diff options
Diffstat (limited to 'tools/lib/perf/evlist.c')
| -rw-r--r-- | tools/lib/perf/evlist.c | 262 |
1 files changed, 203 insertions, 59 deletions
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 9a770bfdc804..3ed023f4b190 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) { @@ -35,31 +36,112 @@ void perf_evlist__init(struct perf_evlist *evlist) static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, struct perf_evsel *evsel) { + if (perf_cpu_map__is_empty(evsel->cpus)) { + if (perf_cpu_map__is_empty(evsel->pmu_cpus)) { + /* + * Assume the unset PMU cpus were for a system-wide + * event, like a software or tracepoint. + */ + evsel->pmu_cpus = perf_cpu_map__new_online_cpus(); + } + if (evlist->has_user_cpus && !evsel->system_wide) { + /* + * Use the user CPUs unless the evsel is set to be + * system wide, such as the dummy event. + */ + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } else { + /* + * System wide and other modes, assume the cpu map + * should be set to all PMU CPUs. + */ + evsel->cpus = perf_cpu_map__get(evsel->pmu_cpus); + } + } /* - * We already have cpus for evsel (via PMU sysfs) so - * keep it, if there's no target cpu list defined. + * Avoid "any CPU"(-1) for uncore and PMUs that require a CPU, even if + * requested. */ - if (!evsel->own_cpus || evlist->has_user_cpus) { + if (evsel->requires_cpu && perf_cpu_map__has_any_cpu(evsel->cpus)) { perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->cpus); - } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) { + evsel->cpus = perf_cpu_map__get(evsel->pmu_cpus); + } + + /* + * Globally requested CPUs replace user requested unless the evsel is + * set to be system wide. + */ + if (evlist->has_user_cpus && !evsel->system_wide) { + assert(!perf_cpu_map__has_any_cpu(evlist->user_requested_cpus)); + if (!perf_cpu_map__equal(evsel->cpus, evlist->user_requested_cpus)) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } + } + + /* Ensure cpus only references valid PMU CPUs. */ + if (!perf_cpu_map__has_any_cpu(evsel->cpus) && + !perf_cpu_map__is_subset(evsel->pmu_cpus, evsel->cpus)) { + struct perf_cpu_map *tmp = perf_cpu_map__intersect(evsel->pmu_cpus, evsel->cpus); + perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->cpus); - } else if (evsel->cpus != evsel->own_cpus) { + evsel->cpus = tmp; + } + + /* + * Was event requested on all the PMU's CPUs but the user requested is + * any CPU (-1)? If so switch to using any CPU (-1) to reduce the number + * of events. + */ + if (!evsel->system_wide && + !evsel->requires_cpu && + perf_cpu_map__equal(evsel->cpus, evsel->pmu_cpus) && + perf_cpu_map__has_any_cpu(evlist->user_requested_cpus)) { perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evsel->own_cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); } - 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); + /* Sanity check assert before the evsel is potentially removed. */ + assert(!evsel->requires_cpu || !perf_cpu_map__has_any_cpu(evsel->cpus)); + + /* + * Empty cpu lists would eventually get opened as "any" so remove + * genuinely empty ones before they're opened in the wrong place. + */ + if (perf_cpu_map__is_empty(evsel->cpus)) { + struct perf_evsel *next = perf_evlist__next(evlist, evsel); + + perf_evlist__remove(evlist, evsel); + /* Keep idx contiguous */ + if (next) + list_for_each_entry_from(next, &evlist->entries, node) + next->idx--; + + return; + } + + if (evsel->system_wide) { + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__new_dummy(); + } else { + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__get(evlist->threads); + } + + perf_cpu_map__merge(&evlist->all_cpus, evsel->cpus); } static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { - struct perf_evsel *evsel; + struct perf_evsel *evsel, *n; + + evlist->needs_map_propagation = true; + + /* Clear the all_cpus set which will be merged into during propagation. */ + perf_cpu_map__put(evlist->all_cpus); + evlist->all_cpus = NULL; - perf_evlist__for_each_evsel(evlist, evsel) + list_for_each_entry_safe(evsel, n, &evlist->entries, node) __perf_evlist__propagate_maps(evlist, evsel); } @@ -69,7 +151,9 @@ void perf_evlist__add(struct perf_evlist *evlist, evsel->idx = evlist->nr_entries; list_add_tail(&evsel->node, &evlist->entries); evlist->nr_entries += 1; - __perf_evlist__propagate_maps(evlist, evsel); + + if (evlist->needs_map_propagation) + __perf_evlist__propagate_maps(evlist, evsel); } void perf_evlist__remove(struct perf_evlist *evlist, @@ -123,10 +207,10 @@ static void perf_evlist__purge(struct perf_evlist *evlist) void perf_evlist__exit(struct perf_evlist *evlist) { - perf_cpu_map__put(evlist->cpus); + perf_cpu_map__put(evlist->user_requested_cpus); perf_cpu_map__put(evlist->all_cpus); perf_thread_map__put(evlist->threads); - evlist->cpus = NULL; + evlist->user_requested_cpus = NULL; evlist->all_cpus = NULL; evlist->threads = NULL; fdarray__exit(&evlist->pollfd); @@ -155,9 +239,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, * original reference count of 1. If that is not the case it is up to * the caller to increase the reference count. */ - if (cpus != evlist->cpus) { - perf_cpu_map__put(evlist->cpus); - evlist->cpus = perf_cpu_map__get(cpus); + if (cpus != evlist->user_requested_cpus) { + perf_cpu_map__put(evlist->user_requested_cpus); + evlist->user_requested_cpus = perf_cpu_map__get(cpus); } if (threads != evlist->threads) { @@ -165,9 +249,6 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, evlist->threads = perf_thread_map__get(threads); } - if (!evlist->all_cpus && cpus) - evlist->all_cpus = perf_cpu_map__get(cpus); - perf_evlist__propagate_maps(evlist); } @@ -224,10 +305,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist) static void perf_evlist__id_hash(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { int hash; - struct perf_sample_id *sid = SID(evsel, cpu, thread); + struct perf_sample_id *sid = SID(evsel, cpu_map_idx, thread); sid->id = id; sid->evsel = evsel; @@ -245,21 +326,27 @@ void perf_evlist__reset_id_hash(struct perf_evlist *evlist) void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { - perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + if (!SID(evsel, cpu_map_idx, thread)) + return; + + perf_evlist__id_hash(evlist, evsel, cpu_map_idx, thread, id); evsel->id[evsel->ids++] = id; } int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd) + int cpu_map_idx, int thread, int fd) { u64 read_data[4] = { 0, }; int id_idx = 1; /* The first entry is the counter value */ u64 id; int ret; + if (!SID(evsel, cpu_map_idx, thread)) + return -1; + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); if (!ret) goto add; @@ -288,13 +375,13 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, id = read_data[id_idx]; add: - perf_evlist__id_add(evlist, evsel, cpu, thread, id); + perf_evlist__id_add(evlist, evsel, cpu_map_idx, thread, id); return 0; } int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { - int nr_cpus = perf_cpu_map__nr(evlist->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; @@ -424,14 +511,15 @@ 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->cpus, cpu_idx); + struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->all_cpus, cpu_idx); struct perf_evsel *evsel; int revent; perf_evlist__for_each_entry(evlist, evsel) { bool overwrite = evsel->attr.write_backward; + enum fdarray_flags flgs; struct perf_mmap *map; int *output, fd, cpu; @@ -474,12 +562,21 @@ 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); + + /* Debug message used by test scripts */ + pr_debug("idx %d: mmapping fd %d\n", idx, *output); 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 { + /* Debug message used by test scripts */ + pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output); if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) return -1; @@ -488,8 +585,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, revent = !overwrite ? POLLIN : 0; - if (!evsel->system_wide && - perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) { + flgs = evsel->system_wide ? fdarray_flag__nonfilterable : fdarray_flag__default; + if (perf_evlist__add_pollfd(evlist, fd, map, revent, flgs) < 0) { perf_mmap__put(map); return -1; } @@ -509,21 +606,37 @@ 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); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); + int cpu, thread, idx = 0; + int nr_mmaps = 0; - for (thread = 0; thread < nr_threads; thread++) { + pr_debug("%s: nr cpu values (may include -1) %d nr threads %d\n", + __func__, nr_cpus, nr_threads); + + /* per-thread mmaps */ + for (thread = 0; thread < nr_threads; thread++, idx++) { int output = -1; int output_overwrite = -1; - if (ops->idx) - ops->idx(evlist, mp, thread, false); + if (mmap_per_evsel(evlist, ops, idx, mp, 0, thread, &output, + &output_overwrite, &nr_mmaps)) + goto out_unmap; + } - if (mmap_per_evsel(evlist, ops, thread, mp, 0, thread, - &output, &output_overwrite)) + /* system-wide mmaps i.e. per-cpu */ + for (cpu = 1; cpu < nr_cpus; cpu++, idx++) { + int output = -1; + int output_overwrite = -1; + + if (mmap_per_evsel(evlist, ops, idx, mp, cpu, 0, &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: @@ -536,23 +649,26 @@ 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->cpus); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); + int nr_mmaps = 0; int cpu, thread; + pr_debug("%s: nr cpu values %d nr threads %d\n", __func__, nr_cpus, nr_threads); + 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 +680,14 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) { int nr_mmaps; - nr_mmaps = perf_cpu_map__nr(evlist->cpus); - if (perf_cpu_map__empty(evlist->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__has_any_cpu_or_is_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; } @@ -575,9 +696,8 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) { + const struct perf_cpu_map *cpus = evlist->all_cpus; struct perf_evsel *evsel; - const struct perf_cpu_map *cpus = evlist->cpus; - const struct perf_thread_map *threads = evlist->threads; if (!ops || !ops->get || !ops->mmap) return -EINVAL; @@ -589,14 +709,14 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, perf_evlist__for_each_entry(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) + perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0) return -ENOMEM; } if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) return -ENOMEM; - if (perf_cpu_map__empty(cpus)) + if (perf_cpu_map__has_any_cpu_or_is_empty(cpus)) return mmap_per_thread(evlist, ops, mp); return mmap_per_cpu(evlist, ops, mp); @@ -645,15 +765,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map, void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader) { - struct perf_evsel *first, *last, *evsel; - - first = list_first_entry(list, struct perf_evsel, node); - last = list_last_entry(list, struct perf_evsel, node); - - leader->nr_members = last->idx - first->idx + 1; + struct perf_evsel *evsel; + int n = 0; - __perf_evlist__for_each_entry(list, evsel) + __perf_evlist__for_each_entry(list, evsel) { evsel->leader = leader; + n++; + } + leader->nr_members = n; } void perf_evlist__set_leader(struct perf_evlist *evlist) @@ -662,7 +781,32 @@ void perf_evlist__set_leader(struct perf_evlist *evlist) struct perf_evsel *first = list_entry(evlist->entries.next, struct perf_evsel, node); - evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; __perf_evlist__set_leader(&evlist->entries, first); } } + +int perf_evlist__nr_groups(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int nr_groups = 0; + + perf_evlist__for_each_evsel(evlist, evsel) { + /* + * evsels by default have a nr_members of 1, and they are their + * own leader. If the nr_members is >1 then this is an + * indication of a group. + */ + if (evsel->leader == evsel && evsel->nr_members > 1) + nr_groups++; + } + return nr_groups; +} + +void perf_evlist__go_system_wide(struct perf_evlist *evlist, struct perf_evsel *evsel) +{ + if (!evsel->system_wide) { + evsel->system_wide = true; + if (evlist->needs_map_propagation) + __perf_evlist__propagate_maps(evlist, evsel); + } +} |