From cb4b9e6813f9243095932c867ff16a7dffa02102 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Thu, 2 Mar 2023 11:11:45 +0800 Subject: perf record: Reuse target::initial_delay This just simply replace record_opts::initial_delay with target::initial_delay. Nothing else is changed. Signed-off-by: Changbin Du Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Hui Wang Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230302031146.2801588-3-changbin.du@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/evsel.c') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 51e8ce6edddc..462cc0673cee 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1334,7 +1334,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, * group leaders for traced executed by perf. */ if (target__none(&opts->target) && evsel__is_group_leader(evsel) && - !opts->initial_delay) + !opts->target.initial_delay) attr->enable_on_exec = 1; if (evsel->immediate) { -- cgit v1.2.3 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/evsel.c | 2 +- tools/perf/util/evsel.h | 6 +++--- tools/perf/util/pmu.c | 6 +++--- tools/perf/util/python.c | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'tools/perf/util/evsel.c') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 462cc0673cee..798f072b2763 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -3139,7 +3139,7 @@ bool evsel__is_hybrid(const struct evsel *evsel) return evsel->pmu_name && perf_pmu__is_hybrid(evsel->pmu_name); } -struct evsel *evsel__leader(struct evsel *evsel) +struct evsel *evsel__leader(const struct evsel *evsel) { return container_of(evsel->core.leader, struct evsel, core); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 814a49ebb7e3..676c499323e9 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -212,8 +212,8 @@ int evsel__object_config(size_t object_size, int (*init)(struct evsel *evsel), void (*fini)(struct evsel *evsel)); -struct perf_pmu *evsel__find_pmu(struct evsel *evsel); -bool evsel__is_aux_event(struct evsel *evsel); +struct perf_pmu *evsel__find_pmu(const struct evsel *evsel); +bool evsel__is_aux_event(const struct evsel *evsel); struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx); @@ -505,7 +505,7 @@ int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); void evsel__zero_per_pkg(struct evsel *evsel); bool evsel__is_hybrid(const struct evsel *evsel); -struct evsel *evsel__leader(struct evsel *evsel); +struct evsel *evsel__leader(const struct evsel *evsel); bool evsel__has_leader(struct evsel *evsel, struct evsel *leader); bool evsel__is_leader(struct evsel *evsel); void evsel__set_leader(struct evsel *evsel, struct evsel *leader); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 43b6182d96b7..45d9b8e28e16 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -988,7 +988,7 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu) return NULL; } -struct perf_pmu *evsel__find_pmu(struct evsel *evsel) +struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) { struct perf_pmu *pmu = NULL; @@ -1000,11 +1000,11 @@ struct perf_pmu *evsel__find_pmu(struct evsel *evsel) break; } - evsel->pmu = pmu; + ((struct evsel *)evsel)->pmu = pmu; return pmu; } -bool evsel__is_aux_event(struct evsel *evsel) +bool evsel__is_aux_event(const struct evsel *evsel) { struct perf_pmu *pmu = evsel__find_pmu(evsel); 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 v1.2.3 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/evsel.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 v1.2.3 From e733f87e8c77751a00a538627eab1ac05e77cf0d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:41 -0800 Subject: perf evsel: Remove use_uncore_alias This flag used to be used when regrouping uncore events in particular due to wildcard matches. This is now handled by sorting evlist and so the flag is redundant. 