From e3b03b6c1a4f3b4564be08809f58584592621a0a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 5 May 2016 16:04:03 -0700 Subject: perf stat: Avoid fractional digits for integer scales When the scaling factor is a full integer don't display fractional digits. This avoids unnecessary .00 output for topdown metrics with scale factors. v2: Remove redundant check. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1462489447-31832-7-git-send-email-andi@firstfloor.org [ Rename 'round' to 'stat_round' as 'round' is defined in math.h, included by this patch, and this breaks the build on ubuntu 12.04 ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5645a8361de6..16a923c1633b 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -66,6 +66,7 @@ #include #include #include +#include #define DEFAULT_SEPARATOR " " #define CNTR_NOT_SUPPORTED "" @@ -986,12 +987,12 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) const char *fmt; if (csv_output) { - fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s"; + fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s"; } else { if (big_num) - fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s"; + fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s"; else - fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s"; + fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s"; } aggr_printout(evsel, id, nr); @@ -1995,7 +1996,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_session *session) { - struct stat_round_event *round = &event->stat_round; + struct stat_round_event *stat_round = &event->stat_round; struct perf_evsel *counter; struct timespec tsh, *ts = NULL; const char **argv = session->header.env.cmdline_argv; @@ -2004,12 +2005,12 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, evlist__for_each(evsel_list, counter) perf_stat_process_counter(&stat_config, counter); - if (round->type == PERF_STAT_ROUND_TYPE__FINAL) - update_stats(&walltime_nsecs_stats, round->time); + if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL) + update_stats(&walltime_nsecs_stats, stat_round->time); - if (stat_config.interval && round->time) { - tsh.tv_sec = round->time / NSECS_PER_SEC; - tsh.tv_nsec = round->time % NSECS_PER_SEC; + if (stat_config.interval && stat_round->time) { + tsh.tv_sec = stat_round->time / NSECS_PER_SEC; + tsh.tv_nsec = stat_round->time % NSECS_PER_SEC; ts = &tsh; } -- cgit v1.2.3 From 6ae98ba611ed1c11ddc5645475bc03b46a3c04e7 Mon Sep 17 00:00:00 2001 From: He Kuang Date: Thu, 12 May 2016 08:43:11 +0000 Subject: perf symbols: Store vdso buildid unconditionally When unwinding callchains on a different machine, vdso info should be available so the unwind process won't be interrupted if address falls into vdso region. But in most cases, the addresses of sample events are not in vdso range, the buildid of a zero hit vdso won't be stored into perf.data. This patch stores vdso buildid regardless of whether the vdso is hit or not. Signed-off-by: He Kuang Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Ekaterina Tumanova Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Kan Liang Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Sukadev Bhattiprolu Cc: Wang Nan Link: http://lkml.kernel.org/r/1463042596-61703-3-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 2 +- tools/perf/util/dso.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index bff425e1232c..67e5966503b2 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -256,7 +256,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd) size_t name_len; bool in_kernel = false; - if (!pos->hit) + if (!pos->hit && !dso__is_vdso(pos)) continue; if (dso__is_vdso(pos)) { diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 3357479082ca..75b75615e2f8 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -7,6 +7,7 @@ #include "auxtrace.h" #include "util.h" #include "debug.h" +#include "vdso.h" char dso__symtab_origin(const struct dso *dso) { @@ -1169,7 +1170,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) struct dso *pos; list_for_each_entry(pos, head, node) { - if (with_hits && !pos->hit) + if (with_hits && !pos->hit && !dso__is_vdso(pos)) continue; if (pos->has_build_id) { have_build_id = true; -- cgit v1.2.3 From b0404be8d6186f9f3c23e2b5ff247e667be90652 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 13 May 2016 15:01:01 +0900 Subject: perf stat: Fix indentation of stalled backend cycle The commit 140aeadc1fb5 ("perf stat: Abstract stat metrics printing") changed how shadow metrics are printed, but it missed to update the width of the stalled backend cycles event to 7.2% like others. This resulted in misaligned output like below: Performance counter stats for 'pwd': 0.638313 task-clock (msec) # 0.567 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec 54 page-faults # 0.085 M/sec 885,600 cycles # 1.387 GHz 558,438 stalled-cycles-frontend # 63.06% frontend cycles idle 431,355 stalled-cycles-backend # 48.71% backend cycles idle 674,956 instructions # 0.76 insn per cycle # 0.83 stalled cycles per insn 130,380 branches # 204.257 M/sec branch-misses 0.001125426 seconds time elapsed Signed-off-by: Namhyung Kim Cc: Andi Kleen Cc: Jiri Olsa Cc: Peter Zijlstra Fixes: 140aeadc1fb5 ("perf stat: Abstract stat metrics printing") Link: http://lkml.kernel.org/r/1463119263-5569-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index fdb71961143e..61200fcac5ef 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -188,7 +188,7 @@ static void print_stalled_cycles_backend(int cpu, color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio); - out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio); + out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio); } static void print_branch_misses(int cpu, -- cgit v1.2.3 From daf4f4786e8af371048e72cb37ac05190e89198a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 13 May 2016 15:01:02 +0900 Subject: perf stat: Update runtime using cpu-clock event Currently only the task-clock event updates the runtime_nsec so it cannot show the metric when using cpu-clock events. However cpu clock works basically same as task-clock, so no need to not update the runtime IMHO. Before: # perf stat -a -e cpu-clock,context-switches,page-faults,cycles sleep 0.1 Performance counter stats for 'system wide': 1217.759506 cpu-clock (msec) 93 context-switches 61 page-faults 18,958,022 cycles 0.101393794 seconds time elapsed After: Performance counter stats for 'system wide': 1220.471884 cpu-clock (msec) # 12.013 CPUs utilized 118 context-switches # 0.097 K/sec 59 page-faults # 0.048 K/sec 17,941,247 cycles # 0.015 GHz 0.101594777 seconds time elapsed Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1463119263-5569-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 61200fcac5ef..aa9efe08762b 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -94,7 +94,8 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, { int ctx = evsel_context(counter); - if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK)) + if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) || + perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK)) update_stats(&runtime_nsecs_stats[cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) update_stats(&runtime_cycles_stats[ctx][cpu], count[0]); @@ -444,7 +445,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ratio = total / avg; print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio); - } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) { + } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) || + perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", avg / ratio); -- cgit v1.2.3 From a1f3d56761df31f0ffeb215b974e26d5613e92a4 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 13 May 2016 15:01:03 +0900 Subject: perf stat: Use cpu-clock event for cpu targets Currently 'perf stat' always counts task-clock event by default. But it's somewhat confusing for system-wide targets (especially with 'sleep N' as the 'sleep' task just sleeps and doesn't use cputime). Changing to cpu-clock event instead for that case makes more sense IMHO. Before: # perf stat -a sleep 0.1 Performance counter stats for 'system wide': 403.038603 task-clock (msec) # 4.001 CPUs utilized 150 context-switches # 0.372 K/sec 7 cpu-migrations # 0.017 K/sec 71 page-faults # 0.176 K/sec 23,705,169 cycles # 0.059 GHz 15,888,166 instructions # 0.67 insn per cycle 3,326,078 branches # 8.253 M/sec 87,643 branch-misses # 2.64% of all branches 0.100737009 seconds time elapsed # After: # perf stat -a sleep 0.1 Performance counter stats for 'system wide': 404.271182 cpu-clock (msec) # 4.000 CPUs utilized 143 context-switches # 0.354 K/sec 13 cpu-migrations # 0.032 K/sec 73 page-faults # 0.181 K/sec 22,119,220 cycles # 0.055 GHz 13,622,065 instructions # 0.62 insn per cycle 2,918,769 branches # 7.220 M/sec 85,033 branch-misses # 2.91% of all branches 0.101073089 seconds time elapsed # Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1463119263-5569-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 16a923c1633b..efdd23221c16 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1905,6 +1905,9 @@ static int add_default_attributes(void) } if (!evsel_list->nr_entries) { + if (target__has_cpu(&target)) + default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK; + if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0) return -1; if (pmu_have_event("cpu", "stalled-cycles-frontend")) { -- cgit v1.2.3 From 0a77582f0407e7f9b5d775bebc31297a1b890be0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sun, 15 May 2016 12:19:40 +0900 Subject: perf symbols: Introduce DSO__NAME_KALLSYMS and DSO__NAME_KCORE Instead of using a raw string, use DSO__NAME_KALLSYMS and DSO__NAME_KCORE macros for kallsyms and kcore. Signed-off-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Brendan Gregg Cc: Hemant Kumar Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20160515031935.4017.50971.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-buildid-cache.c | 8 ++++---- tools/perf/util/annotate.c | 2 +- tools/perf/util/machine.c | 2 +- tools/perf/util/symbol.c | 10 +++++----- tools/perf/util/symbol.h | 3 +++ 5 files changed, 14 insertions(+), 11 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 632efc6b79a0..d75bded21fe0 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -119,8 +119,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force) if (build_id_cache__kcore_buildid(from_dir, sbuildid) < 0) return -1; - scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s", - buildid_dir, sbuildid); + scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s", + buildid_dir, DSO__NAME_KCORE, sbuildid); if (!force && !