diff options
author | Ingo Molnar <mingo@kernel.org> | 2014-06-12 13:53:16 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2014-06-12 13:53:16 +0200 |
commit | 94eb153130ce2c5f5f4959c96ea8197475bd66b6 (patch) | |
tree | 452c7fd4bd5d494d8b170fd5e840a5ae004e65ba /tools/perf | |
parent | 82b897782d10fcc4930c9d4a15b175348fdd2871 (diff) | |
parent | 9b32ba71ba905b90610fc2aad77cb98a373c5624 (diff) | |
download | op-kernel-dev-94eb153130ce2c5f5f4959c96ea8197475bd66b6.zip op-kernel-dev-94eb153130ce2c5f5f4959c96ea8197475bd66b6.tar.gz |
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf into perf/core
Pull perf/core improvements and fixes from Jiri Olsa:
* Bitmask handling and plugin updates (Steven Rostedt)
* Fix pipe check regression in attr event callback (Jiri Olsa)
* Prettify the tags/TAGS/cscope targets output (Jiri Olsa)
* Print array argument as string (Namhyung Kim)
* Pass protection and flags bits through mmap2 interface (Peter Zijlstra)
* Update perf tool mmap2 interface with protection and flag bits (Don Zickus)
* Re-enable mmap interface (Don Zickus)
* Add mem-mode documentation to report command (Don Zickus)
* Add sort on dcacheline (Don Zickus)
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'tools/perf')
-rw-r--r-- | tools/perf/Documentation/perf-report.txt | 23 | ||||
-rw-r--r-- | tools/perf/Makefile.perf | 6 | ||||
-rw-r--r-- | tools/perf/builtin-inject.c | 2 | ||||
-rw-r--r-- | tools/perf/perf.c | 1 | ||||
-rw-r--r-- | tools/perf/tests/dwarf-unwind.c | 2 | ||||
-rw-r--r-- | tools/perf/util/event.c | 57 | ||||
-rw-r--r-- | tools/perf/util/event.h | 2 | ||||
-rw-r--r-- | tools/perf/util/evsel.c | 1 | ||||
-rw-r--r-- | tools/perf/util/hist.c | 9 | ||||
-rw-r--r-- | tools/perf/util/hist.h | 1 | ||||
-rw-r--r-- | tools/perf/util/machine.c | 4 | ||||
-rw-r--r-- | tools/perf/util/map.c | 4 | ||||
-rw-r--r-- | tools/perf/util/map.h | 4 | ||||
-rw-r--r-- | tools/perf/util/scripting-engines/trace-event-perl.c | 1 | ||||
-rw-r--r-- | tools/perf/util/scripting-engines/trace-event-python.c | 2 | ||||
-rw-r--r-- | tools/perf/util/sort.c | 107 | ||||
-rw-r--r-- | tools/perf/util/sort.h | 2 | ||||
-rw-r--r-- | tools/perf/util/util.c | 1 | ||||
-rw-r--r-- | tools/perf/util/util.h | 1 |
19 files changed, 203 insertions, 27 deletions
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index cefdf43..d2b59af 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -117,6 +117,22 @@ OPTIONS By default, every sort keys not specified in -F will be appended automatically. + If --mem-mode option is used, following sort keys are also available + (incompatible with --branch-stack): + symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline. + + - symbol_daddr: name of data symbol being executed on at the time of sample + - dso_daddr: name of library or module containing the data being executed + on at the time of sample + - locked: whether the bus was locked at the time of sample + - tlb: type of tlb access for the data at the time of sample + - mem: type of memory access for the data at the time of sample + - snoop: type of snoop (if any) for the data at the time of sample + - dcacheline: the cacheline the data address is on at the time of sample + + And default sort keys are changed to local_weight, mem, sym, dso, + symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. + -p:: --parent=<regex>:: A regex filter to identify parent. The parent is a caller of this @@ -260,6 +276,13 @@ OPTIONS Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle. +--mem-mode:: + Use the data addresses of samples in addition to instruction addresses + to build the histograms. To generate meaningful output, the perf.data + file must have been obtained using perf record -d -W and using a + special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See + 'perf mem' for simpler access. + --percent-limit:: Do not show entries which have an overhead under that percent. (Default: 0). diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index ae20edf..9670a16 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -819,15 +819,15 @@ TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol TAG_FILES= ../../include/uapi/linux/perf_event.h TAGS: - $(RM) TAGS + $(QUIET_GEN)$(RM) TAGS; \ $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES) tags: - $(RM) tags + $(QUIET_GEN)$(RM) tags; \ $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES) cscope: - $(RM) cscope* + $(QUIET_GEN)$(RM) cscope*; \ $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES) ### Detect prefix changes diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 6a3af00..16c7c11 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -72,7 +72,7 @@ static int perf_event__repipe_attr(struct perf_tool *tool, if (ret) return ret; - if (&inject->output.is_pipe) + if (!inject->output.is_pipe) return 0; return perf_event__repipe_synth(tool, event); diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 78f7b92..95c58fc 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -458,6 +458,7 @@ int main(int argc, const char **argv) /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); + cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE); cmd = perf_extract_argv0_path(argv[0]); if (!cmd) diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 108f0cd..96adb73 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -15,7 +15,7 @@ static int mmap_handler(struct perf_tool *tool __maybe_unused, struct perf_sample *sample __maybe_unused, struct machine *machine) { - return machine__process_mmap_event(machine, event, NULL); + return machine__process_mmap2_event(machine, event, NULL); } static int init_live_machine(struct machine *machine) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 65795b8..d0281bd 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,4 +1,5 @@ #include <linux/types.h> +#include <sys/mman.h> #include "event.h" #include "debug.h" #include "hist.h" @@ -178,13 +179,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, return -1; } - event->header.type = PERF_RECORD_MMAP; + event->header.type = PERF_RECORD_MMAP2; while (1) { char bf[BUFSIZ]; char prot[5]; char execname[PATH_MAX]; char anonstr[] = "//anon"; + unsigned int ino; size_t size; ssize_t n; @@ -195,15 +197,20 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", - &event->mmap.start, &event->mmap.len, prot, - &event->mmap.pgoff, - execname); + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n", + &event->mmap2.start, &event->mmap2.len, prot, + &event->mmap2.pgoff, &event->mmap2.maj, + &event->mmap2.min, + &ino, execname); + /* * Anon maps don't have the execname. */ - if (n < 4) + if (n < 7) continue; + + event->mmap2.ino = (u64)ino; + /* * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c */ @@ -212,6 +219,21 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, else event->header.misc = PERF_RECORD_MISC_GUEST_USER; + /* map protection and flags bits */ + event->mmap2.prot = 0; + event->mmap2.flags = 0; + if (prot[0] == 'r') + event->mmap2.prot |= PROT_READ; + if (prot[1] == 'w') + event->mmap2.prot |= PROT_WRITE; + if (prot[2] == 'x') + event->mmap2.prot |= PROT_EXEC; + + if (prot[3] == 's') + event->mmap2.flags |= MAP_SHARED; + else + event->mmap2.flags |= MAP_PRIVATE; + if (prot[2] != 'x') { if (!mmap_data || prot[0] != 'r') continue; @@ -223,15 +245,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, anonstr); size = strlen(execname) + 1; - memcpy(event->mmap.filename, execname, size); + memcpy(event->mmap2.filename, execname, size); size = PERF_ALIGN(size, sizeof(u64)); - event->mmap.len -= event->mmap.start; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, machine->id_hdr_size); - event->mmap.header.size += machine->id_hdr_size; - event->mmap.pid = tgid; - event->mmap.tid = pid; + event->mmap2.len -= event->mmap.start; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + event->mmap2.header.size += machine->id_hdr_size; + event->mmap2.pid = tgid; + event->mmap2.tid = pid; if (process(tool, event, &synth_sample, machine) != 0) { rc = -1; @@ -612,12 +634,15 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) { return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 - " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n", + " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n", event->mmap2.pid, event->mmap2.tid, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, - (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x', + (event->mmap2.prot & PROT_READ) ? 'r' : '-', + (event->mmap2.prot & PROT_WRITE) ? 'w' : '-', + (event->mmap2.prot & PROT_EXEC) ? 'x' : '-', + (event->mmap2.flags & MAP_SHARED) ? 