summaryrefslogtreecommitdiff
path: root/tools/perf/util/header.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-02-19 17:49:41 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-02-19 17:49:41 -0800
commit8f55cea410dbc56114bb71a3742032070c8108d0 (patch)
tree59605f0ee961274b22f91add33f5c32459471a83 /tools/perf/util/header.c
parentb7133a9a103655cda254987a3c0975fd9d8c443f (diff)
parente259514eef764a5286873618e34c560ecb6cff13 (diff)
downloadlinux-stable-8f55cea410dbc56114bb71a3742032070c8108d0.tar.gz
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf changes from Ingo Molnar: "There are lots of improvements, the biggest changes are: Main kernel side changes: - Improve uprobes performance by adding 'pre-filtering' support, by Oleg Nesterov. - Make some POWER7 events available in sysfs, equivalent to what was done on x86, from Sukadev Bhattiprolu. - tracing updates by Steve Rostedt - mostly misc fixes and smaller improvements. - Use perf/event tracing to report PCI Express advanced errors, by Tony Luck. - Enable northbridge performance counters on AMD family 15h, by Jacob Shin. - This tracing commit: tracing: Remove the extra 4 bytes of padding in events changes the ABI. All involved parties (PowerTop in particular) seem to agree that it's safe to do now with the introduction of libtraceevent, but the devil is in the details ... Main tooling side changes: - Add 'event group view', from Namyung Kim: To use it, 'perf record' should group events when recording. And then perf report parses the saved group relation from file header and prints them together if --group option is provided. You can use the 'perf evlist' command to see event group information: $ perf record -e '{ref-cycles,cycles}' noploop 1 [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.385 MB perf.data (~16807 samples) ] $ perf evlist --group {ref-cycles,cycles} With this example, default perf report will show you each event separately. You can use --group option to enable event group view: $ perf report --group ... # group: {ref-cycles,cycles} # ======== # Samples: 7K of event 'anon group { ref-cycles, cycles }' # Event count (approx.): 6876107743 # # Overhead Command Shared Object Symbol # ................ ....... ................. .......................... 99.84% 99.76% noploop noploop [.] main 0.07% 0.00% noploop ld-2.15.so [.] strcmp 0.03% 0.00% noploop [kernel.kallsyms] [k] timerqueue_del 0.03% 0.03% noploop [kernel.kallsyms] [k] sched_clock_cpu 0.02% 0.00% noploop [kernel.kallsyms] [k] account_user_time 0.01% 0.00% noploop [kernel.kallsyms] [k] __alloc_pages_nodemask 0.00% 0.00% noploop [kernel.kallsyms] [k] native_write_msr_safe 0.00% 0.11% noploop [kernel.kallsyms] [k] _raw_spin_lock 0.00% 0.06% noploop [kernel.kallsyms] [k] find_get_page 0.00% 0.02% noploop [kernel.kallsyms] [k] rcu_check_callbacks 0.00% 0.02% noploop [kernel.kallsyms] [k] __current_kernel_time As you can see the Overhead column now contains both of ref-cycles and cycles and header line shows group information also - 'anon group { ref-cycles, cycles }'. The output is sorted by period of group leader first. - Initial GTK+ annotate browser, from Namhyung Kim. - Add option for runtime switching perf data file in perf report, just press 's' and a menu with the valid files found in the current directory will be presented, from Feng Tang. - Add support to display whole group data for raw columns, from Jiri Olsa. - Add per processor socket count aggregation in perf stat, from Stephane Eranian. - Add interval printing in 'perf stat', from Stephane Eranian. - 'perf test' improvements - Add support for wildcards in tracepoint system name, from Jiri Olsa. - Add anonymous huge page recognition, from Joshua Zhu. - perf build-id cache now can show DSOs present in a perf.data file that are not in the cache, to integrate with build-id servers being put in place by organizations such as Fedora. - perf top now shares more of the evsel config/creation routines with 'record', paving the way for further integration like 'top' snapshots, etc. - perf top now supports DWARF callchains. - Fix mmap limitations on 32-bit, fix from David Miller. - 'perf bench numa mem' NUMA performance measurement suite - ... and lots of fixes, performance improvements, cleanups and other improvements I failed to list - see the shortlog and git log for details." * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (270 commits) perf/x86/amd: Enable northbridge performance counters on AMD family 15h perf/hwbp: Fix cleanup in case of kzalloc failure perf tools: Fix build with bison 2.3 and older. perf tools: Limit unwind support to x86 archs perf annotate: Make it to be able to skip unannotatable symbols perf gtk/annotate: Fail early if it can't annotate perf gtk/annotate: Show source lines with gray color perf gtk/annotate: Support multiple event annotation perf ui/gtk: Implement basic GTK2 annotation browser perf annotate: Fix warning message on a missing vmlinux perf buildid-cache: Add --update option uprobes/perf: Avoid uprobe_apply() whenever possible uprobes/perf: Teach trace_uprobe/perf code to use UPROBE_HANDLER_REMOVE uprobes/perf: Teach trace_uprobe/perf code to pre-filter uprobes/perf: Teach trace_uprobe/perf code to track the active perf_event's uprobes: Introduce uprobe_apply() perf: Introduce hw_perf_event->tp_target and ->tp_list uprobes/perf: Always increment trace_uprobe->nhit uprobes/tracing: Kill uprobe_trace_consumer, embed uprobe_consumer into trace_uprobe uprobes/tracing: Introduce is_trace_uprobe_enabled() ...
