* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (57 commits)
x86, perf events: Check if we have APIC enabled
perf_event: Fix variable initialization in other codepaths
perf kmem: Fix unused argument build warning
perf symbols: perf_header__read_build_ids() offset'n'size should be u64
perf symbols: dsos__read_build_ids() should read both user and kernel buildids
perf tools: Align long options which have no short forms
perf kmem: Show usage if no option is specified
sched: Mark sched_clock() as notrace
perf sched: Add max delay time snapshot
perf tools: Correct size given to memset
perf_event: Fix perf_swevent_hrtimer() variable initialization
perf sched: Fix for getting task's execution time
tracing/kprobes: Fix field creation's bad error handling
perf_event: Cleanup for cpu_clock_perf_event_update()
perf_event: Allocate children's perf_event_ctxp at the right time
perf_event: Clean up __perf_event_init_context()
hw-breakpoints: Modify breakpoints without unregistering them
perf probe: Update perf-probe document
perf probe: Support --del option
trace-kprobe: Support delete probe syntax
...
def_bool y
config X86_DECODER_SELFTEST
- bool "x86 instruction decoder selftest"
- depends on DEBUG_KERNEL
+ bool "x86 instruction decoder selftest"
+ depends on DEBUG_KERNEL && KPROBES
---help---
Perform x86 instruction decoder selftests at build time.
This option is useful for checking the sanity of x86 instruction
If unsure, say N.
+config DEBUG_STRICT_USER_COPY_CHECKS
+ bool "Strict copy size checks"
+ depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING
+ ---help---
+ Enabling this option turns a certain set of sanity checks for user
+ copy operations into compile time failures.
+
+ The copy_from_user() etc checks are there to help test if there
+ are sufficient security checks on the length argument of
+ the copy operation, by having gcc prove that the argument is
+ within bounds.
+
+ If unsure, or if you run an older (pre 4.4) gcc, say N.
+
endmenu
return 0;
/*
- * If we are way outside a reasoable range then just skip forward:
+ * If we are way outside a reasonable range then just skip forward:
*/
if (unlikely(left <= -period)) {
left = period;
data.period = event->hw.last_period;
data.addr = 0;
+ data.raw = NULL;
regs.ip = 0;
/*
u64 val;
data.addr = 0;
+ data.raw = NULL;
cpuc = &__get_cpu_var(cpu_hw_events);
u64 ack, status;
data.addr = 0;
+ data.raw = NULL;
cpuc = &__get_cpu_var(cpu_hw_events);
u64 val;
data.addr = 0;
+ data.raw = NULL;
cpuc = &__get_cpu_var(cpu_hw_events);
x86_pmu = p6_pmu;
- if (!cpu_has_apic) {
- pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n");
- pr_info("no hardware sampling interrupt available.\n");
- x86_pmu.apic = 0;
- }
-
return 0;
}
return 0;
}
+ static void __init pmu_check_apic(void)
+ {
+ if (cpu_has_apic)
+ return;
+
+ x86_pmu.apic = 0;
+ pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n");
+ pr_info("no hardware sampling interrupt available.\n");
+ }
+
void __init init_hw_perf_events(void)
{
int err;
return;
}
+ pmu_check_apic();
+
pr_cont("%s PMU driver.\n", x86_pmu.name);
if (x86_pmu.num_events > X86_PMC_MAX_GENERIC) {
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);
+ static DEFINE_PER_CPU(int, in_ignored_frame);
static void
static int backtrace_stack(void *data, char *name)
{
- per_cpu(in_nmi_frame, smp_processor_id()) =
- x86_is_stack_id(NMI_STACK, name);
+ per_cpu(in_ignored_frame, smp_processor_id()) =
+ x86_is_stack_id(NMI_STACK, name) ||
+ x86_is_stack_id(DEBUG_STACK, name);
return 0;
}
{
struct perf_callchain_entry *entry = data;
- if (per_cpu(in_nmi_frame, smp_processor_id()))
+ if (per_cpu(in_ignored_frame, smp_processor_id()))
return;
if (reliable)
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/kexec.h>
+#include <linux/sysfs.h>
#include <linux/bug.h>
#include <linux/nmi.h>
-#include <linux/sysfs.h>
#include <asm/stacktrace.h>
#include "dumpstack.h"
+#define N_EXCEPTION_STACKS_END \
+ (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
static char x86_stack_ids[][8] = {
- [DEBUG_STACK - 1] = "#DB",
- [NMI_STACK - 1] = "NMI",
- [DOUBLEFAULT_STACK - 1] = "#DF",
- [STACKFAULT_STACK - 1] = "#SS",
- [MCE_STACK - 1] = "#MC",
+ [ DEBUG_STACK-1 ] = "#DB",
+ [ NMI_STACK-1 ] = "NMI",
+ [ DOUBLEFAULT_STACK-1 ] = "#DF",
+ [ STACKFAULT_STACK-1 ] = "#SS",
+ [ MCE_STACK-1 ] = "#MC",
#if DEBUG_STKSZ > EXCEPTION_STKSZ
- [N_EXCEPTION_STACKS ...
