From 990a71e904f6ec2d7d84eecb37e5127b75721985 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:28 -0700 Subject: perf bpf filter: Introduce basic BPF filter expression This implements a tiny parser for the filter expressions used for BPF. Each expression will be converted to struct perf_bpf_filter_expr and be passed to a BPF map. For now, I'd like to start with the very basic comparisons like EQ or GT. The LHS should be a term for sample data and the RHS is a number. The expressions are connected by a comma. For example, period > 10000 ip < 0x1000000000000, cpu == 3 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/util/bpf-filter.c | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 tools/perf/util/bpf-filter.c (limited to 'tools/perf/util/bpf-filter.c') diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c new file mode 100644 index 000000000000..c72e35d51240 --- /dev/null +++ b/tools/perf/util/bpf-filter.c @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include + +#include "util/bpf-filter.h" +#include "util/bpf-filter-flex.h" +#include "util/bpf-filter-bison.h" + +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, + enum perf_bpf_filter_op op, + unsigned long val) +{ + struct perf_bpf_filter_expr *expr; + + expr = malloc(sizeof(*expr)); + if (expr != NULL) { + expr->sample_flags = sample_flags; + expr->op = op; + expr->val = val; + } + return expr; +} + +int perf_bpf_filter__parse(struct list_head *expr_head, const char *str) +{ + YY_BUFFER_STATE buffer; + int ret; + + buffer = perf_bpf_filter__scan_string(str); + + ret = perf_bpf_filter_parse(expr_head); + + perf_bpf_filter__flush_buffer(buffer); + perf_bpf_filter__delete_buffer(buffer); + perf_bpf_filter_lex_destroy(); + + return ret; +} -- cgit v1.2.3 From 56ec9457a4a20c5e07ad94bfb6e23077d54cb28e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:29 -0700 Subject: perf bpf filter: Implement event sample filtering The BPF program will be attached to a perf_event and be triggered when it overflows. It'd iterate the filters map and compare the sample value according to the expression. If any of them fails, the sample would be dropped. Also it needs to have the corresponding sample data for the expression so it compares data->sample_flags with the given value. To access the sample data, it uses the bpf_cast_to_kern_ctx() kfunc which was added in v6.2 kernel. 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/Makefile.perf | 2 +- tools/perf/util/bpf-filter.c | 64 ++++++++++++++ tools/perf/util/bpf-filter.h | 26 +++--- tools/perf/util/bpf_skel/sample-filter.h | 24 +++++ tools/perf/util/bpf_skel/sample_filter.bpf.c | 126 +++++++++++++++++++++++++++ tools/perf/util/evsel.h | 7 +- 6 files changed, 236 insertions(+), 13 deletions(-) create mode 100644 tools/perf/util/bpf_skel/sample-filter.h create mode 100644 tools/perf/util/bpf_skel/sample_filter.bpf.c (limited to 'tools/perf/util/bpf-filter.c') diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index dc9dda09b076..ed6b6a070f79 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1050,7 +1050,7 @@ SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h -SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h +SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT): $(Q)$(MKDIR) -p $@ diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index c72e35d51240..f20e1bc03778 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -1,10 +1,74 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +#include +#include +#include + +#include "util/debug.h" +#include "util/evsel.h" + #include "util/bpf-filter.h" #include "util/bpf-filter-flex.h" #include "util/bpf-filter-bison.h" +#include "bpf_skel/sample-filter.h" +#include "bpf_skel/sample_filter.skel.h" + +#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) + +int perf_bpf_filter__prepare(struct evsel *evsel) +{ + int i, x, y, fd; + struct sample_filter_bpf *skel; + struct bpf_program *prog; + struct bpf_link *link; + struct