Diffstat (limited to 'tools/perf/util/header.c')
-rw-r--r--tools/perf/util/header.c266
1 files changed, 224 insertions, 42 deletions
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b7da4634a047..f4bfd79ef6a7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -148,7 +148,7 @@ static char *do_read_string(int fd, struct perf_header *ph)
u32 len;
char *buf;
- sz = read(fd, &len, sizeof(len));
+ sz = readn(fd, &len, sizeof(len));
if (sz < (ssize_t)sizeof(len))
return NULL;
@@ -159,7 +159,7 @@ static char *do_read_string(int fd, struct perf_header *ph)
if (!buf)
return NULL;
- ret = read(fd, buf, len);
+ ret = readn(fd, buf, len);
if (ret == (ssize_t)len) {
/*
* strings are padded by zeroes
@@ -287,12 +287,12 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd)
struct perf_session *session = container_of(header,
struct perf_session, header);
struct rb_node *nd;
- int err = machine__write_buildid_table(&session->host_machine, fd);
+ int err = machine__write_buildid_table(&session->machines.host, fd);
if (err)
return err;
- for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node);
err = machine__write_buildid_table(pos, fd);
if (err)
@@ -313,7 +313,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
if (is_kallsyms) {
if (symbol_conf.kptr_restrict) {
pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
- return 0;
+ err = 0;
+ goto out_free;
}
realname = (char *) name;
} else
@@ -448,9 +449,9 @@ static int perf_session__cache_build_ids(struct perf_session *session)
if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
return -1;
- ret = machine__cache_build_ids(&session->host_machine, debugdir);
+ ret = machine__cache_build_ids(&session->machines.host, debugdir);
- for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node);
ret |= machine__cache_build_ids(pos, debugdir);
}
@@ -467,9 +468,9 @@ static bool machine__read_build_ids(struct machine *machine, bool with_hits)
static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
{
struct rb_node *nd;
- bool ret = machine__read_build_ids(&session->host_machine, with_hits);
+ bool ret = machine__read_build_ids(&session->machines.host, with_hits);
- for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node);
ret |= machine__read_build_ids(pos, with_hits);
}
@@ -954,6 +955,7 @@ static int write_topo_node(int fd, int node)
}
fclose(fp);
+ fp = NULL;
ret = do_write(fd, &mem_total, sizeof(u64));
if (ret)
@@ -980,7 +982,8 @@ static int write_topo_node(int fd, int node)
ret = do_write_string(fd, buf);
done:
free(buf);
- fclose(fp);
+ if (fp)
+ fclose(fp);
return ret;
}
@@ -1051,16 +1054,25 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
struct perf_pmu *pmu = NULL;
off_t offset = lseek(fd, 0, SEEK_CUR);
__u32 pmu_num = 0;
+ int ret;
/* write real pmu_num later */
- do_write(fd, &pmu_num, sizeof(pmu_num));
+ ret = do_write(fd, &pmu_num, sizeof(pmu_num));
+ if (ret < 0)
+ return ret;
while ((pmu = perf_pmu__scan(pmu))) {
if (!pmu->name)
continue;
pmu_num++;
- do_write(fd, &pmu->type, sizeof(pmu->type));
- do_write_string(fd, pmu->name);
+
+ ret = do_write(fd, &pmu->type, sizeof(pmu->type));
+ if (ret < 0)
+ return ret;
+
+ ret = do_write_string(fd, pmu->name);
+ if (ret < 0)
+ return ret;
}
if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) {
@@ -1073,6 +1085,52 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
}
/*
