diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-13 13:05:08 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-13 13:05:08 -0800 |
commit | 31486372a1e9a66ec2e9e2903b8792bba7e503e1 (patch) | |
tree | 84f61e0758695e6fbee8d2b7d7b9bc4a5ce6e03b /tools/perf/util/evlist.c | |
parent | 8e9a2dba8686187d8c8179e5b86640e653963889 (diff) | |
parent | fcdfafcb73be8fa45909327bbddca46fb362a675 (diff) | |
download | linux-31486372a1e9a66ec2e9e2903b8792bba7e503e1.tar.bz2 |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"The main changes in this cycle were:
Kernel:
- kprobes updates: use better W^X patterns for code modifications,
improve optprobes, remove jprobes. (Masami Hiramatsu, Kees Cook)
- core fixes: event timekeeping (enabled/running times statistics)
fixes, perf_event_read() locking fixes and cleanups, etc. (Peter
Zijlstra)
- Extend x86 Intel free-running PEBS support and support x86
user-register sampling in perf record and perf script. (Andi Kleen)
Tooling:
- Completely rework the way inline frames are handled. Instead of
querying for the inline nodes on-demand in the individual tools, we
now create proper callchain nodes for inlined frames. (Milian
Wolff)
- 'perf trace' updates (Arnaldo Carvalho de Melo)
- Implement a way to print formatted output to per-event files in
'perf script' to facilitate generate flamegraphs, elliminating the
need to write scripts to do that separation (yuzhoujian, Arnaldo
Carvalho de Melo)
- Update vendor events JSON metrics for Intel's Broadwell, Broadwell
Server, Haswell, Haswell Server, IvyBridge, IvyTown, JakeTown,
Sandy Bridge, Skylake, SkyLake Server - and Goldmont Plus V1 (Andi
Kleen, Kan Liang)
- Multithread the synthesizing of PERF_RECORD_ events for
pre-existing threads in 'perf top', speeding up that phase, greatly
improving the user experience in systems such as Intel's Knights
Mill (Kan Liang)
- Introduce the concept of weak groups in 'perf stat': try to set up
a group, but if it's not schedulable fallback to not using a group.
That gives us the best of both worlds: groups if they work, but
still a usable fallback if they don't. E.g: (Andi Kleen)
- perf sched timehist enhancements (David Ahern)
- ... various other enhancements, updates, cleanups and fixes"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (139 commits)
kprobes: Don't spam the build log with deprecation warnings
arm/kprobes: Remove jprobe test case
arm/kprobes: Fix kretprobe test to check correct counter
perf srcline: Show correct function name for srcline of callchains
perf srcline: Fix memory leak in addr2inlines()
perf trace beauty kcmp: Beautify arguments
perf trace beauty: Implement pid_fd beautifier
tools include uapi: Grab a copy of linux/kcmp.h
perf callchain: Fix double mapping al->addr for children without self period
perf stat: Make --per-thread update shadow stats to show metrics
perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
perf tools: Add perf_data_file__write function
perf tools: Add struct perf_data_file
perf tools: Rename struct perf_data_file to perf_data
perf script: Print information about per-event-dump files
perf trace beauty prctl: Generate 'option' string table from kernel headers
tools include uapi: Grab a copy of linux/prctl.h
perf script: Allow creating per-event dump files
perf evsel: Restore evsel->priv as a tool private area
perf script: Use event_format__fprintf()
...
Diffstat (limited to 'tools/perf/util/evlist.c')
-rw-r--r-- | tools/perf/util/evlist.c | 248 |
1 files changed, 0 insertions, 248 deletions
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 6a0d7ffbeba0..c6c891e154a6 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -33,9 +33,6 @@ #include <linux/log2.h> #include <linux/err.h> -static void perf_mmap__munmap(struct perf_mmap *map); -static void perf_mmap__put(struct perf_mmap *map); - #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define SID(e, x, y) xyarray__entry(e->sample_id, x, y) @@ -704,129 +701,6 @@ static 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, - u64 end, u64 *prev) -{ - unsigned char *data = md->base + page_size; - union perf_event *event = NULL; - int diff = end - start; - - if (check_messup) { - /* - * If we're further behind than half the buffer, there's a chance - * the writer will bite our tail and mess up the samples under us. - * - * If we somehow ended up ahead of the 'end', we got messed up. - * - * In either case, truncate and restart at 'end'. - */ - if (diff > md->mask / 2 || diff < 0) { - fprintf(stderr, "WARNING: failed to keep up with mmap data.