perf_bpf_filter_expr *expr; + + skel = sample_filter_bpf__open_and_load(); + if (!skel) { + pr_err("Failed to load perf sample-filter BPF skeleton\n"); + return -1; + } + + i = 0; + fd = bpf_map__fd(skel->maps.filters); + list_for_each_entry(expr, &evsel->bpf_filters, list) { + struct perf_bpf_filter_entry entry = { + .op = expr->op, + .flags = expr->sample_flags, + .value = expr->val, + }; + bpf_map_update_elem(fd, &i, &entry, BPF_ANY); + i++; + } + + prog = skel->progs.perf_sample_filter; + for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) { + for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) { + link = bpf_program__attach_perf_event(prog, FD(evsel, x, y)); + if (IS_ERR(link)) { + pr_err("Failed to attach perf sample-filter program\n"); + return PTR_ERR(link); + } + } + } + evsel->bpf_skel = skel; + return 0; +} + +int perf_bpf_filter__destroy(struct evsel *evsel) +{ + struct perf_bpf_filter_expr *expr, *tmp; + + list_for_each_entry_safe(expr, tmp, &evsel->bpf_filters, list) { + list_del(&expr->list); + free(expr); + } + sample_filter_bpf__destroy(evsel->bpf_skel); + return 0; +} + struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, enum perf_bpf_filter_op op, unsigned long val) diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index 93a0d3de038c..eb8e1ac43cdf 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -4,15 +4,7 @@ #include -enum perf_bpf_filter_op { - PBF_OP_EQ, - PBF_OP_NEQ, - PBF_OP_GT, - PBF_OP_GE, - PBF_OP_LT, - PBF_OP_LE, - PBF_OP_AND, -}; +#include "bpf_skel/sample-filter.h" struct perf_bpf_filter_expr { struct list_head list; @@ -21,16 +13,30 @@ struct perf_bpf_filter_expr { unsigned long val; }; +struct evsel; + #ifdef HAVE_BPF_SKEL struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, enum perf_bpf_filter_op op, unsigned long val); int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); +int perf_bpf_filter__prepare(struct evsel *evsel); +int perf_bpf_filter__destroy(struct evsel *evsel); + #else /* !HAVE_BPF_SKEL */ + static inline int perf_bpf_filter__parse(struct list_head *expr_head __maybe_unused, const char *str __maybe_unused) { - return -ENOSYS; + return -EOPNOTSUPP; +} +static inline int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused) +{ + return -EOPNOTSUPP; +} +static inline int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused) +{ + return -EOPNOTSUPP; } #endif /* HAVE_BPF_SKEL*/ #endif /* PERF_UTIL_BPF_FILTER_H */ diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h new file mode 100644 index 000000000000..862060bfda14 --- /dev/null +++ b/tools/perf/util/bpf_skel/sample-filter.h @@ -0,0 +1,24 @@ +#ifndef PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H +#define PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H + +#define MAX_FILTERS 32 + +/* supported filter operations */ +enum perf_bpf_filter_op { + PBF_OP_EQ, + PBF_OP_NEQ, + PBF_OP_GT, + PBF_OP_GE, + PBF_OP_LT, + PBF_OP_LE, + PBF_OP_AND +}; + +/* BPF map entry for filtering */ +struct perf_bpf_filter_entry { + enum perf_bpf_filter_op op; + __u64 flags; + __u64 value; +}; + +#endif /* PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H */ \ No newline at end of file diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c new file mode 100644 index 000000000000..c07256279c3e --- /dev/null +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2023 Google +#include "vmlinux.h" +#include +#include +#include + +#include "sample-filter.h" + +/* BPF map that will be filled by user space */ +struct filters { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct perf_bpf_filter_entry); + __uint(max_entries, MAX_FILTERS); +} filters SEC(".maps"); + +int dropped; + +void *bpf_cast_to_kern_ctx(void *) __ksym; + +/* new kernel perf_sample_data definition */ +struct perf_sample_data___new { + __u64 sample_flags; +} __attribute__((preserve_access_index)); + +/* helper function to return the given perf sample data */ +static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, + struct perf_bpf_filter_entry *entry) +{ + struct perf_sample_data___new *data = (void *)kctx->data; + + if (!bpf_core_field_exists(data->sample_flags) || + (data->sample_flags & entry->flags) == 0) + return 0; + + switch (entry->flags) { + case PERF_SAMPLE_IP: + return kctx->data->ip; + case PERF_SAMPLE_ID: + return kctx->data->id; + case PERF_SAMPLE_TID: + return kctx->data->tid_entry.tid; + case PERF_SAMPLE_CPU: + return kctx->data->cpu_entry.cpu; + case PERF_SAMPLE_TIME: + return kctx->data->time; + case PERF_SAMPLE_ADDR: + return kctx->data->addr; + case PERF_SAMPLE_PERIOD: + return kctx->data->period; + case PERF_SAMPLE_TRANSACTION: + return kctx->data->txn; + case PERF_SAMPLE_WEIGHT: + return kctx->data->weight.full; + case PERF_SAMPLE_PHYS_ADDR: + return kctx->data->phys_addr; + case PERF_SAMPLE_CODE_PAGE_SIZE: + return kctx->data->code_page_size; + case PERF_SAMPLE_DATA_PAGE_SIZE: + return kctx->data->data_page_size; + default: + break; + } + return 0; +} + +/* BPF program to be called from perf event overflow handler */ +SEC("perf_event") +int perf_sample_filter(void *ctx) +{ + struct bpf_perf_event_data_kern *kctx; + struct perf_bpf_filter_entry *entry; + __u64 sample_data; + int i; + + kctx = bpf_cast_to_kern_ctx(ctx); + + for (i = 0; i < MAX_FILTERS; i++) { + int key = i; /* needed for verifier :( */ + + entry = bpf_map_lookup_elem(&filters, &key); + if (entry == NULL) + break; + sample_data = perf_get_sample(kctx, entry); + + switch (entry->op) { + case PBF_OP_EQ: + if (!(sample_data == entry->value)) + goto drop; + break; + case PBF_OP_NEQ: + if (!(sample_data != entry->value)) + goto drop; + break; + case PBF_OP_GT: + if (!(sample_data > entry->value)) + goto drop; + break; + case PBF_OP_GE: + if (!(sample_data >= entry->value)) + goto drop; + break; + case PBF_OP_LT: + if (!(sample_data < entry->value)) + goto drop; + break; + case PBF_OP_LE: + if (!(sample_data <= entry->value)) + goto drop; + break; + case PBF_OP_AND: + if (!(sample_data & entry->value)) + goto drop; + break; + } + } + /* generate sample data */ + return 1; + +drop: + __sync_fetch_and_add(&dropped, 1); + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index c272c06565c0..68072ec655ce 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -150,8 +150,10 @@ struct evsel { */ struct bpf_counter_ops *bpf_counter_ops; - /* for perf-stat -b */ - struct list_head bpf_counter_list; + union { + struct list_head bpf_counter_list; /* for perf-stat -b */ + struct list_head bpf_filters; /* for perf-record --filter */ + }; /* for perf-stat --use-bpf */ int bperf_leader_prog_fd; @@ -159,6 +161,7 @@ struct evsel { union { struct bperf_leader_bpf *leader_skel; struct bperf_follower_bpf *follower_skel; + void *bpf_skel; }; unsigned long open_flags; int precise_ip_original; -- cgit v1.2.3 From 27c6f2455b29f27c8daf209ec8bdf0ac2c567b74 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:31 -0700 Subject: perf record: Record dropped sample count When it uses bpf filters, event might drop some samples. It'd be nice if it can report how many samples it lost. As LOST_SAMPLES event can carry the similar information, let's use it for bpf filters. To indicate it's from BPF filters, add a new misc flag for that and do not display cpu load warnings. 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/lib/perf/include/perf/event.h | 2 ++ tools/perf/builtin-record.c | 38 +++++++++++++++++++++++-------------- tools/perf/util/bpf-filter.c | 7 +++++++ tools/perf/util/bpf-filter.h | 5 +++++ tools/perf/util/session.c | 3 ++- 5 files changed, 40 insertions(+), 15 deletions(-) (limited to 'tools/perf/util/bpf-filter.c') diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index ad47d7b31046..51b9338f4c11 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -70,6 +70,8 @@ struct perf_record_lost { __u64 lost; }; +#define PERF_RECORD_MISC_LOST_SAMPLES_BPF (1 << 15) + struct perf_record_lost_samples { struct perf_event_header