqdesc.h>
# define ARCH_IRQ_INIT_FLAGS 0
#endif
-#define IRQ_DEFAULT_INIT_FLAGS (IRQ_DISABLED | ARCH_IRQ_INIT_FLAGS)
+#define IRQ_DEFAULT_INIT_FLAGS ARCH_IRQ_INIT_FLAGS
struct irqaction;
extern int setup_irq(unsigned int irq, struct irqaction *new);
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
void move_native_irq(int irq);
void move_masked_irq(int irq);
+void irq_move_irq(struct irq_data *data);
+void irq_move_masked_irq(struct irq_data *data);
#else
static inline void move_native_irq(int irq) { }
static inline void move_masked_irq(int irq) { }
+static inline void irq_move_irq(struct irq_data *data) { }
+static inline void irq_move_masked_irq(struct irq_data *data) { }
#endif
extern int no_irq_affinity;
extern struct irq_chip dummy_irq_chip;
extern void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
- irq_flow_handler_t handle);
-extern void
-set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
irq_flow_handler_t handle, const char *name);
+static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+ irq_flow_handler_t handle)
+{
+ irq_set_chip_and_handler_name(irq, chip, handle, NULL);
+}
+
extern void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
const char *name);
-/*
- * Set a highlevel flow handler for a given IRQ:
- */
static inline void
-set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
+irq_set_handler(unsigned int irq, irq_flow_handler_t handle)
{
- __set_irq_handler(irq, handle, 0, NULL);
+ __irq_set_handler(irq, handle, 0, NULL);
}
/*
* IRQ_NOREQUEST and IRQ_NOPROBE)
*/
static inline void
-set_irq_chained_handler(unsigned int irq,
- irq_flow_handler_t handle)
+irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle)
{
- __set_irq_handler(irq, handle, 1, NULL);
+ __irq_set_handler(irq, handle, 1, NULL);
}
-extern void set_irq_nested_thread(unsigned int irq, int nest);
-
void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
static inline void irq_set_status_flags(unsigned int irq, unsigned long set)
irq_modify_status(irq, clr, 0);
}
-static inline void set_irq_noprobe(unsigned int irq)
+static inline void irq_set_noprobe(unsigned int irq)
{
irq_modify_status(irq, 0, IRQ_NOPROBE);
}
-static inline void set_irq_probe(unsigned int irq)
+static inline void irq_set_probe(unsigned int irq)
{
irq_modify_status(irq, IRQ_NOPROBE, 0);
}
+static inline void irq_set_nested_thread(unsigned int irq, bool nest)
+{
+ if (nest)
+ irq_set_status_flags(irq, IRQ_NESTED_THREAD);
+ else
+ irq_clear_status_flags(irq, IRQ_NESTED_THREAD);
+}
+
/* Handle dynamic irq creation and destruction */
extern unsigned int create_irq_nr(unsigned int irq_want, int node);
extern int create_irq(void);
}
/* Set/get chip/data for an IRQ: */
-extern int set_irq_chip(unsigned int irq, struct irq_chip *chip);
-extern int set_irq_data(unsigned int irq, void *data);
-extern int set_irq_chip_data(unsigned int irq, void *data);
-extern int set_irq_type(unsigned int irq, unsigned int type);
-extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
+extern int irq_set_chip(unsigned int irq, struct irq_chip *chip);
+extern int irq_set_handler_data(unsigned int irq, void *data);
+extern int irq_set_chip_data(unsigned int irq, void *data);
+extern int irq_set_irq_type(unsigned int irq, unsigned int type);
+extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
extern struct irq_data *irq_get_irq_data(unsigned int irq);
-static inline struct irq_chip *get_irq_chip(unsigned int irq)
+static inline struct irq_chip *irq_get_chip(unsigned int irq)
{
struct irq_data *d = irq_get_irq_data(irq);
return d ? d->chip : NULL;
return d->chip;
}
-static inline void *get_irq_chip_data(unsigned int irq)
+static inline void *irq_get_chip_data(unsigned int irq)
{
struct irq_data *d = irq_get_irq_data(irq);
return d ? d->chip_data : NULL;
return d->chip_data;
}
-static inline void *get_irq_data(unsigned int irq)
+static inline void *irq_get_handler_data(unsigned int irq)
{
struct irq_data *d = irq_get_irq_data(irq);
return d ? d->handler_data : NULL;
}
-static inline void *irq_data_get_irq_data(struct irq_data *d)
+static inline void *irq_data_get_irq_handler_data(struct irq_data *d)
{
return d->handler_data;
}
-static inline struct msi_desc *get_irq_msi(unsigned int irq)
+static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
{
struct irq_data *d = irq_get_irq_data(irq);
return d ? d->msi_desc : NULL;
return d->msi_desc;
}
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+/* Please do not use: Use the replacement functions instead */
+static inline int set_irq_chip(unsigned int irq, struct irq_chip *chip)
+{
+ return irq_set_chip(irq, chip);
+}
+static inline int set_irq_data(unsigned int irq, void *data)
+{
+ return irq_set_handler_data(irq, data);
+}
+static inline int set_irq_chip_data(unsigned int irq, void *data)
+{
+ return irq_set_chip_data(irq, data);
+}
+static inline int set_irq_type(unsigned int irq, unsigned int type)
+{
+ return irq_set_irq_type(irq, type);
+}
+static inline int set_irq_msi(unsigned int irq, struct msi_desc *entry)
+{
+ return irq_set_msi_desc(irq, entry);
+}
+static inline struct irq_chip *get_irq_chip(unsigned int irq)
+{
+ return irq_get_chip(irq);
+}
+static inline void *get_irq_chip_data(unsigned int irq)
+{
+ return irq_get_chip_data(irq);
+}
+static inline void *get_irq_data(unsigned int irq)
+{
+ return irq_get_handler_data(irq);
+}
+static inline void *irq_data_get_irq_data(struct irq_data *d)
+{
+ return irq_data_get_irq_handler_data(d);
+}
+static inline struct msi_desc *get_irq_msi(unsigned int irq)
+{
+ return irq_get_msi_desc(irq);
+}
+static inline void set_irq_noprobe(unsigned int irq)
+{
+ irq_set_noprobe(irq);
+}
+static inline void set_irq_probe(unsigned int irq)
+{
+ irq_set_probe(irq);
+}
+static inline void set_irq_nested_thread(unsigned int irq, int nest)
+{
+ irq_set_nested_thread(irq, nest);
+}
+static inline void
+set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+ irq_flow_handler_t handle, const char *name)
+{
+ irq_set_chip_and_handler_name(irq, chip, handle, name);
+}
+static inline void
+set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+ irq_flow_handler_t handle)
+{
+ irq_set_chip_and_handler(irq, chip, handle);
+}
+static inline void
+__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+ const char *name)
+{
+ __irq_set_handler(irq, handle, is_chained, name);
+}
+static inline void set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
+{
+ irq_set_handler(irq, handle);
+}
+static inline void
+set_irq_chained_handler(unsigned int irq, irq_flow_handler_t handle)
+{
+ irq_set_chained_handler(irq, handle);
+}
+#endif
+
int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
void irq_free_descs(unsigned int irq, unsigned int cnt);
int irq_reserve_irqs(unsigned int from, unsigned int cnt);
* For now it's included from <linux/irq.h>
*/
+struct irq_affinity_notify;
struct proc_dir_entry;
struct timer_rand_state;
/**
* @handle_irq: highlevel irq-events handler [if NULL, __do_IRQ()]
* @action: the irq action chain
* @status: status information
+ * @core_internal_state__do_not_mess_with_it: core internal status information
* @depth: disable-depth, for nested irq_disable() calls
* @wake_depth: enable depth, for multiple set_irq_wake() callers
* @irq_count: stats field to detect stalled irqs
* @last_unhandled: aging timer for unhandled count
* @irqs_unhandled: stats field for spurious unhandled interrupts
* @lock: locking for SMP
+ * @affinity_notify: context for notification of affinity changes
* @pending_mask: pending rebalanced interrupts
+ * @threads_oneshot: bitfield to handle shared oneshot threads
* @threads_active: number of irqaction threads currently running
* @wait_for_threads: wait queue for sync_irq to wait for threaded handlers
* @dir: /proc/irq/ procfs entry
struct {
unsigned int irq;
unsigned int node;
+ unsigned int pad_do_not_even_think_about_it;
struct irq_chip *chip;
void *handler_data;
void *chip_data;
struct timer_rand_state *timer_rand_state;
unsigned int __percpu *kstat_irqs;
irq_flow_handler_t handle_irq;
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+ irq_preflow_handler_t preflow_handler;
+#endif
struct irqaction *action; /* IRQ action list */
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+ unsigned int status_use_accessors;
+#else
unsigned int status; /* IRQ status */
-
+#endif
+ unsigned int core_internal_state__do_not_mess_with_it;
unsigned int depth; /* nested irq disables */
unsigned int wake_depth; /* nested wake enables */
unsigned int irq_count; /* For detecting broken IRQs */
raw_spinlock_t lock;
#ifdef CONFIG_SMP
const struct cpumask *affinity_hint;
+ struct irq_affinity_notify *affinity_notify;
#ifdef CONFIG_GENERIC_PENDING_IRQ
cpumask_var_t pending_mask;
#endif
#endif
+ unsigned long threads_oneshot;
atomic_t threads_active;
wait_queue_head_t wait_for_threads;
#ifdef CONFIG_PROC_FS
#ifdef CONFIG_GENERIC_HARDIRQS
-#define get_irq_desc_chip(desc) ((desc)->irq_data.chip)
-#define get_irq_desc_chip_data(desc) ((desc)->irq_data.chip_data)
-#define get_irq_desc_data(desc) ((desc)->irq_data.handler_data)
-#define get_irq_desc_msi(desc) ((desc)->irq_data.msi_desc)
+static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
+{
+ return &desc->irq_data;
+}
+
+static inline struct irq_chip *irq_desc_get_chip(struct irq_desc *desc)
+{
+ return desc->irq_data.chip;
+}
+
+static inline void *irq_desc_get_chip_data(struct irq_desc *desc)
+{
+ return desc->irq_data.chip_data;
+}
+
+static inline void *irq_desc_get_handler_data(struct irq_desc *desc)
+{
+ return desc->irq_data.handler_data;
+}
+
+static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc)
+{
+ return desc->irq_data.msi_desc;
+}
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+static inline struct irq_chip *get_irq_desc_chip(struct irq_desc *desc)
+{
+ return irq_desc_get_chip(desc);
+}
+static inline void *get_irq_desc_data(struct irq_desc *desc)
+{
+ return irq_desc_get_handler_data(desc);
+}
+
+static inline void *get_irq_desc_chip_data(struct irq_desc *desc)
+{
+ return irq_desc_get_chip_data(desc);
+}
+
+static inline struct msi_desc *get_irq_desc_msi(struct irq_desc *desc)
+{
+ return irq_desc_get_msi_desc(desc);
+}
+#endif
/*
* Architectures call this to let the generic IRQ layer
return desc->action != NULL;
}
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
static inline int irq_balancing_disabled(unsigned int irq)
{
struct irq_desc *desc;
desc = irq_to_desc(irq);
return desc->status & IRQ_NO_BALANCING_MASK;
}
+#endif
/* caller has locked the irq_desc and both params are valid */
static inline void __set_irq_handler_unlocked(int irq,
desc = irq_to_desc(irq);
desc->handle_irq = handler;
}
+
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void
+__irq_set_preflow_handler(unsigned int irq, irq_preflow_handler_t handler)
+{
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+ desc->preflow_handler = handler;
+}
+#endif
#endif
#endif
extern unsigned long clock_t_to_jiffies(unsigned long x);
extern u64 jiffies_64_to_clock_t(u64 x);
extern u64 nsec_to_clock_t(u64 x);
+extern u64 nsecs_to_jiffies64(u64 n);
extern unsigned long nsecs_to_jiffies(u64 n);
#define TIMESTAMP_SIZE 30
struct list_head k_list;
void (*get)(struct klist_node *);
void (*put)(struct klist_node *);
-} __attribute__ ((aligned (4)));
+} __attribute__ ((aligned (sizeof(void *))));
#define KLIST_INIT(_name, _get, _put) \
{ .k_lock = __SPIN_LOCK_UNLOCKED(_name.k_lock), \
};
#define KTHREAD_WORKER_INIT(worker) { \
- .lock = SPIN_LOCK_UNLOCKED, \
+ .lock = __SPIN_LOCK_UNLOCKED((worker).lock), \
.work_list = LIST_HEAD_INIT((worker).work_list), \
}
* in an undefined state.
*/
#ifndef CONFIG_DEBUG_LIST
+static inline void __list_del_entry(struct list_head *entry)
+{
+ __list_del(entry->prev, entry->next);
+}
+
static inline void list_del(struct list_head *entry)
{
__list_del(entry->prev, entry->next);
entry->prev = LIST_POISON2;
}
#else
+extern void __list_del_entry(struct list_head *entry);
extern void list_del(struct list_head *entry);
#endif
*/
static inline void list_del_init(struct list_head *entry)
{
- __list_del(entry->prev, entry->next);
+ __list_del_entry(entry);
INIT_LIST_HEAD(entry);
}
*/
static inline void list_move(struct list_head *list, struct list_head *head)
{
- __list_del(list->prev, list->next);
+ __list_del_entry(list);
list_add(list, head);
}
static inline void list_move_tail(struct list_head *list,
struct list_head *head)
{
- __list_del(list->prev, list->next);
+ __list_del_entry(list);
list_add_tail(list, head);
}
u16 irq_masks_cache[WM8994_NUM_IRQ_REGS];
/* Used over suspend/resume */
+ bool suspended;
u16 ldo_regs[WM8994_NUM_LDO_REGS];
u16 gpio_regs[WM8994_NUM_GPIO_REGS];
struct module_attribute mattr;
const char *module_name;
const char *version;
-};
+} __attribute__ ((__aligned__(sizeof(void *))));
struct module_kobject
{
struct path path;
struct qstr last;
struct path root;
- struct file *file;
struct inode *inode; /* path.dentry.d_inode */
unsigned int flags;
unsigned seq;
#define LOOKUP_EXCL 0x0400
#define LOOKUP_RENAME_TARGET 0x0800
+#define LOOKUP_JUMPED 0x1000
+#define LOOKUP_ROOT 0x2000
+#define LOOKUP_EMPTY 0x4000
+
extern int user_path_at(int, const char __user *, unsigned, struct path *);
#define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
extern int kern_path(const char *, unsigned, struct path *);
-extern int path_lookup(const char *, unsigned, struct nameidata *);
+extern int kern_path_parent(const char *, struct nameidata *);
extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
const char *, unsigned int, struct nameidata *);
extern int netdev_info(const struct net_device *dev, const char *format, ...)
__attribute__ ((format (printf, 2, 3)));
+#define MODULE_ALIAS_NETDEV(device) \
+ MODULE_ALIAS("netdev-" device)
+
#if defined(DEBUG)
#define netdev_dbg(__dev, format, args...) \
netdev_printk(KERN_DEBUG, __dev, format, ##args)
unsigned char cl_id_uniquifier;
u32 cl_cb_ident; /* v4.0 callback identifier */
const struct nfs4_minor_version_ops *cl_mvops;
-#endif /* CONFIG_NFS_V4 */
-#ifdef CONFIG_NFS_V4_1
- /* clientid returned from EXCHANGE_ID, used by session operations */
- u64 cl_ex_clid;
/* The sequence id to use for the next CREATE_SESSION */
u32 cl_seqid;
/* The flags used for obtaining the clientid during EXCHANGE_ID */
struct nfs4_session *cl_session; /* sharred session */
struct list_head cl_layouts;
struct pnfs_deviceid_cache *cl_devid_cache; /* pNFS deviceid cache */
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_NFS_V4 */
#ifdef CONFIG_NFS_FSCACHE
struct fscache_cookie *fscache; /* client index cache cookie */
/* maximum number of slots to use */
#define NFS4_MAX_SLOT_TABLE RPC_MAX_SLOT_TABLE
-#if defined(CONFIG_NFS_V4_1)
+#if defined(CONFIG_NFS_V4)
/* Sessions */
#define SLOT_TABLE_SZ (NFS4_MAX_SLOT_TABLE/(8*sizeof(long)))
struct nfs_client *clp;
};
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_NFS_V4 */
#endif
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/printk.h>
#include <asm/atomic.h>
/* Each escaped entry is prefixed by ESCAPE_CODE
int oprofile_add_data64(struct op_entry *entry, u64 val);
int oprofile_write_commit(struct op_entry *entry);
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_HW_PERF_EVENTS
int __init oprofile_perf_init(struct oprofile_operations *ops);
void oprofile_perf_exit(void);
char *op_name_from_perf_id(void);
-#endif /* CONFIG_PERF_EVENTS */
+#else
+static inline int __init oprofile_perf_init(struct oprofile_operations *ops)
+{
+ pr_info("oprofile: hardware counters not available\n");
+ return -ENODEV;
+}
+static inline void oprofile_perf_exit(void) { }
+#endif /* CONFIG_HW_PERF_EVENTS */
#endif /* OPROFILE_H */
};
__u32 bp_type;
- __u64 bp_addr;
- __u64 bp_len;
+ union {
+ __u64 bp_addr;
+ __u64 config1; /* extension of config */
+ };
+ union {
+ __u64 bp_len;
+ __u64 config2; /* extension of config1 */
+ };
};
/*
#define PERF_FLAG_FD_NO_GROUP (1U << 0)
#define PERF_FLAG_FD_OUTPUT (1U << 1)
+#define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */
#ifdef __KERNEL__
/*
*/
#ifdef CONFIG_PERF_EVENTS
+# include <linux/cgroup.h>
# include <asm/perf_event.h>
# include <asm/local64.h>
#endif
unsigned long event_base;
int idx;
int last_cpu;
+ unsigned int extra_reg;
+ u64 extra_config;
+ int extra_alloc;
};
struct { /* software */
struct hrtimer hrtimer;
#define PERF_ATTACH_GROUP 0x02
#define PERF_ATTACH_TASK 0x04
+#ifdef CONFIG_CGROUP_PERF
+/*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+struct perf_cgroup_info {
+ u64 time;
+ u64 timestamp;
+};
+
+struct perf_cgroup {
+ struct cgroup_subsys_state css;
+ struct perf_cgroup_info *info; /* timing info, one per cpu */
+};
+#endif
+
/**
* struct perf_event - performance event kernel representation:
*/
struct event_filter *filter;
#endif
+#ifdef CONFIG_CGROUP_PERF
+ struct perf_cgroup *cgrp; /* cgroup event is attach to */
+ int cgrp_defer_enabled;
+#endif
+
#endif /* CONFIG_PERF_EVENTS */
};
u64 generation;
int pin_count;
struct rcu_head rcu_head;
+ int nr_cgroups; /* cgroup events present */
};
/*
struct list_head rotation_list;
int jiffies_interval;
struct pmu *active_pmu;
+#ifdef CONFIG_CGROUP_PERF
+ struct perf_cgroup *cgrp;
+#endif
};
struct perf_output_handle {
__perf_sw_event(event_id, nr, nmi, regs, addr);
}
-extern atomic_t perf_task_events;
+extern atomic_t perf_sched_events;
static inline void perf_event_task_sched_in(struct task_struct *task)
{
- COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+ COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task));
}
static inline
{
perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
- COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+ COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next));
}
extern void perf_event_mmap(struct vm_area_struct *vma);
extern int sysctl_perf_event_mlock;
extern int sysctl_perf_event_sample_rate;
+extern int perf_proc_update_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
+
static inline bool perf_paranoid_tracepoint_raw(void)
{
return sysctl_perf_event_paranoid > -1;
*
* Simple ASCII art explanation:
*
- * |HEAD |
- * | |
- * |prio_list.prev|<------------------------------------|
- * |prio_list.next|<->|pl|<->|pl|<--------------->|pl|<-|
- * |10 | |10| |21| |21| |21| |40| (prio)
- * | | | | | | | | | | | |
- * | | | | | | | | | | | |
- * |node_list.next|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
- * |node_list.prev|<------------------------------------|
+ * pl:prio_list (only for plist_node)
+ * nl:node_list
+ * HEAD| NODE(S)
+ * |
+ * ||------------------------------------|
+ * ||->|pl|<->|pl|<--------------->|pl|<-|
+ * | |10| |21| |21| |21| |40| (prio)
+ * | | | | | | | | | | |
+ * | | | | | | | | | | |
+ * |->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
+ * |-------------------------------------------|
*
* The nodes on the prio_list list are sorted by priority to simplify
* the insertion of new nodes. There are no nodes with duplicate
#include <linux/spinlock_types.h>
struct plist_head {
- struct list_head prio_list;
struct list_head node_list;
#ifdef CONFIG_DEBUG_PI_LIST
raw_spinlock_t *rawlock;
struct plist_node {
int prio;
- struct plist_head plist;
+ struct list_head prio_list;
+ struct list_head node_list;
};
#ifdef CONFIG_DEBUG_PI_LIST
#endif
#define _PLIST_HEAD_INIT(head) \
- .prio_list = LIST_HEAD_INIT((head).prio_list), \
.node_list = LIST_HEAD_INIT((head).node_list)
/**
#define PLIST_NODE_INIT(node, __prio) \
{ \
.prio = (__prio), \
- .plist = { _PLIST_HEAD_INIT((node).plist) }, \
+ .prio_list = LIST_HEAD_INIT((node).prio_list), \
+ .node_list = LIST_HEAD_INIT((node).node_list), \
}
/**
static inline void
plist_head_init(struct plist_head *head, spinlock_t *lock)
{
- INIT_LIST_HEAD(&head->prio_list);
INIT_LIST_HEAD(&head->node_list);
#ifdef CONFIG_DEBUG_PI_LIST
head->spinlock = lock;
static inline void
plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock)
{
- INIT_LIST_HEAD(&head->prio_list);
INIT_LIST_HEAD(&head->node_list);
#ifdef CONFIG_DEBUG_PI_LIST
head->rawlock = lock;
static inline void plist_node_init(struct plist_node *node, int prio)
{
node->prio = prio;
- plist_head_init(&node->plist, NULL);
+ INIT_LIST_HEAD(&node->prio_list);
+ INIT_LIST_HEAD(&node->node_list);
}
extern void plist_add(struct plist_node *node, struct plist_head *head);
* @head: the head for your list
*/
#define plist_for_each(pos, head) \
- list_for_each_entry(pos, &(head)->node_list, plist.node_list)
+ list_for_each_entry(pos, &(head)->node_list, node_list)
/**
* plist_for_each_safe - iterate safely over a plist of given type
* Iterate over a plist of given type, safe against removal of list entry.
*/
#define plist_for_each_safe(pos, n, head) \
- list_for_each_entry_safe(pos, n, &(head)->node_list, plist.node_list)
+ list_for_each_entry_safe(pos, n, &(head)->node_list, node_list)
/**
* plist_for_each_entry - iterate over list of given type
* @mem: the name of the list_struct within the struct
*/
#define plist_for_each_entry(pos, head, mem) \
- list_for_each_entry(pos, &(head)->node_list, mem.plist.node_list)
+ list_for_each_entry(pos, &(head)->node_list, mem.node_list)
/**
* plist_for_each_entry_safe - iterate safely over list of given type
* Iterate over list of given type, safe against removal of list entry.
*/
#define plist_for_each_entry_safe(pos, n, head, m) \
- list_for_each_entry_safe(pos, n, &(head)->node_list, m.plist.node_list)
+ list_for_each_entry_safe(pos, n, &(head)->node_list, m.node_list)
/**
* plist_head_empty - return !0 if a plist_head is empty
*/
static inline int plist_node_empty(const struct plist_node *node)
{
- return plist_head_empty(&node->plist);
+ return list_empty(&node->node_list);
}
/* All functions below assume the plist_head is not empty. */
static inline struct plist_node *plist_first(const struct plist_head *head)
{
return list_entry(head->node_list.next,
- struct plist_node, plist.node_list);
+ struct plist_node, node_list);
}
/**
static inline struct plist_node *plist_last(const struct plist_head *head)
{
return list_entry(head->node_list.prev,
- struct plist_node, plist.node_list);
+ struct plist_node, node_list);
}
#endif
struct list_head entry;
struct completion completion;
struct wakeup_source *wakeup;
+#else
+ unsigned int should_wakeup:1;
#endif
#ifdef CONFIG_PM_RUNTIME
struct timer_list suspend_timer;
return dev->power.can_wakeup;
}
-static inline bool device_may_wakeup(struct device *dev)
-{
- return false;
-}
-
static inline struct wakeup_source *wakeup_source_create(const char *name)
{
return NULL;
static inline int device_wakeup_enable(struct device *dev)
{
- return -EINVAL;
+ dev->power.should_wakeup = true;
+ return 0;
}
static inline int device_wakeup_disable(struct device *dev)
{
+ dev->power.should_wakeup = false;
return 0;
}
-static inline int device_init_wakeup(struct device *dev, bool val)
+static inline int device_set_wakeup_enable(struct device *dev, bool enable)
{
- dev->power.can_wakeup = val;
- return val ? -EINVAL : 0;
+ dev->power.should_wakeup = enable;
+ return 0;
}
+static inline int device_init_wakeup(struct device *dev, bool val)
+{
+ device_set_wakeup_capable(dev, val);
+ device_set_wakeup_enable(dev, val);
+ return 0;
+}
-static inline int device_set_wakeup_enable(struct device *dev, bool enable)
+static inline bool device_may_wakeup(struct device *dev)
{
- return -EINVAL;
+ return dev->power.can_wakeup && dev->power.should_wakeup;
}
static inline void __pm_stay_awake(struct wakeup_source *ws) {}
--- /dev/null
+/*
+ * posix-clock.h - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#ifndef _LINUX_POSIX_CLOCK_H_
+#define _LINUX_POSIX_CLOCK_H_
+
+#include <linux/cdev.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/posix-timers.h>
+
+struct posix_clock;
+
+/**
+ * struct posix_clock_operations - functional interface to the clock
+ *
+ * Every posix clock is represented by a character device. Drivers may
+ * optionally offer extended capabilities by implementing the
+ * character device methods. The character device file operations are
+ * first handled by the clock device layer, then passed on to the
+ * driver by calling these functions.
+ *
+ * @owner: The clock driver should set to THIS_MODULE
+ * @clock_adjtime: Adjust the clock
+ * @clock_gettime: Read the current time
+ * @clock_getres: Get the clock resolution
+ * @clock_settime: Set the current time value
+ * @timer_create: Create a new timer
+ * @timer_delete: Remove a previously created timer
+ * @timer_gettime: Get remaining time and interval of a timer
+ * @timer_setttime: Set a timer's initial expiration and interval
+ * @fasync: Optional character device fasync method
+ * @mmap: Optional character device mmap method
+ * @open: Optional character device open method
+ * @release: Optional character device release method
+ * @ioctl: Optional character device ioctl method
+ * @read: Optional character device read method
+ * @poll: Optional character device poll method
+ */
+struct posix_clock_operations {
+ struct module *owner;
+
+ int (*clock_adjtime)(struct posix_clock *pc, struct timex *tx);
+
+ int (*clock_gettime)(struct posix_clock *pc, struct timespec *ts);
+
+ int (*clock_getres) (struct posix_clock *pc, struct timespec *ts);
+
+ int (*clock_settime)(struct posix_clock *pc,
+ const struct timespec *ts);
+
+ int (*timer_create) (struct posix_clock *pc, struct k_itimer *kit);
+
+ int (*timer_delete) (struct posix_clock *pc, struct k_itimer *kit);
+
+ void (*timer_gettime)(struct posix_clock *pc,
+ struct k_itimer *kit, struct itimerspec *tsp);
+
+ int (*timer_settime)(struct posix_clock *pc,
+ struct k_itimer *kit, int flags,
+ struct itimerspec *tsp, struct itimerspec *old);
+ /*
+ * Optional character device methods:
+ */
+ int (*fasync) (struct posix_clock *pc,
+ int fd, struct file *file, int on);
+
+ long (*ioctl) (struct posix_clock *pc,
+ unsigned int cmd, unsigned long arg);
+
+ int (*mmap) (struct posix_clock *pc,
+ struct vm_area_struct *vma);
+
+ int (*open) (struct posix_clock *pc, fmode_t f_mode);
+
+ uint (*poll) (struct posix_clock *pc,
+ struct file *file, poll_table *wait);
+
+ int (*release) (struct posix_clock *pc);
+
+ ssize_t (*read) (struct posix_clock *pc,
+ uint flags, char __user *buf, size_t cnt);
+};
+
+/**
+ * struct posix_clock - represents a dynamic posix clock
+ *
+ * @ops: Functional interface to the clock
+ * @cdev: Character device instance for this clock
+ * @kref: Reference count.
+ * @mutex: Protects the 'zombie' field from concurrent access.
+ * @zombie: If 'zombie' is true, then the hardware has disappeared.
+ * @release: A function to free the structure when the reference count reaches
+ * zero. May be NULL if structure is statically allocated.
+ *
+ * Drivers should embed their struct posix_clock within a private
+ * structure, obtaining a reference to it during callbacks using
+ * container_of().
+ */
+struct posix_clock {
+ struct posix_clock_operations ops;
+ struct cdev cdev;
+ struct kref kref;
+ struct mutex mutex;
+ bool zombie;
+ void (*release)(struct posix_clock *clk);
+};
+
+/**
+ * posix_clock_register() - register a new clock
+ * @clk: Pointer to the clock. Caller must provide 'ops' and 'release'
+ * @devid: Allocated device id
+ *
+ * A clock driver calls this function to register itself with the
+ * clock device subsystem. If 'clk' points to dynamically allocated
+ * memory, then the caller must provide a 'release' function to free
+ * that memory.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+int posix_clock_register(struct posix_clock *clk, dev_t devid);
+
+/**
+ * posix_clock_unregister() - unregister a clock
+ * @clk: Clock instance previously registered via posix_clock_register()
+ *
+ * A clock driver calls this function to remove itself from the clock
+ * device subsystem. The posix_clock itself will remain (in an
+ * inactive state) until its reference count drops to zero, at which
+ * point it will be deallocated with its 'release' method.
+ */
+void posix_clock_unregister(struct posix_clock *clk);
+
+#endif
#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/sched.h>
+#include <linux/timex.h>
union cpu_time_count {
cputime_t cpu;
int firing;
};
+/*
+ * Bit fields within a clockid:
+ *
+ * The most significant 29 bits hold either a pid or a file descriptor.
+ *
+ * Bit 2 indicates whether a cpu clock refers to a thread or a process.
+ *
+ * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3.
+ *
+ * A clockid is invalid if bits 2, 1, and 0 are all set.
+ */
#define CPUCLOCK_PID(clock) ((pid_t) ~((clock) >> 3))
#define CPUCLOCK_PERTHREAD(clock) \
(((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
-#define CPUCLOCK_PID_MASK 7
+
#define CPUCLOCK_PERTHREAD_MASK 4
#define CPUCLOCK_WHICH(clock) ((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK)
#define CPUCLOCK_CLOCK_MASK 3
#define CPUCLOCK_VIRT 1
#define CPUCLOCK_SCHED 2
#define CPUCLOCK_MAX 3
+#define CLOCKFD CPUCLOCK_MAX
+#define CLOCKFD_MASK (CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
#define MAKE_PROCESS_CPUCLOCK(pid, clock) \
((~(clockid_t) (pid) << 3) | (clockid_t) (clock))
#define MAKE_THREAD_CPUCLOCK(tid, clock) \
MAKE_PROCESS_CPUCLOCK((tid), (clock) | CPUCLOCK_PERTHREAD_MASK)
+#define FD_TO_CLOCKID(fd) ((~(clockid_t) (fd) << 3) | CLOCKFD)
+#define CLOCKID_TO_FD(clk) ((unsigned int) ~((clk) >> 3))
+
/* POSIX.1b interval timer structure. */
struct k_itimer {
struct list_head list; /* free/ allocate list */
};
struct k_clock {
- int res; /* in nanoseconds */
int (*clock_getres) (const clockid_t which_clock, struct timespec *tp);
- int (*clock_set) (const clockid_t which_clock, struct timespec * tp);
+ int (*clock_set) (const clockid_t which_clock,
+ const struct timespec *tp);
int (*clock_get) (const clockid_t which_clock, struct timespec * tp);
+ int (*clock_adj) (const clockid_t which_clock, struct timex *tx);
int (*timer_create) (struct k_itimer *timer);
int (*nsleep) (const clockid_t which_clock, int flags,
struct timespec *, struct timespec __user *);
struct itimerspec * cur_setting);
};
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
+extern struct k_clock clock_posix_cpu;
+extern struct k_clock clock_posix_dynamic;
-/* error handlers for timer_create, nanosleep and settime */
-int do_posix_clock_nonanosleep(const clockid_t, int flags, struct timespec *,
- struct timespec __user *);
-int do_posix_clock_nosettime(const clockid_t, struct timespec *tp);
+void posix_timers_register_clock(const clockid_t clock_id, struct k_clock *new_clock);
/* function to call to trigger timer event */
int posix_timer_event(struct k_itimer *timr, int si_private);
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *ts);
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *ts);
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *ts);
-int posix_cpu_timer_create(struct k_itimer *timer);
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp, struct timespec __user *rmtp);
-long posix_cpu_nsleep_restart(struct restart_block *restart_block);
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
- struct itimerspec *new, struct itimerspec *old);
-int posix_cpu_timer_del(struct k_itimer *timer);
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp);
-
void posix_cpu_timer_schedule(struct k_itimer *timer);
void run_posix_cpu_timers(struct task_struct *task);
extern long arch_ptrace(struct task_struct *child, long request,
unsigned long addr, unsigned long data);
-extern int ptrace_traceme(void);
extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len);
extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len);
-extern int ptrace_attach(struct task_struct *tsk);
-extern int ptrace_detach(struct task_struct *, unsigned int);
extern void ptrace_disable(struct task_struct *);
extern int ptrace_check_attach(struct task_struct *task, int kill);
extern int ptrace_request(struct task_struct *child, long request,
int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
+
struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer,
unsigned long length);
int ring_buffer_unlock_commit(struct ring_buffer *buffer,
#define LINUX_RIO_REGS_H
/*
- * In RapidIO, each device has a 2MB configuration space that is
+ * In RapidIO, each device has a 16MB configuration space that is
* accessed via maintenance transactions. Portions of configuration
* space are standardized and/or reserved.
*/
+#define RIO_MAINT_SPACE_SZ 0x1000000 /* 16MB of RapidIO mainenance space */
+
#define RIO_DEV_ID_CAR 0x00 /* [I] Device Identity CAR */
#define RIO_DEV_INFO_CAR 0x04 /* [I] Device Information CAR */
#define RIO_ASM_ID_CAR 0x08 /* [I] Assembly Identity CAR */
* The (current) exceptions are mostly filesystem hooks:
* - the proc() hook for procfs
* - non-ioctl() chardev hooks: open(), release(), read_callback()
- * - periodic irq calls: irq_set_state(), irq_set_freq()
*
* REVISIT those periodic irq calls *do* have ops_lock when they're
* issued through ioctl() ...
int (*set_alarm)(struct device *, struct rtc_wkalrm *);
int (*proc)(struct device *, struct seq_file *);
int (*set_mmss)(struct device *, unsigned long secs);
- int (*irq_set_state)(struct device *, int enabled);
- int (*irq_set_freq)(struct device *, int freq);
int (*read_callback)(struct device *, int data);
int (*alarm_irq_enable)(struct device *, unsigned int enabled);
- int (*update_irq_enable)(struct device *, unsigned int enabled);
};
#define RTC_DEVICE_NAME_SIZE 20
struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */
int pie_enabled;
struct work_struct irqwork;
+
+
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+ struct work_struct uie_task;
+ struct timer_list uie_timer;
+ /* Those fields are protected by rtc->irq_lock */
+ unsigned int oldsecs;
+ unsigned int uie_irq_active:1;
+ unsigned int stop_uie_polling:1;
+ unsigned int uie_task_active:1;
+ unsigned int uie_timer_active:1;
+#endif
};
#define to_rtc_device(d) container_of(d, struct rtc_device, dev)
extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm);
extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm);
extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs);
+int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm);
extern int rtc_read_alarm(struct rtc_device *rtc,
struct rtc_wkalrm *alrm);
extern int rtc_set_alarm(struct rtc_device *rtc,
struct rtc_task *task, int freq);
extern int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled);
extern int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled);
+extern int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc,
+ unsigned int enabled);
+void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode);
void rtc_aie_update_irq(void *private);
void rtc_uie_update_irq(void *private);
enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer);
RW_DEP_MAP_INIT(lockname) }
#endif
-/*
- * RW_LOCK_UNLOCKED defeat lockdep state tracking and is hence
- * deprecated.
- *
- * Please use DEFINE_RWLOCK() or __RW_LOCK_UNLOCKED() as appropriate.
- */
-#define RW_LOCK_UNLOCKED __RW_LOCK_UNLOCKED(old_style_rw_init)
-
#define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x)
#endif /* __LINUX_RWLOCK_TYPES_H */
#error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead"
#endif
-#include <linux/spinlock.h>
-#include <linux/list.h>
-
#ifdef __KERNEL__
-
-#include <linux/types.h>
-
-struct rwsem_waiter;
-
/*
* the rw-semaphore definition
* - if activity is 0 then there are no active readers or writers
#endif
};
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-{ 0, __SPIN_LOCK_UNLOCKED(name.wait_lock), LIST_HEAD_INIT((name).wait_list) \
- __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
- struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
- struct lock_class_key *key);
-
-#define init_rwsem(sem) \
-do { \
- static struct lock_class_key __key; \
- \
- __init_rwsem((sem), #sem, &__key); \
-} while (0)
+#define RWSEM_UNLOCKED_VALUE 0x00000000
extern void __down_read(struct rw_semaphore *sem);
extern int __down_read_trylock(struct rw_semaphore *sem);
#include <linux/types.h>
#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
#include <asm/system.h>
#include <asm/atomic.h>
#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
#include <linux/rwsem-spinlock.h> /* use a generic implementation */
#else
-#include <asm/rwsem.h> /* use an arch-specific implementation */
+/* All arch specific implementations share the same struct */
+struct rw_semaphore {
+ long count;
+ spinlock_t wait_lock;
+ struct list_head wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif
+};
+
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+/* Include the arch specific part */
+#include <asm/rwsem.h>
+
+/* In all implementations count != 0 means locked */
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+ return sem->count != 0;
+}
+
+#endif
+
+/* Common initializer macros and functions */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
#endif
+#define __RWSEM_INITIALIZER(name) \
+ { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED(name.wait_lock), \
+ LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
+
+#define DECLARE_RWSEM(name) \
+ struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+ struct lock_class_key *key);
+
+#define init_rwsem(sem) \
+do { \
+ static struct lock_class_key __key; \
+ \
+ __init_rwsem((sem), #sem, &__key); \
+} while (0)
+
/*
* lock for reading
*/
void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*yield_task) (struct rq *rq);
+ bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_fork) (struct task_struct *p);
- void (*switched_from) (struct rq *this_rq, struct task_struct *task,
- int running);
- void (*switched_to) (struct rq *this_rq, struct task_struct *task,
- int running);
+ void (*switched_from) (struct rq *this_rq, struct task_struct *task);
+ void (*switched_to) (struct rq *this_rq, struct task_struct *task);
void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
- int oldprio, int running);
+ int oldprio);
unsigned int (*get_rr_interval) (struct rq *rq,
struct task_struct *task);
/*
* Per process flags
*/
-#define PF_KSOFTIRQD 0x00000001 /* I am ksoftirqd */
#define PF_STARTING 0x00000002 /* being created */
#define PF_EXITING 0x00000004 /* getting shut down */
#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
-#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezeable */
+#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */
#define PF_FREEZER_NOSIG 0x80000000 /* Freezer won't send signals to it */
/*
void __user *buffer, size_t *lenp,
loff_t *ppos);
-extern unsigned int sysctl_sched_compat_yield;
-
#ifdef CONFIG_SCHED_AUTOGROUP
extern unsigned int sysctl_sched_autogroup_enabled;
# define rt_mutex_adjust_pi(p) do { } while (0)
#endif
+extern bool yield_to(struct task_struct *p, bool preempt);
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
extern int task_nice(const struct task_struct *p);
#include <asm/current.h>
-extern void do_timer(unsigned long ticks);
+extern void xtime_update(unsigned long ticks);
extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
#define TASK_SIZE_OF(tsk) TASK_SIZE
#endif
-/*
- * Call the function if the target task is executing on a CPU right now:
- */
-extern void task_oncpu_function_call(struct task_struct *p,
- void (*func) (void *info), void *info);
-
-
#ifdef CONFIG_MM_OWNER
extern void mm_update_next_owner(struct mm_struct *mm);
extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
*/
extern int cap_capable(struct task_struct *tsk, const struct cred *cred,
int cap, int audit);
-extern int cap_settime(struct timespec *ts, struct timezone *tz);
+extern int cap_settime(const struct timespec *ts, const struct timezone *tz);
extern int cap_ptrace_access_check(struct task_struct *child, unsigned int mode);
extern int cap_ptrace_traceme(struct task_struct *parent);
extern int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
int (*quota_on) (struct dentry *dentry);
int (*syslog) (int type);
- int (*settime) (struct timespec *ts, struct timezone *tz);
+ int (*settime) (const struct timespec *ts, const struct timezone *tz);
int (*vm_enough_memory) (struct mm_struct *mm, long pages);
int (*bprm_set_creds) (struct linux_binprm *bprm);
const kernel_cap_t *effective,
const kernel_cap_t *inheritable,
const kernel_cap_t *permitted);
-int security_capable(int cap);
+int security_capable(const struct cred *cred, int cap);
int security_real_capable(struct task_struct *tsk, int cap);
int security_real_capable_noaudit(struct task_struct *tsk, int cap);
int security_sysctl(struct ctl_table *table, int op);
int security_quotactl(int cmds, int type, int id, struct super_block *sb);
int security_quota_on(struct dentry *dentry);
int security_syslog(int type);
-int security_settime(struct timespec *ts, struct timezone *tz);
+int security_settime(const struct timespec *ts, const struct timezone *tz);
int security_vm_enough_memory(long pages);
int security_vm_enough_memory_mm(struct mm_struct *mm, long pages);
int security_vm_enough_memory_kern(long pages);
return cap_capset(new, old, effective, inheritable, permitted);
}
-static inline int security_capable(int cap)
+static inline int security_capable(const struct cred *cred, int cap)
{
- return cap_capable(current, current_cred(), cap, SECURITY_CAP_AUDIT);
+ return cap_capable(current, cred, cap, SECURITY_CAP_AUDIT);
}
static inline int security_real_capable(struct task_struct *tsk, int cap)
return 0;
}
-static inline int security_settime(struct timespec *ts, struct timezone *tz)
+static inline int security_settime(const struct timespec *ts,
+ const struct timezone *tz)
{
return cap_settime(ts, tz);
}
#define __SPIN_LOCK_UNLOCKED(lockname) \
(spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
-/*
- * SPIN_LOCK_UNLOCKED defeats lockdep state tracking and is hence
- * deprecated.
- * Please use DEFINE_SPINLOCK() or __SPIN_LOCK_UNLOCKED() as
- * appropriate.
- */
-#define SPIN_LOCK_UNLOCKED __SPIN_LOCK_UNLOCKED(old_style_spin_init)
-
#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
#include <linux/rwlock_types.h>
struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
const struct rpc_call_ops *ops);
void rpc_put_task(struct rpc_task *);
+void rpc_put_task_async(struct rpc_task *);
void rpc_exit_task(struct rpc_task *);
void rpc_exit(struct rpc_task *, int);
void rpc_release_calldata(const struct rpc_call_ops *, void *);
struct getcpu_cache;
struct old_linux_dirent;
struct perf_event_attr;
+struct file_handle;
#include <linux/types.h>
#include <linux/aio_abi.h>
.class = &event_class_syscall_enter, \
.event.funcs = &enter_syscall_print_funcs, \
.data = (void *)&__syscall_meta_##sname,\
+ .flags = TRACE_EVENT_FL_CAP_ANY, \
}; \
static struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) \
- *__event_enter_##sname = &event_enter_##sname; \
- __TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
+ *__event_enter_##sname = &event_enter_##sname;
#define SYSCALL_TRACE_EXIT_EVENT(sname) \
static struct syscall_metadata __syscall_meta_##sname; \
.class = &event_class_syscall_exit, \
.event.funcs = &exit_syscall_print_funcs, \
.data = (void *)&__syscall_meta_##sname,\
+ .flags = TRACE_EVENT_FL_CAP_ANY, \
}; \
static struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) \
- *__event_exit_##sname = &event_exit_##sname; \
- __TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
+ *__event_exit_##sname = &event_exit_##sname;
#define SYSCALL_METADATA(sname, nb) \
SYSCALL_TRACE_ENTER_EVENT(sname); \
static struct syscall_metadata __used \
__syscall_meta_##sname = { \
.name = "sys"#sname, \
+ .syscall_nr = -1, /* Filled in at boot */ \
.nb_args = nb, \
.types = types_##sname, \
.args = args_##sname, \
static struct syscall_metadata __used \
__syscall_meta__##sname = { \
.name = "sys_"#sname, \
+ .syscall_nr = -1, /* Filled in at boot */ \
.nb_args = 0, \
.enter_event = &event_enter__##sname, \
.exit_event = &event_exit__##sname, \
const struct timespec __user *tp);
asmlinkage long sys_clock_gettime(clockid_t which_clock,
struct timespec __user *tp);
+asmlinkage long sys_clock_adjtime(clockid_t which_clock,
+ struct timex __user *tx);
asmlinkage long sys_clock_getres(clockid_t which_clock,
struct timespec __user *tp);
asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags,
unsigned long prot, unsigned long flags,
unsigned long fd, unsigned long pgoff);
asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
-
+asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
+ struct file_handle __user *handle,
+ int __user *mnt_id, int flag);
+asmlinkage long sys_open_by_handle_at(int mountdirfd,
+ struct file_handle __user *handle,
+ int flags);
#endif
#ifdef __KERNEL__
#include <linux/list.h>
+#include <linux/rcupdate.h>
/* For the /proc/sys support */
struct ctl_table;
struct ctl_table trees. */
struct ctl_table_header
{
- struct ctl_table *ctl_table;
- struct list_head ctl_entry;
- int used;
- int count;
+ union {
+ struct {
+ struct ctl_table *ctl_table;
+ struct list_head ctl_entry;
+ int used;
+ int count;
+ };
+ struct rcu_head rcu;
+ };
struct completion *unregistering;
struct ctl_table *ctl_table_arg;
struct ctl_table_root *root;
struct thermal_cooling_device *thermal_cooling_device_register(char *, void *,
const struct thermal_cooling_device_ops *);
void thermal_cooling_device_unregister(struct thermal_cooling_device *);
+
+#ifdef CONFIG_NET
extern int generate_netlink_event(u32 orig, enum events event);
+#else
+static inline int generate_netlink_event(u32 orig, enum events event)
+{
+ return 0;
+}
+#endif
#endif /* __THERMAL_H__ */
struct restart_block {
long (*fn)(struct restart_block *);
union {
- struct {
- unsigned long arg0, arg1, arg2, arg3;
- };
/* For futex_wait and futex_wait_requeue_pi */
struct {
u32 __user *uaddr;
#define timespec_valid(ts) \
(((ts)->tv_sec >= 0) && (((unsigned long) (ts)->tv_nsec) < NSEC_PER_SEC))
-extern seqlock_t xtime_lock;
-
extern void read_persistent_clock(struct timespec *ts);
extern void read_boot_clock(struct timespec *ts);
extern int update_persistent_clock(struct timespec now);
unsigned long get_seconds(void);
struct timespec current_kernel_time(void);
struct timespec __current_kernel_time(void); /* does not take xtime_lock */
-struct timespec __get_wall_to_monotonic(void); /* does not take xtime_lock */
struct timespec get_monotonic_coarse(void);
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+ struct timespec *wtom, struct timespec *sleep);
#define CURRENT_TIME (current_kernel_time())
#define CURRENT_TIME_SEC ((struct timespec) { get_seconds(), 0 })
#endif
extern void do_gettimeofday(struct timeval *tv);
-extern int do_settimeofday(struct timespec *tv);
-extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz);
+extern int do_settimeofday(const struct timespec *tv);
+extern int do_sys_settimeofday(const struct timespec *tv,
+ const struct timezone *tz);
#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags);
struct itimerval;
struct timespec *ts_real);
extern void getboottime(struct timespec *ts);
extern void monotonic_to_bootbased(struct timespec *ts);
+extern void get_monotonic_boottime(struct timespec *ts);
extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
extern int timekeeping_valid_for_hres(void);
extern u64 timekeeping_max_deferment(void);
-extern void update_wall_time(void);
extern void timekeeping_leap_insert(int leapsecond);
+extern int timekeeping_inject_offset(struct timespec *ts);
struct tms;
extern void do_sys_times(struct tms *);
#define CLOCK_MONOTONIC_RAW 4
#define CLOCK_REALTIME_COARSE 5
#define CLOCK_MONOTONIC_COARSE 6
+#define CLOCK_BOOTTIME 7
/*
* The IDs of various hardware clocks:
long tolerance; /* clock frequency tolerance (ppm)
* (read only)
*/
- struct timeval time; /* (read only) */
+ struct timeval time; /* (read only, except for ADJ_SETOFFSET) */
long tick; /* (modified) usecs between clock ticks */
long ppsfreq; /* pps frequency (scaled ppm) (ro) */
#define ADJ_STATUS 0x0010 /* clock status */
#define ADJ_TIMECONST 0x0020 /* pll time constant */
#define ADJ_TAI 0x0080 /* set TAI offset */
+#define ADJ_SETOFFSET 0x0100 /* add 'time' to current time */
#define ADJ_MICRO 0x1000 /* select microsecond resolution */
#define ADJ_NANO 0x2000 /* select nanosecond resolution */
#define ADJ_TICK 0x4000 /* tick value */
#define USB_CDC_COMM_FEATURE 0x01
#define USB_CDC_CAP_LINE 0x02
-#define USB_CDC_CAP_BRK 0x04
+#define USB_CDC_CAP_BRK 0x04
#define USB_CDC_CAP_NOTIFY 0x08
/* "Union Functional Descriptor" from CDC spec 5.2.3.8 */
__le16 wLength;
} __attribute__ ((packed));
+struct usb_cdc_speed_change {
+ __le32 DLBitRRate; /* contains the downlink bit rate (IN pipe) */
+ __le32 ULBitRate; /* contains the uplink bit rate (OUT pipe) */
+} __attribute__ ((packed));
+
/*-------------------------------------------------------------------------*/
/*
__le16 wNdpOutDivisor;
__le16 wNdpOutPayloadRemainder;
__le16 wNdpOutAlignment;
- __le16 wPadding2;
+ __le16 wNtbOutMaxDatagrams;
} __attribute__ ((packed));
/*
__le16 wHeaderLength;
__le16 wSequence;
__le16 wBlockLength;
- __le16 wFpIndex;
+ __le16 wNdpIndex;
} __attribute__ ((packed));
struct usb_cdc_ncm_nth32 {
__le16 wHeaderLength;
__le16 wSequence;
__le32 dwBlockLength;
- __le32 dwFpIndex;
+ __le32 dwNdpIndex;
} __attribute__ ((packed));
/*
struct usb_cdc_ncm_ndp16 {
__le32 dwSignature;
__le16 wLength;
- __le16 wNextFpIndex;
+ __le16 wNextNdpIndex;
struct usb_cdc_ncm_dpe16 dpe16[0];
} __attribute__ ((packed));
#define USB_CDC_NCM_NCAP_ENCAP_COMMAND (1 << 2)
#define USB_CDC_NCM_NCAP_MAX_DATAGRAM_SIZE (1 << 3)
#define USB_CDC_NCM_NCAP_CRC_MODE (1 << 4)
+#define USB_CDC_NCM_NCAP_NTB_INPUT_SIZE (1 << 5)
/* CDC NCM subclass Table 6-3: NTB Parameter Structure */
#define USB_CDC_NCM_NTB16_SUPPORTED (1 << 0)
#define USB_CDC_NCM_NTB_MIN_IN_SIZE 2048
#define USB_CDC_NCM_NTB_MIN_OUT_SIZE 2048
+/* NTB Input Size Structure */
+struct usb_cdc_ncm_ndp_input_size {
+ __le32 dwNtbInMaxSize;
+ __le16 wNtbInMaxDatagrams;
+ __le16 wReserved;
+} __attribute__ ((packed));
+
/* CDC NCM subclass 6.2.11 SetCrcMode */
#define USB_CDC_NCM_CRC_NOT_APPENDED 0x00
#define USB_CDC_NCM_CRC_APPENDED 0x01
#ifndef __LINUX_USB_GADGET_MSM72K_UDC_H__
#define __LINUX_USB_GADGET_MSM72K_UDC_H__
-#ifdef CONFIG_ARCH_MSM7X00A
-#define USB_SBUSCFG (MSM_USB_BASE + 0x0090)
-#else
#define USB_AHBBURST (MSM_USB_BASE + 0x0090)
#define USB_AHBMODE (MSM_USB_BASE + 0x0098)
-#endif
#define USB_CAPLENGTH (MSM_USB_BASE + 0x0100) /* 8 bit */
#define USB_USBCMD (MSM_USB_BASE + 0x0140)
* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
* anyone can use the definitions to implement compatible drivers/servers.
*
- * Copyright (C) Red Hat, Inc., 2009, 2010
+ * Copyright (C) Red Hat, Inc., 2009, 2010, 2011
+ * Copyright (C) Amit Shah <amit.shah@redhat.com>, 2009, 2010, 2011
*/
/* Feature bits */
enum {
WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */
WQ_UNBOUND = 1 << 1, /* not bound to any cpu */
- WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */
+ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */
WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */
WQ_HIGHPRI = 1 << 4, /* high priority */
WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */
/**
* alloc_ordered_workqueue - allocate an ordered workqueue
* @name: name of the workqueue
- * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_MEM_RECLAIM are meaningful)
+ * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
*
* Allocate an ordered workqueue. An ordered workqueue executes at
* most one work item at any given time in the queued order. They are
#define create_workqueue(name) \
alloc_workqueue((name), WQ_MEM_RECLAIM, 1)
-#define create_freezeable_workqueue(name) \
- alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
+#define create_freezable_workqueue(name) \
+ alloc_workqueue((name), WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
#define create_singlethread_workqueue(name) \
alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
#define IPV6_ADDR_SCOPE_ORGLOCAL 0x08
#define IPV6_ADDR_SCOPE_GLOBAL 0x0e
+/*
+ * Addr flags
+ */
+#ifdef __KERNEL__
+#define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \
+ ((a)->s6_addr[1] & 0x10)
+#define IPV6_ADDR_MC_FLAG_PREFIX(a) \
+ ((a)->s6_addr[1] & 0x20)
+#define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \
+ ((a)->s6_addr[1] & 0x40)
+#endif
+
/*
* fragmentation header
*/
}
#endif
-static inline void
-nf_tproxy_put_sock(struct sock *sk)
-{
- /* TIME_WAIT inet sockets have to be handled differently */
- if ((sk->sk_protocol == IPPROTO_TCP) && (sk->sk_state == TCP_TIME_WAIT))
- inet_twsk_put(inet_twsk(sk));
- else
- sock_put(sk);
-}
-
/* assign a socket to the skb -- consumes sk */
-int
+void
nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk);
#endif
struct qdisc_skb_cb {
unsigned int pkt_len;
- char data[];
+ long data[];
};
static inline int qdisc_qlen(struct Qdisc *q)
#define CONF_ENABLE_ESR 0x0008
#define CONF_ENABLE_IOCARD 0x0010 /* auto-enabled if IO resources or IRQ
* (CONF_ENABLE_IRQ) in use */
+#define CONF_ENABLE_ZVCARD 0x0020
/* flags used by pcmcia_loop_config() autoconfiguration */
#define CONF_AUTO_CHECK_VCC 0x0100 /* check for matching Vcc? */
/*
* R6 (0x06) - Mic Bias Control 0
*/
-#define WM8903_MICDET_HYST_ENA 0x0080 /* MICDET_HYST_ENA */
-#define WM8903_MICDET_HYST_ENA_MASK 0x0080 /* MICDET_HYST_ENA */
-#define WM8903_MICDET_HYST_ENA_SHIFT 7 /* MICDET_HYST_ENA */
-#define WM8903_MICDET_HYST_ENA_WIDTH 1 /* MICDET_HYST_ENA */
-#define WM8903_MICDET_THR_MASK 0x0070 /* MICDET_THR - [6:4] */
-#define WM8903_MICDET_THR_SHIFT 4 /* MICDET_THR - [6:4] */
-#define WM8903_MICDET_THR_WIDTH 3 /* MICDET_THR - [6:4] */
+#define WM8903_MICDET_THR_MASK 0x0030 /* MICDET_THR - [5:4] */
+#define WM8903_MICDET_THR_SHIFT 4 /* MICDET_THR - [5:4] */
+#define WM8903_MICDET_THR_WIDTH 2 /* MICDET_THR - [5:4] */
#define WM8903_MICSHORT_THR_MASK 0x000C /* MICSHORT_THR - [3:2] */
#define WM8903_MICSHORT_THR_SHIFT 2 /* MICSHORT_THR - [3:2] */
#define WM8903_MICSHORT_THR_WIDTH 2 /* MICSHORT_THR - [3:2] */
#include <scsi/scsi_cmnd.h>
#include <net/sock.h>
#include <net/tcp.h>
-#include "target_core_mib.h"
#define TARGET_CORE_MOD_VERSION "v4.0.0-rc6"
#define SHUTDOWN_SIGS (sigmask(SIGKILL)|sigmask(SIGINT)|sigmask(SIGABRT))
SAM_TASK_ATTR_EMULATED
} t10_task_attr_index_t;
+/*
+ * Used for target SCSI statistics
+ */
+typedef enum {
+ SCSI_INST_INDEX,
+ SCSI_DEVICE_INDEX,
+ SCSI_AUTH_INTR_INDEX,
+ SCSI_INDEX_TYPE_MAX
+} scsi_index_t;
+
+struct scsi_index_table {
+ spinlock_t lock;
+ u32 scsi_mib_index[SCSI_INDEX_TYPE_MAX];
+} ____cacheline_aligned;
+
struct se_cmd;
struct t10_alua {
spinlock_t stats_lock;
/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
atomic_t acl_pr_ref_count;
- /* Used for MIB access */
- atomic_t mib_ref_count;
struct se_dev_entry *device_list;
struct se_session *nacl_sess;
struct se_portal_group *se_tpg;
} ____cacheline_aligned;
struct se_session {
- /* Used for MIB access */
- atomic_t mib_ref_count;
u64 sess_bin_isid;
struct se_node_acl *se_node_acl;
struct se_portal_group *se_tpg;
/* Virtual iSCSI devices attached. */
u32 dev_count;
u32 hba_index;
- atomic_t dev_mib_access_count;
atomic_t load_balance_queue;
atomic_t left_queue_depth;
/* Maximum queue depth the HBA can handle. */
#define SE_LUN(c) ((struct se_lun *)(c)->se_lun)
+struct scsi_port_stats {
+ u64 cmd_pdus;
+ u64 tx_data_octets;
+ u64 rx_data_octets;
+} ____cacheline_aligned;
+
struct se_port {
/* RELATIVE TARGET PORT IDENTIFER */
u16 sep_rtpi;
} ____cacheline_aligned;
struct se_tpg_np {
+ struct se_portal_group *tpg_np_parent;
struct config_group tpg_np_group;
} ____cacheline_aligned;
extern int init_se_global(void);
extern void release_se_global(void);
+extern void init_scsi_index_table(void);
+extern u32 scsi_get_new_index(scsi_index_t);
extern void transport_init_queue_obj(struct se_queue_obj *);
extern int transport_subsystem_check_init(void);
extern int transport_subsystem_register(struct se_subsystem_api *);
extern void transport_add_task_to_execute_queue(struct se_task *,
struct se_task *,
struct se_device *);
+extern void transport_remove_task_from_execute_queue(struct se_task *,
+ struct se_device *);
unsigned char *transport_dump_cmd_direction(struct se_cmd *);
extern void transport_dump_dev_state(struct se_device *, char *, int *);
extern void transport_dump_dev_info(struct se_device *, struct se_lun *,
0 : blk_rq_sectors(rq);
__entry->errors = rq->errors;
- blk_fill_rwbs_rq(__entry->rwbs, rq);
+ blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
blk_dump_cmd(__get_str(cmd), rq);
),
__entry->bytes = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
blk_rq_bytes(rq) : 0;
- blk_fill_rwbs_rq(__entry->rwbs, rq);
+ blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
blk_dump_cmd(__get_str(cmd), rq);
memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
),
__entry->nr_sector = blk_rq_sectors(rq);
__entry->old_dev = dev;
__entry->old_sector = from;
- blk_fill_rwbs_rq(__entry->rwbs, rq);
+ blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
),
TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
TP_STRUCT__entry(
__field( u64, mcgcap )
__field( u64, mcgstatus )
- __field( u8, bank )
__field( u64, status )
__field( u64, addr )
__field( u64, misc )
__field( u64, ip )
- __field( u8, cs )
__field( u64, tsc )
__field( u64, walltime )
__field( u32, cpu )
__field( u32, cpuid )
__field( u32, apicid )
__field( u32, socketid )
+ __field( u8, cs )
+ __field( u8, bank )
__field( u8, cpuvendor )
),
TP_fast_assign(
__entry->mcgcap = m->mcgcap;
__entry->mcgstatus = m->mcgstatus;
- __entry->bank = m->bank;
__entry->status = m->status;
__entry->addr = m->addr;
__entry->misc = m->misc;
__entry->ip = m->ip;
- __entry->cs = m->cs;
__entry->tsc = m->tsc;
__entry->walltime = m->time;
__entry->cpu = m->extcpu;
__entry->cpuid = m->cpuid;
__entry->apicid = m->apicid;
__entry->socketid = m->socketid;
+ __entry->cs = m->cs;
+ __entry->bank = m->bank;
__entry->cpuvendor = m->cpuvendor;
),
TP_ARGS(name, wait, ip),
TP_STRUCT__entry(
- __field( bool, wait )
__field( unsigned long, ip )
+ __field( bool, wait )
__string( name, name )
),
TP_fast_assign(
- __entry->wait = wait;
__entry->ip = ip;
+ __entry->wait = wait;
__assign_str(name, name);
),
/* This part must be outside protection */
#include <trace/define_trace.h>
-
TP_STRUCT__entry(
__field( void *, skbaddr )
- __field( unsigned short, protocol )
__field( void *, location )
+ __field( unsigned short, protocol )
),
TP_fast_assign(
__entry->skbaddr = skb;
- __entry->protocol = ntohs(skb->protocol);
__entry->location = location;
+ __entry->protocol = ntohs(skb->protocol);
),
TP_printk("skbaddr=%p protocol=%u location=%p",
int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
#ifdef CONFIG_PCI_MSI
-/* Allocate an irq and a pirq to be used with MSIs. */
-#define XEN_ALLOC_PIRQ (1 << 0)
-#define XEN_ALLOC_IRQ (1 << 1)
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_mask);
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+ int pirq, int vector, const char *name);
#endif
/* De-allocates the above mentioned physical interrupt. */
*/
#define BLKIF_MAX_SEGMENTS_PER_REQUEST 11
-struct blkif_request {
- uint8_t operation; /* BLKIF_OP_??? */
- uint8_t nr_segments; /* number of segments */
- blkif_vdev_t handle; /* only for read/write requests */
- uint64_t id; /* private guest value, echoed in resp */
+struct blkif_request_rw {
blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */
struct blkif_request_segment {
grant_ref_t gref; /* reference to I/O buffer frame */
} seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
};
+struct blkif_request {
+ uint8_t operation; /* BLKIF_OP_??? */
+ uint8_t nr_segments; /* number of segments */
+ blkif_vdev_t handle; /* only for read/write requests */
+ uint64_t id; /* private guest value, echoed in resp */
+ union {
+ struct blkif_request_rw rw;
+ } u;
+};
+
struct blkif_response {
uint64_t id; /* copied from request */
uint8_t operation; /* copied from request */
#define VDISK_REMOVABLE 0x2
#define VDISK_READONLY 0x4
+/* Xen-defined major numbers for virtual disks, they look strangely
+ * familiar */
+#define XEN_IDE0_MAJOR 3
+#define XEN_IDE1_MAJOR 22
+#define XEN_SCSI_DISK0_MAJOR 8
+#define XEN_SCSI_DISK1_MAJOR 65
+#define XEN_SCSI_DISK2_MAJOR 66
+#define XEN_SCSI_DISK3_MAJOR 67
+#define XEN_SCSI_DISK4_MAJOR 68
+#define XEN_SCSI_DISK5_MAJOR 69
+#define XEN_SCSI_DISK6_MAJOR 70
+#define XEN_SCSI_DISK7_MAJOR 71
+#define XEN_SCSI_DISK8_MAJOR 128
+#define XEN_SCSI_DISK9_MAJOR 129
+#define XEN_SCSI_DISK10_MAJOR 130
+#define XEN_SCSI_DISK11_MAJOR 131
+#define XEN_SCSI_DISK12_MAJOR 132
+#define XEN_SCSI_DISK13_MAJOR 133
+#define XEN_SCSI_DISK14_MAJOR 134
+#define XEN_SCSI_DISK15_MAJOR 135
+
#endif /* __XEN_PUBLIC_IO_BLKIF_H__ */
#define __HYPERVISOR_stack_switch 3
#define __HYPERVISOR_set_callbacks 4
#define __HYPERVISOR_fpu_taskswitch 5
-#define __HYPERVISOR_sched_op 6
+#define __HYPERVISOR_sched_op_compat 6
#define __HYPERVISOR_dom0_op 7
#define __HYPERVISOR_set_debugreg 8
#define __HYPERVISOR_get_debugreg 9
#define __HYPERVISOR_mmuext_op 26
#define __HYPERVISOR_acm_op 27
#define __HYPERVISOR_nmi_op 28
-#define __HYPERVISOR_sched_op_new 29
+#define __HYPERVISOR_sched_op 29
#define __HYPERVISOR_callback_op 30
#define __HYPERVISOR_xenoprof_op 31
#define __HYPERVISOR_event_channel_op 32
DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
-void xen_pre_suspend(void);
-void xen_post_suspend(int suspend_cancelled);
-void xen_hvm_post_suspend(int suspend_cancelled);
+void xen_arch_pre_suspend(void);
+void xen_arch_post_suspend(int suspend_cancelled);
+void xen_arch_hvm_post_suspend(int suspend_cancelled);
void xen_mm_pin_all(void);
void xen_mm_unpin_all(void);
for processing it. A preliminary version of these tools is available
at <http://www.gnu.org/software/acct/>.
+config FHANDLE
+ bool "open by fhandle syscalls"
+ select EXPORTFS
+ help
+ If you say Y here, a user level program will be able to map
+ file names to handle and then later use the handle for
+ different file system operations. This is useful in implementing
+ userspace file servers, which now track files using handles instead
+ of names. The handle would remain the same even if file names
+ get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
+ syscalls.
+
config TASKSTATS
bool "Export task/process statistics through netlink (EXPERIMENTAL)"
depends on NET
select this option (if, for some reason, they need to disable it
then noswapaccount does the trick).
+config CGROUP_PERF
+ bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
+ depends on PERF_EVENTS && CGROUPS
+ help
+ This option extends the per-cpu mode to restrict monitoring to
+ threads which belong to the cgroup specified and run on the
+ designated cpu.
+
+ Say N if unsure.
+
menuconfig CGROUP_SCHED
bool "Group CPU scheduler"
depends on EXPERIMENTAL
pre_start = 0;
read_current_timer(&start);
start_jiffies = jiffies;
- while (jiffies <= (start_jiffies + 1)) {
+ while (time_before_eq(jiffies, start_jiffies + 1)) {
pre_start = start;
read_current_timer(&start);
}
pre_end = 0;
end = post_start;
- while (jiffies <=
- (start_jiffies + 1 + DELAY_CALIBRATION_TICKS)) {
+ while (time_before_eq(jiffies, start_jiffies + 1 +
+ DELAY_CALIBRATION_TICKS)) {
pre_end = end;
read_current_timer(&end);
}
}
/* Initialize a parent watch entry. */
-static struct audit_parent *audit_init_parent(struct nameidata *ndp)
+static struct audit_parent *audit_init_parent(struct path *path)
{
- struct inode *inode = ndp->path.dentry->d_inode;
+ struct inode *inode = path->dentry->d_inode;
struct audit_parent *parent;
int ret;
}
/* Get path information necessary for adding watches. */
-static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw)
+static int audit_get_nd(struct audit_watch *watch, struct path *parent)
{
- struct nameidata *ndparent, *ndwatch;
+ struct nameidata nd;
+ struct dentry *d;
int err;
- ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL);
- if (unlikely(!ndparent))
- return -ENOMEM;
+ err = kern_path_parent(watch->path, &nd);
+ if (err)
+ return err;
- ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL);
- if (unlikely(!ndwatch)) {
- kfree(ndparent);
- return -ENOMEM;
+ if (nd.last_type != LAST_NORM) {
+ path_put(&nd.path);
+ return -EINVAL;
}
- err = path_lookup(path, LOOKUP_PARENT, ndparent);
- if (err) {
- kfree(ndparent);
- kfree(ndwatch);
- return err;
+ mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+ if (IS_ERR(d)) {
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ path_put(&nd.path);
+ return PTR_ERR(d);
}
-
- err = path_lookup(path, 0, ndwatch);
- if (err) {
- kfree(ndwatch);
- ndwatch = NULL;
+ if (d->d_inode) {
+ /* update watch filter fields */
+ watch->dev = d->d_inode->i_sb->s_dev;
+ watch->ino = d->d_inode->i_ino;
}
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
- *ndp = ndparent;
- *ndw = ndwatch;
-
+ *parent = nd.path;
+ dput(d);
return 0;
}
-/* Release resources used for watch path information. */
-static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw)
-{
- if (ndp) {
- path_put(&ndp->path);
- kfree(ndp);
- }
- if (ndw) {
- path_put(&ndw->path);
- kfree(ndw);
- }
-}
-
/* Associate the given rule with an existing parent.
* Caller must hold audit_filter_mutex. */
static void audit_add_to_parent(struct audit_krule *krule,
{
struct audit_watch *watch = krule->watch;
struct audit_parent *parent;
- struct nameidata *ndp = NULL, *ndw = NULL;
+ struct path parent_path;
int h, ret = 0;
mutex_unlock(&audit_filter_mutex);
/* Avoid calling path_lookup under audit_filter_mutex. */
- ret = audit_get_nd(watch->path, &ndp, &ndw);
- if (ret) {
- /* caller expects mutex locked */
- mutex_lock(&audit_filter_mutex);
- goto error;
- }
+ ret = audit_get_nd(watch, &parent_path);
+ /* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
- /* update watch filter fields */
- if (ndw) {
- watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev;
- watch->ino = ndw->path.dentry->d_inode->i_ino;
- }
+ if (ret)
+ return ret;
/* either find an old parent or attach a new one */
- parent = audit_find_parent(ndp->path.dentry->d_inode);
+ parent = audit_find_parent(parent_path.dentry->d_inode);
if (!parent) {
- parent = audit_init_parent(ndp);
+ parent = audit_init_parent(&parent_path);
if (IS_ERR(parent)) {
ret = PTR_ERR(parent);
goto error;
h = audit_hash_ino((u32)watch->ino);
*list = &audit_inode_hash[h];
error:
- audit_put_nd(ndp, ndw); /* NULL args OK */
+ path_put(&parent_path);
return ret;
-
}
void audit_remove_watch_rule(struct audit_krule *krule)
BUG();
}
- if (security_capable(cap) == 0) {
+ if (security_capable(current_cred(), cap) == 0) {
current->flags |= PF_SUPERPRIV;
return 1;
}
*/
void cgroup_exit(struct task_struct *tsk, int run_callbacks)
{
- int i;
struct css_set *cg;
-
- if (run_callbacks && need_forkexit_callback) {
- /*
- * modular subsystems can't use callbacks, so no need to lock
- * the subsys array
- */
- for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
- struct cgroup_subsys *ss = subsys[i];
- if (ss->exit)
- ss->exit(ss, tsk);
- }
- }
+ int i;
/*
* Unlink from the css_set task list if necessary.
task_lock(tsk);
cg = tsk->cgroups;
tsk->cgroups = &init_css_set;
+
+ if (run_callbacks && need_forkexit_callback) {
+ /*
+ * modular subsystems can't use callbacks, so no need to lock
+ * the subsys array
+ */
+ for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->exit) {
+ struct cgroup *old_cgrp =
+ rcu_dereference_raw(cg->subsys[i])->cgroup;
+ struct cgroup *cgrp = task_cgroup(tsk, i);
+ ss->exit(ss, cgrp, old_cgrp, tsk);
+ }
+ }
+ }
task_unlock(tsk);
+
if (cg)
put_css_set_taskexit(cg);
}
return ret;
}
+/*
+ * get corresponding css from file open on cgroupfs directory
+ */
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
+{
+ struct cgroup *cgrp;
+ struct inode *inode;
+ struct cgroup_subsys_state *css;
+
+ inode = f->f_dentry->d_inode;
+ /* check in cgroup filesystem dir */
+ if (inode->i_op != &cgroup_dir_inode_operations)
+ return ERR_PTR(-EBADF);
+
+ if (id < 0 || id >= CGROUP_SUBSYS_COUNT)
+ return ERR_PTR(-EINVAL);
+
+ /* get cgroup */
+ cgrp = __d_cgrp(f->f_dentry);
+ css = cgrp->subsys[id];
+ return css ? css : ERR_PTR(-ENOENT);
+}
+
#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
struct cgroup *cont)
put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
}
+static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp)
+{
+ memset(txc, 0, sizeof(struct timex));
+
+ if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) ||
+ __get_user(txc->modes, &utp->modes) ||
+ __get_user(txc->offset, &utp->offset) ||
+ __get_user(txc->freq, &utp->freq) ||
+ __get_user(txc->maxerror, &utp->maxerror) ||
+ __get_user(txc->esterror, &utp->esterror) ||
+ __get_user(txc->status, &utp->status) ||
+ __get_user(txc->constant, &utp->constant) ||
+ __get_user(txc->precision, &utp->precision) ||
+ __get_user(txc->tolerance, &utp->tolerance) ||
+ __get_user(txc->time.tv_sec, &utp->time.tv_sec) ||
+ __get_user(txc->time.tv_usec, &utp->time.tv_usec) ||
+ __get_user(txc->tick, &utp->tick) ||
+ __get_user(txc->ppsfreq, &utp->ppsfreq) ||
+ __get_user(txc->jitter, &utp->jitter) ||
+ __get_user(txc->shift, &utp->shift) ||
+ __get_user(txc->stabil, &utp->stabil) ||
+ __get_user(txc->jitcnt, &utp->jitcnt) ||
+ __get_user(txc->calcnt, &utp->calcnt) ||
+ __get_user(txc->errcnt, &utp->errcnt) ||
+ __get_user(txc->stbcnt, &utp->stbcnt))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc)
+{
+ if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) ||
+ __put_user(txc->modes, &utp->modes) ||
+ __put_user(txc->offset, &utp->offset) ||
+ __put_user(txc->freq, &utp->freq) ||
+ __put_user(txc->maxerror, &utp->maxerror) ||
+ __put_user(txc->esterror, &utp->esterror) ||
+ __put_user(txc->status, &utp->status) ||
+ __put_user(txc->constant, &utp->constant) ||
+ __put_user(txc->precision, &utp->precision) ||
+ __put_user(txc->tolerance, &utp->tolerance) ||
+ __put_user(txc->time.tv_sec, &utp->time.tv_sec) ||
+ __put_user(txc->time.tv_usec, &utp->time.tv_usec) ||
+ __put_user(txc->tick, &utp->tick) ||
+ __put_user(txc->ppsfreq, &utp->ppsfreq) ||
+ __put_user(txc->jitter, &utp->jitter) ||
+ __put_user(txc->shift, &utp->shift) ||
+ __put_user(txc->stabil, &utp->stabil) ||
+ __put_user(txc->jitcnt, &utp->jitcnt) ||
+ __put_user(txc->calcnt, &utp->calcnt) ||
+ __put_user(txc->errcnt, &utp->errcnt) ||
+ __put_user(txc->stbcnt, &utp->stbcnt) ||
+ __put_user(txc->tai, &utp->tai))
+ return -EFAULT;
+ return 0;
+}
+
asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
struct timezone __user *tz)
{
return err;
}
+long compat_sys_clock_adjtime(clockid_t which_clock,
+ struct compat_timex __user *utp)
+{
+ struct timex txc;
+ mm_segment_t oldfs;
+ int err, ret;
+
+ err = compat_get_timex(&txc, utp);
+ if (err)
+ return err;
+
+ oldfs = get_fs();
+ set_fs(KERNEL_DS);
+ ret = sys_clock_adjtime(which_clock, (struct timex __user *) &txc);
+ set_fs(oldfs);
+
+ err = compat_put_timex(utp, &txc);
+ if (err)
+ return err;
+
+ return ret;
+}
+
long compat_sys_clock_getres(clockid_t which_clock,
struct compat_timespec __user *tp)
{
asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
{
struct timex txc;
- int ret;
-
- memset(&txc, 0, sizeof(struct timex));
+ int err, ret;
- if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) ||
- __get_user(txc.modes, &utp->modes) ||
- __get_user(txc.offset, &utp->offset) ||
- __get_user(txc.freq, &utp->freq) ||
- __get_user(txc.maxerror, &utp->maxerror) ||
- __get_user(txc.esterror, &utp->esterror) ||
- __get_user(txc.status, &utp->status) ||
- __get_user(txc.constant, &utp->constant) ||
- __get_user(txc.precision, &utp->precision) ||
- __get_user(txc.tolerance, &utp->tolerance) ||
- __get_user(txc.time.tv_sec, &utp->time.tv_sec) ||
- __get_user(txc.time.tv_usec, &utp->time.tv_usec) ||
- __get_user(txc.tick, &utp->tick) ||
- __get_user(txc.ppsfreq, &utp->ppsfreq) ||
- __get_user(txc.jitter, &utp->jitter) ||
- __get_user(txc.shift, &utp->shift) ||
- __get_user(txc.stabil, &utp->stabil) ||
- __get_user(txc.jitcnt, &utp->jitcnt) ||
- __get_user(txc.calcnt, &utp->calcnt) ||
- __get_user(txc.errcnt, &utp->errcnt) ||
- __get_user(txc.stbcnt, &utp->stbcnt))
- return -EFAULT;
+ err = compat_get_timex(&txc, utp);
+ if (err)
+ return err;
ret = do_adjtimex(&txc);
- if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) ||
- __put_user(txc.modes, &utp->modes) ||
- __put_user(txc.offset, &utp->offset) ||
- __put_user(txc.freq, &utp->freq) ||
- __put_user(txc.maxerror, &utp->maxerror) ||
- __put_user(txc.esterror, &utp->esterror) ||
- __put_user(txc.status, &utp->status) ||
- __put_user(txc.constant, &utp->constant) ||
- __put_user(txc.precision, &utp->precision) ||
- __put_user(txc.tolerance, &utp->tolerance) ||
- __put_user(txc.time.tv_sec, &utp->time.tv_sec) ||
- __put_user(txc.time.tv_usec, &utp->time.tv_usec) ||
- __put_user(txc.tick, &utp->tick) ||
- __put_user(txc.ppsfreq, &utp->ppsfreq) ||
- __put_user(txc.jitter, &utp->jitter) ||
- __put_user(txc.shift, &utp->shift) ||
- __put_user(txc.stabil, &utp->stabil) ||
- __put_user(txc.jitcnt, &utp->jitcnt) ||
- __put_user(txc.calcnt, &utp->calcnt) ||
- __put_user(txc.errcnt, &utp->errcnt) ||
- __put_user(txc.stbcnt, &utp->stbcnt) ||
- __put_user(txc.tai, &utp->tai))
- ret = -EFAULT;
+ err = compat_put_timex(utp, &txc);
+ if (err)
+ return err;
return ret;
}
return -ENODEV;
trialcs = alloc_trial_cpuset(cs);
- if (!trialcs)
- return -ENOMEM;
+ if (!trialcs) {
+ retval = -ENOMEM;
+ goto out;
+ }
switch (cft->private) {
case FILE_CPULIST:
}
free_trial_cpuset(trialcs);
+out:
cgroup_unlock();
return retval;
}
static struct thread_group_cred init_tgcred = {
.usage = ATOMIC_INIT(2),
.tgid = 0,
- .lock = SPIN_LOCK_UNLOCKED,
+ .lock = __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock),
};
#endif
return NULL;
}
-static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
+static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
+ u32 uval, u32 newval)
{
- u32 curval;
+ int ret;
pagefault_disable();
- curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
+ ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
pagefault_enable();
- return curval;
+ return ret;
}
static int get_futex_value_locked(u32 *dest, u32 __user *from)
struct task_struct *task, int set_waiters)
{
int lock_taken, ret, ownerdied = 0;
- u32 uval, newval, curval;
+ u32 uval, newval, curval, vpid = task_pid_vnr(task);
retry:
ret = lock_taken = 0;
* (by doing a 0 -> TID atomic cmpxchg), while holding all
* the locks. It will most likely not succeed.
*/
- newval = task_pid_vnr(task);
+ newval = vpid;
if (set_waiters)
newval |= FUTEX_WAITERS;
- curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
- if (unlikely(curval == -EFAULT))
+ if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
return -EFAULT;
/*
* Detect deadlocks.
*/
- if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+ if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
return -EDEADLK;
/*
*/
if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
/* Keep the OWNER_DIED bit */
- newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+ newval = (curval & ~FUTEX_TID_MASK) | vpid;
ownerdied = 0;
lock_taken = 1;
}
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (unlikely(curval == -EFAULT))
+ if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
return -EFAULT;
if (unlikely(curval != uval))
goto retry;
return ret;
}
+/**
+ * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket
+ * @q: The futex_q to unqueue
+ *
+ * The q->lock_ptr must not be NULL and must be held by the caller.
+ */
+static void __unqueue_futex(struct futex_q *q)
+{
+ struct futex_hash_bucket *hb;
+
+ if (WARN_ON(!q->lock_ptr || !spin_is_locked(q->lock_ptr)
+ || plist_node_empty(&q->list)))
+ return;
+
+ hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
+ plist_del(&q->list, &hb->chain);
+}
+
/*
* The hash bucket lock must be held when this is called.
* Afterwards, the futex_q must not be accessed.
*/
get_task_struct(p);
- plist_del(&q->list, &q->list.plist);
+ __unqueue_futex(q);
/*
* The waiting task can free the futex_q as soon as
* q->lock_ptr = NULL is written, without taking any locks. A
newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
ret = -EFAULT;
else if (curval != uval)
ret = -EINVAL;
* There is no waiter, so we unlock the futex. The owner died
* bit has not to be preserved here. We are the owner:
*/
- oldval = cmpxchg_futex_value_locked(uaddr, uval, 0);
-
- if (oldval == -EFAULT)
- return oldval;
+ if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
+ return -EFAULT;
if (oldval != uval)
return -EAGAIN;
plist_del(&q->list, &hb1->chain);
plist_add(&q->list, &hb2->chain);
q->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.spinlock = &hb2->lock;
-#endif
}
get_futex_key_refs(key2);
q->key = *key2;
get_futex_key_refs(key);
q->key = *key;
- WARN_ON(plist_node_empty(&q->list));
- plist_del(&q->list, &q->list.plist);
+ __unqueue_futex(q);
WARN_ON(!q->rt_waiter);
q->rt_waiter = NULL;
q->lock_ptr = &hb->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.spinlock = &hb->lock;
-#endif
wake_up_state(q->task, TASK_NORMAL);
}
prio = min(current->normal_prio, MAX_RT_PRIO);
plist_node_init(&q->list, prio);
-#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.spinlock = &hb->lock;
-#endif
plist_add(&q->list, &hb->chain);
q->task = current;
spin_unlock(&hb->lock);
spin_unlock(lock_ptr);
goto retry;
}
- WARN_ON(plist_node_empty(&q->list));
- plist_del(&q->list, &q->list.plist);
+ __unqueue_futex(q);
BUG_ON(q->pi_state);
static void unqueue_me_pi(struct futex_q *q)
__releases(q->lock_ptr)
{
- WARN_ON(plist_node_empty(&q->list));
- plist_del(&q->list, &q->list.plist);
+ __unqueue_futex(q);
BUG_ON(!q->pi_state);
free_pi_state(q->pi_state);
/*
* We are here either because we stole the rtmutex from the
- * pending owner or we are the pending owner which failed to
- * get the rtmutex. We have to replace the pending owner TID
- * in the user space variable. This must be atomic as we have
- * to preserve the owner died bit here.
+ * previous highest priority waiter or we are the highest priority
+ * waiter but failed to get the rtmutex the first time.
+ * We have to replace the newowner TID in the user space variable.
+ * This must be atomic as we have to preserve the owner died bit here.
*
* Note: We write the user space value _before_ changing the pi_state
* because we can fault here. Imagine swapped out pages or a fork
while (1) {
newval = (uval & FUTEX_OWNER_DIED) | newtid;
- curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
goto handle_fault;
if (curval == uval)
break;
/*
* To handle the page fault we need to drop the hash bucket
- * lock here. That gives the other task (either the pending
- * owner itself or the task which stole the rtmutex) the
+ * lock here. That gives the other task (either the highest priority
+ * waiter itself or the task which stole the rtmutex) the
* chance to try the fixup of the pi_state. So once we are
* back from handling the fault we need to check the pi_state
* after reacquiring the hash bucket lock and before trying to
/*
* pi_state is incorrect, some other task did a lock steal and
* we returned due to timeout or signal without taking the
- * rt_mutex. Too late. We can access the rt_mutex_owner without
- * locking, as the other task is now blocked on the hash bucket
- * lock. Fix the state up.
+ * rt_mutex. Too late.
*/
+ raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+ if (!owner)
+ owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
+ raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
ret = fixup_pi_state_owner(uaddr, q, owner);
goto out;
}
/*
* Paranoia check. If we did not take the lock, then we should not be
- * the owner, nor the pending owner, of the rt_mutex.
+ * the owner of the rt_mutex.
*/
if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
*
* The basic logical guarantee of a futex is that it blocks ONLY
* if cond(var) is known to be true at the time of blocking, for
- * any cond. If we queued after testing *uaddr, that would open
- * a race condition where we could block indefinitely with
+ * any cond. If we locked the hash-bucket after testing *uaddr, that
+ * would open a race condition where we could block indefinitely with
* cond(var) false, which would violate the guarantee.
*
- * A consequence is that futex_wait() can return zero and absorb
- * a wakeup when *uaddr != val on entry to the syscall. This is
- * rare, but normal.
+ * On the other hand, we insert q and release the hash-bucket only
+ * after testing *uaddr. This guarantees that futex_wait() will NOT
+ * absorb a wakeup if *uaddr does not match the desired values
+ * while the syscall executes.
*/
retry:
ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- u32 uval;
struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
+ u32 uval, vpid = task_pid_vnr(current);
int ret;
retry:
/*
* We release only a lock we actually own:
*/
- if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
+ if ((uval & FUTEX_TID_MASK) != vpid)
return -EPERM;
ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
* again. If it succeeds then we can return without waking
* anyone else up:
*/
- if (!(uval & FUTEX_OWNER_DIED))
- uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0);
-
-
- if (unlikely(uval == -EFAULT))
+ if (!(uval & FUTEX_OWNER_DIED) &&
+ cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
goto pi_faulted;
/*
* Rare case: we managed to release the lock atomically,
* no need to wake anyone else up:
*/
- if (unlikely(uval == task_pid_vnr(current)))
+ if (unlikely(uval == vpid))
goto out_unlock;
/*
* We were woken prior to requeue by a timeout or a signal.
* Unqueue the futex_q and determine which it was.
*/
- plist_del(&q->list, &q->list.plist);
+ plist_del(&q->list, &hb->chain);
/* Handle spurious wakeups gracefully */
ret = -EWOULDBLOCK;
* userspace.
*/
mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
- nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval);
-
- if (nval == -EFAULT)
- return -1;
-
+ /*
+ * We are not holding a lock here, but we want to have
+ * the pagefault_disable/enable() protection because
+ * we want to handle the fault gracefully. If the
+ * access fails we try to fault in the futex with R/W
+ * verification via get_user_pages. get_user() above
+ * does not guarantee R/W access. If that fails we
+ * give up and leave the futex locked.
+ */
+ if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+ if (fault_in_user_writeable(uaddr))
+ return -1;
+ goto retry;
+ }
if (nval != uval)
goto retry;
* implementation, the non-functional ones will return
* -ENOSYS.
*/
- curval = cmpxchg_futex_value_locked(NULL, 0, 0);
- if (curval == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
futex_cmpxchg_enabled = 1;
for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
/*
* The timer bases:
*
- * Note: If we want to add new timer bases, we have to skip the two
- * clock ids captured by the cpu-timers. We do this by holding empty
- * entries rather than doing math adjustment of the clock ids.
- * This ensures that we capture erroneous accesses to these clock ids
- * rather than moving them into the range of valid clock id's.
+ * There are more clockids then hrtimer bases. Thus, we index
+ * into the timer bases by the hrtimer_base_type enum. When trying
+ * to reach a base using a clockid, hrtimer_clockid_to_base()
+ * is used to convert from clockid to the proper hrtimer_base_type.
*/
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
.get_time = &ktime_get,
.resolution = KTIME_LOW_RES,
},
+ {
+ .index = CLOCK_BOOTTIME,
+ .get_time = &ktime_get_boottime,
+ .resolution = KTIME_LOW_RES,
+ },
}
};
+static int hrtimer_clock_to_base_table[MAX_CLOCKS];
+
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+ 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, tomono;
- struct timespec xts, tom;
- unsigned long seq;
+ ktime_t xtim, mono, boot;
+ struct timespec xts, tom, slp;
- do {
- seq = read_seqbegin(&xtime_lock);
- xts = __current_kernel_time();
- tom = __get_wall_to_monotonic();
- } while (read_seqretry(&xtime_lock, seq));
+ get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
xtim = timespec_to_ktime(xts);
- tomono = timespec_to_ktime(tom);
- base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
- base->clock_base[CLOCK_MONOTONIC].softirq_time =
- ktime_add(xtim, tomono);
+ mono = ktime_add(xtim, timespec_to_ktime(tom));
+ boot = ktime_add(mono, timespec_to_ktime(slp));
+ 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;
}
/*
struct hrtimer_cpu_base *new_cpu_base;
int this_cpu = smp_processor_id();
int cpu = hrtimer_get_target(this_cpu, pinned);
+ int basenum = hrtimer_clockid_to_base(base->index);
again:
new_cpu_base = &per_cpu(hrtimer_bases, cpu);
- new_base = &new_cpu_base->clock_base[base->index];
+ new_base = &new_cpu_base->clock_base[basenum];
if (base != new_base) {
/*
static struct debug_obj_descr hrtimer_debug_descr;
+static void *hrtimer_debug_hint(void *addr)
+{
+ return ((struct hrtimer *) addr)->function;
+}
+
/*
* fixup_init is called when:
* - an active object is initialized
static struct debug_obj_descr hrtimer_debug_descr = {
.name = "hrtimer",
+ .debug_hint = hrtimer_debug_hint,
.fixup_init = hrtimer_fixup_init,
.fixup_activate = hrtimer_fixup_activate,
.fixup_free = hrtimer_fixup_free,
static void retrigger_next_event(void *arg)
{
struct hrtimer_cpu_base *base;
- struct timespec realtime_offset, wtm;
- unsigned long seq;
+ struct timespec realtime_offset, wtm, sleep;
if (!hrtimer_hres_active())
return;
- do {
- seq = read_seqbegin(&xtime_lock);
- wtm = __get_wall_to_monotonic();
- } while (read_seqretry(&xtime_lock, seq));
+ get_xtime_and_monotonic_and_sleep_offset(&realtime_offset, &wtm,
+ &sleep);
set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
base = &__get_cpu_var(hrtimer_bases);
/* Adjust CLOCK_REALTIME offset */
raw_spin_lock(&base->lock);
- base->clock_base[CLOCK_REALTIME].offset =
+ base->clock_base[HRTIMER_BASE_REALTIME].offset =
timespec_to_ktime(realtime_offset);
+ base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
+ timespec_to_ktime(sleep);
hrtimer_force_reprogram(base, 0);
raw_spin_unlock(&base->lock);
base->hres_active = 0;
}
-/*
- * Initialize the high resolution related parts of a hrtimer
- */
-static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
-{
-}
-
-
/*
* When High resolution timers are active, try to reprogram. Note, that in case
* the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
return 0;
}
base->hres_active = 1;
- base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
- base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+ base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES;
+ base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES;
+ base->clock_base[HRTIMER_BASE_BOOTTIME].resolution = KTIME_HIGH_RES;
tick_setup_sched_timer();
return 0;
}
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
-static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
#endif /* CONFIG_HIGH_RES_TIMERS */
enum hrtimer_mode mode)
{
struct hrtimer_cpu_base *cpu_base;
+ int base;
memset(timer, 0, sizeof(struct hrtimer));
if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
clock_id = CLOCK_MONOTONIC;
- timer->base = &cpu_base->clock_base[clock_id];
- hrtimer_init_timer_hres(timer);
+ base = hrtimer_clockid_to_base(clock_id);
+ timer->base = &cpu_base->clock_base[base];
timerqueue_init(&timer->node);
#ifdef CONFIG_TIMER_STATS
int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
{
struct hrtimer_cpu_base *cpu_base;
+ int base = hrtimer_clockid_to_base(which_clock);
cpu_base = &__raw_get_cpu_var(hrtimer_bases);
- *tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
+ *tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
return 0;
}
void __init hrtimers_init(void)
{
+ hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
+ hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
+ hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME;
+
hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
+# Select this to activate the generic irq options below
config HAVE_GENERIC_HARDIRQS
- def_bool n
+ bool
if HAVE_GENERIC_HARDIRQS
menu "IRQ subsystem"
# Select this to disable the deprecated stuff
config GENERIC_HARDIRQS_NO_DEPRECATED
- def_bool n
+ bool
+
+config GENERIC_HARDIRQS_NO_COMPAT
+ bool
# Options selectable by the architecture code
+
+# Make sparse irq Kconfig switch below available
config HAVE_SPARSE_IRQ
- def_bool n
+ bool
+# Enable the generic irq autoprobe mechanism
config GENERIC_IRQ_PROBE
- def_bool n
+ bool
+
+# Use the generic /proc/interrupts implementation
+config GENERIC_IRQ_SHOW
+ bool
+# Support for delayed migration from interrupt context
config GENERIC_PENDING_IRQ
- def_bool n
+ bool
+# Alpha specific irq affinity mechanism
config AUTO_IRQ_AFFINITY
- def_bool n
-
-config IRQ_PER_CPU
- def_bool n
+ bool
+# Tasklet based software resend for pending interrupts on enable_irq()
config HARDIRQS_SW_RESEND
- def_bool n
+ bool
+
+# Preflow handler support for fasteoi (sparc64)
+config IRQ_PREFLOW_FASTEOI
+ bool
+
+# Support forced irq threading
+config IRQ_FORCED_THREADING
+ bool
config SPARSE_IRQ
bool "Support sparse irq numbering"
/*
* Autodetection depends on the fact that any interrupt that
* comes in on to an unassigned handler will get stuck with
- * "IRQ_WAITING" cleared and the interrupt disabled.
+ * "IRQS_WAITING" cleared and the interrupt disabled.
*/
static DEFINE_MUTEX(probing_active);
{
struct irq_desc *desc;
unsigned long mask = 0;
- unsigned int status;
int i;
/*
*/
for_each_irq_desc_reverse(i, desc) {
raw_spin_lock_irq(&desc->lock);
- if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
- /*
- * An old-style architecture might still have
- * the handle_bad_irq handler there:
- */
- compat_irq_chip_set_default_handler(desc);
-
+ if (!desc->action && irq_settings_can_probe(desc)) {
/*
* Some chips need to know about probing in
* progress:
if (desc->irq_data.chip->irq_set_type)
desc->irq_data.chip->irq_set_type(&desc->irq_data,
IRQ_TYPE_PROBE);
- desc->irq_data.chip->irq_startup(&desc->irq_data);
+ irq_startup(desc);
}
raw_spin_unlock_irq(&desc->lock);
}
*/
for_each_irq_desc_reverse(i, desc) {
raw_spin_lock_irq(&desc->lock);
- if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
- desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
- if (desc->irq_data.chip->irq_startup(&desc->irq_data))
- desc->status |= IRQ_PENDING;
+ if (!desc->action && irq_settings_can_probe(desc)) {
+ desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
+ if (irq_startup(desc)) {
+ irq_compat_set_pending(desc);
+ desc->istate |= IRQS_PENDING;
+ }
}
raw_spin_unlock_irq(&desc->lock);
}
*/
for_each_irq_desc(i, desc) {
raw_spin_lock_irq(&desc->lock);
- status = desc->status;
- if (status & IRQ_AUTODETECT) {
+ if (desc->istate & IRQS_AUTODETECT) {
/* It triggered already - consider it spurious. */
- if (!(status & IRQ_WAITING)) {
- desc->status = status & ~IRQ_AUTODETECT;
- desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+ if (!(desc->istate & IRQS_WAITING)) {
+ desc->istate &= ~IRQS_AUTODETECT;
+ irq_shutdown(desc);
} else
if (i < 32)
mask |= 1 << i;
*/
unsigned int probe_irq_mask(unsigned long val)
{
- unsigned int status, mask = 0;
+ unsigned int mask = 0;
struct irq_desc *desc;
int i;
for_each_irq_desc(i, desc) {
raw_spin_lock_irq(&desc->lock);
- status = desc->status;
-
- if (status & IRQ_AUTODETECT) {
- if (i < 16 && !(status & IRQ_WAITING))
+ if (desc->istate & IRQS_AUTODETECT) {
+ if (i < 16 && !(desc->istate & IRQS_WAITING))
mask |= 1 << i;
- desc->status = status & ~IRQ_AUTODETECT;
- desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+ desc->istate &= ~IRQS_AUTODETECT;
+ irq_shutdown(desc);
}
raw_spin_unlock_irq(&desc->lock);
}
{
int i, irq_found = 0, nr_of_irqs = 0;
struct irq_desc *desc;
- unsigned int status;
for_each_irq_desc(i, desc) {
raw_spin_lock_irq(&desc->lock);
- status = desc->status;
- if (status & IRQ_AUTODETECT) {
- if (!(status & IRQ_WAITING)) {
+ if (desc->istate & IRQS_AUTODETECT) {
+ if (!(desc->istate & IRQS_WAITING)) {
if (!nr_of_irqs)
irq_found = i;
nr_of_irqs++;
}
- desc->status = status & ~IRQ_AUTODETECT;
- desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+ desc->istate &= ~IRQS_AUTODETECT;
+ irq_shutdown(desc);
}
raw_spin_unlock_irq(&desc->lock);
}
#include "internals.h"
/**
- * set_irq_chip - set the irq chip for an irq
+ * irq_set_chip - set the irq chip for an irq
* @irq: irq number
* @chip: pointer to irq chip description structure
*/
-int set_irq_chip(unsigned int irq, struct irq_chip *chip)
+int irq_set_chip(unsigned int irq, struct irq_chip *chip)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
- if (!desc) {
- WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
+ if (!desc)
return -EINVAL;
- }
if (!chip)
chip = &no_irq_chip;
- raw_spin_lock_irqsave(&desc->lock, flags);
irq_chip_set_defaults(chip);
desc->irq_data.chip = chip;
- raw_spin_unlock_irqrestore(&desc->lock, flags);
-
+ irq_put_desc_unlock(desc, flags);
return 0;
}
-EXPORT_SYMBOL(set_irq_chip);
+EXPORT_SYMBOL(irq_set_chip);
/**
- * set_irq_type - set the irq trigger type for an irq
+ * irq_set_type - set the irq trigger type for an irq
* @irq: irq number
* @type: IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
*/
-int set_irq_type(unsigned int irq, unsigned int type)
+int irq_set_irq_type(unsigned int irq, unsigned int type)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
- int ret = -ENXIO;
+ struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+ int ret = 0;
- if (!desc) {
- printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq);
- return -ENODEV;
- }
+ if (!desc)
+ return -EINVAL;
type &= IRQ_TYPE_SENSE_MASK;
- if (type == IRQ_TYPE_NONE)
- return 0;
-
- raw_spin_lock_irqsave(&desc->lock, flags);
- ret = __irq_set_trigger(desc, irq, type);
- raw_spin_unlock_irqrestore(&desc->lock, flags);
+ if (type != IRQ_TYPE_NONE)
+ ret = __irq_set_trigger(desc, irq, type);
+ irq_put_desc_busunlock(desc, flags);
return ret;
}
-EXPORT_SYMBOL(set_irq_type);
+EXPORT_SYMBOL(irq_set_irq_type);
/**
- * set_irq_data - set irq type data for an irq
+ * irq_set_handler_data - set irq handler data for an irq
* @irq: Interrupt number
* @data: Pointer to interrupt specific data
*
* Set the hardware irq controller data for an irq
*/
-int set_irq_data(unsigned int irq, void *data)
+int irq_set_handler_data(unsigned int irq, void *data)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
- if (!desc) {
- printk(KERN_ERR
- "Trying to install controller data for IRQ%d\n", irq);
+ if (!desc)
return -EINVAL;
- }
-
- raw_spin_lock_irqsave(&desc->lock, flags);
desc->irq_data.handler_data = data;
- raw_spin_unlock_irqrestore(&desc->lock, flags);
+ irq_put_desc_unlock(desc, flags);
return 0;
}
-EXPORT_SYMBOL(set_irq_data);
+EXPORT_SYMBOL(irq_set_handler_data);
/**
- * set_irq_msi - set MSI descriptor data for an irq
+ * irq_set_msi_desc - set MSI descriptor data for an irq
* @irq: Interrupt number
* @entry: Pointer to MSI descriptor data
*
* Set the MSI descriptor entry for an irq
*/
-int set_irq_msi(unsigned int irq, struct msi_desc *entry)
+int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
- if (!desc) {
- printk(KERN_ERR
- "Trying to install msi data for IRQ%d\n", irq);
+ if (!desc)
return -EINVAL;
- }
-
- raw_spin_lock_irqsave(&desc->lock, flags);
desc->irq_data.msi_desc = entry;
if (entry)
entry->irq = irq;
- raw_spin_unlock_irqrestore(&desc->lock, flags);
+ irq_put_desc_unlock(desc, flags);
return 0;
}
/**
- * set_irq_chip_data - set irq chip data for an irq
+ * irq_set_chip_data - set irq chip data for an irq
* @irq: Interrupt number
* @data: Pointer to chip specific data
*
* Set the hardware irq chip data for an irq
*/
-int set_irq_chip_data(unsigned int irq, void *data)
+int irq_set_chip_data(unsigned int irq, void *data)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
- if (!desc) {
- printk(KERN_ERR
- "Trying to install chip data for IRQ%d\n", irq);
- return -EINVAL;
- }
-
- if (!desc->irq_data.chip) {
- printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
+ if (!desc)
return -EINVAL;
- }
-
- raw_spin_lock_irqsave(&desc->lock, flags);
desc->irq_data.chip_data = data;
- raw_spin_unlock_irqrestore(&desc->lock, flags);
-
+ irq_put_desc_unlock(desc, flags);
return 0;
}
-EXPORT_SYMBOL(set_irq_chip_data);
+EXPORT_SYMBOL(irq_set_chip_data);
struct irq_data *irq_get_irq_data(unsigned int irq)
{
}
EXPORT_SYMBOL_GPL(irq_get_irq_data);
-/**
- * set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq
- *
- * @irq: Interrupt number
- * @nest: 0 to clear / 1 to set the IRQ_NESTED_THREAD flag
- *
- * The IRQ_NESTED_THREAD flag indicates that on
- * request_threaded_irq() no separate interrupt thread should be
- * created for the irq as the handler are called nested in the
- * context of a demultiplexing interrupt handler thread.
- */
-void set_irq_nested_thread(unsigned int irq, int nest)
+static void irq_state_clr_disabled(struct irq_desc *desc)
{
- struct irq_desc *desc = irq_to_desc(irq);
- unsigned long flags;
-
- if (!desc)
- return;
-
- raw_spin_lock_irqsave(&desc->lock, flags);
- if (nest)
- desc->status |= IRQ_NESTED_THREAD;
- else
- desc->status &= ~IRQ_NESTED_THREAD;
- raw_spin_unlock_irqrestore(&desc->lock, flags);
+ desc->istate &= ~IRQS_DISABLED;
+ irq_compat_clr_disabled(desc);
}
-EXPORT_SYMBOL_GPL(set_irq_nested_thread);
-/*
- * default enable function
- */
-static void default_enable(struct irq_data *data)
+static void irq_state_set_disabled(struct irq_desc *desc)
{
- struct irq_desc *desc = irq_data_to_desc(data);
+ desc->istate |= IRQS_DISABLED;
+ irq_compat_set_disabled(desc);
+}
- desc->irq_data.chip->irq_unmask(&desc->irq_data);
- desc->status &= ~IRQ_MASKED;
+static void irq_state_clr_masked(struct irq_desc *desc)
+{
+ desc->istate &= ~IRQS_MASKED;
+ irq_compat_clr_masked(desc);
}
-/*
- * default disable function
- */
-static void default_disable(struct irq_data *data)
+static void irq_state_set_masked(struct irq_desc *desc)
{
+ desc->istate |= IRQS_MASKED;
+ irq_compat_set_masked(desc);
}
-/*
- * default startup function
- */
-static unsigned int default_startup(struct irq_data *data)
+int irq_startup(struct irq_desc *desc)
{
- struct irq_desc *desc = irq_data_to_desc(data);
+ irq_state_clr_disabled(desc);
+ desc->depth = 0;
+
+ if (desc->irq_data.chip->irq_startup) {
+ int ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
+ irq_state_clr_masked(desc);
+ return ret;
+ }
- desc->irq_data.chip->irq_enable(data);
+ irq_enable(desc);
return 0;
}
-/*
- * default shutdown function
- */
-static void default_shutdown(struct irq_data *data)
+void irq_shutdown(struct irq_desc *desc)
{
- struct irq_desc *desc = irq_data_to_desc(data);
+ irq_state_set_disabled(desc);
+ desc->depth = 1;
+ if (desc->irq_data.chip->irq_shutdown)
+ desc->irq_data.chip->irq_shutdown(&desc->irq_data);
+ if (desc->irq_data.chip->irq_disable)
+ desc->irq_data.chip->irq_disable(&desc->irq_data);
+ else
+ desc->irq_data.chip->irq_mask(&desc->irq_data);
+ irq_state_set_masked(desc);
+}
- desc->irq_data.chip->irq_mask(&desc->irq_data);
- desc->status |= IRQ_MASKED;
+void irq_enable(struct irq_desc *desc)
+{
+ irq_state_clr_disabled(desc);
+ if (desc->irq_data.chip->irq_enable)
+ desc->irq_data.chip->irq_enable(&desc->irq_data);
+ else
+ desc->irq_data.chip->irq_unmask(&desc->irq_data);
+ irq_state_clr_masked(desc);
+}
+
+void irq_disable(struct irq_desc *desc)
+{
+ irq_state_set_disabled(desc);
+ if (desc->irq_data.chip->irq_disable) {
+ desc->irq_data.chip->irq_disable(&desc->irq_data);
+ irq_state_set_masked(desc);
+ }
}
#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
void irq_chip_set_defaults(struct irq_chip *chip)
{
#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
- /*
- * Compat fixup functions need to be before we set the
- * defaults for enable/disable/startup/shutdown
- */
if (chip->enable)
chip->irq_enable = compat_irq_enable;
if (chip->disable)
chip->irq_shutdown = compat_irq_shutdown;
if (chip->startup)
chip->irq_startup = compat_irq_startup;
-#endif
- /*
- * The real defaults
- */
- if (!chip->irq_enable)
- chip->irq_enable = default_enable;
- if (!chip->irq_disable)
- chip->irq_disable = default_disable;
- if (!chip->irq_startup)
- chip->irq_startup = default_startup;
- /*
- * We use chip->irq_disable, when the user provided its own. When
- * we have default_disable set for chip->irq_disable, then we need
- * to use default_shutdown, otherwise the irq line is not
- * disabled on free_irq():
- */
- if (!chip->irq_shutdown)
- chip->irq_shutdown = chip->irq_disable != default_disable ?
- chip->irq_disable : default_shutdown;
-
-#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
if (!chip->end)
chip->end = dummy_irq_chip.end;
-
- /*
- * Now fix up the remaining compat handlers
- */
if (chip->bus_lock)
chip->irq_bus_lock = compat_bus_lock;
if (chip->bus_sync_unlock)
if (desc->irq_data.chip->irq_ack)
desc->irq_data.chip->irq_ack(&desc->irq_data);
}
- desc->status |= IRQ_MASKED;
+ irq_state_set_masked(desc);
}
-static inline void mask_irq(struct irq_desc *desc)
+void mask_irq(struct irq_desc *desc)
{
if (desc->irq_data.chip->irq_mask) {
desc->irq_data.chip->irq_mask(&desc->irq_data);
- desc->status |= IRQ_MASKED;
+ irq_state_set_masked(desc);
}
}
-static inline void unmask_irq(struct irq_desc *desc)
+void unmask_irq(struct irq_desc *desc)
{
if (desc->irq_data.chip->irq_unmask) {
desc->irq_data.chip->irq_unmask(&desc->irq_data);
- desc->status &= ~IRQ_MASKED;
+ irq_state_clr_masked(desc);
}
}
kstat_incr_irqs_this_cpu(irq, desc);
action = desc->action;
- if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+ if (unlikely(!action || (desc->istate & IRQS_DISABLED)))
goto out_unlock;
- desc->status |= IRQ_INPROGRESS;
+ irq_compat_set_progress(desc);
+ desc->istate |= IRQS_INPROGRESS;
raw_spin_unlock_irq(&desc->lock);
action_ret = action->thread_fn(action->irq, action->dev_id);
note_interrupt(irq, desc, action_ret);
raw_spin_lock_irq(&desc->lock);
- desc->status &= ~IRQ_INPROGRESS;
+ desc->istate &= ~IRQS_INPROGRESS;
+ irq_compat_clr_progress(desc);
out_unlock:
raw_spin_unlock_irq(&desc->lock);
}
EXPORT_SYMBOL_GPL(handle_nested_irq);
+static bool irq_check_poll(struct irq_desc *desc)
+{
+ if (!(desc->istate & IRQS_POLL_INPROGRESS))
+ return false;
+ return irq_wait_for_poll(desc);
+}
+
/**
* handle_simple_irq - Simple and software-decoded IRQs.
* @irq: the interrupt number
void
handle_simple_irq(unsigned int irq, struct irq_desc *desc)
{
- struct irqaction *action;
- irqreturn_t action_ret;
-
raw_spin_lock(&desc->lock);
- if (unlikely(desc->status & IRQ_INPROGRESS))
- goto out_unlock;
- desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+ if (unlikely(desc->istate & IRQS_INPROGRESS))
+ if (!irq_check_poll(desc))
+ goto out_unlock;
+
+ desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
kstat_incr_irqs_this_cpu(irq, desc);
- action = desc->action;
- if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+ if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED)))
goto out_unlock;
- desc->status |= IRQ_INPROGRESS;
- raw_spin_unlock(&desc->lock);
+ handle_irq_event(desc);
- action_ret = handle_IRQ_event(irq, action);
- if (!noirqdebug)
- note_interrupt(irq, desc, action_ret);
-
- raw_spin_lock(&desc->lock);
- desc->status &= ~IRQ_INPROGRESS;
out_unlock:
raw_spin_unlock(&desc->lock);
}
void
handle_level_irq(unsigned int irq, struct irq_desc *desc)
{
- struct irqaction *action;
- irqreturn_t action_ret;
-
raw_spin_lock(&desc->lock);
mask_ack_irq(desc);
- if (unlikely(desc->status & IRQ_INPROGRESS))
- goto out_unlock;
- desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+ if (unlikely(desc->istate & IRQS_INPROGRESS))
+ if (!irq_check_poll(desc))
+ goto out_unlock;
+
+ desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
kstat_incr_irqs_this_cpu(irq, desc);
/*
* If its disabled or no action available
* keep it masked and get out of here
*/
- action = desc->action;
- if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+ if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED)))
goto out_unlock;
- desc->status |= IRQ_INPROGRESS;
- raw_spin_unlock(&desc->lock);
-
- action_ret = handle_IRQ_event(irq, action);
- if (!noirqdebug)
- note_interrupt(irq, desc, action_ret);
+ handle_irq_event(desc);
- raw_spin_lock(&desc->lock);
- desc->status &= ~IRQ_INPROGRESS;
-
- if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
+ if (!(desc->istate & (IRQS_DISABLED | IRQS_ONESHOT)))
unmask_irq(desc);
out_unlock:
raw_spin_unlock(&desc->lock);
}
EXPORT_SYMBOL_GPL(handle_level_irq);
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void preflow_handler(struct irq_desc *desc)
+{
+ if (desc->preflow_handler)
+ desc->preflow_handler(&desc->irq_data);
+}
+#else
+static inline void preflow_handler(struct irq_desc *desc) { }
+#endif
+
/**
* handle_fasteoi_irq - irq handler for transparent controllers
* @irq: the interrupt number
void
handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
{
- struct irqaction *action;
- irqreturn_t action_ret;
-
raw_spin_lock(&desc->lock);
- if (unlikely(desc->status & IRQ_INPROGRESS))
- goto out;
+ if (unlikely(desc->istate & IRQS_INPROGRESS))
+ if (!irq_check_poll(desc))
+ goto out;
- desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+ desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
kstat_incr_irqs_this_cpu(irq, desc);
/*
* If its disabled or no action available
* then mask it and get out of here:
*/
- action = desc->action;
- if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
- desc->status |= IRQ_PENDING;
+ if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED))) {
+ irq_compat_set_pending(desc);
+ desc->istate |= IRQS_PENDING;
mask_irq(desc);
goto out;
}
- desc->status |= IRQ_INPROGRESS;
- desc->status &= ~IRQ_PENDING;
- raw_spin_unlock(&desc->lock);
+ if (desc->istate & IRQS_ONESHOT)
+ mask_irq(desc);
- action_ret = handle_IRQ_event(irq, action);
- if (!noirqdebug)
- note_interrupt(irq, desc, action_ret);
+ preflow_handler(desc);
+ handle_irq_event(desc);
- raw_spin_lock(&desc->lock);
- desc->status &= ~IRQ_INPROGRESS;
-out:
+out_eoi:
desc->irq_data.chip->irq_eoi(&desc->irq_data);
-
+out_unlock:
raw_spin_unlock(&desc->lock);
+ return;
+out:
+ if (!(desc->irq_data.chip->flags & IRQCHIP_EOI_IF_HANDLED))
+ goto out_eoi;
+ goto out_unlock;
}
/**
{
raw_spin_lock(&desc->lock);
- desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-
+ desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
/*
* If we're currently running this IRQ, or its disabled,
* we shouldn't process the IRQ. Mark it pending, handle
* the necessary masking and go out
*/
- if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
- !desc->action)) {
- desc->status |= (IRQ_PENDING | IRQ_MASKED);
- mask_ack_irq(desc);
- goto out_unlock;
+ if (unlikely((desc->istate & (IRQS_DISABLED | IRQS_INPROGRESS) ||
+ !desc->action))) {
+ if (!irq_check_poll(desc)) {
+ irq_compat_set_pending(desc);
+ desc->istate |= IRQS_PENDING;
+ mask_ack_irq(desc);
+ goto out_unlock;
+ }
}
kstat_incr_irqs_this_cpu(irq, desc);
/* Start handling the irq */
desc->irq_data.chip->irq_ack(&desc->irq_data);
- /* Mark the IRQ currently in progress.*/
- desc->status |= IRQ_INPROGRESS;
-
do {
- struct irqaction *action = desc->action;
- irqreturn_t action_ret;
-
- if (unlikely(!action)) {
+ if (unlikely(!desc->action)) {
mask_irq(desc);
goto out_unlock;
}
* one, we could have masked the irq.
* Renable it, if it was not disabled in meantime.
*/
- if (unlikely((desc->status &
- (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
- (IRQ_PENDING | IRQ_MASKED))) {
- unmask_irq(desc);
+ if (unlikely(desc->istate & IRQS_PENDING)) {
+ if (!(desc->istate & IRQS_DISABLED) &&
+ (desc->istate & IRQS_MASKED))
+ unmask_irq(desc);
}
- desc->status &= ~IRQ_PENDING;
- raw_spin_unlock(&desc->lock);
- action_ret = handle_IRQ_event(irq, action);
- if (!noirqdebug)
- note_interrupt(irq, desc, action_ret);
- raw_spin_lock(&desc->lock);
+ handle_irq_event(desc);
- } while ((desc->status & (IRQ_PENDING | IRQ_DISABLED)) == IRQ_PENDING);
+ } while ((desc->istate & IRQS_PENDING) &&
+ !(desc->istate & IRQS_DISABLED));
- desc->status &= ~IRQ_INPROGRESS;
out_unlock:
raw_spin_unlock(&desc->lock);
}
void
handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
{
- irqreturn_t action_ret;
+ struct irq_chip *chip = irq_desc_get_chip(desc);
kstat_incr_irqs_this_cpu(irq, desc);
- if (desc->irq_data.chip->irq_ack)
- desc->irq_data.chip->irq_ack(&desc->irq_data);
+ if (chip->irq_ack)
+ chip->irq_ack(&desc->irq_data);
- action_ret = handle_IRQ_event(irq, desc->action);
- if (!noirqdebug)
- note_interrupt(irq, desc, action_ret);
+ handle_irq_event_percpu(desc, desc->action);
- if (desc->irq_data.chip->irq_eoi)
- desc->irq_data.chip->irq_eoi(&desc->irq_data);
+ if (chip->irq_eoi)
+ chip->irq_eoi(&desc->irq_data);
}
void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
const char *name)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
- if (!desc) {
- printk(KERN_ERR
- "Trying to install type control for IRQ%d\n", irq);
+ if (!desc)
return;
- }
- if (!handle)
+ if (!handle) {
handle = handle_bad_irq;
- else if (desc->irq_data.chip == &no_irq_chip) {
- printk(KERN_WARNING "Trying to install %sinterrupt handler "
- "for IRQ%d\n", is_chained ? "chained " : "", irq);
- /*
- * Some ARM implementations install a handler for really dumb
- * interrupt hardware without setting an irq_chip. This worked
- * with the ARM no_irq_chip but the check in setup_irq would
- * prevent us to setup the interrupt at all. Switch it to
- * dummy_irq_chip for easy transition.
