diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-18 06:32:11 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-18 06:32:11 +0200 |
commit | 57d17378a4a042401b0c2fe211e5a0e3a276cb3d (patch) | |
tree | be65e51a7b11cccb903b44708b98b3af47477304 /tools/lib/perf/evsel.c | |
parent | f0033681f0fe8421baf8db125e57fa6157824c2d (diff) | |
parent | 9bce13ea88f85344b765abe5d3dabdd0f44dc177 (diff) |
Merge tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tool updates from Arnaldo Carvalho de Melo:
"New features:
- Add 'trace' subcommand for 'perf ftrace', setting the stage for
more 'perf ftrace' subcommands. Not using a subcommand yields the
previous behaviour of 'perf ftrace'.
- Add 'latency' subcommand to 'perf ftrace', that can use the
function graph tracer or a BPF optimized one, via the -b/--use-bpf
option.
E.g.:
$ sudo perf ftrace latency -a -T mutex_lock sleep 1
# DURATION | COUNT | GRAPH |
0 - 1 us | 4596 | ######################## |
1 - 2 us | 1680 | ######### |
2 - 4 us | 1106 | ##### |
4 - 8 us | 546 | ## |
8 - 16 us | 562 | ### |
16 - 32 us | 1 | |
32 - 64 us | 0 | |
64 - 128 us | 0 | |
128 - 256 us | 0 | |
256 - 512 us | 0 | |
512 - 1024 us | 0 | |
1 - 2 ms | 0 | |
2 - 4 ms | 0 | |
4 - 8 ms | 0 | |
8 - 16 ms | 0 | |
16 - 32 ms | 0 | |
32 - 64 ms | 0 | |
64 - 128 ms | 0 | |
128 - 256 ms | 0 | |
256 - 512 ms | 0 | |
512 - 1024 ms | 0 | |
1 - ... s | 0 | |
The original implementation of this command was in the bcc tool.
- Support --cputype option for hybrid events in 'perf stat'.
Improvements:
- Call chain improvements for ARM64.
- No need to do any affinity setup when profiling pids.
- Reduce multiplexing with duration_time in 'perf stat' metrics.
- Improve error message for uncore events, stating that some event
groups are can only be used in system wide (-a) mode.
- perf stat metric group leader fixes/improvements, including arch
specific changes to better support Intel topdown events.
- Probe non-deprecated sysfs path first, i.e. try the path
/sys/devices/system/cpu/cpuN/topology/thread_siblings first, then
the old /sys/devices/system/cpu/cpuN/topology/core_cpus.
- Disable debuginfod by default in 'perf record', to avoid stalls on
distros such as Fedora 35.
- Use unbuffered output in 'perf bench' when pipe/tee'ing to a file.
- Enable ignore_missing_thread in 'perf trace'
Fixes:
- Avoid TUI crash when navigating in the annotation of recursive
functions.
- Fix hex dump character output in 'perf script'.
- Fix JSON indentation to 4 spaces standard in the ARM vendor event
files.
- Fix use after free in metric__new().
- Fix IS_ERR_OR_NULL() usage in the perf BPF loader.
- Fix up cross-arch register support, i.e. when printing register
names take into account the architecture where the perf.data file
was collected.
- Fix SMT fallback with large core counts.
- Don't lower case MetricExpr when parsing JSON files so as not to
lose info such as the ":G" event modifier in metrics.
perf test:
- Add basic stress test for sigtrap handling to 'perf test'.
- Fix 'perf test' failures on s/390
- Enable system wide for metricgroups test in 'perf test´.
- Use 3 digits for test numbering now we can have more tests.
Arch specific:
- Add events for Arm Neoverse N2 in the ARM JSON vendor event files
- Support PERF_MEM_LVLNUM encodings in powerpc, that came from a
single patch series, where I incorrectly merged the kernel bits,
that were then reverted after coordination with Michael Ellerman
and Stephen Rothwell.
- Add ARM SPE total latency as PERF_SAMPLE_WEIGHT.
- Update AMD documentation, with info on raw event encoding.
- Add support for global and local variants of the "p_stage_cyc" sort
key, applicable to perf.data files collected on powerpc.
- Remove duplicate and incorrect aux size checks in the ARM CoreSight
ETM code.
Refactorings:
- Add a perf_cpu abstraction to disambiguate CPUs and CPU map
indexes, fixing problems along the way.
- Document CPU map methods.
UAPI sync:
- Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench
mem memcpy'
- Sync UAPI files with the kernel sources: drm, msr-index,
cpufeatures.
Build system
- Enable warnings through HOSTCFLAGS.
- Drop requirement for libstdc++.so for libopencsd check
libperf:
- Make libperf adopt perf_counts_values__scale() from tools/perf/util/.
- Add a stat multiplexing test to libperf"
* tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (115 commits)
perf record: Disable debuginfod by default
perf evlist: No need to do any affinity setup when profiling pids
perf cpumap: Add is_dummy() method
perf metric: Fix metric_leader
perf cputopo: Fix CPU topology reading on s/390
perf metricgroup: Fix use after free in metric__new()
libperf tests: Update a use of the new cpumap API
perf arm: Fix off-by-one directory path
tools arch x86: Sync the msr-index.h copy with the kernel sources
tools headers cpufeatures: Sync with the kernel sources
tools headers UAPI: Update tools's copy of drm.h header
tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy'
perf pmu-events: Don't lower case MetricExpr
perf expr: Add debug logging for literals
perf tools: Probe non-deprecated sysfs path 1st
perf tools: Fix SMT fallback with large core counts
perf cpumap: Give CPUs their own type
perf stat: Correct first_shadow_cpu to return index
perf script: Fix flipped index and cpu
perf c2c: Use more intention revealing iterator
...
Diffstat (limited to 'tools/lib/perf/evsel.c')
-rw-r--r-- | tools/lib/perf/evsel.c | 111 |
1 files changed, 67 insertions, 44 deletions
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 8441e3e1aaac..7ea86a44eae5 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -43,18 +43,22 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } -#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y)) -#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL) +#define FD(_evsel, _cpu_map_idx, _thread) \ + ((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread)) +#define MMAP(_evsel, _cpu_map_idx, _thread) \ + (_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \ + : NULL) int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); if (evsel->fd) { - int cpu, thread; - for (cpu = 0; cpu < ncpus; cpu++) { + int idx, thread; + + for (idx = 0; idx < ncpus; idx++) { for (thread = 0; thread < nthreads; thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); if (fd) *fd = -1; @@ -74,13 +78,13 @@ static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthre static int sys_perf_event_open(struct perf_event_attr *attr, - pid_t pid, int cpu, int group_fd, + pid_t pid, struct perf_cpu cpu, int group_fd, unsigned long flags) { - return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); + return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags); } -static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd) +static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd) { struct perf_evsel *leader = evsel->leader; int *fd; @@ -97,7 +101,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou if (!leader->fd) return -ENOTCONN; - fd = FD(leader, cpu, thread); + fd = FD(leader, cpu_map_idx, thread); if (fd == NULL || *fd == -1) return -EBADF; @@ -109,7 +113,8 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads) { - int cpu, thread, err = 0; + struct perf_cpu cpu; + int idx, thread, err = 0; if (cpus == NULL) { static struct perf_cpu_map *empty_cpu_map; @@ -139,21 +144,21 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) return -ENOMEM; - for (cpu = 0; cpu < cpus->nr; cpu++) { + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { for (thread = 0; thread < threads->nr; thread++) { int fd, group_fd, *evsel_fd; - evsel_fd = FD(evsel, cpu, thread); + evsel_fd = FD(evsel, idx, thread); if (evsel_fd == NULL) return -EINVAL; - err = get_group_fd(evsel, cpu, thread, &group_fd); + err = get_group_fd(evsel, idx, thread, &group_fd); if (err < 0) return err; fd = sys_perf_event_open(&evsel->attr, threads->map[thread].pid, - cpus->map[cpu], group_fd, 0); + cpu, group_fd, 0); if (fd < 0) return -errno; @@ -165,12 +170,12 