header; __u64 lost; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 33ebe42b025e..6df8b823859d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -52,6 +52,7 @@ #include "util/pmu-hybrid.h" #include "util/evlist-hybrid.h" #include "util/off_cpu.h" +#include "util/bpf-filter.h" #include "asm/bug.h" #include "perf.h" #include "cputopo.h" @@ -1856,24 +1857,16 @@ record__switch_output(struct record *rec, bool at_exit) return fd; } -static void __record__read_lost_samples(struct record *rec, struct evsel *evsel, +static void __record__save_lost_samples(struct record *rec, struct evsel *evsel, struct perf_record_lost_samples *lost, - int cpu_idx, int thread_idx) + int cpu_idx, int thread_idx, u64 lost_count, + u16 misc_flag) { - struct perf_counts_values count; struct perf_sample_id *sid; struct perf_sample sample = {}; int id_hdr_size; - if (perf_evsel__read(&evsel->core, cpu_idx, thread_idx, &count) < 0) { - pr_debug("read LOST count failed\n"); - return; - } - - if (count.lost == 0) - return; - - lost->lost = count.lost; + lost->lost = lost_count; if (evsel->core.ids) { sid = xyarray__entry(evsel->core.sample_id, cpu_idx, thread_idx); sample.id = sid->id; @@ -1882,6 +1875,7 @@ static void __record__read_lost_samples(struct record *rec, struct evsel *evsel, id_hdr_size = perf_event__synthesize_id_sample((void *)(lost + 1), evsel->core.attr.sample_type, &sample); lost->header.size = sizeof(*lost) + id_hdr_size; + lost->header.misc = misc_flag; record__write(rec, NULL, lost, lost->header.size); } @@ -1905,6 +1899,7 @@ static void record__read_lost_samples(struct record *rec) evlist__for_each_entry(session->evlist, evsel) { struct xyarray *xy = evsel->core.sample_id; + u64 lost_count; if (xy == NULL || evsel->core.fd == NULL) continue; @@ -1916,12 +1911,27 @@ static void record__read_lost_samples(struct record *rec) for (int x = 0; x < xyarray__max_x(xy); x++) { for (int y = 0; y < xyarray__max_y(xy); y++) { - __record__read_lost_samples(rec, evsel, lost, x, y); + struct perf_counts_values count; + + if (perf_evsel__read(&evsel->core, x, y, &count) < 0) { + pr_debug("read LOST count failed\n"); + goto out; + } + + if (count.lost) { + __record__save_lost_samples(rec, evsel, lost, + x, y, count.lost, 0); + } } } + + lost_count = perf_bpf_filter__lost_count(evsel); + if (lost_count) + __record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count, + PERF_RECORD_MISC_LOST_SAMPLES_BPF); } +out: free(lost); - } static volatile sig_atomic_t workload_exec_errno; diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index f20e1bc03778..7bd6f2e41513 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -69,6 +69,13 @@ int perf_bpf_filter__destroy(struct evsel *evsel) return 0; } +u64 perf_bpf_filter__lost_count(struct evsel *evsel) +{ + struct sample_filter_bpf *skel = evsel->bpf_skel; + + return skel ? skel->bss->dropped : 0; +} + struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, enum perf_bpf_filter_op op, unsigned long val) diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index eb8e1ac43cdf..f0c66764c6d0 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -22,6 +22,7 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flag int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); int perf_bpf_filter__prepare(struct evsel *evsel); int perf_bpf_filter__destroy(struct evsel *evsel); +u64 perf_bpf_filter__lost_count(struct evsel *evsel); #else /* !HAVE_BPF_SKEL */ @@ -38,5 +39,9 @@ static inline int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused) { return -EOPNOTSUPP; } +static inline u64 perf_bpf_filter__lost_count(struct evsel *evsel __maybe_unused) +{ + return 0; +} #endif /* HAVE_BPF_SKEL*/ #endif /* PERF_UTIL_BPF_FILTER_H */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 749d5b5c135b..7d8d057d1772 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1582,7 +1582,8 @@ static int machines__deliver_event(struct machines *machines, evlist->stats.total_lost += event->lost.lost; return tool->lost(tool, event, sample, machine); case PERF_RECORD_LOST_SAMPLES: - if (tool->lost_samples == perf_event__process_lost_samples) + if (tool->lost_samples == perf_event__process_lost_samples && + !