From 3149733584c8f0ab828eada539df7aa488c023a9 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Sat, 11 Sep 2021 10:08:54 +0530 Subject: perf annotate: Add fusion logic for AMD microarchs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit AMD family 15h and above microarchs fuse a subset of cmp/test/ALU instructions with branch instructions[1][2]. Add perf annotate fused instruction support for these microarchs. Before: │ testb $0x80,0x51(%rax) │ ┌──jne 5b3 0.78 │ │ mov %r13,%rdi │ │→ callq mark_page_accessed 1.08 │5b3:└─→mov 0x8(%r13),%rax After: │ ┌──testb $0x80,0x51(%rax) │ ├──jne 5b3 0.78 │ │ mov %r13,%rdi │ │→ callq mark_page_accessed 1.08 │5b3:└─→mov 0x8(%r13),%rax [1] https://bugzilla.kernel.org/attachment.cgi?id=298553 [2] https://bugzilla.kernel.org/attachment.cgi?id=298555 Committer testing: On a: $ grep -m1 "model name" /proc/cpuinfo model name : AMD Ryzen 9 3900X 12-Core Processor $ Samples: 44K of event 'cycles', 4000 Hz, Event count (approx.): 7533249650 _int_malloc /usr/lib64/libc-2.33.so [Percent: local period] Percent│ ┌──test %eax,%eax │ ├──jne 884 │ │↓ jmpq 943 │ │ nop │878:│ add $0x10,%rdx 0.64 │ │ add %eax,%eax 0.57 │ │↓ je cc9 0.77 │884:└─→test %esi,%eax │ ↑ je 878 │ mov 0x18(%rdx),%r15 Reported-by: Kim Phillips Signed-off-by: Ravi Bangoria Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Link: https //lore.kernel.org/r/20210911043854.8373-2-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/annotate/instructions.c | 28 +++++++++++++++++++++++++++- tools/perf/util/annotate.c | 1 - 2 files changed, 27 insertions(+), 2 deletions(-) diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 24ea12ec7e02..305872692bfd 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -144,8 +144,31 @@ static struct ins x86__instructions[] = { { .name = "xorps", .ops = &mov_ops, }, }; -static bool x86__ins_is_fused(struct arch *arch, const char *ins1, +static bool amd__ins_is_fused(struct arch *arch, const char *ins1, const char *ins2) +{ + if (strstr(ins2, "jmp")) + return false; + + /* Family >= 15h supports cmp/test + branch fusion */ + if (arch->family >= 0x15 && (strstarts(ins1, "test") || + (strstarts(ins1, "cmp") && !strstr(ins1, "xchg")))) { + return true; + } + + /* Family >= 19h supports some ALU + branch fusion */ + if (arch->family >= 0x19 && (strstarts(ins1, "add") || + strstarts(ins1, "sub") || strstarts(ins1, "and") || + strstarts(ins1, "inc") || strstarts(ins1, "dec") || + strstarts(ins1, "or") || strstarts(ins1, "xor"))) { + return true; + } + + return false; +} + +static bool intel__ins_is_fused(struct arch *arch, const char *ins1, + const char *ins2) { if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp")) return false; @@ -184,6 +207,9 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid) if (ret == 3) { arch->family = family; arch->model = model; + arch->ins_is_fused = strstarts(cpuid, "AuthenticAMD") ? + amd__ins_is_fused : + intel__ins_is_fused; return 0; } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0bae061b2d6d..b55f35485e43 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -183,7 +183,6 @@ static struct arch architectures[] = { .init = x86__annotate_init, .instructions = x86__instructions, .nr_instructions = ARRAY_SIZE(x86__instructions), - .ins_is_fused = x86__ins_is_fused, .objdump = { .comment_char = '#', }, -- cgit v1.2.3 From ddf0d4dee4cbcabdf5161da3fe744b6cb149db88 Mon Sep 17 00:00:00 2001 From: Muhammad Falak R Wani Date: Sun, 15 Aug 2021 16:06:10 +0530 Subject: perf bpf: Deprecate bpf_map__resize() in favor of bpf_map_set_max_entries() As a part of libbpf 1.0 plan[0], this patch deprecates use of bpf_map__resize in favour of bpf_map__set_max_entries. Reference: https://github.com/libbpf/libbpf/issues/304 [0]: https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0#libbpfh-high-level-apis Signed-off-by: Muhammad Falak R Wani Acked-by: Andrii Nakryiko Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Jiri Olsa Cc: John Fastabend Cc: KP Singh Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Muhammad Falak R Wani Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Song Liu Cc: Yu Kuai Link: http //lore.kernel.org/lkml/20210815103610.27887-1-falakreyaz@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_counter.c | 8 ++++---- tools/perf/util/bpf_counter_cgroup.c | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index ba0f20853651..ced2dac31dcf 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -127,9 +127,9 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id) skel->rodata->num_cpu = evsel__nr_cpus(evsel); - bpf_map__resize(skel->maps.events, evsel__nr_cpus(evsel)); - bpf_map__resize(skel->maps.fentry_readings, 1); - bpf_map__resize(skel->maps.accum_readings, 1); + bpf_map__set_max_entries(skel->maps.events, evsel__nr_cpus(evsel)); + bpf_map__set_max_entries(skel->maps.fentry_readings, 1); + bpf_map__set_max_entries(skel->maps.accum_readings, 1); prog_name = bpf_target_prog_name(prog_fd); if (!prog_name) { @@ -399,7 +399,7 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, return -1; } - bpf_map__resize(skel->maps.events, libbpf_num_possible_cpus()); + bpf_map__set_max_entries(skel->maps.events, libbpf_num_possible_cpus()); err = bperf_leader_bpf__load(skel); if (err) { pr_err("Failed to load leader skeleton\n"); diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 89aa5e71db1a..cbc6c2bca488 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -65,14 +65,14 @@ static int bperf_load_program(struct evlist *evlist) /* we need one copy of events per cpu for reading */ map_size = total_cpus * evlist->core.nr_entries / nr_cgroups; - bpf_map__resize(skel->maps.events, map_size); - bpf_map__resize(skel->maps.cgrp_idx, nr_cgroups); + bpf_map__set_max_entries(skel->maps.events, map_size); + bpf_map__set_max_entries(skel->maps.cgrp_idx, nr_cgroups); /* previous result is saved in a per-cpu array */ map_size = evlist->core.nr_entries / nr_cgroups; - bpf_map__resize(skel->maps.prev_readings, map_size); + bpf_map__set_max_entries(skel->maps.prev_readings, map_size); /* cgroup result needs all events (per-cpu) */ map_size = evlist->core.nr_entries; - bpf_map__resize(skel->maps.cgrp_readings, map_size); + bpf_map__set_max_entries(skel->maps.cgrp_readings, map_size); set_max_rlimit(); -- cgit v1.2.3 From 00e0ca3721cf2ddcb38cf676a3de61933640d31d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 14 Sep 2021 10:00:04 -0700 Subject: perf bpf: Ignore deprecation warning when using libbpf's btf__get_from_id() Perf code re-implements libbpf's btf__load_from_kernel_by_id() API as a weak function, presumably to dynamically link against old version of libbpf shared library. Unfortunately this causes compilation warning when perf is compiled against libbpf v0.6+. For now, just ignore deprecation warning, but there might be a better solution, depending on perf's needs. Signed-off-by: Andrii Nakryiko Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: kernel-team@fb.com LPU-Reference: 20210914170004.4185659-1-andrii@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-event.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 683f6d63560e..1a7112a87736 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -24,7 +24,10 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) { struct btf *btf; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" int err = btf__get_from_id(id, &btf); +#pragma GCC diagnostic pop return err ? ERR_PTR(err) : btf; } -- cgit v1.2.3 From 8228e9361e2a7447eaed87499123e85871c8bc18 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 15 Sep 2021 14:14:28 -0700 Subject: perf parse-events: Avoid enum forward declaration. Enum forward declarations aren't allowed as the size can't be implied. Switch to just using an int. This fixes a clang warning: In file included from tools/perf/bench/evlist-open-close.c:13: tools/perf/bench/../util/parse-events.h:185:6: error: redeclaration of already-defined enum 'perf_tool_event' is a GNU extension [-Werror,-Wgnu-redeclared-enum] enum perf_tool_event; ^ tools/perf/bench/../util/evsel.h:28:6: note: previous definition is here enum perf_tool_event { ^ Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210915211428.1773567-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 +- tools/perf/util/parse-events.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 51a2219df601..5d1346aa0627 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1471,7 +1471,7 @@ out_free_terms: int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, - enum perf_tool_event tool_event) + int tool_event) { return add_event_tool(list, &parse_state->idx, tool_event); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index bf6e41aa9b6a..b32ed3064c49 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -182,10 +182,9 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config); -enum perf_tool_event; int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, - enum perf_tool_event tool_event); + int tool_event); int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2, struct parse_events_error *error, -- cgit v1.2.3 From 84111b9c950ec9a8b31166973e79aa77ddcee7e3 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 10 Aug 2021 21:46:57 -0700 Subject: perf tools: Allow controlling synthesizing PERF_RECORD_ metadata events during record Depending on the use case, it might require some kind of synthesizing and some not. Make it controllable to turn off heavy operations like MMAP for all tasks. Currently all users are converted to enable all the synthesis by default. It'll be updated in the later patch. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Ian Rogers Cc: Ingo Molnar Cc: Jin Yao Cc: Peter Zijlstra Cc: Stephane Eranian Link: https //lore.kernel.org/r/20210811044658.1313391-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/synthesize.c | 4 ++-- tools/perf/builtin-kvm.c | 2 +- tools/perf/builtin-record.c | 6 +++-- tools/perf/builtin-top.c | 2 +- tools/perf/builtin-trace.c | 4 ++-- tools/perf/tests/code-reading.c | 3 ++- tools/perf/tests/mmap-thread-lookup.c | 4 ++-- tools/perf/util/synthetic-events.c | 45 ++++++++++++++++++++--------------- tools/perf/util/synthetic-events.h | 8 +++---- 9 files changed, 44 insertions(+), 34 deletions(-) diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 05f7c923c745..7401ebbac100 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -80,7 +80,7 @@ static int do_run_single_threaded(struct perf_session *session, NULL, target, threads, process_synthesized_event, - data_mmap, + true, data_mmap, nr_threads_synthesize); if (err) return err; @@ -171,7 +171,7 @@ static int do_run_multi_threaded(struct target *target, NULL, target, NULL, process_synthesized_event, - false, + true, false, nr_threads_synthesize); if (err) { perf_session__delete(session); diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index aa1b127ffb5b..c6f352ee57e6 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1456,7 +1456,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, perf_session__set_id_hdr_size(kvm->session); ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true); machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target, - kvm->evlist->core.threads, false, 1); + kvm->evlist->core.threads, true, false, 1); err = kvm_live_open_events(kvm); if (err) goto out; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index b3509d9d20cc..0263e383332f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1266,6 +1266,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) err = perf_event__synthesize_thread_map(&rec->tool, thread_map, process_synthesized_event, &rec->session->machines.host, + true, rec->opts.sample_address); perf_thread_map__put(thread_map); return err; @@ -1480,8 +1481,9 @@ static int record__synthesize(struct record *rec, bool tail) f = process_locked_synthesized_event; } - err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads, - f, opts->sample_address, + err = __machine__synthesize_threads(machine, tool, &opts->target, + rec->evlist->core.threads, + f, true, opts->sample_address, rec->opts.nr_threads_synthesize); if (rec->opts.nr_threads_synthesize > 1) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a3ae9176a83e..020c4f110c10 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1271,7 +1271,7 @@ static int __cmd_top(struct perf_top *top) pr_debug("Couldn't synthesize cgroup events.