diff options
Diffstat (limited to 'tools/lib/perf')
| -rw-r--r-- | tools/lib/perf/Makefile | 2 | ||||
| -rw-r--r-- | tools/lib/perf/cpumap.c | 94 | ||||
| -rw-r--r-- | tools/lib/perf/evlist.c | 31 | ||||
| -rw-r--r-- | tools/lib/perf/include/internal/cpumap.h | 10 | ||||
| -rw-r--r-- | tools/lib/perf/include/internal/evlist.h | 1 | ||||
| -rw-r--r-- | tools/lib/perf/include/internal/rc_check.h | 102 | ||||
| -rw-r--r-- | tools/lib/perf/include/perf/event.h | 2 | ||||
| -rw-r--r-- | tools/lib/perf/include/perf/evlist.h | 1 |
8 files changed, 191 insertions, 52 deletions
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile index d8cad124e4c5..3a9b2140aa04 100644 --- a/tools/lib/perf/Makefile +++ b/tools/lib/perf/Makefile @@ -188,7 +188,7 @@ install_lib: libs cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ) HDRS := bpf_perf.h core.h cpumap.h threadmap.h evlist.h evsel.h event.h mmap.h -INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h threadmap.h xyarray.h +INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h rc_check.h threadmap.h xyarray.h INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/perf INSTALL_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(HDRS)) diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 6cd0be7c1bb4..1229b18bcdb1 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -10,16 +10,21 @@ #include <ctype.h> #include <limits.h> -static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) +void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus) { - struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); + RC_CHK_ACCESS(map)->nr = nr_cpus; +} - if (cpus != NULL) { +struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) +{ + RC_STRUCT(perf_cpu_map) *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); + struct perf_cpu_map *result; + + if (ADD_RC_CHK(result, cpus)) { cpus->nr = nr_cpus; refcount_set(&cpus->refcnt, 1); - } - return cpus; + return result; } struct perf_cpu_map *perf_cpu_map__dummy_new(void) @@ -27,7 +32,7 @@ struct perf_cpu_map *perf_cpu_map__dummy_new(void) struct perf_cpu_map *cpus = perf_cpu_map__alloc(1); if (cpus) - cpus->map[0].cpu = -1; + RC_CHK_ACCESS(cpus)->map[0].cpu = -1; return cpus; } @@ -35,23 +40,30 @@ struct perf_cpu_map *perf_cpu_map__dummy_new(void) static void cpu_map__delete(struct perf_cpu_map *map) { if (map) { - WARN_ONCE(refcount_read(&map->refcnt) != 0, + WARN_ONCE(refcount_read(perf_cpu_map__refcnt(map)) != 0, "cpu_map refcnt unbalanced\n"); - free(map); + RC_CHK_FREE(map); } } struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map) { - if (map) - refcount_inc(&map->refcnt); - return map; + struct perf_cpu_map *result; + + if (RC_CHK_GET(result, map)) + refcount_inc(perf_cpu_map__refcnt(map)); + + return result; } void perf_cpu_map__put(struct perf_cpu_map *map) { - if (map && refcount_dec_and_test(&map->refcnt)) - cpu_map__delete(map); + if (map) { + if (refcount_dec_and_test(perf_cpu_map__refcnt(map))) + cpu_map__delete(map); + else + RC_CHK_PUT(map); + } } static struct perf_cpu_map *cpu_map__default_new(void) @@ -68,7 +80,7 @@ static struct perf_cpu_map *cpu_map__default_new(void) int i; for (i = 0; i < nr_cpus; ++i) - cpus->map[i].cpu = i; + RC_CHK_ACCESS(cpus)->map[i].cpu = i; } return cpus; @@ -94,15 +106,15 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu int i, j; if (cpus != NULL) { - memcpy(cpus->map, tmp_cpus, payload_size); - qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu); + memcpy(RC_CHK_ACCESS(cpus)->map, tmp_cpus, payload_size); + qsort(RC_CHK_ACCESS(cpus)->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu); /* Remove dups */ j = 0; for (i = 0; i < nr_cpus; i++) { - if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu) - cpus->map[j++].cpu = cpus->map[i].cpu; + if (i == 0 || RC_CHK_ACCESS(cpus)->map[i].cpu != RC_CHK_ACCESS(cpus)->map[i - 1].cpu) + RC_CHK_ACCESS(cpus)->map[j++].cpu = RC_CHK_ACCESS(cpus)->map[i].cpu; } - cpus->nr = j; + perf_cpu_map__set_nr(cpus, j); assert(j <= nr_cpus); } return cpus; @@ -263,20 +275,20 @@ struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) .cpu = -1 }; - if (cpus && idx < cpus->nr) - return cpus->map[idx]; + if (cpus && idx < RC_CHK_ACCESS(cpus)->nr) + return RC_CHK_ACCESS(cpus)->map[idx]; return result; } int perf_cpu_map__nr(const struct perf_cpu_map *cpus) { - return cpus ? cpus->nr : 1; + return cpus ? RC_CHK_ACCESS(cpus)->nr : 1; } bool perf_cpu_map__empty(const struct perf_cpu_map *map) { - return map ? map->map[0].cpu == -1 : true; + return map ? RC_CHK_ACCESS(map)->map[0].cpu == -1 : true; } int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) @@ -287,10 +299,10 @@ int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) return -1; low = 0; - high = cpus->nr; + high = RC_CHK_ACCESS(cpus)->nr; while (low < high) { int idx = (low + high) / 2; - struct perf_cpu cpu_at_idx = cpus->map[idx]; + struct perf_cpu cpu_at_idx = RC_CHK_ACCESS(cpus)->map[idx]; if (cpu_at_idx.cpu == cpu.cpu) return idx; @@ -316,7 +328,7 @@ struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map) }; // cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well. - return map->nr > 0 ? map->map[map->nr - 1] : result; + return RC_CHK_ACCESS(map)->nr > 0 ? RC_CHK_ACCESS(map)->map[RC_CHK_ACCESS(map)->nr - 1] : result; } /** Is 'b' a subset of 'a'. */ @@ -324,15 +336,15 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu { if (a == b || !b) return true; - if (!a || b->nr > a->nr) + if (!a || RC_CHK_ACCESS(b)->nr > RC_CHK_ACCESS(a)->nr) return false; - for (int i = 0, j = 0; i < a->nr; i++) { - if (a->map[i].cpu > b->map[j].cpu) + for (int i = 0, j = 0; i < RC_CHK_ACCESS(a)->nr; i++) { + if (RC_CHK_ACCESS(a)->map[i].cpu > RC_CHK_ACCESS(b)->map[j].cpu) return false; - if (a->map[i].cpu == b->map[j].cpu) { + if (RC_CHK_ACCESS(a)->map[i].cpu == RC_CHK_ACCESS(b)->map[j].cpu) { j++; - if (j == b->nr) + if (j == RC_CHK_ACCESS(b)->nr) return true; } } @@ -362,27 +374,27 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, return perf_cpu_map__get(other); } - tmp_len = orig->nr + other->nr; + tmp_len = RC_CHK_ACCESS(orig)->nr + RC_CHK_ACCESS(other)->nr; tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); if (!tmp_cpus) return NULL; /* Standard merge algorithm from wikipedia */ i = j = k = 0; - while (i < orig->nr && j < other->nr) { - if (orig->map[i].cpu <= other->map[j].cpu) { - if (orig->map[i].cpu == other->map[j].cpu) + while (i < RC_CHK_ACCESS(orig)->nr && j < RC_CHK_ACCESS(other)->nr) { + if (RC_CHK_ACCESS(orig)->map[i].cpu <= RC_CHK_ACCESS(other)->map[j].cpu) { + if (RC_CHK_ACCESS(orig)->map[i].cpu == RC_CHK_ACCESS(other)->map[j].cpu) j++; - tmp_cpus[k++] = orig->map[i++]; + tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++]; } else - tmp_cpus[k++] = other->map[j++]; + tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++]; } - while (i < orig->nr) - tmp_cpus[k++] = orig->map[i++]; + while (i < RC_CHK_ACCESS(orig)->nr) + tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++]; - while (j < other->nr) - tmp_cpus[k++] = other->map[j++]; + while (j < RC_CHK_ACCESS(other)->nr) + tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++]; assert(k <= tmp_len); merged = cpu_map__trim_new(k, tmp_cpus); diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 61b637f29b82..81e8b5fcd8ba 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -687,15 +687,14 @@ 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) @@ -704,7 +703,23 @@ 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; +} diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 35dd29642296..49649eb51ce4 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -4,6 +4,7 @@ #include <linux/refcount.h> #include <perf/cpumap.h> +#include <internal/rc_check.h> /** * A sized, reference counted, sorted array of integers representing CPU @@ -12,7 +13,7 @@ * gaps if CPU numbers were used. For events associated with a pid, rather than * a CPU, a single dummy map with an entry of -1 is used. */ -struct perf_cpu_map { +DECLARE_RC_STRUCT(perf_cpu_map) { refcount_t refcnt; /** Length of the map array. */ int nr; @@ -24,7 +25,14 @@ struct perf_cpu_map { #define MAX_NR_CPUS 2048 #endif +struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus); int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu); bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b); +void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus); + +static inline refcount_t *perf_cpu_map__refcnt(struct perf_cpu_map *map) +{ + return &RC_CHK_ACCESS(map)->refcnt; +} #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index 850f07070036..3339bc2f1765 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -17,7 +17,6 @@ struct perf_mmap_param; struct perf_evlist { struct list_head entries; int nr_entries; - int nr_groups; bool has_user_cpus; bool needs_map_propagation; /** diff --git a/tools/lib/perf/include/internal/rc_check.h b/tools/lib/perf/include/internal/rc_check.h new file mode 100644 index 000000000000..d5d771ccdc7b --- /dev/null +++ b/tools/lib/perf/include/internal/rc_check.