- */
- desc->irq_data.chip = &dummy_irq_chip;
+ } else {
+ if (WARN_ON(desc->irq_data.chip == &no_irq_chip))
+ goto out;
}
- chip_bus_lock(desc);
- raw_spin_lock_irqsave(&desc->lock, flags);
-
/* Uninstall? */
if (handle == handle_bad_irq) {
if (desc->irq_data.chip != &no_irq_chip)
mask_ack_irq(desc);
- desc->status |= IRQ_DISABLED;
+ irq_compat_set_disabled(desc);
+ desc->istate |= IRQS_DISABLED;
desc->depth = 1;
}
desc->handle_irq = handle;
desc->name = name;
if (handle != handle_bad_irq && is_chained) {
- desc->status &= ~IRQ_DISABLED;
- desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
- desc->depth = 0;
- desc->irq_data.chip->irq_startup(&desc->irq_data);
+ irq_settings_set_noprobe(desc);
+ irq_settings_set_norequest(desc);
+ irq_startup(desc);
}
- raw_spin_unlock_irqrestore(&desc->lock, flags);
- chip_bus_sync_unlock(desc);
-}
-EXPORT_SYMBOL_GPL(__set_irq_handler);
-
-void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
- irq_flow_handler_t handle)
-{
- set_irq_chip(irq, chip);
- __set_irq_handler(irq, handle, 0, NULL);
+out:
+ irq_put_desc_busunlock(desc, flags);
}
+EXPORT_SYMBOL_GPL(__irq_set_handler);
void
-set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
irq_flow_handler_t handle, const char *name)
{
- set_irq_chip(irq, chip);
- __set_irq_handler(irq, handle, 0, name);
+ irq_set_chip(irq, chip);
+ __irq_set_handler(irq, handle, 0, name);
}
void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
if (!desc)
return;
+ irq_settings_clr_and_set(desc, clr, set);
+
+ irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
+ IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT);
+ if (irq_settings_has_no_balance_set(desc))
+ irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+ if (irq_settings_is_per_cpu(desc))
+ irqd_set(&desc->irq_data, IRQD_PER_CPU);
+ if (irq_settings_can_move_pcntxt(desc))
+ irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT);
- /* Sanitize flags */
- set &= IRQF_MODIFY_MASK;
- clr &= IRQF_MODIFY_MASK;
+ irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc));
- raw_spin_lock_irqsave(&desc->lock, flags);
- desc->status &= ~clr;
- desc->status |= set;
- raw_spin_unlock_irqrestore(&desc->lock, flags);
+ irq_put_desc_unlock(desc, flags);
}
--- /dev/null
+/*
+ * Compat layer for transition period
+ */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+static inline void irq_compat_set_progress(struct irq_desc *desc)
+{
+ desc->status |= IRQ_INPROGRESS;
+}
+
+static inline void irq_compat_clr_progress(struct irq_desc *desc)
+{
+ desc->status &= ~IRQ_INPROGRESS;
+}
+static inline void irq_compat_set_disabled(struct irq_desc *desc)
+{
+ desc->status |= IRQ_DISABLED;
+}
+static inline void irq_compat_clr_disabled(struct irq_desc *desc)
+{
+ desc->status &= ~IRQ_DISABLED;
+}
+static inline void irq_compat_set_pending(struct irq_desc *desc)
+{
+ desc->status |= IRQ_PENDING;
+}
+
+static inline void irq_compat_clr_pending(struct irq_desc *desc)
+{
+ desc->status &= ~IRQ_PENDING;
+}
+static inline void irq_compat_set_masked(struct irq_desc *desc)
+{
+ desc->status |= IRQ_MASKED;
+}
+
+static inline void irq_compat_clr_masked(struct irq_desc *desc)
+{
+ desc->status &= ~IRQ_MASKED;
+}
+static inline void irq_compat_set_move_pending(struct irq_desc *desc)
+{
+ desc->status |= IRQ_MOVE_PENDING;
+}
+
+static inline void irq_compat_clr_move_pending(struct irq_desc *desc)
+{
+ desc->status &= ~IRQ_MOVE_PENDING;
+}
+static inline void irq_compat_set_affinity(struct irq_desc *desc)
+{
+ desc->status |= IRQ_AFFINITY_SET;
+}
+
+static inline void irq_compat_clr_affinity(struct irq_desc *desc)
+{
+ desc->status &= ~IRQ_AFFINITY_SET;
+}
+#else
+static inline void irq_compat_set_progress(struct irq_desc *desc) { }
+static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
+static inline void irq_compat_set_disabled(struct irq_desc *desc) { }
+static inline void irq_compat_clr_disabled(struct irq_desc *desc) { }
+static inline void irq_compat_set_pending(struct irq_desc *desc) { }
+static inline void irq_compat_clr_pending(struct irq_desc *desc) { }
+static inline void irq_compat_set_masked(struct irq_desc *desc) { }
+static inline void irq_compat_clr_masked(struct irq_desc *desc) { }
+static inline void irq_compat_set_move_pending(struct irq_desc *desc) { }
+static inline void irq_compat_clr_move_pending(struct irq_desc *desc) { }
+static inline void irq_compat_set_affinity(struct irq_desc *desc) { }
+static inline void irq_compat_clr_affinity(struct irq_desc *desc) { }
+#endif
+
--- /dev/null
+/*
+ * Debugging printout:
+ */
+
+#include <linux/kallsyms.h>
+
+#define P(f) if (desc->status & f) printk("%14s set\n", #f)
+#define PS(f) if (desc->istate & f) printk("%14s set\n", #f)
+
+static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+ printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n",
+ irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
+ printk("->handle_irq(): %p, ", desc->handle_irq);
+ print_symbol("%s\n", (unsigned long)desc->handle_irq);
+ printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
+ print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
+ printk("->action(): %p\n", desc->action);
+ if (desc->action) {
+ printk("->action->handler(): %p, ", desc->action->handler);
+ print_symbol("%s\n", (unsigned long)desc->action->handler);
+ }
+
+ P(IRQ_LEVEL);
+ P(IRQ_PER_CPU);
+ P(IRQ_NOPROBE);
+ P(IRQ_NOREQUEST);
+ P(IRQ_NOAUTOEN);
+
+ PS(IRQS_AUTODETECT);
+ PS(IRQS_INPROGRESS);
+ PS(IRQS_REPLAY);
+ PS(IRQS_WAITING);
+ PS(IRQS_DISABLED);
+ PS(IRQS_PENDING);
+ PS(IRQS_MASKED);
+}
+
+#undef P
+#undef PS
"but no thread function available.", irq, action->name);
}
-/**
- * handle_IRQ_event - irq action chain handler
- * @irq: the interrupt number
- * @action: the interrupt action chain for this irq
- *
- * Handles the action chain of an irq event
- */
-irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
+static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
+{
+ /*
+ * Wake up the handler thread for this action. In case the
+ * thread crashed and was killed we just pretend that we
+ * handled the interrupt. The hardirq handler has disabled the
+ * device interrupt, so no irq storm is lurking. If the
+ * RUNTHREAD bit is already set, nothing to do.
+ */
+ if (test_bit(IRQTF_DIED, &action->thread_flags) ||
+ test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+ return;
+
+ /*
+ * It's safe to OR the mask lockless here. We have only two
+ * places which write to threads_oneshot: This code and the
+ * irq thread.
+ *
+ * This code is the hard irq context and can never run on two
+ * cpus in parallel. If it ever does we have more serious
+ * problems than this bitmask.
+ *
+ * The irq threads of this irq which clear their "running" bit
+ * in threads_oneshot are serialized via desc->lock against
+ * each other and they are serialized against this code by
+ * IRQS_INPROGRESS.
+ *
+ * Hard irq handler:
+ *
+ * spin_lock(desc->lock);
+ * desc->state |= IRQS_INPROGRESS;
+ * spin_unlock(desc->lock);
+ * set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
+ * desc->threads_oneshot |= mask;
+ * spin_lock(desc->lock);
+ * desc->state &= ~IRQS_INPROGRESS;
+ * spin_unlock(desc->lock);
+ *
+ * irq thread:
+ *
+ * again:
+ * spin_lock(desc->lock);
+ * if (desc->state & IRQS_INPROGRESS) {
+ * spin_unlock(desc->lock);
+ * while(desc->state & IRQS_INPROGRESS)
+ * cpu_relax();
+ * goto again;
+ * }
+ * if (!test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+ * desc->threads_oneshot &= ~mask;
+ * spin_unlock(desc->lock);
+ *
+ * So either the thread waits for us to clear IRQS_INPROGRESS
+ * or we are waiting in the flow handler for desc->lock to be
+ * released before we reach this point. The thread also checks
+ * IRQTF_RUNTHREAD under desc->lock. If set it leaves
+ * threads_oneshot untouched and runs the thread another time.
+ */
+ desc->threads_oneshot |= action->thread_mask;
+ wake_up_process(action->thread);
+}
+
+irqreturn_t
+handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
{
- irqreturn_t ret, retval = IRQ_NONE;
- unsigned int status = 0;
+ irqreturn_t retval = IRQ_NONE;
+ unsigned int random = 0, irq = desc->irq_data.irq;
do {
+ irqreturn_t res;
+
trace_irq_handler_entry(irq, action);
- ret = action->handler(irq, action->dev_id);
- trace_irq_handler_exit(irq, action, ret);
+ res = action->handler(irq, action->dev_id);
+ trace_irq_handler_exit(irq, action, res);
- switch (ret) {
+ if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pF enabled interrupts\n",
+ irq, action->handler))
+ local_irq_disable();
+
+ switch (res) {
case IRQ_WAKE_THREAD:
/*
* Set result to handled so the spurious check
* does not trigger.
*/
- ret = IRQ_HANDLED;
+ res = IRQ_HANDLED;
/*
* Catch drivers which return WAKE_THREAD but
break;
}
- /*
- * Wake up the handler thread for this
- * action. In case the thread crashed and was
- * killed we just pretend that we handled the
- * interrupt. The hardirq handler above has
- * disabled the device interrupt, so no irq
- * storm is lurking.
- */
- if (likely(!test_bit(IRQTF_DIED,
- &action->thread_flags))) {
- set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
- wake_up_process(action->thread);
- }
+ irq_wake_thread(desc, action);
/* Fall through to add to randomness */
case IRQ_HANDLED:
- status |= action->flags;
+ random |= action->flags;
break;
default:
break;
}
- retval |= ret;
+ retval |= res;
action = action->next;
} while (action);
- if (status & IRQF_SAMPLE_RANDOM)
+ if (random & IRQF_SAMPLE_RANDOM)
add_interrupt_randomness(irq);
- local_irq_disable();
+ if (!noirqdebug)
+ note_interrupt(irq, desc, retval);
return retval;
}
+
+irqreturn_t handle_irq_event(struct irq_desc *desc)
+{
+ struct irqaction *action = desc->action;
+ irqreturn_t ret;
+
+ irq_compat_clr_pending(desc);
+ desc->istate &= ~IRQS_PENDING;
+ irq_compat_set_progress(desc);
+ desc->istate |= IRQS_INPROGRESS;
+ raw_spin_unlock(&desc->lock);
+
+ ret = handle_irq_event_percpu(desc, action);
+
+ raw_spin_lock(&desc->lock);
+ desc->istate &= ~IRQS_INPROGRESS;
+ irq_compat_clr_progress(desc);
+ return ret;
+}
+
+/**
+ * handle_IRQ_event - irq action chain handler
+ * @irq: the interrupt number
+ * @action: the interrupt action chain for this irq
+ *
+ * Handles the action chain of an irq event
+ */
+irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
+{
+ return handle_irq_event_percpu(irq_to_desc(irq), action);
+}
/*
* IRQ subsystem internal functions and variables:
+ *
+ * Do not ever include this file from anything else than
+ * kernel/irq/. Do not even think about using any information outside
+ * of this file for your non core code.
*/
#include <linux/irqdesc.h>
+#ifdef CONFIG_SPARSE_IRQ
+# define IRQ_BITMAP_BITS (NR_IRQS + 8196)
+#else
+# define IRQ_BITMAP_BITS NR_IRQS
+#endif
+
+#define istate core_internal_state__do_not_mess_with_it
+
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+# define status status_use_accessors
+#endif
+
extern int noirqdebug;
+/*
+ * Bits used by threaded handlers:
+ * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
+ * IRQTF_DIED - handler thread died
+ * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
+ * IRQTF_AFFINITY - irq thread is requested to adjust affinity
+ * IRQTF_FORCED_THREAD - irq action is force threaded
+ */
+enum {
+ IRQTF_RUNTHREAD,
+ IRQTF_DIED,
+ IRQTF_WARNED,
+ IRQTF_AFFINITY,
+ IRQTF_FORCED_THREAD,
+};
+
+/*
+ * Bit masks for desc->state
+ *
+ * IRQS_AUTODETECT - autodetection in progress
+ * IRQS_SPURIOUS_DISABLED - was disabled due to spurious interrupt
+ * detection
+ * IRQS_POLL_INPROGRESS - polling in progress
+ * IRQS_INPROGRESS - Interrupt in progress
+ * IRQS_ONESHOT - irq is not unmasked in primary handler
+ * IRQS_REPLAY - irq is replayed
+ * IRQS_WAITING - irq is waiting
+ * IRQS_DISABLED - irq is disabled
+ * IRQS_PENDING - irq is pending and replayed later
+ * IRQS_MASKED - irq is masked
+ * IRQS_SUSPENDED - irq is suspended
+ */
+enum {
+ IRQS_AUTODETECT = 0x00000001,
+ IRQS_SPURIOUS_DISABLED = 0x00000002,
+ IRQS_POLL_INPROGRESS = 0x00000008,
+ IRQS_INPROGRESS = 0x00000010,
+ IRQS_ONESHOT = 0x00000020,
+ IRQS_REPLAY = 0x00000040,
+ IRQS_WAITING = 0x00000080,
+ IRQS_DISABLED = 0x00000100,
+ IRQS_PENDING = 0x00000200,
+ IRQS_MASKED = 0x00000400,
+ IRQS_SUSPENDED = 0x00000800,
+};
+
+#include "compat.h"
+#include "debug.h"
+#include "settings.h"
+
#define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data)
/* Set default functions for irq_chip structures: */
extern void irq_chip_set_defaults(struct irq_chip *chip);
-/* Set default handler: */
-extern void compat_irq_chip_set_default_handler(struct irq_desc *desc);
-
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, bool susp);
extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
+extern int irq_startup(struct irq_desc *desc);
+extern void irq_shutdown(struct irq_desc *desc);
+extern void irq_enable(struct irq_desc *desc);
+extern void irq_disable(struct irq_desc *desc);
+extern void mask_irq(struct irq_desc *desc);
+extern void unmask_irq(struct irq_desc *desc);
+
extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
+irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action);
+irqreturn_t handle_irq_event(struct irq_desc *desc);
+
/* Resending of interrupts :*/
void check_irq_resend(struct irq_desc *desc, unsigned int irq);
+bool irq_wait_for_poll(struct irq_desc *desc);
#ifdef CONFIG_PROC_FS
extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
struct irqaction *action) { }
#endif
-extern int irq_select_affinity_usr(unsigned int irq);
+extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
extern void irq_set_thread_affinity(struct irq_desc *desc);
-#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
-static inline void irq_end(unsigned int irq, struct irq_desc *desc)
-{
- if (desc->irq_data.chip && desc->irq_data.chip->end)
- desc->irq_data.chip->end(irq);
-}
-#else
-static inline void irq_end(unsigned int irq, struct irq_desc *desc) { }
-#endif
-
/* Inline functions for support of irq chips on slow busses */
static inline void chip_bus_lock(struct irq_desc *desc)
{
desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
}
+struct irq_desc *
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus);
+void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus);
+
+static inline struct irq_desc *
+irq_get_desc_buslock(unsigned int irq, unsigned long *flags)
+{
+ return __irq_get_desc_lock(irq, flags, true);
+}
+
+static inline void
+irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags)
+{
+ __irq_put_desc_unlock(desc, flags, true);
+}
+
+static inline struct irq_desc *
+irq_get_desc_lock(unsigned int irq, unsigned long *flags)
+{
+ return __irq_get_desc_lock(irq, flags, false);
+}
+
+static inline void
+irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags)
+{
+ __irq_put_desc_unlock(desc, flags, false);
+}
+
/*
- * Debugging printout:
+ * Manipulation functions for irq_data.state
*/
+static inline void irqd_set_move_pending(struct irq_data *d)
+{
+ d->state_use_accessors |= IRQD_SETAFFINITY_PENDING;
+ irq_compat_set_move_pending(irq_data_to_desc(d));
+}
-#include <linux/kallsyms.h>
-
-#define P(f) if (desc->status & f) printk("%14s set\n", #f)
+static inline void irqd_clr_move_pending(struct irq_data *d)
+{
+ d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING;
+ irq_compat_clr_move_pending(irq_data_to_desc(d));
+}
-static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
+static inline void irqd_clear(struct irq_data *d, unsigned int mask)
{
- printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n",
- irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
- printk("->handle_irq(): %p, ", desc->handle_irq);
- print_symbol("%s\n", (unsigned long)desc->handle_irq);
- printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
- print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
- printk("->action(): %p\n", desc->action);
- if (desc->action) {
- printk("->action->handler(): %p, ", desc->action->handler);
- print_symbol("%s\n", (unsigned long)desc->action->handler);
- }
-
- P(IRQ_INPROGRESS);
- P(IRQ_DISABLED);
- P(IRQ_PENDING);
- P(IRQ_REPLAY);
- P(IRQ_AUTODETECT);
- P(IRQ_WAITING);
- P(IRQ_LEVEL);
- P(IRQ_MASKED);
-#ifdef CONFIG_IRQ_PER_CPU
- P(IRQ_PER_CPU);
-#endif
- P(IRQ_NOPROBE);
- P(IRQ_NOREQUEST);
- P(IRQ_NOAUTOEN);
+ d->state_use_accessors &= ~mask;
}
-#undef P
+static inline void irqd_set(struct irq_data *d, unsigned int mask)
+{
+ d->state_use_accessors |= mask;
+}
+static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
+{
+ return d->state_use_accessors & mask;
+}
desc->irq_data.chip_data = NULL;
desc->irq_data.handler_data = NULL;
desc->irq_data.msi_desc = NULL;
- desc->status = IRQ_DEFAULT_INIT_FLAGS;
+ irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
+ desc->istate = IRQS_DISABLED;
desc->handle_irq = handle_bad_irq;
desc->depth = 1;
desc->irq_count = 0;
EXPORT_SYMBOL_GPL(nr_irqs);
static DEFINE_MUTEX(sparse_irq_lock);
-static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
#ifdef CONFIG_SPARSE_IRQ
return NULL;
}
+static int irq_expand_nr_irqs(unsigned int nr)
+{
+ if (nr > IRQ_BITMAP_BITS)
+ return -ENOMEM;
+ nr_irqs = nr;
+ return 0;
+}
+
int __init early_irq_init(void)
{
int i, initcnt, node = first_online_node;
initcnt = arch_probe_nr_irqs();
printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
+ if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
+ nr_irqs = IRQ_BITMAP_BITS;
+
+ if (WARN_ON(initcnt > IRQ_BITMAP_BITS))
+ initcnt = IRQ_BITMAP_BITS;
+
+ if (initcnt > nr_irqs)
+ nr_irqs = initcnt;
+
for (i = 0; i < initcnt; i++) {
desc = alloc_desc(i, node);
set_bit(i, allocated_irqs);
struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
[0 ... NR_IRQS-1] = {
- .status = IRQ_DEFAULT_INIT_FLAGS,
+ .istate = IRQS_DISABLED,
.handle_irq = handle_bad_irq,
.depth = 1,
.lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
for (i = 0; i < count; i++) {
desc[i].irq_data.irq = i;
desc[i].irq_data.chip = &no_irq_chip;
- /* TODO : do this allocation on-demand ... */
desc[i].kstat_irqs = alloc_percpu(unsigned int);
+ irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
alloc_masks(desc + i, GFP_KERNEL, node);
desc_smp_init(desc + i, node);
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
{
-#if defined(CONFIG_KSTAT_IRQS_ONDEMAND)
- struct irq_desc *desc;
- unsigned int i;
-
- for (i = 0; i < cnt; i++) {
- desc = irq_to_desc(start + i);
- if (desc && !desc->kstat_irqs) {
- unsigned int __percpu *stats = alloc_percpu(unsigned int);
-
- if (!stats)
- return -1;
- if (cmpxchg(&desc->kstat_irqs, NULL, stats) != NULL)
- free_percpu(stats);
- }
- }
-#endif
return start;
}
+
+static int irq_expand_nr_irqs(unsigned int nr)
+{
+ return -ENOMEM;
+}
+
#endif /* !CONFIG_SPARSE_IRQ */
/* Dynamic interrupt handling */
mutex_lock(&sparse_irq_lock);
- start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+ start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
+ from, cnt, 0);
ret = -EEXIST;
if (irq >=0 && start != irq)
goto err;
- ret = -ENOMEM;
- if (start >= nr_irqs)
- goto err;
+ if (start + cnt > nr_irqs) {
+ ret = irq_expand_nr_irqs(start + cnt);
+ if (ret)
+ goto err;
+ }
bitmap_set(allocated_irqs, start, cnt);
mutex_unlock(&sparse_irq_lock);
return find_next_bit(allocated_irqs, nr_irqs, offset);
}
+struct irq_desc *
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ if (desc) {
+ if (bus)
+ chip_bus_lock(desc);
+ raw_spin_lock_irqsave(&desc->lock, *flags);
+ }
+ return desc;
+}
+
+void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
+{
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+ if (bus)
+ chip_bus_sync_unlock(desc);
+}
+
/**
* dynamic_irq_cleanup - cleanup a dynamically allocated irq
* @irq: irq number to initialize
#include "internals.h"
+#ifdef CONFIG_IRQ_FORCED_THREADING
+__read_mostly bool force_irqthreads;
+
+static int __init setup_forced_irqthreads(char *arg)
+{
+ force_irqthreads = true;
+ return 0;
+}
+early_param("threadirqs", setup_forced_irqthreads);
+#endif
+
/**
* synchronize_irq - wait for pending IRQ handlers (on other CPUs)
* @irq: interrupt number to wait for
void synchronize_irq(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
- unsigned int status;
+ unsigned int state;
if (!desc)
return;
* Wait until we're out of the critical section. This might
* give the wrong answer due to the lack of memory barriers.
*/
- while (desc->status & IRQ_INPROGRESS)
+ while (desc->istate & IRQS_INPROGRESS)
cpu_relax();
/* Ok, that indicated we're done: double-check carefully. */
raw_spin_lock_irqsave(&desc->lock, flags);
- status = desc->status;
+ state = desc->istate;
raw_spin_unlock_irqrestore(&desc->lock, flags);
/* Oops, that failed? */
- } while (status & IRQ_INPROGRESS);
+ } while (state & IRQS_INPROGRESS);
/*
* We made sure that no hardirq handler is running. Now verify
{
struct irq_desc *desc = irq_to_desc(irq);
- if (CHECK_IRQ_PER_CPU(desc->status) || !desc->irq_data.chip ||
- !desc->irq_data.chip->irq_set_affinity)
+ if (!desc || !irqd_can_balance(&desc->irq_data) ||
+ !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
return 0;
return 1;
}
}
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+static inline bool irq_can_move_pcntxt(struct irq_desc *desc)
+{
+ return irq_settings_can_move_pcntxt(desc);
+}
+static inline bool irq_move_pending(struct irq_desc *desc)
+{
+ return irqd_is_setaffinity_pending(&desc->irq_data);
+}
+static inline void
+irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask)
+{
+ cpumask_copy(desc->pending_mask, mask);
+}
+static inline void
+irq_get_pending(struct cpumask *mask, struct irq_desc *desc)
+{
+ cpumask_copy(mask, desc->pending_mask);
+}
+#else
+static inline bool irq_can_move_pcntxt(struct irq_desc *desc) { return true; }
+static inline bool irq_move_pending(struct irq_desc *desc) { return false; }
+static inline void
+irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { }
+static inline void
+irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
+#endif
+
/**
* irq_set_affinity - Set the irq affinity of a given irq
* @irq: Interrupt to set affinity
* @cpumask: cpumask
*
*/
-int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irq_chip *chip = desc->irq_data.chip;
unsigned long flags;
+ int ret = 0;
if (!chip->irq_set_affinity)
return -EINVAL;
raw_spin_lock_irqsave(&desc->lock, flags);
-#ifdef CONFIG_GENERIC_PENDING_IRQ
- if (desc->status & IRQ_MOVE_PCNTXT) {
- if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
- cpumask_copy(desc->irq_data.affinity, cpumask);
+ if (irq_can_move_pcntxt(desc)) {
+ ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
+ switch (ret) {
+ case IRQ_SET_MASK_OK:
+ cpumask_copy(desc->irq_data.affinity, mask);
+ case IRQ_SET_MASK_OK_NOCOPY:
irq_set_thread_affinity(desc);
+ ret = 0;
}
+ } else {
+ irqd_set_move_pending(&desc->irq_data);
+ irq_copy_pending(desc, mask);
}
- else {
- desc->status |= IRQ_MOVE_PENDING;
- cpumask_copy(desc->pending_mask, cpumask);
- }
-#else
- if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
- cpumask_copy(desc->irq_data.affinity, cpumask);
- irq_set_thread_affinity(desc);
+
+ if (desc->affinity_notify) {
+ kref_get(&desc->affinity_notify->kref);
+ schedule_work(&desc->affinity_notify->work);
}
-#endif
- desc->status |= IRQ_AFFINITY_SET;
+ irq_compat_set_affinity(desc);
+ irqd_set(&desc->irq_data, IRQD_AFFINITY_SET);
raw_spin_unlock_irqrestore(&desc->lock, flags);
- return 0;
+ return ret;
}
int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
+{
+ unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+
+ if (!desc)
+ return -EINVAL;
+ desc->affinity_hint = m;
+ irq_put_desc_unlock(desc, flags);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+
+static void irq_affinity_notify(struct work_struct *work)
+{
+ struct irq_affinity_notify *notify =
+ container_of(work, struct irq_affinity_notify, work);
+ struct irq_desc *desc = irq_to_desc(notify->irq);
+ cpumask_var_t cpumask;
+ unsigned long flags;
+
+ if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL))
+ goto out;
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+ if (irq_move_pending(desc))
+ irq_get_pending(cpumask, desc);
+ else
+ cpumask_copy(cpumask, desc->irq_data.affinity);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+ notify->notify(notify, cpumask);
+
+ free_cpumask_var(cpumask);
+out:
+ kref_put(¬ify->kref, notify->release);
+}
+
+/**
+ * irq_set_affinity_notifier - control notification of IRQ affinity changes
+ * @irq: Interrupt for which to enable/disable notification
+ * @notify: Context for notification, or %NULL to disable
+ * notification. Function pointers must be initialised;
+ * the other fields will be initialised by this function.
+ *
+ * Must be called in process context. Notification may only be enabled
+ * after the IRQ is allocated and must be disabled before the IRQ is
+ * freed using free_irq().
+ */
+int
+irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
{
struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_affinity_notify *old_notify;
unsigned long flags;
+ /* The release function is promised process context */
+ might_sleep();
+
if (!desc)
return -EINVAL;
+ /* Complete initialisation of *notify */
+ if (notify) {
+ notify->irq = irq;
+ kref_init(¬ify->kref);
+ INIT_WORK(¬ify->work, irq_affinity_notify);
+ }
+
raw_spin_lock_irqsave(&desc->lock, flags);
- desc->affinity_hint = m;
+ old_notify = desc->affinity_notify;
+ desc->affinity_notify = notify;
raw_spin_unlock_irqrestore(&desc->lock, flags);
+ if (old_notify)
+ kref_put(&old_notify->kref, old_notify->release);
+
return 0;
}
-EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
#ifndef CONFIG_AUTO_IRQ_AFFINITY
/*
* Generic version of the affinity autoselector.
*/
-static int setup_affinity(unsigned int irq, struct irq_desc *desc)
+static int
+setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
{
+ struct irq_chip *chip = irq_desc_get_chip(desc);
+ struct cpumask *set = irq_default_affinity;
+ int ret;
+
+ /* Excludes PER_CPU and NO_BALANCE interrupts */
if (!irq_can_set_affinity(irq))
return 0;
* Preserve an userspace affinity setup, but make sure that
* one of the targets is online.
*/
- if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
- if (cpumask_any_and(desc->irq_data.affinity, cpu_online_mask)
- < nr_cpu_ids)
- goto set_affinity;
- else
- desc->status &= ~IRQ_AFFINITY_SET;
+ if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
+ if (cpumask_intersects(desc->irq_data.affinity,
+ cpu_online_mask))
+ set = desc->irq_data.affinity;
+ else {
+ irq_compat_clr_affinity(desc);
+ irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET);
+ }
}
- cpumask_and(desc->irq_data.affinity, cpu_online_mask, irq_default_affinity);
-set_affinity:
- desc->irq_data.chip->irq_set_affinity(&desc->irq_data, desc->irq_data.affinity, false);
-
+ cpumask_and(mask, cpu_online_mask, set);
+ ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
+ switch (ret) {
+ case IRQ_SET_MASK_OK:
+ cpumask_copy(desc->irq_data.affinity, mask);
+ case IRQ_SET_MASK_OK_NOCOPY:
+ irq_set_thread_affinity(desc);
+ }
return 0;
}
#else
-static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
+static inline int
+setup_affinity(unsigned int irq, struct irq_desc *d, struct cpumask *mask)
{
return irq_select_affinity(irq);
}
/*
* Called when affinity is set via /proc/irq
*/
-int irq_select_affinity_usr(unsigned int irq)
+int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
int ret;
raw_spin_lock_irqsave(&desc->lock, flags);
- ret = setup_affinity(irq, desc);
- if (!ret)
- irq_set_thread_affinity(desc);
+ ret = setup_affinity(irq, desc, mask);
raw_spin_unlock_irqrestore(&desc->lock, flags);
-
return ret;
}
#else
-static inline int setup_affinity(unsigned int irq, struct irq_desc *desc)
+static inline int
+setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
{
return 0;
}
if (suspend) {
if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND))
return;
- desc->status |= IRQ_SUSPENDED;
+ desc->istate |= IRQS_SUSPENDED;
}
- if (!desc->depth++) {
- desc->status |= IRQ_DISABLED;
- desc->irq_data.chip->irq_disable(&desc->irq_data);
- }
+ if (!desc->depth++)
+ irq_disable(desc);
+}
+
+static int __disable_irq_nosync(unsigned int irq)
+{
+ unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+
+ if (!desc)
+ return -EINVAL;
+ __disable_irq(desc, irq, false);
+ irq_put_desc_busunlock(desc, flags);
+ return 0;
}
/**
*/
void disable_irq_nosync(unsigned int irq)
{
- struct irq_desc *desc = irq_to_desc(irq);
- unsigned long flags;
-
- if (!desc)
- return;
-
- chip_bus_lock(desc);
- raw_spin_lock_irqsave(&desc->lock, flags);
- __disable_irq(desc, irq, false);
- raw_spin_unlock_irqrestore(&desc->lock, flags);
- chip_bus_sync_unlock(desc);
+ __disable_irq_nosync(irq);
}
EXPORT_SYMBOL(disable_irq_nosync);
*/
void disable_irq(unsigned int irq)
{
- struct irq_desc *desc = irq_to_desc(irq);
-
- if (!desc)
- return;
-
- disable_irq_nosync(irq);
- if (desc->action)
+ if (!__disable_irq_nosync(irq))
synchronize_irq(irq);
}
EXPORT_SYMBOL(disable_irq);
void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
{
- if (resume)
- desc->status &= ~IRQ_SUSPENDED;
+ if (resume) {
+ if (!(desc->istate & IRQS_SUSPENDED)) {
+ if (!desc->action)
+ return;
+ if (!(desc->action->flags & IRQF_FORCE_RESUME))
+ return;
+ /* Pretend that it got disabled ! */
+ desc->depth++;
+ }
+ desc->istate &= ~IRQS_SUSPENDED;
+ }
switch (desc->depth) {
case 0:
WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
break;
case 1: {
- unsigned int status = desc->status & ~IRQ_DISABLED;
-
- if (desc->status & IRQ_SUSPENDED)
+ if (desc->istate & IRQS_SUSPENDED)
goto err_out;
/* Prevent probing on this irq: */
- desc->status = status | IRQ_NOPROBE;
+ irq_settings_set_noprobe(desc);
+ irq_enable(desc);
check_irq_resend(desc, irq);
/* fall-through */
}
*/
void enable_irq(unsigned int irq)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
if (!desc)
return;
+ if (WARN(!desc->irq_data.chip,
+ KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
+ goto out;
- if (WARN(!desc->irq_data.chip || !desc->irq_data.chip->irq_enable,
- KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
- return;
-
- chip_bus_lock(desc);
- raw_spin_lock_irqsave(&desc->lock, flags);
__enable_irq(desc, irq, false);
- raw_spin_unlock_irqrestore(&desc->lock, flags);
- chip_bus_sync_unlock(desc);
+out:
+ irq_put_desc_busunlock(desc, flags);
}
EXPORT_SYMBOL(enable_irq);
}
/**
- * set_irq_wake - control irq power management wakeup
+ * irq_set_irq_wake - control irq power management wakeup
* @irq: interrupt to control
* @on: enable/disable power management wakeup
*
* Wakeup mode lets this IRQ wake the system from sleep
* states like "suspend to RAM".
*/
-int set_irq_wake(unsigned int irq, unsigned int on)
+int irq_set_irq_wake(unsigned int irq, unsigned int on)
{
- struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
int ret = 0;
/* wakeup-capable irqs can be shared between drivers that
* don't need to have the same sleep mode behaviors.
*/
- raw_spin_lock_irqsave(&desc->lock, flags);
if (on) {
if (desc->wake_depth++ == 0) {
ret = set_irq_wake_real(irq, on);
if (ret)
desc->wake_depth = 0;
else
- desc->status |= IRQ_WAKEUP;
+ irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
}
} else {
if (desc->wake_depth == 0) {
if (ret)
desc->wake_depth = 1;
else
- desc->status &= ~IRQ_WAKEUP;
+ irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
}
}
-
- raw_spin_unlock_irqrestore(&desc->lock, flags);
+ irq_put_desc_busunlock(desc, flags);
return ret;
}
-EXPORT_SYMBOL(set_irq_wake);
+EXPORT_SYMBOL(irq_set_irq_wake);
/*
* Internal function that tells the architecture code whether a
*/
int can_request_irq(unsigned int irq, unsigned long irqflags)
{
- struct irq_desc *desc = irq_to_desc(irq);
- struct irqaction *action;
unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+ int canrequest = 0;
if (!desc)
return 0;
- if (desc->status & IRQ_NOREQUEST)
- return 0;
-
- raw_spin_lock_irqsave(&desc->lock, flags);
- action = desc->action;
- if (action)
- if (irqflags & action->flags & IRQF_SHARED)
- action = NULL;
-
- raw_spin_unlock_irqrestore(&desc->lock, flags);
-
- return !action;
-}
-
-void compat_irq_chip_set_default_handler(struct irq_desc *desc)
-{
- /*
- * If the architecture still has not overriden
- * the flow handler then zap the default. This
- * should catch incorrect flow-type setting.
- */
- if (desc->handle_irq == &handle_bad_irq)
- desc->handle_irq = NULL;
+ if (irq_settings_can_request(desc)) {
+ if (desc->action)
+ if (irqflags & desc->action->flags & IRQF_SHARED)
+ canrequest =1;
+ }
+ irq_put_desc_unlock(desc, flags);
+ return canrequest;
}
int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
unsigned long flags)
{
- int ret;
struct irq_chip *chip = desc->irq_data.chip;
+ int ret, unmask = 0;
if (!chip || !chip->irq_set_type) {
/*
return 0;
}
+ flags &= IRQ_TYPE_SENSE_MASK;
+
+ if (chip->flags & IRQCHIP_SET_TYPE_MASKED) {
+ if (!(desc->istate & IRQS_MASKED))
+ mask_irq(desc);
+ if (!(desc->istate & IRQS_DISABLED))
+ unmask = 1;
+ }
+
/* caller masked out all except trigger mode flags */
ret = chip->irq_set_type(&desc->irq_data, flags);
- if (ret)
- pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
- flags, irq, chip->irq_set_type);
- else {
- if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
- flags |= IRQ_LEVEL;
- /* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
- desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
- desc->status |= flags;
+ switch (ret) {
+ case IRQ_SET_MASK_OK:
+ irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
+ irqd_set(&desc->irq_data, flags);
+
+ case IRQ_SET_MASK_OK_NOCOPY:
+ flags = irqd_get_trigger_type(&desc->irq_data);
+ irq_settings_set_trigger_mask(desc, flags);
+ irqd_clear(&desc->irq_data, IRQD_LEVEL);
+ irq_settings_clr_level(desc);
+ if (flags & IRQ_TYPE_LEVEL_MASK) {
+ irq_settings_set_level(desc);
+ irqd_set(&desc->irq_data, IRQD_LEVEL);
+ }
if (chip != desc->irq_data.chip)
irq_chip_set_defaults(desc->irq_data.chip);
+ ret = 0;
+ break;
+ default:
+ pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+ flags, irq, chip->irq_set_type);
}
-
+ if (unmask)
+ unmask_irq(desc);
return ret;
}
* handler finished. unmask if the interrupt has not been disabled and
* is marked MASKED.
*/
-static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
+static void irq_finalize_oneshot(struct irq_desc *desc,
+ struct irqaction *action, bool force)
{
+ if (!(desc->istate & IRQS_ONESHOT))
+ return;
again:
chip_bus_lock(desc);
raw_spin_lock_irq(&desc->lock);
* The thread is faster done than the hard interrupt handler
* on the other CPU. If we unmask the irq line then the
* interrupt can come in again and masks the line, leaves due
- * to IRQ_INPROGRESS and the irq line is masked forever.
+ * to IRQS_INPROGRESS and the irq line is masked forever.
+ *
+ * This also serializes the state of shared oneshot handlers
+ * versus "desc->threads_onehsot |= action->thread_mask;" in
+ * irq_wake_thread(). See the comment there which explains the
+ * serialization.
*/
- if (unlikely(desc->status & IRQ_INPROGRESS)) {
+ if (unlikely(desc->istate & IRQS_INPROGRESS)) {
raw_spin_unlock_irq(&desc->lock);
chip_bus_sync_unlock(desc);
cpu_relax();
goto again;
}
- if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
- desc->status &= ~IRQ_MASKED;
+ /*
+ * Now check again, whether the thread should run. Otherwise
+ * we would clear the threads_oneshot bit of this thread which
+ * was just set.
+ */
+ if (!force && test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+ goto out_unlock;
+
+ desc->threads_oneshot &= ~action->thread_mask;
+
+ if (!desc->threads_oneshot && !(desc->istate & IRQS_DISABLED) &&
+ (desc->istate & IRQS_MASKED)) {
+ irq_compat_clr_masked(desc);
+ desc->istate &= ~IRQS_MASKED;
desc->irq_data.chip->irq_unmask(&desc->irq_data);
}
+out_unlock:
raw_spin_unlock_irq(&desc->lock);
chip_bus_sync_unlock(desc);
}
#ifdef CONFIG_SMP
/*
- * Check whether we need to change the affinity of the interrupt thread.
+ * Check whether we need to chasnge the affinity of the interrupt thread.
*/
static void
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
#endif
+/*
+ * Interrupts which are not explicitely requested as threaded
+ * interrupts rely on the implicit bh/preempt disable of the hard irq
+ * context. So we need to disable bh here to avoid deadlocks and other
+ * side effects.
+ */
+static void
+irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+ local_bh_disable();
+ action->thread_fn(action->irq, action->dev_id);
+ irq_finalize_oneshot(desc, action, false);
+ local_bh_enable();
+}
+
+/*
+ * Interrupts explicitely requested as threaded interupts want to be
+ * preemtible - many of them need to sleep and wait for slow busses to
+ * complete.
+ */
+static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+ action->thread_fn(action->irq, action->dev_id);
+ irq_finalize_oneshot(desc, action, false);
+}
+
/*
* Interrupt handler thread
*/
};
struct irqaction *action = data;
struct irq_desc *desc = irq_to_desc(action->irq);
- int wake, oneshot = desc->status & IRQ_ONESHOT;
+ void (*handler_fn)(struct irq_desc *desc, struct irqaction *action);
+ int wake;
+
+ if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
+ &action->thread_flags))
+ handler_fn = irq_forced_thread_fn;
+ else
+ handler_fn = irq_thread_fn;
sched_setscheduler(current, SCHED_FIFO, ¶m);
current->irqaction = action;
atomic_inc(&desc->threads_active);
raw_spin_lock_irq(&desc->lock);
- if (unlikely(desc->status & IRQ_DISABLED)) {
+ if (unlikely(desc->istate & IRQS_DISABLED)) {
/*
* CHECKME: We might need a dedicated
* IRQ_THREAD_PENDING flag here, which
* retriggers the thread in check_irq_resend()
- * but AFAICT IRQ_PENDING should be fine as it
+ * but AFAICT IRQS_PENDING should be fine as it
* retriggers the interrupt itself --- tglx
*/
- desc->status |= IRQ_PENDING;
+ irq_compat_set_pending(desc);
+ desc->istate |= IRQS_PENDING;
raw_spin_unlock_irq(&desc->lock);
} else {
raw_spin_unlock_irq(&desc->lock);
-
- action->thread_fn(action->irq, action->dev_id);
-
- if (oneshot)
- irq_finalize_oneshot(action->irq, desc);
+ handler_fn(desc, action);
}
wake = atomic_dec_and_test(&desc->threads_active);
wake_up(&desc->wait_for_threads);
}
+ /* Prevent a stale desc->threads_oneshot */
+ irq_finalize_oneshot(desc, action, true);
+
/*
* Clear irqaction. Otherwise exit_irq_thread() would make
* fuzz about an active irq thread going into nirvana.
void exit_irq_thread(void)
{
struct task_struct *tsk = current;
+ struct irq_desc *desc;
if (!tsk->irqaction)
return;
"exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
+ desc = irq_to_desc(tsk->irqaction->irq);
+
+ /*
+ * Prevent a stale desc->threads_oneshot. Must be called
+ * before setting the IRQTF_DIED flag.
+ */
+ irq_finalize_oneshot(desc, tsk->irqaction, true);
+
/*
* Set the THREAD DIED flag to prevent further wakeups of the
* soon to be gone threaded handler.
set_bit(IRQTF_DIED, &tsk->irqaction->flags);
}
+static void irq_setup_forced_threading(struct irqaction *new)
+{
+ if (!force_irqthreads)
+ return;
+ if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
+ return;
+
+ new->flags |= IRQF_ONESHOT;
+
+ if (!new->thread_fn) {
+ set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
+ new->thread_fn = new->handler;
+ new->handler = irq_default_primary_handler;
+ }
+}
+
/*
* Internal function to register an irqaction - typically used to
* allocate special interrupts that are part of the architecture.
{
struct irqaction *old, **old_ptr;
const char *old_name = NULL;
- unsigned long flags;
- int nested, shared = 0;
- int ret;
+ unsigned long flags, thread_mask = 0;
+ int ret, nested, shared = 0;
+ cpumask_var_t mask;
if (!desc)
return -EINVAL;
rand_initialize_irq(irq);
}
- /* Oneshot interrupts are not allowed with shared */
- if ((new->flags & IRQF_ONESHOT) && (new->flags & IRQF_SHARED))
- return -EINVAL;
-
/*
* Check whether the interrupt nests into another interrupt
* thread.
*/
- nested = desc->status & IRQ_NESTED_THREAD;
+ nested = irq_settings_is_nested_thread(desc);
if (nested) {
if (!new->thread_fn)
return -EINVAL;
* dummy function which warns when called.
*/
new->handler = irq_nested_primary_handler;
+ } else {
+ irq_setup_forced_threading(new);
}
/*
new->thread = t;
}
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
+ ret = -ENOMEM;
+ goto out_thread;
+ }
+
/*
* The following block of code has to be executed atomically
*/
* Can't share interrupts unless both agree to and are
* the same type (level, edge, polarity). So both flag
* fields must have IRQF_SHARED set and the bits which
- * set the trigger type must match.
+ * set the trigger type must match. Also all must
+ * agree on ONESHOT.
*/
if (!((old->flags & new->flags) & IRQF_SHARED) ||
- ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK)) {
+ ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
+ ((old->flags ^ new->flags) & IRQF_ONESHOT)) {
old_name = old->name;
goto mismatch;
}
-#if defined(CONFIG_IRQ_PER_CPU)
/* All handlers must agree on per-cpuness */
if ((old->flags & IRQF_PERCPU) !=
(new->flags & IRQF_PERCPU))
goto mismatch;
-#endif
/* add new interrupt at end of irq queue */
do {
+ thread_mask |= old->thread_mask;
old_ptr = &old->next;
old = *old_ptr;
} while (old);
shared = 1;
}
+ /*
+ * Setup the thread mask for this irqaction. Unlikely to have
+ * 32 resp 64 irqs sharing one line, but who knows.
+ */
+ if (new->flags & IRQF_ONESHOT && thread_mask == ~0UL) {
+ ret = -EBUSY;
+ goto out_mask;
+ }
+ new->thread_mask = 1 << ffz(thread_mask);
+
if (!shared) {
irq_chip_set_defaults(desc->irq_data.chip);
new->flags & IRQF_TRIGGER_MASK);
if (ret)
- goto out_thread;
- } else
- compat_irq_chip_set_default_handler(desc);
-#if defined(CONFIG_IRQ_PER_CPU)
- if (new->flags & IRQF_PERCPU)
- desc->status |= IRQ_PER_CPU;
-#endif
+ goto out_mask;
+ }
- desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING | IRQ_ONESHOT |
- IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
+ desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
+ IRQS_INPROGRESS | IRQS_ONESHOT | \
+ IRQS_WAITING);
+
+ if (new->flags & IRQF_PERCPU) {
+ irqd_set(&desc->irq_data, IRQD_PER_CPU);
+ irq_settings_set_per_cpu(desc);
+ }
if (new->flags & IRQF_ONESHOT)
- desc->status |= IRQ_ONESHOT;
+ desc->istate |= IRQS_ONESHOT;
- if (!(desc->status & IRQ_NOAUTOEN)) {
- desc->depth = 0;
- desc->status &= ~IRQ_DISABLED;
- desc->irq_data.chip->irq_startup(&desc->irq_data);
- } else
+ if (irq_settings_can_autoenable(desc))
+ irq_startup(desc);
+ else
/* Undo nested disables: */
desc->depth = 1;
/* Exclude IRQ from balancing if requested */
- if (new->flags & IRQF_NOBALANCING)
- desc->status |= IRQ_NO_BALANCING;
+ if (new->flags & IRQF_NOBALANCING) {
+ irq_settings_set_no_balancing(desc);
+ irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+ }
/* Set default affinity mask once everything is setup */
- setup_affinity(irq, desc);
-
- } else if ((new->flags & IRQF_TRIGGER_MASK)
- && (new->flags & IRQF_TRIGGER_MASK)
- != (desc->status & IRQ_TYPE_SENSE_MASK)) {
- /* hope the handler works with the actual trigger mode... */
- pr_warning("IRQ %d uses trigger mode %d; requested %d\n",
- irq, (int)(desc->status & IRQ_TYPE_SENSE_MASK),
- (int)(new->flags & IRQF_TRIGGER_MASK));
+ setup_affinity(irq, desc, mask);
+
+ } else if (new->flags & IRQF_TRIGGER_MASK) {
+ unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
+ unsigned int omsk = irq_settings_get_trigger_mask(desc);
+
+ if (nmsk != omsk)
+ /* hope the handler works with current trigger mode */
+ pr_warning("IRQ %d uses trigger mode %u; requested %u\n",
+ irq, nmsk, omsk);
}
new->irq = irq;
* Check whether we disabled the irq via the spurious handler
* before. Reenable it and give it another chance.
*/
- if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) {
- desc->status &= ~IRQ_SPURIOUS_DISABLED;
+ if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) {
+ desc->istate &= ~IRQS_SPURIOUS_DISABLED;
__enable_irq(desc, irq, false);
}
#endif
ret = -EBUSY;
+out_mask:
+ free_cpumask_var(mask);
+
out_thread:
raw_spin_unlock_irqrestore(&desc->lock, flags);
if (new->thread) {
*/
int setup_irq(unsigned int irq, struct irqaction *act)
{
+ int retval;
struct irq_desc *desc = irq_to_desc(irq);
- return __setup_irq(irq, desc, act);
+ chip_bus_lock(desc);
+ retval = __setup_irq(irq, desc, act);
+ chip_bus_sync_unlock(desc);
+
+ return retval;
}
EXPORT_SYMBOL_GPL(setup_irq);
#endif
/* If this was the last handler, shut down the IRQ line: */
- if (!desc->action) {
- desc->status |= IRQ_DISABLED;
- if (desc->irq_data.chip->irq_shutdown)
- desc->irq_data.chip->irq_shutdown(&desc->irq_data);
- else
- desc->irq_data.chip->irq_disable(&desc->irq_data);
- }
+ if (!desc->action)
+ irq_shutdown(desc);
#ifdef CONFIG_SMP
/* make sure affinity_hint is cleaned up */
if (!desc)
return;
+#ifdef CONFIG_SMP
+ if (WARN_ON(desc->affinity_notify))
+ desc->affinity_notify = NULL;
+#endif
+
chip_bus_lock(desc);
kfree(__free_irq(irq, dev_id));
chip_bus_sync_unlock(desc);
if (!desc)
return -EINVAL;
- if (desc->status & IRQ_NOREQUEST)
+ if (!irq_settings_can_request(desc))
return -EINVAL;
if (!handler) {
if (retval)
kfree(action);
-#ifdef CONFIG_DEBUG_SHIRQ
+#ifdef CONFIG_DEBUG_SHIRQ_FIXME
if (!retval && (irqflags & IRQF_SHARED)) {
/*
* It's a shared IRQ -- the driver ought to be prepared for it
if (!desc)
return -EINVAL;
- if (desc->status & IRQ_NESTED_THREAD) {
+ if (irq_settings_is_nested_thread(desc)) {
ret = request_threaded_irq(irq, NULL, handler,
flags, name, dev_id);
return !ret ? IRQC_IS_NESTED : ret;
#include "internals.h"
-void move_masked_irq(int irq)
+void irq_move_masked_irq(struct irq_data *idata)
{
- struct irq_desc *desc = irq_to_desc(irq);
- struct irq_chip *chip = desc->irq_data.chip;
+ struct irq_desc *desc = irq_data_to_desc(idata);
+ struct irq_chip *chip = idata->chip;
- if (likely(!(desc->status & IRQ_MOVE_PENDING)))
+ if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
return;
/*
* Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
*/
- if (CHECK_IRQ_PER_CPU(desc->status)) {
+ if (!irqd_can_balance(&desc->irq_data)) {
WARN_ON(1);
return;
}
- desc->status &= ~IRQ_MOVE_PENDING;
+ irqd_clr_move_pending(&desc->irq_data);
if (unlikely(cpumask_empty(desc->pending_mask)))
return;
cpumask_clear(desc->pending_mask);
}
-void move_native_irq(int irq)
+void move_masked_irq(int irq)
+{
+ irq_move_masked_irq(irq_get_irq_data(irq));
+}
+
+void irq_move_irq(struct irq_data *idata)
{
- struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_desc *desc = irq_data_to_desc(idata);
bool masked;
- if (likely(!(desc->status & IRQ_MOVE_PENDING)))
+ if (likely(!irqd_is_setaffinity_pending(idata)))
return;
- if (unlikely(desc->status & IRQ_DISABLED))
+ if (unlikely(desc->istate & IRQS_DISABLED))
return;
/*
* threaded interrupt with ONESHOT set, we can end up with an
* interrupt storm.
*/
- masked = desc->status & IRQ_MASKED;
+ masked = desc->istate & IRQS_MASKED;
if (!masked)
- desc->irq_data.chip->irq_mask(&desc->irq_data);
- move_masked_irq(irq);
+ idata->chip->irq_mask(idata);
+ irq_move_masked_irq(idata);
if (!masked)
- desc->irq_data.chip->irq_unmask(&desc->irq_data);
+ idata->chip->irq_unmask(idata);
+}
+
+void move_native_irq(int irq)
+{
+ irq_move_irq(irq_get_irq_data(irq));
}
* During system-wide suspend or hibernation device drivers need to be prevented
* from receiving interrupts and this function is provided for this purpose.
* It marks all interrupt lines in use, except for the timer ones, as disabled
- * and sets the IRQ_SUSPENDED flag for each of them.
+ * and sets the IRQS_SUSPENDED flag for each of them.
*/
void suspend_device_irqs(void)
{
}
for_each_irq_desc(irq, desc)
- if (desc->status & IRQ_SUSPENDED)
+ if (desc->istate & IRQS_SUSPENDED)
synchronize_irq(irq);
}
EXPORT_SYMBOL_GPL(suspend_device_irqs);
* resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
*
* Enable all interrupt lines previously disabled by suspend_device_irqs() that
- * have the IRQ_SUSPENDED flag set.
+ * have the IRQS_SUSPENDED flag set.
*/
void resume_device_irqs(void)
{
for_each_irq_desc(irq, desc) {
unsigned long flags;
- if (!(desc->status & IRQ_SUSPENDED))
- continue;
-
raw_spin_lock_irqsave(&desc->lock, flags);
__enable_irq(desc, irq, true);
raw_spin_unlock_irqrestore(&desc->lock, flags);
struct irq_desc *desc;
int irq;
- for_each_irq_desc(irq, desc)
- if ((desc->status & IRQ_WAKEUP) && (desc->status & IRQ_PENDING))
- return -EBUSY;
+ for_each_irq_desc(irq, desc) {
+ if (irqd_is_wakeup_set(&desc->irq_data)) {
+ if (desc->istate & IRQS_PENDING)
+ return -EBUSY;
+ continue;
+ }
+ /*
+ * Check the non wakeup interrupts whether they need
+ * to be masked before finally going into suspend
+ * state. That's for hardware which has no wakeup
+ * source configuration facility. The chip
+ * implementation indicates that with
+ * IRQCHIP_MASK_ON_SUSPEND.
+ */
+ if (desc->istate & IRQS_SUSPENDED &&
+ irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
+ mask_irq(desc);
+ }
return 0;
}
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
#include "internals.h"
const struct cpumask *mask = desc->irq_data.affinity;
#ifdef CONFIG_GENERIC_PENDING_IRQ
- if (desc->status & IRQ_MOVE_PENDING)
+ if (irqd_is_setaffinity_pending(&desc->irq_data))
mask = desc->pending_mask;
#endif
seq_cpumask(m, mask);
cpumask_var_t new_value;
int err;
- if (!irq_to_desc(irq)->irq_data.chip->irq_set_affinity || no_irq_affinity ||
- irq_balancing_disabled(irq))
+ if (!irq_can_set_affinity(irq) || no_irq_affinity)
return -EIO;
if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
if (!cpumask_intersects(new_value, cpu_online_mask)) {
/* Special case for empty set - allow the architecture
code to set default SMP affinity. */
- err = irq_select_affinity_usr(irq) ? -EINVAL : count;
+ err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count;
} else {
irq_set_affinity(irq, new_value);
err = count;
}
}
+#ifdef CONFIG_GENERIC_IRQ_SHOW
+
+int __weak arch_show_interrupts(struct seq_file *p, int prec)
+{
+ return 0;
+}
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+ static int prec;
+
+ unsigned long flags, any_count = 0;
+ int i = *(loff_t *) v, j;
+ struct irqaction *action;
+ struct irq_desc *desc;
+
+ if (i > nr_irqs)
+ return 0;
+
+ if (i == nr_irqs)
+ return arch_show_interrupts(p, prec);
+
+ /* print header and calculate the width of the first column */
+ if (i == 0) {
+ for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
+ j *= 10;
+
+ seq_printf(p, "%*s", prec + 8, "");
+ for_each_online_cpu(j)
+ seq_printf(p, "CPU%-8d", j);
+ seq_putc(p, '\n');
+ }
+
+ desc = irq_to_desc(i);
+ if (!desc)
+ return 0;
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+ for_each_online_cpu(j)
+ any_count |= kstat_irqs_cpu(i, j);
+ action = desc->action;
+ if (!action && !any_count)
+ goto out;
+
+ seq_printf(p, "%*d: ", prec, i);
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+ seq_printf(p, " %8s", desc->irq_data.chip->name);
+ seq_printf(p, "-%-8s", desc->name);
+
+ if (action) {
+ seq_printf(p, " %s", action->name);
+ while ((action = action->next) != NULL)
+ seq_printf(p, ", %s", action->name);
+ }
+
+ seq_putc(p, '\n');
+out:
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+ return 0;
+}
+#endif
#ifdef CONFIG_HARDIRQS_SW_RESEND
/* Bitmap to handle software resend of interrupts: */
-static DECLARE_BITMAP(irqs_resend, NR_IRQS);
+static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS);
/*
* Run software resends of IRQ's
*/
void check_irq_resend(struct irq_desc *desc, unsigned int irq)
{
- unsigned int status = desc->status;
-
- /*
- * Make sure the interrupt is enabled, before resending it:
- */
- desc->irq_data.chip->irq_enable(&desc->irq_data);
-
/*
* We do not resend level type interrupts. Level type
* interrupts are resent by hardware when they are still
* active.
*/
- if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
- desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
+ if (irq_settings_is_level(desc))
+ return;
+ if (desc->istate & IRQS_REPLAY)
+ return;
+ if (desc->istate & IRQS_PENDING) {
+ irq_compat_clr_pending(desc);
+ desc->istate &= ~IRQS_PENDING;
+ desc->istate |= IRQS_REPLAY;
if (!desc->irq_data.chip->irq_retrigger ||
!desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
--- /dev/null
+/*
+ * Internal header to deal with irq_desc->status which will be renamed
+ * to irq_desc->settings.
+ */
+enum {
+ _IRQ_DEFAULT_INIT_FLAGS = IRQ_DEFAULT_INIT_FLAGS,
+ _IRQ_PER_CPU = IRQ_PER_CPU,
+ _IRQ_LEVEL = IRQ_LEVEL,
+ _IRQ_NOPROBE = IRQ_NOPROBE,
+ _IRQ_NOREQUEST = IRQ_NOREQUEST,
+ _IRQ_NOAUTOEN = IRQ_NOAUTOEN,
+ _IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT,
+ _IRQ_NO_BALANCING = IRQ_NO_BALANCING,
+ _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD,
+ _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK,
+};
+
+#define IRQ_INPROGRESS GOT_YOU_MORON
+#define IRQ_REPLAY GOT_YOU_MORON
+#define IRQ_WAITING GOT_YOU_MORON
+#define IRQ_DISABLED GOT_YOU_MORON
+#define IRQ_PENDING GOT_YOU_MORON
+#define IRQ_MASKED GOT_YOU_MORON
+#define IRQ_WAKEUP GOT_YOU_MORON
+#define IRQ_MOVE_PENDING GOT_YOU_MORON
+#define IRQ_PER_CPU GOT_YOU_MORON
+#define IRQ_NO_BALANCING GOT_YOU_MORON
+#define IRQ_AFFINITY_SET GOT_YOU_MORON
+#define IRQ_LEVEL GOT_YOU_MORON
+#define IRQ_NOPROBE GOT_YOU_MORON
+#define IRQ_NOREQUEST GOT_YOU_MORON
+#define IRQ_NOAUTOEN GOT_YOU_MORON
+#define IRQ_NESTED_THREAD GOT_YOU_MORON
+#undef IRQF_MODIFY_MASK
+#define IRQF_MODIFY_MASK GOT_YOU_MORON
+
+static inline void
+irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set)
+{
+ desc->status &= ~(clr & _IRQF_MODIFY_MASK);
+ desc->status |= (set & _IRQF_MODIFY_MASK);
+}
+
+static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
+{
+ return desc->status & _IRQ_PER_CPU;
+}
+
+static inline void irq_settings_set_per_cpu(struct irq_desc *desc)
+{
+ desc->status |= _IRQ_PER_CPU;
+}
+
+static inline void irq_settings_set_no_balancing(struct irq_desc *desc)
+{
+ desc->status |= _IRQ_NO_BALANCING;
+}
+
+static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc)
+{
+ return desc->status & _IRQ_NO_BALANCING;
+}
+
+static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc)
+{
+ return desc->status & IRQ_TYPE_SENSE_MASK;
+}
+
+static inline void
+irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask)
+{
+ desc->status &= ~IRQ_TYPE_SENSE_MASK;
+ desc->status |= mask & IRQ_TYPE_SENSE_MASK;
+}
+
+static inline bool irq_settings_is_level(struct irq_desc *desc)
+{
+ return desc->status & _IRQ_LEVEL;
+}
+
+static inline void irq_settings_clr_level(struct irq_desc *desc)
+{
+ desc->status &= ~_IRQ_LEVEL;
+}
+
+static inline void irq_settings_set_level(struct irq_desc *desc)
+{
+ desc->status |= _IRQ_LEVEL;
+}
+
+static inline bool irq_settings_can_request(struct irq_desc *desc)
+{
+ return !(desc->status & _IRQ_NOREQUEST);
+}
+
+static inline void irq_settings_clr_norequest(struct irq_desc *desc)
+{
+ desc->status &= ~_IRQ_NOREQUEST;
+}
+
+static inline void irq_settings_set_norequest(struct irq_desc *desc)
+{
+ desc->status |= _IRQ_NOREQUEST;
+}
+
+static inline bool irq_settings_can_probe(struct irq_desc *desc)
+{
+ return !(desc->status & _IRQ_NOPROBE);
+}
+
+static inline void irq_settings_clr_noprobe(struct irq_desc *desc)
+{
+ desc->status &= ~_IRQ_NOPROBE;
+}
+
+static inline void irq_settings_set_noprobe(struct irq_desc *desc)
+{
+ desc->status |= _IRQ_NOPROBE;
+}
+
+static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc)
+{
+ return desc->status & _IRQ_MOVE_PCNTXT;
+}
+
+static inline bool irq_settings_can_autoenable(struct irq_desc *desc)
+{
+ return !(desc->status & _IRQ_NOAUTOEN);
+}
+
+static inline bool irq_settings_is_nested_thread(struct irq_desc *desc)
+{
+ return desc->status & _IRQ_NESTED_THREAD;
+}
+
+/* Nothing should touch desc->status from now on */
+#undef status
+#define status USE_THE_PROPER_WRAPPERS_YOU_MORON
#define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
static void poll_spurious_irqs(unsigned long dummy);
static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0);
+static int irq_poll_cpu;
+static atomic_t irq_poll_active;
+
+/*
+ * We wait here for a poller to finish.
+ *
+ * If the poll runs on this CPU, then we yell loudly and return
+ * false. That will leave the interrupt line disabled in the worst
+ * case, but it should never happen.
+ *
+ * We wait until the poller is done and then recheck disabled and
+ * action (about to be disabled). Only if it's still active, we return
+ * true and let the handler run.
+ */
+bool irq_wait_for_poll(struct irq_desc *desc)
+{
+ if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
+ "irq poll in progress on cpu %d for irq %d\n",
+ smp_processor_id(), desc->irq_data.irq))
+ return false;
+
+#ifdef CONFIG_SMP
+ do {
+ raw_spin_unlock(&desc->lock);
+ while (desc->istate & IRQS_INPROGRESS)
+ cpu_relax();
+ raw_spin_lock(&desc->lock);
+ } while (desc->istate & IRQS_INPROGRESS);
+ /* Might have been disabled in meantime */
+ return !(desc->istate & IRQS_DISABLED) && desc->action;
+#else
+ return false;
+#endif
+}
+
/*
* Recovery handler for misrouted interrupts.
*/
-static int try_one_irq(int irq, struct irq_desc *desc)
+static int try_one_irq(int irq, struct irq_desc *desc, bool force)
{
+ irqreturn_t ret = IRQ_NONE;
struct irqaction *action;
- int ok = 0, work = 0;
raw_spin_lock(&desc->lock);
- /* Already running on another processor */
- if (desc->status & IRQ_INPROGRESS) {
- /*
- * Already running: If it is shared get the other
- * CPU to go looking for our mystery interrupt too
- */
- if (desc->action && (desc->action->flags & IRQF_SHARED))
- desc->status |= IRQ_PENDING;
- raw_spin_unlock(&desc->lock);
- return ok;
- }
- /* Honour the normal IRQ locking */
- desc->status |= IRQ_INPROGRESS;
- action = desc->action;
- raw_spin_unlock(&desc->lock);
- while (action) {
- /* Only shared IRQ handlers are safe to call */
- if (action->flags & IRQF_SHARED) {
- if (action->handler(irq, action->dev_id) ==
- IRQ_HANDLED)
- ok = 1;
- }
- action = action->next;
- }
- local_irq_disable();
- /* Now clean up the flags */
- raw_spin_lock(&desc->lock);
- action = desc->action;
+ /* PER_CPU and nested thread interrupts are never polled */
+ if (irq_settings_is_per_cpu(desc) || irq_settings_is_nested_thread(desc))
+ goto out;
/*
- * While we were looking for a fixup someone queued a real
- * IRQ clashing with our walk:
+ * Do not poll disabled interrupts unless the spurious
+ * disabled poller asks explicitely.
*/
- while ((desc->status & IRQ_PENDING) && action) {
+ if ((desc->istate & IRQS_DISABLED) && !force)
+ goto out;
+
+ /*
+ * All handlers must agree on IRQF_SHARED, so we test just the
+ * first. Check for action->next as well.
+ */
+ action = desc->action;
+ if (!action || !(action->flags & IRQF_SHARED) ||
+ (action->flags & __IRQF_TIMER) || !action->next)
+ goto out;
+
+ /* Already running on another processor */
+ if (desc->istate & IRQS_INPROGRESS) {
/*
- * Perform real IRQ processing for the IRQ we deferred
+ * Already running: If it is shared get the other
+ * CPU to go looking for our mystery interrupt too
*/
- work = 1;
- raw_spin_unlock(&desc->lock);
- handle_IRQ_event(irq, action);
- raw_spin_lock(&desc->lock);
- desc->status &= ~IRQ_PENDING;
+ irq_compat_set_pending(desc);
+ desc->istate |= IRQS_PENDING;
+ goto out;
}
- desc->status &= ~IRQ_INPROGRESS;
- /*
- * If we did actual work for the real IRQ line we must let the
- * IRQ controller clean up too
- */
- if (work)
- irq_end(irq, desc);
- raw_spin_unlock(&desc->lock);
- return ok;
+ /* Mark it poll in progress */
+ desc->istate |= IRQS_POLL_INPROGRESS;
+ do {
+ if (handle_irq_event(desc) == IRQ_HANDLED)
+ ret = IRQ_HANDLED;
+ action = desc->action;
+ } while ((desc->istate & IRQS_PENDING) && action);
+ desc->istate &= ~IRQS_POLL_INPROGRESS;
+out:
+ raw_spin_unlock(&desc->lock);
+ return ret == IRQ_HANDLED;
}
static int misrouted_irq(int irq)
struct irq_desc *desc;
int i, ok = 0;
+ if (atomic_inc_return(&irq_poll_active) == 1)
+ goto out;
+
+ irq_poll_cpu = smp_processor_id();
+
for_each_irq_desc(i, desc) {
if (!i)
continue;
if (i == irq) /* Already tried */
continue;
- if (try_one_irq(i, desc))
+ if (try_one_irq(i, desc, false))
ok = 1;
}
+out:
+ atomic_dec(&irq_poll_active);
/* So the caller can adjust the irq error counts */
return ok;
}
struct irq_desc *desc;
int i;
+ if (atomic_inc_return(&irq_poll_active) != 1)
+ goto out;
+ irq_poll_cpu = smp_processor_id();
+
for_each_irq_desc(i, desc) {
- unsigned int status;
+ unsigned int state;
if (!i)
continue;
/* Racy but it doesn't matter */
- status = desc->status;
+ state = desc->istate;
barrier();
- if (!(status & IRQ_SPURIOUS_DISABLED))
+ if (!(state & IRQS_SPURIOUS_DISABLED))
continue;
local_irq_disable();
- try_one_irq(i, desc);
+ try_one_irq(i, desc, true);
local_irq_enable();
}
-
+out:
+ atomic_dec(&irq_poll_active);
mod_timer(&poll_spurious_irq_timer,
jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
}
*
* (The other 100-of-100,000 interrupts may have been a correctly
* functioning device sharing an IRQ with the failing one)
- *
- * Called under desc->lock
*/
-
static void
__report_bad_irq(unsigned int irq, struct irq_desc *desc,
irqreturn_t action_ret)
{
struct irqaction *action;
+ unsigned long flags;
if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) {
printk(KERN_ERR "irq event %d: bogus return value %x\n",
dump_stack();
printk(KERN_ERR "handlers:\n");
+ /*
+ * We need to take desc->lock here. note_interrupt() is called
+ * w/o desc->lock held, but IRQ_PROGRESS set. We might race
+ * with something else removing an action. It's ok to take
+ * desc->lock here. See synchronize_irq().
+ */
+ raw_spin_lock_irqsave(&desc->lock, flags);
action = desc->action;
while (action) {
printk(KERN_ERR "[<%p>]", action->handler);
printk("\n");
action = action->next;
}
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
}
static void
void note_interrupt(unsigned int irq, struct irq_desc *desc,
irqreturn_t action_ret)
{
+ if (desc->istate & IRQS_POLL_INPROGRESS)
+ return;
+
if (unlikely(action_ret != IRQ_HANDLED)) {
/*
* If we are seeing only the odd spurious IRQ caused by
* Now kill the IRQ
*/
printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
- desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
+ desc->istate |= IRQS_SPURIOUS_DISABLED;
desc->depth++;
- desc->irq_data.chip->irq_disable(&desc->irq_data);
+ irq_disable(desc);
mod_timer(&poll_spurious_irq_timer,
jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
#include <asm/irq_regs.h>
+struct remote_function_call {
+ struct task_struct *p;
+ int (*func)(void *info);
+ void *info;
+ int ret;
+};
+
+static void remote_function(void *data)
+{
+ struct remote_function_call *tfc = data;
+ struct task_struct *p = tfc->p;
+
+ if (p) {
+ tfc->ret = -EAGAIN;
+ if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+ return;
+ }
+
+ tfc->ret = tfc->func(tfc->info);
+}
+
+/**
+ * task_function_call - call a function on the cpu on which a task runs
+ * @p: the task to evaluate
+ * @func: the function to be called
+ * @info: the function call argument
+ *
+ * Calls the function @func when the task is currently running. This might
+ * be on the current CPU, which just calls the function directly
+ *
+ * returns: @func return value, or
+ * -ESRCH - when the process isn't running
+ * -EAGAIN - when the process moved away
+ */
+static int
+task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+{
+ struct remote_function_call data = {
+ .p = p,
+ .func = func,
+ .info = info,
+ .ret = -ESRCH, /* No such (running) process */
+ };
+
+ if (task_curr(p))
+ smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+
+ return data.ret;
+}
+
+/**
+ * cpu_function_call - call a function on the cpu
+ * @func: the function to be called
+ * @info: the function call argument
+ *
+ * Calls the function @func on the remote cpu.
+ *
+ * returns: @func return value or -ENXIO when the cpu is offline
+ */
+static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+{
+ struct remote_function_call data = {
+ .p = NULL,
+ .func = func,
+ .info = info,
+ .ret = -ENXIO, /* No such CPU */
+ };
+
+ smp_call_function_single(cpu, remote_function, &data, 1);
+
+ return data.ret;
+}
+
+#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
+ PERF_FLAG_FD_OUTPUT |\
+ PERF_FLAG_PID_CGROUP)
+
enum event_type_t {
EVENT_FLEXIBLE = 0x1,
EVENT_PINNED = 0x2,
EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
};
-atomic_t perf_task_events __read_mostly;
+/*
+ * perf_sched_events : >0 events exist
+ * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
+ */
+atomic_t perf_sched_events __read_mostly;
+static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+
static atomic_t nr_mmap_events __read_mostly;
static atomic_t nr_comm_events __read_mostly;
static atomic_t nr_task_events __read_mostly;
/*
* max perf event sample rate
*/
-int sysctl_perf_event_sample_rate __read_mostly = 100000;
+#define DEFAULT_MAX_SAMPLE_RATE 100000
+int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
+static int max_samples_per_tick __read_mostly =
+ DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+
+int perf_proc_update_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+ if (ret || !write)
+ return ret;
+
+ max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
+
+ return 0;
+}
static atomic64_t perf_event_id;
enum event_type_t event_type);
static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
- enum event_type_t event_type);
+ enum event_type_t event_type,
+ struct task_struct *task);
+
+static void update_context_time(struct perf_event_context *ctx);
+static u64 perf_event_time(struct perf_event *event);
void __weak perf_event_print_debug(void) { }
return local_clock();
}
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+ return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
+#ifdef CONFIG_CGROUP_PERF
+
+/*
+ * Must ensure cgroup is pinned (css_get) before calling
+ * this function. In other words, we cannot call this function
+ * if there is no cgroup event for the current CPU context.
+ */
+static inline struct perf_cgroup *
+perf_cgroup_from_task(struct task_struct *task)
+{
+ return container_of(task_subsys_state(task, perf_subsys_id),
+ struct perf_cgroup, css);
+}
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+ struct perf_event_context *ctx = event->ctx;
+ struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+
+ return !event->cgrp || event->cgrp == cpuctx->cgrp;
+}
+
+static inline void perf_get_cgroup(struct perf_event *event)
+{
+ css_get(&event->cgrp->css);
+}
+
+static inline void perf_put_cgroup(struct perf_event *event)
+{
+ css_put(&event->cgrp->css);
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{
+ perf_put_cgroup(event);
+ event->cgrp = NULL;
+}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+ return event->cgrp != NULL;
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+ struct perf_cgroup_info *t;
+
+ t = per_cpu_ptr(event->cgrp->info, event->cpu);
+ return t->time;
+}
+
+static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
+{
+ struct perf_cgroup_info *info;
+ u64 now;
+
+ now = perf_clock();
+
+ info = this_cpu_ptr(cgrp->info);
+
+ info->time += now - info->timestamp;
+ info->timestamp = now;
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+ struct perf_cgroup *cgrp_out = cpuctx->cgrp;
+ if (cgrp_out)
+ __update_cgrp_time(cgrp_out);
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+ struct perf_cgroup *cgrp;
+
+ /*
+ * ensure we access cgroup data only when needed and
+ * when we know the cgroup is pinned (css_get)
+ */
+ if (!is_cgroup_event(event))
+ return;
+
+ cgrp = perf_cgroup_from_task(current);
+ /*
+ * Do not update time when cgroup is not active
+ */
+ if (cgrp == event->cgrp)
+ __update_cgrp_time(event->cgrp);
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task,
+ struct perf_event_context *ctx)
+{
+ struct perf_cgroup *cgrp;
+ struct perf_cgroup_info *info;
+
+ /*
+ * ctx->lock held by caller
+ * ensure we do not access cgroup data
+ * unless we have the cgroup pinned (css_get)
+ */
+ if (!task || !ctx->nr_cgroups)
+ return;
+
+ cgrp = perf_cgroup_from_task(task);
+ info = this_cpu_ptr(cgrp->info);
+ info->timestamp = ctx->timestamp;
+}
+
+#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */
+#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */
+
+/*
+ * reschedule events based on the cgroup constraint of task.
+ *
+ * mode SWOUT : schedule out everything
+ * mode SWIN : schedule in based on cgroup for next
+ */
+void perf_cgroup_switch(struct task_struct *task, int mode)
+{
+ struct perf_cpu_context *cpuctx;
+ struct pmu *pmu;
+ unsigned long flags;
+
+ /*
+ * disable interrupts to avoid geting nr_cgroup
+ * changes via __perf_event_disable(). Also
+ * avoids preemption.
+ */
+ local_irq_save(flags);
+
+ /*
+ * we reschedule only in the presence of cgroup
+ * constrained events.
+ */
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(pmu, &pmus, entry) {
+
+ cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+ perf_pmu_disable(cpuctx->ctx.pmu);
+
+ /*
+ * perf_cgroup_events says at least one
+ * context on this CPU has cgroup events.
+ *
+ * ctx->nr_cgroups reports the number of cgroup
+ * events for a context.
+ */
+ if (cpuctx->ctx.nr_cgroups > 0) {
+
+ if (mode & PERF_CGROUP_SWOUT) {
+ cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+ /*
+ * must not be done before ctxswout due
+ * to event_filter_match() in event_sched_out()
+ */
+ cpuctx->cgrp = NULL;
+ }
+
+ if (mode & PERF_CGROUP_SWIN) {
+ /* set cgrp before ctxsw in to
+ * allow event_filter_match() to not
+ * have to pass task around
+ */
+ cpuctx->cgrp = perf_cgroup_from_task(task);
+ cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
+ }
+ }
+
+ perf_pmu_enable(cpuctx->ctx.pmu);
+ }
+
+ rcu_read_unlock();
+
+ local_irq_restore(flags);
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+ perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+ perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+}
+
+static inline int perf_cgroup_connect(int fd, struct perf_event *event,
+ struct perf_event_attr *attr,
+ struct perf_event *group_leader)
+{
+ struct perf_cgroup *cgrp;
+ struct cgroup_subsys_state *css;
+ struct file *file;
+ int ret = 0, fput_needed;
+
+ file = fget_light(fd, &fput_needed);
+ if (!file)
+ return -EBADF;
+
+ css = cgroup_css_from_dir(file, perf_subsys_id);
+ if (IS_ERR(css)) {
+ ret = PTR_ERR(css);
+ goto out;
+ }
+
+ cgrp = container_of(css, struct perf_cgroup, css);
+ event->cgrp = cgrp;
+
+ /* must be done before we fput() the file */
+ perf_get_cgroup(event);
+
+ /*
+ * all events in a group must monitor
+ * the same cgroup because a task belongs
+ * to only one perf cgroup at a time
+ */
+ if (group_leader && group_leader->cgrp != cgrp) {
+ perf_detach_cgroup(event);
+ ret = -EINVAL;
+ }
+out:
+ fput_light(file, fput_needed);
+ return ret;
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+ struct perf_cgroup_info *t;
+ t = per_cpu_ptr(event->cgrp->info, event->cpu);
+ event->shadow_ctx_time = now - t->timestamp;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+ /*
+ * when the current task's perf cgroup does not match
+ * the event's, we need to remember to call the
+ * perf_mark_enable() function the first time a task with
+ * a matching perf cgroup is scheduled in.
+ */
+ if (is_cgroup_event(event) && !perf_cgroup_match(event))
+ event->cgrp_defer_enabled = 1;
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+ struct perf_event_context *ctx)
+{
+ struct perf_event *sub;
+ u64 tstamp = perf_event_time(event);
+
+ if (!event->cgrp_defer_enabled)
+ return;
+
+ event->cgrp_defer_enabled = 0;
+
+ event->tstamp_enabled = tstamp - event->total_time_enabled;
+ list_for_each_entry(sub, &event->sibling_list, group_entry) {
+ if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
+ sub->tstamp_enabled = tstamp - sub->total_time_enabled;
+ sub->cgrp_defer_enabled = 0;
+ }
+ }
+}
+#else /* !CONFIG_CGROUP_PERF */
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+ return true;
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+ return 0;
+}
+
+static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event)
+{
+ return 0;
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+}
+
+static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
+ struct perf_event_attr *attr,
+ struct perf_event *group_leader)
+{
+ return -EINVAL;
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task,
+ struct perf_event_context *ctx)
+{
+}
+
+void
+perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
+{
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+ return 0;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+ struct perf_event_context *ctx)
+{
+}
+#endif
+
void perf_pmu_disable(struct pmu *pmu)
{
int *count = this_cpu_ptr(pmu->pmu_disable_count);
raw_spin_lock_irqsave(&ctx->lock, flags);
--ctx->pin_count;
raw_spin_unlock_irqrestore(&ctx->lock, flags);
- put_ctx(ctx);
}
/*
static u64 perf_event_time(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
+
+ if (is_cgroup_event(event))
+ return perf_cgroup_event_time(event);
+
return ctx ? ctx->time : 0;
}
if (event->state < PERF_EVENT_STATE_INACTIVE ||
event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
return;
-
- if (ctx->is_active)
+ /*
+ * in cgroup mode, time_enabled represents
+ * the time the event was enabled AND active
+ * tasks were in the monitored cgroup. This is
+ * independent of the activity of the context as
+ * there may be a mix of cgroup and non-cgroup events.
+ *
+ * That is why we treat cgroup events differently
+ * here.
+ */
+ if (is_cgroup_event(event))
run_end = perf_event_time(event);
+ else if (ctx->is_active)
+ run_end = ctx->time;
else
run_end = event->tstamp_stopped;
run_end = perf_event_time(event);
event->total_time_running = run_end - event->tstamp_running;
+
}
/*
list_add_tail(&event->group_entry, list);
}
+ if (is_cgroup_event(event))
+ ctx->nr_cgroups++;
+
list_add_rcu(&event->event_entry, &ctx->event_list);
if (!ctx->nr_events)
perf_pmu_rotate_start(ctx->pmu);
event->attach_state &= ~PERF_ATTACH_CONTEXT;
+ if (is_cgroup_event(event))
+ ctx->nr_cgroups--;
+
ctx->nr_events--;
if (event->attr.inherit_stat)
ctx->nr_stat--;
static inline int
event_filter_match(struct perf_event *event)
{
- return event->cpu == -1 || event->cpu == smp_processor_id();
+ return (event->cpu == -1 || event->cpu == smp_processor_id())
+ && perf_cgroup_match(event);
}
static void
*/
if (event->state == PERF_EVENT_STATE_INACTIVE
&& !event_filter_match(event)) {
- delta = ctx->time - event->tstamp_stopped;
+ delta = tstamp - event->tstamp_stopped;
event->tstamp_running += delta;
event->tstamp_stopped = tstamp;
}
cpuctx->exclusive = 0;
}
-static inline struct perf_cpu_context *
-__get_cpu_context(struct perf_event_context *ctx)
-{
- return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
-}
-
/*
* Cross CPU call to remove a performance event
*
* We disable the event on the hardware level first. After that we
* remove it from the context list.
*/
-static void __perf_event_remove_from_context(void *info)
+static int __perf_remove_from_context(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
- /*
- * If this is a task context, we need to check whether it is
- * the current task context of this cpu. If not it has been
- * scheduled out before the smp call arrived.
- */
- if (ctx->task && cpuctx->task_ctx != ctx)
- return;
-
raw_spin_lock(&ctx->lock);
-
event_sched_out(event, cpuctx, ctx);
-
list_del_event(event, ctx);
-
raw_spin_unlock(&ctx->lock);
+
+ return 0;
}
/*
* Remove the event from a task's (or a CPU's) list of events.
*
- * Must be called with ctx->mutex held.
- *
* CPU events are removed with a smp call. For task events we only
* call when the task is on a CPU.
*
* When called from perf_event_exit_task, it's OK because the
* context has been detached from its task.
*/
-static void perf_event_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
+ lockdep_assert_held(&ctx->mutex);
+
if (!task) {
/*
* Per cpu events are removed via an smp call and
* the removal is always successful.
*/
- smp_call_function_single(event->cpu,
- __perf_event_remove_from_context,
- event, 1);
+ cpu_function_call(event->cpu, __perf_remove_from_context, event);
return;
}
retry:
- task_oncpu_function_call(task, __perf_event_remove_from_context,
- event);
+ if (!task_function_call(task, __perf_remove_from_context, event))
+ return;
raw_spin_lock_irq(&ctx->lock);
/*
- * If the context is active we need to retry the smp call.
+ * If we failed to find a running task, but find the context active now
+ * that we've acquired the ctx->lock, retry.
*/
- if (ctx->nr_active && !list_empty(&event->group_entry)) {
+ if (ctx->is_active) {
raw_spin_unlock_irq(&ctx->lock);
goto retry;
}
/*
- * The lock prevents that this context is scheduled in so we
- * can remove the event safely, if the call above did not
- * succeed.
+ * Since the task isn't running, its safe to remove the event, us
+ * holding the ctx->lock ensures the task won't get scheduled in.
*/
- if (!list_empty(&event->group_entry))
- list_del_event(event, ctx);
+ list_del_event(event, ctx);
raw_spin_unlock_irq(&ctx->lock);
}
/*
* Cross CPU call to disable a performance event
*/
-static void __perf_event_disable(void *info)
+static int __perf_event_disable(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
/*
* If this is a per-task event, need to check whether this
* event's task is the current task on this cpu.
+ *
+ * Can trigger due to concurrent perf_event_context_sched_out()
+ * flipping contexts around.
*/
if (ctx->task && cpuctx->task_ctx != ctx)
- return;
+ return -EINVAL;
raw_spin_lock(&ctx->lock);
*/
if (event->state >= PERF_EVENT_STATE_INACTIVE) {
update_context_time(ctx);
+ update_cgrp_time_from_event(event);
update_group_times(event);
if (event == event->group_leader)
group_sched_out(event, cpuctx, ctx);
}
raw_spin_unlock(&ctx->lock);
+
+ return 0;
}
/*
/*
* Disable the event on the cpu that it's on
*/
- smp_call_function_single(event->cpu, __perf_event_disable,
- event, 1);
+ cpu_function_call(event->cpu, __perf_event_disable, event);
return;
}
retry:
- task_oncpu_function_call(task, __perf_event_disable, event);
+ if (!task_function_call(task, __perf_event_disable, event))
+ return;
raw_spin_lock_irq(&ctx->lock);
/*
*/
if (event->state == PERF_EVENT_STATE_ACTIVE) {
raw_spin_unlock_irq(&ctx->lock);
+ /*
+ * Reload the task pointer, it might have been changed by
+ * a concurrent perf_event_context_sched_out().
+ */
+ task = ctx->task;
goto retry;
}
update_group_times(event);
event->state = PERF_EVENT_STATE_OFF;
}
-
raw_spin_unlock_irq(&ctx->lock);
}
+static void perf_set_shadow_time(struct perf_event *event,
+ struct perf_event_context *ctx,
+ u64 tstamp)
+{
+ /*
+ * use the correct time source for the time snapshot
+ *
+ * We could get by without this by leveraging the
+ * fact that to get to this function, the caller
+ * has most likely already called update_context_time()
+ * and update_cgrp_time_xx() and thus both timestamp
+ * are identical (or very close). Given that tstamp is,
+ * already adjusted for cgroup, we could say that:
+ * tstamp - ctx->timestamp
+ * is equivalent to
+ * tstamp - cgrp->timestamp.
+ *
+ * Then, in perf_output_read(), the calculation would
+ * work with no changes because:
+ * - event is guaranteed scheduled in
+ * - no scheduled out in between
+ * - thus the timestamp would be the same
+ *
+ * But this is a bit hairy.
+ *
+ * So instead, we have an explicit cgroup call to remain
+ * within the time time source all along. We believe it
+ * is cleaner and simpler to understand.
+ */
+ if (is_cgroup_event(event))
+ perf_cgroup_set_shadow_time(event, tstamp);
+ else
+ event->shadow_ctx_time = tstamp - ctx->timestamp;
+}
+
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
static int
event_sched_in(struct perf_event *event,
struct perf_cpu_context *cpuctx,
event->state = PERF_EVENT_STATE_ACTIVE;
event->oncpu = smp_processor_id();
+
+ /*
+ * Unthrottle events, since we scheduled we might have missed several
+ * ticks already, also for a heavily scheduling task there is little
+ * guarantee it'll get a tick in a timely manner.
+ */
+ if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
+ perf_log_throttle(event, 1);
+ event->hw.interrupts = 0;
+ }
+
/*
* The new state must be visible before we turn it on in the hardware:
*/
event->tstamp_running += tstamp - event->tstamp_stopped;
- event->shadow_ctx_time = tstamp - ctx->timestamp;
+ perf_set_shadow_time(event, ctx, tstamp);
if (!is_software_event(event))
cpuctx->active_oncpu++;
event->tstamp_stopped = tstamp;
}
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+ struct task_struct *tsk);
+
/*
* Cross CPU call to install and enable a performance event
*
* Must be called with ctx->mutex held
*/
-static void __perf_install_in_context(void *info)
+static int __perf_install_in_context(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
int err;
/*
- * If this is a task context, we need to check whether it is
- * the current task context of this cpu. If not it has been
- * scheduled out before the smp call arrived.
- * Or possibly this is the right context but it isn't
- * on this cpu because it had no events.
+ * In case we're installing a new context to an already running task,
+ * could also happen before perf_event_task_sched_in() on architectures
+ * which do context switches with IRQs enabled.
*/
- if (ctx->task && cpuctx->task_ctx != ctx) {
- if (cpuctx->task_ctx || ctx->task != current)
- return;
- cpuctx->task_ctx = ctx;
- }
+ if (ctx->task && !cpuctx->task_ctx)
+ perf_event_context_sched_in(ctx, ctx->task);
raw_spin_lock(&ctx->lock);
ctx->is_active = 1;
update_context_time(ctx);
+ /*
+ * update cgrp time only if current cgrp
+ * matches event->cgrp. Must be done before
+ * calling add_event_to_ctx()
+ */
+ update_cgrp_time_from_event(event);
add_event_to_ctx(event, ctx);
unlock:
raw_spin_unlock(&ctx->lock);
+
+ return 0;
}
/*
* If the event is attached to a task which is on a CPU we use a smp
* call to enable it in the task context. The task might have been
* scheduled away, but we check this in the smp call again.
- *
- * Must be called with ctx->mutex held.
*/
static void
perf_install_in_context(struct perf_event_context *ctx,
{
struct task_struct *task = ctx->task;
+ lockdep_assert_held(&ctx->mutex);
+
event->ctx = ctx;
if (!task) {
* Per cpu events are installed via an smp call and
* the install is always successful.
*/
- smp_call_function_single(cpu, __perf_install_in_context,
- event, 1);
+ cpu_function_call(cpu, __perf_install_in_context, event);
return;
}
retry:
- task_oncpu_function_call(task, __perf_install_in_context,
- event);
+ if (!task_function_call(task, __perf_install_in_context, event))
+ return;
raw_spin_lock_irq(&ctx->lock);
/*
- * we need to retry the smp call.
+ * If we failed to find a running task, but find the context active now
+ * that we've acquired the ctx->lock, retry.
*/
- if (ctx->is_active && list_empty(&event->group_entry)) {
+ if (ctx->is_active) {
raw_spin_unlock_irq(&ctx->lock);
goto retry;
}
/*
- * The lock prevents that this context is scheduled in so we
- * can add the event safely, if it the call above did not
- * succeed.
+ * Since the task isn't running, its safe to add the event, us holding
+ * the ctx->lock ensures the task won't get scheduled in.
*/
- if (list_empty(&event->group_entry))
- add_event_to_ctx(event, ctx);
+ add_event_to_ctx(event, ctx);
raw_spin_unlock_irq(&ctx->lock);
}
/*
* Cross CPU call to enable a performance event
*/
-static void __perf_event_enable(void *info)
+static int __perf_event_enable(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
int err;
- /*
- * If this is a per-task event, need to check whether this
- * event's task is the current task on this cpu.
- */
- if (ctx->task && cpuctx->task_ctx != ctx) {
- if (cpuctx->task_ctx || ctx->task != current)
- return;
- cpuctx->task_ctx = ctx;
- }
+ if (WARN_ON_ONCE(!ctx->is_active))
+ return -EINVAL;
raw_spin_lock(&ctx->lock);
- ctx->is_active = 1;
update_context_time(ctx);
if (event->state >= PERF_EVENT_STATE_INACTIVE)
goto unlock;
+
+ /*
+ * set current task's cgroup time reference point
+ */
+ perf_cgroup_set_timestamp(current, ctx);
+
__perf_event_mark_enabled(event, ctx);
- if (!event_filter_match(event))
+ if (!event_filter_match(event)) {
+ if (is_cgroup_event(event))
+ perf_cgroup_defer_enabled(event);
goto unlock;
+ }
/*
* If the event is in a group and isn't the group leader,
unlock:
raw_spin_unlock(&ctx->lock);
+
+ return 0;
}
/*
/*
* Enable the event on the cpu that it's on
*/
- smp_call_function_single(event->cpu, __perf_event_enable,
- event, 1);
+ cpu_function_call(event->cpu, __perf_event_enable, event);
return;
}
event->state = PERF_EVENT_STATE_OFF;
retry:
+ if (!ctx->is_active) {
+ __perf_event_mark_enabled(event, ctx);
+ goto out;
+ }
+
raw_spin_unlock_irq(&ctx->lock);
- task_oncpu_function_call(task, __perf_event_enable, event);
+
+ if (!task_function_call(task, __perf_event_enable, event))
+ return;
raw_spin_lock_irq(&ctx->lock);
* If the context is active and the event is still off,
* we need to retry the cross-call.
*/
- if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF)
+ if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
+ /*
+ * task could have been flipped by a concurrent
+ * perf_event_context_sched_out()
+ */
+ task = ctx->task;
goto retry;
-
- /*
- * Since we have the lock this context can't be scheduled
- * in, so we can change the state safely.
- */
- if (event->state == PERF_EVENT_STATE_OFF)
- __perf_event_mark_enabled(event, ctx);
+ }
out:
raw_spin_unlock_irq(&ctx->lock);
if (likely(!ctx->nr_events))
goto out;
update_context_time(ctx);
+ update_cgrp_time_from_cpuctx(cpuctx);
if (!ctx->nr_active)
goto out;
}
}
-void perf_event_context_sched_out(struct task_struct *task, int ctxn,
- struct task_struct *next)
+static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
+ struct task_struct *next)
{
struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
struct perf_event_context *next_ctx;
for_each_task_context_nr(ctxn)
perf_event_context_sched_out(task, ctxn, next);
+
+ /*
+ * if cgroup events exist on this CPU, then we need
+ * to check if we have to switch out PMU state.
+ * cgroup event are system-wide mode only
+ */
+ if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+ perf_cgroup_sched_out(task);
}
static void task_ctx_sched_out(struct perf_event_context *ctx,
if (!event_filter_match(event))
continue;
+ /* may need to reset tstamp_enabled */
+ if (is_cgroup_event(event))
+ perf_cgroup_mark_enabled(event, ctx);
+
if (group_can_go_on(event, cpuctx, 1))
group_sched_in(event, cpuctx, ctx);
if (!event_filter_match(event))
continue;
+ /* may need to reset tstamp_enabled */
+ if (is_cgroup_event(event))
+ perf_cgroup_mark_enabled(event, ctx);
+
if (group_can_go_on(event, cpuctx, can_add_hw)) {
if (group_sched_in(event, cpuctx, ctx))
can_add_hw = 0;
static void
ctx_sched_in(struct perf_event_context *ctx,
struct perf_cpu_context *cpuctx,
- enum event_type_t event_type)
+ enum event_type_t event_type,
+ struct task_struct *task)
{
+ u64 now;
+
raw_spin_lock(&ctx->lock);
ctx->is_active = 1;
if (likely(!ctx->nr_events))
goto out;
- ctx->timestamp = perf_clock();
-
+ now = perf_clock();
+ ctx->timestamp = now;
+ perf_cgroup_set_timestamp(task, ctx);
/*
* First go through the list and put on any pinned groups
* in order to give them the best chance of going on.
}
static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
- enum event_type_t event_type)
+ enum event_type_t event_type,
+ struct task_struct *task)
{
struct perf_event_context *ctx = &cpuctx->ctx;
- ctx_sched_in(ctx, cpuctx, event_type);
+ ctx_sched_in(ctx, cpuctx, event_type, task);
}
static void task_ctx_sched_in(struct perf_event_context *ctx,
{
struct perf_cpu_context *cpuctx;
- cpuctx = __get_cpu_context(ctx);
+ cpuctx = __get_cpu_context(ctx);
if (cpuctx->task_ctx == ctx)
return;
- ctx_sched_in(ctx, cpuctx, event_type);
+ ctx_sched_in(ctx, cpuctx, event_type, NULL);
cpuctx->task_ctx = ctx;
}
-void perf_event_context_sched_in(struct perf_event_context *ctx)
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+ struct task_struct *task)
{
struct perf_cpu_context *cpuctx;
*/
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- ctx_sched_in(ctx, cpuctx, EVENT_PINNED);
- cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
- ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
+ ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
+ cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
+ ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
cpuctx->task_ctx = ctx;
if (likely(!ctx))
continue;
- perf_event_context_sched_in(ctx);
+ perf_event_context_sched_in(ctx, task);
}
+ /*
+ * if cgroup events exist on this CPU, then we need
+ * to check if we have to switch in PMU state.
+ * cgroup event are system-wide mode only
+ */
+ if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+ perf_cgroup_sched_in(task);
}
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_event *event, int enable);
-
static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
{
u64 frequency = event->attr.sample_freq;
* Reduce accuracy by one bit such that @a and @b converge
* to a similar magnitude.
*/
-#define REDUCE_FLS(a, b) \
+#define REDUCE_FLS(a, b) \
do { \
if (a##_fls > b##_fls) { \
a >>= 1; \
if (ctx)
rotate_ctx(ctx);
- cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
+ cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, current);
if (ctx)
task_ctx_sched_in(ctx, EVENT_FLEXIBLE);
raw_spin_unlock(&ctx->lock);
- perf_event_context_sched_in(ctx);
+ perf_event_context_sched_in(ctx, ctx->task);
out:
local_irq_restore(flags);
}
return;
raw_spin_lock(&ctx->lock);
- if (ctx->is_active)
+ if (ctx->is_active) {
update_context_time(ctx);
+ update_cgrp_time_from_event(event);
+ }
update_event_times(event);
if (event->state == PERF_EVENT_STATE_ACTIVE)
event->pmu->read(event);
* (e.g., thread is blocked), in that case
* we cannot update context time
*/
- if (ctx->is_active)
+ if (ctx->is_active) {
update_context_time(ctx);
+ update_cgrp_time_from_event(event);
+ }
update_event_times(event);
raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
}
+/*
+ * Returns a matching context with refcount and pincount.
+ */
static struct perf_event_context *
find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
{
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
ctx = &cpuctx->ctx;
get_ctx(ctx);
+ ++ctx->pin_count;
return ctx;
}
ctx = perf_lock_task_context(task, ctxn, &flags);
if (ctx) {
unclone_ctx(ctx);
+ ++ctx->pin_count;
raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
err = -ESRCH;
else if (task->perf_event_ctxp[ctxn])
err = -EAGAIN;
- else
+ else {
+ ++ctx->pin_count;
rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+ }
mutex_unlock(&task->perf_event_mutex);
if (unlikely(err)) {
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
- jump_label_dec(&perf_task_events);
+ jump_label_dec(&perf_sched_events);
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
if (event->attr.comm)
atomic_dec(&nr_task_events);
if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
put_callchain_buffers();
+ if (is_cgroup_event(event)) {
+ atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
+ jump_label_dec(&perf_sched_events);
+ }
}
if (event->buffer) {
event->buffer = NULL;
}
+ if (is_cgroup_event(event))
+ perf_detach_cgroup(event);
+
if (event->destroy)
event->destroy(event);
if (unlikely(!is_sampling_event(event)))
return 0;
- if (!throttle) {
- hwc->interrupts++;
- } else {
- if (hwc->interrupts != MAX_INTERRUPTS) {
- hwc->interrupts++;
- if (HZ * hwc->interrupts >
- (u64)sysctl_perf_event_sample_rate) {
- hwc->interrupts = MAX_INTERRUPTS;
- perf_log_throttle(event, 0);
- ret = 1;
- }
- } else {
- /*
- * Keep re-disabling events even though on the previous
- * pass we disabled it - just in case we raced with a
- * sched-in and the event got enabled again:
- */
+ if (unlikely(hwc->interrupts >= max_samples_per_tick)) {
+ if (throttle) {
+ hwc->interrupts = MAX_INTERRUPTS;
+ perf_log_throttle(event, 0);
ret = 1;
}
- }
+ } else
+ hwc->interrupts++;
if (event->attr.freq) {
u64 now = perf_clock();
u64 period;
event = container_of(hrtimer, struct perf_event, hw.hrtimer);
+
+ if (event->state != PERF_EVENT_STATE_ACTIVE)
+ return HRTIMER_NORESTART;
+
event->pmu->read(event);
perf_sample_data_init(&data, 0);
if (!is_sampling_event(event))
return;
- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hwc->hrtimer.function = perf_swevent_hrtimer;
-
period = local64_read(&hwc->period_left);
if (period) {
if (period < 0)
}
}
+static void perf_swevent_init_hrtimer(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!is_sampling_event(event))
+ return;
+
+ hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hwc->hrtimer.function = perf_swevent_hrtimer;
+
+ /*
+ * Since hrtimers have a fixed rate, we can do a static freq->period
+ * mapping and avoid the whole period adjust feedback stuff.
+ */
+ if (event->attr.freq) {
+ long freq = event->attr.sample_freq;
+
+ event->attr.sample_period = NSEC_PER_SEC / freq;
+ hwc->sample_period = event->attr.sample_period;
+ local64_set(&hwc->period_left, hwc->sample_period);
+ event->attr.freq = 0;
+ }
+}
+
/*
* Software event: cpu wall time clock
*/
if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
return -ENOENT;
+ perf_swevent_init_hrtimer(event);
+
return 0;
}
static void task_clock_event_read(struct perf_event *event)
{
- u64 time;
-
- if (!in_nmi()) {
- update_context_time(event->ctx);
- time = event->ctx->time;
- } else {
- u64 now = perf_clock();
- u64 delta = now - event->ctx->timestamp;
- time = event->ctx->time + delta;
- }
+ u64 now = perf_clock();
+ u64 delta = now - event->ctx->timestamp;
+ u64 time = event->ctx->time + delta;
task_clock_event_update(event, time);
}
if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
return -ENOENT;
+ perf_swevent_init_hrtimer(event);
+
return 0;
}
{
struct pmu *pmu = NULL;
int idx;
+ int ret;
idx = srcu_read_lock(&pmus_srcu);
rcu_read_lock();
pmu = idr_find(&pmu_idr, event->attr.type);
rcu_read_unlock();
- if (pmu)
+ if (pmu) {
+ ret = pmu->event_init(event);
+ if (ret)
+ pmu = ERR_PTR(ret);
goto unlock;
+ }
list_for_each_entry_rcu(pmu, &pmus, entry) {
- int ret = pmu->event_init(event);
+ ret = pmu->event_init(event);
if (!ret)
goto unlock;
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
- jump_label_inc(&perf_task_events);
+ jump_label_inc(&perf_sched_events);
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
if (event->attr.comm)
int err;
/* for future expandability... */
- if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
+ if (flags & ~PERF_FLAG_ALL)
return -EINVAL;
err = perf_copy_attr(attr_uptr, &attr);
return -EINVAL;
}
+ /*
+ * In cgroup mode, the pid argument is used to pass the fd
+ * opened to the cgroup directory in cgroupfs. The cpu argument
+ * designates the cpu on which to monitor threads from that
+ * cgroup.
+ */
+ if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
+ return -EINVAL;
+
event_fd = get_unused_fd_flags(O_RDWR);
if (event_fd < 0)
return event_fd;
group_leader = NULL;
}
- if (pid != -1) {
+ if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) {
task = find_lively_task_by_vpid(pid);
if (IS_ERR(task)) {
err = PTR_ERR(task);
goto err_task;
}
+ if (flags & PERF_FLAG_PID_CGROUP) {
+ err = perf_cgroup_connect(pid, event, &attr, group_leader);
+ if (err)
+ goto err_alloc;
+ /*
+ * one more event:
+ * - that has cgroup constraint on event->cpu
+ * - that may need work on context switch
+ */
+ atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
+ jump_label_inc(&perf_sched_events);
+ }
+
/*
* Special case software events and allow them to be part of
* any hardware group.
struct perf_event_context *gctx = group_leader->ctx;
mutex_lock(&gctx->mutex);
- perf_event_remove_from_context(group_leader);
+ perf_remove_from_context(group_leader);
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
- perf_event_remove_from_context(sibling);
+ perf_remove_from_context(sibling);
put_ctx(gctx);
}
mutex_unlock(&gctx->mutex);
perf_install_in_context(ctx, event, cpu);
++ctx->generation;
+ perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
event->owner = current;
return event_fd;
err_context:
+ perf_unpin_context(ctx);
put_ctx(ctx);
err_alloc:
free_event(event);
mutex_lock(&ctx->mutex);
perf_install_in_context(ctx, event, cpu);
++ctx->generation;
+ perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
return event;
{
struct perf_event *parent_event;
- perf_event_remove_from_context(child_event);
+ perf_remove_from_context(child_event);
parent_event = child_event->parent;
/*
return 0;
}
- child_ctx = child->perf_event_ctxp[ctxn];
+ child_ctx = child->perf_event_ctxp[ctxn];
if (!child_ctx) {
/*
* This is executed from the parent task context, so
mutex_unlock(&parent_ctx->mutex);
perf_unpin_context(parent_ctx);
+ put_ctx(parent_ctx);
return ret;
}
perf_pmu_rotate_stop(ctx->pmu);
list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
- __perf_event_remove_from_context(event);
+ __perf_remove_from_context(event);
list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
- __perf_event_remove_from_context(event);
+ __perf_remove_from_context(event);
}
static void perf_event_exit_cpu_context(int cpu)
return ret;
}
device_initcall(perf_event_sysfs_init);
+
+#ifdef CONFIG_CGROUP_PERF
+static struct cgroup_subsys_state *perf_cgroup_create(
+ struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ struct perf_cgroup *jc;
+
+ jc = kzalloc(sizeof(*jc), GFP_KERNEL);
+ if (!jc)
+ return ERR_PTR(-ENOMEM);
+
+ jc->info = alloc_percpu(struct perf_cgroup_info);
+ if (!jc->info) {
+ kfree(jc);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return &jc->css;
+}
+
+static void perf_cgroup_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+ struct perf_cgroup *jc;
+ jc = container_of(cgroup_subsys_state(cont, perf_subsys_id),
+ struct perf_cgroup, css);
+ free_percpu(jc->info);
+ kfree(jc);
+}
+
+static int __perf_cgroup_move(void *info)
+{
+ struct task_struct *task = info;
+ perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+ return 0;
+}
+
+static void perf_cgroup_move(struct task_struct *task)
+{
+ task_function_call(task, __perf_cgroup_move, task);
+}
+
+static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup *old_cgrp, struct task_struct *task,
+ bool threadgroup)
+{
+ perf_cgroup_move(task);
+ if (threadgroup) {
+ struct task_struct *c;
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+ perf_cgroup_move(c);
+ }
+ rcu_read_unlock();
+ }
+}
+
+static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup *old_cgrp, struct task_struct *task)
+{
+ /*
+ * cgroup_exit() is called in the copy_process() failure path.
+ * Ignore this case since the task hasn't ran yet, this avoids
+ * trying to poke a half freed task state from generic code.
+ */
+ if (!(task->flags & PF_EXITING))
+ return;
+
+ perf_cgroup_move(task);
+}
+
+struct cgroup_subsys perf_subsys = {
+ .name = "perf_event",
+ .subsys_id = perf_subsys_id,
+ .create = perf_cgroup_create,
+ .destroy = perf_cgroup_destroy,
+ .exit = perf_cgroup_exit,
+ .attach = perf_cgroup_attach,
+};
+#endif /* CONFIG_CGROUP_PERF */
return p->utime;
}
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
{
int error = check_clock(which_clock);
if (!error) {
return error;
}
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+static int
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
{
/*
* You can never reset a CPU clock, but we check for other errors
}
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
{
const pid_t pid = CPUCLOCK_PID(which_clock);
int error = -EINVAL;
* This is called from sys_timer_create() and do_cpu_nanosleep() with the
* new timer already all-zeros initialized.
*/
-int posix_cpu_timer_create(struct k_itimer *new_timer)
+static int posix_cpu_timer_create(struct k_itimer *new_timer)
{
int ret = 0;
const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
* If we return TIMER_RETRY, it's necessary to release the timer's lock
* and try again. (This happens when the timer is in the middle of firing.)
*/
-int posix_cpu_timer_del(struct k_itimer *timer)
+static int posix_cpu_timer_del(struct k_itimer *timer)
{
struct task_struct *p = timer->it.cpu.task;
int ret = 0;
* If we return TIMER_RETRY, it's necessary to release the timer's lock
* and try again. (This happens when the timer is in the middle of firing.)
*/
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
- struct itimerspec *new, struct itimerspec *old)
+static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+ struct itimerspec *new, struct itimerspec *old)
{
struct task_struct *p = timer->it.cpu.task;
union cpu_time_count old_expires, new_expires, old_incr, val;
return ret;
}
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
{
union cpu_time_count now;
struct task_struct *p = timer->it.cpu.task;
return error;
}
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp, struct timespec __user *rmtp)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
+
+static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+ struct timespec *rqtp, struct timespec __user *rmtp)
{
struct restart_block *restart_block =
- ¤t_thread_info()->restart_block;
+ ¤t_thread_info()->restart_block;
struct itimerspec it;
int error;
if (error == -ERESTART_RESTARTBLOCK) {
- if (flags & TIMER_ABSTIME)
+ if (flags & TIMER_ABSTIME)
return -ERESTARTNOHAND;
/*
- * Report back to the user the time still remaining.
- */
- if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ * Report back to the user the time still remaining.
+ */
+ if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
return -EFAULT;
restart_block->fn = posix_cpu_nsleep_restart;
- restart_block->arg0 = which_clock;
- restart_block->arg1 = (unsigned long) rmtp;
- restart_block->arg2 = rqtp->tv_sec;
- restart_block->arg3 = rqtp->tv_nsec;
+ restart_block->nanosleep.index = which_clock;
+ restart_block->nanosleep.rmtp = rmtp;
+ restart_block->nanosleep.expires = timespec_to_ns(rqtp);
}
return error;
}
-long posix_cpu_nsleep_restart(struct restart_block *restart_block)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
{
- clockid_t which_clock = restart_block->arg0;
- struct timespec __user *rmtp;
+ clockid_t which_clock = restart_block->nanosleep.index;
struct timespec t;
struct itimerspec it;
int error;
- rmtp = (struct timespec __user *) restart_block->arg1;
- t.tv_sec = restart_block->arg2;
- t.tv_nsec = restart_block->arg3;
+ t = ns_to_timespec(restart_block->nanosleep.expires);
- restart_block->fn = do_no_restart_syscall;
error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
if (error == -ERESTART_RESTARTBLOCK) {
+ struct timespec __user *rmtp = restart_block->nanosleep.rmtp;
/*
- * Report back to the user the time still remaining.
- */
- if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ * Report back to the user the time still remaining.
+ */
+ if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
return -EFAULT;
- restart_block->fn = posix_cpu_nsleep_restart;
- restart_block->arg0 = which_clock;
- restart_block->arg1 = (unsigned long) rmtp;
- restart_block->arg2 = t.tv_sec;
- restart_block->arg3 = t.tv_nsec;
+ restart_block->nanosleep.expires = timespec_to_ns(&t);
}
return error;
}
-
#define PROCESS_CLOCK MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
#define THREAD_CLOCK MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
timer->it_clock = THREAD_CLOCK;
return posix_cpu_timer_create(timer);
}
-static int thread_cpu_nsleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp, struct timespec __user *rmtp)
-{
- return -EINVAL;
-}
-static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
-{
- return -EINVAL;
-}
+
+struct k_clock clock_posix_cpu = {
+ .clock_getres = posix_cpu_clock_getres,
+ .clock_set = posix_cpu_clock_set,
+ .clock_get = posix_cpu_clock_get,
+ .timer_create = posix_cpu_timer_create,
+ .nsleep = posix_cpu_nsleep,
+ .nsleep_restart = posix_cpu_nsleep_restart,
+ .timer_set = posix_cpu_timer_set,
+ .timer_del = posix_cpu_timer_del,
+ .timer_get = posix_cpu_timer_get,
+};
static __init int init_posix_cpu_timers(void)
{
struct k_clock process = {
- .clock_getres = process_cpu_clock_getres,
- .clock_get = process_cpu_clock_get,
- .clock_set = do_posix_clock_nosettime,
- .timer_create = process_cpu_timer_create,
- .nsleep = process_cpu_nsleep,
- .nsleep_restart = process_cpu_nsleep_restart,
+ .clock_getres = process_cpu_clock_getres,
+ .clock_get = process_cpu_clock_get,
+ .timer_create = process_cpu_timer_create,
+ .nsleep = process_cpu_nsleep,
+ .nsleep_restart = process_cpu_nsleep_restart,
};
struct k_clock thread = {
- .clock_getres = thread_cpu_clock_getres,
- .clock_get = thread_cpu_clock_get,
- .clock_set = do_posix_clock_nosettime,
- .timer_create = thread_cpu_timer_create,
- .nsleep = thread_cpu_nsleep,
- .nsleep_restart = thread_cpu_nsleep_restart,
+ .clock_getres = thread_cpu_clock_getres,
+ .clock_get = thread_cpu_clock_get,
+ .timer_create = thread_cpu_timer_create,
};
struct timespec ts;
- register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
- register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+ posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
+ posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
cputime_to_timespec(cputime_one_jiffy, &ts);
onecputick = ts.tv_nsec;
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/idr.h>
+#include <linux/posix-clock.h>
#include <linux/posix-timers.h>
#include <linux/syscalls.h>
#include <linux/wait.h>
#error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
#endif
+/*
+ * parisc wants ENOTSUP instead of EOPNOTSUPP
+ */
+#ifndef ENOTSUP
+# define ENANOSLEEP_NOTSUP EOPNOTSUPP
+#else
+# define ENANOSLEEP_NOTSUP ENOTSUP
+#endif
/*
* The timer ID is turned into a timer address by idr_find().
/*
* CLOCKs: The POSIX standard calls for a couple of clocks and allows us
* to implement others. This structure defines the various
- * clocks and allows the possibility of adding others. We
- * provide an interface to add clocks to the table and expect
- * the "arch" code to add at least one clock that is high
- * resolution. Here we define the standard CLOCK_REALTIME as a
- * 1/HZ resolution clock.
+ * clocks.
*
* RESOLUTION: Clock resolution is used to round up timer and interval
* times, NOT to report clock times, which are reported with as
* necessary code is written. The standard says we should say
* something about this issue in the documentation...
*
- * FUNCTIONS: The CLOCKs structure defines possible functions to handle
- * various clock functions. For clocks that use the standard
- * system timer code these entries should be NULL. This will
- * allow dispatch without the overhead of indirect function
- * calls. CLOCKS that depend on other sources (e.g. WWV or GPS)
- * must supply functions here, even if the function just returns
- * ENOSYS. The standard POSIX timer management code assumes the
- * following: 1.) The k_itimer struct (sched.h) is used for the
- * timer. 2.) The list, it_lock, it_clock, it_id and it_pid
- * fields are not modified by timer code.
+ * FUNCTIONS: The CLOCKs structure defines possible functions to
+ * handle various clock functions.
*
- * At this time all functions EXCEPT clock_nanosleep can be
- * redirected by the CLOCKS structure. Clock_nanosleep is in
- * there, but the code ignores it.
+ * The standard POSIX timer management code assumes the
+ * following: 1.) The k_itimer struct (sched.h) is used for
+ * the timer. 2.) The list, it_lock, it_clock, it_id and
+ * it_pid fields are not modified by timer code.
*
* Permissions: It is assumed that the clock_settime() function defined
* for each clock will take care of permission checks. Some
*/
static int common_nsleep(const clockid_t, int flags, struct timespec *t,
struct timespec __user *rmtp);
+static int common_timer_create(struct k_itimer *new_timer);
static void common_timer_get(struct k_itimer *, struct itimerspec *);
static int common_timer_set(struct k_itimer *, int,
struct itimerspec *, struct itimerspec *);
spin_unlock_irqrestore(&timr->it_lock, flags);
}
-/*
- * Call the k_clock hook function if non-null, or the default function.
- */
-#define CLOCK_DISPATCH(clock, call, arglist) \
- ((clock) < 0 ? posix_cpu_##call arglist : \
- (posix_clocks[clock].call != NULL \
- ? (*posix_clocks[clock].call) arglist : common_##call arglist))
-
-/*
- * Default clock hook functions when the struct k_clock passed
- * to register_posix_clock leaves a function pointer null.
- *
- * The function common_CALL is the default implementation for
- * the function pointer CALL in struct k_clock.
- */
-
-static inline int common_clock_getres(const clockid_t which_clock,
- struct timespec *tp)
-{
- tp->tv_sec = 0;
- tp->tv_nsec = posix_clocks[which_clock].res;
- return 0;
-}
-
-/*
- * Get real time for posix timers
- */
-static int common_clock_get(clockid_t which_clock, struct timespec *tp)
+/* Get clock_realtime */
+static int posix_clock_realtime_get(clockid_t which_clock, struct timespec *tp)
{
ktime_get_real_ts(tp);
return 0;
}
-static inline int common_clock_set(const clockid_t which_clock,
- struct timespec *tp)
+/* Set clock_realtime */
+static int posix_clock_realtime_set(const clockid_t which_clock,
+ const struct timespec *tp)
{
return do_sys_settimeofday(tp, NULL);
}
-static int common_timer_create(struct k_itimer *new_timer)
-{
- hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
- return 0;
-}
-
-static int no_timer_create(struct k_itimer *new_timer)
-{
- return -EOPNOTSUPP;
-}
-
-static int no_nsleep(const clockid_t which_clock, int flags,
- struct timespec *tsave, struct timespec __user *rmtp)
-{
- return -EOPNOTSUPP;
-}
-
-/*
- * Return nonzero if we know a priori this clockid_t value is bogus.