\n"); machine__synthesize_threads(&top->session->machines.host, &opts->target, - top->evlist->core.threads, false, + top->evlist->core.threads, true, false, top->nr_threads_synthesize); if (top->nr_threads_synthesize > 1) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 2bf21194c7b3..2f1d20553a0a 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1628,8 +1628,8 @@ static int trace__symbols_init(struct trace *trace, struct evlist *evlist) goto out; err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target, - evlist->core.threads, trace__tool_process, false, - 1); + evlist->core.threads, trace__tool_process, + true, false, 1); out: if (err) symbol__exit(); diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9866cddebf23..3a4d932e7ffc 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -606,7 +606,8 @@ static int do_test_code_reading(bool try_kcore) } ret = perf_event__synthesize_thread_map(NULL, threads, - perf_event__process, machine, false); + perf_event__process, machine, + true, false); if (ret < 0) { pr_debug("perf_event__synthesize_thread_map failed\n"); goto out_err; diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 8d9d4cbff76d..6f2da7a72f67 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -135,7 +135,7 @@ static int synth_all(struct machine *machine) { return perf_event__synthesize_threads(NULL, perf_event__process, - machine, 0, 1); + machine, 1, 0, 1); } static int synth_process(struct machine *machine) @@ -147,7 +147,7 @@ static int synth_process(struct machine *machine) err = perf_event__synthesize_thread_map(NULL, map, perf_event__process, - machine, 0); + machine, 1, 0); perf_thread_map__put(map); return err; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a7e981b2d7de..a7a2825356d6 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -715,7 +715,8 @@ static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *fork_event, union perf_event *namespaces_event, pid_t pid, int full, perf_event__handler_t process, - struct perf_tool *tool, struct machine *machine, bool mmap_data) + struct perf_tool *tool, struct machine *machine, + bool needs_mmap, bool mmap_data) { char filename[PATH_MAX]; struct dirent **dirent; @@ -739,7 +740,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, * send mmap only for thread group leader * see thread__init_maps() */ - if (pid == tgid && + if (pid == tgid && needs_mmap && perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data)) return -1; @@ -786,7 +787,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, break; rc = 0; - if (_pid == pid && !kernel_thread) { + if (_pid == pid && !kernel_thread && needs_mmap) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); @@ -806,7 +807,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, - bool mmap_data) + bool needs_mmap, bool mmap_data) { union perf_event *comm_event, *mmap_event, *fork_event; union perf_event *namespaces_event; @@ -836,7 +837,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, fork_event, namespaces_event, perf_thread_map__pid(threads, thread), 0, process, tool, machine, - mmap_data)) { + needs_mmap, mmap_data)) { err = -1; break; } @@ -862,7 +863,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, fork_event, namespaces_event, comm_event->comm.pid, 0, process, tool, machine, - mmap_data)) { + needs_mmap, mmap_data)) { err = -1; break; } @@ -882,6 +883,7 @@ out: static int __perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, + bool needs_mmap, bool mmap_data, struct dirent **dirent, int start, @@ -926,7 +928,7 @@ static int __perf_event__synthesize_threads(struct perf_tool *tool, */ __event__synthesize_thread(comm_event, mmap_event, fork_event, namespaces_event, pid, 1, process, - tool, machine, mmap_data); + tool, machine, needs_mmap, mmap_data); } err = 0; @@ -945,6 +947,7 @@ struct synthesize_threads_arg { struct perf_tool *tool; perf_event__handler_t process; struct machine *machine; + bool needs_mmap; bool mmap_data; struct dirent **dirent; int num; @@ -956,7 +959,8 @@ static void *synthesize_threads_worker(void *arg) struct synthesize_threads_arg *args = arg; __perf_event__synthesize_threads(args->tool, args->process, - args->machine, args->mmap_data, + args->machine, + args->needs_mmap, args->mmap_data, args->dirent, args->start, args->num); return NULL; @@ -965,7 +969,7 @@ static void *synthesize_threads_worker(void *arg) int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, - bool mmap_data, + bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize) { struct synthesize_threads_arg *args = NULL; @@ -994,7 +998,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (thread_nr <= 1) { err = __perf_event__synthesize_threads(tool, process, - machine, mmap_data, + machine, + needs_mmap, mmap_data, dirent, base, n); goto free_dirent; } @@ -1015,6 +1020,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, args[i].tool = tool; args[i].process = process; args[i].machine = machine; + args[i].needs_mmap = needs_mmap; args[i].mmap_data = mmap_data; args[i].dirent = dirent; } @@ -1775,26 +1781,27 @@ out_err: int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, - unsigned int nr_threads_synthesize) + perf_event__handler_t process, bool needs_mmap, + bool data_mmap, unsigned int nr_threads_synthesize) { if (target__has_task(target)) - return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap); + return