From 1c4924220c96392d17e0222c113509fd7b9a0854 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 8 May 2019 15:20:05 +0200 Subject: perf script: Pad DSO name for --call-trace Pad the DSO name in --call-trace so we don't have the indent screwed by different DSO name lengths, as now for kernel there's also BPF code displayed. # perf-with-kcore record pt -e intel_pt//ku -- sleep 1 # perf-core/perf-with-kcore script pt --call-trace Before: sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) kretprobe_perf_func sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) trace_call_bpf sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_get_current_pid_tgid sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_ktime_get_ns sleep 3660 [16] 57036.806464725: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806465045: (bpf_prog_da4fe6b3d2c29b25_trace_return) __htab_map_lookup_elem sleep 3660 [16] 57036.806465366: ([kernel.kallsyms]) memcmp sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_get_current_uid_gid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms]) from_kgid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms]) from_kuid sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_prepare_sample sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_misc_flags sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kvm]) kvm_is_in_guest sleep 3660 [16] 57036.806466649: ([kernel.kallsyms]) __perf_event_header__init_id.isra.0 sleep 3660 [16] 57036.806466649: ([kernel.kallsyms]) perf_output_begin After: sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) kretprobe_perf_func sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) trace_call_bpf sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_get_current_pid_tgid sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_ktime_get_ns sleep 3660 [16] 57036.806464725: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806465045: (bpf_prog_da4fe6b3d2c29b25_trace_return ) __htab_map_lookup_elem sleep 3660 [16] 57036.806465366: ([kernel.kallsyms] ) memcmp sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_get_current_uid_gid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms] ) from_kgid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms] ) from_kuid sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_prepare_sample sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_misc_flags sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) __x86_indirect_thunk_rax Signed-off-by: Jiri Olsa Acked-by: Song Liu Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190508132010.14512-8-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 61cfd8f70989..7adaa6c63a0b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3297,6 +3297,7 @@ static int parse_call_trace(const struct option *opt __maybe_unused, parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0); itrace_parse_synth_opts(opt, "cewp", 0); symbol_conf.nanosecs = true; + symbol_conf.pad_output_len_dso = 50; return 0; } -- cgit v1.2.3 From 490c8cc949eca14bfdbee0ad1cd1c6d3ddf46b77 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 8 May 2019 15:20:08 +0200 Subject: perf script: Add --show-bpf-events to show eBPF related events Add the --show-bpf-events command line option to show the eBPF related events: PERF_RECORD_KSYMBOL PERF_RECORD_BPF_EVENT Usage: # perf record -a ... # perf script --show-bpf-events ... swapper 0 [000] 0.000000: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0ef971d len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174 swapper 0 [000] 0.000000: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 36 ... Committer testing: # perf script --show-bpf-events | egrep -i 'PERF_RECORD_(BPF|KSY)' 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc029a6c3 len 229 type 1 flags 0x0 name bpf_prog_7be49e3934a125ba 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 47 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc029c1ae len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 48 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc02ddd1c len 229 type 1 flags 0x0 name bpf_prog_7be49e3934a125ba 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 49 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc02dfc11 len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 50 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc045da0a len 229 type 1 flags 0x0 name bpf_prog_7be49e3934a125ba 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 51 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc04ef4b4 len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 52 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc09e15da len 229 type 1 flags 0x0 name bpf_prog_7be49e3934a125ba 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 53 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0d2b1a3 len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 54 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0fd9850 len 381 type 1 flags 0x0 name bpf_prog_819967866022f1e1_sys_enter 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 179 0 PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0feb1ec len 191 type 1 flags 0x0 name bpf_prog_c1bd85c092d6e4aa_sys_exit 0 PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 180 ^C[root@quaco pt]# perf evlist intel_pt//ku dummy:u # Signed-off-by: Jiri Olsa Acked-by: Song Liu Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stanislav Fomichev Link: http://lkml.kernel.org/r/20190508132010.14512-11-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 7adaa6c63a0b..3a48a2627670 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1606,6 +1606,7 @@ struct perf_script { bool show_namespace_events; bool show_lost_events; bool show_round_events; + bool show_bpf_events; bool allocated; bool per_event_dump; struct cpu_map *cpus; @@ -2318,6 +2319,41 @@ process_finished_round_event(struct perf_tool *tool __maybe_unused, return 0; } +static int +process_bpf_events(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct thread *thread; + struct perf_script *script = container_of(tool, struct perf_script, tool); + struct perf_session *session = script->session; + struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + + if (machine__process_ksymbol(machine, event, sample) < 0) + return -1; + + if (!evsel->attr.sample_id_all) { + perf_event__fprintf(event, stdout); + return 0; + } + + thread = machine__findnew_thread(machine, sample->pid, sample->tid); + if (thread == NULL) { + pr_debug("problem processing MMAP event, skipping it.\n"); + return -1; + } + + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + event->header.type, stdout); + perf_event__fprintf(event, stdout); + } + + thread__put(thread); + return 0; +} + static void sig_handler(int sig __maybe_unused) { session_done = 1; @@ -2420,6 +2456,10 @@ static int __cmd_script(struct perf_script *script) script->tool.ordered_events = false; script->tool.finished_round = process_finished_round_event; } + if (script->show_bpf_events) { + script->tool.ksymbol = process_bpf_events; + script->tool.bpf_event = process_bpf_events; + } if (perf_script__setup_per_event_dump(script)) { pr_err("Couldn't create the per event dump files\n"); @@ -3439,6 +3479,8 @@ int cmd_script(int argc, const char **argv) "Show lost events (if recorded)"), OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events, "Show round events (if recorded)"), + OPT_BOOLEAN('\0', "show-bpf-events", &script.show_bpf_events, + "Show bpf related events (if recorded)"), OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump, "Dump trace output to files named by the monitored events"), OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), -- cgit v1.2.3 From 68fb45bf175e702aec6668c776050e5dbd2a6f1f Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 20 May 2019 14:37:14 +0300 Subject: perf script: Add output of IPC ratio Add field 'ipc' to display instructions-per-cycle. Example: perf record -e intel_pt/cyc/u ls perf script --insn-trace --xed -F+ipc,-dso,-cpu,-tid ls 2670177.697113434: 7f0dfdbcd090 _start+0x0 mov %rsp, %rdi IPC: 0.00 (1/877) ls 2670177.697113434: 7f0dfdbcd093 _start+0x3 callq 0x7f0dfdbce030 ls 2670177.697113434: 7f0dfdbce030 _dl_start+0x0 pushq %rbp ls 2670177.697113434: 7f0dfdbce031 _dl_start+0x1 mov %rsp, %rbp ls 2670177.697113434: 7f0dfdbce034 _dl_start+0x4 pushq %r15 ls 2670177.697113434: 7f0dfdbce036 _dl_start+0x6 pushq %r14 ls 2670177.697113434: 7f0dfdbce038 _dl_start+0x8 pushq %r13 ls 2670177.697113434: 7f0dfdbce03a _dl_start+0xa pushq %r12 ls 2670177.697113434: 7f0dfdbce03c _dl_start+0xc mov %rdi, %r12 ls 2670177.697113434: 7f0dfdbce03f _dl_start+0xf pushq %rbx ls 2670177.697113434: 7f0dfdbce040 _dl_start+0x10 sub $0x38, %rsp ls 2670177.697113434: 7f0dfdbce044 _dl_start+0x14 rdtsc ls 2670177.697113434: 7f0dfdbce046 _dl_start+0x16 mov %eax, %eax ls 2670177.697113434: 7f0dfdbce048 _dl_start+0x18 shl $0x20, %rdx ls 2670177.697113434: 7f0dfdbce04c _dl_start+0x1c or %rax, %rdx ls 2670177.697114471: 7f0dfdbce04f _dl_start+0x1f movq 0x27e22(%rip), %rax IPC: 0.00 (15/1685) ls 2670177.697116177: 7f0dfdbce056 _dl_start+0x26 movq %rdx, 0x27683(%rip) IPC: 0.00 (1/881) Note, the IPC values are low due to page faults at the beginning of execution. The additional cycles are due to the time to enter the kernel, not the actual kernel page fault handler. Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20190520113728.14389-9-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 3a48a2627670..80c722ade852 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -102,6 +102,7 @@ enum perf_output_field { PERF_OUTPUT_METRIC = 1U << 28, PERF_OUTPUT_MISC = 1U << 29, PERF_OUTPUT_SRCCODE = 1U << 30, + PERF_OUTPUT_IPC = 1U << 31, }; struct output_option { @@ -139,6 +140,7 @@ struct output_option { {.str = "metric", .field = PERF_OUTPUT_METRIC}, {.str = "misc", .field = PERF_OUTPUT_MISC}, {.str = "srccode", .field = PERF_OUTPUT_SRCCODE}, + {.str = "ipc", .field = PERF_OUTPUT_IPC}, }; enum { @@ -1268,6 +1270,20 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, return printed; } +static int perf_sample__fprintf_ipc(struct perf_sample *sample, + struct perf_event_attr *attr, FILE *fp) +{ + unsigned int ipc; + + if (!PRINT_FIELD(IPC) || !sample->cyc_cnt || !sample->insn_cnt) + return 0; + + ipc = (sample->insn_cnt * 100) / sample->cyc_cnt; + + return fprintf(fp, " \t IPC: %u.%02u (%" PRIu64 "/%" PRIu64 ") ", + ipc / 100, ipc % 100, sample->insn_cnt, sample->cyc_cnt); +} + static int perf_sample__fprintf_bts(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, @@ -1312,6 +1328,8 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, printed += perf_sample__fprintf_addr(sample, thread, attr, fp); } + printed += perf_sample__fprintf_ipc(sample, attr, fp); + if (print_srcline_last) printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp); @@ -1859,6 +1877,9 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(PHYS_ADDR)) fprintf(fp, "%16" PRIx64, sample->phys_addr); + + perf_sample__fprintf_ipc(sample, attr, fp); + fprintf(fp, "\n"); if (PRINT_FIELD(SRCCODE)) { @@ -3433,7 +3454,7 @@ int cmd_script(int argc, const char **argv) "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,srcline,period,iregs,uregs,brstack," "brstacksym,flags,bpf-output,brstackinsn,brstackoff," - "callindent,insn,insnlen,synth,phys_addr,metric,misc", + "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), -- cgit v1.2.3 From 400ae9818fe64899cea921a89c7078e0df9e41ea Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 4 Jun 2019 16:00:00 +0300 Subject: perf script: Set perf time interval in itrace_synth_ops Instruction trace decoders can optimize output based on what time intervals will be filtered, so pass that information in itrace_synth_ops. Signed-off-by: Adrian Hunter Cc: Jin Yao Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20190604130017.31207-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 80c722ade852..61f00055476a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3829,6 +3829,10 @@ int cmd_script(int argc, const char **argv) &script.range_num); if (err < 0) goto out_delete; + + itrace_synth_opts__set_time_range(&itrace_synth_opts, + script.ptime_range, + script.range_num); } err = __cmd_script(&script); @@ -3836,8 +3840,10 @@ int cmd_script(int argc, const char **argv) flush_scripting(); out_delete: - if (script.ptime_range) + if (script.ptime_range) { + itrace_synth_opts__clear_time_range(&itrace_synth_opts); zfree(&script.ptime_range); + } perf_evlist__free_stats(session->evlist); perf_session__delete(session); -- cgit v1.2.3 From 3052ba56bcb589046eca6a931bd897742653d2cb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 