From 5b11749b36499f917c9c3fa6e494cdd630ff456e Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 24 Jan 2022 10:41:54 +0200 Subject: perf script: Display Intel PT CFE (Control Flow Event) / EVD (Event Data) synthesized event Similar to other Intel PT synth events, display Event Trace events recorded by CFE / EVD packets. Signed-off-by: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Link: https://lore.kernel.org/r/20220124084201.2699795-19-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index abae8184e171..08e8ef5fcf83 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1811,6 +1811,43 @@ static int perf_sample__fprintf_synth_psb(struct perf_sample *sample, FILE *fp) return len + perf_sample__fprintf_pt_spacing(len, fp); } +/* Intel PT Event Trace */ +static int perf_sample__fprintf_synth_evt(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_evt *data = perf_sample__synth_ptr(sample); + const char *cfe[32] = {NULL, "INTR", "IRET", "SMI", "RSM", "SIPI", + "INIT", "VMENTRY", "VMEXIT", "VMEXIT_INTR", + "SHUTDOWN"}; + const char *evd[64] = {"PFA", "VMXQ", "VMXR"}; + const char *s; + int len, i; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + s = cfe[data->type]; + if (s) { + len = fprintf(fp, " cfe: %s IP: %d vector: %u", + s, data->ip, data->vector); + } else { + len = fprintf(fp, " cfe: %u IP: %d vector: %u", + data->type, data->ip, data->vector); + } + for (i = 0; i < data->evd_cnt; i++) { + unsigned int et = data->evd[i].evd_type & 0x3f; + + s = evd[et]; + if (s) { + len += fprintf(fp, " %s: %#" PRIx64, + s, data->evd[i].payload); + } else { + len += fprintf(fp, " EVD_%u: %#" PRIx64, + et, data->evd[i].payload); + } + } + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + static int perf_sample__fprintf_synth(struct perf_sample *sample, struct evsel *evsel, FILE *fp) { @@ -1829,6 +1866,8 @@ static int perf_sample__fprintf_synth(struct perf_sample *sample, return perf_sample__fprintf_synth_cbr(sample, fp); case PERF_SYNTH_INTEL_PSB: return perf_sample__fprintf_synth_psb(sample, fp); + case PERF_SYNTH_INTEL_EVT: + return perf_sample__fprintf_synth_evt(sample, fp); default: break; } -- cgit v1.2.3 From a48b96ca5a6572895b1f1c9f28e8de226a2c61a4 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 24 Jan 2022 10:41:55 +0200 Subject: perf script: Display Intel PT iflag synthesized event Similar to other Intel PT synth events, display changes to the interrupt flag represented by the MODE.Exec packet. Signed-off-by: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Link: https://lore.kernel.org/r/20220124084201.2699795-20-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 08e8ef5fcf83..517d5f7a7d39 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1848,6 +1848,19 @@ static int perf_sample__fprintf_synth_evt(struct perf_sample *sample, FILE *fp) return len + perf_sample__fprintf_pt_spacing(len, fp); } +static int perf_sample__fprintf_synth_iflag_chg(struct perf_sample *sample, FILE *fp) +{ + struct perf_synth_intel_iflag_chg *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return 0; + + len = fprintf(fp, " IFLAG: %d->%d %s branch", !data->iflag, data->iflag, + data->via_branch ? "via" : "non"); + return len + perf_sample__fprintf_pt_spacing(len, fp); +} + static int perf_sample__fprintf_synth(struct perf_sample *sample, struct evsel *evsel, FILE *fp) { @@ -1868,6 +1881,8 @@ static int perf_sample__fprintf_synth(struct perf_sample *sample, return perf_sample__fprintf_synth_psb(sample, fp); case PERF_SYNTH_INTEL_EVT: return perf_sample__fprintf_synth_evt(sample, fp); + case PERF_SYNTH_INTEL_IFLAG_CHG: + return perf_sample__fprintf_synth_iflag_chg(sample, fp); default: break; } -- cgit v1.2.3 From 2673859865e28d19f7b5e3f25fbe15382b8b6c47 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 24 Jan 2022 10:41:56 +0200 Subject: perf script: Display new D (Intr Disabled) and t (Intr Toggle) flags Amend the display to include D and t flags in the same way as the x flag. Signed-off-by: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Link: https://lore.kernel.org/r/20220124084201.2699795-21-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 13 ++++++++----- tools/perf/builtin-script.c | 24 ++++++++++++++++-------- 2 files changed, 24 insertions(+), 13 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index b0070718784d..afd4718475c9 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -195,16 +195,19 @@ OPTIONS At this point usage is displayed, and perf-script exits. The flags field is synthesized and may have a value when Instruction - Trace decoding. The flags are "bcrosyiABExgh" which stand for branch, + Trace decoding. The flags are "bcrosyiABExghDt" which stand for branch, call, return, conditional, system, asynchronous, interrupt, - transaction abort, trace begin, trace end, in transaction, VM-Entry, and VM-Exit - respectively. Known combinations of flags are printed more nicely e.g. + transaction abort, trace begin, trace end, in transaction, VM-Entry, + VM-Exit, interrupt disabled and interrupt disable toggle respectively. + Known combinations of flags are printed more nicely e.g. "call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b", "int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs", "async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB", "tr end" for "bE", "vmentry" for "bcg", "vmexit" for "bch". - However the "x" flag will be displayed separately in those - cases e.g. "jcc (x)" for a condition branch within a transaction. + However the "x", "D" and "t" flags will be displayed separately in those + cases e.g. "jcc (xD)" for a condition branch within a transaction + with interrupts disabled. Note, interrupts becoming disabled is "t", + whereas interrupts becoming enabled is "Dt". The callindent field is synthesized and may have a value when Instruction Trace decoding. For calls and returns, it will display the diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 517d5f7a7d39..9e032343f1c6 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1579,26 +1579,34 @@ static const char *sample_flags_to_name(u32 flags) int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz) { + u32 xf = PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_INTR_DISABLE | + PERF_IP_FLAG_INTR_TOGGLE; const char *chars = PERF_IP_FLAG_CHARS; const size_t n = strlen(PERF_IP_FLAG_CHARS); - bool in_tx = flags & PERF_IP_FLAG_IN_TX; const char *name = NULL; size_t i, pos = 0; + char xs[16] = {0}; - name = sample_flags_to_name(flags & ~PERF_IP_FLAG_IN_TX); + if (flags & xf) + snprintf(xs, sizeof(xs), "(%s%s%s)", + flags & PERF_IP_FLAG_IN_TX ? "x" : "", + flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", + flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); + + name = sample_flags_to_name(flags & ~xf); if (name) - return snprintf(str, sz, "%-15s%4s", name, in_tx ? "(x)" : ""); + return snprintf(str, sz, "%-15s%6s", name, xs); if (flags & PERF_IP_FLAG_TRACE_BEGIN) { - name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_BEGIN)); + name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_BEGIN)); if (name) - return snprintf(str, sz, "tr strt %-7s%4s", name, in_tx ? "(x)" : ""); + return snprintf(str, sz, "tr strt %-7s%6s", name, xs); } if (flags & PERF_IP_FLAG_TRACE_END) { - name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_END)); + name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_END)); if (name) - return snprintf(str, sz, "tr end %-7s%4s", name, in_tx ? "(x)" : ""); + return snprintf(str, sz, "tr end %-7s%6s", name, xs); } for (i = 0; i < n; i++, flags >>= 1) { @@ -1620,7 +1628,7 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp) char str[SAMPLE_FLAGS_BUF_SIZE]; perf_sample__sprintf_flags(flags, str, sizeof(str)); - return fprintf(fp, " %-19s ", str); + return fprintf(fp, " %-21s ", str); } struct printer_data { -- cgit v1.2.3 From b2dac688a5265379e0f13856b78cb627af07cf42 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 7 Mar 2022 17:19:16 +0000 Subject: perf script: Refactor branch stack printing Remove duplicate code so that future changes to flags are always made to all 3 printing variations. Signed-off-by: James Clark Cc: Alexander Shishkin Cc: Anshuman Khandual Cc: German Gomez Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Link: https://lore.kernel.org/r/20220307171917.2555829-4-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9e032343f1c6..fac2e9470926 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -857,6 +857,15 @@ mispred_str(struct branch_entry *br) return br->flags.predicted ? 