perf_event__synthesize_thread_map(tool, threads, process, machine, + needs_mmap, data_mmap); else if (target__has_cpu(target)) - return perf_event__synthesize_threads(tool, process, - machine, data_mmap, + return perf_event__synthesize_threads(tool, process, machine, + needs_mmap, data_mmap, nr_threads_synthesize); /* command specified */ return 0; } int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, - unsigned int nr_threads_synthesize) + struct perf_thread_map *threads, bool needs_mmap, + bool data_mmap, unsigned int nr_threads_synthesize) { return __machine__synthesize_threads(machine, NULL, target, threads, - perf_event__process, data_mmap, - nr_threads_synthesize); + perf_event__process, needs_mmap, + data_mmap, nr_threads_synthesize); } static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id) diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index c845e2b9b444..44f72d56ca4d 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -53,8 +53,8 @@ int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct p int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine); -int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data); -int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize); +int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data); +int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize); int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process); int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine); @@ -65,10 +65,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, + perf_event__handler_t process, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, + struct perf_thread_map *threads, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); #ifdef HAVE_AUXTRACE_SUPPORT -- cgit v1.2.3 From 41b740b6e8a994e5830daa5e15785522874f7456 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 10 Aug 2021 21:46:58 -0700 Subject: perf record: Add --synth option Add an option to control the synthesizing behavior. --synth Fine-tune event synthesis: default=all This can be useful when we know it doesn't need some synthesis like in a specific usecase and/or when using pipe: $ perf record -a --all-cgroups --synth cgroup -o- sleep 1 | \ > perf report -i- -s cgroup Committer notes: Added a clarification to the man page entry for --synth that this is about pre-existing threads. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Ian Rogers Cc: Ingo Molnar Cc: Jin Yao Cc: Peter Zijlstra Cc: Stephane Eranian Link: https //lore.kernel.org/r/20210811044658.1313391-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 16 +++++++++++ tools/perf/builtin-record.c | 48 ++++++++++++++++++++++++++------ tools/perf/util/record.h | 1 + tools/perf/util/synthetic-events.c | 28 +++++++++++++++++++ tools/perf/util/synthetic-events.h | 12 ++++++++ 5 files changed, 96 insertions(+), 9 deletions(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index f1079ee7f2ec..2d7df8703cf2 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -596,6 +596,22 @@ options. 'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj in config file is set to true. +--synth=TYPE:: +Collect and synthesize given type of events (comma separated). Note that +this option controls the synthesis from the /proc filesystem which represent +task status for pre-existing threads. + +Kernel (and some other) events are recorded regardless of the +choice in this option. For example, --synth=no would have MMAP events for +kernel and modules. + +Available types are: + 'task' - synthesize FORK and COMM events for each task + 'mmap' - synthesize MMAP events for each process (implies 'task') + 'cgroup' - synthesize CGROUP events for each cgroup + 'all' - synthesize all events (default) + 'no' - do not synthesize any of the above events + --tail-synthesize:: Instead of collecting non-sample events (for example, fork, comm, mmap) at the beginning of record, collect them during finalizing an output file. diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 0263e383332f..41bb884f5a74 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1255,6 +1255,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) { int err; struct perf_thread_map *thread_map; + bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP; if (rec->opts.tail_synthesize != tail) return 0; @@ -1266,7 +1267,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) err = perf_event__synthesize_thread_map(&rec->tool, thread_map, process_synthesized_event, &rec->session->machines.host, - true, + needs_mmap, rec->opts.sample_address); perf_thread_map__put(thread_map); return err; @@ -1471,20 +1472,26 @@ static int record__synthesize(struct record *rec, bool tail) if (err < 0) pr_warning("Couldn't synthesize bpf events.\n"); - err = perf_event__synthesize_cgroups(tool, process_synthesized_event, - machine); - if (err < 0) - pr_warning("Couldn't synthesize cgroup events.\n"); + if (rec->opts.synth & PERF_SYNTH_CGROUP) { + err = perf_event__synthesize_cgroups(tool, process_synthesized_event, + machine); + if (err < 0) + pr_warning("Couldn't synthesize cgroup events.