* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (46 commits)
powerpc64: convert to dynamic percpu allocator
sparc64: use embedding percpu first chunk allocator
percpu: kill lpage first chunk allocator
x86,percpu: use embedding for 64bit NUMA and page for 32bit NUMA
percpu: update embedding first chunk allocator to handle sparse units
percpu: use group information to allocate vmap areas sparsely
vmalloc: implement pcpu_get_vm_areas()
vmalloc: separate out insert_vmalloc_vm()
percpu: add chunk->base_addr
percpu: add pcpu_unit_offsets[]
percpu: introduce pcpu_alloc_info and pcpu_group_info
percpu: move pcpu_lpage_build_unit_map() and pcpul_lpage_dump_cfg() upward
percpu: add @align to pcpu_fc_alloc_fn_t
percpu: make @dyn_size mandatory for pcpu_setup_first_chunk()
percpu: drop @static_size from first chunk allocators
percpu: generalize first chunk allocator selection
percpu: build first chunk allocators selectively
percpu: rename 4k first chunk allocator to page
percpu: improve boot messages
percpu: fix pcpu_reclaim() locking
...
Fix trivial conflict as by Tejun Heo in kernel/sched.c
ISAPNP ISA PnP code is enabled.
ISDN Appropriate ISDN support is enabled.
JOY Appropriate joystick support is enabled.
+ KVM Kernel Virtual Machine support is enabled.
LIBATA Libata driver is enabled
LP Printer support is enabled.
LOOP Loopback device support is enabled.
kstack=N [X86] Print N words from the kernel stack
in oops dumps.
+ kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
+ Default is 0 (don't ignore, but inject #GP)
+
+ kvm.oos_shadow= [KVM] Disable out-of-sync shadow paging.
+ Default is 1 (enabled)
+
+ kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
+ Default is 0 (off)
+
+ kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU)
+ for all guests.
+ Default is 1 (enabled) if in 64bit or 32bit-PAE mode
+
+ kvm-intel.bypass_guest_pf=
+ [KVM,Intel] Disables bypassing of guest page faults
+ on Intel chips. Default is 1 (enabled)
+
+ kvm-intel.ept= [KVM,Intel] Disable extended page tables
+ (virtualized MMU) support on capable Intel chips.
+ Default is 1 (enabled)
+
+ kvm-intel.emulate_invalid_guest_state=
+ [KVM,Intel] Enable emulation of invalid guest states
+ Default is 0 (disabled)
+
+ kvm-intel.flexpriority=
+ [KVM,Intel] Disable FlexPriority feature (TPR shadow).
+ Default is 1 (enabled)
+
+ kvm-intel.unrestricted_guest=
+ [KVM,Intel] Disable unrestricted guest feature
+ (virtualized real and unpaged mode) on capable
+ Intel chips. Default is 1 (enabled)
+
+ kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification
+ feature (tagged TLBs) on capable Intel chips.
+ Default is 1 (enabled)
+
l2cr= [PPC]
l3cr= [PPC]
[NFS] set the TCP port on which the NFSv4 callback
channel should listen.
+ nfs.cache_getent=
+ [NFS] sets the pathname to the program which is used
+ to update the NFS client cache entries.
+
+ nfs.cache_getent_timeout=
+ [NFS] sets the timeout after which an attempt to
+ update a cache entry is deemed to have failed.
+
nfs.idmap_cache_timeout=
[NFS] set the maximum lifetime for idmapper cache
entries.
symbolic names: lapic and ioapic
Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic
+ netpoll.carrier_timeout=
+ [NET] Specifies amount of time (in seconds) that
+ netpoll should wait for a carrier. By default netpoll
+ waits 4 seconds.
+
no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
emulation library even if a 387 maths coprocessor
is present.
Format: { 0 | 1 }
See arch/parisc/kernel/pdc_chassis.c
- percpu_alloc= [X86] Select which percpu first chunk allocator to use.
- Allowed values are one of "lpage", "embed" and "4k".
- See comments in arch/x86/kernel/setup_percpu.c for
- details on each allocator. This parameter is primarily
- for debugging and performance comparison.
+ percpu_alloc= Select which percpu first chunk allocator to use.
+ Currently supported values are "embed" and "page".
+ Archs may support subset or none of the selections.
+ See comments in mm/percpu.c for details on each
+ allocator. This parameter is primarily for debugging
+ and performance comparison.
pf. [PARIDE]
See Documentation/blockdev/paride.txt.
stifb= [HW]
Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
+ sunrpc.min_resvport=
+ sunrpc.max_resvport=
+ [NFS,SUNRPC]
+ SunRPC servers often require that client requests
+ originate from a privileged port (i.e. a port in the
+ range 0 < portnr < 1024).
+ An administrator who wishes to reserve some of these
+ ports for other uses may adjust the range that the
+ kernel's sunrpc client considers to be privileged
+ using these two parameters to set the minimum and
+ maximum port values.
+
sunrpc.pool_mode=
[NFS]
Control how the NFS server code allocates CPUs to
pernode one pool for each NUMA node (equivalent
to global on non-NUMA machines)
+ sunrpc.tcp_slot_table_entries=
+ sunrpc.udp_slot_table_entries=
+ [NFS,SUNRPC]
+ Sets the upper limit on the number of simultaneous
+ RPC calls that can be sent from the client to a
+ server. Increasing these values may allow you to
+ improve throughput, but will also increase the
+ amount of memory reserved for use by the client.
+
swiotlb= [IA-64] Number of I/O TLB slabs
switches= [HW,M68k]
trace_buf_size=nn[KMG]
[FTRACE] will set tracing buffer size.
+ trace_event=[event-list]
+ [FTRACE] Set and start specified trace events in order
+ to facilitate early boot debugging.
+ See also Documentation/trace/events.txt
+
trix= [HW,OSS] MediaTrix AudioTrix Pro
Format:
<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 31
-EXTRAVERSION = -rc6
+EXTRAVERSION =
NAME = Man-Eating Seals of Antiquity
# *DOCUMENTATION*
MODFLAGS = -DMODULE
CFLAGS_MODULE = $(MODFLAGS)
AFLAGS_MODULE = $(MODFLAGS)
- LDFLAGS_MODULE =
+ LDFLAGS_MODULE = -T $(srctree)/scripts/module-common.lds
CFLAGS_KERNEL =
AFLAGS_KERNEL =
CFLAGS_GCOV = -fprofile-arcs -ftest-coverage
bool
default y
+ config HAVE_LEGACY_PER_CPU_AREA
+ def_bool y
+
config HAVE_SETUP_PER_CPU_AREA
def_bool y
bool
select GENERIC_ALLOCATOR
+config ARCH_USES_PG_UNCACHED
+ def_bool y
+ depends on IA64_UNCACHED_ALLOCATOR
+
config AUDIT_ARCH
bool
default y
#define NR_STAB_CACHE_ENTRIES 8
static DEFINE_PER_CPU(long, stab_cache_ptr);
- static DEFINE_PER_CPU(long, stab_cache[NR_STAB_CACHE_ENTRIES]);
+ static DEFINE_PER_CPU(long [NR_STAB_CACHE_ENTRIES], stab_cache);
/*
* Create a segment table entry for the given esid/vsid pair.
{
struct stab_entry *stab = (struct stab_entry *) get_paca()->stab_addr;
struct stab_entry *ste;
- unsigned long offset = __get_cpu_var(stab_cache_ptr);
+ unsigned long offset;
unsigned long pc = KSTK_EIP(tsk);
unsigned long stack = KSTK_ESP(tsk);
unsigned long unmapped_base;
/* Force previous translations to complete. DRENG */
asm volatile("isync" : : : "memory");
+ /*
+ * We need interrupts hard-disabled here, not just soft-disabled,
+ * so that a PMU interrupt can't occur, which might try to access
+ * user memory (to get a stack trace) and possible cause an STAB miss
+ * which would update the stab_cache/stab_cache_ptr per-cpu variables.
+ */
+ hard_irq_disable();
+
+ offset = __get_cpu_var(stab_cache_ptr);
if (offset <= NR_STAB_CACHE_ENTRIES) {
int i;
. = ALIGN(PAGE_SIZE);
_eshared = .; /* End of shareable data */
- . = ALIGN(16); /* Exception table */
- __ex_table : {
- __start___ex_table = .;
- *(__ex_table)
- __stop___ex_table = .;
- } :data
-
- .data : { /* Data */
- DATA_DATA
- CONSTRUCTORS
- }
-
- . = ALIGN(PAGE_SIZE);
- .data_nosave : {
- __nosave_begin = .;
- *(.data.nosave)
- }
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
-
- . = ALIGN(PAGE_SIZE);
- .data.page_aligned : {
- *(.data.idt)
- }
+ EXCEPTION_TABLE(16) :data
- . = ALIGN(0x100);
- .data.cacheline_aligned : {
- *(.data.cacheline_aligned)
- }
+ RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE)
- . = ALIGN(0x100);
- .data.read_mostly : {
- *(.data.read_mostly)
- }
_edata = .; /* End of data section */
- . = ALIGN(THREAD_SIZE); /* init_task */
- .data.init_task : {
- *(.data.init_task)
- }
-
/* will be freed after init */
. = ALIGN(PAGE_SIZE); /* Init code and data */
__init_begin = .;
- .init.text : {
- _sinittext = .;
- INIT_TEXT
- _einittext = .;
- }
+
+ INIT_TEXT_SECTION(PAGE_SIZE)
+
/*
* .exit.text is discarded at runtime, not link time,
* to deal with references from __bug_table
/* early.c uses stsi, which requires page aligned data. */
. = ALIGN(PAGE_SIZE);
- .init.data : {
- INIT_DATA
- }
- . = ALIGN(0x100);
- .init.setup : {
- __setup_start = .;
- *(.init.setup)
- __setup_end = .;
- }
- .initcall.init : {
- __initcall_start = .;
- INITCALLS
- __initcall_end = .;
- }
-
- .con_initcall.init : {
- __con_initcall_start = .;
- *(.con_initcall.init)
- __con_initcall_end = .;
- }
- SECURITY_INIT
-
-#ifdef CONFIG_BLK_DEV_INITRD
- . = ALIGN(0x100);
- .init.ramfs : {
- __initramfs_start = .;
- *(.init.ramfs)
- . = ALIGN(2);
- __initramfs_end = .;
- }
-#endif
+ INIT_DATA_SECTION(0x100)
PERCPU(PAGE_SIZE)
. = ALIGN(PAGE_SIZE);
__init_end = .; /* freed after init ends here */
- /* BSS */
- .bss : {
- __bss_start = .;
- *(.bss)
- . = ALIGN(2);
- __bss_stop = .;
- }
+ BSS_SECTION(0, 2, 0)
_end = . ;
- /* Sections to be discarded */
- /DISCARD/ : {
- EXIT_DATA
- *(.exitcall.exit)
- }
-
/* Debugging sections. */
STABS_DEBUG
DWARF_DEBUG
+
+ /* Sections to be discarded */
+ DISCARDS
}
select ARCH_WANT_OPTIONAL_GPIOLIB
select RTC_CLASS
select RTC_DRV_M48T59
+ select HAVE_PERF_COUNTERS
+ select HAVE_DMA_ATTRS
+ select HAVE_DMA_API_DEBUG
config SPARC32
def_bool !64BIT
select RTC_DRV_BQ4802
select RTC_DRV_SUN4V
select RTC_DRV_STARFIRE
+ select HAVE_PERF_COUNTERS
config ARCH_DEFCONFIG
string
config HAVE_SETUP_PER_CPU_AREA
def_bool y if SPARC64
- config HAVE_DYNAMIC_PER_CPU_AREA
+ config NEED_PER_CPU_EMBED_FIRST_CHUNK
def_bool y if SPARC64
config GENERIC_HARDIRQS_NO__DO_IRQ
If unsure, say N.
+config SPARC_LEON
+ bool "Sparc Leon processor family"
+ depends on SPARC32
+ ---help---
+ If you say Y here if you are running on a SPARC-LEON processor.
+ The LEON processor is a synthesizable VHDL model of the
+ SPARC-v8 standard. LEON is part of the GRLIB collection of
+ IP cores that are distributed under GPL. GRLIB can be downloaded
+ from www.gaisler.com. You can download a sparc-linux cross-compilation
+ toolchain at www.gaisler.com.
+
endmenu
menu "Bus options (PCI etc.)"
select HAVE_FUNCTION_GRAPH_FP_TEST
select HAVE_FUNCTION_TRACE_MCOUNT_TEST
select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
- select HAVE_FTRACE_SYSCALLS
+ select HAVE_SYSCALL_TRACEPOINTS
select HAVE_KVM
select HAVE_ARCH_KGDB
select HAVE_ARCH_TRACEHOOK
config HAVE_SETUP_PER_CPU_AREA
def_bool y
- config HAVE_DYNAMIC_PER_CPU_AREA
+ config NEED_PER_CPU_EMBED_FIRST_CHUNK
+ def_bool y
+
+ config NEED_PER_CPU_PAGE_FIRST_CHUNK
def_bool y
config HAVE_CPUMASK_OF_CPU_MAP
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
+config HAVE_INTEL_TXT
+ def_bool y
+ depends on EXPERIMENTAL && DMAR && ACPI
+
# Use the generic interrupt handling code in kernel/irq/:
config GENERIC_HARDIRQS
bool
bool "GART IOMMU support" if EMBEDDED
default y
select SWIOTLB
- select AGP
depends on X86_64 && PCI
---help---
Support for full DMA access of devices with 32bit memory access only
If unsure, say Y.
+config ARCH_USES_PG_UNCACHED
+ def_bool y
+ depends on X86_PAT
+
config EFI
bool "EFI runtime service support"
depends on ACPI
#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x
#define __my_cpu_offset percpu_read(this_cpu_off)
#else
-#define __percpu_arg(x) "%" #x
+#define __percpu_arg(x) "%P" #x
#endif
/*
} \
} while (0)
-#define percpu_from_op(op, var) \
+#define percpu_from_op(op, var, constraint) \
({ \
typeof(var) ret__; \
switch (sizeof(var)) { \
case 1: \
asm(op "b "__percpu_arg(1)",%0" \
: "=q" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 2: \
asm(op "w "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 4: \
asm(op "l "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 8: \
asm(op "q "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
default: __bad_percpu_size(); \
} \
ret__; \
})
-#define percpu_read(var) percpu_from_op("mov", per_cpu__##var)
+/*
+ * percpu_read() makes gcc load the percpu variable every time it is
+ * accessed while percpu_read_stable() allows the value to be cached.
+ * percpu_read_stable() is more efficient and can be used if its value
+ * is guaranteed to be valid across cpus. The current users include
+ * get_current() and get_thread_info() both of which are actually
+ * per-thread variables implemented as per-cpu variables and thus
+ * stable for the duration of the respective task.
+ */
+#define percpu_read(var) percpu_from_op("mov", per_cpu__##var, \
+ "m" (per_cpu__##var))
+#define percpu_read_stable(var) percpu_from_op("mov", per_cpu__##var, \
+ "p" (&per_cpu__##var))
#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val)
#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val)
#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val)
/* We can use this directly for local CPU (faster). */
DECLARE_PER_CPU(unsigned long, this_cpu_off);
- #ifdef CONFIG_NEED_MULTIPLE_NODES
- void *pcpu_lpage_remapped(void *kaddr);
- #else
- static inline void *pcpu_lpage_remapped(void *kaddr)
- {
- return NULL;
- }
- #endif
-
#endif /* !__ASSEMBLY__ */
#ifdef CONFIG_SMP
set_bit(0, &mce_need_notify);
}
+void __weak decode_mce(struct mce *m)
+{
+ return;
+}
+
static void print_mce(struct mce *m)
{
printk(KERN_EMERG
printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
m->cpuvendor, m->cpuid, m->time, m->socketid,
m->apicid);
+
+ decode_mce(m);
}
static void print_mce_head(void)
static void print_mce_tail(void)
{
printk(KERN_EMERG "This is not a software problem!\n"
- "Run through mcelog --ascii to decode and contact your hardware vendor\n");
+#if (!defined(CONFIG_EDAC) || !defined(CONFIG_CPU_SUP_AMD))
+ "Run through mcelog --ascii to decode and contact your hardware vendor\n"
+#endif
+ );
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
*/
static int check_interval = 5 * 60; /* 5 minutes */
- static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
+ static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);
static void mcheck_timer(unsigned long data)
* Alert userspace if needed. If we logged an MCE, reduce the
* polling interval, otherwise increase the polling interval.