'P' : 'M'; } +static int print_bstack_flags(FILE *fp, struct branch_entry *br) +{ + return fprintf(fp, "/%c/%c/%c/%d ", + mispred_str(br), + br->flags.in_tx ? 'X' : '-', + br->flags.abort ? 'A' : '-', + br->flags.cycles); +} + static int perf_sample__fprintf_brstack(struct perf_sample *sample, struct thread *thread, struct perf_event_attr *attr, FILE *fp) @@ -895,11 +904,7 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, printed += fprintf(fp, ")"); } - printed += fprintf(fp, "/%c/%c/%c/%d ", - mispred_str(entries + i), - entries[i].flags.in_tx ? 'X' : '-', - entries[i].flags.abort ? 'A' : '-', - entries[i].flags.cycles); + printed += print_bstack_flags(fp, entries + i); } return printed; @@ -941,11 +946,7 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, printed += map__fprintf_dsoname(alt.map, fp); printed += fprintf(fp, ")"); } - printed += fprintf(fp, "/%c/%c/%c/%d ", - mispred_str(entries + i), - entries[i].flags.in_tx ? 'X' : '-', - entries[i].flags.abort ? 'A' : '-', - entries[i].flags.cycles); + printed += print_bstack_flags(fp, entries + i); } return printed; @@ -991,11 +992,7 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, printed += map__fprintf_dsoname(alt.map, fp); printed += fprintf(fp, ")"); } - printed += fprintf(fp, "/%c/%c/%c/%d ", - mispred_str(entries + i), - entries[i].flags.in_tx ? 'X' : '-', - entries[i].flags.abort ? 'A' : '-', - entries[i].flags.cycles); + printed += print_bstack_flags(fp, entries + i); } return printed; -- cgit v1.2.3 From 1f48989cdc7d57d32a56b7cc5eb968c04d30529c Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 7 Mar 2022 17:19:17 +0000 Subject: perf script: Output branch sample type The type info is saved when using '-j save_type'. Output this in 'perf script' so it can be accessed by other tools or for debugging. It's appended to the end of the list of fields so any existing tools that split on / and access fields via an index are not affected. Also output '-' instead of 'N/A' when the branch type isn't saved because / is used as a field separator. Entries before this change look like this: 0xaaaadb350838/0xaaaadb3507a4/P/-/-/0 And afterwards like this: 0xaaaadb350838/0xaaaadb3507a4/P/-/-/0/CALL or this if no type info is saved: 0x7fb57586df6b/0x7fb5758731f0/P/-/-/143/- Signed-off-by: James Clark Cc: Alexander Shishkin Cc: Anshuman Khandual Cc: German Gomez Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Link: https://lore.kernel.org/r/20220307171917.2555829-5-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index fac2e9470926..5e4a262a6825 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -859,11 +859,12 @@ mispred_str(struct branch_entry *br) static int print_bstack_flags(FILE *fp, struct branch_entry *br) { - return fprintf(fp, "/%c/%c/%c/%d ", + return fprintf(fp, "/%c/%c/%c/%d/%s ", mispred_str(br), br->flags.in_tx ? 'X' : '-', br->flags.abort ? 'A' : '-', - br->flags.cycles); + br->flags.cycles, + br->flags.type ? branch_type_name(br->flags.type) : "-"); } static int perf_sample__fprintf_brstack(struct perf_sample *sample, -- cgit v1.2.3 From 6f680c6aa276ceff7dde98d5ae3f19574cd12eff Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 21 Mar 2022 07:00:12 -0700 Subject: perf script: Add 'brstackinsnlen' for branch stacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When analyzing with 'perf script', it's useful to understand the captured instruction and the next sequential instruction. To calculate the address of the next sequential instruction, the length of the captured instruction is required. For example, you can’t know the next