- N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
+ [ N_EXCEPTION_STACKS ...
+ N_EXCEPTION_STACKS_END ] = "#DB[?]"
#endif
- };
+};
int x86_is_stack_id(int id, char *name)
{
}
static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
- unsigned *usedp, char **idp)
+ unsigned *usedp, char **idp)
{
unsigned k;
return NULL;
}
+ static inline int
+ in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
+ unsigned long *irq_stack_end)
+ {
+ return (stack >= irq_stack && stack < irq_stack_end);
+ }
+
+ /*
+ * We are returning from the irq stack and go to the previous one.
+ * If the previous stack is also in the irq stack, then bp in the first
+ * frame of the irq stack points to the previous, interrupted one.
+ * Otherwise we have another level of indirection: We first save
+ * the bp of the previous stack, then we switch the stack to the irq one
+ * and save a new bp that links to the previous one.
+ * (See save_args())
+ */
+ static inline unsigned long
+ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
+ unsigned long *irq_stack, unsigned long *irq_stack_end)
+ {
+ #ifdef CONFIG_FRAME_POINTER
+ struct stack_frame *frame = (struct stack_frame *)bp;
+
+ if (!in_irq_stack(stack, irq_stack, irq_stack_end))
+ return (unsigned long)frame->next_frame;
+ #endif
+ return bp;
+ }
+
/*
* x86-64 can have up to three kernel stacks:
* process stack
irq_stack = irq_stack_end -
(IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
- if (stack >= irq_stack && stack < irq_stack_end) {
+ if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
if (ops->stack(data, "IRQ") < 0)
break;
bp = print_context_stack(tinfo, stack, bp,
* pointer (index -1 to end) in the IRQ stack:
*/
stack = (unsigned long *) (irq_stack_end[-1]);
+ bp = fixup_bp_irq_link(bp, stack, irq_stack,
+ irq_stack_end);
irq_stack_end = NULL;
ops->stack(data, "EOI");
continue;
void
show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *sp, unsigned long bp, char *log_lvl)
+ unsigned long *sp, unsigned long bp, char *log_lvl)
{
+ unsigned long *irq_stack_end;
+ unsigned long *irq_stack;
unsigned long *stack;
+ int cpu;
int i;
- const int cpu = smp_processor_id();
- unsigned long *irq_stack_end =
- (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
- unsigned long *irq_stack =
- (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
+
+ preempt_disable();
+ cpu = smp_processor_id();
+
+ irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
+ irq_stack = (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
/*
- * debugging aid: "show_stack(NULL, NULL);" prints the
- * back trace for this cpu.
+ * Debugging aid: "show_stack(NULL, NULL);" prints the
+ * back trace for this cpu:
*/
-
if (sp == NULL) {
if (task)
sp = (unsigned long *)task->thread.sp;
printk(" %016lx", *stack++);
touch_nmi_watchdog();
}
+ preempt_enable();
+
printk("\n");
show_trace_log_lvl(task, regs, sp, bp, log_lvl);
}
return ud2 == 0x0b0f;
}
-
#endif
apicinterrupt LOCAL_TIMER_VECTOR \
apic_timer_interrupt smp_apic_timer_interrupt
-apicinterrupt GENERIC_INTERRUPT_VECTOR \
- generic_interrupt smp_generic_interrupt
+apicinterrupt X86_PLATFORM_IPI_VECTOR \
+ x86_platform_ipi smp_x86_platform_ipi
#ifdef CONFIG_SMP
apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \
TRACE_IRQS_OFF
movq %rsp,%rdi /* pt_regs pointer */
xorl %esi,%esi /* no error code */
- PER_CPU(init_tss, %rbp)
- subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
+ PER_CPU(init_tss, %r12)
+ subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12)
call \do_sym
- addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
+ addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12)
jmp paranoid_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
END(\sym)
leaq irq_return(%rip),%rcx
cmpq %rcx,RIP+8(%rsp)
je error_swapgs
- movl %ecx,%ecx /* zero extend */
- cmpq %rcx,RIP+8(%rsp)
- je error_swapgs
+ movl %ecx,%eax /* zero extend */
+ cmpq %rax,RIP+8(%rsp)
+ je bstep_iret
cmpq $gs_change,RIP+8(%rsp)
je error_swapgs
jmp error_sti
+
+bstep_iret:
+ /* Fix truncated RIP */
+ movq %rcx,RIP+8(%rsp)
+ jmp error_swapgs
END(error_entry)
extern void calc_global_load(void);
-extern u64 cpu_nr_migrations(int cpu);
extern unsigned long get_parent_ip(unsigned long addr);
}
#endif
-extern unsigned long long time_sync_thresh;
-
/*
* Task state bitmask. NOTE! These bits are also
* encoded in fs/proc/array.c: get_task_state().