*/
- n = &__get_cpu_var(next_interval);
+ n = &__get_cpu_var(mce_next_interval);
if (mce_notify_irq())
*n = max(*n/2, HZ/100);
else
}
/* Add per CPU specific workarounds here */
-static void mce_cpu_quirks(struct cpuinfo_x86 *c)
+static int mce_cpu_quirks(struct cpuinfo_x86 *c)
{
+ if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
+ pr_info("MCE: unknown CPU type - not enabling MCE support.\n");
+ return -EOPNOTSUPP;
+ }
+
/* This should be disabled by the BIOS, but isn't always */
if (c->x86_vendor == X86_VENDOR_AMD) {
if (c->x86 == 15 && banks > 4) {
if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) &&
monarch_timeout < 0)
monarch_timeout = USEC_PER_SEC;
+
+ /*
+ * There are also broken BIOSes on some Pentium M and
+ * earlier systems:
+ */
+ if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0)
+ mce_bootlog = 0;
}
if (monarch_timeout < 0)
monarch_timeout = 0;
if (mce_bootlog != 0)
mce_panic_timeout = 30;
+
+ return 0;
}
static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c)
static void mce_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
- int *n = &__get_cpu_var(next_interval);
+ int *n = &__get_cpu_var(mce_next_interval);
if (mce_ignore_ce)
return;
if (!mce_available(c))
return;
- if (mce_cap_init() < 0) {
+ if (mce_cap_init() < 0 || mce_cpu_quirks(c) < 0) {
mce_disabled = 1;
return;
}
- mce_cpu_quirks(c);
machine_check_vector = do_machine_check;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
t->expires = round_jiffies(jiffies +
- __get_cpu_var(next_interval));
+ __get_cpu_var(mce_next_interval));
add_timer_on(t, cpu);
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
break;
struct threshold_block *blocks;
cpumask_var_t cpus;
};
- static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
+ static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
#ifdef CONFIG_SMP
static unsigned char shared_bank[NR_BANKS] = {
int i, err = 0;
struct threshold_bank *b = NULL;
char name[32];
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
sprintf(name, "threshold_bank%i", bank);
#ifdef CONFIG_SMP
if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
- i = cpumask_first(cpu_core_mask(cpu));
+ i = cpumask_first(c->llc_shared_map);
/* first core not up yet */
if (cpu_data(i).cpu_core_id)
if (err)
goto out;
- cpumask_copy(b->cpus, cpu_core_mask(cpu));
+ cpumask_copy(b->cpus, c->llc_shared_map);
per_cpu(threshold_banks, cpu)[bank] = b;
goto out;
#ifndef CONFIG_SMP
cpumask_setall(b->cpus);
#else
- cpumask_copy(b->cpus, cpu_core_mask(cpu));
+ cpumask_copy(b->cpus, c->llc_shared_map);
#endif
per_cpu(threshold_banks, cpu)[bank] = b;
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
* Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
*
* For licencing details see kernel-base/COPYING
*/
#include <linux/sched.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
+#include <linux/cpu.h>
#include <asm/apic.h>
#include <asm/stacktrace.h>
static u64 perf_counter_mask __read_mostly;
+/* The maximal number of PEBS counters: */
+#define MAX_PEBS_COUNTERS 4
+
+/* The size of a BTS record in bytes: */
+#define BTS_RECORD_SIZE 24
+
+/* The size of a per-cpu BTS buffer in bytes: */
+#define BTS_BUFFER_SIZE (BTS_RECORD_SIZE * 1024)
+
+/* The BTS overflow threshold in bytes from the end of the buffer: */
+#define BTS_OVFL_TH (BTS_RECORD_SIZE * 64)
+
+
+/*
+ * Bits in the debugctlmsr controlling branch tracing.
+ */
+#define X86_DEBUGCTL_TR (1 << 6)
+#define X86_DEBUGCTL_BTS (1 << 7)
+#define X86_DEBUGCTL_BTINT (1 << 8)
+#define X86_DEBUGCTL_BTS_OFF_OS (1 << 9)
+#define X86_DEBUGCTL_BTS_OFF_USR (1 << 10)
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+ u64 bts_buffer_base;
+ u64 bts_index;
+ u64 bts_absolute_maximum;
+ u64 bts_interrupt_threshold;
+ u64 pebs_buffer_base;
+ u64 pebs_index;
+ u64 pebs_absolute_maximum;
+ u64 pebs_interrupt_threshold;
+ u64 pebs_counter_reset[MAX_PEBS_COUNTERS];
+};
+
struct cpu_hw_counters {
struct perf_counter *counters[X86_PMC_IDX_MAX];
unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
unsigned long interrupts;
int enabled;
+ struct debug_store *ds;
};
/*
int apic;
u64 max_period;
u64 intel_ctrl;
+ void (*enable_bts)(u64 config);
+ void (*disable_bts)(void);
};
static struct x86_pmu x86_pmu __read_mostly;
u64 prev_raw_count, new_raw_count;
s64 delta;
+ if (idx == X86_PMC_IDX_FIXED_BTS)
+ return 0;
+
/*
* Careful: an NMI might modify the previous counter value.
*
#endif
}
+static inline bool bts_available(void)
+{
+ return x86_pmu.enable_bts != NULL;
+}
+
+static inline void init_debug_store_on_cpu(int cpu)
+{
+ struct debug_store *ds = per_cpu(cpu_hw_counters, cpu).ds;
+
+ if (!ds)
+ return;
+
+ wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
+ (u32)((u64)(unsigned long)ds),
+ (u32)((u64)(unsigned long)ds >> 32));
+}
+
+static inline void fini_debug_store_on_cpu(int cpu)
+{
+ if (!per_cpu(cpu_hw_counters, cpu).ds)
+ return;
+
+ wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
+}
+
+static void release_bts_hardware(void)
+{
+ int cpu;
+
+ if (!bts_available())
+ return;
+
+ get_online_cpus();
+
+ for_each_online_cpu(cpu)
+ fini_debug_store_on_cpu(cpu);
+
+ for_each_possible_cpu(cpu) {
+ struct debug_store *ds = per_cpu(cpu_hw_counters, cpu).ds;
+
+ if (!ds)
+ continue;
+
+ per_cpu(cpu_hw_counters, cpu).ds = NULL;
+
+ kfree((void *)(unsigned long)ds->bts_buffer_base);
+ kfree(ds);
+ }
+
+ put_online_cpus();
+}
+
+static int reserve_bts_hardware(void)
+{
+ int cpu, err = 0;
+
+ if (!bts_available())
+ return 0;
+
+ get_online_cpus();
+
+ for_each_possible_cpu(cpu) {
+ struct debug_store *ds;
+ void *buffer;
+
+ err = -ENOMEM;
+ buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
+ if (unlikely(!buffer))
+ break;
+
+ ds = kzalloc(sizeof(*ds), GFP_KERNEL);
+ if (unlikely(!ds)) {
+ kfree(buffer);
+ break;
+ }
+
+ ds->bts_buffer_base = (u64)(unsigned long)buffer;
+ ds->bts_index = ds->bts_buffer_base;
+ ds->bts_absolute_maximum =
+ ds->bts_buffer_base + BTS_BUFFER_SIZE;
+ ds->bts_interrupt_threshold =
+ ds->bts_absolute_maximum - BTS_OVFL_TH;
+
+ per_cpu(cpu_hw_counters, cpu).ds = ds;
+ err = 0;
+ }
+
+ if (err)
+ release_bts_hardware();
+ else {
+ for_each_online_cpu(cpu)
+ init_debug_store_on_cpu(cpu);
+ }
+
+ put_online_cpus();
+
+ return err;
+}
+
static void hw_perf_counter_destroy(struct perf_counter *counter)
{
if (atomic_dec_and_mutex_lock(&active_counters, &pmc_reserve_mutex)) {
release_pmc_hardware();
+ release_bts_hardware();
mutex_unlock(&pmc_reserve_mutex);
}
}
return 0;
}
+static void intel_pmu_enable_bts(u64 config)
+{
+ unsigned long debugctlmsr;
+
+ debugctlmsr = get_debugctlmsr();
+
+ debugctlmsr |= X86_DEBUGCTL_TR;
+ debugctlmsr |= X86_DEBUGCTL_BTS;
+ debugctlmsr |= X86_DEBUGCTL_BTINT;
+
+ if (!(config & ARCH_PERFMON_EVENTSEL_OS))
+ debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
+
+ if (!(config & ARCH_PERFMON_EVENTSEL_USR))
+ debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
+
+ update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_bts(void)
+{
+ struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+ unsigned long debugctlmsr;
+
+ if (!cpuc->ds)
+ return;
+
+ debugctlmsr = get_debugctlmsr();
+
+ debugctlmsr &=
+ ~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
+ X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
+
+ update_debugctlmsr(debugctlmsr);
+}
+
/*
* Setup the hardware configuration for a given attr_type
*/
err = 0;
if (!atomic_inc_not_zero(&active_counters)) {
mutex_lock(&pmc_reserve_mutex);
- if (atomic_read(&active_counters) == 0 && !reserve_pmc_hardware())
- err = -EBUSY;
- else
+ if (atomic_read(&active_counters) == 0) {
+ if (!reserve_pmc_hardware())
+ err = -EBUSY;
+ else
+ err = reserve_bts_hardware();
+ }
+ if (!err)
atomic_inc(&active_counters);
mutex_unlock(&pmc_reserve_mutex);
}
if (config == -1LL)
return -EINVAL;
+ /*
+ * Branch tracing:
+ */
+ if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
+ (hwc->sample_period == 1)) {
+ /* BTS is not supported by this architecture. */
+ if (!bts_available())
+ return -EOPNOTSUPP;
+
+ /* BTS is currently only allowed for user-mode. */
+ if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+ return -EOPNOTSUPP;
+ }
+
hwc->config |= config;
return 0;
static void intel_pmu_disable_all(void)
{
+ struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+
+ if (!cpuc->enabled)
+ return;
+
+ cpuc->enabled = 0;
+ barrier();
+
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+
+ if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+ intel_pmu_disable_bts();
}
static void amd_pmu_disable_all(void)
static void intel_pmu_enable_all(void)
{
+ struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+
+ if (cpuc->enabled)
+ return;
+
+ cpuc->enabled = 1;
+ barrier();
+
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+
+ if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+ struct perf_counter *counter =
+ cpuc->counters[X86_PMC_IDX_FIXED_BTS];
+
+ if (WARN_ON_ONCE(!counter))
+ return;
+
+ intel_pmu_enable_bts(counter->hw.config);
+ }
}
static void amd_pmu_enable_all(void)
static inline void
intel_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
{
+ if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+ intel_pmu_disable_bts();
+ return;
+ }
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc, idx);
return;
x86_pmu_disable_counter(hwc, idx);
}
- static DEFINE_PER_CPU(u64, prev_left[X86_PMC_IDX_MAX]);
+ static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
/*
* Set the next IRQ period, based on the hwc->period_left value.
s64 period = hwc->sample_period;
int err, ret = 0;
+ if (idx == X86_PMC_IDX_FIXED_BTS)
+ return 0;
+
/*
* If we are way outside a reasoable range then just skip forward:
*/
if (left > x86_pmu.max_period)
left = x86_pmu.max_period;
- per_cpu(prev_left[idx], smp_processor_id()) = left;
+ per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
/*
* The hw counter starts counting from this counter offset,
static void intel_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
{
+ if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+ if (!__get_cpu_var(cpu_hw_counters).enabled)
+ return;
+
+ intel_pmu_enable_bts(hwc->config);
+ return;
+ }
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_enable_fixed(hwc, idx);
return;
{
unsigned int event;
+ event = hwc->config & ARCH_PERFMON_EVENT_MASK;
+
+ if (unlikely((event ==
+ x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
+ (hwc->sample_period == 1)))
+ return X86_PMC_IDX_FIXED_BTS;
+
if (!x86_pmu.num_counters_fixed)
return -1;
- event = hwc->config & ARCH_PERFMON_EVENT_MASK;
-
if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
return X86_PMC_IDX_FIXED_INSTRUCTIONS;
if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES)))
int idx;
idx = fixed_mode_idx(counter, hwc);
- if (idx >= 0) {
+ if (idx == X86_PMC_IDX_FIXED_BTS) {
+ /* BTS is already occupied. */
+ if (test_and_set_bit(idx, cpuc->used_mask))
+ return -EAGAIN;
+
+ hwc->config_base = 0;
+ hwc->counter_base = 0;
+ hwc->idx = idx;
+ } else if (idx >= 0) {
/*
* Try to get the fixed counter, if that is already taken
* then try to get a generic counter:
rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
rdmsrl(x86_pmu.perfctr + idx, pmc_count);
- prev_left = per_cpu(prev_left[idx], cpu);
+ prev_left = per_cpu(pmc_prev_left[idx], cpu);
pr_info("CPU#%d: gen-PMC%d ctrl: %016llx\n",
cpu, idx, pmc_ctrl);
local_irq_restore(flags);
}
+static void intel_pmu_drain_bts_buffer(struct cpu_hw_counters *cpuc,
+ struct perf_sample_data *data)
+{
+ struct debug_store *ds = cpuc->ds;
+ struct bts_record {
+ u64 from;
+ u64 to;
+ u64 flags;
+ };
+ struct perf_counter *counter = cpuc->counters[X86_PMC_IDX_FIXED_BTS];
+ unsigned long orig_ip = data->regs->ip;
+ struct bts_record *at, *top;
+
+ if (!counter)
+ return;
+
+ if (!ds)
+ return;
+
+ at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+ top = (struct bts_record *)(unsigned long)ds->bts_index;
+
+ ds->bts_index = ds->bts_buffer_base;
+
+ for (; at < top; at++) {
+ data->regs->ip = at->from;
+ data->addr = at->to;
+
+ perf_counter_output(counter, 1, data);
+ }
+
+ data->regs->ip = orig_ip;
+ data->addr = 0;
+
+ /* There's new data available. */
+ counter->pending_kill = POLL_IN;
+}
+
static void x86_pmu_disable(struct perf_counter *counter)
{
struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
* that we are disabling:
*/
x86_perf_counter_update(counter, hwc, idx);
+
+ /* Drain the remaining BTS records. */
+ if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+ struct perf_sample_data data;
+ struct pt_regs regs;
+
+ data.regs = ®s;
+ intel_pmu_drain_bts_buffer(cpuc, &data);
+ }
cpuc->counters[idx] = NULL;
clear_bit(idx, cpuc->used_mask);
static void intel_pmu_reset(void)
{
+ struct debug_store *ds = __get_cpu_var(cpu_hw_counters).ds;
unsigned long flags;
int idx;
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
}
+ if (ds)
+ ds->bts_index = ds->bts_buffer_base;
local_irq_restore(flags);
}
cpuc = &__get_cpu_var(cpu_hw_counters);
perf_disable();
+ intel_pmu_drain_bts_buffer(cpuc, &data);
status = intel_pmu_get_status();
if (!status) {
perf_enable();
* the generic counter period:
*/
.max_period = (1ULL << 31) - 1,
+ .enable_bts = intel_pmu_enable_bts,
+ .disable_bts = intel_pmu_disable_bts,
};
static struct x86_pmu amd_pmu = {
entry->ip[entry->nr++] = ip;
}
- static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry);
- static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry);
+ static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
+ static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
static DEFINE_PER_CPU(int, in_nmi_frame);
struct perf_callchain_entry *entry;
if (in_nmi())
- entry = &__get_cpu_var(nmi_entry);
+ entry = &__get_cpu_var(pmc_nmi_entry);
else
- entry = &__get_cpu_var(irq_entry);
+ entry = &__get_cpu_var(pmc_irq_entry);
entry->nr = 0;
return entry;
}
+
+void hw_perf_counter_setup_online(int cpu)
+{
+ init_debug_store_on_cpu(cpu);
+}
data PT_LOAD FLAGS(7); /* RWE */
#ifdef CONFIG_X86_64
user PT_LOAD FLAGS(7); /* RWE */
- data.init PT_LOAD FLAGS(7); /* RWE */
#ifdef CONFIG_SMP
percpu PT_LOAD FLAGS(7); /* RWE */
#endif
- data.init2 PT_LOAD FLAGS(7); /* RWE */
+ init PT_LOAD FLAGS(7); /* RWE */
#endif
note PT_NOTE FLAGS(0); /* ___ */
}
__stop___ex_table = .;
} :text = 0x9090
- RODATA
+ RO_DATA(PAGE_SIZE)
/* Data */
- . = ALIGN(PAGE_SIZE);
.data : AT(ADDR(.data) - LOAD_OFFSET) {
/* Start of data section */
_sdata = .;
- DATA_DATA
- CONSTRUCTORS
- } :data
+
+ /* init_task */
+ INIT_TASK_DATA(THREAD_SIZE)
#ifdef CONFIG_X86_32
- /* 32 bit has nosave before _edata */
- . = ALIGN(PAGE_SIZE);
- .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
- __nosave_begin = .;
- *(.data.nosave)
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
- }
+ /* 32 bit has nosave before _edata */
+ NOSAVE_DATA
#endif
- . = ALIGN(PAGE_SIZE);
- .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
- *(.data.page_aligned)
+ PAGE_ALIGNED_DATA(PAGE_SIZE)
*(.data.idt)
- }
-#ifdef CONFIG_X86_32
- . = ALIGN(32);
-#else
- . = ALIGN(PAGE_SIZE);
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-#endif
- .data.cacheline_aligned :
- AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
- *(.data.cacheline_aligned)
- }
+ CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES)
- /* rarely changed data like cpu maps */
-#ifdef CONFIG_X86_32
- . = ALIGN(32);
-#else
- . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
-#endif
- .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
- *(.data.read_mostly)
+ DATA_DATA
+ CONSTRUCTORS
+
+ /* rarely changed data like cpu maps */
+ READ_MOSTLY_DATA(CONFIG_X86_INTERNODE_CACHE_BYTES)
/* End of data section */
_edata = .;
- }
+ } :data
#ifdef CONFIG_X86_64
#define VSYSCALL_ADDR (-10*1024*1024)
-#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + \
- SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + \
- SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data) + SIZEOF(.data) + \
+ PAGE_SIZE - 1) & ~(PAGE_SIZE - 1))
+#define VSYSCALL_VIRT_ADDR ((ADDR(.data) + SIZEOF(.data) + \
+ PAGE_SIZE - 1) & ~(PAGE_SIZE - 1))
#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
#endif /* CONFIG_X86_64 */
- /* init_task */
- . = ALIGN(THREAD_SIZE);
- .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
- *(.data.init_task)
+ /* Init code and data - will be freed after init */
+ . = ALIGN(PAGE_SIZE);
+ .init.begin : AT(ADDR(.init.begin) - LOAD_OFFSET) {
+ __init_begin = .; /* paired with __init_end */
}
-#ifdef CONFIG_X86_64
- :data.init
-#endif
+#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
/*
- * smp_locks might be freed after init
- * start/end must be page aligned
+ * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
+ * output PHDR, so the next output section - .init.text - should
+ * start another segment - init.
