From c9fdfa14c3792c0160849c484e83aa57afd80ccc Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 14 May 2015 23:09:58 +0200 Subject: perf: add new PERF_SAMPLE_BRANCH_IND_JUMP branch sample type This patch adds a new branch_sample_type flag to enable filtering branch sampling to indirect jumps. The support is subject to hardware or kernel software support on each architecture. Filtering on indirect jump is useful to study the targets of the jump. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andi Kleen Cc: Andrew Morton Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@redhat.com Cc: dsahern@gmail.com Cc: jolsa@redhat.com Cc: kan.liang@intel.com Cc: namhyung@kernel.org Link: http://lkml.kernel.org/r/1431637800-31061-2-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- include/uapi/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 309211b3eb67..c4622f1ce046 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -167,6 +167,7 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */ PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */ + PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -186,6 +187,7 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, + PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; -- cgit v1.2.3 From f38b0dbb491a6987e198aa6b428db8692a6480f8 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Sun, 10 May 2015 15:13:14 -0400 Subject: perf/x86/intel: Introduce PERF_RECORD_LOST_SAMPLES After enlarging the PEBS interrupt threshold, there may be some mixed up PEBS samples which are discarded by the kernel. This patch makes the kernel emit a PERF_RECORD_LOST_SAMPLES record with the number of possible discarded records when it is impossible to demux the samples. It makes sure the user is not left in the dark about such discards. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@infradead.org Cc: eranian@google.com Link: http://lkml.kernel.org/r/1431285195-14269-8-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_ds.c | 20 ++++++++++++++++--- include/linux/perf_event.h | 3 +++ include/uapi/linux/perf_event.h | 12 +++++++++++ kernel/events/core.c | 33 +++++++++++++++++++++++++++++++ 4 files changed, 65 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 266079a3a646..34d0c4816141 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -1126,6 +1126,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) void *base, *at, *top; int bit; short counts[MAX_PEBS_EVENTS] = {}; + short error[MAX_PEBS_EVENTS] = {}; if (!x86_pmu.pebs_active) return; @@ -1169,20 +1170,33 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) /* slow path */ pebs_status = p->status & cpuc->pebs_enabled; pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; - if (pebs_status != (1 << bit)) + if (pebs_status != (1 << bit)) { + u8 i; + + for_each_set_bit(i, (unsigned long *)&pebs_status, + MAX_PEBS_EVENTS) + error[i]++; continue; + } } counts[bit]++; } for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { - if (counts[bit] == 0) + if ((counts[bit] == 0) && (error[bit] == 0)) continue; event = cpuc->events[bit]; WARN_ON_ONCE(!event); WARN_ON_ONCE(!event->attr.precise_ip); - __intel_pmu_pebs_event(event, iregs, base, top, bit, counts[bit]); + /* log dropped samples number */ + if (error[bit]) + perf_log_lost_samples(event, error[bit]); + + if (counts[bit]) { + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit]); + } } } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5f192e1bc98e..a204d5266f5f 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -743,6 +743,9 @@ perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); +extern void +perf_log_lost_samples(struct perf_event *event, u64 lost); + static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index c4622f1ce046..613ed9ad588f 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -802,6 +802,18 @@ enum perf_event_type { */ PERF_RECORD_ITRACE_START = 12, + /* + * Records the dropped/lost sample number. + * + * struct { + * struct perf_event_header header; + * + * u64 lost; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_LOST_SAMPLES = 13, + PERF_RECORD_MAX, /* non-ABI */ }; diff --git a/kernel/events/core.c b/kernel/events/core.c index e499b4e43aff..9e0773d5d110 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5974,6 +5974,39 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head, perf_output_end(&handle); } +/* + * Lost/dropped samples logging + */ +void perf_log_lost_samples(struct perf_event *event, u64 lost) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + struct { + struct perf_event_header header; + u64 lost; + } lost_samples_event = { + .header = { + .type = PERF_RECORD_LOST_SAMPLES, + .misc = 0, + .size = sizeof(lost_samples_event), + }, + .lost = lost, + }; + + perf_event_header__init_id(&lost_samples_event.header, &sample, event); + + ret = perf_output_begin(&handle, event, + lost_samples_event.header.size); + if (ret) + return; + + perf_output_put(&handle, lost_samples_event); + perf_event__output_id_sample(event, &handle, &sample); + perf_output_end(&handle); +} + /* * IRQ throttle logging */ -- cgit v1.2.3 From 930e6fcd2bcce9bcd9d4aa7e755678d33f3fe6f4 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 17 Jun 2015 09:51:10 -0400 Subject: perf tools: Add time out to force stop proc map processing System wide sampling like 'perf top' or 'perf record -a' read all threads /proc/xxx/maps before sampling. If there are any threads which generating a keeping growing huge maps, perf will do infinite loop during synthesizing. Nothing will be sampled. This patch fixes this issue by adding per-thread timeout to force stop this kind of endless proc map processing. PERF_RECORD_MISC_PROC_MAP_PARSE_TIME_OUT is introduced to indicate that the mmap record are truncated by time out. User will get warning notification when truncated mmap records are detected. Reported-by: Ying Huang Signed-off-by: Kan Liang Cc: Andi Kleen Cc: David Ahern Cc: Ying Huang Link: http://lkml.kernel.org/r/1434549071-25611-1-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/uapi/linux/perf_event.h | 4 ++++ tools/perf/util/event.c | 18 ++++++++++++++++++ tools/perf/util/event.h | 1 + tools/perf/util/session.c | 11 +++++++++++ 4 files changed, 34 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 613ed9ad588f..d97f84c080da 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -565,6 +565,10 @@ struct perf_event_mmap_page { #define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0) #define PERF_RECORD_MISC_GUEST_USER (5 << 0) +/* + * Indicates that /proc/PID/maps parsing are truncated by time out. + */ +#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12) /* * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on * different events so can reuse the same bit position. diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 793b1503d437..416ba80c628f 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -213,6 +213,8 @@ static int perf_event__synthesize_fork(struct perf_tool *tool, return 0; } +#define PROC_MAP_PARSE_TIMEOUT (500 * 1000000ULL) + int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, @@ -222,6 +224,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, { char filename[PATH_MAX]; FILE *fp; + unsigned long long t; + bool truncation = false; int rc = 0; if (machine__is_default_guest(machine)) @@ -240,6 +244,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, } event->header.type = PERF_RECORD_MMAP2; + t = rdclock(); while (1) { char bf[BUFSIZ]; @@ -253,6 +258,12 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, if (fgets(bf, sizeof(bf), fp) == NULL) break; + if ((rdclock() - t) > PROC_MAP_PARSE_TIMEOUT) { + pr_warning("Reading %s time out.\n", filename); + truncation = true; + goto out; + } + /* ensure null termination since stack will be reused. */ strcpy(execname, ""); @@ -301,6 +312,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, event->header.misc |= PERF_RECORD_MISC_MMAP_DATA; } +out: + if (truncation) + event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT; + if (!strcmp(execname, "")) strcpy(execname, anonstr); @@ -319,6 +334,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, rc = -1; break; } + + if (truncation) + break; } fclose(fp); diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 5dc51ada05df..39868f529cab 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -265,6 +265,7 @@ struct events_stats { u32 nr_unknown_id; u32 nr_unprocessable_samples; u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX]; + u32 nr_proc_map_timeout; }; struct attr_event { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c371336d1eb2..2d882fd1f1b9 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1064,6 +1064,8 @@ static int machines__deliver_event(struct machines *machines, case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); case PERF_RECORD_MMAP2: + if (event->header.misc & PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT) + ++evlist->stats.nr_proc_map_timeout; return tool->mmap2(tool, event, sample, machine); case PERF_RECORD_COMM: return tool->comm(tool, event, sample, machine); @@ -1360,6 +1362,15 @@ static void perf_session__warn_about_errors(const struct perf_session *session) ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events); events_stats__auxtrace_error_warn(stats); + + if (stats->nr_proc_map_timeout != 0) { + ui__warning("%d map information files for pre-existing threads were\n" + "not processed, if there are samples for addresses they\n" + "will not be resolved, you may find out which are these\n" + "threads by running with -v and redirecting the output\n" + "to a file.\n", + stats->nr_proc_map_timeout); + } } static int perf_session__flush_thread_stack(struct thread *thread, -- cgit v1.2.3