- */
-static inline int invalid_clockid(const clockid_t which_clock)
+static int posix_clock_realtime_adj(const clockid_t which_clock,
+ struct timex *t)
{
- if (which_clock < 0) /* CPU clock, posix_cpu_* will check it */
- return 0;
- if ((unsigned) which_clock >= MAX_CLOCKS)
- return 1;
- if (posix_clocks[which_clock].clock_getres != NULL)
- return 0;
- if (posix_clocks[which_clock].res != 0)
- return 0;
- return 1;
+ return do_adjtimex(t);
}
/*
}
/*
- * Get monotonic time for posix timers
+ * Get monotonic-raw time for posix timers
*/
static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
{
*tp = ktime_to_timespec(KTIME_LOW_RES);
return 0;
}
+
+static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
+{
+ get_monotonic_boottime(tp);
+ 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 = hrtimer_get_res,
+ .clock_get = posix_clock_realtime_get,
+ .clock_set = posix_clock_realtime_set,
+ .clock_adj = posix_clock_realtime_adj,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
};
struct k_clock clock_monotonic = {
- .clock_getres = hrtimer_get_res,
- .clock_get = posix_ktime_get_ts,
- .clock_set = do_posix_clock_nosettime,
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_ktime_get_ts,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
};
struct k_clock clock_monotonic_raw = {
- .clock_getres = hrtimer_get_res,
- .clock_get = posix_get_monotonic_raw,
- .clock_set = do_posix_clock_nosettime,
- .timer_create = no_timer_create,
- .nsleep = no_nsleep,
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_get_monotonic_raw,
};
struct k_clock clock_realtime_coarse = {
- .clock_getres = posix_get_coarse_res,
- .clock_get = posix_get_realtime_coarse,
- .clock_set = do_posix_clock_nosettime,
- .timer_create = no_timer_create,
- .nsleep = no_nsleep,
+ .clock_getres = posix_get_coarse_res,
+ .clock_get = posix_get_realtime_coarse,
};
struct k_clock clock_monotonic_coarse = {
- .clock_getres = posix_get_coarse_res,
- .clock_get = posix_get_monotonic_coarse,
- .clock_set = do_posix_clock_nosettime,
- .timer_create = no_timer_create,
- .nsleep = no_nsleep,
+ .clock_getres = posix_get_coarse_res,
+ .clock_get = posix_get_monotonic_coarse,
+ };
+ struct k_clock clock_boottime = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_get_boottime,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
};
- register_posix_clock(CLOCK_REALTIME, &clock_realtime);
- register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
- register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
- register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
- register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+ posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
+ posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
+ posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
+ posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
+ posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+ posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
posix_timers_cache = kmem_cache_create("posix_timers_cache",
sizeof (struct k_itimer), 0, SLAB_PANIC,
return task_pid(rtn);
}
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
+void posix_timers_register_clock(const clockid_t clock_id,
+ struct k_clock *new_clock)
{
if ((unsigned) clock_id >= MAX_CLOCKS) {
- printk("POSIX clock register failed for clock_id %d\n",
+ printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
+ clock_id);
+ return;
+ }
+
+ if (!new_clock->clock_get) {
+ printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n",
+ clock_id);
+ return;
+ }
+ if (!new_clock->clock_getres) {
+ printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n",
clock_id);
return;
}
posix_clocks[clock_id] = *new_clock;
}
-EXPORT_SYMBOL_GPL(register_posix_clock);
+EXPORT_SYMBOL_GPL(posix_timers_register_clock);
static struct k_itimer * alloc_posix_timer(void)
{
kmem_cache_free(posix_timers_cache, tmr);
}
+static struct k_clock *clockid_to_kclock(const clockid_t id)
+{
+ if (id < 0)
+ return (id & CLOCKFD_MASK) == CLOCKFD ?
+ &clock_posix_dynamic : &clock_posix_cpu;
+
+ if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
+ return NULL;
+ return &posix_clocks[id];
+}
+
+static int common_timer_create(struct k_itimer *new_timer)
+{
+ hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
+ return 0;
+}
+
/* Create a POSIX.1b interval timer. */
SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
struct sigevent __user *, timer_event_spec,
timer_t __user *, created_timer_id)
{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
struct k_itimer *new_timer;
int error, new_timer_id;
sigevent_t event;
int it_id_set = IT_ID_NOT_SET;
- if (invalid_clockid(which_clock))
+ if (!kc)
return -EINVAL;
+ if (!kc->timer_create)
+ return -EOPNOTSUPP;
new_timer = alloc_posix_timer();
if (unlikely(!new_timer))
goto out;
}
- error = CLOCK_DISPATCH(which_clock, timer_create, (new_timer));
+ error = kc->timer_create(new_timer);
if (error)
goto out;
spin_unlock_irq(¤t->sighand->siglock);
return 0;
- /*
+ /*
* In the case of the timer belonging to another task, after
* the task is unlocked, the timer is owned by the other task
* and may cease to exist at any time. Don't use or modify
SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
struct itimerspec __user *, setting)
{
- struct k_itimer *timr;
struct itimerspec cur_setting;
+ struct k_itimer *timr;
+ struct k_clock *kc;
unsigned long flags;
+ int ret = 0;
timr = lock_timer(timer_id, &flags);
if (!timr)
return -EINVAL;
- CLOCK_DISPATCH(timr->it_clock, timer_get, (timr, &cur_setting));
+ kc = clockid_to_kclock(timr->it_clock);
+ if (WARN_ON_ONCE(!kc || !kc->timer_get))
+ ret = -EINVAL;
+ else
+ kc->timer_get(timr, &cur_setting);
unlock_timer(timr, flags);
- if (copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
+ if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
return -EFAULT;
- return 0;
+ return ret;
}
/*
int error = 0;
unsigned long flag;
struct itimerspec *rtn = old_setting ? &old_spec : NULL;
+ struct k_clock *kc;
if (!new_setting)
return -EINVAL;
if (!timr)
return -EINVAL;
- error = CLOCK_DISPATCH(timr->it_clock, timer_set,
- (timr, flags, &new_spec, rtn));
+ kc = clockid_to_kclock(timr->it_clock);
+ if (WARN_ON_ONCE(!kc || !kc->timer_set))
+ error = -EINVAL;
+ else
+ error = kc->timer_set(timr, flags, &new_spec, rtn);
unlock_timer(timr, flag);
if (error == TIMER_RETRY) {
return error;
}
-static inline int common_timer_del(struct k_itimer *timer)
+static int common_timer_del(struct k_itimer *timer)
{
timer->it.real.interval.tv64 = 0;
static inline int timer_delete_hook(struct k_itimer *timer)
{
- return CLOCK_DISPATCH(timer->it_clock, timer_del, (timer));
+ struct k_clock *kc = clockid_to_kclock(timer->it_clock);
+
+ if (WARN_ON_ONCE(!kc || !kc->timer_del))
+ return -EINVAL;
+ return kc->timer_del(timer);
}
/* Delete a POSIX.1b interval timer. */
}
}
-/* Not available / possible... functions */
-int do_posix_clock_nosettime(const clockid_t clockid, struct timespec *tp)
-{
- return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(do_posix_clock_nosettime);
-
-int do_posix_clock_nonanosleep(const clockid_t clock, int flags,
- struct timespec *t, struct timespec __user *r)
-{
-#ifndef ENOTSUP
- return -EOPNOTSUPP; /* aka ENOTSUP in userland for POSIX */
-#else /* parisc does define it separately. */
- return -ENOTSUP;
-#endif
-}
-EXPORT_SYMBOL_GPL(do_posix_clock_nonanosleep);
-
SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
const struct timespec __user *, tp)
{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec new_tp;
- if (invalid_clockid(which_clock))
+ if (!kc || !kc->clock_set)
return -EINVAL;
+
if (copy_from_user(&new_tp, tp, sizeof (*tp)))
return -EFAULT;
- return CLOCK_DISPATCH(which_clock, clock_set, (which_clock, &new_tp));
+ return kc->clock_set(which_clock, &new_tp);
}
SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
struct timespec __user *,tp)
{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec kernel_tp;
int error;
- if (invalid_clockid(which_clock))
+ if (!kc)
return -EINVAL;
- error = CLOCK_DISPATCH(which_clock, clock_get,
- (which_clock, &kernel_tp));
+
+ error = kc->clock_get(which_clock, &kernel_tp);
+
if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
error = -EFAULT;
return error;
+}
+
+SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
+ struct timex __user *, utx)
+{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timex ktx;
+ int err;
+
+ if (!kc)
+ return -EINVAL;
+ if (!kc->clock_adj)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&ktx, utx, sizeof(ktx)))
+ return -EFAULT;
+
+ err = kc->clock_adj(which_clock, &ktx);
+
+ if (!err && copy_to_user(utx, &ktx, sizeof(ktx)))
+ return -EFAULT;
+ return err;
}
SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
struct timespec __user *, tp)
{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec rtn_tp;
int error;
- if (invalid_clockid(which_clock))
+ if (!kc)
return -EINVAL;
- error = CLOCK_DISPATCH(which_clock, clock_getres,
- (which_clock, &rtn_tp));
+ error = kc->clock_getres(which_clock, &rtn_tp);
- if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp))) {
+ if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp)))
error = -EFAULT;
- }
return error;
}
const struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec t;
- if (invalid_clockid(which_clock))
+ if (!kc)
return -EINVAL;
+ if (!kc->nsleep)
+ return -ENANOSLEEP_NOTSUP;
if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
return -EFAULT;
if (!timespec_valid(&t))
return -EINVAL;
- return CLOCK_DISPATCH(which_clock, nsleep,
- (which_clock, flags, &t, rmtp));
-}
-
-/*
- * nanosleep_restart for monotonic and realtime clocks
- */
-static int common_nsleep_restart(struct restart_block *restart_block)
-{
- return hrtimer_nanosleep_restart(restart_block);
+ return kc->nsleep(which_clock, flags, &t, rmtp);
}
/*
* This will restart clock_nanosleep. This is required only by
* compat_clock_nanosleep_restart for now.
*/
-long
-clock_nanosleep_restart(struct restart_block *restart_block)
+long clock_nanosleep_restart(struct restart_block *restart_block)
{
- clockid_t which_clock = restart_block->arg0;
+ clockid_t which_clock = restart_block->nanosleep.index;
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+
+ if (WARN_ON_ONCE(!kc || !kc->nsleep_restart))
+ return -EINVAL;
- return CLOCK_DISPATCH(which_clock, nsleep_restart,
- (restart_block));
+ return kc->nsleep_restart(restart_block);
}
static int __init pm_start_workqueue(void)
{
- pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0);
+ pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
return pm_wq ? 0 : -ENOMEM;
}
*/
#define TIMEOUT (20 * HZ)
-static inline int freezeable(struct task_struct * p)
+static inline int freezable(struct task_struct * p)
{
if ((p == current) ||
(p->flags & PF_NOFREEZE) ||
todo = 0;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
- if (frozen(p) || !freezeable(p))
+ if (frozen(p) || !freezable(p))
continue;
if (!freeze_task(p, sig_only))
read_lock(&tasklist_lock);
do_each_thread(g, p) {
- if (!freezeable(p))
+ if (!freezable(p))
continue;
if (nosig_only && should_send_signal(p))
swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
unsigned int nr_pages, unsigned int nr_highmem)
{
- int error = 0;
-
if (nr_highmem > 0) {
- error = get_highmem_buffer(PG_ANY);
- if (error)
+ if (get_highmem_buffer(PG_ANY))
goto err_out;
if (nr_highmem > alloc_highmem) {
nr_highmem -= alloc_highmem;
err_out:
swsusp_free();
- return error;
+ return -ENOMEM;
}
asmlinkage int swsusp_save(void)
int dmesg_restrict;
#endif
+static int syslog_action_restricted(int type)
+{
+ if (dmesg_restrict)
+ return 1;
+ /* Unless restricted, we allow "read all" and "get buffer size" for everybody */
+ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER;
+}
+
+static int check_syslog_permissions(int type, bool from_file)
+{
+ /*
+ * If this is from /proc/kmsg and we've already opened it, then we've
+ * already done the capabilities checks at open time.
+ */
+ if (from_file && type != SYSLOG_ACTION_OPEN)
+ return 0;
+
+ if (syslog_action_restricted(type)) {
+ if (capable(CAP_SYSLOG))
+ return 0;
+ /* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */
+ if (capable(CAP_SYS_ADMIN)) {
+ WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
+ "but no CAP_SYSLOG (deprecated).\n");
+ return 0;
+ }
+ return -EPERM;
+ }
+ return 0;
+}
+
int do_syslog(int type, char __user *buf, int len, bool from_file)
{
unsigned i, j, limit, count;
int do_clear = 0;
char c;
- int error = 0;
+ int error;
- /*
- * If this is from /proc/kmsg we only do the capabilities checks
- * at open time.
- */
- if (type == SYSLOG_ACTION_OPEN || !from_file) {
- if (dmesg_restrict && !capable(CAP_SYSLOG))
- goto warn; /* switch to return -EPERM after 2.6.39 */
- if ((type != SYSLOG_ACTION_READ_ALL &&
- type != SYSLOG_ACTION_SIZE_BUFFER) &&
- !capable(CAP_SYSLOG))
- goto warn; /* switch to return -EPERM after 2.6.39 */
- }
+ error = check_syslog_permissions(type, from_file);
+ if (error)
+ goto out;
error = security_syslog(type);
if (error)
}
out:
return error;
-warn:
- /* remove after 2.6.39 */
- if (capable(CAP_SYS_ADMIN))
- WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
- "but no CAP_SYSLOG (deprecated and denied).\n");
- return -EPERM;
}
SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
return !err;
}
-int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task)
{
int retval;
* Performs checks and sets PT_PTRACED.
* Should be used by all ptrace implementations for PTRACE_TRACEME.
*/
-int ptrace_traceme(void)
+static int ptrace_traceme(void)
{
int ret = -EPERM;
return false;
}
-int ptrace_detach(struct task_struct *child, unsigned int data)
+static int ptrace_detach(struct task_struct *child, unsigned int data)
{
bool dead = false;
child->exit_code = data;
dead = __ptrace_detach(current, child);
if (!child->exit_state)
- wake_up_process(child);
+ wake_up_state(child, TASK_TRACED | TASK_STOPPED);
}
write_unlock_irq(&tasklist_lock);
put_pid(waiter->deadlock_task_pid);
TRACE_WARN_ON(!plist_node_empty(&waiter->list_entry));
TRACE_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
- TRACE_WARN_ON(waiter->task);
memset(waiter, 0x22, sizeof(*waiter));
}
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/sched.h>
-#include <linux/smp_lock.h>
#include <linux/spinlock.h>
#include <linux/sysdev.h>
#include <linux/timer.h>
int opcode;
int opdata;
int mutexes[MAX_RT_TEST_MUTEXES];
- int bkl;
int event;
struct sys_device sysdev;
};
RTTEST_LOCKINTNOWAIT, /* 6 Lock interruptible no wait in wakeup, data = lockindex */
RTTEST_LOCKCONT, /* 7 Continue locking after the wakeup delay */
RTTEST_UNLOCK, /* 8 Unlock, data = lockindex */
- RTTEST_LOCKBKL, /* 9 Lock BKL */
- RTTEST_UNLOCKBKL, /* 10 Unlock BKL */
- RTTEST_SIGNAL, /* 11 Signal other test thread, data = thread id */
+ /* 9, 10 - reserved for BKL commemoration */
+ RTTEST_SIGNAL = 11, /* 11 Signal other test thread, data = thread id */
RTTEST_RESETEVENT = 98, /* 98 Reset event counter */
RTTEST_RESET = 99, /* 99 Reset all pending operations */
};
td->mutexes[i] = 0;
}
}
-
- if (!lockwakeup && td->bkl == 4) {
-#ifdef CONFIG_LOCK_KERNEL
- unlock_kernel();
-#endif
- td->bkl = 0;
- }
return 0;
case RTTEST_RESETEVENT:
td->mutexes[id] = 0;
return 0;
- case RTTEST_LOCKBKL:
- if (td->bkl)
- return 0;
- td->bkl = 1;
-#ifdef CONFIG_LOCK_KERNEL
- lock_kernel();
-#endif
- td->bkl = 4;
- return 0;
-
- case RTTEST_UNLOCKBKL:
- if (td->bkl != 4)
- break;
-#ifdef CONFIG_LOCK_KERNEL
- unlock_kernel();
-#endif
- td->bkl = 0;
- return 0;
-
default:
break;
}
td->event = atomic_add_return(1, &rttest_event);
break;
- case RTTEST_LOCKBKL:
default:
break;
}
td->event = atomic_add_return(1, &rttest_event);
return;
- case RTTEST_LOCKBKL:
- return;
default:
return;
}
spin_lock(&rttest_lock);
curr += sprintf(curr,
- "O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, K: %d, M:",
+ "O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, M:",
td->opcode, td->event, tsk->state,
(MAX_RT_PRIO - 1) - tsk->prio,
(MAX_RT_PRIO - 1) - tsk->normal_prio,
- tsk->pi_blocked_on, td->bkl);
+ tsk->pi_blocked_on);
for (i = MAX_RT_TEST_MUTEXES - 1; i >=0 ; i--)
curr += sprintf(curr, "%d", td->mutexes[i]);
/*
* lock->owner state tracking:
*
- * lock->owner holds the task_struct pointer of the owner. Bit 0 and 1
- * are used to keep track of the "owner is pending" and "lock has
- * waiters" state.
+ * lock->owner holds the task_struct pointer of the owner. Bit 0
+ * is used to keep track of the "lock has waiters" state.
*
- * owner bit1 bit0
- * NULL 0 0 lock is free (fast acquire possible)
- * NULL 0 1 invalid state
- * NULL 1 0 Transitional State*
- * NULL 1 1 invalid state
- * taskpointer 0 0 lock is held (fast release possible)
- * taskpointer 0 1 task is pending owner
- * taskpointer 1 0 lock is held and has waiters
- * taskpointer 1 1 task is pending owner and lock has more waiters
- *
- * Pending ownership is assigned to the top (highest priority)
- * waiter of the lock, when the lock is released. The thread is woken
- * up and can now take the lock. Until the lock is taken (bit 0
- * cleared) a competing higher priority thread can steal the lock
- * which puts the woken up thread back on the waiters list.
+ * owner bit0
+ * NULL 0 lock is free (fast acquire possible)
+ * NULL 1 lock is free and has waiters and the top waiter
+ * is going to take the lock*
+ * taskpointer 0 lock is held (fast release possible)
+ * taskpointer 1 lock is held and has waiters**
*
* The fast atomic compare exchange based acquire and release is only
- * possible when bit 0 and 1 of lock->owner are 0.
+ * possible when bit 0 of lock->owner is 0.
+ *
+ * (*) It also can be a transitional state when grabbing the lock
+ * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
+ * we need to set the bit0 before looking at the lock, and the owner may be
+ * NULL in this small time, hence this can be a transitional state.
*
- * (*) There's a small time where the owner can be NULL and the
- * "lock has waiters" bit is set. This can happen when grabbing the lock.
- * To prevent a cmpxchg of the owner releasing the lock, we need to set this
- * bit before looking at the lock, hence the reason this is a transitional
- * state.
+ * (**) There is a small time when bit 0 is set but there are no
+ * waiters. This can happen when grabbing the lock in the slow path.
+ * To prevent a cmpxchg of the owner releasing the lock, we need to
+ * set this bit before looking at the lock.
*/
static void
-rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
- unsigned long mask)
+rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
{
- unsigned long val = (unsigned long)owner | mask;
+ unsigned long val = (unsigned long)owner;
if (rt_mutex_has_waiters(lock))
val |= RT_MUTEX_HAS_WAITERS;
* reached or the state of the chain has changed while we
* dropped the locks.
*/
- if (!waiter || !waiter->task)
+ if (!waiter)
goto out_unlock_pi;
/*
* Check the orig_waiter state. After we dropped the locks,
- * the previous owner of the lock might have released the lock
- * and made us the pending owner:
+ * the previous owner of the lock might have released the lock.
*/
- if (orig_waiter && !orig_waiter->task)
+ if (orig_waiter && !rt_mutex_owner(orig_lock))
goto out_unlock_pi;
/*
/* Release the task */
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ if (!rt_mutex_owner(lock)) {
+ /*
+ * If the requeue above changed the top waiter, then we need
+ * to wake the new top waiter up to try to get the lock.
+ */
+
+ if (top_waiter != rt_mutex_top_waiter(lock))
+ wake_up_process(rt_mutex_top_waiter(lock)->task);
+ raw_spin_unlock(&lock->wait_lock);
+ goto out_put_task;
+ }
put_task_struct(task);
/* Grab the next task */
return ret;
}
-/*
- * Optimization: check if we can steal the lock from the
- * assigned pending owner [which might not have taken the
- * lock yet]:
- */
-static inline int try_to_steal_lock(struct rt_mutex *lock,
- struct task_struct *task)
-{
- struct task_struct *pendowner = rt_mutex_owner(lock);
- struct rt_mutex_waiter *next;
- unsigned long flags;
-
- if (!rt_mutex_owner_pending(lock))
- return 0;
-
- if (pendowner == task)
- return 1;
-
- raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
- if (task->prio >= pendowner->prio) {
- raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
- return 0;
- }
-
- /*
- * Check if a waiter is enqueued on the pending owners
- * pi_waiters list. Remove it and readjust pending owners
- * priority.
- */
- if (likely(!rt_mutex_has_waiters(lock))) {
- raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
- return 1;
- }
-
- /* No chain handling, pending owner is not blocked on anything: */
- next = rt_mutex_top_waiter(lock);
- plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
- __rt_mutex_adjust_prio(pendowner);
- raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
- /*
- * We are going to steal the lock and a waiter was
- * enqueued on the pending owners pi_waiters queue. So
- * we have to enqueue this waiter into
- * task->pi_waiters list. This covers the case,
- * where task is boosted because it holds another
- * lock and gets unboosted because the booster is
- * interrupted, so we would delay a waiter with higher
- * priority as task->normal_prio.
- *
- * Note: in the rare case of a SCHED_OTHER task changing
- * its priority and thus stealing the lock, next->task
- * might be task:
- */
- if (likely(next->task != task)) {
- raw_spin_lock_irqsave(&task->pi_lock, flags);
- plist_add(&next->pi_list_entry, &task->pi_waiters);
- __rt_mutex_adjust_prio(task);
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- }
- return 1;
-}
-
/*
* Try to take an rt-mutex
*
- * This fails
- * - when the lock has a real owner
- * - when a different pending owner exists and has higher priority than current
- *
* Must be called with lock->wait_lock held.
+ *
+ * @lock: the lock to be acquired.
+ * @task: the task which wants to acquire the lock
+ * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
*/
-static int try_to_take_rt_mutex(struct rt_mutex *lock)
+static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+ struct rt_mutex_waiter *waiter)
{
/*
* We have to be careful here if the atomic speedups are
*/
mark_rt_mutex_waiters(lock);
- if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current))
+ if (rt_mutex_owner(lock))
return 0;
+ /*
+ * It will get the lock because of one of these conditions:
+ * 1) there is no waiter
+ * 2) higher priority than waiters
+ * 3) it is top waiter
+ */
+ if (rt_mutex_has_waiters(lock)) {
+ if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+ if (!waiter || waiter != rt_mutex_top_waiter(lock))
+ return 0;
+ }
+ }
+
+ if (waiter || rt_mutex_has_waiters(lock)) {
+ unsigned long flags;
+ struct rt_mutex_waiter *top;
+
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+ /* remove the queued waiter. */
+ if (waiter) {
+ plist_del(&waiter->list_entry, &lock->wait_list);
+ task->pi_blocked_on = NULL;
+ }
+
+ /*
+ * We have to enqueue the top waiter(if it exists) into
+ * task->pi_waiters list.
+ */
+ if (rt_mutex_has_waiters(lock)) {
+ top = rt_mutex_top_waiter(lock);
+ top->pi_list_entry.prio = top->list_entry.prio;
+ plist_add(&top->pi_list_entry, &task->pi_waiters);
+ }
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ }
+
/* We got the lock. */
debug_rt_mutex_lock(lock);
- rt_mutex_set_owner(lock, current, 0);
+ rt_mutex_set_owner(lock, task);
- rt_mutex_deadlock_account_lock(lock, current);
+ rt_mutex_deadlock_account_lock(lock, task);
return 1;
}
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ if (!owner)
+ return 0;
+
if (waiter == rt_mutex_top_waiter(lock)) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
/*
* Wake up the next waiter on the lock.
*
- * Remove the top waiter from the current tasks waiter list and from
- * the lock waiter list. Set it as pending owner. Then wake it up.
+ * Remove the top waiter from the current tasks waiter list and wake it up.
*
* Called with lock->wait_lock held.
*/
static void wakeup_next_waiter(struct rt_mutex *lock)
{
struct rt_mutex_waiter *waiter;
- struct task_struct *pendowner;
unsigned long flags;
raw_spin_lock_irqsave(¤t->pi_lock, flags);
waiter = rt_mutex_top_waiter(lock);
- plist_del(&waiter->list_entry, &lock->wait_list);
/*
* Remove it from current->pi_waiters. We do not adjust a
* lock->wait_lock.
*/
plist_del(&waiter->pi_list_entry, ¤t->pi_waiters);
- pendowner = waiter->task;
- waiter->task = NULL;
- rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
+ rt_mutex_set_owner(lock, NULL);
raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
- /*
- * Clear the pi_blocked_on variable and enqueue a possible
- * waiter into the pi_waiters list of the pending owner. This
- * prevents that in case the pending owner gets unboosted a
- * waiter with higher priority than pending-owner->normal_prio
- * is blocked on the unboosted (pending) owner.
- */
- raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
-
- WARN_ON(!pendowner->pi_blocked_on);
- WARN_ON(pendowner->pi_blocked_on != waiter);
- WARN_ON(pendowner->pi_blocked_on->lock != lock);
-
- pendowner->pi_blocked_on = NULL;
-
- if (rt_mutex_has_waiters(lock)) {
- struct rt_mutex_waiter *next;
-
- next = rt_mutex_top_waiter(lock);
- plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
- }
- raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
- wake_up_process(pendowner);
+ wake_up_process(waiter->task);
}
/*
- * Remove a waiter from a lock
+ * Remove a waiter from a lock and give up
*
- * Must be called with lock->wait_lock held
+ * Must be called with lock->wait_lock held and
+ * have just failed to try_to_take_rt_mutex().
*/
static void remove_waiter(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter)
raw_spin_lock_irqsave(¤t->pi_lock, flags);
plist_del(&waiter->list_entry, &lock->wait_list);
- waiter->task = NULL;
current->pi_blocked_on = NULL;
raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
- if (first && owner != current) {
+ if (!owner)
+ return;
+
+ if (first) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
* or TASK_UNINTERRUPTIBLE)
* @timeout: the pre-initialized and started timer, or NULL for none
* @waiter: the pre-initialized rt_mutex_waiter
- * @detect_deadlock: passed to task_blocks_on_rt_mutex
*
* lock->wait_lock must be held by the caller.
*/
static int __sched
__rt_mutex_slowlock(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- struct rt_mutex_waiter *waiter,
- int detect_deadlock)
+ struct rt_mutex_waiter *waiter)
{
int ret = 0;
for (;;) {
/* Try to acquire the lock: */
- if (try_to_take_rt_mutex(lock))
+ if (try_to_take_rt_mutex(lock, current, waiter))
break;
/*
break;
}
- /*
- * waiter->task is NULL the first time we come here and
- * when we have been woken up by the previous owner
- * but the lock got stolen by a higher prio task.
- */
- if (!waiter->task) {
- ret = task_blocks_on_rt_mutex(lock, waiter, current,
- detect_deadlock);
- /*
- * If we got woken up by the owner then start loop
- * all over without going into schedule to try
- * to get the lock now:
- */
- if (unlikely(!waiter->task)) {
- /*
- * Reset the return value. We might
- * have returned with -EDEADLK and the
- * owner released the lock while we
- * were walking the pi chain.
- */
- ret = 0;
- continue;
- }
- if (unlikely(ret))
- break;
- }
-
raw_spin_unlock(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
- if (waiter->task)
- schedule_rt_mutex(lock);
+ schedule_rt_mutex(lock);
raw_spin_lock(&lock->wait_lock);
set_current_state(state);
int ret = 0;
debug_rt_mutex_init_waiter(&waiter);
- waiter.task = NULL;
raw_spin_lock(&lock->wait_lock);
/* Try to acquire the lock again: */
- if (try_to_take_rt_mutex(lock)) {
+ if (try_to_take_rt_mutex(lock, current, NULL)) {
raw_spin_unlock(&lock->wait_lock);
return 0;
}
timeout->task = NULL;
}
- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
- detect_deadlock);
+ ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+
+ if (likely(!ret))
+ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
set_current_state(TASK_RUNNING);
- if (unlikely(waiter.task))
+ if (unlikely(ret))
remove_waiter(lock, &waiter);
/*
if (unlikely(timeout))
hrtimer_cancel(&timeout->timer);
- /*
- * Readjust priority, when we did not get the lock. We might
- * have been the pending owner and boosted. Since we did not
- * take the lock, the PI boost has to go.
- */
- if (unlikely(ret))
- rt_mutex_adjust_prio(current);
-
debug_rt_mutex_free_waiter(&waiter);
return ret;
if (likely(rt_mutex_owner(lock) != current)) {
- ret = try_to_take_rt_mutex(lock);
+ ret = try_to_take_rt_mutex(lock, current, NULL);
/*
* try_to_take_rt_mutex() sets the lock waiters
* bit unconditionally. Clean this up.
{
__rt_mutex_init(lock, NULL);
debug_rt_mutex_proxy_lock(lock, proxy_owner);
- rt_mutex_set_owner(lock, proxy_owner, 0);
+ rt_mutex_set_owner(lock, proxy_owner);
rt_mutex_deadlock_account_lock(lock, proxy_owner);
}
struct task_struct *proxy_owner)
{
debug_rt_mutex_proxy_unlock(lock);
- rt_mutex_set_owner(lock, NULL, 0);
+ rt_mutex_set_owner(lock, NULL);
rt_mutex_deadlock_account_unlock(proxy_owner);
}
raw_spin_lock(&lock->wait_lock);
- mark_rt_mutex_waiters(lock);
-
- if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
- /* We got the lock for task. */
- debug_rt_mutex_lock(lock);
- rt_mutex_set_owner(lock, task, 0);
+ if (try_to_take_rt_mutex(lock, task, NULL)) {
raw_spin_unlock(&lock->wait_lock);
- rt_mutex_deadlock_account_lock(lock, task);
return 1;
}
ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
- if (ret && !waiter->task) {
+ if (ret && !rt_mutex_owner(lock)) {
/*
* Reset the return value. We might have
* returned with -EDEADLK and the owner
*/
ret = 0;
}
+
+ if (unlikely(ret))
+ remove_waiter(lock, waiter);
+
raw_spin_unlock(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
set_current_state(TASK_INTERRUPTIBLE);
- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
- detect_deadlock);
+ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
set_current_state(TASK_RUNNING);
- if (unlikely(waiter->task))
+ if (unlikely(ret))
remove_waiter(lock, waiter);
/*
raw_spin_unlock(&lock->wait_lock);
- /*
- * Readjust priority, when we did not get the lock. We might have been
- * the pending owner and boosted. Since we did not take the lock, the
- * PI boost has to go.
- */
- if (unlikely(ret))
- rt_mutex_adjust_prio(current);
-
return ret;
}
/*
* lock->owner state tracking:
*/
-#define RT_MUTEX_OWNER_PENDING 1UL
-#define RT_MUTEX_HAS_WAITERS 2UL
-#define RT_MUTEX_OWNER_MASKALL 3UL
+#define RT_MUTEX_HAS_WAITERS 1UL
+#define RT_MUTEX_OWNER_MASKALL 1UL
static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
{
((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
}
-static inline struct task_struct *rt_mutex_real_owner(struct rt_mutex *lock)
-{
- return (struct task_struct *)
- ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
-}
-
-static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
-{
- return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
-}
-
/*
* PI-futex support (proxy locking functions, etc.):
*/
* 'curr' points to currently running entity on this cfs_rq.
* It is set to NULL otherwise (i.e when none are currently running).
*/
- struct sched_entity *curr, *next, *last;
+ struct sched_entity *curr, *next, *last, *skip;
unsigned int nr_spread_over;
struct task_group *tg;
struct cgroup_subsys_state *css;
- if (p->flags & PF_EXITING)
- return &root_task_group;
-
css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
lockdep_is_held(&task_rq(p)->lock));
tg = container_of(css, struct task_group, css);
__release(rq2->lock);
}
+#else /* CONFIG_SMP */
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+ __acquires(rq1->lock)
+ __acquires(rq2->lock)
+{
+ BUG_ON(!irqs_disabled());
+ BUG_ON(rq1 != rq2);
+ raw_spin_lock(&rq1->lock);
+ __acquire(rq2->lock); /* Fake it out ;) */
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+ __releases(rq1->lock)
+ __releases(rq2->lock)
+{
+ BUG_ON(rq1 != rq2);
+ raw_spin_unlock(&rq1->lock);
+ __release(rq2->lock);
+}
+
#endif
static void calc_load_account_idle(struct rq *this_rq);
*/
if (hardirq_count())
__this_cpu_add(cpu_hardirq_time, delta);
- else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
__this_cpu_add(cpu_softirq_time, delta);
irq_time_write_end();
sched_rt_avg_update(rq, irq_delta);
}
+static int irqtime_account_hi_update(void)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_hardirq_time);
+ if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_softirq_time);
+ if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+#define sched_clock_irqtime (0)
+
static void update_rq_clock_task(struct rq *rq, s64 delta)
{
rq->clock_task += delta;
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
- int oldprio, int running)
+ int oldprio)
{
if (prev_class != p->sched_class) {
if (prev_class->switched_from)
- prev_class->switched_from(rq, p, running);
- p->sched_class->switched_to(rq, p, running);
- } else
- p->sched_class->prio_changed(rq, p, oldprio, running);
+ prev_class->switched_from(rq, p);
+ p->sched_class->switched_to(rq, p);
+ } else if (oldprio != p->prio)
+ p->sched_class->prio_changed(rq, p, oldprio);
}
static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
* yield - it could be a while.
*/
if (unlikely(on_rq)) {
- schedule_timeout_uninterruptible(1);
+ ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
+
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_hrtimeout(&to, HRTIMER_MODE_REL);
continue;
}
EXPORT_SYMBOL_GPL(kick_process);
#endif /* CONFIG_SMP */
-/**
- * task_oncpu_function_call - call a function on the cpu on which a task runs
- * @p: the task to evaluate
- * @func: the function to be called
- * @info: the function call argument
- *
- * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
- */
-void task_oncpu_function_call(struct task_struct *p,
- void (*func) (void *info), void *info)
-{
- int cpu;
-
- preempt_disable();
- cpu = task_cpu(p);
- if (task_curr(p))
- smp_call_function_single(cpu, func, info, 1);
- preempt_enable();
-}
-
#ifdef CONFIG_SMP
/*
* ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
+ p->se.vruntime = 0;
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
+ sched_info_switch(prev, next);
+ perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
prepare_lock_switch(rq, next);
prepare_arch_switch(next);
+ trace_sched_switch(prev, next);
}
/**
struct mm_struct *mm, *oldmm;
prepare_task_switch(rq, prev, next);
- trace_sched_switch(prev, next);
+
mm = next->mm;
oldmm = prev->active_mm;
/*
}
}
+/*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled, cputime64_t *target_cputime64)
+{
+ cputime64_t tmp = cputime_to_cputime64(cputime);
+
+ /* Add system time to process. */
+ p->stime = cputime_add(p->stime, cputime);
+ p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
+ account_group_system_time(p, cputime);
+
+ /* Add system time to cpustat. */
+ *target_cputime64 = cputime64_add(*target_cputime64, tmp);
+ cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+
+ /* Account for system time used */
+ acct_update_integrals(p);
+}
+
/*
* Account system cpu time to a process.
* @p: the process that the cpu time gets accounted to
cputime_t cputime, cputime_t cputime_scaled)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- cputime64_t tmp;
+ cputime64_t *target_cputime64;
if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
account_guest_time(p, cputime, cputime_scaled);
return;
}
- /* Add system time to process. */
- p->stime = cputime_add(p->stime, cputime);
- p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
- account_group_system_time(p, cputime);
-
- /* Add system time to cpustat. */
- tmp = cputime_to_cputime64(cputime);
if (hardirq_count() - hardirq_offset)
- cpustat->irq = cputime64_add(cpustat->irq, tmp);
+ target_cputime64 = &cpustat->irq;
else if (in_serving_softirq())
- cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+ target_cputime64 = &cpustat->softirq;
else
- cpustat->system = cputime64_add(cpustat->system, tmp);
+ target_cputime64 = &cpustat->system;
- cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
-
- /* Account for system time used */
- acct_update_integrals(p);
+ __account_system_time(p, cputime, cputime_scaled, target_cputime64);
}
/*
* Account for involuntary wait time.
- * @steal: the cpu time spent in involuntary wait
+ * @cputime: the cpu time spent in involuntary wait
*/
void account_steal_time(cputime_t cputime)
{
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ * - check for guest_time
+ * - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq)
+{
+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+ if (irqtime_account_hi_update()) {
+ cpustat->irq = cputime64_add(cpustat->irq, tmp);
+ } else if (irqtime_account_si_update()) {
+ cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+ } else if (this_cpu_ksoftirqd() == p) {
+ /*
+ * ksoftirqd time do not get accounted in cpu_softirq_time.
+ * So, we have to handle it separately here.
+ * Also, p->stime needs to be updated for ksoftirqd.
+ */
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ &cpustat->softirq);
+ } else if (user_tick) {
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else if (p == rq->idle) {
+ account_idle_time(cputime_one_jiffy);
+ } else if (p->flags & PF_VCPU) { /* System time or guest time */
+ account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else {
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ &cpustat->system);
+ }
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+ int i;
+ struct rq *rq = this_rq();
+
+ for (i = 0; i < ticks; i++)
+ irqtime_account_process_tick(current, 0, rq);
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+static void irqtime_account_idle_ticks(int ticks) {}
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq) {}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
/*
* Account a single tick of cpu time.
* @p: the process that the cpu time gets accounted to
cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
struct rq *rq = this_rq();
+ if (sched_clock_irqtime) {
+ irqtime_account_process_tick(p, user_tick, rq);
+ return;
+ }
+
if (user_tick)
account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
*/
void account_idle_ticks(unsigned long ticks)
{
+
+ if (sched_clock_irqtime) {
+ irqtime_account_idle_ticks(ticks);
+ return;
+ }
+
account_idle_time(jiffies_to_cputime(ticks));
}
rq->skip_clock_update = 0;
if (likely(prev != next)) {
- sched_info_switch(prev, next);
- perf_event_task_sched_out(prev, next);
-
rq->nr_switches++;
rq->curr = next;
++*switch_count;
{
__wake_up_common(q, mode, 1, 0, key);
}
+EXPORT_SYMBOL_GPL(__wake_up_locked_key);
/**
* __wake_up_sync_key - wake up threads blocked on a waitqueue.
if (running)
p->sched_class->set_curr_task(rq);
- if (on_rq) {
+ if (on_rq)
enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
- check_class_changed(rq, p, prev_class, oldprio, running);
- }
+ check_class_changed(rq, p, prev_class, oldprio);
task_rq_unlock(rq, &flags);
}
param->sched_priority > rlim_rtprio)
return -EPERM;
}
+
/*
- * Like positive nice levels, dont allow tasks to
- * move out of SCHED_IDLE either:
+ * Treat SCHED_IDLE as nice 20. Only allow a switch to
+ * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
*/
- if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
- return -EPERM;
+ if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
+ if (!can_nice(p, TASK_NICE(p)))
+ return -EPERM;
+ }
/* can't change other user's priorities */
if (!check_same_owner(p))
if (running)
p->sched_class->set_curr_task(rq);
- if (on_rq) {
+ if (on_rq)
activate_task(rq, p, 0);
- check_class_changed(rq, p, prev_class, oldprio, running);
- }
+ check_class_changed(rq, p, prev_class, oldprio);
__task_rq_unlock(rq);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}
EXPORT_SYMBOL(yield);
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ *
+ * Returns true if we indeed boosted the target task.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+ struct task_struct *curr = current;
+ struct rq *rq, *p_rq;
+ unsigned long flags;
+ bool yielded = 0;
+
+ local_irq_save(flags);
+ rq = this_rq();
+
+again:
+ p_rq = task_rq(p);
+ double_rq_lock(rq, p_rq);
+ while (task_rq(p) != p_rq) {
+ double_rq_unlock(rq, p_rq);
+ goto again;
+ }
+
+ if (!curr->sched_class->yield_to_task)
+ goto out;
+
+ if (curr->sched_class != p->sched_class)
+ goto out;
+
+ if (task_running(p_rq, p) || p->state)
+ goto out;
+
+ yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+ if (yielded) {
+ schedstat_inc(rq, yld_count);
+ /*
+ * Make p's CPU reschedule; pick_next_entity takes care of
+ * fairness.
+ */
+ if (preempt && rq != p_rq)
+ resched_task(p_rq->curr);
+ }
+
+out:
+ double_rq_unlock(rq, p_rq);
+ local_irq_restore(flags);
+
+ if (yielded)
+ schedule();
+
+ return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
* The idle tasks have their own, simple scheduling class:
*/
idle->sched_class = &idle_sched_class;
- ftrace_graph_init_task(idle);
+ ftrace_graph_init_idle_task(idle, cpu);
}
/*
INIT_LIST_HEAD(&cfs_rq->tasks);
#ifdef CONFIG_FAIR_GROUP_SCHED
cfs_rq->rq = rq;
+ /* allow initial update_cfs_load() to truncate */
+#ifdef CONFIG_SMP
+ cfs_rq->load_stamp = 1;
+#endif
#endif
cfs_rq->min_vruntime = (u64)(-(1LL << 20));
}
#ifdef CONFIG_MAGIC_SYSRQ
static void normalize_task(struct rq *rq, struct task_struct *p)
{
+ const struct sched_class *prev_class = p->sched_class;
+ int old_prio = p->prio;
int on_rq;
on_rq = p->se.on_rq;
activate_task(rq, p, 0);
resched_task(rq->curr);
}
+
+ check_class_changed(rq, p, prev_class, old_prio);
}
void normalize_rt_tasks(void)
/* Propagate contribution to hierarchy */
raw_spin_lock_irqsave(&rq->lock, flags);
for_each_sched_entity(se)
- update_cfs_shares(group_cfs_rq(se), 0);
+ update_cfs_shares(group_cfs_rq(se));
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
}
static void
-cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup *old_cgrp, struct task_struct *task)
{
/*
* cgroup_exit() is called in the copy_process() failure path.
static void __init autogroup_init(struct task_struct *init_task)
{
autogroup_default.tg = &root_task_group;
- root_task_group.autogroup = &autogroup_default;
kref_init(&autogroup_default.kref);
init_rwsem(&autogroup_default.lock);
init_task->signal->autogroup = &autogroup_default;
static inline bool task_group_is_autogroup(struct task_group *tg)
{
- return tg != &root_task_group && tg->autogroup;
+ return !!tg->autogroup;
}
static inline struct task_group *
p->signal->autogroup = autogroup_kref_get(ag);
+ if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+ goto out;
+
t = p;
do {
sched_move_task(t);
} while_each_thread(p, t);
+out:
unlock_task_sighand(p, &flags);
autogroup_kref_put(prev);
}
{
struct autogroup *ag = autogroup_task_get(p);
+ if (!task_group_is_autogroup(ag->tg))
+ goto out;
+
down_read(&ag->lock);
seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
up_read(&ag->lock);
+out:
autogroup_kref_put(ag);
}
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SCHED_DEBUG
static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
{
- int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
- if (!enabled || !tg->autogroup)
+ if (!task_group_is_autogroup(tg))
return 0;
return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
#ifdef CONFIG_SCHED_AUTOGROUP
struct autogroup {
+ /*
+ * reference doesn't mean how many thread attach to this
+ * autogroup now. It just stands for the number of task
+ * could use this autogroup.
+ */
struct kref kref;
struct task_group *tg;
struct rw_semaphore lock;
raw_spin_lock_irqsave(&rq->lock, flags);
if (cfs_rq->rb_leftmost)
- MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
+ MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
last = __pick_last_entity(cfs_rq);
if (last)
max_vruntime = last->vruntime;
*/
unsigned int sysctl_sched_child_runs_first __read_mostly;
-/*
- * sys_sched_yield() compat mode
- *
- * This option switches the agressive yield implementation of the
- * old scheduler back on.
- */
-unsigned int __read_mostly sysctl_sched_compat_yield;
-
/*
* SCHED_OTHER wake-up granularity.
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
-static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = cfs_rq->rb_leftmost;
return rb_entry(left, struct sched_entity, run_node);
}
+static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+{
+ struct rb_node *next = rb_next(&se->run_node);
+
+ if (!next)
+ return NULL;
+
+ return rb_entry(next, struct sched_entity, run_node);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
* Scheduling class statistics methods:
*/
-#ifdef CONFIG_SCHED_DEBUG
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
}
static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+static void update_cfs_shares(struct cfs_rq *cfs_rq);
/*
* Update the current task's runtime statistics. Skip current tasks that
now - cfs_rq->load_last > 4 * period) {
cfs_rq->load_period = 0;
cfs_rq->load_avg = 0;
+ delta = period - 1;
}
cfs_rq->load_stamp = now;
list_del_leaf_cfs_rq(cfs_rq);
}
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
- long weight_delta)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
long load_weight, load, shares;
- load = cfs_rq->load.weight + weight_delta;
+ load = cfs_rq->load.weight;
load_weight = atomic_read(&tg->load_weight);
- load_weight -= cfs_rq->load_contribution;
load_weight += load;
+ load_weight -= cfs_rq->load_contribution;
shares = (tg->shares * load);
if (load_weight)
{
if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
}
# else /* CONFIG_SMP */
{
}
-static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
- long weight_delta)
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
return tg->shares;
}
account_entity_enqueue(cfs_rq, se);
}
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static void update_cfs_shares(struct cfs_rq *cfs_rq)
{
struct task_group *tg;
struct sched_entity *se;
if (likely(se->load.weight == tg->shares))
return;
#endif
- shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
+ shares = calc_cfs_shares(cfs_rq, tg);
reweight_entity(cfs_rq_of(se), se, shares);
}
{
}
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
{
}
*/
update_curr(cfs_rq);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, se->load.weight);
account_entity_enqueue(cfs_rq, se);
+ update_cfs_shares(cfs_rq);
if (flags & ENQUEUE_WAKEUP) {
place_entity(cfs_rq, se, 0);
list_add_leaf_cfs_rq(cfs_rq);
}
-static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies_last(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->last == se)
+ cfs_rq->last = NULL;
+ else
+ break;
+ }
+}
+
+static void __clear_buddies_next(struct sched_entity *se)
{
- if (!se || cfs_rq->last == se)
- cfs_rq->last = NULL;
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->next == se)
+ cfs_rq->next = NULL;
+ else
+ break;
+ }
+}
- if (!se || cfs_rq->next == se)
- cfs_rq->next = NULL;
+static void __clear_buddies_skip(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->skip == se)
+ cfs_rq->skip = NULL;
+ else
+ break;
+ }
}
static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- for_each_sched_entity(se)
- __clear_buddies(cfs_rq_of(se), se);
+ if (cfs_rq->last == se)
+ __clear_buddies_last(se);
+
+ if (cfs_rq->next == se)
+ __clear_buddies_next(se);
+
+ if (cfs_rq->skip == se)
+ __clear_buddies_skip(se);
}
static void
update_cfs_load(cfs_rq, 0);
account_entity_dequeue(cfs_rq, se);
update_min_vruntime(cfs_rq);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
/*
* Normalize the entity after updating the min_vruntime because the
return;
if (cfs_rq->nr_running > 1) {
- struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
s64 delta = curr->vruntime - se->vruntime;
if (delta < 0)
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
+/*
+ * Pick the next process, keeping these things in mind, in this order:
+ * 1) keep things fair between processes/task groups
+ * 2) pick the "next" process, since someone really wants that to run
+ * 3) pick the "last" process, for cache locality
+ * 4) do not run the "skip" process, if something else is available
+ */
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
struct sched_entity *left = se;
- if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
- se = cfs_rq->next;
+ /*
+ * Avoid running the skip buddy, if running something else can
+ * be done without getting too unfair.
+ */
+ if (cfs_rq->skip == se) {
+ struct sched_entity *second = __pick_next_entity(se);
+ if (second && wakeup_preempt_entity(second, left) < 1)
+ se = second;
+ }
/*
* Prefer last buddy, try to return the CPU to a preempted task.
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
se = cfs_rq->last;
+ /*
+ * Someone really wants this to run. If it's not unfair, run it.
+ */
+ if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+ se = cfs_rq->next;
+
clear_buddies(cfs_rq, se);
return se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
hrtick_update(rq);
struct cfs_rq *cfs_rq = cfs_rq_of(se);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
hrtick_update(rq);
}
-/*
- * sched_yield() support is very simple - we dequeue and enqueue.
- *
- * If compat_yield is turned on then we requeue to the end of the tree.
- */
-static void yield_task_fair(struct rq *rq)
-{
- struct task_struct *curr = rq->curr;
- struct cfs_rq *cfs_rq = task_cfs_rq(curr);
- struct sched_entity *rightmost, *se = &curr->se;
-
- /*
- * Are we the only task in the tree?
- */
- if (unlikely(cfs_rq->nr_running == 1))
- return;
-
- clear_buddies(cfs_rq, se);
-
- if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
- update_rq_clock(rq);
- /*
- * Update run-time statistics of the 'current'.
- */
- update_curr(cfs_rq);
-
- return;
- }
- /*
- * Find the rightmost entry in the rbtree:
- */
- rightmost = __pick_last_entity(cfs_rq);
- /*
- * Already in the rightmost position?
- */
- if (unlikely(!rightmost || entity_before(rightmost, se)))
- return;
-
- /*
- * Minimally necessary key value to be last in the tree:
- * Upon rescheduling, sched_class::put_prev_task() will place
- * 'current' within the tree based on its new key value.
- */
- se->vruntime = rightmost->vruntime + 1;
-}
-
#ifdef CONFIG_SMP
static void task_waking_fair(struct rq *rq, struct task_struct *p)
}
}
+static void set_skip_buddy(struct sched_entity *se)
+{
+ if (likely(task_of(se)->policy != SCHED_IDLE)) {
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->skip = se;
+ }
+}
+
/*
* Preempt the current task with a newly woken task if needed:
*/
if (test_tsk_need_resched(curr))
return;
+ /* Idle tasks are by definition preempted by non-idle tasks. */
+ if (unlikely(curr->policy == SCHED_IDLE) &&
+ likely(p->policy != SCHED_IDLE))
+ goto preempt;
+
/*
- * Batch and idle tasks do not preempt (their preemption is driven by
- * the tick):
+ * Batch and idle tasks do not preempt non-idle tasks (their preemption
+ * is driven by the tick):
*/
if (unlikely(p->policy != SCHED_NORMAL))
return;
- /* Idle tasks are by definition preempted by everybody. */
- if (unlikely(curr->policy == SCHED_IDLE))
- goto preempt;
if (!sched_feat(WAKEUP_PREEMPT))
return;
}
}
+/*
+ * sched_yield() is very simple
+ *
+ * The magic of dealing with the ->skip buddy is in pick_next_entity.
+ */
+static void yield_task_fair(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+ struct sched_entity *se = &curr->se;
+
+ /*
+ * Are we the only task in the tree?
+ */
+ if (unlikely(rq->nr_running == 1))
+ return;
+
+ clear_buddies(cfs_rq, se);
+
+ if (curr->policy != SCHED_BATCH) {
+ update_rq_clock(rq);
+ /*
+ * Update run-time statistics of the 'current'.
+ */
+ update_curr(cfs_rq);
+ }
+
+ set_skip_buddy(se);
+}
+
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+ struct sched_entity *se = &p->se;
+
+ if (!se->on_rq)
+ return false;
+
+ /* Tell the scheduler that we'd really like pse to run next. */
+ set_next_buddy(se);
+
+ yield_task_fair(rq);
+
+ return true;
+}
+
#ifdef CONFIG_SMP
/**************************************************
* Fair scheduling class load-balancing methods:
* We need to update shares after updating tg->load_weight in
* order to adjust the weight of groups with long running tasks.
*/
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
* @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @sd_idle: Idle status of the sched_domain containing group.
* @local_group: Does group contain this_cpu.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
*/
static inline void update_sg_lb_stats(struct sched_domain *sd,
struct sched_group *group, int this_cpu,
- enum cpu_idle_type idle, int load_idx, int *sd_idle,
+ enum cpu_idle_type idle, int load_idx,
int local_group, const struct cpumask *cpus,
int *balance, struct sg_lb_stats *sgs)
{
for_each_cpu_and(i, sched_group_cpus(group), cpus) {
struct rq *rq = cpu_rq(i);
- if (*sd_idle && rq->nr_running)
- *sd_idle = 0;
-
/* Bias balancing toward cpus of our domain */
if (local_group) {
if (idle_cpu(i) && !first_idle_cpu) {
/*
* Consider the group unbalanced when the imbalance is larger
- * than the average weight of two tasks.
+ * than the average weight of a task.
*
* APZ: with cgroup the avg task weight can vary wildly and
* might not be a suitable number - should we keep a
if (sgs->sum_nr_running)
avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
- if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
+ if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
sgs->group_imb = 1;
sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
* @sd: sched_domain whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
- * @sd_idle: Idle status of the sched_domain containing sg.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
*/
static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
- enum cpu_idle_type idle, int *sd_idle,
- const struct cpumask *cpus, int *balance,
- struct sd_lb_stats *sds)
+ enum cpu_idle_type idle, const struct cpumask *cpus,
+ int *balance, struct sd_lb_stats *sds)
{
struct sched_domain *child = sd->child;
struct sched_group *sg = sd->groups;
local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg));
memset(&sgs, 0, sizeof(sgs));
- update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, sd_idle,
+ update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx,
local_group, cpus, balance, &sgs);
if (local_group && !(*balance))
* @imbalance: Variable which stores amount of weighted load which should
* be moved to restore balance/put a group to idle.
* @idle: The idle status of this_cpu.
- * @sd_idle: The idleness of sd
* @cpus: The set of CPUs under consideration for load-balancing.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
unsigned long *imbalance, enum cpu_idle_type idle,
- int *sd_idle, const struct cpumask *cpus, int *balance)
+ const struct cpumask *cpus, int *balance)
{
struct sd_lb_stats sds;
* Compute the various statistics relavent for load balancing at
* this level.
*/
- update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
- balance, &sds);
-
- /* Cases where imbalance does not exist from POV of this_cpu */
- /* 1) this_cpu is not the appropriate cpu to perform load balancing
- * at this level.
- * 2) There is no busy sibling group to pull from.
- * 3) This group is the busiest group.
- * 4) This group is more busy than the avg busieness at this
- * sched_domain.
- * 5) The imbalance is within the specified limit.
- *
- * Note: when doing newidle balance, if the local group has excess
- * capacity (i.e. nr_running < group_capacity) and the busiest group
- * does not have any capacity, we force a load balance to pull tasks
- * to the local group. In this case, we skip past checks 3, 4 and 5.
+ update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds);
+
+ /*
+ * this_cpu is not the appropriate cpu to perform load balancing at
+ * this level.
*/
if (!(*balance))
goto ret;
check_asym_packing(sd, &sds, this_cpu, imbalance))
return sds.busiest;
+ /* There is no busy sibling group to pull tasks from */
if (!sds.busiest || sds.busiest_nr_running == 0)
goto out_balanced;
- /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+ /*
+ * If the busiest group is imbalanced the below checks don't
+ * work because they assumes all things are equal, which typically
+ * isn't true due to cpus_allowed constraints and the like.
+ */
+ if (sds.group_imb)
+ goto force_balance;
+
+ /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
!sds.busiest_has_capacity)
goto force_balance;
+ /*
+ * If the local group is more busy than the selected busiest group
+ * don't try and pull any tasks.
+ */
if (sds.this_load >= sds.max_load)
goto out_balanced;
+ /*
+ * Don't pull any tasks if this group is already above the domain
+ * average load.
+ */
sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
-
if (sds.this_load >= sds.avg_load)
goto out_balanced;
- /*
- * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
- * And to check for busy balance use !idle_cpu instead of
- * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
- * even when they are idle.
- */
- if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
- if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
- goto out_balanced;
- } else {
+ if (idle == CPU_IDLE) {
/*
* This cpu is idle. If the busiest group load doesn't
* have more tasks than the number of available cpu's and
* there is no imbalance between this and busiest group
* wrt to idle cpu's, it is balanced.
*/
- if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
+ if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
sds.busiest_nr_running <= sds.busiest_group_weight)
goto out_balanced;
+ } else {
+ /*
+ * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
+ * imbalance_pct to be conservative.
+ */
+ if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+ goto out_balanced;
}
force_balance:
/* Working cpumask for load_balance and load_balance_newidle. */
static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
-static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
+static int need_active_balance(struct sched_domain *sd, int idle,
int busiest_cpu, int this_cpu)
{
if (idle == CPU_NEWLY_IDLE) {
* move_tasks() will succeed. ld_moved will be true and this
* active balance code will not be triggered.
*/
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- return 0;
-
if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
return 0;
}
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
- int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+ int ld_moved, all_pinned = 0, active_balance = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
cpumask_copy(cpus, cpu_active_mask);
- /*
- * When power savings policy is enabled for the parent domain, idle
- * sibling can pick up load irrespective of busy siblings. In this case,
- * let the state of idle sibling percolate up as CPU_IDLE, instead of
- * portraying it as CPU_NOT_IDLE.
- */
- if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- sd_idle = 1;
-
schedstat_inc(sd, lb_count[idle]);
redo:
- group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+ group = find_busiest_group(sd, this_cpu, &imbalance, idle,
cpus, balance);
if (*balance == 0)
if (idle != CPU_NEWLY_IDLE)
sd->nr_balance_failed++;
- if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
- this_cpu)) {
+ if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) {
raw_spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the active_load_balance_cpu_stop,
sd->balance_interval *= 2;
}
- if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- ld_moved = -1;
-
goto out;
out_balanced:
(sd->balance_interval < sd->max_interval))
sd->balance_interval *= 2;
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- ld_moved = -1;
- else
- ld_moved = 0;
+ ld_moved = 0;
out:
return ld_moved;
}
if (load_balance(cpu, rq, sd, idle, &balance)) {
/*
* We've pulled tasks over so either we're no
- * longer idle, or one of our SMT siblings is
- * not idle.
+ * longer idle.
*/
idle = CPU_NOT_IDLE;
}
* Priority of the task has changed. Check to see if we preempt
* the current task.
*/
-static void prio_changed_fair(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
{
+ if (!p->se.on_rq)
+ return;
+
/*
* Reschedule if we are currently running on this runqueue and
* our priority decreased, or if we are not currently running on
* this runqueue and our priority is higher than the current's
*/
- if (running) {
+ if (rq->curr == p) {
if (p->prio > oldprio)
resched_task(rq->curr);
} else
check_preempt_curr(rq, p, 0);
}
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+ struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /*
+ * Ensure the task's vruntime is normalized, so that when its
+ * switched back to the fair class the enqueue_entity(.flags=0) will
+ * do the right thing.
+ *
+ * If it was on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it was !on_rq, then only when
+ * the task is sleeping will it still have non-normalized vruntime.
+ */
+ if (!se->on_rq && p->state != TASK_RUNNING) {
+ /*
+ * Fix up our vruntime so that the current sleep doesn't
+ * cause 'unlimited' sleep bonus.
+ */
+ place_entity(cfs_rq, se, 0);
+ se->vruntime -= cfs_rq->min_vruntime;
+ }
+}
+
/*
* We switched to the sched_fair class.
*/
-static void switched_to_fair(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
{
+ if (!p->se.on_rq)
+ return;
+
/*
* We were most likely switched from sched_rt, so
* kick off the schedule if running, otherwise just see
* if we can still preempt the current task.
*/
- if (running)
+ if (rq->curr == p)
resched_task(rq->curr);
else
check_preempt_curr(rq, p, 0);
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
+ .yield_to_task = yield_to_task_fair,
.check_preempt_curr = check_preempt_wakeup,
.task_fork = task_fork_fair,
.prio_changed = prio_changed_fair,
+ .switched_from = switched_from_fair,
.switched_to = switched_to_fair,
.get_rr_interval = get_rr_interval_fair,
{
}
-static void switched_to_idle(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_idle(struct rq *rq, struct task_struct *p)
{
- /* Can this actually happen?? */
- if (running)
- resched_task(rq->curr);
- else
- check_preempt_curr(rq, p, 0);
+ BUG();
}
-static void prio_changed_idle(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
{
- /* This can happen for hot plug CPUS */
-
- /*
- * Reschedule if we are currently running on this runqueue and
- * our priority decreased, or if we are not currently running on
- * this runqueue and our priority is higher than the current's
- */
- if (running) {
- if (p->prio > oldprio)
- resched_task(rq->curr);
- } else
- check_preempt_curr(rq, p, 0);
+ BUG();
}
static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
- int this_cpu = smp_processor_id();
struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
struct sched_rt_entity *rt_se;
- rt_se = rt_rq->tg->rt_se[this_cpu];
+ int cpu = cpu_of(rq_of_rt_rq(rt_rq));
+
+ rt_se = rt_rq->tg->rt_se[cpu];
if (rt_rq->rt_nr_running) {
if (rt_se && !on_rt_rq(rt_se))
static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
- int this_cpu = smp_processor_id();
struct sched_rt_entity *rt_se;
+ int cpu = cpu_of(rq_of_rt_rq(rt_rq));
- rt_se = rt_rq->tg->rt_se[this_cpu];
+ rt_se = rt_rq->tg->rt_se[cpu];
if (rt_se && on_rt_rq(rt_se))
dequeue_rt_entity(rt_se);
if (rt_rq->rt_time || rt_rq->rt_nr_running)
idle = 0;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
- } else if (rt_rq->rt_nr_running)
+ } else if (rt_rq->rt_nr_running) {
idle = 0;
+ if (!rt_rq_throttled(rt_rq))
+ enqueue = 1;
+ }
if (enqueue)
sched_rt_rq_enqueue(rt_rq);
* When switch from the rt queue, we bring ourselves to a position
* that we might want to pull RT tasks from other runqueues.
*/
-static void switched_from_rt(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_from_rt(struct rq *rq, struct task_struct *p)
{
/*
* If there are other RT tasks then we will reschedule
* we may need to handle the pulling of RT tasks
* now.
*/
- if (!rq->rt.rt_nr_running)
+ if (p->se.on_rq && !rq->rt.rt_nr_running)
pull_rt_task(rq);
}
* with RT tasks. In this case we try to push them off to
* other runqueues.
*/
-static void switched_to_rt(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_rt(struct rq *rq, struct task_struct *p)
{
int check_resched = 1;
* If that current running task is also an RT task
* then see if we can move to another run queue.
*/
- if (!running) {
+ if (p->se.on_rq && rq->curr != p) {
#ifdef CONFIG_SMP
if (rq->rt.overloaded && push_rt_task(rq) &&
/* Don't resched if we changed runqueues */
* Priority of the task has changed. This may cause
* us to initiate a push or pull.
*/
-static void prio_changed_rt(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
{
- if (running) {
+ if (!p->se.on_rq)
+ return;
+
+ if (rq->curr == p) {
#ifdef CONFIG_SMP
/*
* If our priority decreases while running, we
{
}
-static void switched_to_stop(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_stop(struct rq *rq, struct task_struct *p)
{
BUG(); /* its impossible to change to this class */
}
-static void prio_changed_stop(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
{
BUG(); /* how!?, what priority? */
}
static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
char *softirq_to_name[NR_SOFTIRQS] = {
"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
}
#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
-# define invoke_softirq() __do_softirq()
+static inline void invoke_softirq(void)
+{
+ if (!force_irqthreads)
+ __do_softirq();
+ else
+ wakeup_softirqd();
+}
#else
-# define invoke_softirq() do_softirq()
+static inline void invoke_softirq(void)
+{
+ if (!force_irqthreads)
+ do_softirq();
+ else
+ wakeup_softirqd();
+}
#endif
/*
{
set_current_state(TASK_INTERRUPTIBLE);
- current->flags |= PF_KSOFTIRQD;
while (!kthread_should_stop()) {
preempt_disable();
if (!local_softirq_pending()) {
don't process */
if (cpu_is_offline((long)__bind_cpu))
goto wait_to_die;
- do_softirq();
+ local_irq_disable();
+ if (local_softirq_pending())
+ __do_softirq();
+ local_irq_enable();
preempt_enable_no_resched();
cond_resched();
preempt_disable();
/* fanotify! */
cond_syscall(sys_fanotify_init);
cond_syscall(sys_fanotify_mark);
+
+/* open by handle */
+cond_syscall(sys_name_to_handle_at);
+cond_syscall(sys_open_by_handle_at);
+cond_syscall(compat_sys_open_by_handle_at);
static struct ctl_table root_table[];
static struct ctl_table_root sysctl_table_root;
static struct ctl_table_header root_table_header = {
- .count = 1,
+ {{.count = 1,
.ctl_table = root_table,
- .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
+ .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
.root = &sysctl_table_root,
.set = &sysctl_table_root.default_set,
};
.mode = 0644,
.proc_handler = sched_rt_handler,
},
- {
- .procname = "sched_compat_yield",
- .data = &sysctl_sched_compat_yield,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
#ifdef CONFIG_SCHED_AUTOGROUP
{
.procname = "sched_autogroup_enabled",
.data = &sysctl_sched_autogroup_enabled,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
.data = &sysctl_perf_event_sample_rate,
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = perf_proc_update_handler,
},
#endif
#ifdef CONFIG_KMEMCHECK
spin_unlock(&sysctl_lock);
}
+static void free_head(struct rcu_head *rcu)
+{
+ kfree(container_of(rcu, struct ctl_table_header, rcu));
+}
+
void sysctl_head_put(struct ctl_table_header *head)
{
spin_lock(&sysctl_lock);
if (!--head->count)
- kfree(head);
+ call_rcu(&head->rcu, free_head);
spin_unlock(&sysctl_lock);
}
start_unregistering(header);
if (!--header->parent->count) {
WARN_ON(1);
- kfree(header->parent);
+ call_rcu(&header->parent->rcu, free_head);
}
if (!--header->count)
- kfree(header);
+ call_rcu(&header->rcu, free_head);
spin_unlock(&sysctl_lock);
}
void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
{
const struct bin_table *table = NULL;
- struct nameidata nd;
struct vfsmount *mnt;
struct file *file;
ssize_t result;
char *pathname;
int flags;
- int acc_mode;
pathname = sysctl_getname(name, nlen, &table);
result = PTR_ERR(pathname);
/* How should the sysctl be accessed? */
if (oldval && oldlen && newval && newlen) {
flags = O_RDWR;
- acc_mode = MAY_READ | MAY_WRITE;
} else if (newval && newlen) {
flags = O_WRONLY;
- acc_mode = MAY_WRITE;
} else if (oldval && oldlen) {
flags = O_RDONLY;
- acc_mode = MAY_READ;
} else {
result = 0;
goto out_putname;
}
mnt = current->nsproxy->pid_ns->proc_mnt;
- result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd);
- if (result)
- goto out_putname;
-
- result = may_open(&nd.path, acc_mode, flags);
- if (result)
- goto out_putpath;
-
- file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred());
+ file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
result = PTR_ERR(file);
if (IS_ERR(file))
goto out_putname;
putname(pathname);
out:
return result;
-
-out_putpath:
- path_put(&nd.path);
- goto out_putname;
}
* various programs will get confused when the clock gets warped.
*/
-int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
+int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
{
static int firsttime = 1;
int error = 0;
}
/**
- * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
*
* @n: nsecs in u64
*
* NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
* ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
*/
-unsigned long nsecs_to_jiffies(u64 n)
+u64 nsecs_to_jiffies64(u64 n)
{
#if (NSEC_PER_SEC % HZ) == 0
/* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
#endif
}
-#if (BITS_PER_LONG < 64)
-u64 get_jiffies_64(void)
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n: nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
{
- unsigned long seq;
- u64 ret;
-
- do {
- seq = read_seqbegin(&xtime_lock);
- ret = jiffies_64;
- } while (read_seqretry(&xtime_lock, seq));
- return ret;
+ return (unsigned long)nsecs_to_jiffies64(n);
}
-EXPORT_SYMBOL(get_jiffies_64);
-#endif
-
-EXPORT_SYMBOL(jiffies);
/*
* Add two timespec values and do a safety check for overflow.
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timeconv.o posix-clock.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/sysdev.h>
-#include <linux/tick.h>
#include "tick-internal.h"
************************************************************************/
#include <linux/clocksource.h>
#include <linux/jiffies.h>
+#include <linux/module.h>
#include <linux/init.h>
+#include "tick-internal.h"
+
/* The Jiffies based clocksource is the lowest common
* denominator clock source which should function on
* all systems. It has the same coarse resolution as
.shift = JIFFIES_SHIFT,
};
+#if (BITS_PER_LONG < 64)
+u64 get_jiffies_64(void)
+{
+ unsigned long seq;
+ u64 ret;
+
+ do {
+ seq = read_seqbegin(&xtime_lock);
+ ret = jiffies_64;
+ } while (read_seqretry(&xtime_lock, seq));
+ return ret;
+}
+EXPORT_SYMBOL(get_jiffies_64);
+#endif
+
+EXPORT_SYMBOL(jiffies);
+
static int __init init_jiffies_clocksource(void)
{
return clocksource_register(&clocksource_jiffies);
#include <linux/mm.h>
#include <linux/module.h>
+#include "tick-internal.h"
+
/*
* NTP timekeeping variables:
*/
hrtimer_cancel(&leap_timer);
}
+ if (txc->modes & ADJ_SETOFFSET) {
+ struct timespec delta;
+ delta.tv_sec = txc->time.tv_sec;
+ delta.tv_nsec = txc->time.tv_usec;
+ if (!(txc->modes & ADJ_NANO))
+ delta.tv_nsec *= 1000;
+ result = timekeeping_inject_offset(&delta);
+ if (result)
+ return result;
+ }
+
getnstimeofday(&ts);
write_seqlock_irq(&xtime_lock);
--- /dev/null
+/*
+ * posix-clock.c - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/mutex.h>
+#include <linux/posix-clock.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+static void delete_clock(struct kref *kref);
+
+/*
+ * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
+ */
+static struct posix_clock *get_posix_clock(struct file *fp)
+{
+ struct posix_clock *clk = fp->private_data;
+
+ mutex_lock(&clk->mutex);
+
+ if (!clk->zombie)
+ return clk;
+
+ mutex_unlock(&clk->mutex);
+
+ return NULL;
+}
+
+static void put_posix_clock(struct posix_clock *clk)
+{
+ mutex_unlock(&clk->mutex);
+}
+
+static ssize_t posix_clock_read(struct file *fp, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct posix_clock *clk = get_posix_clock(fp);
+ int err = -EINVAL;
+
+ if (!clk)
+ return -ENODEV;
+
+ if (clk->ops.read)
+ err = clk->ops.read(clk, fp->f_flags, buf, count);
+
+ put_posix_clock(clk);
+
+ return err;
+}
+
+static unsigned int posix_clock_poll(struct file *fp, poll_table *wait)
+{
+ struct posix_clock *clk = get_posix_clock(fp);
+ int result = 0;
+
+ if (!clk)
+ return -ENODEV;
+
+ if (clk->ops.poll)
+ result = clk->ops.poll(clk, fp, wait);
+
+ put_posix_clock(clk);
+
+ return result;
+}
+
+static int posix_clock_fasync(int fd, struct file *fp, int on)
+{
+ struct posix_clock *clk = get_posix_clock(fp);
+ int err = 0;
+
+ if (!clk)
+ return -ENODEV;
+
+ if (clk->ops.fasync)
+ err = clk->ops.fasync(clk, fd, fp, on);
+
+ put_posix_clock(clk);
+
+ return err;
+}
+
+static int posix_clock_mmap(struct file *fp, struct vm_area_struct *vma)
+{
+ struct posix_clock *clk = get_posix_clock(fp);
+ int err = -ENODEV;
+
+ if (!clk)
+ return -ENODEV;
+
+ if (clk->ops.mmap)
+ err = clk->ops.mmap(clk, vma);
+
+ put_posix_clock(clk);
+
+ return err;
+}
+
+static long posix_clock_ioctl(struct file *fp,
+ unsigned int cmd, unsigned long arg)
+{
+ struct posix_clock *clk = get_posix_clock(fp);
+ int err = -ENOTTY;
+
+ if (!clk)
+ return -ENODEV;
+
+ if (clk->ops.ioctl)
+ err = clk->ops.ioctl(clk, cmd, arg);
+
+ put_posix_clock(clk);
+
+ return err;
+}
+
+#ifdef CONFIG_COMPAT
+static long posix_clock_compat_ioctl(struct file *fp,
+ unsigned int cmd, unsigned long arg)
+{
+ struct posix_clock *clk = get_posix_clock(fp);
+ int err = -ENOTTY;
+
+ if (!clk)
+ return -ENODEV;
+
+ if (clk->ops.ioctl)
+ err = clk->ops.ioctl(clk, cmd, arg);
+
+ put_posix_clock(clk);
+
+ return err;
+}
+#endif
+
+static int posix_clock_open(struct inode *inode, struct file *fp)
+{
+ int err;
+ struct posix_clock *clk =
+ container_of(inode->i_cdev, struct posix_clock, cdev);
+
+ mutex_lock(&clk->mutex);
+
+ if (clk->zombie) {
+ err = -ENODEV;
+ goto out;
+ }
+ if (clk->ops.open)
+ err = clk->ops.open(clk, fp->f_mode);
+ else
+ err = 0;
+
+ if (!err) {
+ kref_get(&clk->kref);
+ fp->private_data = clk;
+ }
+out:
+ mutex_unlock(&clk->mutex);
+ return err;
+}
+
+static int posix_clock_release(struct inode *inode, struct file *fp)
+{
+ struct posix_clock *clk = fp->private_data;
+ int err = 0;
+
+ if (clk->ops.release)
+ err = clk->ops.release(clk);
+
+ kref_put(&clk->kref, delete_clock);
+
+ fp->private_data = NULL;
+
+ return err;
+}
+
+static const struct file_operations posix_clock_file_operations = {
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+ .read = posix_clock_read,
+ .poll = posix_clock_poll,
+ .unlocked_ioctl = posix_clock_ioctl,
+ .open = posix_clock_open,
+ .release = posix_clock_release,
+ .fasync = posix_clock_fasync,
+ .mmap = posix_clock_mmap,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = posix_clock_compat_ioctl,
+#endif
+};
+
+int posix_clock_register(struct posix_clock *clk, dev_t devid)
+{
+ int err;
+
+ kref_init(&clk->kref);
+ mutex_init(&clk->mutex);
+
+ cdev_init(&clk->cdev, &posix_clock_file_operations);
+ clk->cdev.owner = clk->ops.owner;
+ err = cdev_add(&clk->cdev, devid, 1);
+ if (err)
+ goto no_cdev;
+
+ return err;
+no_cdev:
+ mutex_destroy(&clk->mutex);
+ return err;
+}
+EXPORT_SYMBOL_GPL(posix_clock_register);
+
+static void delete_clock(struct kref *kref)
+{
+ struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
+ mutex_destroy(&clk->mutex);
+ if (clk->release)
+ clk->release(clk);
+}
+
+void posix_clock_unregister(struct posix_clock *clk)
+{
+ cdev_del(&clk->cdev);
+
+ mutex_lock(&clk->mutex);
+ clk->zombie = true;
+ mutex_unlock(&clk->mutex);
+
+ kref_put(&clk->kref, delete_clock);
+}
+EXPORT_SYMBOL_GPL(posix_clock_unregister);
+
+struct posix_clock_desc {
+ struct file *fp;
+ struct posix_clock *clk;
+};
+
+static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd)
+{
+ struct file *fp = fget(CLOCKID_TO_FD(id));
+ int err = -EINVAL;
+
+ if (!fp)
+ return err;
+
+ if (fp->f_op->open != posix_clock_open || !fp->private_data)
+ goto out;
+
+ cd->fp = fp;
+ cd->clk = get_posix_clock(fp);
+
+ err = cd->clk ? 0 : -ENODEV;
+out:
+ if (err)
+ fput(fp);
+ return err;
+}
+
+static void put_clock_desc(struct posix_clock_desc *cd)
+{
+ put_posix_clock(cd->clk);
+ fput(cd->fp);
+}
+
+static int pc_clock_adjtime(clockid_t id, struct timex *tx)
+{
+ struct posix_clock_desc cd;
+ int err;
+
+ err = get_clock_desc(id, &cd);
+ if (err)
+ return err;
+
+ if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+ err = -EACCES;
+ goto out;
+ }
+
+ if (cd.clk->ops.clock_adjtime)
+ err = cd.clk->ops.clock_adjtime(cd.clk, tx);
+ else
+ err = -EOPNOTSUPP;
+out:
+ put_clock_desc(&cd);
+
+ return err;
+}
+
+static int pc_clock_gettime(clockid_t id, struct timespec *ts)
+{
+ struct posix_clock_desc cd;
+ int err;
+
+ err = get_clock_desc(id, &cd);
+ if (err)
+ return err;
+
+ if (cd.clk->ops.clock_gettime)
+ err = cd.clk->ops.clock_gettime(cd.clk, ts);
+ else
+ err = -EOPNOTSUPP;
+
+ put_clock_desc(&cd);
+
+ return err;
+}
+
+static int pc_clock_getres(clockid_t id, struct timespec *ts)
+{
+ struct posix_clock_desc cd;
+ int err;
+
+ err = get_clock_desc(id, &cd);
+ if (err)
+ return err;
+
+ if (cd.clk->ops.clock_getres)
+ err = cd.clk->ops.clock_getres(cd.clk, ts);
+ else
+ err = -EOPNOTSUPP;
+
+ put_clock_desc(&cd);
+
+ return err;
+}
+
+static int pc_clock_settime(clockid_t id, const struct timespec *ts)
+{
+ struct posix_clock_desc cd;
+ int err;
+
+ err = get_clock_desc(id, &cd);
+ if (err)
+ return err;
+
+ if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+ err = -EACCES;
+ goto out;
+ }
+
+ if (cd.clk->ops.clock_settime)
+ err = cd.clk->ops.clock_settime(cd.clk, ts);
+ else
+ err = -EOPNOTSUPP;
+out:
+ put_clock_desc(&cd);
+
+ return err;
+}
+
+static int pc_timer_create(struct k_itimer *kit)
+{
+ clockid_t id = kit->it_clock;
+ struct posix_clock_desc cd;
+ int err;
+
+ err = get_clock_desc(id, &cd);
+ if (err)
+ return err;
+
+ if (cd.clk->ops.timer_create)
+ err = cd.clk->ops.timer_create(cd.clk, kit);
+ else
+ err = -EOPNOTSUPP;
+
+ put_clock_desc(&cd);
+
+ return err;
+}
+
+static int pc_timer_delete(struct k_itimer *kit)
+{
+ clockid_t id = kit->it_clock;
+ struct posix_clock_desc cd;
+ int err;
+
+ err = get_clock_desc(id, &cd);
+ if (err)
+ return err;
+
+ if (cd.clk->ops.timer_delete)
+ err = cd.clk->ops.timer_delete(cd.clk, kit);
+ else
+ err = -EOPNOTSUPP;
+
+ put_clock_desc(&cd);
+
+ return err;
+}
+
+static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
+{
+ clockid_t id = kit->it_clock;
+ struct posix_clock_desc cd;
+
+ if (get_clock_desc(id, &cd))
+ return;
+
+ if (cd.clk->ops.timer_gettime)
+ cd.clk->ops.timer_gettime(cd.clk, kit, ts);
+
+ put_clock_desc(&cd);
+}
+
+static int pc_timer_settime(struct k_itimer *kit, int flags,
+ struct itimerspec *ts, struct itimerspec *old)
+{
+ clockid_t id = kit->it_clock;
+ struct posix_clock_desc cd;
+ int err;
+
+ err = get_clock_desc(id, &cd);
+ if (err)
+ return err;
+
+ if (cd.clk->ops.timer_settime)
+ err = cd.clk->ops.timer_settime(cd.clk, kit, flags, ts, old);
+ else
+ err = -EOPNOTSUPP;
+
+ put_clock_desc(&cd);
+
+ return err;
+}
+
+struct k_clock clock_posix_dynamic = {
+ .clock_getres = pc_clock_getres,
+ .clock_set = pc_clock_settime,
+ .clock_get = pc_clock_gettime,
+ .clock_adj = pc_clock_adjtime,
+ .timer_create = pc_timer_create,
+ .timer_set = pc_timer_settime,
+ .timer_del = pc_timer_delete,
+ .timer_get = pc_timer_gettime,
+};
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
#include "tick-internal.h"
return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
}
+/*
+ * Check whether the broadcast device supports oneshot.
+ */
+bool tick_broadcast_oneshot_available(void)
+{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+ return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
+}
+
#endif
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
#include <asm/irq_regs.h>
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
- return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT);
+ if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return 0;
+ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+ return 1;
+ return tick_broadcast_oneshot_available();
}
/*
/*
* tick internal variable and functions used by low/high res code
*/
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
#define TICK_DO_TIMER_NONE -1
#define TICK_DO_TIMER_BOOT -2
extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
extern int tick_broadcast_oneshot_active(void);
extern void tick_check_oneshot_broadcast(int cpu);
+bool tick_broadcast_oneshot_available(void);
# else /* BROADCAST */
static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_broadcast_oneshot_active(void) { return 0; }
static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline bool tick_broadcast_oneshot_available(void) { return true; }
# endif /* !BROADCAST */
#else /* !ONESHOT */
return 0;
}
static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline bool tick_broadcast_oneshot_available(void) { return false; }
#endif /* !TICK_ONESHOT */
/*
{
return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
}
+
+#endif
+
+extern void do_timer(unsigned long ticks);
+extern seqlock_t xtime_lock;
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
#include "tick-internal.h"
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
-#include <linux/tick.h>
#include <linux/module.h>
#include <asm/irq_regs.h>
*
* Sets the time of day to the new time and update NTP and notify hrtimers
*/
-int do_settimeofday(struct timespec *tv)
+int do_settimeofday(const struct timespec *tv)
{
struct timespec ts_delta;
unsigned long flags;
EXPORT_SYMBOL(do_settimeofday);
+
+/**
+ * timekeeping_inject_offset - Adds or subtracts from the current time.
+ * @tv: pointer to the timespec variable containing the offset
+ *
+ * Adds or subtracts an offset value from the current time.
+ */
+int timekeeping_inject_offset(struct timespec *ts)
+{
+ unsigned long flags;
+
+ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+ return -EINVAL;
+
+ write_seqlock_irqsave(&xtime_lock, flags);
+
+ timekeeping_forward_now();
+
+ xtime = timespec_add(xtime, *ts);
+ wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
+
+ timekeeper.ntp_error = 0;
+ ntp_clear();
+
+ update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+ timekeeper.mult);
+
+ write_sequnlock_irqrestore(&xtime_lock, flags);
+
+ /* signal hrtimers about time change */
+ clock_was_set();
+
+ return 0;
+}
+EXPORT_SYMBOL(timekeeping_inject_offset);
+
/**
* change_clocksource - Swaps clocksources if a new one is available
*
*
* Called from the timer interrupt, must hold a write on xtime_lock.
*/
-void update_wall_time(void)
+static void update_wall_time(void)
{
struct clocksource *clock;
cycle_t offset;
* getboottime - Return the real time of system boot.
* @ts: pointer to the timespec to be set
*
- * Returns the time of day in a timespec.
+ * Returns the wall-time of boot in a timespec.
*
* This is based on the wall_to_monotonic offset and the total suspend
* time. Calls to settimeofday will affect the value returned (which
}
EXPORT_SYMBOL_GPL(getboottime);
+
+/**
+ * get_monotonic_boottime - Returns monotonic time since boot
+ * @ts: pointer to the timespec to be set
+ *
+ * Returns the monotonic time since boot in a timespec.
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also
+ * includes the time spent in suspend.
+ */
+void get_monotonic_boottime(struct timespec *ts)
+{
+ struct timespec tomono, sleep;
+ unsigned int seq;
+ s64 nsecs;
+
+ WARN_ON(timekeeping_suspended);
+
+ do {
+ seq = read_seqbegin(&xtime_lock);
+ *ts = xtime;
+ tomono = wall_to_monotonic;
+ sleep = total_sleep_time;
+ nsecs = timekeeping_get_ns();
+
+ } while (read_seqretry(&xtime_lock, seq));
+
+ set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
+ ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
+}
+EXPORT_SYMBOL_GPL(get_monotonic_boottime);
+
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in a ktime
+ *
+ * Returns the monotonic time since boot in a ktime
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also
+ * includes the time spent in suspend.
+ */
+ktime_t ktime_get_boottime(void)
+{
+ struct timespec ts;
+
+ get_monotonic_boottime(&ts);
+ return timespec_to_ktime(ts);
+}
+EXPORT_SYMBOL_GPL(ktime_get_boottime);
+
/**
* monotonic_to_bootbased - Convert the monotonic time to boot based.
* @ts: pointer to the timespec to be converted
return xtime;
}
-struct timespec __get_wall_to_monotonic(void)
-{
- return wall_to_monotonic;
-}
-
struct timespec current_kernel_time(void)
{
struct timespec now;
now.tv_nsec + mono.tv_nsec);
return now;
}
+
+/*
+ * The 64-bit jiffies value is not atomic - you MUST NOT read it
+ * without sampling the sequence number in xtime_lock.
+ * jiffies is defined in the linker script...
+ */
+void do_timer(unsigned long ticks)
+{
+ jiffies_64 += ticks;
+ update_wall_time();
+ calc_global_load(ticks);
+}
+
+/**
+ * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic,
+ * and sleep offsets.
+ * @xtim: pointer to timespec to be set with xtime
+ * @wtom: pointer to timespec to be set with wall_to_monotonic
+ * @sleep: pointer to timespec to be set with time in suspend
+ */
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+ struct timespec *wtom, struct timespec *sleep)
+{
+ unsigned long seq;
+
+ do {
+ seq = read_seqbegin(&xtime_lock);
+ *xtim = xtime;
+ *wtom = wall_to_monotonic;
+ *sleep = total_sleep_time;
+ } while (read_seqretry(&xtime_lock, seq));
+}
+
+/**
+ * xtime_update() - advances the timekeeping infrastructure
+ * @ticks: number of ticks, that have elapsed since the last call.
+ *
+ * Must be called with interrupts disabled.
+ */
+void xtime_update(unsigned long ticks)
+{
+ write_seqlock(&xtime_lock);
+ do_timer(ticks);
+ write_sequnlock(&xtime_lock);
+}
char symname[KSYM_NAME_LEN];
if (lookup_symbol_name((unsigned long)sym, symname) < 0)
- SEQ_printf(m, "<%p>", sym);
+ SEQ_printf(m, "<%pK>", sym);
else
SEQ_printf(m, "%s", symname);
}
static void
print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
{
- SEQ_printf(m, " .base: %p\n", base);
+ SEQ_printf(m, " .base: %pK\n", base);
SEQ_printf(m, " .index: %d\n",
base->index);
SEQ_printf(m, " .resolution: %Lu nsecs\n",
static struct debug_obj_descr timer_debug_descr;
+static void *timer_debug_hint(void *addr)
+{
+ return ((struct timer_list *) addr)->function;
+}
+
/*
* fixup_init is called when:
* - an active object is initialized
static struct debug_obj_descr timer_debug_descr = {
.name = "timer_list",
+ .debug_hint = timer_debug_hint,
.fixup_init = timer_fixup_init,
.fixup_activate = timer_fixup_activate,
.fixup_free = timer_fixup_free,
*
* Synchronization rules: Callers must prevent restarting of the timer,
* otherwise this function is meaningless. It must not be called from
- * hardirq contexts. The caller must not hold locks which would prevent
+ * interrupt contexts. The caller must not hold locks which would prevent
* completion of the timer's handler. The timer's handler must not call
* add_timer_on(). Upon exit the timer is not queued and the handler is
* not running on any CPU.
*
+ * Note: You must not hold locks that are held in interrupt context
+ * while calling this function. Even if the lock has nothing to do
+ * with the timer in question. Here's why:
+ *
+ * CPU0 CPU1
+ * ---- ----
+ * <SOFTIRQ>
+ * call_timer_fn();
+ * base->running_timer = mytimer;
+ * spin_lock_irq(somelock);
+ * <IRQ>
+ * spin_lock(somelock);
+ * del_timer_sync(mytimer);
+ * while (base->running_timer == mytimer);
+ *
+ * Now del_timer_sync() will never return and never release somelock.
+ * The interrupt on the other CPU is waiting to grab somelock but
+ * it has interrupted the softirq that CPU0 is waiting to finish.
+ *
* The function returns whether it has deactivated a pending timer or not.
*/
int del_timer_sync(struct timer_list *timer)
#ifdef CONFIG_LOCKDEP
unsigned long flags;
- raw_local_irq_save(flags);
- local_bh_disable();
+ /*
+ * If lockdep gives a backtrace here, please reference
+ * the synchronization rules above.
+ */
+ local_irq_save(flags);
lock_map_acquire(&timer->lockdep_map);
lock_map_release(&timer->lockdep_map);
- _local_bh_enable();
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
#endif
/*
* don't use it in hardirq context, because it
raise_softirq(TIMER_SOFTIRQ);
}
-/*
- * The 64-bit jiffies value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
- * jiffies is defined in the linker script...
- */
-
-void do_timer(unsigned long ticks)
-{
- jiffies_64 += ticks;
- update_wall_time();
- calc_global_load(ticks);
-}
-
#ifdef __ARCH_WANT_SYS_ALARM
/*
!blk_tracer_enabled))
return;
+ /*
+ * If the BLK_TC_NOTIFY action mask isn't set, don't send any note
+ * message to the trace.
+ */
+ if (!(bt->act_mask & BLK_TC_NOTIFY))
+ return;
+
local_irq_save(flags);
buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
va_start(args, fmt);
rwbs[i] = '\0';
}
-void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
-{
- int rw = rq->cmd_flags & 0x03;
- int bytes;
-
- if (rq->cmd_flags & REQ_DISCARD)
- rw |= REQ_DISCARD;
-
- if (rq->cmd_flags & REQ_SECURE)
- rw |= REQ_SECURE;
-
- bytes = blk_rq_bytes(rq);
-
- blk_fill_rwbs(rwbs, rw, bytes);
-}
-
#endif /* CONFIG_EVENT_TRACING */
/* The cpu_boot init_task->ret_stack will never be freed */
for_each_online_cpu(cpu) {
if (!idle_task(cpu)->ret_stack)
- ftrace_graph_init_task(idle_task(cpu));
+ ftrace_graph_init_idle_task(idle_task(cpu), cpu);
}
do {
mutex_unlock(&ftrace_lock);
}
+static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack);
+
+static void
+graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
+{
+ atomic_set(&t->tracing_graph_pause, 0);
+ atomic_set(&t->trace_overrun, 0);
+ t->ftrace_timestamp = 0;
+ /* make curr_ret_stack visable before we add the ret_stack */
+ smp_wmb();
+ t->ret_stack = ret_stack;
+}
+
+/*
+ * Allocate a return stack for the idle task. May be the first
+ * time through, or it may be done by CPU hotplug online.
+ */
+void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
+{
+ t->curr_ret_stack = -1;
+ /*
+ * The idle task has no parent, it either has its own
+ * stack or no stack at all.
+ */
+ if (t->ret_stack)
+ WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu));
+
+ if (ftrace_graph_active) {
+ struct ftrace_ret_stack *ret_stack;
+
+ ret_stack = per_cpu(idle_ret_stack, cpu);
+ if (!ret_stack) {
+ ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+ * sizeof(struct ftrace_ret_stack),
+ GFP_KERNEL);
+ if (!ret_stack)
+ return;
+ per_cpu(idle_ret_stack, cpu) = ret_stack;
+ }
+ graph_init_task(t, ret_stack);
+ }
+}
+
/* Allocate a return stack for newly created task */
void ftrace_graph_init_task(struct task_struct *t)
{
GFP_KERNEL);
if (!ret_stack)
return;
- atomic_set(&t->tracing_graph_pause, 0);
- atomic_set(&t->trace_overrun, 0);
- t->ftrace_timestamp = 0;
- /* make curr_ret_stack visable before we add the ret_stack */
- smp_wmb();
- t->ret_stack = ret_stack;
+ graph_init_task(t, ret_stack);
}
}
*/
#include <linux/ring_buffer.h>
#include <linux/trace_clock.h>
-#include <linux/ftrace_irq.h>
#include <linux/spinlock.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
}
EXPORT_SYMBOL_GPL(ring_buffer_resize);
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
+{
+ mutex_lock(&buffer->mutex);
+ if (val)
+ buffer->flags |= RB_FL_OVERWRITE;
+ else
+ buffer->flags &= ~RB_FL_OVERWRITE;
+ mutex_unlock(&buffer->mutex);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
+
static inline void *
__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
{
if (likely(ts >= cpu_buffer->write_stamp)) {
delta = diff;
if (unlikely(test_time_stamp(delta))) {
+ int local_clock_stable = 1;
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+ local_clock_stable = sched_clock_stable;
+#endif
WARN_ONCE(delta > (1ULL << 59),
- KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+ KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
(unsigned long long)delta,
(unsigned long long)ts,
- (unsigned long long)cpu_buffer->write_stamp);
+ (unsigned long long)cpu_buffer->write_stamp,
+ local_clock_stable ? "" :
+ "If you just came from a suspend/resume,\n"
+ "please switch to the trace global clock:\n"
+ " echo global > /sys/kernel/debug/tracing/trace_clock\n");
add_timestamp = 1;
}
}
#include "trace.h"
#include "trace_output.h"
-#define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE)
-
/*
* On boot up, the ring buffer is set to the minimum size, so that
* we do not waste memory on systems that are not using tracing.
/* trace_flags holds trace_options default values */
unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
- TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
+ TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
static int trace_stop_count;
static DEFINE_SPINLOCK(tracing_start_lock);
"sleep-time",
"graph-time",
"record-cmd",
+ "overwrite",
NULL
};
tracing_reset_online_cpus(tr);
current_trace = type;
+
+ /* If we expanded the buffers, make sure the max is expanded too */
+ if (ring_buffer_expanded && type->use_max_tr)
+ ring_buffer_resize(max_tr.buffer, trace_buf_size);
+
/* the test is responsible for initializing and enabling */
pr_info("Testing tracer %s: ", type->name);
ret = type->selftest(type, tr);
/* Only reset on passing, to avoid touching corrupted buffers */
tracing_reset_online_cpus(tr);
+ /* Shrink the max buffer again */
+ if (ring_buffer_expanded && type->use_max_tr)
+ ring_buffer_resize(max_tr.buffer, 1);
+
printk(KERN_CONT "PASSED\n");
}
#endif
entry->preempt_count = pc & 0xff;
entry->pid = (tsk) ? tsk->pid : 0;
- entry->lock_depth = (tsk) ? tsk->lock_depth : 0;
entry->flags =
#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
seq_puts(m, "# | / _----=> need-resched \n");
seq_puts(m, "# || / _---=> hardirq/softirq \n");
seq_puts(m, "# ||| / _--=> preempt-depth \n");
- seq_puts(m, "# |||| /_--=> lock-depth \n");
- seq_puts(m, "# |||||/ delay \n");
- seq_puts(m, "# cmd pid |||||| time | caller \n");
- seq_puts(m, "# \\ / |||||| \\ | / \n");
+ seq_puts(m, "# |||| / delay \n");
+ seq_puts(m, "# cmd pid ||||| time | caller \n");
+ seq_puts(m, "# \\ / ||||| \\ | / \n");
}
static void print_func_help_header(struct seq_file *m)
if (mask == TRACE_ITER_RECORD_CMD)
trace_event_enable_cmd_record(enabled);
+
+ if (mask == TRACE_ITER_OVERWRITE)
+ ring_buffer_change_overwrite(global_trace.buffer, enabled);
}
static ssize_t
mutex_lock(&trace_types_lock);
if (tracer_enabled ^ val) {
+
+ /* Only need to warn if this is used to change the state */
+ WARN_ONCE(1, "tracing_enabled is deprecated. Use tracing_on");
+
if (val) {
tracer_enabled = 1;
if (current_trace->start)
__init static int tracer_alloc_buffers(void)
{
int ring_buf_size;
+ enum ring_buffer_flags rb_flags;
int i;
int ret = -ENOMEM;
+
if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
goto out;
else
ring_buf_size = 1;
+ rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
cpumask_copy(tracing_cpumask, cpu_all_mask);
/* TODO: make the number of buffers hot pluggable with CPUS */
- global_trace.buffer = ring_buffer_alloc(ring_buf_size,
- TRACE_BUFFER_FLAGS);
+ global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
if (!global_trace.buffer) {
printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
WARN_ON(1);
#ifdef CONFIG_TRACER_MAX_TRACE
- max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
+ max_tr.buffer = ring_buffer_alloc(1, rb_flags);
if (!max_tr.buffer) {
printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
WARN_ON(1);
/* If you handled the flag setting, return 0 */
int (*set_flag)(u32 old_flags, u32 bit, int set);
struct tracer *next;
- int print_max;
struct tracer_flags *flags;
+ int print_max;
int use_max_tr;
};
TRACE_ITER_SLEEP_TIME = 0x40000,
TRACE_ITER_GRAPH_TIME = 0x80000,
TRACE_ITER_RECORD_CMD = 0x100000,
+ TRACE_ITER_OVERWRITE = 0x200000,
};
/*
};
struct event_filter {
- int n_preds;
- struct filter_pred **preds;
+ int n_preds; /* Number assigned */
+ int a_preds; /* allocated */
+ struct filter_pred *preds;
+ struct filter_pred *root;
char *filter_string;
};
int nr_events;
};
+#define FILTER_PRED_INVALID ((unsigned short)-1)
+#define FILTER_PRED_IS_RIGHT (1 << 15)
+#define FILTER_PRED_FOLD (1 << 15)
+
+/*
+ * The max preds is the size of unsigned short with
+ * two flags at the MSBs. One bit is used for both the IS_RIGHT
+ * and FOLD flags. The other is reserved.
+ *
+ * 2^14 preds is way more than enough.
+ */
+#define MAX_FILTER_PRED 16384
+
struct filter_pred;
struct regex;
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
- int val1, int val2);
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
typedef int (*regex_match_func)(char *str, struct regex *r, int len);
filter_pred_fn_t fn;
u64 val;
struct regex regex;
- char *field_name;
+ /*
+ * Leaf nodes use field_name, ops is used by AND and OR
+ * nodes. The field_name is always freed when freeing a pred.
+ * We can overload field_name for ops and have it freed
+ * as well.
+ */
+ union {
+ char *field_name;
+ unsigned short *ops;
+ };
int offset;
int not;
int op;
- int pop_n;
+ unsigned short index;
+ unsigned short parent;
+ unsigned short left;
+ unsigned short right;
};
extern struct list_head ftrace_common_fields;
*/
#define FTRACE_CTX_FIELDS \
__field( unsigned int, prev_pid ) \
+ __field( unsigned int, next_pid ) \
+ __field( unsigned int, next_cpu ) \
__field( unsigned char, prev_prio ) \
__field( unsigned char, prev_state ) \
- __field( unsigned int, next_pid ) \
__field( unsigned char, next_prio ) \
- __field( unsigned char, next_state ) \
- __field( unsigned int, next_cpu )
+ __field( unsigned char, next_state )
FTRACE_ENTRY(context_switch, ctx_switch_entry,
__common_field(unsigned char, flags);
__common_field(unsigned char, preempt_count);
__common_field(int, pid);
- __common_field(int, lock_depth);
return ret;
}
{
return __ftrace_set_clr_event(NULL, system, event, set);
}
+EXPORT_SYMBOL_GPL(trace_set_clr_event);
/* 128 should be much more than enough */
#define EVENT_BUF_SIZE 127
} operand;
};
+struct pred_stack {
+ struct filter_pred **preds;
+ int index;
+};
+
#define DEFINE_COMPARISON_PRED(type) \
-static int filter_pred_##type(struct filter_pred *pred, void *event, \
- int val1, int val2) \
+static int filter_pred_##type(struct filter_pred *pred, void *event) \
{ \
type *addr = (type *)(event + pred->offset); \
type val = (type)pred->val; \
}
#define DEFINE_EQUALITY_PRED(size) \
-static int filter_pred_##size(struct filter_pred *pred, void *event, \
- int val1, int val2) \
+static int filter_pred_##size(struct filter_pred *pred, void *event) \
{ \
u##size *addr = (u##size *)(event + pred->offset); \
u##size val = (u##size)pred->val; \
DEFINE_EQUALITY_PRED(16);
DEFINE_EQUALITY_PRED(8);
-static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
- void *event __attribute((unused)),
- int val1, int val2)
-{
- return val1 && val2;
-}
-
-static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
- void *event __attribute((unused)),
- int val1, int val2)
-{
- return val1 || val2;
-}
-
/* Filter predicate for fixed sized arrays of characters */
-static int filter_pred_string(struct filter_pred *pred, void *event,
- int val1, int val2)
+static int filter_pred_string(struct filter_pred *pred, void *event)
{
char *addr = (char *)(event + pred->offset);
int cmp, match;
}
/* Filter predicate for char * pointers */
-static int filter_pred_pchar(struct filter_pred *pred, void *event,
- int val1, int val2)
+static int filter_pred_pchar(struct filter_pred *pred, void *event)
{
char **addr = (char **)(event + pred->offset);
int cmp, match;
* and add it to the address of the entry, and at last we have
* the address of the string.
*/
-static int filter_pred_strloc(struct filter_pred *pred, void *event,
- int val1, int val2)
+static int filter_pred_strloc(struct filter_pred *pred, void *event)
{
u32 str_item = *(u32 *)(event + pred->offset);
int str_loc = str_item & 0xffff;
return match;
}
-static int filter_pred_none(struct filter_pred *pred, void *event,
- int val1, int val2)
+static int filter_pred_none(struct filter_pred *pred, void *event)
{
return 0;
}
pred->not ^= not;
}
+enum move_type {
+ MOVE_DOWN,
+ MOVE_UP_FROM_LEFT,
+ MOVE_UP_FROM_RIGHT
+};
+
+static struct filter_pred *
+get_pred_parent(struct filter_pred *pred, struct filter_pred *preds,
+ int index, enum move_type *move)
+{
+ if (pred->parent & FILTER_PRED_IS_RIGHT)
+ *move = MOVE_UP_FROM_RIGHT;
+ else
+ *move = MOVE_UP_FROM_LEFT;
+ pred = &preds[pred->parent & ~FILTER_PRED_IS_RIGHT];
+
+ return pred;
+}
+
+/*
+ * A series of AND or ORs where found together. Instead of
+ * climbing up and down the tree branches, an array of the
+ * ops were made in order of checks. We can just move across
+ * the array and short circuit if needed.
+ */
+static int process_ops(struct filter_pred *preds,
+ struct filter_pred *op, void *rec)
+{
+ struct filter_pred *pred;
+ int type;
+ int match;
+ int i;
+
+ /*
+ * Micro-optimization: We set type to true if op
+ * is an OR and false otherwise (AND). Then we
+ * just need to test if the match is equal to
+ * the type, and if it is, we can short circuit the
+ * rest of the checks:
+ *
+ * if ((match && op->op == OP_OR) ||
+ * (!match && op->op == OP_AND))
+ * return match;
+ */
+ type = op->op == OP_OR;
+
+ for (i = 0; i < op->val; i++) {
+ pred = &preds[op->ops[i]];
+ match = pred->fn(pred, rec);
+ if (!!match == type)
+ return match;
+ }
+ return match;
+}
+
/* return 1 if event matches, 0 otherwise (discard) */
int filter_match_preds(struct event_filter *filter, void *rec)
{
- int match, top = 0, val1 = 0, val2 = 0;
- int stack[MAX_FILTER_PRED];
+ int match = -1;
+ enum move_type move = MOVE_DOWN;
+ struct filter_pred *preds;
struct filter_pred *pred;
- int i;
+ struct filter_pred *root;
+ int n_preds;
+ int done = 0;
+
+ /* no filter is considered a match */
+ if (!filter)
+ return 1;
+
+ n_preds = filter->n_preds;
+
+ if (!n_preds)
+ return 1;
+
+ /*
+ * n_preds, root and filter->preds are protect with preemption disabled.
+ */
+ preds = rcu_dereference_sched(filter->preds);
+ root = rcu_dereference_sched(filter->root);
+ if (!root)
+ return 1;
+
+ pred = root;
- for (i = 0; i < filter->n_preds; i++) {
- pred = filter->preds[i];
- if (!pred->pop_n) {
- match = pred->fn(pred, rec, val1, val2);
- stack[top++] = match;
+ /* match is currently meaningless */
+ match = -1;
+
+ do {
+ switch (move) {
+ case MOVE_DOWN:
+ /* only AND and OR have children */
+ if (pred->left != FILTER_PRED_INVALID) {
+ /* If ops is set, then it was folded. */
+ if (!pred->ops) {
+ /* keep going to down the left side */
+ pred = &preds[pred->left];
+ continue;
+ }
+ /* We can treat folded ops as a leaf node */
+ match = process_ops(preds, pred, rec);
+ } else
+ match = pred->fn(pred, rec);
+ /* If this pred is the only pred */
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ /*
+ * Check for short circuits.
+ *
+ * Optimization: !!match == (pred->op == OP_OR)
+ * is the same as:
+ * if ((match && pred->op == OP_OR) ||
+ * (!match && pred->op == OP_AND))
+ */
+ if (!!match == (pred->op == OP_OR)) {
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ /* now go down the right side of the tree. */
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ /* We finished this equation. */
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
continue;
}
- if (pred->pop_n > top) {
- WARN_ON_ONCE(1);
- return 0;
- }
- val1 = stack[--top];
- val2 = stack[--top];
- match = pred->fn(pred, rec, val1, val2);
- stack[top++] = match;
- }
+ done = 1;
+ } while (!done);
- return stack[--top];
+ return match;
}
EXPORT_SYMBOL_GPL(filter_match_preds);
static void remove_filter_string(struct event_filter *filter)
{
+ if (!filter)
+ return;
+
kfree(filter->filter_string);
filter->filter_string = NULL;
}
void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
{
- struct event_filter *filter = call->filter;
+ struct event_filter *filter;
mutex_lock(&event_mutex);
+ filter = call->filter;
if (filter && filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
void print_subsystem_event_filter(struct event_subsystem *system,
struct trace_seq *s)
{
- struct event_filter *filter = system->filter;
+ struct event_filter *filter;
mutex_lock(&event_mutex);
+ filter = system->filter;
if (filter && filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
pred->regex.len = 0;
}
-static int filter_set_pred(struct filter_pred *dest,
+static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
+{
+ stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
+ if (!stack->preds)
+ return -ENOMEM;
+ stack->index = n_preds;
+ return 0;
+}
+
+static void __free_pred_stack(struct pred_stack *stack)
+{
+ kfree(stack->preds);
+ stack->index = 0;
+}
+
+static int __push_pred_stack(struct pred_stack *stack,
+ struct filter_pred *pred)
+{
+ int index = stack->index;
+
+ if (WARN_ON(index == 0))
+ return -ENOSPC;
+
+ stack->preds[--index] = pred;
+ stack->index = index;
+ return 0;
+}
+
+static struct filter_pred *
+__pop_pred_stack(struct pred_stack *stack)
+{
+ struct filter_pred *pred;
+ int index = stack->index;
+
+ pred = stack->preds[index++];
+ if (!pred)
+ return NULL;
+
+ stack->index = index;
+ return pred;
+}
+
+static int filter_set_pred(struct event_filter *filter,
+ int idx,
+ struct pred_stack *stack,
struct filter_pred *src,
filter_pred_fn_t fn)
{
+ struct filter_pred *dest = &filter->preds[idx];
+ struct filter_pred *left;
+ struct filter_pred *right;
+
*dest = *src;
if (src->field_name) {
dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
return -ENOMEM;
}
dest->fn = fn;
+ dest->index = idx;
- return 0;
+ if (dest->op == OP_OR || dest->op == OP_AND) {
+ right = __pop_pred_stack(stack);
+ left = __pop_pred_stack(stack);
+ if (!left || !right)
+ return -EINVAL;
+ /*
+ * If both children can be folded
+ * and they are the same op as this op or a leaf,
+ * then this op can be folded.
+ */
+ if (left->index & FILTER_PRED_FOLD &&
+ (left->op == dest->op ||
+ left->left == FILTER_PRED_INVALID) &&
+ right->index & FILTER_PRED_FOLD &&
+ (right->op == dest->op ||
+ right->left == FILTER_PRED_INVALID))
+ dest->index |= FILTER_PRED_FOLD;
+
+ dest->left = left->index & ~FILTER_PRED_FOLD;
+ dest->right = right->index & ~FILTER_PRED_FOLD;
+ left->parent = dest->index & ~FILTER_PRED_FOLD;
+ right->parent = dest->index | FILTER_PRED_IS_RIGHT;
+ } else {
+ /*
+ * Make dest->left invalid to be used as a quick
+ * way to know this is a leaf node.
+ */
+ dest->left = FILTER_PRED_INVALID;
+
+ /* All leafs allow folding the parent ops. */
+ dest->index |= FILTER_PRED_FOLD;
+ }
+
+ return __push_pred_stack(stack, dest);
}
-static void filter_disable_preds(struct ftrace_event_call *call)
+static void __free_preds(struct event_filter *filter)
{
- struct event_filter *filter = call->filter;
int i;
- call->flags &= ~TRACE_EVENT_FL_FILTERED;
+ if (filter->preds) {
+ for (i = 0; i < filter->a_preds; i++)
+ kfree(filter->preds[i].field_name);
+ kfree(filter->preds);
+ filter->preds = NULL;
+ }
+ filter->a_preds = 0;
filter->n_preds = 0;
-
- for (i = 0; i < MAX_FILTER_PRED; i++)
- filter->preds[i]->fn = filter_pred_none;
}
-static void __free_preds(struct event_filter *filter)
+static void filter_disable(struct ftrace_event_call *call)
{
- int i;
+ call->flags &= ~TRACE_EVENT_FL_FILTERED;
+}
+static void __free_filter(struct event_filter *filter)
+{
if (!filter)
return;
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- if (filter->preds[i])
- filter_free_pred(filter->preds[i]);
- }
- kfree(filter->preds);
+ __free_preds(filter);
kfree(filter->filter_string);
kfree(filter);
}
+/*
+ * Called when destroying the ftrace_event_call.
+ * The call is being freed, so we do not need to worry about
+ * the call being currently used. This is for module code removing
+ * the tracepoints from within it.
+ */
void destroy_preds(struct ftrace_event_call *call)
{
- __free_preds(call->filter);
+ __free_filter(call->filter);
call->filter = NULL;
- call->flags &= ~TRACE_EVENT_FL_FILTERED;
}
-static struct event_filter *__alloc_preds(void)
+static struct event_filter *__alloc_filter(void)
{
struct event_filter *filter;
+
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ return filter;
+}
+
+static int __alloc_preds(struct event_filter *filter, int n_preds)
+{
struct filter_pred *pred;
int i;
- filter = kzalloc(sizeof(*filter), GFP_KERNEL);
- if (!filter)
- return ERR_PTR(-ENOMEM);
+ if (filter->preds)
+ __free_preds(filter);
- filter->n_preds = 0;
+ filter->preds =
+ kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL);
- filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
if (!filter->preds)
- goto oom;
+ return -ENOMEM;
- for (i = 0; i < MAX_FILTER_PRED; i++) {
- pred = kzalloc(sizeof(*pred), GFP_KERNEL);
- if (!pred)
- goto oom;
+ filter->a_preds = n_preds;
+ filter->n_preds = 0;
+
+ for (i = 0; i < n_preds; i++) {
+ pred = &filter->preds[i];
pred->fn = filter_pred_none;
- filter->preds[i] = pred;
}
- return filter;
-
-oom:
- __free_preds(filter);
- return ERR_PTR(-ENOMEM);
-}
-
-static int init_preds(struct ftrace_event_call *call)
-{
- if (call->filter)
- return 0;
-
- call->flags &= ~TRACE_EVENT_FL_FILTERED;
- call->filter = __alloc_preds();
- if (IS_ERR(call->filter))
- return PTR_ERR(call->filter);
-
return 0;
}
-static int init_subsystem_preds(struct event_subsystem *system)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
{
struct ftrace_event_call *call;
- int err;
list_for_each_entry(call, &ftrace_events, list) {
if (strcmp(call->class->system, system->name) != 0)
continue;
- err = init_preds(call);
- if (err)
- return err;
+ filter_disable(call);
+ remove_filter_string(call->filter);
}
-
- return 0;
}
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static void filter_free_subsystem_filters(struct event_subsystem *system)
{
struct ftrace_event_call *call;
list_for_each_entry(call, &ftrace_events, list) {
if (strcmp(call->class->system, system->name) != 0)
continue;
-
- filter_disable_preds(call);
- remove_filter_string(call->filter);
+ __free_filter(call->filter);
+ call->filter = NULL;
}
}
struct ftrace_event_call *call,
struct event_filter *filter,
struct filter_pred *pred,
+ struct pred_stack *stack,
filter_pred_fn_t fn)
{
int idx, err;
- if (filter->n_preds == MAX_FILTER_PRED) {
+ if (WARN_ON(filter->n_preds == filter->a_preds)) {
parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
return -ENOSPC;
}
idx = filter->n_preds;
- filter_clear_pred(filter->preds[idx]);
- err = filter_set_pred(filter->preds[idx], pred, fn);
+ filter_clear_pred(&filter->preds[idx]);
+ err = filter_set_pred(filter, idx, stack, pred, fn);
if (err)
return err;
struct ftrace_event_call *call,
struct event_filter *filter,
struct filter_pred *pred,
+ struct pred_stack *stack,
bool dry_run)
{
struct ftrace_event_field *field;
unsigned long long val;
int ret;
- pred->fn = filter_pred_none;
+ fn = pred->fn = filter_pred_none;
- if (pred->op == OP_AND) {
- pred->pop_n = 2;
- fn = filter_pred_and;
+ if (pred->op == OP_AND)
goto add_pred_fn;
- } else if (pred->op == OP_OR) {
- pred->pop_n = 2;
- fn = filter_pred_or;
+ else if (pred->op == OP_OR)
goto add_pred_fn;
- }
field = find_event_field(call, pred->field_name);
if (!field) {
add_pred_fn:
if (!dry_run)
- return filter_add_pred_fn(ps, call, filter, pred, fn);
+ return filter_add_pred_fn(ps, call, filter, pred, stack, fn);
return 0;
}
return 0;
}
+static int count_preds(struct filter_parse_state *ps)
+{
+ struct postfix_elt *elt;
+ int n_preds = 0;
+
+ list_for_each_entry(elt, &ps->postfix, list) {
+ if (elt->op == OP_NONE)
+ continue;
+ n_preds++;
+ }
+
+ return n_preds;
+}
+
+/*
+ * The tree is walked at filtering of an event. If the tree is not correctly
+ * built, it may cause an infinite loop. Check here that the tree does
+ * indeed terminate.
+ */
+static int check_pred_tree(struct event_filter *filter,
+ struct filter_pred *root)
+{
+ struct filter_pred *preds;
+ struct filter_pred *pred;
+ enum move_type move = MOVE_DOWN;
+ int count = 0;
+ int done = 0;
+ int max;
+
+ /*
+ * The max that we can hit a node is three times.
+ * Once going down, once coming up from left, and
+ * once coming up from right. This is more than enough
+ * since leafs are only hit a single time.
+ */
+ max = 3 * filter->n_preds;
+
+ preds = filter->preds;
+ if (!preds)
+ return -EINVAL;
+ pred = root;
+
+ do {
+ if (WARN_ON(count++ > max))
+ return -EINVAL;
+
+ switch (move) {
+ case MOVE_DOWN:
+ if (pred->left != FILTER_PRED_INVALID) {
+ pred = &preds[pred->left];
+ continue;
+ }
+ /* A leaf at the root is just a leaf in the tree */
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ done = 1;
+ } while (!done);
+
+ /* We are fine. */
+ return 0;
+}
+
+static int count_leafs(struct filter_pred *preds, struct filter_pred *root)
+{
+ struct filter_pred *pred;
+ enum move_type move = MOVE_DOWN;
+ int count = 0;
+ int done = 0;
+
+ pred = root;
+
+ do {
+ switch (move) {
+ case MOVE_DOWN:
+ if (pred->left != FILTER_PRED_INVALID) {
+ pred = &preds[pred->left];
+ continue;
+ }
+ /* A leaf at the root is just a leaf in the tree */
+ if (pred == root)
+ return 1;
+ count++;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ done = 1;
+ } while (!done);
+
+ return count;
+}
+
+static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
+{
+ struct filter_pred *pred;
+ enum move_type move = MOVE_DOWN;
+ int count = 0;
+ int children;
+ int done = 0;
+
+ /* No need to keep the fold flag */
+ root->index &= ~FILTER_PRED_FOLD;
+
+ /* If the root is a leaf then do nothing */
+ if (root->left == FILTER_PRED_INVALID)
+ return 0;
+
+ /* count the children */
+ children = count_leafs(preds, &preds[root->left]);
+ children += count_leafs(preds, &preds[root->right]);
+
+ root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL);
+ if (!root->ops)
+ return -ENOMEM;
+
+ root->val = children;
+
+ pred = root;
+ do {
+ switch (move) {
+ case MOVE_DOWN:
+ if (pred->left != FILTER_PRED_INVALID) {
+ pred = &preds[pred->left];
+ continue;
+ }
+ if (WARN_ON(count == children))
+ return -EINVAL;
+ pred->index &= ~FILTER_PRED_FOLD;
+ root->ops[count++] = pred->index;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ done = 1;
+ } while (!done);
+
+ return 0;
+}
+
+/*
+ * To optimize the processing of the ops, if we have several "ors" or
+ * "ands" together, we can put them in an array and process them all
+ * together speeding up the filter logic.
+ */
+static int fold_pred_tree(struct event_filter *filter,
+ struct filter_pred *root)
+{
+ struct filter_pred *preds;
+ struct filter_pred *pred;
+ enum move_type move = MOVE_DOWN;
+ int done = 0;
+ int err;
+
+ preds = filter->preds;
+ if (!preds)
+ return -EINVAL;
+ pred = root;
+
+ do {
+ switch (move) {
+ case MOVE_DOWN:
+ if (pred->index & FILTER_PRED_FOLD) {
+ err = fold_pred(preds, pred);
+ if (err)
+ return err;
+ /* Folded nodes are like leafs */
+ } else if (pred->left != FILTER_PRED_INVALID) {
+ pred = &preds[pred->left];
+ continue;
+ }
+
+ /* A leaf at the root is just a leaf in the tree */
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ case MOVE_UP_FROM_LEFT:
+ pred = &preds[pred->right];
+ move = MOVE_DOWN;
+ continue;
+ case MOVE_UP_FROM_RIGHT:
+ if (pred == root)
+ break;
+ pred = get_pred_parent(pred, preds,
+ pred->parent, &move);
+ continue;
+ }
+ done = 1;
+ } while (!done);
+
+ return 0;
+}
+
static int replace_preds(struct ftrace_event_call *call,
struct event_filter *filter,
struct filter_parse_state *ps,
{
char *operand1 = NULL, *operand2 = NULL;
struct filter_pred *pred;
+ struct filter_pred *root;
struct postfix_elt *elt;
+ struct pred_stack stack = { }; /* init to NULL */
int err;
int n_preds = 0;
+ n_preds = count_preds(ps);
+ if (n_preds >= MAX_FILTER_PRED) {
+ parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+ return -ENOSPC;
+ }
+
err = check_preds(ps);
if (err)
return err;
+ if (!dry_run) {
+ err = __alloc_pred_stack(&stack, n_preds);
+ if (err)
+ return err;
+ err = __alloc_preds(filter, n_preds);
+ if (err)
+ goto fail;
+ }
+
+ n_preds = 0;
list_for_each_entry(elt, &ps->postfix, list) {
if (elt->op == OP_NONE) {
if (!operand1)
operand2 = elt->operand;
else {
parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
- return -EINVAL;
+ err = -EINVAL;
+ goto fail;
}
continue;
}
- if (n_preds++ == MAX_FILTER_PRED) {
+ if (WARN_ON(n_preds++ == MAX_FILTER_PRED)) {
parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
- return -ENOSPC;
+ err = -ENOSPC;
+ goto fail;
}
if (elt->op == OP_AND || elt->op == OP_OR) {
if (!operand1 || !operand2) {
parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
- return -EINVAL;
+ err = -EINVAL;
+ goto fail;
}
pred = create_pred(elt->op, operand1, operand2);
add_pred:
- if (!pred)
- return -ENOMEM;
- err = filter_add_pred(ps, call, filter, pred, dry_run);
+ if (!pred) {
+ err = -ENOMEM;
+ goto fail;
+ }
+ err = filter_add_pred(ps, call, filter, pred, &stack, dry_run);
filter_free_pred(pred);
if (err)
- return err;
+ goto fail;
operand1 = operand2 = NULL;
}
- return 0;
+ if (!dry_run) {
+ /* We should have one item left on the stack */
+ pred = __pop_pred_stack(&stack);
+ if (!pred)
+ return -EINVAL;
+ /* This item is where we start from in matching */
+ root = pred;
+ /* Make sure the stack is empty */
+ pred = __pop_pred_stack(&stack);
+ if (WARN_ON(pred)) {
+ err = -EINVAL;
+ filter->root = NULL;
+ goto fail;
+ }
+ err = check_pred_tree(filter, root);
+ if (err)
+ goto fail;
+
+ /* Optimize the tree */
+ err = fold_pred_tree(filter, root);
+ if (err)
+ goto fail;
+
+ /* We don't set root until we know it works */
+ barrier();
+ filter->root = root;
+ }
+
+ err = 0;
+fail:
+ __free_pred_stack(&stack);
+ return err;
}
+struct filter_list {
+ struct list_head list;
+ struct event_filter *filter;
+};
+
static int replace_system_preds(struct event_subsystem *system,
struct filter_parse_state *ps,
char *filter_string)
{
struct ftrace_event_call *call;
+ struct filter_list *filter_item;
+ struct filter_list *tmp;
+ LIST_HEAD(filter_list);
bool fail = true;
int err;
list_for_each_entry(call, &ftrace_events, list) {
- struct event_filter *filter = call->filter;
if (strcmp(call->class->system, system->name) != 0)
continue;
- /* try to see if the filter can be applied */
- err = replace_preds(call, filter, ps, filter_string, true);
+ /*
+ * Try to see if the filter can be applied
+ * (filter arg is ignored on dry_run)
+ */
+ err = replace_preds(call, NULL, ps, filter_string, true);
if (err)
+ goto fail;
+ }
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ struct event_filter *filter;
+
+ if (strcmp(call->class->system, system->name) != 0)
continue;
- /* really apply the filter */
- filter_disable_preds(call);
- err = replace_preds(call, filter, ps, filter_string, false);
+ filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
+ if (!filter_item)
+ goto fail_mem;
+
+ list_add_tail(&filter_item->list, &filter_list);
+
+ filter_item->filter = __alloc_filter();
+ if (!filter_item->filter)
+ goto fail_mem;
+ filter = filter_item->filter;
+
+ /* Can only fail on no memory */
+ err = replace_filter_string(filter, filter_string);
if (err)
- filter_disable_preds(call);
- else {
+ goto fail_mem;
+
+ err = replace_preds(call, filter, ps, filter_string, false);
+ if (err) {
+ filter_disable(call);
+ parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+ append_filter_err(ps, filter);
+ } else
call->flags |= TRACE_EVENT_FL_FILTERED;
- replace_filter_string(filter, filter_string);
- }
+ /*
+ * Regardless of if this returned an error, we still
+ * replace the filter for the call.
+ */
+ filter = call->filter;
+ call->filter = filter_item->filter;
+ filter_item->filter = filter;
+
fail = false;
}
- if (fail) {
- parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
- return -EINVAL;
+ if (fail)
+ goto fail;
+
+ /*
+ * The calls can still be using the old filters.
+ * Do a synchronize_sched() to ensure all calls are
+ * done with them before we free them.
+ */
+ synchronize_sched();
+ list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+ __free_filter(filter_item->filter);
+ list_del(&filter_item->list);
+ kfree(filter_item);
}
return 0;
+ fail:
+ /* No call succeeded */
+ list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+ list_del(&filter_item->list);
+ kfree(filter_item);
+ }
+ parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+ return -EINVAL;
+ fail_mem:
+ /* If any call succeeded, we still need to sync */
+ if (!fail)
+ synchronize_sched();
+ list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
+ __free_filter(filter_item->filter);
+ list_del(&filter_item->list);
+ kfree(filter_item);
+ }
+ return -ENOMEM;
}
int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
{
- int err;
struct filter_parse_state *ps;
+ struct event_filter *filter;
+ struct event_filter *tmp;
+ int err = 0;
mutex_lock(&event_mutex);
- err = init_preds(call);
- if (err)
- goto out_unlock;
-
if (!strcmp(strstrip(filter_string), "0")) {
- filter_disable_preds(call);
- remove_filter_string(call->filter);
+ filter_disable(call);
+ filter = call->filter;
+ if (!filter)
+ goto out_unlock;
+ call->filter = NULL;
+ /* Make sure the filter is not being used */
+ synchronize_sched();
+ __free_filter(filter);
goto out_unlock;
}
if (!ps)
goto out_unlock;
- filter_disable_preds(call);
- replace_filter_string(call->filter, filter_string);
+ filter = __alloc_filter();
+ if (!filter) {
+ kfree(ps);
+ goto out_unlock;
+ }
+
+ replace_filter_string(filter, filter_string);
parse_init(ps, filter_ops, filter_string);
err = filter_parse(ps);
if (err) {
- append_filter_err(ps, call->filter);
+ append_filter_err(ps, filter);
goto out;
}
- err = replace_preds(call, call->filter, ps, filter_string, false);
- if (err)
- append_filter_err(ps, call->filter);
- else
+ err = replace_preds(call, filter, ps, filter_string, false);
+ if (err) {
+ filter_disable(call);
+ append_filter_err(ps, filter);
+ } else
call->flags |= TRACE_EVENT_FL_FILTERED;
out:
+ /*
+ * Always swap the call filter with the new filter
+ * even if there was an error. If there was an error
+ * in the filter, we disable the filter and show the error
+ * string
+ */
+ tmp = call->filter;
+ call->filter = filter;
+ if (tmp) {
+ /* Make sure the call is done with the filter */
+ synchronize_sched();
+ __free_filter(tmp);
+ }
filter_opstack_clear(ps);
postfix_clear(ps);
kfree(ps);
int apply_subsystem_event_filter(struct event_subsystem *system,
char *filter_string)
{
- int err;
struct filter_parse_state *ps;
+ struct event_filter *filter;
+ int err = 0;
mutex_lock(&event_mutex);
- err = init_subsystem_preds(system);
- if (err)
- goto out_unlock;
-
if (!strcmp(strstrip(filter_string), "0")) {
filter_free_subsystem_preds(system);
remove_filter_string(system->filter);
+ filter = system->filter;
+ system->filter = NULL;
+ /* Ensure all filters are no longer used */
+ synchronize_sched();
+ filter_free_subsystem_filters(system);
+ __free_filter(filter);
goto out_unlock;
}
if (!ps)
goto out_unlock;
- replace_filter_string(system->filter, filter_string);
+ filter = __alloc_filter();
+ if (!filter)
+ goto out;
+
+ replace_filter_string(filter, filter_string);
+ /*
+ * No event actually uses the system filter
+ * we can free it without synchronize_sched().
+ */
+ __free_filter(system->filter);
+ system->filter = filter;
parse_init(ps, filter_ops, filter_string);
err = filter_parse(ps);
struct event_filter *filter = event->filter;
event->filter = NULL;
- __free_preds(filter);
+ __free_filter(filter);
}
int ftrace_profile_set_filter(struct perf_event *event, int event_id,
if (event->filter)
goto out_unlock;
- filter = __alloc_preds();
- if (IS_ERR(filter)) {
+ filter = __alloc_filter();
+ if (!filter) {
err = PTR_ERR(filter);
goto out_unlock;
}
err = -ENOMEM;
ps = kzalloc(sizeof(*ps), GFP_KERNEL);
if (!ps)
- goto free_preds;
+ goto free_filter;
parse_init(ps, filter_ops, filter_str);
err = filter_parse(ps);
postfix_clear(ps);
kfree(ps);
-free_preds:
+free_filter:
if (err)
- __free_preds(filter);
+ __free_filter(filter);
out_unlock:
mutex_unlock(&event_mutex);
kfree(data);
}
+/* Bitfield fetch function */
+struct bitfield_fetch_param {
+ struct fetch_param orig;
+ unsigned char hi_shift;
+ unsigned char low_shift;
+};
+
+#define DEFINE_FETCH_bitfield(type) \
+static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
+ void *data, void *dest) \
+{ \
+ struct bitfield_fetch_param *bprm = data; \
+ type buf = 0; \
+ call_fetch(&bprm->orig, regs, &buf); \
+ if (buf) { \
+ buf <<= bprm->hi_shift; \
+ buf >>= bprm->low_shift; \
+ } \
+ *(type *)dest = buf; \
+}
+DEFINE_BASIC_FETCH_FUNCS(bitfield)
+#define fetch_bitfield_string NULL
+#define fetch_bitfield_string_size NULL
+
+static __kprobes void
+free_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+ /*
+ * Don't check the bitfield itself, because this must be the
+ * last fetch function.
+ */
+ if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+ free_deref_fetch_param(data->orig.data);
+ else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+ free_symbol_cache(data->orig.data);
+ kfree(data);
+}
/* Default (unsigned long) fetch type */
#define __DEFAULT_FETCH_TYPE(t) u##t
#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
FETCH_MTD_memory,
FETCH_MTD_symbol,
FETCH_MTD_deref,
+ FETCH_MTD_bitfield,
FETCH_MTD_END,
};
ASSIGN_FETCH_FUNC(memory, ftype), \
ASSIGN_FETCH_FUNC(symbol, ftype), \
ASSIGN_FETCH_FUNC(deref, ftype), \
+ASSIGN_FETCH_FUNC(bitfield, ftype), \
} \
}
if (!type)
type = DEFAULT_FETCH_TYPE_STR;
+ /* Special case: bitfield */
+ if (*type == 'b') {
+ unsigned long bs;
+ type = strchr(type, '/');
+ if (!type)
+ goto fail;
+ type++;
+ if (strict_strtoul(type, 0, &bs))
+ goto fail;
+ switch (bs) {
+ case 8:
+ return find_fetch_type("u8");
+ case 16:
+ return find_fetch_type("u16");
+ case 32:
+ return find_fetch_type("u32");
+ case 64:
+ return find_fetch_type("u64");
+ default:
+ goto fail;
+ }
+ }
+
for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
if (strcmp(type, fetch_type_table[i].name) == 0)
return &fetch_type_table[i];
+fail:
return NULL;
}
static void free_probe_arg(struct probe_arg *arg)
{
- if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+ if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+ free_bitfield_fetch_param(arg->fetch.data);
+ else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
free_deref_fetch_param(arg->fetch.data);
else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
free_symbol_cache(arg->fetch.data);
}
break;
case '+': /* deref memory */
+ arg++; /* Skip '+', because strict_strtol() rejects it. */
case '-':
tmp = strchr(arg, '(');
if (!tmp)
break;
*tmp = '\0';
- ret = strict_strtol(arg + 1, 0, &offset);
+ ret = strict_strtol(arg, 0, &offset);
if (ret)
break;
- if (arg[0] == '-')
- offset = -offset;
arg = tmp + 1;
tmp = strrchr(arg, ')');
if (tmp) {
return ret;
}
+#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long))
+
+/* Bitfield type needs to be parsed into a fetch function */
+static int __parse_bitfield_probe_arg(const char *bf,
+ const struct fetch_type *t,
+ struct fetch_param *f)
+{
+ struct bitfield_fetch_param *bprm;
+ unsigned long bw, bo;
+ char *tail;
+
+ if (*bf != 'b')
+ return 0;
+
+ bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+ if (!bprm)
+ return -ENOMEM;
+ bprm->orig = *f;
+ f->fn = t->fetch[FETCH_MTD_bitfield];
+ f->data = (void *)bprm;
+
+ bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */
+ if (bw == 0 || *tail != '@')
+ return -EINVAL;
+
+ bf = tail + 1;
+ bo = simple_strtoul(bf, &tail, 0);
+ if (tail == bf || *tail != '/')
+ return -EINVAL;
+
+ bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo);
+ bprm->low_shift = bprm->hi_shift + bo;
+ return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0;
+}
+
/* String length checking wrapper */
static int parse_probe_arg(char *arg, struct trace_probe *tp,
struct probe_arg *parg, int is_return)
parg->offset = tp->size;
tp->size += parg->type->size;
ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
+ if (ret >= 0 && t != NULL)
+ ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
if (ret >= 0) {
parg->fetch_size.fn = get_fetch_size_function(parg->type,
parg->fetch.fn);
return ret;
}
-#define WRITE_BUFSIZE 128
+#define WRITE_BUFSIZE 4096
static ssize_t probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
* @entry: The trace entry field from the ring buffer
*
* Prints the generic fields of irqs off, in hard or softirq, preempt
- * count and lock depth.
+ * count.
*/
int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
{
- int hardirq, softirq;
+ char hardsoft_irq;
+ char need_resched;
+ char irqs_off;
+ int hardirq;
+ int softirq;
int ret;
hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
+ irqs_off =
+ (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+ (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
+ '.';
+ need_resched =
+ (entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.';
+ hardsoft_irq =
+ (hardirq && softirq) ? 'H' :
+ hardirq ? 'h' :
+ softirq ? 's' :
+ '.';
+
if (!trace_seq_printf(s, "%c%c%c",
- (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
- (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
- 'X' : '.',
- (entry->flags & TRACE_FLAG_NEED_RESCHED) ?
- 'N' : '.',
- (hardirq && softirq) ? 'H' :
- hardirq ? 'h' : softirq ? 's' : '.'))
+ irqs_off, need_resched, hardsoft_irq))
return 0;
if (entry->preempt_count)
else
ret = trace_seq_putc(s, '.');
- if (!ret)
- return 0;
-
- if (entry->lock_depth < 0)
- return trace_seq_putc(s, '.');
-
- return trace_seq_printf(s, "%d", entry->lock_depth);
+ return ret;
}
static int
ctx_trace = tr;
}
-static void stop_sched_trace(struct trace_array *tr)
-{
- tracing_stop_sched_switch_record();
-}
-
-static int sched_switch_trace_init(struct trace_array *tr)
-{
- ctx_trace = tr;
- tracing_reset_online_cpus(tr);
- tracing_start_sched_switch_record();
- return 0;
-}
-
-static void sched_switch_trace_reset(struct trace_array *tr)
-{
- if (sched_ref)
- stop_sched_trace(tr);
-}
-
-static void sched_switch_trace_start(struct trace_array *tr)
-{
- sched_stopped = 0;
-}
-
-static void sched_switch_trace_stop(struct trace_array *tr)
-{
- sched_stopped = 1;
-}
-
-static struct tracer sched_switch_trace __read_mostly =
-{
- .name = "sched_switch",
- .init = sched_switch_trace_init,
- .reset = sched_switch_trace_reset,
- .start = sched_switch_trace_start,
- .stop = sched_switch_trace_stop,
- .wait_pipe = poll_wait_pipe,
-#ifdef CONFIG_FTRACE_SELFTEST
- .selftest = trace_selftest_startup_sched_switch,
-#endif
-};
-
-__init static int init_sched_switch_trace(void)
-{
- return register_tracer(&sched_switch_trace);
-}
-device_initcall(init_sched_switch_trace);
-
static struct syscall_metadata **syscalls_metadata;
+#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+ /*
+ * Only compare after the "sys" prefix. Archs that use
+ * syscall wrappers may have syscalls symbols aliases prefixed
+ * with "SyS" instead of "sys", leading to an unwanted
+ * mismatch.
+ */
+ return !strcmp(sym + 3, name + 3);
+}
+#endif
+
static __init struct syscall_metadata *
find_syscall_meta(unsigned long syscall)
{
stop = __stop_syscalls_metadata;
kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+ if (arch_syscall_match_sym_name(str, "sys_ni_syscall"))
+ return NULL;
+
for ( ; start < stop; start++) {
- /*
- * Only compare after the "sys" prefix. Archs that use
- * syscall wrappers may have syscalls symbols aliases prefixed
- * with "SyS" instead of "sys", leading to an unwanted
- * mismatch.
- */
- if ((*start)->name && !strcmp((*start)->name + 3, str + 3))
+ if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name))
return *start;
}
return NULL;
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
- if (num < 0 || num >= NR_syscalls)
+ if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_enter)
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
- if (num < 0 || num >= NR_syscalls)
+ if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return;
mutex_lock(&syscall_trace_lock);
sys_refcount_enter--;
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
- if (num < 0 || num >= NR_syscalls)
+ if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_exit)
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
- if (num < 0 || num >= NR_syscalls)
+ if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
return;
mutex_lock(&syscall_trace_lock);
sys_refcount_exit--;
int init_syscall_trace(struct ftrace_event_call *call)
{
int id;
+ int num;
+
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
+ if (num < 0 || num >= NR_syscalls) {
+ pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
+ ((struct syscall_metadata *)call->data)->name);
+ return -ENOSYS;
+ }
if (set_syscall_print_fmt(call) < 0)
return -ENOMEM;
return id;
}
-unsigned long __init arch_syscall_addr(int nr)
+unsigned long __init __weak arch_syscall_addr(int nr)
{
return (unsigned long)sys_call_table[nr];
}
goto out_save;
}
- printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
- cpu, PTR_ERR(event));
+
+ /* vary the KERN level based on the returned errno */
+ if (PTR_ERR(event) == -EOPNOTSUPP)
+ printk(KERN_INFO "NMI watchdog disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
+ else if (PTR_ERR(event) == -ENOENT)
+ printk(KERN_WARNING "NMI watchdog disabled (cpu%i): hardware events not enabled\n", cpu);
+ else
+ printk(KERN_ERR "NMI watchdog disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event));
return PTR_ERR(event);
/* success path */
MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */
IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */
- MAYDAY_INITIAL_TIMEOUT = HZ / 100, /* call for help after 10ms */
+ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2,
+ /* call for help after 10ms
+ (min two ticks) */
MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */
CREATE_COOLDOWN = HZ, /* time to breath after fail */
TRUSTEE_COOLDOWN = HZ / 10, /* for trustee draining */
static struct debug_obj_descr work_debug_descr;
+static void *work_debug_hint(void *addr)
+{
+ return ((struct work_struct *) addr)->func;
+}
+
/*
* fixup_init is called when:
* - an active object is initialized
static struct debug_obj_descr work_debug_descr = {
.name = "work_struct",
+ .debug_hint = work_debug_hint,
.fixup_init = work_fixup_init,
.fixup_activate = work_fixup_activate,
.fixup_free = work_fixup_free,
move_linked_works(work, scheduled, &n);
process_scheduled_works(rescuer);
+
+ /*
+ * Leave this gcwq. If keep_working() is %true, notify a
+ * regular worker; otherwise, we end up with 0 concurrency
+ * and stalling the execution.
+ */
+ if (keep_working(gcwq))
+ wake_up_worker(gcwq);
+
spin_unlock_irq(&gcwq->lock);
}
*/
spin_lock(&workqueue_lock);
- if (workqueue_freezing && wq->flags & WQ_FREEZEABLE)
+ if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
for_each_cwq_cpu(cpu, wq)
get_cwq(cpu, wq)->max_active = 0;
spin_lock_irq(&gcwq->lock);
- if (!(wq->flags & WQ_FREEZEABLE) ||
+ if (!(wq->flags & WQ_FREEZABLE) ||
!(gcwq->flags & GCWQ_FREEZING))
get_cwq(gcwq->cpu, wq)->max_active = max_active;
* want to get it over with ASAP - spam rescuers, wake up as
* many idlers as necessary and create new ones till the
* worklist is empty. Note that if the gcwq is frozen, there
- * may be frozen works in freezeable cwqs. Don't declare
+ * may be frozen works in freezable cwqs. Don't declare
* completion while frozen.
*/
while (gcwq->nr_workers != gcwq->nr_idle ||
/**
* freeze_workqueues_begin - begin freezing workqueues
*
- * Start freezing workqueues. After this function returns, all
- * freezeable workqueues will queue new works to their frozen_works
- * list instead of gcwq->worklist.
+ * Start freezing workqueues. After this function returns, all freezable
+ * workqueues will queue new works to their frozen_works list instead of
+ * gcwq->worklist.
*
* CONTEXT:
* Grabs and releases workqueue_lock and gcwq->lock's.
list_for_each_entry(wq, &workqueues, list) {
struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
- if (cwq && wq->flags & WQ_FREEZEABLE)
+ if (cwq && wq->flags & WQ_FREEZABLE)
cwq->max_active = 0;
}
}
/**
- * freeze_workqueues_busy - are freezeable workqueues still busy?
+ * freeze_workqueues_busy - are freezable workqueues still busy?
*
* Check whether freezing is complete. This function must be called
* between freeze_workqueues_begin() and thaw_workqueues().
* Grabs and releases workqueue_lock.
*
* RETURNS:
- * %true if some freezeable workqueues are still busy. %false if
- * freezing is complete.
+ * %true if some freezable workqueues are still busy. %false if freezing
+ * is complete.
*/
bool freeze_workqueues_busy(void)
{
list_for_each_entry(wq, &workqueues, list) {
struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
- if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+ if (!cwq || !(wq->flags & WQ_FREEZABLE))
continue;
BUG_ON(cwq->nr_active < 0);
list_for_each_entry(wq, &workqueues, list) {
struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
- if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+ if (!cwq || !(wq->flags & WQ_FREEZABLE))
continue;
/* restore max_active and repopulate worklist */
config FRAME_POINTER
bool "Compile the kernel with frame pointers"
depends on DEBUG_KERNEL && \
- (CRIS || M68K || M68KNOMMU || FRV || UML || \
+ (CRIS || M68K || FRV || UML || \
AVR32 || SUPERH || BLACKFIN || MN10300) || \
ARCH_WANT_FRAME_POINTERS
default y if (DEBUG_INFO && UML) || ARCH_WANT_FRAME_POINTERS
static void debug_print_object(struct debug_obj *obj, char *msg)
{
+ struct debug_obj_descr *descr = obj->descr;
static int limit;
- if (limit < 5 && obj->descr != descr_test) {
+ if (limit < 5 && descr != descr_test) {
+ void *hint = descr->debug_hint ?
+ descr->debug_hint(obj->object) : NULL;
limit++;
WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) "
- "object type: %s\n",
+ "object type: %s hint: %pS\n",
msg, obj_states[obj->state], obj->astate,
- obj->descr->name);
+ descr->name, hint);
}
debug_objects_warnings++;
}
}
EXPORT_SYMBOL(__list_add);
+void __list_del_entry(struct list_head *entry)
+{
+ struct list_head *prev, *next;
+
+ prev = entry->prev;
+ next = entry->next;
+
+ if (WARN(next == LIST_POISON1,
+ "list_del corruption, %p->next is LIST_POISON1 (%p)\n",
+ entry, LIST_POISON1) ||
+ WARN(prev == LIST_POISON2,
+ "list_del corruption, %p->prev is LIST_POISON2 (%p)\n",
+ entry, LIST_POISON2) ||
+ WARN(prev->next != entry,
+ "list_del corruption. prev->next should be %p, "
+ "but was %p\n", entry, prev->next) ||
+ WARN(next->prev != entry,
+ "list_del corruption. next->prev should be %p, "
+ "but was %p\n", entry, next->prev))
+ return;
+
+ __list_del(prev, next);
+}
+EXPORT_SYMBOL(__list_del_entry);
+
/**
* list_del - deletes entry from list.
* @entry: the element to delete from the list.
*/
void list_del(struct list_head *entry)
{
- WARN(entry->next == LIST_POISON1,
- "list_del corruption, next is LIST_POISON1 (%p)\n",
- LIST_POISON1);
- WARN(entry->next != LIST_POISON1 && entry->prev == LIST_POISON2,
- "list_del corruption, prev is LIST_POISON2 (%p)\n",
- LIST_POISON2);
- WARN(entry->prev->next != entry,
- "list_del corruption. prev->next should be %p, "
- "but was %p\n", entry, entry->prev->next);
- WARN(entry->next->prev != entry,
- "list_del corruption. next->prev should be %p, "
- "but was %p\n", entry, entry->next->prev);
- __list_del(entry->prev, entry->next);
+ __list_del_entry(entry);
entry->next = LIST_POISON1;
entry->prev = LIST_POISON2;
}
{
int i, len = 0;
- for (i = 0; i < n; i++) {
+ for (i = 0; i < n; i++, p++) {
if (p->len)
len += nla_total_size(p->len);
else if (nla_attr_minlen[p->type])
#ifdef CONFIG_DEBUG_PI_LIST
+static struct plist_head test_head;
+
static void plist_check_prev_next(struct list_head *t, struct list_head *p,
struct list_head *n)
{
static void plist_check_head(struct plist_head *head)
{
- WARN_ON(!head->rawlock && !head->spinlock);
+ WARN_ON(head != &test_head && !head->rawlock && !head->spinlock);
if (head->rawlock)
WARN_ON_SMP(!raw_spin_is_locked(head->rawlock));
if (head->spinlock)
WARN_ON_SMP(!spin_is_locked(head->spinlock));
- plist_check_list(&head->prio_list);
+ if (!plist_head_empty(head))
+ plist_check_list(&plist_first(head)->prio_list);
plist_check_list(&head->node_list);
}
*/
void plist_add(struct plist_node *node, struct plist_head *head)
{
- struct plist_node *iter;
+ struct plist_node *first, *iter, *prev = NULL;
+ struct list_head *node_next = &head->node_list;
plist_check_head(head);
WARN_ON(!plist_node_empty(node));
+ WARN_ON(!list_empty(&node->prio_list));
+
+ if (plist_head_empty(head))
+ goto ins_node;
- list_for_each_entry(iter, &head->prio_list, plist.prio_list) {
- if (node->prio < iter->prio)
- goto lt_prio;
- else if (node->prio == iter->prio) {
- iter = list_entry(iter->plist.prio_list.next,
- struct plist_node, plist.prio_list);
- goto eq_prio;
+ first = iter = plist_first(head);
+
+ do {
+ if (node->prio < iter->prio) {
+ node_next = &iter->node_list;
+ break;
}
- }
-lt_prio:
- list_add_tail(&node->plist.prio_list, &iter->plist.prio_list);
-eq_prio:
- list_add_tail(&node->plist.node_list, &iter->plist.node_list);
+ prev = iter;
+ iter = list_entry(iter->prio_list.next,
+ struct plist_node, prio_list);
+ } while (iter != first);
+
+ if (!prev || prev->prio != node->prio)
+ list_add_tail(&node->prio_list, &iter->prio_list);
+ins_node:
+ list_add_tail(&node->node_list, node_next);
plist_check_head(head);
}
{
plist_check_head(head);
- if (!list_empty(&node->plist.prio_list)) {
- struct plist_node *next = plist_first(&node->plist);
+ if (!list_empty(&node->prio_list)) {
+ if (node->node_list.next != &head->node_list) {
+ struct plist_node *next;
+
+ next = list_entry(node->node_list.next,
+ struct plist_node, node_list);
- list_move_tail(&next->plist.prio_list, &node->plist.prio_list);
- list_del_init(&node->plist.prio_list);
+ /* add the next plist_node into prio_list */
+ if (list_empty(&next->prio_list))
+ list_add(&next->prio_list, &node->prio_list);
+ }
+ list_del_init(&node->prio_list);
}
- list_del_init(&node->plist.node_list);
+ list_del_init(&node->node_list);
plist_check_head(head);
}
+
+#ifdef CONFIG_DEBUG_PI_LIST
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+static struct plist_node __initdata test_node[241];
+
+static void __init plist_test_check(int nr_expect)
+{
+ struct plist_node *first, *prio_pos, *node_pos;
+
+ if (plist_head_empty(&test_head)) {
+ BUG_ON(nr_expect != 0);
+ return;
+ }
+
+ prio_pos = first = plist_first(&test_head);
+ plist_for_each(node_pos, &test_head) {
+ if (nr_expect-- < 0)
+ break;
+ if (node_pos == first)
+ continue;
+ if (node_pos->prio == prio_pos->prio) {
+ BUG_ON(!list_empty(&node_pos->prio_list));
+ continue;
+ }
+
+ BUG_ON(prio_pos->prio > node_pos->prio);
+ BUG_ON(prio_pos->prio_list.next != &node_pos->prio_list);
+ prio_pos = node_pos;
+ }
+
+ BUG_ON(nr_expect != 0);
+ BUG_ON(prio_pos->prio_list.next != &first->prio_list);
+}
+
+static int __init plist_test(void)
+{
+ int nr_expect = 0, i, loop;
+ unsigned int r = local_clock();
+
+ printk(KERN_INFO "start plist test\n");
+ plist_head_init(&test_head, NULL);
+ for (i = 0; i < ARRAY_SIZE(test_node); i++)
+ plist_node_init(test_node + i, 0);
+
+ for (loop = 0; loop < 1000; loop++) {
+ r = r * 193939 % 47629;
+ i = r % ARRAY_SIZE(test_node);
+ if (plist_node_empty(test_node + i)) {
+ r = r * 193939 % 47629;
+ test_node[i].prio = r % 99;
+ plist_add(test_node + i, &test_head);
+ nr_expect++;
+ } else {
+ plist_del(test_node + i, &test_head);
+ nr_expect--;
+ }
+ plist_test_check(nr_expect);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(test_node); i++) {
+ if (plist_node_empty(test_node + i))
+ continue;
+ plist_del(test_node + i, &test_head);
+ nr_expect--;
+ plist_test_check(nr_expect);
+ }
+
+ printk(KERN_INFO "end plist test\n");
+ return 0;
+}
+
+module_init(plist_test);
+
+#endif
/*
* wait for the read lock to be granted
*/
-asmregparm struct rw_semaphore __sched *
-rwsem_down_read_failed(struct rw_semaphore *sem)
+struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
{
return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_READ,
-RWSEM_ACTIVE_READ_BIAS);
/*
* wait for the write lock to be granted
*/
-asmregparm struct rw_semaphore __sched *
-rwsem_down_write_failed(struct rw_semaphore *sem)
+struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
{
return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_WRITE,
-RWSEM_ACTIVE_WRITE_BIAS);
* handle waking up a waiter on the semaphore
* - up_read/up_write has decremented the active part of count if we come here
*/
-asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
+struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
{
unsigned long flags;
* - caller incremented waiting part of count and discovered it still negative
* - just wake up any readers at the front of the queue
*/
-asmregparm struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
+struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
{
unsigned long flags;
/*
* Ensure that the address returned is DMA'ble
*/
- if (!dma_capable(dev, dev_addr, size))
- panic("map_single: bounce buffer is not DMA'ble");
+ if (!dma_capable(dev, dev_addr, size)) {
+ swiotlb_tbl_unmap_single(dev, map, size, dir);
+ dev_addr = swiotlb_virt_to_bus(dev, io_tlb_overflow_buffer);
+ }
return dev_addr;
}
static inline struct page *alloc_hugepage_vma(int defrag,
struct vm_area_struct *vma,
- unsigned long haddr)
+ unsigned long haddr, int nd)
{
return alloc_pages_vma(alloc_hugepage_gfpmask(defrag),
- HPAGE_PMD_ORDER, vma, haddr);
+ HPAGE_PMD_ORDER, vma, haddr, nd);
}
#ifndef CONFIG_NUMA
if (unlikely(khugepaged_enter(vma)))
return VM_FAULT_OOM;
page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
- vma, haddr);
+ vma, haddr, numa_node_id());
if (unlikely(!page))
goto out;
if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
}
for (i = 0; i < HPAGE_PMD_NR; i++) {
- pages[i] = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
- vma, address);
+ pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE,
+ vma, address, page_to_nid(page));
if (unlikely(!pages[i] ||
mem_cgroup_newpage_charge(pages[i], mm,
GFP_KERNEL))) {
if (transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow())
new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
- vma, haddr);
+ vma, haddr, numa_node_id());
else
new_page = NULL;
static void collapse_huge_page(struct mm_struct *mm,
unsigned long address,
struct page **hpage,
- struct vm_area_struct *vma)
+ struct vm_area_struct *vma,
+ int node)
{
pgd_t *pgd;
pud_t *pud;
#ifndef CONFIG_NUMA
VM_BUG_ON(!*hpage);
new_page = *hpage;
+ if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
+ up_read(&mm->mmap_sem);
+ return;
+ }
#else
VM_BUG_ON(*hpage);
/*
* mmap_sem in read mode is good idea also to allow greater
* scalability.
*/
- new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address);
+ new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
+ node);
if (unlikely(!new_page)) {
up_read(&mm->mmap_sem);
*hpage = ERR_PTR(-ENOMEM);
return;
}
-#endif
if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
up_read(&mm->mmap_sem);
put_page(new_page);
return;
}
+#endif
/* after allocating the hugepage upgrade to mmap_sem write mode */
up_read(&mm->mmap_sem);
/* VM_PFNMAP vmas may have vm_ops null but vm_file set */
if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
goto out;
+ if (is_vma_temporary_stack(vma))
+ goto out;
VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
pgd = pgd_offset(mm, address);
set_pmd_at(mm, address, pmd, _pmd);
spin_unlock(&mm->page_table_lock);
anon_vma_unlock(vma->anon_vma);
- mem_cgroup_uncharge_page(new_page);
goto out;
}
return;
out:
+ mem_cgroup_uncharge_page(new_page);
#ifdef CONFIG_NUMA
put_page(new_page);
#endif
struct page *page;
unsigned long _address;
spinlock_t *ptl;
+ int node = -1;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
page = vm_normal_page(vma, _address, pteval);
if (unlikely(!page))
goto out_unmap;
+ /*
+ * Chose the node of the first page. This could
+ * be more sophisticated and look at more pages,
+ * but isn't for now.
+ */
+ if (node == -1)
+ node = page_to_nid(page);
VM_BUG_ON(PageCompound(page));
if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
goto out_unmap;
pte_unmap_unlock(pte, ptl);
if (ret)
/* collapse_huge_page will return with the mmap_sem released */
- collapse_huge_page(mm, address, hpage, vma);
+ collapse_huge_page(mm, address, hpage, vma, node);
out:
return ret;
}
if ((!(vma->vm_flags & VM_HUGEPAGE) &&
!khugepaged_always()) ||
(vma->vm_flags & VM_NOHUGEPAGE)) {
+ skip:
progress++;
continue;
}
-
/* VM_PFNMAP vmas may have vm_ops null but vm_file set */
- if (!vma->anon_vma || vma->vm_ops || vma->vm_file) {
- khugepaged_scan.address = vma->vm_end;
- progress++;
- continue;
- }
+ if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
+ goto skip;
+ if (is_vma_temporary_stack(vma))
+ goto skip;
+
VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
hend = vma->vm_end & HPAGE_PMD_MASK;
- if (hstart >= hend) {
- progress++;
- continue;
- }
+ if (hstart >= hend)
+ goto skip;
+ if (khugepaged_scan.address > hend)
+ goto skip;
if (khugepaged_scan.address < hstart)
khugepaged_scan.address = hstart;
- if (khugepaged_scan.address > hend) {
- khugepaged_scan.address = hend + HPAGE_PMD_SIZE;
- progress++;
- continue;
- }
- BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
+ VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
while (khugepaged_scan.address < hend) {
int ret;
breakouterloop_mmap_sem:
spin_lock(&khugepaged_mm_lock);
- BUG_ON(khugepaged_scan.mm_slot != mm_slot);
+ VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot);
/*
* Release the current mm_slot if this mm is about to die, or
* if we scanned all vmas of this mm.
for (;;) {
mutex_unlock(&khugepaged_mutex);
- BUG_ON(khugepaged_thread != current);
+ VM_BUG_ON(khugepaged_thread != current);
khugepaged_loop();
- BUG_ON(khugepaged_thread != current);
+ VM_BUG_ON(khugepaged_thread != current);
mutex_lock(&khugepaged_mutex);
if (!khugepaged_enabled())
BUG_ON(0 == size);
- size = memblock_align_up(size, align);
-
/* Pump up max_addr */
if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
end = memblock.current_limit;
&ptl);
if (!pte_same(*page_table, orig_pte)) {
unlock_page(old_page);
- page_cache_release(old_page);
goto unlock;
}
page_cache_release(old_page);
&ptl);
if (!pte_same(*page_table, orig_pte)) {
unlock_page(old_page);
- page_cache_release(old_page);
goto unlock;
}
}
__SetPageUptodate(new_page);
- /*
- * Don't let another task, with possibly unlocked vma,
- * keep the mlocked page.
- */
- if ((vma->vm_flags & VM_LOCKED) && old_page) {
- lock_page(old_page); /* for LRU manipulation */
- clear_page_mlock(old_page);
- unlock_page(old_page);
- }
-
if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
goto oom_free_new;
if (new_page)
page_cache_release(new_page);
- if (old_page)
- page_cache_release(old_page);
unlock:
pte_unmap_unlock(page_table, ptl);
+ if (old_page) {
+ /*
+ * Don't let another task, with possibly unlocked vma,
+ * keep the mlocked page.
+ */
+ if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) {
+ lock_page(old_page); /* LRU manipulation */
+ munlock_vma_page(old_page);
+ unlock_page(old_page);
+ }
+ page_cache_release(old_page);
+ }
return ret;
oom_free_new:
page_cache_release(new_page);
details.last_index = ULONG_MAX;
details.i_mmap_lock = &mapping->i_mmap_lock;
+ mutex_lock(&mapping->unmap_mutex);
spin_lock(&mapping->i_mmap_lock);
/* Protect against endless unmapping loops */
if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->unmap_mutex);
}
EXPORT_SYMBOL(unmap_mapping_range);
goto out;
}
charged = 1;
- /*
- * Don't let another task, with possibly unlocked vma,
- * keep the mlocked page.
- */
- if (vma->vm_flags & VM_LOCKED)
- clear_page_mlock(vmf.page);
copy_user_highpage(page, vmf.page, address, vma);
__SetPageUptodate(page);
} else {
}
/* Return a zonelist indicated by gfp for node representing a mempolicy */
-static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy)
+static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy,
+ int nd)
{
- int nd = numa_node_id();
-
switch (policy->mode) {
case MPOL_PREFERRED:
if (!(policy->flags & MPOL_F_LOCAL))
zl = node_zonelist(interleave_nid(*mpol, vma, addr,
huge_page_shift(hstate_vma(vma))), gfp_flags);
} else {
- zl = policy_zonelist(gfp_flags, *mpol);
+ zl = policy_zonelist(gfp_flags, *mpol, numa_node_id());
if ((*mpol)->mode == MPOL_BIND)
*nodemask = &(*mpol)->v.nodes;
}
*/
struct page *
alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
- unsigned long addr)
+ unsigned long addr, int node)
{
struct mempolicy *pol = get_vma_policy(current, vma, addr);
struct zonelist *zl;
if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
unsigned nid;
- nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
+ nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
mpol_cond_put(pol);
page = alloc_page_interleave(gfp, order, nid);
put_mems_allowed();
return page;
}
- zl = policy_zonelist(gfp, pol);
+ zl = policy_zonelist(gfp, pol, node);
if (unlikely(mpol_needs_cond_ref(pol))) {
/*
* slow path: ref counted shared policy
page = alloc_page_interleave(gfp, order, interleave_nodes(pol));
else
page = __alloc_pages_nodemask(gfp, order,
- policy_zonelist(gfp, pol), policy_nodemask(gfp, pol));
+ policy_zonelist(gfp, pol, numa_node_id()),
+ policy_nodemask(gfp, pol));
put_mems_allowed();
return page;
}
return -EPERM;
/* Find the mm_struct */
- read_lock(&tasklist_lock);
+ rcu_read_lock();
task = pid ? find_task_by_vpid(pid) : current;
if (!task) {
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
return -ESRCH;
}
mm = get_task_mm(task);
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
if (!mm)
return -EINVAL;
*/
mapping = vma->vm_file->f_mapping;
spin_lock(&mapping->i_mmap_lock);
- if (new_vma->vm_truncate_count &&
- new_vma->vm_truncate_count != vma->vm_truncate_count)
- new_vma->vm_truncate_count = 0;
+ new_vma->vm_truncate_count = 0;
}
/*
for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
unsigned long check = pfn + iter;
- if (!pfn_valid_within(check)) {
- iter++;
+ if (!pfn_valid_within(check))
continue;
- }
+
page = pfn_to_page(check);
if (!page_count(page)) {
if (PageBuddy(page))
struct mm_struct *mm = vma->vm_mm;
int referenced = 0;
- /*
- * Don't want to elevate referenced for mlocked page that gets this far,
- * in order that it progresses to try_to_unmap and is moved to the
- * unevictable list.
- */
- if (vma->vm_flags & VM_LOCKED) {
- *mapcount = 0; /* break early from loop */
- *vm_flags |= VM_LOCKED;
- goto out;
- }
-
- /* Pretend the page is referenced if the task has the
- swap token and is in the middle of a page fault. */
- if (mm != current->mm && has_swap_token(mm) &&
- rwsem_is_locked(&mm->mmap_sem))
- referenced++;
-
if (unlikely(PageTransHuge(page))) {
pmd_t *pmd;
spin_lock(&mm->page_table_lock);
+ /*
+ * rmap might return false positives; we must filter
+ * these out using page_check_address_pmd().
+ */
pmd = page_check_address_pmd(page, mm, address,
PAGE_CHECK_ADDRESS_PMD_FLAG);
- if (pmd && !pmd_trans_splitting(*pmd) &&
- pmdp_clear_flush_young_notify(vma, address, pmd))
+ if (!pmd) {
+ spin_unlock(&mm->page_table_lock);
+ goto out;
+ }
+
+ if (vma->vm_flags & VM_LOCKED) {
+ spin_unlock(&mm->page_table_lock);
+ *mapcount = 0; /* break early from loop */
+ *vm_flags |= VM_LOCKED;
+ goto out;
+ }
+
+ /* go ahead even if the pmd is pmd_trans_splitting() */
+ if (pmdp_clear_flush_young_notify(vma, address, pmd))
referenced++;
spin_unlock(&mm->page_table_lock);
} else {
pte_t *pte;
spinlock_t *ptl;
+ /*
+ * rmap might return false positives; we must filter
+ * these out using page_check_address().
+ */
pte = page_check_address(page, mm, address, &ptl, 0);
if (!pte)
goto out;
+ if (vma->vm_flags & VM_LOCKED) {
+ pte_unmap_unlock(pte, ptl);
+ *mapcount = 0; /* break early from loop */
+ *vm_flags |= VM_LOCKED;
+ goto out;
+ }
+
if (ptep_clear_flush_young_notify(vma, address, pte)) {
/*
* Don't treat a reference through a sequentially read
pte_unmap_unlock(pte, ptl);
}
+ /* Pretend the page is referenced if the task has the
+ swap token and is in the middle of a page fault. */
+ if (mm != current->mm && has_swap_token(mm) &&
+ rwsem_is_locked(&mm->mmap_sem))
+ referenced++;
+
(*mapcount)--;
if (referenced)
{
struct inode *inode = dentry->d_inode;
- if (*len < 3)
+ if (*len < 3) {
+ *len = 3;
return 255;
+ }
if (inode_unhashed(inode)) {
/* Unfortunately insert_inode_hash is not idempotent,
error = -EINVAL;
if (S_ISBLK(inode->i_mode)) {
- bdev = I_BDEV(inode);
+ bdev = bdgrab(I_BDEV(inode));
error = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL,
sys_swapon);
if (error < 0) {
next = start;
while (next <= end &&
pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+ mem_cgroup_uncharge_start();
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
pgoff_t page_index = page->index;
unlock_page(page);
}
pagevec_release(&pvec);
+ mem_cgroup_uncharge_end();
cond_resched();
}
if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION))
return false;
- /*
- * If we failed to reclaim and have scanned the full list, stop.
- * NOTE: Checking just nr_reclaimed would exit reclaim/compaction far
- * faster but obviously would be less likely to succeed
- * allocation. If this is desirable, use GFP_REPEAT to decide
- * if both reclaimed and scanned should be checked or just
- * reclaimed
- */
- if (!nr_reclaimed && !nr_scanned)
- return false;
+ /* Consider stopping depending on scan and reclaim activity */
+ if (sc->gfp_mask & __GFP_REPEAT) {
+ /*
+ * For __GFP_REPEAT allocations, stop reclaiming if the
+ * full LRU list has been scanned and we are still failing
+ * to reclaim pages. This full LRU scan is potentially
+ * expensive but a __GFP_REPEAT caller really wants to succeed
+ */
+ if (!nr_reclaimed && !nr_scanned)
+ return false;
+ } else {
+ /*
+ * For non-__GFP_REPEAT allocations which can presumably
+ * fail without consequence, stop if we failed to reclaim
+ * any pages from the last SWAP_CLUSTER_MAX number of
+ * pages that were scanned. This will return to the
+ * caller faster at the risk reclaim/compaction and
+ * the resulting allocation attempt fails
+ */
+ if (!nr_reclaimed)
+ return false;
+ }
/*
* If we have not reclaimed enough pages for compaction and the
unsigned long nr[NR_LRU_LISTS];
unsigned long nr_to_scan;
enum lru_list l;
- unsigned long nr_reclaimed;
+ unsigned long nr_reclaimed, nr_scanned;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
- unsigned long nr_scanned = sc->nr_scanned;
restart:
nr_reclaimed = 0;
+ nr_scanned = sc->nr_scanned;
get_scan_count(zone, sc, nr, priority);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
obj-$(CONFIG_INET) += ipv4/
obj-$(CONFIG_XFRM) += xfrm/
obj-$(CONFIG_UNIX) += unix/
-ifneq ($(CONFIG_IPV6),)
-obj-y += ipv6/
-endif
+obj-$(CONFIG_NET) += ipv6/
obj-$(CONFIG_PACKET) += packet/
obj-$(CONFIG_NET_KEY) += key/
obj-$(CONFIG_BRIDGE) += bridge/
skb = tfp->skb;
}
+ if (skb_linearize(skb) < 0 || skb_linearize(tmp_skb) < 0)
+ goto err;
+
skb_pull(tmp_skb, sizeof(struct unicast_frag_packet));
- if (pskb_expand_head(skb, 0, tmp_skb->len, GFP_ATOMIC) < 0) {
- /* free buffered skb, skb will be freed later */
- kfree_skb(tfp->skb);
- return NULL;
- }
+ if (pskb_expand_head(skb, 0, tmp_skb->len, GFP_ATOMIC) < 0)
+ goto err;
/* move free entry to end */
tfp->skb = NULL;
unicast_packet->packet_type = BAT_UNICAST;
return skb;
+
+err:
+ /* free buffered skb, skb will be freed later */
+ kfree_skb(tfp->skb);
+ return NULL;
}
static void frag_create_entry(struct list_head *head, struct sk_buff *skb)
result = L2CAP_CR_SEC_BLOCK;
else
result = L2CAP_CR_BAD_PSM;
+ sk->sk_state = BT_DISCONN;
rsp.scid = cpu_to_le16(l2cap_pi(sk)->dcid);
rsp.dcid = cpu_to_le16(l2cap_pi(sk)->scid);
break;
}
+ tty_unlock();
schedule();
+ tty_lock();
}
set_current_state(TASK_RUNNING);
remove_wait_queue(&dev->wait, &wait);
tristate "802.1d Ethernet Bridging"
select LLC
select STP
+ depends on IPV6 || IPV6=n
---help---
If you say Y here, then your Linux box will be able to act as an
Ethernet bridge, which means that the different Ethernet segments it
if (is_multicast_ether_addr(dest)) {
mdst = br_mdb_get(br, skb);
if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) {
- if ((mdst && !hlist_unhashed(&mdst->mglist)) ||
+ if ((mdst && mdst->mglist) ||
br_multicast_is_router(br))
skb2 = skb;
br_multicast_forward(mdst, skb, skb2);
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static inline int ipv6_is_local_multicast(const struct in6_addr *addr)
+static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
{
- if (ipv6_addr_is_multicast(addr) &&
- IPV6_ADDR_MC_SCOPE(addr) <= IPV6_ADDR_SCOPE_LINKLOCAL)
+ if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
return 1;
return 0;
}
if (!netif_running(br->dev) || timer_pending(&mp->timer))
goto out;
- if (!hlist_unhashed(&mp->mglist))
- hlist_del_init(&mp->mglist);
+ mp->mglist = false;
if (mp->ports)
goto out;
del_timer(&p->query_timer);
call_rcu_bh(&p->rcu, br_multicast_free_pg);
- if (!mp->ports && hlist_unhashed(&mp->mglist) &&
+ if (!mp->ports && !mp->mglist &&
netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
eth = eth_hdr(skb);
memcpy(eth->h_source, br->dev->dev_addr, 6);
- ipv6_eth_mc_map(group, eth->h_dest);
eth->h_proto = htons(ETH_P_IPV6);
skb_put(skb, sizeof(*eth));
ip6h->payload_len = htons(8 + sizeof(*mldq));
ip6h->nexthdr = IPPROTO_HOPOPTS;
ip6h->hop_limit = 1;
- ipv6_addr_set(&ip6h->saddr, 0, 0, 0, 0);
+ ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
+ &ip6h->saddr);
ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1));
+ ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
hopopt = (u8 *)(ip6h + 1);
hopopt[0] = IPPROTO_ICMPV6; /* next hdr */
struct net_bridge *br = mp->br;
spin_lock(&br->multicast_lock);
- if (!netif_running(br->dev) || hlist_unhashed(&mp->mglist) ||
+ if (!netif_running(br->dev) || !mp->mglist ||
mp->queries_sent >= br->multicast_last_member_count)
goto out;
goto err;
if (!port) {
- hlist_add_head(&mp->mglist, &br->mglist);
+ mp->mglist = true;
mod_timer(&mp->timer, now + br->multicast_membership_interval);
goto out;
}
{
struct br_ip br_group;
- if (ipv6_is_local_multicast(group))
+ if (!ipv6_is_transient_multicast(group))
return 0;
ipv6_addr_copy(&br_group.u.ip6, group);
- br_group.proto = htons(ETH_P_IP);
+ br_group.proto = htons(ETH_P_IPV6);
return br_multicast_add_group(br, port, &br_group);
}
nsrcs = skb_header_pointer(skb,
len + offsetof(struct mld2_grec,
- grec_mca),
+ grec_nsrcs),
sizeof(_nsrcs), &_nsrcs);
if (!nsrcs)
return -EINVAL;
if (!pskb_may_pull(skb,
len + sizeof(*grec) +
- sizeof(struct in6_addr) * (*nsrcs)))
+ sizeof(struct in6_addr) * ntohs(*nsrcs)))
return -EINVAL;
grec = (struct mld2_grec *)(skb->data + len);
- len += sizeof(*grec) + sizeof(struct in6_addr) * (*nsrcs);
+ len += sizeof(*grec) +
+ sizeof(struct in6_addr) * ntohs(*nsrcs);
/* We treat these as MLDv1 reports for now. */
switch (grec->grec_type) {
max_delay *= br->multicast_last_member_count;
- if (!hlist_unhashed(&mp->mglist) &&
+ if (mp->mglist &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, now + max_delay) :
try_to_del_timer_sync(&mp->timer) >= 0))
if (timer_pending(&p->timer) ?
time_after(p->timer.expires, now + max_delay) :
try_to_del_timer_sync(&p->timer) >= 0)
- mod_timer(&mp->timer, now + max_delay);
+ mod_timer(&p->timer, now + max_delay);
}
out:
goto out;
max_delay *= br->multicast_last_member_count;
- if (!hlist_unhashed(&mp->mglist) &&
+ if (mp->mglist &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, now + max_delay) :
try_to_del_timer_sync(&mp->timer) >= 0))
if (timer_pending(&p->timer) ?
time_after(p->timer.expires, now + max_delay) :
try_to_del_timer_sync(&p->timer) >= 0)
- mod_timer(&mp->timer, now + max_delay);
+ mod_timer(&p->timer, now + max_delay);
}
out:
br->multicast_last_member_interval;
if (!port) {
- if (!hlist_unhashed(&mp->mglist) &&
+ if (mp->mglist &&
(timer_pending(&mp->timer) ?
time_after(mp->timer.expires, time) :
try_to_del_timer_sync(&mp->timer) >= 0)) {
{
struct br_ip br_group;
- if (ipv6_is_local_multicast(group))
+ if (!ipv6_is_transient_multicast(group))
return;
ipv6_addr_copy(&br_group.u.ip6, group);
struct net_bridge_mdb_entry
{
struct hlist_node hlist[2];
- struct hlist_node mglist;
struct net_bridge *br;
struct net_bridge_port_group __rcu *ports;
struct rcu_head rcu;
struct timer_list timer;
struct timer_list query_timer;
struct br_ip addr;
+ bool mglist;
u32 queries_sent;
};
spinlock_t multicast_lock;
struct net_bridge_mdb_htable __rcu *mdb;
struct hlist_head router_list;
- struct hlist_head mglist;
struct timer_list multicast_router_timer;
struct timer_list multicast_querier_timer;
priv->conn_req.sockaddr.u.dgm.connection_id = -1;
priv->flowenabled = false;
- ASSERT_RTNL();
init_waitqueue_head(&priv->netmgmt_wq);
- list_add(&priv->list_field, &chnl_net_list);
}
ret = register_netdevice(dev);
if (ret)
pr_warn("device rtml registration failed\n");
+ else
+ list_add(&caifdev->list_field, &chnl_net_list);
return ret;
}
{
struct kvec iov = {buf, len};
struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+ int r;
- return kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags);
+ r = kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags);
+ if (r == -EAGAIN)
+ r = 0;
+ return r;
}
/*
size_t kvlen, size_t len, int more)
{
struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+ int r;
if (more)
msg.msg_flags |= MSG_MORE;
else
msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */
- return kernel_sendmsg(sock, &msg, iov, kvlen, len);
+ r = kernel_sendmsg(sock, &msg, iov, kvlen, len);
+ if (r == -EAGAIN)
+ r = 0;
+ return r;
}
ceph_msg_put(con->out_msg);
con->out_msg = NULL;
}
- con->out_keepalive_pending = false;
con->in_seq = 0;
con->in_seq_acked = 0;
}
(msg->pages || msg->pagelist || msg->bio || in_trail))
kunmap(page);
+ if (ret == -EAGAIN)
+ ret = 0;
if (ret <= 0)
goto out;
con->auth_retry);
if (con->auth_retry == 2) {
con->error_msg = "connect authorization failure";
- reset_connection(con);
- set_bit(CLOSED, &con->state);
return -1;
}
con->auth_retry = 1;
/* open the socket first? */
if (con->sock == NULL) {
- /*
- * if we were STANDBY and are reconnecting _this_
- * connection, bump connect_seq now. Always bump
- * global_seq.
- */
- if (test_and_clear_bit(STANDBY, &con->state))
- con->connect_seq++;
-
prepare_write_banner(msgr, con);
prepare_write_connect(msgr, con, 1);
prepare_read_banner(con);
if (con->out_skip) {
ret = write_partial_skip(con);
if (ret <= 0)
- goto done;
- if (ret < 0) {
- dout("try_write write_partial_skip err %d\n", ret);
- goto done;
- }
+ goto out;
}
if (con->out_kvec_left) {
ret = write_partial_kvec(con);
if (ret <= 0)
- goto done;
+ goto out;
}
/* msg pages? */
if (ret == 1)
goto more_kvec; /* we need to send the footer, too! */
if (ret == 0)
- goto done;
+ goto out;
if (ret < 0) {
dout("try_write write_partial_msg_pages err %d\n",
ret);
- goto done;
+ goto out;
}
}
/* Nothing to do! */
clear_bit(WRITE_PENDING, &con->state);
dout("try_write nothing else to write.\n");
-done:
ret = 0;
out:
- dout("try_write done on %p\n", con);
+ dout("try_write done on %p ret %d\n", con, ret);
return ret;
}
dout("try_read connecting\n");
ret = read_partial_banner(con);
if (ret <= 0)
- goto done;
- if (process_banner(con) < 0) {
- ret = -1;
goto out;
- }
+ ret = process_banner(con);
+ if (ret < 0)
+ goto out;
}
ret = read_partial_connect(con);
if (ret <= 0)
- goto done;
- if (process_connect(con) < 0) {
- ret = -1;
goto out;
- }
+ ret = process_connect(con);
+ if (ret < 0)
+ goto out;
goto more;
}
dout("skipping %d / %d bytes\n", skip, -con->in_base_pos);
ret = ceph_tcp_recvmsg(con->sock, buf, skip);
if (ret <= 0)
- goto done;
+ goto out;
con->in_base_pos += ret;
if (con->in_base_pos)
goto more;
*/
ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1);
if (ret <= 0)
- goto done;
+ goto out;
dout("try_read got tag %d\n", (int)con->in_tag);
switch (con->in_tag) {
case CEPH_MSGR_TAG_MSG:
break;
case CEPH_MSGR_TAG_CLOSE:
set_bit(CLOSED, &con->state); /* fixme */
- goto done;
+ goto out;
default:
goto bad_tag;
}
case -EBADMSG:
con->error_msg = "bad crc";
ret = -EIO;
- goto out;
+ break;
case -EIO:
con->error_msg = "io error";
- goto out;
- default:
- goto done;
+ break;
}
+ goto out;
}
if (con->in_tag == CEPH_MSGR_TAG_READY)
goto more;
if (con->in_tag == CEPH_MSGR_TAG_ACK) {
ret = read_partial_ack(con);
if (ret <= 0)
- goto done;
+ goto out;
process_ack(con);
goto more;
}
-done:
- ret = 0;
out:
- dout("try_read done on %p\n", con);
+ dout("try_read done on %p ret %d\n", con, ret);
return ret;
bad_tag:
work.work);
mutex_lock(&con->mutex);
+ if (test_and_clear_bit(BACKOFF, &con->state)) {
+ dout("con_work %p backing off\n", con);
+ if (queue_delayed_work(ceph_msgr_wq, &con->work,
+ round_jiffies_relative(con->delay))) {
+ dout("con_work %p backoff %lu\n", con, con->delay);
+ mutex_unlock(&con->mutex);
+ return;
+ } else {
+ con->ops->put(con);
+ dout("con_work %p FAILED to back off %lu\n", con,
+ con->delay);
+ }
+ }
+ if (test_bit(STANDBY, &con->state)) {
+ dout("con_work %p STANDBY\n", con);
+ goto done;
+ }
if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */
dout("con_work CLOSED\n");
con_close_socket(con);
/* Requeue anything that hasn't been acked */
list_splice_init(&con->out_sent, &con->out_queue);
- /* If there are no messages in the queue, place the connection
- * in a STANDBY state (i.e., don't try to reconnect just yet). */
- if (list_empty(&con->out_queue) && !con->out_keepalive_pending) {
- dout("fault setting STANDBY\n");
+ /* If there are no messages queued or keepalive pending, place
+ * the connection in a STANDBY state */
+ if (list_empty(&con->out_queue) &&
+ !test_bit(KEEPALIVE_PENDING, &con->state)) {
+ dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
+ clear_bit(WRITE_PENDING, &con->state);
set_bit(STANDBY, &con->state);
} else {
/* retry after a delay. */
con->delay = BASE_DELAY_INTERVAL;
else if (con->delay < MAX_DELAY_INTERVAL)
con->delay *= 2;
- dout("fault queueing %p delay %lu\n", con, con->delay);
con->ops->get(con);
if (queue_delayed_work(ceph_msgr_wq, &con->work,
- round_jiffies_relative(con->delay)) == 0)
+ round_jiffies_relative(con->delay))) {
+ dout("fault queued %p delay %lu\n", con, con->delay);
+ } else {
con->ops->put(con);
+ dout("fault failed to queue %p delay %lu, backoff\n",
+ con, con->delay);
+ /*
+ * In many cases we see a socket state change
+ * while con_work is running and end up
+ * queuing (non-delayed) work, such that we
+ * can't backoff with a delay. Set a flag so
+ * that when con_work restarts we schedule the
+ * delay then.
+ */
+ set_bit(BACKOFF, &con->state);
+ }
}
out_unlock:
}
EXPORT_SYMBOL(ceph_messenger_destroy);
+static void clear_standby(struct ceph_connection *con)
+{
+ /* come back from STANDBY? */
+ if (test_and_clear_bit(STANDBY, &con->state)) {
+ mutex_lock(&con->mutex);
+ dout("clear_standby %p and ++connect_seq\n", con);
+ con->connect_seq++;
+ WARN_ON(test_bit(WRITE_PENDING, &con->state));
+ WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state));
+ mutex_unlock(&con->mutex);
+ }
+}
+
/*
* Queue up an outgoing message on the given connection.
*/
/* if there wasn't anything waiting to send before, queue
* new work */
+ clear_standby(con);
if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
queue_con(con);
}
*/
void ceph_con_keepalive(struct ceph_connection *con)
{
+ dout("con_keepalive %p\n", con);
+ clear_standby(con);
if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 &&
test_and_set_bit(WRITE_PENDING, &con->state) == 0)
queue_con(con);
int num_pages, bool write_page)
{
struct page **pages;
- int rc;
+ int got = 0;
+ int rc = 0;
pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
if (!pages)
return ERR_PTR(-ENOMEM);
down_read(¤t->mm->mmap_sem);
- rc = get_user_pages(current, current->mm, (unsigned long)data,
- num_pages, write_page, 0, pages, NULL);
+ while (got < num_pages) {
+ rc = get_user_pages(current, current->mm,
+ (unsigned long)data + ((unsigned long)got * PAGE_SIZE),
+ num_pages - got, write_page, 0, pages + got, NULL);
+ if (rc < 0)
+ break;
+ BUG_ON(rc == 0);
+ got += rc;
+ }
up_read(¤t->mm->mmap_sem);
- if (rc < num_pages)
+ if (rc < 0)
goto fail;
return pages;
fail:
- ceph_put_page_vector(pages, rc > 0 ? rc : 0, false);
+ ceph_put_page_vector(pages, got, false);
return ERR_PTR(rc);
}
EXPORT_SYMBOL(ceph_get_direct_page_vector);
void dev_load(struct net *net, const char *name)
{
struct net_device *dev;
+ int no_module;
rcu_read_lock();
dev = dev_get_by_name_rcu(net, name);
rcu_read_unlock();
- if (!dev && capable(CAP_NET_ADMIN))
- request_module("%s", name);
+ no_module = !dev;
+ if (no_module && capable(CAP_NET_ADMIN))
+ no_module = request_module("netdev-%s", name);
+ if (no_module && capable(CAP_SYS_MODULE)) {
+ if (!request_module("%s", name))
+ pr_err("Loading kernel module for a network device "
+"with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s "
+"instead\n", name);
+ }
}
EXPORT_SYMBOL(dev_load);
static int __dev_close(struct net_device *dev)
{
+ int retval;
LIST_HEAD(single);
list_add(&dev->unreg_list, &single);
- return __dev_close_many(&single);
+ retval = __dev_close_many(&single);
+ list_del(&single);
+ return retval;
}
int dev_close_many(struct list_head *head)
list_add(&dev->unreg_list, &single);
dev_close_many(&single);
-
+ list_del(&single);
return 0;
}
EXPORT_SYMBOL(dev_close);
list_add(&dev->unreg_list, &single);
rollback_registered_many(&single);
+ list_del(&single);
}
unsigned long netdev_fix_features(unsigned long features, const char *name)
dev_net_set(dev, &init_net);
+ dev->gso_max_size = GSO_MAX_SIZE;
+
+ INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
+ dev->ethtool_ntuple_list.count = 0;
+ INIT_LIST_HEAD(&dev->napi_list);
+ INIT_LIST_HEAD(&dev->unreg_list);
+ INIT_LIST_HEAD(&dev->link_watch_list);
+ dev->priv_flags = IFF_XMIT_DST_RELEASE;
+ setup(dev);
+
dev->num_tx_queues = txqs;
dev->real_num_tx_queues = txqs;
if (netif_alloc_netdev_queues(dev))
- goto free_pcpu;
+ goto free_all;
#ifdef CONFIG_RPS
dev->num_rx_queues = rxqs;
dev->real_num_rx_queues = rxqs;
if (netif_alloc_rx_queues(dev))
- goto free_pcpu;
+ goto free_all;
#endif
- dev->gso_max_size = GSO_MAX_SIZE;
-
- INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
- dev->ethtool_ntuple_list.count = 0;
- INIT_LIST_HEAD(&dev->napi_list);
- INIT_LIST_HEAD(&dev->unreg_list);
- INIT_LIST_HEAD(&dev->link_watch_list);
- dev->priv_flags = IFF_XMIT_DST_RELEASE;
- setup(dev);
strcpy(dev->name, name);
return dev;
+free_all:
+ free_netdev(dev);
+ return NULL;
+
free_pcpu:
free_percpu(dev->pcpu_refcnt);
kfree(dev->_tx);
}
}
unregister_netdevice_many(&dev_kill_list);
+ list_del(&dev_kill_list);
rtnl_unlock();
}
list_for_each_entry(ha, &from_list->list, list) {
type = addr_type ? addr_type : ha->type;
- __hw_addr_del(to_list, ha->addr, addr_len, addr_type);
+ __hw_addr_del(to_list, ha->addr, addr_len, type);
}
}
EXPORT_SYMBOL(__hw_addr_del_multiple);
pkt_dev->started_at);
ktime_t idle = ns_to_ktime(pkt_dev->idle_acc);
- p += sprintf(p, "OK: %llu(c%llu+d%llu) nsec, %llu (%dbyte,%dfrags)\n",
+ p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n",
(unsigned long long)ktime_to_us(elapsed),
(unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)),
(unsigned long long)ktime_to_us(idle),
int fd = fdp[i];
struct file *file;
- if (fd < 0 || !(file = fget(fd)))
+ if (fd < 0 || !(file = fget_raw(fd)))
return -EBADF;
*fpp++ = file;
fpl->count++;
dcb->cmd = DCB_CMD_GAPP;
app_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_APP);
+ if (!app_nest)
+ goto out_cancel;
+
ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_IDTYPE, idtype);
if (ret)
goto out_cancel;
goto err;
}
- if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setets) {
+ if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) {
struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]);
err = ops->ieee_setpfc(netdev, pfc);
if (err)
u8 dcb_setapp(struct net_device *dev, struct dcb_app *new)
{
struct dcb_app_type *itr;
+ struct dcb_app_type event;
+
+ memcpy(&event.name, dev->name, sizeof(event.name));
+ memcpy(&event.app, new, sizeof(event.app));
spin_lock(&dcb_lock);
/* Search for existing match and replace */
}
out:
spin_unlock(&dcb_lock);
- call_dcbevent_notifiers(DCB_APP_EVENT, new);
+ call_dcbevent_notifiers(DCB_APP_EVENT, &event);
return 0;
}
EXPORT_SYMBOL(dcb_setapp);
/* Caller (dccp_v4_do_rcv) will send Reset */
dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
return 1;
+ } else if (sk->sk_state == DCCP_CLOSED) {
+ dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
+ return 1;
}
if (sk->sk_state != DCCP_REQUESTING && sk->sk_state != DCCP_RESPOND) {
}
switch (sk->sk_state) {
- case DCCP_CLOSED:
- dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
- return 1;
-
case DCCP_REQUESTING:
queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len);
if (queued >= 0)
size_t result_len = 0;
const char *data = _data, *end, *opt;
- kenter("%%%d,%s,'%s',%zu",
- key->serial, key->description, data, datalen);
+ kenter("%%%d,%s,'%*.*s',%zu",
+ key->serial, key->description,
+ (int)datalen, (int)datalen, data, datalen);
if (datalen <= 1 || !data || data[datalen - 1] != '\0')
return -EINVAL;
seq_printf(m, ": %u", key->datalen);
}
+/*
+ * read the DNS data
+ * - the key's semaphore is read-locked
+ */
+static long dns_resolver_read(const struct key *key,
+ char __user *buffer, size_t buflen)
+{
+ if (key->type_data.x[0])
+ return key->type_data.x[0];
+
+ return user_read(key, buffer, buflen);
+}
+
struct key_type key_type_dns_resolver = {
.name = "dns_resolver",
.instantiate = dns_resolver_instantiate,
.revoke = user_revoke,
.destroy = user_destroy,
.describe = dns_resolver_describe,
- .read = user_read,
+ .read = dns_resolver_read,
};
static int __init init_dns_resolver(void)
ifap = &ifa->ifa_next) {
if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
sin_orig.sin_addr.s_addr ==
- ifa->ifa_address) {
+ ifa->ifa_local) {
break; /* found */
}
}
return mtu >= 68;
}
+static void inetdev_send_gratuitous_arp(struct net_device *dev,
+ struct in_device *in_dev)
+
+{
+ struct in_ifaddr *ifa = in_dev->ifa_list;
+
+ if (!ifa)
+ return;
+
+ arp_send(ARPOP_REQUEST, ETH_P_ARP,
+ ifa->ifa_local, dev,
+ ifa->ifa_local, NULL,
+ dev->dev_addr, NULL);
+}
+
/* Called only under RTNL semaphore */
static int inetdev_event(struct notifier_block *this, unsigned long event,
}
ip_mc_up(in_dev);
/* fall through */
- case NETDEV_NOTIFY_PEERS:
case NETDEV_CHANGEADDR:
+ if (!IN_DEV_ARP_NOTIFY(in_dev))
+ break;
+ /* fall through */
+ case NETDEV_NOTIFY_PEERS:
/* Send gratuitous ARP to notify of link change */
- if (IN_DEV_ARP_NOTIFY(in_dev)) {
- struct in_ifaddr *ifa = in_dev->ifa_list;
-
- if (ifa)
- arp_send(ARPOP_REQUEST, ETH_P_ARP,
- ifa->ifa_address, dev,
- ifa->ifa_address, NULL,
- dev->dev_addr, NULL);
- }
+ inetdev_send_gratuitous_arp(dev, in_dev);
break;
case NETDEV_DOWN:
ip_mc_down(in_dev);
}
rcu_read_unlock();
+ local_bh_disable();
inet_twsk_deschedule(tw, twdr);
+ local_bh_enable();
inet_twsk_put(tw);
goto restart_rcu;
}
.fl4_dst = dst,
.fl4_src = tiph->saddr,
.fl4_tos = RT_TOS(tos),
+ .proto = IPPROTO_GRE,
.fl_gre_key = tunnel->parms.o_key
};
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("gre");
MODULE_ALIAS_RTNL_LINK("gretap");
-MODULE_ALIAS("gre0");
+MODULE_ALIAS_NETDEV("gre0");
module_init(ipip_init);
module_exit(ipip_fini);
MODULE_LICENSE("GPL");
-MODULE_ALIAS("tunl0");
+MODULE_ALIAS_NETDEV("tunl0");
.destroy = ipv4_dst_destroy,
.check = ipv4_blackhole_dst_check,
.default_mtu = ipv4_blackhole_default_mtu,
+ .default_advmss = ipv4_default_advmss,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
};
}
/* D-SACK for already forgotten data... Do dumb counting. */
- if (dup_sack &&
+ if (dup_sack && tp->undo_marker && tp->undo_retrans &&
!after(end_seq_0, prior_snd_una) &&
after(end_seq_0, tp->undo_marker))
tp->undo_retrans--;
/* Account D-SACK for retransmitted packet. */
if (dup_sack && (sacked & TCPCB_RETRANS)) {
- if (after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
+ if (tp->undo_marker && tp->undo_retrans &&
+ after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
tp->undo_retrans--;
if (sacked & TCPCB_SACKED_ACKED)
state->reord = min(fack_count, state->reord);
if (!tp->retrans_stamp)
tp->retrans_stamp = TCP_SKB_CB(skb)->when;
- tp->undo_retrans++;
+ tp->undo_retrans += tcp_skb_pcount(skb);
/* snd_nxt is stored to detect loss of retransmitted segment,
* see tcp_input.c tcp_sacktag_write_queue().
MODULE_AUTHOR("Ville Nuorvala");
MODULE_DESCRIPTION("IPv6 tunneling device");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETDEV("ip6tnl0");
#ifdef IP6_TNL_DEBUG
#define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__)
if (p != NULL) {
sb_add(m, "%02x", *p++);
for (i = 1; i < len; i++)
- sb_add(m, ":%02x", p[i]);
+ sb_add(m, ":%02x", *p++);
}
sb_add(m, " ");
.destroy = ip6_dst_destroy,
.check = ip6_dst_check,
.default_mtu = ip6_blackhole_default_mtu,
+ .default_advmss = ip6_default_advmss,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
};
if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
- else
+ else if (!(rt->dst.flags & DST_HOST))
nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
+ else
+ goto out2;
dst_release(&rt->dst);
rt = nrt ? : net->ipv6.ip6_null_entry;
int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- struct net *net = current->nsproxy->net_ns;
- int delay = net->ipv6.sysctl.flush_delay;
- if (write) {
- proc_dointvec(ctl, write, buffer, lenp, ppos);
- fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
- return 0;
- } else
+ struct net *net;
+ int delay;
+ if (!write)
return -EINVAL;
+
+ net = (struct net *)ctl->extra1;
+ delay = net->ipv6.sysctl.flush_delay;
+ proc_dointvec(ctl, write, buffer, lenp, ppos);
+ fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
+ return 0;
}
ctl_table ipv6_route_table_template[] = {
if (table) {
table[0].data = &net->ipv6.sysctl.flush_delay;
+ table[0].extra1 = net;
table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh;
table[2].data = &net->ipv6.sysctl.ip6_rt_max_size;
table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
module_init(sit_init);
module_exit(sit_cleanup);
MODULE_LICENSE("GPL");
-MODULE_ALIAS("sit0");
+MODULE_ALIAS_NETDEV("sit0");
*cookie ^= 2;
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_TX_OFFCHAN;
local->hw_roc_skb = skb;
+ local->hw_roc_skb_for_status = skb;
mutex_unlock(&local->mtx);
return 0;
if (ret == 0) {
kfree_skb(local->hw_roc_skb);
local->hw_roc_skb = NULL;
+ local->hw_roc_skb_for_status = NULL;
}
mutex_unlock(&local->mtx);
struct ieee80211_channel *hw_roc_channel;
struct net_device *hw_roc_dev;
- struct sk_buff *hw_roc_skb;
+ struct sk_buff *hw_roc_skb, *hw_roc_skb_for_status;
struct work_struct hw_roc_start, hw_roc_done;
enum nl80211_channel_type hw_roc_channel_type;
unsigned int hw_roc_duration;
}
mutex_unlock(&local->iflist_mtx);
unregister_netdevice_many(&unreg_list);
+ list_del(&unreg_list);
}
static u32 ieee80211_idle_off(struct ieee80211_local *local,
if (is_multicast_ether_addr(hdr->addr1))
return;
+ /*
+ * In case we receive frames after disassociation.
+ */
+ if (!sdata->u.mgd.associated)
+ return;
+
ieee80211_sta_reset_conn_monitor(sdata);
}
if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) {
struct ieee80211_work *wk;
+ u64 cookie = (unsigned long)skb;
rcu_read_lock();
list_for_each_entry_rcu(wk, &local->work_list, list) {
break;
}
rcu_read_unlock();
+ if (local->hw_roc_skb_for_status == skb) {
+ cookie = local->hw_roc_cookie ^ 2;
+ local->hw_roc_skb_for_status = NULL;
+ }
cfg80211_mgmt_tx_status(
- skb->dev, (unsigned long) skb, skb->data, skb->len,
+ skb->dev, cookie, skb->data, skb->len,
!!(info->flags & IEEE80211_TX_STAT_ACK), GFP_ATOMIC);
}
skb_orphan(skb);
}
- if (skb_header_cloned(skb))
+ if (skb_cloned(skb))
I802_DEBUG_INC(local->tx_expand_skb_head_cloned);
else if (head_need || tail_need)
I802_DEBUG_INC(local->tx_expand_skb_head);
switch (sdata->vif.type) {
case NL80211_IFTYPE_STATION:
changed |= BSS_CHANGED_ASSOC;
+ mutex_lock(&sdata->u.mgd.mtx);
ieee80211_bss_info_change_notify(sdata, changed);
+ mutex_unlock(&sdata->u.mgd.mtx);
break;
case NL80211_IFTYPE_ADHOC:
changed |= BSS_CHANGED_IBSS;
/* Optimization: we don't need to hold module
reference here, since function can't sleep. --RR */
+repeat:
verdict = elem->hook(hook, skb, indev, outdev, okfn);
if (verdict != NF_ACCEPT) {
#ifdef CONFIG_NETFILTER_DEBUG
#endif
if (verdict != NF_REPEAT)
return verdict;
- *i = (*i)->prev;
+ goto repeat;
}
}
return NF_ACCEPT;
dest->u_threshold = udest->u_threshold;
dest->l_threshold = udest->l_threshold;
- spin_lock(&dest->dst_lock);
+ spin_lock_bh(&dest->dst_lock);
ip_vs_dst_reset(dest);
- spin_unlock(&dest->dst_lock);
+ spin_unlock_bh(&dest->dst_lock);
if (add)
ip_vs_new_estimator(&dest->stats);
if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_REPLY, ct);
out:
- if (tmpl)
- nf_ct_put(tmpl);
+ if (tmpl) {
+ /* Special case: we have to repeat this hook, assign the
+ * template again to this packet. We assume that this packet
+ * has no conntrack assigned. This is used by nf_ct_tcp. */
+ if (ret == NF_REPEAT)
+ skb->nfct = (struct nf_conntrack *)tmpl;
+ else
+ nf_ct_put(tmpl);
+ }
return ret;
}
int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger)
{
+ if (pf >= ARRAY_SIZE(nf_loggers))
+ return -EINVAL;
mutex_lock(&nf_log_mutex);
if (__find_logger(pf, logger->name) == NULL) {
mutex_unlock(&nf_log_mutex);
void nf_log_unbind_pf(u_int8_t pf)
{
+ if (pf >= ARRAY_SIZE(nf_loggers))
+ return;
mutex_lock(&nf_log_mutex);
rcu_assign_pointer(nf_loggers[pf], NULL);
mutex_unlock(&nf_log_mutex);
skb->destructor = NULL;
if (sk)
- nf_tproxy_put_sock(sk);
+ sock_put(sk);
}
/* consumes sk */
-int
+void
nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
{
- bool transparent = (sk->sk_state == TCP_TIME_WAIT) ?
- inet_twsk(sk)->tw_transparent :
- inet_sk(sk)->transparent;
-
- if (transparent) {
- skb_orphan(skb);
- skb->sk = sk;
- skb->destructor = nf_tproxy_destructor;
- return 1;
- } else
- nf_tproxy_put_sock(sk);
-
- return 0;
+ /* assigning tw sockets complicates things; most
+ * skb->sk->X checks would have to test sk->sk_state first */
+ if (sk->sk_state == TCP_TIME_WAIT) {
+ inet_twsk_put(inet_twsk(sk));
+ return;
+ }
+
+ skb_orphan(skb);
+ skb->sk = sk;
+ skb->destructor = nf_tproxy_destructor;
}
EXPORT_SYMBOL_GPL(nf_tproxy_assign_sock);
#include <net/netfilter/nf_tproxy_core.h>
#include <linux/netfilter/xt_TPROXY.h>
+static bool tproxy_sk_is_transparent(struct sock *sk)
+{
+ if (sk->sk_state != TCP_TIME_WAIT) {
+ if (inet_sk(sk)->transparent)
+ return true;
+ sock_put(sk);
+ } else {
+ if (inet_twsk(sk)->tw_transparent)
+ return true;
+ inet_twsk_put(inet_twsk(sk));
+ }
+ return false;
+}
+
static inline __be32
tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
{
skb->dev, NFT_LOOKUP_LISTENER);
/* NOTE: assign_sock consumes our sk reference */
- if (sk && nf_tproxy_assign_sock(skb, sk)) {
+ if (sk && tproxy_sk_is_transparent(sk)) {
/* This should be in a separate target, but we don't do multiple
targets on the same rule yet */
skb->mark = (skb->mark & ~mark_mask) ^ mark_value;
pr_debug("redirecting: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n",
iph->protocol, &iph->daddr, ntohs(hp->dest),
&laddr, ntohs(lport), skb->mark);
+
+ nf_tproxy_assign_sock(skb, sk);
return NF_ACCEPT;
}
par->in, NFT_LOOKUP_LISTENER);
/* NOTE: assign_sock consumes our sk reference */
- if (sk && nf_tproxy_assign_sock(skb, sk)) {
+ if (sk && tproxy_sk_is_transparent(sk)) {
/* This should be in a separate target, but we don't do multiple
targets on the same rule yet */
skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value;
pr_debug("redirecting: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n",
tproto, &iph->saddr, ntohs(hp->source),
laddr, ntohs(lport), skb->mark);
+
+ nf_tproxy_assign_sock(skb, sk);
return NF_ACCEPT;
}
#include <net/netfilter/nf_conntrack.h>
#endif
+static void
+xt_socket_put_sk(struct sock *sk)
+{
+ if (sk->sk_state == TCP_TIME_WAIT)
+ inet_twsk_put(inet_twsk(sk));
+ else
+ sock_put(sk);
+}
+
static int
extract_icmp4_fields(const struct sk_buff *skb,
u8 *protocol,
(sk->sk_state == TCP_TIME_WAIT &&
inet_twsk(sk)->tw_transparent));
- nf_tproxy_put_sock(sk);
+ xt_socket_put_sk(sk);
if (wildcard || !transparent)
sk = NULL;
(sk->sk_state == TCP_TIME_WAIT &&
inet_twsk(sk)->tw_transparent));
- nf_tproxy_put_sock(sk);
+ xt_socket_put_sk(sk);
if (wildcard || !transparent)
sk = NULL;
int noblock = flags&MSG_DONTWAIT;
size_t copied;
struct sk_buff *skb, *data_skb;
- int err;
+ int err, ret;
if (flags&MSG_OOB)
return -EOPNOTSUPP;
skb_free_datagram(sk, skb);
- if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2)
- netlink_dump(sk);
+ if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
+ ret = netlink_dump(sk);
+ if (ret) {
+ sk->sk_err = ret;
+ sk->sk_error_report(sk);
+ }
+ }
scm_recv(sock, msg, siocb->scm, flags);
out:
struct netlink_callback *cb;
struct sock *sk;
struct netlink_sock *nlk;
+ int ret;
cb = kzalloc(sizeof(*cb), GFP_KERNEL);
if (cb == NULL)
nlk->cb = cb;
mutex_unlock(nlk->cb_mutex);
- netlink_dump(sk);
+ ret = netlink_dump(sk);
+
sock_put(sk);
+ if (ret)
+ return ret;
+
/* We successfully started a dump, by returning -EINTR we
* signal not to send ACK even if it was requested.
*/
if (conn->c_loopback
&& rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) {
rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
- return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
+ scat = &rm->data.op_sg[sg];
+ ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
+ ret = min_t(int, ret, scat->length - conn->c_xmit_data_off);
+ return ret;
}
/* FIXME we may overallocate here */
unsigned int hdr_off, unsigned int sg,
unsigned int off)
{
+ struct scatterlist *sgp = &rm->data.op_sg[sg];
+ int ret = sizeof(struct rds_header) +
+ be32_to_cpu(rm->m_inc.i_hdr.h_len);
+
/* Do not send cong updates to loopback */
if (rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) {
rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
- return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
+ ret = min_t(int, ret, sgp->length - conn->c_xmit_data_off);
+ goto out;
}
BUG_ON(hdr_off || sg || off);
NULL);
rds_inc_put(&rm->m_inc);
-
- return sizeof(struct rds_header) + be32_to_cpu(rm->m_inc.i_hdr.h_len);
+out:
+ return ret;
}
/*
goto protocol_error;
}
+ case RXRPC_PACKET_TYPE_ACKALL:
case RXRPC_PACKET_TYPE_ACK:
/* ACK processing is done in process context */
read_lock_bh(&call->state_lock);
return ret;
plen -= sizeof(*token);
- token = kmalloc(sizeof(*token), GFP_KERNEL);
+ token = kzalloc(sizeof(*token), GFP_KERNEL);
if (!token)
return -ENOMEM;
- token->kad = kmalloc(plen, GFP_KERNEL);
+ token->kad = kzalloc(plen, GFP_KERNEL);
if (!token->kad) {
kfree(token);
return -ENOMEM;
goto error;
ret = -ENOMEM;
- token = kmalloc(sizeof(*token), GFP_KERNEL);
+ token = kzalloc(sizeof(*token), GFP_KERNEL);
if (!token)
goto error;
- token->kad = kmalloc(plen, GFP_KERNEL);
+ token->kad = kzalloc(plen, GFP_KERNEL);
if (!token->kad)
goto error_free;
list_add(&dev->unreg_list, &single);
dev_deactivate_many(&single);
+ list_del(&single);
}
static void dev_init_scheduler_queue(struct net_device *dev,
*errp = sctp_make_op_error_fixed(asoc, chunk);
if (*errp) {
- sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM,
- WORD_ROUND(ntohs(param.p->length)));
- sctp_addto_chunk_fixed(*errp,
- WORD_ROUND(ntohs(param.p->length)),
- param.v);
+ if (!sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM,
+ WORD_ROUND(ntohs(param.p->length))))
+ sctp_addto_chunk_fixed(*errp,
+ WORD_ROUND(ntohs(param.p->length)),
+ param.v);
} else {
/* If there is no memory for generating the ERROR
* report as specified, an ABORT will be triggered
/*
* Mark an RPC call as having completed by clearing the 'active' bit
+ * and then waking up all tasks that were sleeping.
*/
-static void rpc_mark_complete_task(struct rpc_task *task)
+static int rpc_complete_task(struct rpc_task *task)
{
- smp_mb__before_clear_bit();
+ void *m = &task->tk_runstate;
+ wait_queue_head_t *wq = bit_waitqueue(m, RPC_TASK_ACTIVE);
+ struct wait_bit_key k = __WAIT_BIT_KEY_INITIALIZER(m, RPC_TASK_ACTIVE);
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&wq->lock, flags);
clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
- smp_mb__after_clear_bit();
- wake_up_bit(&task->tk_runstate, RPC_TASK_ACTIVE);
+ ret = atomic_dec_and_test(&task->tk_count);
+ if (waitqueue_active(wq))
+ __wake_up_locked_key(wq, TASK_NORMAL, &k);
+ spin_unlock_irqrestore(&wq->lock, flags);
+ return ret;
}
/*
* Allow callers to wait for completion of an RPC call
+ *
+ * Note the use of out_of_line_wait_on_bit() rather than wait_on_bit()
+ * to enforce taking of the wq->lock and hence avoid races with
+ * rpc_complete_task().
*/
int __rpc_wait_for_completion_task(struct rpc_task *task, int (*action)(void *))
{
if (action == NULL)
action = rpc_wait_bit_killable;
- return wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE,
+ return out_of_line_wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE,
action, TASK_KILLABLE);
}
EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task);
rpc_free_task(container_of(work, struct rpc_task, u.tk_work));
}
-void rpc_put_task(struct rpc_task *task)
+static void rpc_release_resources_task(struct rpc_task *task)
{
- if (!atomic_dec_and_test(&task->tk_count))
- return;
- /* Release resources */
if (task->tk_rqstp)
xprt_release(task);
if (task->tk_msg.rpc_cred)
put_rpccred(task->tk_msg.rpc_cred);
rpc_task_release_client(task);
- if (task->tk_workqueue != NULL) {
+}
+
+static void rpc_final_put_task(struct rpc_task *task,
+ struct workqueue_struct *q)
+{
+ if (q != NULL) {
INIT_WORK(&task->u.tk_work, rpc_async_release);
- queue_work(task->tk_workqueue, &task->u.tk_work);
+ queue_work(q, &task->u.tk_work);
} else
rpc_free_task(task);
}
+
+static void rpc_do_put_task(struct rpc_task *task, struct workqueue_struct *q)
+{
+ if (atomic_dec_and_test(&task->tk_count)) {
+ rpc_release_resources_task(task);
+ rpc_final_put_task(task, q);
+ }
+}
+
+void rpc_put_task(struct rpc_task *task)
+{
+ rpc_do_put_task(task, NULL);
+}
EXPORT_SYMBOL_GPL(rpc_put_task);
+void rpc_put_task_async(struct rpc_task *task)
+{
+ rpc_do_put_task(task, task->tk_workqueue);
+}
+EXPORT_SYMBOL_GPL(rpc_put_task_async);
+
static void rpc_release_task(struct rpc_task *task)
{
dprintk("RPC: %5u release task\n", task->tk_pid);
BUG_ON (RPC_IS_QUEUED(task));
- /* Wake up anyone who is waiting for task completion */
- rpc_mark_complete_task(task);
+ rpc_release_resources_task(task);
- rpc_put_task(task);
+ /*
+ * Note: at this point we have been removed from rpc_clnt->cl_tasks,
+ * so it should be safe to use task->tk_count as a test for whether
+ * or not any other processes still hold references to our rpc_task.
+ */
+ if (atomic_read(&task->tk_count) != 1 + !RPC_IS_ASYNC(task)) {
+ /* Wake up anyone who may be waiting for task completion */
+ if (!rpc_complete_task(task))
+ return;
+ } else {
+ if (!atomic_dec_and_test(&task->tk_count))
+ return;
+ }
+ rpc_final_put_task(task, task->tk_workqueue);
}
int rpciod_up(void)
p, 0, length, DMA_FROM_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device, ctxt->sge[0].addr)) {
put_page(p);
+ svc_rdma_put_context(ctxt, 1);
return;
}
atomic_inc(&xprt->sc_dma_used);
}
xs_reclassify_socket(family, sock);
- if (xs_bind(transport, sock)) {
+ err = xs_bind(transport, sock);
+ if (err) {
sock_release(sock);
goto out;
}
* Get the parent directory, calculate the hash for last
* component.
*/
- err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd);
+ err = kern_path_parent(sunaddr->sun_path, &nd);
if (err)
goto out_mknod_parent;
msg->msg_namelen = 0;
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (err) {
+ err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+ goto out;
+ }
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb) {
memset(&tmp_scm, 0, sizeof(tmp_scm));
}
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (err) {
+ err = sock_intr_errno(timeo);
+ goto out;
+ }
do {
int chunk;
timeo = unix_stream_data_wait(sk, timeo);
- if (signal_pending(current)) {
+ if (signal_pending(current)
+ || mutex_lock_interruptible(&u->readlock)) {
err = sock_intr_errno(timeo);
goto out;
}
- mutex_lock(&u->readlock);
+
continue;
unlock:
unix_state_unlock(sk);
/*
* Socket ?
*/
- if (S_ISSOCK(inode->i_mode)) {
+ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
struct socket *sock = SOCKET_I(inode);
struct sock *s = sock->sk;
return freq;
if (freq == 0)
return -EINVAL;
- wdev_lock(wdev);
mutex_lock(&rdev->devlist_mtx);
+ wdev_lock(wdev);
err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT);
- mutex_unlock(&rdev->devlist_mtx);
wdev_unlock(wdev);
+ mutex_unlock(&rdev->devlist_mtx);
return err;
default:
return -EOPNOTSUPP;
#include <net/sock.h>
#include <net/x25.h>
-/*
- * Parse a set of facilities into the facilities structures. Unrecognised
- * facilities are written to the debug log file.
+/**
+ * x25_parse_facilities - Parse facilities from skb into the facilities structs
+ *
+ * @skb: sk_buff to parse
+ * @facilities: Regular facilites, updated as facilities are found
+ * @dte_facs: ITU DTE facilities, updated as DTE facilities are found
+ * @vc_fac_mask: mask is updated with all facilities found
+ *
+ * Return codes:
+ * -1 - Parsing error, caller should drop call and clean up
+ * 0 - Parse OK, this skb has no facilities
+ * >0 - Parse OK, returns the length of the facilities header
+ *
*/
int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities,
struct x25_dte_facilities *dte_facs, unsigned long *vc_fac_mask)
switch (*p & X25_FAC_CLASS_MASK) {
case X25_FAC_CLASS_A:
if (len < 2)
- return 0;
+ return -1;
switch (*p) {
case X25_FAC_REVERSE:
if((p[1] & 0x81) == 0x81) {
break;
case X25_FAC_CLASS_B:
if (len < 3)
- return 0;
+ return -1;
switch (*p) {
case X25_FAC_PACKET_SIZE:
facilities->pacsize_in = p[1];
break;
case X25_FAC_CLASS_C:
if (len < 4)
- return 0;
+ return -1;
printk(KERN_DEBUG "X.25: unknown facility %02X, "
"values %02X, %02X, %02X\n",
p[0], p[1], p[2], p[3]);
break;
case X25_FAC_CLASS_D:
if (len < p[1] + 2)
- return 0;
+ return -1;
switch (*p) {
case X25_FAC_CALLING_AE:
if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1)
- return 0;
+ return -1;
dte_facs->calling_len = p[2];
memcpy(dte_facs->calling_ae, &p[3], p[1] - 1);
*vc_fac_mask |= X25_MASK_CALLING_AE;
break;
case X25_FAC_CALLED_AE:
if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1)
- return 0;
+ return -1;
dte_facs->called_len = p[2];
memcpy(dte_facs->called_ae, &p[3], p[1] - 1);
*vc_fac_mask |= X25_MASK_CALLED_AE;
{
struct x25_address source_addr, dest_addr;
int len;
+ struct x25_sock *x25 = x25_sk(sk);
switch (frametype) {
case X25_CALL_ACCEPTED: {
- struct x25_sock *x25 = x25_sk(sk);
x25_stop_timer(sk);
x25->condition = 0x00;
&dest_addr);
if (len > 0)
skb_pull(skb, len);
+ else if (len < 0)
+ goto out_clear;
len = x25_parse_facilities(skb, &x25->facilities,
&x25->dte_facilities,
&x25->vc_facil_mask);
if (len > 0)
skb_pull(skb, len);
- else
- return -1;
+ else if (len < 0)
+ goto out_clear;
/*
* Copy any Call User Data.
*/
}
return 0;
+
+out_clear:
+ x25_write_internal(sk, X25_CLEAR_REQUEST);
+ x25->state = X25_STATE_2;
+ x25_start_t23timer(sk);
+ return 0;
}
/*
write_lock_bh(&x25_neigh_list_lock);
list_for_each_safe(entry, tmp, &x25_neigh_list) {
+ struct net_device *dev;
+
nb = list_entry(entry, struct x25_neigh, node);
+ dev = nb->dev;
__x25_remove_neigh(nb);
- dev_put(nb->dev);
+ dev_put(dev);
}
write_unlock_bh(&x25_neigh_list_lock);
}
default:
BUG();
}
- xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS);
+ xdst = dst_alloc(dst_ops);
xfrm_policy_put_afinfo(afinfo);
- xdst->flo.ops = &xfrm_bundle_fc_ops;
+ if (likely(xdst))
+ xdst->flo.ops = &xfrm_bundle_fc_ops;
+ else
+ xdst = ERR_PTR(-ENOBUFS);
return xdst;
}
close(fd);
}
+/*
+ * Important: The below generated source_foo.o and deps_foo.o variable
+ * assignments are parsed not only by make, but also by the rather simple
+ * parser in scripts/mod/sumversion.c.
+ */
static void parse_dep_file(void *map, size_t len)
{
char *m = map;
char *end = m + len;
char *p;
char s[PATH_MAX];
+ int first;
p = strchr(m, ':');
if (!p) {
exit(1);
}
memcpy(s, m, p-m); s[p-m] = 0;
- printf("deps_%s := \\\n", target);
m = p+1;
clear_config();
+ first = 1;
while (m < end) {
while (m < end && (*m == ' ' || *m == '\\' || *m == '\n'))
m++;
if (strrcmp(s, "include/generated/autoconf.h") &&
strrcmp(s, "arch/um/include/uml-config.h") &&
strrcmp(s, ".ver")) {
- printf(" %s \\\n", s);
+ /*
+ * Do not list the source file as dependency, so that
+ * kbuild is not confused if a .c file is rewritten
+ * into .S or vice versa. Storing it in source_* is
+ * needed for modpost to compute srcversions.
+ */
+ if (first) {
+ printf("source_%s := %s\n\n", target, s);
+ printf("deps_%s := \\\n", target);
+ } else
+ printf(" %s \\\n", s);
do_config_file(s);
}
+ first = 0;
m = p + 1;
}
printf("\n%s: $(deps_%s)\n\n", target, target);
WARN("Use of volatile is usually wrong: see Documentation/volatile-considered-harmful.txt\n" . $herecurr);
}
-# SPIN_LOCK_UNLOCKED & RW_LOCK_UNLOCKED are deprecated
- if ($line =~ /\b(SPIN_LOCK_UNLOCKED|RW_LOCK_UNLOCKED)/) {
- ERROR("Use of $1 is deprecated: see Documentation/spinlocks.txt\n" . $herecurr);
- }
-
# warn about #if 0
if ($line =~ /^.\s*\#\s*if\s+0\b/) {
CHK("if this code is redundant consider removing it\n" .
#!/usr/bin/perl -w
#
-# Copywrite 2005-2009 - Steven Rostedt
+# Copyright 2005-2009 - Steven Rostedt
# Licensed under the terms of the GNU GPL License version 2
#
# It's simple enough to figure out how this works.
return 0;
}
-/* We have dir/file.o. Open dir/.file.o.cmd, look for deps_ line to
- * figure out source file. */
+/* We have dir/file.o. Open dir/.file.o.cmd, look for source_ and deps_ line
+ * to figure out source files. */
static int parse_source_files(const char *objfile, struct md4_ctx *md)
{
char *cmd, *file, *line, *dir;
*/
while ((line = get_next_line(&pos, file, flen)) != NULL) {
char* p = line;
+
+ if (strncmp(line, "source_", sizeof("source_")-1) == 0) {
+ p = strrchr(line, ' ');
+ if (!p) {
+ warn("malformed line: %s\n", line);
+ goto out_file;
+ }
+ p++;
+ if (!parse_file(p, md)) {
+ warn("could not open %s: %s\n",
+ p, strerror(errno));
+ goto out_file;
+ }
+ continue;
+ }
if (strncmp(line, "deps_", sizeof("deps_")-1) == 0) {
check_files = 1;
continue;
fi
# Build header package
-find . -name Makefile -o -name Kconfig\* -o -name \*.pl > /tmp/files$$
-find arch/x86/include include scripts -type f >> /tmp/files$$
+(cd $srctree; find . -name Makefile -o -name Kconfig\* -o -name \*.pl > /tmp/files$$)
+(cd $srctree; find arch/$SRCARCH/include include scripts -type f >> /tmp/files$$)
(cd $objtree; find .config Module.symvers include scripts -type f >> /tmp/objfiles$$)
destdir=$kernel_headers_dir/usr/src/linux-headers-$version
mkdir -p "$destdir"
-tar -c -f - -T /tmp/files$$ | (cd $destdir; tar -xf -)
+(cd $srctree; tar -c -f - -T /tmp/files$$) | (cd $destdir; tar -xf -)
(cd $objtree; tar -c -f - -T /tmp/objfiles$$) | (cd $destdir; tar -xf -)
rm -f /tmp/files$$ /tmp/objfiles$$
arch=$(dpkg --print-architecture)
static int
is_mcounted_section_name(char const *const txtname)
{
- return 0 == strcmp(".text", txtname) ||
+ return 0 == strcmp(".text", txtname) ||
+ 0 == strcmp(".ref.text", txtname) ||
0 == strcmp(".sched.text", txtname) ||
0 == strcmp(".spinlock.text", txtname) ||
0 == strcmp(".irqentry.text", txtname) ||
# Acceptable sections to record.
my %text_sections = (
".text" => 1,
+ ".ref.text" => 1,
".sched.text" => 1,
".spinlock.text" => 1,
".irqentry.text" => 1,
"lockintnowait" : "6",
"lockcont" : "7",
"unlock" : "8",
- "lockbkl" : "9",
- "unlockbkl" : "10",
"signal" : "11",
"resetevent" : "98",
"reset" : "99",
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal 0
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal 0
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal 0
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal 0
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
# lockintnowait lock nr (0-7)
# lockcont lock nr (0-7)
# unlock lock nr (0-7)
-# lockbkl lock nr (0-7)
-# unlockbkl lock nr (0-7)
# signal thread to signal (0-7)
# reset 0
# resetevent 0
# blocked lock nr (0-7)
# blockedwake lock nr (0-7)
# unlocked lock nr (0-7)
-# lockedbkl dont care
-# blockedbkl dont care
-# unlockedbkl dont care
# opcodeeq command opcode or number
# opcodelt number
# opcodegt number
* Determine whether the current process may set the system clock and timezone
* information, returning 0 if permission granted, -ve if denied.