*/
- . = ALIGN(PAGE_SIZE);
- .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
- __smp_locks = .;
- *(.smp_locks)
- __smp_locks_end = .;
- . = ALIGN(PAGE_SIZE);
- }
+ PERCPU_VADDR(0, :percpu)
+#endif
- /* Init code and data - will be freed after init */
- . = ALIGN(PAGE_SIZE);
.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
- __init_begin = .; /* paired with __init_end */
_sinittext = .;
INIT_TEXT
_einittext = .;
}
+#ifdef CONFIG_X86_64
+ :init
+#endif
.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
INIT_DATA
}
#endif
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
- /*
- * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
- * output PHDR, so the next output section - __data_nosave - should
- * start another section data.init2. Also, pda should be at the head of
- * percpu area. Preallocate it and define the percpu offset symbol
- * so that it can be accessed as a percpu variable.
- */
- . = ALIGN(PAGE_SIZE);
- PERCPU_VADDR(0, :percpu)
-#else
+#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
PERCPU(PAGE_SIZE)
#endif
__init_end = .;
}
+ /*
+ * smp_locks might be freed after init
+ * start/end must be page aligned
+ */
+ . = ALIGN(PAGE_SIZE);
+ .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
+ __smp_locks = .;
+ *(.smp_locks)
+ __smp_locks_end = .;
+ . = ALIGN(PAGE_SIZE);
+ }
+
#ifdef CONFIG_X86_64
.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __nosave_begin = .;
- *(.data.nosave)
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
- } :data.init2
- /* use another section data.init2, see PERCPU_VADDR() above */
+ NOSAVE_DATA
+ }
#endif
/* BSS */
_end = .;
}
- /* Sections to be discarded */
- /DISCARD/ : {
- *(.exitcall.exit)
- *(.eh_frame)
- *(.discard)
- }
-
STABS_DEBUG
DWARF_DEBUG
+
+ /* Sections to be discarded */
+ DISCARDS
+ /DISCARD/ : { *(.eh_frame) }
}
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/pfn.h>
+ #include <linux/percpu.h>
#include <asm/e820.h>
#include <asm/processor.h>
{
struct cpa_data alias_cpa;
unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT);
- unsigned long vaddr, remapped;
+ unsigned long vaddr;
int ret;
if (cpa->pfn >= max_pfn_mapped)
}
#endif
- /*
- * If the PMD page was partially used for per-cpu remapping,
- * the recycled area needs to be split and modified. Because
- * the area is always proper subset of a PMD page
- * cpa->numpages is guaranteed to be 1 for these areas, so
- * there's no need to loop over and check for further remaps.
- */
- remapped = (unsigned long)pcpu_lpage_remapped((void *)laddr);
- if (remapped) {
- WARN_ON(cpa->numpages > 1);
- alias_cpa = *cpa;
- alias_cpa.vaddr = &remapped;
- alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
- ret = __change_page_attr_set_clr(&alias_cpa, 0);
- if (ret)
- return ret;
- }
-
return 0;
}
{
struct cpa_data cpa;
int ret, cache, checkalias;
+ unsigned long baddr = 0;
/*
* Check, if we are requested to change a not supported
*/
WARN_ON_ONCE(1);
}
+ /*
+ * Save address for cache flush. *addr is modified in the call
+ * to __change_page_attr_set_clr() below.
+ */
+ baddr = *addr;
}
/* Must avoid aliasing mappings in the highmem code */
cpa_flush_array(addr, numpages, cache,
cpa.flags, pages);
} else
- cpa_flush_range(*addr, numpages, cache);
+ cpa_flush_range(baddr, numpages, cache);
} else
cpa_flush_all(cache);
static struct kmem_cache *cfq_pool;
static struct kmem_cache *cfq_ioc_pool;
- static DEFINE_PER_CPU(unsigned long, ioc_count);
+ static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
static struct completion *ioc_gone;
static DEFINE_SPINLOCK(ioc_gone_lock);
struct rb_root prio_trees[CFQ_PRIO_LISTS];
unsigned int busy_queues;
- /*
- * Used to track any pending rt requests so we can pre-empt current
- * non-RT cfqq in service when this value is non-zero.
- */
- unsigned int busy_rt_queues;
- int rq_in_driver;
+ int rq_in_driver[2];
int sync_flight;
/*
CFQ_CFQQ_FLAG_on_rr = 0, /* on round-robin busy list */
CFQ_CFQQ_FLAG_wait_request, /* waiting for a request */
CFQ_CFQQ_FLAG_must_dispatch, /* must be allowed a dispatch */
- CFQ_CFQQ_FLAG_must_alloc, /* must be allowed rq alloc */
CFQ_CFQQ_FLAG_must_alloc_slice, /* per-slice must_alloc flag */
CFQ_CFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */
CFQ_CFQQ_FLAG_idle_window, /* slice idling enabled */
CFQ_CFQQ_FNS(on_rr);
CFQ_CFQQ_FNS(wait_request);
CFQ_CFQQ_FNS(must_dispatch);
-CFQ_CFQQ_FNS(must_alloc);
CFQ_CFQQ_FNS(must_alloc_slice);
CFQ_CFQQ_FNS(fifo_expire);
CFQ_CFQQ_FNS(idle_window);
static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
struct io_context *);
+static inline int rq_in_driver(struct cfq_data *cfqd)
+{
+ return cfqd->rq_in_driver[0] + cfqd->rq_in_driver[1];
+}
+
static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
int is_sync)
{
*/
static inline int cfq_bio_sync(struct bio *bio)
{
- if (bio_data_dir(bio) == READ || bio_sync(bio))
+ if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO))
return 1;
return 0;
BUG_ON(cfq_cfqq_on_rr(cfqq));
cfq_mark_cfqq_on_rr(cfqq);
cfqd->busy_queues++;
- if (cfq_class_rt(cfqq))
- cfqd->busy_rt_queues++;
cfq_resort_rr_list(cfqd, cfqq);
}
BUG_ON(!cfqd->busy_queues);
cfqd->busy_queues--;
- if (cfq_class_rt(cfqq))
- cfqd->busy_rt_queues--;
}
/*
{
struct cfq_data *cfqd = q->elevator->elevator_data;
- cfqd->rq_in_driver++;
+ cfqd->rq_in_driver[rq_is_sync(rq)]++;
cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
- cfqd->rq_in_driver);
+ rq_in_driver(cfqd));
cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
}
static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
+ const int sync = rq_is_sync(rq);
- WARN_ON(!cfqd->rq_in_driver);
- cfqd->rq_in_driver--;
+ WARN_ON(!cfqd->rq_in_driver[sync]);
+ cfqd->rq_in_driver[sync]--;
cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
- cfqd->rq_in_driver);
+ rq_in_driver(cfqd));
}
static void cfq_remove_request(struct request *rq)
/*
* still requests with the driver, don't idle
*/
- if (cfqd->rq_in_driver)
+ if (rq_in_driver(cfqd))
return;
/*
cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");
+ cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
cfq_remove_request(rq);
cfqq->dispatched++;
elv_dispatch_sort(q, rq);
if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
goto expire;
- /*
- * If we have a RT cfqq waiting, then we pre-empt the current non-rt
- * cfqq.
- */
- if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
- /*
- * We simulate this as cfqq timed out so that it gets to bank
- * the remaining of its time slice.
- */
- cfq_log_cfqq(cfqd, cfqq, "preempt");
- cfq_slice_expired(cfqd, 1);
- goto new_queue;
- }
-
/*
* The active queue has requests and isn't expired, allow it to
* dispatch.
if (!cfqq)
return 0;
+ /*
+ * Drain async requests before we start sync IO
+ */
+ if (cfq_cfqq_idle_window(cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
+ return 0;
+
/*
* If this is an async queue and we have sync IO in flight, let it wait
*/
cfq_slice_expired(cfqd, 0);
}
- cfq_log(cfqd, "dispatched a request");
+ cfq_log_cfqq(cfqd, cfqq, "dispatched a request");
return 1;
}
cic = container_of(head, struct cfq_io_context, rcu_head);
kmem_cache_free(cfq_ioc_pool, cic);
- elv_ioc_count_dec(ioc_count);
+ elv_ioc_count_dec(cfq_ioc_count);
if (ioc_gone) {
/*
* complete ioc_gone and set it back to NULL
*/
spin_lock(&ioc_gone_lock);
- if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+ if (ioc_gone && !elv_ioc_count_read(cfq_ioc_count)) {
complete(ioc_gone);
ioc_gone = NULL;
}
INIT_HLIST_NODE(&cic->cic_list);
cic->dtor = cfq_free_io_context;
cic->exit = cfq_exit_io_context;
- elv_ioc_count_inc(ioc_count);
+ elv_ioc_count_inc(cfq_ioc_count);
}
return cic;
*/
static void cfq_update_hw_tag(struct cfq_data *cfqd)
{
- if (cfqd->rq_in_driver > cfqd->rq_in_driver_peak)
- cfqd->rq_in_driver_peak = cfqd->rq_in_driver;
+ if (rq_in_driver(cfqd) > cfqd->rq_in_driver_peak)
+ cfqd->rq_in_driver_peak = rq_in_driver(cfqd);
if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
- cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
+ rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
return;
if (cfqd->hw_tag_samples++ < 50)
cfq_update_hw_tag(cfqd);
- WARN_ON(!cfqd->rq_in_driver);
+ WARN_ON(!cfqd->rq_in_driver[sync]);
WARN_ON(!cfqq->dispatched);
- cfqd->rq_in_driver--;
+ cfqd->rq_in_driver[sync]--;
cfqq->dispatched--;
if (cfq_cfqq_sync(cfqq))
cfq_arm_slice_timer(cfqd);
}
- if (!cfqd->rq_in_driver)
+ if (!rq_in_driver(cfqd))
cfq_schedule_dispatch(cfqd);
}
static inline int __cfq_may_queue(struct cfq_queue *cfqq)
{
- if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
- !cfq_cfqq_must_alloc_slice(cfqq)) {
+ if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
cfq_mark_cfqq_must_alloc_slice(cfqq);
return ELV_MQUEUE_MUST;
}
}
cfqq->allocated[rw]++;
- cfq_clear_cfqq_must_alloc(cfqq);
atomic_inc(&cfqq->ref);
spin_unlock_irqrestore(q->queue_lock, flags);
* this also protects us from entering cfq_slab_kill() with
* pending RCU callbacks
*/
- if (elv_ioc_count_read(ioc_count))
+ if (elv_ioc_count_read(cfq_ioc_count))
wait_for_completion(&all_gone);
cfq_slab_kill();
}
/*
* Base implementations of per-CPU variable declarations and definitions, where
* the section in which the variable is to be placed is provided by the
- * 'section' argument. This may be used to affect the parameters governing the
+ * 'sec' argument. This may be used to affect the parameters governing the
* variable's storage.
*
* NOTE! The sections for the DECLARE and for the DEFINE must match, lest
* linkage errors occur due the compiler generating the wrong code to access
* that section.
*/
- #define DECLARE_PER_CPU_SECTION(type, name, section) \
- extern \
- __attribute__((__section__(PER_CPU_BASE_SECTION section))) \
- PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-
- #define DEFINE_PER_CPU_SECTION(type, name, section) \
- __attribute__((__section__(PER_CPU_BASE_SECTION section))) \
- PER_CPU_ATTRIBUTES PER_CPU_DEF_ATTRIBUTES \
+ #define __PCPU_ATTRS(sec) \
+ __attribute__((section(PER_CPU_BASE_SECTION sec))) \
+ PER_CPU_ATTRIBUTES
+
+ #define __PCPU_DUMMY_ATTRS \
+ __attribute__((section(".discard"), unused))
+
+ /*
+ * s390 and alpha modules require percpu variables to be defined as
+ * weak to force the compiler to generate GOT based external
+ * references for them. This is necessary because percpu sections
+ * will be located outside of the usually addressable area.
+ *
+ * This definition puts the following two extra restrictions when
+ * defining percpu variables.
+ *
+ * 1. The symbol must be globally unique, even the static ones.
+ * 2. Static percpu variables cannot be defined inside a function.
+ *
+ * Archs which need weak percpu definitions should define
+ * ARCH_NEEDS_WEAK_PER_CPU in asm/percpu.h when necessary.
+ *
+ * To ensure that the generic code observes the above two
+ * restrictions, if CONFIG_DEBUG_FORCE_WEAK_PER_CPU is set weak
+ * definition is used for all cases.
+ */
+ #if defined(ARCH_NEEDS_WEAK_PER_CPU) || defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU)
+ /*
+ * __pcpu_scope_* dummy variable is used to enforce scope. It
+ * receives the static modifier when it's used in front of
+ * DEFINE_PER_CPU() and will trigger build failure if
+ * DECLARE_PER_CPU() is used for the same variable.
+ *
+ * __pcpu_unique_* dummy variable is used to enforce symbol uniqueness
+ * such that hidden weak symbol collision, which will cause unrelated
+ * variables to share the same address, can be detected during build.
+ */
+ #define DECLARE_PER_CPU_SECTION(type, name, sec) \
+ extern __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \
+ extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name
+
+ #define DEFINE_PER_CPU_SECTION(type, name, sec) \
+ __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \
+ __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \
+ __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \
+ __typeof__(type) per_cpu__##name
+ #else
+ /*
+ * Normal declaration and definition macros.
+ */
+ #define DECLARE_PER_CPU_SECTION(type, name, sec) \
+ extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name
+
+ #define DEFINE_PER_CPU_SECTION(type, name, sec) \
+ __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \
__typeof__(type) per_cpu__##name
+ #endif
/*
* Variant on the per-CPU variable declaration/definition theme used for
DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
+#define DECLARE_PER_CPU_ALIGNED(type, name) \
+ DECLARE_PER_CPU_SECTION(type, name, PER_CPU_ALIGNED_SECTION) \
+ ____cacheline_aligned
+
+#define DEFINE_PER_CPU_ALIGNED(type, name) \
+ DEFINE_PER_CPU_SECTION(type, name, PER_CPU_ALIGNED_SECTION) \
+ ____cacheline_aligned
+
/*
* Declaration/definition used for per-CPU variables that must be page aligned.
*/
-#define DECLARE_PER_CPU_PAGE_ALIGNED(type, name) \
- DECLARE_PER_CPU_SECTION(type, name, ".page_aligned")
+#define DECLARE_PER_CPU_PAGE_ALIGNED(type, name) \
+ DECLARE_PER_CPU_SECTION(type, name, ".page_aligned") \
+ __aligned(PAGE_SIZE)
#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \
- DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
+ DEFINE_PER_CPU_SECTION(type, name, ".page_aligned") \
+ __aligned(PAGE_SIZE)
/*
* Intermodule exports for per-CPU variables.