+ * File format:
+ *
+ * struct group_descs {
+ * u32 nr_groups;
+ * struct group_desc {
+ * char name[];
+ * u32 leader_idx;
+ * u32 nr_members;
+ * }[nr_groups];
+ * };
+ */
+static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
+ struct perf_evlist *evlist)
+{
+ u32 nr_groups = evlist->nr_groups;
+ struct perf_evsel *evsel;
+ int ret;
+
+ ret = do_write(fd, &nr_groups, sizeof(nr_groups));
+ if (ret < 0)
+ return ret;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ if (perf_evsel__is_group_leader(evsel) &&
+ evsel->nr_members > 1) {
+ const char *name = evsel->group_name ?: "{anon_group}";
+ u32 leader_idx = evsel->idx;
+ u32 nr_members = evsel->nr_members;
+
+ ret = do_write_string(fd, name);
+ if (ret < 0)
+ return ret;
+
+ ret = do_write(fd, &leader_idx, sizeof(leader_idx));
+ if (ret < 0)
+ return ret;
+
+ ret = do_write(fd, &nr_members, sizeof(nr_members));
+ if (ret < 0)
+ return ret;
+ }
+ }
+ return 0;
+}
+
+/*
* default get_cpuid(): nothing gets recorded
* actual implementation must be in arch/$(ARCH)/util/header.c
*/
@@ -1209,14 +1267,14 @@ read_event_desc(struct perf_header *ph, int fd)
size_t msz;
/* number of events */
- ret = read(fd, &nre, sizeof(nre));
+ ret = readn(fd, &nre, sizeof(nre));
if (ret != (ssize_t)sizeof(nre))
goto error;
if (ph->needs_swap)
nre = bswap_32(nre);
- ret = read(fd, &sz, sizeof(sz));
+ ret = readn(fd, &sz, sizeof(sz));
if (ret != (ssize_t)sizeof(sz))
goto error;
@@ -1244,7 +1302,7 @@ read_event_desc(struct perf_header *ph, int fd)
* must read entire on-file attr struct to
* sync up with layout.
*/
- ret = read(fd, buf, sz);
+ ret = readn(fd, buf, sz);
if (ret != (ssize_t)sz)
goto error;
@@ -1253,7 +1311,7 @@ read_event_desc(struct perf_header *ph, int fd)
memcpy(&evsel->attr, buf, msz);
- ret = read(fd, &nr, sizeof(nr));
+ ret = readn(fd, &nr, sizeof(nr));
if (ret != (ssize_t)sizeof(nr))
goto error;
@@ -1274,7 +1332,7 @@ read_event_desc(struct perf_header *ph, int fd)
evsel->id = id;
for (j = 0 ; j < nr; j++) {
- ret = read(fd, id, sizeof(*id));
+ ret = readn(fd, id, sizeof(*id));
if (ret != (ssize_t)sizeof(*id))
goto error;
if (ph->needs_swap)
@@ -1435,6 +1493,31 @@ error:
fprintf(fp, "# pmu mappings: unable to read\n");
}
+static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
+ FILE *fp)
+{
+ struct perf_session *session;
+ struct perf_evsel *evsel;
+ u32 nr = 0;
+
+ session = container_of(ph, struct perf_session, header);
+
+ list_for_each_entry(evsel, &session->evlist->entries, node) {
+ if (perf_evsel__is_group_leader(evsel) &&
+ evsel->nr_members > 1) {
+ fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
+ perf_evsel__name(evsel));
+
+ nr = evsel->nr_members - 1;
+ } else if (nr) {
+ fprintf(fp, ",%s", perf_evsel__name(evsel));
+
+ if (--nr == 0)
+ fprintf(fp, "}\n");
+ }
+ }
+}
+
static int __event_process_build_id(struct build_id_event *bev,
char *filename,
struct perf_session *session)
@@ -1506,14 +1589,14 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
while (offset < limit) {
ssize_t len;
- if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
+ if (readn(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
return -1;
if (header->needs_swap)
perf_event_header__bswap(&old_bev.header);
len = old_bev.header.size - sizeof(old_bev);
- if (read(input, filename, len) != len)
+ if (readn(input, filename, len) != len)