\n"); + } if (rec->opts.nr_threads_synthesize > 1) { perf_set_multithreaded(); f = process_locked_synthesized_event; } - err = __machine__synthesize_threads(machine, tool, &opts->target, - rec->evlist->core.threads, - f, true, opts->sample_address, - rec->opts.nr_threads_synthesize); + if (rec->opts.synth & PERF_SYNTH_TASK) { + bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP; + + err = __machine__synthesize_threads(machine, tool, &opts->target, + rec->evlist->core.threads, + f, needs_mmap, opts->sample_address, + rec->opts.nr_threads_synthesize); + } if (rec->opts.nr_threads_synthesize > 1) perf_set_singlethreaded(); @@ -2393,6 +2400,26 @@ static int process_timestamp_boundary(struct perf_tool *tool, return 0; } +static int parse_record_synth_option(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + struct record_opts *opts = opt->value; + char *p = strdup(str); + + if (p == NULL) + return -1; + + opts->synth = parse_synth_opt(p); + free(p); + + if (opts->synth < 0) { + pr_err("Invalid synth option: %s\n", str); + return -1; + } + return 0; +} + /* * XXX Ideally would be local to cmd_record() and passed to a record__new * because we need to have access to it in record__exit, that is called @@ -2418,6 +2445,7 @@ static struct record record = { .nr_threads_synthesize = 1, .ctl_fd = -1, .ctl_fd_ack = -1, + .synth = PERF_SYNTH_ALL, }, .tool = { .sample = process_sample_event, @@ -2633,6 +2661,8 @@ static struct option __record_options[] = { "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n" "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.", parse_control_option), + OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup", + "Fine-tune event synthesis: default=all", parse_record_synth_option), OPT_END() }; diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 68f471d9a88b..ef6c2715fdd9 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -77,6 +77,7 @@ struct record_opts { int ctl_fd; int ctl_fd_ack; bool ctl_fd_close; + int synth; }; extern const char * const *record_usage; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a7a2825356d6..198982109f0f 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -2237,3 +2237,31 @@ int perf_event__synthesize_for_pipe(struct perf_tool *tool, return ret; } + +int parse_synth_opt(char *synth) +{ + char *p, *q; + int ret = 0; + + if (synth == NULL) + return -1; + + for (q = synth; (p = strsep(&q, ",")); p = q) { + if (!strcasecmp(p, "no") || !strcasecmp(p, "none")) + return 0; + + if (!strcasecmp(p, "all")) + return PERF_SYNTH_ALL; + + if (!strcasecmp(p, "task")) + ret |= PERF_SYNTH_TASK; + else if (!strcasecmp(p, "mmap")) + ret |= PERF_SYNTH_TASK | PERF_SYNTH_MMAP; + else if (!strcasecmp(p, "cgroup")) + ret |= PERF_SYNTH_CGROUP; + else + return -1; + } + + return ret; +} diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index 44f72d56ca4d..c931433bacbf 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -27,6 +27,18 @@ struct target; union perf_event; +enum perf_record_synth { + PERF_SYNTH_TASK = 1 << 0, + PERF_SYNTH_MMAP = 1 << 1, + PERF_SYNTH_CGROUP = 1 << 2, + + /* last element */ + PERF_SYNTH_MAX = 1 << 3, +}; +#define PERF_SYNTH_ALL (PERF_SYNTH_MAX - 1) + +int parse_synth_opt(char *str); + typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); -- cgit v1.2.3 From b28e5e439109fe6fd9fa047654ae99d0b7bc5ccc Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 16 Jun 2021 22:55:54 -0700 Subject: perf daemon: Avoid msan warnings on send_cmd As a full union is always sent, ensure all bytes of the union are initialized with memset to avoid msan warnings of use of uninitialized memory. An example warning from the daemon test: Uninitialized bytes in __interceptor_write at offset 71 inside [0x7ffd98da6280, 72) ==11602==WARNING: MemorySanitizer: use-of-uninitialized-value #0 0x5597edccdbe4 in ion tools/lib/perf/lib.c:18:6 #1 0x5597edccdbe4 in writen tools/lib/perf/lib.c:47:9 #2 0x5597ed221d30 in send_cmd tools/perf/builtin-daemon.c:1376:22 #3 0x5597ed21b48c in cmd_daemon tools/perf/builtin-daemon.c #4 0x5597ed1d6b67 in run_builtin tools/perf/perf.c:313:11 #5 0x5597ed1d6036 in handle_internal_command tools/perf/perf.c:365:8 #6 0x5597ed1d6036 in run_argv tools/perf/perf.c:409:2 #7 0x5597ed1d6036 in main tools/perf/perf.c:539:3 SUMMARY: MemorySanitizer: use-of-uninitialized-value tools/lib/perf/lib.c:18:6 in ion Exiting Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210617055554.1917997-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-daemon.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index 61929f63a047..c13201fb09c3 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -1403,8 +1403,10 @@ out: static int send_cmd_list(struct daemon *daemon) { - union cmd cmd = { .cmd = CMD_LIST, }; + union cmd cmd; + memset(&cmd, 0, sizeof(cmd)); + cmd.list.cmd = CMD_LIST; cmd.list.verbose = verbose; cmd.list.csv_sep = daemon->csv_sep ? *daemon->csv_sep : 0; @@ -1432,6 +1434,7 @@ static int __cmd_signal(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); cmd.signal.cmd = CMD_SIGNAL, cmd.signal.sig = SIGUSR2; strncpy(cmd.signal.name, name, sizeof(cmd.signal.name) - 1); @@ -1446,7 +1449,7 @@ static int __cmd_stop(struct daemon *daemon, struct option parent_options[], OPT_PARENT(parent_options), OPT_END() }; - union cmd cmd = { .cmd = CMD_STOP, }; + union cmd cmd; argc = parse_options(argc, argv, start_options, daemon_usage, 0); if (argc) @@ -1457,6 +1460,8 @@ static int __cmd_stop(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = CMD_STOP; return send_cmd(daemon, &cmd); } @@ -1470,7 +1475,7 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[], OPT_PARENT(parent_options), OPT_END() }; - union cmd cmd = { .cmd = CMD_PING, }; + union cmd cmd; argc = parse_options(argc, argv, ping_options, daemon_usage, 0); if (argc) @@ -1481,6 +1486,8 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = CMD_PING; scnprintf(cmd.ping.name, sizeof(cmd.ping.name), "%s", name); return send_cmd(daemon, &cmd); } -- cgit v1.2.3 From cb7bfb1da6f609bf954d5f164733ff35b1cb4d4e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 27 Jan 2021 10:46:29 -0800 Subject: perf parse-events: Remove unnecessary #includes Minor cleanup motivated by trying to separately fuzz test parse-events. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210127184629.516169-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 -- tools/perf/util/parse-events.l | 1 - 2 files changed, 3 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5d1346aa0627..85d3d77d3c6a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -19,8 +19,6 @@ #include #include "string2.h" #include "strlist.h" -#include "symbol.h" -#include "header.h" #include "bpf-loader.h" #include "debug.h" #include diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 923849024b15..47da7a0c5df4 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -12,7 +12,6 @@ #include #include #include -#include "../perf.h" #include "parse-events.h" #include "parse-events-bison.h" #include "evsel.h" -- cgit v1.2.3 From 6c93f39f2f435d822c2f765650f405acebdc49fc Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Thu, 9 Sep 2021 14:18:44 +0800 Subject: perf list: Display pmu prefix for partially supported hybrid cache events Part of hardware cache events are only available on one CPU PMU. For example, 'L1-dcache-load-misses' is only available on cpu_core. perf list should clearly report this info. root@otcpl-adl-s-2:~# ./perf list Before: L1-dcache-load-misses [Hardware cache event] L1-dcache-loads [Hardware cache event] L1-dcache-stores [Hardware cache event] L1-icache-load-misses [Hardware cache event] L1-icache-loads [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-stores [Hardware cache event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-stores [Hardware cache event] iTLB-load-misses [Hardware cache event] node-load-misses [Hardware cache event] node-loads [Hardware cache event] node-store-misses [Hardware cache event] node-stores [Hardware cache event] After: L1-dcache-loads [Hardware cache event] L1-dcache-stores [Hardware cache event] L1-icache-load-misses [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-stores [Hardware cache event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] cpu_atom/L1-icache-loads/ [Hardware cache event] cpu_core/L1-dcache-load-misses/ [Hardware cache event] cpu_core/node-load-misses/ [Hardware cache event] cpu_core/node-loads/ [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-stores [Hardware cache event] iTLB-load-misses [Hardware cache event] Now we can clearly see 'L1-dcache-load-misses' is only available on cpu_core. If without pmu prefix, it indicates the event is available on both cpu_core and cpu_atom. Signed-off-by: Jin Yao Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210909061844.10221-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 76 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 68 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 85d3d77d3c6a..067f830dea4b 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2701,7 +2701,7 @@ next: return 0; } -static bool is_event_supported(u8 type, unsigned config) +static bool is_event_supported(u8 type, u64 config) { bool ret = true; int open_return; @@ -2821,10 +2821,18 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, int print_hwcache_events(const char *event_glob, bool name_only) { - unsigned int type, op, i, evt_i = 0, evt_num = 0; - char name[64]; - char **evt_list = NULL; + unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0; + char name[64], new_name[128]; + char **evt_list = NULL, **evt_pmus = NULL; bool evt_num_known = false; + struct perf_pmu *pmu = NULL; + + if (perf_pmu__has_hybrid()) { + npmus = perf_pmu__hybrid_pmu_num(); + evt_pmus = zalloc(sizeof(char *) * npmus); + if (!evt_pmus) + goto out_enomem; + } restart: if (evt_num_known) { @@ -2840,20 +2848,61 @@ restart: continue; for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + unsigned int hybrid_supported = 0, j; + bool supported; + __evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name)); if (event_glob != NULL && !strglobmatch(name, event_glob)) continue; - if (!is_event_supported(PERF_TYPE_HW_CACHE, - type | (op << 8) | (i << 16))) - continue; + if (!perf_pmu__has_hybrid()) { + if (!is_event_supported(PERF_TYPE_HW_CACHE, + type | (op << 8) | (i << 16))) { + continue; + } + } else { + perf_pmu__for_each_hybrid_pmu(pmu) { + if (!evt_num_known) { + evt_num++; + continue; + } + + supported = is_event_supported( + PERF_TYPE_HW_CACHE, + type | (op << 8) | (i << 16) | + ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT)); + if (supported) { + snprintf(new_name, sizeof(new_name), "%s/%s/", + pmu->name, name); + evt_pmus[hybrid_supported] = strdup(new_name); + hybrid_supported++; + } + } + + if (hybrid_supported == 0) + continue; + } if (!evt_num_known) { evt_num++; continue; } - evt_list[evt_i] = strdup(name); + if ((hybrid_supported == 0) || + (hybrid_supported == npmus)) { + evt_list[evt_i] = strdup(name); + if (npmus > 0) { + for (j = 0; j < npmus; j++) + zfree(&evt_pmus[j]); + } + } else { + for (j = 0; j < hybrid_supported; j++) { + evt_list[evt_i++] = evt_pmus[j]; + evt_pmus[j] = NULL; + } + continue; + } + if (evt_list[evt_i] == NULL) goto out_enomem; evt_i++; @@ -2865,6 +2914,13 @@ restart: evt_num_known = true; goto restart; } + + for (evt_i = 0; evt_i < evt_num; evt_i++) { + if (!evt_list[evt_i]) + break; + } + + evt_num = evt_i; qsort(evt_list, evt_num, sizeof(char *), cmp_string); evt_i = 0; while (evt_i < evt_num) { @@ -2883,6 +2939,10 @@ out_free: for (evt_i = 0; evt_i < evt_num; evt_i++) zfree(&evt_list[evt_i]); zfree(&evt_list); + + for (evt_i = 0; evt_i < npmus; evt_i++) + zfree(&evt_pmus[evt_i]); + zfree(&evt_pmus); return evt_num; out_enomem: -- cgit v1.2.3 From 0ba37e05c240c7b38e5a327a96f404798a8698ff Mon Sep 17 00:00:00 2001 From: William Cohen Date: Sun, 26 Sep 2021 20:51:15 -0400 Subject: perf annotate: Add riscv64 support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds basic arch initialization and instruction associate support for the riscv64 CPU architecture. Example output: $ perf annotate --stdio2 Samples: 122K of event 'task-clock:u', 4000 Hz, Event count (approx.): 30637250000, [percent: local period] strcmp() /usr/lib64/libc-2.32.so Percent Disassembly of section .text: 0000000000069a30 : __GI_strcmp(): const unsigned char *s2 = (const unsigned char *) p2; unsigned char c1, c2; do { c1 = (unsigned char) *s1++; 37.30 lbu a5,0(a0) c2 = (unsigned char) *s2++; 1.23 addi a1,a1,1 c1 = (unsigned char) *s1++; 18.68 addi a0,a0,1 c2 = (unsigned char) *s2++; 1.37 lbu a4,-1(a1) if (c1 == '\0') 18.71 ↓ beqz a5,18 return c1 - c2; } Signed-off-by: William Cohen Cc: Albert Ou Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: linux-riscv@lists.infradead.org Link: http://lore.kernel.org/lkml/20210927005115.610264-1-wcohen@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/riscv64/annotate/instructions.c | 34 +++++++++++++++++++++++++ tools/perf/util/annotate.c | 5 ++++ 2 files changed, 39 insertions(+) create mode 100644 tools/perf/arch/riscv64/annotate/instructions.c diff --git a/tools/perf/arch/riscv64/annotate/instructions.c b/tools/perf/arch/riscv64/annotate/instructions.c new file mode 100644 index 000000000000..869a0eb28953 --- /dev/null +++ b/tools/perf/arch/riscv64/annotate/instructions.