#define smp_init() do { } while (0)
#endif
- static inline void setup_per_cpu_areas(void) { }
static inline void setup_nr_cpu_ids(void) { }
static inline void smp_prepare_cpus(unsigned int maxcpus) { }
nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
}
- #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
- unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-
- EXPORT_SYMBOL(__per_cpu_offset);
-
- static void __init setup_per_cpu_areas(void)
- {
- unsigned long size, i;
- char *ptr;
- unsigned long nr_possible_cpus = num_possible_cpus();
-
- /* Copy section for each CPU (we discard the original) */
- size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
- ptr = alloc_bootmem_pages(size * nr_possible_cpus);
-
- for_each_possible_cpu(i) {
- __per_cpu_offset[i] = ptr - __per_cpu_start;
- memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
- ptr += size;
- }
- }
- #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
-
/* Called by boot processor to activate the rest. */
static void __init smp_init(void)
{
{
int pid;
+ rcu_scheduler_starting();
kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
numa_default_policy();
pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
* at least once to get things moving:
*/
init_idle_bootup_task(current);
- rcu_scheduler_starting();
preempt_enable_no_resched();
schedule();
preempt_disable();
softirq_init();
timekeeping_init();
time_init();
- sched_clock_init();
profile_init();
if (!irqs_disabled())
printk(KERN_CRIT "start_kernel(): bug: interrupts were "
numa_policy_init();
if (late_time_init)
late_time_init();
+ sched_clock_init();
calibrate_delay();
pidmap_init();
anon_vma_init();
int initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
+static char msgbuf[64];
+static struct boot_trace_call call;
+static struct boot_trace_ret ret;
+
int do_one_initcall(initcall_t fn)
{
int count = preempt_count();
ktime_t calltime, delta, rettime;
- char msgbuf[64];
- struct boot_trace_call call;
- struct boot_trace_ret ret;
if (initcall_debug) {
call.caller = task_pid_nr(current);
#include <linux/percpu.h>
#include <linux/kmemleak.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/module.h>
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
#if 0
#define DEBUGP printk
#else
#ifdef CONFIG_SMP
- #ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+ #ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
static void *percpu_modalloc(unsigned long size, unsigned long align,
const char *name)
free_percpu(freeme);
}
- #else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+ #else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
/* Number of blocks used and allocated. */
static unsigned int pcpu_num_used, pcpu_num_allocated;
}
__initcall(percpu_modinit);
- #endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+ #endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
static unsigned int find_pcpusec(Elf_Ehdr *hdr,
Elf_Shdr *sechdrs,
}
EXPORT_SYMBOL(__symbol_put);
+/* Note this assumes addr is a function, which it currently always is. */
void symbol_put_addr(void *addr)
{
struct module *modaddr;
+ unsigned long a = (unsigned long)dereference_function_descriptor(addr);
- if (core_kernel_text((unsigned long)addr))
+ if (core_kernel_text(a))
return;
/* module_text_address is safe here: we're supposed to have reference
* to module from symbol_get, so it can't go away. */
- modaddr = __module_text_address((unsigned long)addr);
+ modaddr = __module_text_address(a);
BUG_ON(!modaddr);
module_put(modaddr);
}
if (module) {
unsigned int cpu = get_cpu();
local_dec(__module_ref_addr(module, cpu));
+ trace_module_put(module, _RET_IP_,
+ local_read(__module_ref_addr(module, cpu)));
/* Maybe they're waiting for us to drop reference? */
if (unlikely(!module_is_live(module)))
wake_up_process(module->waiter);
struct module_notes_attrs *notes_attrs;
struct bin_attribute *nattr;
+ /* failed to create section attributes, so can't create notes */
+ if (!mod->sect_attrs)
+ return;
+
/* Count notes sections and allocate structures. */
notes = 0;
for (i = 0; i < nsect; i++)
/* Free a module, remove from lists, etc (must hold module_mutex). */
static void free_module(struct module *mod)
{
+ trace_module_free(mod);
+
/* Delete from various lists */
stop_machine(__unlink_module, mod, NULL);
remove_notes_attrs(mod);
/* Get rid of temporary copy */
vfree(hdr);
+ trace_module_load(mod);
+
/* Done! */
return mod;
/*
* perf counter paranoia level:
- * 0 - not paranoid
- * 1 - disallow cpu counters to unpriv
- * 2 - disallow kernel profiling to unpriv
+ * -1 - not paranoid at all
+ * 0 - disallow raw tracepoint access for unpriv
+ * 1 - disallow cpu counters for unpriv
+ * 2 - disallow kernel profiling for unpriv
*/
-int sysctl_perf_counter_paranoid __read_mostly;
+int sysctl_perf_counter_paranoid __read_mostly = 1;
+
+static inline bool perf_paranoid_tracepoint_raw(void)
+{
+ return sysctl_perf_counter_paranoid > -1;
+}
static inline bool perf_paranoid_cpu(void)
{
void __weak perf_counter_print_debug(void) { }
- static DEFINE_PER_CPU(int, disable_count);
+ static DEFINE_PER_CPU(int, perf_disable_count);
void __perf_disable(void)
{
- __get_cpu_var(disable_count)++;
+ __get_cpu_var(perf_disable_count)++;
}
bool __perf_enable(void)
{
- return !--__get_cpu_var(disable_count);
+ return !--__get_cpu_var(perf_disable_count);
}
void perf_disable(void)
struct perf_counter_context *ctx = counter->ctx;
u64 run_end;
- if (counter->state < PERF_COUNTER_STATE_INACTIVE)
+ if (counter->state < PERF_COUNTER_STATE_INACTIVE ||
+ counter->group_leader->state < PERF_COUNTER_STATE_INACTIVE)
return;
counter->total_time_enabled = ctx->time - counter->tstamp_enabled;
*/
if (counter->state >= PERF_COUNTER_STATE_INACTIVE) {
update_context_time(ctx);
- update_counter_times(counter);
+ update_group_times(counter);
if (counter == counter->group_leader)
group_sched_out(counter, cpuctx, ctx);
else
* in, so we can change the state safely.
*/
if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
- update_counter_times(counter);
+ update_group_times(counter);
counter->state = PERF_COUNTER_STATE_OFF;
}
spin_unlock_irq(&ctx->lock);
}
+/*
+ * Put a counter into inactive state and update time fields.
+ * Enabling the leader of a group effectively enables all
+ * the group members that aren't explicitly disabled, so we
+ * have to update their ->tstamp_enabled also.
+ * Note: this works for group members as well as group leaders
+ * since the non-leader members' sibling_lists will be empty.
+ */
+static void __perf_counter_mark_enabled(struct perf_counter *counter,
+ struct perf_counter_context *ctx)
+{
+ struct perf_counter *sub;
+
+ counter->state = PERF_COUNTER_STATE_INACTIVE;
+ counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+ list_for_each_entry(sub, &counter->sibling_list, list_entry)
+ if (sub->state >= PERF_COUNTER_STATE_INACTIVE)
+ sub->tstamp_enabled =
+ ctx->time - sub->total_time_enabled;
+}
+
/*
* Cross CPU call to enable a performance counter
*/
if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
goto unlock;
- counter->state = PERF_COUNTER_STATE_INACTIVE;
- counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+ __perf_counter_mark_enabled(counter, ctx);
/*
* If the counter is in a group and isn't the group leader,
* Since we have the lock this context can't be scheduled
* in, so we can change the state safely.
*/
- if (counter->state == PERF_COUNTER_STATE_OFF) {
- counter->state = PERF_COUNTER_STATE_INACTIVE;
- counter->tstamp_enabled =
- ctx->time - counter->total_time_enabled;
- }
+ if (counter->state == PERF_COUNTER_STATE_OFF)
+ __perf_counter_mark_enabled(counter, ctx);
+
out:
spin_unlock_irq(&ctx->lock);
}
counter->attr.enable_on_exec = 0;
if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
continue;
- counter->state = PERF_COUNTER_STATE_INACTIVE;
- counter->tstamp_enabled =
- ctx->time - counter->total_time_enabled;
+ __perf_counter_mark_enabled(counter, ctx);
enabled = 1;
}
*/
static void __perf_counter_read(void *info)
{
+ struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
struct perf_counter *counter = info;
struct perf_counter_context *ctx = counter->ctx;
unsigned long flags;
+ /*
+ * 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. In that case
+ * counter->count would have been updated to a recent sample
+ * when the counter was scheduled out.
+ */
+ if (ctx->task && cpuctx->task_ctx != ctx)
+ return;
+
local_irq_save(flags);
if (ctx->is_active)
update_context_time(ctx);
atomic_dec(&nr_task_counters);
}
+ if (counter->output) {
+ fput(counter->output->filp);
+ counter->output = NULL;
+ }
+
if (counter->destroy)
counter->destroy(counter);
size += err;
list_for_each_entry(sub, &leader->sibling_list, list_entry) {
- err = perf_counter_read_entry(counter, read_format,
+ err = perf_counter_read_entry(sub, read_format,
buf + size);
if (err < 0)
return err;
return ret;
}
+int perf_counter_set_output(struct perf_counter *counter, int output_fd);
+
static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct perf_counter *counter = file->private_data;
case PERF_COUNTER_IOC_PERIOD:
return perf_counter_period(counter, (u64 __user *)arg);
+ case PERF_COUNTER_IOC_SET_OUTPUT:
+ return perf_counter_set_output(counter, arg);
+
default:
return -ENOTTY;
}
return 0;
}
+#ifndef PERF_COUNTER_INDEX_OFFSET
+# define PERF_COUNTER_INDEX_OFFSET 0
+#endif
+
static int perf_counter_index(struct perf_counter *counter)
{
if (counter->state != PERF_COUNTER_STATE_ACTIVE)
WARN_ON_ONCE(counter->ctx->parent_ctx);
mutex_lock(&counter->mmap_mutex);
+ if (counter->output) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+
if (atomic_inc_not_zero(&counter->mmap_count)) {
if (nr_pages != counter->data->nr_pages)
ret = -EINVAL;
struct perf_counter *counter, unsigned int size,
int nmi, int sample)
{
+ struct perf_counter *output_counter;
struct perf_mmap_data *data;
unsigned int offset, head;
int have_lost;
u64 lost;
} lost_event;
+ rcu_read_lock();
/*
* For inherited counters we send all the output towards the parent.
*/
if (counter->parent)
counter = counter->parent;
- rcu_read_lock();
+ output_counter = rcu_dereference(counter->output);
+ if (output_counter)
+ counter = output_counter;
+
data = rcu_dereference(counter->data);
if (!data)
goto out;
* have these.
*/
if ((counter->attr.sample_type & PERF_SAMPLE_RAW) &&
+ perf_paranoid_tracepoint_raw() &&
!capable(CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
hwc->sample_period = attr->sample_period;
if (attr->freq && attr->sample_freq)
hwc->sample_period = 1;
+ hwc->last_period = hwc->sample_period;
atomic64_set(&hwc->period_left, hwc->sample_period);
if (val)
goto err_size;
}
+ size = sizeof(*attr);
}
ret = copy_from_user(attr, uattr, size);
goto out;
}
+int perf_counter_set_output(struct perf_counter *counter, int output_fd)
+{
+ struct perf_counter *output_counter = NULL;
+ struct file *output_file = NULL;
+ struct perf_counter *old_output;
+ int fput_needed = 0;
+ int ret = -EINVAL;
+
+ if (!output_fd)
+ goto set;
+
+ output_file = fget_light(output_fd, &fput_needed);
+ if (!output_file)
+ return -EBADF;
+
+ if (output_file->f_op != &perf_fops)
+ goto out;
+
+ output_counter = output_file->private_data;
+
+ /* Don't chain output fds */
+ if (output_counter->output)
+ goto out;
+
+ /* Don't set an output fd when we already have an output channel */
+ if (counter->data)
+ goto out;
+
+ atomic_long_inc(&output_file->f_count);
+
+set:
+ mutex_lock(&counter->mmap_mutex);
+ old_output = counter->output;
+ rcu_assign_pointer(counter->output, output_counter);
+ mutex_unlock(&counter->mmap_mutex);
+
+ if (old_output) {
+ /*
+ * we need to make sure no existing perf_output_*()
+ * is still referencing this counter.
+ */
+ synchronize_rcu();
+ fput(old_output->filp);
+ }
+
+ ret = 0;
+out:
+ fput_light(output_file, fput_needed);
+ return ret;
+}
+
/**
* sys_perf_counter_open - open a performance counter, associate it to a task/cpu
*
struct file *group_file = NULL;
int fput_needed = 0;
int fput_needed2 = 0;
- int ret;
+ int err;
/* for future expandability... */
- if (flags)
+ if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
return -EINVAL;
- ret = perf_copy_attr(attr_uptr, &attr);
- if (ret)
- return ret;
+ err = perf_copy_attr(attr_uptr, &attr);
+ if (err)
+ return err;
if (!attr.exclude_kernel) {
if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
* Look up the group leader (we will attach this counter to it):
*/
group_leader = NULL;
- if (group_fd != -1) {
- ret = -EINVAL;
+ if (group_fd != -1 && !(flags & PERF_FLAG_FD_NO_GROUP)) {
+ err = -EINVAL;
group_file = fget_light(group_fd, &fput_needed);
if (!group_file)
goto err_put_context;
counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
NULL, GFP_KERNEL);
- ret = PTR_ERR(counter);
+ err = PTR_ERR(counter);
if (IS_ERR(counter))
goto err_put_context;
- ret = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
- if (ret < 0)
+ err = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
+ if (err < 0)
goto err_free_put_context;
- counter_file = fget_light(ret, &fput_needed2);
+ counter_file = fget_light(err, &fput_needed2);
if (!counter_file)
goto err_free_put_context;
+ if (flags & PERF_FLAG_FD_OUTPUT) {
+ err = perf_counter_set_output(counter, group_fd);
+ if (err)
+ goto err_fput_free_put_context;
+ }
+
counter->filp = counter_file;
WARN_ON_ONCE(ctx->parent_ctx);
mutex_lock(&ctx->mutex);
list_add_tail(&counter->owner_entry, ¤t->perf_counter_list);
mutex_unlock(¤t->perf_counter_mutex);
+err_fput_free_put_context:
fput_light(counter_file, fput_needed2);
-out_fput:
- fput_light(group_file, fput_needed);
-
- return ret;
-
err_free_put_context:
- kfree(counter);
+ if (err < 0)
+ kfree(counter);
err_put_context:
- put_ctx(ctx);
+ if (err < 0)
+ put_ctx(ctx);
+
+ fput_light(group_file, fput_needed);
- goto out_fput;
+ return err;
}
/*
#include <linux/tsacct_kern.h>
#include <linux/kprobes.h>
#include <linux/delayacct.h>
-#include <linux/reciprocal_div.h>
#include <linux/unistd.h>
#include <linux/pagemap.h>
#include <linux/hrtimer.h>
*/
#define RUNTIME_INF ((u64)~0ULL)
-#ifdef CONFIG_SMP
-
static void double_rq_lock(struct rq *rq1, struct rq *rq2);
-/*
- * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
- * Since cpu_power is a 'constant', we can use a reciprocal divide.
- */
-static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
-{
- return reciprocal_divide(load, sg->reciprocal_cpu_power);
-}
-
-/*
- * Each time a sched group cpu_power is changed,
- * we must compute its reciprocal value
- */
-static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
-{
- sg->__cpu_power += val;
- sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
-}
-#endif
-
static inline int rt_policy(int policy)
{
if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
/*
* Root task group.
- * Every UID task group (including init_task_group aka UID-0) will
- * be a child to this group.
+ * Every UID task group (including init_task_group aka UID-0) will
+ * be a child to this group.
*/
struct task_group root_task_group;
/* Default task group's sched entity on each cpu */
static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
/* Default task group's cfs_rq on each cpu */
- static DEFINE_PER_CPU(struct cfs_rq, init_tg_cfs_rq) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_cfs_rq);
++static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
- static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
+ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
#endif /* CONFIG_RT_GROUP_SCHED */
#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
unsigned char idle_at_tick;
/* For active balancing */
+ int post_schedule;
int active_balance;
int push_cpu;
/* cpu of this runqueue: */
struct task_struct *migration_thread;
struct list_head migration_queue;
+
+ u64 rt_avg;
+ u64 age_stamp;
#endif
/* calc_load related fields */
#define this_rq() (&__get_cpu_var(runqueues))
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
+#define raw_rq() (&__raw_get_cpu_var(runqueues))
inline void update_rq_clock(struct rq *rq)
{
*/
unsigned int sysctl_sched_shares_thresh = 4;
+/*
+ * period over which we average the RT time consumption, measured
+ * in ms.
+ *
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
+
/*
* period over which we measure -rt task cpu usage in us.
* default: 1s
}
#endif /* CONFIG_NO_HZ */
+static u64 sched_avg_period(void)
+{
+ return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
+}
+
+static void sched_avg_update(struct rq *rq)
+{
+ s64 period = sched_avg_period();
+
+ while ((s64)(rq->clock - rq->age_stamp) > period) {
+ rq->age_stamp += period;
+ rq->rt_avg /= 2;
+ }
+}
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+ rq->rt_avg += rt_delta;
+ sched_avg_update(rq);
+}
+
#else /* !CONFIG_SMP */
static void resched_task(struct task_struct *p)
{
assert_spin_locked(&task_rq(p)->lock);
set_tsk_need_resched(p);
}
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+}
#endif /* CONFIG_SMP */
#if BITS_PER_LONG == 32
#ifdef CONFIG_FAIR_GROUP_SCHED
+struct update_shares_data {
+ unsigned long rq_weight[NR_CPUS];
+};
+
+static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
/*
* Calculate and set the cpu's group shares.
