| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 2 Oct 2015 14:18:46 +0900
From: Namhyung Kim <namhyung@...nel.org>
To: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Jiri Olsa <jolsa@...hat.com>,
LKML <linux-kernel@...r.kernel.org>,
Frederic Weisbecker <fweisbec@...il.com>,
Stephane Eranian <eranian@...gle.com>,
David Ahern <dsahern@...il.com>,
Andi Kleen <andi@...stfloor.org>,
Adrian Hunter <adrian.hunter@...el.com>
Subject: [RFC/PATCH 05/38] perf tools: Create separate mmap for dummy tracking event
When indexed data file support is enabled, a dummy tracking event will
be used to track metadata (like task, comm and mmap events) for a
session and actual samples will be recorded in separate (intermediate)
files and then merged (with index table).
Provide separate mmap to the dummy tracking event. The size is fixed
to 128KiB (+ 1 page) as the event rate will be lower than samples. I
originally wanted to use a single mmap for this but cross-cpu sharing
is prohibited so it's per-cpu (or per-task) like normal mmaps.
Cc: Adrian Hunter <adrian.hunter@...el.com>
Signed-off-by: Namhyung Kim <namhyung@...nel.org>
---
tools/perf/builtin-record.c | 2 +-
tools/perf/util/evlist.c | 106 ++++++++++++++++++++++++++++++++++----------
tools/perf/util/evlist.h | 9 ++++
3 files changed, 93 insertions(+), 24 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0accac6e0812..33dc2eafe2b5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -74,7 +74,7 @@ static int process_synthesized_event(struct perf_tool *tool,
static int record__mmap_read(struct record *rec, int idx)
{
- struct perf_mmap *md = &rec->evlist->mmap[idx];
+ struct perf_mmap *md = perf_evlist__mmap_desc(rec->evlist, idx);
u64 head = perf_mmap__read_head(md);
u64 old = md->prev;
unsigned char *data = md->base + page_size;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8d31883cbeb8..25a9c3b5f473 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -743,7 +743,7 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
{
- struct perf_mmap *md = &evlist->mmap[idx];
+ struct perf_mmap *md = perf_evlist__mmap_desc(evlist, idx);
u64 head;
u64 old = md->prev;
unsigned char *data = md->base + page_size;
@@ -812,28 +812,38 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
static bool perf_evlist__mmap_empty(struct perf_evlist *evlist, int idx)
{
- struct perf_mmap *md = &evlist->mmap[idx];
+ struct perf_mmap *md = perf_evlist__mmap_desc(evlist, idx);
- return perf_mmap__read_head(md) == md->prev &&
- evlist->auxtrace_mmap[idx].base == NULL;
+ if (perf_mmap__read_head(md) != md->prev)
+ return false;
+
+ if (idx >= 0)
+ return !evlist->auxtrace_mmap[idx].base;
+ return true;
}
static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
{
- atomic_inc(&evlist->mmap[idx].refcnt);
+ struct perf_mmap *md = perf_evlist__mmap_desc(evlist, idx);
+
+ atomic_inc(&md->refcnt);
}
static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
{
- BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
+ struct perf_mmap *md = perf_evlist__mmap_desc(evlist, idx);
+
+ BUG_ON(atomic_read(&md->refcnt) == 0);
- if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
- __perf_evlist__munmap(evlist, idx);
+ if (!atomic_dec_and_test(&md->refcnt))
+ return;
+
+ __perf_evlist__munmap(evlist, idx);
}
void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
{
- struct perf_mmap *md = &evlist->mmap[idx];
+ struct perf_mmap *md = perf_evlist__mmap_desc(evlist, idx);
if (!evlist->overwrite) {
u64 old = md->prev;
@@ -875,14 +885,15 @@ void __weak auxtrace_mmap_params__set_idx(
static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
{
- if (evlist->mmap[idx].base != NULL) {
- size_t mmap_len = perf_evlist__mmap_len(evlist->mmap[idx].mask);
+ struct perf_mmap *md = perf_evlist__mmap_desc(evlist, idx);
+
+ if (md->base != NULL) {
+ size_t mmap_len = perf_evlist__mmap_len(md->mask);
- munmap(evlist->mmap[idx].base, mmap_len);
- evlist->mmap[idx].base = NULL;
- atomic_set(&evlist->mmap[idx].refcnt, 0);
+ munmap(md->base, mmap_len);
+ md->base = NULL;
+ atomic_set(&md->refcnt, 0);
}
- auxtrace_mmap__munmap(&evlist->auxtrace_mmap[idx]);
}
void perf_evlist__munmap(struct perf_evlist *evlist)
@@ -892,13 +903,17 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
if (evlist->mmap == NULL)
return;
- for (i = 0; i < evlist->nr_mmaps; i++)
+ for (i = 0; i < evlist->nr_mmaps; i++) {
__perf_evlist__munmap(evlist, i);
+ auxtrace_mmap__munmap(&evlist->auxtrace_mmap[i]);
+ if (evlist->track_mmap)
