diff options
Diffstat (limited to 'tools/lib/perf')
| -rw-r--r-- | tools/lib/perf/evlist.c | 84 | ||||
| -rw-r--r-- | tools/lib/perf/evsel.c | 51 | ||||
| -rw-r--r-- | tools/lib/perf/include/internal/evlist.h | 3 | ||||
| -rw-r--r-- | tools/lib/perf/include/internal/evsel.h | 11 | ||||
| -rw-r--r-- | tools/lib/perf/include/internal/lib.h | 2 | ||||
| -rw-r--r-- | tools/lib/perf/include/perf/cpumap.h | 3 | ||||
| -rw-r--r-- | tools/lib/perf/include/perf/evsel.h | 1 | ||||
| -rw-r--r-- | tools/lib/perf/lib.c | 20 |
8 files changed, 115 insertions, 60 deletions
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index a09315538a30..e6c98a6e3908 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -23,6 +23,7 @@ #include <perf/cpumap.h> #include <perf/threadmap.h> #include <api/fd/array.h> +#include "internal.h" void perf_evlist__init(struct perf_evlist *evlist) { @@ -39,10 +40,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, * We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ - if (!evsel->own_cpus || evlist->has_user_cpus) { - perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); - } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) { + if (!evsel->own_cpus || + (!evsel->system_wide && evlist->has_user_cpus) || + (!evsel->system_wide && + !evsel->requires_cpu && + perf_cpu_map__empty(evlist->user_requested_cpus))) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); } else if (evsel->cpus != evsel->own_cpus) { @@ -50,8 +52,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, evsel->cpus = perf_cpu_map__get(evsel->own_cpus); } - perf_thread_map__put(evsel->threads); - evsel->threads = perf_thread_map__get(evlist->threads); + if (!evsel->system_wide) { + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__get(evlist->threads); + } + evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus); } @@ -59,6 +64,10 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { struct perf_evsel *evsel; + /* Recomputing all_cpus, so start with a blank slate. */ + perf_cpu_map__put(evlist->all_cpus); + evlist->all_cpus = NULL; + perf_evlist__for_each_evsel(evlist, evsel) __perf_evlist__propagate_maps(evlist, evsel); } @@ -294,7 +303,7 @@ add: int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { - int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); int nr_threads = perf_thread_map__nr(evlist->threads); int nfds = 0; struct perf_evsel *evsel; @@ -424,9 +433,9 @@ static void perf_evlist__set_mmap_first(struct perf_evlist *evlist, struct perf_ static int mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, int idx, struct perf_mmap_param *mp, int cpu_idx, - int thread, int *_output, int *_output_overwrite) + int thread, int *_output, int *_output_overwrite, int *nr_mmaps) { - struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx); + struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->all_cpus, cpu_idx); struct perf_evsel *evsel; int revent; @@ -474,9 +483,14 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, */ refcount_set(&map->refcnt, 2); + if (ops->idx) + ops->idx(evlist, evsel, mp, idx); + if (ops->mmap(map, mp, *output, evlist_cpu) < 0) return -1; + *nr_mmaps += 1; + if (!idx) perf_evlist__set_mmap_first(evlist, map, overwrite); } else { @@ -506,53 +520,28 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, } static int -mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, - struct perf_mmap_param *mp) -{ - int thread; - int nr_threads = perf_thread_map__nr(evlist->threads); - - for (thread = 0; thread < nr_threads; thread++) { - int output = -1; - int output_overwrite = -1; - - if (ops->idx) - ops->idx(evlist, mp, thread, false); - - if (mmap_per_evsel(evlist, ops, thread, mp, 0, thread, - &output, &output_overwrite)) - goto out_unmap; - } - - return 0; - -out_unmap: - perf_evlist__munmap(evlist); - return -1; -} - -static int mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) { int nr_threads = perf_thread_map__nr(evlist->threads); - int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); + int nr_mmaps = 0; int cpu, thread; for (cpu = 0; cpu < nr_cpus; cpu++) { int output = -1; int output_overwrite = -1; - if (ops->idx) - ops->idx(evlist, mp, cpu, true); - for (thread = 0; thread < nr_threads; thread++) { if (mmap_per_evsel(evlist, ops, cpu, mp, cpu, - thread, &output, &output_overwrite)) + thread, &output, &output_overwrite, &nr_mmaps)) goto out_unmap; } } + if (nr_mmaps != evlist->nr_mmaps) + pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps); + return 0; out_unmap: @@ -564,9 +553,14 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) { int nr_mmaps; - nr_mmaps = perf_cpu_map__nr(evlist->user_requested_cpus); - if (perf_cpu_map__empty(evlist->user_requested_cpus)) - nr_mmaps = perf_thread_map__nr(evlist->threads); + /* One for each CPU */ + nr_mmaps = perf_cpu_map__nr(evlist->all_cpus); + if (perf_cpu_map__empty(evlist->all_cpus)) { + /* Plus one for each thread */ + nr_mmaps += perf_thread_map__nr(evlist->threads); + /* Minus the per-thread CPU (-1) */ + nr_mmaps -= 1; + } return nr_mmaps; } @@ -576,7 +570,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, struct perf_mmap_param *mp) { struct perf_evsel *evsel; - const struct perf_cpu_map *cpus = evlist->user_requested_cpus; if (!ops || !ops->get || !ops->mmap) return -EINVAL; @@ -595,9 +588,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) return -ENOMEM; - if (perf_cpu_map__empty(cpus)) - return mmap_per_thread(evlist, ops, mp); - return mmap_per_cpu(evlist, ops, mp); } diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 210ea7c06ce8..952f3520d5c2 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -149,23 +149,30 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, int fd, group_fd, *evsel_fd; evsel_fd = FD(evsel, idx, thread); - if (evsel_fd == NULL) - return -EINVAL; + if (evsel_fd == NULL) { + err = -EINVAL; + goto out; + } err = get_group_fd(evsel, idx, thread, &group_fd); if (err < 0) - return err; + goto out; fd = sys_perf_event_open(&evsel->attr, threads->map[thread].pid, cpu, group_fd, 0); - if (fd < 0) - return -errno; + if (fd < 0) { + err = -errno; + goto out; + } *evsel_fd = fd; } } +out: + if (err) + perf_evsel__close(evsel); return err; } @@ -328,6 +335,17 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, return 0; } +static int perf_evsel__ioctl(struct perf_evsel *evsel, int ioc, void *arg, + int cpu_map_idx, int thread) +{ + int *fd = FD(evsel, cpu_map_idx, thread); + + if (fd == NULL || *fd < 0) + return -1; + + return ioctl(*fd, ioc, arg); +} + static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ioc, void *arg, int cpu_map_idx) @@ -335,13 +353,7 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int err; - int *fd = FD(evsel, cpu_map_idx, thread); - - if (fd == NULL || *fd < 0) - return -1; - - err = ioctl(*fd, ioc, arg); + int err = perf_evsel__ioctl(evsel, ioc, arg, cpu_map_idx, thread); if (err) return err; @@ -355,6 +367,21 @@ 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_map_idx); } +int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread) +{ + struct perf_cpu cpu __maybe_unused; + int idx; + int err; + + perf_cpu_map__for_each_cpu(cpu, idx, evsel->cpus) { + err = perf_evsel__ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, idx, thread); + if (err) + return err; + } + + return 0; +} + int perf_evsel__enable(struct perf_evsel *evsel) { int i; diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index e3e64f37db7b..6f89aec3e608 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -38,7 +38,8 @@ struct perf_evlist { }; typedef void -(*perf_evlist_mmap__cb_idx_t)(struct perf_evlist*, struct perf_mmap_param*, int, bool); +(*perf_evlist_mmap__cb_idx_t)(struct perf_evlist*, struct perf_evsel*, + struct perf_mmap_param*, int); typedef struct perf_mmap* (*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int); typedef int diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h index cfc9ebd7968e..2a912a1f1989 100644 --- a/tools/lib/perf/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h @@ -49,7 +49,18 @@ struct perf_evsel { /* parse modifier helper */ int nr_members; + /* + * system_wide is for events that need to be on every CPU, irrespective + * of user requested CPUs or threads. Map propagation will set cpus to + * this event's own_cpus, whereby they will contribute to evlist + * all_cpus. + */ bool system_wide; + /* + * Some events, for example uncore events, require a CPU. + * i.e. it cannot be the 'any CPU' value of -1. + */ + bool requires_cpu; int idx; }; diff --git a/tools/lib/perf/include/internal/lib.h b/tools/lib/perf/include/internal/lib.h index 5175d491b2d4..85471a4b900f 100644 --- a/tools/lib/perf/include/internal/lib.h +++ b/tools/lib/perf/include/internal/lib.h @@ -9,4 +9,6 @@ extern unsigned int page_size; ssize_t readn(int fd, void *buf, size_t n); ssize_t writen(int fd, const void *buf, size_t n); +ssize_t preadn(int fd, void *buf, size_t n, off_t offs); + #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 4a2edbdb5e2b..24de795b09bb 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -31,4 +31,7 @@ LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_c (idx) < perf_cpu_map__nr(cpus); \ (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx)) +#define perf_cpu_map__for_each_idx(idx, cpus) \ + for ((idx) = 0; (idx) < perf_cpu_map__nr(cpus); (idx)++) + #endif /* __LIBPERF_CPUMAP_H */ diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h index 2a9516b42d15..699c0ed97d34 100644 --- a/tools/lib/perf/include/perf/evsel.h +++ b/tools/lib/perf/include/perf/evsel.h @@ -36,6 +36,7 @@ LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); +LIBPERF_API int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); diff --git a/tools/lib/perf/lib.c b/tools/lib/perf/lib.c index 18658931fc71..696fb0ea67c6 100644 --- a/tools/lib/perf/lib.c +++ b/tools/lib/perf/lib.c @@ -38,6 +38,26 @@ ssize_t readn(int fd, void *buf, size_t n) return ion(true, fd, buf, n); } +ssize_t preadn(int fd, void *buf, size_t n, off_t offs) +{ + size_t left = n; + + while (left) { + ssize_t ret = pread(fd, buf, left, offs); + + if (ret < 0 && errno == EINTR) + continue; + if (ret <= 0) + return ret; + + left -= ret; + buf += ret; + offs += ret; + } + + return n; +} + /* * Write exactly 'n' bytes or return an error. */ |