*/
-static void
-update_group_shares_cpu(struct task_group *tg, int cpu,
- unsigned long sd_shares, unsigned long sd_rq_weight)
+static void update_group_shares_cpu(struct task_group *tg, int cpu,
+ unsigned long sd_shares,
+ unsigned long sd_rq_weight,
+ struct update_shares_data *usd)
{
- unsigned long shares;
- unsigned long rq_weight;
-
- if (!tg->se[cpu])
- return;
+ unsigned long shares, rq_weight;
+ int boost = 0;
- rq_weight = tg->cfs_rq[cpu]->rq_weight;
+ rq_weight = usd->rq_weight[cpu];
+ if (!rq_weight) {
+ boost = 1;
+ rq_weight = NICE_0_LOAD;
+ }
/*
- * \Sum shares * rq_weight
- * shares = -----------------------
- * \Sum rq_weight
- *
+ * \Sum_j shares_j * rq_weight_i
+ * shares_i = -----------------------------
+ * \Sum_j rq_weight_j
*/
shares = (sd_shares * rq_weight) / sd_rq_weight;
shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
unsigned long flags;
spin_lock_irqsave(&rq->lock, flags);
- tg->cfs_rq[cpu]->shares = shares;
-
+ tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
+ tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
__set_se_shares(tg->se[cpu], shares);
spin_unlock_irqrestore(&rq->lock, flags);
}
*/
static int tg_shares_up(struct task_group *tg, void *data)
{
- unsigned long weight, rq_weight = 0;
- unsigned long shares = 0;
+ unsigned long weight, rq_weight = 0, shares = 0;
+ struct update_shares_data *usd;
struct sched_domain *sd = data;
+ unsigned long flags;
int i;
+ if (!tg->se[0])
+ return 0;
+
+ local_irq_save(flags);
+ usd = &__get_cpu_var(update_shares_data);
+
for_each_cpu(i, sched_domain_span(sd)) {
+ weight = tg->cfs_rq[i]->load.weight;
+ usd->rq_weight[i] = weight;
+
/*
* If there are currently no tasks on the cpu pretend there
* is one of average load so that when a new task gets to
* run here it will not get delayed by group starvation.
*/
- weight = tg->cfs_rq[i]->load.weight;
if (!weight)
weight = NICE_0_LOAD;
- tg->cfs_rq[i]->rq_weight = weight;
rq_weight += weight;
shares += tg->cfs_rq[i]->shares;
}
shares = tg->shares;
for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight);
+ update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+
+ local_irq_restore(flags);
return 0;
}
static void update_shares(struct sched_domain *sd)
{
- u64 now = cpu_clock(raw_smp_processor_id());
- s64 elapsed = now - sd->last_update;
+ s64 elapsed;
+ u64 now;
+
+ if (root_task_group_empty())
+ return;
+
+ now = cpu_clock(raw_smp_processor_id());
+ elapsed = now - sd->last_update;
if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
sd->last_update = now;
static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
{
+ if (root_task_group_empty())
+ return;
+
spin_unlock(&rq->lock);
update_shares(sd);
spin_lock(&rq->lock);
static void update_h_load(long cpu)
{
+ if (root_task_group_empty())
+ return;
+
walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
}
}
/* Adjust by relative CPU power of the group */
- avg_load = sg_div_cpu_power(group,
- avg_load * SCHED_LOAD_SCALE);
+ avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
if (local_group) {
this_load = avg_load;
set_task_cpu(p, cpu);
/*
- * Make sure we do not leak PI boosting priority to the child:
+ * Make sure we do not leak PI boosting priority to the child.
*/
p->prio = current->normal_prio;
+
+ /*
+ * Revert to default priority/policy on fork if requested.
+ */
+ if (unlikely(p->sched_reset_on_fork)) {
+ if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+ p->policy = SCHED_NORMAL;
+
+ if (p->normal_prio < DEFAULT_PRIO)
+ p->prio = DEFAULT_PRIO;
+
+ if (PRIO_TO_NICE(p->static_prio) < 0) {
+ p->static_prio = NICE_TO_PRIO(0);
+ set_load_weight(p);
+ }
+
+ /*
+ * We don't need the reset flag anymore after the fork. It has
+ * fulfilled its duty:
+ */
+ p->sched_reset_on_fork = 0;
+ }
+
if (!rt_prio(p->prio))
p->sched_class = &fair_sched_class;
{
struct mm_struct *mm = rq->prev_mm;
long prev_state;
-#ifdef CONFIG_SMP
- int post_schedule = 0;
-
- if (current->sched_class->needs_post_schedule)
- post_schedule = current->sched_class->needs_post_schedule(rq);
-#endif
rq->prev_mm = NULL;
finish_arch_switch(prev);
perf_counter_task_sched_in(current, cpu_of(rq));
finish_lock_switch(rq, prev);
-#ifdef CONFIG_SMP
- if (post_schedule)
- current->sched_class->post_schedule(rq);
-#endif
fire_sched_in_preempt_notifiers(current);
if (mm)
}
}
+#ifdef CONFIG_SMP
+
+/* assumes rq->lock is held */
+static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
+{
+ if (prev->sched_class->pre_schedule)
+ prev->sched_class->pre_schedule(rq, prev);
+}
+
+/* rq->lock is NOT held, but preemption is disabled */
+static inline void post_schedule(struct rq *rq)
+{
+ if (rq->post_schedule) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&rq->lock, flags);
+ if (rq->curr->sched_class->post_schedule)
+ rq->curr->sched_class->post_schedule(rq);
+ spin_unlock_irqrestore(&rq->lock, flags);
+
+ rq->post_schedule = 0;
+ }
+}
+
+#else
+
+static inline void pre_schedule(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline void post_schedule(struct rq *rq)
+{
+}
+
+#endif
+
/**
* schedule_tail - first thing a freshly forked thread must call.
* @prev: the thread we just switched away from.
struct rq *rq = this_rq();
finish_task_switch(rq, prev);
+
+ /*
+ * FIXME: do we need to worry about rq being invalidated by the
+ * task_switch?
+ */
+ post_schedule(rq);
+
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
/* In this case, finish_task_switch does not reenable preemption */
preempt_enable();
{
const struct sched_class *class;
- for (class = sched_class_highest; class; class = class->next)
+ for_each_class(class) {
if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
return 1;
+ }
return 0;
}
* capacity but still has some space to pick up some load
* from other group and save more power
*/
- if (sgs->sum_nr_running > sgs->group_capacity - 1)
+ if (sgs->sum_nr_running + 1 > sgs->group_capacity)
return;
if (sgs->sum_nr_running > sds->leader_nr_running ||
}
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+ unsigned long weight = cpumask_weight(sched_domain_span(sd));
+ unsigned long smt_gain = sd->smt_gain;
+
+ smt_gain /= weight;
+
+ return smt_gain;
+}
+
+unsigned long scale_rt_power(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ u64 total, available;
+
+ sched_avg_update(rq);
+
+ total = sched_avg_period() + (rq->clock - rq->age_stamp);
+ available = total - rq->rt_avg;
+
+ if (unlikely((s64)total < SCHED_LOAD_SCALE))
+ total = SCHED_LOAD_SCALE;
+
+ total >>= SCHED_LOAD_SHIFT;
+
+ return div_u64(available, total);
+}
+
+static void update_cpu_power(struct sched_domain *sd, int cpu)
+{
+ unsigned long weight = cpumask_weight(sched_domain_span(sd));
+ unsigned long power = SCHED_LOAD_SCALE;
+ struct sched_group *sdg = sd->groups;
+
+ /* here we could scale based on cpufreq */
+
+ if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+ power *= arch_scale_smt_power(sd, cpu);
+ power >>= SCHED_LOAD_SHIFT;
+ }
+
+ power *= scale_rt_power(cpu);
+ power >>= SCHED_LOAD_SHIFT;
+
+ if (!power)
+ power = 1;
+
+ sdg->cpu_power = power;
+}
+
+static void update_group_power(struct sched_domain *sd, int cpu)
+{
+ struct sched_domain *child = sd->child;
+ struct sched_group *group, *sdg = sd->groups;
+ unsigned long power;
+
+ if (!child) {
+ update_cpu_power(sd, cpu);
+ return;
+ }
+
+ power = 0;
+
+ group = child->groups;
+ do {
+ power += group->cpu_power;
+ group = group->next;
+ } while (group != child->groups);
+
+ sdg->cpu_power = power;
+}
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
* @balance: Should we balance.
* @sgs: variable to hold the statistics for this group.
*/
-static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
+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,
int local_group, const struct cpumask *cpus,
int *balance, struct sg_lb_stats *sgs)
unsigned long sum_avg_load_per_task;
unsigned long avg_load_per_task;
- if (local_group)
+ if (local_group) {
balance_cpu = group_first_cpu(group);
+ if (balance_cpu == this_cpu)
+ update_group_power(sd, this_cpu);
+ }
/* Tally up the load of all CPUs in the group */
sum_avg_load_per_task = avg_load_per_task = 0;
}
/* Adjust by relative CPU power of the group */
- sgs->avg_load = sg_div_cpu_power(group,
- sgs->group_load * SCHED_LOAD_SCALE);
+ sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
/*
* normalized nr_running number somewhere that negates
* the hierarchy?
*/
- avg_load_per_task = sg_div_cpu_power(group,
- sum_avg_load_per_task * SCHED_LOAD_SCALE);
+ avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
+ group->cpu_power;
if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
sgs->group_imb = 1;
- sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
-
+ sgs->group_capacity =
+ DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
}
/**
const struct cpumask *cpus, int *balance,
struct sd_lb_stats *sds)
{
+ struct sched_domain *child = sd->child;
struct sched_group *group = sd->groups;
struct sg_lb_stats sgs;
- int load_idx;
+ int load_idx, prefer_sibling = 0;
+
+ if (child && child->flags & SD_PREFER_SIBLING)
+ prefer_sibling = 1;
init_sd_power_savings_stats(sd, sds, idle);
load_idx = get_sd_load_idx(sd, idle);
local_group = cpumask_test_cpu(this_cpu,
sched_group_cpus(group));
memset(&sgs, 0, sizeof(sgs));
- update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
+ update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
local_group, cpus, balance, &sgs);
if (local_group && balance && !(*balance))
return;
sds->total_load += sgs.group_load;
- sds->total_pwr += group->__cpu_power;
+ sds->total_pwr += group->cpu_power;
+
+ /*
+ * In case the child domain prefers tasks go to siblings
+ * first, lower the group capacity to one so that we'll try
+ * and move all the excess tasks away.
+ */
+ if (prefer_sibling)
+ sgs.group_capacity = min(sgs.group_capacity, 1UL);
if (local_group) {
sds->this_load = sgs.avg_load;
update_sd_power_savings_stats(group, sds, local_group, &sgs);
group = group->next;
} while (group != sd->groups);
-
}
/**
* moving them.
*/
- pwr_now += sds->busiest->__cpu_power *
+ pwr_now += sds->busiest->cpu_power *
min(sds->busiest_load_per_task, sds->max_load);
- pwr_now += sds->this->__cpu_power *
+ pwr_now += sds->this->cpu_power *
min(sds->this_load_per_task, sds->this_load);
pwr_now /= SCHED_LOAD_SCALE;
/* Amount of load we'd subtract */
- tmp = sg_div_cpu_power(sds->busiest,
- sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+ tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+ sds->busiest->cpu_power;
if (sds->max_load > tmp)
- pwr_move += sds->busiest->__cpu_power *
+ pwr_move += sds->busiest->cpu_power *
min(sds->busiest_load_per_task, sds->max_load - tmp);
/* Amount of load we'd add */
- if (sds->max_load * sds->busiest->__cpu_power <
+ if (sds->max_load * sds->busiest->cpu_power <
sds->busiest_load_per_task * SCHED_LOAD_SCALE)
- tmp = sg_div_cpu_power(sds->this,
- sds->max_load * sds->busiest->__cpu_power);
+ tmp = (sds->max_load * sds->busiest->cpu_power) /
+ sds->this->cpu_power;
else
- tmp = sg_div_cpu_power(sds->this,
- sds->busiest_load_per_task * SCHED_LOAD_SCALE);
- pwr_move += sds->this->__cpu_power *
+ tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+ sds->this->cpu_power;
+ pwr_move += sds->this->cpu_power *
min(sds->this_load_per_task, sds->this_load + tmp);
pwr_move /= SCHED_LOAD_SCALE;
sds->max_load - sds->busiest_load_per_task);
/* How much load to actually move to equalise the imbalance */
- *imbalance = min(max_pull * sds->busiest->__cpu_power,
- (sds->avg_load - sds->this_load) * sds->this->__cpu_power)
+ *imbalance = min(max_pull * sds->busiest->cpu_power,
+ (sds->avg_load - sds->this_load) * sds->this->cpu_power)
/ SCHED_LOAD_SCALE;
/*
return NULL;
}
+static struct sched_group *group_of(int cpu)
+{
+ struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd);
+
+ if (!sd)
+ return NULL;
+
+ return sd->groups;
+}
+
+static unsigned long power_of(int cpu)
+{
+ struct sched_group *group = group_of(cpu);
+
+ if (!group)
+ return SCHED_LOAD_SCALE;
+
+ return group->cpu_power;
+}
+
/*
* find_busiest_queue - find the busiest runqueue among the cpus in group.
*/
int i;
for_each_cpu(i, sched_group_cpus(group)) {
+ unsigned long power = power_of(i);
+ unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
unsigned long wl;
if (!cpumask_test_cpu(i, cpus))
continue;
rq = cpu_rq(i);
- wl = weighted_cpuload(i);
+ wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
+ wl /= power;
- if (rq->nr_running == 1 && wl > imbalance)
+ if (capacity && rq->nr_running == 1 && wl > imbalance)
continue;
if (wl > max_load) {
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
- rcu_qsctr_inc(cpu);
+ rcu_sched_qs(cpu);
prev = rq->curr;
switch_count = &prev->nivcsw;
switch_count = &prev->nvcsw;
}
-#ifdef CONFIG_SMP
- if (prev->sched_class->pre_schedule)
- prev->sched_class->pre_schedule(rq, prev);
-#endif
+ pre_schedule(rq, prev);
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
} else
spin_unlock_irq(&rq->lock);
+ post_schedule(rq);
+
if (unlikely(reacquire_kernel_lock(current) < 0))
goto need_resched_nonpreemptible;
unsigned long flags;
const struct sched_class *prev_class = p->sched_class;
struct rq *rq;
+ int reset_on_fork;
/* may grab non-irq protected spin_locks */
BUG_ON(in_interrupt());
recheck:
/* double check policy once rq lock held */
- if (policy < 0)
+ if (policy < 0) {
+ reset_on_fork = p->sched_reset_on_fork;
policy = oldpolicy = p->policy;
- else if (policy != SCHED_FIFO && policy != SCHED_RR &&
- policy != SCHED_NORMAL && policy != SCHED_BATCH &&
- policy != SCHED_IDLE)
- return -EINVAL;
+ } else {
+ reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
+ policy &= ~SCHED_RESET_ON_FORK;
+
+ if (policy != SCHED_FIFO && policy != SCHED_RR &&
+ policy != SCHED_NORMAL && policy != SCHED_BATCH &&
+ policy != SCHED_IDLE)
+ return -EINVAL;
+ }
+
/*
* Valid priorities for SCHED_FIFO and SCHED_RR are
* 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
/* can't change other user's priorities */
if (!check_same_owner(p))
return -EPERM;
+
+ /* Normal users shall not reset the sched_reset_on_fork flag */
+ if (p->sched_reset_on_fork && !reset_on_fork)
+ return -EPERM;
}
if (user) {
if (running)
p->sched_class->put_prev_task(rq, p);
+ p->sched_reset_on_fork = reset_on_fork;
+
oldprio = p->prio;
__setscheduler(rq, p, policy, param->sched_priority);
if (p) {
retval = security_task_getscheduler(p);
if (!retval)
- retval = p->policy;
+ retval = p->policy
+ | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
}
read_unlock(&tasklist_lock);
return retval;
}
/**
- * sys_sched_getscheduler - get the RT priority of a thread
+ * sys_sched_getparam - get the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the RT priority.
*/
static void __cond_resched(void)
{
-#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
- __might_sleep(__FILE__, __LINE__);
-#endif
- /*
- * The BKS might be reacquired before we have dropped
- * PREEMPT_ACTIVE, which could trigger a second
- * cond_resched() call.
- */
- do {
- add_preempt_count(PREEMPT_ACTIVE);
- schedule();
- sub_preempt_count(PREEMPT_ACTIVE);
- } while (need_resched());
+ add_preempt_count(PREEMPT_ACTIVE);
+ schedule();
+ sub_preempt_count(PREEMPT_ACTIVE);
}
int __sched _cond_resched(void)
EXPORT_SYMBOL(_cond_resched);
/*
- * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
* call schedule, and on return reacquire the lock.
*
* This works OK both with and without CONFIG_PREEMPT. We do strange low-level
* operations here to prevent schedule() from being called twice (once via
* spin_unlock(), once by hand).
*/
-int cond_resched_lock(spinlock_t *lock)
+int __cond_resched_lock(spinlock_t *lock)
{
int resched = should_resched();
int ret = 0;
+ lockdep_assert_held(lock);
+
if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
if (resched)
}
return ret;
}
-EXPORT_SYMBOL(cond_resched_lock);
+EXPORT_SYMBOL(__cond_resched_lock);
-int __sched cond_resched_softirq(void)
+int __sched __cond_resched_softirq(void)
{
BUG_ON(!in_softirq());
}
return 0;
}
-EXPORT_SYMBOL(cond_resched_softirq);
+EXPORT_SYMBOL(__cond_resched_softirq);
/**
* yield - yield the current processor to other threads.