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) { @@ -131,8 +131,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force) if (build_id_cache__kcore_dir(dir, sizeof(dir))) return -1; - scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s", - buildid_dir, sbuildid, dir); + scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s/%s", + buildid_dir, DSO__NAME_KCORE, sbuildid, dir); if (mkdir_p(to_dir, 0755)) return -1; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 4db73d5a0dbc..b811924e5e1b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1122,7 +1122,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) } else if (dso__is_kcore(dso)) { goto fallback; } else if (readlink(symfs_filename, command, sizeof(command)) < 0 || - strstr(command, "[kernel.kallsyms]") || + strstr(command, DSO__NAME_KALLSYMS) || access(symfs_filename, R_OK)) { free(filename); fallback: diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 639a2903065e..18dd96bdde05 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -709,7 +709,7 @@ static struct dso *machine__get_kernel(struct machine *machine) if (machine__is_host(machine)) { vmlinux_name = symbol_conf.vmlinux_name; if (!vmlinux_name) - vmlinux_name = "[kernel.kallsyms]"; + vmlinux_name = DSO__NAME_KALLSYMS; kernel = machine__findnew_kernel(machine, vmlinux_name, "[kernel]", DSO_TYPE_KERNEL); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 7fb33304fb4e..2252b545ff43 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1662,8 +1662,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map) build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); - scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir, - sbuild_id); + scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir, + DSO__NAME_KCORE, sbuild_id); /* Use /proc/kallsyms if possible */ if (is_host) { @@ -1699,8 +1699,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map) if (!find_matching_kcore(map, path, sizeof(path))) return strdup(path); - scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s", - buildid_dir, sbuild_id); + scnprintf(path, sizeof(path), "%s/%s/%s", + buildid_dir, DSO__NAME_KALLSYMS, sbuild_id); if (access(path, F_OK)) { pr_err("No kallsyms or vmlinux with build-id %s was found\n", @@ -1769,7 +1769,7 @@ do_kallsyms: if (err > 0 && !dso__is_kcore(dso)) { dso->binary_type = DSO_BINARY_TYPE__KALLSYMS; - dso__set_long_name(dso, "[kernel.kallsyms]", false); + dso__set_long_name(dso, DSO__NAME_KALLSYMS, false); map__fixup_start(map); map__fixup_end(map); } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2b5e4ed76fcb..25f2fd672c2e 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -44,6 +44,9 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, #define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ #endif +#define DSO__NAME_KALLSYMS "[kernel.kallsyms]" +#define DSO__NAME_KCORE "[kernel.kcore]" + /** struct symbol - symtab entry * * @ignore - resolvable but tools ignore it (e.g. idle routines) -- cgit v1.2.3 From a29d5c9b8167dbc21a7ca8c0302e3799f9063b4e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 16 May 2016 21:16:54 -0300 Subject: perf tools: Separate accounting of contexts and real addresses in a stack trace The perf_sample->ip_callchain->nr value includes all the entries in the ip_callchain->ip[] array, real addresses and PERF_CONTEXT_{KERNEL,USER,etc}, while what the user expects is that what is in the kernel.perf_event_max_stack sysctl or in the upcoming per event perf_event_attr.sample_max_stack knob be honoured in terms of IP addresses in the stack trace. So match the kernel support and validate chain->nr taking into account both kernel.perf_event_max_stack and kernel.perf_event_max_contexts_per_stack. Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: David Ahern Cc: Frederic Weisbecker Cc: He Kuang Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: Wang Nan Cc: Zefan Li Link: http://lkml.kernel.org/n/tip-mgx0jpzfdq4uq4abfa40byu0@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/perf.c | 3 +++ tools/perf/util/machine.c | 26 +++++++++++++++++--------- tools/perf/util/util.c | 3 ++- tools/perf/util/util.h | 3 ++- 4 files changed, 24 insertions(+), 11 deletions(-) (limited to 'tools') diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 797000842d40..15982cee5ef3 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -549,6 +549,9 @@ int main(int argc, const char **argv) if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0) sysctl_perf_event_max_stack = value; + if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0) + sysctl_perf_event_max_contexts_per_stack = value; + cmd = extract_argv0_path(argv[0]); if (!cmd) cmd = "perf-help"; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 18dd96bdde05..7ba9fadb68af 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1811,9 +1811,9 @@ static int thread__resolve_callchain_sample(struct thread *thread, { struct branch_stack *branch = sample->branch_stack; struct ip_callchain *chain = sample->callchain; - int chain_nr = min(max_stack, (int)chain->nr); + int chain_nr = chain->nr; u8 cpumode = PERF_RECORD_MISC_USER; - int i, j, err; + int i, j, err, nr_entries, nr_contexts; int skip_idx = -1; int first_call = 0; @@ -1828,7 +1828,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, * Based on DWARF debug information, some architectures skip * a callchain entry saved by the kernel. */ - if (chain->nr < sysctl_perf_event_max_stack) + if (chain_nr < sysctl_perf_event_max_stack) skip_idx = arch_skip_callchain_idx(thread, chain); /* @@ -1889,12 +1889,8 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) { - pr_warning("corrupted callchain. skipping...\n"); - return 0; - } - - for (i = first_call; i < chain_nr; i++) { + for (i = first_call, nr_entries = 0, nr_contexts = 0; + i < chain_nr && nr_entries < max_stack; i++) { u64 ip; if (callchain_param.order == ORDER_CALLEE) @@ -1908,6 +1904,14 @@ check_calls: #endif ip = chain->ips[j]; + if (ip >= PERF_CONTEXT_MAX) { + if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack) + goto out_corrupted_callchain; + } else { + if (++nr_entries > sysctl_perf_event_max_stack) + goto out_corrupted_callchain; + } + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); if (err) @@ -1915,6 +1919,10 @@ check_calls: } return 0; + +out_corrupted_callchain: + pr_warning("corrupted callchain. skipping...\n"); + return 0; } static int unwind_entry(struct unwind_entry *entry, void *arg) diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index eab077ad6ca9..23504ad5d6dd 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -33,7 +33,8 @@ struct callchain_param callchain_param = { unsigned int page_size; int cacheline_size; -unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; +int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; +int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK; bool test_attr__enabled; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 7651633a8dc7..1e8c3167b9fb 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -261,7 +261,8 @@ void sighandler_dump_stack(int sig); extern unsigned int page_size; extern int cacheline_size; -extern unsigned int sysctl_perf_event_max_stack; +extern int sysctl_perf_event_max_stack; +extern int sysctl_perf_event_max_contexts_per_stack; struct parse_tag { char tag; -- cgit v1.2.3 From 45e90056904b12d8dd74e0d2ea6dfd5e4394104d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 17 May 2016 11:52:26 -0300 Subject: perf machine: Do not bail out if not managing to read ref reloc symbol This means the user can't access /proc/kallsyms, for instance, because /proc/sys/kernel/kptr_restrict is set to 1. Instead leave the ref_reloc_sym as NULL and code using it will cope. This allows 'perf trace' to work on such systems for !root, the only issue would be when trying to resolve kernel symbols, which happens, for instance, in some libtracevent plugins. A warning for that case will be provided in the next patch in this series. Noticed in Ubuntu 16.04, that comes with kptr_restrict=1. Reported-by: Milian Wolff Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-knpu3z4iyp2dxpdfm798fac4@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 7ba9fadb68af..b277984aaa93 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1135,10 +1135,10 @@ int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); const char *name; - u64 addr = machine__get_running_kernel_start(machine, &name); + u64 addr; int ret; - if (!addr || kernel == NULL) + if (kernel == NULL) return -1; ret = __machine__create_kernel_maps(machine, kernel); @@ -1160,8 +1160,9 @@ int machine__create_kernel_maps(struct machine *machine) */ map_groups__fixup_end(&machine->kmaps); - if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, - addr)) { + addr = machine__get_running_kernel_start(machine, &name); + if (!addr) { + } else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { machine__destroy_kernel_maps(machine); return -1; } -- cgit v1.2.3 From caf8a0d0499792ac1b3f5b0b84e5890df0039cb6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 17 May 2016 11:56:24 -0300 Subject: perf trace: Warn when trying to resolve kernel addresses with kptr_restrict=1 Hook into the libtraceevent plugin kernel symbol resolver to warn the user that that can't happen with kptr_restrict=1. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-9gc412xx1gl0lvqj1d1xwlyb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 20 +++++++++++++++++++- tools/perf/util/machine.c | 1 + tools/perf/util/machine.h | 1 + 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6e5c325148e4..e488ac756f39 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1160,6 +1160,24 @@ static int trace__tool_process(struct perf_tool *tool, return trace__process_event(trace, machine, event, sample); } +static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp) +{ + struct machine *machine = vmachine; + + if (machine->kptr_restrict_warned) + return NULL; + + if (symbol_conf.kptr_restrict) { + pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n" + "Check /proc/sys/kernel/kptr_restrict.\n\n" + "Kernel samples will not be resolved.\n"); + machine->kptr_restrict_warned = true; + return NULL; + } + + return machine__resolve_kernel_addr(vmachine, addrp, modp); +} + static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) { int err = symbol__init(NULL); @@ -1171,7 +1189,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) if (trace->host == NULL) return -ENOMEM; - if (trace_event__register_resolver(trace->host, machine__resolve_kernel_addr) < 0) + if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0) return -errno; err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target, diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b277984aaa93..bdc33ce40bdc 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -43,6 +43,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->symbol_filter = NULL; machine->id_hdr_size = 0; + machine->kptr_restrict_warned = false; machine->comm_exec = false; machine->kernel_start = 0; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 83f46790c52f..41ac9cfd416b 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -28,6 +28,7 @@ struct machine { pid_t pid; u16 id_hdr_size; bool comm_exec; + bool kptr_restrict_warned; char *root_dir; struct rb_root threads; pthread_rwlock_t threads_lock; -- cgit v1.2.3 From e77a07425f4391da2f08b0f9a09df4e70626204d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 17 May 2016 11:58:52 -0300 Subject: perf top: Use machine->kptr_restrict_warned Its now there, no need to have it too. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-y18oeou494uy11im7u9to0dx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 6 +++--- tools/perf/util/top.h | 1 - 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 1793da585676..2a6cc254ad0c 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -732,7 +732,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if (machine__resolve(machine, &al, sample) < 0) return; - if (!top->kptr_restrict_warned && + if (!machine->kptr_restrict_warned && symbol_conf.kptr_restrict && al.cpumode == PERF_RECORD_MISC_KERNEL) { ui__warning( @@ -743,7 +743,7 @@ static void perf_event__process_sample(struct perf_tool *tool, " modules" : ""); if (use_browser <= 0) sleep(5); - top->kptr_restrict_warned = true; + machine->kptr_restrict_warned = true; } if (al.sym == NULL) { @@ -759,7 +759,7 @@ static void perf_event__process_sample(struct perf_tool *tool, * --hide-kernel-symbols, even if the user specifies an * invalid --vmlinux ;-) */ - if (!top->kptr_restrict_warned && !top->vmlinux_warned && + if (!machine->kptr_restrict_warned && !top->vmlinux_warned && al.map == machine->vmlinux_maps[MAP__FUNCTION] && RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) { if (symbol_conf.vmlinux_name) { diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index f92c37abb0a8..b2940c88734a 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -27,7 +27,6 @@ struct perf_top { int max_stack; bool hide_kernel_symbols, hide_user_symbols, zero; bool use_tui, use_stdio; - bool kptr_restrict_warned; bool vmlinux_warned; bool dump_symtab; struct hist_entry *sym_filter_entry; -- cgit v1.2.3 From c008f78f9309a3be3548e11f48b8dfb08f2eb8fc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 17 May 2016 12:13:54 -0300 Subject: perf trace: Fix exit_group() formatting This doesn't return, so there is no raw_syscalls:sys_exit for it, add the ending ')', without any return value, since it is void. Reported-by: Ingo Molnar Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-vh2mii0g4qlveuc4joufbipu@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index e488ac756f39..a2f3aa09c7f4 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1552,7 +1552,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, if (sc->is_exit) { if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) { trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output); - fprintf(trace->output, "%-70s\n", ttrace->entry_str); + fprintf(trace->output, "%-70s)\n", ttrace->entry_str); } } else { ttrace->entry_pending = true; -- cgit v1.2.3 From bf8bddbf1971d40549f33bc6f70623cf53bbfa2f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 19 May 2016 11:14:15 -0300 Subject: perf callchain: Stop validating callchains by the max_stack sysctl As thread__resolve_callchain_sample can be used for handling perf.data files, that could've been recorded with a large max_stack sysctl setting than what the system used for analysis has set. Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: David Ahern Cc: Frederic Weisbecker Cc: He Kuang Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: Wang Nan Cc: Zefan Li Link: http://lkml.kernel.org/n/tip-2995bt2g5yq2m05vga4kip6m@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 25 +++++-------------------- 1 file changed, 5 insertions(+), 20 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index bdc33ce40bdc..205d27017361 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1771,11 +1771,6 @@ static int resolve_lbr_callchain_sample(struct thread *thread, */ int mix_chain_nr = i + 1 + lbr_nr + 1; - if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) { - pr_warning("corrupted callchain. skipping...\n"); - return 0; - } - for (j = 0; j < mix_chain_nr; j++) { if (callchain_param.order == ORDER_CALLEE) { if (j < i + 1) @@ -1815,7 +1810,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, struct ip_callchain *chain = sample->callchain; int chain_nr = chain->nr; u8 cpumode = PERF_RECORD_MISC_USER; - int i, j, err, nr_entries, nr_contexts; + int i, j, err, nr_entries; int skip_idx = -1; int first_call = 0; @@ -1830,8 +1825,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, * Based on DWARF debug information, some architectures skip * a callchain entry saved by the kernel. */ - if (chain_nr < sysctl_perf_event_max_stack) - skip_idx = arch_skip_callchain_idx(thread, chain); + skip_idx = arch_skip_callchain_idx(thread, chain); /* * Add branches to call stack for easier browsing. This gives @@ -1891,7 +1885,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - for (i = first_call, nr_entries = 0, nr_contexts = 0; + for (i = first_call, nr_entries = 0; i < chain_nr && nr_entries < max_stack; i++) { u64 ip; @@ -1906,13 +1900,8 @@ check_calls: #endif ip = chain->ips[j]; - if (ip >= PERF_CONTEXT_MAX) { - if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack) - goto out_corrupted_callchain; - } else { - if (++nr_entries > sysctl_perf_event_max_stack) - goto out_corrupted_callchain; - } + if (ip < PERF_CONTEXT_MAX) + ++nr_entries; err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); @@ -1921,10 +1910,6 @@ check_calls: } return 0; - -out_corrupted_callchain: - pr_warning("corrupted callchain. skipping...\n"); - return 0; } static int unwind_entry(struct unwind_entry *entry, void *arg) -- cgit v1.2.3 From fe176085a4d45fb241c04beea872ecbb8bef6a55 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 19 May 2016 11:34:06 -0300 Subject: perf tools: Fix usage of max_stack sysctl We cannot limit processing stacks from the current value of the sysctl, as we may be processing perf.data files, possibly from other machines. Instead use the old PERF_MAX_STACK_DEPTH, the sysctl default, that can be overriden using --max-stack or equivalent. Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: David Ahern Cc: Frederic Weisbecker Cc: He Kuang Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: Wang Nan Cc: Zefan Li Fixes: 4cb93446c587 ("perf tools: Set the maximum allowed stack from /proc/sys/kernel/perf_event_max_stack") Link: http://lkml.kernel.org/n/tip-eqeutsr7n7wy0c36z24ytvii@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 2 +- tools/perf/Documentation/perf-script.txt | 2 +- tools/perf/Documentation/perf-trace.txt | 3 ++- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-script.c | 2 -- tools/perf/builtin-trace.c | 2 +- tools/perf/util/db-export.c | 3 +-- tools/perf/util/scripting-engines/trace-event-perl.c | 3 +-- 8 files changed, 8 insertions(+), 11 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index ebaf849e30ef..496d42cdf02b 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -248,7 +248,7 @@ OPTIONS Note that when using the --itrace option the synthesized callchain size will override this value if the synthesized callchain size is bigger. - Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. + Default: 127 -G:: --inverted:: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index a856a1095893..4fc44c75263f 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -267,7 +267,7 @@ include::itrace.txt[] Note that when using the --itrace option the synthesized callchain size will override this value if the synthesized callchain size is bigger. - Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. + Default: 127 --ns:: Use 9 decimal places when displaying time (i.e. show the nanoseconds) diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 6afe20121bc0..1ab0782369b1 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -143,7 +143,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. Implies '--call-graph dwarf' when --call-graph not present on the command line, on systems where DWARF unwinding was built in. - Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise. + Default: /proc/sys/kernel/perf_event_max_stack when present for + live sessions (without --input/-i), 127 otherwise. --min-stack:: Set the stack depth limit when parsing the callchain, anything diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 87d40e3c4078..9bc71c6a54f6 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -691,7 +691,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .ordered_events = true, .ordering_requires_timestamps = true, }, - .max_stack = sysctl_perf_event_max_stack, + .max_stack = PERF_MAX_STACK_DEPTH, .pretty_printing_style = "normal", .socket_filter = -1, }; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index efca81679bb3..0a83f4bacc7c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2067,8 +2067,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; - scripting_max_stack = sysctl_perf_event_max_stack; - setup_scripting(); argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage, diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index a2f3aa09c7f4..7401de71d097 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2905,7 +2905,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) mmap_pages_user_set = false; if (trace.max_stack == UINT_MAX) { - trace.max_stack = sysctl_perf_event_max_stack; + trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack; max_stack_user_set = false; } diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 8d96c80cc67e..c9a6dc173e74 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -298,8 +298,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, */ callchain_param.order = ORDER_CALLER; err = thread__resolve_callchain(thread, &callchain_cursor, evsel, - sample, NULL, NULL, - sysctl_perf_event_max_stack); + sample, NULL, NULL, PERF_MAX_STACK_DEPTH); if (err) { callchain_param.order = saved_order; return NULL; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 62c7f6988e0e..5d1eb1ccd96c 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -264,8 +264,7 @@ static SV *perl_process_callchain(struct perf_sample *sample, goto exit; if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, - sample, NULL, NULL, - sysctl_perf_event_max_stack) != 0) { + sample, NULL, NULL, scripting_max_stack) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); goto exit; } -- cgit v1.2.3 From 58c0400176b2cd35da43f3115fa94ca937483aca Mon Sep 17 00:00:00 2001 From: Chris Ryder Date: Thu, 19 May 2016 17:59:45 +0100 Subject: perf annotate: Fix identification of ARM blt and bls instructions The ARM blt and bls instructions are not correctly identified when parsing assembly because the list of recognised instructions must be sorted by name. Swap the ordering of blt and bls. Signed-off-by: Chris Ryder Acked-by: Pawel Moll Cc: Alexander Shishkin Cc: Mark Rutland Cc: Peter Zijlstra Cc: Will Deacon Link: http://lkml.kernel.org/r/560e196b7c79b7ff853caae13d8719a31479cb1a.1463676839.git.chris.ryder@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index b811924e5e1b..3d9f2ca2ed2d 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -372,8 +372,8 @@ static struct ins instructions[] = { { .name = "bgt", .ops = &jump_ops, }, { .name = "bhi", .ops = &jump_ops, }, { .name = "bl", .ops = &call_ops, }, - { .name = "blt", .ops = &jump_ops, }, { .name = "bls", .ops = &jump_ops, }, + { .name = "blt", .ops = &jump_ops, }, { .name = "blx", .ops = &call_ops, }, { .name = "bne", .ops = &jump_ops, }, #endif -- cgit v1.2.3 From 7e4c1498130d7b6c26e6669839af4c7e321c9fec Mon Sep 17 00:00:00 2001 From: Chris Ryder Date: Thu, 19 May 2016 17:59:46 +0100 Subject: perf annotate: Sort list of recognised instructions Currently the list of instructions recognised by perf annotate has to be explicitly written in sorted order. This makes it easy to make mistakes when adding new instructions. Sort the list of instructions on first access. Signed-off-by: Chris Ryder Acked-by: Pawel Moll Cc: Alexander Shishkin Cc: Mark Rutland Cc: Peter Zijlstra Cc: Will Deacon Link: http://lkml.kernel.org/r/4268febaf32f47f322c166fb2fe98cfec7041e11.1463676839.git.chris.ryder@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 3d9f2ca2ed2d..7e5a1e8874ce 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -354,9 +354,6 @@ static struct ins_ops nop_ops = { .scnprintf = nop__scnprintf, }; -/* - * Must be sorted by name! - */ static struct ins instructions[] = { { .name = "add", .ops = &mov_ops, }, { .name = "addl", .ops = &mov_ops, }, @@ -449,18 +446,39 @@ static struct ins instructions[] = { { .name = "xbeginq", .ops = &jump_ops, }, }; -static int ins__cmp(const void *name, const void *insp) +static int ins__key_cmp(const void *name, const void *insp) { const struct ins *ins = insp; return strcmp(name, ins->name); } +static int ins__cmp(const void *a, const void *b) +{ + const struct ins *ia = a; + const struct ins *ib = b; + + return strcmp(ia->name, ib->name); +} + +static void ins__sort(void) +{ + const int nmemb = ARRAY_SIZE(instructions); + + qsort(instructions, nmemb, sizeof(struct ins), ins__cmp); +} + static struct ins *ins__find(const char *name) { const int nmemb = ARRAY_SIZE(instructions); + static bool sorted; + + if (!sorted) { + ins__sort(); + sorted = true; + } - return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp); + return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp); } int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym) -- cgit v1.2.3 From caa36ed7ba82caa9f685dd04aa10d0bf87ea8b6a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 19 May 2016 19:00:27 -0300 Subject: perf trace: Only auto set call-graph to "dwarf" when syscalls are being traced When --min-stack or --max-stack is passwd but --no-syscalls is also in effect, there is no point in automatically setting '--call-graph dwarf'. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-pq922i7h9wef0pho1dqpttvn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 7401de71d097..487c10401d46 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2910,7 +2910,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) } #ifdef HAVE_DWARF_UNWIND_SUPPORT - if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled) + if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls) record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false); #endif -- cgit v1.2.3 From a706670900073d236938d539d1109338d64b47bb Mon Sep 17 00:00:00 2001 From: He Kuang Date: Thu, 19 May 2016 11:47:37 +0000 Subject: perf tools: Set buildid dir under symfs when --symfs is provided This patch moves the reference of buildid dir to 'symfs/.debug' and skips the local buildid dir when '--symfs' is given, so that every single file opened by perf is relative to symfs directory now. Signed-off-by: He Kuang Acked-by: David Ahern Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ekaterina Tumanova Cc: Josh Poimboeuf Cc: Kan Liang Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Sukadev Bhattiprolu Cc: Wang Nan Link: http://lkml.kernel.org/r/1463658462-85131-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 5 +++-- tools/perf/builtin-diff.c | 5 +++-- tools/perf/builtin-report.c | 5 +++-- tools/perf/builtin-script.c | 5 +++-- tools/perf/builtin-timechart.c | 5 +++-- tools/perf/util/dso.c | 4 +--- tools/perf/util/symbol.c | 23 +++++++++++++++++++++++ tools/perf/util/symbol.h | 2 ++ 8 files changed, 41 insertions(+), 13 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 814158393656..25c81734a950 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -324,8 +324,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing, "Skip symbols that cannot be annotated"), OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"), - OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", - "Look for files with symbols relative to this directory"), + OPT_CALLBACK(0, "symfs", NULL, "directory", + "Look for files with symbols relative to this directory", + symbol__config_symfs), OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src, "Interleave source code with assembly code (default)"), OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 9ce354f469dc..f7645a42708e 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -812,8 +812,9 @@ static const struct option options[] = { OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator", "separator for columns, no spaces will be added between " "columns '.' is reserved."), - OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", - "Look for files with symbols relative to this directory"), + OPT_CALLBACK(0, "symfs", NULL, "directory", + "Look for files with symbols relative to this directory", + symbol__config_symfs), OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."), OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", "How to display percentage of filtered entries", parse_filter_percentage), diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 9bc71c6a54f6..a87cb338bdf1 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -770,8 +770,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "columns '.' is reserved."), OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved, "Only display entries resolved to a symbol"), - OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", - "Look for files with symbols relative to this directory"), + OPT_CALLBACK(0, "symfs", NULL, "directory", + "Look for files with symbols relative to this directory", + symbol__config_symfs), OPT_STRING('C', "cpu", &report.cpu_list, "cpu", "list of cpus to profile"), OPT_BOOLEAN('I', "show-info", &report.show_full_info, diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 0a83f4bacc7c..e3ce2f34d3ad 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2010,8 +2010,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "file", "kallsyms pathname"), OPT_BOOLEAN('G', "hide-call-graph", &no_callchain, "When printing symbols do not display call chain"), - OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", - "Look for files with symbols relative to this directory"), + OPT_CALLBACK(0, "symfs", NULL, "directory", + "Look for files with symbols relative to this directory", + symbol__config_symfs), OPT_CALLBACK('F', "fields", NULL, "str", "comma separated output fields prepend with 'type:'. " "Valid types: hw,sw,trace,raw. " diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 40cc9bb3506c..733a55422d03 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -1945,8 +1945,9 @@ int cmd_timechart(int argc, const char **argv, OPT_CALLBACK('p', "process", NULL, "process", "process selector. Pass a pid or process name.", parse_process), - OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", - "Look for files with symbols relative to this directory"), + OPT_CALLBACK(0, "symfs", NULL, "directory", + "Look for files with symbols relative to this directory", + symbol__config_symfs), OPT_INTEGER('n', "proc-num", &tchart.proc_num, "min. number of tasks to print"), OPT_BOOLEAN('t', "topology", &tchart.topology, diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 75b75615e2f8..5d286f5d7906 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -63,9 +63,7 @@ int dso__read_binary_type_filename(const struct dso *dso, } break; case DSO_BINARY_TYPE__BUILD_ID_CACHE: - /* skip the locally configured cache if a symfs is given */ - if (symbol_conf.symfs[0] || - (dso__build_id_filename(dso, filename, size) == NULL)) + if (dso__build_id_filename(dso, filename, size) == NULL) ret = -1; break; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 2252b545ff43..20f9cb32b703 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2033,3 +2033,26 @@ void symbol__exit(void) symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL; symbol_conf.initialized = false; } + +int symbol__config_symfs(const struct option *opt __maybe_unused, + const char *dir, int unset __maybe_unused) +{ + char *bf = NULL; + int ret; + + symbol_conf.symfs = strdup(dir); + if (symbol_conf.symfs == NULL) + return -ENOMEM; + + /* skip the locally configured cache if a symfs is given, and + * config buildid dir to symfs/.debug + */ + ret = asprintf(&bf, "%s/%s", dir, ".debug"); + if (ret < 0) + return -ENOMEM; + + set_buildid_dir(bf); + + free(bf); + return 0; +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 25f2fd672c2e..fa415347dbf9 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -290,6 +290,8 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type); bool symbol__restricted_filename(const char *filename, const char *restricted_filename); bool symbol__is_idle(struct symbol *sym); +int symbol__config_symfs(const struct option *opt __maybe_unused, + const char *dir, int unset __maybe_unused); int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, symbol_filter_t filter, -- cgit v1.2.3 From b90dc17a5d14a881f9bb3b58edb3d71075d58afb Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 20 May 2016 16:38:23 +0000 Subject: perf evsel: Add overwrite attribute and check write_backward Add 'overwrite' attribute to evsel to mark whether this event is overwritable. The following commits will support syntax like: # perf record -e cycles/overwrite/ ... An overwritable evsel requires kernel support for the perf_event_attr.write_backward ring buffer feature. Add it to perf_missing_feature. Signed-off-by: Wang Nan Cc: He Kuang Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1463762315-155689-2-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 13 +++++++++++++ tools/perf/util/evsel.h | 1 + 2 files changed, 14 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 964c7c3602c0..02c177d14c8d 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -37,6 +37,7 @@ static struct { bool clockid; bool clockid_wrong; bool lbr_flags; + bool write_backward; } perf_missing_features; static clockid_t clockid; @@ -1376,6 +1377,8 @@ fallback_missing_features: if (perf_missing_features.lbr_flags) evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | PERF_SAMPLE_BRANCH_NO_CYCLES); + if (perf_missing_features.write_backward) + evsel->attr.write_backward = false; retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; @@ -1438,6 +1441,12 @@ retry_open: err = -EINVAL; goto out_close; } + + if (evsel->overwrite && + perf_missing_features.write_backward) { + err = -EINVAL; + goto out_close; + } } } @@ -1500,6 +1509,10 @@ try_fallback: PERF_SAMPLE_BRANCH_NO_FLAGS))) { perf_missing_features.lbr_flags = true; goto fallback_missing_features; + } else if (!perf_missing_features.write_backward && + evsel->attr.write_backward) { + perf_missing_features.write_backward = true; + goto fallback_missing_features; } out_close: diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 8a644fef452c..c1f10159804c 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -112,6 +112,7 @@ struct perf_evsel { bool tracking; bool per_pkg; bool precise_max; + bool overwrite; /* parse modifier helper */ int exclude_GH; int nr_members; -- cgit v1.2.3 From d4c6fb36ac2c82f8f0c05b04cf102dcdc2d5a14d Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 20 May 2016 16:38:24 +0000 Subject: perf evsel: Record fd into perf_mmap Add a fd field into struct perf_mmap so that perf can track the mmap fd. This feature will be used for toggling overwrite ring buffers. Signed-off-by: Wang Nan Cc: He Kuang Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1463762315-155689-3-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 6 ++++++ tools/perf/util/evlist.h | 1 + 2 files changed, 7 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index c4bfe11479a0..1a370db02a8c 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -881,6 +881,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) if (evlist->mmap[idx].base != NULL) { munmap(evlist->mmap[idx].base, evlist->mmap_len); evlist->mmap[idx].base = NULL; + evlist->mmap[idx].fd = -1; atomic_set(&evlist->mmap[idx].refcnt, 0); } auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap); @@ -901,10 +902,14 @@ void perf_evlist__munmap(struct perf_evlist *evlist) static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) { + int i; + evlist->nr_mmaps = cpu_map__nr(evlist->cpus); if (cpu_map__empty(evlist->cpus)) evlist->nr_mmaps = thread_map__nr(evlist->threads); evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); + for (i = 0; i < evlist->nr_mmaps; i++) + evlist->mmap[i].fd = -1; return evlist->mmap != NULL ? 0 : -ENOMEM; } @@ -941,6 +946,7 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx, evlist->mmap[idx].base = NULL; return -1; } + evlist->mmap[idx].fd = fd; if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap, &mp->auxtrace_mp, evlist->mmap[idx].base, fd)) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 85d1b59802e8..0d165b1d8f77 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -28,6 +28,7 @@ struct record_opts; struct perf_mmap { void *base; int mask; + int fd; atomic_t refcnt; u64 prev; struct auxtrace_mmap auxtrace_mmap; -- cgit v1.2.3 From 508be0dfe6287d4e6452f5a1dc08856df74cb217 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 20 May 2016 13:15:08 -0700 Subject: perf report: Add srcline_from/to branch sort keys Add "srcline_from" and "srcline_to" branch sort keys that allow to show the source lines of a branch. That makes it much easier to track down where particular branches happen in the program, for example to examine branch mispredictions, or to associate it with cycle counts: % perf record -b -e cycles:p ./tcall % perf report --sort srcline_from,srcline_to,mispredict ... 15.10% tcall.c:18 tcall.c:10 N 14.83% tcall.c:11 tcall.c:5 N 14.12% tcall.c:7 tcall.c:12 N 14.04% tcall.c:12 tcall.c:5 N 12.42% tcall.c:17 tcall.c:18 N 12.39% tcall.c:7 tcall.c:13 N 12.27% tcall.c:13 tcall.c:17 N ... % perf report --sort srcline_from,srcline_to,cycles ... 17.12% tcall.c:18 tcall.c:11 1 17.01% tcall.c:12 tcall.c:6 1 16.98% tcall.c:11 tcall.c:6 1 15.91% tcall.c:17 tcall.c:18 1 6.38% tcall.c:7 tcall.c:17 7 4.80% tcall.c:7 tcall.c:12 8 4.21% tcall.c:7 tcall.c:17 8 2.67% tcall.c:7 tcall.c:12 7 2.62% tcall.c:7 tcall.c:12 10 2.10% tcall.c:7 tcall.c:17 9 1.58% tcall.c:7 tcall.c:12 6 1.44% tcall.c:7 tcall.c:12 5 1.38% tcall.c:7 tcall.c:12 9 1.06% tcall.c:7 tcall.c:17 13 1.05% tcall.c:7 tcall.c:12 4 1.01% tcall.c:7 tcall.c:17 6 Open issues: - Some kernel symbols get misresolved. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/1463775308-32748-1-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 3 +- tools/perf/util/hist.c | 9 ++++ tools/perf/util/hist.h | 2 + tools/perf/util/sort.c | 84 ++++++++++++++++++++++++++++++++ tools/perf/util/sort.h | 2 + tools/perf/util/symbol.h | 2 + 6 files changed, 101 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 496d42cdf02b..9cbddc290aff 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -103,12 +103,13 @@ OPTIONS If --branch-stack option is used, following sort keys are also available: - dso_from, dso_to, symbol_from, symbol_to, mispredict. - dso_from: name of library or module branched from - dso_to: name of library or module branched to - symbol_from: name of function branched from - symbol_to: name of function branched to + - srcline_from: source file and line branched from + - srcline_to: source file and line branched to - mispredict: "N" for predicted branch, "Y" for mispredicted branch - in_tx: branch in TSX transaction - abort: TSX transaction abort. diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index cfab531437c7..d1f19e0012d4 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -117,6 +117,13 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); hists__set_unres_dso_col_len(hists, HISTC_DSO_TO); } + + if (h->branch_info->srcline_from) + hists__new_col_len(hists, HISTC_SRCLINE_FROM, + strlen(h->branch_info->srcline_from)); + if (h->branch_info->srcline_to) + hists__new_col_len(hists, HISTC_SRCLINE_TO, + strlen(h->branch_info->srcline_to)); } if (h->mem_info) { @@ -1042,6 +1049,8 @@ void hist_entry__delete(struct hist_entry *he) if (he->branch_info) { map__zput(he->branch_info->from.map); map__zput(he->branch_info->to.map); + free_srcline(he->branch_info->srcline_from); + free_srcline(he->branch_info->srcline_to); zfree(&he->branch_info); } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 0f84bfb42bb1..7b54ccf1b737 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -52,6 +52,8 @@ enum hist_column { HISTC_MEM_IADDR_SYMBOL, HISTC_TRANSACTION, HISTC_CYCLES, + HISTC_SRCLINE_FROM, + HISTC_SRCLINE_TO, HISTC_TRACE, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 20e69edd5006..c4e9bd70723c 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -353,6 +353,88 @@ struct sort_entry sort_srcline = { .se_width_idx = HISTC_SRCLINE, }; +/* --sort srcline_from */ + +static int64_t +sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->branch_info->srcline_from) { + struct map *map = left->branch_info->from.map; + if (!map) + left->branch_info->srcline_from = SRCLINE_UNKNOWN; + else + left->branch_info->srcline_from = get_srcline(map->dso, + map__rip_2objdump(map, + left->branch_info->from.al_addr), + left->branch_info->from.sym, true); + } + if (!right->branch_info->srcline_from) { + struct map *map = right->branch_info->from.map; + if (!map) + right->branch_info->srcline_from = SRCLINE_UNKNOWN; + else + right->branch_info->srcline_from = get_srcline(map->dso, + map__rip_2objdump(map, + right->branch_info->from.al_addr), + right->branch_info->from.sym, true); + } + return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from); +} + +static int hist_entry__srcline_from_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_from); +} + +struct sort_entry sort_srcline_from = { + .se_header = "From Source:Line", + .se_cmp = sort__srcline_from_cmp, + .se_snprintf = hist_entry__srcline_from_snprintf, + .se_width_idx = HISTC_SRCLINE_FROM, +}; + +/* --sort srcline_to */ + +static int64_t +sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->branch_info->srcline_to) { + struct map *map = left->branch_info->to.map; + if (!map) + left->branch_info->srcline_to = SRCLINE_UNKNOWN; + else + left->branch_info->srcline_to = get_srcline(map->dso, + map__rip_2objdump(map, + left->branch_info->to.al_addr), + left->branch_info->from.sym, true); + } + if (!right->branch_info->srcline_to) { + struct map *map = right->branch_info->to.map; + if (!map) + right->branch_info->srcline_to = SRCLINE_UNKNOWN; + else + right->branch_info->srcline_to = get_srcline(map->dso, + map__rip_2objdump(map, + right->branch_info->to.al_addr), + right->branch_info->to.sym, true); + } + return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to); +} + +static int hist_entry__srcline_to_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_to); +} + +struct sort_entry sort_srcline_to = { + .se_header = "To Source:Line", + .se_cmp = sort__srcline_to_cmp, + .se_snprintf = hist_entry__srcline_to_snprintf, + .se_width_idx = HISTC_SRCLINE_TO, +}; + /* --sort srcfile */ static char no_srcfile[1]; @@ -1347,6 +1429,8 @@ static struct sort_dimension bstack_sort_dimensions[] = { DIM(SORT_IN_TX, "in_tx", sort_in_tx), DIM(SORT_ABORT, "abort", sort_abort), DIM(SORT_CYCLES, "cycles", sort_cycles), + DIM(SORT_SRCLINE_FROM, "srcline_from", sort_srcline_from), + DIM(SORT_SRCLINE_TO, "srcline_to", sort_srcline_to), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 42927f448bcb..ebb59cacd092 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -215,6 +215,8 @@ enum sort_type { SORT_ABORT, SORT_IN_TX, SORT_CYCLES, + SORT_SRCLINE_FROM, + SORT_SRCLINE_TO, /* memory mode specific sort keys */ __SORT_MEMORY_MODE, diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fa415347dbf9..b10d558a8803 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -186,6 +186,8 @@ struct branch_info { struct addr_map_symbol from; struct addr_map_symbol to; struct branch_flags flags; + char *srcline_from; + char *srcline_to; }; struct mem_info { -- cgit v1.2.3 From b6565c908ad7eb28dfdda9578ec5a074e080cedc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 23 May 2016 12:59:53 -0300 Subject: perf trace: Use the fd->name beautifier as default for "fd" args Noticed when the 'setsockopt' 'fd' arg wasn't being formatted via the SCA_FD beautifier, so just remove the setting of "fd" args to SCA_FD and do it when reading the syscall info, like we do for args of type "pid_t", i.e. "fd" as the name should be enough as the decision to use the SFA_FD beautifier. For odd cases we can just do it explicitely. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-0qissgetiuqmqyj4b6ancmpn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 132 +++++++++++++++++++-------------------------- 1 file changed, 54 insertions(+), 78 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 487c10401d46..181f69cd6a8e 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -595,65 +595,45 @@ static struct syscall_fmt { { .name = "connect", .errmsg = true, }, { .name = "creat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, - { .name = "dup", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "dup2", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "dup3", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "dup", .errmsg = true, }, + { .name = "dup2", .errmsg = true, }, + { .name = "dup3", .errmsg = true, }, { .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), }, { .name = "eventfd2", .errmsg = true, .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, }, { .name = "faccessat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ - [1] = SCA_FILENAME, /* filename */ }, }, - { .name = "fadvise64", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "fallocate", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "fchdir", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "fchmod", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [1] = SCA_FILENAME, /* filename */ }, }, + { .name = "fadvise64", .errmsg = true, }, + { .name = "fallocate", .errmsg = true, }, + { .name = "fchdir", .errmsg = true, }, + { .name = "fchmod", .errmsg = true, }, { .name = "fchmodat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ [1] = SCA_FILENAME, /* filename */ }, }, - { .name = "fchown", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchown", .errmsg = true, }, { .name = "fchownat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ [1] = SCA_FILENAME, /* filename */ }, }, { .name = "fcntl", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [1] = SCA_STRARRAY, /* cmd */ }, + .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ }, .arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, }, - { .name = "fdatasync", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fdatasync", .errmsg = true, }, { .name = "flock", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [1] = SCA_FLOCK, /* cmd */ }, }, - { .name = "fsetxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "fstat", .errmsg = true, .alias = "newfstat", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, }, + { .name = "fsetxattr", .errmsg = true, }, + { .name = "fstat", .errmsg = true, .alias = "newfstat", }, { .name = "fstatat", .errmsg = true, .alias = "newfstatat", - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ - [1] = SCA_FILENAME, /* filename */ }, }, - { .name = "fstatfs", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "fsync", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "ftruncate", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [1] = SCA_FILENAME, /* filename */ }, }, + { .name = "fstatfs", .errmsg = true, }, + { .name = "fsync", .errmsg = true, }, + { .name = "ftruncate", .errmsg = true, }, { .name = "futex", .errmsg = true, .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, }, { .name = "futimesat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ [1] = SCA_FILENAME, /* filename */ }, }, - { .name = "getdents", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "getdents64", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "getdents", .errmsg = true, }, + { .name = "getdents64", .errmsg = true, }, { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, { .name = "getpid", .errpid = true, }, { .name = "getpgid", .errpid = true, }, @@ -666,7 +646,7 @@ static struct syscall_fmt { { .name = "inotify_add_watch", .errmsg = true, .arg_scnprintf = { [1] = SCA_FILENAME, /* pathname */ }, }, { .name = "ioctl", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ + .arg_scnprintf = { #if defined(__i386__) || defined(__x86_64__) /* * FIXME: Make this available to all arches. @@ -693,8 +673,7 @@ static struct syscall_fmt { { .name = "lremovexattr", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, { .name = "lseek", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [2] = SCA_STRARRAY, /* whence */ }, + .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ }, .arg_parm = { [2] = &strarray__whences, /* whence */ }, }, { .name = "lsetxattr", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, @@ -722,8 +701,7 @@ static struct syscall_fmt { { .name = "mmap", .hexret = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ [2] = SCA_MMAP_PROT, /* prot */ - [3] = SCA_MMAP_FLAGS, /* flags */ - [4] = SCA_FD, /* fd */ }, }, + [3] = SCA_MMAP_FLAGS, /* flags */ }, }, { .name = "mprotect", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* start */ [2] = SCA_MMAP_PROT, /* prot */ }, }, @@ -760,33 +738,24 @@ static struct syscall_fmt { .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, }, { .name = "poll", .errmsg = true, .timeout = true, }, { .name = "ppoll", .errmsg = true, .timeout = true, }, - { .name = "pread", .errmsg = true, .alias = "pread64", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "preadv", .errmsg = true, .alias = "pread", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "pread", .errmsg = true, .alias = "pread64", }, + { .name = "preadv", .errmsg = true, .alias = "pread", }, { .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), }, - { .name = "pwrite", .errmsg = true, .alias = "pwrite64", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "pwritev", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "read", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "pwrite", .errmsg = true, .alias = "pwrite64", }, + { .name = "pwritev", .errmsg = true, }, + { .name = "read", .errmsg = true, }, { .name = "readlink", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, }, { .name = "readlinkat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ [1] = SCA_FILENAME, /* pathname */ }, }, - { .name = "readv", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "readv", .errmsg = true, }, { .name = "recvfrom", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [3] = SCA_MSG_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "recvmmsg", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [3] = SCA_MSG_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "recvmsg", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [2] = SCA_MSG_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "removexattr", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, { .name = "renameat", .errmsg = true, @@ -807,22 +776,18 @@ static struct syscall_fmt { [1] = SCA_SECCOMP_FLAGS, /* flags */ }, }, { .name = "select", .errmsg = true, .timeout = true, }, { .name = "sendmmsg", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [3] = SCA_MSG_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "sendmsg", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [2] = SCA_MSG_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "sendto", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ - [3] = SCA_MSG_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "set_tid_address", .errpid = true, }, { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), }, { .name = "setpgid", .errmsg = true, }, { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "setxattr", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, - { .name = "shutdown", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "shutdown", .errmsg = true, }, { .name = "socket", .errmsg = true, .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ [1] = SCA_SK_TYPE, /* type */ }, @@ -858,16 +823,13 @@ static struct syscall_fmt { [1] = SCA_FILENAME, /* filename */ }, }, { .name = "utimes", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, - { .name = "vmsplice", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "vmsplice", .errmsg = true, }, { .name = "wait4", .errpid = true, .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, }, { .name = "waitid", .errpid = true, .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, }, - { .name = "write", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, - { .name = "writev", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "write", .errmsg = true, }, + { .name = "writev", .errmsg = true, }, }; static int syscall_fmt__cmp(const void *name, const void *fmtp) @@ -1204,7 +1166,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) static int syscall__set_arg_fmts(struct syscall *sc) { struct format_field *field; - int idx = 0; + int idx = 0, len; sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *)); if (sc->arg_scnprintf == NULL) @@ -1222,6 +1184,20 @@ static int syscall__set_arg_fmts(struct syscall *sc) sc->arg_scnprintf[idx] = SCA_PID; else if (strcmp(field->type, "umode_t") == 0) sc->arg_scnprintf[idx] = SCA_MODE_T; + else if ((strcmp(field->type, "int") == 0 || + strcmp(field->type, "unsigned int") == 0 || + strcmp(field->type, "long") == 0) && + (len = strlen(field->name)) >= 2 && + strcmp(field->name + len - 2, "fd") == 0) { + /* + * /sys/kernel/tracing/events/syscalls/sys_enter* + * egrep 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c + * 65 int + * 23 unsigned int + * 7 unsigned long + */ + sc->arg_scnprintf[idx] = SCA_FD; + } ++idx; } -- cgit v1.2.3 From 12f3ca4fc8e27aa602c9c3c717d755b1e8f7fd47 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 23 May 2016 16:37:55 -0300 Subject: perf trace: Use the ptr->name beautifier as default for "filename" args Auto-attach the ptr->name beautifier to syscall args "filename", "path" and "pathname" if they are of type "const char *". Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-jxii4qmcgoppftv0zdvml9d7@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 120 ++++++++++++++++----------------------------- 1 file changed, 43 insertions(+), 77 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 181f69cd6a8e..5c50fe70d6b3 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -576,44 +576,36 @@ static struct syscall_fmt { bool hexret; } syscall_fmts[] = { { .name = "access", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ - [1] = SCA_ACCMODE, /* mode */ }, }, + .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, }, { .name = "arch_prctl", .errmsg = true, .alias = "prctl", }, { .name = "bpf", .errmsg = true, STRARRAY(0, cmd, bpf_cmd), }, { .name = "brk", .hexret = true, .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, }, - { .name = "chdir", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, - { .name = "chmod", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, - { .name = "chroot", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, + { .name = "chdir", .errmsg = true, }, + { .name = "chmod", .errmsg = true, }, + { .name = "chroot", .errmsg = true, }, { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), }, { .name = "clone", .errpid = true, }, { .name = "close", .errmsg = true, .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, { .name = "connect", .errmsg = true, }, - { .name = "creat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "creat", .errmsg = true, }, { .name = "dup", .errmsg = true, }, { .name = "dup2", .errmsg = true, }, { .name = "dup3", .errmsg = true, }, { .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), }, { .name = "eventfd2", .errmsg = true, .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, }, - { .name = "faccessat", .errmsg = true, - .arg_scnprintf = { [1] = SCA_FILENAME, /* filename */ }, }, + { .name = "faccessat", .errmsg = true, }, { .name = "fadvise64", .errmsg = true, }, { .name = "fallocate", .errmsg = true, }, { .name = "fchdir", .errmsg = true, }, { .name = "fchmod", .errmsg = true, }, { .name = "fchmodat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ - [1] = SCA_FILENAME, /* filename */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "fchown", .errmsg = true, }, { .name = "fchownat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ - [1] = SCA_FILENAME, /* filename */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "fcntl", .errmsg = true, .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ }, .arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, }, @@ -622,16 +614,14 @@ static struct syscall_fmt { .arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, }, { .name = "fsetxattr", .errmsg = true, }, { .name = "fstat", .errmsg = true, .alias = "newfstat", }, - { .name = "fstatat", .errmsg = true, .alias = "newfstatat", - .arg_scnprintf = { [1] = SCA_FILENAME, /* filename */ }, }, + { .name = "fstatat", .errmsg = true, .alias = "newfstatat", }, { .name = "fstatfs", .errmsg = true, }, { .name = "fsync", .errmsg = true, }, { .name = "ftruncate", .errmsg = true, }, { .name = "futex", .errmsg = true, .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, }, { .name = "futimesat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ - [1] = SCA_FILENAME, /* filename */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "getdents", .errmsg = true, }, { .name = "getdents64", .errmsg = true, }, { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, @@ -641,10 +631,8 @@ static struct syscall_fmt { { .name = "getrandom", .errmsg = true, .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, }, { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, - { .name = "getxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, - { .name = "inotify_add_watch", .errmsg = true, - .arg_scnprintf = { [1] = SCA_FILENAME, /* pathname */ }, }, + { .name = "getxattr", .errmsg = true, }, + { .name = "inotify_add_watch", .errmsg = true, }, { .name = "ioctl", .errmsg = true, .arg_scnprintf = { #if defined(__i386__) || defined(__x86_64__) @@ -660,40 +648,28 @@ static struct syscall_fmt { { .name = "keyctl", .errmsg = true, STRARRAY(0, option, keyctl_options), }, { .name = "kill", .errmsg = true, .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, - { .name = "lchown", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, - { .name = "lgetxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "lchown", .errmsg = true, }, + { .name = "lgetxattr", .errmsg = true, }, { .name = "linkat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, - { .name = "listxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, - { .name = "llistxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, - { .name = "lremovexattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "listxattr", .errmsg = true, }, + { .name = "llistxattr", .errmsg = true, }, + { .name = "lremovexattr", .errmsg = true, }, { .name = "lseek", .errmsg = true, .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ }, .arg_parm = { [2] = &strarray__whences, /* whence */ }, }, - { .name = "lsetxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, - { .name = "lstat", .errmsg = true, .alias = "newlstat", - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, - { .name = "lsxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "lsetxattr", .errmsg = true, }, + { .name = "lstat", .errmsg = true, .alias = "newlstat", }, + { .name = "lsxattr", .errmsg = true, }, { .name = "madvise", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* start */ [2] = SCA_MADV_BHV, /* behavior */ }, }, - { .name = "mkdir", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "mkdir", .errmsg = true, }, { .name = "mkdirat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ - [1] = SCA_FILENAME, /* pathname */ }, }, - { .name = "mknod", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "mknod", .errmsg = true, }, { .name = "mknodat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ - [1] = SCA_FILENAME, /* filename */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "mlock", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "mlockall", .errmsg = true, @@ -718,17 +694,14 @@ static struct syscall_fmt { { .name = "name_to_handle_at", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "newfstatat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ - [1] = SCA_FILENAME, /* filename */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "open", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ - [1] = SCA_OPEN_FLAGS, /* flags */ }, }, + .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, }, { .name = "open_by_handle_at", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ [2] = SCA_OPEN_FLAGS, /* flags */ }, }, { .name = "openat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ - [1] = SCA_FILENAME, /* filename */ [2] = SCA_OPEN_FLAGS, /* flags */ }, }, { .name = "perf_event_open", .errmsg = true, .arg_scnprintf = { [2] = SCA_INT, /* cpu */ @@ -744,11 +717,9 @@ static struct syscall_fmt { { .name = "pwrite", .errmsg = true, .alias = "pwrite64", }, { .name = "pwritev", .errmsg = true, }, { .name = "read", .errmsg = true, }, - { .name = "readlink", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, }, + { .name = "readlink", .errmsg = true, }, { .name = "readlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ - [1] = SCA_FILENAME, /* pathname */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "readv", .errmsg = true, }, { .name = "recvfrom", .errmsg = true, .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, @@ -756,12 +727,10 @@ static struct syscall_fmt { .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "recvmsg", .errmsg = true, .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, - { .name = "removexattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "removexattr", .errmsg = true, }, { .name = "renameat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, - { .name = "rmdir", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "rmdir", .errmsg = true, }, { .name = "rt_sigaction", .errmsg = true, .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, }, { .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), }, @@ -785,8 +754,7 @@ static struct syscall_fmt { { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), }, { .name = "setpgid", .errmsg = true, }, { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, - { .name = "setxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "setxattr", .errmsg = true, }, { .name = "shutdown", .errmsg = true, }, { .name = "socket", .errmsg = true, .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ @@ -796,10 +764,8 @@ static struct syscall_fmt { .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ [1] = SCA_SK_TYPE, /* type */ }, .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, - { .name = "stat", .errmsg = true, .alias = "newstat", - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, - { .name = "statfs", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, + { .name = "stat", .errmsg = true, .alias = "newstat", }, + { .name = "statfs", .errmsg = true, }, { .name = "swapoff", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, }, { .name = "swapon", .errmsg = true, @@ -810,19 +776,14 @@ static struct syscall_fmt { .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, { .name = "tkill", .errmsg = true, .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, - { .name = "truncate", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* path */ }, }, + { .name = "truncate", .errmsg = true, }, { .name = "uname", .errmsg = true, .alias = "newuname", }, { .name = "unlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ - [1] = SCA_FILENAME, /* pathname */ }, }, - { .name = "utime", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "utime", .errmsg = true, }, { .name = "utimensat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ - [1] = SCA_FILENAME, /* filename */ }, }, - { .name = "utimes", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, }, + { .name = "utimes", .errmsg = true, }, { .name = "vmsplice", .errmsg = true, }, { .name = "wait4", .errpid = true, .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, }, @@ -1178,6 +1139,11 @@ static int syscall__set_arg_fmts(struct syscall *sc) for (field = sc->args; field; field = field->next) { if (sc->fmt && sc->fmt->arg_scnprintf[idx]) sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx]; + else if (strcmp(field->type, "const char *") == 0 && + (strcmp(field->name, "filename") == 0 || + strcmp(field->name, "path") == 0 || + strcmp(field->name, "pathname") == 0)) + sc->arg_scnprintf[idx] = SCA_FILENAME; else if (field->flags & FIELD_IS_POINTER) sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex; else if (strcmp(field->type, "pid_t") == 0) -- cgit v1.2.3 From 65aea2338765da1a58cc26eeb84d72308492ecb5 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 23 May 2016 07:13:38 +0000 Subject: perf evlist: Add API to pause/resume perf_evlist__toggle_{pause,resume}() are introduced to pause/resume events in an evlist. Utilize PERF_EVENT_IOC_PAUSE_OUTPUT ioctl. Following commits use them to ensure overwrite ring buffer is paused before reading. Signed-off-by: Wang Nan Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1463987628-163563-2-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang [ Return -1, like all other ioctl() usage in evlist.c, rename 'pause' arg to avoid breaking the build on ubuntu 12.04 and other old systems ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 27 +++++++++++++++++++++++++++ tools/perf/util/evlist.h | 2 ++ 2 files changed, 29 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 1a370db02a8c..904523a2be90 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -679,6 +679,33 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, return NULL; } +static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value) +{ + int i; + + for (i = 0; i < evlist->nr_mmaps; i++) { + int fd = evlist->mmap[i].fd; + int err; + + if (fd < 0) + continue; + err = ioctl(fd, PERF_EVENT_IOC_PAUSE_OUTPUT, value ? 1 : 0); + if (err) + return err; + } + return 0; +} + +int perf_evlist__pause(struct perf_evlist *evlist) +{ + return perf_evlist__set_paused(evlist, true); +} + +int perf_evlist__resume(struct perf_evlist *evlist) +{ + return perf_evlist__set_paused(evlist, false); +} + /* When check_messup is true, 'end' must points to a good entry */ static union perf_event * perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start, diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 0d165b1d8f77..97090b70976d 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -136,6 +136,8 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx); void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); +int perf_evlist__pause(struct perf_evlist *evlist); +int perf_evlist__resume(struct perf_evlist *evlist); int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); -- cgit v1.2.3 From 2d11c65071d489e20b3a811167507939dd8c2eac Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 23 May 2016 07:13:39 +0000 Subject: perf record: Prevent reading invalid data in record__mmap_read When record__mmap_read() requires data more than the size of ring buffer, drop those data to avoid accessing invalid memory. This can happen when reading from overwritable ring buffer, which should be avoided. However, check this for robustness. Signed-off-by: Wang Nan Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1463987628-163563-3-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f3679c44d3f3..f302cc937ca5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -40,6 +40,7 @@ #include #include #include +#include struct record { @@ -98,6 +99,13 @@ static int record__mmap_read(struct record *rec, int idx) rec->samples++; size = head - old; + if (size > (unsigned long)(md->mask) + 1) { + WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); + + md->prev = head; + perf_evlist__mmap_consume(rec->evlist, idx); + return 0; + } if ((old & md->mask) + size != (head & md->mask)) { buf = &data[old & md->mask]; -- cgit v1.2.3 From 09fa4f401296f555afb6f2f4282717644d94722e Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 23 May 2016 07:13:40 +0000 Subject: perf record: Rename variable to make code clear record__mmap_read() writes data from ring buffer into perf.data. 'head' is maintained by the kernel, points to the last written record. 'old' is maintained by perf, points to the record read in previous round. record__mmap_read() saves data from 'old' to 'head' to perf.data. The names of these variables are not very intutive. In addition, when dealing with backward writing ring buffer, the md->prev pointer should point to 'head' instead of the last byte it got. Add 'start' and 'end' pointer to make code clear and set md->prev to 'head' instead of the moved 'old' pointer. This patch doesn't change behavior since: buf = &data[old & md->mask]; size = head - old; old += size; <--- Here, old == head Signed-off-by: Wang Nan Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1463987628-163563-4-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f302cc937ca5..73ce651c84f6 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -88,17 +88,18 @@ static int record__mmap_read(struct record *rec, int idx) struct perf_mmap *md = &rec->evlist->mmap[idx]; u64 head = perf_mmap__read_head(md); u64 old = md->prev; + u64 end = head, start = old; unsigned char *data = md->base + page_size; unsigned long size; void *buf; int rc = 0; - if (old == head) + if (start == end) return 0; rec->samples++; - size = head - old; + size = end - start; if (size > (unsigned long)(md->mask) + 1) { WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); @@ -107,10 +108,10 @@ static int record__mmap_read(struct record *rec, int idx) return 0; } - if ((old & md->mask) + size != (head & md->mask)) { - buf = &data[old & md->mask]; - size = md->mask + 1 - (old & md->mask); - old += size; + if ((start & md->mask) + size != (end & md->mask)) { + buf = &data[start & md->mask]; + size = md->mask + 1 - (start & md->mask); + start += size; if (record__write(rec, buf, size) < 0) { rc = -1; @@ -118,16 +119,16 @@ static int record__mmap_read(struct record *rec, int idx) } } - buf = &data[old & md->mask]; - size = head - old; - old += size; + buf = &data[start & md->mask]; + size = end - start; + start += size; if (record__write(rec, buf, size) < 0) { rc = -1; goto out; } - md->prev = old; + md->prev = head; perf_evlist__mmap_consume(rec->evlist, idx); out: return rc; -- cgit v1.2.3 From 3a62a7b8200a177ad96161e4f2678514e6ee301e Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 23 May 2016 07:13:41 +0000 Subject: perf record: Read from backward ring buffer Introduce rb_find_range() to find start and end position from a backward ring buffer. Signed-off-by: Wang Nan Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1463987628-163563-5-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 52 +++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/evlist.c | 1 + tools/perf/util/evlist.h | 1 + 3 files changed, 54 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 73ce651c84f6..dc3fcb597e4c 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -83,6 +83,54 @@ static int process_synthesized_event(struct perf_tool *tool, return record__write(rec, event, event->header.size); } +static int +backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end) +{ + struct perf_event_header *pheader; + u64 evt_head = head; + int size = mask + 1; + + pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head); + pheader = (struct perf_event_header *)(buf + (head & mask)); + *start = head; + while (true) { + if (evt_head - head >= (unsigned int)size) { + pr_debug("Finshed reading backward ring buffer: rewind\n"); + if (evt_head - head > (unsigned int)size) + evt_head -= pheader->size; + *end = evt_head; + return 0; + } + + pheader = (struct perf_event_header *)(buf + (evt_head & mask)); + + if (pheader->size == 0) { + pr_debug("Finshed reading backward ring buffer: get start\n"); + *end = evt_head; + return 0; + } + + evt_head += pheader->size; + pr_debug3("move evt_head: %"PRIx64"\n", evt_head); + } + WARN_ONCE(1, "Shouldn't get here\n"); + return -1; +} + +static int +rb_find_range(struct perf_evlist *evlist, + void *data, int mask, u64 head, u64 old, + u64 *start, u64 *end) +{ + if (!evlist->backward) { + *start = old; + *end = head; + return 0; + } + + return backward_rb_find_range(data, mask, head, start, end); +} + static int record__mmap_read(struct record *rec, int idx) { struct perf_mmap *md = &rec->evlist->mmap[idx]; @@ -94,6 +142,10 @@ static int record__mmap_read(struct record *rec, int idx) void *buf; int rc = 0; + if (rb_find_range(rec->evlist, data, md->mask, head, + old, &start, &end)) + return -1; + if (start == end) return 0; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 904523a2be90..e82ba90cc969 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -44,6 +44,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, perf_evlist__set_maps(evlist, cpus, threads); fdarray__init(&evlist->pollfd, 64); evlist->workload.pid = -1; + evlist->backward = false; } struct perf_evlist *perf_evlist__new(void) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 97090b70976d..d740fb877ab6 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -44,6 +44,7 @@ struct perf_evlist { bool overwrite; bool enabled; bool has_user_cpus; + bool backward; size_t mmap_len; int id_pos; int is_pos; -- cgit v1.2.3