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, return err; } -static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) +static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx) { int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); if (fd && *fd >= 0) { close(*fd); @@ -181,10 +186,8 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) void perf_evsel__close_fd(struct perf_evsel *evsel) { - int cpu; - - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) - perf_evsel__close_fd_cpu(evsel, cpu); + for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++) + perf_evsel__close_fd_cpu(evsel, idx); } void perf_evsel__free_fd(struct perf_evsel *evsel) @@ -202,29 +205,29 @@ void perf_evsel__close(struct perf_evsel *evsel) perf_evsel__free_fd(evsel); } -void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu) +void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx) { if (evsel->fd == NULL) return; - perf_evsel__close_fd_cpu(evsel, cpu); + perf_evsel__close_fd_cpu(evsel, cpu_map_idx); } void perf_evsel__munmap(struct perf_evsel *evsel) { - int cpu, thread; + int idx, thread; if (evsel->fd == NULL || evsel->mmap == NULL) return; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); if (fd == NULL || *fd < 0) continue; - perf_mmap__munmap(MMAP(evsel, cpu, thread)); + perf_mmap__munmap(MMAP(evsel, idx, thread)); } } @@ -234,7 +237,7 @@ void perf_evsel__munmap(struct perf_evsel *evsel) int perf_evsel__mmap(struct perf_evsel *evsel, int pages) { - int ret, cpu, thread; + int ret, idx, thread; struct perf_mmap_param mp = { .prot = PROT_READ | PROT_WRITE, .mask = (pages * page_size) - 1, @@ -246,15 +249,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0) return -ENOMEM; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); struct perf_mmap *map; + struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx); if (fd == NULL || *fd < 0) continue; - map = MMAP(evsel, cpu, thread); + map = MMAP(evsel, idx, thread); perf_mmap__init(map, NULL, false, NULL); ret = perf_mmap__mmap(map, &mp, *fd, cpu); @@ -268,14 +272,14 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) return 0; } -void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread) +void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); - if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL) + if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL) return NULL; - return MMAP(evsel, cpu, thread)->base; + return MMAP(evsel, cpu_map_idx, thread)->base; } int perf_evsel__read_size(struct perf_evsel *evsel) @@ -303,19 +307,19 @@ int perf_evsel__read_size(struct perf_evsel *evsel) return size; } -int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, +int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count) { size_t size = perf_evsel__read_size(evsel); - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); memset(count, 0, sizeof(*count)); if (fd == NULL || *fd < 0) return -EINVAL; - if (MMAP(evsel, cpu, thread) && - !perf_mmap__read_self(MMAP(evsel, cpu, thread), count)) + if (MMAP(evsel, cpu_map_idx, thread) && + !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count)) return 0; if (readn(*fd, count->values, size) <= 0) @@ -326,13 +330,13 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ioc, void *arg, - int cpu) + int cpu_map_idx) { int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { int err; - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); if (fd == NULL || *fd < 0) return -1; @@ -346,9 +350,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, return 0; } -int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu) +int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu); + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx); } int perf_evsel__enable(struct perf_evsel *evsel) @@ -361,9 +365,9 @@ int perf_evsel__enable(struct perf_evsel *evsel) return err; } -int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu) +int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu); + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx); } int perf_evsel__disable(struct perf_evsel *evsel) @@ -431,3 +435,22 @@ void perf_evsel__free_id(struct perf_evsel *evsel) zfree(&evsel->id); evsel->ids = 0; } + +void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, __s8 *pscaled) +{ + s8 scaled = 0; + + if (scale) { + if (count->run == 0) { + scaled = -1; + count->val = 0; + } else if (count->run < count->ena) { + scaled = 1; + count->val = (u64)((double)count->val * count->ena / count->run); + } + } + + if (pscaled) + *pscaled = scaled; +} |