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __LIBPERF_INTERNAL_RC_CHECK_H +#define __LIBPERF_INTERNAL_RC_CHECK_H + +#include <stdlib.h> +#include <linux/zalloc.h> + +/* + * Enable reference count checking implicitly with leak checking, which is + * integrated into address sanitizer. + */ +#if defined(LEAK_SANITIZER) || defined(ADDRESS_SANITIZER) +#define REFCNT_CHECKING 1 +#endif + +/* + * Shared reference count checking macros. + * + * Reference count checking is an approach to sanitizing the use of reference + * counted structs. It leverages address and leak sanitizers to make sure gets + * are paired with a put. Reference count checking adds a malloc-ed layer of + * indirection on a get, and frees it on a put. A missed put will be reported as + * a memory leak. A double put will be reported as a double free. Accessing + * after a put will cause a use-after-free and/or a segfault. + */ + +#ifndef REFCNT_CHECKING +/* Replaces "struct foo" so that the pointer may be interposed. */ +#define DECLARE_RC_STRUCT(struct_name) \ + struct struct_name + +/* Declare a reference counted struct variable. */ +#define RC_STRUCT(struct_name) struct struct_name + +/* + * Interpose the indirection. Result will hold the indirection and object is the + * reference counted struct. + */ +#define ADD_RC_CHK(result, object) (result = object, object) + +/* Strip the indirection layer. */ +#define RC_CHK_ACCESS(object) object + +/* Frees the object and the indirection layer. */ +#define RC_CHK_FREE(object) free(object) + +/* A get operation adding the indirection layer. */ +#define RC_CHK_GET(result, object) ADD_RC_CHK(result, object) + +/* A put operation removing the indirection layer. */ +#define RC_CHK_PUT(object) {} + +#else + +/* Replaces "struct foo" so that the pointer may be interposed. */ +#define DECLARE_RC_STRUCT(struct_name) \ + struct original_##struct_name; \ + struct struct_name { \ + struct original_##struct_name *orig; \ + }; \ + struct original_##struct_name + +/* Declare a reference counted struct variable. */ +#define RC_STRUCT(struct_name) struct original_##struct_name + +/* + * Interpose the indirection. Result will hold the indirection and object is the + * reference counted struct. + */ +#define ADD_RC_CHK(result, object) \ + ( \ + object ? (result = malloc(sizeof(*result)), \ + result ? (result->orig = object, result) \ + : (result = NULL, NULL)) \ + : (result = NULL, NULL) \ + ) + +/* Strip the indirection layer. */ +#define RC_CHK_ACCESS(object) object->orig + +/* Frees the object and the indirection layer. */ +#define RC_CHK_FREE(object) \ + do { \ + zfree(&object->orig); \ + free(object); \ + } while(0) + +/* A get operation adding the indirection layer. */ +#define RC_CHK_GET(result, object) ADD_RC_CHK(result, (object ? object->orig : NULL)) + +/* A put operation removing the indirection layer. */ +#define RC_CHK_PUT(object) \ + do { \ + if (object) { \ + object->orig = NULL; \ + free(object); \ + } \ + } while(0) + +#endif + +#endif /* __LIBPERF_INTERNAL_RC_CHECK_H */ diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index ad47d7b31046..51b9338f4c11 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -70,6 +70,8 @@ struct perf_record_lost { __u64 lost; }; +#define PERF_RECORD_MISC_LOST_SAMPLES_BPF (1 << 15) + struct perf_record_lost_samples { struct perf_event_header header; __u64 lost; diff --git a/tools/lib/perf/include/perf/evlist.h b/tools/lib/perf/include/perf/evlist.h index 9ca399d49bb4..e894b770779e 100644 --- a/tools/lib/perf/include/perf/evlist.h +++ b/tools/lib/perf/include/perf/evlist.h @@ -47,4 +47,5 @@ LIBPERF_API struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist, (pos) = perf_evlist__next_mmap((evlist), (pos), overwrite)) LIBPERF_API void perf_evlist__set_leader(struct perf_evlist *evlist); +LIBPERF_API int perf_evlist__nr_groups(struct perf_evlist *evlist); #endif /* __LIBPERF_EVLIST_H */ |