*/
-int cap_settime(struct timespec *ts, struct timezone *tz)
+int cap_settime(const struct timespec *ts, const struct timezone *tz)
{
if (!capable(CAP_SYS_TIME))
return -EPERM;
effective, inheritable, permitted);
}
-int security_capable(int cap)
+int security_capable(const struct cred *cred, int cap)
{
- return security_ops->capable(current, current_cred(), cap,
- SECURITY_CAP_AUDIT);
+ return security_ops->capable(current, cred, cap, SECURITY_CAP_AUDIT);
}
int security_real_capable(struct task_struct *tsk, int cap)
return security_ops->syslog(type);
}
-int security_settime(struct timespec *ts, struct timezone *tz)
+int security_settime(const struct timespec *ts, const struct timezone *tz)
{
return security_ops->settime(ts, tz);
}
{
struct snd_hrtimer *stime = container_of(hrt, struct snd_hrtimer, hrt);
struct snd_timer *t = stime->timer;
+ unsigned long oruns;
if (!atomic_read(&stime->running))
return HRTIMER_NORESTART;
- hrtimer_forward_now(hrt, ns_to_ktime(t->sticks * resolution));
- snd_timer_interrupt(stime->timer, t->sticks);
+ oruns = hrtimer_forward_now(hrt, ns_to_ktime(t->sticks * resolution));
+ snd_timer_interrupt(stime->timer, t->sticks * oruns);
if (!atomic_read(&stime->running))
return HRTIMER_NORESTART;
}
static struct snd_timer_hardware hrtimer_hw = {
- .flags = SNDRV_TIMER_HW_AUTO,
+ .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_TASKLET,
.open = snd_hrtimer_open,
.close = snd_hrtimer_close,
.start = snd_hrtimer_start,
fail_input:
input_free_device(jack->input_dev);
+ kfree(jack->id);
kfree(jack);
return err;
}
static int inline vortex_adbdma_getlinearpos(vortex_t * vortex, int adbdma)
{
stream_t *dma = &vortex->dma_adb[adbdma];
- int temp;
+ int temp, page, delta;
temp = hwread(vortex->mmio, VORTEX_ADBDMA_STAT + (adbdma << 2));
- temp = (dma->period_virt * dma->period_bytes) + (temp & (dma->period_bytes - 1));
- return temp;
+ page = (temp & ADB_SUBBUF_MASK) >> ADB_SUBBUF_SHIFT;
+ if (dma->nr_periods >= 4)
+ delta = (page - dma->period_real) & 3;
+ else {
+ delta = (page - dma->period_real);
+ if (delta < 0)
+ delta += dma->nr_periods;
+ }
+ return (dma->period_virt + delta) * dma->period_bytes
+ + (temp & (dma->period_bytes - 1));
}
static void vortex_adbdma_startfifo(vortex_t * vortex, int adbdma)
SND_PCI_QUIRK(0x1043, 0x813d, "ASUS P5AD2", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1043, 0x81b3, "ASUS", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1043, 0x81e7, "ASUS M2V", POS_FIX_LPIB),
+ SND_PCI_QUIRK(0x1043, 0x8410, "ASUS", POS_FIX_LPIB),
SND_PCI_QUIRK(0x104d, 0x9069, "Sony VPCS11V9E", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1106, 0x3288, "ASUS M2V-MX SE", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1179, 0xff10, "Toshiba A100-259", POS_FIX_LPIB),
if (err < 0)
goto out_free;
#ifdef CONFIG_SND_HDA_PATCH_LOADER
- if (patch[dev]) {
+ if (patch[dev] && *patch[dev]) {
snd_printk(KERN_ERR SFX "Applying patch firmware '%s'\n",
patch[dev]);
err = snd_hda_load_patch(chip->bus, patch[dev]);
{0x11, AC_VERB_SET_PROC_COEF, 0x0008},
{0x11, AC_VERB_SET_PROC_STATE, 0x00},
+#if 0 /* Don't to set to D3 as we are in power-up sequence */
{0x07, AC_VERB_SET_POWER_STATE, 0x03}, /* S/PDIF Rx: D3 */
{0x08, AC_VERB_SET_POWER_STATE, 0x03}, /* S/PDIF Tx: D3 */
/*{0x01, AC_VERB_SET_POWER_STATE, 0x03},*/ /* AFG: D3 This is already handled */
+#endif
{} /* terminator */
};
SND_PCI_QUIRK(0x1028, 0x0401, "Dell Vostro 1014", CXT5066_DELL_VOSTRO),
SND_PCI_QUIRK(0x1028, 0x0402, "Dell Vostro", CXT5066_DELL_VOSTRO),
SND_PCI_QUIRK(0x1028, 0x0408, "Dell Inspiron One 19T", CXT5066_IDEAPAD),
+ SND_PCI_QUIRK(0x1028, 0x050f, "Dell Inspiron", CXT5066_IDEAPAD),
+ SND_PCI_QUIRK(0x1028, 0x0510, "Dell Vostro", CXT5066_IDEAPAD),
SND_PCI_QUIRK(0x103c, 0x360b, "HP G60", CXT5066_HP_LAPTOP),
SND_PCI_QUIRK(0x1043, 0x13f3, "Asus A52J", CXT5066_ASUS),
SND_PCI_QUIRK(0x1043, 0x1643, "Asus K52JU", CXT5066_ASUS),
}
}
spec->multiout.dac_nids = spec->private_dac_nids;
- spec->multiout.max_channels = nums * 2;
+ spec->multiout.max_channels = spec->multiout.num_dacs * 2;
if (cfg->hp_outs > 0)
spec->auto_mute = 1;
return 0;
}
-static int cx_auto_add_volume(struct hda_codec *codec, const char *basename,
+static int cx_auto_add_volume_idx(struct hda_codec *codec, const char *basename,
const char *dir, int cidx,
- hda_nid_t nid, int hda_dir)
+ hda_nid_t nid, int hda_dir, int amp_idx)
{
static char name[32];
static struct snd_kcontrol_new knew[] = {
for (i = 0; i < 2; i++) {
struct snd_kcontrol *kctl;
- knew[i].private_value = HDA_COMPOSE_AMP_VAL(nid, 3, 0, hda_dir);
+ knew[i].private_value = HDA_COMPOSE_AMP_VAL(nid, 3, amp_idx,
+ hda_dir);
knew[i].subdevice = HDA_SUBDEV_AMP_FLAG;
knew[i].index = cidx;
snprintf(name, sizeof(name), "%s%s %s", basename, dir, sfx[i]);
return 0;
}
+#define cx_auto_add_volume(codec, str, dir, cidx, nid, hda_dir) \
+ cx_auto_add_volume_idx(codec, str, dir, cidx, nid, hda_dir, 0)
+
#define cx_auto_add_pb_volume(codec, nid, str, idx) \
cx_auto_add_volume(codec, str, " Playback", idx, nid, HDA_OUTPUT)
struct conexant_spec *spec = codec->spec;
struct auto_pin_cfg *cfg = &spec->autocfg;
static const char *prev_label;
- int i, err, cidx;
+ int i, err, cidx, conn_len;
+ hda_nid_t conn[HDA_MAX_CONNECTIONS];
+
+ int multi_adc_volume = 0; /* If the ADC nid has several input volumes */
+ int adc_nid = spec->adc_nids[0];
+
+ conn_len = snd_hda_get_connections(codec, adc_nid, conn,
+ HDA_MAX_CONNECTIONS);
+ if (conn_len < 0)
+ return conn_len;
+
+ multi_adc_volume = cfg->num_inputs > 1 && conn_len > 1;
+ if (!multi_adc_volume) {
+ err = cx_auto_add_volume(codec, "Capture", "", 0, adc_nid,
+ HDA_INPUT);
+ if (err < 0)
+ return err;
+ }
- err = cx_auto_add_volume(codec, "Capture", "", 0, spec->adc_nids[0],
- HDA_INPUT);
- if (err < 0)
- return err;
prev_label = NULL;
cidx = 0;
for (i = 0; i < cfg->num_inputs; i++) {
hda_nid_t nid = cfg->inputs[i].pin;
const char *label;
- if (!(get_wcaps(codec, nid) & AC_WCAP_IN_AMP))
+ int j;
+ int pin_amp = get_wcaps(codec, nid) & AC_WCAP_IN_AMP;
+ if (!pin_amp && !multi_adc_volume)
continue;
+
label = hda_get_autocfg_input_label(codec, cfg, i);
if (label == prev_label)
cidx++;
else
cidx = 0;
prev_label = label;
- err = cx_auto_add_volume(codec, label, " Capture", cidx,
- nid, HDA_INPUT);
- if (err < 0)
- return err;
+
+ if (pin_amp) {
+ err = cx_auto_add_volume(codec, label, " Boost", cidx,
+ nid, HDA_INPUT);
+ if (err < 0)
+ return err;
+ }
+
+ if (!multi_adc_volume)
+ continue;
+ for (j = 0; j < conn_len; j++) {
+ if (conn[j] == nid) {
+ err = cx_auto_add_volume_idx(codec, label,
+ " Capture", cidx, adc_nid, HDA_INPUT, j);
+ if (err < 0)
+ return err;
+ break;
+ }
+ }
}
return 0;
}
.patch = patch_cxt5066 },
{ .id = 0x14f15069, .name = "CX20585",
.patch = patch_cxt5066 },
+ { .id = 0x14f1506e, .name = "CX20590",
+ .patch = patch_cxt5066 },
{ .id = 0x14f15097, .name = "CX20631",
.patch = patch_conexant_auto },
{ .id = 0x14f15098, .name = "CX20632",
MODULE_ALIAS("snd-hda-codec-id:14f15067");
MODULE_ALIAS("snd-hda-codec-id:14f15068");
MODULE_ALIAS("snd-hda-codec-id:14f15069");
+MODULE_ALIAS("snd-hda-codec-id:14f1506e");
MODULE_ALIAS("snd-hda-codec-id:14f15097");
MODULE_ALIAS("snd-hda-codec-id:14f15098");
MODULE_ALIAS("snd-hda-codec-id:14f150a1");
hdmi_ai->ver = 0x01;
hdmi_ai->len = 0x0a;
hdmi_ai->CC02_CT47 = channels - 1;
+ hdmi_ai->CA = ca;
hdmi_checksum_audio_infoframe(hdmi_ai);
} else if (spec->sink_eld[i].conn_type == 1) { /* DisplayPort */
struct dp_audio_infoframe *dp_ai;
dp_ai->len = 0x1b;
dp_ai->ver = 0x11 << 2;
dp_ai->CC02_CT47 = channels - 1;
+ dp_ai->CA = ca;
} else {
snd_printd("HDMI: unknown connection type at pin %d\n",
pin_nid);
{ .id = 0x10de0012, .name = "GPU 12 HDMI/DP", .patch = patch_nvhdmi_8ch_89 },
{ .id = 0x10de0013, .name = "GPU 13 HDMI/DP", .patch = patch_nvhdmi_8ch_89 },
{ .id = 0x10de0014, .name = "GPU 14 HDMI/DP", .patch = patch_nvhdmi_8ch_89 },
+{ .id = 0x10de0015, .name = "GPU 15 HDMI/DP", .patch = patch_nvhdmi_8ch_89 },
+{ .id = 0x10de0016, .name = "GPU 16 HDMI/DP", .patch = patch_nvhdmi_8ch_89 },
+/* 17 is known to be absent */
{ .id = 0x10de0018, .name = "GPU 18 HDMI/DP", .patch = patch_nvhdmi_8ch_89 },
{ .id = 0x10de0019, .name = "GPU 19 HDMI/DP", .patch = patch_nvhdmi_8ch_89 },
{ .id = 0x10de001a, .name = "GPU 1a HDMI/DP", .patch = patch_nvhdmi_8ch_89 },
MODULE_ALIAS("snd-hda-codec-id:10de0012");
MODULE_ALIAS("snd-hda-codec-id:10de0013");
MODULE_ALIAS("snd-hda-codec-id:10de0014");
+MODULE_ALIAS("snd-hda-codec-id:10de0015");
+MODULE_ALIAS("snd-hda-codec-id:10de0016");
MODULE_ALIAS("snd-hda-codec-id:10de0018");
MODULE_ALIAS("snd-hda-codec-id:10de0019");
MODULE_ALIAS("snd-hda-codec-id:10de001a");
nid = spec->autocfg.hp_pins[i];
if (!nid)
break;
- if (snd_hda_jack_detect(codec, nid)) {
- spec->jack_present = 1;
- break;
- }
- alc_report_jack(codec, spec->autocfg.hp_pins[i]);
+ alc_report_jack(codec, nid);
+ spec->jack_present |= snd_hda_jack_detect(codec, nid);
}
mute = spec->jack_present ? HDA_AMP_MUTE : 0;
{ } /* end */
};
+static struct snd_kcontrol_new alc888_acer_aspire_4930g_mixer[] = {
+ HDA_CODEC_VOLUME("Front Playback Volume", 0x0c, 0x0, HDA_OUTPUT),
+ HDA_BIND_MUTE("Front Playback Switch", 0x0c, 2, HDA_INPUT),
+ HDA_CODEC_VOLUME("Surround Playback Volume", 0x0d, 0x0, HDA_OUTPUT),
+ HDA_BIND_MUTE("Surround Playback Switch", 0x0d, 2, HDA_INPUT),
+ HDA_CODEC_VOLUME_MONO("Center Playback Volume", 0x0f, 2, 0x0,
+ HDA_OUTPUT),
+ HDA_BIND_MUTE_MONO("Center Playback Switch", 0x0f, 2, 2, HDA_INPUT),
+ HDA_CODEC_VOLUME_MONO("LFE Playback Volume", 0x0f, 1, 0x0, HDA_OUTPUT),
+ HDA_BIND_MUTE_MONO("LFE Playback Switch", 0x0f, 1, 2, HDA_INPUT),
+ HDA_CODEC_VOLUME("Side Playback Volume", 0x0e, 0x0, HDA_OUTPUT),
+ HDA_BIND_MUTE("Side Playback Switch", 0x0e, 2, HDA_INPUT),
+ HDA_CODEC_VOLUME("CD Playback Volume", 0x0b, 0x04, HDA_INPUT),
+ HDA_CODEC_MUTE("CD Playback Switch", 0x0b, 0x04, HDA_INPUT),
+ HDA_CODEC_VOLUME("Line Playback Volume", 0x0b, 0x02, HDA_INPUT),
+ HDA_CODEC_MUTE("Line Playback Switch", 0x0b, 0x02, HDA_INPUT),
+ HDA_CODEC_VOLUME("Mic Playback Volume", 0x0b, 0x0, HDA_INPUT),
+ HDA_CODEC_VOLUME("Mic Boost Volume", 0x18, 0, HDA_INPUT),
+ HDA_CODEC_MUTE("Mic Playback Switch", 0x0b, 0x0, HDA_INPUT),
+ { } /* end */
+};
+
+
static struct snd_kcontrol_new alc889_acer_aspire_8930g_mixer[] = {
HDA_CODEC_VOLUME("Front Playback Volume", 0x0c, 0x0, HDA_OUTPUT),
HDA_BIND_MUTE("Front Playback Switch", 0x0c, 2, HDA_INPUT),
.init_hook = alc_automute_amp,
},
[ALC888_ACER_ASPIRE_4930G] = {
- .mixers = { alc888_base_mixer,
+ .mixers = { alc888_acer_aspire_4930g_mixer,
alc883_chmode_mixer },
.init_verbs = { alc883_init_verbs, alc880_gpio1_init_verbs,
alc888_acer_aspire_4930g_verbs },
SND_PCI_QUIRK(0x1043, 0x11e3, "ASUS U33Jc", ALC269VB_AMIC),
SND_PCI_QUIRK(0x1043, 0x1273, "ASUS UL80Jt", ALC269VB_AMIC),
SND_PCI_QUIRK(0x1043, 0x1283, "ASUS U53Jc", ALC269_AMIC),
- SND_PCI_QUIRK(0x1043, 0x12b3, "ASUS N82Jv", ALC269_AMIC),
+ SND_PCI_QUIRK(0x1043, 0x12b3, "ASUS N82JV", ALC269VB_AMIC),
SND_PCI_QUIRK(0x1043, 0x12d3, "ASUS N61Jv", ALC269_AMIC),
SND_PCI_QUIRK(0x1043, 0x13a3, "ASUS UL30Vt", ALC269_AMIC),
SND_PCI_QUIRK(0x1043, 0x1373, "ASUS G73JX", ALC269_AMIC),
ALC662_3ST_6ch_DIG),
SND_PCI_QUIRK_MASK(0x1854, 0xf000, 0x2000, "ASUS H13-200x",
ALC663_ASUS_H13),
+ SND_PCI_QUIRK(0x1991, 0x5628, "Ordissimo EVE", ALC662_LENOVO_101E),
{}
};
};
static struct snd_pci_quirk alc662_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1025, 0x0308, "Acer Aspire 8942G", ALC662_FIXUP_ASPIRE),
SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE),
SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD),
0x0f, 0x10, 0x11, 0x1f, 0x20,
};
-static hda_nid_t stac92hd88xxx_pin_nids[10] = {
+static hda_nid_t stac92hd87xxx_pin_nids[6] = {
+ 0x0a, 0x0b, 0x0c, 0x0d,
+ 0x0f, 0x11,
+};
+
+static hda_nid_t stac92hd88xxx_pin_nids[8] = {
0x0a, 0x0b, 0x0c, 0x0d,
0x0f, 0x11, 0x1f, 0x20,
};
switch (codec->vendor_id) {
case 0x111d76d1:
case 0x111d76d9:
+ case 0x111d76e5:
spec->dmic_nids = stac92hd87b_dmic_nids;
spec->num_dmics = stac92xx_connected_ports(codec,
stac92hd87b_dmic_nids,
STAC92HD87B_NUM_DMICS);
- spec->num_pins = ARRAY_SIZE(stac92hd88xxx_pin_nids);
- spec->pin_nids = stac92hd88xxx_pin_nids;
+ spec->num_pins = ARRAY_SIZE(stac92hd87xxx_pin_nids);
+ spec->pin_nids = stac92hd87xxx_pin_nids;
spec->mono_nid = 0;
spec->num_pwrs = 0;
break;
case 0x111d7667:
case 0x111d7668:
case 0x111d7669:
+ case 0x111d76e3:
spec->num_dmics = stac92xx_connected_ports(codec,
stac92hd88xxx_dmic_nids,
STAC92HD88XXX_NUM_DMICS);
{ .id = 0x111d76cd, .name = "92HD89F2", .patch = patch_stac92hd73xx },
{ .id = 0x111d76ce, .name = "92HD89F1", .patch = patch_stac92hd73xx },
{ .id = 0x111d76e0, .name = "92HD91BXX", .patch = patch_stac92hd83xxx},
+ { .id = 0x111d76e3, .name = "92HD98BXX", .patch = patch_stac92hd83xxx},
+ { .id = 0x111d76e5, .name = "92HD99BXX", .patch = patch_stac92hd83xxx},
{ .id = 0x111d76e7, .name = "92HD90BXX", .patch = patch_stac92hd83xxx},
{} /* terminator */
};
hda_nid_t nid = cfg->inputs[i].pin;
if (spec->smart51_enabled && is_smart51_pins(spec, nid))
ctl = PIN_OUT;
- else if (i == AUTO_PIN_MIC)
+ else if (cfg->inputs[i].type == AUTO_PIN_MIC)
ctl = PIN_VREF50;
else
ctl = PIN_IN;
return 0;
}
-static const u8 cx20442_reg = CX20442_TELOUT | CX20442_MIC;
+static const u8 cx20442_reg;
static struct snd_soc_codec_driver cx20442_codec_dev = {
.probe = cx20442_codec_probe,
WM8903_MICDET_EINT | WM8903_MICSHRT_EINT,
irq_mask);
- if (det && shrt) {
+ if (det || shrt) {
/* Enable mic detection, this may not have been set through
* platform data (eg, if the defaults are OK). */
snd_soc_update_bits(codec, WM8903_WRITE_SEQUENCER_0,
#define WM8903_VMID_RES_50K 2
#define WM8903_VMID_RES_250K 3
-#define WM8903_VMID_RES_5K 4
+#define WM8903_VMID_RES_5K 6
/*
* R8 (0x08) - Analogue DAC 0
SOC_SINGLE("DAC Playback Limiter Threshold",
WM8978_DAC_LIMITER_2, 4, 7, 0),
SOC_SINGLE("DAC Playback Limiter Boost",
- WM8978_DAC_LIMITER_2, 0, 15, 0),
+ WM8978_DAC_LIMITER_2, 0, 12, 0),
SOC_ENUM("ALC Enable Switch", alc1),
SOC_SINGLE("ALC Capture Min Gain", WM8978_ALC_CONTROL_1, 0, 7, 0),
SOC_SINGLE("ALC Capture Max Gain", WM8978_ALC_CONTROL_1, 3, 7, 0),
- SOC_SINGLE("ALC Capture Hold", WM8978_ALC_CONTROL_2, 4, 7, 0),
+ SOC_SINGLE("ALC Capture Hold", WM8978_ALC_CONTROL_2, 4, 10, 0),
SOC_SINGLE("ALC Capture Target", WM8978_ALC_CONTROL_2, 0, 15, 0),
SOC_ENUM("ALC Capture Mode", alc3),
- SOC_SINGLE("ALC Capture Decay", WM8978_ALC_CONTROL_3, 4, 15, 0),
- SOC_SINGLE("ALC Capture Attack", WM8978_ALC_CONTROL_3, 0, 15, 0),
+ SOC_SINGLE("ALC Capture Decay", WM8978_ALC_CONTROL_3, 4, 10, 0),
+ SOC_SINGLE("ALC Capture Attack", WM8978_ALC_CONTROL_3, 0, 10, 0),
SOC_SINGLE("ALC Capture Noise Gate Switch", WM8978_NOISE_GATE, 3, 1, 0),
SOC_SINGLE("ALC Capture Noise Gate Threshold",
WM8978_LOUT2_SPK_CONTROL, WM8978_ROUT2_SPK_CONTROL, 6, 1, 1),
/* DAC / ADC oversampling */
- SOC_SINGLE("DAC 128x Oversampling Switch", WM8978_DAC_CONTROL, 8, 1, 0),
- SOC_SINGLE("ADC 128x Oversampling Switch", WM8978_ADC_CONTROL, 8, 1, 0),
+ SOC_SINGLE("DAC 128x Oversampling Switch", WM8978_DAC_CONTROL,
+ 5, 1, 0),
+ SOC_SINGLE("ADC 128x Oversampling Switch", WM8978_ADC_CONTROL,
+ 5, 1, 0),
};
/* Mixer #1: Output (OUT1, OUT2) Mixer: mix AUX, Input mixer output and DAC */
int revision;
struct wm8994_pdata *pdata;
+
+ unsigned int aif1clk_enable:1;
+ unsigned int aif2clk_enable:1;
+
+ unsigned int aif1clk_disable:1;
+ unsigned int aif2clk_disable:1;
};
static int wm8994_readable(unsigned int reg)
}
}
+static int late_enable_ev(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_codec *codec = w->codec;
+ struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
+
+ switch (event) {
+ case SND_SOC_DAPM_PRE_PMU:
+ if (wm8994->aif1clk_enable) {
+ snd_soc_update_bits(codec, WM8994_AIF1_CLOCKING_1,
+ WM8994_AIF1CLK_ENA_MASK,
+ WM8994_AIF1CLK_ENA);
+ wm8994->aif1clk_enable = 0;
+ }
+ if (wm8994->aif2clk_enable) {
+ snd_soc_update_bits(codec, WM8994_AIF2_CLOCKING_1,
+ WM8994_AIF2CLK_ENA_MASK,
+ WM8994_AIF2CLK_ENA);
+ wm8994->aif2clk_enable = 0;
+ }
+ break;
+ }
+
+ return 0;
+}
+
+static int late_disable_ev(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_codec *codec = w->codec;
+ struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
+
+ switch (event) {
+ case SND_SOC_DAPM_POST_PMD:
+ if (wm8994->aif1clk_disable) {
+ snd_soc_update_bits(codec, WM8994_AIF1_CLOCKING_1,
+ WM8994_AIF1CLK_ENA_MASK, 0);
+ wm8994->aif1clk_disable = 0;
+ }
+ if (wm8994->aif2clk_disable) {
+ snd_soc_update_bits(codec, WM8994_AIF2_CLOCKING_1,
+ WM8994_AIF2CLK_ENA_MASK, 0);
+ wm8994->aif2clk_disable = 0;
+ }
+ break;
+ }
+
+ return 0;
+}
+
+static int aif1clk_ev(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_codec *codec = w->codec;
+ struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
+
+ switch (event) {
+ case SND_SOC_DAPM_PRE_PMU:
+ wm8994->aif1clk_enable = 1;
+ break;
+ case SND_SOC_DAPM_POST_PMD:
+ wm8994->aif1clk_disable = 1;
+ break;
+ }
+
+ return 0;
+}
+
+static int aif2clk_ev(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_codec *codec = w->codec;
+ struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
+
+ switch (event) {
+ case SND_SOC_DAPM_PRE_PMU:
+ wm8994->aif2clk_enable = 1;
+ break;
+ case SND_SOC_DAPM_POST_PMD:
+ wm8994->aif2clk_disable = 1;
+ break;
+ }
+
+ return 0;
+}
+
+static int adc_mux_ev(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ late_enable_ev(w, kcontrol, event);
+ return 0;
+}
+
+static int dac_ev(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_codec *codec = w->codec;
+ unsigned int mask = 1 << w->shift;
+
+ snd_soc_update_bits(codec, WM8994_POWER_MANAGEMENT_5,
+ mask, mask);
+ return 0;
+}
+
static const char *hp_mux_text[] = {
"Mixer",
"DAC",
static const struct snd_kcontrol_new aif2dacr_src_mux =
SOC_DAPM_ENUM("AIF2DACR Mux", aif2dacr_src_enum);
+static const struct snd_soc_dapm_widget wm8994_lateclk_revd_widgets[] = {
+SND_SOC_DAPM_SUPPLY("AIF1CLK", SND_SOC_NOPM, 0, 0, aif1clk_ev,
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+SND_SOC_DAPM_SUPPLY("AIF2CLK", SND_SOC_NOPM, 0, 0, aif2clk_ev,
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+
+SND_SOC_DAPM_PGA_E("Late DAC1L Enable PGA", SND_SOC_NOPM, 0, 0, NULL, 0,
+ late_enable_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_PGA_E("Late DAC1R Enable PGA", SND_SOC_NOPM, 0, 0, NULL, 0,
+ late_enable_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_PGA_E("Late DAC2L Enable PGA", SND_SOC_NOPM, 0, 0, NULL, 0,
+ late_enable_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_PGA_E("Late DAC2R Enable PGA", SND_SOC_NOPM, 0, 0, NULL, 0,
+ late_enable_ev, SND_SOC_DAPM_PRE_PMU),
+
+SND_SOC_DAPM_POST("Late Disable PGA", late_disable_ev)
+};
+
+static const struct snd_soc_dapm_widget wm8994_lateclk_widgets[] = {
+SND_SOC_DAPM_SUPPLY("AIF1CLK", WM8994_AIF1_CLOCKING_1, 0, 0, NULL, 0),
+SND_SOC_DAPM_SUPPLY("AIF2CLK", WM8994_AIF2_CLOCKING_1, 0, 0, NULL, 0)
+};
+
+static const struct snd_soc_dapm_widget wm8994_dac_revd_widgets[] = {
+SND_SOC_DAPM_DAC_E("DAC2L", NULL, SND_SOC_NOPM, 3, 0,
+ dac_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_DAC_E("DAC2R", NULL, SND_SOC_NOPM, 2, 0,
+ dac_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_DAC_E("DAC1L", NULL, SND_SOC_NOPM, 1, 0,
+ dac_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_DAC_E("DAC1R", NULL, SND_SOC_NOPM, 0, 0,
+ dac_ev, SND_SOC_DAPM_PRE_PMU),
+};
+
+static const struct snd_soc_dapm_widget wm8994_dac_widgets[] = {
+SND_SOC_DAPM_DAC("DAC2L", NULL, WM8994_POWER_MANAGEMENT_5, 3, 0),
+SND_SOC_DAPM_DAC("DAC2R", NULL, WM8994_POWER_MANAGEMENT_5, 2, 0),
+SND_SOC_DAPM_DAC("DAC1L", NULL, WM8994_POWER_MANAGEMENT_5, 1, 0),
+SND_SOC_DAPM_DAC("DAC1R", NULL, WM8994_POWER_MANAGEMENT_5, 0, 0),
+};
+
+static const struct snd_soc_dapm_widget wm8994_adc_revd_widgets[] = {
+SND_SOC_DAPM_MUX_E("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux,
+ adc_mux_ev, SND_SOC_DAPM_PRE_PMU),
+SND_SOC_DAPM_MUX_E("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux,
+ adc_mux_ev, SND_SOC_DAPM_PRE_PMU),
+};
+
+static const struct snd_soc_dapm_widget wm8994_adc_widgets[] = {
+SND_SOC_DAPM_MUX("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux),
+SND_SOC_DAPM_MUX("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux),
+};
+
static const struct snd_soc_dapm_widget wm8994_dapm_widgets[] = {
SND_SOC_DAPM_INPUT("DMIC1DAT"),
SND_SOC_DAPM_INPUT("DMIC2DAT"),
SND_SOC_DAPM_SUPPLY("DSP2CLK", WM8994_CLOCKING_1, 2, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("DSPINTCLK", WM8994_CLOCKING_1, 1, 0, NULL, 0),
-SND_SOC_DAPM_SUPPLY("AIF1CLK", WM8994_AIF1_CLOCKING_1, 0, 0, NULL, 0),
-SND_SOC_DAPM_SUPPLY("AIF2CLK", WM8994_AIF2_CLOCKING_1, 0, 0, NULL, 0),
-
-SND_SOC_DAPM_AIF_OUT("AIF1ADC1L", "AIF1 Capture",
+SND_SOC_DAPM_AIF_OUT("AIF1ADC1L", NULL,
0, WM8994_POWER_MANAGEMENT_4, 9, 0),
-SND_SOC_DAPM_AIF_OUT("AIF1ADC1R", "AIF1 Capture",
+SND_SOC_DAPM_AIF_OUT("AIF1ADC1R", NULL,
0, WM8994_POWER_MANAGEMENT_4, 8, 0),
SND_SOC_DAPM_AIF_IN_E("AIF1DAC1L", NULL, 0,
WM8994_POWER_MANAGEMENT_5, 9, 0, wm8958_aif_ev,
WM8994_POWER_MANAGEMENT_5, 8, 0, wm8958_aif_ev,
SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
-SND_SOC_DAPM_AIF_OUT("AIF1ADC2L", "AIF1 Capture",
+SND_SOC_DAPM_AIF_OUT("AIF1ADC2L", NULL,
0, WM8994_POWER_MANAGEMENT_4, 11, 0),
-SND_SOC_DAPM_AIF_OUT("AIF1ADC2R", "AIF1 Capture",
+SND_SOC_DAPM_AIF_OUT("AIF1ADC2R", NULL,
0, WM8994_POWER_MANAGEMENT_4, 10, 0),
SND_SOC_DAPM_AIF_IN_E("AIF1DAC2L", NULL, 0,
WM8994_POWER_MANAGEMENT_5, 11, 0, wm8958_aif_ev,
SND_SOC_DAPM_AIF_IN("AIF1DACDAT", "AIF1 Playback", 0, SND_SOC_NOPM, 0, 0),
SND_SOC_DAPM_AIF_IN("AIF2DACDAT", "AIF2 Playback", 0, SND_SOC_NOPM, 0, 0),
+SND_SOC_DAPM_AIF_OUT("AIF1ADCDAT", "AIF1 Capture", 0, SND_SOC_NOPM, 0, 0),
SND_SOC_DAPM_AIF_OUT("AIF2ADCDAT", "AIF2 Capture", 0, SND_SOC_NOPM, 0, 0),
SND_SOC_DAPM_MUX("AIF1DAC Mux", SND_SOC_NOPM, 0, 0, &aif1dac_mux),
SND_SOC_DAPM_ADC("ADCL", NULL, SND_SOC_NOPM, 1, 0),
SND_SOC_DAPM_ADC("ADCR", NULL, SND_SOC_NOPM, 0, 0),
-SND_SOC_DAPM_MUX("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux),
-SND_SOC_DAPM_MUX("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux),
-
-SND_SOC_DAPM_DAC("DAC2L", NULL, WM8994_POWER_MANAGEMENT_5, 3, 0),
-SND_SOC_DAPM_DAC("DAC2R", NULL, WM8994_POWER_MANAGEMENT_5, 2, 0),
-SND_SOC_DAPM_DAC("DAC1L", NULL, WM8994_POWER_MANAGEMENT_5, 1, 0),
-SND_SOC_DAPM_DAC("DAC1R", NULL, WM8994_POWER_MANAGEMENT_5, 0, 0),
-
SND_SOC_DAPM_MUX("Left Headphone Mux", SND_SOC_NOPM, 0, 0, &hpl_mux),
SND_SOC_DAPM_MUX("Right Headphone Mux", SND_SOC_NOPM, 0, 0, &hpr_mux),
{ "AIF2ADC Mux", "AIF3DACDAT", "AIF3ADCDAT" },
/* DAC1 inputs */
- { "DAC1L", NULL, "DAC1L Mixer" },
{ "DAC1L Mixer", "AIF2 Switch", "AIF2DACL" },
{ "DAC1L Mixer", "AIF1.2 Switch", "AIF1DAC2L" },
{ "DAC1L Mixer", "AIF1.1 Switch", "AIF1DAC1L" },
{ "DAC1L Mixer", "Left Sidetone Switch", "Left Sidetone" },
{ "DAC1L Mixer", "Right Sidetone Switch", "Right Sidetone" },
- { "DAC1R", NULL, "DAC1R Mixer" },
{ "DAC1R Mixer", "AIF2 Switch", "AIF2DACR" },
{ "DAC1R Mixer", "AIF1.2 Switch", "AIF1DAC2R" },
{ "DAC1R Mixer", "AIF1.1 Switch", "AIF1DAC1R" },
/* DAC2/AIF2 outputs */
{ "AIF2ADCL", NULL, "AIF2DAC2L Mixer" },
- { "DAC2L", NULL, "AIF2DAC2L Mixer" },
{ "AIF2DAC2L Mixer", "AIF2 Switch", "AIF2DACL" },
{ "AIF2DAC2L Mixer", "AIF1.2 Switch", "AIF1DAC2L" },
{ "AIF2DAC2L Mixer", "AIF1.1 Switch", "AIF1DAC1L" },
{ "AIF2DAC2L Mixer", "Right Sidetone Switch", "Right Sidetone" },
{ "AIF2ADCR", NULL, "AIF2DAC2R Mixer" },
- { "DAC2R", NULL, "AIF2DAC2R Mixer" },
{ "AIF2DAC2R Mixer", "AIF2 Switch", "AIF2DACR" },
{ "AIF2DAC2R Mixer", "AIF1.2 Switch", "AIF1DAC2R" },
{ "AIF2DAC2R Mixer", "AIF1.1 Switch", "AIF1DAC1R" },
{ "AIF2DAC2R Mixer", "Left Sidetone Switch", "Left Sidetone" },
{ "AIF2DAC2R Mixer", "Right Sidetone Switch", "Right Sidetone" },
+ { "AIF1ADCDAT", NULL, "AIF1ADC1L" },
+ { "AIF1ADCDAT", NULL, "AIF1ADC1R" },
+ { "AIF1ADCDAT", NULL, "AIF1ADC2L" },
+ { "AIF1ADCDAT", NULL, "AIF1ADC2R" },
+
{ "AIF2ADCDAT", NULL, "AIF2ADC Mux" },
/* AIF3 output */
{ "Right Headphone Mux", "DAC", "DAC1R" },
};
+static const struct snd_soc_dapm_route wm8994_lateclk_revd_intercon[] = {
+ { "DAC1L", NULL, "Late DAC1L Enable PGA" },
+ { "Late DAC1L Enable PGA", NULL, "DAC1L Mixer" },
+ { "DAC1R", NULL, "Late DAC1R Enable PGA" },
+ { "Late DAC1R Enable PGA", NULL, "DAC1R Mixer" },
+ { "DAC2L", NULL, "Late DAC2L Enable PGA" },
+ { "Late DAC2L Enable PGA", NULL, "AIF2DAC2L Mixer" },
+ { "DAC2R", NULL, "Late DAC2R Enable PGA" },
+ { "Late DAC2R Enable PGA", NULL, "AIF2DAC2R Mixer" }
+};
+
+static const struct snd_soc_dapm_route wm8994_lateclk_intercon[] = {
+ { "DAC1L", NULL, "DAC1L Mixer" },
+ { "DAC1R", NULL, "DAC1R Mixer" },
+ { "DAC2L", NULL, "AIF2DAC2L Mixer" },
+ { "DAC2R", NULL, "AIF2DAC2R Mixer" },
+};
+
+static const struct snd_soc_dapm_route wm8994_revd_intercon[] = {
+ { "AIF1DACDAT", NULL, "AIF2DACDAT" },
+ { "AIF2DACDAT", NULL, "AIF1DACDAT" },
+ { "AIF1ADCDAT", NULL, "AIF2ADCDAT" },
+ { "AIF2ADCDAT", NULL, "AIF1ADCDAT" },
+};
+
static const struct snd_soc_dapm_route wm8994_intercon[] = {
{ "AIF2DACL", NULL, "AIF2DAC Mux" },
{ "AIF2DACR", NULL, "AIF2DAC Mux" },
{
struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
int i, ret;
+ unsigned int val, mask;
+
+ if (wm8994->revision < 4) {
+ /* force a HW read */
+ val = wm8994_reg_read(codec->control_data,
+ WM8994_POWER_MANAGEMENT_5);
+
+ /* modify the cache only */
+ codec->cache_only = 1;
+ mask = WM8994_DAC1R_ENA | WM8994_DAC1L_ENA |
+ WM8994_DAC2R_ENA | WM8994_DAC2L_ENA;
+ val &= mask;
+ snd_soc_update_bits(codec, WM8994_POWER_MANAGEMENT_5,
+ mask, val);
+ codec->cache_only = 0;
+ }
/* Restore the registers */
ret = snd_soc_cache_sync(codec);
report |= SND_JACK_BTN_5;
done:
- snd_soc_jack_report(wm8994->micdet[0].jack,
+ snd_soc_jack_report(wm8994->micdet[0].jack, report,
SND_JACK_BTN_0 | SND_JACK_BTN_1 | SND_JACK_BTN_2 |
SND_JACK_BTN_3 | SND_JACK_BTN_4 | SND_JACK_BTN_5 |
- SND_JACK_MICROPHONE | SND_JACK_VIDEOOUT,
- report);
+ SND_JACK_MICROPHONE | SND_JACK_VIDEOOUT);
}
/**
case WM8994:
snd_soc_dapm_new_controls(dapm, wm8994_specific_dapm_widgets,
ARRAY_SIZE(wm8994_specific_dapm_widgets));
+ if (wm8994->revision < 4) {
+ snd_soc_dapm_new_controls(dapm, wm8994_lateclk_revd_widgets,
+ ARRAY_SIZE(wm8994_lateclk_revd_widgets));
+ snd_soc_dapm_new_controls(dapm, wm8994_adc_revd_widgets,
+ ARRAY_SIZE(wm8994_adc_revd_widgets));
+ snd_soc_dapm_new_controls(dapm, wm8994_dac_revd_widgets,
+ ARRAY_SIZE(wm8994_dac_revd_widgets));
+ } else {
+ snd_soc_dapm_new_controls(dapm, wm8994_lateclk_widgets,
+ ARRAY_SIZE(wm8994_lateclk_widgets));
+ snd_soc_dapm_new_controls(dapm, wm8994_adc_widgets,
+ ARRAY_SIZE(wm8994_adc_widgets));
+ snd_soc_dapm_new_controls(dapm, wm8994_dac_widgets,
+ ARRAY_SIZE(wm8994_dac_widgets));
+ }
break;
case WM8958:
snd_soc_add_controls(codec, wm8958_snd_controls,
ARRAY_SIZE(wm8958_snd_controls));
+ snd_soc_dapm_new_controls(dapm, wm8994_lateclk_widgets,
+ ARRAY_SIZE(wm8994_lateclk_widgets));
+ snd_soc_dapm_new_controls(dapm, wm8994_adc_widgets,
+ ARRAY_SIZE(wm8994_adc_widgets));
+ snd_soc_dapm_new_controls(dapm, wm8994_dac_widgets,
+ ARRAY_SIZE(wm8994_dac_widgets));
snd_soc_dapm_new_controls(dapm, wm8958_dapm_widgets,
ARRAY_SIZE(wm8958_dapm_widgets));
break;
case WM8994:
snd_soc_dapm_add_routes(dapm, wm8994_intercon,
ARRAY_SIZE(wm8994_intercon));
+
+ if (wm8994->revision < 4) {
+ snd_soc_dapm_add_routes(dapm, wm8994_revd_intercon,
+ ARRAY_SIZE(wm8994_revd_intercon));
+ snd_soc_dapm_add_routes(dapm, wm8994_lateclk_revd_intercon,
+ ARRAY_SIZE(wm8994_lateclk_revd_intercon));
+ } else {
+ snd_soc_dapm_add_routes(dapm, wm8994_lateclk_intercon,
+ ARRAY_SIZE(wm8994_lateclk_intercon));
+ }
break;
case WM8958:
+ snd_soc_dapm_add_routes(dapm, wm8994_lateclk_intercon,
+ ARRAY_SIZE(wm8994_lateclk_intercon));
snd_soc_dapm_add_routes(dapm, wm8958_intercon,
ARRAY_SIZE(wm8958_intercon));
break;
#include <linux/moduleparam.h>
#include <linux/init.h>
#include <linux/delay.h>
+#include <linux/device.h>
#include <linux/pm.h>
#include <linux/i2c.h>
#include <linux/platform_device.h>
wm9081->control_type = SND_SOC_I2C;
wm9081->control_data = i2c;
+ if (dev_get_platdata(&i2c->dev))
+ memcpy(&wm9081->retune, dev_get_platdata(&i2c->dev),
+ sizeof(wm9081->retune));
+
ret = snd_soc_register_codec(&i2c->dev,
&soc_codec_dev_wm9081, &wm9081_dai, 1);
if (ret < 0)
};
static const struct snd_soc_dapm_route analogue_routes[] = {
+ { "MICBIAS1", NULL, "CLK_SYS" },
+ { "MICBIAS2", NULL, "CLK_SYS" },
+
{ "IN1L PGA", "IN1LP Switch", "IN1LP" },
{ "IN1L PGA", "IN1LN Switch", "IN1LN" },
.ops = &evm_spdif_ops,
},
};
-static struct snd_soc_dai_link da8xx_evm_dai = {
+
+static struct snd_soc_dai_link da830_evm_dai = {
+ .name = "TLV320AIC3X",
+ .stream_name = "AIC3X",
+ .cpu_dai_name = "davinci-mcasp.1",
+ .codec_dai_name = "tlv320aic3x-hifi",
+ .codec_name = "tlv320aic3x-codec.1-0018",
+ .platform_name = "davinci-pcm-audio",
+ .init = evm_aic3x_init,
+ .ops = &evm_ops,
+};
+
+static struct snd_soc_dai_link da850_evm_dai = {
.name = "TLV320AIC3X",
.stream_name = "AIC3X",
.cpu_dai_name= "davinci-mcasp.0",
static struct snd_soc_card da830_snd_soc_card = {
.name = "DA830/OMAP-L137 EVM",
- .dai_link = &da8xx_evm_dai,
+ .dai_link = &da830_evm_dai,
.num_links = 1,
};
static struct snd_soc_card da850_snd_soc_card = {
.name = "DA850/OMAP-L138 EVM",
- .dai_link = &da8xx_evm_dai,
+ .dai_link = &da850_evm_dai,
.num_links = 1,
};
.name = "tlv320aic23",
.stream_name = "TLV320AIC23",
.codec_dai_name = "tlv320aic23-hifi",
- .platform_name = "imx-pcm-audio.0",
+ .platform_name = "imx-fiq-pcm-audio.0",
.codec_name = "tlv320aic23-codec.0-001a",
.cpu_dai_name = "imx-ssi.0",
.ops = &eukrea_tlv320_snd_ops,
.cpu_dai_name ="omap-mcbsp-dai.0",
.codec_dai_name = "tlv320aic23-hifi",
.platform_name = "omap-pcm-audio",
- .codec_name = "tlv320aic23-codec",
+ .codec_name = "tlv320aic23-codec.2-001a",
.init = am3517evm_aic23_init,
.ops = &am3517evm_ops,
};
{
.name = "AC97",
.stream_name = "AC97 HiFi",
- .cpu_dai_name = "pxa-ac97.0",
+ .cpu_dai_name = "pxa2xx-ac97",
.codec_dai_name = "wm9705-hifi",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9705-codec",
{
.name = "AC97 Aux",
.stream_name = "AC97 Aux",
- .cpu_dai_name = "pxa-ac97.1",
+ .cpu_dai_name = "pxa2xx-ac97-aux",
.codec_dai_name = "wm9705-aux",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9705-codec",
{
.name = "AC97",
.stream_name = "AC97 HiFi",
- .cpu_dai_name = "pxa-ac97.0",
+ .cpu_dai_name = "pxa2xx-ac97",
.codec_dai_name = "wm9705-hifi",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9705-codec",
{
.name = "AC97 Aux",
.stream_name = "AC97 Aux",
- .cpu_dai_name = "pxa-ac97.1",
+ .cpu_dai_name = "pxa2xx-ac97-aux",
.codec_dai_name ="wm9705-aux",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9705-codec",
{
.name = "AC97",
.stream_name = "AC97 HiFi",
- .cpu_dai_name = "pxa-ac97.0",
+ .cpu_dai_name = "pxa2xx-ac97",
.codec_dai_name = "wm9712-hifi",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9712-codec",
{
.name = "AC97 Aux",
.stream_name = "AC97 Aux",
- .cpu_dai_name = "pxa-ac97.1",
+ .cpu_dai_name = "pxa2xx-ac97-aux",
.codec_dai_name ="wm9712-aux",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9712-codec",
{
.name = "AC97",
.stream_name = "AC97 HiFi",
- .cpu_dai_name = "pxa-ac97.0",
+ .cpu_dai_name = "pxa2xx-ac97",
.codec_dai_name = "wm9712-hifi",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9712-codec",
{
.name = "AC97 Aux",
.stream_name = "AC97 Aux",
- .cpu_dai_name = "pxa-ac97.1",
+ .cpu_dai_name = "pxa2xx-ac97-aux",
.codec_dai_name ="wm9712-aux",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9712-codec",
{
.name = "AC97",
.stream_name = "AC97 HiFi",
- .cpu_dai_name = "pxa-ac97.0",
+ .cpu_dai_name = "pxa2xx-ac97",
.codec_dai_name = "wm9713-hifi",
.codec_name = "wm9713-codec",
.init = mioa701_wm9713_init,
{
.name = "AC97 Aux",
.stream_name = "AC97 Aux",
- .cpu_dai_name = "pxa-ac97.1",
+ .cpu_dai_name = "pxa2xx-ac97-aux",
.codec_dai_name ="wm9713-aux",
.codec_name = "wm9713-codec",
.platform_name = "pxa-pcm-audio",
{
.name = "AC97 HiFi",
.stream_name = "AC97 HiFi",
- .cpu_dai_name = "pxa-ac97.0",
+ .cpu_dai_name = "pxa2xx-ac97",
.codec_dai_name = "wm9712-hifi",
.codec_name = "wm9712-codec",
.platform_name = "pxa-pcm-audio",
{
.name = "AC97 Aux",
.stream_name = "AC97 Aux",
- .cpu_dai_name = "pxa-ac97.1",
+ .cpu_dai_name = "pxa2xx-ac97-aux",
.codec_dai_name = "wm9712-aux",
.codec_name = "wm9712-codec",
.platform_name = "pxa-pcm-audio",
{
.name = "AC97",
.stream_name = "AC97 HiFi",
- .cpu_dai_name = "pxa-ac97.0",
+ .cpu_dai_name = "pxa2xx-ac97",
.codec_dai_name = "wm9712-hifi",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9712-codec",
{
.name = "AC97 Aux",
.stream_name = "AC97 Aux",
- .cpu_dai_name = "pxa-ac97.1",
+ .cpu_dai_name = "pxa2xx-ac97-aux",
.codec_dai_name = "wm9712-aux",
.platform_name = "pxa-pcm-audio",
.codec_name = "wm9712-codec",
.stream_name = "AC97 HiFi",
.codec_name = "wm9713-codec",
.platform_name = "pxa-pcm-audio",
- .cpu_dai_name = "pxa-ac97.0",
+ .cpu_dai_name = "pxa2xx-ac97",
.codec_name = "wm9713-hifi",
.init = zylonite_wm9713_init,
},
.stream_name = "AC97 Aux",
.codec_name = "wm9713-codec",
.platform_name = "pxa-pcm-audio",
- .cpu_dai_name = "pxa-ac97.1",
+ .cpu_dai_name = "pxa2xx-ac97-aux",
.codec_name = "wm9713-aux",
},
{
rtd = &card->rtd_aux[num];
name = aux_dev->name;
}
+ rtd->card = card;
/* machine controls, routes and widgets are not prefixed */
temp = codec->name_prefix;
/* register the rtd device */
rtd->codec = codec;
- rtd->card = card;
rtd->dev.parent = card->dev;
rtd->dev.release = rtd_release;
rtd->dev.init_name = name;
!path->connected(path->source, path->sink))
continue;
- if (path->sink && path->sink->power_check &&
+ if (!path->sink)
+ continue;
+
+ if (path->sink->force) {
+ power = 1;
+ break;
+ }
+
+ if (path->sink->power_check &&
path->sink->power_check(path->sink)) {
power = 1;
break;
}
if (!list_empty(&pending))
- dapm_seq_run_coalesced(dapm, &pending);
+ dapm_seq_run_coalesced(cur_dapm, &pending);
}
static void dapm_widget_update(struct snd_soc_dapm_context *dapm)
int snd_soc_dapm_new_widgets(struct snd_soc_dapm_context *dapm)
{
struct snd_soc_dapm_widget *w;
+ unsigned int val;
list_for_each_entry(w, &dapm->card->widgets, list)
{
case snd_soc_dapm_post:
break;
}
+
+ /* Read the initial power state from the device */
+ if (w->reg >= 0) {
+ val = snd_soc_read(w->codec, w->reg);
+ val &= 1 << w->shift;
+ if (w->invert)
+ val = !val;
+
+ if (val)
+ w->power = 1;
+ }
+
w->new = 1;
}
}
dev->pcm->private_data = dev;
- strcpy(dev->pcm->name, dev->product_name);
+ strlcpy(dev->pcm->name, dev->product_name, sizeof(dev->pcm->name));
memset(dev->sub_playback, 0, sizeof(dev->sub_playback));
memset(dev->sub_capture, 0, sizeof(dev->sub_capture));
if (ret < 0)
return ret;
- strcpy(rmidi->name, device->product_name);
+ strlcpy(rmidi->name, device->product_name, sizeof(rmidi->name));
rmidi->info_flags = SNDRV_RAWMIDI_INFO_DUPLEX;
rmidi->private_data = device;
return -ENOMEM;
}
+ mutex_init(&chip->shutdown_mutex);
chip->index = idx;
chip->dev = dev;
chip->card = card;
chip = ptr;
card = chip->card;
mutex_lock(®ister_mutex);
+ mutex_lock(&chip->shutdown_mutex);
chip->shutdown = 1;
chip->num_interfaces--;
if (chip->num_interfaces <= 0) {
snd_usb_mixer_disconnect(p);
}
usb_chip[chip->index] = NULL;
+ mutex_unlock(&chip->shutdown_mutex);
mutex_unlock(®ister_mutex);
snd_card_free_when_closed(card);
} else {
+ mutex_unlock(&chip->shutdown_mutex);
mutex_unlock(®ister_mutex);
}
}
};
-/*E-mu 0202(0404) eXtension Unit(XU) control*/
+/*E-mu 0202/0404/0204 eXtension Unit(XU) control*/
enum {
USB_XU_CLOCK_RATE = 0xe301,
USB_XU_CLOCK_SOURCE = 0xe302,
cval->initialized = 1;
} else {
if (type == USB_XU_CLOCK_RATE) {
- /* E-Mu USB 0404/0202/TrackerPre
+ /* E-Mu USB 0404/0202/TrackerPre/0204
* samplerate control quirk
*/
cval->min = 0;
}
if (changed) {
+ mutex_lock(&subs->stream->chip->shutdown_mutex);
/* format changed */
snd_usb_release_substream_urbs(subs, 0);
/* influenced: period_bytes, channels, rate, format, */
params_rate(hw_params),
snd_pcm_format_physical_width(params_format(hw_params)) *
params_channels(hw_params));
+ mutex_unlock(&subs->stream->chip->shutdown_mutex);
}
return ret;
subs->cur_audiofmt = NULL;
subs->cur_rate = 0;
subs->period_bytes = 0;
- if (!subs->stream->chip->shutdown)
- snd_usb_release_substream_urbs(subs, 0);
+ mutex_lock(&subs->stream->chip->shutdown_mutex);
+ snd_usb_release_substream_urbs(subs, 0);
+ mutex_unlock(&subs->stream->chip->shutdown_mutex);
return snd_pcm_lib_free_vmalloc_buffer(substream);
}
.idProduct = 0x3f0a,
.bInterfaceClass = USB_CLASS_AUDIO,
},
+{
+ /* E-Mu 0204 USB */
+ .match_flags = USB_DEVICE_ID_MATCH_DEVICE,
+ .idVendor = 0x041e,
+ .idProduct = 0x3f19,
+ .bInterfaceClass = USB_CLASS_AUDIO,
+},
/*
* Logitech QuickCam: bDeviceClass is vendor-specific, so generic interface
}
/*
- * For E-Mu 0404USB/0202USB/TrackerPre sample rate should be set for device,
+ * For E-Mu 0404USB/0202USB/TrackerPre/0204 sample rate should be set for device,
* not for interface.
*/
case USB_ID(0x041e, 0x3f02): /* E-Mu 0202 USB */
case USB_ID(0x041e, 0x3f04): /* E-Mu 0404 USB */
case USB_ID(0x041e, 0x3f0a): /* E-Mu Tracker Pre */
+ case USB_ID(0x041e, 0x3f19): /* E-Mu 0204 USB */
set_format_emu_quirk(subs, fmt);
break;
}
struct snd_card *card;
u32 usb_id;
int shutdown;
+ struct mutex shutdown_mutex;
unsigned int txfr_quirk:1; /* Subframe boundaries on transfers */
int num_interfaces;
int num_suspended_intf;
-PERF-BUILD-OPTIONS
PERF-CFLAGS
PERF-GUI-VARS
PERF-VERSION-FILE
$(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
$(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir)
-install-html: html
- '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
+#install-html: html
+# '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
../PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
$(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) PERF-VERSION-FILE
sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
mv $@+ $@
-install-webdoc : html
- '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
+# UNIMPLEMENTED
+#install-webdoc : html
+# '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
-quick-install: quick-install-man
+# quick-install: quick-install-man
-quick-install-man:
- '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
+# quick-install-man:
+# '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
-quick-install-html:
- '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
+#quick-install-html:
+# '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
.PHONY: .FORCE-PERF-VERSION-FILE
SYNOPSIS
--------
[verse]
-'perf list'
+'perf list' [hw|sw|cache|tracepoint|event_glob]
DESCRIPTION
-----------
OPTIONS
-------
-None
+
+Without options all known events will be listed.
+
+To limit the list use:
+
+. 'hw' or 'hardware' to list hardware events such as cache-misses, etc.
+
+. 'sw' or 'software' to list software events such as context switches, etc.
+
+. 'cache' or 'hwcache' to list hardware cache events such as L1-dcache-loads, etc.
+
+. 'tracepoint' to list all tracepoint events, alternatively use
+ 'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
+ block, etc.
+
+. If none of the above is matched, it will apply the supplied glob to all
+ events, printing the ones that match.
+
+One or more types can be used at the same time, listing the events for the
+types specified.
SEE ALSO
--------
'perf lock report' reports statistical data.
-OPTIONS
--------
+COMMON OPTIONS
+--------------
-i::
--input=<file>::
--dump-raw-trace::
Dump raw trace in ASCII.
+REPORT OPTIONS
+--------------
+
+-k::
+--key=<value>::
+ Sorting key. Possible values: acquired (default), contended,
+ wait_total, wait_max, wait_min.
+
SEE ALSO
--------
linkperf:perf[1]
or
'perf probe' --list
or
-'perf probe' [options] --line='FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]'
+'perf probe' [options] --line='LINE'
or
'perf probe' [options] --vars='PROBEPOINT'
(Only for --vars) Show external defined variables in addition to local
variables.
+-F::
+--funcs::
+ Show available functions in given module or kernel.
+
+--filter=FILTER::
+ (Only for --vars and --funcs) Set filter. FILTER is a combination of glob
+ pattern, see FILTER PATTERN for detail.
+ Default FILTER is "!__k???tab_* & !__crc_*" for --vars, and "!_*"
+ for --funcs.
+ If several filters are specified, only the last filter is used.
+
-f::
--force::
Forcibly add events with existing name.
-----------
Line range is described by following syntax.
- "FUNC[:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]"
+ "FUNC[@SRC][:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]"
FUNC specifies the function name of showing lines. 'RLN' is the start line
number from function entry line, and 'RLN2' is the end line number. As same as
probe syntax, 'SRC' means the source file path, 'ALN' is start line number,
and 'ALN2' is end line number in the file. It is also possible to specify how
-many lines to show by using 'NUM'.
+many lines to show by using 'NUM'. Moreover, 'FUNC@SRC' combination is good
+for searching a specific function when several functions share same name.
So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.
LAZY MATCHING
This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)
+FILTER PATTERN
+--------------
+ The filter pattern is a glob matching pattern(s) to filter variables.
+ In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")".
+
+e.g.
+ With --filter "foo* | bar*", perf probe -V shows variables which start with "foo" or "bar".
+ With --filter "!foo* & *bar", perf probe -V shows variables which don't start with "foo" and end with "bar", like "fizzbar". But "foobar" is filtered out.
EXAMPLES
--------
where the information in the perf.data file (which includes buildids)
is sufficient.
+-G name,...::
+--cgroup name,...::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]
print counts using a CSV-style output to make it easy to import directly into
spreadsheets. Columns are separated by the string specified in SEP.
+-G name::
+--cgroup name::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
EXAMPLES
--------
endif
# The default target of this Makefile is...
-all::
+all:
ifneq ($(OUTPUT),)
# check that the output directory actually exists
$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
endif
-# Define V=1 to have a more verbose compile.
-# Define V=2 to have an even more verbose compile.
-#
-# Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf()
-# or vsnprintf() return -1 instead of number of characters which would
-# have been written to the final string if enough space had been available.
-#
-# Define FREAD_READS_DIRECTORIES if your are on a system which succeeds
-# when attempting to read from an fopen'ed directory.
-#
-# Define NO_OPENSSL environment variable if you do not have OpenSSL.
-# This also implies MOZILLA_SHA1.
-#
-# Define CURLDIR=/foo/bar if your curl header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
-#
-# Define EXPATDIR=/foo/bar if your expat header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
-#
-# Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent.
-#
-# Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks
-# d_type in struct dirent (latest Cygwin -- will be fixed soonish).
-#
-# Define NO_C99_FORMAT if your formatted IO functions (printf/scanf et.al.)
-# do not support the 'size specifiers' introduced by C99, namely ll, hh,
-# j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t).
-# some C compilers supported these specifiers prior to C99 as an extension.
-#
-# Define NO_STRCASESTR if you don't have strcasestr.
-#
-# Define NO_MEMMEM if you don't have memmem.
-#
-# Define NO_STRTOUMAX if you don't have strtoumax in the C library.
-# If your compiler also does not support long long or does not have
-# strtoull, define NO_STRTOULL.
-#
-# Define NO_SETENV if you don't have setenv in the C library.
-#
-# Define NO_UNSETENV if you don't have unsetenv in the C library.
-#
-# Define NO_MKDTEMP if you don't have mkdtemp in the C library.
-#
-# Define NO_SYS_SELECT_H if you don't have sys/select.h.
-#
-# Define NO_SYMLINK_HEAD if you never want .perf/HEAD to be a symbolic link.
-# Enable it on Windows. By default, symrefs are still used.
-#
-# Define NO_SVN_TESTS if you want to skip time-consuming SVN interoperability
-# tests. These tests take up a significant amount of the total test time
-# but are not needed unless you plan to talk to SVN repos.
-#
-# Define NO_FINK if you are building on Darwin/Mac OS X, have Fink
-# installed in /sw, but don't want PERF to link against any libraries
-# installed there. If defined you may specify your own (or Fink's)
-# include directories and library directories by defining CFLAGS
-# and LDFLAGS appropriately.
-#
-# Define NO_DARWIN_PORTS if you are building on Darwin/Mac OS X,
-# have DarwinPorts installed in /opt/local, but don't want PERF to
-# link against any libraries installed there. If defined you may
-# specify your own (or DarwinPort's) include directories and
-# library directories by defining CFLAGS and LDFLAGS appropriately.
-#
-# Define PPC_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for PowerPC.
-#
-# Define ARM_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for ARM.
-#
-# Define MOZILLA_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast
-# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default
-# choice) has very fast version optimized for i586.
-#
-# Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin).
-#
-# Define NEEDS_LIBICONV if linking with libc is not enough (Darwin).
-#
-# Define NEEDS_SOCKET if linking with libc is not enough (SunOS,
-# Patrick Mauritz).
-#
-# Define NO_MMAP if you want to avoid mmap.
-#
-# Define NO_PTHREADS if you do not have or do not want to use Pthreads.
-#
-# Define NO_PREAD if you have a problem with pread() system call (e.g.
-# cygwin.dll before v1.5.22).
-#
-# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is
-# generally faster on your platform than accessing the working directory.
-#
-# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support
-# the executable mode bit, but doesn't really do so.
-#
-# Define NO_IPV6 if you lack IPv6 support and getaddrinfo().
-#
-# Define NO_SOCKADDR_STORAGE if your platform does not have struct
-# sockaddr_storage.
-#
-# Define NO_ICONV if your libc does not properly support iconv.
-#
-# Define OLD_ICONV if your library has an old iconv(), where the second
-# (input buffer pointer) parameter is declared with type (const char **).
-#
-# Define NO_DEFLATE_BOUND if your zlib does not have deflateBound.
-#
-# Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib"
-# that tells runtime paths to dynamic libraries;
-# "-Wl,-rpath=/path/lib" is used instead.
-#
-# Define USE_NSEC below if you want perf to care about sub-second file mtimes
-# and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and
-# it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely
-# randomly break unless your underlying filesystem supports those sub-second
-# times (my ext3 doesn't).
-#
-# Define USE_ST_TIMESPEC if your "struct stat" uses "st_ctimespec" instead of
-# "st_ctim"
-#
-# Define NO_NSEC if your "struct stat" does not have "st_ctim.tv_nsec"
-# available. This automatically turns USE_NSEC off.
-#
-# Define USE_STDEV below if you want perf to care about the underlying device
-# change being considered an inode change from the update-index perspective.
-#
-# Define NO_ST_BLOCKS_IN_STRUCT_STAT if your platform does not have st_blocks
-# field that counts the on-disk footprint in 512-byte blocks.
+# Define V to have a more verbose compile.
#
# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
#
# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
#
-# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's
-# MakeMaker (e.g. using ActiveState under Cygwin).
-#
-# Define NO_PERL if you do not want Perl scripts or libraries at all.
-#
-# Define INTERNAL_QSORT to use Git's implementation of qsort(), which
-# is a simplified version of the merge sort used in glibc. This is
-# recommended if Git triggers O(n^2) behavior in your platform's qsort().
-#
-# Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call
-# your external grep (e.g., if your system lacks grep, if its grep is
-# broken, or spawning external process is slower than built-in grep perf has).
-#
# Define LDFLAGS=-static to build a static binary.
#
# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
-include $(OUTPUT)PERF-VERSION-FILE
-uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not')
-uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not')
-uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not')
-uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not')
-uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not')
-uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not')
+uname_M := $(shell uname -m 2>/dev/null || echo not)
ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-e s/arm.*/arm/ -e s/sa110/arm/ \
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
endif
-# CFLAGS and LDFLAGS are for the users to override from the command line.
-
#
# Include saner warnings here, which can catch bugs:
#
AR = $(CROSS_COMPILE)ar
RM = rm -f
MKDIR = mkdir
-TAR = tar
FIND = find
INSTALL = install
-RPMBUILD = rpmbuild
-PTHREAD_LIBS = -lpthread
# sparse is architecture-neutral, which means that we need to tell it
# explicitly what architecture to check for. Fix this up for yours..
SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
-ifeq ($(V), 2)
- QUIET_STDERR = ">/dev/null"
-else
- QUIET_STDERR = ">/dev/null 2>&1"
-endif
-
-include feature-tests.mak
ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
# Guard against environment variables
BUILTIN_OBJS =
-BUILT_INS =
-COMPAT_CFLAGS =
-COMPAT_OBJS =
LIB_H =
LIB_OBJS =
-SCRIPT_PERL =
+PYRF_OBJS =
SCRIPT_SH =
-TEST_PROGRAMS =
SCRIPT_SH += perf-archive.sh
grep-libs = $(filter -l%,$(1))
strip-libs = $(filter-out -l%,$(1))
+$(OUTPUT)python/perf.so: $(PYRF_OBJS)
+ $(QUIET_GEN)python util/setup.py --quiet build_ext --build-lib='$(OUTPUT)python' \
+ --build-temp='$(OUTPUT)python/temp'
#
# No Perl scripts right now:
#
-# SCRIPT_PERL += perf-add--interactive.perl
-
-SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \
- $(patsubst %.perl,%,$(SCRIPT_PERL))
-
-# Empty...
-EXTRA_PROGRAMS =
-
-# ... and all the rest that could be moved out of bindir to perfexecdir
-PROGRAMS += $(EXTRA_PROGRAMS)
+SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
#
# Single 'perf' binary right now:
#
PROGRAMS += $(OUTPUT)perf
-# List built-in command $C whose implementation cmd_$C() is not in
-# builtin-$C.o but is linked in as part of some other command.
-#
+LANG_BINDINGS =
# what 'all' will build and 'install' will install, in perfexecdir
ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
# what 'all' will build but not install in perfexecdir
-OTHER_PROGRAMS = $(OUTPUT)perf$X
+OTHER_PROGRAMS = $(OUTPUT)perf
# Set paths to tools early so that they can be used for version tests.
ifndef SHELL_PATH
LIB_H += util/include/asm/dwarf2.h
LIB_H += util/include/asm/cpufeature.h
LIB_H += perf.h
+LIB_H += util/annotate.h
LIB_H += util/cache.h
LIB_H += util/callchain.h
LIB_H += util/build-id.h
LIB_H += util/debugfs.h
LIB_H += util/event.h
LIB_H += util/evsel.h
+LIB_H += util/evlist.h
LIB_H += util/exec_cmd.h
LIB_H += util/types.h
LIB_H += util/levenshtein.h
LIB_H += util/session.h
LIB_H += util/strbuf.h
LIB_H += util/strlist.h
+LIB_H += util/strfilter.h
LIB_H += util/svghelper.h
LIB_H += util/run-command.h
LIB_H += util/sigchain.h
LIB_H += util/sort.h
LIB_H += util/hist.h
LIB_H += util/thread.h
+LIB_H += util/thread_map.h
LIB_H += util/trace-event.h
LIB_H += util/probe-finder.h
LIB_H += util/probe-event.h
LIB_H += util/pstack.h
LIB_H += util/cpumap.h
+LIB_H += util/top.h
LIB_H += $(ARCH_INCLUDE)
+LIB_H += util/cgroup.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
+LIB_OBJS += $(OUTPUT)util/annotate.o
LIB_OBJS += $(OUTPUT)util/build-id.o
LIB_OBJS += $(OUTPUT)util/config.o
LIB_OBJS += $(OUTPUT)util/ctype.o
LIB_OBJS += $(OUTPUT)util/debugfs.o
LIB_OBJS += $(OUTPUT)util/environment.o
LIB_OBJS += $(OUTPUT)util/event.o
+LIB_OBJS += $(OUTPUT)util/evlist.o
LIB_OBJS += $(OUTPUT)util/evsel.o
LIB_OBJS += $(OUTPUT)util/exec_cmd.o
LIB_OBJS += $(OUTPUT)util/help.o
LIB_OBJS += $(OUTPUT)util/strbuf.o
LIB_OBJS += $(OUTPUT)util/string.o
LIB_OBJS += $(OUTPUT)util/strlist.o
+LIB_OBJS += $(OUTPUT)util/strfilter.o
+LIB_OBJS += $(OUTPUT)util/top.o
LIB_OBJS += $(OUTPUT)util/usage.o
LIB_OBJS += $(OUTPUT)util/wrapper.o
LIB_OBJS += $(OUTPUT)util/sigchain.o
LIB_OBJS += $(OUTPUT)util/pstack.o
LIB_OBJS += $(OUTPUT)util/session.o
LIB_OBJS += $(OUTPUT)util/thread.o
+LIB_OBJS += $(OUTPUT)util/thread_map.o
LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
LIB_OBJS += $(OUTPUT)util/trace-event-read.o
LIB_OBJS += $(OUTPUT)util/trace-event-info.o
LIB_OBJS += $(OUTPUT)util/util.o
LIB_OBJS += $(OUTPUT)util/xyarray.o
LIB_OBJS += $(OUTPUT)util/cpumap.o
+LIB_OBJS += $(OUTPUT)util/cgroup.o
BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
PERFLIBS = $(LIB_FILE)
+# Files needed for the python binding, perf.so
+# pyrf is just an internal name needed for all those wrappers.
+# This has to be in sync with what is in the 'sources' variable in
+# tools/perf/util/setup.py
+
+PYRF_OBJS += $(OUTPUT)util/cpumap.o
+PYRF_OBJS += $(OUTPUT)util/ctype.o
+PYRF_OBJS += $(OUTPUT)util/evlist.o
+PYRF_OBJS += $(OUTPUT)util/evsel.o
+PYRF_OBJS += $(OUTPUT)util/python.o
+PYRF_OBJS += $(OUTPUT)util/thread_map.o
+PYRF_OBJS += $(OUTPUT)util/util.o
+PYRF_OBJS += $(OUTPUT)util/xyarray.o
+
#
# Platform specific tweaks
#
-include arch/$(ARCH)/Makefile
-ifeq ($(uname_S),Darwin)
- ifndef NO_FINK
- ifeq ($(shell test -d /sw/lib && echo y),y)
- BASIC_CFLAGS += -I/sw/include
- BASIC_LDFLAGS += -L/sw/lib
- endif
- endif
- ifndef NO_DARWIN_PORTS
- ifeq ($(shell test -d /opt/local/lib && echo y),y)
- BASIC_CFLAGS += -I/opt/local/include
- BASIC_LDFLAGS += -L/opt/local/lib
- endif
- endif
- PTHREAD_LIBS =
-endif
-
ifneq ($(OUTPUT),)
BASIC_CFLAGS += -I$(OUTPUT)
endif
LIB_OBJS += $(OUTPUT)util/ui/browsers/annotate.o
LIB_OBJS += $(OUTPUT)util/ui/browsers/hists.o
LIB_OBJS += $(OUTPUT)util/ui/browsers/map.o
+ LIB_OBJS += $(OUTPUT)util/ui/browsers/top.o
LIB_OBJS += $(OUTPUT)util/ui/helpline.o
LIB_OBJS += $(OUTPUT)util/ui/progress.o
LIB_OBJS += $(OUTPUT)util/ui/util.o
LIB_H += util/ui/libslang.h
LIB_H += util/ui/progress.h
LIB_H += util/ui/util.h
+ LIB_H += util/ui/ui.h
endif
endif
PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
+ msg := $(warning No Python.h found, install python-dev[el] to have python support in 'perf script' and to build the python bindings)
BASIC_CFLAGS += -DNO_LIBPYTHON
else
ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
EXTLIBS += $(PYTHON_EMBED_LIBADD)
LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
+ LANG_BINDINGS += $(OUTPUT)python/perf.so
endif
endif
endif
endif
-ifndef CC_LD_DYNPATH
- ifdef NO_R_TO_GCC_LINKER
- # Some gcc does not accept and pass -R to the linker to specify
- # the runtime dynamic library path.
- CC_LD_DYNPATH = -Wl,-rpath,
- else
- CC_LD_DYNPATH = -R
- endif
-endif
-
-ifdef NEEDS_SOCKET
- EXTLIBS += -lsocket
-endif
-ifdef NEEDS_NSL
- EXTLIBS += -lnsl
-endif
-ifdef NO_D_TYPE_IN_DIRENT
- BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT
-endif
-ifdef NO_D_INO_IN_DIRENT
- BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT
-endif
-ifdef NO_ST_BLOCKS_IN_STRUCT_STAT
- BASIC_CFLAGS += -DNO_ST_BLOCKS_IN_STRUCT_STAT
-endif
-ifdef USE_NSEC
- BASIC_CFLAGS += -DUSE_NSEC
-endif
-ifdef USE_ST_TIMESPEC
- BASIC_CFLAGS += -DUSE_ST_TIMESPEC
-endif
-ifdef NO_NSEC
- BASIC_CFLAGS += -DNO_NSEC
-endif
-ifdef NO_C99_FORMAT
- BASIC_CFLAGS += -DNO_C99_FORMAT
-endif
-ifdef SNPRINTF_RETURNS_BOGUS
- COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS
- COMPAT_OBJS += $(OUTPUT)compat/snprintf.o
-endif
-ifdef FREAD_READS_DIRECTORIES
- COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES
- COMPAT_OBJS += $(OUTPUT)compat/fopen.o
-endif
-ifdef NO_SYMLINK_HEAD
- BASIC_CFLAGS += -DNO_SYMLINK_HEAD
-endif
-ifdef NO_STRCASESTR
- COMPAT_CFLAGS += -DNO_STRCASESTR
- COMPAT_OBJS += $(OUTPUT)compat/strcasestr.o
-endif
-ifdef NO_STRTOUMAX
- COMPAT_CFLAGS += -DNO_STRTOUMAX
- COMPAT_OBJS += $(OUTPUT)compat/strtoumax.o
-endif
-ifdef NO_STRTOULL
- COMPAT_CFLAGS += -DNO_STRTOULL
-endif
-ifdef NO_SETENV
- COMPAT_CFLAGS += -DNO_SETENV
- COMPAT_OBJS += $(OUTPUT)compat/setenv.o
-endif
-ifdef NO_MKDTEMP
- COMPAT_CFLAGS += -DNO_MKDTEMP
- COMPAT_OBJS += $(OUTPUT)compat/mkdtemp.o
-endif
-ifdef NO_UNSETENV
- COMPAT_CFLAGS += -DNO_UNSETENV
- COMPAT_OBJS += $(OUTPUT)compat/unsetenv.o
-endif
-ifdef NO_SYS_SELECT_H
- BASIC_CFLAGS += -DNO_SYS_SELECT_H
-endif
-ifdef NO_MMAP
- COMPAT_CFLAGS += -DNO_MMAP
- COMPAT_OBJS += $(OUTPUT)compat/mmap.o
-else
- ifdef USE_WIN32_MMAP
- COMPAT_CFLAGS += -DUSE_WIN32_MMAP
- COMPAT_OBJS += $(OUTPUT)compat/win32mmap.o
- endif
-endif
-ifdef NO_PREAD
- COMPAT_CFLAGS += -DNO_PREAD
- COMPAT_OBJS += $(OUTPUT)compat/pread.o
-endif
-ifdef NO_FAST_WORKING_DIRECTORY
- BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY
-endif
-ifdef NO_TRUSTABLE_FILEMODE
- BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE
-endif
-ifdef NO_IPV6
- BASIC_CFLAGS += -DNO_IPV6
-endif
-ifdef NO_UINTMAX_T
- BASIC_CFLAGS += -Duintmax_t=uint32_t
-endif
-ifdef NO_SOCKADDR_STORAGE
-ifdef NO_IPV6
- BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in
-else
- BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6
-endif
-endif
-ifdef NO_INET_NTOP
- LIB_OBJS += $(OUTPUT)compat/inet_ntop.o
-endif
-ifdef NO_INET_PTON
- LIB_OBJS += $(OUTPUT)compat/inet_pton.o
-endif
-
-ifdef NO_ICONV
- BASIC_CFLAGS += -DNO_ICONV
-endif
-
-ifdef OLD_ICONV
- BASIC_CFLAGS += -DOLD_ICONV
-endif
-
-ifdef NO_DEFLATE_BOUND
- BASIC_CFLAGS += -DNO_DEFLATE_BOUND
-endif
-
-ifdef PPC_SHA1
- SHA1_HEADER = "ppc/sha1.h"
- LIB_OBJS += $(OUTPUT)ppc/sha1.o ppc/sha1ppc.o
-else
-ifdef ARM_SHA1
- SHA1_HEADER = "arm/sha1.h"
- LIB_OBJS += $(OUTPUT)arm/sha1.o $(OUTPUT)arm/sha1_arm.o
-else
-ifdef MOZILLA_SHA1
- SHA1_HEADER = "mozilla-sha1/sha1.h"
- LIB_OBJS += $(OUTPUT)mozilla-sha1/sha1.o
-else
- SHA1_HEADER = <openssl/sha.h>
- EXTLIBS += $(LIB_4_CRYPTO)
-endif
-endif
-endif
-ifdef NO_PERL_MAKEMAKER
- export NO_PERL_MAKEMAKER
-endif
-ifdef NO_HSTRERROR
- COMPAT_CFLAGS += -DNO_HSTRERROR
- COMPAT_OBJS += $(OUTPUT)compat/hstrerror.o
-endif
-ifdef NO_MEMMEM
- COMPAT_CFLAGS += -DNO_MEMMEM
- COMPAT_OBJS += $(OUTPUT)compat/memmem.o
-endif
-ifdef INTERNAL_QSORT
- COMPAT_CFLAGS += -DINTERNAL_QSORT
- COMPAT_OBJS += $(OUTPUT)compat/qsort.o
-endif
-ifdef RUNTIME_PREFIX
- COMPAT_CFLAGS += -DRUNTIME_PREFIX
-endif
-
-ifdef DIR_HAS_BSD_GROUP_SEMANTICS
- COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS
-endif
-ifdef NO_EXTERNAL_GREP
- BASIC_CFLAGS += -DNO_EXTERNAL_GREP
-endif
-
-ifeq ($(PERL_PATH),)
-NO_PERL=NoThanks
-endif
-
-QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir
-QUIET_SUBDIR1 =
-
-ifneq ($(findstring $(MAKEFLAGS),w),w)
-PRINT_DIR = --no-print-directory
-else # "make -w"
-NO_SUBDIR = :
-endif
-
ifneq ($(findstring $(MAKEFLAGS),s),s)
ifndef V
QUIET_CC = @echo ' ' CC $@;
QUIET_AR = @echo ' ' AR $@;
QUIET_LINK = @echo ' ' LINK $@;
QUIET_MKDIR = @echo ' ' MKDIR $@;
- QUIET_BUILT_IN = @echo ' ' BUILTIN $@;
QUIET_GEN = @echo ' ' GEN $@;
- QUIET_SUBDIR0 = +@subdir=
- QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \
- $(MAKE) $(PRINT_DIR) -C $$subdir
- export V
- export QUIET_GEN
- export QUIET_BUILT_IN
endif
endif
# Shell quote (do not use $(call) to accommodate ancient setups);
-SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER))
ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
prefix_SQ = $(subst ','\'',$(prefix))
SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
-PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH))
LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS)
-BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \
- $(COMPAT_CFLAGS)
-LIB_OBJS += $(COMPAT_OBJS)
-
ALL_CFLAGS += $(BASIC_CFLAGS)
ALL_CFLAGS += $(ARCH_CFLAGS)
ALL_LDFLAGS += $(BASIC_LDFLAGS)
-export TAR INSTALL DESTDIR SHELL_PATH
+export INSTALL SHELL_PATH
### Build rules
SHELL = $(SHELL_PATH)
-all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS
-ifneq (,$X)
- $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
-endif
-
-all::
+all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
please_set_SHELL_PATH_to_a_more_modern_shell:
@$$(:)
shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
-strip: $(PROGRAMS) $(OUTPUT)perf$X
- $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf$X
+strip: $(PROGRAMS) $(OUTPUT)perf
+ $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf
$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \
'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
-$(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
+$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
$(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \
$(BUILTIN_OBJS) $(LIBS) -o $@
'-DPERF_MAN_PATH="$(mandir_SQ)"' \
'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
-$(BUILT_INS): $(OUTPUT)perf$X
- $(QUIET_BUILT_IN)$(RM) $@ && \
- ln perf$X $@ 2>/dev/null || \
- ln -s perf$X $@ 2>/dev/null || \
- cp perf$X $@
-
$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
-$(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
- $(QUIET_GEN)$(RM) $(OUTPUT)$@ $(OUTPUT)$@+ && \
- sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
- -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \
- -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \
- -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
- -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
- $@.sh > $(OUTPUT)$@+ && \
- chmod +x $(OUTPUT)$@+ && \
- mv $(OUTPUT)$@+ $(OUTPUT)$@
-
-configure: configure.ac
- $(QUIET_GEN)$(RM) $@ $<+ && \
- sed -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
- $< > $<+ && \
- autoconf -o $@ $<+ && \
- $(RM) $<+
+$(SCRIPTS) : % : %.sh
+ $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
# These can record PERF_VERSION
$(OUTPUT)perf.o perf.spec \
- $(patsubst %.sh,%,$(SCRIPT_SH)) \
- $(patsubst %.perl,%,$(SCRIPT_PERL)) \
+ $(SCRIPTS) \
: $(OUTPUT)PERF-VERSION-FILE
$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
'-DPREFIX="$(prefix_SQ)"' \
$<
-$(OUTPUT)builtin-init-db.o: builtin-init-db.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
-
$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
$(OUTPUT)util/ui/browsers/annotate.o: util/ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+$(OUTPUT)util/ui/browsers/top.o: util/ui/browsers/top.c $(OUTPUT)PERF-CFLAGS
+ $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
$(OUTPUT)util/ui/browsers/hists.o: util/ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
-$(OUTPUT)perf-%$X: %.o $(PERFLIBS)
+$(OUTPUT)perf-%: %.o $(PERFLIBS)
$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
-$(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
-builtin-revert.o wt-status.o: wt-status.h
+$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
# we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
# we depend the various files onto their directories.
$(LIB_FILE): $(LIB_OBJS)
$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
+help:
+ @echo 'Perf make targets:'
+ @echo ' doc - make *all* documentation (see below)'
+ @echo ' man - make manpage documentation (access with man <foo>)'
+ @echo ' html - make html documentation'
+ @echo ' info - make GNU info documentation (access with info <foo>)'
+ @echo ' pdf - make pdf documentation'
+ @echo ' TAGS - use etags to make tag information for source browsing'
+ @echo ' tags - use ctags to make tag information for source browsing'
+ @echo ' cscope - use cscope to make interactive browsing database'
+ @echo ''
+ @echo 'Perf install targets:'
+ @echo ' NOTE: documentation build requires asciidoc, xmlto packages to be installed'
+ @echo ' HINT: use "make prefix=<path> <install target>" to install to a particular'
+ @echo ' path like make prefix=/usr/local install install-doc'
+ @echo ' install - install compiled binaries'
+ @echo ' install-doc - install *all* documentation'
+ @echo ' install-man - install manpage documentation'
+ @echo ' install-html - install html documentation'
+ @echo ' install-info - install GNU info documentation'
+ @echo ' install-pdf - install pdf documentation'
+ @echo ''
+ @echo ' quick-install-doc - alias for quick-install-man'
+ @echo ' quick-install-man - install the documentation quickly'
+ @echo ' quick-install-html - install the html documentation quickly'
+ @echo ''
+ @echo 'Perf maintainer targets:'
+ @echo ' distclean - alias to clean'
+ @echo ' clean - clean all binary objects and build output'
+
doc:
$(MAKE) -C Documentation all
echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
fi
-# We need to apply sq twice, once to protect from the shell
-# that runs $(OUTPUT)PERF-BUILD-OPTIONS, and then again to protect it
-# and the first level quoting from the shell that runs "echo".
-$(OUTPUT)PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
- @echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@
- @echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
- @echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
- @echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@
-
### Testing rules
-#
-# None right now:
-#
-# TEST_PROGRAMS += test-something$X
-
-all:: $(TEST_PROGRAMS)
-
# GNU make supports exporting all variables by "export" without parameters.
# However, the environment gets quite big, and some programs have problems
# with that.
-export NO_SVN_TESTS
-
check: $(OUTPUT)common-cmds.h
if sparse; \
then \
sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
done; \
else \
- echo 2>&1 "Did you mean 'make test'?"; \
exit 1; \
fi
-remove-dashes:
- ./fixup-builtins $(BUILT_INS) $(PROGRAMS) $(SCRIPTS)
-
### Installation rules
-ifneq ($(filter /%,$(firstword $(template_dir))),)
-template_instdir = $(template_dir)
-else
-template_instdir = $(prefix)/$(template_dir)
-endif
-export template_instdir
-
ifneq ($(filter /%,$(firstword $(perfexecdir))),)
perfexec_instdir = $(perfexecdir)
else
perfexec_instdir = $(prefix)/$(perfexecdir)
endif
perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
-export perfexec_instdir
install: all
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
- $(INSTALL) $(OUTPUT)perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
+ $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
-ifdef BUILT_INS
- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
- $(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-ifneq (,$X)
- $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) $(OUTPUT)perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
-endif
-endif
-
install-doc:
$(MAKE) -C Documentation install
quick-install-html:
$(MAKE) -C Documentation quick-install-html
-
-### Maintainer's dist rules
-#
-# None right now
-#
-#
-# perf.spec: perf.spec.in
-# sed -e 's/@@VERSION@@/$(PERF_VERSION)/g' < $< > $@+
-# mv $@+ $@
-#
-# PERF_TARNAME=perf-$(PERF_VERSION)
-# dist: perf.spec perf-archive$(X) configure
-# ./perf-archive --format=tar \
-# --prefix=$(PERF_TARNAME)/ HEAD^{tree} > $(PERF_TARNAME).tar
-# @mkdir -p $(PERF_TARNAME)
-# @cp perf.spec configure $(PERF_TARNAME)
-# @echo $(PERF_VERSION) > $(PERF_TARNAME)/version
-# $(TAR) rf $(PERF_TARNAME).tar \
-# $(PERF_TARNAME)/perf.spec \
-# $(PERF_TARNAME)/configure \
-# $(PERF_TARNAME)/version
-# @$(RM) -r $(PERF_TARNAME)
-# gzip -f -9 $(PERF_TARNAME).tar
-#
-# htmldocs = perf-htmldocs-$(PERF_VERSION)
-# manpages = perf-manpages-$(PERF_VERSION)
-# dist-doc:
-# $(RM) -r .doc-tmp-dir
-# mkdir .doc-tmp-dir
-# $(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc
-# cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar .
-# gzip -n -9 -f $(htmldocs).tar
-# :
-# $(RM) -r .doc-tmp-dir
-# mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7
-# $(MAKE) -C Documentation DESTDIR=./ \
-# man1dir=../.doc-tmp-dir/man1 \
-# man5dir=../.doc-tmp-dir/man5 \
-# man7dir=../.doc-tmp-dir/man7 \
-# install
-# cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar .
-# gzip -n -9 -f $(manpages).tar
-# $(RM) -r .doc-tmp-dir
-#
-# rpm: dist
-# $(RPMBUILD) -ta $(PERF_TARNAME).tar.gz
-
### Cleaning rules
-distclean: clean
-# $(RM) configure
-
clean:
- $(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE)
- $(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X
- $(RM) $(TEST_PROGRAMS)
+ $(RM) $(OUTPUT){*.o,*/*.o,*/*/*.o,*/*/*/*.o,$(LIB_FILE),perf-archive}
+ $(RM) $(ALL_PROGRAMS) perf
$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
- $(RM) -r autom4te.cache
- $(RM) config.log config.mak.autogen config.mak.append config.status config.cache
- $(RM) -r $(PERF_TARNAME) .doc-tmp-dir
- $(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz
- $(RM) $(htmldocs).tar.gz $(manpages).tar.gz
$(MAKE) -C Documentation/ clean
- $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-BUILD-OPTIONS
+ $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
+ @python util/setup.py clean --build-lib='$(OUTPUT)python' \
+ --build-temp='$(OUTPUT)python/temp'
.PHONY: all install clean strip
.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
-.PHONY: .FORCE-PERF-BUILD-OPTIONS
-
-### Make sure built-ins do not have dups and listed in perf.c
-#
-check-builtins::
- ./check-builtins.sh
-
-### Test suite coverage testing
-#
-# None right now
-#
-# .PHONY: coverage coverage-clean coverage-build coverage-report
-#
-# coverage:
-# $(MAKE) coverage-build
-# $(MAKE) coverage-report
-#
-# coverage-clean:
-# rm -f *.gcda *.gcno
-#
-# COVERAGE_CFLAGS = $(CFLAGS) -O0 -ftest-coverage -fprofile-arcs
-# COVERAGE_LDFLAGS = $(CFLAGS) -O0 -lgcov
-#
-# coverage-build: coverage-clean
-# $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" all
-# $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" \
-# -j1 test
-#
-# coverage-report:
-# gcov -b *.c */*.c
-# grep '^function.*called 0 ' *.c.gcov */*.c.gcov \
-# | sed -e 's/\([^:]*\)\.gcov: *function \([^ ]*\) called.*/\1: \2/' \
-# | tee coverage-untested-functions
* discarding returned value of read(), write()
* causes error in building environment for perf
*/
- int ret, wait_stat;
+ int __used ret, wait_stat;
pid_t pid, retpid;
argc = parse_options(argc, argv, options,
#include "util/util.h"
+#include "util/util.h"
#include "util/color.h"
#include <linux/list.h>
#include "util/cache.h"
#include "perf.h"
#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/annotate.h"
#include "util/event.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
static const char *sym_hist_filter;
-static int hists__add_entry(struct hists *self, struct addr_location *al)
+static int perf_evlist__add_sample(struct perf_evlist *evlist,
+ struct perf_sample *sample,
+ struct addr_location *al)
{
+ struct perf_evsel *evsel;
struct hist_entry *he;
+ int ret;
if (sym_hist_filter != NULL &&
(al->sym == NULL || strcmp(sym_hist_filter, al->sym->name) != 0)) {
return 0;
}
- he = __hists__add_entry(self, al, NULL, 1);
+ evsel = perf_evlist__id2evsel(evlist, sample->id);
+ if (evsel == NULL) {
+ /*
+ * FIXME: Propagate this back, but at least we're in a builtin,
+ * where exit() is allowed. ;-)
+ */
+ ui__warning("Invalid %s file, contains samples with id not in "
+ "its header!\n", input_name);
+ exit_browser(0);
+ exit(1);
+ }
+
+ he = __hists__add_entry(&evsel->hists, al, NULL, 1);
if (he == NULL)
return -ENOMEM;
- return hist_entry__inc_addr_samples(he, al->addr);
+ ret = 0;
+ if (he->ms.sym != NULL) {
+ struct annotation *notes = symbol__annotation(he->ms.sym);
+ if (notes->src == NULL &&
+ symbol__alloc_hist(he->ms.sym, evlist->nr_entries) < 0)
+ return -ENOMEM;
+
+ ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+ }
+
+ evsel->hists.stats.total_period += sample->period;
+ hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+ return ret;
}
-static int process_sample_event(event_t *event, struct sample_data *sample,
+static int process_sample_event(union perf_event *event,
+ struct perf_sample *sample,
struct perf_session *session)
{
struct addr_location al;
- if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
+ if (perf_event__preprocess_sample(event, session, &al, sample,
+ symbol__annotate_init) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
- if (!al.filtered && hists__add_entry(&session->hists, &al)) {
+ if (!al.filtered && perf_evlist__add_sample(session->evlist, sample, &al)) {
pr_warning("problem incrementing symbol count, "
"skipping event\n");
return -1;
return 0;
}
-static int objdump_line__print(struct objdump_line *self,
- struct list_head *head,
- struct hist_entry *he, u64 len)
-{
- struct symbol *sym = he->ms.sym;
- static const char *prev_line;
- static const char *prev_color;
-
- if (self->offset != -1) {
- const char *path = NULL;
- unsigned int hits = 0;
- double percent = 0.0;
- const char *color;
- struct sym_priv *priv = symbol__priv(sym);
- struct sym_ext *sym_ext = priv->ext;
- struct sym_hist *h = priv->hist;
- s64 offset = self->offset;
- struct objdump_line *next = objdump__get_next_ip_line(head, self);
-
- while (offset < (s64)len &&
- (next == NULL || offset < next->offset)) {
- if (sym_ext) {
- if (path == NULL)
- path = sym_ext[offset].path;
- percent += sym_ext[offset].percent;
- } else
- hits += h->ip[offset];
-
- ++offset;
- }
-
- if (sym_ext == NULL && h->sum)
- percent = 100.0 * hits / h->sum;
-
- color = get_percent_color(percent);
-
- /*
- * Also color the filename and line if needed, with
- * the same color than the percentage. Don't print it
- * twice for close colored ip with the same filename:line
- */
- if (path) {
- if (!prev_line || strcmp(prev_line, path)
- || color != prev_color) {
- color_fprintf(stdout, color, " %s", path);
- prev_line = path;
- prev_color = color;
- }
- }
-
- color_fprintf(stdout, color, " %7.2f", percent);
- printf(" : ");
- color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", self->line);
- } else {
- if (!*self->line)
- printf(" :\n");
- else
- printf(" : %s\n", self->line);
- }
-
- return 0;
-}
-
-static struct rb_root root_sym_ext;
-
-static void insert_source_line(struct sym_ext *sym_ext)
-{
- struct sym_ext *iter;
- struct rb_node **p = &root_sym_ext.rb_node;
- struct rb_node *parent = NULL;
-
- while (*p != NULL) {
- parent = *p;
- iter = rb_entry(parent, struct sym_ext, node);
-
- if (sym_ext->percent > iter->percent)
- p = &(*p)->rb_left;
- else
- p = &(*p)->rb_right;
- }
-
- rb_link_node(&sym_ext->node, parent, p);
- rb_insert_color(&sym_ext->node, &root_sym_ext);
-}
-
-static void free_source_line(struct hist_entry *he, int len)
-{
- struct sym_priv *priv = symbol__priv(he->ms.sym);
- struct sym_ext *sym_ext = priv->ext;
- int i;
-
- if (!sym_ext)
- return;
-
- for (i = 0; i < len; i++)
- free(sym_ext[i].path);
- free(sym_ext);
-
- priv->ext = NULL;
- root_sym_ext = RB_ROOT;
-}
-
-/* Get the filename:line for the colored entries */
-static void
-get_source_line(struct hist_entry *he, int len, const char *filename)
-{
- struct symbol *sym = he->ms.sym;
- u64 start;
- int i;
- char cmd[PATH_MAX * 2];
- struct sym_ext *sym_ext;
- struct sym_priv *priv = symbol__priv(sym);
- struct sym_hist *h = priv->hist;
-
- if (!h->sum)
- return;
-
- sym_ext = priv->ext = calloc(len, sizeof(struct sym_ext));
- if (!priv->ext)
- return;
-
- start = he->ms.map->unmap_ip(he->ms.map, sym->start);
-
- for (i = 0; i < len; i++) {
- char *path = NULL;
- size_t line_len;
- u64 offset;
- FILE *fp;
-
- sym_ext[i].percent = 100.0 * h->ip[i] / h->sum;
- if (sym_ext[i].percent <= 0.5)
- continue;
-
- offset = start + i;
- sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
- fp = popen(cmd, "r");
- if (!fp)
- continue;
-
- if (getline(&path, &line_len, fp) < 0 || !line_len)
- goto next;
-
- sym_ext[i].path = malloc(sizeof(char) * line_len + 1);
- if (!sym_ext[i].path)
- goto next;
-
- strcpy(sym_ext[i].path, path);
- insert_source_line(&sym_ext[i]);
-
- next:
- pclose(fp);
- }
-}
-
-static void print_summary(const char *filename)
-{
- struct sym_ext *sym_ext;
- struct rb_node *node;
-
- printf("\nSorted summary for file %s\n", filename);
- printf("----------------------------------------------\n\n");
-
- if (RB_EMPTY_ROOT(&root_sym_ext)) {
- printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
- return;
- }
-
- node = rb_first(&root_sym_ext);
- while (node) {
- double percent;
- const char *color;
- char *path;
-
- sym_ext = rb_entry(node, struct sym_ext, node);
- percent = sym_ext->percent;
- color = get_percent_color(percent);
- path = sym_ext->path;
-
- color_fprintf(stdout, color, " %7.2f %s", percent, path);
- node = rb_next(node);
- }
-}
-
-static void hist_entry__print_hits(struct hist_entry *self)
-{
- struct symbol *sym = self->ms.sym;
- struct sym_priv *priv = symbol__priv(sym);
- struct sym_hist *h = priv->hist;
- u64 len = sym->end - sym->start, offset;
-
- for (offset = 0; offset < len; ++offset)
- if (h->ip[offset] != 0)
- printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
- sym->start + offset, h->ip[offset]);
- printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
-}
-
-static int hist_entry__tty_annotate(struct hist_entry *he)
+static int hist_entry__tty_annotate(struct hist_entry *he, int evidx)
{
- struct map *map = he->ms.map;
- struct dso *dso = map->dso;
- struct symbol *sym = he->ms.sym;
- const char *filename = dso->long_name, *d_filename;
- u64 len;
- LIST_HEAD(head);
- struct objdump_line *pos, *n;
-
- if (hist_entry__annotate(he, &head, 0) < 0)
- return -1;
-
- if (full_paths)
- d_filename = filename;
- else
- d_filename = basename(filename);
-
- len = sym->end - sym->start;
-
- if (print_line) {
- get_source_line(he, len, filename);
- print_summary(filename);
- }
-
- printf("\n\n------------------------------------------------\n");
- printf(" Percent | Source code & Disassembly of %s\n", d_filename);
- printf("------------------------------------------------\n");
-
- if (verbose)
- hist_entry__print_hits(he);
-
- list_for_each_entry_safe(pos, n, &head, node) {
- objdump_line__print(pos, &head, he, len);
- list_del(&pos->node);
- objdump_line__free(pos);
- }
-
- if (print_line)
- free_source_line(he, len);
-
- return 0;
+ return symbol__tty_annotate(he->ms.sym, he->ms.map, evidx,
+ print_line, full_paths, 0, 0);
}
-static void hists__find_annotations(struct hists *self)
+static void hists__find_annotations(struct hists *self, int evidx)
{
struct rb_node *nd = rb_first(&self->entries), *next;
int key = KEY_RIGHT;
while (nd) {
struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
- struct sym_priv *priv;
+ struct annotation *notes;
if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
goto find_next;
- priv = symbol__priv(he->ms.sym);
- if (priv->hist == NULL) {
+ notes = symbol__annotation(he->ms.sym);
+ if (notes->src == NULL) {
find_next:
if (key == KEY_LEFT)
nd = rb_prev(nd);
}
if (use_browser > 0) {
- key = hist_entry__tui_annotate(he);
+ key = hist_entry__tui_annotate(he, evidx);
switch (key) {
case KEY_RIGHT:
next = rb_next(nd);
if (next != NULL)
nd = next;
} else {
- hist_entry__tty_annotate(he);
+ hist_entry__tty_annotate(he, evidx);
nd = rb_next(nd);
/*
* Since we have a hist_entry per IP for the same
- * symbol, free he->ms.sym->hist to signal we already
+ * symbol, free he->ms.sym->src to signal we already
* processed this symbol.
*/
- free(priv->hist);
- priv->hist = NULL;
+ free(notes->src);
+ notes->src = NULL;
}
}
}
static struct perf_event_ops event_ops = {
.sample = process_sample_event,
- .mmap = event__process_mmap,
- .comm = event__process_comm,
- .fork = event__process_task,
+ .mmap = perf_event__process_mmap,
+ .comm = perf_event__process_comm,
+ .fork = perf_event__process_task,
.ordered_samples = true,
.ordering_requires_timestamps = true,
};
{
int ret;
struct perf_session *session;
+ struct perf_evsel *pos;
+ u64 total_nr_samples;
session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
if (session == NULL)
if (verbose > 2)
perf_session__fprintf_dsos(session, stdout);
- hists__collapse_resort(&session->hists);
- hists__output_resort(&session->hists);
- hists__find_annotations(&session->hists);
-out_delete:
- perf_session__delete(session);
+ total_nr_samples = 0;
+ list_for_each_entry(pos, &session->evlist->entries, node) {
+ struct hists *hists = &pos->hists;
+ u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+ if (nr_samples > 0) {
+ total_nr_samples += nr_samples;
+ hists__collapse_resort(hists);
+ hists__output_resort(hists);
+ hists__find_annotations(hists, pos->idx);
+ }
+ }
+ if (total_nr_samples == 0) {
+ ui__warning("The %s file has no samples!\n", input_name);
+ goto out_delete;
+ }
+out_delete:
+ /*
+ * Speed up the exit process, for large files this can
+ * take quite a while.
+ *
+ * XXX Enable this when using valgrind or if we ever
+ * librarize this command.
+ *
+ * Also experiment with obstacks to see how much speed
+ * up we'll get here.
+ *
+ * perf_session__delete(session);
+ */
return ret;
}
else if (use_tui)
use_browser = 1;
- setup_browser();
+ setup_browser(true);
- symbol_conf.priv_size = sizeof(struct sym_priv);
+ symbol_conf.priv_size = sizeof(struct annotation);
symbol_conf.try_vmlinux_path = true;
if (symbol__init() < 0)
return -ENOMEM;
}
-static int diff__process_sample_event(event_t *event,
- struct sample_data *sample,
+static int diff__process_sample_event(union perf_event *event,
+ struct perf_sample *sample,
struct perf_session *session)
{
struct addr_location al;
- if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
+ if (perf_event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
event->header.type);
return -1;
static struct perf_event_ops event_ops = {
.sample = diff__process_sample_event,
- .mmap = event__process_mmap,
- .comm = event__process_comm,
- .exit = event__process_task,
- .fork = event__process_task,
- .lost = event__process_lost,
+ .mmap = perf_event__process_mmap,
+ .comm = perf_event__process_comm,
+ .exit = perf_event__process_task,
+ .fork = perf_event__process_task,
+ .lost = perf_event__process_lost,
.ordered_samples = true,
.ordering_requires_timestamps = true,
};
static char const *input_name = "-";
static bool inject_build_ids;
-static int event__repipe_synth(event_t *event,
- struct perf_session *session __used)
+static int perf_event__repipe_synth(union perf_event *event,
+ struct perf_session *session __used)
{
uint32_t size;
void *buf = event;
return 0;
}
-static int event__repipe(event_t *event, struct sample_data *sample __used,
- struct perf_session *session)
+static int perf_event__repipe(union perf_event *event,
+ struct perf_sample *sample __used,
+ struct perf_session *session)
{
- return event__repipe_synth(event, session);
+ return perf_event__repipe_synth(event, session);
}
-static int event__repipe_mmap(event_t *self, struct sample_data *sample,
- struct perf_session *session)
+static int perf_event__repipe_mmap(union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_session *session)
{
int err;
- err = event__process_mmap(self, sample, session);
- event__repipe(self, sample, session);
+ err = perf_event__process_mmap(event, sample, session);
+ perf_event__repipe(event, sample, session);
return err;
}
-static int event__repipe_task(event_t *self, struct sample_data *sample,
- struct perf_session *session)
+static int perf_event__repipe_task(union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_session *session)
{
int err;
- err = event__process_task(self, sample, session);
- event__repipe(self, sample, session);
+ err = perf_event__process_task(event, sample, session);
+ perf_event__repipe(event, sample, session);
return err;
}
-static int event__repipe_tracing_data(event_t *self,
- struct perf_session *session)
+static int perf_event__repipe_tracing_data(union perf_event *event,
+ struct perf_session *session)
{
int err;
- event__repipe_synth(self, session);
- err = event__process_tracing_data(self, session);
+ perf_event__repipe_synth(event, session);
+ err = perf_event__process_tracing_data(event, session);
return err;
}
if (self->kernel)
misc = PERF_RECORD_MISC_KERNEL;
- err = event__synthesize_build_id(self, misc, event__repipe,
- machine, session);
+ err = perf_event__synthesize_build_id(self, misc, perf_event__repipe,
+ machine, session);
if (err) {
pr_err("Can't synthesize build_id event for %s\n", self->long_name);
return -1;
return 0;
}
-static int event__inject_buildid(event_t *event, struct sample_data *sample,
- struct perf_session *session)
+static int perf_event__inject_buildid(union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_session *session)
{
struct addr_location al;
struct thread *thread;
}
repipe:
- event__repipe(event, sample, session);
+ perf_event__repipe(event, sample, session);
return 0;
}
struct perf_event_ops inject_ops = {
- .sample = event__repipe,
- .mmap = event__repipe,
- .comm = event__repipe,
- .fork = event__repipe,
- .exit = event__repipe,
- .lost = event__repipe,
- .read = event__repipe,
- .throttle = event__repipe,
- .unthrottle = event__repipe,
- .attr = event__repipe_synth,
- .event_type = event__repipe_synth,
- .tracing_data = event__repipe_synth,
- .build_id = event__repipe_synth,
+ .sample = perf_event__repipe,
+ .mmap = perf_event__repipe,
+ .comm = perf_event__repipe,
+ .fork = perf_event__repipe,
+ .exit = perf_event__repipe,
+ .lost = perf_event__repipe,
+ .read = perf_event__repipe,
+ .throttle = perf_event__repipe,
+ .unthrottle = perf_event__repipe,
+ .attr = perf_event__repipe_synth,
+ .event_type = perf_event__repipe_synth,
+ .tracing_data = perf_event__repipe_synth,
+ .build_id = perf_event__repipe_synth,
};
extern volatile int session_done;
signal(SIGINT, sig_handler);
if (inject_build_ids) {
- inject_ops.sample = event__inject_buildid;
- inject_ops.mmap = event__repipe_mmap;
- inject_ops.fork = event__repipe_task;
- inject_ops.tracing_data = event__repipe_tracing_data;
+ inject_ops.sample = perf_event__inject_buildid;
+ inject_ops.mmap = perf_event__repipe_mmap;
+ inject_ops.fork = perf_event__repipe_task;
+ inject_ops.tracing_data = perf_event__repipe_tracing_data;
}
session = perf_session__new(input_name, O_RDONLY, false, true, &inject_ops);
s_alloc->alloc_cpu = -1;
}
-static void
-process_raw_event(event_t *raw_event __used, void *data,
- int cpu, u64 timestamp, struct thread *thread)
+static void process_raw_event(union perf_event *raw_event __used, void *data,
+ int cpu, u64 timestamp, struct thread *thread)
{
struct event *event;
int type;
}
}
-static int process_sample_event(event_t *event, struct sample_data *sample,
+static int process_sample_event(union perf_event *event,
+ struct perf_sample *sample,
struct perf_session *session)
{
struct thread *thread = perf_session__findnew(session, event->ip.pid);
static struct perf_event_ops event_ops = {
.sample = process_sample_event,
- .comm = event__process_comm,
+ .comm = perf_event__process_comm,
.ordered_samples = true,
};
*
* Copyright (C) 2009, Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
*/
#include "builtin.h"
#include "util/parse-events.h"
#include "util/cache.h"
-int cmd_list(int argc __used, const char **argv __used, const char *prefix __used)
+int cmd_list(int argc, const char **argv, const char *prefix __used)
{
setup_pager();
- print_events();
+
+ if (argc == 1)
+ print_events(NULL);
+ else {
+ int i;
+
+ for (i = 1; i < argc; ++i) {
+ if (i > 1)
+ putchar('\n');
+ if (strncmp(argv[i], "tracepoint", 10) == 0)
+ print_tracepoint_events(NULL, NULL);
+ else if (strcmp(argv[i], "hw") == 0 ||
+ strcmp(argv[i], "hardware") == 0)
+ print_events_type(PERF_TYPE_HARDWARE);
+ else if (strcmp(argv[i], "sw") == 0 ||
+ strcmp(argv[i], "software") == 0)
+ print_events_type(PERF_TYPE_SOFTWARE);
+ else if (strcmp(argv[i], "cache") == 0 ||
+ strcmp(argv[i], "hwcache") == 0)
+ print_hwcache_events(NULL);
+ else {
+ char *sep = strchr(argv[i], ':'), *s;
+ int sep_idx;
+
+ if (sep == NULL) {
+ print_events(argv[i]);
+ continue;
+ }
+ sep_idx = sep - argv[i];
+ s = strdup(argv[i]);
+ if (s == NULL)
+ return -1;
+
+ s[sep_idx] = '\0';
+ print_tracepoint_events(s, s + sep_idx + 1);
+ free(s);
+ }
+ }
+ }
return 0;
}
die("Unknown type of information\n");
}
-static int process_sample_event(event_t *self, struct sample_data *sample,
+static int process_sample_event(union perf_event *event, struct perf_sample *sample,
struct perf_session *s)
{
struct thread *thread = perf_session__findnew(s, sample->tid);
if (thread == NULL) {
pr_debug("problem processing %d event, skipping it.\n",
- self->header.type);
+ event->header.type);
return -1;
}
static struct perf_event_ops eops = {
.sample = process_sample_event,
- .comm = event__process_comm,
+ .comm = perf_event__process_comm,
.ordered_samples = true,
};
static const struct option report_options[] = {
OPT_STRING('k', "key", &sort_key, "acquired",
- "key for sorting"),
+ "key for sorting (acquired / contended / wait_total / wait_max / wait_min)"),
/* TODO: type */
OPT_END()
};
#include "builtin.h"
#include "util/util.h"
#include "util/strlist.h"
+#include "util/strfilter.h"
#include "util/symbol.h"
#include "util/debug.h"
#include "util/debugfs.h"
#include "util/probe-finder.h"
#include "util/probe-event.h"
+#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
+#define DEFAULT_FUNC_FILTER "!_*"
#define MAX_PATH_LEN 256
/* Session management structure */
bool show_lines;
bool show_vars;
bool show_ext_vars;
+ bool show_funcs;
bool mod_events;
int nevents;
struct perf_probe_event events[MAX_PROBES];
struct line_range line_range;
const char *target_module;
int max_probe_points;
+ struct strfilter *filter;
} params;
/* Parse an event definition. Note that any error must die. */
}
#endif
+static int opt_set_filter(const struct option *opt __used,
+ const char *str, int unset __used)
+{
+ 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;
+ }
+ }
+
+ return 0;
+}
+
static const char * const probe_usage[] = {
"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
OPT__DRY_RUN(&probe_event_dry_run),
OPT_INTEGER('\0', "max-probes", ¶ms.max_probe_points,
"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('\0', "filter", NULL,
+ "[!]FILTER", "Set a filter (with --vars/funcs only)\n"
+ "\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n"
+ "\t\t\t \"" DEFAULT_FUNC_FILTER "\" for --funcs)",
+ opt_set_filter),
OPT_END()
};
params.max_probe_points = MAX_PROBES;
if ((!params.nevents && !params.dellist && !params.list_events &&
- !params.show_lines))
+ !params.show_lines && !params.show_funcs))
usage_with_options(probe_usage, options);
/*
pr_err(" Error: Don't use --list with --vars.\n");
usage_with_options(probe_usage, options);
}
+ if (params.show_funcs) {
+ pr_err(" Error: Don't use --list with --funcs.\n");
+ usage_with_options(probe_usage, options);
+ }
ret = show_perf_probe_events();
if (ret < 0)
pr_err(" Error: Failed to show event list. (%d)\n",
ret);
return ret;
}
+ if (params.show_funcs) {
+ if (params.nevents != 0 || params.dellist) {
+ pr_err(" Error: Don't use --funcs with"
+ " --add/--del.\n");
+ usage_with_options(probe_usage, options);
+ }
+ if (params.show_lines) {
+ pr_err(" Error: Don't use --funcs with --line.\n");
+ usage_with_options(probe_usage, options);
+ }
+ if (params.show_vars) {
+ pr_err(" Error: Don't use --funcs with --vars.\n");
+ usage_with_options(probe_usage, options);
+ }
+ if (!params.filter)
+ params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
+ NULL);
+ ret = show_available_funcs(params.target_module,
+ params.filter);
+ strfilter__delete(params.filter);
+ if (ret < 0)
+ pr_err(" Error: Failed to show functions."
+ " (%d)\n", ret);
+ return ret;
+ }
#ifdef DWARF_SUPPORT
if (params.show_lines) {
" --add/--del.\n");
usage_with_options(probe_usage, options);
}
+ 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_module,
+ params.filter,
params.show_ext_vars);
+ strfilter__delete(params.filter);
if (ret < 0)
pr_err(" Error: Failed to show vars. (%d)\n", ret);
return ret;
#include "util/header.h"
#include "util/event.h"
+#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/session.h"
#include "util/symbol.h"
#include "util/cpumap.h"
+#include "util/thread_map.h"
#include <unistd.h>
#include <sched.h>
static u64 user_interval = ULLONG_MAX;
static u64 default_interval = 0;
-static u64 sample_type;
-static struct cpu_map *cpus;
static unsigned int page_size;
static unsigned int mmap_pages = 128;
static unsigned int user_freq = UINT_MAX;
static int freq = 1000;
static int output;
static int pipe_output = 0;
-static const char *output_name = "perf.data";
+static const char *output_name = NULL;
static int group = 0;
static int realtime_prio = 0;
static bool nodelay = false;
static bool system_wide = false;
static pid_t target_pid = -1;
static pid_t target_tid = -1;
-static struct thread_map *threads;
static pid_t child_pid = -1;
static bool no_inherit = false;
static enum write_mode_t write_mode = WRITE_FORCE;
static bool sample_time = false;
static bool no_buildid = false;
static bool no_buildid_cache = false;
+static struct perf_evlist *evsel_list;
static long samples = 0;
static u64 bytes_written = 0;
-static struct pollfd *event_array;
-
-static int nr_poll = 0;
-static int nr_cpu = 0;
-
static int file_new = 1;
static off_t post_processing_offset;
static struct perf_session *session;
static const char *cpu_list;
-struct mmap_data {
- void *base;
- unsigned int mask;
- unsigned int prev;
-};
-
-static struct mmap_data mmap_array[MAX_NR_CPUS];
-
-static unsigned long mmap_read_head(struct mmap_data *md)
-{
- struct perf_event_mmap_page *pc = md->base;
- long head;
-
- head = pc->data_head;
- rmb();
-
- return head;
-}
-
-static void mmap_write_tail(struct mmap_data *md, unsigned long tail)
-{
- struct perf_event_mmap_page *pc = md->base;
-
- /*
- * ensure all reads are done before we write the tail out.
- */
- /* mb(); */
- pc->data_tail = tail;
-}
-
static void advance_output(size_t size)
{
bytes_written += size;
}
}
-static int process_synthesized_event(event_t *event,
- struct sample_data *sample __used,
+static int process_synthesized_event(union perf_event *event,
+ struct perf_sample *sample __used,
struct perf_session *self __used)
{
write_output(event, event->header.size);
return 0;
}
-static void mmap_read(struct mmap_data *md)
+static void mmap_read(struct perf_mmap *md)
{
- unsigned int head = mmap_read_head(md);
+ unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
unsigned char *data = md->base + page_size;
unsigned long size;
void *buf;
- int diff;
- /*
- * If we're further behind than half the buffer, there's a chance
- * the writer will bite our tail and mess up the samples under us.
- *
- * If we somehow ended up ahead of the head, we got messed up.
- *
- * In either case, truncate and restart at head.
- */
- diff = head - old;
- if (diff < 0) {
- fprintf(stderr, "WARNING: failed to keep up with mmap data\n");
- /*
- * head points to a known good entry, start there.
- */
- old = head;
- }
+ if (old == head)
+ return;
- if (old != head)
- samples++;
+ samples++;
size = head - old;
write_output(buf, size);
md->prev = old;
- mmap_write_tail(md, old);
+ perf_mmap__write_tail(md, old);
}
static volatile int done = 0;
kill(getpid(), signr);
}
-static int group_fd;
-
-static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int nr)
-{
- struct perf_header_attr *h_attr;
-
- if (nr < session->header.attrs) {
- h_attr = session->header.attr[nr];
- } else {
- h_attr = perf_header_attr__new(a);
- if (h_attr != NULL)
- if (perf_header__add_attr(&session->header, h_attr) < 0) {
- perf_header_attr__delete(h_attr);
- h_attr = NULL;
- }
- }
-
- return h_attr;
-}
-
-static void create_counter(struct perf_evsel *evsel, int cpu)
+static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
{
- char *filter = evsel->filter;
struct perf_event_attr *attr = &evsel->attr;
- struct perf_header_attr *h_attr;
int track = !evsel->idx; /* only the first counter needs these */
- int thread_index;
- int ret;
- struct {
- u64 count;
- u64 time_enabled;
- u64 time_running;
- u64 id;
- } read_data;
- /*
- * Check if parse_single_tracepoint_event has already asked for
- * PERF_SAMPLE_TIME.
- *
- * XXX this is kludgy but short term fix for problems introduced by
- * eac23d1c that broke 'perf script' by having different sample_types
- * when using multiple tracepoint events when we use a perf binary
- * that tries to use sample_id_all on an older kernel.
- *
- * We need to move counter creation to perf_session, support
- * different sample_types, etc.
- */
- bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING |
attr->sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
- if (nr_counters > 1)
+ if (evlist->nr_entries > 1)
attr->sample_type |= PERF_SAMPLE_ID;
/*
attr->mmap = track;
attr->comm = track;
- attr->inherit = !no_inherit;
+
if (target_pid == -1 && target_tid == -1 && !system_wide) {
attr->disabled = 1;
attr->enable_on_exec = 1;
}
-retry_sample_id:
- attr->sample_id_all = sample_id_all_avail ? 1 : 0;
+}
- for (thread_index = 0; thread_index < threads->nr; thread_index++) {
-try_again:
- FD(evsel, nr_cpu, thread_index) = sys_perf_event_open(attr, threads->map[thread_index], cpu, group_fd, 0);
+static bool perf_evlist__equal(struct perf_evlist *evlist,
+ struct perf_evlist *other)
+{
+ struct perf_evsel *pos, *pair;
+
+ if (evlist->nr_entries != other->nr_entries)
+ return false;
+
+ pair = list_entry(other->entries.next, struct perf_evsel, node);
- if (FD(evsel, nr_cpu, thread_index) < 0) {
+ list_for_each_entry(pos, &evlist->entries, node) {
+ if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0))
+ return false;
+ pair = list_entry(pair->node.next, struct perf_evsel, node);
+ }
+
+ return true;
+}
+
+static void open_counters(struct perf_evlist *evlist)
+{
+ struct perf_evsel *pos;
+
+ list_for_each_entry(pos, &evlist->entries, node) {
+ struct perf_event_attr *attr = &pos->attr;
+ /*
+ * Check if parse_single_tracepoint_event has already asked for
+ * PERF_SAMPLE_TIME.
+ *
+ * XXX this is kludgy but short term fix for problems introduced by
+ * eac23d1c that broke 'perf script' by having different sample_types
+ * when using multiple tracepoint events when we use a perf binary
+ * that tries to use sample_id_all on an older kernel.
+ *
+ * We need to move counter creation to perf_session, support
+ * different sample_types, etc.
+ */
+ bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
+
+ config_attr(pos, evlist);
+retry_sample_id:
+ attr->sample_id_all = sample_id_all_avail ? 1 : 0;
+try_again:
+ if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
+ !no_inherit) < 0) {
int err = errno;
if (err == EPERM || err == EACCES)
}
printf("\n");
error("sys_perf_event_open() syscall returned with %d (%s). /bin/dmesg may provide additional information.\n",
- FD(evsel, nr_cpu, thread_index), strerror(err));
+ err, strerror(err));
#if defined(__i386__) || defined(__x86_64__)
if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
#endif
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
- exit(-1);
}
+ }
- h_attr = get_header_attr(attr, evsel->idx);
- if (h_attr == NULL)
- die("nomem\n");
+ if (perf_evlist__set_filters(evlist)) {
+ error("failed to set filter with %d (%s)\n", errno,
+ strerror(errno));
+ exit(-1);
+ }
- if (!file_new) {
- if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
- fprintf(stderr, "incompatible append\n");
- exit(-1);
- }
- }
+ if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
+ die("failed to mmap with %d (%s)\n", errno, strerror(errno));
- if (read(FD(evsel, nr_cpu, thread_index), &read_data, sizeof(read_data)) == -1) {
- perror("Unable to read perf file descriptor");
+ if (file_new)
+ session->evlist = evlist;
+ else {
+ if (!perf_evlist__equal(session->evlist, evlist)) {
+ fprintf(stderr, "incompatible append\n");
exit(-1);
}
+ }
- if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
- pr_warning("Not enough memory to add id\n");
- exit(-1);
- }
-
- assert(FD(evsel, nr_cpu, thread_index) >= 0);
- fcntl(FD(evsel, nr_cpu, thread_index), F_SETFL, O_NONBLOCK);
-
- /*
- * First counter acts as the group leader:
- */
- if (group && group_fd == -1)
- group_fd = FD(evsel, nr_cpu, thread_index);
-
- if (evsel->idx || thread_index) {
- struct perf_evsel *first;
- first = list_entry(evsel_list.next, struct perf_evsel, node);
- ret = ioctl(FD(evsel, nr_cpu, thread_index),
- PERF_EVENT_IOC_SET_OUTPUT,
- FD(first, nr_cpu, 0));
- if (ret) {
- error("failed to set output: %d (%s)\n", errno,
- strerror(errno));
- exit(-1);
- }
- } else {
- mmap_array[nr_cpu].prev = 0;
- mmap_array[nr_cpu].mask = mmap_pages*page_size - 1;
- mmap_array[nr_cpu].base = mmap(NULL, (mmap_pages+1)*page_size,
- PROT_READ | PROT_WRITE, MAP_SHARED, FD(evsel, nr_cpu, thread_index), 0);
- if (mmap_array[nr_cpu].base == MAP_FAILED) {
- error("failed to mmap with %d (%s)\n", errno, strerror(errno));
- exit(-1);
- }
-
- event_array[nr_poll].fd = FD(evsel, nr_cpu, thread_index);
- event_array[nr_poll].events = POLLIN;
- nr_poll++;
- }
-
- if (filter != NULL) {
- ret = ioctl(FD(evsel, nr_cpu, thread_index),
- PERF_EVENT_IOC_SET_FILTER, filter);
- if (ret) {
- error("failed to set filter with %d (%s)\n", errno,
- strerror(errno));
- exit(-1);
- }
- }
- }
-
- if (!sample_type)
- sample_type = attr->sample_type;
-}
-
-static void open_counters(int cpu)
-{
- struct perf_evsel *pos;
-
- group_fd = -1;
-
- list_for_each_entry(pos, &evsel_list, node)
- create_counter(pos, cpu);
-
- nr_cpu++;
+ perf_session__update_sample_type(session);
}
static int process_buildids(void)
if (!no_buildid)
process_buildids();
- perf_header__write(&session->header, output, true);
+ perf_session__write_header(session, evsel_list, output, true);
perf_session__delete(session);
- perf_evsel_list__delete();
+ perf_evlist__delete(evsel_list);
symbol__exit();
}
}
-static void event__synthesize_guest_os(struct machine *machine, void *data)
+static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
{
int err;
struct perf_session *psession = data;
*method is used to avoid symbol missing when the first addr is
*in module instead of in guest kernel.
*/
- err = event__synthesize_modules(process_synthesized_event,
- psession, machine);
+ err = perf_event__synthesize_modules(process_synthesized_event,
+ psession, machine);
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
* We use _stext for guest kernel because guest kernel's /proc/kallsyms
* have no _text sometimes.
*/
- err = event__synthesize_kernel_mmap(process_synthesized_event,
- psession, machine, "_text");
+ err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+ psession, machine, "_text");
if (err < 0)
- err = event__synthesize_kernel_mmap(process_synthesized_event,
- psession, machine, "_stext");
+ err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+ psession, machine,
+ "_stext");
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
{
int i;
- for (i = 0; i < nr_cpu; i++) {
- if (mmap_array[i].base)
- mmap_read(&mmap_array[i]);
+ for (i = 0; i < evsel_list->cpus->nr; i++) {
+ if (evsel_list->mmap[i].base)
+ mmap_read(&evsel_list->mmap[i]);
}
if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
exit(-1);
}
- if (!strcmp(output_name, "-"))
- pipe_output = 1;
- else if (!stat(output_name, &st) && st.st_size) {
- if (write_mode == WRITE_FORCE) {
- char oldname[PATH_MAX];
- snprintf(oldname, sizeof(oldname), "%s.old",
- output_name);
- unlink(oldname);
- rename(output_name, oldname);
+ if (!output_name) {
+ if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
+ pipe_output = 1;
+ else
+ output_name = "perf.data";
+ }
+ if (output_name) {
+ if (!strcmp(output_name, "-"))
+ pipe_output = 1;
+ else if (!stat(output_name, &st) && st.st_size) {
+ if (write_mode == WRITE_FORCE) {
+ char oldname[PATH_MAX];
+ snprintf(oldname, sizeof(oldname), "%s.old",
+ output_name);
+ unlink(oldname);
+ rename(output_name, oldname);
+ }
+ } else if (write_mode == WRITE_APPEND) {
+ write_mode = WRITE_FORCE;
}
- } else if (write_mode == WRITE_APPEND) {
- write_mode = WRITE_FORCE;
}
flags = O_CREAT|O_RDWR;
perf_header__set_feat(&session->header, HEADER_BUILD_ID);
if (!file_new) {
- err = perf_header__read(session, output);
+ err = perf_session__read_header(session, output);
if (err < 0)
goto out_delete_session;
}
- if (have_tracepoints(&evsel_list))
+ if (have_tracepoints(&evsel_list->entries))
perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
- /*
- * perf_session__delete(session) will be called at atexit_header()
- */
- atexit(atexit_header);
-
if (forks) {
child_pid = fork();
if (child_pid < 0) {
}
if (!system_wide && target_tid == -1 && target_pid == -1)
- threads->map[0] = child_pid;
+ evsel_list->threads->map[0] = child_pid;
close(child_ready_pipe[1]);
close(go_pipe[0]);
close(child_ready_pipe[0]);
}
- if (!system_wide && no_inherit && !cpu_list) {
- open_counters(-1);
- } else {
- for (i = 0; i < cpus->nr; i++)
- open_counters(cpus->map[i]);
- }
+ open_counters(evsel_list);
- perf_session__set_sample_type(session, sample_type);
+ /*
+ * perf_session__delete(session) will be called at atexit_header()
+ */
+ atexit(atexit_header);
if (pipe_output) {
err = perf_header__write_pipe(output);
if (err < 0)
return err;
} else if (file_new) {
- err = perf_header__write(&session->header, output, false);
+ err = perf_session__write_header(session, evsel_list,
+ output, false);
if (err < 0)
return err;
}
post_processing_offset = lseek(output, 0, SEEK_CUR);
- perf_session__set_sample_id_all(session, sample_id_all_avail);
-
if (pipe_output) {
- err = event__synthesize_attrs(&session->header,
- process_synthesized_event,
- session);
+ err = perf_session__synthesize_attrs(session,
+ process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");
return err;
}
- err = event__synthesize_event_types(process_synthesized_event,
- session);
+ err = perf_event__synthesize_event_types(process_synthesized_event,
+ session);
if (err < 0) {
pr_err("Couldn't synthesize event_types.\n");
return err;
}
- if (have_tracepoints(&evsel_list)) {
+ if (have_tracepoints(&evsel_list->entries)) {
/*
* FIXME err <= 0 here actually means that
* there were no tracepoints so its not really
* return this more properly and also
* propagate errors that now are calling die()
*/
- err = event__synthesize_tracing_data(output, &evsel_list,
- process_synthesized_event,
- session);
+ err = perf_event__synthesize_tracing_data(output, evsel_list,
+ process_synthesized_event,
+ session);
if (err <= 0) {
pr_err("Couldn't record tracing data.\n");
return err;
return -1;
}
- err = event__synthesize_kernel_mmap(process_synthesized_event,
- session, machine, "_text");
+ err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+ session, machine, "_text");
if (err < 0)
- err = event__synthesize_kernel_mmap(process_synthesized_event,
- session, machine, "_stext");
+ err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+ session, machine, "_stext");
if (err < 0)
pr_err("Couldn't record kernel reference relocation symbol\n"
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
"Check /proc/kallsyms permission or run as root.\n");
- err = event__synthesize_modules(process_synthesized_event,
- session, machine);
+ err = perf_event__synthesize_modules(process_synthesized_event,
+ session, machine);
if (err < 0)
pr_err("Couldn't record kernel module information.\n"
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
"Check /proc/modules permission or run as root.\n");
if (perf_guest)
- perf_session__process_machines(session, event__synthesize_guest_os);
+ perf_session__process_machines(session,
+ perf_event__synthesize_guest_os);
if (!system_wide)
- event__synthesize_thread(target_tid, process_synthesized_event,
- session);
+ perf_event__synthesize_thread_map(evsel_list->threads,
+ process_synthesized_event,
+ session);
else
- event__synthesize_threads(process_synthesized_event, session);
+ perf_event__synthesize_threads(process_synthesized_event,
+ session);
if (realtime_prio) {
struct sched_param param;
if (hits == samples) {
if (done)
break;
- err = poll(event_array, nr_poll, -1);
+ err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
waking++;
}
if (done) {
- for (i = 0; i < nr_cpu; i++) {
+ for (i = 0; i < evsel_list->cpus->nr; i++) {
struct perf_evsel *pos;
- list_for_each_entry(pos, &evsel_list, node) {
+ list_for_each_entry(pos, &evsel_list->entries, node) {
for (thread = 0;
- thread < threads->nr;
+ thread < evsel_list->threads->nr;
thread++)
ioctl(FD(pos, i, thread),
PERF_EVENT_IOC_DISABLE);
static bool force, append_file;
const struct option record_options[] = {
- OPT_CALLBACK('e', "event", NULL, "event",
+ OPT_CALLBACK('e', "event", &evsel_list, "event",
"event selector. use 'perf list' to list available events",
parse_events),
- OPT_CALLBACK(0, "filter", NULL, "filter",
+ OPT_CALLBACK(0, "filter", &evsel_list, "filter",
"event filter", parse_filter),
OPT_INTEGER('p', "pid", &target_pid,
"record events on existing process id"),
"do not update the buildid cache"),
OPT_BOOLEAN('B', "no-buildid", &no_buildid,
"do not collect buildids in perf.data"),
+ OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+ "monitor event in cgroup name only",
+ parse_cgroups),
OPT_END()
};
int err = -ENOMEM;
struct perf_evsel *pos;
+ evsel_list = perf_evlist__new(NULL, NULL);
+ if (evsel_list == NULL)
+ return -ENOMEM;
+
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && target_pid == -1 && target_tid == -1 &&
write_mode = WRITE_FORCE;
}
+ if (nr_cgroups && !system_wide) {
+ fprintf(stderr, "cgroup monitoring only available in"
+ " system-wide mode\n");
+ usage_with_options(record_usage, record_options);
+ }
+
symbol__init();
if (no_buildid_cache || no_buildid)
disable_buildid_cache();
- if (list_empty(&evsel_list) && perf_evsel_list__create_default() < 0) {
+ if (evsel_list->nr_entries == 0 &&
+ perf_evlist__add_default(evsel_list) < 0) {
pr_err("Not enough memory for event selector list\n");
goto out_symbol_exit;
}
if (target_pid != -1)
target_tid = target_pid;
- threads = thread_map__new(target_pid, target_tid);
- if (threads == NULL) {
- pr_err("Problems finding threads of monitor\n");
+ if (perf_evlist__create_maps(evsel_list, target_pid,
+ target_tid, cpu_list) < 0)
usage_with_options(record_usage, record_options);
- }
- cpus = cpu_map__new(cpu_list);
- if (cpus == NULL) {
- perror("failed to parse CPUs map");
- return -1;
- }
-
- list_for_each_entry(pos, &evsel_list, node) {
- if (perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0)
+ list_for_each_entry(pos, &evsel_list->entries, node) {
+ if (perf_evsel__alloc_fd(pos, evsel_list->cpus->nr,
+ evsel_list->threads->nr) < 0)
goto out_free_fd;
if (perf_header__push_event(pos->attr.config, event_name(pos)))
goto out_free_fd;
}
- event_array = malloc((sizeof(struct pollfd) * MAX_NR_CPUS *
- MAX_COUNTERS * threads->nr));
- if (!event_array)
+
+ if (perf_evlist__alloc_pollfd(evsel_list) < 0)
goto out_free_fd;
if (user_interval != ULLONG_MAX)
} else {
fprintf(stderr, "frequency and count are zero, aborting\n");
err = -EINVAL;
- goto out_free_event_array;
+ goto out_free_fd;
}
err = __cmd_record(argc, argv);
-
-out_free_event_array:
- free(event_array);
out_free_fd:
- thread_map__delete(threads);
- threads = NULL;
+ perf_evlist__delete_maps(evsel_list);
out_symbol_exit:
symbol__exit();
return err;
#include "util/util.h"
+#include "util/annotate.h"
#include "util/color.h"
#include <linux/list.h>
#include "util/cache.h"
#include "perf.h"
#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
#include "util/header.h"
#include "util/session.h"
static const char *pretty_printing_style = default_pretty_printing_style;
static char callchain_default_opt[] = "fractal,0.5";
+static symbol_filter_t annotate_init;
-static struct hists *perf_session__hists_findnew(struct perf_session *self,
- u64 event_stream, u32 type,
- u64 config)
-{
- struct rb_node **p = &self->hists_tree.rb_node;
- struct rb_node *parent = NULL;
- struct hists *iter, *new;
-
- while (*p != NULL) {
- parent = *p;
- iter = rb_entry(parent, struct hists, rb_node);
- if (iter->config == config)
- return iter;
-
-
- if (config > iter->config)
- p = &(*p)->rb_right;
- else
- p = &(*p)->rb_left;
- }
-
- new = malloc(sizeof(struct hists));
- if (new == NULL)
- return NULL;
- memset(new, 0, sizeof(struct hists));
- new->event_stream = event_stream;
- new->config = config;
- new->type = type;
- rb_link_node(&new->rb_node, parent, p);
- rb_insert_color(&new->rb_node, &self->hists_tree);
- return new;
-}
-
-static int perf_session__add_hist_entry(struct perf_session *self,
+static int perf_session__add_hist_entry(struct perf_session *session,
struct addr_location *al,
- struct sample_data *data)
+ struct perf_sample *sample)
{
- struct map_symbol *syms = NULL;
struct symbol *parent = NULL;
- int err = -ENOMEM;
+ int err = 0;
struct hist_entry *he;
- struct hists *hists;
- struct perf_event_attr *attr;
-
- if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) {
- syms = perf_session__resolve_callchain(self, al->thread,
- data->callchain, &parent);
- if (syms == NULL)
- return -ENOMEM;
+ struct perf_evsel *evsel;
+
+ if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
+ err = perf_session__resolve_callchain(session, al->thread,
+ sample->callchain, &parent);
+ if (err)
+ return err;
}
- attr = perf_header__find_attr(data->id, &self->header);
- if (attr)
- hists = perf_session__hists_findnew(self, data->id, attr->type, attr->config);
- else
- hists = perf_session__hists_findnew(self, data->id, 0, 0);
- if (hists == NULL)
- goto out_free_syms;
- he = __hists__add_entry(hists, al, parent, data->period);
+ evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+ if (evsel == NULL) {
+ /*
+ * FIXME: Propagate this back, but at least we're in a builtin,
+ * where exit() is allowed. ;-)
+ */
+ ui__warning("Invalid %s file, contains samples with id %" PRIu64 " not in "
+ "its header!\n", input_name, sample->id);
+ exit_browser(0);
+ exit(1);
+ }
+
+ he = __hists__add_entry(&evsel->hists, al, parent, sample->period);
if (he == NULL)
- goto out_free_syms;
- err = 0;
+ return -ENOMEM;
+
if (symbol_conf.use_callchain) {
- err = callchain_append(he->callchain, data->callchain, syms,
- data->period);
+ err = callchain_append(he->callchain, &session->callchain_cursor,
+ sample->period);
if (err)
- goto out_free_syms;
+ return err;
}
/*
* Only in the newt browser we are doing integrated annotation,
* so we don't allocated the extra space needed because the stdio
* code will not use it.