(event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF)) evlist->stats.total_lost_samples += event->lost_samples.lost; return tool->lost_samples(tool, event, sample, machine); case PERF_RECORD_READ: -- cgit v1.2.3 From 335818470f558de5dc37bbcb31f97b303605a9df Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:32 -0700 Subject: perf bpf filter: Add 'pid' sample data support The pid is special because it's saved in the PERF_SAMPLE_TID together. So it needs to differenciate tid and pid using the 'part' field in the perf bpf filter entry struct. 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/util/bpf-filter.c | 4 +++- tools/perf/util/bpf-filter.h | 3 ++- tools/perf/util/bpf-filter.l | 11 ++++++++++- tools/perf/util/bpf-filter.y | 7 +++++-- tools/perf/util/bpf_skel/sample-filter.h | 3 ++- tools/perf/util/bpf_skel/sample_filter.bpf.c | 5 ++++- 6 files changed, 26 insertions(+), 7 deletions(-) (limited to 'tools/perf/util/bpf-filter.c') diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index 7bd6f2e41513..743c69fd6cd4 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -36,6 +36,7 @@ int perf_bpf_filter__prepare(struct evsel *evsel) list_for_each_entry(expr, &evsel->bpf_filters, list) { struct perf_bpf_filter_entry entry = { .op = expr->op, + .part = expr->part, .flags = expr->sample_flags, .value = expr->val, }; @@ -76,7 +77,7 @@ u64 perf_bpf_filter__lost_count(struct evsel *evsel) return skel ? skel->bss->dropped : 0; } -struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, int part, enum perf_bpf_filter_op op, unsigned long val) { @@ -85,6 +86,7 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flag expr = malloc(sizeof(*expr)); if (expr != NULL) { expr->sample_flags = sample_flags; + expr->part = part; expr->op = op; expr->val = val; } diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index f0c66764c6d0..3f8827bd965f 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -9,6 +9,7 @@ struct perf_bpf_filter_expr { struct list_head list; enum perf_bpf_filter_op op; + int part; unsigned long sample_flags; unsigned long val; }; @@ -16,7 +17,7 @@ struct perf_bpf_filter_expr { struct evsel; #ifdef HAVE_BPF_SKEL -struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, int part, enum perf_bpf_filter_op op, unsigned long val); int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index f6c0b74ea285..ec12fc4d2ab8 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -11,7 +11,15 @@ static int sample(unsigned long sample_flag) { - perf_bpf_filter_lval.sample = sample_flag; + perf_bpf_filter_lval.sample.type = sample_flag; + perf_bpf_filter_lval.sample.part = 0; + return BFT_SAMPLE; +} + +static int sample_part(unsigned long sample_flag, int part) +{ + perf_bpf_filter_lval.sample.type = sample_flag; + perf_bpf_filter_lval.sample.part = part; return BFT_SAMPLE; } @@ -56,6 +64,7 @@ ident [_a-zA-Z][_a-zA-Z0-9]+ ip { return sample(PERF_SAMPLE_IP); } id { return sample(PERF_SAMPLE_ID); } tid { return sample(PERF_SAMPLE_TID); } +pid { return sample_part(PERF_SAMPLE_TID, 1); } cpu { return sample(PERF_SAMPLE_CPU); } time { return sample(PERF_SAMPLE_TIME); } addr { return sample(PERF_SAMPLE_ADDR); } diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y index 13eca612ecca..0ca6532afd8d 100644 --- a/tools/perf/util/bpf-filter.y +++ b/tools/perf/util/bpf-filter.y @@ -20,7 +20,10 @@ static void perf_bpf_filter_error(struct list_head *expr __maybe_unused, %union { unsigned long num; - unsigned long sample; + struct { + unsigned long type; + int part; + } sample; enum perf_bpf_filter_op op; struct perf_bpf_filter_expr *expr; } @@ -48,7 +51,7 @@ filter_term filter_term: BFT_SAMPLE BFT_OP BFT_NUM { - $$ = perf_bpf_filter_expr__new($1, $2, $3); + $$ = perf_bpf_filter_expr__new($1.type, $1.part, $2, $3); } %% diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h index 862060bfda14..6b9fd554ad7b 100644 --- a/tools/perf/util/bpf_skel/sample-filter.h +++ b/tools/perf/util/bpf_skel/sample-filter.h @@ -17,7 +17,8 @@ enum perf_bpf_filter_op { /* BPF map entry for filtering */ struct perf_bpf_filter_entry { enum perf_bpf_filter_op op; - __u64 flags; + __u32 part; /* sub-sample type info when it has multiple values */ + __u64 flags; /* perf sample type flags */ __u64 value; }; diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index c07256279c3e..dddf38c27bb7 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -40,7 +40,10 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, case PERF_SAMPLE_ID: return kctx->data->id; case PERF_SAMPLE_TID: - return kctx->data->tid_entry.tid; + if (entry->part) + return kctx->data->tid_entry.pid; + else + return kctx->data->tid_entry.tid; case PERF_SAMPLE_CPU: return kctx->data->cpu_entry.cpu; case PERF_SAMPLE_TIME: -- cgit v1.2.3 From 46996dd7f655889a3dbbb514a0fa8bb614d6bd74 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:35 -0700 Subject: perf bpf filter: Add logical OR operator It supports two or more expressions connected as a group and the group result is considered true when one of them returns true. The new group operators (GROUP_BEGIN and GROUP_END) are added to setup and check the condition. As it doesn't allow nested groups, the condition is saved in local variables. For example, the following is to get samples only if the data source memory level is L2 cache or the weight value is greater than 30. $ sudo ./perf record -adW -e cpu/mem-loads/pp \ > --filter 'mem_lvl == l2 || weight > 30' -- sleep 1 $ sudo ./perf script -F data_src,weight 10668100842 |OP LOAD|LVL L3 or L3 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 47 11868100242 |OP LOAD|LVL LFB/MAB or LFB/MAB hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 57 10668100842 |OP LOAD|LVL L3 or L3 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 56 10650100842 |OP LOAD|LVL L3 or L3 hit|SNP None|TLB L2 miss|LCK No|BLK N/A 144 10468100442 |OP LOAD|LVL L2 or L2 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 16 10468100442 |OP LOAD|LVL L2 or L2 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 20 11868100242 |OP LOAD|LVL LFB/MAB or LFB/MAB hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 189 1026a100142 |OP LOAD|LVL L1 or L1 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A 193 10468100442 |OP LOAD|LVL L2 or L2 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 18 ... 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/util/bpf-filter.c | 25 ++++++++++++++++++ tools/perf/util/bpf-filter.h | 1 + tools/perf/util/bpf-filter.l | 1 + tools/perf/util/bpf-filter.y | 25 ++++++++++++++++-- tools/perf/util/bpf_skel/sample-filter.h | 6 +++-- tools/perf/util/bpf_skel/sample_filter.bpf.c | 38 ++++++++++++++++++---------- 6 files changed, 79 insertions(+), 17 deletions(-) (limited to 'tools/perf/util/bpf-filter.c') diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index 743c69fd6cd4..bd638737e12f 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -42,8 +42,32 @@ int perf_bpf_filter__prepare(struct evsel *evsel) }; bpf_map_update_elem(fd, &i, &entry, BPF_ANY); i++; + + if (expr->op == PBF_OP_GROUP_BEGIN) { + struct perf_bpf_filter_expr *group; + + list_for_each_entry(group, &expr->groups, list) { + struct perf_bpf_filter_entry group_entry = { + .op = group->op, + .part = group->part, + .flags = group->sample_flags, + .value = group->val, + }; + bpf_map_update_elem(fd, &i, &group_entry, BPF_ANY); + i++; + } + + memset(&entry, 0, sizeof(entry)); + entry.op = PBF_OP_GROUP_END; + bpf_map_update_elem(fd, &i, &entry, BPF_ANY); + i++; + } } + if (i > MAX_FILTERS) { + pr_err("Too many filters: %d (max = %d)\n", i, MAX_FILTERS); + return -1; + } prog = skel->progs.perf_sample_filter; for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) { for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) { @@ -89,6 +113,7 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flag expr->part = part; expr->op = op; expr->val = val; + INIT_LIST_HEAD(&expr->groups); } return expr; } diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index 3f8827bd965f..7afd159411b8 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -8,6 +8,7 @@ struct perf_bpf_filter_expr { struct list_head list; + struct list_head groups; enum perf_bpf_filter_op op; int part; unsigned long sample_flags; diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index 3e66b7a0215e..d4ff0f1345cd 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -151,6 +151,7 @@ hops2 { return constant(PERF_MEM_HOPS_2); } hops3 { return constant(PERF_MEM_HOPS_3); } "," { return ','; } +"||" { return BFT_LOGICAL_OR; } {ident} { return error("ident"); } . { return error("input"); } diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y index 0ca6532afd8d..07d6c7926c13 100644 --- a/tools/perf/util/bpf-filter.y +++ b/tools/perf/util/bpf-filter.y @@ -28,8 +28,8 @@ static void perf_bpf_filter_error(struct list_head *expr __maybe_unused, struct perf_bpf_filter_expr *expr; } -%token BFT_SAMPLE BFT_OP BFT_ERROR BFT_NUM -%type filter_term +%token BFT_SAMPLE BFT_OP BFT_ERROR BFT_NUM BFT_LOGICAL_OR +%type filter_term filter_expr %destructor { free ($$); } %type BFT_SAMPLE %type BFT_OP @@ -49,6 +49,27 @@ filter_term } filter_term: +filter_term BFT_LOGICAL_OR filter_expr +{ + struct perf_bpf_filter_expr *expr; + + if ($1->op == PBF_OP_GROUP_BEGIN) { + expr = $1; + } else { + expr = perf_bpf_filter_expr__new(0, 0, PBF_OP_GROUP_BEGIN, 1); + list_add_tail(&$1->list, &expr->groups); + } + expr->val++; + list_add_tail(&$3->list, &expr->groups); + $$ = expr; +} +| +filter_expr +{ + $$ = $1; +} + +filter_expr: BFT_SAMPLE BFT_OP BFT_NUM { $$ = perf_bpf_filter_expr__new($1.type, $1.part, $2, $3); diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h index 6b9fd554ad7b..2e96e1ab084a 100644 --- a/tools/perf/util/bpf_skel/sample-filter.h +++ b/tools/perf/util/bpf_skel/sample-filter.h @@ -1,7 +1,7 @@ #ifndef PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H #define PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H -#define MAX_FILTERS 32 +#define MAX_FILTERS 64 /* supported filter operations */ enum perf_bpf_filter_op { @@ -11,7 +11,9 @@ enum perf_bpf_filter_op { PBF_OP_GE, PBF_OP_LT, PBF_OP_LE, - PBF_OP_AND + PBF_OP_AND, + PBF_OP_GROUP_BEGIN, + PBF_OP_GROUP_END, }; /* BPF map entry for filtering */ diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index 88dbc788d257..57e3c67d6d37 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -99,6 +99,14 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, return 0; } +#define CHECK_RESULT(data, op, val) \ + if (!(data op val)) { \ + if (!in_group) \ + goto drop; \ + } else if (in_group) { \ + group_result = 1; \ + } + /* BPF program to be called from perf event overflow handler */ SEC("perf_event") int perf_sample_filter(void *ctx) @@ -106,6 +114,8 @@ int perf_sample_filter(void *ctx) struct bpf_perf_event_data_kern *kctx; struct perf_bpf_filter_entry *entry; __u64 sample_data; + int in_group = 0; + int group_result = 0; int i; kctx = bpf_cast_to_kern_ctx(ctx); @@ -120,32 +130,34 @@ int perf_sample_filter(void *ctx) switch (entry->op) { case PBF_OP_EQ: - if (!(sample_data == entry->value)) - goto drop; + CHECK_RESULT(sample_data, ==, entry->value) break; case PBF_OP_NEQ: - if (!(sample_data != entry->value)) - goto drop; + CHECK_RESULT(sample_data, !=, entry->value) break; case PBF_OP_GT: - if (!(sample_data > entry->value)) - goto drop; + CHECK_RESULT(sample_data, >, entry->value) break; case PBF_OP_GE: - if (!(sample_data >= entry->value)) - goto drop; + CHECK_RESULT(sample_data, >=, entry->value) break; case PBF_OP_LT: - if (!(sample_data < entry->value)) - goto drop; + CHECK_RESULT(sample_data, <, entry->value) break; case PBF_OP_LE: - if (!