return -1;
bev.header = old_bev.header;
@@ -1548,14 +1631,14 @@ static int perf_header__read_build_ids(struct perf_header *header,
while (offset < limit) {
ssize_t len;
- if (read(input, &bev, sizeof(bev)) != sizeof(bev))
+ if (readn(input, &bev, sizeof(bev)) != sizeof(bev))
goto out;
if (header->needs_swap)
perf_event_header__bswap(&bev.header);
len = bev.header.size - sizeof(bev);
- if (read(input, filename, len) != len)
+ if (readn(input, filename, len) != len)
goto out;
/*
* The a1645ce1 changeset:
@@ -1641,7 +1724,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
size_t ret;
u32 nr;
- ret = read(fd, &nr, sizeof(nr));
+ ret = readn(fd, &nr, sizeof(nr));
if (ret != sizeof(nr))
return -1;
@@ -1650,7 +1733,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
ph->env.nr_cpus_online = nr;
- ret = read(fd, &nr, sizeof(nr));
+ ret = readn(fd, &nr, sizeof(nr));
if (ret != sizeof(nr))
return -1;
@@ -1684,7 +1767,7 @@ static int process_total_mem(struct perf_file_section *section __maybe_unused,
uint64_t mem;
size_t ret;
- ret = read(fd, &mem, sizeof(mem));
+ ret = readn(fd, &mem, sizeof(mem));
if (ret != sizeof(mem))
return -1;
@@ -1756,7 +1839,7 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused,
u32 nr, i;
struct strbuf sb;
- ret = read(fd, &nr, sizeof(nr));
+ ret = readn(fd, &nr, sizeof(nr));
if (ret != sizeof(nr))
return -1;
@@ -1792,7 +1875,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
char *str;
struct strbuf sb;
- ret = read(fd, &nr, sizeof(nr));
+ ret = readn(fd, &nr, sizeof(nr));
if (ret != sizeof(nr))
return -1;
@@ -1813,7 +1896,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
}
ph->env.sibling_cores = strbuf_detach(&sb, NULL);
- ret = read(fd, &nr, sizeof(nr));
+ ret = readn(fd, &nr, sizeof(nr));
if (ret != sizeof(nr))
return -1;
@@ -1850,7 +1933,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
struct strbuf sb;
/* nr nodes */
- ret = read(fd, &nr, sizeof(nr));
+ ret = readn(fd, &nr, sizeof(nr));
if (ret != sizeof(nr))
goto error;
@@ -1862,15 +1945,15 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
for (i = 0; i < nr; i++) {
/* node number */
- ret = read(fd, &node, sizeof(node));
+ ret = readn(fd, &node, sizeof(node));
if (ret != sizeof(node))
goto error;
- ret = read(fd, &mem_total, sizeof(u64));
+ ret = readn(fd, &mem_total, sizeof(u64));
if (ret != sizeof(u64))
goto error;
- ret = read(fd, &mem_free, sizeof(u64));
+ ret = readn(fd, &mem_free, sizeof(u64));
if (ret != sizeof(u64))
goto error;
@@ -1909,7 +1992,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
u32 type;
struct strbuf sb;
- ret = read(fd, &pmu_num, sizeof(pmu_num));
+ ret = readn(fd, &pmu_num, sizeof(pmu_num));
if (ret != sizeof(pmu_num))
return -1;
@@ -1925,7 +2008,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
strbuf_init(&sb, 128);
while (pmu_num) {
- if (read(fd, &type, sizeof(type)) != sizeof(type))
+ if (readn(fd, &type, sizeof(type)) != sizeof(type))
goto error;
if (ph->needs_swap)
type = bswap_32(type);
@@ -1949,6 +2032,98 @@ error:
return -1;
}
+static int process_group_desc(struct perf_file_section *section __maybe_unused,
+ struct perf_header *ph, int fd,
+ void *data __maybe_unused)
+{
+ size_t ret = -1;
+ u32 i, nr, nr_groups;
+ struct perf_session *session;
+ struct perf_evsel *evsel, *leader = NULL;
+ struct group_desc {
+ char *name;
+ u32 leader_idx;
+ u32 nr_members;
+ } *desc;
+
+ if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups))
+ return -1;
+
+ if (ph->needs_swap)
+ nr_groups = bswap_32(nr_groups);
+
+ ph->env.nr_groups = nr_groups;
+ if (!nr_groups) {
+ pr_debug("group desc not available\n");
+ return 0;
+ }
+
+ desc = calloc(nr_groups, sizeof(*desc));
+ if (!desc)
+ return -1;
+
+ for (i = 0; i < nr_groups; i++) {
+ desc[i].name = do_read_string(fd, ph);
+ if (!desc[i].name)
+ goto out_free;
+
+ if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32))
+ goto out_free;
+
+ if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32))
+ goto out_free;
+
+ if (ph->needs_swap) {
+ desc[i].leader_idx = bswap_32(desc[i].leader_idx);
+ desc[i].nr_members = bswap_32(desc[i].nr_members);
+ }
+ }
+
+ /*
+ * Rebuild group relationship based on the group_desc
+ */
+ session = container_of(ph, struct perf_session, header);
+ session->evlist->nr_groups = nr_groups;
+
+ i = nr = 0;
+ list_for_each_entry(evsel, &session->evlist->entries, node) {
+ if (evsel->idx == (int) desc[i].leader_idx) {
+ evsel->leader = evsel;
+ /* {anon_group} is a dummy name */
+ if (strcmp(desc[i].name, "{anon_group}"))
+ evsel->group_name = desc[i].name;
+ evsel->nr_members = desc[i].nr_members;
+
+ if (i >= nr_groups || nr > 0) {
+ pr_debug("invalid group desc\n");
+ goto out_free;
+ }
+
+ leader = evsel;
+ nr = evsel->nr_members - 1;
+ i++;
+ } else if (nr) {
+ /* This is a group member */
+ evsel->leader = leader;
+
+ nr--;
+ }
+ }
+
+ if (i != nr_groups || nr != 0) {
+ pr_debug("invalid group desc\n");
+ goto out_free;
+ }
+
+ ret = 0;
+out_free:
+ while ((int) --i >= 0)
+ free(desc[i].name);
+ free(desc);
+
+ return ret;
+}
+
struct feature_ops {
int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1988,6 +2163,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology),
FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings),
+ FEAT_OPP(HEADER_GROUP_DESC, group_desc),
};
struct header_print_data {
@@ -2077,7 +2253,7 @@ static int perf_header__adds_write(struct perf_header *header,
if (!nr_sections)
return 0;
- feat_sec = p = calloc(sizeof(*feat_sec), nr_sections);
+ feat_sec = p = calloc(nr_sections, sizeof(*feat_sec));
if (feat_sec == NULL)
return -ENOMEM;
@@ -2249,7 +2425,7 @@ int perf_header__process_sections(struct perf_header *header, int fd,
if (!nr_sections)
return 0;
- feat_sec = sec = calloc(sizeof(*feat_sec), nr_sections);
+ feat_sec = sec = calloc(nr_sections, sizeof(*feat_sec));
if (!feat_sec)
return -1;
@@ -2912,16 +3088,22 @@ int perf_event__process_tracing_data(union perf_event *event,
session->repipe);
padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
- if (read(session->fd, buf, padding) < 0)
- die("reading input file");
+ if (readn(session->fd, buf, padding) < 0) {
+ pr_err("%s: reading input file", __func__);
+ return -1;
+ }
if (session->repipe) {
int retw = write(STDOUT_FILENO, buf, padding);
- if (retw <= 0 || retw != padding)
- die("repiping tracing data padding");
+ if (retw <= 0 || retw != padding) {
+ pr_err("%s: repiping tracing data padding", __func__);
+ return -1;
+ }
}
- if (size_read + padding != size)
- die("tracing data size mismatch");
+ if (size_read + padding != size) {
+ pr_err("%s: tracing data size mismatch", __func__);
+ return -1;
+ }
perf_evlist__prepare_tracepoint_events(session->evlist,
session->pevent);