From 3f6da3905398826d85731247e7fbcf53400c18bd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 5 Mar 2010 13:01:18 +0100 Subject: perf: Rework and fix the arch CPU-hotplug hooks Remove the hw_perf_event_*() hotplug hooks in favour of per PMU hotplug notifiers. This has the advantage of reducing the static weak interface as well as exposing all hotplug actions to the PMU. Use this to fix x86 hotplug usage where we did things in ONLINE which should have been done in UP_PREPARE or STARTING. Signed-off-by: Peter Zijlstra Cc: Paul Mundt Cc: paulus@samba.org Cc: eranian@google.com Cc: robert.richter@amd.com Cc: fweisbec@gmail.com Cc: Arnaldo Carvalho de Melo LKML-Reference: <20100305154128.736225361@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6f8cd7da1a01..80acbf3d5de1 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -936,5 +936,21 @@ static inline void perf_event_disable(struct perf_event *event) { } #define perf_output_put(handle, x) \ perf_output_copy((handle), &(x), sizeof(x)) +/* + * This has to have a higher priority than migration_notifier in sched.c. + */ +#define perf_cpu_notifier(fn) \ +do { \ + static struct notifier_block fn##_nb __cpuinitdata = \ + { .notifier_call = fn, .priority = 20 }; \ + fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_STARTING, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_ONLINE, \ + (void *)(unsigned long)smp_processor_id()); \ + register_cpu_notifier(&fn##_nb); \ +} while (0) + #endif /* __KERNEL__ */ #endif /* _LINUX_PERF_EVENT_H */ -- cgit v1.2.1 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 --- include/linux/perf_event.h | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 80acbf3d5de1..70cffd052c04 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -452,6 +452,7 @@ enum perf_callchain_context { #include #include #include +#include #include #define PERF_MAX_STACK_DEPTH 255 @@ -847,6 +848,44 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) __perf_sw_event(event_id, nr, nmi, regs, addr); } +extern void +perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); + +/* + * Take a snapshot of the regs. Skip ip and frame pointer to + * the nth caller. We only need a few of the regs: + * - ip for PERF_SAMPLE_IP + * - cs for user_mode() tests + * - bp for callchains + * - eflags, for future purposes, just in case + */ +static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip) +{ + unsigned long ip; + + memset(regs, 0, sizeof(*regs)); + + switch (skip) { + case 1 : + ip = CALLER_ADDR0; + break; + case 2 : + ip = CALLER_ADDR1; + break; + case 3 : + ip = CALLER_ADDR2; + break; + case 4: + ip = CALLER_ADDR3; + break; + /* No need to support further for now */ + default: + ip = 0; + } + + return perf_arch_fetch_caller_regs(regs, ip, skip); +} + extern void __perf_event_mmap(struct vm_area_struct *vma); static inline void perf_event_mmap(struct vm_area_struct *vma) @@ -880,7 +919,8 @@ static inline bool perf_paranoid_kernel(void) } extern void perf_event_init(void); -extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size); +extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, + int entry_size, struct pt_regs *regs); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags -- cgit v1.2.1 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 --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 70cffd052c04..95477038a72a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -453,6 +453,7 @@ enum perf_callchain_context { #include #include #include +#include #include #define PERF_MAX_STACK_DEPTH 255 -- cgit v1.2.1