*/
- if (use_browser > 0)
- err = hist_entry__inc_addr_samples(he, al->addr);
-out_free_syms:
- free(syms);
- return err;
-}
+ if (al->sym != NULL && use_browser > 0) {
+ struct annotation *notes = symbol__annotation(he->ms.sym);
-static int add_event_total(struct perf_session *session,
- struct sample_data *data,
- struct perf_event_attr *attr)
-{
- struct hists *hists;
+ assert(evsel != NULL);
- if (attr)
- hists = perf_session__hists_findnew(session, data->id,
- attr->type, attr->config);
- else
- hists = perf_session__hists_findnew(session, data->id, 0, 0);
+ err = -ENOMEM;
+ if (notes->src == NULL &&
+ symbol__alloc_hist(he->ms.sym, session->evlist->nr_entries) < 0)
+ goto out;
- if (!hists)
- return -ENOMEM;
+ err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+ }
- hists->stats.total_period += data->period;
- /*
- * FIXME: add_event_total should be moved from here to
- * perf_session__process_event so that the proper hist is passed to
- * the event_op methods.
- */
- hists__inc_nr_events(hists, PERF_RECORD_SAMPLE);
- session->hists.stats.total_period += data->period;
- return 0;
+ evsel->hists.stats.total_period += sample->period;
+ hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+out:
+ return err;
}
-static int process_sample_event(event_t *event, struct sample_data *sample,
+
+static int process_sample_event(union perf_event *event,
+ struct perf_sample *sample,
struct perf_session *session)
{
struct addr_location al;
- struct perf_event_attr *attr;
- if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
+ if (perf_event__preprocess_sample(event, session, &al, sample,
+ annotate_init) < 0) {
fprintf(stderr, "problem processing %d event, skipping it.\n",
event->header.type);
return -1;
return -1;
}
- attr = perf_header__find_attr(sample->id, &session->header);
-
- if (add_event_total(session, sample, attr)) {
- pr_debug("problem adding event period\n");
- return -1;
- }
-
return 0;
}
-static int process_read_event(event_t *event, struct sample_data *sample __used,
- struct perf_session *session __used)
+static int process_read_event(union perf_event *event,
+ struct perf_sample *sample __used,
+ struct perf_session *session)
{
- struct perf_event_attr *attr;
-
- attr = perf_header__find_attr(event->read.id, &session->header);
-
+ struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist,
+ event->read.id);
if (show_threads) {
- const char *name = attr ? __event_name(attr->type, attr->config)
- : "unknown";
+ const char *name = evsel ? event_name(evsel) : "unknown";
perf_read_values_add_value(&show_threads_values,
event->read.pid, event->read.tid,
event->read.id,
}
dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
- attr ? __event_name(attr->type, attr->config) : "FAIL",
+ evsel ? event_name(evsel) : "FAIL",
event->read.value);
return 0;
} else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
!symbol_conf.use_callchain) {
symbol_conf.use_callchain = true;
- if (register_callchain_param(&callchain_param) < 0) {
+ if (callchain_register_param(&callchain_param) < 0) {
fprintf(stderr, "Can't register callchain"
" params\n");
return -EINVAL;
}
static struct perf_event_ops event_ops = {
- .sample = process_sample_event,
- .mmap = event__process_mmap,
- .comm = event__process_comm,
- .exit = event__process_task,
- .fork = event__process_task,
- .lost = event__process_lost,
- .read = process_read_event,
- .attr = event__process_attr,
- .event_type = event__process_event_type,
- .tracing_data = event__process_tracing_data,
- .build_id = event__process_build_id,
+ .sample = process_sample_event,
+ .mmap = perf_event__process_mmap,
+ .comm = perf_event__process_comm,
+ .exit = perf_event__process_task,
+ .fork = perf_event__process_task,
+ .lost = perf_event__process_lost,
+ .read = process_read_event,
+ .attr = perf_event__process_attr,
+ .event_type = perf_event__process_event_type,
+ .tracing_data = perf_event__process_tracing_data,
+ .build_id = perf_event__process_build_id,
.ordered_samples = true,
.ordering_requires_timestamps = true,
};
return ret + fprintf(fp, "\n#\n");
}
-static int hists__tty_browse_tree(struct rb_root *tree, const char *help)
+static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
+ const char *help)
{
- struct rb_node *next = rb_first(tree);
+ struct perf_evsel *pos;
- while (next) {
- struct hists *hists = rb_entry(next, struct hists, rb_node);
+ list_for_each_entry(pos, &evlist->entries, node) {
+ struct hists *hists = &pos->hists;
const char *evname = NULL;
if (rb_first(&hists->entries) != rb_last(&hists->entries))
- evname = __event_name(hists->type, hists->config);
+ evname = event_name(pos);
hists__fprintf_nr_sample_events(hists, evname, stdout);
hists__fprintf(hists, NULL, false, stdout);
fprintf(stdout, "\n\n");
- next = rb_next(&hists->rb_node);
}
if (sort_order == default_sort_order &&
static int __cmd_report(void)
{
int ret = -EINVAL;
+ u64 nr_samples;
struct perf_session *session;
- struct rb_node *next;
+ struct perf_evsel *pos;
const char *help = "For a higher level overview, try: perf report --sort comm,dso";
signal(SIGINT, sig_handler);
if (verbose > 2)
perf_session__fprintf_dsos(session, stdout);
- next = rb_first(&session->hists_tree);
- while (next) {
- struct hists *hists;
+ nr_samples = 0;
+ list_for_each_entry(pos, &session->evlist->entries, node) {
+ struct hists *hists = &pos->hists;
- hists = rb_entry(next, struct hists, rb_node);
hists__collapse_resort(hists);
hists__output_resort(hists);
- next = rb_next(&hists->rb_node);
+ nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
+ }
+
+ if (nr_samples == 0) {
+ ui__warning("The %s file has no samples!\n", input_name);
+ goto out_delete;
}
if (use_browser > 0)
- hists__tui_browse_tree(&session->hists_tree, help);
+ perf_evlist__tui_browse_hists(session->evlist, help);
else
- hists__tty_browse_tree(&session->hists_tree, help);
+ perf_evlist__tty_browse_hists(session->evlist, help);
out_delete:
/*
if (tok2)
callchain_param.print_limit = strtod(tok2, &endptr);
setup:
- if (register_callchain_param(&callchain_param) < 0) {
+ if (callchain_register_param(&callchain_param) < 0) {
fprintf(stderr, "Can't register callchain params\n");
return -1;
}
use_browser = 1;
if (strcmp(input_name, "-") != 0)
- setup_browser();
+ setup_browser(true);
else
use_browser = 0;
/*
* implementation.
*/
if (use_browser > 0) {
- symbol_conf.priv_size = sizeof(struct sym_priv);
+ symbol_conf.priv_size = sizeof(struct annotation);
+ annotate_init = symbol__annotate_init;
/*
* For searching by name on the "Browse map details".
* providing it only in verbose mode not to bloat too
process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom)
{
int ret = 0;
- u64 now;
- long long delta;
-
- now = get_nsecs();
- delta = start_time + atom->timestamp - now;
switch (atom->type) {
case SCHED_EVENT_RUN:
static void run_one_test(void)
{
- u64 T0, T1, delta, avg_delta, fluct, std_dev;
+ u64 T0, T1, delta, avg_delta, fluct;
T0 = get_nsecs();
wait_for_tasks();
else
fluct = delta - avg_delta;
sum_fluct += fluct;
- std_dev = sum_fluct / nr_runs / sqrt(nr_runs);
if (!run_avg)
run_avg = delta;
run_avg = (run_avg*9 + delta)/10;
u64 timestamp,
struct thread *thread __used)
{
- struct task_desc *prev, *next;
+ struct task_desc *prev, __used *next;
u64 timestamp0;
s64 delta;
u64 timestamp,
struct thread *thread __used)
{
- struct thread *sched_out, *sched_in;
+ struct thread *sched_out __used, *sched_in;
int new_shortname;
u64 timestamp0;
s64 delta;
event, cpu, timestamp, thread);
}
-static void
-process_raw_event(event_t *raw_event __used, struct perf_session *session,
- void *data, int cpu, u64 timestamp, struct thread *thread)
+static void process_raw_event(union perf_event *raw_event __used,
+ struct perf_session *session, void *data, int cpu,
+ u64 timestamp, struct thread *thread)
{
struct event *event;
int type;
process_sched_migrate_task_event(data, session, event, cpu, timestamp, thread);
}
-static int process_sample_event(event_t *event, struct sample_data *sample,
+static int process_sample_event(union perf_event *event,
+ struct perf_sample *sample,
struct perf_session *session)
{
struct thread *thread;
static struct perf_event_ops event_ops = {
.sample = process_sample_event,
- .comm = event__process_comm,
- .lost = event__process_lost,
- .fork = event__process_task,
+ .comm = perf_event__process_comm,
+ .lost = perf_event__process_lost,
+ .fork = perf_event__process_task,
.ordered_samples = true,
};
static char const *input_name = "perf.data";
-static int process_sample_event(event_t *event, struct sample_data *sample,
+static int process_sample_event(union perf_event *event,
+ struct perf_sample *sample,
struct perf_session *session)
{
struct thread *thread = perf_session__findnew(session, event->ip.pid);
}
static struct perf_event_ops event_ops = {
- .sample = process_sample_event,
- .comm = event__process_comm,
- .attr = event__process_attr,
- .event_type = event__process_event_type,
- .tracing_data = event__process_tracing_data,
- .build_id = event__process_build_id,
- .ordering_requires_timestamps = true,
+ .sample = process_sample_event,
+ .comm = perf_event__process_comm,
+ .attr = perf_event__process_attr,
+ .event_type = perf_event__process_event_type,
+ .tracing_data = perf_event__process_tracing_data,
+ .build_id = perf_event__process_build_id,
.ordered_samples = true,
+ .ordering_requires_timestamps = true,
};
extern volatile int session_done;
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/event.h"
+#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/header.h"
#include "util/cpumap.h"
#include "util/thread.h"
+#include "util/thread_map.h"
#include <sys/prctl.h>
#include <math.h>
};
+struct perf_evlist *evsel_list;
+
static bool system_wide = false;
-static struct cpu_map *cpus;
static int run_idx = 0;
static int run_count = 1;
static bool no_aggr = false;
static pid_t target_pid = -1;
static pid_t target_tid = -1;
-static struct thread_map *threads;
static pid_t child_pid = -1;
static bool null_run = false;
static bool big_num = true;
PERF_FORMAT_TOTAL_TIME_RUNNING;
if (system_wide)
- return perf_evsel__open_per_cpu(evsel, cpus);
+ return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false);
attr->inherit = !no_inherit;
if (target_pid == -1 && target_tid == -1) {
attr->enable_on_exec = 1;
}
- return perf_evsel__open_per_thread(evsel, threads);
+ return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false);
}
/*
u64 *count = counter->counts->aggr.values;
int i;
- if (__perf_evsel__read(counter, cpus->nr, threads->nr, scale) < 0)
+ if (__perf_evsel__read(counter, evsel_list->cpus->nr,
+ evsel_list->threads->nr, scale) < 0)
return -1;
for (i = 0; i < 3; i++)
u64 *count;
int cpu;
- for (cpu = 0; cpu < cpus->nr; cpu++) {
+ for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
return -1;
}
if (target_tid == -1 && target_pid == -1 && !system_wide)
- threads->map[0] = child_pid;
+ evsel_list->threads->map[0] = child_pid;
/*
* Wait for the child to be ready to exec.
close(child_ready_pipe[0]);
}
- list_for_each_entry(counter, &evsel_list, node) {
+ list_for_each_entry(counter, &evsel_list->entries, node) {
if (create_perf_stat_counter(counter) < 0) {
if (errno == -EPERM || errno == -EACCES) {
error("You may not have permission to collect %sstats.\n"
update_stats(&walltime_nsecs_stats, t1 - t0);
if (no_aggr) {
- list_for_each_entry(counter, &evsel_list, node) {
+ list_for_each_entry(counter, &evsel_list->entries, node) {
read_counter(counter);
- perf_evsel__close_fd(counter, cpus->nr, 1);
+ perf_evsel__close_fd(counter, evsel_list->cpus->nr, 1);
}
} else {
- list_for_each_entry(counter, &evsel_list, node) {
+ list_for_each_entry(counter, &evsel_list->entries, node) {
read_counter_aggr(counter);
- perf_evsel__close_fd(counter, cpus->nr, threads->nr);
+ perf_evsel__close_fd(counter, evsel_list->cpus->nr,
+ evsel_list->threads->nr);
}
}
if (no_aggr)
sprintf(cpustr, "CPU%*d%s",
csv_output ? 0 : -4,
- cpus->map[cpu], csv_sep);
+ evsel_list->cpus->map[cpu], csv_sep);
fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(evsel));
+ if (evsel->cgrp)
+ fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
+
if (csv_output)
return;
if (no_aggr)
sprintf(cpustr, "CPU%*d%s",
csv_output ? 0 : -4,
- cpus->map[cpu], csv_sep);
+ evsel_list->cpus->map[cpu], csv_sep);
else
cpu = 0;
fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(evsel));
+ if (evsel->cgrp)
+ fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
+
if (csv_output)
return;
int scaled = counter->counts->scaled;
if (scaled == -1) {
- fprintf(stderr, "%*s%s%-24s\n",
+ fprintf(stderr, "%*s%s%*s",
csv_output ? 0 : 18,
- "<not counted>", csv_sep, event_name(counter));
+ "<not counted>",
+ csv_sep,
+ csv_output ? 0 : -24,
+ event_name(counter));
+
+ if (counter->cgrp)
+ fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
+
+ fputc('\n', stderr);
return;
}
fprintf(stderr, " (scaled from %.2f%%)",
100 * avg_running / avg_enabled);
}
-
fprintf(stderr, "\n");
}
u64 ena, run, val;
int cpu;
- for (cpu = 0; cpu < cpus->nr; cpu++) {
+ for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
val = counter->counts->cpu[cpu].val;
ena = counter->counts->cpu[cpu].ena;
run = counter->counts->cpu[cpu].run;
if (run == 0 || ena == 0) {
- fprintf(stderr, "CPU%*d%s%*s%s%-24s",
+ fprintf(stderr, "CPU%*d%s%*s%s%*s",
csv_output ? 0 : -4,
- cpus->map[cpu], csv_sep,
+ evsel_list->cpus->map[cpu], csv_sep,
csv_output ? 0 : 18,
"<not counted>", csv_sep,
+ csv_output ? 0 : -24,
event_name(counter));
- fprintf(stderr, "\n");
+ if (counter->cgrp)
+ fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
+
+ fputc('\n', stderr);
continue;
}
100.0 * run / ena);
}
}
- fprintf(stderr, "\n");
+ fputc('\n', stderr);
}
}
}
if (no_aggr) {
- list_for_each_entry(counter, &evsel_list, node)
+ list_for_each_entry(counter, &evsel_list->entries, node)
print_counter(counter);
} else {
- list_for_each_entry(counter, &evsel_list, node)
+ list_for_each_entry(counter, &evsel_list->entries, node)
print_counter_aggr(counter);
}
}
static const struct option options[] = {
- OPT_CALLBACK('e', "event", NULL, "event",
+ OPT_CALLBACK('e', "event", &evsel_list, "event",
"event selector. use 'perf list' to list available events",
parse_events),
OPT_BOOLEAN('i', "no-inherit", &no_inherit,
"disable CPU count aggregation"),
OPT_STRING('x', "field-separator", &csv_sep, "separator",
"print counts with custom separator"),
+ OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+ "monitor event in cgroup name only",
+ parse_cgroups),
OPT_END()
};
setlocale(LC_ALL, "");
+ evsel_list = perf_evlist__new(NULL, NULL);
+ if (evsel_list == NULL)
+ return -ENOMEM;
+
argc = parse_options(argc, argv, options, stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (run_count <= 0)
usage_with_options(stat_usage, options);
- /* no_aggr is for system-wide only */
- if (no_aggr && !system_wide)
+ /* no_aggr, cgroup are for system-wide only */
+ if ((no_aggr || nr_cgroups) && !system_wide) {
+ fprintf(stderr, "both cgroup and no-aggregation "
+ "modes only available in system-wide mode\n");
+
usage_with_options(stat_usage, options);
+ }
/* Set attrs and nr_counters if no event is selected and !null_run */
- if (!null_run && !nr_counters) {
+ if (!null_run && !evsel_list->nr_entries) {
size_t c;
- nr_counters = ARRAY_SIZE(default_attrs);
-
for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) {
- pos = perf_evsel__new(&default_attrs[c],
- nr_counters);
+ pos = perf_evsel__new(&default_attrs[c], c);
if (pos == NULL)
goto out;
- list_add(&pos->node, &evsel_list);
+ perf_evlist__add(evsel_list, pos);
}
}
if (target_pid != -1)
target_tid = target_pid;
- threads = thread_map__new(target_pid, target_tid);
- if (threads == NULL) {
+ evsel_list->threads = thread_map__new(target_pid, target_tid);
+ if (evsel_list->threads == NULL) {
pr_err("Problems finding threads of monitor\n");
usage_with_options(stat_usage, options);
}
if (system_wide)
- cpus = cpu_map__new(cpu_list);
+ evsel_list->cpus = cpu_map__new(cpu_list);
else
- cpus = cpu_map__dummy_new();
+ evsel_list->cpus = cpu_map__dummy_new();
- if (cpus == NULL) {
+ if (evsel_list->cpus == NULL) {
perror("failed to parse CPUs map");
usage_with_options(stat_usage, options);
return -1;
}
- list_for_each_entry(pos, &evsel_list, node) {
+ list_for_each_entry(pos, &evsel_list->entries, node) {
if (perf_evsel__alloc_stat_priv(pos) < 0 ||
- perf_evsel__alloc_counts(pos, cpus->nr) < 0 ||
- perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0)
+ perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0 ||
+ perf_evsel__alloc_fd(pos, evsel_list->cpus->nr, evsel_list->threads->nr) < 0)
goto out_free_fd;
}
if (status != -1)
print_stat(argc, argv);
out_free_fd:
- list_for_each_entry(pos, &evsel_list, node)
+ list_for_each_entry(pos, &evsel_list->entries, node)
perf_evsel__free_stat_priv(pos);
- perf_evsel_list__delete();
+ perf_evlist__delete_maps(evsel_list);
out:
- thread_map__delete(threads);
- threads = NULL;
+ perf_evlist__delete(evsel_list);
return status;
}
#include "util/cache.h"
#include "util/debug.h"
+#include "util/evlist.h"
#include "util/parse-options.h"
-#include "util/session.h"
+#include "util/parse-events.h"
#include "util/symbol.h"
-#include "util/thread.h"
+#include "util/thread_map.h"
static long page_size;
#include "util/evsel.h"
#include <sys/types.h>
-static int trace_event__id(const char *event_name)
+static int trace_event__id(const char *evname)
{
char *filename;
int err = -1, fd;
if (asprintf(&filename,
"/sys/kernel/debug/tracing/events/syscalls/%s/id",
- event_name) < 0)
+ evname) < 0)
return -1;
fd = open(filename, O_RDONLY);
goto out_thread_map_delete;
}
- if (perf_evsel__open_per_thread(evsel, threads) < 0) {
+ if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
}
cpus = cpu_map__new(NULL);
- if (threads == NULL) {
- pr_debug("thread_map__new\n");
- return -1;
+ if (cpus == NULL) {
+ pr_debug("cpu_map__new\n");
+ goto out_thread_map_delete;
}
goto out_thread_map_delete;
}
- if (perf_evsel__open(evsel, cpus, threads) < 0) {
+ if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
goto out_close_fd;
}
+ err = 0;
+
for (cpu = 0; cpu < cpus->nr; ++cpu) {
unsigned int expected;
if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
pr_debug("perf_evsel__open_read_on_cpu\n");
- goto out_close_fd;
+ 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);
- goto out_close_fd;
+ err = -1;
}
}
- err = 0;
out_close_fd:
perf_evsel__close_fd(evsel, 1, threads->nr);
out_evsel_delete:
return err;
}
+/*
+ * This test will generate random numbers of calls to some getpid syscalls,
+ * then establish an mmap for a group of events that are created to monitor
+ * the syscalls.
+ *
+ * It will receive the events, using mmap, use its PERF_SAMPLE_ID generated
+ * sample.id field to map back to its respective perf_evsel instance.
+ *
+ * Then it checks if the number of syscalls reported as perf events by
+ * the kernel corresponds to the number of syscalls made.
+ */
+static int test__basic_mmap(void)
+{
+ int err = -1;
+ union perf_event *event;
+ struct thread_map *threads;
+ struct cpu_map *cpus;
+ struct perf_evlist *evlist;
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_TRACEPOINT,
+ .read_format = PERF_FORMAT_ID,
+ .sample_type = PERF_SAMPLE_ID,
+ .watermark = 0,
+ };
+ cpu_set_t cpu_set;
+ const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
+ "getpgid", };
+ pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
+ (void*)getpgid };
+#define nsyscalls ARRAY_SIZE(syscall_names)
+ int ids[nsyscalls];
+ unsigned int nr_events[nsyscalls],
+ expected_nr_events[nsyscalls], i, j;
+ struct perf_evsel *evsels[nsyscalls], *evsel;
+
+ for (i = 0; i < nsyscalls; ++i) {
+ char name[64];
+
+ snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
+ ids[i] = trace_event__id(name);
+ if (ids[i] < 0) {
+ pr_debug("Is debugfs mounted on /sys/kernel/debug?\n");
+ return -1;
+ }
+ nr_events[i] = 0;
+ expected_nr_events[i] = random() % 257;
+ }
+
+ threads = thread_map__new(-1, getpid());
+ 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_free_threads;
+ }
+
+ CPU_ZERO(&cpu_set);
+ CPU_SET(cpus->map[0], &cpu_set);
+ sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
+ if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+ pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+ cpus->map[0], strerror(errno));
+ goto out_free_cpus;
+ }
+
+ evlist = perf_evlist__new(cpus, threads);
+ if (evlist == NULL) {
+ pr_debug("perf_evlist__new\n");
+ goto out_free_cpus;
+ }
+
+ /* anonymous union fields, can't be initialized above */
+ attr.wakeup_events = 1;
+ attr.sample_period = 1;
+
+ for (i = 0; i < nsyscalls; ++i) {
+ attr.config = ids[i];
+ evsels[i] = perf_evsel__new(&attr, i);
+ if (evsels[i] == NULL) {
+ pr_debug("perf_evsel__new\n");
+ goto out_free_evlist;
+ }
+
+ perf_evlist__add(evlist, evsels[i]);
+
+ if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) {
+ pr_debug("failed to open counter: %s, "
+ "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+ strerror(errno));
+ goto out_close_fd;
+ }
+ }
+
+ if (perf_evlist__mmap(evlist, 128, true) < 0) {
+ pr_debug("failed to mmap events: %d (%s)\n", errno,
+ strerror(errno));
+ goto out_close_fd;
+ }
+
+ for (i = 0; i < nsyscalls; ++i)
+ for (j = 0; j < expected_nr_events[i]; ++j) {
+ int foo = syscalls[i]();
+ ++foo;
+ }
+
+ while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) {
+ struct perf_sample sample;
+
+ if (event->header.type != PERF_RECORD_SAMPLE) {
+ pr_debug("unexpected %s event\n",
+ perf_event__name(event->header.type));
+ goto out_munmap;
+ }
+
+ perf_event__parse_sample(event, attr.sample_type, false, &sample);
+ evsel = perf_evlist__id2evsel(evlist, sample.id);
+ if (evsel == NULL) {
+ pr_debug("event with id %" PRIu64
+ " doesn't map to an evsel\n", sample.id);
+ goto out_munmap;
+ }
+ nr_events[evsel->idx]++;
+ }
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
+ pr_debug("expected %d %s events, got %d\n",
+ expected_nr_events[evsel->idx],
+ event_name(evsel), nr_events[evsel->idx]);
+ goto out_munmap;
+ }
+ }
+
+ err = 0;
+out_munmap:
+ perf_evlist__munmap(evlist);
+out_close_fd:
+ for (i = 0; i < nsyscalls; ++i)
+ perf_evsel__close_fd(evsels[i], 1, threads->nr);
+out_free_evlist:
+ perf_evlist__delete(evlist);
+out_free_cpus:
+ cpu_map__delete(cpus);
+out_free_threads:
+ thread_map__delete(threads);
+ return err;
+#undef nsyscalls
+}
+
static struct test {
const char *desc;
int (*func)(void);
.desc = "detect open syscall event on all cpus",
.func = test__open_syscall_event_on_all_cpus,
},
+ {
+ .desc = "read samples using the mmap interface",
+ .func = test__basic_mmap,
+ },
{
.func = NULL,
},
c->start_time = start;
if (p->start_time == 0 || p->start_time > start)
p->start_time = start;
-
- if (cpu > numcpus)
- numcpus = cpu;
}
#define MAX_CPUS 4096
static u64 cpus_pstate_start_times[MAX_CPUS];
static u64 cpus_pstate_state[MAX_CPUS];
-static int process_comm_event(event_t *event, struct sample_data *sample __used,
+static int process_comm_event(union perf_event *event,
+ struct perf_sample *sample __used,
struct perf_session *session __used)
{
pid_set_comm(event->comm.tid, event->comm.comm);
return 0;
}
-static int process_fork_event(event_t *event, struct sample_data *sample __used,
+static int process_fork_event(union perf_event *event,
+ struct perf_sample *sample __used,
struct perf_session *session __used)
{
pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
return 0;
}
-static int process_exit_event(event_t *event, struct sample_data *sample __used,
+static int process_exit_event(union perf_event *event,
+ struct perf_sample *sample __used,
struct perf_session *session __used)
{
pid_exit(event->fork.pid, event->fork.time);
}
-static int process_sample_event(event_t *event __used,
- struct sample_data *sample,
+static int process_sample_event(union perf_event *event __used,
+ struct perf_sample *sample,
struct perf_session *session)
{
struct trace_entry *te;
if (!event_str)
return 0;
+ if (sample->cpu > numcpus)
+ numcpus = sample->cpu;
+
if (strcmp(event_str, "power:cpu_idle") == 0) {
struct power_processor_entry *ppe = (void *)te;
if (ppe->state == (u32)PWR_EVENT_EXIT)
#include "perf.h"
+#include "util/annotate.h"
+#include "util/cache.h"
#include "util/color.h"
+#include "util/evlist.h"
#include "util/evsel.h"
#include "util/session.h"
#include "util/symbol.h"
#include "util/thread.h"
+#include "util/thread_map.h"
+#include "util/top.h"
#include "util/util.h"
#include <linux/rbtree.h>
#include "util/parse-options.h"
#include <errno.h>
#include <time.h>
#include <sched.h>
-#include <pthread.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+static struct perf_top top = {
+ .count_filter = 5,
+ .delay_secs = 2,
+ .display_weighted = -1,
+ .target_pid = -1,
+ .target_tid = -1,
+ .active_symbols = LIST_HEAD_INIT(top.active_symbols),
+ .active_symbols_lock = PTHREAD_MUTEX_INITIALIZER,
+ .active_symbols_cond = PTHREAD_COND_INITIALIZER,
+ .freq = 1000, /* 1 KHz */
+};
+
static bool system_wide = false;
-static int default_interval = 0;
+static bool use_tui, use_stdio;
-static int count_filter = 5;
-static int print_entries;
+static int default_interval = 0;
-static int target_pid = -1;
-static int target_tid = -1;
-static struct thread_map *threads;
static bool inherit = false;
-static struct cpu_map *cpus;
static int realtime_prio = 0;
static bool group = false;
static unsigned int page_size;
-static unsigned int mmap_pages = 16;
-static int freq = 1000; /* 1 KHz */
+static unsigned int mmap_pages = 128;
-static int delay_secs = 2;
-static bool zero = false;
static bool dump_symtab = false;
-static bool hide_kernel_symbols = false;
-static bool hide_user_symbols = false;
static struct winsize winsize;
-/*
- * Source
- */
-
-struct source_line {
- u64 eip;
- unsigned long count[MAX_COUNTERS];
- char *line;
- struct source_line *next;
-};
-
static const char *sym_filter = NULL;
-struct sym_entry *sym_filter_entry = NULL;
struct sym_entry *sym_filter_entry_sched = NULL;
static int sym_pcnt_filter = 5;
-static int sym_counter = 0;
-static struct perf_evsel *sym_evsel = NULL;
-static int display_weighted = -1;
-static const char *cpu_list;
-
-/*
- * Symbols
- */
-
-struct sym_entry_source {
- struct source_line *source;
- struct source_line *lines;
- struct source_line **lines_tail;
- pthread_mutex_t lock;
-};
-
-struct sym_entry {
- struct rb_node rb_node;
- struct list_head node;
- unsigned long snap_count;
- double weight;
- int skip;
- u16 name_len;
- u8 origin;
- struct map *map;
- struct sym_entry_source *src;
- unsigned long count[0];
-};
/*
* Source functions
*/
-static inline struct symbol *sym_entry__symbol(struct sym_entry *self)
-{
- return ((void *)self) + symbol_conf.priv_size;
-}
-
void get_term_dimensions(struct winsize *ws)
{
char *s = getenv("LINES");
static void update_print_entries(struct winsize *ws)
{
- print_entries = ws->ws_row;
+ top.print_entries = ws->ws_row;
- if (print_entries > 9)
- print_entries -= 9;
+ if (top.print_entries > 9)
+ top.print_entries -= 9;
}
static void sig_winch_handler(int sig __used)
static int parse_source(struct sym_entry *syme)
{
struct symbol *sym;
- struct sym_entry_source *source;
+ struct annotation *notes;
struct map *map;
- FILE *file;
- char command[PATH_MAX*2];
- const char *path;
- u64 len;
+ int err = -1;
if (!syme)
return -1;
/*
* We can't annotate with just /proc/kallsyms
*/
- if (map->dso->origin == DSO__ORIG_KERNEL)
+ if (map->dso->origin == DSO__ORIG_KERNEL) {
+ pr_err("Can't annotate %s: No vmlinux file was found in the "
+ "path\n", sym->name);
+ sleep(1);
return -1;
-
- if (syme->src == NULL) {
- syme->src = zalloc(sizeof(*source));
- if (syme->src == NULL)
- return -1;
- pthread_mutex_init(&syme->src->lock, NULL);
}
- source = syme->src;
-
- if (source->lines) {
- pthread_mutex_lock(&source->lock);
+ notes = symbol__annotation(sym);
+ if (notes->src != NULL) {
+ pthread_mutex_lock(¬es->lock);
goto out_assign;
}
- path = map->dso->long_name;
-
- len = sym->end - sym->start;
-
- sprintf(command,
- "objdump --start-address=%#0*" PRIx64 " --stop-address=%#0*" PRIx64 " -dS %s",
- BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start),
- BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path);
-
- file = popen(command, "r");
- if (!file)
- return -1;
-
- pthread_mutex_lock(&source->lock);
- source->lines_tail = &source->lines;
- while (!feof(file)) {
- struct source_line *src;
- size_t dummy = 0;
- char *c, *sep;
- src = malloc(sizeof(struct source_line));
- assert(src != NULL);
- memset(src, 0, sizeof(struct source_line));
+ pthread_mutex_lock(¬es->lock);
- if (getline(&src->line, &dummy, file) < 0)
- break;
- if (!src->line)
- break;
-
- c = strchr(src->line, '\n');
- if (c)
- *c = 0;
-
- src->next = NULL;
- *source->lines_tail = src;
- source->lines_tail = &src->next;
-
- src->eip = strtoull(src->line, &sep, 16);
- if (*sep == ':')
- src->eip = map__objdump_2ip(map, src->eip);
- else /* this line has no ip info (e.g. source line) */
- src->eip = 0;
+ if (symbol__alloc_hist(sym, top.evlist->nr_entries) < 0) {
+ pthread_mutex_unlock(¬es->lock);
+ pr_err("Not enough memory for annotating '%s' symbol!\n",
+ sym->name);
+ sleep(1);
+ return err;
}
- pclose(file);
+
+ err = symbol__annotate(sym, syme->map, 0);
+ if (err == 0) {
out_assign:
- sym_filter_entry = syme;
- pthread_mutex_unlock(&source->lock);
- return 0;
+ top.sym_filter_entry = syme;
+ }
+
+ pthread_mutex_unlock(¬es->lock);
+ return err;
}
static void __zero_source_counters(struct sym_entry *syme)
{
- int i;
- struct source_line *line;
-
- line = syme->src->lines;
- while (line) {
- for (i = 0; i < nr_counters; i++)
- line->count[i] = 0;
- line = line->next;
- }
+ struct symbol *sym = sym_entry__symbol(syme);
+ symbol__annotate_zero_histograms(sym);
}
static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
{
- struct source_line *line;
-
- if (syme != sym_filter_entry)
- return;
+ struct annotation *notes;
+ struct symbol *sym;
- if (pthread_mutex_trylock(&syme->src->lock))
+ if (syme != top.sym_filter_entry)
return;
- if (syme->src == NULL || syme->src->source == NULL)
- goto out_unlock;
-
- for (line = syme->src->lines; line; line = line->next) {
- /* skip lines without IP info */
- if (line->eip == 0)
- continue;
- if (line->eip == ip) {
- line->count[counter]++;
- break;
- }
- if (line->eip > ip)
- break;
- }
-out_unlock:
- pthread_mutex_unlock(&syme->src->lock);
-}
-
-#define PATTERN_LEN (BITS_PER_LONG / 4 + 2)
-
-static void lookup_sym_source(struct sym_entry *syme)
-{
- struct symbol *symbol = sym_entry__symbol(syme);
- struct source_line *line;
- char pattern[PATTERN_LEN + 1];
-
- sprintf(pattern, "%0*" PRIx64 " <", BITS_PER_LONG / 4,
- map__rip_2objdump(syme->map, symbol->start));
-
- pthread_mutex_lock(&syme->src->lock);
- for (line = syme->src->lines; line; line = line->next) {
- if (memcmp(line->line, pattern, PATTERN_LEN) == 0) {
- syme->src->source = line;
- break;
- }
- }
- pthread_mutex_unlock(&syme->src->lock);
-}
+ sym = sym_entry__symbol(syme);
+ notes = symbol__annotation(sym);
-static void show_lines(struct source_line *queue, int count, int total)
-{
- int i;
- struct source_line *line;
+ if (pthread_mutex_trylock(¬es->lock))
+ return;
- line = queue;
- for (i = 0; i < count; i++) {
- float pcnt = 100.0*(float)line->count[sym_counter]/(float)total;
+ ip = syme->map->map_ip(syme->map, ip);
+ symbol__inc_addr_samples(sym, syme->map, counter, ip);
- printf("%8li %4.1f%%\t%s\n", line->count[sym_counter], pcnt, line->line);
- line = line->next;
- }
+ pthread_mutex_unlock(¬es->lock);
}
-#define TRACE_COUNT 3
-
static void show_details(struct sym_entry *syme)
{
+ struct annotation *notes;
struct symbol *symbol;
- struct source_line *line;
- struct source_line *line_queue = NULL;
- int displayed = 0;
- int line_queue_count = 0, total = 0, more = 0;
+ int more;
if (!syme)
return;
- if (!syme->src->source)
- lookup_sym_source(syme);
-
- if (!syme->src->source)
- return;
-
symbol = sym_entry__symbol(syme);
- printf("Showing %s for %s\n", event_name(sym_evsel), symbol->name);
- printf(" Events Pcnt (>=%d%%)\n", sym_pcnt_filter);
-
- pthread_mutex_lock(&syme->src->lock);
- line = syme->src->source;
- while (line) {
- total += line->count[sym_counter];
- line = line->next;
- }
-
- line = syme->src->source;
- while (line) {
- float pcnt = 0.0;
-
- if (!line_queue_count)
- line_queue = line;
- line_queue_count++;
-
- if (line->count[sym_counter])
- pcnt = 100.0 * line->count[sym_counter] / (float)total;
- if (pcnt >= (float)sym_pcnt_filter) {
- if (displayed <= print_entries)
- show_lines(line_queue, line_queue_count, total);
- else more++;
- displayed += line_queue_count;
- line_queue_count = 0;
- line_queue = NULL;
- } else if (line_queue_count > TRACE_COUNT) {
- line_queue = line_queue->next;
- line_queue_count--;
- }
-
- line->count[sym_counter] = zero ? 0 : line->count[sym_counter] * 7 / 8;
- line = line->next;
- }
- pthread_mutex_unlock(&syme->src->lock);
- if (more)
- printf("%d lines not displayed, maybe increase display entries [e]\n", more);
-}
+ notes = symbol__annotation(symbol);
-/*
- * Symbols will be added here in event__process_sample and will get out
- * after decayed.
- */
-static LIST_HEAD(active_symbols);
-static pthread_mutex_t active_symbols_lock = PTHREAD_MUTEX_INITIALIZER;
-
-/*
- * Ordering weight: count-1 * count-2 * ... / count-n
- */
-static double sym_weight(const struct sym_entry *sym)
-{
- double weight = sym->snap_count;
- int counter;
-
- if (!display_weighted)
- return weight;
+ pthread_mutex_lock(¬es->lock);
- for (counter = 1; counter < nr_counters-1; counter++)
- weight *= sym->count[counter];
+ if (notes->src == NULL)
+ goto out_unlock;
- weight /= (sym->count[counter] + 1);
+ printf("Showing %s for %s\n", event_name(top.sym_evsel), symbol->name);
+ printf(" Events Pcnt (>=%d%%)\n", sym_pcnt_filter);
- return weight;
+ more = symbol__annotate_printf(symbol, syme->map, top.sym_evsel->idx,
+ 0, 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 (more != 0)
+ printf("%d lines not displayed, maybe increase display entries [e]\n", more);
+out_unlock:
+ pthread_mutex_unlock(¬es->lock);
}
-static long samples;
-static long kernel_samples, us_samples;
-static long exact_samples;
-static long guest_us_samples, guest_kernel_samples;
static const char CONSOLE_CLEAR[] = "\e[H\e[2J";
static void __list_insert_active_sym(struct sym_entry *syme)
{
- list_add(&syme->node, &active_symbols);
-}
-
-static void list_remove_active_sym(struct sym_entry *syme)
-{
- pthread_mutex_lock(&active_symbols_lock);
- list_del_init(&syme->node);
- pthread_mutex_unlock(&active_symbols_lock);
+ list_add(&syme->node, &top.active_symbols);
}
-static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
+static void print_sym_table(struct perf_session *session)
{
- struct rb_node **p = &tree->rb_node;
- struct rb_node *parent = NULL;
- struct sym_entry *iter;
-
- while (*p != NULL) {
- parent = *p;
- iter = rb_entry(parent, struct sym_entry, rb_node);
-
- if (se->weight > iter->weight)
- p = &(*p)->rb_left;
- else
- p = &(*p)->rb_right;
- }
-
- rb_link_node(&se->rb_node, parent, p);
- rb_insert_color(&se->rb_node, tree);
-}
-
-static void print_sym_table(void)
-{
- int printed = 0, j;
- struct perf_evsel *counter;
- int snap = !display_weighted ? sym_counter : 0;
- float samples_per_sec = samples/delay_secs;
- float ksamples_per_sec = kernel_samples/delay_secs;
- float us_samples_per_sec = (us_samples)/delay_secs;
- float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs;
- float guest_us_samples_per_sec = (guest_us_samples)/delay_secs;
- float esamples_percent = (100.0*exact_samples)/samples;
- float sum_ksamples = 0.0;
- struct sym_entry *syme, *n;
- struct rb_root tmp = RB_ROOT;
+ char bf[160];
+ int printed = 0;
struct rb_node *nd;
- int sym_width = 0, dso_width = 0, dso_short_width = 0;
+ struct sym_entry *syme;
+ struct rb_root tmp = RB_ROOT;
const int win_width = winsize.ws_col - 1;
-
- samples = us_samples = kernel_samples = exact_samples = 0;
- guest_kernel_samples = guest_us_samples = 0;
-
- /* Sort the active symbols */
- pthread_mutex_lock(&active_symbols_lock);
- syme = list_entry(active_symbols.next, struct sym_entry, node);
- pthread_mutex_unlock(&active_symbols_lock);
-
- list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
- syme->snap_count = syme->count[snap];
- if (syme->snap_count != 0) {
-
- if ((hide_user_symbols &&
- syme->origin == PERF_RECORD_MISC_USER) ||
- (hide_kernel_symbols &&
- syme->origin == PERF_RECORD_MISC_KERNEL)) {
- list_remove_active_sym(syme);
- continue;
- }
- syme->weight = sym_weight(syme);
- rb_insert_active_sym(&tmp, syme);
- sum_ksamples += syme->snap_count;
-
- for (j = 0; j < nr_counters; j++)
- syme->count[j] = zero ? 0 : syme->count[j] * 7 / 8;
- } else
- list_remove_active_sym(syme);
- }
+ int sym_width, dso_width, dso_short_width;
+ float sum_ksamples = perf_top__decay_samples(&top, &tmp);
puts(CONSOLE_CLEAR);
- printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
- if (!perf_guest) {
- printf(" PerfTop:%8.0f irqs/sec kernel:%4.1f%%"
- " exact: %4.1f%% [",
- samples_per_sec,
- 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
- samples_per_sec)),
- esamples_percent);
- } else {
- printf(" PerfTop:%8.0f irqs/sec kernel:%4.1f%% us:%4.1f%%"
- " guest kernel:%4.1f%% guest us:%4.1f%%"
- " exact: %4.1f%% [",
- samples_per_sec,
- 100.0 - (100.0 * ((samples_per_sec-ksamples_per_sec) /
- samples_per_sec)),
- 100.0 - (100.0 * ((samples_per_sec-us_samples_per_sec) /
- samples_per_sec)),
- 100.0 - (100.0 * ((samples_per_sec -
- guest_kernel_samples_per_sec) /
- samples_per_sec)),
- 100.0 - (100.0 * ((samples_per_sec -
- guest_us_samples_per_sec) /
- samples_per_sec)),
- esamples_percent);
- }
-
- if (nr_counters == 1 || !display_weighted) {
- struct perf_evsel *first;
- first = list_entry(evsel_list.next, struct perf_evsel, node);
- printf("%" PRIu64, (uint64_t)first->attr.sample_period);
- if (freq)
- printf("Hz ");
- else
- printf(" ");
- }
-
- if (!display_weighted)
- printf("%s", event_name(sym_evsel));
- else list_for_each_entry(counter, &evsel_list, node) {
- if (counter->idx)
- printf("/");
-
- printf("%s", event_name(counter));
- }
+ perf_top__header_snprintf(&top, bf, sizeof(bf));
+ printf("%s\n", bf);
- printf( "], ");
-
- if (target_pid != -1)
- printf(" (target_pid: %d", target_pid);
- else if (target_tid != -1)
- printf(" (target_tid: %d", target_tid);
- else
- printf(" (all");
-
- if (cpu_list)
- printf(", CPU%s: %s)\n", cpus->nr > 1 ? "s" : "", cpu_list);
- else {
- if (target_tid != -1)
- printf(")\n");
- else
- printf(", %d CPU%s)\n", cpus->nr, cpus->nr > 1 ? "s" : "");
- }
+ perf_top__reset_sample_counters(&top);
printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
- if (sym_filter_entry) {
- show_details(sym_filter_entry);
- return;
+ if (session->hists.stats.total_lost != 0) {
+ color_fprintf(stdout, PERF_COLOR_RED, "WARNING:");
+ printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n",
+ session->hists.stats.total_lost);
}
- /*
- * Find the longest symbol name that will be displayed
- */
- for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) {
- syme = rb_entry(nd, struct sym_entry, rb_node);
- if (++printed > print_entries ||
- (int)syme->snap_count < count_filter)
- continue;
-
- if (syme->map->dso->long_name_len > dso_width)
- dso_width = syme->map->dso->long_name_len;
-
- if (syme->map->dso->short_name_len > dso_short_width)
- dso_short_width = syme->map->dso->short_name_len;
-
- if (syme->name_len > sym_width)
- sym_width = syme->name_len;
+ if (top.sym_filter_entry) {
+ show_details(top.sym_filter_entry);
+ return;
}
- printed = 0;
+ perf_top__find_widths(&top, &tmp, &dso_width, &dso_short_width,
+ &sym_width);
if (sym_width + dso_width > winsize.ws_col - 29) {
dso_width = dso_short_width;
sym_width = winsize.ws_col - dso_width - 29;
}
putchar('\n');
- if (nr_counters == 1)
+ if (top.evlist->nr_entries == 1)
printf(" samples pcnt");
else
printf(" weight samples pcnt");
printf(" RIP ");
printf(" %-*.*s DSO\n", sym_width, sym_width, "function");
printf(" %s _______ _____",
- nr_counters == 1 ? " " : "______");
+ top.evlist->nr_entries == 1 ? " " : "______");
if (verbose)
printf(" ________________");
printf(" %-*.*s", sym_width, sym_width, graph_line);
syme = rb_entry(nd, struct sym_entry, rb_node);
sym = sym_entry__symbol(syme);
- if (++printed > print_entries || (int)syme->snap_count < count_filter)
+ if (++printed > top.print_entries ||
+ (int)syme->snap_count < top.count_filter)
continue;
pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) /
sum_ksamples));
- if (nr_counters == 1 || !display_weighted)
+ if (top.evlist->nr_entries == 1 || !top.display_weighted)
printf("%20.2f ", syme->weight);
else
printf("%9.1f %10ld ", syme->weight, syme->snap_count);
/* zero counters of active symbol */
if (syme) {
- pthread_mutex_lock(&syme->src->lock);
__zero_source_counters(syme);
*target = NULL;
- pthread_mutex_unlock(&syme->src->lock);
}
fprintf(stdout, "\n%s: ", msg);
if (p)
*p = 0;
- pthread_mutex_lock(&active_symbols_lock);
- syme = list_entry(active_symbols.next, struct sym_entry, node);
- pthread_mutex_unlock(&active_symbols_lock);
+ pthread_mutex_lock(&top.active_symbols_lock);
+ syme = list_entry(top.active_symbols.next, struct sym_entry, node);
+ pthread_mutex_unlock(&top.active_symbols_lock);
- list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
+ list_for_each_entry_safe_from(syme, n, &top.active_symbols, node) {
struct symbol *sym = sym_entry__symbol(syme);
if (!strcmp(buf, sym->name)) {
{
char *name = NULL;
- if (sym_filter_entry) {
- struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+ if (top.sym_filter_entry) {
+ struct symbol *sym = sym_entry__symbol(top.sym_filter_entry);
name = sym->name;
}
fprintf(stdout, "\nMapped keys:\n");
- fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", delay_secs);
- fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", print_entries);
+ fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", top.delay_secs);
+ fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top.print_entries);
- if (nr_counters > 1)
- fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(sym_evsel));
+ if (top.evlist->nr_entries > 1)
+ fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(top.sym_evsel));
- fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", count_filter);
+ fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top.count_filter);
fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter);
fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL");
fprintf(stdout, "\t[S] stop annotation.\n");
- if (nr_counters > 1)
- fprintf(stdout, "\t[w] toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0);
+ if (top.evlist->nr_entries > 1)
+ fprintf(stdout, "\t[w] toggle display weighted/count[E]r. \t(%d)\n", top.display_weighted ? 1 : 0);
fprintf(stdout,
"\t[K] hide kernel_symbols symbols. \t(%s)\n",
- hide_kernel_symbols ? "yes" : "no");
+ top.hide_kernel_symbols ? "yes" : "no");
fprintf(stdout,
"\t[U] hide user symbols. \t(%s)\n",
- hide_user_symbols ? "yes" : "no");
- fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", zero ? 1 : 0);
+ top.hide_user_symbols ? "yes" : "no");
+ fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", top.zero ? 1 : 0);
fprintf(stdout, "\t[qQ] quit.\n");
}
return 1;
case 'E':
case 'w':
- return nr_counters > 1 ? 1 : 0;
+ return top.evlist->nr_entries > 1 ? 1 : 0;
default:
break;
}
switch (c) {
case 'd':
- prompt_integer(&delay_secs, "Enter display delay");
- if (delay_secs < 1)
- delay_secs = 1;
+ prompt_integer(&top.delay_secs, "Enter display delay");
+ if (top.delay_secs < 1)
+ top.delay_secs = 1;
break;
case 'e':
- prompt_integer(&print_entries, "Enter display entries (lines)");
- if (print_entries == 0) {
+ prompt_integer(&top.print_entries, "Enter display entries (lines)");
+ if (top.print_entries == 0) {
sig_winch_handler(SIGWINCH);
signal(SIGWINCH, sig_winch_handler);
} else
signal(SIGWINCH, SIG_DFL);
break;
case 'E':
- if (nr_counters > 1) {
+ if (top.evlist->nr_entries > 1) {
fprintf(stderr, "\nAvailable events:");
- list_for_each_entry(sym_evsel, &evsel_list, node)
- fprintf(stderr, "\n\t%d %s", sym_evsel->idx, event_name(sym_evsel));
+ list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
+ fprintf(stderr, "\n\t%d %s", top.sym_evsel->idx, event_name(top.sym_evsel));
- prompt_integer(&sym_counter, "Enter details event counter");
+ prompt_integer(&top.sym_counter, "Enter details event counter");
- if (sym_counter >= nr_counters) {
- sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node);
- sym_counter = 0;
- fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(sym_evsel));
+ if (top.sym_counter >= top.evlist->nr_entries) {
+ top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
+ top.sym_counter = 0;
+ fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top.sym_evsel));
sleep(1);
break;
}
- list_for_each_entry(sym_evsel, &evsel_list, node)
- if (sym_evsel->idx == sym_counter)
+ list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
+ if (top.sym_evsel->idx == top.sym_counter)
break;
- } else sym_counter = 0;
+ } else top.sym_counter = 0;
break;
case 'f':
- prompt_integer(&count_filter, "Enter display event count filter");
+ prompt_integer(&top.count_filter, "Enter display event count filter");
break;
case 'F':
prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)");
break;
case 'K':
- hide_kernel_symbols = !hide_kernel_symbols;
+ top.hide_kernel_symbols = !top.hide_kernel_symbols;
break;
case 'q':
case 'Q':
perf_session__fprintf_dsos(session, stderr);
exit(0);
case 's':
- prompt_symbol(&sym_filter_entry, "Enter details symbol");
+ prompt_symbol(&top.sym_filter_entry, "Enter details symbol");
break;
case 'S':
- if (!sym_filter_entry)
+ if (!top.sym_filter_entry)
break;
else {
- struct sym_entry *syme = sym_filter_entry;
+ struct sym_entry *syme = top.sym_filter_entry;
- pthread_mutex_lock(&syme->src->lock);
- sym_filter_entry = NULL;
+ top.sym_filter_entry = NULL;
__zero_source_counters(syme);
- pthread_mutex_unlock(&syme->src->lock);
}
break;
case 'U':
- hide_user_symbols = !hide_user_symbols;
+ top.hide_user_symbols = !top.hide_user_symbols;
break;
case 'w':
- display_weighted = ~display_weighted;
+ top.display_weighted = ~top.display_weighted;
break;
case 'z':
- zero = !zero;
+ top.zero = !top.zero;
break;
default:
break;
}
}
+static void *display_thread_tui(void *arg __used)
+{
+ int err = 0;
+ pthread_mutex_lock(&top.active_symbols_lock);
+ while (list_empty(&top.active_symbols)) {
+ err = pthread_cond_wait(&top.active_symbols_cond,
+ &top.active_symbols_lock);
+ if (err)
+ break;
+ }
+ pthread_mutex_unlock(&top.active_symbols_lock);
+ if (!err)
+ perf_top__tui_browser(&top);
+ exit_browser(0);
+ exit(0);
+ return NULL;
+}
+
static void *display_thread(void *arg __used)
{
struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
tc.c_cc[VTIME] = 0;
repeat:
- delay_msecs = delay_secs * 1000;
+ delay_msecs = top.delay_secs * 1000;
tcsetattr(0, TCSANOW, &tc);
/* trash return*/
getc(stdin);
do {
- print_sym_table();
+ print_sym_table(session);
} while (!poll(&stdin_poll, 1, delay_msecs) == 1);
c = getc(stdin);
/* Tag samples to be skipped. */
static const char *skip_symbols[] = {
"default_idle",
+ "native_safe_halt",
"cpu_idle",
"enter_idle",
"exit_idle",
syme = symbol__priv(sym);
syme->map = map;
- syme->src = NULL;
+ symbol__annotate_init(map, sym);
- if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) {
+ if (!top.sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) {
/* schedule initial sym_filter_entry setup */
sym_filter_entry_sched = syme;
sym_filter = NULL;
}
}
- if (!syme->skip)
- syme->name_len = strlen(sym->name);
-
return 0;
}
-static void event__process_sample(const event_t *self,
- struct sample_data *sample,
- struct perf_session *session,
- struct perf_evsel *evsel)
+static void perf_event__process_sample(const union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_session *session)
{
- u64 ip = self->ip.ip;
+ u64 ip = event->ip.ip;
struct sym_entry *syme;
struct addr_location al;
struct machine *machine;
- u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ u8 origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- ++samples;
+ ++top.samples;
switch (origin) {
case PERF_RECORD_MISC_USER:
- ++us_samples;
- if (hide_user_symbols)
+ ++top.us_samples;
+ if (top.hide_user_symbols)
return;
machine = perf_session__find_host_machine(session);
break;
case PERF_RECORD_MISC_KERNEL:
- ++kernel_samples;
- if (hide_kernel_symbols)
+ ++top.kernel_samples;
+ if (top.hide_kernel_symbols)
return;
machine = perf_session__find_host_machine(session);
break;
case PERF_RECORD_MISC_GUEST_KERNEL:
- ++guest_kernel_samples;
- machine = perf_session__find_machine(session, self->ip.pid);
+ ++top.guest_kernel_samples;
+ machine = perf_session__find_machine(session, event->ip.pid);
break;
case PERF_RECORD_MISC_GUEST_USER:
- ++guest_us_samples;
+ ++top.guest_us_samples;
/*
* TODO: we don't process guest user from host side
* except simple counting.
if (!machine && perf_guest) {
pr_err("Can't find guest [%d]'s kernel information\n",
- self->ip.pid);
+ event->ip.pid);
return;
}
- if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
- exact_samples++;
+ if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
+ top.exact_samples++;
- if (event__preprocess_sample(self, session, &al, sample,
- symbol_filter) < 0 ||
+ if (perf_event__preprocess_sample(event, session, &al, sample,
+ symbol_filter) < 0 ||
al.filtered)
return;
*/
if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
- pr_err("The %s file can't be used\n",
- symbol_conf.vmlinux_name);
+ ui__warning("The %s file can't be used\n",
+ symbol_conf.vmlinux_name);
+ exit_browser(0);
exit(1);
}
/* let's see, whether we need to install initial sym_filter_entry */
if (sym_filter_entry_sched) {
- sym_filter_entry = sym_filter_entry_sched;
+ top.sym_filter_entry = sym_filter_entry_sched;
sym_filter_entry_sched = NULL;
- if (parse_source(sym_filter_entry) < 0) {
- struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+ if (parse_source(top.sym_filter_entry) < 0) {
+ struct symbol *sym = sym_entry__symbol(top.sym_filter_entry);
pr_err("Can't annotate %s", sym->name);
- if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
+ if (top.sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
pr_err(": No vmlinux file was found in the path:\n");
machine__fprintf_vmlinux_path(machine, stderr);
} else
syme = symbol__priv(al.sym);
if (!syme->skip) {
- syme->count[evsel->idx]++;
+ struct perf_evsel *evsel;
+
syme->origin = origin;
+ evsel = perf_evlist__id2evsel(top.evlist, sample->id);
+ assert(evsel != NULL);
+ syme->count[evsel->idx]++;
record_precise_ip(syme, evsel->idx, ip);
- pthread_mutex_lock(&active_symbols_lock);
- if (list_empty(&syme->node) || !syme->node.next)
+ pthread_mutex_lock(&top.active_symbols_lock);
+ if (list_empty(&syme->node) || !syme->node.next) {
+ static bool first = true;
__list_insert_active_sym(syme);
- pthread_mutex_unlock(&active_symbols_lock);
+ if (first) {
+ pthread_cond_broadcast(&top.active_symbols_cond);
+ first = false;
+ }
+ }
+ pthread_mutex_unlock(&top.active_symbols_lock);
}
}
-struct mmap_data {
- void *base;
- int mask;
- unsigned int prev;
-};
-
-static int perf_evsel__alloc_mmap_per_thread(struct perf_evsel *evsel,
- int ncpus, int nthreads)
-{
- evsel->priv = xyarray__new(ncpus, nthreads, sizeof(struct mmap_data));
- return evsel->priv != NULL ? 0 : -ENOMEM;
-}
-
-static void perf_evsel__free_mmap(struct perf_evsel *evsel)
-{
- xyarray__delete(evsel->priv);
- evsel->priv = NULL;
-}
-
-static unsigned int mmap_read_head(struct mmap_data *md)
-{
- struct perf_event_mmap_page *pc = md->base;
- int head;
-
- head = pc->data_head;
- rmb();
-
- return head;
-}
-
-static void perf_session__mmap_read_counter(struct perf_session *self,
- struct perf_evsel *evsel,
- int cpu, int thread_idx)
+static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu)
{
- struct xyarray *mmap_array = evsel->priv;
- struct mmap_data *md = xyarray__entry(mmap_array, cpu, thread_idx);
- unsigned int head = mmap_read_head(md);
- unsigned int old = md->prev;
- unsigned char *data = md->base + page_size;
- struct sample_data sample;
- int diff;
-
- /*
- * If we're further behind than half the buffer, there's a chance
- * the writer will bite our tail and mess up the samples under us.
- *
- * If we somehow ended up ahead of the head, we got messed up.
- *
- * In either case, truncate and restart at head.
- */
- diff = head - old;
- if (diff > md->mask / 2 || diff < 0) {
- fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
- /*
- * head points to a known good entry, start there.
- */
- old = head;
- }
-
- for (; old != head;) {
- event_t *event = (event_t *)&data[old & md->mask];
-
- event_t event_copy;
+ struct perf_sample sample;
+ union perf_event *event;
- size_t size = event->header.size;
+ while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) {
+ perf_session__parse_sample(self, event, &sample);
- /*
- * Event straddles the mmap boundary -- header should always
- * be inside due to u64 alignment of output.
- */
- if ((old & md->mask) + size != ((old + size) & md->mask)) {
- unsigned int offset = old;
- unsigned int len = min(sizeof(*event), size), cpy;
- void *dst = &event_copy;
-
- do {
- cpy = min(md->mask + 1 - (offset & md->mask), len);
- memcpy(dst, &data[offset & md->mask], cpy);
- offset += cpy;
- dst += cpy;
- len -= cpy;
- } while (len);
-
- event = &event_copy;
- }
-
- event__parse_sample(event, self, &sample);
if (event->header.type == PERF_RECORD_SAMPLE)
- event__process_sample(event, &sample, self, evsel);
+ perf_event__process_sample(event, &sample, self);
else
- event__process(event, &sample, self);
- old += size;
+ perf_event__process(event, &sample, self);
}
-
- md->prev = old;
}
-static struct pollfd *event_array;
-
static void perf_session__mmap_read(struct perf_session *self)
{
- struct perf_evsel *counter;
- int i, thread_index;
-
- for (i = 0; i < cpus->nr; i++) {
- list_for_each_entry(counter, &evsel_list, node) {
- for (thread_index = 0;
- thread_index < threads->nr;
- thread_index++) {
- perf_session__mmap_read_counter(self,
- counter, i, thread_index);
- }
- }
- }
-}
+ int i;
-int nr_poll;
-int group_fd;
+ for (i = 0; i < top.evlist->cpus->nr; i++)
+ perf_session__mmap_read_cpu(self, i);
+}
-static void start_counter(int i, struct perf_evsel *evsel)
+static void start_counters(struct perf_evlist *evlist)
{
- struct xyarray *mmap_array = evsel->priv;
- struct mmap_data *mm;
- struct perf_event_attr *attr;
- int cpu = -1;
- int thread_index;
-
- if (target_tid == -1)
- cpu = cpus->map[i];
+ struct perf_evsel *counter;
- attr = &evsel->attr;
+ list_for_each_entry(counter, &evlist->entries, node) {
+ struct perf_event_attr *attr = &counter->attr;
- attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+ attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
- if (freq) {
- attr->sample_type |= PERF_SAMPLE_PERIOD;
- attr->freq = 1;
- attr->sample_freq = freq;
- }
+ if (top.freq) {
+ attr->sample_type |= PERF_SAMPLE_PERIOD;
+ attr->freq = 1;
+ attr->sample_freq = top.freq;
+ }
- attr->inherit = (cpu < 0) && inherit;
- attr->mmap = 1;
+ if (evlist->nr_entries > 1) {
+ attr->sample_type |= PERF_SAMPLE_ID;
+ attr->read_format |= PERF_FORMAT_ID;
+ }
- for (thread_index = 0; thread_index < threads->nr; thread_index++) {
+ attr->mmap = 1;
try_again:
- FD(evsel, i, thread_index) = sys_perf_event_open(attr,
- threads->map[thread_index], cpu, group_fd, 0);
-
- if (FD(evsel, i, thread_index) < 0) {
+ if (perf_evsel__open(counter, top.evlist->cpus,
+ top.evlist->threads, group, inherit) < 0) {
int err = errno;
if (err == EPERM || err == EACCES)
* based cpu-clock-tick sw counter, which
* is always available even if no PMU support:
*/
- if (attr->type == PERF_TYPE_HARDWARE
- && attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+ if (attr->type == PERF_TYPE_HARDWARE &&
+ attr->config == PERF_COUNT_HW_CPU_CYCLES) {
if (verbose)
warning(" ... trying to fall back to cpu-clock-ticks\n");
goto try_again;
}
printf("\n");
- error("sys_perf_event_open() syscall returned with %d (%s). /bin/dmesg may provide additional information.\n",
- FD(evsel, i, thread_index), strerror(err));
+ error("sys_perf_event_open() syscall returned with %d "
+ "(%s). /bin/dmesg may provide additional information.\n",
+ err, strerror(err));
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
exit(-1);
}
- assert(FD(evsel, i, thread_index) >= 0);
- fcntl(FD(evsel, i, thread_index), F_SETFL, O_NONBLOCK);
-
- /*
- * First counter acts as the group leader:
- */
- if (group && group_fd == -1)
- group_fd = FD(evsel, i, thread_index);
-
- event_array[nr_poll].fd = FD(evsel, i, thread_index);
- event_array[nr_poll].events = POLLIN;
- nr_poll++;
-
- mm = xyarray__entry(mmap_array, i, thread_index);
- mm->prev = 0;
- mm->mask = mmap_pages*page_size - 1;
- mm->base = mmap(NULL, (mmap_pages+1)*page_size,
- PROT_READ, MAP_SHARED, FD(evsel, i, thread_index), 0);
- if (mm->base == MAP_FAILED)
- die("failed to mmap with %d (%s)\n", errno, strerror(errno));
}
+
+ if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
+ die("failed to mmap with %d (%s)\n", errno, strerror(errno));
}
static int __cmd_top(void)
{
pthread_t thread;
- struct perf_evsel *counter;
- int i, ret;
+ int ret __used;
/*
* FIXME: perf_session__new should allow passing a O_MMAP, so that all this
* mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
if (session == NULL)
return -ENOMEM;
- if (target_tid != -1)
- event__synthesize_thread(target_tid, event__process, session);
+ if (top.target_tid != -1)
+ perf_event__synthesize_thread_map(top.evlist->threads,
+ perf_event__process, session);
else
- event__synthesize_threads(event__process, session);
+ perf_event__synthesize_threads(perf_event__process, session);
- for (i = 0; i < cpus->nr; i++) {
- group_fd = -1;
- list_for_each_entry(counter, &evsel_list, node)
- start_counter(i, counter);
- }
+ start_counters(top.evlist);
+ session->evlist = top.evlist;
+ perf_session__update_sample_type(session);
/* Wait for a minimal set of events before starting the snapshot */
- poll(&event_array[0], nr_poll, 100);
+ poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
perf_session__mmap_read(session);
- if (pthread_create(&thread, NULL, display_thread, session)) {
+ if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
+ display_thread), session)) {
printf("Could not create display thread.\n");
exit(-1);
}
}
while (1) {
- int hits = samples;
+ u64 hits = top.samples;
perf_session__mmap_read(session);
- if (hits == samples)
- ret = poll(event_array, nr_poll, 100);
+ if (hits == top.samples)
+ ret = poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
}
return 0;
};
static const struct option options[] = {
- OPT_CALLBACK('e', "event", NULL, "event",
+ OPT_CALLBACK('e', "event", &top.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events),
OPT_INTEGER('c', "count", &default_interval,
"event period to sample"),
- OPT_INTEGER('p', "pid", &target_pid,
+ OPT_INTEGER('p', "pid", &top.target_pid,
"profile events on existing process id"),
- OPT_INTEGER('t', "tid", &target_tid,
+ OPT_INTEGER('t', "tid", &top.target_tid,
"profile events on existing thread id"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
- OPT_STRING('C', "cpu", &cpu_list, "cpu",
+ OPT_STRING('C', "cpu", &top.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
- OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols,
+ OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
"hide kernel symbols"),
OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
OPT_INTEGER('r', "realtime", &realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
- OPT_INTEGER('d', "delay", &delay_secs,
+ OPT_INTEGER('d', "delay", &top.delay_secs,
"number of seconds to delay between refreshes"),
OPT_BOOLEAN('D', "dump-symtab", &dump_symtab,
"dump the symbol table used for profiling"),
- OPT_INTEGER('f', "count-filter", &count_filter,
+ OPT_INTEGER('f', "count-filter", &top.count_filter,
"only display functions with more events than this"),
OPT_BOOLEAN('g', "group", &group,
"put the counters into a counter group"),
"child tasks inherit counters"),
OPT_STRING('s', "sym-annotate", &sym_filter, "symbol name",
"symbol to annotate"),
- OPT_BOOLEAN('z', "zero", &zero,
+ OPT_BOOLEAN('z', "zero", &top.zero,
"zero history across updates"),
- OPT_INTEGER('F', "freq", &freq,
+ OPT_INTEGER('F', "freq", &top.freq,
"profile at this frequency"),
- OPT_INTEGER('E', "entries", &print_entries,
+ OPT_INTEGER('E', "entries", &top.print_entries,
"display this many functions"),
- OPT_BOOLEAN('U', "hide_user_symbols", &hide_user_symbols,
+ OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
"hide user symbols"),
+ OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+ OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_END()
struct perf_evsel *pos;
int status = -ENOMEM;
+ top.evlist = perf_evlist__new(NULL, NULL);
+ if (top.evlist == NULL)
+ return -ENOMEM;
+
page_size = sysconf(_SC_PAGE_SIZE);
argc = parse_options(argc, argv, options, top_usage, 0);
if (argc)
usage_with_options(top_usage, options);
- if (target_pid != -1)
- target_tid = target_pid;
+ /*
+ * XXX For now start disabled, only using TUI if explicitely asked for.
+ * Change that when handle_keys equivalent gets written, live annotation
+ * done, etc.
+ */
+ use_browser = 0;
- threads = thread_map__new(target_pid, target_tid);
- if (threads == NULL) {
- pr_err("Problems finding threads of monitor\n");
- usage_with_options(top_usage, options);
- }
+ if (use_stdio)
+ use_browser = 0;
+ else if (use_tui)
+ use_browser = 1;
- event_array = malloc((sizeof(struct pollfd) *
- MAX_NR_CPUS * MAX_COUNTERS * threads->nr));
- if (!event_array)
- return -ENOMEM;
+ setup_browser(false);
/* CPU and PID are mutually exclusive */
- if (target_tid > 0 && cpu_list) {
+ if (top.target_tid > 0 && top.cpu_list) {
printf("WARNING: PID switch overriding CPU\n");
sleep(1);
- cpu_list = NULL;
+ top.cpu_list = NULL;
}
- if (!nr_counters && perf_evsel_list__create_default() < 0) {
+ if (top.target_pid != -1)
+ top.target_tid = top.target_pid;
+
+ if (perf_evlist__create_maps(top.evlist, top.target_pid,
+ top.target_tid, top.cpu_list) < 0)
+ usage_with_options(top_usage, options);
+
+ if (!top.evlist->nr_entries &&
+ perf_evlist__add_default(top.evlist) < 0) {
pr_err("Not enough memory for event selector list\n");
return -ENOMEM;
}
- if (delay_secs < 1)
- delay_secs = 1;
+ if (top.delay_secs < 1)
+ top.delay_secs = 1;
/*
* User specified count overrides default frequency.
*/
if (default_interval)
- freq = 0;
- else if (freq) {
- default_interval = freq;
+ top.freq = 0;
+ else if (top.freq) {
+ default_interval = top.freq;
} else {
fprintf(stderr, "frequency and count are zero, aborting\n");
exit(EXIT_FAILURE);
}
- if (target_tid != -1)
- cpus = cpu_map__dummy_new();
- else
- cpus = cpu_map__new(cpu_list);
-
- if (cpus == NULL)
- usage_with_options(top_usage, options);
-
- list_for_each_entry(pos, &evsel_list, node) {
- if (perf_evsel__alloc_mmap_per_thread(pos, cpus->nr, threads->nr) < 0 ||
- perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0)
+ list_for_each_entry(pos, &top.evlist->entries, node) {
+ if (perf_evsel__alloc_fd(pos, top.evlist->cpus->nr,
+ top.evlist->threads->nr) < 0)
goto out_free_fd;
/*
* Fill in the ones not specifically initialized via -c:
pos->attr.sample_period = default_interval;
}
- sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node);
+ if (perf_evlist__alloc_pollfd(top.evlist) < 0 ||
+ perf_evlist__alloc_mmap(top.evlist) < 0)
+ goto out_free_fd;
+
+ top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
- symbol_conf.priv_size = (sizeof(struct sym_entry) +
- (nr_counters + 1) * sizeof(unsigned long));
+ symbol_conf.priv_size = (sizeof(struct sym_entry) + sizeof(struct annotation) +
+ (top.evlist->nr_entries + 1) * sizeof(unsigned long));
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
if (symbol__init() < 0)
return -1;
get_term_dimensions(&winsize);
- if (print_entries == 0) {
+ if (top.print_entries == 0) {
update_print_entries(&winsize);
signal(SIGWINCH, sig_winch_handler);
}
status = __cmd_top();
out_free_fd:
- list_for_each_entry(pos, &evsel_list, node)
- perf_evsel__free_mmap(pos);
- perf_evsel_list__delete();
+ perf_evlist__delete(top.evlist);
return status;
}
#include "util/types.h"
#include <stdbool.h>
+struct perf_mmap {
+ void *base;
+ int mask;
+ unsigned int prev;
+};
+
+static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
+{
+ struct perf_event_mmap_page *pc = mm->base;
+ int head = pc->data_head;
+ rmb();
+ return head;
+}
+
+static inline void perf_mmap__write_tail(struct perf_mmap *md,
+ unsigned long tail)
+{
+ struct perf_event_mmap_page *pc = md->base;
+
+ /*
+ * ensure all reads are done before we write the tail out.
+ */
+ /* mb(); */
+ pc->data_tail = tail;
+}
+
/*
* prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all
* counters in the current task.
--- /dev/null
+#! /usr/bin/python
+# -*- python -*-
+# -*- coding: utf-8 -*-
+# twatch - Experimental use of the perf python interface
+# Copyright (C) 2011 Arnaldo Carvalho de Melo <acme@redhat.com>
+#
+# This application 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; version 2.
+#
+# This application 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.
+
+import perf
+
+def main():
+ cpus = perf.cpu_map()
+ threads = perf.thread_map()
+ evsel = perf.evsel(task = 1, comm = 1, mmap = 0,
+ wakeup_events = 1, sample_period = 1,
+ sample_id_all = 1,
+ sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_TID)
+ evsel.open(cpus = cpus, threads = threads);
+ evlist = perf.evlist(cpus, threads)
+ evlist.add(evsel)
+ evlist.mmap()
+ while True:
+ evlist.poll(timeout = -1)
+ for cpu in cpus:
+ event = evlist.read_on_cpu(cpu)
+ if not event:
+ continue
+ print "cpu: %2d, pid: %4d, tid: %4d" % (event.sample_cpu,
+ event.sample_pid,
+ event.sample_tid),
+ print event
+
+if __name__ == '__main__':
+ main()
--- /dev/null
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-annotate.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "util.h"
+#include "build-id.h"
+#include "color.h"
+#include "cache.h"
+#include "symbol.h"
+#include "debug.h"
+#include "annotate.h"
+#include <pthread.h>
+
+int symbol__annotate_init(struct map *map __used, struct symbol *sym)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ pthread_mutex_init(¬es->lock, NULL);
+ return 0;
+}
+
+int symbol__alloc_hist(struct symbol *sym, int nevents)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ size_t sizeof_sym_hist = (sizeof(struct sym_hist) +
+ (sym->end - sym->start) * sizeof(u64));
+
+ notes->src = zalloc(sizeof(*notes->src) + nevents * sizeof_sym_hist);
+ if (notes->src == NULL)
+ return -1;
+ notes->src->sizeof_sym_hist = sizeof_sym_hist;
+ notes->src->nr_histograms = nevents;
+ INIT_LIST_HEAD(¬es->src->source);
+ return 0;
+}
+
+void symbol__annotate_zero_histograms(struct symbol *sym)
+{
+ struct annotation *notes = symbol__annotation(sym);
+
+ pthread_mutex_lock(¬es->lock);
+ if (notes->src != NULL)
+ memset(notes->src->histograms, 0,
+ notes->src->nr_histograms * notes->src->sizeof_sym_hist);
+ pthread_mutex_unlock(¬es->lock);
+}
+
+int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+ int evidx, u64 addr)
+{
+ unsigned offset;
+ struct annotation *notes;
+ struct sym_hist *h;
+
+ notes = symbol__annotation(sym);
+ if (notes->src == NULL)
+ return -ENOMEM;
+
+ pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
+
+ if (addr >= sym->end)
+ return 0;
+
+ offset = addr - sym->start;
+ h = annotation__histogram(notes, evidx);
+ h->sum++;
+ h->addr[offset]++;
+
+ pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
+ ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name,
+ addr, addr - sym->start, evidx, h->addr[offset]);
+ return 0;
+}
+
+static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize)
+{
+ struct objdump_line *self = malloc(sizeof(*self) + privsize);
+
+ if (self != NULL) {
+ self->offset = offset;
+ self->line = line;
+ }
+
+ return self;
+}
+
+void objdump_line__free(struct objdump_line *self)
+{
+ free(self->line);
+ free(self);
+}
+
+static void objdump__add_line(struct list_head *head, struct objdump_line *line)
+{
+ list_add_tail(&line->node, head);
+}
+
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+ struct objdump_line *pos)
+{
+ list_for_each_entry_continue(pos, head, node)
+ if (pos->offset >= 0)
+ return pos;
+
+ return NULL;
+}
+
+static int objdump_line__print(struct objdump_line *oline, struct symbol *sym,
+ int evidx, u64 len, int min_pcnt,
+ int printed, int max_lines,
+ struct objdump_line *queue)
+{
+ static const char *prev_line;
+ static const char *prev_color;
+
+ if (oline->offset != -1) {
+ const char *path = NULL;
+ unsigned int hits = 0;
+ double percent = 0.0;
+ const char *color;
+ struct annotation *notes = symbol__annotation(sym);
+ struct source_line *src_line = notes->src->lines;
+ struct sym_hist *h = annotation__histogram(notes, evidx);
+ s64 offset = oline->offset;
+ struct objdump_line *next;
+
+ next = objdump__get_next_ip_line(¬es->src->source, oline);
+
+ while (offset < (s64)len &&
+ (next == NULL || offset < next->offset)) {
+ if (src_line) {
+ if (path == NULL)
+ path = src_line[offset].path;
+ percent += src_line[offset].percent;
+ } else
+ hits += h->addr[offset];
+
+ ++offset;
+ }
+
+ if (src_line == NULL && h->sum)
+ percent = 100.0 * hits / h->sum;
+
+ if (percent < min_pcnt)
+ return -1;
+
+ if (max_lines && printed >= max_lines)
+ return 1;
+
+ if (queue != NULL) {
+ list_for_each_entry_from(queue, ¬es->src->source, node) {
+ if (queue == oline)
+ break;
+ objdump_line__print(queue, sym, evidx, len,
+ 0, 0, 1, NULL);
+ }
+ }
+
+ color = get_percent_color(percent);
+
+ /*
+ * Also color the filename and line if needed, with
+ * the same color than the percentage. Don't print it
+ * twice for close colored addr with the same filename:line
+ */
+ if (path) {
+ if (!prev_line || strcmp(prev_line, path)
+ || color != prev_color) {
+ color_fprintf(stdout, color, " %s", path);
+ prev_line = path;
+ prev_color = color;
+ }
+ }
+
+ color_fprintf(stdout, color, " %7.2f", percent);
+ printf(" : ");
+ color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", oline->line);
+ } else if (max_lines && printed >= max_lines)
+ return 1;
+ else {
+ if (queue)
+ return -1;
+
+ if (!*oline->line)
+ printf(" :\n");
+ else
+ printf(" : %s\n", oline->line);
+ }
+
+ return 0;
+}
+
+static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
+ FILE *file, size_t privsize)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct objdump_line *objdump_line;
+ char *line = NULL, *tmp, *tmp2, *c;
+ size_t line_len;
+ s64 line_ip, offset = -1;
+
+ if (getline(&line, &line_len, file) < 0)
+ return -1;
+
+ if (!line)
+ return -1;
+
+ while (line_len != 0 && isspace(line[line_len - 1]))
+ line[--line_len] = '\0';
+
+ c = strchr(line, '\n');
+ if (c)
+ *c = 0;
+
+ line_ip = -1;
+
+ /*
+ * Strip leading spaces:
+ */
+ tmp = line;
+ while (*tmp) {
+ if (*tmp != ' ')
+ break;
+ tmp++;
+ }
+
+ if (*tmp) {
+ /*
+ * Parse hexa addresses followed by ':'
+ */
+ line_ip = strtoull(tmp, &tmp2, 16);
+ if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
+ line_ip = -1;
+ }
+
+ if (line_ip != -1) {
+ u64 start = map__rip_2objdump(map, sym->start),
+ end = map__rip_2objdump(map, sym->end);
+
+ offset = line_ip - start;
+ if (offset < 0 || (u64)line_ip > end)
+ offset = -1;
+ }
+
+ objdump_line = objdump_line__new(offset, line, privsize);
+ if (objdump_line == NULL) {
+ free(line);
+ return -1;
+ }
+ objdump__add_line(¬es->src->source, objdump_line);
+
+ return 0;
+}
+
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
+{
+ struct dso *dso = map->dso;
+ char *filename = dso__build_id_filename(dso, NULL, 0);
+ bool free_filename = true;
+ char command[PATH_MAX * 2];
+ FILE *file;
+ int err = 0;
+ char symfs_filename[PATH_MAX];
+
+ if (filename) {
+ snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+ symbol_conf.symfs, filename);
+ }
+
+ if (filename == NULL) {
+ if (dso->has_build_id) {
+ pr_err("Can't annotate %s: not enough memory\n",
+ sym->name);
+ return -ENOMEM;
+ }
+ goto fallback;
+ } else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
+ strstr(command, "[kernel.kallsyms]") ||
+ access(symfs_filename, R_OK)) {
+ free(filename);
+fallback:
+ /*
+ * If we don't have build-ids or the build-id file isn't in the
+ * cache, or is just a kallsyms file, well, lets hope that this
+ * DSO is the same as when 'perf record' ran.
+ */
+ filename = dso->long_name;
+ snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+ symbol_conf.symfs, filename);
+ free_filename = false;
+ }
+
+ if (dso->origin == DSO__ORIG_KERNEL) {
+ char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
+ char *build_id_msg = NULL;
+
+ if (dso->annotate_warned)
+ goto out_free_filename;
+
+ if (dso->has_build_id) {
+ build_id__sprintf(dso->build_id,
+ sizeof(dso->build_id), bf + 15);
+ build_id_msg = bf;
+ }
+ err = -ENOENT;
+ dso->annotate_warned = 1;
+ pr_err("Can't annotate %s: No vmlinux file%s was found in the "
+ "path.\nPlease use 'perf buildid-cache -av vmlinux' or "
+ "--vmlinux vmlinux.\n",
+ sym->name, build_id_msg ?: "");
+ goto out_free_filename;
+ }
+
+ pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
+ filename, sym->name, map->unmap_ip(map, sym->start),
+ map->unmap_ip(map, sym->end));
+
+ pr_debug("annotating [%p] %30s : [%p] %30s\n",
+ dso, dso->long_name, sym, sym->name);
+
+ snprintf(command, sizeof(command),
+ "objdump --start-address=0x%016" PRIx64
+ " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand",
+ map__rip_2objdump(map, sym->start),
+ map__rip_2objdump(map, sym->end),
+ symfs_filename, filename);
+
+ pr_debug("Executing: %s\n", command);
+
+ file = popen(command, "r");
+ if (!file)
+ goto out_free_filename;
+
+ while (!feof(file))
+ if (symbol__parse_objdump_line(sym, map, file, privsize) < 0)
+ break;
+
+ pclose(file);
+out_free_filename:
+ if (free_filename)
+ free(filename);
+ return err;
+}
+
+static void insert_source_line(struct rb_root *root, struct source_line *src_line)
+{
+ struct source_line *iter;
+ struct rb_node **p = &root->rb_node;
+ struct rb_node *parent = NULL;
+
+ while (*p != NULL) {
+ parent = *p;
+ iter = rb_entry(parent, struct source_line, node);
+
+ if (src_line->percent > iter->percent)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+
+ rb_link_node(&src_line->node, parent, p);
+ rb_insert_color(&src_line->node, root);
+}
+
+static void symbol__free_source_line(struct symbol *sym, int len)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct source_line *src_line = notes->src->lines;
+ int i;
+
+ for (i = 0; i < len; i++)
+ free(src_line[i].path);
+
+ free(src_line);
+ notes->src->lines = NULL;
+}
+
+/* Get the filename:line for the colored entries */
+static int symbol__get_source_line(struct symbol *sym, struct map *map,
+ int evidx, struct rb_root *root, int len,
+ const char *filename)
+{
+ u64 start;
+ int i;
+ char cmd[PATH_MAX * 2];
+ struct source_line *src_line;
+ struct annotation *notes = symbol__annotation(sym);
+ struct sym_hist *h = annotation__histogram(notes, evidx);
+
+ if (!h->sum)
+ return 0;
+
+ src_line = notes->src->lines = calloc(len, sizeof(struct source_line));
+ if (!notes->src->lines)
+ return -1;
+
+ start = map->unmap_ip(map, sym->start);
+
+ for (i = 0; i < len; i++) {
+ char *path = NULL;
+ size_t line_len;
+ u64 offset;
+ FILE *fp;
+
+ src_line[i].percent = 100.0 * h->addr[i] / h->sum;
+ if (src_line[i].percent <= 0.5)
+ continue;
+
+ offset = start + i;
+ sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
+ fp = popen(cmd, "r");
+ if (!fp)
+ continue;
+
+ if (getline(&path, &line_len, fp) < 0 || !line_len)
+ goto next;
+
+ src_line[i].path = malloc(sizeof(char) * line_len + 1);
+ if (!src_line[i].path)
+ goto next;
+
+ strcpy(src_line[i].path, path);
+ insert_source_line(root, &src_line[i]);
+
+ next:
+ pclose(fp);
+ }
+
+ return 0;
+}
+
+static void print_summary(struct rb_root *root, const char *filename)
+{
+ struct source_line *src_line;
+ struct rb_node *node;
+
+ printf("\nSorted summary for file %s\n", filename);
+ printf("----------------------------------------------\n\n");
+
+ if (RB_EMPTY_ROOT(root)) {
+ printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
+ return;
+ }
+
+ node = rb_first(root);
+ while (node) {
+ double percent;
+ const char *color;
+ char *path;
+
+ src_line = rb_entry(node, struct source_line, node);
+ percent = src_line->percent;
+ color = get_percent_color(percent);
+ path = src_line->path;
+
+ color_fprintf(stdout, color, " %7.2f %s", percent, path);
+ node = rb_next(node);
+ }
+}
+
+static void symbol__annotate_hits(struct symbol *sym, int evidx)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct sym_hist *h = annotation__histogram(notes, evidx);
+ u64 len = sym->end - sym->start, offset;
+
+ for (offset = 0; offset < len; ++offset)
+ if (h->addr[offset] != 0)
+ printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
+ sym->start + offset, h->addr[offset]);
+ printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+}
+
+int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
+ bool full_paths, int min_pcnt, int max_lines,
+ int context)
+{
+ struct dso *dso = map->dso;
+ const char *filename = dso->long_name, *d_filename;
+ struct annotation *notes = symbol__annotation(sym);
+ struct objdump_line *pos, *queue = NULL;
+ int printed = 2, queue_len = 0;
+ int more = 0;
+ u64 len;
+
+ if (full_paths)
+ d_filename = filename;
+ else
+ d_filename = basename(filename);
+
+ len = sym->end - sym->start;
+
+ printf(" Percent | Source code & Disassembly of %s\n", d_filename);
+ printf("------------------------------------------------\n");
+
+ if (verbose)
+ symbol__annotate_hits(sym, evidx);
+
+ list_for_each_entry(pos, ¬es->src->source, node) {
+ if (context && queue == NULL) {
+ queue = pos;
+ queue_len = 0;
+ }
+
+ switch (objdump_line__print(pos, sym, evidx, len, min_pcnt,
+ printed, max_lines, queue)) {
+ case 0:
+ ++printed;
+ if (context) {
+ printed += queue_len;
+ queue = NULL;
+ queue_len = 0;
+ }
+ break;
+ case 1:
+ /* filtered by max_lines */
+ ++more;
+ break;
+ case -1:
+ default:
+ /*
+ * Filtered by min_pcnt or non IP lines when
+ * context != 0
+ */
+ if (!context)
+ break;
+ if (queue_len == context)
+ queue = list_entry(queue->node.next, typeof(*queue), node);
+ else
+ ++queue_len;
+ break;
+ }
+ }
+
+ return more;
+}
+
+void symbol__annotate_zero_histogram(struct symbol *sym, int evidx)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct sym_hist *h = annotation__histogram(notes, evidx);
+
+ memset(h, 0, notes->src->sizeof_sym_hist);
+}
+
+void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct sym_hist *h = annotation__histogram(notes, evidx);
+ struct objdump_line *pos;
+ int len = sym->end - sym->start;
+
+ h->sum = 0;
+
+ list_for_each_entry(pos, ¬es->src->source, node) {
+ if (pos->offset != -1 && pos->offset < len) {
+ h->addr[pos->offset] = h->addr[pos->offset] * 7 / 8;
+ h->sum += h->addr[pos->offset];
+ }
+ }
+}
+
+void objdump_line_list__purge(struct list_head *head)
+{
+ struct objdump_line *pos, *n;
+
+ list_for_each_entry_safe(pos, n, head, node) {
+ list_del(&pos->node);
+ objdump_line__free(pos);
+ }
+}
+
+int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
+ bool print_lines, bool full_paths, int min_pcnt,
+ int max_lines)
+{
+ struct dso *dso = map->dso;
+ const char *filename = dso->long_name;
+ struct rb_root source_line = RB_ROOT;
+ u64 len;
+
+ if (symbol__annotate(sym, map, 0) < 0)
+ return -1;
+
+ len = sym->end - sym->start;
+
+ if (print_lines) {
+ symbol__get_source_line(sym, map, evidx, &source_line,
+ len, filename);
+ print_summary(&source_line, filename);
+ }
+
+ symbol__annotate_printf(sym, map, evidx, full_paths,
+ min_pcnt, max_lines, 0);
+ if (print_lines)
+ symbol__free_source_line(sym, len);
+
+ objdump_line_list__purge(&symbol__annotation(sym)->src->source);
+
+ return 0;
+}
--- /dev/null
+#ifndef __PERF_ANNOTATE_H
+#define __PERF_ANNOTATE_H
+
+#include <stdbool.h>
+#include "types.h"
+#include "symbol.h"
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+struct objdump_line {
+ struct list_head node;
+ s64 offset;
+ char *line;
+};
+
+void objdump_line__free(struct objdump_line *self);
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+ struct objdump_line *pos);
+
+struct sym_hist {
+ u64 sum;
+ u64 addr[0];
+};
+
+struct source_line {
+ struct rb_node node;
+ double percent;
+ char *path;
+};
+
+/** struct annotated_source - symbols with hits have this attached as in sannotation
+ *
+ * @histogram: Array of addr hit histograms per event being monitored
+ * @lines: If 'print_lines' is specified, per source code line percentages
+ * @source: source parsed from objdump -dS
+ *
+ * lines is allocated, percentages calculated and all sorted by percentage
+ * when the annotation is about to be presented, so the percentages are for
+ * one of the entries in the histogram array, i.e. for the event/counter being
+ * presented. It is deallocated right after symbol__{tui,tty,etc}_annotate
+ * returns.
+ */
+struct annotated_source {
+ struct list_head source;
+ struct source_line *lines;
+ int nr_histograms;
+ int sizeof_sym_hist;
+ struct sym_hist histograms[0];
+};
+
+struct annotation {
+ pthread_mutex_t lock;
+ struct annotated_source *src;
+};
+
+struct sannotation {
+ struct annotation annotation;
+ struct symbol symbol;
+};
+
+static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
+{
+ return (((void *)¬es->src->histograms) +
+ (notes->src->sizeof_sym_hist * idx));
+}
+
+static inline struct annotation *symbol__annotation(struct symbol *sym)
+{
+ struct sannotation *a = container_of(sym, struct sannotation, symbol);
+ return &a->annotation;
+}
+
+int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+ int evidx, u64 addr);
+int symbol__alloc_hist(struct symbol *sym, int nevents);
+void symbol__annotate_zero_histograms(struct symbol *sym);
+
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+int symbol__annotate_init(struct map *map __used, struct symbol *sym);
+int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
+ bool full_paths, int min_pcnt, int max_lines,
+ int context);
+void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
+void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
+void objdump_line_list__purge(struct list_head *head);
+
+int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
+ bool print_lines, bool full_paths, int min_pcnt,
+ int max_lines);
+
+#ifdef NO_NEWT_SUPPORT
+static inline int symbol__tui_annotate(struct symbol *sym __used,
+ struct map *map __used,
+ int evidx __used, int refresh __used)
+{
+ return 0;
+}
+#else
+int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+ int refresh);
+#endif
+
+#endif /* __PERF_ANNOTATE_H */
#include <linux/kernel.h>
#include "debug.h"
-static int build_id__mark_dso_hit(event_t *event,
- struct sample_data *sample __used,
+static int build_id__mark_dso_hit(union perf_event *event,
+ struct perf_sample *sample __used,
struct perf_session *session)
{
struct addr_location al;
return 0;
}
-static int event__exit_del_thread(event_t *self, struct sample_data *sample __used,
- struct perf_session *session)
+static int perf_event__exit_del_thread(union perf_event *event,
+ struct perf_sample *sample __used,
+ struct perf_session *session)
{
- struct thread *thread = perf_session__findnew(session, self->fork.tid);
+ struct thread *thread = perf_session__findnew(session, event->fork.tid);
- dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
- self->fork.ppid, self->fork.ptid);
+ dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
+ event->fork.ppid, event->fork.ptid);
if (thread) {
rb_erase(&thread->rb_node, &session->threads);
struct perf_event_ops build_id__mark_dso_hit_ops = {
.sample = build_id__mark_dso_hit,
- .mmap = event__process_mmap,
- .fork = event__process_task,
- .exit = event__exit_del_thread,
+ .mmap = perf_event__process_mmap,
+ .fork = perf_event__process_task,
+ .exit = perf_event__exit_del_thread,
};
char *dso__build_id_filename(struct dso *self, char *bf, size_t size)
extern int use_browser;
#ifdef NO_NEWT_SUPPORT
-static inline void setup_browser(void)
+static inline void setup_browser(bool fallback_to_pager)
{
- setup_pager();
+ if (fallback_to_pager)
+ setup_pager();
}
static inline void exit_browser(bool wait_for_ok __used) {}
#else
-void setup_browser(void);
+void setup_browser(bool fallback_to_pager);
void exit_browser(bool wait_for_ok);
#endif
/*
- * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com>
*
* Handle the callchains from the stream in an ad-hoc radix tree and then
* sort them in an rbtree.
#include "util.h"
#include "callchain.h"
-bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
+bool ip_callchain__valid(struct ip_callchain *chain,
+ const union perf_event *event)
{
unsigned int chain_size = event->header.size;
chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
}
#define chain_for_each_child(child, parent) \
- list_for_each_entry(child, &parent->children, brothers)
+ list_for_each_entry(child, &parent->children, siblings)
#define chain_for_each_child_safe(child, next, parent) \
- list_for_each_entry_safe(child, next, &parent->children, brothers)
+ list_for_each_entry_safe(child, next, &parent->children, siblings)
static void
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct callchain_node *rnode;
- u64 chain_cumul = cumul_hits(chain);
+ u64 chain_cumul = callchain_cumul_hits(chain);
while (*p) {
u64 rnode_cumul;
parent = *p;
rnode = rb_entry(parent, struct callchain_node, rb_node);
- rnode_cumul = cumul_hits(rnode);
+ rnode_cumul = callchain_cumul_hits(rnode);
switch (mode) {
case CHAIN_FLAT:
chain_for_each_child(child, node) {
__sort_chain_graph_abs(child, min_hit);
- if (cumul_hits(child) >= min_hit)
+ if (callchain_cumul_hits(child) >= min_hit)
rb_insert_callchain(&node->rb_root, child,
CHAIN_GRAPH_ABS);
}
chain_for_each_child(child, node) {
__sort_chain_graph_rel(child, min_percent);
- if (cumul_hits(child) >= min_hit)
+ if (callchain_cumul_hits(child) >= min_hit)
rb_insert_callchain(&node->rb_root, child,
CHAIN_GRAPH_REL);
}
rb_root->rb_node = chain_root->node.rb_root.rb_node;
}
-int register_callchain_param(struct callchain_param *param)
+int callchain_register_param(struct callchain_param *param)
{
switch (param->mode) {
case CHAIN_GRAPH_ABS:
chain_for_each_child(next, new)
next->parent = new;
}
- list_add_tail(&new->brothers, &parent->children);
+ list_add_tail(&new->siblings, &parent->children);
return new;
}
-struct resolved_ip {
- u64 ip;
- struct map_symbol ms;
-};
-
-struct resolved_chain {
- u64 nr;
- struct resolved_ip ips[0];
-};
-
-
/*
* Fill the node with callchain values
*/
static void
-fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
+fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
{
- unsigned int i;
+ struct callchain_cursor_node *cursor_node;
+
+ node->val_nr = cursor->nr - cursor->pos;
+ if (!node->val_nr)
+ pr_warning("Warning: empty node in callchain tree\n");
- for (i = start; i < chain->nr; i++) {
+ cursor_node = callchain_cursor_current(cursor);
+
+ while (cursor_node) {
struct callchain_list *call;
call = zalloc(sizeof(*call));
perror("not enough memory for the code path tree");
return;
}
- call->ip = chain->ips[i].ip;
- call->ms = chain->ips[i].ms;
+ call->ip = cursor_node->ip;
+ call->ms.sym = cursor_node->sym;
+ call->ms.map = cursor_node->map;
list_add_tail(&call->list, &node->val);
+
+ callchain_cursor_advance(cursor);
+ cursor_node = callchain_cursor_current(cursor);
}
- node->val_nr = chain->nr - start;
- if (!node->val_nr)
- pr_warning("Warning: empty node in callchain tree\n");
}
static void
-add_child(struct callchain_node *parent, struct resolved_chain *chain,
- int start, u64 period)
+add_child(struct callchain_node *parent,
+ struct callchain_cursor *cursor,
+ u64 period)
{
struct callchain_node *new;
new = create_child(parent, false);
- fill_node(new, chain, start);
+ fill_node(new, cursor);
new->children_hit = 0;
new->hit = period;
* Then create another child to host the given callchain of new branch
*/
static void
-split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
- struct callchain_list *to_split, int idx_parents, int idx_local,
- u64 period)
+split_add_child(struct callchain_node *parent,
+ struct callchain_cursor *cursor,
+ struct callchain_list *to_split,
+ u64 idx_parents, u64 idx_local, u64 period)
{
struct callchain_node *new;
struct list_head *old_tail;
/* split the hits */
new->hit = parent->hit;
new->children_hit = parent->children_hit;
- parent->children_hit = cumul_hits(new);
+ parent->children_hit = callchain_cumul_hits(new);
new->val_nr = parent->val_nr - idx_local;
parent->val_nr = idx_local;
/* create a new child for the new branch if any */
- if (idx_total < chain->nr) {
+ if (idx_total < cursor->nr) {
parent->hit = 0;
- add_child(parent, chain, idx_total, period);
+ add_child(parent, cursor, period);
parent->children_hit += period;
} else {
parent->hit = period;
}
static int
-append_chain(struct callchain_node *root, struct resolved_chain *chain,
- unsigned int start, u64 period);
+append_chain(struct callchain_node *root,
+ struct callchain_cursor *cursor,
+ u64 period);
static void
-append_chain_children(struct callchain_node *root, struct resolved_chain *chain,
- unsigned int start, u64 period)
+append_chain_children(struct callchain_node *root,
+ struct callchain_cursor *cursor,
+ u64 period)
{
struct callchain_node *rnode;
/* lookup in childrens */
chain_for_each_child(rnode, root) {
- unsigned int ret = append_chain(rnode, chain, start, period);
+ unsigned int ret = append_chain(rnode, cursor, period);
if (!ret)
goto inc_children_hit;
}
/* nothing in children, add to the current node */
- add_child(root, chain, start, period);
+ add_child(root, cursor, period);
inc_children_hit:
root->children_hit += period;
}
static int
-append_chain(struct callchain_node *root, struct resolved_chain *chain,
- unsigned int start, u64 period)
+append_chain(struct callchain_node *root,
+ struct callchain_cursor *cursor,
+ u64 period)
{
+ struct callchain_cursor_node *curr_snap = cursor->curr;
struct callchain_list *cnode;
- unsigned int i = start;
+ u64 start = cursor->pos;
bool found = false;
+ u64 matches;
/*
* Lookup in the current node
* anywhere inside a function.
*/
list_for_each_entry(cnode, &root->val, list) {
+ struct callchain_cursor_node *node;
struct symbol *sym;
- if (i == chain->nr)
+ node = callchain_cursor_current(cursor);
+ if (!node)
break;
- sym = chain->ips[i].ms.sym;
+ sym = node->sym;
if (cnode->ms.sym && sym) {
if (cnode->ms.sym->start != sym->start)
break;
- } else if (cnode->ip != chain->ips[i].ip)
+ } else if (cnode->ip != node->ip)
break;
if (!found)
found = true;
- i++;
+
+ callchain_cursor_advance(cursor);
}
/* matches not, relay on the parent */
- if (!found)
+ if (!found) {
+ cursor->curr = curr_snap;
+ cursor->pos = start;
return -1;
+ }
+
+ matches = cursor->pos - start;
/* we match only a part of the node. Split it and add the new chain */
- if (i - start < root->val_nr) {
- split_add_child(root, chain, cnode, start, i - start, period);
+ if (matches < root->val_nr) {
+ split_add_child(root, cursor, cnode, start, matches, period);
return 0;
}
/* we match 100% of the path, increment the hit */
- if (i - start == root->val_nr && i == chain->nr) {
+ if (matches == root->val_nr && cursor->pos == cursor->nr) {
root->hit += period;
return 0;
}
/* We match the node and still have a part remaining */
- append_chain_children(root, chain, i, period);
+ append_chain_children(root, cursor, period);
return 0;
}
-static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
- struct map_symbol *syms)
-{
- int i, j = 0;
-
- for (i = 0; i < (int)old->nr; i++) {
- if (old->ips[i] >= PERF_CONTEXT_MAX)
- continue;
-
- new->ips[j].ip = old->ips[i];
- new->ips[j].ms = syms[i];
- j++;
- }
-
- new->nr = j;
-}
-
-
-int callchain_append(struct callchain_root *root, struct ip_callchain *chain,
- struct map_symbol *syms, u64 period)
+int callchain_append(struct callchain_root *root,
+ struct callchain_cursor *cursor,
+ u64 period)
{
- struct resolved_chain *filtered;
-
- if (!chain->nr)
+ if (!cursor->nr)
return 0;
- filtered = zalloc(sizeof(*filtered) +
- chain->nr * sizeof(struct resolved_ip));
- if (!filtered)
- return -ENOMEM;
-
- filter_context(chain, filtered, syms);
-
- if (!filtered->nr)
- goto end;
+ callchain_cursor_commit(cursor);
- append_chain_children(&root->node, filtered, 0, period);
+ append_chain_children(&root->node, cursor, period);
- if (filtered->nr > root->max_depth)
- root->max_depth = filtered->nr;
-end:
- free(filtered);
+ if (cursor->nr > root->max_depth)
+ root->max_depth = cursor->nr;
return 0;
}
static int
-merge_chain_branch(struct callchain_node *dst, struct callchain_node *src,
- struct resolved_chain *chain)
+merge_chain_branch(struct callchain_cursor *cursor,
+ struct callchain_node *dst, struct callchain_node *src)
{
+ struct callchain_cursor_node **old_last = cursor->last;
struct callchain_node *child, *next_child;
struct callchain_list *list, *next_list;
- int old_pos = chain->nr;
+ int old_pos = cursor->nr;
int err = 0;
list_for_each_entry_safe(list, next_list, &src->val, list) {
- chain->ips[chain->nr].ip = list->ip;
- chain->ips[chain->nr].ms = list->ms;
- chain->nr++;
+ callchain_cursor_append(cursor, list->ip,
+ list->ms.map, list->ms.sym);
list_del(&list->list);
free(list);
}
- if (src->hit)
- append_chain_children(dst, chain, 0, src->hit);
+ if (src->hit) {
+ callchain_cursor_commit(cursor);
+ append_chain_children(dst, cursor, src->hit);
+ }
chain_for_each_child_safe(child, next_child, src) {
- err = merge_chain_branch(dst, child, chain);
+ err = merge_chain_branch(cursor, dst, child);
if (err)
break;
- list_del(&child->brothers);
+ list_del(&child->siblings);
free(child);
}
- chain->nr = old_pos;
+ cursor->nr = old_pos;
+ cursor->last = old_last;
return err;
}
-int callchain_merge(struct callchain_root *dst, struct callchain_root *src)
+int callchain_merge(struct callchain_cursor *cursor,
+ struct callchain_root *dst, struct callchain_root *src)
+{
+ return merge_chain_branch(cursor, &dst->node, &src->node);
+}
+
+int callchain_cursor_append(struct callchain_cursor *cursor,
+ u64 ip, struct map *map, struct symbol *sym)
{
- struct resolved_chain *chain;
- int err;
+ struct callchain_cursor_node *node = *cursor->last;
- chain = malloc(sizeof(*chain) +
- src->max_depth * sizeof(struct resolved_ip));
- if (!chain)
- return -ENOMEM;
+ if (!node) {
+ node = calloc(sizeof(*node), 1);
+ if (!node)
+ return -ENOMEM;
- chain->nr = 0;
+ *cursor->last = node;
+ }
- err = merge_chain_branch(&dst->node, &src->node, chain);
+ node->ip = ip;
+ node->map = map;
+ node->sym = sym;
- free(chain);
+ cursor->nr++;
- return err;
+ cursor->last = &node->next;
+
+ return 0;
}
struct callchain_node {
struct callchain_node *parent;
- struct list_head brothers;
+ struct list_head siblings;
struct list_head children;
struct list_head val;
struct rb_node rb_node; /* to sort nodes in an rbtree */
struct list_head list;
};
+/*
+ * A callchain cursor is a single linked list that
+ * let one feed a callchain progressively.
+ * It keeps persitent allocated entries to minimize
+ * allocations.
+ */
+struct callchain_cursor_node {
+ u64 ip;
+ struct map *map;
+ struct symbol *sym;
+ struct callchain_cursor_node *next;
+};
+
+struct callchain_cursor {
+ u64 nr;
+ struct callchain_cursor_node *first;
+ struct callchain_cursor_node **last;
+ u64 pos;
+ struct callchain_cursor_node *curr;
+};
+
static inline void callchain_init(struct callchain_root *root)
{
- INIT_LIST_HEAD(&root->node.brothers);
+ INIT_LIST_HEAD(&root->node.siblings);
INIT_LIST_HEAD(&root->node.children);
INIT_LIST_HEAD(&root->node.val);
root->max_depth = 0;
}
-static inline u64 cumul_hits(struct callchain_node *node)
+static inline u64 callchain_cumul_hits(struct callchain_node *node)
{
return node->hit + node->children_hit;
}
-int register_callchain_param(struct callchain_param *param);
-int callchain_append(struct callchain_root *root, struct ip_callchain *chain,
- struct map_symbol *syms, u64 period);
-int callchain_merge(struct callchain_root *dst, struct callchain_root *src);
+int callchain_register_param(struct callchain_param *param);
+int callchain_append(struct callchain_root *root,
+ struct callchain_cursor *cursor,
+ u64 period);
+
+int callchain_merge(struct callchain_cursor *cursor,
+ struct callchain_root *dst, struct callchain_root *src);
+
+bool ip_callchain__valid(struct ip_callchain *chain,
+ const union perf_event *event);
+/*
+ * Initialize a cursor before adding entries inside, but keep
+ * the previously allocated entries as a cache.
+ */
+static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
+{
+ cursor->nr = 0;
+ cursor->last = &cursor->first;
+}
+
+int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
+ struct map *map, struct symbol *sym);
-bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event);
+/* Close a cursor writing session. Initialize for the reader */
+static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
+{
+ cursor->curr = cursor->first;
+ cursor->pos = 0;
+}
+
+/* Cursor reading iteration helpers */
+static inline struct callchain_cursor_node *
+callchain_cursor_current(struct callchain_cursor *cursor)
+{
+ if (cursor->pos == cursor->nr)
+ return NULL;
+
+ return cursor->curr;
+}
+
+static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
+{
+ cursor->curr = cursor->curr->next;
+ cursor->pos++;
+}
#endif /* __PERF_CALLCHAIN_H */
--- /dev/null
+#include "util.h"
+#include "../perf.h"
+#include "parse-options.h"
+#include "evsel.h"
+#include "cgroup.h"
+#include "debugfs.h" /* MAX_PATH, STR() */
+#include "evlist.h"
+
+int nr_cgroups;
+
+static int
+cgroupfs_find_mountpoint(char *buf, size_t maxlen)
+{
+ FILE *fp;
+ char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1];
+ char *token, *saved_ptr;
+ int found = 0;
+
+ fp = fopen("/proc/mounts", "r");
+ if (!fp)
+ return -1;
+
+ /*
+ * in order to handle split hierarchy, we need to scan /proc/mounts
+ * and inspect every cgroupfs mount point to find one that has
+ * perf_event subsystem
+ */
+ while (fscanf(fp, "%*s %"STR(MAX_PATH)"s %"STR(MAX_PATH)"s %"
+ STR(MAX_PATH)"s %*d %*d\n",
+ mountpoint, type, tokens) == 3) {
+
+ if (!strcmp(type, "cgroup")) {
+
+ token = strtok_r(tokens, ",", &saved_ptr);
+
+ while (token != NULL) {
+ if (!strcmp(token, "perf_event")) {
+ found = 1;
+ break;
+ }
+ token = strtok_r(NULL, ",", &saved_ptr);
+ }
+ }
+ if (found)
+ break;
+ }
+ fclose(fp);
+ if (!found)
+ return -1;
+
+ if (strlen(mountpoint) < maxlen) {
+ strcpy(buf, mountpoint);
+ return 0;
+ }
+ return -1;
+}
+
+static int open_cgroup(char *name)
+{
+ char path[MAX_PATH+1];
+ char mnt[MAX_PATH+1];
+ int fd;
+
+
+ if (cgroupfs_find_mountpoint(mnt, MAX_PATH+1))
+ return -1;
+
+ snprintf(path, MAX_PATH, "%s/%s", mnt, name);
+
+ fd = open(path, O_RDONLY);
+ if (fd == -1)
+ fprintf(stderr, "no access to cgroup %s\n", path);
+
+ return fd;
+}
+
+static int add_cgroup(struct perf_evlist *evlist, char *str)
+{
+ struct perf_evsel *counter;
+ struct cgroup_sel *cgrp = NULL;
+ int n;
+ /*
+ * check if cgrp is already defined, if so we reuse it
+ */
+ list_for_each_entry(counter, &evlist->entries, node) {
+ cgrp = counter->cgrp;
+ if (!cgrp)
+ continue;
+ if (!strcmp(cgrp->name, str))
+ break;
+
+ cgrp = NULL;
+ }
+
+ if (!cgrp) {
+ cgrp = zalloc(sizeof(*cgrp));
+ if (!cgrp)
+ return -1;
+
+ cgrp->name = str;
+
+ cgrp->fd = open_cgroup(str);
+ if (cgrp->fd == -1) {
+ free(cgrp);
+ return -1;
+ }
+ }
+
+ /*
+ * find corresponding event
+ * if add cgroup N, then need to find event N
+ */
+ n = 0;
+ list_for_each_entry(counter, &evlist->entries, node) {
+ if (n == nr_cgroups)
+ goto found;
+ n++;
+ }
+ if (cgrp->refcnt == 0)
+ free(cgrp);
+
+ return -1;
+found:
+ cgrp->refcnt++;
+ counter->cgrp = cgrp;
+ return 0;
+}
+
+void close_cgroup(struct cgroup_sel *cgrp)
+{
+ if (!cgrp)
+ return;
+
+ /* XXX: not reentrant */
+ if (--cgrp->refcnt == 0) {
+ close(cgrp->fd);
+ free(cgrp->name);
+ free(cgrp);
+ }
+}
+
+int parse_cgroups(const struct option *opt __used, const char *str,
+ int unset __used)
+{
+ struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+ const char *p, *e, *eos = str + strlen(str);
+ char *s;
+ int ret;
+
+ if (list_empty(&evlist->entries)) {
+ fprintf(stderr, "must define events before cgroups\n");
+ return -1;
+ }
+
+ for (;;) {
+ p = strchr(str, ',');
+ e = p ? p : eos;
+
+ /* allow empty cgroups, i.e., skip */
+ if (e - str) {
+ /* termination added */
+ s = strndup(str, e - str);
+ if (!s)
+ return -1;
+ ret = add_cgroup(evlist, s);
+ if (ret) {
+ free(s);
+ return -1;
+ }
+ }
+ /* nr_cgroups is increased een for empty cgroups */
+ nr_cgroups++;
+ if (!p)
+ break;
+ str = p+1;
+ }
+ return 0;
+}
--- /dev/null
+#ifndef __CGROUP_H__
+#define __CGROUP_H__
+
+struct option;
+
+struct cgroup_sel {
+ char *name;
+ int fd;
+ int refcnt;
+};
+
+
+extern int nr_cgroups; /* number of explicit cgroups defined */
+extern void close_cgroup(struct cgroup_sel *cgrp);
+extern int parse_cgroups(const struct option *opt, const char *str, int unset);
+
+#endif /* __CGROUP_H__ */
return cpus;
}
+
+void cpu_map__delete(struct cpu_map *map)
+{
+ free(map);
+}
struct cpu_map *cpu_map__new(const char *cpu_list);
struct cpu_map *cpu_map__dummy_new(void);
-void *cpu_map__delete(struct cpu_map *map);
+void cpu_map__delete(struct cpu_map *map);
#endif /* __PERF_CPUMAP_H */
}
#endif
-void trace_event(event_t *event)
+void trace_event(union perf_event *event)
{
unsigned char *raw_event = (void *)event;
const char *color = PERF_COLOR_BLUE;
extern bool quiet, dump_trace;
int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
-void trace_event(event_t *event);
+void trace_event(union perf_event *event);
struct ui_progress;
#include "string.h"
#include "strlist.h"
#include "thread.h"
+#include "thread_map.h"
-static const char *event__name[] = {
+static const char *perf_event__names[] = {
[0] = "TOTAL",
[PERF_RECORD_MMAP] = "MMAP",
[PERF_RECORD_LOST] = "LOST",
[PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND",
};
-const char *event__get_event_name(unsigned int id)
+const char *perf_event__name(unsigned int id)
{
- if (id >= ARRAY_SIZE(event__name))
+ if (id >= ARRAY_SIZE(perf_event__names))
return "INVALID";
- if (!event__name[id])
+ if (!perf_event__names[id])
return "UNKNOWN";
- return event__name[id];
+ return perf_event__names[id];
}
-static struct sample_data synth_sample = {
+static struct perf_sample synth_sample = {
.pid = -1,
.tid = -1,
.time = -1,
.period = 1,
};
-static pid_t event__synthesize_comm(event_t *event, pid_t pid, int full,
- event__handler_t process,
- struct perf_session *session)
+static pid_t perf_event__synthesize_comm(union perf_event *event, pid_t pid,
+ int full, perf_event__handler_t process,
+ struct perf_session *session)
{
char filename[PATH_MAX];
char bf[BUFSIZ];
return tgid;
}
-static int event__synthesize_mmap_events(event_t *event, pid_t pid, pid_t tgid,
- event__handler_t process,
- struct perf_session *session)
+static int perf_event__synthesize_mmap_events(union perf_event *event,
+ pid_t pid, pid_t tgid,
+ perf_event__handler_t process,
+ struct perf_session *session)
{
char filename[PATH_MAX];
FILE *fp;
return 0;
}
-int event__synthesize_modules(event__handler_t process,
- struct perf_session *session,
- struct machine *machine)
+int perf_event__synthesize_modules(perf_event__handler_t process,
+ struct perf_session *session,
+ struct machine *machine)
{
struct rb_node *nd;
struct map_groups *kmaps = &machine->kmaps;
- event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size);
-
+ union perf_event *event = zalloc((sizeof(event->mmap) +
+ session->id_hdr_size));
if (event == NULL) {
pr_debug("Not enough memory synthesizing mmap event "
"for kernel modules\n");
return 0;
}
-static int __event__synthesize_thread(event_t *comm_event, event_t *mmap_event,
- pid_t pid, event__handler_t process,
+static int __event__synthesize_thread(union perf_event *comm_event,
+ union perf_event *mmap_event,
+ pid_t pid, perf_event__handler_t process,
struct perf_session *session)
{
- pid_t tgid = event__synthesize_comm(comm_event, pid, 1, process,
+ pid_t tgid = perf_event__synthesize_comm(comm_event, pid, 1, process,
session);
if (tgid == -1)
return -1;
- return event__synthesize_mmap_events(mmap_event, pid, tgid,
+ return perf_event__synthesize_mmap_events(mmap_event, pid, tgid,
process, session);
}
-int event__synthesize_thread(pid_t pid, event__handler_t process,
- struct perf_session *session)
+int perf_event__synthesize_thread_map(struct thread_map *threads,
+ perf_event__handler_t process,
+ struct perf_session *session)
{
- event_t *comm_event, *mmap_event;
- int err = -1;
+ union perf_event *comm_event, *mmap_event;
+ int err = -1, thread;
comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
if (comm_event == NULL)
if (mmap_event == NULL)
goto out_free_comm;
- err = __event__synthesize_thread(comm_event, mmap_event, pid,
- process, session);
+ err = 0;
+ for (thread = 0; thread < threads->nr; ++thread) {
+ if (__event__synthesize_thread(comm_event, mmap_event,
+ threads->map[thread],
+ process, session)) {
+ err = -1;
+ break;
+ }
+ }
free(mmap_event);
out_free_comm:
free(comm_event);
return err;
}
-int event__synthesize_threads(event__handler_t process,
- struct perf_session *session)
+int perf_event__synthesize_threads(perf_event__handler_t process,
+ struct perf_session *session)
{
DIR *proc;
struct dirent dirent, *next;
- event_t *comm_event, *mmap_event;
+ union perf_event *comm_event, *mmap_event;
int err = -1;
comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
return 1;
}
-int event__synthesize_kernel_mmap(event__handler_t process,
- struct perf_session *session,
- struct machine *machine,
- const char *symbol_name)
+int perf_event__synthesize_kernel_mmap(perf_event__handler_t process,
+ struct perf_session *session,
+ struct machine *machine,
+ const char *symbol_name)
{
size_t size;
const char *filename, *mmap_name;
* kernels.