*/
void __sched io_schedule(void)
{
- struct rq *rq = &__raw_get_cpu_var(runqueues);
+ struct rq *rq = raw_rq();
delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
+ current->in_iowait = 1;
schedule();
+ current->in_iowait = 0;
atomic_dec(&rq->nr_iowait);
delayacct_blkio_end();
}
long __sched io_schedule_timeout(long timeout)
{
- struct rq *rq = &__raw_get_cpu_var(runqueues);
+ struct rq *rq = raw_rq();
long ret;
delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
+ current->in_iowait = 1;
ret = schedule_timeout(timeout);
+ current->in_iowait = 0;
atomic_dec(&rq->nr_iowait);
delayacct_blkio_end();
return ret;
if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
/* Need help from migration thread: drop lock and wait. */
+ struct task_struct *mt = rq->migration_thread;
+
+ get_task_struct(mt);
task_rq_unlock(rq, &flags);
wake_up_process(rq->migration_thread);
+ put_task_struct(mt);
wait_for_completion(&req.done);
tlb_migrate_finish(p->mm);
return 0;
return ret;
}
+#define RCU_MIGRATION_IDLE 0
+#define RCU_MIGRATION_NEED_QS 1
+#define RCU_MIGRATION_GOT_QS 2
+#define RCU_MIGRATION_MUST_SYNC 3
+
/*
* migration_thread - this is a highprio system thread that performs
* thread migration by bumping thread off CPU then 'pushing' onto
*/
static int migration_thread(void *data)
{
+ int badcpu;
int cpu = (long)data;
struct rq *rq;
req = list_entry(head->next, struct migration_req, list);
list_del_init(head->next);
- spin_unlock(&rq->lock);
- __migrate_task(req->task, cpu, req->dest_cpu);
+ if (req->task != NULL) {
+ spin_unlock(&rq->lock);
+ __migrate_task(req->task, cpu, req->dest_cpu);
+ } else if (likely(cpu == (badcpu = smp_processor_id()))) {
+ req->dest_cpu = RCU_MIGRATION_GOT_QS;
+ spin_unlock(&rq->lock);
+ } else {
+ req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
+ spin_unlock(&rq->lock);
+ WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
+ }
local_irq_enable();
complete(&req->done);
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
- return err;
+ return 0;
}
early_initcall(migration_init);
#endif
break;
}
- if (!group->__cpu_power) {
+ if (!group->cpu_power) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
printk(KERN_CONT " %s", str);
- if (group->__cpu_power != SCHED_LOAD_SCALE) {
- printk(KERN_CONT " (__cpu_power = %d)",
- group->__cpu_power);
+ if (group->cpu_power != SCHED_LOAD_SCALE) {
+ printk(KERN_CONT " (cpu_power = %d)",
+ group->cpu_power);
}
group = group->next;
rq->rd = rd;
cpumask_set_cpu(rq->cpu, rd->span);
- if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
+ if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
set_rq_online(rq);
spin_unlock_irqrestore(&rq->lock, flags);
continue;
cpumask_clear(sched_group_cpus(sg));
- sg->__cpu_power = 0;
+ sg->cpu_power = 0;
for_each_cpu(j, span) {
if (group_fn(j, cpu_map, NULL, tmpmask) != group)
DECLARE_BITMAP(span, CONFIG_NR_CPUS);
};
+struct s_data {
+#ifdef CONFIG_NUMA
+ int sd_allnodes;
+ cpumask_var_t domainspan;
+ cpumask_var_t covered;
+ cpumask_var_t notcovered;
+#endif
+ cpumask_var_t nodemask;
+ cpumask_var_t this_sibling_map;
+ cpumask_var_t this_core_map;
+ cpumask_var_t send_covered;
+ cpumask_var_t tmpmask;
+ struct sched_group **sched_group_nodes;
+ struct root_domain *rd;
+};
+
+enum s_alloc {
+ sa_sched_groups = 0,
+ sa_rootdomain,
+ sa_tmpmask,
+ sa_send_covered,
+ sa_this_core_map,
+ sa_this_sibling_map,
+ sa_nodemask,
+ sa_sched_group_nodes,
+#ifdef CONFIG_NUMA
+ sa_notcovered,
+ sa_covered,
+ sa_domainspan,
+#endif
+ sa_none,
+};
+
/*
* SMT sched-domains:
*/
continue;
}
- sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+ sg->cpu_power += sd->groups->cpu_power;
}
sg = sg->next;
} while (sg != group_head);
}
+
+static int build_numa_sched_groups(struct s_data *d,
+ const struct cpumask *cpu_map, int num)
+{
+ struct sched_domain *sd;
+ struct sched_group *sg, *prev;
+ int n, j;
+
+ cpumask_clear(d->covered);
+ cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map);
+ if (cpumask_empty(d->nodemask)) {
+ d->sched_group_nodes[num] = NULL;
+ goto out;
+ }
+
+ sched_domain_node_span(num, d->domainspan);
+ cpumask_and(d->domainspan, d->domainspan, cpu_map);
+
+ sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+ GFP_KERNEL, num);
+ if (!sg) {
+ printk(KERN_WARNING "Can not alloc domain group for node %d\n",
+ num);
+ return -ENOMEM;
+ }
+ d->sched_group_nodes[num] = sg;
+
+ for_each_cpu(j, d->nodemask) {
+ sd = &per_cpu(node_domains, j).sd;
+ sd->groups = sg;
+ }
+
+ sg->cpu_power = 0;
+ cpumask_copy(sched_group_cpus(sg), d->nodemask);
+ sg->next = sg;
+ cpumask_or(d->covered, d->covered, d->nodemask);
+
+ prev = sg;
+ for (j = 0; j < nr_node_ids; j++) {
+ n = (num + j) % nr_node_ids;
+ cpumask_complement(d->notcovered, d->covered);
+ cpumask_and(d->tmpmask, d->notcovered, cpu_map);
+ cpumask_and(d->tmpmask, d->tmpmask, d->domainspan);
+ if (cpumask_empty(d->tmpmask))
+ break;
+ cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n));
+ if (cpumask_empty(d->tmpmask))
+ continue;
+ sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+ GFP_KERNEL, num);
+ if (!sg) {
+ printk(KERN_WARNING
+ "Can not alloc domain group for node %d\n", j);
+ return -ENOMEM;
+ }
+ sg->cpu_power = 0;
+ cpumask_copy(sched_group_cpus(sg), d->tmpmask);
+ sg->next = prev->next;
+ cpumask_or(d->covered, d->covered, d->tmpmask);
+ prev->next = sg;
+ prev = sg;
+ }
+out:
+ return 0;
+}
#endif /* CONFIG_NUMA */
#ifdef CONFIG_NUMA
* there are asymmetries in the topology. If there are asymmetries, group
* having more cpu_power will pickup more load compared to the group having
* less cpu_power.
- *
- * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
- * the maximum number of tasks a group can handle in the presence of other idle
- * or lightly loaded groups in the same sched domain.
*/
static void init_sched_groups_power(int cpu, struct sched_domain *sd)
{
struct sched_domain *child;
struct sched_group *group;
+ long power;
+ int weight;
WARN_ON(!sd || !sd->groups);
child = sd->child;
- sd->groups->__cpu_power = 0;
+ sd->groups->cpu_power = 0;
- /*
- * For perf policy, if the groups in child domain share resources
- * (for example cores sharing some portions of the cache hierarchy
- * or SMT), then set this domain groups cpu_power such that each group
- * can handle only one task, when there are other idle groups in the
- * same sched domain.
- */
- if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
- (child->flags &
- (SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
- sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
+ if (!child) {
+ power = SCHED_LOAD_SCALE;
+ weight = cpumask_weight(sched_domain_span(sd));
+ /*
+ * SMT siblings share the power of a single core.
+ * Usually multiple threads get a better yield out of
+ * that one core than a single thread would have,
+ * reflect that in sd->smt_gain.
+ */
+ if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+ power *= sd->smt_gain;
+ power /= weight;
+ power >>= SCHED_LOAD_SHIFT;
+ }
+ sd->groups->cpu_power += power;
return;
}
/*
- * add cpu_power of each child group to this groups cpu_power
+ * Add cpu_power of each child group to this groups cpu_power.
*/
group = child->groups;
do {
- sg_inc_cpu_power(sd->groups, group->__cpu_power);
+ sd->groups->cpu_power += group->cpu_power;
group = group->next;
} while (group != child->groups);
}
}
}
-/*
- * Build sched domains for a given set of cpus and attach the sched domains
- * to the individual cpus
- */
-static int __build_sched_domains(const struct cpumask *cpu_map,
- struct sched_domain_attr *attr)
-{
- int i, err = -ENOMEM;
- struct root_domain *rd;
- cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered,
- tmpmask;
+static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
+ const struct cpumask *cpu_map)
+{
+ switch (what) {
+ case sa_sched_groups:
+ free_sched_groups(cpu_map, d->tmpmask); /* fall through */
+ d->sched_group_nodes = NULL;
+ case sa_rootdomain:
+ free_rootdomain(d->rd); /* fall through */
+ case sa_tmpmask:
+ free_cpumask_var(d->tmpmask); /* fall through */
+ case sa_send_covered:
+ free_cpumask_var(d->send_covered); /* fall through */
+ case sa_this_core_map:
+ free_cpumask_var(d->this_core_map); /* fall through */
+ case sa_this_sibling_map:
+ free_cpumask_var(d->this_sibling_map); /* fall through */
+ case sa_nodemask:
+ free_cpumask_var(d->nodemask); /* fall through */
+ case sa_sched_group_nodes:
#ifdef CONFIG_NUMA
- cpumask_var_t domainspan, covered, notcovered;
- struct sched_group **sched_group_nodes = NULL;
- int sd_allnodes = 0;
-
- if (!alloc_cpumask_var(&domainspan, GFP_KERNEL))
- goto out;
- if (!alloc_cpumask_var(&covered, GFP_KERNEL))
- goto free_domainspan;
- if (!alloc_cpumask_var(¬covered, GFP_KERNEL))
- goto free_covered;
-#endif
-
- if (!alloc_cpumask_var(&nodemask, GFP_KERNEL))
- goto free_notcovered;
- if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL))
- goto free_nodemask;
- if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL))
- goto free_this_sibling_map;
- if (!alloc_cpumask_var(&send_covered, GFP_KERNEL))
- goto free_this_core_map;
- if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
- goto free_send_covered;
+ kfree(d->sched_group_nodes); /* fall through */
+ case sa_notcovered:
+ free_cpumask_var(d->notcovered); /* fall through */
+ case sa_covered:
+ free_cpumask_var(d->covered); /* fall through */
+ case sa_domainspan:
+ free_cpumask_var(d->domainspan); /* fall through */
+#endif
+ case sa_none:
+ break;
+ }
+}
+static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
+ const struct cpumask *cpu_map)
+{
#ifdef CONFIG_NUMA
- /*
- * Allocate the per-node list of sched groups
- */
- sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *),
- GFP_KERNEL);
- if (!sched_group_nodes) {
+ if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL))
+ return sa_none;
+ if (!alloc_cpumask_var(&d->covered, GFP_KERNEL))
+ return sa_domainspan;
+ if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL))
+ return sa_covered;
+ /* Allocate the per-node list of sched groups */
+ d->sched_group_nodes = kcalloc(nr_node_ids,
+ sizeof(struct sched_group *), GFP_KERNEL);
+ if (!d->sched_group_nodes) {
printk(KERN_WARNING "Can not alloc sched group node list\n");
- goto free_tmpmask;
- }
-#endif
-
- rd = alloc_rootdomain();
- if (!rd) {
+ return sa_notcovered;
+ }
+ sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes;
+#endif
+ if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL))
+ return sa_sched_group_nodes;
+ if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL))
+ return sa_nodemask;
+ if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
+ return sa_this_sibling_map;
+ if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+ return sa_this_core_map;
+ if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
+ return sa_send_covered;
+ d->rd = alloc_rootdomain();
+ if (!d->rd) {
printk(KERN_WARNING "Cannot alloc root domain\n");
- goto free_sched_groups;
+ return sa_tmpmask;
}
+ return sa_rootdomain;
+}
+static struct sched_domain *__build_numa_sched_domains(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i)
+{
+ struct sched_domain *sd = NULL;
#ifdef CONFIG_NUMA
- sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
-#endif
-
- /*
- * Set up domains for cpus specified by the cpu_map.
- */
- for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = NULL, *p;
-
- cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
-
-#ifdef CONFIG_NUMA
- if (cpumask_weight(cpu_map) >
- SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
- sd = &per_cpu(allnodes_domains, i).sd;
- SD_INIT(sd, ALLNODES);
- set_domain_attribute(sd, attr);
- cpumask_copy(sched_domain_span(sd), cpu_map);
- cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
- p = sd;
- sd_allnodes = 1;
- } else
- p = NULL;
+ struct sched_domain *parent;
- sd = &per_cpu(node_domains, i).sd;
- SD_INIT(sd, NODE);
+ d->sd_allnodes = 0;
+ if (cpumask_weight(cpu_map) >
+ SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) {
+ sd = &per_cpu(allnodes_domains, i).sd;
+ SD_INIT(sd, ALLNODES);
set_domain_attribute(sd, attr);
- sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
- sd->parent = p;
- if (p)
- p->child = sd;
- cpumask_and(sched_domain_span(sd),
- sched_domain_span(sd), cpu_map);
+ cpumask_copy(sched_domain_span(sd), cpu_map);
+ cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask);
+ d->sd_allnodes = 1;
+ }
+ parent = sd;
+
+ sd = &per_cpu(node_domains, i).sd;
+ SD_INIT(sd, NODE);
+ set_domain_attribute(sd, attr);
+ sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
+ sd->parent = parent;
+ if (parent)
+ parent->child = sd;
+ cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map);
#endif
+ return sd;
+}
- p = sd;
- sd = &per_cpu(phys_domains, i).sd;
- SD_INIT(sd, CPU);
- set_domain_attribute(sd, attr);
- cpumask_copy(sched_domain_span(sd), nodemask);
- sd->parent = p;
- if (p)
- p->child = sd;
- cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask);
+static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+ struct sched_domain *parent, int i)
+{
+ struct sched_domain *sd;
+ sd = &per_cpu(phys_domains, i).sd;
+ SD_INIT(sd, CPU);
+ set_domain_attribute(sd, attr);
+ cpumask_copy(sched_domain_span(sd), d->nodemask);
+ sd->parent = parent;
+ if (parent)
+ parent->child = sd;
+ cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask);
+ return sd;
+}
+static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+ struct sched_domain *parent, int i)
+{
+ struct sched_domain *sd = parent;
#ifdef CONFIG_SCHED_MC
- p = sd;
- sd = &per_cpu(core_domains, i).sd;
- SD_INIT(sd, MC);
- set_domain_attribute(sd, attr);
- cpumask_and(sched_domain_span(sd), cpu_map,
- cpu_coregroup_mask(i));
- sd->parent = p;
- p->child = sd;
- cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
+ sd = &per_cpu(core_domains, i).sd;
+ SD_INIT(sd, MC);
+ set_domain_attribute(sd, attr);
+ cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i));
+ sd->parent = parent;
+ parent->child = sd;
+ cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask);
#endif
+ return sd;
+}
+static struct sched_domain *__build_smt_sched_domain(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+ struct sched_domain *parent, int i)
+{
+ struct sched_domain *sd = parent;
#ifdef CONFIG_SCHED_SMT
- p = sd;
- sd = &per_cpu(cpu_domains, i).sd;
- SD_INIT(sd, SIBLING);
- set_domain_attribute(sd, attr);
- cpumask_and(sched_domain_span(sd),
- topology_thread_cpumask(i), cpu_map);
- sd->parent = p;
- p->child = sd;
- cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
+ sd = &per_cpu(cpu_domains, i).sd;
+ SD_INIT(sd, SIBLING);
+ set_domain_attribute(sd, attr);
+ cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i));
+ sd->parent = parent;
+ parent->child = sd;
+ cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask);
#endif
- }
+ return sd;
+}
+static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
+ const struct cpumask *cpu_map, int cpu)
+{
+ switch (l) {
#ifdef CONFIG_SCHED_SMT
- /* Set up CPU (sibling) groups */
- for_each_cpu(i, cpu_map) {
- cpumask_and(this_sibling_map,
- topology_thread_cpumask(i), cpu_map);
- if (i != cpumask_first(this_sibling_map))
- continue;
-
- init_sched_build_groups(this_sibling_map, cpu_map,
- &cpu_to_cpu_group,
- send_covered, tmpmask);
- }
+ case SD_LV_SIBLING: /* set up CPU (sibling) groups */
+ cpumask_and(d->this_sibling_map, cpu_map,
+ topology_thread_cpumask(cpu));
+ if (cpu == cpumask_first(d->this_sibling_map))
+ init_sched_build_groups(d->this_sibling_map, cpu_map,
+ &cpu_to_cpu_group,
+ d->send_covered, d->tmpmask);
+ break;
#endif
-
#ifdef CONFIG_SCHED_MC
- /* Set up multi-core groups */
- for_each_cpu(i, cpu_map) {
- cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
- if (i != cpumask_first(this_core_map))
- continue;
-
- init_sched_build_groups(this_core_map, cpu_map,
- &cpu_to_core_group,
- send_covered, tmpmask);
- }
+ case SD_LV_MC: /* set up multi-core groups */
+ cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu));
+ if (cpu == cpumask_first(d->this_core_map))
+ init_sched_build_groups(d->this_core_map, cpu_map,
+ &cpu_to_core_group,
+ d->send_covered, d->tmpmask);
+ break;
#endif
-
- /* Set up physical groups */
- for (i = 0; i < nr_node_ids; i++) {
- cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
- if (cpumask_empty(nodemask))
- continue;
-
- init_sched_build_groups(nodemask, cpu_map,
- &cpu_to_phys_group,
- send_covered, tmpmask);
- }
-
+ case SD_LV_CPU: /* set up physical groups */
+ cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
+ if (!cpumask_empty(d->nodemask))
+ init_sched_build_groups(d->nodemask, cpu_map,
+ &cpu_to_phys_group,
+ d->send_covered, d->tmpmask);
+ break;
#ifdef CONFIG_NUMA
- /* Set up node groups */
- if (sd_allnodes) {
- init_sched_build_groups(cpu_map, cpu_map,
- &cpu_to_allnodes_group,
- send_covered, tmpmask);
+ case SD_LV_ALLNODES:
+ init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group,
+ d->send_covered, d->tmpmask);
+ break;
+#endif
+ default:
+ break;
}
+}
- for (i = 0; i < nr_node_ids; i++) {
- /* Set up node groups */
- struct sched_group *sg, *prev;
- int j;
-
- cpumask_clear(covered);
- cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
- if (cpumask_empty(nodemask)) {
- sched_group_nodes[i] = NULL;
- continue;
- }
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+static int __build_sched_domains(const struct cpumask *cpu_map,
+ struct sched_domain_attr *attr)
+{
+ enum s_alloc alloc_state = sa_none;
+ struct s_data d;
+ struct sched_domain *sd;
+ int i;
+#ifdef CONFIG_NUMA
+ d.sd_allnodes = 0;
+#endif
- sched_domain_node_span(i, domainspan);
- cpumask_and(domainspan, domainspan, cpu_map);
+ alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
+ if (alloc_state != sa_rootdomain)
+ goto error;
+ alloc_state = sa_sched_groups;
- sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
- GFP_KERNEL, i);
- if (!sg) {
- printk(KERN_WARNING "Can not alloc domain group for "
- "node %d\n", i);
- goto error;
- }
- sched_group_nodes[i] = sg;
- for_each_cpu(j, nodemask) {
- struct sched_domain *sd;
+ /*
+ * Set up domains for cpus specified by the cpu_map.
