From 44ee63587dce85593c22497140db16f4e5027860 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 17 Feb 2010 10:50:50 +0900 Subject: percpu: Add __percpu sparse annotations to hw_breakpoint Add __percpu sparse annotations to hw_breakpoint. These annotations are to make sparse consider percpu variables to be in a different address space and warn if accessed without going through percpu accessors. This patch doesn't affect normal builds. In kernel/hw_breakpoint.c, per_cpu(nr_task_bp_pinned, cpu)'s will trigger spurious noderef related warnings from sparse. Changing it to &per_cpu(nr_task_bp_pinned[0], cpu) will work around the problem but deemed to ugly by the maintainer. Leave it alone until better solution can be found. Signed-off-by: Tejun Heo Cc: Stephen Rothwell Cc: K.Prasad LKML-Reference: <4B7B4B7A.9050902@kernel.org> Signed-off-by: Frederic Weisbecker --- include/linux/hw_breakpoint.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index 5977b724f7c6..c70d27af03f9 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -66,14 +66,14 @@ register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, perf_overflow_handler_t triggered, int cpu); -extern struct perf_event ** +extern struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered); extern int register_perf_hw_breakpoint(struct perf_event *bp); extern int __register_perf_hw_breakpoint(struct perf_event *bp); extern void unregister_hw_breakpoint(struct perf_event *bp); -extern void unregister_wide_hw_breakpoint(struct perf_event **cpu_events); +extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events); extern int dbg_reserve_bp_slot(struct perf_event *bp); extern int dbg_release_bp_slot(struct perf_event *bp); @@ -100,7 +100,7 @@ static inline struct perf_event * register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, perf_overflow_handler_t triggered, int cpu) { return NULL; } -static inline struct perf_event ** +static inline struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered) { return NULL; } static inline int @@ -109,7 +109,7 @@ static inline int __register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } static inline void unregister_hw_breakpoint(struct perf_event *bp) { } static inline void -unregister_wide_hw_breakpoint(struct perf_event **cpu_events) { } +unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) { } static inline int reserve_bp_slot(struct perf_event *bp) {return -ENOSYS; } static inline void release_bp_slot(struct perf_event *bp) { } -- cgit v1.2.3 From dd8b1cf681eab40bc5afb67bdd06b2ca341f5669 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 27 Feb 2010 17:10:39 +0100 Subject: perf: Remove pointless breakpoint union Remove pointless union in the breakpoint field of hw_perf_event. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Paul Mackerras --- include/linux/perf_event.h | 5 ++--- lib/Kconfig.debug | 8 +++++--- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7b18b4fd5df7..04f06b4be297 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -487,9 +487,8 @@ struct hw_perf_event { struct hrtimer hrtimer; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT - union { /* breakpoint */ - struct arch_hw_breakpoint info; - }; + /* breakpoint */ + struct arch_hw_breakpoint info; #endif }; atomic64_t prev_count; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 65f964e7fe78..4dc24cc13f5c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -520,11 +520,13 @@ config LOCK_STAT For more details, see Documentation/lockstat.txt - You can analyze lock events with "perf lock", subcommand of perf. - If you want to use "perf lock", you need to turn on CONFIG_EVENT_TRACING. + This also enables lock events required by "perf lock", + subcommand of perf. + If you want to use "perf lock", you also need to turn on + CONFIG_EVENT_TRACING. CONFIG_LOCK_STAT defines "contended" and "acquired" lock events. - (CONFIG_LOCKDEP defines "acquire" and "release" events.) + (CONFIG_LOCKDEP defines "acquire" and "release" events.) config DEBUG_LOCKDEP bool "Lock dependency engine debugging" -- cgit v1.2.3 From 320ebf09cbb6d01954c9a060266aa8e0d27f4638 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 2 Mar 2010 12:35:37 +0100 Subject: perf, x86: Restrict the ANY flag The ANY flag can show SMT data of another task (like 'top'), so we want to disable it when system-wide profiling is disabled. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 3 +++ include/linux/perf_event.h | 15 +++++++++++++++ kernel/perf_event.c | 15 --------------- 3 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 6531b4bdb22d..aab2e1ce9dee 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -503,6 +503,9 @@ static int __hw_perf_event_init(struct perf_event *event) */ if (attr->type == PERF_TYPE_RAW) { hwc->config |= x86_pmu.raw_event(attr->config); + if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) && + perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) + return -EACCES; return 0; } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 04f06b4be297..90e0521b1690 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -857,6 +857,21 @@ extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; +static inline bool perf_paranoid_tracepoint_raw(void) +{ + return sysctl_perf_event_paranoid > -1; +} + +static inline bool perf_paranoid_cpu(void) +{ + return sysctl_perf_event_paranoid > 0; +} + +static inline bool perf_paranoid_kernel(void) +{ + return sysctl_perf_event_paranoid > 1; +} + 