's' : 'p', event->mmap2.filename); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index d970232..9ba2eb3 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -27,6 +27,8 @@ struct mmap2_event { u32 min; u64 ino; u64 ino_generation; + u32 prot; + u32 flags; char filename[PATH_MAX]; }; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 5c28d82..21154da 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -659,6 +659,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) perf_evsel__set_sample_bit(evsel, WEIGHT); attr->mmap = track; + attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; if (opts->sample_transaction) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 5a0a4b2..30df618 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -128,6 +128,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) + unresolved_col_width + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); + hists__new_col_len(hists, HISTC_MEM_DCACHELINE, + symlen + 1); } else { symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, @@ -439,9 +441,10 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .map = al->map, .sym = al->sym, }, - .cpu = al->cpu, - .ip = al->addr, - .level = al->level, + .cpu = al->cpu, + .cpumode = al->cpumode, + .ip = al->addr, + .level = al->level, .stat = { .nr_events = 1, .period = period, diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index d2bf035..742f49a 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -72,6 +72,7 @@ enum hist_column { HISTC_MEM_TLB, HISTC_MEM_LVL, HISTC_MEM_SNOOP, + HISTC_MEM_DCACHELINE, HISTC_TRANSACTION, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 7409ac8..0e5fea9 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1060,6 +1060,8 @@ int machine__process_mmap2_event(struct machine *machine, event->mmap2.pid, event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, + event->mmap2.prot, + event->mmap2.flags, event->mmap2.filename, type); if (map == NULL) @@ -1105,7 +1107,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event map = map__new(&machine->user_dsos, event->mmap.start, event->mmap.len, event->mmap.pgoff, - event->mmap.pid, 0, 0, 0, 0, + event->mmap.pid, 0, 0, 0, 0, 0, 0, event->mmap.filename, type); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8ccbb32..25c571f 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -138,7 +138,7 @@ void map__init(struct map *map, enum map_type type, struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, char *filename, + u64 ino_gen, u32 prot, u32 flags, char *filename, enum map_type type) { struct map *map = malloc(sizeof(*map)); @@ -157,6 +157,8 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, map->min = d_min; map->ino = ino; map->ino_generation = ino_gen; + map->prot = prot; + map->flags = flags; if ((anon || no_dso) && type == MAP__FUNCTION) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index ae2d451..7758c72 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -35,6 +35,8 @@ struct map { bool referenced; bool erange_warned; u32 priv; + u32 prot; + u32 flags; u64 pgoff; u64 reloc; u32 maj, min; /* only valid for MMAP2 record */ @@ -118,7 +120,7 @@ void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, - u64 ino_gen, + u64 ino_gen, u32 prot, u32 flags, char *filename, enum map_type type); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); void map__delete(struct map *map); diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index e108207..af7da56 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -215,6 +215,7 @@ static void define_event_symbols(struct event_format *event, case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_STRING: + case PRINT_BITMASK: break; case PRINT_TYPE: define_event_symbols(event, ev_name, args->typecast.item); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index cd9774d..1c41932 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -197,6 +197,7 @@ static void define_event_symbols(struct event_format *event, case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_FUNC: + case PRINT_BITMASK: /* we should warn... */ return; } @@ -622,6 +623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s=", f->name); if (f->flags & FIELD_IS_STRING || f->flags & FIELD_IS_FLAG || + f->flags & FIELD_IS_ARRAY || f->flags & FIELD_IS_SYMBOLIC) fprintf(ofp, "%%s"); else if (f->flags & FIELD_IS_SIGNED) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 45512ba..1ec57dd 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,3 +1,4 @@ +#include <sys/mman.h> #include "sort.h" #include "hist.h" #include "comm.h" @@ -784,6 +785,104 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*s", width, out); } +static inline u64 cl_address(u64 address) +{ + /* return the cacheline of the address */ + return (address & ~(cacheline_size - 1)); +} + +static int64_t +sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) +{ + u64 l, r; + struct map *l_map, *r_map; + + if (!left->mem_info) return -1; + if (!right->mem_info) return 1; + + /* group event types together */ + if (left->cpumode > right->cpumode) return -1; + if (left->cpumode < right->cpumode) return 1; + + l_map = left->mem_info->daddr.map; + r_map = right->mem_info->daddr.map; + + /* if both are NULL, jump to sort on al_addr instead */ + if (!l_map && !r_map) + goto addr; + + if (!l_map) return -1; + if (!r_map) return 1; + + if (l_map->maj > r_map->maj) return -1; + if (l_map->maj < r_map->maj) return 1; + + if (l_map->min > r_map->min) return -1; + if (l_map->min < r_map->min) return 1; + + if (l_map->ino > r_map->ino) return -1; + if (l_map->ino < r_map->ino) return 1; + + if (l_map->ino_generation > r_map->ino_generation) return -1; + if (l_map->ino_generation < r_map->ino_generation) return 1; + + /* + * Addresses with no major/minor numbers are assumed to be + * anonymous in userspace. Sort those on pid then address. + * + * The kernel and non-zero major/minor mapped areas are + * assumed to be unity mapped. Sort those on address. + */ + + if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && + (!(l_map->flags & MAP_SHARED)) && + !l_map->maj && !l_map->min && !l_map->ino && + !l_map->ino_generation) { + /* userspace anonymous */ + + if (left->thread->pid_ > right->thread->pid_) return -1; + if (left->thread->pid_ < right->thread->pid_) return 1; + } + +addr: + /* al_addr does all the right addr - start + offset calculations */ + l = cl_address(left->mem_info->daddr.al_addr); + r = cl_address(right->mem_info->daddr.al_addr); + + if (l > r) return -1; + if (l < r) return 1; + + return 0; +} + +static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + + uint64_t addr = 0; + struct map *map = NULL; + struct symbol *sym = NULL; + char level = he->level; + + if (he->mem_info) { + addr = cl_address(he->mem_info->daddr.al_addr); + map = he->mem_info->daddr.map; + sym = he->mem_info->daddr.sym; + + /* print [s] for shared data mmaps */ + if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && + map && (map->type == MAP__VARIABLE) && + (map->flags & MAP_SHARED) && + (map->maj || map->min || map->ino || + map->ino_generation)) + level = 's'; + else if (!map) + level = 'X'; + } + return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size, + width); +} + struct sort_entry sort_mispredict = { .se_header = "Branch Mispredicted", .se_cmp = sort__mispredict_cmp, @@ -876,6 +975,13 @@ struct sort_entry sort_mem_snoop = { .se_width_idx = HISTC_MEM_SNOOP, }; +struct sort_entry sort_mem_dcacheline = { + .se_header = "Data Cacheline", + .se_cmp = sort__dcacheline_cmp, + .se_snprintf = hist_entry__dcacheline_snprintf, + .se_width_idx = HISTC_MEM_DCACHELINE, +}; + static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -1043,6 +1149,7 @@ static struct sort_dimension memory_sort_dimensions[] = { DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb), DIM(SORT_MEM_LVL, "mem", sort_mem_lvl), DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), + DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 5bf0098..041f0c9 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -89,6 +89,7 @@ struct hist_entry { u64 ip; u64 transaction; s32 cpu; + u8 cpumode; struct hist_entry_diff diff; @@ -185,6 +186,7 @@ enum sort_type { SORT_MEM_TLB, SORT_MEM_LVL, SORT_MEM_SNOOP, + SORT_MEM_DCACHELINE, }; /* diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 7fff6be..95aefa7 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -17,6 +17,7 @@ * XXX We need to find a better place for these things... */ unsigned int page_size; +int cacheline_size; bool test_attr__enabled; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index b03da44..6686436 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -304,6 +304,7 @@ char *rtrim(char *s); void dump_stack(void); extern unsigned int page_size; +extern int cacheline_size; void get_term_dimensions(struct winsize *ws); |