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 | 1 - tools/perf/util/evsel.h | 1 - tools/perf/util/parse-events.c | 12 +++--------- tools/perf/util/parse-events.h | 3 +-- tools/perf/util/parse-events.y | 11 +++++++---- 5 files changed, 11 insertions(+), 17 deletions(-) (limited to 'tools/perf/util/evsel.c') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 3dda8a25cf50..a83d8cd5eb51 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -458,7 +458,6 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->per_pkg = orig->per_pkg; evsel->percore = orig->percore; evsel->precise_max = orig->precise_max; - evsel->use_uncore_alias = orig->use_uncore_alias; evsel->is_libpfm_event = orig->is_libpfm_event; evsel->exclude_GH = orig->exclude_GH; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d26745ca6147..c272c06565c0 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -89,7 +89,6 @@ struct evsel { bool per_pkg; bool percore; bool precise_max; - bool use_uncore_alias; bool is_libpfm_event; bool auto_merge_stats; bool collect_stat; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 394ab23089d0..93a90651266f 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1445,15 +1445,13 @@ static int parse_events__inside_hybrid_pmu(struct parse_events_state *parse_stat int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, - bool auto_merge_stats, - bool use_alias) + bool auto_merge_stats) { struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; struct evsel *evsel; struct parse_events_error *err = parse_state->error; - bool use_uncore_alias; LIST_HEAD(config_terms); pmu = parse_state->fake_pmu ?: perf_pmu__find(name); @@ -1488,8 +1486,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, memset(&attr, 0, sizeof(attr)); } - use_uncore_alias = (pmu->is_uncore && use_alias); - if (!head_config) { attr.type = pmu->type; evsel = __add_event(list, &parse_state->idx, &attr, @@ -1499,7 +1495,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, /*cpu_list=*/NULL); if (evsel) { evsel->pmu_name = name ? strdup(name) : NULL; - evsel->use_uncore_alias = use_uncore_alias; return 0; } else { return -ENOMEM; @@ -1560,7 +1555,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->use_config_name = true; evsel->pmu_name = name ? strdup(name) : NULL; - evsel->use_uncore_alias = use_uncore_alias; evsel->percore = config_term_percore(&evsel->config_terms); if (parse_state->fake_pmu) @@ -1622,7 +1616,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, pmu->name, orig_head, - true, true)) { + /*auto_merge_stats=*/true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; @@ -1634,7 +1628,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, if (parse_state->fake_pmu) { if (!parse_events_add_pmu(parse_state, list, str, head, - true, true)) { + /*auto_merge_stats=*/true)) { pr_debug("%s -> %s/%s/\n", str, "fake_pmu", str); ok++; } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 22fc11b0bd59..fdac44dc696b 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -183,8 +183,7 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, - bool auto_merge_stats, - bool use_alias); + bool auto_merge_stats); struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, const char *name, const char *metric_id, diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 90d12f2bc8be..f1b153c72d67 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -313,7 +313,7 @@ event_pmu_name opt_pmu_config list = alloc_list(); if (!list) CLEANUP_YYABORT; - if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2, /*auto_merge_stats=*/false)) { struct perf_pmu *pmu = NULL; int ok = 0; @@ -330,8 +330,10 @@ event_pmu_name opt_pmu_config !perf_pmu__match(pattern, pmu->alias_name, $1)) { if (parse_events_copy_term_list(orig_terms, &terms)) CLEANUP_YYABORT; - if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false)) + if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, + /*auto_merge_stats=*/true)) { ok++; + } parse_events_terms__delete(terms); } } @@ -407,7 +409,8 @@ PE_PMU_EVENT_FAKE sep_dc if (!list) YYABORT; - err = parse_events_add_pmu(_parse_state, list, $1, NULL, false, false); + err = parse_events_add_pmu(_parse_state, list, $1, /*head_config=*/NULL, + /*auto_merge_stats=*/false); free($1); if (err < 0) { free(list); @@ -425,7 +428,7 @@ PE_PMU_EVENT_FAKE opt_pmu_config if (!list) YYABORT; - err = parse_events_add_pmu(_parse_state, list, $1, $2, false, false); + err = parse_events_add_pmu(_parse_state, list, $1, $2, /*auto_merge_stats=*/false); free($1); parse_events_terms__delete($2); if (err < 0) { -- cgit v1.2.3 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/evsel.