sequential instruction after an unconditional branch unless you calculate that based on its length. For branch stacks, 'perf script' only prints the instruction bytes with 'brstackinsn', but lacks the instruction length. Add 'brstackinsnlen' to print the instruction length. $ perf script -F ip,brstackinsn,brstackinsnlen --xed 7fa555be8f75 _start: 00007fa555be8090 mov %rsp, %rdi ilen: 3 00007fa555be8093 callq 0x7fa555be8ea0 ilen: 5 # PRED 102 cycles [102] 0.02 IPC _dl_start+38: 00007fa555be8ec6 movq %rdx,0x227853(%rip) ilen: 7 00007fa555be8ecd leaq 0x227f94(%rip),%rdx ilen: 7 Signed-off-by: Kan Liang Cc: Ahmad Yasin Cc: Andi Kleen Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/1647871212-184070-1-git-send-email-kan.liang@linux.intel.com [ Added the new field to tools/perf/Documentation/perf-script.txt ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 8 ++++-- tools/perf/builtin-script.c | 44 +++++++++++++++++++++++--------- 2 files changed, 38 insertions(+), 14 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index afd4718475c9..2012a8e6c90b 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -129,8 +129,8 @@ OPTIONS Comma separated list of fields to print. Options are: 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, srccode, ipc, data_page_size, code_page_size, ins_lat. + brstackinsn, brstackinsnlen, brstackoff, callindent, insn, insnlen, synth, + phys_addr, metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -241,6 +241,10 @@ OPTIONS is printed. This is the full execution path leading to the sample. This is only supported when the sample was recorded with perf record -b or -j any. + Use brstackinsnlen to print the brstackinsn lenght. For example, you + can’t know the next sequential instruction after an unconditional branch unless + you calculate that based on its length. + The brstackoff field will print an offset into a specific dso/binary. With the metric option perf script can compute metrics for diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 88c52d49852c..f12dc5ed354d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -124,6 +124,7 @@ enum perf_output_field { PERF_OUTPUT_DATA_PAGE_SIZE = 1ULL << 33, PERF_OUTPUT_CODE_PAGE_SIZE = 1ULL << 34, PERF_OUTPUT_INS_LAT = 1ULL << 35, + PERF_OUTPUT_BRSTACKINSNLEN = 1ULL << 36, }; struct perf_script { @@ -191,6 +192,7 @@ struct output_option { {.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE}, {.str = "code_page_size", .field = PERF_OUTPUT_CODE_PAGE_SIZE}, {.str = "ins_lat", .field = PERF_OUTPUT_INS_LAT}, + {.str = "brstackinsnlen", .field = PERF_OUTPUT_BRSTACKINSNLEN}, }; enum { @@ -488,7 +490,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) "selected. Hence, no address to lookup the source line number.\n"); return -EINVAL; } - if (PRINT_FIELD(BRSTACKINSN) && !allow_user_set && + if ((PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN)) && !allow_user_set && !(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY)) { pr_err("Display of branch stack assembler requested, but non all-branch filter set\n" "Hint: run 'perf record -b ...'\n"); @@ -1120,10 +1122,17 @@ static int print_srccode(struct thread *thread, u8 cpumode, uint64_t addr) static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, struct perf_insn *x, u8 *inbuf, int len, - int insn, FILE *fp, int *total_cycles) + int insn, FILE *fp, int *total_cycles, + struct perf_event_attr *attr) { - int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip, - dump_insn(x, ip, inbuf, len, NULL), + int ilen = 0; + int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t", ip, + dump_insn(x, ip, inbuf, len, &ilen)); + + if (PRINT_FIELD(BRSTACKINSNLEN)) + printed += fprintf(fp, "ilen: %d\t", ilen); + + printed += fprintf(fp, "#%s%s%s%s", en->flags.predicted ? " PRED" : "", en->flags.mispred ? " MISPRED" : "", en->flags.in_tx ? " INTX" : "", @@ -1209,7 +1218,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, printed += ip__fprintf_sym(entries[nr - 