extern signed long schedule_timeout_interruptible(signed long timeout);
extern signed long schedule_timeout_killable(signed long timeout);
extern signed long schedule_timeout_uninterruptible(signed long timeout);
-asmlinkage void __schedule(void);
asmlinkage void schedule(void);
extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
cputime_t utime, stime, cutime, cstime;
cputime_t gtime;
cputime_t cgtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+ cputime_t prev_utime, prev_stime;
+#endif
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
unsigned long inblock, oublock, cinblock, coublock;
return to_cpumask(sd->span);
}
-extern void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new);
+/* Allocate an array of sched domains, for partition_sched_domains(). */
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
+
/* Test a flag in parent sched domain */
static inline int test_sd_parent(struct sched_domain *sd, int flag)
{
struct sched_domain_attr;
static inline void
-partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
}
cputime_t utime, stime, utimescaled, stimescaled;
cputime_t gtime;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
cputime_t prev_utime, prev_stime;
+#endif
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time; /* monotonic time */
struct timespec real_start_time; /* boot based time */
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned int irq_events;
- int hardirqs_enabled;
unsigned long hardirq_enable_ip;
- unsigned int hardirq_enable_event;
unsigned long hardirq_disable_ip;
+ unsigned int hardirq_enable_event;
unsigned int hardirq_disable_event;
- int softirqs_enabled;
+ int hardirqs_enabled;
+ int hardirq_context;
unsigned long softirq_disable_ip;
- unsigned int softirq_disable_event;
unsigned long softirq_enable_ip;
+ unsigned int softirq_disable_event;
unsigned int softirq_enable_event;
- int hardirq_context;
+ int softirqs_enabled;
int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
__put_task_struct(t);
}
-extern cputime_t task_utime(struct task_struct *p);
-extern cputime_t task_stime(struct task_struct *p);
-extern cputime_t task_gtime(struct task_struct *p);
+extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
/*
* Per process flags
extern int sched_clock_stable;
#endif
- extern unsigned long long sched_clock(void);
+ /* ftrace calls sched_clock() directly */
+ extern unsigned long long notrace sched_clock(void);
extern void sched_clock_init(void);
extern u64 sched_clock_cpu(int cpu);
return info <= SEND_SIG_FORCED;
}
-/* True if we are on the alternate signal stack. */
-
+/*
+ * True if we are on the alternate signal stack.
+ */
static inline int on_sig_stack(unsigned long sp)
{
- return (sp - current->sas_ss_sp < current->sas_ss_size);
+#ifdef CONFIG_STACK_GROWSUP
+ return sp >= current->sas_ss_sp &&
+ sp - current->sas_ss_sp < current->sas_ss_size;
+#else
+ return sp > current->sas_ss_sp &&
+ sp - current->sas_ss_sp <= current->sas_ss_size;
+#endif
}
static inline int sas_ss_flags(unsigned long sp)
/*
* Each CPU has a list of per CPU events:
*/
- DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
+ static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
int perf_max_events __read_mostly = 1;
static int perf_reserved_percpu __read_mostly;
if (!task) {
/*
* Per cpu events are removed via an smp call and
- * the removal is always sucessful.
+ * the removal is always successful.
*/
smp_call_function_single(event->cpu,
__perf_event_remove_from_context,
* is the current context on this CPU and preemption is disabled,
* hence we can't get into perf_event_task_sched_out for this context.
*/
- static void perf_event_disable(struct perf_event *event)
+ void perf_event_disable(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
if (!task) {
/*
* Per cpu events are installed via an smp call and
- * the install is always sucessful.
+ * the install is always successful.