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_bp_event(struct perf_event *event, void *data); diff --git a/kernel/perf_event.c b/kernel/perf_event.c index a661e7991865..482d5e1d3764 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -56,21 +56,6 @@ static atomic_t nr_task_events __read_mostly; */ int sysctl_perf_event_paranoid __read_mostly = 1; -static inline bool perf_paranoid_tracepoint_raw(void) -{ - return sysctl_perf_event_paranoid > -1; -} - -static inline bool perf_paranoid_cpu(void) -{ - return sysctl_perf_event_paranoid > 0; -} - -static inline bool perf_paranoid_kernel(void) -{ - return sysctl_perf_event_paranoid > 1; -} - int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */ /* -- cgit v1.2.3 From dc1d628a67a8f042e711ea5accc0beedc3ef0092 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 3 Mar 2010 15:55:04 +0100 Subject: perf: Provide generic perf_sample_data initialization This makes it easier to extend perf_sample_data and fixes a bug on arm and sparc, which failed to set ->raw to NULL, which can cause crashes when combined with PERF_SAMPLE_RAW. It also optimizes PowerPC and tracepoint, because the struct initialization is forced to zero out the whole structure. Signed-off-by: Peter Zijlstra Acked-by: Jean Pihet Reviewed-by: Frederic Weisbecker Acked-by: David S. Miller Cc: Jamie Iles Cc: Paul Mackerras Cc: Stephane Eranian Cc: stable@kernel.org LKML-Reference: <20100304140100.315416040@chello.nl> Signed-off-by: Ingo Molnar --- arch/arm/kernel/perf_event.c | 4 ++-- arch/powerpc/kernel/perf_event.c | 8 ++++---- arch/sparc/kernel/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.c | 3 +-- arch/x86/kernel/cpu/perf_event_intel.c | 6 ++---- include/linux/perf_event.h | 7 +++++++ kernel/perf_event.c | 21 ++++++++------------- 7 files changed, 25 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index c54ceb3d1f97..3875d99cc40f 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -965,7 +965,7 @@ armv6pmu_handle_irq(int irq_num, */ armv6_pmcr_write(pmcr); - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx <= armpmu->num_events; ++idx) { @@ -1945,7 +1945,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx <= armpmu->num_events; ++idx) { diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index b6cf8f1f4d35..5120bd44f69a 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -1164,10 +1164,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, * Finally record data if requested. */ if (record) { - struct perf_sample_data data = { - .addr = ~0ULL, - .period = event->hw.last_period, - }; + struct perf_sample_data data; + + perf_sample_data_init(&data, ~0ULL); + data.period = event->hw.last_period; if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 9f2b2bac8b2b..6504208f375f 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1189,7 +1189,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self, regs = args->regs; - data.addr = 0; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 97cddbf32936..42aafd11e170 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1097,8 +1097,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 73102df8bfc1..44b60c852107 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -590,10 +590,9 @@ static void intel_pmu_drain_bts_buffer(void) ds->bts_index = ds->bts_buffer_base; + perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - data.addr = 0; - data.raw = NULL; regs.ip = 0; /* @@ -742,8 +741,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) int bit, loops; u64 ack, status; - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 90e0521b1690..6f8cd7da1a01 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -801,6 +801,13 @@ struct perf_sample_data { struct perf_raw_record *raw; }; +static inline +void perf_sample_data_init(struct perf_sample_data *data, u64 addr) +{ + data->addr = addr; + data->raw = NULL; +} + extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, diff --git a/kernel/perf_event.c b/kernel/perf_event.c index e68745053013..4393b9e73740 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4108,8 +4108,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi, if (rctx < 0) return; - data.addr = addr; - data.raw = NULL; + perf_sample_data_init(&data, addr); do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs); @@ -4154,11 +4153,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) struct perf_event *event; u64 period; - event = container_of(hrtimer, struct perf_event, hw.hrtimer); + event = container_of(hrtimer, struct perf_event, hw.hrtimer); event->pmu->read(event); - data.addr = 0; - data.raw = NULL; + perf_sample_data_init(&data, 0); data.period = event->hw.last_period; regs = get_irq_regs(); /* @@ -4322,17 +4320,15 @@ static const struct pmu perf_ops_task_clock = { void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size) { + struct pt_regs *regs = get_irq_regs(); + struct perf_sample_data data; struct perf_raw_record raw = { .size = entry_size, .data = record, }; - struct perf_sample_data data = { - .addr = addr, - .raw = &raw, - }; - - struct pt_regs *regs = get_irq_regs(); + perf_sample_data_init(&data, addr); + data.raw = &raw; if (!regs) regs = task_pt_regs(current); @@ -4448,8 +4444,7 @@ void perf_bp_event(struct perf_event *bp, void *data) struct perf_sample_data sample; struct pt_regs *regs = data; - sample.raw = NULL; - sample.addr = bp->attr.bp_addr; + perf_sample_data_init(&sample, bp->attr.bp_addr); if (!perf_exclude_event(bp, regs)) perf_swevent_add(bp, 1, 1, &sample, regs); -- cgit v1.2.3