\n"); - - /* - * 'end' points to a known good entry, start there. - */ - start = end; - diff = 0; - } - } - - if (diff >= (int)sizeof(event->header)) { - size_t size; - - event = (union perf_event *)&data[start & md->mask]; - size = event->header.size; - - if (size < sizeof(event->header) || diff < (int)size) { - event = NULL; - goto broken_event; - } - - /* - * Event straddles the mmap boundary -- header should always - * be inside due to u64 alignment of output. - */ - if ((start & md->mask) + size != ((start + size) & md->mask)) { - unsigned int offset = start; - unsigned int len = min(sizeof(*event), size), cpy; - void *dst = md->event_copy; - - do { - cpy = min(md->mask + 1 - (offset & md->mask), len); - memcpy(dst, &data[offset & md->mask], cpy); - offset += cpy; - dst += cpy; - len -= cpy; - } while (len); - - event = (union perf_event *) md->event_copy; - } - - start += size; - } - -broken_event: - if (prev) - *prev = start; - - return event; -} - -union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup) -{ - u64 head; - u64 old = md->prev; - - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&md->refcnt)) - return NULL; - - head = perf_mmap__read_head(md); - - return perf_mmap__read(md, check_messup, old, head, &md->prev); -} - -union perf_event * -perf_mmap__read_backward(struct perf_mmap *md) -{ - u64 head, end; - u64 start = md->prev; - - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&md->refcnt)) - return NULL; - - head = perf_mmap__read_head(md); - if (!head) - return NULL; - - /* - * 'head' pointer starts from 0. Kernel minus sizeof(record) form - * it each time when kernel writes to it, so in fact 'head' is - * negative. 'end' pointer is made manually by adding the size of - * the ring buffer to 'head' pointer, means the validate data can - * read is the whole ring buffer. If 'end' is positive, the ring - * buffer has not fully filled, so we must adjust 'end' to 0. - * - * However, since both 'head' and 'end' is unsigned, we can't - * simply compare 'end' against 0. Here we compare '-head' and - * the size of the ring buffer, where -head is the number of bytes - * kernel write to the ring buffer. - */ - if (-head < (u64)(md->mask + 1)) - end = 0; - else - end = head + md->mask + 1; - - return perf_mmap__read(md, false, start, end, &md->prev); -} - union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx) { struct perf_mmap *md = &evlist->mmap[idx]; @@ -857,96 +731,16 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) return perf_evlist__mmap_read_forward(evlist, idx); } -void perf_mmap__read_catchup(struct perf_mmap *md) -{ - u64 head; - - if (!refcount_read(&md->refcnt)) - return; - - head = perf_mmap__read_head(md); - md->prev = head; -} - void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) { perf_mmap__read_catchup(&evlist->mmap[idx]); } -static bool perf_mmap__empty(struct perf_mmap *md) -{ - return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base; -} - -static void perf_mmap__get(struct perf_mmap *map) -{ - refcount_inc(&map->refcnt); -} - -static void perf_mmap__put(struct perf_mmap *md) -{ - BUG_ON(md->base && refcount_read(&md->refcnt) == 0); - - if (refcount_dec_and_test(&md->refcnt)) - perf_mmap__munmap(md); -} - -void perf_mmap__consume(struct perf_mmap *md, bool overwrite) -{ - if (!overwrite) { - u64 old = md->prev; - - perf_mmap__write_tail(md, old); - } - - if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md)) - perf_mmap__put(md); -} - void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) { perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite); } -int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused, - struct auxtrace_mmap_params *mp __maybe_unused, - void *userpg __maybe_unused, - int fd __maybe_unused) -{ - return 0; -} - -void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused) -{ -} - -void __weak auxtrace_mmap_params__init( - struct auxtrace_mmap_params *mp __maybe_unused, - off_t auxtrace_offset __maybe_unused, - unsigned int auxtrace_pages __maybe_unused, - bool auxtrace_overwrite __maybe_unused) -{ -} - -void __weak auxtrace_mmap_params__set_idx( - struct auxtrace_mmap_params *mp __maybe_unused, - struct perf_evlist *evlist __maybe_unused, - int idx __maybe_unused, - bool per_cpu __maybe_unused) -{ -} - -static void perf_mmap__munmap(struct perf_mmap *map) -{ - if (map->base != NULL) { - munmap(map->base, perf_mmap__mmap_len(map)); - map->base = NULL; - map->fd = -1; - refcount_set(&map->refcnt, 0); - } - auxtrace_mmap__munmap(&map->auxtrace_mmap); -} - static void perf_evlist__munmap_nofree(struct perf_evlist *evlist) { int i; @@ -995,48 +789,6 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) return map; } -struct mmap_params { - int prot; - int mask; - struct auxtrace_mmap_params auxtrace_mp; -}; - -static int perf_mmap__mmap(struct perf_mmap *map, - struct mmap_params *mp, int fd) -{ - /* - * The last one will be done at perf_evlist__mmap_consume(), so that we - * make sure we don't prevent tools from consuming every last event in - * the ring buffer. - * - * I.e. we can get the POLLHUP meaning that the fd doesn't exist - * anymore, but the last events for it are still in the ring buffer, - * waiting to be consumed. - * - * Tools can chose to ignore this at their own discretion, but the - * evlist layer can't just drop it when filtering events in - * perf_evlist__filter_pollfd(). - */ - refcount_set(&map->refcnt, 2); - map->prev = 0; - map->mask = mp->mask; - map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, - MAP_SHARED, fd, 0); - if (map->base == MAP_FAILED) { - pr_debug2("failed to mmap perf event ring buffer, error %d\n", - errno); - map->base = NULL; - return -1; - } - map->fd = fd; - - if (auxtrace_mmap__mmap(&map->auxtrace_mmap, - &mp->auxtrace_mp, map->base, fd)) - return -1; - - return 0; -} - static bool perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused, struct perf_evsel *evsel) |