25 Jun 2019 17:27:31 -0300 Subject: tools perf: Move from sane_ctype.h obtained from git to the Linux's original We got the sane_ctype.h headers from git and kept using it so far, but since that code originally came from the kernel sources to the git sources, perhaps its better to just use the one in the kernel, so that we can leverage tools/perf/check_headers.sh to be notified when our copy gets out of sync, i.e. when fixes or goodies are added to the code we've copied. This will help with things like tools/lib/string.c where we want to have more things in common with the kernel, such as strim(), skip_spaces(), etc so as to go on removing the things that we have in tools/perf/util/ and instead using the code in the kernel, indirectly and removing things like EXPORT_SYMBOL(), etc, getting notified when fixes and improvements are made to the original code. Hopefully this also should help with reducing the difference of code hosted in tools/ to the one in the kernel proper. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-7k9868l713wqtgo01xxygn12@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 61f00055476a..0131f7a0d48d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -49,7 +49,7 @@ #include #include -#include "sane_ctype.h" +#include static char const *script_name; static char const *generate_script_lang; -- cgit v1.2.3 From 328584804edc950fb4608c9a38e396ac71ef22b6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 26 Jun 2019 11:42:03 -0300 Subject: perf tools: Ditch rtrim(), use skip_spaces() to get closer to the kernel MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit No change in behaviour, just using the same kernel idiom for such operation. Cc: Adrian Hunter Cc: André Goddard Rosa Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-a85lkptkt0ru40irpga8yf54@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 0131f7a0d48d..520e5b6b9ef9 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2880,7 +2880,7 @@ static int read_script_info(struct script_desc *desc, const char *filename) return -1; while (fgets(line, sizeof(line), fp)) { - p = ltrim(line); + p = skip_spaces(line); if (strlen(p) == 0) continue; if (*p != '#') @@ -2889,19 +2889,19 @@ static int read_script_info(struct script_desc *desc, const char *filename) if (strlen(p) && *p == '!') continue; - p = ltrim(p); + p = skip_spaces(p); if (strlen(p) && p[strlen(p) - 1] == '\n') p[strlen(p) - 1] = '\0'; if (!strncmp(p, "description:", strlen("description:"))) { p += strlen("description:"); - desc->half_liner = strdup(ltrim(p)); + desc->half_liner = strdup(skip_spaces(p)); continue; } if (!strncmp(p, "args:", strlen("args:"))) { p += strlen("args:"); - desc->args = strdup(ltrim(p)); + desc->args = strdup(skip_spaces(p)); continue; } } @@ -3008,7 +3008,7 @@ static int check_ev_match(char *dir_name, char *scriptname, return -1; while (fgets(line, sizeof(line), fp)) { - p = ltrim(line); + p = skip_spaces(line); if (*p == '#') continue; @@ -3018,7 +3018,7 @@ static int check_ev_match(char *dir_name, char *scriptname, break; p += 2; - p = ltrim(p); + p = skip_spaces(p); len = strcspn(p, " \t"); if (!len) break; -- cgit v1.2.3 From 15a108af1a18b597bfbd7f7b3c7b4823bfbaf8df Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 28 Jun 2019 17:16:58 -0300 Subject: perf script: Allow specifying the files to process guest samples The 'perf kvm' command set up things so that we can record, report, top, etc, but not 'script', so make 'perf script' be able to process samples by allowing to pass guest kallsyms, vmlinux, modules, etc, and if at least one of those is provided, set perf_guest to true so that guest samples get properly resolved. Testing it: # perf kvm --guest --guestkallsyms /wb/rhel6.kallsyms --guestmodules /wb/rhel6.modules record -e cycles:Gk ^C[ perf record: Woken up 7 times to write data ] [ perf record: Captured and wrote 3.602 MB perf.data.guest (10492 samples) ] # # perf evlist -i perf.data.guest cycles:Gk # perf evlist -v -i perf.data.guest cycles:Gk: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, exclude_user: 1, exclude_hv: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_host: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1 # # perf kvm --guestkallsyms /wb/rhel6.kallsyms --guestmodules /wb/rhel6.modules report --stdio -s sym | head -30 # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 10K of event 'cycles:Gk' # Event count (approx.): 2434201408 # # Overhead Symbol # ........ .............................................. # 11.93% [g] avtab_search_node 3.95% [g] sidtab_context_to_sid 2.41% [g] n_tty_write 2.20% [g] _spin_unlock_irqrestore 1.37% [g] _aesni_dec4 1.33% [g] kmem_cache_alloc 1.07% [g] native_write_cr0 0.99% [g] kfree 0.95% [g] _spin_lock 0.91% [g] __memset 0.87% [g] schedule 0.83% [g] _spin_lock_irqsave 0.76% [g] __kmalloc 0.67% [g] avc_has_perm_noaudit 0.66% [g] kmem_cache_free 0.65% [g] glue_xts_crypt_128bit 0.59% [g] __d_lookup 0.59% [g] __audit_syscall_exit 0.56% [g] __memcpy # Then, when trying to use perf script to generate a python script and then process the events after adding a python hook for non-tracepoint events: # perf script -i perf.data.guest -g python generated Python script: perf-script.py # vim perf-script.py # tail -2 perf-script.py def process_event(param_dict): print(param_dict["symbol"]) # # perf script -i perf.data.guest -s perf-script.py | head in trace_begin vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit vmx_vmexit 231 # We'd see just the vmx_vmexit, i.e. the samples from the guest don't show up. After this patch: # perf script --guestkallsyms /wb/rhel6.kallsyms --guestmodules /wb/rhel6.modules -i perf.data.guest -s perf-script.py 2> /dev/null | head -30 in trace_begin apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt save_args do_timer drain_array inode_permission avc_has_perm_noaudit run_timer_softirq apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt apic_timer_interrupt kvm_guest_apic_eoi_write run_posix_cpu_timers _spin_lock handle_pte_fault rcu_irq_enter delay_tsc delay_tsc native_read_tsc apic_timer_interrupt sys_open internal_add_timer list_del rcu_exit_nohz # Jiri Olsa noticed we need to set 'perf_guest' to true if we want to process guest samples and I made it be set if one of the guest files settings get set via the command line options added in this patch, that match those present in the 'perf kvm' command. We probably want to have 'perf record', 'perf report' etc to notice that there are guest samples and do the right thing, which is to look for files with some suffix that make it be associated with the guest used to collect the samples, i.e. if a vmlinux file is passed, we can get the build-id from it, if not some other identifier or simply looking for "kallsyms.guest", for instance, in the current directory. Reported-by: Mariano Pache Tested-by: Mariano Pache Cc: Adrian Hunter Cc: Alexander Yarygin Cc: Ali Raza Cc: Christian Borntraeger Cc: Jiri Olsa Cc: Joe Mario Cc: Larry Woodman Cc: Namhyung Kim Cc: Orran Krieger Cc: Ramkumar Ramachandra Cc: Yunlong Song Link: https://lkml.kernel.org/n/tip-d54gj64rerlxcqsrod05biwn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 520e5b6b9ef9..2f6232f1bfdc 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3522,6 +3522,15 @@ int cmd_script(int argc, const char **argv) "Time span of interest (start,stop)"), OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, "Show inline function"), + OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory", + "guest mount directory under which every guest os" + " instance has a subdir"), + OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name, + "file", "file saving guest os vmlinux"), + OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms, + "file", "file saving guest os /proc/kallsyms"), + OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, + "file", "file saving guest os /proc/modules"), OPT_END() }; const char * const script_subcommands[] = { "record", "report", NULL }; @@ -3541,6 +3550,16 @@ int cmd_script(int argc, const char **argv) argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage, PARSE_OPT_STOP_AT_NON_OPTION); + if (symbol_conf.guestmount || + symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_kallsyms || + symbol_conf.default_guest_modules) { + /* + * Enable guest sample processing. + */ + perf_guest = true; + } + data.path = input_name; data.force = symbol_conf.force; -- cgit v1.2.3