From bf0db8c759ba137cebfeda9eecc1f728cb14dab7 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 29 Feb 2024 08:18:28 -0800 Subject: [PATCH] perf script: Minimize "not reaching sample" for '-F +brstackinsn' In some situations 'perf script -F +brstackinsn' sees a lot of "not reaching sample" messages. This happens when the last LBR block before the sample contains a branch that is not in the LBR, and the instruction dumping stops. $ perf record -b emacs -Q --batch '()' [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.396 MB perf.data (443 samples) ] $ perf script -F +brstackinsn ... 00007f0ab2d171a4 insn: 41 0f 94 c0 00007f0ab2d171a8 insn: 83 fa 01 00007f0ab2d171ab insn: 74 d3 # PRED 6 cycles [313] 1.00 IPC 00007f0ab2d17180 insn: 45 84 c0 00007f0ab2d17183 insn: 74 28 ... not reaching sample ... $ perf script -F +brstackinsn | grep -c reach 136 $ This is a problem for further analysis that wants to see the full code upto the sample. There are two common cases where the message is bogus: - The LBR only logs taken branches, but the branch might be a conditional branch that is not taken (that is the most common case actually) - The LBR sampling uses a filter ignoring some branches, but the perf script check checks for all branches. This patch fixes these two conditions, by only checking for conditional branches, as well as checking the perf_event_attr's branch filter attributes. For the test case above it fixes all the messages: $ ./perf script -F +brstackinsn | grep -c reach 0 Note that there are still conditions when the message is hit -- sometimes there can be a unconditional branch that misses the LBR update before the sample -- but they are much more rare now. Signed-off-by: Andi Kleen Reviewed-by: Adrian Hunter Link: https://lore.kernel.org/r/20240229161828.386397-1-ak@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 6 ++++-- tools/perf/util/dump-insn.c | 2 +- tools/perf/util/dump-insn.h | 2 +- tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c | 5 +++-- 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 206b08426555..dbe792b52c5c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1428,7 +1428,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, * Due to pipeline delays the LBRs might be missing a branch * or two, which can result in very large or negative blocks * between final branch and sample. When this happens just - * continue walking after the last TO until we hit a branch. + * continue walking after the last TO. */ start = entries[0].to; end = sample->ip; @@ -1463,7 +1463,9 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, printed += fprintf(fp, "\n"); if (ilen == 0) break; - if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) { + if ((attr->branch_sample_type == 0 || attr->branch_sample_type & PERF_SAMPLE_BRANCH_ANY) + && arch_is_uncond_branch(buffer + off, len - off, x.is64bit) + && start + off != sample->ip) { /* * Hit a missing branch. Just stop. */ diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c index 2bd8585db93c..c1cc0ade48d0 100644 --- a/tools/perf/util/dump-insn.c +++ b/tools/perf/util/dump-insn.c @@ -15,7 +15,7 @@ const char *dump_insn(struct perf_insn *x __maybe_unused, } __weak -int arch_is_branch(const unsigned char *buf __maybe_unused, +int arch_is_uncond_branch(const unsigned char *buf __maybe_unused, size_t len __maybe_unused, int x86_64 __maybe_unused) { diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h index 4a7797dd6d09..20d4d7bb5275 100644 --- a/tools/perf/util/dump-insn.h +++ b/tools/perf/util/dump-insn.h @@ -21,6 +21,6 @@ struct perf_insn { const char *dump_insn(struct perf_insn *x, u64 ip, u8 *inbuf, int inlen, int *lenp); -int arch_is_branch(const unsigned char *buf, size_t len, int x86_64); +int arch_is_uncond_branch(const unsigned char *buf, size_t len, int x86_64); #endif diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 4407130d91f8..47cf35799a4d 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -209,12 +209,13 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64, return 0; } -int arch_is_branch(const unsigned char *buf, size_t len, int x86_64) +int arch_is_uncond_branch(const unsigned char *buf, size_t len, int x86_64) { struct intel_pt_insn in; if (intel_pt_get_insn(buf, len, x86_64, &in) < 0) return -1; - return in.branch != INTEL_PT_BR_NO_BRANCH; + return in.branch == INTEL_PT_BR_UNCONDITIONAL || + in.branch == INTEL_PT_BR_INDIRECT; } const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,