From 61e67fb9d3ed13e6a7f58652ae4979b9c872fa57 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 3 Mar 2010 07:38:37 +0100 Subject: perf/x86-64: Use frame pointer to walk on irq and process stacks We were using the frame pointer based stack walker on every contexts in x86-32, but not in x86-64 where we only use the seven-league boots on the exception stacks. Use it also on irq and process stacks. This utterly accelerate the captures. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo --- arch/x86/kernel/dumpstack_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index d5e2a2ebb627..272c9f1f05f3 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -208,7 +208,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (in_irq_stack(stack, irq_stack, irq_stack_end)) { if (ops->stack(data, "IRQ") < 0) break; - bp = print_context_stack(tinfo, stack, bp, + bp = ops->walk_stack(tinfo, stack, bp, ops, data, irq_stack_end, &graph); /* * We link to the next stack (which would be @@ -229,7 +229,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, /* * This handles the process stack: */ - bp = print_context_stack(tinfo, stack, bp, ops, data, NULL, &graph); + bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); put_cpu(); } EXPORT_SYMBOL(dump_trace); -- cgit v1.2.2 From 5331d7b84613b8325362dde53dc2bff2fb87d351 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 4 Mar 2010 21:15:56 +0100 Subject: perf: Introduce new perf_fetch_caller_regs() for hot regs snapshot Events that trigger overflows by interrupting a context can use get_irq_regs() or task_pt_regs() to retrieve the state when the event triggered. But this is not the case for some other class of events like trace events as tracepoints are executed in the same context than the code that triggered the event. It means we need a different api to capture the regs there, namely we need a hot snapshot to get the most important informations for perf: the instruction pointer to get the event origin, the frame pointer for the callchain, the code segment for user_mode() tests (we always use __KERNEL_CS as trace events always occur from the kernel) and the eflags for further purposes. v2: rename perf_save_regs to perf_fetch_caller_regs as per Masami's suggestion. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Thomas Gleixner Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Arnaldo Carvalho de Melo Cc: Masami Hiramatsu Cc: Jason Baron Cc: Archs --- arch/x86/kernel/cpu/perf_event.c | 12 ++++++++++++ arch/x86/kernel/dumpstack.h | 15 +++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1d665a0b202c..c6bde7d7afdc 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1707,3 +1707,15 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } + +void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) +{ + regs->ip = ip; + /* + * perf_arch_fetch_caller_regs adds another call, we need to increment + * the skip level + */ + regs->bp = rewind_frame_pointer(skip + 1); + regs->cs = __KERNEL_CS; + local_save_flags(regs->flags); +} diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h index 4fd1420faffa..29e5f7c845b2 100644 --- a/arch/x86/kernel/dumpstack.h +++ b/arch/x86/kernel/dumpstack.h @@ -29,4 +29,19 @@ struct stack_frame { struct stack_frame *next_frame; unsigned long return_address; }; + +static inline unsigned long rewind_frame_pointer(int n) +{ + struct stack_frame *frame; + + get_bp(frame); + +#ifdef CONFIG_FRAME_POINTER + while (n--) + frame = frame->next_frame; #endif + + return (unsigned long)frame; +} + +#endif /* DUMPSTACK_H */ -- cgit v1.2.2 From 85cfabbcd10f8d112feee6e2ec64ee78033b6d3c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 11 Mar 2010 13:06:56 +0100 Subject: perf, ppc: Fix compile error due to new cpu notifiers Fix: arch/powerpc/kernel/perf_event.c:1334: error: 'power_pmu_notifier' undeclared (first use in this function) arch/powerpc/kernel/perf_event.c:1334: error: (Each undeclared identifier is reported only once arch/powerpc/kernel/perf_event.c:1334: error: for each function it appears in.) arch/powerpc/kernel/perf_event.c:1334: error: implicit declaration of function 'power_pmu_notifier' arch/powerpc/kernel/perf_event.c:1334: error: implicit declaration of function 'register_cpu_notifier' Due to commit 3f6da390 (perf: Rework and fix the arch CPU-hotplug hooks). Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index fbe101d7505d..08460a2e9f41 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1298,7 +1298,7 @@ static void power_pmu_setup(int cpu) } static int __cpuinit -power_pmu_notify(struct notifier_block *self, unsigned long action, void *hcpu) +power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; -- cgit v1.2.2 From 45e16a6834b6af098702e5ea6c9a40de42ff77d8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 11 Mar 2010 13:40:30 +0100 Subject: perf, x86: Fix hw_perf_enable() event assignment What happens is that we schedule badly like: <...>-1987 [019] 280.252808: x86_pmu_start: event-46/1300c0: idx: 0 <...>-1987 [019] 280.252811: x86_pmu_start: event-47/1300c0: idx: 1 <...>-1987 [019] 280.252812: x86_pmu_start: event-48/1300c0: idx: 2 <...>-1987 [019] 280.252813: x86_pmu_start: event-49/1300c0: idx: 3 <...>-1987 [019] 280.252814: x86_pmu_start: event-50/1300c0: idx: 32 <...>-1987 [019] 280.252825: x86_pmu_stop: event-46/1300c0: idx: 0 <...>-1987 [019] 280.252826: x86_pmu_stop: event-47/1300c0: idx: 1 <...>-1987 [019] 280.252827: x86_pmu_stop: event-48/1300c0: idx: 2 <...>-1987 [019] 280.252828: x86_pmu_stop: event-49/1300c0: idx: 3 <...>-1987 [019] 280.252829: x86_pmu_stop: event-50/1300c0: idx: 32 <...>-1987 [019] 280.252834: x86_pmu_start: event-47/1300c0: idx: 1 <...>-1987 [019] 280.252834: x86_pmu_start: event-48/1300c0: idx: 2 <...>-1987 [019] 280.252835: x86_pmu_start: event-49/1300c0: idx: 3 <...>-1987 [019] 280.252836: x86_pmu_start: event-50/1300c0: idx: 32 <...>-1987 [019] 280.252837: x86_pmu_start: event-51/1300c0: idx: 32 *FAIL* This happens because we only iterate the n_running events in the first pass, and reset their index to -1 if they don't match to force a re-assignment. Now, in our RR example, n_running == 0 because we fully unscheduled, so event-50 will retain its idx==32, even though in scheduling it will have gotten idx=0, and we don't trigger the re-assign path. The easiest way to fix this is the below patch, which simply validates the full assignment in the second pass. Reported-by: Stephane Eranian Signed-off-by: Peter Zijlstra LKML-Reference: <1268311069.5037.31.camel@laptop> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index c6bde7d7afdc..5fb490c6ee5c 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -811,7 +811,6 @@ void hw_perf_enable(void) * step2: reprogram moved events into new counters */ for (i = 0; i < n_running; i++) { - event = cpuc->event_list[i]; hwc = &event->hw; @@ -826,21 +825,16 @@ void hw_perf_enable(void) continue; x86_pmu_stop(event); - - hwc->idx = -1; } for (i = 0; i < cpuc->n_events; i++) { - event = cpuc->event_list[i]; hwc = &event->hw; - if (i < n_running && - match_prev_assignment(hwc, cpuc, i)) - continue; - - if (hwc->idx == -1) + if (!match_prev_assignment(hwc, cpuc, i)) x86_assign_hw_event(event, cpuc, i); + else if (i < n_running) + continue; x86_pmu_start(event); } -- cgit v1.2.2 From 639fe4b12f92b54c9c3b38c82cdafaa38cfd3e63 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 11 Mar 2010 15:30:35 +0800 Subject: perf: export perf_trace_regs and perf_arch_fetch_caller_regs Export perf_trace_regs and perf_arch_fetch_caller_regs since module will use these. Signed-off-by: Xiao Guangrong [ use EXPORT_PER_CPU_SYMBOL_GPL() ] Signed-off-by: Peter Zijlstra LKML-Reference: <4B989C1B.2090407@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5fb490c6ee5c..7645faea8e85 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1713,3 +1713,4 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski regs->cs = __KERNEL_CS; local_save_flags(regs->flags); } +EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs); -- cgit v1.2.2