(sample_data <= entry->value)) - goto drop; + CHECK_RESULT(sample_data, <=, entry->value) break; case PBF_OP_AND: - if (!(sample_data & entry->value)) + CHECK_RESULT(sample_data, &, entry->value) + break; + case PBF_OP_GROUP_BEGIN: + in_group = 1; + group_result = 0; + break; + case PBF_OP_GROUP_END: + if (group_result == 0) goto drop; + in_group = 0; break; } } -- cgit v1.2.3 From 4310551b76e0d6762abb78fc23d50dcc3c608c33 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:36 -0700 Subject: perf bpf filter: Show warning for missing sample flags For a BPF filter to work properly, users need to provide appropriate options to enable the sample types. Otherwise the BPF program would see an invalid value (i.e. always 0) and filter won't work well. Show a warning message if sample types are missing like below. $ sudo ./perf record -e cycles --filter 'addr < 100' true Error: cycles event does not have PERF_SAMPLE_ADDR Hint: please add -d option to perf record. failed to set filter "BPF" on event cycles with 22 (Invalid argument) Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa 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/builtin-record.c | 2 +- tools/perf/util/bpf-filter.c | 62 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+), 1 deletion(-) (limited to 'tools/perf/util/bpf-filter.c') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 6df8b823859d..7b7e74a56346 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1353,7 +1353,7 @@ try_again: if (evlist__apply_filters(evlist, &pos)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", - pos->filter, evsel__name(pos), errno, + pos->filter ?: "BPF", evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); rc = -1; goto out; diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index bd638737e12f..0b30688d78a7 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -17,6 +17,64 @@ #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) +#define __PERF_SAMPLE_TYPE(st, opt) { st, #st, opt } +#define PERF_SAMPLE_TYPE(_st, opt) __PERF_SAMPLE_TYPE(PERF_SAMPLE_##_st, opt) + +static const struct perf_sample_info { + u64 type; + const char *name; + const char *option; +} sample_table[] = { + /* default sample flags */ + PERF_SAMPLE_TYPE(IP, NULL), + PERF_SAMPLE_TYPE(TID, NULL), + PERF_SAMPLE_TYPE(PERIOD, NULL), + /* flags mostly set by default, but still have options */ + PERF_SAMPLE_TYPE(ID, "--sample-identifier"), + PERF_SAMPLE_TYPE(CPU, "--sample-cpu"), + PERF_SAMPLE_TYPE(TIME, "-T"), + /* optional sample flags */ + PERF_SAMPLE_TYPE(ADDR, "-d"), + PERF_SAMPLE_TYPE(DATA_SRC, "-d"), + PERF_SAMPLE_TYPE(PHYS_ADDR, "--phys-data"), + PERF_SAMPLE_TYPE(WEIGHT, "-W"), + PERF_SAMPLE_TYPE(WEIGHT_STRUCT, "-W"), + PERF_SAMPLE_TYPE(TRANSACTION, "--transaction"), + PERF_SAMPLE_TYPE(CODE_PAGE_SIZE, "--code-page-size"), + PERF_SAMPLE_TYPE(DATA_PAGE_SIZE, "--data-page-size"), +}; + +static const struct perf_sample_info *get_sample_info(u64 flags) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(sample_table); i++) { + if (sample_table[i].type == flags) + return &sample_table[i]; + } + return NULL; +} + +static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr *expr) +{ + const struct perf_sample_info *info; + + if (evsel->core.attr.sample_type & expr->sample_flags) + return 0; + + info = get_sample_info(expr->sample_flags); + if (info == NULL) { + pr_err("Error: %s event does not have sample flags %lx\n", + evsel__name(evsel), expr->sample_flags); + return -1; + } + + pr_err("Error: %s event does not have %s\n", evsel__name(evsel), info->name); + if (info->option) + pr_err(" Hint: please add %s option to perf record\n", info->option); + return -1; +} + int perf_bpf_filter__prepare(struct evsel *evsel) { int i, x, y, fd; @@ -40,6 +98,10 @@ int perf_bpf_filter__prepare(struct evsel *evsel) .flags = expr->sample_flags, .value = expr->val, }; + + if (check_sample_flags(evsel, expr) < 0) + return -1; + bpf_map_update_elem(fd, &i, &entry, BPF_ANY); i++; -- cgit v1.2.3