+ */
+ for_each_cpu(i, cpu_map) {
+ cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)),
+ cpu_map);
- sd = &per_cpu(node_domains, j).sd;
- sd->groups = sg;
- }
- sg->__cpu_power = 0;
- cpumask_copy(sched_group_cpus(sg), nodemask);
- sg->next = sg;
- cpumask_or(covered, covered, nodemask);
- prev = sg;
+ sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
+ sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+ sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
+ sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
+ }
- for (j = 0; j < nr_node_ids; j++) {
- int n = (i + j) % nr_node_ids;
+ for_each_cpu(i, cpu_map) {
+ build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+ build_sched_groups(&d, SD_LV_MC, cpu_map, i);
+ }
- cpumask_complement(notcovered, covered);
- cpumask_and(tmpmask, notcovered, cpu_map);
- cpumask_and(tmpmask, tmpmask, domainspan);
- if (cpumask_empty(tmpmask))
- break;
+ /* Set up physical groups */
+ for (i = 0; i < nr_node_ids; i++)
+ build_sched_groups(&d, SD_LV_CPU, cpu_map, i);
- cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
- if (cpumask_empty(tmpmask))
- continue;
+#ifdef CONFIG_NUMA
+ /* Set up node groups */
+ if (d.sd_allnodes)
+ build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0);
- sg = kmalloc_node(sizeof(struct sched_group) +
- cpumask_size(),
- GFP_KERNEL, i);
- if (!sg) {
- printk(KERN_WARNING
- "Can not alloc domain group for node %d\n", j);
- goto error;
- }
- sg->__cpu_power = 0;
- cpumask_copy(sched_group_cpus(sg), tmpmask);
- sg->next = prev->next;
- cpumask_or(covered, covered, tmpmask);
- prev->next = sg;
- prev = sg;
- }
- }
+ for (i = 0; i < nr_node_ids; i++)
+ if (build_numa_sched_groups(&d, cpu_map, i))
+ goto error;
#endif
/* Calculate CPU power for physical packages and nodes */
#ifdef CONFIG_SCHED_SMT
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = &per_cpu(cpu_domains, i).sd;
-
+ sd = &per_cpu(cpu_domains, i).sd;
init_sched_groups_power(i, sd);
}
#endif
#ifdef CONFIG_SCHED_MC
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = &per_cpu(core_domains, i).sd;
-
+ sd = &per_cpu(core_domains, i).sd;
init_sched_groups_power(i, sd);
}
#endif
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = &per_cpu(phys_domains, i).sd;
-
+ sd = &per_cpu(phys_domains, i).sd;
init_sched_groups_power(i, sd);
}
#ifdef CONFIG_NUMA
for (i = 0; i < nr_node_ids; i++)
- init_numa_sched_groups_power(sched_group_nodes[i]);
+ init_numa_sched_groups_power(d.sched_group_nodes[i]);
- if (sd_allnodes) {
+ if (d.sd_allnodes) {
struct sched_group *sg;
cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
- tmpmask);
+ d.tmpmask);
init_numa_sched_groups_power(sg);
}
#endif
/* Attach the domains */
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
sd = &per_cpu(cpu_domains, i).sd;
#elif defined(CONFIG_SCHED_MC)
#else
sd = &per_cpu(phys_domains, i).sd;
#endif
- cpu_attach_domain(sd, rd, i);
+ cpu_attach_domain(sd, d.rd, i);
}
- err = 0;
-
-free_tmpmask:
- free_cpumask_var(tmpmask);
-free_send_covered:
- free_cpumask_var(send_covered);
-free_this_core_map:
- free_cpumask_var(this_core_map);
-free_this_sibling_map:
- free_cpumask_var(this_sibling_map);
-free_nodemask:
- free_cpumask_var(nodemask);
-free_notcovered:
-#ifdef CONFIG_NUMA
- free_cpumask_var(notcovered);
-free_covered:
- free_cpumask_var(covered);
-free_domainspan:
- free_cpumask_var(domainspan);
-out:
-#endif
- return err;
-
-free_sched_groups:
-#ifdef CONFIG_NUMA
- kfree(sched_group_nodes);
-#endif
- goto free_tmpmask;
+ d.sched_group_nodes = NULL; /* don't free this we still need it */
+ __free_domain_allocs(&d, sa_tmpmask, cpu_map);
+ return 0;
-#ifdef CONFIG_NUMA
error:
- free_sched_groups(cpu_map, tmpmask);
- free_rootdomain(rd);
- goto free_tmpmask;
-#endif
+ __free_domain_allocs(&d, alloc_state, cpu_map);
+ return -ENOMEM;
}
static int build_sched_domains(const struct cpumask *cpu_map)
* system cpu resource, based on the weight assigned to root
* user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
* by letting tasks of init_task_group sit in a separate cfs_rq
- * (init_cfs_rq) and having one entity represent this group of
+ * (init_tg_cfs_rq) and having one entity represent this group of
* tasks in rq->cfs (i.e init_task_group->se[] != NULL).
*/
init_tg_cfs_entry(&init_task_group,
- &per_cpu(init_cfs_rq, i),
+ &per_cpu(init_tg_cfs_rq, i),
&per_cpu(init_sched_entity, i), i, 1,
root_task_group.se[i]);
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
+ rq->post_schedule = 0;
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
}
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-void __might_sleep(char *file, int line)
+static inline int preempt_count_equals(int preempt_offset)
+{
+ int nested = preempt_count() & ~PREEMPT_ACTIVE;
+
+ return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
+}
+
+void __might_sleep(char *file, int line, int preempt_offset)
{
#ifdef in_atomic
static unsigned long prev_jiffy; /* ratelimiting */
- if ((!in_atomic() && !irqs_disabled()) ||
- system_state != SYSTEM_RUNNING || oops_in_progress)
+ if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+ system_state != SYSTEM_RUNNING || oops_in_progress)
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
.subsys_id = cpuacct_subsys_id,
};
#endif /* CONFIG_CGROUP_CPUACCT */
+
+#ifndef CONFIG_SMP
+
+int rcu_expedited_torture_stats(char *page)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
+
+void synchronize_sched_expedited(void)
+{
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static DEFINE_PER_CPU(struct migration_req, rcu_migration_req);
+static DEFINE_MUTEX(rcu_sched_expedited_mutex);
+
+#define RCU_EXPEDITED_STATE_POST -2
+#define RCU_EXPEDITED_STATE_IDLE -1
+
+static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+
+int rcu_expedited_torture_stats(char *page)
+{
+ int cnt = 0;
+ int cpu;
+
+ cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state);
+ for_each_online_cpu(cpu) {
+ cnt += sprintf(&page[cnt], " %d:%d",
+ cpu, per_cpu(rcu_migration_req, cpu).dest_cpu);
+ }
+ cnt += sprintf(&page[cnt], "\n");
+ return cnt;
+}
+EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
+
+static long synchronize_sched_expedited_count;
+
+/*
+ * Wait for an rcu-sched grace period to elapse, but use "big hammer"
+ * approach to force grace period to end quickly. This consumes
+ * significant time on all CPUs, and is thus not recommended for
+ * any sort of common-case code.
+ *
+ * Note that it is illegal to call this function while holding any
+ * lock that is acquired by a CPU-hotplug notifier. Failing to
+ * observe this restriction will result in deadlock.
+ */
+void synchronize_sched_expedited(void)
+{
+ int cpu;
+ unsigned long flags;
+ bool need_full_sync = 0;
+ struct rq *rq;
+ struct migration_req *req;
+ long snap;
+ int trycount = 0;
+
+ smp_mb(); /* ensure prior mod happens before capturing snap. */
+ snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1;
+ get_online_cpus();
+ while (!mutex_trylock(&rcu_sched_expedited_mutex)) {
+ put_online_cpus();
+ if (trycount++ < 10)
+ udelay(trycount * num_online_cpus());
+ else {
+ synchronize_sched();
+ return;
+ }
+ if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) {
+ smp_mb(); /* ensure test happens before caller kfree */
+ return;
+ }
+ get_online_cpus();
+ }
+ rcu_expedited_state = RCU_EXPEDITED_STATE_POST;
+ for_each_online_cpu(cpu) {
+ rq = cpu_rq(cpu);
+ req = &per_cpu(rcu_migration_req, cpu);
+ init_completion(&req->done);
+ req->task = NULL;
+ req->dest_cpu = RCU_MIGRATION_NEED_QS;
+ spin_lock_irqsave(&rq->lock, flags);
+ list_add(&req->list, &rq->migration_queue);
+ spin_unlock_irqrestore(&rq->lock, flags);
+ wake_up_process(rq->migration_thread);
+ }
+ for_each_online_cpu(cpu) {
+ rcu_expedited_state = cpu;
+ req = &per_cpu(rcu_migration_req, cpu);
+ rq = cpu_rq(cpu);
+ wait_for_completion(&req->done);
+ spin_lock_irqsave(&rq->lock, flags);
+ if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
+ need_full_sync = 1;
+ req->dest_cpu = RCU_MIGRATION_IDLE;
+ spin_unlock_irqrestore(&rq->lock, flags);
+ }
+ rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+ mutex_unlock(&rcu_sched_expedited_mutex);
+ put_online_cpus();
+ if (need_full_sync)
+ synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#endif /* #else #ifndef CONFIG_SMP */
#include <linux/ctype.h>
#include <linux/delay.h>
+#include <asm/setup.h>
+
#include "trace_output.h"
#define TRACE_SYSTEM "TRACE_SYSTEM"
LIST_HEAD(ftrace_events);
-int trace_define_field(struct ftrace_event_call *call, char *type,
- char *name, int offset, int size, int is_signed)
+int trace_define_field(struct ftrace_event_call *call, const char *type,
+ const char *name, int offset, int size, int is_signed,
+ int filter_type)
{
struct ftrace_event_field *field;
if (!field->type)
goto err;
+ if (filter_type == FILTER_OTHER)
+ field->filter_type = filter_assign_type(type);
+ else
+ field->filter_type = filter_type;
+
field->offset = offset;
field->size = size;
field->is_signed = is_signed;
+
list_add(&field->link, &call->fields);
return 0;
}
EXPORT_SYMBOL_GPL(trace_define_field);
+#define __common_field(type, item) \
+ ret = trace_define_field(call, #type, "common_" #item, \
+ offsetof(typeof(ent), item), \
+ sizeof(ent.item), \
+ is_signed_type(type), FILTER_OTHER); \
+ if (ret) \
+ return ret;
+
+int trace_define_common_fields(struct ftrace_event_call *call)
+{
+ int ret;
+ struct trace_entry ent;
+
+ __common_field(unsigned short, type);
+ __common_field(unsigned char, flags);
+ __common_field(unsigned char, preempt_count);
+ __common_field(int, pid);
+ __common_field(int, tgid);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(trace_define_common_fields);
+
#ifdef CONFIG_MODULES
static void trace_destroy_fields(struct ftrace_event_call *call)
if (call->enabled) {
call->enabled = 0;
tracing_stop_cmdline_record();
- call->unregfunc();
+ call->unregfunc(call->data);
}
break;
case 1:
if (!call->enabled) {
call->enabled = 1;
tracing_start_cmdline_record();
- call->regfunc();
+ call->regfunc(call->data);
}
break;
}
trace_seq_printf(s, "format:\n");
trace_write_header(s);
- r = call->show_format(s);
+ r = call->show_format(call, s);
if (!r) {
/*
* ug! The format output is bigger than a PAGE!!
/* First see if we did not already create this dir */
list_for_each_entry(system, &event_subsystems, list) {
- if (strcmp(system->name, name) == 0)
+ if (strcmp(system->name, name) == 0) {
+ system->nr_events++;
return system->entry;
+ }
}
/* need to create new entry */
return d_events;
}
+ system->nr_events = 1;
system->name = kstrdup(name, GFP_KERNEL);
if (!system->name) {
debugfs_remove(system->entry);
if (strcmp(call->system, TRACE_SYSTEM) != 0)
d_events = event_subsystem_dir(call->system, d_events);
- if (call->raw_init) {
- ret = call->raw_init();
- if (ret < 0) {
- pr_warning("Could not initialize trace point"
- " events/%s\n", call->name);
- return ret;
- }
- }
-
call->dir = debugfs_create_dir(call->name, d_events);
if (!call->dir) {
pr_warning("Could not create debugfs "
id);
if (call->define_fields) {
- ret = call->define_fields();
+ ret = call->define_fields(call);
if (ret < 0) {
pr_warning("Could not initialize trace point"
" events/%s\n", call->name);
struct file_operations filter;
};
+static void remove_subsystem_dir(const char *name)
+{
+ struct event_subsystem *system;
+
+ if (strcmp(name, TRACE_SYSTEM) == 0)
+ return;
+
+ list_for_each_entry(system, &event_subsystems, list) {
+ if (strcmp(system->name, name) == 0) {
+ if (!--system->nr_events) {
+ struct event_filter *filter = system->filter;
+
+ debugfs_remove_recursive(system->entry);
+ list_del(&system->list);
+ if (filter) {
+ kfree(filter->filter_string);
+ kfree(filter);
+ }
+ kfree(system->name);
+ kfree(system);
+ }
+ break;
+ }
+ }
+}
+
static struct ftrace_module_file_ops *
trace_create_file_ops(struct module *mod)
{
struct ftrace_module_file_ops *file_ops = NULL;
struct ftrace_event_call *call, *start, *end;
struct dentry *d_events;
+ int ret;
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
/* The linker may leave blanks */
if (!call->name)
continue;
-
+ if (call->raw_init) {
+ ret = call->raw_init();
+ if (ret < 0) {
+ if (ret != -ENOSYS)
+ pr_warning("Could not initialize trace "
+ "point events/%s\n", call->name);
+ continue;
+ }
+ }
/*
* This module has events, create file ops for this module
* if not already done.
list_del(&call->list);
trace_destroy_fields(call);
destroy_preds(call);
+ remove_subsystem_dir(call->system);
}
}
extern struct ftrace_event_call __start_ftrace_events[];
extern struct ftrace_event_call __stop_ftrace_events[];
+static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
+
+static __init int setup_trace_event(char *str)
+{
+ strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+ ring_buffer_expanded = 1;
+ tracing_selftest_disabled = 1;
+
+ return 1;
+}
+__setup("trace_event=", setup_trace_event);
+
static __init int event_trace_init(void)
{
struct ftrace_event_call *call;
struct dentry *entry;
struct dentry *d_events;
int ret;
+ char *buf = bootup_event_buf;
+ char *token;
d_tracer = tracing_init_dentry();
if (!d_tracer)
/* The linker may leave blanks */
if (!call->name)
continue;
+ if (call->raw_init) {
+ ret = call->raw_init();
+ if (ret < 0) {
+ if (ret != -ENOSYS)
+ pr_warning("Could not initialize trace "
+ "point events/%s\n", call->name);
+ continue;
+ }
+ }
list_add(&call->list, &ftrace_events);
event_create_dir(call, d_events, &ftrace_event_id_fops,
&ftrace_enable_fops, &ftrace_event_filter_fops,
&ftrace_event_format_fops);
}
+ while (true) {
+ token = strsep(&buf, ",");
+
+ if (!token)
+ break;
+ if (!*token)
+ continue;
+
+ ret = ftrace_set_clr_event(token, 1);
+ if (ret)
+ pr_warning("Failed to enable trace event: %s\n", token);
+ }
+
ret = register_module_notifier(&trace_module_nb);
if (ret)
pr_warning("Failed to register trace events module notifier\n");
#ifdef CONFIG_FUNCTION_TRACER
- static DEFINE_PER_CPU(atomic_t, test_event_disable);
+ static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
static void
function_test_events_call(unsigned long ip, unsigned long parent_ip)
{
struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
struct ftrace_entry *entry;
unsigned long flags;
long disabled;
pc = preempt_count();
resched = ftrace_preempt_disable();
cpu = raw_smp_processor_id();
- disabled = atomic_inc_return(&per_cpu(test_event_disable, cpu));
+ disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));
if (disabled != 1)
goto out;
local_save_flags(flags);
- event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+ event = trace_current_buffer_lock_reserve(&buffer,
+ TRACE_FN, sizeof(*entry),
flags, pc);
if (!event)
goto out;
entry->ip = ip;
entry->parent_ip = parent_ip;
- trace_nowake_buffer_unlock_commit(event, flags, pc);
+ trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
out:
- atomic_dec(&per_cpu(test_event_disable, cpu));
+ atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
ftrace_preempt_enable(resched);
}
static __init int event_trace_self_tests_init(void)
{
-
- event_trace_self_tests();
-
- event_trace_self_test_with_function();
+ if (!tracing_selftest_disabled) {
+ event_trace_self_tests();
+ event_trace_self_test_with_function();
+ }
return 0;
}
This is a relatively cheap check but if you care about maximum
performance, say N.