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +static +struct ins_ops *riscv64__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + if (!strncmp(name, "jal", 3) || + !strncmp(name, "jr", 2) || + !strncmp(name, "call", 4)) + ops = &call_ops; + else if (!strncmp(name, "ret", 3)) + ops = &ret_ops; + else if (name[0] == 'j' || name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +static +int riscv64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->associate_instruction_ops = riscv64__associate_ins_ops; + arch->initialized = true; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index b55f35485e43..4bab2273303a 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -151,6 +151,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/mips/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" +#include "arch/riscv64/annotate/instructions.c" #include "arch/s390/annotate/instructions.c" #include "arch/sparc/annotate/instructions.c" @@ -191,6 +192,10 @@ static struct arch architectures[] = { .name = "powerpc", .init = powerpc__annotate_init, }, + { + .name = "riscv64", + .init = riscv64__annotate_init, + }, { .name = "s390", .init = s390__annotate_init, -- cgit v1.2.3 From 0e46c8307574a8e2dac8d7ba97e0f6f4bbee67a5 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 Sep 2021 14:15:01 -0300 Subject: perf jevents: Add __maybe_unused attribute to unused function arg The tools/perf/pmu-events/jevents.c file isn't being compiled with -Werror and -Wextra, which will be the case soon, so before we turn those compiler flags on, fix what it would flag. Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Like Xu Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo To: John Garry --- tools/perf/pmu-events/jevents.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 6731b3cf0c2f..323e1dfe2436 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -45,6 +45,7 @@ #include /* getrlimit */ #include #include +#include #include #include "jsmn.h" #include "json.h" @@ -470,7 +471,7 @@ static void free_arch_std_events(void) } } -static int save_arch_std_events(void *data, struct json_event *je) +static int save_arch_std_events(void *data __maybe_unused, struct json_event *je) { struct event_struct *es; -- cgit v1.2.3 From 4a87dea9e60fe10079f01e06a58c4f9dfb667940 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 17 Sep 2021 11:42:39 -0700 Subject: perf test: Workload test of metric and metricgroups Test every metric and metricgroup with 'true' as a workload. For metrics, check that we see the metric printed or get unsupported. If the 'true' workload executes too quickly retry with 'perf bench internals synthesize'. v3. Fix test condition (thanks to Paul A. Clarke ). Add a fallback case of a larger workload so that we don't ignore "". v2. Switched the workload to something faster. Signed-off-by: Ian Rogers Reviewed-by: John Garry Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210917184240.2181186-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat_all_metricgroups.sh | 12 ++++++++++++ tools/perf/tests/shell/stat_all_metrics.sh | 22 ++++++++++++++++++++++ 2 files changed, 34 insertions(+) create mode 100755 tools/perf/tests/shell/stat_all_metricgroups.sh create mode 100755 tools/perf/tests/shell/stat_all_metrics.sh diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh new file mode 100755 index 000000000000..de24d374ce24 --- /dev/null +++ b/tools/perf/tests/shell/stat_all_metricgroups.sh @@ -0,0 +1,12 @@ +#!/bin/sh +# perf all metricgroups test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for m in $(perf list --raw-dump metricgroups); do + echo "Testing $m" + perf stat -M "$m" true +done + +exit 0 diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh new file mode 100755 index 000000000000..7f4ba3cad632 --- /dev/null +++ b/tools/perf/tests/shell/stat_all_metrics.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# perf all metrics test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for m in $(perf list --raw-dump metrics); do + echo "Testing $m" + result=$(perf stat -M "$m" true 2>&1) + if [[ ! "$result" =~ "$m" ]] && [[ ! "$result" =~ "" ]]; then + # We failed to see the metric and the events are support. Possibly the + # workload was too small so retry with something longer. + result=$(perf stat -M "$m" perf bench internals synthesize 2>&1) + if [[ ! "$result" =~ "$m" ]]; then + echo "Metric '$m' not printed in:" + echo "$result" + exit 1 + fi + fi +done + +exit 0 -- cgit v1.2.3 From 3d5ac9effcc640d5d66bc6d833e1dcc9faa279aa Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 17 Sep 2021 11:42:40 -0700 Subject: perf test: Workload test of all PMUs Iterate over the list of PMUs and run the 'true' workload on them. If the event isn't printed then run the large 'perf bench internals synthesize' workload and check the event is counted. On a Skylake this test takes 1m15s mainly running the 'true' workload. Suggested-by: John Garry Signed-off-by: Ian Rogers Reviewed-by: John Garry Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Paul