1].from, thread, x.cpumode, x.cpu, &lastsym, attr, fp); printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1], - &x, buffer, len, 0, fp, &total_cycles); + &x, buffer, len, 0, fp, &total_cycles, + attr); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, entries[nr - 1].from); } @@ -1240,14 +1250,17 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); if (ip == end) { printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp, - &total_cycles); + &total_cycles, attr); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, ip); break; } else { ilen = 0; - printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip, + printed += fprintf(fp, "\t%016" PRIx64 "\t%s", ip, dump_insn(&x, ip, buffer + off, len - off, &ilen)); + if (PRINT_FIELD(BRSTACKINSNLEN)) + printed += fprintf(fp, "\tilen: %d", ilen); + printed += fprintf(fp, "\n"); if (ilen == 0) break; if (PRINT_FIELD(SRCCODE)) @@ -1290,16 +1303,23 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, machine, thread, &x.is64bit, &x.cpumode, false); if (len <= 0) goto out; - printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip, - dump_insn(&x, sample->ip, buffer, len, NULL)); + ilen = 0; + printed += fprintf(fp, "\t%016" PRIx64 "\t%s", sample->ip, + dump_insn(&x, sample->ip, buffer, len, &ilen)); + if (PRINT_FIELD(BRSTACKINSNLEN)) + printed += fprintf(fp, "\tilen: %d", ilen); + printed += fprintf(fp, "\n"); if (PRINT_FIELD(SRCCODE)) print_srccode(thread, x.cpumode, sample->ip); goto out; } for (off = 0; off <= end - start; off += ilen) { ilen = 0; - printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off, + printed += fprintf(fp, "\t%016" PRIx64 "\t%s", start + off, dump_insn(&x, start + off, buffer + off, len - off, &ilen)); + if (PRINT_FIELD(BRSTACKINSNLEN)) + printed += fprintf(fp, "\tilen: %d", ilen); + printed += fprintf(fp, "\n"); if (ilen == 0) break; if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) { @@ -1457,7 +1477,7 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, for (i = 0; i < sample->insn_len; i++) printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]); } - if (PRINT_FIELD(BRSTACKINSN)) + if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN)) printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp); return printed; @@ -3776,7 +3796,7 @@ int cmd_script(int argc, const char **argv) "Valid types: hw,sw,trace,raw,synth. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,srcline,period,iregs,uregs,brstack," - "brstacksym,flags,bpf-output,brstackinsn,brstackoff," + "brstacksym,flags,bpf-output,brstackinsn,brstackinsnlen,brstackoff," "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod," "data_page_size,code_page_size,ins_lat", parse_output_fields), -- cgit v1.2.3 From ae0f4eb34fc3014f7eba78fab90a0e98e441a4cd Mon Sep 17 00:00:00 2001 From: Wei Li Date: Fri, 25 Mar 2022 17:20:32 +0800 Subject: perf tools: Enhance the matching of sub-commands abbreviations We support short command 'rec*' for 'record' and 'rep*' for 'report' in lots of sub-commands, but the matching is not quite strict currnetly. It may be puzzling sometime, like we mis-type a 'recport' to report but it will perform 'record' in fact without any message. To fix this, add a check to ensure that the short cmd is valid prefix of the real command. Committer testing: [root@quaco ~]# perf c2c re sleep 1 Usage: perf c2c {record|report} -v, --verbose be more verbose (show counter open errors, etc) # perf c2c rec sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.038 MB perf.data (16 samples) ] # perf c2c recport sleep 1 Usage: perf c2c {record|report} -v, --verbose be more verbose (show counter open errors, etc) # perf c2c record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.038 MB perf.data (15 samples) ] # perf c2c records sleep 1 Usage: perf c2c {record|report} -v, --verbose be more verbose (show counter open errors, etc) # Signed-off-by: Wei Li Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Hanjun Guo Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Rui Xiang Link: http://lore.kernel.org/lkml/20220325092032.2956161-1-liwei391@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-c2c.c | 5 +++-- tools/perf/builtin-kmem.c | 2 +- tools/perf/builtin-kvm.c | 9 +++++---- tools/perf/builtin-lock.c | 5 +++-- tools/perf/builtin-mem.c | 5 +++-- tools/perf/builtin-sched.c | 4 ++-- tools/perf/builtin-script.c | 4 ++-- tools/perf/builtin-stat.c | 4 ++-- tools/perf/builtin-timechart.c | 3 ++- 9 files changed, 23 insertions(+), 18 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 14f787c67140..fbbed434014f 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -44,6 +44,7 @@ #include "../perf.h" #include "pmu.h" #include "pmu-hybrid.h" +#include "string2.h" struct c2c_hists { struct hists hists; @@ -3025,9 +3026,9 @@ int cmd_c2c(int argc, const char **argv) if (!argc) usage_with_options(c2c_usage, c2c_options); - if (!strncmp(argv[0], "rec", 3)) { + if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) { return perf_c2c__record(argc, argv); - } else if (!strncmp(argv[0], "rep", 3)) { + } else if (strlen(argv[0]) > 2 && strstarts("report", argv[0])) { return perf_c2c__report(argc, argv); } else { usage_with_options(c2c_usage, c2c_options); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 99d7ff9a8eff..ebfab2ca1702 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1946,7 +1946,7 @@ int cmd_kmem(int argc, const char **argv) kmem_page = 1; } - if (!strncmp(argv[0], "rec", 3)) { + if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) { symbol__init(NULL); return __cmd_record(argc, argv); } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index b23a1f3eaeda..2fa687f73e5e 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -24,6 +24,7 @@ #include "util/ordered-events.h" #include "util/kvm-stat.h" #include "ui/ui.h" +#include "util/string2.h" #include #ifdef HAVE_TIMERFD_SUPPORT @@ -1500,10 +1501,10 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) goto perf_stat; } - if (!strncmp(argv[1], "rec", 3)) + if (strlen(argv[1]) > 2 && strstarts("record", argv[1])) return kvm_events_record(&kvm, argc - 1, argv + 1); - if (!strncmp(argv[1], "rep", 3)) + if (strlen(argv[1]) > 2 && strstarts("report", argv[1])) return kvm_events_report(&kvm, argc - 1 , argv + 1); #ifdef HAVE_TIMERFD_SUPPORT @@ -1631,9 +1632,9 @@ int cmd_kvm(int argc, const char **argv) } } - if (!strncmp(argv[0], "rec", 3)) + if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) return __cmd_record(file_name, argc, argv); - else if (!strncmp(argv[0], "rep", 3)) + else if (strlen(argv[0]) > 2 && strstarts("report", argv[0])) return __cmd_report(file_name, argc, argv); else if (!strncmp(argv[0], "diff", 4)) return cmd_diff(argc, argv); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index a7089760a7de..cdfe1d4ced4b 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -18,6 +18,7 @@ #include "util/session.h" #include "util/tool.h" #include "util/data.h" +#include "util/string2.h" #include #include @@ -1166,9 +1167,9 @@ int cmd_lock(int argc, const char **argv) if (!argc) usage_with_options(lock_usage, lock_options); - if (!strncmp(argv[0], "rec", 3)) { + if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) { return __cmd_record(argc, argv); - } else if (!strncmp(argv[0], "report", 6)) { + } else if (strlen(argv[0]) > 2 && strstarts("report", argv[0])) { trace_handler = &report_lock_ops; if (argc) { argc = parse_options(argc, argv, diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index fcf65a59bea2..9e435fd23503 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -20,6 +20,7 @@ #include "util/symbol.h" #include "util/pmu.h" #include "util/pmu-hybrid.h" +#include "util/string2.h" #include #define MEM_OPERATION_LOAD 0x1 @@ -496,9 +497,9 @@ int cmd_mem(int argc, const char **argv) mem.input_name = "perf.data"; } - if (!strncmp(argv[0], "rec", 3)) + if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) return __cmd_record(argc, argv, &mem); - else if (!strncmp(argv[0], "rep", 3)) + else if (strlen(argv[0]) > 2 && strstarts("report", argv[0])) return report_events(argc, argv, &mem); else usage_with_options(mem_usage, mem_options); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 72d446de9c60..646bd938927a 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3561,7 +3561,7 @@ int cmd_sched(int argc, const char **argv) if (!strcmp(argv[0], "script")) return cmd_script(argc, argv); - if (!strncmp(argv[0], "rec", 3)) { + if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) { return __cmd_record(argc, argv); } else if (!strncmp(argv[0], "lat", 3)) { sched.tp_handler = &lat_ops; @@ -3581,7 +3581,7 @@ int cmd_sched(int argc, const char **argv) sched.tp_handler = &map_ops; setup_sorting(&sched, latency_options, latency_usage); return perf_sched__map(&sched); - } else if (!strncmp(argv[0], "rep", 3)) { + } else if (strlen(argv[0]) > 2 && strstarts("replay", argv[0])) { sched.tp_handler = &replay_ops; if (argc) { argc = parse_options(argc, argv, replay_options, replay_usage, 0); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index f12dc5ed354d..a2f117936188 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3922,13 +3922,13 @@ int cmd_script(int argc, const char **argv) if (symbol__validate_sym_arguments()) return -1; - if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) { + if (argc > 1 && strlen(argv[0]) > 2 && strstarts("record", argv[0])) { rec_script_path = get_script_path(argv[1], RECORD_SUFFIX); if (!rec_script_path) return cmd_record(argc, argv); } - if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) { + if (argc > 1 && strlen(argv[0]) > 2 && strstarts("report", argv[0])) { rep_script_path = get_script_path(argv[1], REPORT_SUFFIX); if (!rep_script_path) { fprintf(stderr, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 60baa3dadc4b..4ee40de698a4 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2271,11 +2271,11 @@ int cmd_stat(int argc, const char **argv) } else stat_config.csv_sep = DEFAULT_SEPARATOR; - if (argc && !strncmp(argv[0], "rec", 3)) { + if (argc && strlen(argv[0]) > 2 && strstarts("record", argv[0])) { argc = __cmd_record(argc, argv); if (argc < 0) return -1; - } else if (argc && !strncmp(argv[0], "rep", 3)) + } else if (argc && strlen(argv[0]) > 2 && strstarts("report", argv[0])) return __cmd_report(argc, argv); interval = stat_config.interval; diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 43bf4d67edb0..afce731cec16 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -35,6 +35,7 @@ #include "util/tool.h" #include "util/data.h" #include "util/debug.h" +#include "util/string2.h" #include #ifdef LACKS_OPEN_MEMSTREAM_PROTOTYPE @@ -1983,7 +1984,7 @@ int cmd_timechart(int argc, const char **argv) return -1; } - if (argc && !strncmp(argv[0], "rec", 3)) { + if (argc && strlen(argv[0]) > 2 && strstarts("record", argv[0])) { argc = parse_options(argc, argv, timechart_record_options, timechart_record_usage, PARSE_OPT_STOP_AT_NON_OPTION); -- cgit v1.2.3 From c6d8df01064333dcf140eda996abdb60a60e24b3 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Sun, 17 Apr 2022 19:48:37 +0800 Subject: perf script: Always allow field 'data_src' for auxtrace If use command 'perf script -F,+data_src' to dump memory samples with Arm SPE trace data, it reports error: # perf script -F,+data_src Samples for 'dummy:u' event do not have DATA_SRC attribute set. Cannot print 'data_src' field. This is because the 'dummy:u' event is absent DATA_SRC bit in its sample type, so if a file contains AUX area tracing data then always allow field 'data_src' to be selected as an option for perf script. Fixes: e55ed3423c1bb29f ("perf arm-spe: Synthesize memory event") Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220417114837.839896-1-leo.yan@linaro.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 a2f117936188..cf5eab5431b4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -461,7 +461,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(DATA_SRC) && - evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC)) + evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set)) return -EINVAL; if (PRINT_FIELD(WEIGHT) && -- cgit v1.2.3 From a5014310f7a9b6486daa8e8852e3d1f2ba323328 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 9 May 2022 18:23:59 +0300 Subject: perf script: Print Intel ptwrite value as a string if it is ASCII It can be convenient to put a string value into a ptwrite payload as a quick and easy way to identify what is being printed. To make that useful, if the Intel ptwrite payload value contains only printable ASCII characters padded with NULLs, then print it also as a string. Using the example program from the "Emulated PTWRITE" section of tools/perf/Documentation/perf-intel-pt.txt: $ echo -n "Hello" | od -t x8 0000000 0000006f6c6c6548 0000005 $ perf record -e intel_pt//u ./eg_ptw 0x0000006f6c6c6548 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data ] $ perf script --itrace=ew eg_ptw 35563 [005] 18256.087338: ptwrite: IP: 0 payload: 0x6f6c6c6548 Hello 55e764db5196 perf_emulate_ptwrite+0x16 (/home/user/eg_ptw) $ Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: https://lore.kernel.org/r/20220509152400.376613-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index cf5eab5431b4..ae6d216df438 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1742,16 +1742,44 @@ static int perf_sample__fprintf_pt_spacing(int len, FILE *fp) return perf_sample__fprintf_spacing(len, 34, fp); } +/* If a value contains only printable ASCII characters padded with NULLs */ +static bool ptw_is_prt(u64 val) +{ + char c; + u32 i; + + for (i = 0; i < sizeof(val); i++) { + c = ((char *)&val)[i]; + if (!c) + break; + if (!isprint(c) || !isascii(c)) + return false; + } + for (; i < sizeof(val); i++) { + c = ((char *)&val)[i]; + if (c) + return false; + } + return true; +} + static int perf_sample__fprintf_synth_ptwrite(struct perf_sample *sample, FILE *fp) { struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample); + char str[sizeof(u64) + 1] = ""; int len; + u64 val; if (perf_sample__bad_synth_size(sample, *data)) return 0; - len = fprintf(fp, " IP: %u payload: %#" PRIx64 " ", - data->ip, le64_to_cpu(data->payload)); + val = le64_to_cpu(data->payload); + if (ptw_is_prt(val)) { + memcpy(str, &val, sizeof(val)); + str[sizeof(val)] = 0; + } + len = fprintf(fp, " IP: %u payload: %#" PRIx64 " %s ", + data->ip, val, str); return len + perf_sample__fprintf_pt_spacing(len, fp); } -- cgit v1.2.3 From 5b208144602f7557f569a26b907da2283cc9b4ac Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 17 May 2022 16:10:09 +0300 Subject: perf script: Add guest_code support Add an option to indicate that guest code can be found in the hypervisor process. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Leo Yan Cc: Namhyung Kim Cc: kvm@vger.kernel.org Link: https://lore.kernel.org/r/20220517131011.6117-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 4 ++++ tools/perf/builtin-script.c | 5 ++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 2012a8e6c90b..1a557ff8f210 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -499,6 +499,10 @@ include::itrace.txt[] The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. +--guest-code:: + Indicate that guest code can be found in the hypervisor process, + which is a common case for KVM test programs. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ae6d216df438..c689054002cc 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3912,6 +3912,8 @@ int cmd_script(int argc, const char **argv) "file", "file saving guest os /proc/kallsyms"), OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, "file", "file saving guest os /proc/modules"), + OPT_BOOLEAN(0, "guest-code", &symbol_conf.guest_code, + "Guest code can be found in hypervisor process"), OPT_BOOLEAN('\0', "stitch-lbr", &script.stitch_lbr, "Enable LBR callgraph stitching approach"), OPTS_EVSWITCH(&script.evswitch), @@ -3937,7 +3939,8 @@ int cmd_script(int argc, const char **argv) if (symbol_conf.guestmount || symbol_conf.default_guest_vmlinux_name || symbol_conf.default_guest_kallsyms || - symbol_conf.default_guest_modules) { + symbol_conf.default_guest_modules || + symbol_conf.guest_code) { /* * Enable guest sample processing. */ -- cgit v1.2.3