diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 3728b50e52e20d0eb43780ec354d0c2242d6c414..88d52ed85ffc1c1ae82b644b8dc766f5a2e6e025 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1073,9 +1073,18 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, /* * Print final block upto 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. */ start = br->entries[0].to; end = sample->ip; + if (end < start) { + /* Missing jump. Scan 128 bytes for the next branch */ + end = start + 128; + } len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true); printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp); if (len <= 0) { @@ -1084,7 +1093,6 @@ 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)); if (PRINT_FIELD(SRCCODE)) @@ -1096,6 +1104,13 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, dump_insn(&x, start + off, buffer + off, len - off, &ilen)); if (ilen == 0) break; + if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) { + /* + * Hit a missing branch. Just stop. + */ + printed += fprintf(fp, "\t... not reaching sample ...\n"); + break; + } if (PRINT_FIELD(SRCCODE)) print_srccode(thread, x.cpumode, start + off); } diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c index 10988d3de7cec8940f3e4904cdb537a6f32cc690..2bd8585db93c30df83d2d0740a596a56a2a1f8f7 100644 --- a/tools/perf/util/dump-insn.c +++ b/tools/perf/util/dump-insn.c @@ -13,3 +13,11 @@ const char *dump_insn(struct perf_insn *x __maybe_unused, *lenp = 0; return "?"; } + +__weak +int arch_is_branch(const unsigned char *buf __maybe_unused, + size_t len __maybe_unused, + int x86_64 __maybe_unused) +{ + return 0; +} diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h index 0e06280a88602bb28d4596fbce45314e06aa4236..650125061530934c3f175d90ca8c82e2c59f99ca 100644 --- a/tools/perf/util/dump-insn.h +++ b/tools/perf/util/dump-insn.h @@ -20,4 +20,6 @@ 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); + #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 54818828023bf4ad0960165d26afce60fe7166d1..1c0e289f01e6fe077079de8de4ae7f6fe3c43323 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 @@ -180,6 +180,14 @@ 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) +{ + 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; +} + const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused, u8 *inbuf, int inlen, int *lenp) {