*/
struct process_symbol_args args = { .name = symbol_name, };
- event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size);
-
+ union perf_event *event = zalloc((sizeof(event->mmap) +
+ session->id_hdr_size));
if (event == NULL) {
pr_debug("Not enough memory synthesizing mmap event "
"for kernel modules\n");
return err;
}
-static void thread__comm_adjust(struct thread *self, struct hists *hists)
-{
- char *comm = self->comm;
-
- if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
- (!symbol_conf.comm_list ||
- strlist__has_entry(symbol_conf.comm_list, comm))) {
- u16 slen = strlen(comm);
-
- if (hists__new_col_len(hists, HISTC_COMM, slen))
- hists__set_col_len(hists, HISTC_THREAD, slen + 6);
- }
-}
-
-static int thread__set_comm_adjust(struct thread *self, const char *comm,
- struct hists *hists)
-{
- int ret = thread__set_comm(self, comm);
-
- if (ret)
- return ret;
-
- thread__comm_adjust(self, hists);
-
- return 0;
-}
-
-int event__process_comm(event_t *self, struct sample_data *sample __used,
- struct perf_session *session)
+int perf_event__process_comm(union perf_event *event,
+ struct perf_sample *sample __used,
+ struct perf_session *session)
{
- struct thread *thread = perf_session__findnew(session, self->comm.tid);
+ struct thread *thread = perf_session__findnew(session, event->comm.tid);
- dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid);
+ dump_printf(": %s:%d\n", event->comm.comm, event->comm.tid);
- if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm,
- &session->hists)) {
+ if (thread == NULL || thread__set_comm(thread, event->comm.comm)) {
dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
return -1;
}
return 0;
}
-int event__process_lost(event_t *self, struct sample_data *sample __used,
- struct perf_session *session)
+int perf_event__process_lost(union perf_event *event,
+ struct perf_sample *sample __used,
+ struct perf_session *session)
{
dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
- self->lost.id, self->lost.lost);
- session->hists.stats.total_lost += self->lost.lost;
+ event->lost.id, event->lost.lost);
+ session->hists.stats.total_lost += event->lost.lost;
return 0;
}
-static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
+static void perf_event__set_kernel_mmap_len(union perf_event *event,
+ struct map **maps)
{
- maps[MAP__FUNCTION]->start = self->mmap.start;
- maps[MAP__FUNCTION]->end = self->mmap.start + self->mmap.len;
+ maps[MAP__FUNCTION]->start = event->mmap.start;
+ maps[MAP__FUNCTION]->end = event->mmap.start + event->mmap.len;
/*
* Be a bit paranoid here, some perf.data file came with
* a zero sized synthesized MMAP event for the kernel.
maps[MAP__FUNCTION]->end = ~0ULL;
}
-static int event__process_kernel_mmap(event_t *self,
- struct perf_session *session)
+static int perf_event__process_kernel_mmap(union perf_event *event,
+ struct perf_session *session)
{
struct map *map;
char kmmap_prefix[PATH_MAX];
enum dso_kernel_type kernel_type;
bool is_kernel_mmap;
- machine = perf_session__findnew_machine(session, self->mmap.pid);
+ machine = perf_session__findnew_machine(session, event->mmap.pid);
if (!machine) {
- pr_err("Can't find id %d's machine\n", self->mmap.pid);
+ pr_err("Can't find id %d's machine\n", event->mmap.pid);
goto out_problem;
}
else
kernel_type = DSO_TYPE_GUEST_KERNEL;
- is_kernel_mmap = memcmp(self->mmap.filename,
+ is_kernel_mmap = memcmp(event->mmap.filename,
kmmap_prefix,
strlen(kmmap_prefix)) == 0;
- if (self->mmap.filename[0] == '/' ||
- (!is_kernel_mmap && self->mmap.filename[0] == '[')) {
+ if (event->mmap.filename[0] == '/' ||
+ (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
char short_module_name[1024];
char *name, *dot;
- if (self->mmap.filename[0] == '/') {
- name = strrchr(self->mmap.filename, '/');
+ if (event->mmap.filename[0] == '/') {
+ name = strrchr(event->mmap.filename, '/');
if (name == NULL)
goto out_problem;
"[%.*s]", (int)(dot - name), name);
strxfrchar(short_module_name, '-', '_');
} else
- strcpy(short_module_name, self->mmap.filename);
+ strcpy(short_module_name, event->mmap.filename);
- map = machine__new_module(machine, self->mmap.start,
- self->mmap.filename);
+ map = machine__new_module(machine, event->mmap.start,
+ event->mmap.filename);
if (map == NULL)
goto out_problem;
map->dso->short_name = name;
map->dso->sname_alloc = 1;
- map->end = map->start + self->mmap.len;
+ map->end = map->start + event->mmap.len;
} else if (is_kernel_mmap) {
- const char *symbol_name = (self->mmap.filename +
+ const char *symbol_name = (event->mmap.filename +
strlen(kmmap_prefix));
/*
* Should be there already, from the build-id table in
if (__machine__create_kernel_maps(machine, kernel) < 0)
goto out_problem;
- event_set_kernel_mmap_len(machine->vmlinux_maps, self);
+ perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
symbol_name,
- self->mmap.pgoff);
+ event->mmap.pgoff);
if (machine__is_default_guest(machine)) {
/*
* preload dso of guest kernel and modules
return -1;
}
-int event__process_mmap(event_t *self, struct sample_data *sample __used,
- struct perf_session *session)
+int perf_event__process_mmap(union perf_event *event,
+ struct perf_sample *sample __used,
+ struct perf_session *session)
{
struct machine *machine;
struct thread *thread;
struct map *map;
- u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
int ret = 0;
dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
- self->mmap.pid, self->mmap.tid, self->mmap.start,
- self->mmap.len, self->mmap.pgoff, self->mmap.filename);
+ event->mmap.pid, event->mmap.tid, event->mmap.start,
+ event->mmap.len, event->mmap.pgoff, event->mmap.filename);
if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
cpumode == PERF_RECORD_MISC_KERNEL) {
- ret = event__process_kernel_mmap(self, session);
+ ret = perf_event__process_kernel_mmap(event, session);
if (ret < 0)
goto out_problem;
return 0;
machine = perf_session__find_host_machine(session);
if (machine == NULL)
goto out_problem;
- thread = perf_session__findnew(session, self->mmap.pid);
+ thread = perf_session__findnew(session, event->mmap.pid);
if (thread == NULL)
goto out_problem;
- map = map__new(&machine->user_dsos, self->mmap.start,
- self->mmap.len, self->mmap.pgoff,
- self->mmap.pid, self->mmap.filename,
+ map = map__new(&machine->user_dsos, event->mmap.start,
+ event->mmap.len, event->mmap.pgoff,
+ event->mmap.pid, event->mmap.filename,
MAP__FUNCTION);
if (map == NULL)
goto out_problem;
return 0;
}
-int event__process_task(event_t *self, struct sample_data *sample __used,
- struct perf_session *session)
+int perf_event__process_task(union perf_event *event,
+ struct perf_sample *sample __used,
+ struct perf_session *session)
{
- struct thread *thread = perf_session__findnew(session, self->fork.tid);
- struct thread *parent = perf_session__findnew(session, self->fork.ptid);
+ struct thread *thread = perf_session__findnew(session, event->fork.tid);
+ struct thread *parent = perf_session__findnew(session, event->fork.ptid);
- dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
- self->fork.ppid, self->fork.ptid);
+ dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
+ event->fork.ppid, event->fork.ptid);
- if (self->header.type == PERF_RECORD_EXIT) {
+ if (event->header.type == PERF_RECORD_EXIT) {
perf_session__remove_thread(session, thread);
return 0;
}
return 0;
}
-int event__process(event_t *event, struct sample_data *sample,
- struct perf_session *session)
+int perf_event__process(union perf_event *event, struct perf_sample *sample,
+ struct perf_session *session)
{
switch (event->header.type) {
case PERF_RECORD_COMM:
- event__process_comm(event, sample, session);
+ perf_event__process_comm(event, sample, session);
break;
case PERF_RECORD_MMAP:
- event__process_mmap(event, sample, session);
+ perf_event__process_mmap(event, sample, session);
break;
case PERF_RECORD_FORK:
case PERF_RECORD_EXIT:
- event__process_task(event, sample, session);
+ perf_event__process_task(event, sample, session);
break;
+ case PERF_RECORD_LOST:
+ perf_event__process_lost(event, sample, session);
default:
break;
}
al->sym = NULL;
}
-static void dso__calc_col_width(struct dso *self, struct hists *hists)
-{
- if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
- (!symbol_conf.dso_list ||
- strlist__has_entry(symbol_conf.dso_list, self->name))) {
- u16 slen = dso__name_len(self);
- hists__new_col_len(hists, HISTC_DSO, slen);
- }
-
- self->slen_calculated = 1;
-}
-
-int event__preprocess_sample(const event_t *self, struct perf_session *session,
- struct addr_location *al, struct sample_data *data,
- symbol_filter_t filter)
+int perf_event__preprocess_sample(const union perf_event *event,
+ struct perf_session *session,
+ struct addr_location *al,
+ struct perf_sample *sample,
+ symbol_filter_t filter)
{
- u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- struct thread *thread = perf_session__findnew(session, self->ip.pid);
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ struct thread *thread = perf_session__findnew(session, event->ip.pid);
if (thread == NULL)
return -1;
machine__create_kernel_maps(&session->host_machine);
thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
- self->ip.pid, self->ip.ip, al);
+ event->ip.pid, event->ip.ip, al);
dump_printf(" ...... dso: %s\n",
al->map ? al->map->dso->long_name :
al->level == 'H' ? "[hypervisor]" : "<not found>");
al->sym = NULL;
- al->cpu = data->cpu;
+ al->cpu = sample->cpu;
if (al->map) {
if (symbol_conf.dso_list &&
strlist__has_entry(symbol_conf.dso_list,
al->map->dso->long_name)))))
goto out_filtered;
- /*
- * We have to do this here as we may have a dso with no symbol
- * hit that has a name longer than the ones with symbols
- * sampled.
- */
- if (!sort_dso.elide && !al->map->dso->slen_calculated)
- dso__calc_col_width(al->map->dso, &session->hists);
al->sym = map__find_symbol(al->map, al->addr, filter);
- } else {
- const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
-
- if (hists__col_len(&session->hists, HISTC_DSO) < unresolved_col_width &&
- !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
- !symbol_conf.dso_list)
- hists__set_col_len(&session->hists, HISTC_DSO,
- unresolved_col_width);
}
if (symbol_conf.sym_list && al->sym &&
al->filtered = true;
return 0;
}
-
-static int event__parse_id_sample(const event_t *event,
- struct perf_session *session,
- struct sample_data *sample)
-{
- const u64 *array;
- u64 type;
-
- sample->cpu = sample->pid = sample->tid = -1;
- sample->stream_id = sample->id = sample->time = -1ULL;
-
- if (!session->sample_id_all)
- return 0;
-
- array = event->sample.array;
- array += ((event->header.size -
- sizeof(event->header)) / sizeof(u64)) - 1;
- type = session->sample_type;
-
- if (type & PERF_SAMPLE_CPU) {
- u32 *p = (u32 *)array;
- sample->cpu = *p;
- array--;
- }
-
- if (type & PERF_SAMPLE_STREAM_ID) {
- sample->stream_id = *array;
- array--;
- }
-
- if (type & PERF_SAMPLE_ID) {
- sample->id = *array;
- array--;
- }
-
- if (type & PERF_SAMPLE_TIME) {
- sample->time = *array;
- array--;
- }
-
- if (type & PERF_SAMPLE_TID) {
- u32 *p = (u32 *)array;
- sample->pid = p[0];
- sample->tid = p[1];
- }
-
- return 0;
-}
-
-int event__parse_sample(const event_t *event, struct perf_session *session,
- struct sample_data *data)
-{
- const u64 *array;
- u64 type;
-
- if (event->header.type != PERF_RECORD_SAMPLE)
- return event__parse_id_sample(event, session, data);
-
- array = event->sample.array;
- type = session->sample_type;
-
- if (type & PERF_SAMPLE_IP) {
- data->ip = event->ip.ip;
- array++;
- }
-
- if (type & PERF_SAMPLE_TID) {
- u32 *p = (u32 *)array;
- data->pid = p[0];
- data->tid = p[1];
- array++;
- }
-
- if (type & PERF_SAMPLE_TIME) {
- data->time = *array;
- array++;
- }
-
- if (type & PERF_SAMPLE_ADDR) {
- data->addr = *array;
- array++;
- }
-
- data->id = -1ULL;
- if (type & PERF_SAMPLE_ID) {
- data->id = *array;
- array++;
- }
-
- if (type & PERF_SAMPLE_STREAM_ID) {
- data->stream_id = *array;
- array++;
- }
-
- if (type & PERF_SAMPLE_CPU) {
- u32 *p = (u32 *)array;
- data->cpu = *p;
- array++;
- } else
- data->cpu = -1;
-
- if (type & PERF_SAMPLE_PERIOD) {
- data->period = *array;
- array++;
- }
-
- if (type & PERF_SAMPLE_READ) {
- pr_debug("PERF_SAMPLE_READ is unsuported for now\n");
- return -1;
- }
-
- if (type & PERF_SAMPLE_CALLCHAIN) {
- data->callchain = (struct ip_callchain *)array;
- array += 1 + data->callchain->nr;
- }
-
- if (type & PERF_SAMPLE_RAW) {
- u32 *p = (u32 *)array;
- data->raw_size = *p;
- p++;
- data->raw_data = p;
- }
-
- return 0;
-}
u64 array[];
};
-struct sample_data {
+struct perf_sample {
u64 ip;
u32 pid, tid;
u64 time;
u32 size;
};
-typedef union event_union {
+union perf_event {
struct perf_event_header header;
struct ip_event ip;
struct mmap_event mmap;
struct event_type_event event_type;
struct tracing_data_event tracing_data;
struct build_id_event build_id;
-} event_t;
+};
-void event__print_totals(void);
+void perf_event__print_totals(void);
struct perf_session;
+struct thread_map;
-typedef int (*event__handler_synth_t)(event_t *event,
+typedef int (*perf_event__handler_synth_t)(union perf_event *event,
+ struct perf_session *session);
+typedef int (*perf_event__handler_t)(union perf_event *event,
+ struct perf_sample *sample,
struct perf_session *session);
-typedef int (*event__handler_t)(event_t *event, struct sample_data *sample,
- struct perf_session *session);
-int event__synthesize_thread(pid_t pid, event__handler_t process,
+int perf_event__synthesize_thread_map(struct thread_map *threads,
+ perf_event__handler_t process,
+ struct perf_session *session);
+int perf_event__synthesize_threads(perf_event__handler_t process,
+ struct perf_session *session);
+int perf_event__synthesize_kernel_mmap(perf_event__handler_t process,
+ struct perf_session *session,
+ struct machine *machine,
+ const char *symbol_name);
+
+int perf_event__synthesize_modules(perf_event__handler_t process,
+ struct perf_session *session,
+ struct machine *machine);
+
+int perf_event__process_comm(union perf_event *event, struct perf_sample *sample,
struct perf_session *session);
-int event__synthesize_threads(event__handler_t process,
- struct perf_session *session);
-int event__synthesize_kernel_mmap(event__handler_t process,
- struct perf_session *session,
- struct machine *machine,
- const char *symbol_name);
-
-int event__synthesize_modules(event__handler_t process,
- struct perf_session *session,
- struct machine *machine);
-
-int event__process_comm(event_t *self, struct sample_data *sample,
- struct perf_session *session);
-int event__process_lost(event_t *self, struct sample_data *sample,
- struct perf_session *session);
-int event__process_mmap(event_t *self, struct sample_data *sample,
- struct perf_session *session);
-int event__process_task(event_t *self, struct sample_data *sample,
+int perf_event__process_lost(union perf_event *event, struct perf_sample *sample,
+ struct perf_session *session);
+int perf_event__process_mmap(union perf_event *event, struct perf_sample *sample,
+ struct perf_session *session);
+int perf_event__process_task(union perf_event *event, struct perf_sample *sample,
+ struct perf_session *session);
+int perf_event__process(union perf_event *event, struct perf_sample *sample,
struct perf_session *session);
-int event__process(event_t *event, struct sample_data *sample,
- struct perf_session *session);
struct addr_location;
-int event__preprocess_sample(const event_t *self, struct perf_session *session,
- struct addr_location *al, struct sample_data *data,
- symbol_filter_t filter);
-int event__parse_sample(const event_t *event, struct perf_session *session,
- struct sample_data *sample);
+int perf_event__preprocess_sample(const union perf_event *self,
+ struct perf_session *session,
+ struct addr_location *al,
+ struct perf_sample *sample,
+ symbol_filter_t filter);
+
+const char *perf_event__name(unsigned int id);
-const char *event__get_event_name(unsigned int id);
+int perf_event__parse_sample(const union perf_event *event, u64 type,
+ bool sample_id_all, struct perf_sample *sample);
#endif /* __PERF_RECORD_H */
--- /dev/null
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include <poll.h>
+#include "cpumap.h"
+#include "thread_map.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "util.h"
+
+#include <sys/mman.h>
+
+#include <linux/bitops.h>
+#include <linux/hash.h>
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+ struct thread_map *threads)
+{
+ int i;
+
+ for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
+ INIT_HLIST_HEAD(&evlist->heads[i]);
+ INIT_LIST_HEAD(&evlist->entries);
+ perf_evlist__set_maps(evlist, cpus, threads);
+}
+
+struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
+ struct thread_map *threads)
+{
+ struct perf_evlist *evlist = zalloc(sizeof(*evlist));
+
+ if (evlist != NULL)
+ perf_evlist__init(evlist, cpus, threads);
+
+ return evlist;
+}
+
+static void perf_evlist__purge(struct perf_evlist *evlist)
+{
+ struct perf_evsel *pos, *n;
+
+ list_for_each_entry_safe(pos, n, &evlist->entries, node) {
+ list_del_init(&pos->node);
+ perf_evsel__delete(pos);
+ }
+
+ evlist->nr_entries = 0;
+}
+
+void perf_evlist__exit(struct perf_evlist *evlist)
+{
+ free(evlist->mmap);
+ free(evlist->pollfd);
+ evlist->mmap = NULL;
+ evlist->pollfd = NULL;
+}
+
+void perf_evlist__delete(struct perf_evlist *evlist)
+{
+ perf_evlist__purge(evlist);
+ perf_evlist__exit(evlist);
+ free(evlist);
+}
+
+void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
+{
+ list_add_tail(&entry->node, &evlist->entries);
+ ++evlist->nr_entries;
+}
+
+int perf_evlist__add_default(struct perf_evlist *evlist)
+{
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ };
+ struct perf_evsel *evsel = perf_evsel__new(&attr, 0);
+
+ if (evsel == NULL)
+ return -ENOMEM;
+
+ perf_evlist__add(evlist, evsel);
+ return 0;
+}
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+{
+ int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
+ evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
+ return evlist->pollfd != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+{
+ fcntl(fd, F_SETFL, O_NONBLOCK);
+ evlist->pollfd[evlist->nr_fds].fd = fd;
+ evlist->pollfd[evlist->nr_fds].events = POLLIN;
+ evlist->nr_fds++;
+}
+
+static void perf_evlist__id_hash(struct perf_evlist *evlist,
+ struct perf_evsel *evsel,
+ int cpu, int thread, u64 id)
+{
+ int hash;
+ struct perf_sample_id *sid = SID(evsel, cpu, thread);
+
+ sid->id = id;
+ sid->evsel = evsel;
+ hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
+ hlist_add_head(&sid->node, &evlist->heads[hash]);
+}
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+ int cpu, int thread, u64 id)
+{
+ perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
+ evsel->id[evsel->ids++] = id;
+}
+
+static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+ struct perf_evsel *evsel,
+ int cpu, int thread, int fd)
+{
+ u64 read_data[4] = { 0, };
+ int id_idx = 1; /* The first entry is the counter value */
+
+ if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
+ read(fd, &read_data, sizeof(read_data)) == -1)
+ return -1;
+
+ if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+ ++id_idx;
+ if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+ ++id_idx;
+
+ perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]);
+ return 0;
+}
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
+{
+ struct hlist_head *head;
+ struct hlist_node *pos;
+ struct perf_sample_id *sid;
+ int hash;
+
+ if (evlist->nr_entries == 1)
+ return list_entry(evlist->entries.next, struct perf_evsel, node);
+
+ hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
+ head = &evlist->heads[hash];
+
+ hlist_for_each_entry(sid, pos, head, node)
+ if (sid->id == id)
+ return sid->evsel;
+ return NULL;
+}
+
+union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
+{
+ /* XXX Move this to perf.c, making it generally available */
+ unsigned int page_size = sysconf(_SC_PAGE_SIZE);
+ struct perf_mmap *md = &evlist->mmap[cpu];
+ unsigned int head = perf_mmap__read_head(md);
+ unsigned int old = md->prev;
+ unsigned char *data = md->base + page_size;
+ union perf_event *event = NULL;
+
+ if (evlist->overwrite) {
+ /*
+ * If we're further behind than half the buffer, there's a chance
+ * the writer will bite our tail and mess up the samples under us.
+ *
+ * If we somehow ended up ahead of the head, we got messed up.
+ *
+ * In either case, truncate and restart at head.
+ */
+ int diff = head - old;
+ if (diff > md->mask / 2 || diff < 0) {
+ fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
+
+ /*
+ * head points to a known good entry, start there.
+ */
+ old = head;
+ }
+ }
+
+ if (old != head) {
+ size_t size;
+
+ event = (union perf_event *)&data[old & md->mask];
+ size = event->header.size;
+
+ /*
+ * Event straddles the mmap boundary -- header should always
+ * be inside due to u64 alignment of output.
+ */
+ if ((old & md->mask) + size != ((old + size) & md->mask)) {
+ unsigned int offset = old;
+ unsigned int len = min(sizeof(*event), size), cpy;
+ void *dst = &evlist->event_copy;
+
+ do {
+ cpy = min(md->mask + 1 - (offset & md->mask), len);
+ memcpy(dst, &data[offset & md->mask], cpy);
+ offset += cpy;
+ dst += cpy;
+ len -= cpy;
+ } while (len);
+
+ event = &evlist->event_copy;
+ }
+
+ old += size;
+ }
+
+ md->prev = old;
+
+ if (!evlist->overwrite)
+ perf_mmap__write_tail(md, old);
+
+ return event;
+}
+
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+ int cpu;
+
+ for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+ if (evlist->mmap[cpu].base != NULL) {
+ munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+ evlist->mmap[cpu].base = NULL;
+ }
+ }
+}
+
+int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+{
+ evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
+ return evlist->mmap != NULL ? 0 : -ENOMEM;
+}
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
+ int mask, int fd)
+{
+ evlist->mmap[cpu].prev = 0;
+ evlist->mmap[cpu].mask = mask;
+ evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
+ MAP_SHARED, fd, 0);
+ if (evlist->mmap[cpu].base == MAP_FAILED)
+ return -1;
+
+ perf_evlist__add_pollfd(evlist, fd);
+ return 0;
+}
+
+/** perf_evlist__mmap - Create per cpu maps to receive events
+ *
+ * @evlist - list of events
+ * @pages - map length in pages
+ * @overwrite - overwrite older events?
+ *
+ * If overwrite is false the user needs to signal event consuption using:
+ *
+ * struct perf_mmap *m = &evlist->mmap[cpu];
+ * unsigned int head = perf_mmap__read_head(m);
+ *
+ * perf_mmap__write_tail(m, head)
+ *
+ * Using perf_evlist__read_on_cpu does this automatically.
+ */
+int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
+{
+ unsigned int page_size = sysconf(_SC_PAGE_SIZE);
+ int mask = pages * page_size - 1, cpu;
+ struct perf_evsel *first_evsel, *evsel;
+ const struct cpu_map *cpus = evlist->cpus;
+ const struct thread_map *threads = evlist->threads;
+ int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+
+ if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+ return -ENOMEM;
+
+ if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+ return -ENOMEM;
+
+ evlist->overwrite = overwrite;
+ evlist->mmap_len = (pages + 1) * page_size;
+ first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+ evsel->sample_id == NULL &&
+ perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
+ return -ENOMEM;
+
+ for (cpu = 0; cpu < cpus->nr; cpu++) {
+ for (thread = 0; thread < threads->nr; thread++) {
+ int fd = FD(evsel, cpu, thread);
+
+ if (evsel->idx || thread) {
+ if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
+ FD(first_evsel, cpu, 0)) != 0)
+ goto out_unmap;
+ } else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
+ goto out_unmap;
+
+ if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+ perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+ goto out_unmap;
+ }
+ }
+ }
+
+ return 0;
+
+out_unmap:
+ for (cpu = 0; cpu < cpus->nr; cpu++) {
+ if (evlist->mmap[cpu].base != NULL) {
+ munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+ evlist->mmap[cpu].base = NULL;
+ }
+ }
+ return -1;
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
+ pid_t target_tid, const char *cpu_list)
+{
+ evlist->threads = thread_map__new(target_pid, target_tid);
+
+ if (evlist->threads == NULL)
+ return -1;
+
+ if (target_tid != -1)
+ evlist->cpus = cpu_map__dummy_new();
+ else
+ evlist->cpus = cpu_map__new(cpu_list);
+
+ if (evlist->cpus == NULL)
+ goto out_delete_threads;
+
+ return 0;
+
+out_delete_threads:
+ thread_map__delete(evlist->threads);
+ return -1;
+}
+
+void perf_evlist__delete_maps(struct perf_evlist *evlist)
+{
+ cpu_map__delete(evlist->cpus);
+ thread_map__delete(evlist->threads);
+ evlist->cpus = NULL;
+ evlist->threads = NULL;
+}
+
+int perf_evlist__set_filters(struct perf_evlist *evlist)
+{
+ const struct thread_map *threads = evlist->threads;
+ const struct cpu_map *cpus = evlist->cpus;
+ struct perf_evsel *evsel;
+ char *filter;
+ int thread;
+ int cpu;
+ int err;
+ int fd;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ filter = evsel->filter;
+ if (!filter)
+ continue;
+ for (cpu = 0; cpu < cpus->nr; cpu++) {
+ for (thread = 0; thread < threads->nr; thread++) {
+ fd = FD(evsel, cpu, thread);
+ err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter);
+ if (err)
+ return err;
+ }
+ }
+ }
+
+ return 0;
+}
--- /dev/null
+#ifndef __PERF_EVLIST_H
+#define __PERF_EVLIST_H 1
+
+#include <linux/list.h>
+#include "../perf.h"
+#include "event.h"
+
+struct pollfd;
+struct thread_map;
+struct cpu_map;
+
+#define PERF_EVLIST__HLIST_BITS 8
+#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
+
+struct perf_evlist {
+ struct list_head entries;
+ struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
+ int nr_entries;
+ int nr_fds;
+ int mmap_len;
+ bool overwrite;
+ union perf_event event_copy;
+ struct perf_mmap *mmap;
+ struct pollfd *pollfd;
+ struct thread_map *threads;
+ struct cpu_map *cpus;
+};
+
+struct perf_evsel;
+
+struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
+ struct thread_map *threads);
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+ struct thread_map *threads);
+void perf_evlist__exit(struct perf_evlist *evlist);
+void perf_evlist__delete(struct perf_evlist *evlist);
+
+void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
+int perf_evlist__add_default(struct perf_evlist *evlist);
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+ int cpu, int thread, u64 id);
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
+void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
+
+union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu);
+
+int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
+int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
+void perf_evlist__munmap(struct perf_evlist *evlist);
+
+static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
+ struct cpu_map *cpus,
+ struct thread_map *threads)
+{
+ evlist->cpus = cpus;
+ evlist->threads = threads;
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
+ pid_t target_tid, const char *cpu_list);
+void perf_evlist__delete_maps(struct perf_evlist *evlist);
+int perf_evlist__set_filters(struct perf_evlist *evlist);
+
+#endif /* __PERF_EVLIST_H */
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
#include "evsel.h"
-#include "../perf.h"
+#include "evlist.h"
#include "util.h"
#include "cpumap.h"
-#include "thread.h"
+#include "thread_map.h"
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+void perf_evsel__init(struct perf_evsel *evsel,
+ struct perf_event_attr *attr, int idx)
+{
+ evsel->idx = idx;
+ evsel->attr = *attr;
+ INIT_LIST_HEAD(&evsel->node);
+}
+
struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
{
struct perf_evsel *evsel = zalloc(sizeof(*evsel));
- if (evsel != NULL) {
- evsel->idx = idx;
- evsel->attr = *attr;
- INIT_LIST_HEAD(&evsel->node);
- }
+ if (evsel != NULL)
+ perf_evsel__init(evsel, attr, idx);
return evsel;
}
return evsel->fd != NULL ? 0 : -ENOMEM;
}
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+ evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
+ if (evsel->sample_id == NULL)
+ return -ENOMEM;
+
+ evsel->id = zalloc(ncpus * nthreads * sizeof(u64));
+ if (evsel->id == NULL) {
+ xyarray__delete(evsel->sample_id);
+ evsel->sample_id = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
{
evsel->counts = zalloc((sizeof(*evsel->counts) +
evsel->fd = NULL;
}
+void perf_evsel__free_id(struct perf_evsel *evsel)
+{
+ xyarray__delete(evsel->sample_id);
+ evsel->sample_id = NULL;
+ free(evsel->id);
+ evsel->id = NULL;
+}
+
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
int cpu, thread;
}
}
-void perf_evsel__delete(struct perf_evsel *evsel)
+void perf_evsel__exit(struct perf_evsel *evsel)
{
assert(list_empty(&evsel->node));
xyarray__delete(evsel->fd);
+ xyarray__delete(evsel->sample_id);
+ free(evsel->id);
+}
+
+void perf_evsel__delete(struct perf_evsel *evsel)
+{
+ perf_evsel__exit(evsel);
+ close_cgroup(evsel->cgrp);
+ free(evsel->name);
free(evsel);
}
}
static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads)
+ struct thread_map *threads, bool group, bool inherit)
{
int cpu, thread;
+ unsigned long flags = 0;
+ int pid = -1;
if (evsel->fd == NULL &&
perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
return -1;
+ if (evsel->cgrp) {
+ flags = PERF_FLAG_PID_CGROUP;
+ pid = evsel->cgrp->fd;
+ }
+
for (cpu = 0; cpu < cpus->nr; cpu++) {
+ int group_fd = -1;
+ /*
+ * Don't allow mmap() of inherited per-task counters. This
+ * would create a performance issue due to all children writing
+ * to the same buffer.
+ *
+ * FIXME:
+ * Proper fix is not to pass 'inherit' to perf_evsel__open*,
+ * but a 'flags' parameter, with 'group' folded there as well,
+ * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
+ * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
+ * set. Lets go for the minimal fix first tho.
+ */
+ evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
+
for (thread = 0; thread < threads->nr; thread++) {
+
+ if (!evsel->cgrp)
+ pid = threads->map[thread];
+
FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
- threads->map[thread],
- cpus->map[cpu], -1, 0);
+ pid,
+ cpus->map[cpu],
+ group_fd, flags);
if (FD(evsel, cpu, thread) < 0)
goto out_close;
+
+ if (group && group_fd == -1)
+ group_fd = FD(evsel, cpu, thread);
}
}
.threads = { -1, },
};
-int perf_evsel__open(struct perf_evsel *evsel,
- struct cpu_map *cpus, struct thread_map *threads)
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+ struct thread_map *threads, bool group, bool inherit)
{
-
if (cpus == NULL) {
/* Work around old compiler warnings about strict aliasing */
cpus = &empty_cpu_map.map;
if (threads == NULL)
threads = &empty_thread_map.map;
- return __perf_evsel__open(evsel, cpus, threads);
+ return __perf_evsel__open(evsel, cpus, threads, group, inherit);
}
-int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus)
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
+ struct cpu_map *cpus, bool group, bool inherit)
{
- return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
+ return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+}
+
+int perf_evsel__open_per_thread(struct perf_evsel *evsel,
+ struct thread_map *threads, bool group, bool inherit)
+{
+ return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+}
+
+static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
+ struct perf_sample *sample)
+{
+ const u64 *array = event->sample.array;
+
+ array += ((event->header.size -
+ sizeof(event->header)) / sizeof(u64)) - 1;
+
+ if (type & PERF_SAMPLE_CPU) {
+ u32 *p = (u32 *)array;
+ sample->cpu = *p;
+ array--;
+ }
+
+ if (type & PERF_SAMPLE_STREAM_ID) {
+ sample->stream_id = *array;
+ array--;
+ }
+
+ if (type & PERF_SAMPLE_ID) {
+ sample->id = *array;
+ array--;
+ }
+
+ if (type & PERF_SAMPLE_TIME) {
+ sample->time = *array;
+ array--;
+ }
+
+ if (type & PERF_SAMPLE_TID) {
+ u32 *p = (u32 *)array;
+ sample->pid = p[0];
+ sample->tid = p[1];
+ }
+
+ return 0;
}
-int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads)
+int perf_event__parse_sample(const union perf_event *event, u64 type,
+ bool sample_id_all, struct perf_sample *data)
{
- return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
+ const u64 *array;
+
+ data->cpu = data->pid = data->tid = -1;
+ data->stream_id = data->id = data->time = -1ULL;
+
+ if (event->header.type != PERF_RECORD_SAMPLE) {
+ if (!sample_id_all)
+ return 0;
+ return perf_event__parse_id_sample(event, type, data);
+ }
+
+ array = event->sample.array;
+
+ if (type & PERF_SAMPLE_IP) {
+ data->ip = event->ip.ip;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_TID) {
+ u32 *p = (u32 *)array;
+ data->pid = p[0];
+ data->tid = p[1];
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_TIME) {
+ data->time = *array;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_ADDR) {
+ data->addr = *array;
+ array++;
+ }
+
+ data->id = -1ULL;
+ if (type & PERF_SAMPLE_ID) {
+ data->id = *array;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_STREAM_ID) {
+ data->stream_id = *array;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_CPU) {
+ u32 *p = (u32 *)array;
+ data->cpu = *p;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_PERIOD) {
+ data->period = *array;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_READ) {
+ fprintf(stderr, "PERF_SAMPLE_READ is unsuported for now\n");
+ return -1;
+ }
+
+ if (type & PERF_SAMPLE_CALLCHAIN) {
+ data->callchain = (struct ip_callchain *)array;
+ array += 1 + data->callchain->nr;
+ }
+
+ if (type & PERF_SAMPLE_RAW) {
+ u32 *p = (u32 *)array;
+ data->raw_size = *p;
+ p++;
+ data->raw_data = p;
+ }
+
+ return 0;
}
#include "../../../include/linux/perf_event.h"
#include "types.h"
#include "xyarray.h"
+#include "cgroup.h"
+#include "hist.h"
struct perf_counts_values {
union {
struct perf_counts_values cpu[];
};
+struct perf_evsel;
+
+/*
+ * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
+ * more than one entry in the evlist.
+ */
+struct perf_sample_id {
+ struct hlist_node node;
+ u64 id;
+ struct perf_evsel *evsel;
+};
+
+/** struct perf_evsel - event selector
+ *
+ * @name - Can be set to retain the original event name passed by the user,
+ * so that when showing results in tools such as 'perf stat', we
+ * show the name used, not some alias.
+ */
struct perf_evsel {
struct list_head node;
struct perf_event_attr attr;
char *filter;
struct xyarray *fd;
+ struct xyarray *sample_id;
+ u64 *id;
struct perf_counts *counts;
int idx;
- void *priv;
+ int ids;
+ struct hists hists;
+ char *name;
+ union {
+ void *priv;
+ off_t id_offset;
+ };
+ struct cgroup_sel *cgrp;
};
struct cpu_map;
struct thread_map;
+struct perf_evlist;
struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
+void perf_evsel__init(struct perf_evsel *evsel,
+ struct perf_event_attr *attr, int idx);
+void perf_evsel__exit(struct perf_evsel *evsel);
void perf_evsel__delete(struct perf_evsel *evsel);
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+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__free_fd(struct perf_evsel *evsel);
+void perf_evsel__free_id(struct perf_evsel *evsel);
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
-int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus);
-int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads);
-int perf_evsel__open(struct perf_evsel *evsel,
- struct cpu_map *cpus, struct thread_map *threads);
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
+ struct cpu_map *cpus, bool group, bool inherit);
+int perf_evsel__open_per_thread(struct perf_evsel *evsel,
+ struct thread_map *threads, bool group, bool inherit);
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+ struct thread_map *threads, bool group, bool inherit);
#define perf_evsel__match(evsel, t, c) \
(evsel->attr.type == PERF_TYPE_##t && \
const char *system_path(const char *path)
{
-#ifdef RUNTIME_PREFIX
- static const char *prefix;
-#else
static const char *prefix = PREFIX;
-#endif
struct strbuf d = STRBUF_INIT;
if (is_absolute_path(path))
return path;
-#ifdef RUNTIME_PREFIX
- assert(argv0_path);
- assert(is_absolute_path(argv0_path));
-
- if (!prefix &&
- !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) &&
- !(prefix = strip_path_suffix(argv0_path, BINDIR)) &&
- !(prefix = strip_path_suffix(argv0_path, "perf"))) {
- prefix = PREFIX;
- fprintf(stderr, "RUNTIME_PREFIX requested, "
- "but prefix computation failed. "
- "Using static fallback '%s'.\n", prefix);
- }
-#endif
-
strbuf_addf(&d, "%s/%s", prefix, path);
path = strbuf_detach(&d, NULL);
return path;
#include <linux/list.h>
#include <linux/kernel.h>
+#include "evlist.h"
+#include "evsel.h"
#include "util.h"
#include "header.h"
#include "../perf.h"
static bool no_buildid_cache = false;
-/*
- * Create new perf.data header attribute:
- */
-struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr)
-{
- struct perf_header_attr *self = malloc(sizeof(*self));
-
- if (self != NULL) {
- self->attr = *attr;
- self->ids = 0;
- self->size = 1;
- self->id = malloc(sizeof(u64));
- if (self->id == NULL) {
- free(self);
- self = NULL;
- }
- }
-
- return self;
-}
-
-void perf_header_attr__delete(struct perf_header_attr *self)
-{
- free(self->id);
- free(self);
-}
-
-int perf_header_attr__add_id(struct perf_header_attr *self, u64 id)
-{
- int pos = self->ids;
-
- self->ids++;
- if (self->ids > self->size) {
- int nsize = self->size * 2;
- u64 *nid = realloc(self->id, nsize * sizeof(u64));
-
- if (nid == NULL)
- return -1;
-
- self->size = nsize;
- self->id = nid;
- }
- self->id[pos] = id;
- return 0;
-}
-
-int perf_header__init(struct perf_header *self)
-{
- self->size = 1;
- self->attr = malloc(sizeof(void *));
- return self->attr == NULL ? -ENOMEM : 0;
-}
-
-void perf_header__exit(struct perf_header *self)
-{
- int i;
- for (i = 0; i < self->attrs; ++i)
- perf_header_attr__delete(self->attr[i]);
- free(self->attr);
-}
-
-int perf_header__add_attr(struct perf_header *self,
- struct perf_header_attr *attr)
-{
- if (self->frozen)
- return -1;
-
- if (self->attrs == self->size) {
- int nsize = self->size * 2;
- struct perf_header_attr **nattr;
-
- nattr = realloc(self->attr, nsize * sizeof(void *));
- if (nattr == NULL)
- return -1;
-
- self->size = nsize;
- self->attr = nattr;
- }
-
- self->attr[self->attrs++] = attr;
- return 0;
-}
-
static int event_count;
static struct perf_trace_event_type *events;
struct perf_file_section ids;
};
-void perf_header__set_feat(struct perf_header *self, int feat)
+void perf_header__set_feat(struct perf_header *header, int feat)
{
- set_bit(feat, self->adds_features);
+ set_bit(feat, header->adds_features);
}
-void perf_header__clear_feat(struct perf_header *self, int feat)
+void perf_header__clear_feat(struct perf_header *header, int feat)
{
- clear_bit(feat, self->adds_features);
+ clear_bit(feat, header->adds_features);
}
-bool perf_header__has_feat(const struct perf_header *self, int feat)
+bool perf_header__has_feat(const struct perf_header *header, int feat)
{
- return test_bit(feat, self->adds_features);
+ return test_bit(feat, header->adds_features);
}
static int do_write(int fd, const void *buf, size_t size)
return 0;
}
-static int machine__write_buildid_table(struct machine *self, int fd)
+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(self)) {
+ if (!machine__is_host(machine)) {
kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
umisc = PERF_RECORD_MISC_GUEST_USER;
}
- err = __dsos__write_buildid_table(&self->kernel_dsos, self->pid,
+ err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid,
kmisc, fd);
if (err == 0)
- err = __dsos__write_buildid_table(&self->user_dsos,
- self->pid, umisc, fd);
+ err = __dsos__write_buildid_table(&machine->user_dsos,
+ machine->pid, umisc, fd);
return err;
}
const char *name, bool is_kallsyms)
{
const size_t size = PATH_MAX;
- char *realname = realpath(name, NULL),
- *filename = malloc(size),
+ char *realname, *filename = malloc(size),
*linkname = malloc(size), *targetname;
int len, err = -1;
+ if (is_kallsyms)
+ realname = (char *)name;
+ else
+ realname = realpath(name, NULL);
+
if (realname == NULL || filename == NULL || linkname == NULL)
goto out_free;
if (symlink(targetname, linkname) == 0)
err = 0;
out_free:
- free(realname);
+ if (!is_kallsyms)
+ free(realname);
free(filename);
free(linkname);
return err;
return err;
}
-static int dso__cache_build_id(struct dso *self, const char *debugdir)
+static int dso__cache_build_id(struct dso *dso, const char *debugdir)
{
- bool is_kallsyms = self->kernel && self->long_name[0] != '/';
+ bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
- return build_id_cache__add_b(self->build_id, sizeof(self->build_id),
- self->long_name, debugdir, is_kallsyms);
+ return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
+ dso->long_name, debugdir, is_kallsyms);
}
static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
return err;
}
-static int machine__cache_build_ids(struct machine *self, const char *debugdir)
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
{
- int ret = __dsos__cache_build_ids(&self->kernel_dsos, debugdir);
- ret |= __dsos__cache_build_ids(&self->user_dsos, debugdir);
+ int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir);
+ ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir);
return ret;
}
-static int perf_session__cache_build_ids(struct perf_session *self)
+static int perf_session__cache_build_ids(struct perf_session *session)
{
struct rb_node *nd;
int ret;
if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
return -1;
- ret = machine__cache_build_ids(&self->host_machine, debugdir);
+ ret = machine__cache_build_ids(&session->host_machine, debugdir);
- for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node);
ret |= machine__cache_build_ids(pos, debugdir);
}
return ret ? -1 : 0;
}
-static bool machine__read_build_ids(struct machine *self, bool with_hits)
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
{
- bool ret = __dsos__read_build_ids(&self->kernel_dsos, with_hits);
- ret |= __dsos__read_build_ids(&self->user_dsos, with_hits);
+ bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
+ ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
return ret;
}
-static bool perf_session__read_build_ids(struct perf_session *self, bool with_hits)
+static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
{
struct rb_node *nd;
- bool ret = machine__read_build_ids(&self->host_machine, with_hits);
+ bool ret = machine__read_build_ids(&session->host_machine, with_hits);
- for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node);
ret |= machine__read_build_ids(pos, with_hits);
}
return ret;
}
-static int perf_header__adds_write(struct perf_header *self, int fd)
+static int perf_header__adds_write(struct perf_header *header,
+ struct perf_evlist *evlist, int fd)
{
int nr_sections;
struct perf_session *session;
u64 sec_start;
int idx = 0, err;
- session = container_of(self, struct perf_session, header);
+ session = container_of(header, struct perf_session, header);
- if (perf_header__has_feat(self, HEADER_BUILD_ID &&
+ if (perf_header__has_feat(header, HEADER_BUILD_ID &&
!perf_session__read_build_ids(session, true)))
- perf_header__clear_feat(self, HEADER_BUILD_ID);
+ perf_header__clear_feat(header, HEADER_BUILD_ID);
- nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
+ nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
if (!nr_sections)
return 0;
sec_size = sizeof(*feat_sec) * nr_sections;
- sec_start = self->data_offset + self->data_size;
+ sec_start = header->data_offset + header->data_size;
lseek(fd, sec_start + sec_size, SEEK_SET);
- if (perf_header__has_feat(self, HEADER_TRACE_INFO)) {
+ if (perf_header__has_feat(header, HEADER_TRACE_INFO)) {
struct perf_file_section *trace_sec;
trace_sec = &feat_sec[idx++];
/* Write trace info */
trace_sec->offset = lseek(fd, 0, SEEK_CUR);
- read_tracing_data(fd, &evsel_list);
+ read_tracing_data(fd, &evlist->entries);
trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset;
}
- if (perf_header__has_feat(self, HEADER_BUILD_ID)) {
+ if (perf_header__has_feat(header, HEADER_BUILD_ID)) {
struct perf_file_section *buildid_sec;
buildid_sec = &feat_sec[idx++];
/* Write build-ids */
buildid_sec->offset = lseek(fd, 0, SEEK_CUR);
- err = dsos__write_buildid_table(self, fd);
+ err = dsos__write_buildid_table(header, fd);
if (err < 0) {
pr_debug("failed to write buildid table\n");
goto out_free;
return 0;
}
-int perf_header__write(struct perf_header *self, int fd, bool at_exit)
+int perf_session__write_header(struct perf_session *session,
+ struct perf_evlist *evlist,
+ int fd, bool at_exit)
{
struct perf_file_header f_header;
struct perf_file_attr f_attr;
- struct perf_header_attr *attr;
- int i, err;
+ struct perf_header *header = &session->header;
+ struct perf_evsel *attr, *pair = NULL;
+ int err;
lseek(fd, sizeof(f_header), SEEK_SET);
- for (i = 0; i < self->attrs; i++) {
- attr = self->attr[i];
+ if (session->evlist != evlist)
+ pair = list_entry(session->evlist->entries.next, struct perf_evsel, node);
+ list_for_each_entry(attr, &evlist->entries, node) {
attr->id_offset = lseek(fd, 0, SEEK_CUR);
err = do_write(fd, attr->id, attr->ids * sizeof(u64));
if (err < 0) {
+out_err_write:
pr_debug("failed to write perf header\n");
return err;
}
+ if (session->evlist != evlist) {
+ err = do_write(fd, pair->id, pair->ids * sizeof(u64));
+ if (err < 0)
+ goto out_err_write;
+ attr->ids += pair->ids;
+ pair = list_entry(pair->node.next, struct perf_evsel, node);
+ }
}
+ header->attr_offset = lseek(fd, 0, SEEK_CUR);
- self->attr_offset = lseek(fd, 0, SEEK_CUR);
-
- for (i = 0; i < self->attrs; i++) {
- attr = self->attr[i];
-
+ list_for_each_entry(attr, &evlist->entries, node) {
f_attr = (struct perf_file_attr){
.attr = attr->attr,
.ids = {
}
}
- self->event_offset = lseek(fd, 0, SEEK_CUR);
- self->event_size = event_count * sizeof(struct perf_trace_event_type);
+ header->event_offset = lseek(fd, 0, SEEK_CUR);
+ header->event_size = event_count * sizeof(struct perf_trace_event_type);
if (events) {
- err = do_write(fd, events, self->event_size);
+ err = do_write(fd, events, header->event_size);
if (err < 0) {
pr_debug("failed to write perf header events\n");
return err;
}
}
- self->data_offset = lseek(fd, 0, SEEK_CUR);
+ header->data_offset = lseek(fd, 0, SEEK_CUR);
if (at_exit) {
- err = perf_header__adds_write(self, fd);
+ err = perf_header__adds_write(header, evlist, fd);
if (err < 0)
return err;
}
.size = sizeof(f_header),
.attr_size = sizeof(f_attr),
.attrs = {
- .offset = self->attr_offset,
- .size = self->attrs * sizeof(f_attr),
+ .offset = header->attr_offset,
+ .size = evlist->nr_entries * sizeof(f_attr),
},
.data = {
- .offset = self->data_offset,
- .size = self->data_size,
+ .offset = header->data_offset,
+ .size = header->data_size,
},
.event_types = {
- .offset = self->event_offset,
- .size = self->event_size,
+ .offset = header->event_offset,
+ .size = header->event_size,
},
};
- memcpy(&f_header.adds_features, &self->adds_features, sizeof(self->adds_features));
+ memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features));
lseek(fd, 0, SEEK_SET);
err = do_write(fd, &f_header, sizeof(f_header));
pr_debug("failed to write perf header\n");
return err;
}
- lseek(fd, self->data_offset + self->data_size, SEEK_SET);
+ lseek(fd, header->data_offset + header->data_size, SEEK_SET);
- self->frozen = 1;
+ header->frozen = 1;
return 0;
}
-static int perf_header__getbuffer64(struct perf_header *self,
+static int perf_header__getbuffer64(struct perf_header *header,
int fd, void *buf, size_t size)
{
if (readn(fd, buf, size) <= 0)
return -1;
- if (self->needs_swap)
+ if (header->needs_swap)
mem_bswap_64(buf, size);
return 0;
}
-int perf_header__process_sections(struct perf_header *self, int fd,
- int (*process)(struct perf_file_section *self,
+int perf_header__process_sections(struct perf_header *header, int fd,
+ int (*process)(struct perf_file_section *section,
struct perf_header *ph,
int feat, int fd))
{
int idx = 0;
int err = -1, feat = 1;
- nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
+ nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
if (!nr_sections)
return 0;
sec_size = sizeof(*feat_sec) * nr_sections;
- lseek(fd, self->data_offset + self->data_size, SEEK_SET);
+ lseek(fd, header->data_offset + header->data_size, SEEK_SET);
- if (perf_header__getbuffer64(self, fd, feat_sec, sec_size))
+ if (perf_header__getbuffer64(header, fd, feat_sec, sec_size))
goto out_free;
err = 0;
while (idx < nr_sections && feat < HEADER_LAST_FEATURE) {
- if (perf_header__has_feat(self, feat)) {
+ if (perf_header__has_feat(header, feat)) {
struct perf_file_section *sec = &feat_sec[idx++];
- err = process(sec, self, feat, fd);
+ err = process(sec, header, feat, fd);
if (err < 0)
break;
}
return err;
}
-int perf_file_header__read(struct perf_file_header *self,
+int perf_file_header__read(struct perf_file_header *header,
struct perf_header *ph, int fd)
{
lseek(fd, 0, SEEK_SET);
- if (readn(fd, self, sizeof(*self)) <= 0 ||
- memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+ if (readn(fd, header, sizeof(*header)) <= 0 ||
+ memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
return -1;
- if (self->attr_size != sizeof(struct perf_file_attr)) {
- u64 attr_size = bswap_64(self->attr_size);
+ if (header->attr_size != sizeof(struct perf_file_attr)) {
+ u64 attr_size = bswap_64(header->attr_size);
if (attr_size != sizeof(struct perf_file_attr))
return -1;
- mem_bswap_64(self, offsetof(struct perf_file_header,
+ mem_bswap_64(header, offsetof(struct perf_file_header,
adds_features));
ph->needs_swap = true;
}
- if (self->size != sizeof(*self)) {
+ if (header->size != sizeof(*header)) {
/* Support the previous format */
- if (self->size == offsetof(typeof(*self), adds_features))
- bitmap_zero(self->adds_features, HEADER_FEAT_BITS);
+ if (header->size == offsetof(typeof(*header), adds_features))
+ bitmap_zero(header->adds_features, HEADER_FEAT_BITS);
else
return -1;
}
- memcpy(&ph->adds_features, &self->adds_features,
+ memcpy(&ph->adds_features, &header->adds_features,
sizeof(ph->adds_features));
/*
* FIXME: hack that assumes that if we need swap the perf.data file
perf_header__set_feat(ph, HEADER_BUILD_ID);
}
- ph->event_offset = self->event_types.offset;
- ph->event_size = self->event_types.size;
- ph->data_offset = self->data.offset;
- ph->data_size = self->data.size;
+ ph->event_offset = header->event_types.offset;
+ ph->event_size = header->event_types.size;
+ ph->data_offset = header->data.offset;
+ ph->data_size = header->data.size;
return 0;
}
return err;
}
-static int perf_header__read_build_ids(struct perf_header *self,
- int input, u64 offset, u64 size)
+static int perf_header__read_build_ids(struct perf_header *header,
+ int input, u64 offset, u64 size)
{
- struct perf_session *session = container_of(self,
- struct perf_session, header);
+ struct perf_session *session = container_of(header, struct perf_session, header);
struct build_id_event bev;
char filename[PATH_MAX];
u64 limit = offset + size;
if (read(input, &bev, sizeof(bev)) != sizeof(bev))
goto out;
- if (self->needs_swap)
+ if (header->needs_swap)
perf_event_header__bswap(&bev.header);
len = bev.header.size - sizeof(bev);
return err;
}
-static int perf_file_section__process(struct perf_file_section *self,
+static int perf_file_section__process(struct perf_file_section *section,
struct perf_header *ph,
int feat, int fd)
{
- if (lseek(fd, self->offset, SEEK_SET) == (off_t)-1) {
+ if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
- "%d, continuing...\n", self->offset, feat);
+ "%d, continuing...\n", section->offset, feat);
return 0;
}
break;
case HEADER_BUILD_ID:
- if (perf_header__read_build_ids(ph, fd, self->offset, self->size))
+ if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
pr_debug("Failed to read buildids, continuing...\n");
break;
default:
return 0;
}
-static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
struct perf_header *ph, int fd,
bool repipe)
{
- if (readn(fd, self, sizeof(*self)) <= 0 ||
- memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+ if (readn(fd, header, sizeof(*header)) <= 0 ||
+ memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
return -1;
- if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0)
+ if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
return -1;
- if (self->size != sizeof(*self)) {
- u64 size = bswap_64(self->size);
+ if (header->size != sizeof(*header)) {
+ u64 size = bswap_64(header->size);
- if (size != sizeof(*self))
+ if (size != sizeof(*header))
return -1;
ph->needs_swap = true;
static int perf_header__read_pipe(struct perf_session *session, int fd)
{
- struct perf_header *self = &session->header;
+ struct perf_header *header = &session->header;
struct perf_pipe_file_header f_header;
- if (perf_file_header__read_pipe(&f_header, self, fd,
+ if (perf_file_header__read_pipe(&f_header, header, fd,
session->repipe) < 0) {
pr_debug("incompatible file format\n");
return -EINVAL;
return 0;
}
-int perf_header__read(struct perf_session *session, int fd)
+int perf_session__read_header(struct perf_session *session, int fd)
{
- struct perf_header *self = &session->header;
+ struct perf_header *header = &session->header;
struct perf_file_header f_header;
struct perf_file_attr f_attr;
u64 f_id;
int nr_attrs, nr_ids, i, j;
+ session->evlist = perf_evlist__new(NULL, NULL);
+ if (session->evlist == NULL)
+ return -ENOMEM;
+
if (session->fd_pipe)
return perf_header__read_pipe(session, fd);
- if (perf_file_header__read(&f_header, self, fd) < 0) {
+ if (perf_file_header__read(&f_header, header, fd) < 0) {
pr_debug("incompatible file format\n");
return -EINVAL;
}
lseek(fd, f_header.attrs.offset, SEEK_SET);
for (i = 0; i < nr_attrs; i++) {
- struct perf_header_attr *attr;
+ struct perf_evsel *evsel;
off_t tmp;
- if (perf_header__getbuffer64(self, fd, &f_attr, sizeof(f_attr)))
+ if (perf_header__getbuffer64(header, fd, &f_attr, sizeof(f_attr)))
goto out_errno;
tmp = lseek(fd, 0, SEEK_CUR);
+ evsel = perf_evsel__new(&f_attr.attr, i);
- attr = perf_header_attr__new(&f_attr.attr);
- if (attr == NULL)
- return -ENOMEM;
+ if (evsel == NULL)
+ goto out_delete_evlist;
+ /*
+ * Do it before so that if perf_evsel__alloc_id fails, this
+ * entry gets purged too at perf_evlist__delete().
+ */
+ perf_evlist__add(session->evlist, evsel);
nr_ids = f_attr.ids.size / sizeof(u64);
+ /*
+ * We don't have the cpu and thread maps on the header, so
+ * for allocating the perf_sample_id table we fake 1 cpu and
+ * hattr->ids threads.
+ */
+ if (perf_evsel__alloc_id(evsel, 1, nr_ids))
+ goto out_delete_evlist;
+
lseek(fd, f_attr.ids.offset, SEEK_SET);
for (j = 0; j < nr_ids; j++) {
- if (perf_header__getbuffer64(self, fd, &f_id, sizeof(f_id)))
+ if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id)))
goto out_errno;
- if (perf_header_attr__add_id(attr, f_id) < 0) {
- perf_header_attr__delete(attr);
- return -ENOMEM;
- }
- }
- if (perf_header__add_attr(self, attr) < 0) {
- perf_header_attr__delete(attr);
- return -ENOMEM;
+ perf_evlist__id_add(session->evlist, evsel, 0, j, f_id);
}
lseek(fd, tmp, SEEK_SET);
events = malloc(f_header.event_types.size);
if (events == NULL)
return -ENOMEM;
- if (perf_header__getbuffer64(self, fd, events,
+ if (perf_header__getbuffer64(header, fd, events,
f_header.event_types.size))
goto out_errno;
event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type);
}
- perf_header__process_sections(self, fd, perf_file_section__process);
+ perf_header__process_sections(header, fd, perf_file_section__process);
- lseek(fd, self->data_offset, SEEK_SET);
+ lseek(fd, header->data_offset, SEEK_SET);
- self->frozen = 1;
+ header->frozen = 1;
return 0;
out_errno:
return -errno;
+
+out_delete_evlist:
+ perf_evlist__delete(session->evlist);
+ session->evlist = NULL;
+ return -ENOMEM;
}
-u64 perf_header__sample_type(struct perf_header *header)
+u64 perf_evlist__sample_type(struct perf_evlist *evlist)
{
+ struct perf_evsel *pos;
u64 type = 0;
- int i;
-
- for (i = 0; i < header->attrs; i++) {
- struct perf_header_attr *attr = header->attr[i];
+ list_for_each_entry(pos, &evlist->entries, node) {
if (!type)
- type = attr->attr.sample_type;
- else if (type != attr->attr.sample_type)
+ type = pos->attr.sample_type;
+ else if (type != pos->attr.sample_type)
die("non matching sample_type");
}
return type;
}
-bool perf_header__sample_id_all(const struct perf_header *header)
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
{
bool value = false, first = true;
- int i;
-
- for (i = 0; i < header->attrs; i++) {
- struct perf_header_attr *attr = header->attr[i];
+ struct perf_evsel *pos;
+ list_for_each_entry(pos, &evlist->entries, node) {
if (first) {
- value = attr->attr.sample_id_all;
+ value = pos->attr.sample_id_all;
first = false;
- } else if (value != attr->attr.sample_id_all)
+ } else if (value != pos->attr.sample_id_all)
die("non matching sample_id_all");
}
return value;
}
-struct perf_event_attr *
-perf_header__find_attr(u64 id, struct perf_header *header)
-{
- int i;
-
- /*
- * We set id to -1 if the data file doesn't contain sample
- * ids. This can happen when the data file contains one type
- * of event and in that case, the header can still store the
- * event attribute information. Check for this and avoid
- * walking through the entire list of ids which may be large.
- */
- if (id == -1ULL) {
- if (header->attrs > 0)
- return &header->attr[0]->attr;
- return NULL;
- }
-
- for (i = 0; i < header->attrs; i++) {
- struct perf_header_attr *attr = header->attr[i];
- int j;
-
- for (j = 0; j < attr->ids; j++) {
- if (attr->id[j] == id)
- return &attr->attr;
- }
- }
-
- return NULL;
-}
-
-int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
- event__handler_t process,
- struct perf_session *session)
+int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+ perf_event__handler_t process,
+ struct perf_session *session)
{
- event_t *ev;
+ union perf_event *ev;
size_t size;
int err;
return err;
}
-int event__synthesize_attrs(struct perf_header *self, event__handler_t process,
- struct perf_session *session)
+int perf_session__synthesize_attrs(struct perf_session *session,
+ perf_event__handler_t process)
{
- struct perf_header_attr *attr;
- int i, err = 0;
-
- for (i = 0; i < self->attrs; i++) {
- attr = self->attr[i];
+ struct perf_evsel *attr;
+ int err = 0;
- err = event__synthesize_attr(&attr->attr, attr->ids, attr->id,
- process, session);
+ list_for_each_entry(attr, &session->evlist->entries, node) {
+ err = perf_event__synthesize_attr(&attr->attr, attr->ids,
+ attr->id, process, session);
if (err) {
pr_debug("failed to create perf header attribute\n");
return err;
return err;
}
-int event__process_attr(event_t *self, struct perf_session *session)
+int perf_event__process_attr(union perf_event *event,
+ struct perf_session *session)
{
- struct perf_header_attr *attr;
unsigned int i, ids, n_ids;
+ struct perf_evsel *evsel;
+
+ if (session->evlist == NULL) {
+ session->evlist = perf_evlist__new(NULL, NULL);
+ if (session->evlist == NULL)
+ return -ENOMEM;
+ }
- attr = perf_header_attr__new(&self->attr.attr);
- if (attr == NULL)
+ evsel = perf_evsel__new(&event->attr.attr,
+ session->evlist->nr_entries);
+ if (evsel == NULL)
return -ENOMEM;
- ids = self->header.size;
- ids -= (void *)&self->attr.id - (void *)self;
+ perf_evlist__add(session->evlist, evsel);
+
+ ids = event->header.size;
+ ids -= (void *)&event->attr.id - (void *)event;
n_ids = ids / sizeof(u64);
+ /*
+ * We don't have the cpu and thread maps on the header, so
+ * for allocating the perf_sample_id table we fake 1 cpu and
+ * hattr->ids threads.
+ */
+ if (perf_evsel__alloc_id(evsel, 1, n_ids))
+ return -ENOMEM;
for (i = 0; i < n_ids; i++) {
- if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) {
- perf_header_attr__delete(attr);
- return -ENOMEM;
- }
- }
-
- if (perf_header__add_attr(&session->header, attr) < 0) {
- perf_header_attr__delete(attr);
- return -ENOMEM;
+ perf_evlist__id_add(session->evlist, evsel, 0, i,
+ event->attr.id[i]);
}
perf_session__update_sample_type(session);
return 0;
}
-int event__synthesize_event_type(u64 event_id, char *name,
- event__handler_t process,
- struct perf_session *session)
+int perf_event__synthesize_event_type(u64 event_id, char *name,
+ perf_event__handler_t process,
+ struct perf_session *session)
{
- event_t ev;
+ union perf_event ev;
size_t size = 0;
int err = 0;
return err;
}
-int event__synthesize_event_types(event__handler_t process,
- struct perf_session *session)
+int perf_event__synthesize_event_types(perf_event__handler_t process,
+ struct perf_session *session)
{
struct perf_trace_event_type *type;
int i, err = 0;
for (i = 0; i < event_count; i++) {
type = &events[i];
- err = event__synthesize_event_type(type->event_id, type->name,
- process, session);
+ err = perf_event__synthesize_event_type(type->event_id,
+ type->name, process,
+ session);
if (err) {
pr_debug("failed to create perf header event type\n");
return err;
return err;
}
-int event__process_event_type(event_t *self,
- struct perf_session *session __unused)
+int perf_event__process_event_type(union perf_event *event,
+ struct perf_session *session __unused)
{
- if (perf_header__push_event(self->event_type.event_type.event_id,
- self->event_type.event_type.name) < 0)
+ if (perf_header__push_event(event->event_type.event_type.event_id,
+ event->event_type.event_type.name) < 0)
return -ENOMEM;
return 0;
}
-int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
- event__handler_t process,
+int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist,
+ perf_event__handler_t process,
struct perf_session *session __unused)
{
- event_t ev;
+ union perf_event ev;
ssize_t size = 0, aligned_size = 0, padding;
- int err = 0;
+ int err __used = 0;
memset(&ev, 0, sizeof(ev));
ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
- size = read_tracing_data_size(fd, pattrs);
+ size = read_tracing_data_size(fd, &evlist->entries);
if (size <= 0)
return size;
aligned_size = ALIGN(size, sizeof(u64));
process(&ev, NULL, session);
- err = read_tracing_data(fd, pattrs);
+ err = read_tracing_data(fd, &evlist->entries);
write_padded(fd, NULL, 0, padding);
return aligned_size;
}
-int event__process_tracing_data(event_t *self,
- struct perf_session *session)
+int perf_event__process_tracing_data(union perf_event *event,
+ struct perf_session *session)
{
- ssize_t size_read, padding, size = self->tracing_data.size;
+ ssize_t size_read, padding, size = event->tracing_data.size;
off_t offset = lseek(session->fd, 0, SEEK_CUR);
char buf[BUFSIZ];
return size_read + padding;
}
-int event__synthesize_build_id(struct dso *pos, u16 misc,
- event__handler_t process,
- struct machine *machine,
- struct perf_session *session)
+int perf_event__synthesize_build_id(struct dso *pos, u16 misc,
+ perf_event__handler_t process,
+ struct machine *machine,
+ struct perf_session *session)
{
- event_t ev;
+ union perf_event ev;
size_t len;
int err = 0;
return err;
}
-int event__process_build_id(event_t *self,
- struct perf_session *session)
+int perf_event__process_build_id(union perf_event *event,
+ struct perf_session *session)
{
- __event_process_build_id(&self->build_id,
- self->build_id.filename,
+ __event_process_build_id(&event->build_id,
+ event->build_id.filename,
session);
return 0;
}
#include <linux/bitmap.h>
-struct perf_header_attr {
- struct perf_event_attr attr;
- int ids, size;
- u64 *id;
- off_t id_offset;
-};
-
enum {
HEADER_TRACE_INFO = 1,
HEADER_BUILD_ID,
struct perf_header;
-int perf_file_header__read(struct perf_file_header *self,
+int perf_file_header__read(struct perf_file_header *header,
struct perf_header *ph, int fd);
struct perf_header {
int frozen;
- int attrs, size;
bool needs_swap;
- struct perf_header_attr **attr;
s64 attr_offset;
u64 data_offset;
u64 data_size;
DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
};
-int perf_header__init(struct perf_header *self);
-void perf_header__exit(struct perf_header *self);
+struct perf_evlist;
-int perf_header__read(struct perf_session *session, int fd);
-int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_session__read_header(struct perf_session *session, int fd);
+int perf_session__write_header(struct perf_session *session,
+ struct perf_evlist *evlist,
+ int fd, bool at_exit);
int perf_header__write_pipe(int fd);
-int perf_header__add_attr(struct perf_header *self,
- struct perf_header_attr *attr);
-
int perf_header__push_event(u64 id, const char *name);
char *perf_header__find_event(u64 id);
-struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr);
-void perf_header_attr__delete(struct perf_header_attr *self);
+u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
+void perf_header__set_feat(struct perf_header *header, int feat);
+void perf_header__clear_feat(struct perf_header *header, int feat);
+bool perf_header__has_feat(const struct perf_header *header, int feat);
-int perf_header_attr__add_id(struct perf_header_attr *self, u64 id);
-
-u64 perf_header__sample_type(struct perf_header *header);
-bool perf_header__sample_id_all(const struct perf_header *header);
-struct perf_event_attr *
-perf_header__find_attr(u64 id, struct perf_header *header);
-void perf_header__set_feat(struct perf_header *self, int feat);
-void perf_header__clear_feat(struct perf_header *self, int feat);
-bool perf_header__has_feat(const struct perf_header *self, int feat);
-
-int perf_header__process_sections(struct perf_header *self, int fd,
- int (*process)(struct perf_file_section *self,
+int perf_header__process_sections(struct perf_header *header, int fd,
+ int (*process)(struct perf_file_section *section,
struct perf_header *ph,
int feat, int fd));
const char *name, bool is_kallsyms);
int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
-int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
- event__handler_t process,
- struct perf_session *session);
-int event__synthesize_attrs(struct perf_header *self,
- event__handler_t process,
- struct perf_session *session);
-int event__process_attr(event_t *self, struct perf_session *session);
-
-int event__synthesize_event_type(u64 event_id, char *name,
- event__handler_t process,
- struct perf_session *session);
-int event__synthesize_event_types(event__handler_t process,
- struct perf_session *session);
-int event__process_event_type(event_t *self,
- struct perf_session *session);
-
-int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
- event__handler_t process,
- struct perf_session *session);
-int event__process_tracing_data(event_t *self,
+int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+ perf_event__handler_t process,
struct perf_session *session);
+int perf_session__synthesize_attrs(struct perf_session *session,
+ perf_event__handler_t process);
+int perf_event__process_attr(union perf_event *event, struct perf_session *session);
+
+int perf_event__synthesize_event_type(u64 event_id, char *name,
+ perf_event__handler_t process,
+ struct perf_session *session);
+int perf_event__synthesize_event_types(perf_event__handler_t process,
+ struct perf_session *session);
+int perf_event__process_event_type(union perf_event *event,
+ struct perf_session *session);
-int event__synthesize_build_id(struct dso *pos, u16 misc,
- event__handler_t process,
- struct machine *machine,
- struct perf_session *session);
-int event__process_build_id(event_t *self, struct perf_session *session);
-
+int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist,
+ perf_event__handler_t process,
+ struct perf_session *session);
+int perf_event__process_tracing_data(union perf_event *event,
+ struct perf_session *session);
+
+int perf_event__synthesize_build_id(struct dso *pos, u16 misc,
+ perf_event__handler_t process,
+ struct machine *machine,
+ struct perf_session *session);
+int perf_event__process_build_id(union perf_event *event,
+ struct perf_session *session);
#endif /* __PERF_HEADER_H */
+#include "annotate.h"
#include "util.h"
#include "build-id.h"
#include "hist.h"
if (h->ms.sym)
hists__new_col_len(self, HISTC_SYMBOL, h->ms.sym->namelen);
+ else {
+ const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+ if (hists__col_len(self, HISTC_DSO) < unresolved_col_width &&
+ !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+ !symbol_conf.dso_list)
+ hists__set_col_len(self, HISTC_DSO,
+ unresolved_col_width);
+ }
len = thread__comm_len(h->thread);
if (hists__new_col_len(self, HISTC_COMM, len))
* collapse the histogram
*/
-static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
+static bool hists__collapse_insert_entry(struct hists *self,
+ struct rb_root *root,
+ struct hist_entry *he)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
if (!cmp) {
iter->period += he->period;
- if (symbol_conf.use_callchain)
- callchain_merge(iter->callchain, he->callchain);
+ if (symbol_conf.use_callchain) {
+ callchain_cursor_reset(&self->callchain_cursor);
+ callchain_merge(&self->callchain_cursor, iter->callchain,
+ he->callchain);
+ }
hist_entry__free(he);
return false;
}
next = rb_next(&n->rb_node);
rb_erase(&n->rb_node, &self->entries);
- if (collapse__insert_entry(&tmp, n))
+ if (hists__collapse_insert_entry(self, &tmp, n))
hists__inc_nr_entries(self, n);
}
u64 cumul;
child = rb_entry(node, struct callchain_node, rb_node);
- cumul = cumul_hits(child);
+ cumul = callchain_cumul_hits(child);
remaining -= cumul;
/*
{
struct sort_entry *se;
u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
+ u64 nr_events;
const char *sep = symbol_conf.field_sep;
int ret;
if (pair_hists) {
period = self->pair ? self->pair->period : 0;
+ nr_events = self->pair ? self->pair->nr_events : 0;
total = pair_hists->stats.total_period;
period_sys = self->pair ? self->pair->period_sys : 0;
period_us = self->pair ? self->pair->period_us : 0;
period_guest_us = self->pair ? self->pair->period_guest_us : 0;
} else {
period = self->period;
+ nr_events = self->nr_events;
total = session_total;
period_sys = self->period_sys;
period_us = self->period_us;
if (symbol_conf.show_nr_samples) {
if (sep)
- ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period);
+ ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, nr_events);
else
- ret += snprintf(s + ret, size - ret, "%11" PRIu64, period);
+ ret += snprintf(s + ret, size - ret, "%11" PRIu64, nr_events);
}
if (pair_hists) {
}
}
-static int symbol__alloc_hist(struct symbol *self)
-{
- struct sym_priv *priv = symbol__priv(self);
- const int size = (sizeof(*priv->hist) +
- (self->end - self->start) * sizeof(u64));
-
- priv->hist = zalloc(size);
- return priv->hist == NULL ? -1 : 0;
-}
-
-int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
-{
- unsigned int sym_size, offset;
- struct symbol *sym = self->ms.sym;
- struct sym_priv *priv;
- struct sym_hist *h;
-
- if (!sym || !self->ms.map)
- return 0;
-
- priv = symbol__priv(sym);
- if (priv->hist == NULL && symbol__alloc_hist(sym) < 0)
- return -ENOMEM;
-
- sym_size = sym->end - sym->start;
- offset = ip - sym->start;
-
- pr_debug3("%s: ip=%#" PRIx64 "\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
-
- if (offset >= sym_size)
- return 0;
-
- h = priv->hist;
- h->sum++;
- h->ip[offset]++;
-
- pr_debug3("%#" PRIx64 " %s: period++ [ip: %#" PRIx64 ", %#" PRIx64
- "] => %" PRIu64 "\n", self->ms.sym->start, self->ms.sym->name,
- ip, ip - self->ms.sym->start, h->ip[offset]);
- return 0;
-}
-
-static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize)
-{
- struct objdump_line *self = malloc(sizeof(*self) + privsize);
-
- if (self != NULL) {
- self->offset = offset;
- self->line = line;
- }
-
- return self;
-}
-
-void objdump_line__free(struct objdump_line *self)
-{
- free(self->line);
- free(self);
-}
-
-static void objdump__add_line(struct list_head *head, struct objdump_line *line)
-{
- list_add_tail(&line->node, head);
-}
-
-struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
- struct objdump_line *pos)
-{
- list_for_each_entry_continue(pos, head, node)
- if (pos->offset >= 0)
- return pos;
-
- return NULL;
-}
-
-static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
- struct list_head *head, size_t privsize)
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
{
- struct symbol *sym = self->ms.sym;
- struct objdump_line *objdump_line;
- char *line = NULL, *tmp, *tmp2, *c;
- size_t line_len;
- s64 line_ip, offset = -1;
-
- if (getline(&line, &line_len, file) < 0)
- return -1;
-
- if (!line)
- return -1;
-
- while (line_len != 0 && isspace(line[line_len - 1]))
- line[--line_len] = '\0';
-
- c = strchr(line, '\n');
- if (c)
- *c = 0;
-
- line_ip = -1;
-
- /*
- * Strip leading spaces:
- */
- tmp = line;
- while (*tmp) {
- if (*tmp != ' ')
- break;
- tmp++;
- }
-
- if (*tmp) {
- /*
- * Parse hexa addresses followed by ':'
- */
- line_ip = strtoull(tmp, &tmp2, 16);
- if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
- line_ip = -1;
- }
-
- if (line_ip != -1) {
- u64 start = map__rip_2objdump(self->ms.map, sym->start),
- end = map__rip_2objdump(self->ms.map, sym->end);
-
- offset = line_ip - start;
- if (offset < 0 || (u64)line_ip > end)
- offset = -1;
- }
-
- objdump_line = objdump_line__new(offset, line, privsize);
- if (objdump_line == NULL) {
- free(line);
- return -1;
- }
- objdump__add_line(head, objdump_line);
-
- return 0;
+ return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
}
-int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
- size_t privsize)
+int hist_entry__annotate(struct hist_entry *he, size_t privsize)
{
- struct symbol *sym = self->ms.sym;
- struct map *map = self->ms.map;
- struct dso *dso = map->dso;
- char *filename = dso__build_id_filename(dso, NULL, 0);
- bool free_filename = true;
- char command[PATH_MAX * 2];
- FILE *file;
- int err = 0;
- u64 len;
- char symfs_filename[PATH_MAX];
-
- if (filename) {
- snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
- symbol_conf.symfs, filename);
- }
-
- if (filename == NULL) {
- if (dso->has_build_id) {
- pr_err("Can't annotate %s: not enough memory\n",
- sym->name);
- return -ENOMEM;
- }
- goto fallback;
- } else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
- strstr(command, "[kernel.kallsyms]") ||
- access(symfs_filename, R_OK)) {
- free(filename);
-fallback:
- /*
- * If we don't have build-ids or the build-id file isn't in the
- * cache, or is just a kallsyms file, well, lets hope that this
- * DSO is the same as when 'perf record' ran.
- */
- filename = dso->long_name;
- snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
- symbol_conf.symfs, filename);
- free_filename = false;
- }
-
- if (dso->origin == DSO__ORIG_KERNEL) {
- if (dso->annotate_warned)
- goto out_free_filename;
- err = -ENOENT;
- dso->annotate_warned = 1;
- pr_err("Can't annotate %s: No vmlinux file was found in the "
- "path\n", sym->name);
- goto out_free_filename;
- }
-
- pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
- filename, sym->name, map->unmap_ip(map, sym->start),
- map->unmap_ip(map, sym->end));
-
- len = sym->end - sym->start;
-
- pr_debug("annotating [%p] %30s : [%p] %30s\n",
- dso, dso->long_name, sym, sym->name);
-
- snprintf(command, sizeof(command),
- "objdump --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand",
- map__rip_2objdump(map, sym->start),
- map__rip_2objdump(map, sym->end),
- symfs_filename, filename);
-
- pr_debug("Executing: %s\n", command);
-
- file = popen(command, "r");
- if (!file)
- goto out_free_filename;
-
- while (!feof(file))
- if (hist_entry__parse_objdump_line(self, file, head, privsize) < 0)
- break;
-
- pclose(file);
-out_free_filename:
- if (free_filename)
- free(filename);
- return err;
+ return symbol__annotate(he->ms.sym, he->ms.map, privsize);
}
void hists__inc_nr_events(struct hists *self, u32 type)
size_t ret = 0;
for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
- const char *name = event__get_event_name(i);
+ const char *name;
+
+ if (self->stats.nr_events[i] == 0)
+ continue;
+ name = perf_event__name(i);
if (!strcmp(name, "UNKNOWN"))
continue;
struct hist_entry;
struct addr_location;
struct symbol;
-struct rb_root;
-
-struct objdump_line {
- struct list_head node;
- s64 offset;
- char *line;
-};
-
-void objdump_line__free(struct objdump_line *self);
-struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
- struct objdump_line *pos);
-
-struct sym_hist {
- u64 sum;
- u64 ip[0];
-};
-
-struct sym_ext {
- struct rb_node node;
- double percent;
- char *path;
-};
-
-struct sym_priv {
- struct sym_hist *hist;
- struct sym_ext *ext;
-};
/*
* The kernel collects the number of events it couldn't send in a stretch and
};
struct hists {
- struct rb_node rb_node;
struct rb_root entries;
u64 nr_entries;
struct events_stats stats;
- u64 config;
u64 event_stream;
- u32 type;
u16 col_len[HISTC_NR_COLS];
+ /* Best would be to reuse the session callchain cursor */
+ struct callchain_cursor callchain_cursor;
};
struct hist_entry *__hists__add_entry(struct hists *self,
size_t hists__fprintf(struct hists *self, struct hists *pair,
bool show_displacement, FILE *fp);
-int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip);
-int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
- size_t privsize);
+int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr);
+int hist_entry__annotate(struct hist_entry *self, size_t privsize);
void hists__filter_by_dso(struct hists *self, const struct dso *dso);
void hists__filter_by_thread(struct hists *self, const struct thread *thread);
void hists__set_col_len(struct hists *self, enum hist_column col, u16 len);
bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len);
-#ifdef NO_NEWT_SUPPORT
-static inline int hists__browse(struct hists *self __used,
- const char *helpline __used,
- const char *ev_name __used)
-{
- return 0;
-}
+struct perf_evlist;
-static inline int hists__tui_browse_tree(struct rb_root *self __used,
- const char *help __used)
+#ifdef NO_NEWT_SUPPORT
+static inline
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __used,
+ const char *help __used)
{
return 0;
}
-static inline int hist_entry__tui_annotate(struct hist_entry *self __used)
+static inline int hist_entry__tui_annotate(struct hist_entry *self __used,
+ int evidx __used)
{
return 0;
}
#define KEY_RIGHT -2
#else
#include <newt.h>
-int hists__browse(struct hists *self, const char *helpline,
- const char *ev_name);
-int hist_entry__tui_annotate(struct hist_entry *self);
+int hist_entry__tui_annotate(struct hist_entry *self, int evidx);
#define KEY_LEFT NEWT_KEY_LEFT
#define KEY_RIGHT NEWT_KEY_RIGHT
-int hists__tui_browse_tree(struct rb_root *self, const char *help);
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help);
#endif
unsigned int hists__sort_list_width(struct hists *self);
+#include <linux/kernel.h>
#include "../../../../include/linux/list.h"
#ifndef PERF_LIST_H
#include "../../../include/linux/hw_breakpoint.h"
#include "util.h"
#include "../perf.h"
+#include "evlist.h"
#include "evsel.h"
#include "parse-options.h"
#include "parse-events.h"
#include "header.h"
#include "debugfs.h"
-int nr_counters;
-
-LIST_HEAD(evsel_list);
-
struct event_symbol {
u8 type;
u64 config;
u64 config = evsel->attr.config;
int type = evsel->attr.type;
+ if (evsel->name)
+ return evsel->name;
+
return __event_name(type, config);
}
/* sys + ':' + event + ':' + flags*/
#define MAX_EVOPT_LEN (MAX_EVENT_LENGTH * 2 + 2 + 128)
static enum event_result
-parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
- char *flags)
+parse_multiple_tracepoint_event(const struct option *opt, char *sys_name,
+ const char *evt_exp, char *flags)
{
char evt_path[MAXPATHLEN];
struct dirent *evt_ent;
if (len < 0)
return EVT_FAILED;
- if (parse_events(NULL, event_opt, 0))
+ if (parse_events(opt, event_opt, 0))
return EVT_FAILED;
}
return EVT_HANDLED_ALL;
}
-static enum event_result parse_tracepoint_event(const char **strp,
- struct perf_event_attr *attr)
+static enum event_result
+parse_tracepoint_event(const struct option *opt, const char **strp,
+ struct perf_event_attr *attr)
{
const char *evt_name;
char *flags = NULL, *comma_loc;
return EVT_FAILED;
if (strpbrk(evt_name, "*?")) {
*strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */
- return parse_multiple_tracepoint_event(sys_name, evt_name,
+ return parse_multiple_tracepoint_event(opt, sys_name, evt_name,
flags);
} else {
return parse_single_tracepoint_event(sys_name, evt_name,
* Symbolic names are (almost) exactly matched.
*/
static enum event_result
-parse_event_symbols(const char **str, struct perf_event_attr *attr)
+parse_event_symbols(const struct option *opt, const char **str,
+ struct perf_event_attr *attr)
{
enum event_result ret;
- ret = parse_tracepoint_event(str, attr);
+ ret = parse_tracepoint_event(opt, str, attr);
if (ret != EVT_FAILED)
goto modifier;
return ret;
}
-int parse_events(const struct option *opt __used, const char *str, int unset __used)
+int parse_events(const struct option *opt, const char *str, int unset __used)
{
+ struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
struct perf_event_attr attr;
enum event_result ret;
+ const char *ostr;
for (;;) {
+ ostr = str;
memset(&attr, 0, sizeof(attr));
- ret = parse_event_symbols(&str, &attr);
+ ret = parse_event_symbols(opt, &str, &attr);
if (ret == EVT_FAILED)
return -1;
if (ret != EVT_HANDLED_ALL) {
struct perf_evsel *evsel;
- evsel = perf_evsel__new(&attr,
- nr_counters);
+ evsel = perf_evsel__new(&attr, evlist->nr_entries);
if (evsel == NULL)
return -1;
- list_add_tail(&evsel->node, &evsel_list);
- ++nr_counters;
+ perf_evlist__add(evlist, evsel);
+
+ evsel->name = calloc(str - ostr + 1, 1);
+ if (!evsel->name)
+ return -1;
+ strncpy(evsel->name, ostr, str - ostr);
}
if (*str == 0)
return 0;
}
-int parse_filter(const struct option *opt __used, const char *str,
+int parse_filter(const struct option *opt, const char *str,
int unset __used)
{
+ struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
struct perf_evsel *last = NULL;
- if (!list_empty(&evsel_list))
- last = list_entry(evsel_list.prev, struct perf_evsel, node);
+ if (evlist->nr_entries > 0)
+ last = list_entry(evlist->entries.prev, struct perf_evsel, node);
if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
fprintf(stderr,
* Print the events from <debugfs_mount_point>/tracing/events
*/
-static void print_tracepoint_events(void)
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob)
{
DIR *sys_dir, *evt_dir;
struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
return;
for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+ if (subsys_glob != NULL &&
+ !strglobmatch(sys_dirent.d_name, subsys_glob))
+ continue;
snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
sys_dirent.d_name);
continue;
for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+ if (event_glob != NULL &&
+ !strglobmatch(evt_dirent.d_name, event_glob))
+ continue;
+
snprintf(evt_path, MAXPATHLEN, "%s:%s",
sys_dirent.d_name, evt_dirent.d_name);
printf(" %-42s [%s]\n", evt_path,
return 0;
}
+void print_events_type(u8 type)
+{
+ struct event_symbol *syms = event_symbols;
+ unsigned int i;
+ char name[64];
+
+ for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
+ if (type != syms->type)
+ continue;
+
+ if (strlen(syms->alias))
+ snprintf(name, sizeof(name), "%s OR %s",
+ syms->symbol, syms->alias);
+ else
+ snprintf(name, sizeof(name), "%s", syms->symbol);
+
+ printf(" %-42s [%s]\n", name,
+ event_type_descriptors[type]);
+ }
+}
+
+int print_hwcache_events(const char *event_glob)
+{
+ unsigned int type, op, i, printed = 0;
+
+ for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
+ for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
+ /* skip invalid cache type */
+ if (!is_cache_op_valid(type, op))
+ continue;
+
+ for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+ char *name = event_cache_name(type, op, i);
+
+ if (event_glob != NULL &&
+ !strglobmatch(name, event_glob))
+ continue;
+
+ printf(" %-42s [%s]\n", name,
+ event_type_descriptors[PERF_TYPE_HW_CACHE]);
+ ++printed;
+ }
+ }
+ }
+
+ return printed;
+}
+
/*
* Print the help text for the event symbols:
*/
-void print_events(void)
+void print_events(const char *event_glob)
{
struct event_symbol *syms = event_symbols;
- unsigned int i, type, op, prev_type = -1;
+ unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0;
char name[40];
printf("\n");
for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
type = syms->type;
- if (type != prev_type)
+ if (type != prev_type && printed) {
printf("\n");
+ printed = 0;
+ ntypes_printed++;
+ }
+
+ if (event_glob != NULL &&
+ !(strglobmatch(syms->symbol, event_glob) ||
+ (syms->alias && strglobmatch(syms->alias, event_glob))))
+ continue;
if (strlen(syms->alias))
sprintf(name, "%s OR %s", syms->symbol, syms->alias);
event_type_descriptors[type]);
prev_type = type;
+ ++printed;
}
- printf("\n");
- for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
- for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
- /* skip invalid cache type */
- if (!is_cache_op_valid(type, op))
- continue;
-
- for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
- printf(" %-42s [%s]\n",
- event_cache_name(type, op, i),
- event_type_descriptors[PERF_TYPE_HW_CACHE]);
- }
- }
+ if (ntypes_printed) {
+ printed = 0;
+ printf("\n");
}
+ print_hwcache_events(event_glob);
+
+ if (event_glob != NULL)
+ return;
printf("\n");
printf(" %-42s [%s]\n",
event_type_descriptors[PERF_TYPE_BREAKPOINT]);
printf("\n");
- print_tracepoint_events();
+ print_tracepoint_events(NULL, NULL);
exit(129);
}
-
-int perf_evsel_list__create_default(void)
-{
- struct perf_evsel *evsel;
- struct perf_event_attr attr;
-
- memset(&attr, 0, sizeof(attr));
- attr.type = PERF_TYPE_HARDWARE;
- attr.config = PERF_COUNT_HW_CPU_CYCLES;
-
- evsel = perf_evsel__new(&attr, 0);
-
- if (evsel == NULL)
- return -ENOMEM;
-
- list_add(&evsel->node, &evsel_list);
- ++nr_counters;
- return 0;
-}
-
-void perf_evsel_list__delete(void)
-{
- struct perf_evsel *pos, *n;
-
- list_for_each_entry_safe(pos, n, &evsel_list, node) {
- list_del_init(&pos->node);
- perf_evsel__delete(pos);
- }
- nr_counters = 0;
-}
struct list_head;
struct perf_evsel;
-extern struct list_head evsel_list;
-
-int perf_evsel_list__create_default(void);
-void perf_evsel_list__delete(void);
-
struct option;
struct tracepoint_path {
extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
extern bool have_tracepoints(struct list_head *evlist);
-extern int nr_counters;
-
const char *event_name(struct perf_evsel *event);
extern const char *__event_name(int type, u64 config);
#define EVENTS_HELP_MAX (128*1024)
-extern void print_events(void);
+void print_events(const char *event_glob);
+void print_events_type(u8 type);
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob);
+int print_hwcache_events(const char *event_glob);
extern int is_valid_tracepoint(const char *event_string);
extern char debugfs_path[];
#include <string.h>
#include <stdarg.h>
#include <limits.h>
+#include <elf.h>
#undef _GNU_SOURCE
#include "util.h"
NULL);
}
-const char *kernel_get_module_path(const char *module)
+static struct map *kernel_get_module_map(const char *module)
+{
+ struct rb_node *nd;
+ struct map_groups *grp = &machine.kmaps;
+
+ 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);
+ if (strncmp(pos->dso->short_name + 1, module,
+ pos->dso->short_name_len - 2) == 0) {
+ return pos;
+ }
+ }
+ return NULL;
+}
+
+static struct dso *kernel_get_module_dso(const char *module)
{
struct dso *dso;
struct map *map;
}
}
found:
- return dso->long_name;
+ 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;
}
#ifdef DWARF_SUPPORT
setup_pager();
if (lr->function)
- fprintf(stdout, "<%s:%d>\n", lr->function,
+ fprintf(stdout, "<%s@%s:%d>\n", lr->function, lr->path,
lr->start - lr->offset);
else
fprintf(stdout, "<%s:%d>\n", lr->path, lr->start);
}
static int show_available_vars_at(int fd, struct perf_probe_event *pev,
- int max_vls, bool externs)
+ int max_vls, struct strfilter *_filter,
+ bool externs)
{
char *buf;
- int ret, i;
+ int ret, i, nvars;
struct str_node *node;
struct variable_list *vls = NULL, *vl;
+ const char *var;
buf = synthesize_perf_probe_point(&pev->point);
if (!buf)
pr_debug("Searching variables at %s\n", buf);
ret = find_available_vars_at(fd, pev, &vls, max_vls, externs);
- if (ret > 0) {
- /* Some variables were found */
- fprintf(stdout, "Available variables at %s\n", buf);
- for (i = 0; i < ret; i++) {
- vl = &vls[i];
- /*
- * A probe point might be converted to
- * several trace points.
- */
- fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol,
- vl->point.offset);
- free(vl->point.symbol);
- if (vl->vars) {
- strlist__for_each(node, vl->vars)
+ if (ret <= 0) {
+ pr_err("Failed to find variables at %s (%d)\n", buf, ret);
+ goto end;
+ }
+ /* Some variables are found */
+ fprintf(stdout, "Available variables at %s\n", buf);
+ for (i = 0; i < ret; i++) {
+ vl = &vls[i];
+ /*
+ * A probe point might be converted to
+ * several trace points.
+ */
+ fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol,
+ vl->point.offset);
+ free(vl->point.symbol);
+ nvars = 0;
+ if (vl->vars) {
+ strlist__for_each(node, vl->vars) {
+ var = strchr(node->s, '\t') + 1;
+ if (strfilter__compare(_filter, var)) {
fprintf(stdout, "\t\t%s\n", node->s);
- strlist__delete(vl->vars);
- } else
- fprintf(stdout, "(No variables)\n");
+ nvars++;
+ }
+ }
+ strlist__delete(vl->vars);
}
- free(vls);
- } else
- pr_err("Failed to find variables at %s (%d)\n", buf, ret);
-
+ if (nvars == 0)
+ fprintf(stdout, "\t\t(No matched variables)\n");
+ }
+ free(vls);
+end:
free(buf);
return ret;
}
/* Show available variables on given probe point */
int show_available_vars(struct perf_probe_event *pevs, int npevs,
- int max_vls, const char *module, bool externs)
+ int max_vls, const char *module,
+ struct strfilter *_filter, bool externs)
{
int i, fd, ret = 0;
setup_pager();
for (i = 0; i < npevs && ret >= 0; i++)
- ret = show_available_vars_at(fd, &pevs[i], max_vls, externs);
+ ret = show_available_vars_at(fd, &pevs[i], max_vls, _filter,
+ externs);
close(fd);
return ret;
int show_available_vars(struct perf_probe_event *pevs __unused,
int npevs __unused, int max_vls __unused,
- const char *module __unused, bool externs __unused)
+ const char *module __unused,
+ struct strfilter *filter __unused,
+ bool externs __unused)
{
pr_warning("Debuginfo-analysis is not supported.\n");
return -ENOSYS;
* The line range syntax is described by:
*
* SRC[:SLN[+NUM|-ELN]]
- * FNC[:SLN[+NUM|-ELN]]
+ * FNC[@SRC][:SLN[+NUM|-ELN]]
*/
int parse_line_range_desc(const char *arg, struct line_range *lr)
{
- char *range, *name = strdup(arg);
+ char *range, *file, *name = strdup(arg);
int err;
if (!name)
}
}
- if (strchr(name, '.'))
+ file = strchr(name, '@');
+ if (file) {
+ *file = '\0';
+ lr->file = strdup(++file);
+ if (lr->file == NULL) {
+ err = -ENOMEM;
+ goto err;
+ }
+ lr->function = name;
+ } else if (strchr(name, '.'))
lr->file = name;
else
lr->function = name;
}
/* Loop 2: add all events */
- for (i = 0; i < npevs && ret >= 0; i++)
+ for (i = 0; i < npevs; i++) {
ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
pkgs[i].ntevs, force_add);
+ if (ret < 0)
+ break;
+ }
end:
/* Loop 3: cleanup and free trace events */
for (i = 0; i < npevs; i++) {
return ret;
}
+/* TODO: don't use a global variable for filter ... */
+static struct strfilter *available_func_filter;
+
+/*
+ * If a symbol corresponds to a function with global binding and
+ * matches filter return 0. For all others return 1.
+ */
+static int filter_available_functions(struct map *map __unused,
+ struct symbol *sym)
+{
+ if (sym->binding == STB_GLOBAL &&
+ strfilter__compare(available_func_filter, sym->name))
+ return 0;
+ return 1;
+}
+
+int show_available_funcs(const char *module, struct strfilter *_filter)
+{
+ struct map *map;
+ int ret;
+
+ setup_pager();
+
+ ret = init_vmlinux();
+ if (ret < 0)
+ return ret;
+ map = kernel_get_module_map(module);
+ if (!map) {
+ pr_err("Failed to find %s map.\n", (module) ? : "kernel");
+ return -EINVAL;
+ }
+ available_func_filter = _filter;
+ if (map__load(map, filter_available_functions)) {
+ pr_err("Failed to load map.\n");
+ return -EINVAL;
+ }
+ if (!dso__sorted_by_name(map->dso, map->type))
+ dso__sort_by_name(map->dso, map->type);
+
+ dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+ return 0;
+}
#include <stdbool.h>
#include "strlist.h"
+#include "strfilter.h"
extern bool probe_event_dry_run;
extern int show_line_range(struct line_range *lr, const char *module);
extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
int max_probe_points, const char *module,
- bool externs);
+ struct strfilter *filter, bool externs);
+extern int show_available_funcs(const char *module, struct strfilter *filter);
/* Maximum index number of event-name postfix */
#include <ctype.h>
#include <dwarf-regs.h>
+#include <linux/bitops.h>
#include "event.h"
#include "debug.h"
#include "util.h"
return name ? (strcmp(tname, name) == 0) : false;
}
+/* Get callsite line number of inline-function instance */
+static int die_get_call_lineno(Dwarf_Die *in_die)
+{
+ Dwarf_Attribute attr;
+ Dwarf_Word ret;
+
+ if (!dwarf_attr(in_die, DW_AT_call_line, &attr))
+ return -ENOENT;
+
+ dwarf_formudata(&attr, &ret);
+ return (int)ret;
+}
+
/* Get type die */
static Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
{
return vr_die;
}
-static bool die_is_signed_type(Dwarf_Die *tp_die)
+static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name,
+ Dwarf_Word *result)
{
Dwarf_Attribute attr;
+
+ if (dwarf_attr(tp_die, attr_name, &attr) == NULL ||
+ dwarf_formudata(&attr, result) != 0)
+ return -ENOENT;
+
+ return 0;
+}
+
+static bool die_is_signed_type(Dwarf_Die *tp_die)
+{
Dwarf_Word ret;
- if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL ||
- dwarf_formudata(&attr, &ret) != 0)
+ if (die_get_attr_udata(tp_die, DW_AT_encoding, &ret))
return false;
return (ret == DW_ATE_signed_char || ret == DW_ATE_signed ||
static int die_get_byte_size(Dwarf_Die *tp_die)
{
- Dwarf_Attribute attr;
Dwarf_Word ret;
- if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL ||
- dwarf_formudata(&attr, &ret) != 0)
+ if (die_get_attr_udata(tp_die, DW_AT_byte_size, &ret))
+ return 0;
+
+ return (int)ret;
+}
+
+static int die_get_bit_size(Dwarf_Die *tp_die)
+{
+ Dwarf_Word ret;
+
+ if (die_get_attr_udata(tp_die, DW_AT_bit_size, &ret))
+ return 0;
+
+ return (int)ret;
+}
+
+static int die_get_bit_offset(Dwarf_Die *tp_die)
+{
+ Dwarf_Word ret;
+
+ if (die_get_attr_udata(tp_die, DW_AT_bit_offset, &ret))
return 0;
return (int)ret;
return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
}
+/* Walker on lines (Note: line number will not be sorted) */
+typedef int (* line_walk_handler_t) (const char *fname, int lineno,
+ Dwarf_Addr addr, void *data);
+
+struct __line_walk_param {
+ const char *fname;
+ line_walk_handler_t handler;
+ void *data;
+ int retval;
+};
+
+static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data)
+{
+ struct __line_walk_param *lw = data;
+ Dwarf_Addr addr;
+ int lineno;
+
+ if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) {
+ lineno = die_get_call_lineno(in_die);
+ if (lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) {
+ lw->retval = lw->handler(lw->fname, lineno, addr,
+ lw->data);
+ if (lw->retval != 0)
+ return DIE_FIND_CB_FOUND;
+ }
+ }
+ return DIE_FIND_CB_SIBLING;
+}
+
+/* Walk on lines of blocks included in given DIE */
+static int __die_walk_funclines(Dwarf_Die *sp_die,
+ line_walk_handler_t handler, void *data)
+{
+ struct __line_walk_param lw = {
+ .handler = handler,
+ .data = data,
+ .retval = 0,
+ };
+ Dwarf_Die die_mem;
+ Dwarf_Addr addr;
+ int lineno;
+
+ /* Handle function declaration line */
+ lw.fname = dwarf_decl_file(sp_die);
+ if (lw.fname && dwarf_decl_line(sp_die, &lineno) == 0 &&
+ dwarf_entrypc(sp_die, &addr) == 0) {
+ lw.retval = handler(lw.fname, lineno, addr, data);
+ if (lw.retval != 0)
+ goto done;
+ }
+ die_find_child(sp_die, __die_walk_funclines_cb, &lw, &die_mem);
+done:
+ return lw.retval;
+}
+
+static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data)
+{
+ struct __line_walk_param *lw = data;
+
+ lw->retval = __die_walk_funclines(sp_die, lw->handler, lw->data);
+ if (lw->retval != 0)
+ return DWARF_CB_ABORT;
+
+ return DWARF_CB_OK;
+}
+
+/*
+ * Walk on lines inside given PDIE. If the PDIE is subprogram, walk only on
+ * the lines inside the subprogram, otherwise PDIE must be a CU DIE.
+ */
+static int die_walk_lines(Dwarf_Die *pdie, line_walk_handler_t handler,
+ void *data)
+{
+ Dwarf_Lines *lines;
+ Dwarf_Line *line;
+ Dwarf_Addr addr;
+ const char *fname;
+ int lineno, ret = 0;
+ Dwarf_Die die_mem, *cu_die;
+ size_t nlines, i;
+
+ /* Get the CU die */
+ if (dwarf_tag(pdie) == DW_TAG_subprogram)
+ cu_die = dwarf_diecu(pdie, &die_mem, NULL, NULL);
+ else
+ cu_die = pdie;
+ if (!cu_die) {
+ pr_debug2("Failed to get CU from subprogram\n");
+ return -EINVAL;
+ }
+
+ /* Get lines list in the CU */
+ if (dwarf_getsrclines(cu_die, &lines, &nlines) != 0) {
+ pr_debug2("Failed to get source lines on this CU.\n");
+ return -ENOENT;
+ }
+ pr_debug2("Get %zd lines from this CU\n", nlines);
+
+ /* Walk on the lines on lines list */
+ for (i = 0; i < nlines; i++) {
+ line = dwarf_onesrcline(lines, i);
+ if (line == NULL ||
+ dwarf_lineno(line, &lineno) != 0 ||
+ dwarf_lineaddr(line, &addr) != 0) {
+ pr_debug2("Failed to get line info. "
+ "Possible error in debuginfo.\n");
+ continue;
+ }
+ /* Filter lines based on address */
+ if (pdie != cu_die)
+ /*
+ * Address filtering
+ * The line is included in given function, and
+ * no inline block includes it.
+ */
+ if (!dwarf_haspc(pdie, addr) ||
+ die_find_inlinefunc(pdie, addr, &die_mem))
+ continue;
+ /* Get source line */
+ fname = dwarf_linesrc(line, NULL, NULL);
+
+ ret = handler(fname, lineno, addr, data);
+ if (ret != 0)
+ return ret;
+ }
+
+ /*
+ * Dwarf lines doesn't include function declarations and inlined
+ * subroutines. We have to check functions list or given function.
+ */
+ if (pdie != cu_die)
+ ret = __die_walk_funclines(pdie, handler, data);
+ else {
+ struct __line_walk_param param = {
+ .handler = handler,
+ .data = data,
+ .retval = 0,
+ };
+ dwarf_getfuncs(cu_die, __die_walk_culines_cb, ¶m, 0);
+ ret = param.retval;
+ }
+
+ return ret;
+}
+
struct __find_variable_param {
const char *name;
Dwarf_Addr addr;
return 0;
}
+#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_LONG / sizeof(long))
+
static int convert_variable_type(Dwarf_Die *vr_die,
struct probe_trace_arg *tvar,
const char *cast)
return (tvar->type == NULL) ? -ENOMEM : 0;
}
+ if (die_get_bit_size(vr_die) != 0) {
+ /* This is a bitfield */
+ ret = snprintf(buf, 16, "b%d@%d/%zd", die_get_bit_size(vr_die),
+ die_get_bit_offset(vr_die),
+ BYTES_TO_BITS(die_get_byte_size(vr_die)));
+ goto formatted;
+ }
+
if (die_get_real_type(vr_die, &type) == NULL) {
pr_warning("Failed to get a type information of %s.\n",
dwarf_diename(vr_die));
return (tvar->type == NULL) ? -ENOMEM : 0;
}
- ret = die_get_byte_size(&type) * 8;
- if (ret) {
- /* Check the bitwidth */
- if (ret > MAX_BASIC_TYPE_BITS) {
- pr_info("%s exceeds max-bitwidth."
- " Cut down to %d bits.\n",
- dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
- ret = MAX_BASIC_TYPE_BITS;
- }
+ ret = BYTES_TO_BITS(die_get_byte_size(&type));
+ if (!ret)
+ /* No size ... try to use default type */
+ return 0;
- ret = snprintf(buf, 16, "%c%d",
- die_is_signed_type(&type) ? 's' : 'u', ret);
- if (ret < 0 || ret >= 16) {
- if (ret >= 16)
- ret = -E2BIG;
- pr_warning("Failed to convert variable type: %s\n",
- strerror(-ret));
- return ret;
- }
- tvar->type = strdup(buf);
- if (tvar->type == NULL)
- return -ENOMEM;
+ /* Check the bitwidth */
+ if (ret > MAX_BASIC_TYPE_BITS) {
+ pr_info("%s exceeds max-bitwidth. Cut down to %d bits.\n",
+ dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
+ ret = MAX_BASIC_TYPE_BITS;
+ }
+ ret = snprintf(buf, 16, "%c%d",
+ die_is_signed_type(&type) ? 's' : 'u', ret);
+
+formatted:
+ if (ret < 0 || ret >= 16) {
+ if (ret >= 16)
+ ret = -E2BIG;
+ pr_warning("Failed to convert variable type: %s\n",
+ strerror(-ret));
+ return ret;
}
+ tvar->type = strdup(buf);
+ if (tvar->type == NULL)
+ return -ENOMEM;
return 0;
}
return ret;
}
-/* Find probe point from its line number */
-static int find_probe_point_by_line(struct probe_finder *pf)
+static int probe_point_line_walker(const char *fname, int lineno,
+ Dwarf_Addr addr, void *data)
{
- Dwarf_Lines *lines;
- Dwarf_Line *line;
- size_t nlines, i;
- Dwarf_Addr addr;
- int lineno;
- int ret = 0;
-
- if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
- pr_warning("No source lines found.\n");
- return -ENOENT;
- }
+ struct probe_finder *pf = data;
+ int ret;
- for (i = 0; i < nlines && ret == 0; i++) {
- line = dwarf_onesrcline(lines, i);
- if (dwarf_lineno(line, &lineno) != 0 ||
- lineno != pf->lno)
- continue;
+ if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0)
+ return 0;
- /* TODO: Get fileno from line, but how? */
- if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
- continue;
+ pf->addr = addr;
+ ret = call_probe_finder(NULL, pf);
- if (dwarf_lineaddr(line, &addr) != 0) {
- pr_warning("Failed to get the address of the line.\n");
- return -ENOENT;
- }
- pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n",
- (int)i, lineno, (uintmax_t)addr);
- pf->addr = addr;
+ /* Continue if no error, because the line will be in inline function */
+ return ret < 0 ? ret : 0;
+}
- ret = call_probe_finder(NULL, pf);
- /* Continuing, because target line might be inlined. */
- }
- return ret;
+/* Find probe point from its line number */
+static int find_probe_point_by_line(struct probe_finder *pf)
+{
+ return die_walk_lines(&pf->cu_die, probe_point_line_walker, pf);
}
/* Find lines which match lazy pattern */
static int find_lazy_match_lines(struct list_head *head,
const char *fname, const char *pat)
{
- char *fbuf, *p1, *p2;
- int fd, line, nlines = -1;
- struct stat st;
-
- fd = open(fname, O_RDONLY);
- if (fd < 0) {
- pr_warning("Failed to open %s: %s\n", fname, strerror(-fd));
+ FILE *fp;
+ char *line = NULL;
+ size_t line_len;
+ ssize_t len;
+ int count = 0, linenum = 1;
+
+ fp = fopen(fname, "r");
+ if (!fp) {
+ pr_warning("Failed to open %s: %s\n", fname, strerror(errno));
return -errno;
}
- if (fstat(fd, &st) < 0) {
- pr_warning("Failed to get the size of %s: %s\n",
- fname, strerror(errno));
- nlines = -errno;
- goto out_close;
- }
-
- nlines = -ENOMEM;
- fbuf = malloc(st.st_size + 2);
- if (fbuf == NULL)
- goto out_close;
- if (read(fd, fbuf, st.st_size) < 0) {
- pr_warning("Failed to read %s: %s\n", fname, strerror(errno));
- nlines = -errno;
- goto out_free_fbuf;
- }
- fbuf[st.st_size] = '\n'; /* Dummy line */
- fbuf[st.st_size + 1] = '\0';
- p1 = fbuf;
- line = 1;
- nlines = 0;
- while ((p2 = strchr(p1, '\n')) != NULL) {
- *p2 = '\0';
- if (strlazymatch(p1, pat)) {
- line_list__add_line(head, line);
- nlines++;
+ while ((len = getline(&line, &line_len, fp)) > 0) {
+
+ if (line[len - 1] == '\n')
+ line[len - 1] = '\0';
+
+ if (strlazymatch(line, pat)) {
+ line_list__add_line(head, linenum);
+ count++;
}
- line++;
- p1 = p2 + 1;
+ linenum++;
}
-out_free_fbuf:
- free(fbuf);
-out_close:
- close(fd);
- return nlines;
+
+ if (ferror(fp))
+ count = -errno;
+ free(line);
+ fclose(fp);
+
+ if (count == 0)
+ pr_debug("No matched lines found in %s.\n", fname);
+ return count;
+}
+
+static int probe_point_lazy_walker(const char *fname, int lineno,
+ Dwarf_Addr addr, void *data)
+{
+ struct probe_finder *pf = data;
+ int ret;
+
+ if (!line_list__has_line(&pf->lcache, lineno) ||
+ strtailcmp(fname, pf->fname) != 0)
+ return 0;
+
+ pr_debug("Probe line found: line:%d addr:0x%llx\n",
+ lineno, (unsigned long long)addr);
+ pf->addr = addr;
+ ret = call_probe_finder(NULL, pf);
+
+ /*
+ * Continue if no error, because the lazy pattern will match
+ * to other lines
+ */
+ return ret < 0 ? ret : 0;
}
/* Find probe points from lazy pattern */
static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
{
- Dwarf_Lines *lines;
- Dwarf_Line *line;
- size_t nlines, i;
- Dwarf_Addr addr;
- Dwarf_Die die_mem;
- int lineno;
int ret = 0;
if (list_empty(&pf->lcache)) {
/* Matching lazy line pattern */
ret = find_lazy_match_lines(&pf->lcache, pf->fname,
pf->pev->point.lazy_line);
- if (ret == 0) {
- pr_debug("No matched lines found in %s.\n", pf->fname);
- return 0;
- } else if (ret < 0)
+ if (ret <= 0)
return ret;
}
- if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
- pr_warning("No source lines found.\n");
- return -ENOENT;
- }
-
- for (i = 0; i < nlines && ret >= 0; i++) {
- line = dwarf_onesrcline(lines, i);
-
- if (dwarf_lineno(line, &lineno) != 0 ||
- !line_list__has_line(&pf->lcache, lineno))
- continue;
-
- /* TODO: Get fileno from line, but how? */
- if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
- continue;
-
- if (dwarf_lineaddr(line, &addr) != 0) {
- pr_debug("Failed to get the address of line %d.\n",
- lineno);
- continue;
- }
- if (sp_die) {
- /* Address filtering 1: does sp_die include addr? */
- if (!dwarf_haspc(sp_die, addr))
- continue;
- /* Address filtering 2: No child include addr? */
- if (die_find_inlinefunc(sp_die, addr, &die_mem))
- continue;
- }
-
- pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n",
- (int)i, lineno, (unsigned long long)addr);
- pf->addr = addr;
-
- ret = call_probe_finder(sp_die, pf);
- /* Continuing, because target line might be inlined. */
- }
- /* TODO: deallocate lines, but how? */
- return ret;
+ return die_walk_lines(sp_die, probe_point_lazy_walker, pf);
}
/* Callback parameter with return value */
off = 0;
line_list__init(&pf->lcache);
/* Loop on CUs (Compilation Unit) */
- while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) &&
- ret >= 0) {
+ while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
/* Get the DIE(Debugging Information Entry) of this CU */
diep = dwarf_offdie(dbg, off + cuhl, &pf->cu_die);
if (!diep)
pf->lno = pp->line;
ret = find_probe_point_by_line(pf);
}
+ if (ret < 0)
+ break;
}
off = noff;
}
return line_list__add_line(&lr->line_list, lineno);
}
-/* Search function declaration lines */
-static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data)
+static int line_range_walk_cb(const char *fname, int lineno,
+ Dwarf_Addr addr __used,
+ void *data)
{
- struct dwarf_callback_param *param = data;
- struct line_finder *lf = param->data;
- const char *src;
- int lineno;
+ struct line_finder *lf = data;
- src = dwarf_decl_file(sp_die);
- if (src && strtailcmp(src, lf->fname) != 0)
- return DWARF_CB_OK;
-
- if (dwarf_decl_line(sp_die, &lineno) != 0 ||
+ if ((strtailcmp(fname, lf->fname) != 0) ||
(lf->lno_s > lineno || lf->lno_e < lineno))
- return DWARF_CB_OK;
+ return 0;
- param->retval = line_range_add_line(src, lineno, lf->lr);
- if (param->retval < 0)
- return DWARF_CB_ABORT;
- return DWARF_CB_OK;
-}
+ if (line_range_add_line(fname, lineno, lf->lr) < 0)
+ return -EINVAL;
-static int find_line_range_func_decl_lines(struct line_finder *lf)
-{
- struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
- dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, ¶m, 0);
- return param.retval;
+ return 0;
}
/* Find line range from its line number */
static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
{
- Dwarf_Lines *lines;
- Dwarf_Line *line;
- size_t nlines, i;
- Dwarf_Addr addr;
- int lineno, ret = 0;
- const char *src;
- Dwarf_Die die_mem;
-
- line_list__init(&lf->lr->line_list);
- if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) {
- pr_warning("No source lines found.\n");
- return -ENOENT;
- }
-
- /* Search probable lines on lines list */
- for (i = 0; i < nlines; i++) {
- line = dwarf_onesrcline(lines, i);
- if (dwarf_lineno(line, &lineno) != 0 ||
- (lf->lno_s > lineno || lf->lno_e < lineno))
- continue;
-
- if (sp_die) {
- /* Address filtering 1: does sp_die include addr? */
- if (dwarf_lineaddr(line, &addr) != 0 ||
- !dwarf_haspc(sp_die, addr))
- continue;
-
- /* Address filtering 2: No child include addr? */
- if (die_find_inlinefunc(sp_die, addr, &die_mem))
- continue;
- }
-
- /* TODO: Get fileno from line, but how? */
- src = dwarf_linesrc(line, NULL, NULL);
- if (strtailcmp(src, lf->fname) != 0)
- continue;
-
- ret = line_range_add_line(src, lineno, lf->lr);
- if (ret < 0)
- return ret;
- }
+ int ret;
- /*
- * Dwarf lines doesn't include function declarations. We have to
- * check functions list or given function.
