From c6d616fe10c62f528c8c52663aec338d2f4ee4c3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:37 -0800 Subject: perf evsel: Allow const evsel for certain accesses List sorting, added later to evlist, passes const elements requiring helper functions to also be const. Make the argument to evsel__find_pmu, evsel__is_aux_event and evsel__leader const. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/python.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/python.c') diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 42e8b813d010..ab48ffbb6448 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -83,7 +83,7 @@ const char *perf_env__arch(struct perf_env *env __maybe_unused) * far, for the perf python binding known usecases, revisit if this become * necessary. */ -struct perf_pmu *evsel__find_pmu(struct evsel *evsel __maybe_unused) +struct perf_pmu *evsel__find_pmu(const struct evsel *evsel __maybe_unused) { return NULL; } -- cgit From 7abf0bccaaec77043358ee07e694d31cf9a7dd76 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:38 -0800 Subject: perf evsel: Add function to compute group PMU name The computed name respects software events and aux event groups, such that the pmu_name is changed to be that of the aux event leader or group leader for software events. This is done as a later change will split events that are in different PMUs into different groups. Committer notes: Added a stub for this new function so that 'perf test python' passes. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 24 ++++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + tools/perf/util/python.c | 5 +++++ 3 files changed, 30 insertions(+) (limited to 'tools/perf/util/python.c') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 798f072b2763..3dda8a25cf50 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -821,6 +821,30 @@ out_unknown: return "unknown"; } +const char *evsel__group_pmu_name(const struct evsel *evsel) +{ + const struct evsel *leader; + + /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ + if (evsel->pmu_name) + return evsel->pmu_name; + /* + * Software events may be in a group with other uncore PMU events. Use + * the pmu_name of the group leader to avoid breaking the software event + * out of the group. + * + * Aux event leaders, like intel_pt, expect a group with events from + * other PMUs, so substitute the AUX event's PMU in this case. + */ + leader = evsel__leader(evsel); + if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && + leader->pmu_name) { + return leader->pmu_name; + } + + return "cpu"; +} + const char *evsel__metric_id(const struct evsel *evsel) { if (evsel->metric_id) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 676c499323e9..d26745ca6147 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -280,6 +280,7 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size); int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *evsel__name(struct evsel *evsel); +const char *evsel__group_pmu_name(const struct evsel *evsel); const char *evsel__metric_id(const struct evsel *evsel); static inline bool evsel__is_tool(const struct evsel *evsel) diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index ab48ffbb6448..be336f1b2b68 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -93,6 +93,11 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, return EOF; } +bool evsel__is_aux_event(const struct evsel *evsel __maybe_unused) +{ + return false; +} + /* * Add this one here not to drag util/metricgroup.c */ -- cgit From d180aa56b50dd243dec89b24d23e0a59c3f0c0eb Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:30 -0700 Subject: perf record: Add BPF event filter support Use --filter option to set BPF filter for generic events other than the tracepoints or Intel PT. The BPF program will check the sample data and filter according to the expression. For example, the below is the typical perf record for frequency mode. The sample period started from 1 and increased gradually. $ sudo ./perf record -e cycles true $ sudo ./perf script perf-exec 2272336 546683.916875: 1 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916892: 1 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916899: 3 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916905: 17 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916911: 100 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916917: 589 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916924: 3470 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916930: 20465 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) true 2272336 546683.916940: 119873 cycles: ffffffff8283afdd perf_iterate_ctx+0x2d ([kernel.kallsyms]) true 2272336 546683.917003: 461349 cycles: ffffffff82892517 vma_interval_tree_insert+0x37 ([kernel.kallsyms]) true 2272336 546683.917237: 635778 cycles: ffffffff82a11400 security_mmap_file+0x20 ([kernel.kallsyms]) When you add a BPF filter to get samples having periods greater than 1000, the output would look like below: $ sudo ./perf record -e cycles --filter 'period > 1000' true $ sudo ./perf script perf-exec 2273949 546850.708501: 5029 cycles: ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms]) perf-exec 2273949 546850.708508: 32409 cycles: ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms]) perf-exec 2273949 546850.708526: 143369 cycles: ffffffff82b4cdbf xas_start+0x5f ([kernel.kallsyms]) perf-exec 2273949 546850.708600: 372650 cycles: ffffffff8286b8f7 __pagevec_lru_add+0x117 ([kernel.kallsyms]) perf-exec 2273949 546850.708791: 482953 cycles: ffffffff829190de __mod_memcg_lruvec_state+0x4e ([kernel.kallsyms]) true 2273949 546850.709036: 501985 cycles: ffffffff828add7c tlb_gather_mmu+0x4c ([kernel.kallsyms]) true 2273949 546850.709292: 503065 cycles: 7f2446d97c03 _dl_map_object_deps+0x973 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) Committer notes: Add stubs for perf_bpf_filter__prepare() and perf_bpf_filter__destroy() to tools/perf/util/python.c to keep it building. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 15 ++++++++++++--- tools/perf/util/bpf_counter.c | 3 +-- tools/perf/util/evlist.c | 25 ++++++++++++++++++------- tools/perf/util/evsel.c | 2 ++ tools/perf/util/parse-events.c | 8 +++----- tools/perf/util/python.c | 14 ++++++++++++++ 6 files changed, 50 insertions(+), 17 deletions(-) (limited to 'tools/perf/util/python.c') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index ff815c2f67e8..122f71726eaa 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -119,9 +119,12 @@ OPTIONS "perf report" to view group events together. --filter=:: - Event filter. This option should follow an event selector (-e) which - selects either tracepoint event(s) or a hardware trace PMU - (e.g. Intel PT or CoreSight). + Event filter. This option should follow an event selector (-e). + If the event is a tracepoint, the filter string will be parsed by + the kernel. If the event is a hardware trace PMU (e.g. Intel PT + or CoreSight), it'll be processed as an address filter. Otherwise + it means a general filter using BPF which can be applied for any + kind of event. - tracepoint filters @@ -176,6 +179,12 @@ OPTIONS Multiple filters can be separated with space or comma. + - bpf filters + + A BPF filter can access the sample data and make a decision based on the + data. Users need to set an appropriate sample type to use the BPF + filter. + --exclude-perf:: Don't record events issued by perf itself. This option should follow an event selector (-e) which selects tracepoint event(s). It adds a diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index aa78a15a6f0a..1b77436e067e 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -763,8 +763,7 @@ extern struct bpf_counter_ops bperf_cgrp_ops; static inline bool bpf_counter_skip(struct evsel *evsel) { - return list_empty(&evsel->bpf_counter_list) && - evsel->follower_skel == NULL; + return evsel->bpf_counter_ops == NULL; } int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index b74e12239aec..cc491a037836 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -31,6 +31,7 @@ #include "util/evlist-hybrid.h" #include "util/pmu.h" #include "util/sample.h" +#include "util/bpf-filter.h" #include #include #include @@ -1086,17 +1087,27 @@ int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) int err = 0; evlist__for_each_entry(evlist, evsel) { - if (evsel->filter == NULL) - continue; - /* * filters only work for tracepoint event, which doesn't have cpu limit. * So evlist and evsel should always be same. */ - err = perf_evsel__apply_filter(&evsel->core, evsel->filter); - if (err) { - *err_evsel = evsel; - break; + if (evsel->filter) { + err = perf_evsel__apply_filter(&evsel->core, evsel->filter); + if (err) { + *err_evsel = evsel; + break; + } + } + + /* + * non-tracepoint events can have BPF filters. + */ + if (!list_empty(&evsel->bpf_filters)) { + err = perf_bpf_filter__prepare(evsel); + if (err) { + *err_evsel = evsel; + break; + } } } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a83d8cd5eb51..dc3faf005c3b 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -50,6 +50,7 @@ #include "off_cpu.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" +#include "util/bpf-filter.h" #include #include #include @@ -1517,6 +1518,7 @@ void evsel__exit(struct evsel *evsel) assert(list_empty(&evsel->core.node)); assert(evsel->evlist == NULL); bpf_counter__destroy(evsel); + perf_bpf_filter__destroy(evsel); evsel__free_counts(evsel); perf_evsel__free_fd(&evsel->core); perf_evsel__free_id(&evsel->core); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3b2e5bb3e852..6c5cf5244486 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -28,6 +28,7 @@ #include "perf.h" #include "util/parse-events-hybrid.h" #include "util/pmu-hybrid.h" +#include "util/bpf-filter.h" #include "tracepoint.h" #include "thread_map.h" @@ -2542,11 +2543,8 @@ static int set_filter(struct evsel *evsel, const void *arg) perf_pmu__scan_file(pmu, "nr_addr_filters", "%d", &nr_addr_filters); - if (!nr_addr_filters) { - fprintf(stderr, - "This CPU does not support address filtering\n"); - return -1; - } + if (!nr_addr_filters) + return perf_bpf_filter__parse(&evsel->bpf_filters, str); if (evsel__append_addr_filter(evsel, str) < 0) { fprintf(stderr, diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index be336f1b2b68..0faea4c75eed 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -19,6 +19,7 @@ #include "mmap.h" #include "stat.h" #include "metricgroup.h" +#include "util/bpf-filter.h" #include "util/env.h" #include "util/pmu.h" #include @@ -135,6 +136,19 @@ int bpf_counter__disable(struct evsel *evsel __maybe_unused) return 0; } +// not to drag util/bpf-filter.c +#ifdef HAVE_BPF_SKEL +int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused) +{ + return 0; +} + +int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused) +{ + return 0; +} +#endif + /* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. -- cgit