Clarke Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210917184240.2181186-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat_all_pmu.sh | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100755 tools/perf/tests/shell/stat_all_pmu.sh diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh new file mode 100755 index 000000000000..2de7fd0394fd --- /dev/null +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# perf all PMU test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for p in $(perf list --raw-dump pmu); do + echo "Testing $p" + result=$(perf stat -e "$p" true 2>&1) + if [[ ! "$result" =~ "$p" ]] && [[ ! "$result" =~ "" ]]; then + # We failed to see the event and it is supported. Possibly the workload was + # too small so retry with something longer. + result=$(perf stat -e "$p" perf bench internals synthesize 2>&1) + if [[ ! "$result" =~ "$p" ]]; then + echo "Event '$p' not printed in:" + echo "$result" + exit 1 + fi + fi +done + +exit 0 -- cgit v1.2.3 From b758a61b391fb5ed749f4848f444d8223ae0a324 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 17:10:21 -0700 Subject: perf tools: Enable libtracefs dynamic linking Currently libtracefs isn't used by perf, but there are potential improvements by using it as identified Steven Rostedt's e-mail: https://lore.kernel.org/lkml/20210610154759.1ef958f0@oasis.local.home/ This change is modelled on the dynamic libtraceevent patch by Michael Petlan: https://lore.kernel.org/linux-perf-users/20210428092023.4009-1-mpetlan@redhat.com/ v3. Adds file missed in v1 and v2 spotted by Jiri Olsa. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20210923001024.550263-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 4 ++++ tools/build/feature/test-libtracefs.c | 10 ++++++++++ tools/perf/Makefile.config | 9 +++++++++ tools/perf/Makefile.perf | 2 ++ 5 files changed, 26 insertions(+) create mode 100644 tools/build/feature/test-libtracefs.c diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 3dd2f68366f9..45a9a59828c3 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -52,6 +52,7 @@ FEATURE_TESTS_BASIC := \ libslang \ libslang-include-subdir \ libtraceevent \ + libtracefs \ libcrypto \ libunwind \ pthread-attr-setaffinity-np \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index eff55d287db1..d024b5204ba0 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -36,6 +36,7 @@ FILES= \ test-libslang.bin \ test-libslang-include-subdir.bin \ test-libtraceevent.bin \ + test-libtracefs.bin \ test-libcrypto.bin \ test-libunwind.bin \ test-libunwind-debug-frame.bin \ @@ -199,6 +200,9 @@ $(OUTPUT)test-libslang-include-subdir.bin: $(OUTPUT)test-libtraceevent.bin: $(BUILD) -ltraceevent +$(OUTPUT)test-libtracefs.bin: + $(BUILD) -ltracefs + $(OUTPUT)test-libcrypto.bin: $(BUILD) -lcrypto diff --git a/tools/build/feature/test-libtracefs.c b/tools/build/feature/test-libtracefs.c new file mode 100644 index 000000000000..8eff16c0c10b --- /dev/null +++ b/tools/build/feature/test-libtracefs.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +int main(void) +{ + struct tracefs_instance *inst = tracefs_instance_create("dummy"); + + tracefs_instance_destroy(inst); + return 0; +} diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 446180401e26..00ec900ddbca 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1098,6 +1098,15 @@ ifdef LIBTRACEEVENT_DYNAMIC endif endif +ifdef LIBTRACEFS_DYNAMIC + $(call feature_check,libtracefs) + ifeq ($(feature-libtracefs), 1) + EXTLIBS += -ltracefs + else + dummy := $(error Error: No libtracefs devel library found, please install libtracefs-dev); + endif +endif + # Among the variables below, these: # perfexecdir # perf_include_dir diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e04313c4d840..7df13e74450c 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -130,6 +130,8 @@ include ../scripts/utilities.mak # # Define LIBTRACEEVENT_DYNAMIC to enable libtraceevent dynamic linking # +# Define LIBTRACEFS_DYNAMIC to enable libtracefs dynamic linking +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL -- cgit v1.2.3 From 569715164ba2125cf5014aa6de7154ebdb95fef4 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 17:10:22 -0700 Subject: perf tools: Add define for libtraceevent version The definition is derived from pkg-config as discussed in: https://lore.kernel.org/lkml/20210610155915.20a252d3@oasis.local.home/ The definition is computed using expr rather than passed to be computed in C code, this avoids complications with quote in the variable expansions. For example see the target python/perf.so in Makefile.perf. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20210923001024.550263-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 00ec900ddbca..2001c315f0db 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1093,6 +1093,12 @@ ifdef LIBTRACEEVENT_DYNAMIC $(call feature_check,libtraceevent) ifeq ($(feature-libtraceevent), 1) EXTLIBS += -ltraceevent + LIBTRACEEVENT_VERSION := $(shell $(PKG_CONFIG) --modversion libtraceevent) + LIBTRACEEVENT_VERSION_1 := $(word 1, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_2 := $(word 2, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_CPP := $(shell expr $(LIBTRACEEVENT_VERSION_1) \* 255 \* 255 + $(LIBTRACEEVENT_VERSION_2) \* 255 + $(LIBTRACEEVENT_VERSION_3)) + CFLAGS += -DLIBTRACEEVENT_VERSION=$(LIBTRACEEVENT_VERSION_CPP) else dummy := $(error Error: No libtraceevent devel library found, please install libtraceevent-devel); endif -- cgit v1.2.3 From 359cad09e40bedf927ea6046d27ccf977c83b71a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 17:10:23 -0700 Subject: perf tools: Add define for libtracefs version This will allow version specific support of libtracefs. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov (VMware) Cc: linux-trace-devel@vger.kernel.org Link: http://lore.kernel.org/lkml/20210923001024.550263-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo