From 473a778a2f2949972b52ad7fc61577f381f2d05e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 2 Jun 2014 23:20:16 -0400 Subject: tools lib traceevent: Added support for __get_bitmask() macro Coming in v3.16, trace events will be able to save bitmasks in raw format in the ring buffer and output it with the __get_bitmask() macro. In order for userspace tools to parse this, it must be able to handle the __get_bitmask() call and be able to convert the data that's in the ring buffer into a nice bitmask format. The output is similar to what the kernel uses to print bitmasks, with a comma separator every 4 bytes (8 characters). This allows for cpumasks to also be saved efficiently. The first user is the thermal:thermal_power_limit event which has the following output: thermal_power_limit: cpus=0000000f freq=1900000 cdev_state=0 power=5252 Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino Signed-off-by: Steven Rostedt Acked-by: Namhyung Kim Tested-by: Javi Merino Link: http://lkml.kernel.org/r/20140603032224.229186537@goodmis.org Signed-off-by: Jiri Olsa --- tools/perf/util/scripting-engines/trace-event-perl.c | 1 + tools/perf/util/scripting-engines/trace-event-python.c | 1 + 2 files changed, 2 insertions(+) (limited to 'tools/perf') 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..c3de097 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; } -- cgit v1.1 From a261e4a09a073451057e9dbe17783255ea94598d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 5 Jun 2014 18:51:44 +0200 Subject: perf tools: Fix pipe check regression in attr event callback The file factoring in builtin-inject.c object introduced regression in attr event callback. The commit is: 3406912 perf inject: Handle output file via perf_data_file object Following hunk reversed the logic: - if (!inject->pipe_output) + if (&inject->output.is_pipe) putting it back, following example now works: $ perf record -o - kill | perf inject -b | perf report -i - Plus removing extra '&' (kudos to Arnaldo) Reported-by: Stephane Eranian Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20140605204117.GA1771@krava.redhat.com Signed-off-by: Jiri Olsa --- tools/perf/builtin-inject.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') 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); -- cgit v1.1 From b0815d07ec12959da2104822561e0df26dc4bf3d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 4 Jun 2014 14:43:58 +0200 Subject: perf tools: Prettify the tags/TAGS/cscope targets output Add tags/TAGS/cscope targets to the quiet family. $ make tags cscope BUILD: Doing 'make -j4' parallel build GEN tags $ make cscope BUILD: Doing 'make -j4' parallel build GEN cscope Reviewed-by: David Ahern Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jean Pihet Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1401893676-32205-1-git-send-email-jolsa@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/Makefile.perf | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf') 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 -- cgit v1.1 From e646fe730a324098a718f1c9b2f349efb99d5457 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 29 May 2014 13:44:55 +0900 Subject: perf script/python: Print array argument as string With the Sebastian's change of handling num array argument (of raw syscall enter), the script still failed to work like this: $ perf record -e raw_syscalls:* sleep 1 $ perf script -g python $ perf script -s perf-script.py ... Traceback (most recent call last): File "perf-script.py", line 42, in raw_syscalls__sys_enter (id, args), TypeError: %u format: a number is required, not list Fatal Python error: problem in Python trace event handler Aborted (core dumped) This is because the generated script tries to print the array arg as unsigned integer (%u). Since the python seems to convert arguments to strings by default, just using %s solved the problem for me. Signed-off-by: Namhyung Kim Cc: Tom Zanussi Cc: Sebastian Andrzej Siewior Link: http://lkml.kernel.org/r/1401338695-18837-1-git-send-email-namhyung@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/util/scripting-engines/trace-event-python.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf') diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index c3de097..1c41932 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -623,6 +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) -- cgit v1.1 From 7ef807034ef33f8afe33fa7957c73954e8e4f89c Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Mon, 19 May 2014 15:13:49 -0400 Subject: perf tools: Update mmap2 interface with protection and flag bits The kernel piece passes more info now. Update the perf tool to reflect that and adjust the synthesized maps to play along. Signed-off-by: Don Zickus Link: http://lkml.kernel.org/r/1400526833-141779-4-git-send-email-dzickus@redhat.com Signed-off-by: Jiri Olsa --- tools/perf/util/event.c | 23 +++++++++++++++++++++-- tools/perf/util/event.h | 2 ++ tools/perf/util/machine.c | 4 +++- tools/perf/util/map.c | 4 +++- tools/perf/util/map.h | 4 +++- 5 files changed, 32 insertions(+), 5 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 65795b8..ce43cba 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,4 +1,5 @@ #include +#include #include "event.h" #include "debug.h" #include "hist.h" @@ -212,6 +213,21 @@ 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; @@ -612,12 +628,15 @@ 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/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); -- cgit v1.1 From a5a5ba72843dd05f991184d6cb9a4471acce1005 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 30 May 2014 10:49:42 -0400 Subject: Revert "perf: Disable PERF_RECORD_MMAP2 support" This reverts commit 3090ffb5a2515990182f3f55b0688a7817325488. Re-enable the mmap2 interface as we will have a user soon. Since things have changed since perf disabled mmap2, small tweaks to the revert had to be done: o commit 9d4ecc88 forced (n!=8) to become (n<7) o a new libunwind test needed updating to use mmap2 interface Signed-off-by: Don Zickus Link: http://lkml.kernel.org/r/1401461382-209586-1-git-send-email-dzickus@redhat.com Signed-off-by: Jiri Olsa --- tools/perf/tests/dwarf-unwind.c | 2 +- tools/perf/util/event.c | 34 ++++++++++++++++++++-------------- tools/perf/util/evsel.c | 1 + 3 files changed, 22 insertions(+), 15 deletions(-) (limited to 'tools/perf') 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 ce43cba..d0281bd 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -179,13 +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; @@ -196,15 +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 */ @@ -239,15 +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; 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) -- cgit v1.1 From 75e906c9601aee73b88d6e6dc02371f8c3ca24d7 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 23 May 2014 18:41:23 +0200 Subject: perf report: Add mem-mode documentation to report command Add mem-mode sorting types and mem-mode itself to perf-report documentation. Signed-off-by: Don Zickus Link: http://lkml.kernel.org/r/1400526833-141779-5-git-send-email-dzickus@redhat.com Signed-off-by: Jiri Olsa --- tools/perf/Documentation/perf-report.txt | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index cefdf43..00fbfb6 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -117,6 +117,21 @@ 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. + + - 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 + + And default sort keys are changed to local_weight, mem, sym, dso, + symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. + -p:: --parent=:: A regex filter to identify parent. The parent is a caller of this @@ -260,6 +275,13 @@ 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). -- cgit v1.1 From 7365be55eee37ddb4f487263b4ba5bc8beb9638f Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Tue, 27 May 2014 12:28:05 -0400 Subject: perf tools: Add cpumode to struct hist_entry The next patch needs to sort on cpumode, so add it to hist_entry to be tracked. Signed-off-by: Don Zickus Link: http://lkml.kernel.org/r/1401208087-181977-6-git-send-email-dzickus@redhat.com Signed-off-by: Jiri Olsa --- tools/perf/util/hist.c | 7 ++++--- tools/perf/util/sort.h | 1 + 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 5a0a4b2..d5f47a4 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -439,9 +439,10 @@ 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/sort.h b/tools/perf/util/sort.h index 5bf0098..6de22f8 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; -- cgit v1.1 From 2b1b71003ea809e619bd73e74dfc2a73069de66f Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 30 May 2014 16:10:05 -0400 Subject: perf tools: Add support to dynamically get cacheline size Different arches may have different cacheline sizes. Look it up and set a global variable for reference. Signed-off-by: Don Zickus Link: http://lkml.kernel.org/r/1401480605-97442-1-git-send-email-dzickus@redhat.com Signed-off-by: Jiri Olsa --- tools/perf/perf.c | 1 + tools/perf/util/util.c | 1 + tools/perf/util/util.h | 1 + 3 files changed, 3 insertions(+) (limited to 'tools/perf') 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/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); -- cgit v1.1 From 9b32ba71ba905b90610fc2aad77cb98a373c5624 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Sun, 1 Jun 2014 15:38:29 +0200 Subject: perf tools: Add dcacheline sort In perf's 'mem-mode', one can get access to a whole bunch of details specific to a particular sample instruction. A bunch of those details relate to the data address. One interesting thing you can do with data addresses is to convert them into a unique cacheline they belong too. Organizing these data cachelines into similar groups and sorting them can reveal cache contention. This patch creates an alogorithm based on various sample details that can help group entries together into data cachelines and allows 'perf report' to sort on it. The algorithm relies on having proper mmap2 support in the kernel to help determine if the memory map the data address belongs to is private to a pid or globally shared. The alogortithm is as follows: o group cpumodes together o group entries with discovered maps together o sort on major, minor, inode and inode generation numbers o if userspace anon, then sort on pid o sort on cachelines based on data addresses The 'dcacheline' sort option in 'perf report' only works in 'mem-mode'. Sample output: # # Samples: 206 of event 'cpu/mem-loads/pp' # Total weight : 2534 # Sort order : dcacheline,pid # # Overhead Samples Data Cacheline Command: Pid # ........ ............ ...................................................................... .................. # 13.22% 1 [k] 0xffff88042f08ebc0 swapper: 0 9.27% 1 [k] 0xffff88082e8cea80 swapper: 0 3.59% 2 [k] 0xffffffff819ba180 swapper: 0 0.32% 1 [k] arch_trigger_all_cpu_backtrace_handler_na.23901+0xffffffffffffffe0 swapper: 0 0.32% 1 [k] timekeeper_seq+0xfffffffffffffff8 swapper: 0 Note: Added a '+1' to symlen size in hists__calc_col_len to prevent the next column from prematurely tabbing over and mis-aligning. Not sure what the problem is. Signed-off-by: Don Zickus Link: http://lkml.kernel.org/r/1401208087-181977-8-git-send-email-dzickus@redhat.com Signed-off-by: Jiri Olsa --- tools/perf/Documentation/perf-report.txt | 3 +- tools/perf/util/hist.c | 2 + tools/perf/util/hist.h | 1 + tools/perf/util/sort.c | 107 +++++++++++++++++++++++++++++++ tools/perf/util/sort.h | 1 + 5 files changed, 113 insertions(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 00fbfb6..d2b59af 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -119,7 +119,7 @@ OPTIONS If --mem-mode option is used, following sort keys are also available (incompatible with --branch-stack): - symbol_daddr, dso_daddr, locked, tlb, mem, snoop. + 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 @@ -128,6 +128,7 @@ OPTIONS - 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'. diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index d5f47a4..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, 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/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 #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 6de22f8..041f0c9 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -186,6 +186,7 @@ enum sort_type { SORT_MEM_TLB, SORT_MEM_LVL, SORT_MEM_SNOOP, + SORT_MEM_DCACHELINE, }; /* -- cgit v1.1