- */
- if (sp_die) {
- src = dwarf_decl_file(sp_die);
- if (src && dwarf_decl_line(sp_die, &lineno) == 0 &&
- (lf->lno_s <= lineno && lf->lno_e >= lineno))
- ret = line_range_add_line(src, lineno, lf->lr);
- } else
- ret = find_line_range_func_decl_lines(lf);
+ ret = die_walk_lines(sp_die ?: &lf->cu_die, line_range_walk_cb, lf);
/* Update status */
if (ret >= 0)
struct line_finder *lf = param->data;
struct line_range *lr = lf->lr;
- pr_debug("find (%llx) %s\n",
- (unsigned long long)dwarf_dieoffset(sp_die),
- dwarf_diename(sp_die));
if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
die_compare_name(sp_die, lr->function)) {
lf->fname = dwarf_decl_file(sp_die);
--- /dev/null
+#include <Python.h>
+#include <structmember.h>
+#include <inttypes.h>
+#include <poll.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "event.h"
+#include "cpumap.h"
+#include "thread_map.h"
+
+/* Define PyVarObject_HEAD_INIT for python 2.5 */
+#ifndef PyVarObject_HEAD_INIT
+# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
+#endif
+
+struct throttle_event {
+ struct perf_event_header header;
+ u64 time;
+ u64 id;
+ u64 stream_id;
+};
+
+PyMODINIT_FUNC initperf(void);
+
+#define member_def(type, member, ptype, help) \
+ { #member, ptype, \
+ offsetof(struct pyrf_event, event) + offsetof(struct type, member), \
+ 0, help }
+
+#define sample_member_def(name, member, ptype, help) \
+ { #name, ptype, \
+ offsetof(struct pyrf_event, sample) + offsetof(struct perf_sample, member), \
+ 0, help }
+
+struct pyrf_event {
+ PyObject_HEAD
+ struct perf_sample sample;
+ union perf_event event;
+};
+
+#define sample_members \
+ sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \
+ sample_member_def(sample_pid, pid, T_INT, "event pid"), \
+ sample_member_def(sample_tid, tid, T_INT, "event tid"), \
+ sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \
+ sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"), \
+ sample_member_def(sample_id, id, T_ULONGLONG, "event id"), \
+ sample_member_def(sample_stream_id, stream_id, T_ULONGLONG, "event stream id"), \
+ sample_member_def(sample_period, period, T_ULONGLONG, "event period"), \
+ sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"),
+
+static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object.");
+
+static PyMemberDef pyrf_mmap_event__members[] = {
+ sample_members
+ member_def(perf_event_header, type, T_UINT, "event type"),
+ member_def(mmap_event, pid, T_UINT, "event pid"),
+ member_def(mmap_event, tid, T_UINT, "event tid"),
+ member_def(mmap_event, start, T_ULONGLONG, "start of the map"),
+ member_def(mmap_event, len, T_ULONGLONG, "map length"),
+ member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"),
+ member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"),
+ { .name = NULL, },
+};
+
+static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent)
+{
+ PyObject *ret;
+ char *s;
+
+ if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", "
+ "length: %#" PRIx64 ", offset: %#" PRIx64 ", "
+ "filename: %s }",
+ pevent->event.mmap.pid, pevent->event.mmap.tid,
+ pevent->event.mmap.start, pevent->event.mmap.len,
+ pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) {
+ ret = PyErr_NoMemory();
+ } else {
+ ret = PyString_FromString(s);
+ free(s);
+ }
+ return ret;
+}
+
+static PyTypeObject pyrf_mmap_event__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.mmap_event",
+ .tp_basicsize = sizeof(struct pyrf_event),
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_mmap_event__doc,
+ .tp_members = pyrf_mmap_event__members,
+ .tp_repr = (reprfunc)pyrf_mmap_event__repr,
+};
+
+static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object.");
+
+static PyMemberDef pyrf_task_event__members[] = {
+ sample_members
+ member_def(perf_event_header, type, T_UINT, "event type"),
+ member_def(fork_event, pid, T_UINT, "event pid"),
+ member_def(fork_event, ppid, T_UINT, "event ppid"),
+ member_def(fork_event, tid, T_UINT, "event tid"),
+ member_def(fork_event, ptid, T_UINT, "event ptid"),
+ member_def(fork_event, time, T_ULONGLONG, "timestamp"),
+ { .name = NULL, },
+};
+
+static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
+{
+ return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
+ "ptid: %u, time: %" PRIu64 "}",
+ pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
+ pevent->event.fork.pid,
+ pevent->event.fork.ppid,
+ pevent->event.fork.tid,
+ pevent->event.fork.ptid,
+ pevent->event.fork.time);
+}
+
+static PyTypeObject pyrf_task_event__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.task_event",
+ .tp_basicsize = sizeof(struct pyrf_event),
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_task_event__doc,
+ .tp_members = pyrf_task_event__members,
+ .tp_repr = (reprfunc)pyrf_task_event__repr,
+};
+
+static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object.");
+
+static PyMemberDef pyrf_comm_event__members[] = {
+ sample_members
+ member_def(perf_event_header, type, T_UINT, "event type"),
+ member_def(comm_event, pid, T_UINT, "event pid"),
+ member_def(comm_event, tid, T_UINT, "event tid"),
+ member_def(comm_event, comm, T_STRING_INPLACE, "process name"),
+ { .name = NULL, },
+};
+
+static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent)
+{
+ return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
+ pevent->event.comm.pid,
+ pevent->event.comm.tid,
+ pevent->event.comm.comm);
+}
+
+static PyTypeObject pyrf_comm_event__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.comm_event",
+ .tp_basicsize = sizeof(struct pyrf_event),
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_comm_event__doc,
+ .tp_members = pyrf_comm_event__members,
+ .tp_repr = (reprfunc)pyrf_comm_event__repr,
+};
+
+static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object.");
+
+static PyMemberDef pyrf_throttle_event__members[] = {
+ sample_members
+ member_def(perf_event_header, type, T_UINT, "event type"),
+ member_def(throttle_event, time, T_ULONGLONG, "timestamp"),
+ member_def(throttle_event, id, T_ULONGLONG, "event id"),
+ member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"),
+ { .name = NULL, },
+};
+
+static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
+{
+ struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1);
+
+ return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
+ ", stream_id: %" PRIu64 " }",
+ pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
+ te->time, te->id, te->stream_id);
+}
+
+static PyTypeObject pyrf_throttle_event__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.throttle_event",
+ .tp_basicsize = sizeof(struct pyrf_event),
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_throttle_event__doc,
+ .tp_members = pyrf_throttle_event__members,
+ .tp_repr = (reprfunc)pyrf_throttle_event__repr,
+};
+
+static int pyrf_event__setup_types(void)
+{
+ int err;
+ pyrf_mmap_event__type.tp_new =
+ pyrf_task_event__type.tp_new =
+ pyrf_comm_event__type.tp_new =
+ pyrf_throttle_event__type.tp_new = PyType_GenericNew;
+ err = PyType_Ready(&pyrf_mmap_event__type);
+ if (err < 0)
+ goto out;
+ err = PyType_Ready(&pyrf_task_event__type);
+ if (err < 0)
+ goto out;
+ err = PyType_Ready(&pyrf_comm_event__type);
+ if (err < 0)
+ goto out;
+ err = PyType_Ready(&pyrf_throttle_event__type);
+ if (err < 0)
+ goto out;
+out:
+ return err;
+}
+
+static PyTypeObject *pyrf_event__type[] = {
+ [PERF_RECORD_MMAP] = &pyrf_mmap_event__type,
+ [PERF_RECORD_LOST] = &pyrf_mmap_event__type,
+ [PERF_RECORD_COMM] = &pyrf_comm_event__type,
+ [PERF_RECORD_EXIT] = &pyrf_task_event__type,
+ [PERF_RECORD_THROTTLE] = &pyrf_throttle_event__type,
+ [PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type,
+ [PERF_RECORD_FORK] = &pyrf_task_event__type,
+ [PERF_RECORD_READ] = &pyrf_mmap_event__type,
+ [PERF_RECORD_SAMPLE] = &pyrf_mmap_event__type,
+};
+
+static PyObject *pyrf_event__new(union perf_event *event)
+{
+ struct pyrf_event *pevent;
+ PyTypeObject *ptype;
+
+ if (event->header.type < PERF_RECORD_MMAP ||
+ event->header.type > PERF_RECORD_SAMPLE)
+ return NULL;
+
+ ptype = pyrf_event__type[event->header.type];
+ pevent = PyObject_New(struct pyrf_event, ptype);
+ if (pevent != NULL)
+ memcpy(&pevent->event, event, event->header.size);
+ return (PyObject *)pevent;
+}
+
+struct pyrf_cpu_map {
+ PyObject_HEAD
+
+ struct cpu_map *cpus;
+};
+
+static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
+ PyObject *args, PyObject *kwargs)
+{
+ static char *kwlist[] = { "cpustr", NULL, NULL, };
+ char *cpustr = NULL;
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|s",
+ kwlist, &cpustr))
+ return -1;
+
+ pcpus->cpus = cpu_map__new(cpustr);
+ if (pcpus->cpus == NULL)
+ return -1;
+ return 0;
+}
+
+static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
+{
+ cpu_map__delete(pcpus->cpus);
+ pcpus->ob_type->tp_free((PyObject*)pcpus);
+}
+
+static Py_ssize_t pyrf_cpu_map__length(PyObject *obj)
+{
+ struct pyrf_cpu_map *pcpus = (void *)obj;
+
+ return pcpus->cpus->nr;
+}
+
+static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i)
+{
+ struct pyrf_cpu_map *pcpus = (void *)obj;
+
+ if (i >= pcpus->cpus->nr)
+ return NULL;
+
+ return Py_BuildValue("i", pcpus->cpus->map[i]);
+}
+
+static PySequenceMethods pyrf_cpu_map__sequence_methods = {
+ .sq_length = pyrf_cpu_map__length,
+ .sq_item = pyrf_cpu_map__item,
+};
+
+static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object.");
+
+static PyTypeObject pyrf_cpu_map__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.cpu_map",
+ .tp_basicsize = sizeof(struct pyrf_cpu_map),
+ .tp_dealloc = (destructor)pyrf_cpu_map__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_cpu_map__doc,
+ .tp_as_sequence = &pyrf_cpu_map__sequence_methods,
+ .tp_init = (initproc)pyrf_cpu_map__init,
+};
+
+static int pyrf_cpu_map__setup_types(void)
+{
+ pyrf_cpu_map__type.tp_new = PyType_GenericNew;
+ return PyType_Ready(&pyrf_cpu_map__type);
+}
+
+struct pyrf_thread_map {
+ PyObject_HEAD
+
+ struct thread_map *threads;
+};
+
+static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
+ PyObject *args, PyObject *kwargs)
+{
+ static char *kwlist[] = { "pid", "tid", NULL, NULL, };
+ int pid = -1, tid = -1;
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii",
+ kwlist, &pid, &tid))
+ return -1;
+
+ pthreads->threads = thread_map__new(pid, tid);
+ if (pthreads->threads == NULL)
+ return -1;
+ return 0;
+}
+
+static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
+{
+ thread_map__delete(pthreads->threads);
+ pthreads->ob_type->tp_free((PyObject*)pthreads);
+}
+
+static Py_ssize_t pyrf_thread_map__length(PyObject *obj)
+{
+ struct pyrf_thread_map *pthreads = (void *)obj;
+
+ return pthreads->threads->nr;
+}
+
+static PyObject *pyrf_thread_map__item(PyObject *obj, Py_ssize_t i)
+{
+ struct pyrf_thread_map *pthreads = (void *)obj;
+
+ if (i >= pthreads->threads->nr)
+ return NULL;
+
+ return Py_BuildValue("i", pthreads->threads->map[i]);
+}
+
+static PySequenceMethods pyrf_thread_map__sequence_methods = {
+ .sq_length = pyrf_thread_map__length,
+ .sq_item = pyrf_thread_map__item,
+};
+
+static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object.");
+
+static PyTypeObject pyrf_thread_map__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.thread_map",
+ .tp_basicsize = sizeof(struct pyrf_thread_map),
+ .tp_dealloc = (destructor)pyrf_thread_map__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_thread_map__doc,
+ .tp_as_sequence = &pyrf_thread_map__sequence_methods,
+ .tp_init = (initproc)pyrf_thread_map__init,
+};
+
+static int pyrf_thread_map__setup_types(void)
+{
+ pyrf_thread_map__type.tp_new = PyType_GenericNew;
+ return PyType_Ready(&pyrf_thread_map__type);
+}
+
+struct pyrf_evsel {
+ PyObject_HEAD
+
+ struct perf_evsel evsel;
+};
+
+static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
+ PyObject *args, PyObject *kwargs)
+{
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ .sample_type = PERF_SAMPLE_PERIOD | PERF_SAMPLE_TID,
+ };
+ static char *kwlist[] = {
+ "type",
+ "config",
+ "sample_freq",
+ "sample_period",
+ "sample_type",
+ "read_format",
+ "disabled",
+ "inherit",
+ "pinned",
+ "exclusive",
+ "exclude_user",
+ "exclude_kernel",
+ "exclude_hv",
+ "exclude_idle",
+ "mmap",
+ "comm",
+ "freq",
+ "inherit_stat",
+ "enable_on_exec",
+ "task",
+ "watermark",
+ "precise_ip",
+ "mmap_data",
+ "sample_id_all",
+ "wakeup_events",
+ "bp_type",
+ "bp_addr",
+ "bp_len", NULL, NULL, };
+ u64 sample_period = 0;
+ u32 disabled = 0,
+ inherit = 0,
+ pinned = 0,
+ exclusive = 0,
+ exclude_user = 0,
+ exclude_kernel = 0,
+ exclude_hv = 0,
+ exclude_idle = 0,
+ mmap = 0,
+ comm = 0,
+ freq = 1,
+ inherit_stat = 0,
+ enable_on_exec = 0,
+ task = 0,
+ watermark = 0,
+ precise_ip = 0,
+ mmap_data = 0,
+ sample_id_all = 1;
+ int idx = 0;
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs,
+ "|iKiKKiiiiiiiiiiiiiiiiiiiiiKK", kwlist,
+ &attr.type, &attr.config, &attr.sample_freq,
+ &sample_period, &attr.sample_type,
+ &attr.read_format, &disabled, &inherit,
+ &pinned, &exclusive, &exclude_user,
+ &exclude_kernel, &exclude_hv, &exclude_idle,
+ &mmap, &comm, &freq, &inherit_stat,
+ &enable_on_exec, &task, &watermark,
+ &precise_ip, &mmap_data, &sample_id_all,
+ &attr.wakeup_events, &attr.bp_type,
+ &attr.bp_addr, &attr.bp_len, &idx))
+ return -1;
+
+ /* union... */
+ if (sample_period != 0) {
+ if (attr.sample_freq != 0)
+ return -1; /* FIXME: throw right exception */
+ attr.sample_period = sample_period;
+ }
+
+ /* Bitfields */
+ attr.disabled = disabled;
+ attr.inherit = inherit;
+ attr.pinned = pinned;
+ attr.exclusive = exclusive;
+ attr.exclude_user = exclude_user;
+ attr.exclude_kernel = exclude_kernel;
+ attr.exclude_hv = exclude_hv;
+ attr.exclude_idle = exclude_idle;
+ attr.mmap = mmap;
+ attr.comm = comm;
+ attr.freq = freq;
+ attr.inherit_stat = inherit_stat;
+ attr.enable_on_exec = enable_on_exec;
+ attr.task = task;
+ attr.watermark = watermark;
+ attr.precise_ip = precise_ip;
+ attr.mmap_data = mmap_data;
+ attr.sample_id_all = sample_id_all;
+
+ perf_evsel__init(&pevsel->evsel, &attr, idx);
+ return 0;
+}
+
+static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
+{
+ perf_evsel__exit(&pevsel->evsel);
+ pevsel->ob_type->tp_free((PyObject*)pevsel);
+}
+
+static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
+ PyObject *args, PyObject *kwargs)
+{
+ struct perf_evsel *evsel = &pevsel->evsel;
+ struct cpu_map *cpus = NULL;
+ struct thread_map *threads = NULL;
+ PyObject *pcpus = NULL, *pthreads = NULL;
+ int group = 0, overwrite = 0;
+ static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL};
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
+ &pcpus, &pthreads, &group, &overwrite))
+ return NULL;
+
+ if (pthreads != NULL)
+ threads = ((struct pyrf_thread_map *)pthreads)->threads;
+
+ if (pcpus != NULL)
+ cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
+
+ if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) {
+ PyErr_SetFromErrno(PyExc_OSError);
+ return NULL;
+ }
+
+ Py_INCREF(Py_None);
+ return Py_None;
+}
+
+static PyMethodDef pyrf_evsel__methods[] = {
+ {
+ .ml_name = "open",
+ .ml_meth = (PyCFunction)pyrf_evsel__open,
+ .ml_flags = METH_VARARGS | METH_KEYWORDS,
+ .ml_doc = PyDoc_STR("open the event selector file descriptor table.")
+ },
+ { .ml_name = NULL, }
+};
+
+static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object.");
+
+static PyTypeObject pyrf_evsel__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.evsel",
+ .tp_basicsize = sizeof(struct pyrf_evsel),
+ .tp_dealloc = (destructor)pyrf_evsel__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_evsel__doc,
+ .tp_methods = pyrf_evsel__methods,
+ .tp_init = (initproc)pyrf_evsel__init,
+};
+
+static int pyrf_evsel__setup_types(void)
+{
+ pyrf_evsel__type.tp_new = PyType_GenericNew;
+ return PyType_Ready(&pyrf_evsel__type);
+}
+
+struct pyrf_evlist {
+ PyObject_HEAD
+
+ struct perf_evlist evlist;
+};
+
+static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
+ PyObject *args, PyObject *kwargs __used)
+{
+ PyObject *pcpus = NULL, *pthreads = NULL;
+ struct cpu_map *cpus;
+ struct thread_map *threads;
+
+ if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads))
+ return -1;
+
+ threads = ((struct pyrf_thread_map *)pthreads)->threads;
+ cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
+ perf_evlist__init(&pevlist->evlist, cpus, threads);
+ return 0;
+}
+
+static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
+{
+ perf_evlist__exit(&pevlist->evlist);
+ pevlist->ob_type->tp_free((PyObject*)pevlist);
+}
+
+static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
+ PyObject *args, PyObject *kwargs)
+{
+ struct perf_evlist *evlist = &pevlist->evlist;
+ static char *kwlist[] = {"pages", "overwrite",
+ NULL, NULL};
+ int pages = 128, overwrite = false;
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", kwlist,
+ &pages, &overwrite))
+ return NULL;
+
+ if (perf_evlist__mmap(evlist, pages, overwrite) < 0) {
+ PyErr_SetFromErrno(PyExc_OSError);
+ return NULL;
+ }
+
+ Py_INCREF(Py_None);
+ return Py_None;
+}
+
+static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
+ PyObject *args, PyObject *kwargs)
+{
+ struct perf_evlist *evlist = &pevlist->evlist;
+ static char *kwlist[] = {"timeout", NULL, NULL};
+ int timeout = -1, n;
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
+ return NULL;
+
+ n = poll(evlist->pollfd, evlist->nr_fds, timeout);
+ if (n < 0) {
+ PyErr_SetFromErrno(PyExc_OSError);
+ return NULL;
+ }
+
+ return Py_BuildValue("i", n);
+}
+
+static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
+ PyObject *args __used, PyObject *kwargs __used)
+{
+ struct perf_evlist *evlist = &pevlist->evlist;
+ PyObject *list = PyList_New(0);
+ int i;
+
+ for (i = 0; i < evlist->nr_fds; ++i) {
+ PyObject *file;
+ FILE *fp = fdopen(evlist->pollfd[i].fd, "r");
+
+ if (fp == NULL)
+ goto free_list;
+
+ file = PyFile_FromFile(fp, "perf", "r", NULL);
+ if (file == NULL)
+ goto free_list;
+
+ if (PyList_Append(list, file) != 0) {
+ Py_DECREF(file);
+ goto free_list;
+ }
+
+ Py_DECREF(file);
+ }
+
+ return list;
+free_list:
+ return PyErr_NoMemory();
+}
+
+
+static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
+ PyObject *args, PyObject *kwargs __used)
+{
+ struct perf_evlist *evlist = &pevlist->evlist;
+ PyObject *pevsel;
+ struct perf_evsel *evsel;
+
+ if (!PyArg_ParseTuple(args, "O", &pevsel))
+ return NULL;
+
+ Py_INCREF(pevsel);
+ evsel = &((struct pyrf_evsel *)pevsel)->evsel;
+ evsel->idx = evlist->nr_entries;
+ perf_evlist__add(evlist, evsel);
+
+ return Py_BuildValue("i", evlist->nr_entries);
+}
+
+static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
+ PyObject *args, PyObject *kwargs)
+{
+ struct perf_evlist *evlist = &pevlist->evlist;
+ union perf_event *event;
+ int sample_id_all = 1, cpu;
+ static char *kwlist[] = {"sample_id_all", NULL, NULL};
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
+ &cpu, &sample_id_all))
+ return NULL;
+
+ event = perf_evlist__read_on_cpu(evlist, cpu);
+ if (event != NULL) {
+ struct perf_evsel *first;
+ PyObject *pyevent = pyrf_event__new(event);
+ struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
+
+ if (pyevent == NULL)
+ return PyErr_NoMemory();
+
+ first = list_entry(evlist->entries.next, struct perf_evsel, node);
+ perf_event__parse_sample(event, first->attr.sample_type, sample_id_all,
+ &pevent->sample);
+ return pyevent;
+ }
+
+ Py_INCREF(Py_None);
+ return Py_None;
+}
+
+static PyMethodDef pyrf_evlist__methods[] = {
+ {
+ .ml_name = "mmap",
+ .ml_meth = (PyCFunction)pyrf_evlist__mmap,
+ .ml_flags = METH_VARARGS | METH_KEYWORDS,
+ .ml_doc = PyDoc_STR("mmap the file descriptor table.")
+ },
+ {
+ .ml_name = "poll",
+ .ml_meth = (PyCFunction)pyrf_evlist__poll,
+ .ml_flags = METH_VARARGS | METH_KEYWORDS,
+ .ml_doc = PyDoc_STR("poll the file descriptor table.")
+ },
+ {
+ .ml_name = "get_pollfd",
+ .ml_meth = (PyCFunction)pyrf_evlist__get_pollfd,
+ .ml_flags = METH_VARARGS | METH_KEYWORDS,
+ .ml_doc = PyDoc_STR("get the poll file descriptor table.")
+ },
+ {
+ .ml_name = "add",
+ .ml_meth = (PyCFunction)pyrf_evlist__add,
+ .ml_flags = METH_VARARGS | METH_KEYWORDS,
+ .ml_doc = PyDoc_STR("adds an event selector to the list.")
+ },
+ {
+ .ml_name = "read_on_cpu",
+ .ml_meth = (PyCFunction)pyrf_evlist__read_on_cpu,
+ .ml_flags = METH_VARARGS | METH_KEYWORDS,
+ .ml_doc = PyDoc_STR("reads an event.")
+ },
+ { .ml_name = NULL, }
+};
+
+static Py_ssize_t pyrf_evlist__length(PyObject *obj)
+{
+ struct pyrf_evlist *pevlist = (void *)obj;
+
+ return pevlist->evlist.nr_entries;
+}
+
+static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
+{
+ struct pyrf_evlist *pevlist = (void *)obj;
+ struct perf_evsel *pos;
+
+ if (i >= pevlist->evlist.nr_entries)
+ return NULL;
+
+ list_for_each_entry(pos, &pevlist->evlist.entries, node)
+ if (i-- == 0)
+ break;
+
+ return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
+}
+
+static PySequenceMethods pyrf_evlist__sequence_methods = {
+ .sq_length = pyrf_evlist__length,
+ .sq_item = pyrf_evlist__item,
+};
+
+static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object.");
+
+static PyTypeObject pyrf_evlist__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.evlist",
+ .tp_basicsize = sizeof(struct pyrf_evlist),
+ .tp_dealloc = (destructor)pyrf_evlist__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_as_sequence = &pyrf_evlist__sequence_methods,
+ .tp_doc = pyrf_evlist__doc,
+ .tp_methods = pyrf_evlist__methods,
+ .tp_init = (initproc)pyrf_evlist__init,
+};
+
+static int pyrf_evlist__setup_types(void)
+{
+ pyrf_evlist__type.tp_new = PyType_GenericNew;
+ return PyType_Ready(&pyrf_evlist__type);
+}
+
+static struct {
+ const char *name;
+ int value;
+} perf__constants[] = {
+ { "TYPE_HARDWARE", PERF_TYPE_HARDWARE },
+ { "TYPE_SOFTWARE", PERF_TYPE_SOFTWARE },
+ { "TYPE_TRACEPOINT", PERF_TYPE_TRACEPOINT },
+ { "TYPE_HW_CACHE", PERF_TYPE_HW_CACHE },
+ { "TYPE_RAW", PERF_TYPE_RAW },
+ { "TYPE_BREAKPOINT", PERF_TYPE_BREAKPOINT },
+
+ { "COUNT_HW_CPU_CYCLES", PERF_COUNT_HW_CPU_CYCLES },
+ { "COUNT_HW_INSTRUCTIONS", PERF_COUNT_HW_INSTRUCTIONS },
+ { "COUNT_HW_CACHE_REFERENCES", PERF_COUNT_HW_CACHE_REFERENCES },
+ { "COUNT_HW_CACHE_MISSES", PERF_COUNT_HW_CACHE_MISSES },
+ { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+ { "COUNT_HW_BRANCH_MISSES", PERF_COUNT_HW_BRANCH_MISSES },
+ { "COUNT_HW_BUS_CYCLES", PERF_COUNT_HW_BUS_CYCLES },
+ { "COUNT_HW_CACHE_L1D", PERF_COUNT_HW_CACHE_L1D },
+ { "COUNT_HW_CACHE_L1I", PERF_COUNT_HW_CACHE_L1I },
+ { "COUNT_HW_CACHE_LL", PERF_COUNT_HW_CACHE_LL },
+ { "COUNT_HW_CACHE_DTLB", PERF_COUNT_HW_CACHE_DTLB },
+ { "COUNT_HW_CACHE_ITLB", PERF_COUNT_HW_CACHE_ITLB },
+ { "COUNT_HW_CACHE_BPU", PERF_COUNT_HW_CACHE_BPU },
+ { "COUNT_HW_CACHE_OP_READ", PERF_COUNT_HW_CACHE_OP_READ },
+ { "COUNT_HW_CACHE_OP_WRITE", PERF_COUNT_HW_CACHE_OP_WRITE },
+ { "COUNT_HW_CACHE_OP_PREFETCH", PERF_COUNT_HW_CACHE_OP_PREFETCH },
+ { "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS },
+ { "COUNT_HW_CACHE_RESULT_MISS", PERF_COUNT_HW_CACHE_RESULT_MISS },
+
+ { "COUNT_SW_CPU_CLOCK", PERF_COUNT_SW_CPU_CLOCK },
+ { "COUNT_SW_TASK_CLOCK", PERF_COUNT_SW_TASK_CLOCK },
+ { "COUNT_SW_PAGE_FAULTS", PERF_COUNT_SW_PAGE_FAULTS },
+ { "COUNT_SW_CONTEXT_SWITCHES", PERF_COUNT_SW_CONTEXT_SWITCHES },
+ { "COUNT_SW_CPU_MIGRATIONS", PERF_COUNT_SW_CPU_MIGRATIONS },
+ { "COUNT_SW_PAGE_FAULTS_MIN", PERF_COUNT_SW_PAGE_FAULTS_MIN },
+ { "COUNT_SW_PAGE_FAULTS_MAJ", PERF_COUNT_SW_PAGE_FAULTS_MAJ },
+ { "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS },
+ { "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS },
+
+ { "SAMPLE_IP", PERF_SAMPLE_IP },
+ { "SAMPLE_TID", PERF_SAMPLE_TID },
+ { "SAMPLE_TIME", PERF_SAMPLE_TIME },
+ { "SAMPLE_ADDR", PERF_SAMPLE_ADDR },
+ { "SAMPLE_READ", PERF_SAMPLE_READ },
+ { "SAMPLE_CALLCHAIN", PERF_SAMPLE_CALLCHAIN },
+ { "SAMPLE_ID", PERF_SAMPLE_ID },
+ { "SAMPLE_CPU", PERF_SAMPLE_CPU },
+ { "SAMPLE_PERIOD", PERF_SAMPLE_PERIOD },
+ { "SAMPLE_STREAM_ID", PERF_SAMPLE_STREAM_ID },
+ { "SAMPLE_RAW", PERF_SAMPLE_RAW },
+
+ { "FORMAT_TOTAL_TIME_ENABLED", PERF_FORMAT_TOTAL_TIME_ENABLED },
+ { "FORMAT_TOTAL_TIME_RUNNING", PERF_FORMAT_TOTAL_TIME_RUNNING },
+ { "FORMAT_ID", PERF_FORMAT_ID },
+ { "FORMAT_GROUP", PERF_FORMAT_GROUP },
+
+ { "RECORD_MMAP", PERF_RECORD_MMAP },
+ { "RECORD_LOST", PERF_RECORD_LOST },
+ { "RECORD_COMM", PERF_RECORD_COMM },
+ { "RECORD_EXIT", PERF_RECORD_EXIT },
+ { "RECORD_THROTTLE", PERF_RECORD_THROTTLE },
+ { "RECORD_UNTHROTTLE", PERF_RECORD_UNTHROTTLE },
+ { "RECORD_FORK", PERF_RECORD_FORK },
+ { "RECORD_READ", PERF_RECORD_READ },
+ { "RECORD_SAMPLE", PERF_RECORD_SAMPLE },
+ { .name = NULL, },
+};
+
+static PyMethodDef perf__methods[] = {
+ { .ml_name = NULL, }
+};
+
+PyMODINIT_FUNC initperf(void)
+{
+ PyObject *obj;
+ int i;
+ PyObject *dict, *module = Py_InitModule("perf", perf__methods);
+
+ if (module == NULL ||
+ pyrf_event__setup_types() < 0 ||
+ pyrf_evlist__setup_types() < 0 ||
+ pyrf_evsel__setup_types() < 0 ||
+ pyrf_thread_map__setup_types() < 0 ||
+ pyrf_cpu_map__setup_types() < 0)
+ return;
+
+ Py_INCREF(&pyrf_evlist__type);
+ PyModule_AddObject(module, "evlist", (PyObject*)&pyrf_evlist__type);
+
+ Py_INCREF(&pyrf_evsel__type);
+ PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type);
+
+ Py_INCREF(&pyrf_thread_map__type);
+ PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type);
+
+ Py_INCREF(&pyrf_cpu_map__type);
+ PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type);
+
+ dict = PyModule_GetDict(module);
+ if (dict == NULL)
+ goto error;
+
+ for (i = 0; perf__constants[i].name != NULL; i++) {
+ obj = PyInt_FromLong(perf__constants[i].value);
+ if (obj == NULL)
+ goto error;
+ PyDict_SetItemString(dict, perf__constants[i].name, obj);
+ Py_DECREF(obj);
+ }
+
+error:
+ if (PyErr_Occurred())
+ PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
+}
context = PyCObject_FromVoidPtr(scripting_context, NULL);
PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
- PyTuple_SetItem(t, n++,
- PyCObject_FromVoidPtr(scripting_context, NULL));
+ PyTuple_SetItem(t, n++, context);
if (handler) {
PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
#include <sys/types.h>
#include <sys/mman.h>
+#include "evlist.h"
+#include "evsel.h"
#include "session.h"
#include "sort.h"
#include "util.h"
self->fd_pipe = true;
self->fd = STDIN_FILENO;
- if (perf_header__read(self, self->fd) < 0)
+ if (perf_session__read_header(self, self->fd) < 0)
pr_err("incompatible file format");
return 0;
goto out_close;
}
- if (perf_header__read(self, self->fd) < 0) {
+ if (perf_session__read_header(self, self->fd) < 0) {
pr_err("incompatible file format");
goto out_close;
}
static void perf_session__id_header_size(struct perf_session *session)
{
- struct sample_data *data;
+ struct perf_sample *data;
u64 sample_type = session->sample_type;
u16 size = 0;
session->id_hdr_size = size;
}
-void perf_session__set_sample_id_all(struct perf_session *session, bool value)
-{
- session->sample_id_all = value;
- perf_session__id_header_size(session);
-}
-
-void perf_session__set_sample_type(struct perf_session *session, u64 type)
-{
- session->sample_type = type;
-}
-
void perf_session__update_sample_type(struct perf_session *self)
{
- self->sample_type = perf_header__sample_type(&self->header);
- self->sample_id_all = perf_header__sample_id_all(&self->header);
+ self->sample_type = perf_evlist__sample_type(self->evlist);
+ self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
perf_session__id_header_size(self);
}
if (self == NULL)
goto out;
- if (perf_header__init(&self->header) < 0)
- goto out_free;
-
memcpy(self->filename, filename, len);
self->threads = RB_ROOT;
INIT_LIST_HEAD(&self->dead_threads);
- self->hists_tree = RB_ROOT;
self->last_match = NULL;
/*
* On 64bit we can mmap the data file in one go. No need for tiny mmap
if (mode == O_RDONLY) {
if (perf_session__open(self, force) < 0)
goto out_delete;
+ perf_session__update_sample_type(self);
} else if (mode == O_WRONLY) {
/*
* In O_RDONLY mode this will be performed when reading the
- * kernel MMAP event, in event__process_mmap().
+ * kernel MMAP event, in perf_event__process_mmap().
*/
if (perf_session__create_kernel_maps(self) < 0)
goto out_delete;
}
- perf_session__update_sample_type(self);
-
if (ops && ops->ordering_requires_timestamps &&
ops->ordered_samples && !self->sample_id_all) {
dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
out:
return self;
-out_free:
- free(self);
- return NULL;
out_delete:
perf_session__delete(self);
return NULL;
void perf_session__delete(struct perf_session *self)
{
- perf_header__exit(&self->header);
perf_session__destroy_kernel_maps(self);
perf_session__delete_dead_threads(self);
perf_session__delete_threads(self);
return 0;
}
-struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
- struct thread *thread,
- struct ip_callchain *chain,
- struct symbol **parent)
+int perf_session__resolve_callchain(struct perf_session *self,
+ struct thread *thread,
+ struct ip_callchain *chain,
+ struct symbol **parent)
{
u8 cpumode = PERF_RECORD_MISC_USER;
unsigned int i;
- struct map_symbol *syms = calloc(chain->nr, sizeof(*syms));
+ int err;
- if (!syms)
- return NULL;
+ callchain_cursor_reset(&self->callchain_cursor);
for (i = 0; i < chain->nr; i++) {
u64 ip = chain->ips[i];
*parent = al.sym;
if (!symbol_conf.use_callchain)
break;
- syms[i].map = al.map;
- syms[i].sym = al.sym;
}
+
+ err = callchain_cursor_append(&self->callchain_cursor,
+ ip, al.map, al.sym);
+ if (err)
+ return err;
}
- return syms;
+ return 0;
}
-static int process_event_synth_stub(event_t *event __used,
+static int process_event_synth_stub(union perf_event *event __used,
struct perf_session *session __used)
{
dump_printf(": unhandled!\n");
return 0;
}
-static int process_event_stub(event_t *event __used,
- struct sample_data *sample __used,
+static int process_event_stub(union perf_event *event __used,
+ struct perf_sample *sample __used,
struct perf_session *session __used)
{
dump_printf(": unhandled!\n");
return 0;
}
-static int process_finished_round_stub(event_t *event __used,
+static int process_finished_round_stub(union perf_event *event __used,
struct perf_session *session __used,
struct perf_event_ops *ops __used)
{
return 0;
}
-static int process_finished_round(event_t *event,
+static int process_finished_round(union perf_event *event,
struct perf_session *session,
struct perf_event_ops *ops);
if (handler->exit == NULL)
handler->exit = process_event_stub;
if (handler->lost == NULL)
- handler->lost = event__process_lost;
+ handler->lost = perf_event__process_lost;
if (handler->read == NULL)
handler->read = process_event_stub;
if (handler->throttle == NULL)
}
}
-static void event__all64_swap(event_t *self)
+static void perf_event__all64_swap(union perf_event *event)
{
- struct perf_event_header *hdr = &self->header;
- mem_bswap_64(hdr + 1, self->header.size - sizeof(*hdr));
+ struct perf_event_header *hdr = &event->header;
+ mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
}
-static void event__comm_swap(event_t *self)
+static void perf_event__comm_swap(union perf_event *event)
{
- self->comm.pid = bswap_32(self->comm.pid);
- self->comm.tid = bswap_32(self->comm.tid);
+ event->comm.pid = bswap_32(event->comm.pid);
+ event->comm.tid = bswap_32(event->comm.tid);
}
-static void event__mmap_swap(event_t *self)
+static void perf_event__mmap_swap(union perf_event *event)
{
- self->mmap.pid = bswap_32(self->mmap.pid);
- self->mmap.tid = bswap_32(self->mmap.tid);
- self->mmap.start = bswap_64(self->mmap.start);
- self->mmap.len = bswap_64(self->mmap.len);
- self->mmap.pgoff = bswap_64(self->mmap.pgoff);
+ event->mmap.pid = bswap_32(event->mmap.pid);
+ event->mmap.tid = bswap_32(event->mmap.tid);
+ event->mmap.start = bswap_64(event->mmap.start);
+ event->mmap.len = bswap_64(event->mmap.len);
+ event->mmap.pgoff = bswap_64(event->mmap.pgoff);
}
-static void event__task_swap(event_t *self)
+static void perf_event__task_swap(union perf_event *event)
{
- self->fork.pid = bswap_32(self->fork.pid);
- self->fork.tid = bswap_32(self->fork.tid);
- self->fork.ppid = bswap_32(self->fork.ppid);
- self->fork.ptid = bswap_32(self->fork.ptid);
- self->fork.time = bswap_64(self->fork.time);
+ event->fork.pid = bswap_32(event->fork.pid);
+ event->fork.tid = bswap_32(event->fork.tid);
+ event->fork.ppid = bswap_32(event->fork.ppid);
+ event->fork.ptid = bswap_32(event->fork.ptid);
+ event->fork.time = bswap_64(event->fork.time);
}
-static void event__read_swap(event_t *self)
+static void perf_event__read_swap(union perf_event *event)
{
- self->read.pid = bswap_32(self->read.pid);
- self->read.tid = bswap_32(self->read.tid);
- self->read.value = bswap_64(self->read.value);
- self->read.time_enabled = bswap_64(self->read.time_enabled);
- self->read.time_running = bswap_64(self->read.time_running);
- self->read.id = bswap_64(self->read.id);
+ event->read.pid = bswap_32(event->read.pid);
+ event->read.tid = bswap_32(event->read.tid);
+ event->read.value = bswap_64(event->read.value);
+ event->read.time_enabled = bswap_64(event->read.time_enabled);
+ event->read.time_running = bswap_64(event->read.time_running);
+ event->read.id = bswap_64(event->read.id);
}
-static void event__attr_swap(event_t *self)
+static void perf_event__attr_swap(union perf_event *event)
{
size_t size;
- self->attr.attr.type = bswap_32(self->attr.attr.type);
- self->attr.attr.size = bswap_32(self->attr.attr.size);
- self->attr.attr.config = bswap_64(self->attr.attr.config);
- self->attr.attr.sample_period = bswap_64(self->attr.attr.sample_period);
- self->attr.attr.sample_type = bswap_64(self->attr.attr.sample_type);
- self->attr.attr.read_format = bswap_64(self->attr.attr.read_format);
- self->attr.attr.wakeup_events = bswap_32(self->attr.attr.wakeup_events);
- self->attr.attr.bp_type = bswap_32(self->attr.attr.bp_type);
- self->attr.attr.bp_addr = bswap_64(self->attr.attr.bp_addr);
- self->attr.attr.bp_len = bswap_64(self->attr.attr.bp_len);
-
- size = self->header.size;
- size -= (void *)&self->attr.id - (void *)self;
- mem_bswap_64(self->attr.id, size);
+ event->attr.attr.type = bswap_32(event->attr.attr.type);
+ event->attr.attr.size = bswap_32(event->attr.attr.size);
+ event->attr.attr.config = bswap_64(event->attr.attr.config);
+ event->attr.attr.sample_period = bswap_64(event->attr.attr.sample_period);
+ event->attr.attr.sample_type = bswap_64(event->attr.attr.sample_type);
+ event->attr.attr.read_format = bswap_64(event->attr.attr.read_format);
+ event->attr.attr.wakeup_events = bswap_32(event->attr.attr.wakeup_events);
+ event->attr.attr.bp_type = bswap_32(event->attr.attr.bp_type);
+ event->attr.attr.bp_addr = bswap_64(event->attr.attr.bp_addr);
+ event->attr.attr.bp_len = bswap_64(event->attr.attr.bp_len);
+
+ size = event->header.size;
+ size -= (void *)&event->attr.id - (void *)event;
+ mem_bswap_64(event->attr.id, size);
}
-static void event__event_type_swap(event_t *self)
+static void perf_event__event_type_swap(union perf_event *event)
{
- self->event_type.event_type.event_id =
- bswap_64(self->event_type.event_type.event_id);
+ event->event_type.event_type.event_id =
+ bswap_64(event->event_type.event_type.event_id);
}
-static void event__tracing_data_swap(event_t *self)
+static void perf_event__tracing_data_swap(union perf_event *event)
{
- self->tracing_data.size = bswap_32(self->tracing_data.size);
+ event->tracing_data.size = bswap_32(event->tracing_data.size);
}
-typedef void (*event__swap_op)(event_t *self);
-
-static event__swap_op event__swap_ops[] = {
- [PERF_RECORD_MMAP] = event__mmap_swap,
- [PERF_RECORD_COMM] = event__comm_swap,
- [PERF_RECORD_FORK] = event__task_swap,
- [PERF_RECORD_EXIT] = event__task_swap,
- [PERF_RECORD_LOST] = event__all64_swap,
- [PERF_RECORD_READ] = event__read_swap,
- [PERF_RECORD_SAMPLE] = event__all64_swap,
- [PERF_RECORD_HEADER_ATTR] = event__attr_swap,
- [PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap,
- [PERF_RECORD_HEADER_TRACING_DATA] = event__tracing_data_swap,
- [PERF_RECORD_HEADER_BUILD_ID] = NULL,
- [PERF_RECORD_HEADER_MAX] = NULL,
+typedef void (*perf_event__swap_op)(union perf_event *event);
+
+static perf_event__swap_op perf_event__swap_ops[] = {
+ [PERF_RECORD_MMAP] = perf_event__mmap_swap,
+ [PERF_RECORD_COMM] = perf_event__comm_swap,
+ [PERF_RECORD_FORK] = perf_event__task_swap,
+ [PERF_RECORD_EXIT] = perf_event__task_swap,
+ [PERF_RECORD_LOST] = perf_event__all64_swap,
+ [PERF_RECORD_READ] = perf_event__read_swap,
+ [PERF_RECORD_SAMPLE] = perf_event__all64_swap,
+ [PERF_RECORD_HEADER_ATTR] = perf_event__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_HEADER_MAX] = NULL,
};
struct sample_queue {
u64 timestamp;
u64 file_offset;
- event_t *event;
+ union perf_event *event;
struct list_head list;
};
}
static int perf_session_deliver_event(struct perf_session *session,
- event_t *event,
- struct sample_data *sample,
+ union perf_event *event,
+ struct perf_sample *sample,
struct perf_event_ops *ops,
u64 file_offset);
struct ordered_samples *os = &s->ordered_samples;
struct list_head *head = &os->samples;
struct sample_queue *tmp, *iter;
- struct sample_data sample;
+ struct perf_sample sample;
u64 limit = os->next_flush;
u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
if (iter->timestamp > limit)
break;
- event__parse_sample(iter->event, s, &sample);
+ perf_session__parse_sample(s, iter->event, &sample);
perf_session_deliver_event(s, iter->event, &sample, ops,
iter->file_offset);
* Flush every events below timestamp 7
* etc...
*/
-static int process_finished_round(event_t *event __used,
+static int process_finished_round(union perf_event *event __used,
struct perf_session *session,
struct perf_event_ops *ops)
{
#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue))
-static int perf_session_queue_event(struct perf_session *s, event_t *event,
- struct sample_data *data, u64 file_offset)
+static int perf_session_queue_event(struct perf_session *s, union perf_event *event,
+ struct perf_sample *sample, u64 file_offset)
{
struct ordered_samples *os = &s->ordered_samples;
struct list_head *sc = &os->sample_cache;
- u64 timestamp = data->time;
+ u64 timestamp = sample->time;
struct sample_queue *new;
if (!timestamp || timestamp == ~0ULL)
return 0;
}
-static void callchain__printf(struct sample_data *sample)
+static void callchain__printf(struct perf_sample *sample)
{
unsigned int i;
}
static void perf_session__print_tstamp(struct perf_session *session,
- event_t *event,
- struct sample_data *sample)
+ union perf_event *event,
+ struct perf_sample *sample)
{
if (event->header.type != PERF_RECORD_SAMPLE &&
!session->sample_id_all) {
printf("%" PRIu64 " ", sample->time);
}
-static void dump_event(struct perf_session *session, event_t *event,
- u64 file_offset, struct sample_data *sample)
+static void dump_event(struct perf_session *session, union perf_event *event,
+ u64 file_offset, struct perf_sample *sample)
{
if (!dump_trace)
return;
perf_session__print_tstamp(session, event, sample);
printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
- event->header.size, event__get_event_name(event->header.type));
+ event->header.size, perf_event__name(event->header.type));
}
-static void dump_sample(struct perf_session *session, event_t *event,
- struct sample_data *sample)
+static void dump_sample(struct perf_session *session, union perf_event *event,
+ struct perf_sample *sample)
{
if (!dump_trace)
return;
}
static int perf_session_deliver_event(struct perf_session *session,
- event_t *event,
- struct sample_data *sample,
+ union perf_event *event,
+ struct perf_sample *sample,
struct perf_event_ops *ops,
u64 file_offset)
{
}
static int perf_session__preprocess_sample(struct perf_session *session,
- event_t *event, struct sample_data *sample)
+ union perf_event *event, struct perf_sample *sample)
{
if (event->header.type != PERF_RECORD_SAMPLE ||
!(session->sample_type & PERF_SAMPLE_CALLCHAIN))
return 0;
}
-static int perf_session__process_user_event(struct perf_session *session, event_t *event,
+static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
struct perf_event_ops *ops, u64 file_offset)
{
dump_event(session, event, file_offset, NULL);
}
static int perf_session__process_event(struct perf_session *session,
- event_t *event,
+ union perf_event *event,
struct perf_event_ops *ops,
u64 file_offset)
{
- struct sample_data sample;
+ struct perf_sample sample;
int ret;
- if (session->header.needs_swap && event__swap_ops[event->header.type])
- event__swap_ops[event->header.type](event);
+ if (session->header.needs_swap &&
+ perf_event__swap_ops[event->header.type])
+ perf_event__swap_ops[event->header.type](event);
if (event->header.type >= PERF_RECORD_HEADER_MAX)
return -EINVAL;
/*
* For all kernel events we get the sample data
*/
- event__parse_sample(event, session, &sample);
+ perf_session__parse_sample(session, event, &sample);
/* Preprocess sample records - precheck callchains */
if (perf_session__preprocess_sample(session, event, &sample))
static void perf_session__warn_about_errors(const struct perf_session *session,
const struct perf_event_ops *ops)
{
- if (ops->lost == event__process_lost &&
+ if (ops->lost == perf_event__process_lost &&
session->hists.stats.total_lost != 0) {
ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64
"!\n\nCheck IO/CPU overload!\n\n",
static int __perf_session__process_pipe_events(struct perf_session *self,
struct perf_event_ops *ops)
{
- event_t event;
+ union perf_event event;
uint32_t size;
int skip = 0;
u64 head;
struct ui_progress *progress;
size_t page_size, mmap_size;
char *buf, *mmaps[8];
- event_t *event;
+ union perf_event *event;
uint32_t size;
perf_event_ops__fill_defaults(ops);
file_pos = file_offset + head;
more:
- event = (event_t *)(buf + head);
+ event = (union perf_event *)(buf + head);
if (session->header.needs_swap)
perf_event_header__bswap(&event->header);
size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits);
return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
}
+
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
+{
+ struct perf_evsel *pos;
+ size_t ret = fprintf(fp, "Aggregated stats:\n");
+
+ ret += hists__fprintf_nr_events(&session->hists, fp);
+
+ list_for_each_entry(pos, &session->evlist->entries, node) {
+ ret += fprintf(fp, "%s stats:\n", event_name(pos));
+ ret += hists__fprintf_nr_events(&pos->hists, fp);
+ }
+
+ return ret;
+}
struct thread *last_match;
struct machine host_machine;
struct rb_root machines;
- struct rb_root hists_tree;
+ struct perf_evlist *evlist;
/*
- * FIXME: should point to the first entry in hists_tree and
- * be a hists instance. Right now its only 'report'
- * that is using ->hists_tree while all the rest use
- * ->hists.
+ * FIXME: Need to split this up further, we need global
+ * stats + per event stats. 'perf diff' also needs
+ * to properly support multiple events in a single
+ * perf.data file.
*/
struct hists hists;
u64 sample_type;
int cwdlen;
char *cwd;
struct ordered_samples ordered_samples;
- char filename[0];
+ struct callchain_cursor callchain_cursor;
+ char filename[0];
};
struct perf_event_ops;
-typedef int (*event_op)(event_t *self, struct sample_data *sample,
+typedef int (*event_op)(union perf_event *self, struct perf_sample *sample,
struct perf_session *session);
-typedef int (*event_synth_op)(event_t *self, struct perf_session *session);
-typedef int (*event_op2)(event_t *self, struct perf_session *session,
+typedef int (*event_synth_op)(union perf_event *self,
+ struct perf_session *session);
+typedef int (*event_op2)(union perf_event *self, struct perf_session *session,
struct perf_event_ops *ops);
struct perf_event_ops {
int perf_session__process_events(struct perf_session *self,
struct perf_event_ops *event_ops);
-struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
- struct thread *thread,
- struct ip_callchain *chain,
- struct symbol **parent);
+int perf_session__resolve_callchain(struct perf_session *self,
+ struct thread *thread,
+ struct ip_callchain *chain,
+ struct symbol **parent);
bool perf_session__has_traces(struct perf_session *self, const char *msg);
int perf_session__create_kernel_maps(struct perf_session *self);
void perf_session__update_sample_type(struct perf_session *self);
-void perf_session__set_sample_id_all(struct perf_session *session, bool value);
-void perf_session__set_sample_type(struct perf_session *session, u64 type);
void perf_session__remove_thread(struct perf_session *self, struct thread *th);
static inline
size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
FILE *fp, bool with_hits);
-static inline
-size_t perf_session__fprintf_nr_events(struct perf_session *self, FILE *fp)
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
+
+static inline int perf_session__parse_sample(struct perf_session *session,
+ const union perf_event *event,
+ struct perf_sample *sample)
{
- return hists__fprintf_nr_events(&self->hists, fp);
+ return perf_event__parse_sample(event, session->sample_type,
+ session->sample_id_all, sample);
}
+
#endif /* __PERF_SESSION_H */
--- /dev/null
+#!/usr/bin/python2
+
+from distutils.core import setup, Extension
+
+perf = Extension('perf',
+ sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
+ 'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
+ 'util/util.c', 'util/xyarray.c', 'util/cgroup.c'],
+ include_dirs = ['util/include'],
+ extra_compile_args = ['-fno-strict-aliasing', '-Wno-write-strings'])
+
+setup(name='perf',
+ version='0.1',
+ description='Interface with the Linux profiling infrastructure',
+ author='Arnaldo Carvalho de Melo',
+ author_email='acme@redhat.com',
+ license='GPLv2',
+ url='http://perf.wiki.kernel.org',
+ ext_modules=[perf])
--- /dev/null
+#include "util.h"
+#include "string.h"
+#include "strfilter.h"
+
+/* Operators */
+static const char *OP_and = "&"; /* Logical AND */
+static const char *OP_or = "|"; /* Logical OR */
+static const char *OP_not = "!"; /* Logical NOT */
+
+#define is_operator(c) ((c) == '|' || (c) == '&' || (c) == '!')
+#define is_separator(c) (is_operator(c) || (c) == '(' || (c) == ')')
+
+static void strfilter_node__delete(struct strfilter_node *self)
+{
+ if (self) {
+ if (self->p && !is_operator(*self->p))
+ free((char *)self->p);
+ strfilter_node__delete(self->l);
+ strfilter_node__delete(self->r);
+ free(self);
+ }
+}
+
+void strfilter__delete(struct strfilter *self)
+{
+ if (self) {
+ strfilter_node__delete(self->root);
+ free(self);
+ }
+}
+
+static const char *get_token(const char *s, const char **e)
+{
+ const char *p;
+
+ while (isspace(*s)) /* Skip spaces */
+ s++;
+
+ if (*s == '\0') {
+ p = s;
+ goto end;
+ }
+
+ p = s + 1;
+ if (!is_separator(*s)) {
+ /* End search */
+retry:
+ while (*p && !is_separator(*p) && !isspace(*p))
+ p++;
+ /* Escape and special case: '!' is also used in glob pattern */
+ if (*(p - 1) == '\\' || (*p == '!' && *(p - 1) == '[')) {
+ p++;
+ goto retry;
+ }
+ }
+end:
+ *e = p;
+ return s;
+}
+
+static struct strfilter_node *strfilter_node__alloc(const char *op,
+ struct strfilter_node *l,
+ struct strfilter_node *r)
+{
+ struct strfilter_node *ret = zalloc(sizeof(struct strfilter_node));
+
+ if (ret) {
+ ret->p = op;
+ ret->l = l;
+ ret->r = r;
+ }
+
+ return ret;
+}
+
+static struct strfilter_node *strfilter_node__new(const char *s,
+ const char **ep)
+{
+ struct strfilter_node root, *cur, *last_op;
+ const char *e;
+
+ if (!s)
+ return NULL;
+
+ memset(&root, 0, sizeof(root));
+ last_op = cur = &root;
+
+ s = get_token(s, &e);
+ while (*s != '\0' && *s != ')') {
+ switch (*s) {
+ case '&': /* Exchg last OP->r with AND */
+ if (!cur->r || !last_op->r)
+ goto error;
+ cur = strfilter_node__alloc(OP_and, last_op->r, NULL);
+ if (!cur)
+ goto nomem;
+ last_op->r = cur;
+ last_op = cur;
+ break;
+ case '|': /* Exchg the root with OR */
+ if (!cur->r || !root.r)
+ goto error;
+ cur = strfilter_node__alloc(OP_or, root.r, NULL);
+ if (!cur)
+ goto nomem;
+ root.r = cur;
+ last_op = cur;
+ break;
+ case '!': /* Add NOT as a leaf node */
+ if (cur->r)
+ goto error;
+ cur->r = strfilter_node__alloc(OP_not, NULL, NULL);
+ if (!cur->r)
+ goto nomem;
+ cur = cur->r;
+ break;
+ case '(': /* Recursively parses inside the parenthesis */
+ if (cur->r)
+ goto error;
+ cur->r = strfilter_node__new(s + 1, &s);
+ if (!s)
+ goto nomem;
+ if (!cur->r || *s != ')')
+ goto error;
+ e = s + 1;
+ break;
+ default:
+ if (cur->r)
+ goto error;
+ cur->r = strfilter_node__alloc(NULL, NULL, NULL);
+ if (!cur->r)
+ goto nomem;
+ cur->r->p = strndup(s, e - s);
+ if (!cur->r->p)
+ goto nomem;
+ }
+ s = get_token(e, &e);
+ }
+ if (!cur->r)
+ goto error;
+ *ep = s;
+ return root.r;
+nomem:
+ s = NULL;
+error:
+ *ep = s;
+ strfilter_node__delete(root.r);
+ return NULL;
+}
+
+/*
+ * Parse filter rule and return new strfilter.
+ * Return NULL if fail, and *ep == NULL if memory allocation failed.
+ */
+struct strfilter *strfilter__new(const char *rules, const char **err)
+{
+ struct strfilter *ret = zalloc(sizeof(struct strfilter));
+ const char *ep = NULL;
+
+ if (ret)
+ ret->root = strfilter_node__new(rules, &ep);
+
+ if (!ret || !ret->root || *ep != '\0') {
+ if (err)
+ *err = ep;
+ strfilter__delete(ret);
+ ret = NULL;
+ }
+
+ return ret;
+}
+
+static bool strfilter_node__compare(struct strfilter_node *self,
+ const char *str)
+{
+ if (!self || !self->p)
+ return false;
+
+ switch (*self->p) {
+ case '|': /* OR */
+ return strfilter_node__compare(self->l, str) ||
+ strfilter_node__compare(self->r, str);
+ case '&': /* AND */
+ return strfilter_node__compare(self->l, str) &&
+ strfilter_node__compare(self->r, str);
+ case '!': /* NOT */
+ return !strfilter_node__compare(self->r, str);
+ default:
+ return strglobmatch(str, self->p);
+ }
+}
+
+/* Return true if STR matches the filter rules */
+bool strfilter__compare(struct strfilter *self, const char *str)
+{
+ if (!self)
+ return false;
+ return strfilter_node__compare(self->root, str);
+}
--- /dev/null
+#ifndef __PERF_STRFILTER_H
+#define __PERF_STRFILTER_H
+/* General purpose glob matching filter */
+
+#include <linux/list.h>
+#include <stdbool.h>
+
+/* A node of string filter */
+struct strfilter_node {
+ struct strfilter_node *l; /* Tree left branche (for &,|) */
+ struct strfilter_node *r; /* Tree right branche (for !,&,|) */
+ const char *p; /* Operator or rule */
+};
+
+/* String filter */
+struct strfilter {
+ struct strfilter_node *root;
+};
+
+/**
+ * strfilter__new - Create a new string filter
+ * @rules: Filter rule, which is a combination of glob expressions.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and return new strfilter. Return NULL if an error detected.
+ * In that case, *@err will indicate where it is detected, and *@err is NULL
+ * if a memory allocation is failed.
+ */
+struct strfilter *strfilter__new(const char *rules, const char **err);
+
+/**
+ * strfilter__compare - compare given string and a string filter
+ * @self: String filter
+ * @str: target string
+ *
+ * Compare @str and @self. Return true if the str match the rule
+ */
+bool strfilter__compare(struct strfilter *self, const char *str);
+
+/**
+ * strfilter__delete - delete a string filter
+ * @self: String filter to delete
+ *
+ * Delete @self.
+ */
+void strfilter__delete(struct strfilter *self);
+
+#endif
return;
svg_legenda_box(0, "Running", "sample");
- svg_legenda_box(100, "Idle","rect.c1");
- svg_legenda_box(200, "Deeper Idle", "rect.c3");
- svg_legenda_box(350, "Deepest Idle", "rect.c6");
+ svg_legenda_box(100, "Idle","c1");
+ svg_legenda_box(200, "Deeper Idle", "c3");
+ svg_legenda_box(350, "Deepest Idle", "c6");
svg_legenda_box(550, "Sleeping", "process2");
svg_legenda_box(650, "Waiting for cpu", "waiting");
svg_legenda_box(800, "Blocked on IO", "blocked");
dso__set_short_name(self, self->name);
for (i = 0; i < MAP__NR_TYPES; ++i)
self->symbols[i] = self->symbol_names[i] = RB_ROOT;
- self->slen_calculated = 0;
self->origin = DSO__ORIG_NOT_FOUND;
self->loaded = 0;
self->sorted_by_name = 0;
symbol_conf.symfs, self->long_name);
break;
case DSO__ORIG_GUEST_KMODULE:
- if (map->groups && map->groups->machine)
- root_dir = map->groups->machine->root_dir;
+ if (map->groups && machine)
+ root_dir = machine->root_dir;
else
root_dir = "";
snprintf(name, size, "%s%s%s", symbol_conf.symfs,
int err = -1, fd;
char symfs_vmlinux[PATH_MAX];
- snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s/%s",
+ snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
symbol_conf.symfs, vmlinux);
fd = open(symfs_vmlinux, O_RDONLY);
if (fd < 0)
struct rb_root symbol_names[MAP__NR_TYPES];
enum dso_kernel_type kernel;
u8 adjust_symbols:1;
- u8 slen_calculated:1;
u8 has_build_id:1;
u8 hit:1;
u8 annotate_warned:1;
#include "util.h"
#include "debug.h"
-/* Skip "." and ".." directories */
-static int filter(const struct dirent *dir)
-{
- if (dir->d_name[0] == '.')
- return 0;
- else
- return 1;
-}
-
-struct thread_map *thread_map__new_by_pid(pid_t pid)
-{
- struct thread_map *threads;
- char name[256];
- int items;
- struct dirent **namelist = NULL;
- int i;
-
- sprintf(name, "/proc/%d/task", pid);
- items = scandir(name, &namelist, filter, NULL);
- if (items <= 0)
- return NULL;
-
- threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
- if (threads != NULL) {
- for (i = 0; i < items; i++)
- threads->map[i] = atoi(namelist[i]->d_name);
- threads->nr = items;
- }
-
- for (i=0; i<items; i++)
- free(namelist[i]);
- free(namelist);
-
- return threads;
-}
-
-struct thread_map *thread_map__new_by_tid(pid_t tid)
-{
- struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
-
- if (threads != NULL) {
- threads->map[0] = tid;
- threads->nr = 1;
- }
-
- return threads;
-}
-
-struct thread_map *thread_map__new(pid_t pid, pid_t tid)
-{
- if (pid != -1)
- return thread_map__new_by_pid(pid);
- return thread_map__new_by_tid(tid);
-}
-
static struct thread *thread__new(pid_t pid)
{
struct thread *self = zalloc(sizeof(*self));
int comm_len;
};
-struct thread_map {
- int nr;
- int map[];
-};
-
struct perf_session;
void thread__delete(struct thread *self);
-struct thread_map *thread_map__new_by_pid(pid_t pid);
-struct thread_map *thread_map__new_by_tid(pid_t tid);
-struct thread_map *thread_map__new(pid_t pid, pid_t tid);
-
-static inline void thread_map__delete(struct thread_map *threads)
-{
- free(threads);
-}
-
int thread__set_comm(struct thread *self, const char *comm);
int thread__comm_len(struct thread *self);
struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
--- /dev/null
+#include <dirent.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "thread_map.h"
+
+/* Skip "." and ".." directories */
+static int filter(const struct dirent *dir)
+{
+ if (dir->d_name[0] == '.')
+ return 0;
+ else
+ return 1;
+}
+
+struct thread_map *thread_map__new_by_pid(pid_t pid)
+{
+ struct thread_map *threads;
+ char name[256];
+ int items;
+ struct dirent **namelist = NULL;
+ int i;
+
+ sprintf(name, "/proc/%d/task", pid);
+ items = scandir(name, &namelist, filter, NULL);
+ if (items <= 0)
+ return NULL;
+
+ threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+ if (threads != NULL) {
+ for (i = 0; i < items; i++)
+ threads->map[i] = atoi(namelist[i]->d_name);
+ threads->nr = items;
+ }
+
+ for (i=0; i<items; i++)
+ free(namelist[i]);
+ free(namelist);
+
+ return threads;
+}
+
+struct thread_map *thread_map__new_by_tid(pid_t tid)
+{
+ struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+
+ if (threads != NULL) {
+ threads->map[0] = tid;
+ threads->nr = 1;
+ }
+
+ return threads;
+}
+
+struct thread_map *thread_map__new(pid_t pid, pid_t tid)
+{
+ if (pid != -1)
+ return thread_map__new_by_pid(pid);
+ return thread_map__new_by_tid(tid);
+}
+
+void thread_map__delete(struct thread_map *threads)
+{
+ free(threads);
+}
--- /dev/null
+#ifndef __PERF_THREAD_MAP_H
+#define __PERF_THREAD_MAP_H
+
+#include <sys/types.h>
+
+struct thread_map {
+ int nr;
+ int map[];
+};
+
+struct thread_map *thread_map__new_by_pid(pid_t pid);
+struct thread_map *thread_map__new_by_tid(pid_t tid);
+struct thread_map *thread_map__new(pid_t pid, pid_t tid);
+void thread_map__delete(struct thread_map *threads);
+#endif /* __PERF_THREAD_MAP_H */
--- /dev/null
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Refactored from builtin-top.c, see that files for further copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "cpumap.h"
+#include "event.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "symbol.h"
+#include "top.h"
+#include <inttypes.h>
+
+/*
+ * Ordering weight: count-1 * count-2 * ... / count-n
+ */
+static double sym_weight(const struct sym_entry *sym, struct perf_top *top)
+{
+ double weight = sym->snap_count;
+ int counter;
+
+ if (!top->display_weighted)
+ return weight;
+
+ for (counter = 1; counter < top->evlist->nr_entries - 1; counter++)
+ weight *= sym->count[counter];
+
+ weight /= (sym->count[counter] + 1);
+
+ return weight;
+}
+
+static void perf_top__remove_active_sym(struct perf_top *top, struct sym_entry *syme)
+{
+ pthread_mutex_lock(&top->active_symbols_lock);
+ list_del_init(&syme->node);
+ pthread_mutex_unlock(&top->active_symbols_lock);
+}
+
+static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
+{
+ struct rb_node **p = &tree->rb_node;
+ struct rb_node *parent = NULL;
+ struct sym_entry *iter;
+
+ while (*p != NULL) {
+ parent = *p;
+ iter = rb_entry(parent, struct sym_entry, rb_node);
+
+ if (se->weight > iter->weight)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+
+ rb_link_node(&se->rb_node, parent, p);
+ rb_insert_color(&se->rb_node, tree);
+}
+
+#define SNPRINTF(buf, size, fmt, args...) \
+({ \
+ size_t r = snprintf(buf, size, fmt, ## args); \
+ r > size ? size : r; \
+})
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
+{
+ struct perf_evsel *counter;
+ float samples_per_sec = top->samples / top->delay_secs;
+ float ksamples_per_sec = top->kernel_samples / top->delay_secs;
+ float esamples_percent = (100.0 * top->exact_samples) / top->samples;
+ size_t ret = 0;
+
+ if (!perf_guest) {
+ ret = SNPRINTF(bf, size,
+ " PerfTop:%8.0f irqs/sec kernel:%4.1f%%"
+ " exact: %4.1f%% [", samples_per_sec,
+ 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+ samples_per_sec)),
+ esamples_percent);
+ } else {
+ float us_samples_per_sec = top->us_samples / top->delay_secs;
+ float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs;
+ float guest_us_samples_per_sec = top->guest_us_samples / top->delay_secs;
+
+ ret = SNPRINTF(bf, size,
+ " PerfTop:%8.0f irqs/sec kernel:%4.1f%% us:%4.1f%%"
+ " guest kernel:%4.1f%% guest us:%4.1f%%"
+ " exact: %4.1f%% [", samples_per_sec,
+ 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+ samples_per_sec)),
+ 100.0 - (100.0 * ((samples_per_sec - us_samples_per_sec) /
+ samples_per_sec)),
+ 100.0 - (100.0 * ((samples_per_sec -
+ guest_kernel_samples_per_sec) /
+ samples_per_sec)),
+ 100.0 - (100.0 * ((samples_per_sec -
+ guest_us_samples_per_sec) /
+ samples_per_sec)),
+ esamples_percent);
+ }
+
+ if (top->evlist->nr_entries == 1 || !top->display_weighted) {
+ struct perf_evsel *first;
+ first = list_entry(top->evlist->entries.next, struct perf_evsel, node);
+ ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
+ (uint64_t)first->attr.sample_period,
+ top->freq ? "Hz" : "");
+ }
+
+ if (!top->display_weighted) {
+ ret += SNPRINTF(bf + ret, size - ret, "%s",
+ event_name(top->sym_evsel));
+ } else {
+ /*
+ * Don't let events eat all the space. Leaving 30 bytes
+ * for the rest should be enough.
+ */
+ size_t last_pos = size - 30;
+
+ list_for_each_entry(counter, &top->evlist->entries, node) {
+ ret += SNPRINTF(bf + ret, size - ret, "%s%s",
+ counter->idx ? "/" : "",
+ event_name(counter));
+ if (ret > last_pos) {
+ sprintf(bf + last_pos - 3, "..");
+ ret = last_pos - 1;
+ break;
+ }
+ }
+ }
+
+ ret += SNPRINTF(bf + ret, size - ret, "], ");
+
+ if (top->target_pid != -1)
+ ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %d",
+ top->target_pid);
+ else if (top->target_tid != -1)
+ ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %d",
+ top->target_tid);
+ else
+ ret += SNPRINTF(bf + ret, size - ret, " (all");
+
+ if (top->cpu_list)
+ ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
+ top->evlist->cpus->nr > 1 ? "s" : "", top->cpu_list);
+ else {
+ if (top->target_tid != -1)
+ ret += SNPRINTF(bf + ret, size - ret, ")");
+ else
+ ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
+ top->evlist->cpus->nr,
+ top->evlist->cpus->nr > 1 ? "s" : "");
+ }
+
+ return ret;
+}
+
+void perf_top__reset_sample_counters(struct perf_top *top)
+{
+ top->samples = top->us_samples = top->kernel_samples =
+ top->exact_samples = top->guest_kernel_samples =
+ top->guest_us_samples = 0;
+}
+
+float perf_top__decay_samples(struct perf_top *top, struct rb_root *root)
+{
+ struct sym_entry *syme, *n;
+ float sum_ksamples = 0.0;
+ int snap = !top->display_weighted ? top->sym_counter : 0, j;
+
+ /* Sort the active symbols */
+ pthread_mutex_lock(&top->active_symbols_lock);
+ syme = list_entry(top->active_symbols.next, struct sym_entry, node);
+ pthread_mutex_unlock(&top->active_symbols_lock);
+
+ top->rb_entries = 0;
+ list_for_each_entry_safe_from(syme, n, &top->active_symbols, node) {
+ syme->snap_count = syme->count[snap];
+ if (syme->snap_count != 0) {
+
+ if ((top->hide_user_symbols &&
+ syme->origin == PERF_RECORD_MISC_USER) ||
+ (top->hide_kernel_symbols &&
+ syme->origin == PERF_RECORD_MISC_KERNEL)) {
+ perf_top__remove_active_sym(top, syme);
+ continue;
+ }
+ syme->weight = sym_weight(syme, top);
+
+ if ((int)syme->snap_count >= top->count_filter) {
+ rb_insert_active_sym(root, syme);
+ ++top->rb_entries;
+ }
+ sum_ksamples += syme->snap_count;
+
+ for (j = 0; j < top->evlist->nr_entries; j++)
+ syme->count[j] = top->zero ? 0 : syme->count[j] * 7 / 8;
+ } else
+ perf_top__remove_active_sym(top, syme);
+ }
+
+ return sum_ksamples;
+}
+
+/*
+ * Find the longest symbol name that will be displayed
+ */
+void perf_top__find_widths(struct perf_top *top, struct rb_root *root,
+ int *dso_width, int *dso_short_width, int *sym_width)
+{
+ struct rb_node *nd;
+ int printed = 0;
+
+ *sym_width = *dso_width = *dso_short_width = 0;
+
+ for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+ struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node);
+ struct symbol *sym = sym_entry__symbol(syme);
+
+ if (++printed > top->print_entries ||
+ (int)syme->snap_count < top->count_filter)
+ continue;
+
+ if (syme->map->dso->long_name_len > *dso_width)
+ *dso_width = syme->map->dso->long_name_len;
+
+ if (syme->map->dso->short_name_len > *dso_short_width)
+ *dso_short_width = syme->map->dso->short_name_len;
+
+ if (sym->namelen > *sym_width)
+ *sym_width = sym->namelen;
+ }
+}
--- /dev/null
+#ifndef __PERF_TOP_H
+#define __PERF_TOP_H 1
+
+#include "types.h"
+#include "../perf.h"
+#include <stddef.h>
+#include <pthread.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+struct perf_evlist;
+struct perf_evsel;
+
+struct sym_entry {
+ struct rb_node rb_node;
+ struct list_head node;
+ unsigned long snap_count;
+ double weight;
+ int skip;
+ u8 origin;
+ struct map *map;
+ unsigned long count[0];
+};
+
+static inline struct symbol *sym_entry__symbol(struct sym_entry *self)
+{
+ return ((void *)self) + symbol_conf.priv_size;
+}
+
+struct perf_top {
+ struct perf_evlist *evlist;
+ /*
+ * Symbols will be added here in perf_event__process_sample and will
+ * get out after decayed.
+ */
+ struct list_head active_symbols;
+ pthread_mutex_t active_symbols_lock;
+ pthread_cond_t active_symbols_cond;
+ u64 samples;
+ u64 kernel_samples, us_samples;
+ u64 exact_samples;
+ u64 guest_us_samples, guest_kernel_samples;
+ int print_entries, count_filter, delay_secs;
+ int display_weighted, freq, rb_entries, sym_counter;
+ pid_t target_pid, target_tid;
+ bool hide_kernel_symbols, hide_user_symbols, zero;
+ const char *cpu_list;
+ struct sym_entry *sym_filter_entry;
+ struct perf_evsel *sym_evsel;
+};
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
+void perf_top__reset_sample_counters(struct perf_top *top);
+float perf_top__decay_samples(struct perf_top *top, struct rb_root *root);
+void perf_top__find_widths(struct perf_top *top, struct rb_root *root,
+ int *dso_width, int *dso_short_width, int *sym_width);
+
+#ifdef NO_NEWT_SUPPORT
+static inline int perf_top__tui_browser(struct perf_top *top __used)
+{
+ return 0;
+}
+#else
+int perf_top__tui_browser(struct perf_top *top);
+#endif
+#endif /* __PERF_TOP_H */
char *next = NULL;
char *addr_str;
char ch;
- int ret;
+ int ret __used;
int i;
line = strtok_r(file, "\n", &next);
#include "libslang.h"
+#include "ui.h"
#include <linux/compiler.h>
#include <linux/list.h>
#include <linux/rbtree.h>
}
}
+void __ui_browser__show_title(struct ui_browser *browser, const char *title)
+{
+ SLsmg_gotorc(0, 0);
+ ui_browser__set_color(browser, NEWT_COLORSET_ROOT);
+ slsmg_write_nstring(title, browser->width);
+}
+
+void ui_browser__show_title(struct ui_browser *browser, const char *title)
+{
+ pthread_mutex_lock(&ui__lock);
+ __ui_browser__show_title(browser, title);
+ pthread_mutex_unlock(&ui__lock);
+}
+
int ui_browser__show(struct ui_browser *self, const char *title,
const char *helpline, ...)
{
if (self->sb == NULL)
return -1;
- SLsmg_gotorc(0, 0);
- ui_browser__set_color(self, NEWT_COLORSET_ROOT);
- slsmg_write_nstring(title, self->width);
+ pthread_mutex_lock(&ui__lock);
+ __ui_browser__show_title(self, title);
ui_browser__add_exit_keys(self, keys);
newtFormAddComponent(self->form, self->sb);
va_start(ap, helpline);
ui_helpline__vpush(helpline, ap);
va_end(ap);
+ pthread_mutex_unlock(&ui__lock);
return 0;
}
void ui_browser__hide(struct ui_browser *self)
{
+ pthread_mutex_lock(&ui__lock);
newtFormDestroy(self->form);
self->form = NULL;
ui_helpline__pop();
+ pthread_mutex_unlock(&ui__lock);
}
int ui_browser__refresh(struct ui_browser *self)
{
int row;
+ pthread_mutex_lock(&ui__lock);
newtScrollbarSet(self->sb, self->index, self->nr_entries - 1);
row = self->refresh(self);
ui_browser__set_color(self, HE_COLORSET_NORMAL);
SLsmg_fill_region(self->y + row, self->x,
self->height - row, self->width, ' ');
+ pthread_mutex_unlock(&ui__lock);
return 0;
}
u32 nr_entries;
};
-
void ui_browser__set_color(struct ui_browser *self, int color);
void ui_browser__set_percent_color(struct ui_browser *self,
double percent, bool current);
void ui_browser__gotorc(struct ui_browser *self, int y, int x);
void ui_browser__add_exit_key(struct ui_browser *self, int key);
void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]);
+void __ui_browser__show_title(struct ui_browser *browser, const char *title);
+void ui_browser__show_title(struct ui_browser *browser, const char *title);
int ui_browser__show(struct ui_browser *self, const char *title,
const char *helpline, ...);
void ui_browser__hide(struct ui_browser *self);
#include "../browser.h"
#include "../helpline.h"
#include "../libslang.h"
+#include "../../annotate.h"
#include "../../hist.h"
#include "../../sort.h"
#include "../../symbol.h"
+#include "../../annotate.h"
+#include <pthread.h>
static void ui__error_window(const char *fmt, ...)
{
struct objdump_line_rb_node *olrb = objdump_line__rb(ol);
ui_browser__set_percent_color(self, olrb->percent, current_entry);
slsmg_printf(" %7.2f ", olrb->percent);
- if (!current_entry)
- ui_browser__set_color(self, HE_COLORSET_CODE);
} else {
ui_browser__set_percent_color(self, 0, current_entry);
slsmg_write_nstring(" ", 9);
slsmg_write_nstring(" ", width - 18);
else
slsmg_write_nstring(ol->line, width - 18);
+
+ if (!current_entry)
+ ui_browser__set_color(self, HE_COLORSET_CODE);
}
static double objdump_line__calc_percent(struct objdump_line *self,
- struct list_head *head,
- struct symbol *sym)
+ struct symbol *sym, int evidx)
{
double percent = 0.0;
if (self->offset != -1) {
int len = sym->end - sym->start;
unsigned int hits = 0;
- struct sym_priv *priv = symbol__priv(sym);
- struct sym_ext *sym_ext = priv->ext;
- struct sym_hist *h = priv->hist;
+ struct annotation *notes = symbol__annotation(sym);
+ struct source_line *src_line = notes->src->lines;
+ struct sym_hist *h = annotation__histogram(notes, evidx);
s64 offset = self->offset;
- struct objdump_line *next = objdump__get_next_ip_line(head, self);
-
+ struct objdump_line *next;
+ next = objdump__get_next_ip_line(¬es->src->source, self);
while (offset < (s64)len &&
(next == NULL || offset < next->offset)) {
- if (sym_ext) {
- percent += sym_ext[offset].percent;
+ if (src_line) {
+ percent += src_line[offset].percent;
} else
- hits += h->ip[offset];
+ hits += h->addr[offset];
++offset;
}
-
- if (sym_ext == NULL && h->sum)
+ /*
+ * If the percentage wasn't already calculated in
+ * symbol__get_source_line, do it now:
+ */
+ if (src_line == NULL && h->sum)
percent = 100.0 * hits / h->sum;
}
self->curr_hot = nd;
}
-static int annotate_browser__run(struct annotate_browser *self)
+static void annotate_browser__calc_percent(struct annotate_browser *browser,
+ int evidx)
{
- struct rb_node *nd;
- struct hist_entry *he = self->b.priv;
- int key;
+ struct symbol *sym = browser->b.priv;
+ struct annotation *notes = symbol__annotation(sym);
+ struct objdump_line *pos;
- if (ui_browser__show(&self->b, he->ms.sym->name,
- "<-, -> or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0)
- return -1;
+ browser->entries = RB_ROOT;
+
+ pthread_mutex_lock(¬es->lock);
+
+ list_for_each_entry(pos, ¬es->src->source, node) {
+ struct objdump_line_rb_node *rbpos = objdump_line__rb(pos);
+ rbpos->percent = objdump_line__calc_percent(pos, sym, evidx);
+ if (rbpos->percent < 0.01) {
+ RB_CLEAR_NODE(&rbpos->rb_node);
+ continue;
+ }
+ objdump__insert_line(&browser->entries, rbpos);
+ }
+ pthread_mutex_unlock(¬es->lock);
+
+ browser->curr_hot = rb_last(&browser->entries);
+}
+
+static int annotate_browser__run(struct annotate_browser *self, int evidx,
+ int refresh)
+{
+ struct rb_node *nd = NULL;
+ struct symbol *sym = self->b.priv;
/*
- * To allow builtin-annotate to cycle thru multiple symbols by
+ * RIGHT To allow builtin-annotate to cycle thru multiple symbols by
* examining the exit key for this function.
*/
- ui_browser__add_exit_key(&self->b, NEWT_KEY_RIGHT);
+ int exit_keys[] = { 'H', NEWT_KEY_TAB, NEWT_KEY_UNTAB,
+ NEWT_KEY_RIGHT, 0 };
+ int key;
+
+ if (ui_browser__show(&self->b, sym->name,
+ "<-, -> or ESC: exit, TAB/shift+TAB: "
+ "cycle hottest lines, H: Hottest") < 0)
+ return -1;
+
+ ui_browser__add_exit_keys(&self->b, exit_keys);
+ annotate_browser__calc_percent(self, evidx);
+
+ if (self->curr_hot)
+ annotate_browser__set_top(self, self->curr_hot);
nd = self->curr_hot;
- if (nd) {
- int tabs[] = { NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0 };
- ui_browser__add_exit_keys(&self->b, tabs);
- }
+
+ if (refresh != 0)
+ newtFormSetTimer(self->b.form, refresh);
while (1) {
key = ui_browser__run(&self->b);
+ if (refresh != 0) {
+ annotate_browser__calc_percent(self, evidx);
+ /*
+ * Current line focus got out of the list of most active
+ * lines, NULL it so that if TAB|UNTAB is pressed, we
+ * move to curr_hot (current hottest line).
+ */
+ if (nd != NULL && RB_EMPTY_NODE(nd))
+ nd = NULL;
+ }
+
switch (key) {
+ case -1:
+ /*
+ * FIXME we need to check if it was
+ * es.reason == NEWT_EXIT_TIMER
+ */
+ if (refresh != 0)
+ symbol__annotate_decay_histogram(sym, evidx);
+ continue;
case NEWT_KEY_TAB:
- nd = rb_prev(nd);
- if (nd == NULL)
- nd = rb_last(&self->entries);
- annotate_browser__set_top(self, nd);
+ if (nd != NULL) {
+ nd = rb_prev(nd);
+ if (nd == NULL)
+ nd = rb_last(&self->entries);
+ } else
+ nd = self->curr_hot;
break;
case NEWT_KEY_UNTAB:
- nd = rb_next(nd);
- if (nd == NULL)
- nd = rb_first(&self->entries);
- annotate_browser__set_top(self, nd);
+ if (nd != NULL)
+ nd = rb_next(nd);
+ if (nd == NULL)
+ nd = rb_first(&self->entries);
+ else
+ nd = self->curr_hot;
+ break;
+ case 'H':
+ nd = self->curr_hot;
break;
default:
goto out;
}
+
+ if (nd != NULL)
+ annotate_browser__set_top(self, nd);
}
out:
ui_browser__hide(&self->b);
return key;
}
-int hist_entry__tui_annotate(struct hist_entry *self)
+int hist_entry__tui_annotate(struct hist_entry *he, int evidx)
+{
+ return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, 0);
+}
+
+int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+ int refresh)
{
struct objdump_line *pos, *n;
- struct objdump_line_rb_node *rbpos;
- LIST_HEAD(head);
+ struct annotation *notes = symbol__annotation(sym);
struct annotate_browser browser = {
.b = {
- .entries = &head,
+ .entries = ¬es->src->source,
.refresh = ui_browser__list_head_refresh,
.seek = ui_browser__list_head_seek,
.write = annotate_browser__write,
- .priv = self,
+ .priv = sym,
},
};
int ret;
- if (self->ms.sym == NULL)
+ if (sym == NULL)
return -1;
- if (self->ms.map->dso->annotate_warned)
+ if (map->dso->annotate_warned)
return -1;
- if (hist_entry__annotate(self, &head, sizeof(*rbpos)) < 0) {
+ if (symbol__annotate(sym, map, sizeof(struct objdump_line_rb_node)) < 0) {
ui__error_window(ui_helpline__last_msg);
return -1;
}
ui_helpline__push("Press <- or ESC to exit");
- list_for_each_entry(pos, &head, node) {
+ list_for_each_entry(pos, ¬es->src->source, node) {
+ struct objdump_line_rb_node *rbpos;
size_t line_len = strlen(pos->line);
+
if (browser.b.width < line_len)
browser.b.width = line_len;
rbpos = objdump_line__rb(pos);
rbpos->idx = browser.b.nr_entries++;
- rbpos->percent = objdump_line__calc_percent(pos, &head, self->ms.sym);
- if (rbpos->percent < 0.01)
- continue;
- objdump__insert_line(&browser.entries, rbpos);
}
- /*
- * Position the browser at the hottest line.
- */
- browser.curr_hot = rb_last(&browser.entries);
- if (browser.curr_hot)
- annotate_browser__set_top(&browser, browser.curr_hot);
-
browser.b.width += 18; /* Percentage */
- ret = annotate_browser__run(&browser);
- list_for_each_entry_safe(pos, n, &head, node) {
+ ret = annotate_browser__run(&browser, evidx, refresh);
+ list_for_each_entry_safe(pos, n, ¬es->src->source, node) {
list_del(&pos->node);
objdump_line__free(pos);
}
#include <newt.h>
#include <linux/rbtree.h>
+#include "../../evsel.h"
+#include "../../evlist.h"
#include "../../hist.h"
#include "../../pstack.h"
#include "../../sort.h"
{
int key;
int exit_keys[] = { 'a', '?', 'h', 'C', 'd', 'D', 'E', 't',
- NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT, 0, };
+ NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT,
+ NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0, };
self->b.entries = &self->hists->entries;
self->b.nr_entries = self->hists->nr_entries;
while (node) {
struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
struct rb_node *next = rb_next(node);
- u64 cumul = cumul_hits(child);
+ u64 cumul = callchain_cumul_hits(child);
struct callchain_list *chain;
char folded_sign = ' ';
int first = true;
struct rb_node *nd;
bool first = true;
+ if (self->nr_entries == 0)
+ return;
+
switch (whence) {
case SEEK_SET:
nd = hists__filter_entries(rb_first(self->entries));
return printed;
}
-int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
+static int perf_evsel__hists_browse(struct perf_evsel *evsel,
+ const char *helpline, const char *ev_name,
+ bool left_exits)
{
+ struct hists *self = &evsel->hists;
struct hist_browser *browser = hist_browser__new(self);
struct pstack *fstack;
const struct thread *thread_filter = NULL;
hists__browser_title(self, msg, sizeof(msg), ev_name,
dso_filter, thread_filter);
while (1) {
- const struct thread *thread;
- const struct dso *dso;
+ const struct thread *thread = NULL;
+ const struct dso *dso = NULL;
char *options[16];
int nr_options = 0, choice = 0, i,
annotate = -2, zoom_dso = -2, zoom_thread = -2,
key = hist_browser__run(browser, msg);
- thread = hist_browser__selected_thread(browser);
- dso = browser->selection->map ? browser->selection->map->dso : NULL;
+ if (browser->he_selection != NULL) {
+ thread = hist_browser__selected_thread(browser);
+ dso = browser->selection->map ? browser->selection->map->dso : NULL;
+ }
switch (key) {
case NEWT_KEY_TAB:
*/
goto out_free_stack;
case 'a':
- if (browser->selection->map == NULL &&
+ if (browser->selection == NULL ||
+ browser->selection->map == NULL ||
browser->selection->map->dso->annotate_warned)
continue;
goto do_annotate;
"E Expand all callchains\n"
"d Zoom into current DSO\n"
"t Zoom into current Thread\n"
+ "TAB/UNTAB Switch events\n"
"q/CTRL+C Exit browser");
continue;
case NEWT_KEY_ENTER:
case NEWT_KEY_LEFT: {
const void *top;
- if (pstack__empty(fstack))
+ if (pstack__empty(fstack)) {
+ /*
+ * Go back to the perf_evsel_menu__run or other user
+ */
+ if (left_exits)
+ goto out_free_stack;
continue;
+ }
top = pstack__pop(fstack);
if (top == &dso_filter)
goto zoom_out_dso;
continue;
}
case NEWT_KEY_ESCAPE:
- if (!ui__dialog_yesno("Do you really want to exit?"))
+ if (!left_exits &&
+ !ui__dialog_yesno("Do you really want to exit?"))
continue;
/* Fall thru */
default:
goto out_free_stack;
}
- if (browser->selection->sym != NULL &&
+ if (browser->selection != NULL &&
+ browser->selection->sym != NULL &&
!browser->selection->map->dso->annotate_warned &&
asprintf(&options[nr_options], "Annotate %s",
browser->selection->sym->name) > 0)
(dso->kernel ? "the Kernel" : dso->short_name)) > 0)
zoom_dso = nr_options++;
- if (browser->selection->map != NULL &&
+ if (browser->selection != NULL &&
+ browser->selection->map != NULL &&
asprintf(&options[nr_options], "Browse map details") > 0)
browse_map = nr_options++;
if (choice == annotate) {
struct hist_entry *he;
do_annotate:
- if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) {
- browser->selection->map->dso->annotate_warned = 1;
- ui_helpline__puts("No vmlinux file found, can't "
- "annotate with just a "
- "kallsyms file");
- continue;
- }
-
he = hist_browser__selected_entry(browser);
if (he == NULL)
continue;
- hist_entry__tui_annotate(he);
+ hist_entry__tui_annotate(he, evsel->idx);
} else if (choice == browse_map)
map__browse(browser->selection->map);
else if (choice == zoom_dso) {
return key;
}
-int hists__tui_browse_tree(struct rb_root *self, const char *help)
+struct perf_evsel_menu {
+ struct ui_browser b;
+ struct perf_evsel *selection;
+};
+
+static void perf_evsel_menu__write(struct ui_browser *browser,
+ void *entry, int row)
+{
+ struct perf_evsel_menu *menu = container_of(browser,
+ struct perf_evsel_menu, b);
+ struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+ bool current_entry = ui_browser__is_current_entry(browser, row);
+ unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+ const char *ev_name = event_name(evsel);
+ char bf[256], unit;
+
+ ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+ HE_COLORSET_NORMAL);
+
+ nr_events = convert_unit(nr_events, &unit);
+ snprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events,
+ unit, unit == ' ' ? "" : " ", ev_name);
+ slsmg_write_nstring(bf, browser->width);
+
+ if (current_entry)
+ menu->selection = evsel;
+}
+
+static int perf_evsel_menu__run(struct perf_evsel_menu *menu, const char *help)
{
- struct rb_node *first = rb_first(self), *nd = first, *next;
- int key = 0;
+ int exit_keys[] = { NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, };
+ struct perf_evlist *evlist = menu->b.priv;
+ struct perf_evsel *pos;
+ const char *ev_name, *title = "Available samples";
+ int key;
+
+ if (ui_browser__show(&menu->b, title,
+ "ESC: exit, ENTER|->: Browse histograms") < 0)
+ return -1;
+
+ ui_browser__add_exit_keys(&menu->b, exit_keys);
- while (nd) {
- struct hists *hists = rb_entry(nd, struct hists, rb_node);
- const char *ev_name = __event_name(hists->type, hists->config);
+ while (1) {
+ key = ui_browser__run(&menu->b);
- key = hists__browse(hists, help, ev_name);
switch (key) {
- case NEWT_KEY_TAB:
- next = rb_next(nd);
- if (next)
- nd = next;
+ case NEWT_KEY_RIGHT:
+ case NEWT_KEY_ENTER:
+ if (!menu->selection)
+ continue;
+ pos = menu->selection;
+browse_hists:
+ ev_name = event_name(pos);
+ key = perf_evsel__hists_browse(pos, help, ev_name, true);
+ ui_browser__show_title(&menu->b, title);
break;
- case NEWT_KEY_UNTAB:
- if (nd == first)
+ case NEWT_KEY_LEFT:
+ continue;
+ case NEWT_KEY_ESCAPE:
+ if (!ui__dialog_yesno("Do you really want to exit?"))
continue;
- nd = rb_prev(nd);
+ /* Fall thru */
+ default:
+ goto out;
+ }
+
+ switch (key) {
+ case NEWT_KEY_TAB:
+ if (pos->node.next == &evlist->entries)
+ pos = list_entry(evlist->entries.next, struct perf_evsel, node);
+ else
+ pos = list_entry(pos->node.next, struct perf_evsel, node);
+ goto browse_hists;
+ case NEWT_KEY_UNTAB:
+ if (pos->node.prev == &evlist->entries)
+ pos = list_entry(evlist->entries.prev, struct perf_evsel, node);
+ else
+ pos = list_entry(pos->node.prev, struct perf_evsel, node);
+ goto browse_hists;
+ case 'q':
+ case CTRL('c'):
+ goto out;
default:
- return key;
+ break;
}
}
+out:
+ ui_browser__hide(&menu->b);
return key;
}
+
+static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
+ const char *help)
+{
+ struct perf_evsel *pos;
+ struct perf_evsel_menu menu = {
+ .b = {
+ .entries = &evlist->entries,
+ .refresh = ui_browser__list_head_refresh,
+ .seek = ui_browser__list_head_seek,
+ .write = perf_evsel_menu__write,
+ .nr_entries = evlist->nr_entries,
+ .priv = evlist,
+ },
+ };
+
+ ui_helpline__push("Press ESC to exit");
+
+ list_for_each_entry(pos, &evlist->entries, node) {
+ const char *ev_name = event_name(pos);
+ size_t line_len = strlen(ev_name) + 7;
+
+ if (menu.b.width < line_len)
+ menu.b.width = line_len;
+ /*
+ * Cache the evsel name, tracepoints have a _high_ cost per
+ * event_name() call.
+ */
+ if (pos->name == NULL)
+ pos->name = strdup(ev_name);
+ }
+
+ return perf_evsel_menu__run(&menu, help);
+}
+
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help)
+{
+
+ if (evlist->nr_entries == 1) {
+ struct perf_evsel *first = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+ const char *ev_name = event_name(first);
+ return perf_evsel__hists_browse(first, help, ev_name, false);
+ }
+
+ return __perf_evlist__tui_browse_hists(evlist, help);
+}
out_free_form:
newtPopWindow();
newtFormDestroy(form);
- return 0;
+ return err;
}
struct map_browser {
--- /dev/null
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "../browser.h"
+#include "../../annotate.h"
+#include "../helpline.h"
+#include "../libslang.h"
+#include "../util.h"
+#include "../../evlist.h"
+#include "../../hist.h"
+#include "../../sort.h"
+#include "../../symbol.h"
+#include "../../top.h"
+
+struct perf_top_browser {
+ struct ui_browser b;
+ struct rb_root root;
+ struct sym_entry *selection;
+ float sum_ksamples;
+ int dso_width;
+ int dso_short_width;
+ int sym_width;
+};
+
+static void perf_top_browser__write(struct ui_browser *browser, void *entry, int row)
+{
+ struct perf_top_browser *top_browser = container_of(browser, struct perf_top_browser, b);
+ struct sym_entry *syme = rb_entry(entry, struct sym_entry, rb_node);
+ bool current_entry = ui_browser__is_current_entry(browser, row);
+ struct symbol *symbol = sym_entry__symbol(syme);
+ struct perf_top *top = browser->priv;
+ int width = browser->width;
+ double pcnt;
+
+ pcnt = 100.0 - (100.0 * ((top_browser->sum_ksamples - syme->snap_count) /
+ top_browser->sum_ksamples));
+ ui_browser__set_percent_color(browser, pcnt, current_entry);
+
+ if (top->evlist->nr_entries == 1 || !top->display_weighted) {
+ slsmg_printf("%20.2f ", syme->weight);
+ width -= 24;
+ } else {
+ slsmg_printf("%9.1f %10ld ", syme->weight, syme->snap_count);
+ width -= 23;
+ }
+
+ slsmg_printf("%4.1f%%", pcnt);
+ width -= 7;
+
+ if (verbose) {
+ slsmg_printf(" %016" PRIx64, symbol->start);
+ width -= 17;
+ }
+
+ slsmg_printf(" %-*.*s ", top_browser->sym_width, top_browser->sym_width,
+ symbol->name);
+ width -= top_browser->sym_width;
+ slsmg_write_nstring(width >= syme->map->dso->long_name_len ?
+ syme->map->dso->long_name :
+ syme->map->dso->short_name, width);
+
+ if (current_entry)
+ top_browser->selection = syme;
+}
+
+static void perf_top_browser__update_rb_tree(struct perf_top_browser *browser)
+{
+ struct perf_top *top = browser->b.priv;
+ u64 top_idx = browser->b.top_idx;
+
+ browser->root = RB_ROOT;
+ browser->b.top = NULL;
+ browser->sum_ksamples = perf_top__decay_samples(top, &browser->root);
+ /*
+ * No active symbols
+ */
+ if (top->rb_entries == 0)
+ return;
+
+ perf_top__find_widths(top, &browser->root, &browser->dso_width,
+ &browser->dso_short_width,
+ &browser->sym_width);
+ if (browser->sym_width + browser->dso_width > browser->b.width - 29) {
+ browser->dso_width = browser->dso_short_width;
+ if (browser->sym_width + browser->dso_width > browser->b.width - 29)
+ browser->sym_width = browser->b.width - browser->dso_width - 29;
+ }
+
+ /*
+ * Adjust the ui_browser indexes since the entries in the browser->root
+ * rb_tree may have changed, then seek it from start, so that we get a
+ * possible new top of the screen.
+ */
+ browser->b.nr_entries = top->rb_entries;
+
+ if (top_idx >= browser->b.nr_entries) {
+ if (browser->b.height >= browser->b.nr_entries)
+ top_idx = browser->b.nr_entries - browser->b.height;
+ else
+ top_idx = 0;
+ }
+
+ if (browser->b.index >= top_idx + browser->b.height)
+ browser->b.index = top_idx + browser->b.index - browser->b.top_idx;
+
+ if (browser->b.index >= browser->b.nr_entries)
+ browser->b.index = browser->b.nr_entries - 1;
+
+ browser->b.top_idx = top_idx;
+ browser->b.seek(&browser->b, top_idx, SEEK_SET);
+}
+
+static void perf_top_browser__annotate(struct perf_top_browser *browser)
+{
+ struct sym_entry *syme = browser->selection;
+ struct symbol *sym = sym_entry__symbol(syme);
+ struct annotation *notes = symbol__annotation(sym);
+ struct perf_top *top = browser->b.priv;
+
+ if (notes->src != NULL)
+ goto do_annotation;
+
+ pthread_mutex_lock(¬es->lock);
+
+ top->sym_filter_entry = NULL;
+
+ if (symbol__alloc_hist(sym, top->evlist->nr_entries) < 0) {
+ pr_err("Not enough memory for annotating '%s' symbol!\n",
+ sym->name);
+ pthread_mutex_unlock(¬es->lock);
+ return;
+ }
+
+ top->sym_filter_entry = syme;
+
+ pthread_mutex_unlock(¬es->lock);
+do_annotation:
+ symbol__tui_annotate(sym, syme->map, 0, top->delay_secs * 1000);
+}
+
+static int perf_top_browser__run(struct perf_top_browser *browser)
+{
+ int key;
+ char title[160];
+ struct perf_top *top = browser->b.priv;
+ int delay_msecs = top->delay_secs * 1000;
+ int exit_keys[] = { 'a', NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, };
+
+ perf_top_browser__update_rb_tree(browser);
+ perf_top__header_snprintf(top, title, sizeof(title));
+ perf_top__reset_sample_counters(top);
+
+ if (ui_browser__show(&browser->b, title,
+ "ESC: exit, ENTER|->|a: Live Annotate") < 0)
+ return -1;
+
+ newtFormSetTimer(browser->b.form, delay_msecs);
+ ui_browser__add_exit_keys(&browser->b, exit_keys);
+
+ while (1) {
+ key = ui_browser__run(&browser->b);
+
+ switch (key) {
+ case -1:
+ /* FIXME we need to check if it was es.reason == NEWT_EXIT_TIMER */
+ perf_top_browser__update_rb_tree(browser);
+ perf_top__header_snprintf(top, title, sizeof(title));
+ perf_top__reset_sample_counters(top);
+ ui_browser__set_color(&browser->b, NEWT_COLORSET_ROOT);
+ SLsmg_gotorc(0, 0);
+ slsmg_write_nstring(title, browser->b.width);
+ break;
+ case 'a':
+ case NEWT_KEY_RIGHT:
+ case NEWT_KEY_ENTER:
+ if (browser->selection)
+ perf_top_browser__annotate(browser);
+ break;
+ case NEWT_KEY_LEFT:
+ continue;
+ case NEWT_KEY_ESCAPE:
+ if (!ui__dialog_yesno("Do you really want to exit?"))
+ continue;
+ /* Fall thru */
+ default:
+ goto out;
+ }
+ }
+out:
+ ui_browser__hide(&browser->b);
+ return key;
+}
+
+int perf_top__tui_browser(struct perf_top *top)
+{
+ struct perf_top_browser browser = {
+ .b = {
+ .entries = &browser.root,
+ .refresh = ui_browser__rb_tree_refresh,
+ .seek = ui_browser__rb_tree_seek,
+ .write = perf_top_browser__write,
+ .priv = top,
+ },
+ };
+
+ ui_helpline__push("Press <- or ESC to exit");
+ return perf_top_browser__run(&browser);
+}
#include "../debug.h"
#include "helpline.h"
+#include "ui.h"
void ui_helpline__pop(void)
{
int ret;
static int backlog;
- ret = vsnprintf(ui_helpline__last_msg + backlog,
+ pthread_mutex_lock(&ui__lock);
+ ret = vsnprintf(ui_helpline__last_msg + backlog,
sizeof(ui_helpline__last_msg) - backlog, format, ap);
backlog += ret;
newtRefresh();
backlog = 0;
}
+ pthread_mutex_unlock(&ui__lock);
return ret;
}
#if SLANG_VERSION < 20104
#define slsmg_printf(msg, args...) \
- SLsmg_printf((char *)msg, ##args)
+ SLsmg_printf((char *)(msg), ##args)
#define slsmg_write_nstring(msg, len) \
- SLsmg_write_nstring((char *)msg, len)
+ SLsmg_write_nstring((char *)(msg), len)
#define sltt_set_color(obj, name, fg, bg) \
- SLtt_set_color(obj,(char *)name, (char *)fg, (char *)bg)
+ SLtt_set_color(obj,(char *)(name), (char *)(fg), (char *)(bg))
#else
#define slsmg_printf SLsmg_printf
#define slsmg_write_nstring SLsmg_write_nstring
#include "../debug.h"
#include "browser.h"
#include "helpline.h"
+#include "ui.h"
+
+pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
static void newt_suspend(void *d __used)
{
newtResume();
}
-void setup_browser(void)
+void setup_browser(bool fallback_to_pager)
{
if (!isatty(1) || !use_browser || dump_trace) {
use_browser = 0;
- setup_pager();
+ if (fallback_to_pager)
+ setup_pager();
return;
}
--- /dev/null
+#ifndef _PERF_UI_H_
+#define _PERF_UI_H_ 1
+
+#include <pthread.h>
+
+extern pthread_mutex_t ui__lock;
+
+#endif /* _PERF_UI_H_ */
#include "../debug.h"
#include "browser.h"
#include "helpline.h"
+#include "ui.h"
#include "util.h"
static void newt_form__set_exit_keys(newtComponent self)
va_list args;
va_start(args, format);
- if (use_browser > 0)
+ if (use_browser > 0) {
+ pthread_mutex_lock(&ui__lock);
newtWinMessagev((char *)warning_str, (char *)ok,
(char *)format, args);
- else
+ pthread_mutex_unlock(&ui__lock);
+ } else
vfprintf(stderr, format, args);
va_end(args);
}
#include <sys/poll.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
-#ifndef NO_SYS_SELECT_H
#include <sys/select.h>
-#endif
#include <netinet/in.h>
#include <netinet/tcp.h>
#include <arpa/inet.h>
#include "types.h"
#include <sys/ttydefaults.h>
-#ifndef NO_ICONV
-#include <iconv.h>
-#endif
-
extern const char *graph_line;
extern const char *graph_dotted_line;
extern char buildid_dir[];
return x;
}
-#ifndef DIR_HAS_BSD_GROUP_SEMANTICS
-# define FORCE_DIR_SET_GID S_ISGID
-#else
-# define FORCE_DIR_SET_GID 0
-#endif
-
-#ifdef NO_NSEC
-#undef USE_NSEC
-#define ST_CTIME_NSEC(st) 0
-#define ST_MTIME_NSEC(st) 0
-#else
-#ifdef USE_ST_TIMESPEC
-#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec))
-#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec))
-#else
-#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec))
-#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec))
-#endif
-#endif
-
int mkdir_p(char *path, mode_t mode);
int copyfile(const char *from, const char *to);
int num_cpus;
-typedef struct per_cpu_counters {
+struct counters {
unsigned long long tsc; /* per thread */
unsigned long long aperf; /* per thread */
unsigned long long mperf; /* per thread */
int pkg;
int core;
int cpu;
- struct per_cpu_counters *next;
-} PCC;
+ struct counters *next;
+};
-PCC *pcc_even;
-PCC *pcc_odd;
-PCC *pcc_delta;
-PCC *pcc_average;
+struct counters *cnt_even;
+struct counters *cnt_odd;
+struct counters *cnt_delta;
+struct counters *cnt_average;
struct timeval tv_even;
struct timeval tv_odd;
struct timeval tv_delta;
return msr;
}
-void print_header()
+void print_header(void)
{
if (show_pkg)
fprintf(stderr, "pkg ");
putc('\n', stderr);
}
-void dump_pcc(PCC *pcc)
+void dump_cnt(struct counters *cnt)
{
- fprintf(stderr, "package: %d ", pcc->pkg);
- fprintf(stderr, "core:: %d ", pcc->core);
- fprintf(stderr, "CPU: %d ", pcc->cpu);
- fprintf(stderr, "TSC: %016llX\n", pcc->tsc);
- fprintf(stderr, "c3: %016llX\n", pcc->c3);
- fprintf(stderr, "c6: %016llX\n", pcc->c6);
- fprintf(stderr, "c7: %016llX\n", pcc->c7);
- fprintf(stderr, "aperf: %016llX\n", pcc->aperf);
- fprintf(stderr, "pc2: %016llX\n", pcc->pc2);
- fprintf(stderr, "pc3: %016llX\n", pcc->pc3);
- fprintf(stderr, "pc6: %016llX\n", pcc->pc6);
- fprintf(stderr, "pc7: %016llX\n", pcc->pc7);
- fprintf(stderr, "msr0x%x: %016llX\n", extra_msr_offset, pcc->extra_msr);
+ fprintf(stderr, "package: %d ", cnt->pkg);
+ fprintf(stderr, "core:: %d ", cnt->core);
+ fprintf(stderr, "CPU: %d ", cnt->cpu);
+ fprintf(stderr, "TSC: %016llX\n", cnt->tsc);
+ fprintf(stderr, "c3: %016llX\n", cnt->c3);
+ fprintf(stderr, "c6: %016llX\n", cnt->c6);
+ fprintf(stderr, "c7: %016llX\n", cnt->c7);
+ fprintf(stderr, "aperf: %016llX\n", cnt->aperf);
+ fprintf(stderr, "pc2: %016llX\n", cnt->pc2);
+ fprintf(stderr, "pc3: %016llX\n", cnt->pc3);
+ fprintf(stderr, "pc6: %016llX\n", cnt->pc6);
+ fprintf(stderr, "pc7: %016llX\n", cnt->pc7);
+ fprintf(stderr, "msr0x%x: %016llX\n", extra_msr_offset, cnt->extra_msr);
}
-void dump_list(PCC *pcc)
+void dump_list(struct counters *cnt)
{
- printf("dump_list 0x%p\n", pcc);
+ printf("dump_list 0x%p\n", cnt);
- for (; pcc; pcc = pcc->next)
- dump_pcc(pcc);
+ for (; cnt; cnt = cnt->next)
+ dump_cnt(cnt);
}
-void print_pcc(PCC *p)
+void print_cnt(struct counters *p)
{
double interval_float;
interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
/* topology columns, print blanks on 1st (average) line */
- if (p == pcc_average) {
+ if (p == cnt_average) {
if (show_pkg)
fprintf(stderr, " ");
if (show_core)
putc('\n', stderr);
}
-void print_counters(PCC *cnt)
+void print_counters(struct counters *counters)
{
- PCC *pcc;
+ struct counters *cnt;
print_header();
if (num_cpus > 1)
- print_pcc(pcc_average);
+ print_cnt(cnt_average);
- for (pcc = cnt; pcc != NULL; pcc = pcc->next)
- print_pcc(pcc);
+ for (cnt = counters; cnt != NULL; cnt = cnt->next)
+ print_cnt(cnt);
}
#define SUBTRACT_COUNTER(after, before, delta) (delta = (after - before), (before > after))
-
-int compute_delta(PCC *after, PCC *before, PCC *delta)
+int compute_delta(struct counters *after,
+ struct counters *before, struct counters *delta)
{
int errors = 0;
int perf_err = 0;
delta->extra_msr = after->extra_msr;
if (errors) {
fprintf(stderr, "ERROR cpu%d before:\n", before->cpu);
- dump_pcc(before);
+ dump_cnt(before);
fprintf(stderr, "ERROR cpu%d after:\n", before->cpu);
- dump_pcc(after);
+ dump_cnt(after);
errors = 0;
}
}
return 0;
}
-void compute_average(PCC *delta, PCC *avg)
+void compute_average(struct counters *delta, struct counters *avg)
{
- PCC *sum;
+ struct counters *sum;
- sum = calloc(1, sizeof(PCC));
+ sum = calloc(1, sizeof(struct counters));
if (sum == NULL) {
perror("calloc sum");
exit(1);
free(sum);
}
-void get_counters(PCC *pcc)
+void get_counters(struct counters *cnt)
{
- for ( ; pcc; pcc = pcc->next) {
- pcc->tsc = get_msr(pcc->cpu, MSR_TSC);
+ for ( ; cnt; cnt = cnt->next) {
+ cnt->tsc = get_msr(cnt->cpu, MSR_TSC);
if (do_nhm_cstates)
- pcc->c3 = get_msr(pcc->cpu, MSR_CORE_C3_RESIDENCY);
+ cnt->c3 = get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY);
if (do_nhm_cstates)
- pcc->c6 = get_msr(pcc->cpu, MSR_CORE_C6_RESIDENCY);
+ cnt->c6 = get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY);
if (do_snb_cstates)
- pcc->c7 = get_msr(pcc->cpu, MSR_CORE_C7_RESIDENCY);
+ cnt->c7 = get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY);
if (has_aperf)
- pcc->aperf = get_msr(pcc->cpu, MSR_APERF);
+ cnt->aperf = get_msr(cnt->cpu, MSR_APERF);
if (has_aperf)
- pcc->mperf = get_msr(pcc->cpu, MSR_MPERF);
+ cnt->mperf = get_msr(cnt->cpu, MSR_MPERF);
if (do_snb_cstates)
- pcc->pc2 = get_msr(pcc->cpu, MSR_PKG_C2_RESIDENCY);
+ cnt->pc2 = get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY);
if (do_nhm_cstates)
- pcc->pc3 = get_msr(pcc->cpu, MSR_PKG_C3_RESIDENCY);
+ cnt->pc3 = get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY);
if (do_nhm_cstates)
- pcc->pc6 = get_msr(pcc->cpu, MSR_PKG_C6_RESIDENCY);
+ cnt->pc6 = get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY);
if (do_snb_cstates)
- pcc->pc7 = get_msr(pcc->cpu, MSR_PKG_C7_RESIDENCY);
+ cnt->pc7 = get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY);
if (extra_msr_offset)
- pcc->extra_msr = get_msr(pcc->cpu, extra_msr_offset);
+ cnt->extra_msr = get_msr(cnt->cpu, extra_msr_offset);
}
}
-
-void print_nehalem_info()
+void print_nehalem_info(void)
{
unsigned long long msr;
unsigned int ratio;
}
-void free_counter_list(PCC *list)
+void free_counter_list(struct counters *list)
{
- PCC *p;
+ struct counters *p;
for (p = list; p; ) {
- PCC *free_me;
+ struct counters *free_me;
free_me = p;
p = p->next;
free(free_me);
}
- return;
}
void free_all_counters(void)
{
- free_counter_list(pcc_even);
- pcc_even = NULL;
+ free_counter_list(cnt_even);
+ cnt_even = NULL;
- free_counter_list(pcc_odd);
- pcc_odd = NULL;
+ free_counter_list(cnt_odd);
+ cnt_odd = NULL;
- free_counter_list(pcc_delta);
- pcc_delta = NULL;
+ free_counter_list(cnt_delta);
+ cnt_delta = NULL;
- free_counter_list(pcc_average);
- pcc_average = NULL;
+ free_counter_list(cnt_average);
+ cnt_average = NULL;
}
-void insert_cpu_counters(PCC **list, PCC *new)
+void insert_counters(struct counters **list,
+ struct counters *new)
{
- PCC *prev;
+ struct counters *prev;
/*
* list was empty
*/
new->next = prev->next;
prev->next = new;
-
- return;
}
-void alloc_new_cpu_counters(int pkg, int core, int cpu)
+void alloc_new_counters(int pkg, int core, int cpu)
{
- PCC *new;
+ struct counters *new;
if (verbose > 1)
printf("pkg%d core%d, cpu%d\n", pkg, core, cpu);
- new = (PCC *)calloc(1, sizeof(PCC));
+ new = (struct counters *)calloc(1, sizeof(struct counters));
if (new == NULL) {
perror("calloc");
exit(1);
new->pkg = pkg;
new->core = core;
new->cpu = cpu;
- insert_cpu_counters(&pcc_odd, new);
+ insert_counters(&cnt_odd, new);
- new = (PCC *)calloc(1, sizeof(PCC));
+ new = (struct counters *)calloc(1,
+ sizeof(struct counters));
if (new == NULL) {
perror("calloc");
exit(1);
new->pkg = pkg;
new->core = core;
new->cpu = cpu;
- insert_cpu_counters(&pcc_even, new);
+ insert_counters(&cnt_even, new);
- new = (PCC *)calloc(1, sizeof(PCC));
+ new = (struct counters *)calloc(1, sizeof(struct counters));
if (new == NULL) {
perror("calloc");
exit(1);
new->pkg = pkg;
new->core = core;
new->cpu = cpu;
- insert_cpu_counters(&pcc_delta, new);
+ insert_counters(&cnt_delta, new);
- new = (PCC *)calloc(1, sizeof(PCC));
+ new = (struct counters *)calloc(1, sizeof(struct counters));
if (new == NULL) {
perror("calloc");
exit(1);
new->pkg = pkg;
new->core = core;
new->cpu = cpu;
- pcc_average = new;
+ cnt_average = new;
}
int get_physical_package_id(int cpu)
{
printf("turbostat: topology changed, re-initializing.\n");
free_all_counters();
- num_cpus = for_all_cpus(alloc_new_cpu_counters);
+ num_cpus = for_all_cpus(alloc_new_counters);
need_reinitialize = 0;
printf("num_cpus is now %d\n", num_cpus);
}
/*
* check to see if a cpu came on-line
*/
-void verify_num_cpus()
+void verify_num_cpus(void)
{
int new_num_cpus;
num_cpus, new_num_cpus);
need_reinitialize = 1;
}
-
- return;
}
void turbostat_loop()
{
restart:
- get_counters(pcc_even);
+ get_counters(cnt_even);
gettimeofday(&tv_even, (struct timezone *)NULL);
while (1) {
goto restart;
}
sleep(interval_sec);
- get_counters(pcc_odd);
+ get_counters(cnt_odd);
gettimeofday(&tv_odd, (struct timezone *)NULL);
- compute_delta(pcc_odd, pcc_even, pcc_delta);
+ compute_delta(cnt_odd, cnt_even, cnt_delta);
timersub(&tv_odd, &tv_even, &tv_delta);
- compute_average(pcc_delta, pcc_average);
- print_counters(pcc_delta);
+ compute_average(cnt_delta, cnt_average);
+ print_counters(cnt_delta);
if (need_reinitialize) {
re_initialize();
goto restart;
}
sleep(interval_sec);
- get_counters(pcc_even);
+ get_counters(cnt_even);
gettimeofday(&tv_even, (struct timezone *)NULL);
- compute_delta(pcc_even, pcc_odd, pcc_delta);
+ compute_delta(cnt_even, cnt_odd, cnt_delta);
timersub(&tv_even, &tv_odd, &tv_delta);
- compute_average(pcc_delta, pcc_average);
- print_counters(pcc_delta);
+ compute_average(cnt_delta, cnt_average);
+ print_counters(cnt_delta);
}
}
* this check is valid for both Intel and AMD
*/
asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000007));
- has_invariant_tsc = edx && (1 << 8);
+ has_invariant_tsc = edx & (1 << 8);
if (!has_invariant_tsc) {
fprintf(stderr, "No invariant TSC\n");
*/
asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6));
- has_aperf = ecx && (1 << 0);
+ has_aperf = ecx & (1 << 0);
if (!has_aperf) {
fprintf(stderr, "No APERF MSR\n");
exit(1);
check_dev_msr();
check_super_user();
- num_cpus = for_all_cpus(alloc_new_cpu_counters);
+ num_cpus = for_all_cpus(alloc_new_counters);
if (verbose)
print_nehalem_info();
{
int retval;
pid_t child_pid;
- get_counters(pcc_even);
+ get_counters(cnt_even);
gettimeofday(&tv_even, (struct timezone *)NULL);
child_pid = fork();
exit(1);
}
}
- get_counters(pcc_odd);
+ get_counters(cnt_odd);
gettimeofday(&tv_odd, (struct timezone *)NULL);
- retval = compute_delta(pcc_odd, pcc_even, pcc_delta);
+ retval = compute_delta(cnt_odd, cnt_even, cnt_delta);
timersub(&tv_odd, &tv_even, &tv_delta);
- compute_average(pcc_delta, pcc_average);
+ compute_average(cnt_delta, cnt_average);
if (!retval)
- print_counters(pcc_delta);
+ print_counters(cnt_delta);
fprintf(stderr, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);;
#!/usr/bin/perl -w
#
-# Copywrite 2010 - Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+# Copyright 2010 - Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
# Licensed under the terms of the GNU GPL License version 2
#