+config DEBUG_CREDENTIALS
+ bool "Debug credential management"
+ depends on DEBUG_KERNEL
+ help
+ Enable this to turn on some debug checking for credential
+ management. The additional code keeps track of the number of
+ pointers from task_structs to any given cred struct, and checks to
+ see that this number never exceeds the usage count of the cred
+ struct.
+
+ Furthermore, if SELinux is enabled, this also checks that the
+ security pointer in the cred struct is never seen to be invalid.
+
+ If unsure, say N.
+
#
# Select this config option from the architecture Kconfig, if it
# it is preferred to always offer frame pointers as a config
config RCU_CPU_STALL_DETECTOR
bool "Check for stalled CPUs delaying RCU grace periods"
- depends on CLASSIC_RCU || TREE_RCU
+ depends on TREE_RCU || TREE_PREEMPT_RCU
default n
help
This option causes RCU to printk information on which
Say N if you are unsure.
+ config DEBUG_FORCE_WEAK_PER_CPU
+ bool "Force weak per-cpu definitions"
+ depends on DEBUG_KERNEL
+ help
+ s390 and alpha require percpu variables in modules to be
+ defined weak to work around addressing range issue which
+ puts the following two restrictions on percpu variable
+ definitions.
+
+ 1. percpu symbols must be unique whether static or not
+ 2. percpu variables can't be defined inside a function
+
+ To ensure that generic code follows the above rules, this
+ option forces all percpu variables to be defined as weak.
+
config LKDTM
tristate "Linux Kernel Dump Test Tool Module"
depends on DEBUG_KERNEL
vmalloc.o
obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
- maccess.o page_alloc.o page-writeback.o pdflush.o \
+ maccess.o page_alloc.o page-writeback.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
page_isolation.o mm_init.o $(mmu-y)
obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
obj-$(CONFIG_FS_XIP) += filemap_xip.o
obj-$(CONFIG_MIGRATION) += migrate.o
- ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+ ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
obj-$(CONFIG_SMP) += percpu.o
else
obj-$(CONFIG_SMP) += allocpercpu.o
#include <linux/buffer_head.h>
#include <linux/pagevec.h>
-/*
- * The maximum number of pages to writeout in a single bdflush/kupdate
- * operation. We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode. Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES 1024
-
/*
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
* will look to see if it needs to force writeback or throttling.
/* End of sysctl-exported parameters */
-static void background_writeout(unsigned long _min_pages);
-
/*
* Scale the writeback cache size proportional to the relative writeout speeds.
*
/*
*
*/
-static DEFINE_SPINLOCK(bdi_lock);
static unsigned int bdi_min_ratio;
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
int ret = 0;
- unsigned long flags;
- spin_lock_irqsave(&bdi_lock, flags);
+ spin_lock(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
ret = -EINVAL;
}
}
- spin_unlock_irqrestore(&bdi_lock, flags);
+ spin_unlock(&bdi_lock);
return ret;
}
int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
{
- unsigned long flags;
int ret = 0;
if (max_ratio > 100)
return -EINVAL;
- spin_lock_irqsave(&bdi_lock, flags);
+ spin_lock(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
- spin_unlock_irqrestore(&bdi_lock, flags);
+ spin_unlock(&bdi_lock);
return ret;
}
* up.
*/
if (bdi_nr_reclaimable > bdi_thresh) {
- writeback_inodes(&wbc);
+ writeback_inodes_wbc(&wbc);
pages_written += write_chunk - wbc.nr_to_write;
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
if (pages_written >= write_chunk)
break; /* We've done our duty */
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ schedule_timeout(1);
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
* background_thresh, to keep the amount of dirty memory low.
*/
if ((laptop_mode && pages_written) ||
- (!laptop_mode && (global_page_state(NR_FILE_DIRTY)
- + global_page_state(NR_UNSTABLE_NFS)
- > background_thresh)))
- pdflush_operation(background_writeout, 0);
+ (!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY)
+ + global_page_state(NR_UNSTABLE_NFS))
+ > background_thresh))) {
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ .nr_to_write = nr_writeback,
+ };
+
+
+ bdi_start_writeback(&wbc);
+ }
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
}
}
+ static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
+
/**
* balance_dirty_pages_ratelimited_nr - balance dirty memory state
* @mapping: address_space which was dirtied
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
unsigned long nr_pages_dirtied)
{
- static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
unsigned long ratelimit;
unsigned long *p;
* tasks in balance_dirty_pages(). Period.
*/
preempt_disable();
- p = &__get_cpu_var(ratelimits);
+ p = &__get_cpu_var(bdp_ratelimits);
*p += nr_pages_dirtied;
if (unlikely(*p >= ratelimit)) {
*p = 0;
}
}
-/*
- * writeback at least _min_pages, and keep writing until the amount of dirty
- * memory is less than the background threshold, or until we're all clean.
- */
-static void background_writeout(unsigned long _min_pages)
-{
- long min_pages = _min_pages;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = NULL,
- .nr_to_write = 0,
- .nonblocking = 1,
- .range_cyclic = 1,
- };
-
- for ( ; ; ) {
- unsigned long background_thresh;
- unsigned long dirty_thresh;
-
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
- if (global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) < background_thresh
- && min_pages <= 0)
- break;
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- wbc.pages_skipped = 0;
- writeback_inodes(&wbc);
- min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
- /* Wrote less than expected */
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- else
- break;
- }
- }
-}
-
-/*
- * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
- * the whole world. Returns 0 if a pdflush thread was dispatched. Returns
- * -1 if all pdflush threads were busy.
- */
-int wakeup_pdflush(long nr_pages)
-{
- if (nr_pages == 0)
- nr_pages = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- return pdflush_operation(background_writeout, nr_pages);
-}
-
-static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);
-static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
-/*
- * Periodic writeback of "old" data.
- *
- * Define "old": the first time one of an inode's pages is dirtied, we mark the
- * dirtying-time in the inode's address_space. So this periodic writeback code
- * just walks the superblock inode list, writing back any inodes which are
- * older than a specific point in time.
- *
- * Try to run once per dirty_writeback_interval. But if a writeback event
- * takes longer than a dirty_writeback_interval interval, then leave a
- * one-second gap.
- *
- * older_than_this takes precedence over nr_to_write. So we'll only write back
- * all dirty pages if they are all attached to "old" mappings.
- */
-static void wb_kupdate(unsigned long arg)
-{
- unsigned long oldest_jif;
- unsigned long start_jif;
- unsigned long next_jif;
- long nr_to_write;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = &oldest_jif,
- .nr_to_write = 0,
- .nonblocking = 1,
- .for_kupdate = 1,
- .range_cyclic = 1,
- };
-
- sync_supers();
-
- oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10);
- start_jif = jiffies;
- next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10);
- nr_to_write = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
- while (nr_to_write > 0) {
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- writeback_inodes(&wbc);
- if (wbc.nr_to_write > 0) {
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- else
- break; /* All the old data is written */
- }
- nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- }
- if (time_before(next_jif, jiffies + HZ))
- next_jif = jiffies + HZ;
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, next_jif);
-}
-
/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, file, buffer, length, ppos);
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, jiffies +
- msecs_to_jiffies(dirty_writeback_interval * 10));
- else
- del_timer(&wb_timer);
return 0;
}
-static void wb_timer_fn(unsigned long unused)
+static void do_laptop_sync(struct work_struct *work)
{
- if (pdflush_operation(wb_kupdate, 0) < 0)
- mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
-}
-
-static void laptop_flush(unsigned long unused)
-{
- sys_sync();
+ wakeup_flusher_threads(0);
+ kfree(work);
}
static void laptop_timer_fn(unsigned long unused)
{
- pdflush_operation(laptop_flush, 0);
+ struct work_struct *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work) {
+ INIT_WORK(work, do_laptop_sync);
+ schedule_work(work);
+ }
}
/*
{
int shift;
- mod_timer(&wb_timer,
- jiffies + msecs_to_jiffies(dirty_writeback_interval * 10));
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
#define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
SLAB_POISON | SLAB_STORE_USER)
+/*
+ * Debugging flags that require metadata to be stored in the slab. These get
+ * disabled when slub_debug=O is used and a cache's min order increases with
+ * metadata.
+ */
+#define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
+
/*
* Set of flags that will prevent slab merging
*/
#endif
static char *slub_debug_slabs;
+static int disable_higher_order_debug;
/*
* Object debugging
slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
print_section("Padding", end - remainder, remainder);
- restore_bytes(s, "slab padding", POISON_INUSE, start, end);
+ restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end);
return 0;
}
*/
goto check_slabs;
+ if (tolower(*str) == 'o') {
+ /*
+ * Avoid enabling debugging on caches if its minimum order
+ * would increase as a result.
+ */
+ disable_higher_order_debug = 1;
+ goto out;
+ }
+
slub_debug = 0;
if (*str == '-')
/*
* Enable debugging if selected on the kernel commandline.
*/
if (slub_debug && (!slub_debug_slabs ||
- strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)) == 0))
- flags |= slub_debug;
+ !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))
+ flags |= slub_debug;
return flags;
}
}
if (kmemcheck_enabled
- && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS)))
- {
+ && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
int pages = 1 << oo_order(oo);
kmemcheck_alloc_shadow(page, oo_order(oo), flags, node);
"default order: %d, min order: %d\n", s->name, s->objsize,
s->size, oo_order(s->oo), oo_order(s->min));
+ if (oo_order(s->min) > get_order(s->objsize))
+ printk(KERN_WARNING " %s debugging increased min order, use "
+ "slub_debug=O to disable.\n", s->name);
+
for_each_online_node(node) {
struct kmem_cache_node *n = get_node(s, node);
unsigned long nr_slabs;
return order;
fraction /= 2;
}
- min_objects --;
+ min_objects--;
}
/*
*/
#define NR_KMEM_CACHE_CPU 100
- static DEFINE_PER_CPU(struct kmem_cache_cpu,
- kmem_cache_cpu)[NR_KMEM_CACHE_CPU];
+ static DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU],
+ kmem_cache_cpu);
static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS);
* on bootup.
*/
align = calculate_alignment(flags, align, s->objsize);
+ s->align = align;
/*
* SLUB stores one object immediately after another beginning from
if (!calculate_sizes(s, -1))
goto error;
+ if (disable_higher_order_debug) {
+ /*
+ * Disable debugging flags that store metadata if the min slab
+ * order increased.
+ */
+ if (get_order(s->size) > get_order(s->objsize)) {
+ s->flags &= ~DEBUG_METADATA_FLAGS;
+ s->offset = 0;
+ if (!calculate_sizes(s, -1))
+ goto error;
+ }
+ }
/*
* The larger the object size is, the more pages we want on the partial
*/
void kmem_cache_destroy(struct kmem_cache *s)
{
- if (s->flags & SLAB_DESTROY_BY_RCU)
- rcu_barrier();
down_write(&slub_lock);
s->refcount--;
if (!s->refcount) {
"still has objects.\n", s->name, __func__);
dump_stack();
}
+ if (s->flags & SLAB_DESTROY_BY_RCU)
+ rcu_barrier();
sysfs_slab_remove(s);
} else
up_write(&slub_lock);
2 /* 192 */
};
+static inline int size_index_elem(size_t bytes)
+{
+ return (bytes - 1) / 8;
+}
+
static struct kmem_cache *get_slab(size_t size, gfp_t flags)
{
int index;
if (!size)
return ZERO_SIZE_PTR;
- index = size_index[(size - 1) / 8];
+ index = size_index[size_index_elem(size)];
} else
index = fls(size - 1);
slab_state = PARTIAL;
/* Caches that are not of the two-to-the-power-of size */
- if (KMALLOC_MIN_SIZE <= 64) {
+ if (KMALLOC_MIN_SIZE <= 32) {
create_kmalloc_cache(&kmalloc_caches[1],
"kmalloc-96", 96, GFP_NOWAIT);
caches++;
+ }
+ if (KMALLOC_MIN_SIZE <= 64) {
create_kmalloc_cache(&kmalloc_caches[2],
"kmalloc-192", 192, GFP_NOWAIT);
caches++;
BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
- for (i = 8; i < KMALLOC_MIN_SIZE; i += 8)
- size_index[(i - 1) / 8] = KMALLOC_SHIFT_LOW;
+ for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
+ int elem = size_index_elem(i);
+ if (elem >= ARRAY_SIZE(size_index))
+ break;
+ size_index[elem] = KMALLOC_SHIFT_LOW;
+ }
- if (KMALLOC_MIN_SIZE == 128) {
+ if (KMALLOC_MIN_SIZE == 64) {
+ /*
+ * The 96 byte size cache is not used if the alignment
+ * is 64 byte.
+ */
+ for (i = 64 + 8; i <= 96; i += 8)
+ size_index[size_index_elem(i)] = 7;
+ } else if (KMALLOC_MIN_SIZE == 128) {
/*
* The 192 byte sized cache is not used if the alignment
* is 128 byte. Redirect kmalloc to use the 256 byte cache
* instead.
*/
for (i = 128 + 8; i <= 192; i += 8)
- size_index[(i - 1) / 8] = 8;
+ size_index[size_index_elem(i)] = 8;
}
slab_state = UP;
}
err = sysfs_create_group(&s->kobj, &slab_attr_group);
- if (err)
+ if (err) {
+ kobject_del(&s->kobj);
+ kobject_put(&s->kobj);
return err;
+ }
kobject_uevent(&s->kobj, KOBJ_ADD);
if (!unmergeable) {
/* Setup first alias */
static int __init slab_proc_init(void)
{
- proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
+ proc_create("slabinfo", S_IRUGO, NULL, &proc_slabinfo_operations);
return 0;
}
module_init(slab_proc_init);
#include "rds.h"
#include "ib.h"
- DEFINE_PER_CPU(struct rds_ib_statistics, rds_ib_stats) ____cacheline_aligned;
+ DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_ib_statistics, rds_ib_stats);
-static char *rds_ib_stat_names[] = {
+static const char *const rds_ib_stat_names[] = {
"ib_connect_raced",
"ib_listen_closed_stale",
"ib_tx_cq_call",
#include "rds.h"
#include "iw.h"
- DEFINE_PER_CPU(struct rds_iw_statistics, rds_iw_stats) ____cacheline_aligned;
+ DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_iw_statistics, rds_iw_stats);
-static char *rds_iw_stat_names[] = {
+static const char *const rds_iw_stat_names[] = {
"iw_connect_raced",
"iw_listen_closed_stale",
"iw_tx_cq_call",
unsigned long r_offset;
};
- DEFINE_PER_CPU(struct rds_page_remainder, rds_page_remainders) ____cacheline_aligned;
+ DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders);
/*
* returns 0 on success or -errno on failure.
return 0;
}
+EXPORT_SYMBOL_GPL(rds_page_copy_user);
/*
* Message allocation uses this to build up regions of a message.