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 v1.2.3 From cf57cf51d7c63595a50359694537b41aa05dda7e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 13:56:59 -0700 Subject: perf evsel: Avoid SEGV if delete is called on NULL Seen in "perf stat --bpf-counters --for-each-cgroup test" running in a container: libbpf: Failed to bump RLIMIT_MEMLOCK (err = -1), you might need to do it explicitly! libbpf: Error in bpf_object__probe_loading():Operation not permitted(1). Couldn't load trivial BPF program. Make sure your kernel supports BPF (CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is set to big enough value. libbpf: failed to load object 'bperf_cgroup_bpf' libbpf: failed to load BPF skeleton 'bperf_cgroup_bpf': -1 Failed to load cgroup skeleton #0 0x55f28a650981 in list_empty tools/include/linux/list.h:189 #1 0x55f28a6593b4 in evsel__exit util/evsel.c:1518 #2 0x55f28a6596af in evsel__delete util/evsel.c:1544 #3 0x55f28a89d166 in bperf_cgrp__destroy util/bpf_counter_cgroup.c:283 #4 0x55f28a899e9a in bpf_counter__destroy util/bpf_counter.c:816 #5 0x55f28a659455 in evsel__exit util/evsel.c:1520 #6 0x55f28a6596af in evsel__delete util/evsel.c:1544 #7 0x55f28a640d4d in evlist__purge util/evlist.c:148 #8 0x55f28a640ea6 in evlist__delete util/evlist.c:169 #9 0x55f28a4efbf2 in cmd_stat tools/perf/builtin-stat.c:2598 #10 0x55f28a6050c2 in run_builtin tools/perf/perf.c:330 #11 0x55f28a605633 in handle_internal_command tools/perf/perf.c:384 #12 0x55f28a6059fb in run_argv tools/perf/perf.c:428 #13 0x55f28a6061d3 in main tools/perf/perf.c:562 Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230410205659.3131608-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf/util/evsel.c') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index dc3faf005c3b..fe3ce765a4f3 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1541,6 +1541,9 @@ void evsel__exit(struct evsel *evsel) void evsel__delete(struct evsel *evsel) { + if (!evsel) + return; + evsel__exit(evsel); free(evsel); } -- cgit v1.2.3 From cdf13c0918c9b1b233d6db690fc4c06afbc29e57 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: perf evsel: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Also remove one NULL test before free(), as it accepts a NULL arg and we get one line shaved not doing it explicitely. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'tools/perf/util/evsel.c') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index fe3ce765a4f3..a85a987128aa 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2917,8 +2917,7 @@ bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize) if (asprintf(&new_name, "%s%su", name, sep) < 0) return false; - if (evsel->name) - free(evsel->name); + free(evsel->name); evsel->name = new_name; scnprintf(msg, msgsize, "kernel.perf_event_paranoid=%d, trying " "to fall back to excluding kernel and hypervisor " @@ -3156,7 +3155,7 @@ void evsel__zero_per_pkg(struct evsel *evsel) if (evsel->per_pkg_mask) { hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt) - free((void *)cur->pkey); + zfree(&cur->pkey); hashmap__clear(evsel->per_pkg_mask); } -- cgit v1.2.3 From ce1d3bc2733224573600e5564203345caea814eb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 20 Apr 2023 15:54:11 -0300 Subject: perf evsel: Introduce evsel__name_is() method to check if the evsel name is equal to a given string This makes the logic a bit clear by avoiding the !strcmp() pattern and also a way to intercept the pointer if we need to do extra validation on it or to do lazy setting of evsel->name via evsel__name(evsel). Reviewed-by: "Liang, Kan" Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZEGLM8VehJbS0gP2@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/util/kvm-stat.c | 4 ++-- tools/perf/arch/powerpc/util/kvm-stat.c | 4 ++-- tools/perf/arch/x86/util/kvm-stat.c | 8 ++++---- tools/perf/builtin-kvm.c | 6 +++--- tools/perf/builtin-stat.c | 2 +- tools/perf/tests/expand-cgroup.c | 2 +- tools/perf/tests/parse-events.c | 12 ++++++------ tools/perf/tests/parse-metric.c | 2 +- tools/perf/tests/pmu-events.c | 2 +- tools/perf/util/evlist.c | 4 ++-- tools/perf/util/evsel.c | 7 ++++++- tools/perf/util/evsel.h | 1 + tools/perf/util/sort.c | 2 +- 13 files changed, 31 insertions(+), 25 deletions(-) (limited to 'tools/perf/util/evsel.c') diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c index 72ca9bb45804..6611aa21cba9 100644 --- a/tools/perf/arch/arm64/util/kvm-stat.c +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -44,14 +44,14 @@ static bool event_begin(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { - return !strcmp(evsel->name, kvm_entry_trace); + return evsel__name_is(evsel, kvm_entry_trace); } static bool event_end(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { - if (!strcmp(evsel->name, kvm_exit_trace)) { + if (evsel__name_is(evsel, kvm_exit_trace)) { event_get_key(evsel, sample, key); return true; } diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index d04a08c9fd19..ea1220d66b67 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -60,13 +60,13 @@ static bool hcall_event_end(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { - return (!strcmp(evsel->name, kvm_events_tp[3])); + return (evsel__name_is(evsel, kvm_events_tp[3])); } static bool hcall_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { - if (!strcmp(evsel->name, kvm_events_tp[2])) { + if (evsel__name_is(evsel, kvm_events_tp[2])) { hcall_event_get_key(evsel, sample, key); return true; } diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index ef513def03ba..424716518b75 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -46,7 +46,7 @@ static bool mmio_event_begin(struct evsel *evsel, return true; /* MMIO write begin event in kernel. */ - if (!strcmp(evsel->name, "kvm:kvm_mmio") && + if (evsel__name_is(evsel, "kvm:kvm_mmio") && evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { mmio_event_get_key(evsel, sample, key); return true; @@ -63,7 +63,7 @@ static bool mmio_event_end(struct evsel *evsel, struct perf_sample *sample, return true; /* MMIO read end event in kernel.*/ - if (!strcmp(evsel->name, "kvm:kvm_mmio") && + if (evsel__name_is(evsel, "kvm:kvm_mmio") && evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { mmio_event_get_key(evsel, sample, key); return true; @@ -101,7 +101,7 @@ static bool ioport_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { - if (!strcmp(evsel->name, "kvm:kvm_pio")) { + if (evsel__name_is(evsel, "kvm:kvm_pio")) { ioport_event_get_key(evsel, sample, key); return true; } @@ -145,7 +145,7 @@ static bool msr_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { - if (!strcmp(evsel->name, "kvm:kvm_msr")) { + if (evsel__name_is(evsel, "kvm:kvm_msr")) { msr_event_get_key(evsel, sample, key); return true; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 747d19336340..71165036e4ca 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -625,7 +625,7 @@ void exit_event_get_key(struct evsel *evsel, bool kvm_exit_event(struct evsel *evsel) { - return !strcmp(evsel->name, kvm_exit_trace); + return evsel__name_is(evsel, kvm_exit_trace); } bool exit_event_begin(struct evsel *evsel, @@ -641,7 +641,7 @@ bool exit_event_begin(struct evsel *evsel, bool kvm_entry_event(struct evsel *evsel) { - return !strcmp(evsel->name, kvm_entry_trace); + return evsel__name_is(evsel, kvm_entry_trace); } bool exit_event_end(struct evsel *evsel, @@ -878,7 +878,7 @@ static bool is_child_event(struct perf_kvm_stat *kvm, return false; for (; child_ops->name; child_ops++) { - if (!strcmp(evsel->name, child_ops->name)) { + if (evsel__name_is(evsel, child_ops->name)) { child_ops->get_key(evsel, sample, key); return true; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d3cbee7460fc..efda63f6bf32 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2170,7 +2170,7 @@ static void setup_system_wide(int forks) evlist__for_each_entry(evsel_list, counter) { if (!counter->core.requires_cpu && - strcmp(counter->name, "duration_time")) { + !evsel__name_is(counter, "duration_time")) { return; } } diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index ec340880a848..9c1a1f18db75 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -61,7 +61,7 @@ static int test_expand_events(struct evlist *evlist, i = 0; evlist__for_each_entry(evlist, evsel) { - if (strcmp(evsel->name, ev_name[i % nr_events])) { + if (!evsel__name_is(evsel, ev_name[i % nr_events])) { pr_debug("event name doesn't match:\n"); pr_debug(" evsel[%d]: %s\n expected: %s\n", i, evsel->name, ev_name[i % nr_events]); diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 6eb1400443ad..8068cfd89b84 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1401,7 +1401,7 @@ static int test__checkevent_config_symbol(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "insn")); return TEST_OK; } @@ -1409,7 +1409,7 @@ static int test__checkevent_config_raw(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "rawpmu")); return TEST_OK; } @@ -1417,7 +1417,7 @@ static int test__checkevent_config_num(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "numpmu")); return TEST_OK; } @@ -1425,7 +1425,7 @@ static int test__checkevent_config_cache(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "cachepmu")); return TEST_OK; } @@ -1438,7 +1438,7 @@ static int test__intel_pt(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "intel_pt//u")); return TEST_OK; } @@ -1446,7 +1446,7 @@ static int test__checkevent_complex_name(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0); + TEST_ASSERT_VAL("wrong complex name parsing", evsel__name_is(evsel, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks")); return TEST_OK; } diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index c43b056f9fa3..1185b79e6274 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -39,7 +39,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); evsel->stats->aggr->counts.val = count; - if (!strcmp(evsel->name, "duration_time")) + if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); } } diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 7f8e86452527..1dff863b9711 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -866,7 +866,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { evsel->stats->aggr->counts.val = k; - if (!strcmp(evsel->name, "duration_time")) + if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, k); k++; } diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 2260e27adf44..a0504316b06f 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -467,7 +467,7 @@ static int evsel__strcmp(struct evsel *pos, char *evsel_name) return 0; if (evsel__is_dummy_event(pos)) return 1; - return strcmp(pos->name, evsel_name); + return !evsel__name_is(pos, evsel_name); } static int evlist__is_enabled(struct evlist *evlist) @@ -1706,7 +1706,7 @@ struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str) evlist__for_each_entry(evlist, evsel) { if (!evsel->name) continue; - if (strcmp(str, evsel->name) == 0) + if (evsel__name_is(evsel, str)) return evsel; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a85a987128aa..356c07f03be6 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -821,6 +821,11 @@ out_unknown: return "unknown"; } +bool evsel__name_is(struct evsel *evsel, const char *name) +{ + return !strcmp(evsel__name(evsel), name); +} + const char *evsel__group_pmu_name(const struct evsel *evsel) { const struct evsel *leader; @@ -1146,7 +1151,7 @@ static void evsel__set_default_freq_period(struct record_opts *opts, static bool evsel__is_offcpu_event(struct evsel *evsel) { - return evsel__is_bpf_output(evsel) && !strcmp(evsel->name, OFFCPU_EVENT); + return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT); } /* diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 68072ec655ce..1e5d640e4a9b 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -282,6 +282,7 @@ 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); +bool evsel__name_is(struct evsel *evsel, const char *name); const char *evsel__group_pmu_name(const struct evsel *evsel); const char *evsel__metric_id(const struct evsel *evsel); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 31b1cd0935e2..650cd8df4041 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2893,7 +2893,7 @@ static struct evsel *find_evsel(struct evlist *evlist, char *event_name) full_name = !!strchr(event_name, ':'); evlist__for_each_entry(evlist, pos) { /* case 2 */ - if (full_name && !strcmp(pos->name, event_name)) + if (full_name && evsel__name_is(pos, event_name)) return pos; /* case 3 */ if (!full_name && strstr(pos->name, event_name)) { -- cgit v1.2.3