*/
smp_call_function_single(cpu, __perf_install_in_context,
event, 1);
* perf_event_for_each_child or perf_event_for_each as described
* for perf_event_disable.
*/
- static void perf_event_enable(struct perf_event *event)
+ void perf_event_enable(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
__perf_event_init_context(struct perf_event_context *ctx,
struct task_struct *task)
{
- memset(ctx, 0, sizeof(*ctx));
spin_lock_init(&ctx->lock);
mutex_init(&ctx->mutex);
INIT_LIST_HEAD(&ctx->group_list);
}
if (!ctx) {
- ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+ ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
err = -ENOMEM;
if (!ctx)
goto errout;
event->pmu->read(event);
data.addr = 0;
+ data.raw = NULL;
data.period = event->hw.last_period;
regs = get_irq_regs();
/*
u64 now;
now = cpu_clock(cpu);
- prev = atomic64_read(&event->hw.prev_count);
- atomic64_set(&event->hw.prev_count, now);
+ prev = atomic64_xchg(&event->hw.prev_count, now);
atomic64_add(now - prev, &event->count);
}
static const struct pmu *bp_perf_event_init(struct perf_event *bp)
{
int err;
- /*
- * The breakpoint is already filled if we haven't created the counter
- * through perf syscall
- * FIXME: manage to get trigerred to NULL if it comes from syscalls
- */
- if (!bp->callback)
- err = register_perf_hw_breakpoint(bp);
- else
- err = __register_perf_hw_breakpoint(bp);
+
+ err = register_perf_hw_breakpoint(bp);
if (err)
return ERR_PTR(err);
struct perf_sample_data sample;
struct pt_regs *regs = data;
+ sample.raw = NULL;
sample.addr = bp->attr.bp_addr;
if (!perf_exclude_event(bp, regs))
struct perf_event_context *ctx,
struct perf_event *group_leader,
struct perf_event *parent_event,
- perf_callback_t callback,
+ perf_overflow_handler_t overflow_handler,
gfp_t gfpflags)
{
const struct pmu *pmu;
event->state = PERF_EVENT_STATE_INACTIVE;
- if (!callback && parent_event)
- callback = parent_event->callback;
+ if (!overflow_handler && parent_event)
+ overflow_handler = parent_event->overflow_handler;
- event->callback = callback;
+ event->overflow_handler = overflow_handler;
if (attr->disabled)
event->state = PERF_EVENT_STATE_OFF;
*/
struct perf_event *
perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
- pid_t pid, perf_callback_t callback)
+ pid_t pid,
+ perf_overflow_handler_t overflow_handler)
{
struct perf_event *event;
struct perf_event_context *ctx;
}
event = perf_event_alloc(attr, cpu, ctx, NULL,
- NULL, callback, GFP_KERNEL);
+ NULL, overflow_handler, GFP_KERNEL);
if (IS_ERR(event)) {
err = PTR_ERR(event);
goto err_put_context;
*/
int perf_event_init_task(struct task_struct *child)
{
- struct perf_event_context *child_ctx, *parent_ctx;
+ struct perf_event_context *child_ctx = NULL, *parent_ctx;
struct perf_event_context *cloned_ctx;
struct perf_event *event;
struct task_struct *parent = current;
if (likely(!parent->perf_event_ctxp))
return 0;
- /*
- * This is executed from the parent task context, so inherit
- * events that have been marked for cloning.
- * First allocate and initialize a context for the child.
- */
-
- child_ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
- if (!child_ctx)
- return -ENOMEM;
-
- __perf_event_init_context(child_ctx, child);
- child->perf_event_ctxp = child_ctx;
- get_task_struct(child);
-
/*
* If the parent's context is a clone, pin it so it won't get
* swapped under us.
continue;
}
+ if (!child->perf_event_ctxp) {
+ /*
+ * This is executed from the parent task context, so
+ * inherit events that have been marked for cloning.
+ * First allocate and initialize a context for the
+ * child.
+ */
+
+ child_ctx = kzalloc(sizeof(struct perf_event_context),
+ GFP_KERNEL);
+ if (!child_ctx) {
+ ret = -ENOMEM;
+ goto exit;
+ }
+
+ __perf_event_init_context(child_ctx, child);
+ child->perf_event_ctxp = child_ctx;
+ get_task_struct(child);
+ }
+
ret = inherit_group(event, parent, parent_ctx,
child, child_ctx);
if (ret) {
get_ctx(child_ctx->parent_ctx);
}
+ exit:
mutex_unlock(&parent_ctx->mutex);
perf_unpin_context(parent_ctx);