+ __perf_evlist__munmap(evlist, track_mmap_idx(i));
+ }
zfree(&evlist->mmap);
}
-static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static int perf_evlist__alloc_mmap(struct perf_evlist *evlist, bool track_mmap)
{
evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
if (cpu_map__empty(evlist->cpus))
@@ -912,12 +927,22 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
zfree(&evlist->mmap);
return -ENOMEM;
}
+ if (track_mmap) {
+ evlist->track_mmap = calloc(evlist->nr_mmaps,
+ sizeof(struct perf_mmap));
+ if (evlist->track_mmap == NULL) {
+ zfree(&evlist->mmap);
+ zfree(&evlist->auxtrace_mmap);
+ return -ENOMEM;
+ }
+ }
return 0;
}
struct mmap_params {
int prot;
size_t len;
+ bool track_mmap;
struct auxtrace_mmap_params auxtrace_mp;
};
@@ -954,12 +979,16 @@ static int perf_mmap__mmap(struct perf_mmap *desc,
struct perf_mmap *perf_evlist__mmap_desc(struct perf_evlist *evlist, int idx)
{
- return &evlist->mmap[idx];
+ if (idx >= 0)
+ return &evlist->mmap[idx];
+ else
+ return &evlist->track_mmap[track_mmap_idx(idx)];
}
static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
struct mmap_params *mp, int cpu,
- int thread, int *output)
+ int thread, int *output,
+ int *track_output)
{
struct perf_evsel *evsel;
@@ -972,7 +1001,30 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
fd = FD(evsel, cpu, thread);
- if (*output == -1) {
+ if (mp->track_mmap && perf_evsel__is_dummy_tracking(evsel)) {
+ size_t old_len = mp->len;
+
+ /* mark idx as track mmap idx (negative) */
+ idx = track_mmap_idx(idx);
+
+ desc = perf_evlist__mmap_desc(evlist, idx);
+ mp->len = TRACK_MMAP_SIZE;
+
+ if (*track_output == -1) {
+ *track_output = fd;
+ if (perf_mmap__mmap(desc, mp, fd) < 0)
+ return -1;
+ } else {
+ if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
+ *track_output) != 0)
+ return -1;
+
+ perf_evlist__mmap_get(evlist, idx);
+ }
+
+ mp->len = old_len;
+
+ } else if (*output == -1) {
*output = fd;
if (perf_mmap__mmap(desc, mp, *output) < 0)
return -1;
@@ -1008,6 +1060,11 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
perf_evlist__set_sid_idx(evlist, evsel, idx, cpu,
thread);
}
+
+ if (mp->track_mmap && perf_evsel__is_dummy_tracking(evsel)) {
+ /* restore idx as normal mmap idx (positive) */
+ idx = track_mmap_idx(idx);
+ }
}
return 0;
@@ -1023,13 +1080,15 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
pr_debug2("perf event ring buffer mmapped per cpu\n");
for (cpu = 0; cpu < nr_cpus; cpu++) {
int output = -1;
+ int track_output = -1;
auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
true);
for (thread = 0; thread < nr_threads; thread++) {
if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
- thread, &output))
+ thread, &output,
+ &track_output))
goto out_unmap;
}
}
@@ -1051,12 +1110,13 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
pr_debug2("perf event ring buffer mmapped per thread\n");
for (thread = 0; thread < nr_threads; thread++) {
int output = -1;
+ int track_output = -1;
auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
false);
if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
- &output))
+ &output, &track_output))
goto out_unmap;
}
@@ -1204,7 +1264,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
.prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
};
- if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+ if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist, mp.track_mmap) < 0)
return -ENOMEM;
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 79f8245300ad..fc53eb817c51 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -33,6 +33,8 @@ struct perf_mmap {
char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
};
+#define TRACK_MMAP_SIZE (((128 * 1024 / page_size) + 1) * page_size)
+
struct perf_evlist {
struct list_head entries;
struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
@@ -52,6 +54,7 @@ struct perf_evlist {
} workload;
struct fdarray pollfd;
struct perf_mmap *mmap;
+ struct perf_mmap *track_mmap;
struct auxtrace_mmap *auxtrace_mmap;
struct thread_map *threads;
struct cpu_map *cpus;
@@ -224,6 +227,12 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
void perf_evlist__to_front(struct perf_evlist *evlist,
struct perf_evsel *move_evsel);
+/* convert from/to negative idx for track mmap */
+static inline int track_mmap_idx(int idx)
+{
+ return -idx - 1;
+}
+
/**
* __evlist__for_each - iterate thru all the evsels
* @list: list_head instance to iterate
--
2.6.0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists