diff options
Diffstat (limited to 'tools/perf/util')
26 files changed, 648 insertions, 229 deletions
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 49ff825f745c..bc3302da702b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -248,7 +248,7 @@ static struct ins_ops call_ops = { bool ins__is_call(const struct ins *ins) { - return ins->ops == &call_ops; + return ins->ops == &call_ops || ins->ops == &s390_call_ops; } static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 6470ea2aa25e..fb357a00dd86 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -233,9 +233,9 @@ static void *auxtrace_copy_data(u64 size, struct perf_session *session) return p; } -static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, - unsigned int idx, - struct auxtrace_buffer *buffer) +static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues, + unsigned int idx, + struct auxtrace_buffer *buffer) { struct auxtrace_queue *queue; int err; @@ -286,7 +286,7 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues, return -ENOMEM; b->size = BUFFER_LIMIT_FOR_32_BIT; b->consecutive = consecutive; - err = auxtrace_queues__add_buffer(queues, idx, b); + err = auxtrace_queues__queue_buffer(queues, idx, b); if (err) { auxtrace_buffer__free(b); return err; @@ -302,11 +302,14 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues, return 0; } -static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues, - struct perf_session *session, - unsigned int idx, - struct auxtrace_buffer *buffer) +static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, + struct perf_session *session, + unsigned int idx, + struct auxtrace_buffer *buffer, + struct auxtrace_buffer **buffer_ptr) { + int err; + if (session->one_mmap) { buffer->data = buffer->data_offset - session->one_mmap_offset + session->one_mmap_addr; @@ -317,14 +320,20 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues, buffer->data_needs_freeing = true; } else if (BITS_PER_LONG == 32 && buffer->size > BUFFER_LIMIT_FOR_32_BIT) { - int err; - err = auxtrace_queues__split_buffer(queues, idx, buffer); if (err) return err; } - return auxtrace_queues__add_buffer(queues, idx, buffer); + err = auxtrace_queues__queue_buffer(queues, idx, buffer); + if (err) + return err; + + /* FIXME: Doesn't work for split buffer */ + if (buffer_ptr) + *buffer_ptr = buffer; + + return 0; } static bool filter_cpu(struct perf_session *session, int cpu) @@ -359,13 +368,11 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, buffer->size = event->auxtrace.size; idx = event->auxtrace.idx; - err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer); + err = auxtrace_queues__add_buffer(queues, session, idx, buffer, + buffer_ptr); if (err) goto out_err; - if (buffer_ptr) - *buffer_ptr = buffer; - return 0; out_err: diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 453c148d2158..e731f55da072 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -130,6 +130,7 @@ struct auxtrace_index { /** * struct auxtrace - session callbacks to allow AUX area data decoding. * @process_event: lets the decoder see all session events + * @process_auxtrace_event: process a PERF_RECORD_AUXTRACE event * @flush_events: process any remaining data * @free_events: free resources associated with event processing * @free: free resources associated with the session @@ -301,6 +302,7 @@ struct auxtrace_mmap_params { * @parse_snapshot_options: parse snapshot options * @reference: provide a 64-bit reference number for auxtrace_event * @read_finish: called after reading from an auxtrace mmap + * @alignment: alignment (if any) for AUX area data */ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 5dd9b5ea314d..78408f5c4bad 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -71,7 +71,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) return -1; } -static int open_cgroup(char *name) +static int open_cgroup(const char *name) { char path[PATH_MAX + 1]; char mnt[PATH_MAX + 1]; @@ -90,41 +90,64 @@ static int open_cgroup(char *name) return fd; } -static int add_cgroup(struct perf_evlist *evlist, char *str) +static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str) { struct perf_evsel *counter; - struct cgroup_sel *cgrp = NULL; - int n; + struct cgroup *cgrp = NULL; /* * check if cgrp is already defined, if so we reuse it */ evlist__for_each_entry(evlist, counter) { - cgrp = counter->cgrp; - if (!cgrp) + if (!counter->cgrp) continue; - if (!strcmp(cgrp->name, str)) { - refcount_inc(&cgrp->refcnt); + if (!strcmp(counter->cgrp->name, str)) { + cgrp = cgroup__get(counter->cgrp); break; } - - cgrp = NULL; } - if (!cgrp) { - cgrp = zalloc(sizeof(*cgrp)); - if (!cgrp) - return -1; + return cgrp; +} + +static struct cgroup *cgroup__new(const char *name) +{ + struct cgroup *cgroup = zalloc(sizeof(*cgroup)); - cgrp->name = str; - refcount_set(&cgrp->refcnt, 1); + if (cgroup != NULL) { + refcount_set(&cgroup->refcnt, 1); - cgrp->fd = open_cgroup(str); - if (cgrp->fd == -1) { - free(cgrp); - return -1; - } + cgroup->name = strdup(name); + if (!cgroup->name) + goto out_err; + cgroup->fd = open_cgroup(name); + if (cgroup->fd == -1) + goto out_free_name; } + return cgroup; + +out_free_name: + free(cgroup->name); +out_err: + free(cgroup); + return NULL; +} + +struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name) +{ + struct cgroup *cgroup = evlist__find_cgroup(evlist, name); + + return cgroup ?: cgroup__new(name); +} + +static int add_cgroup(struct perf_evlist *evlist, const char *str) +{ + struct perf_evsel *counter; + struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str); + int n; + + if (!cgrp) + return -1; /* * find corresponding event * if add cgroup N, then need to find event N @@ -135,30 +158,55 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) goto found; n++; } - if (refcount_dec_and_test(&cgrp->refcnt)) - free(cgrp); + cgroup__put(cgrp); return -1; found: counter->cgrp = cgrp; return 0; } -void close_cgroup(struct cgroup_sel *cgrp) +static void cgroup__delete(struct cgroup *cgroup) +{ + close(cgroup->fd); + zfree(&cgroup->name); + free(cgroup); +} + +void cgroup__put(struct cgroup *cgrp) { if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) { - close(cgrp->fd); - zfree(&cgrp->name); - free(cgrp); + cgroup__delete(cgrp); } } -int parse_cgroups(const struct option *opt __maybe_unused, const char *str, +struct cgroup *cgroup__get(struct cgroup *cgroup) +{ + if (cgroup) + refcount_inc(&cgroup->refcnt); + return cgroup; +} + +static void evsel__set_default_cgroup(struct perf_evsel *evsel, struct cgroup *cgroup) +{ + if (evsel->cgrp == NULL) + evsel->cgrp = cgroup__get(cgroup); +} + +void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup) +{ + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) + evsel__set_default_cgroup(evsel, cgroup); +} + +int parse_cgroups(const struct option *opt, const char *str, int unset __maybe_unused) { struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; struct perf_evsel *counter; - struct cgroup_sel *cgrp = NULL; + struct cgroup *cgrp = NULL; const char *p, *e, *eos = str + strlen(str); char *s; int ret, i; @@ -179,10 +227,9 @@ int parse_cgroups(const struct option *opt __maybe_unused, const char *str, if (!s) return -1; ret = add_cgroup(evlist, s); - if (ret) { - free(s); + free(s); + if (ret) return -1; - } } /* nr_cgroups is increased een for empty cgroups */ nr_cgroups++; diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index afafc87e9201..f033a80c1b14 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -6,7 +6,7 @@ struct option; -struct cgroup_sel { +struct cgroup { char *name; int fd; refcount_t refcnt; @@ -14,7 +14,16 @@ struct cgroup_sel { extern int nr_cgroups; /* number of explicit cgroups defined */ -void close_cgroup(struct cgroup_sel *cgrp); + +struct cgroup *cgroup__get(struct cgroup *cgroup); +void cgroup__put(struct cgroup *cgroup); + +struct perf_evlist; + +struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name); + +void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup); + int parse_cgroups(const struct option *opt, const char *str, int unset); #endif /* __CGROUP_H__ */ diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index bf970f57dce0..c4ef2e523367 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -27,6 +27,12 @@ struct numa_node { struct cpu_map *map; }; +struct memory_node { + u64 node; + u64 size; + unsigned long *set; +}; + struct perf_env { char *hostname; char *os_release; @@ -43,6 +49,7 @@ struct perf_env { int nr_sibling_cores; int nr_sibling_threads; int nr_numa_nodes; + int nr_memory_nodes; int nr_pmu_mappings; int nr_groups; char *cmdline; @@ -54,6 +61,8 @@ struct perf_env { struct cpu_cache_level *caches; int caches_cnt; struct numa_node *numa_nodes; + struct memory_node *memory_nodes; + unsigned long long memory_bsize; }; extern struct perf_env perf_env; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 41a4666f1519..a59281d64368 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -722,7 +722,8 @@ void perf_evlist__munmap(struct perf_evlist *evlist) zfree(&evlist->overwrite_mmap); } -static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) +static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist, + bool overwrite) { int i; struct perf_mmap *map; @@ -736,6 +737,7 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) for (i = 0; i < evlist->nr_mmaps; i++) { map[i].fd = -1; + map[i].overwrite = overwrite; /* * When the perf_mmap() call is made we grab one refcount, plus * one extra to let perf_mmap__consume() get the last @@ -779,7 +781,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, maps = evlist->overwrite_mmap; if (!maps) { - maps = perf_evlist__alloc_mmap(evlist); + maps = perf_evlist__alloc_mmap(evlist, true); if (!maps) return -1; evlist->overwrite_mmap = maps; @@ -1029,7 +1031,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, struct mmap_params mp; if (!evlist->mmap) - evlist->mmap = perf_evlist__alloc_mmap(evlist); + evlist->mmap = perf_evlist__alloc_mmap(evlist, false); if (!evlist->mmap) return -ENOMEM; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index b56e1c2ddaee..1ac8d9236efd 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -244,6 +244,7 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->metric_name = NULL; evsel->metric_events = NULL; evsel->collect_stat = false; + evsel->pmu_name = NULL; } struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -621,22 +622,34 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel) return evsel->group_name ?: "anon group"; } +/* + * Returns the group details for the specified leader, + * with following rules. + * + * For record -e '{cycles,instructions}' + * 'anon group { cycles:u, instructions:u }' + * + * For record -e 'cycles,instructions' and report --group + * 'cycles:u, instructions:u' + */ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) { - int ret; + int ret = 0; struct perf_evsel *pos; const char *group_name = perf_evsel__group_name(evsel); - ret = scnprintf(buf, size, "%s", group_name); + if (!evsel->forced_leader) + ret = scnprintf(buf, size, "%s { ", group_name); - ret += scnprintf(buf + ret, size - ret, " { %s", + ret += scnprintf(buf + ret, size - ret, "%s", perf_evsel__name(evsel)); for_each_group_member(pos, evsel) ret += scnprintf(buf + ret, size - ret, ", %s", perf_evsel__name(pos)); - ret += scnprintf(buf + ret, size - ret, " }"); + if (!evsel->forced_leader) + ret += scnprintf(buf + ret, size - ret, " }"); return ret; } @@ -1233,7 +1246,7 @@ void perf_evsel__exit(struct perf_evsel *evsel) perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); perf_evsel__free_config_terms(evsel); - close_cgroup(evsel->cgrp); + cgroup__put(evsel->cgrp); cpu_map__put(evsel->cpus); cpu_map__put(evsel->own_cpus); thread_map__put(evsel->threads); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index a7487c6d1866..d3ee3af618ef 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -30,7 +30,7 @@ struct perf_sample_id { u64 period; }; -struct cgroup_sel; +struct cgroup; /* * The 'struct perf_evsel_config_term' is used to pass event @@ -107,7 +107,7 @@ struct perf_evsel { struct perf_stat_evsel *stats; void *priv; u64 db_id; - struct cgroup_sel *cgrp; + struct cgroup *cgrp; void *handler; struct cpu_map *cpus; struct cpu_map *own_cpus; @@ -125,6 +125,7 @@ struct perf_evsel { bool per_pkg; bool precise_max; bool ignore_missing_thread; + bool forced_leader; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -142,6 +143,7 @@ struct perf_evsel { struct perf_evsel **metric_events; bool collect_stat; bool weak_group; + const char *pmu_name; }; union u64_swap { diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a326e0d8b5b6..e14b3f7c7212 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -17,6 +17,7 @@ #include <sys/stat.h> #include <sys/utsname.h> #include <linux/time64.h> +#include <dirent.h> #include "evlist.h" #include "evsel.h" @@ -37,6 +38,7 @@ #include "asm/bug.h" #include "tool.h" #include "time-utils.h" +#include "units.h" #include "sane_ctype.h" @@ -132,6 +134,25 @@ int do_write(struct feat_fd *ff, const void *buf, size_t size) } /* Return: 0 if succeded, -ERR if failed. */ +static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size) +{ + u64 *p = (u64 *) set; + int i, ret; + + ret = do_write(ff, &size, sizeof(size)); + if (ret < 0) + return ret; + + for (i = 0; (u64) i < BITS_TO_U64(size); i++) { + ret = do_write(ff, p + i, sizeof(*p)); + if (ret < 0) + return ret; + } + + return 0; +} + +/* Return: 0 if succeded, -ERR if failed. */ int write_padded(struct feat_fd *ff, const void *bf, size_t count, size_t count_aligned) { @@ -243,6 +264,38 @@ static char *do_read_string(struct feat_fd *ff) return NULL; } +/* Return: 0 if succeded, -ERR if failed. */ +static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) +{ + unsigned long *set; + u64 size, *p; + int i, ret; + + ret = do_read_u64(ff, &size); + if (ret) + return ret; + + set = bitmap_alloc(size); + if (!set) + return -ENOMEM; + + bitmap_zero(set, size); + + p = (u64 *) set; + + for (i = 0; (u64) i < BITS_TO_U64(size); i++) { + ret = do_read_u64(ff, p + i); + if (ret < 0) { + free(set); + return ret; + } + } + + *pset = set; + *psize = size; + return 0; +} + static int write_tracing_data(struct feat_fd *ff, struct perf_evlist *evlist) { @@ -1196,6 +1249,176 @@ static int write_sample_time(struct feat_fd *ff, sizeof(evlist->last_sample_time)); } + +static int memory_node__read(struct memory_node *n, unsigned long idx) +{ + unsigned int phys, size = 0; + char path[PATH_MAX]; + struct dirent *ent; + DIR *dir; + +#define for_each_memory(mem, dir) \ + while ((ent = readdir(dir))) \ + if (strcmp(ent->d_name, ".") && \ + strcmp(ent->d_name, "..") && \ + sscanf(ent->d_name, "memory%u", &mem) == 1) + + scnprintf(path, PATH_MAX, + "%s/devices/system/node/node%lu", + sysfs__mountpoint(), idx); + + dir = opendir(path); + if (!dir) { + pr_warning("failed: cant' open memory sysfs data\n"); + return -1; + } + + for_each_memory(phys, dir) { + size = max(phys, size); + } + + size++; + + n->set = bitmap_alloc(size); + if (!n->set) { + closedir(dir); + return -ENOMEM; + } + + bitmap_zero(n->set, size); + n->node = idx; + n->size = size; + + rewinddir(dir); + + for_each_memory(phys, dir) { + set_bit(phys, n->set); + } + + closedir(dir); + return 0; +} + +static int memory_node__sort(const void *a, const void *b) +{ + const struct memory_node *na = a; + const struct memory_node *nb = b; + + return na->node - nb->node; +} + +static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) +{ + char path[PATH_MAX]; + struct dirent *ent; + DIR *dir; + u64 cnt = 0; + int ret = 0; + + scnprintf(path, PATH_MAX, "%s/devices/system/node/", + sysfs__mountpoint()); + + dir = opendir(path); + if (!dir) { + pr_warning("failed: can't open node sysfs data\n"); + return -1; + } + + while (!ret && (ent = readdir(dir))) { + unsigned int idx; + int r; + + if (!strcmp(ent->d_name, ".") || + !strcmp(ent->d_name, "..")) + continue; + + r = sscanf(ent->d_name, "node%u", &idx); + if (r != 1) + continue; + + if (WARN_ONCE(cnt >= size, + "failed to write MEM_TOPOLOGY, way too many nodes\n")) + return -1; + + ret = memory_node__read(&nodes[cnt++], idx); + } + + *cntp = cnt; + closedir(dir); + + if (!ret) + qsort(nodes, cnt, sizeof(nodes[0]), memory_node__sort); + + return ret; +} + +#define MAX_MEMORY_NODES 2000 + +/* + * The MEM_TOPOLOGY holds physical memory map for every + * node in system. The format of data is as follows: + * + * 0 - version | for future changes + * 8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes + * 16 - count | number of nodes + * + * For each node we store map of physical indexes for + * each node: + * + * 32 - node id | node index + * 40 - size | size of bitmap + * 48 - bitmap | bitmap of memory indexes that belongs to node + */ +static int write_mem_topology(struct feat_fd *ff __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + static struct memory_node nodes[MAX_MEMORY_NODES]; + u64 bsize, version = 1, i, nr; + int ret; + + ret = sysfs__read_xll("devices/system/memory/block_size_bytes", + (unsigned long long *) &bsize); + if (ret) + return ret; + + ret = build_mem_topology(&nodes[0], MAX_MEMORY_NODES, &nr); + if (ret) + return ret; + + ret = do_write(ff, &version, sizeof(version)); + if (ret < 0) + goto out; + + ret = do_write(ff, &bsize, sizeof(bsize)); + if (ret < 0) + goto out; + + ret = do_write(ff, &nr, sizeof(nr)); + if (ret < 0) + goto out; + + for (i = 0; i < nr; i++) { + struct memory_node *n = &nodes[i]; + + #define _W(v) \ + ret = do_write(ff, &n->v, sizeof(n->v)); \ + if (ret < 0) \ + goto out; + + _W(node) + _W(size) + + #undef _W + + ret = do_write_bitmap(ff, n->set, n->size); + if (ret < 0) + goto out; + } + +out: + return ret; +} + static void print_hostname(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); @@ -1543,6 +1766,35 @@ static void print_sample_time(struct feat_fd *ff, FILE *fp) fprintf(fp, "# sample duration : %10.3f ms\n", d); } +static void memory_node__fprintf(struct memory_node *n, + unsigned long long bsize, FILE *fp) +{ + char buf_map[100], buf_size[50]; + unsigned long long size; + + size = bsize * bitmap_weight(n->set, n->size); + unit_number__scnprintf(buf_size, 50, size); + + bitmap_scnprintf(n->set, n->size, buf_map, 100); + fprintf(fp, "# %3" PRIu64 " [%s]: %s\n", n->node, buf_size, buf_map); +} + +static void print_mem_topology(struct feat_fd *ff, FILE *fp) +{ + struct memory_node *nodes; + int i, nr; + + nodes = ff->ph->env.memory_nodes; + nr = ff->ph->env.nr_memory_nodes; + + fprintf(fp, "# memory nodes (nr %d, block size 0x%llx):\n", + nr, ff->ph->env.memory_bsize); + + for (i = 0; i < nr; i++) { + memory_node__fprintf(&nodes[i], ff->ph->env.memory_bsize, fp); + } +} + static int __event_process_build_id(struct build_id_event *bev, char *filename, struct perf_session *session) @@ -2205,6 +2457,58 @@ static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused) return 0; } +static int process_mem_topology(struct feat_fd *ff, + void *data __maybe_unused) +{ + struct memory_node *nodes; + u64 version, i, nr, bsize; + int ret = -1; + + if (do_read_u64(ff, &version)) + return -1; + + if (version != 1) + return -1; + + if (do_read_u64(ff, &bsize)) + return -1; + + if (do_read_u64(ff, &nr)) + return -1; + + nodes = zalloc(sizeof(*nodes) * nr); + if (!nodes) + return -1; + + for (i = 0; i < nr; i++) { + struct memory_node n; + + #define _R(v) \ + if (do_read_u64(ff, &n.v)) \ + goto out; \ + + _R(node) + _R(size) + + #undef _R + + if (do_read_bitmap(ff, &n.set, &n.size)) + goto out; + + nodes[i] = n; + } + + ff->ph->env.memory_bsize = bsize; + ff->ph->env.memory_nodes = nodes; + ff->ph->env.nr_memory_nodes = nr; + ret = 0; + +out: + if (ret) + free(nodes); + return ret; +} + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2263,6 +2567,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPN(STAT, stat, false), FEAT_OPN(CACHE, cache, true), FEAT_OPR(SAMPLE_TIME, sample_time, false), + FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), }; struct header_print_data { @@ -2318,7 +2623,12 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) if (ret == -1) return -1; - fprintf(fp, "# captured on: %s", ctime(&st.st_ctime)); + fprintf(fp, "# captured on : %s", ctime(&st.st_ctime)); + + fprintf(fp, "# header version : %u\n", header->version); + fprintf(fp, "# data offset : %" PRIu64 "\n", header->data_offset); + fprintf(fp, "# data size : %" PRIu64 "\n", header->data_size); + fprintf(fp, "# feat offset : %" PRIu64 "\n", header->feat_offset); perf_header__process_sections(header, fd, &hd, perf_file_section__fprintf_info); diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 942bdec6d70d..90d4577a92dc 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -36,6 +36,7 @@ enum { HEADER_STAT, HEADER_CACHE, HEADER_SAMPLE_TIME, + HEADER_MEM_TOPOLOGY, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 44a8456cea10..7d968892ee39 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -536,7 +536,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, * This mem info was allocated from sample__resolve_mem * and will not be used anymore. */ - zfree(&entry->mem_info); + mem_info__zput(entry->mem_info); /* If the map of an existing hist_entry has * become out-of-date due to an exec() or @@ -1139,7 +1139,7 @@ void hist_entry__delete(struct hist_entry *he) if (he->mem_info) { map__zput(he->mem_info->iaddr.map); map__zput(he->mem_info->daddr.map); - zfree(&he->mem_info); + mem_info__zput(he->mem_info); } zfree(&he->stat_acc); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index aa1593ce551d..f9157aed1289 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1378,6 +1378,7 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder) intel_pt_clear_tx_flags(decoder); decoder->have_tma = false; decoder->cbr = 0; + decoder->timestamp_insn_cnt = 0; decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC; decoder->overflow = true; return -EOVERFLOW; @@ -1616,6 +1617,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_PWRX: intel_pt_log("ERROR: Missing TIP after FUP\n"); decoder->pkt_state = INTEL_PT_STATE_ERR3; + decoder->pkt_step = 0; return -ENOENT; case INTEL_PT_OVF: @@ -2390,14 +2392,6 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) return &decoder->state; } -static bool intel_pt_at_psb(unsigned char *buf, size_t len) -{ - if (len < INTEL_PT_PSB_LEN) - return false; - return memmem(buf, INTEL_PT_PSB_LEN, INTEL_PT_PSB_STR, - INTEL_PT_PSB_LEN); -} - /** * intel_pt_next_psb - move buffer pointer to the start of the next PSB packet. * @buf: pointer to buffer pointer @@ -2486,6 +2480,7 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len) * @buf: buffer * @len: size of buffer * @tsc: TSC value returned + * @rem: returns remaining size when TSC is found * * Find a TSC packet in @buf and return the TSC value. This function assumes * that @buf starts at a PSB and that PSB+ will contain TSC and so stops if a @@ -2493,7 +2488,8 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len) * * Return: %true if TSC is found, false otherwise. */ -static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc) +static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc, + size_t *rem) { struct intel_pt_pkt packet; int ret; @@ -2504,6 +2500,7 @@ static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc) return false; if (packet.type == INTEL_PT_TSC) { *tsc = packet.payload; + *rem = len; return true; } if (packet.type == INTEL_PT_PSBEND) @@ -2554,6 +2551,8 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2) * @len_a: size of first buffer * @buf_b: second buffer * @len_b: size of second buffer + * @consecutive: returns true if there is data in buf_b that is consecutive + * to buf_a * * If the trace contains TSC we can look at the last TSC of @buf_a and the * first TSC of @buf_b in order to determine if the buffers overlap, and then @@ -2566,33 +2565,41 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2) static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a, size_t len_a, unsigned char *buf_b, - size_t len_b) + size_t len_b, bool *consecutive) { uint64_t tsc_a, tsc_b; unsigned char *p; - size_t len; + size_t len, rem_a, rem_b; p = intel_pt_last_psb(buf_a, len_a); if (!p) return buf_b; /* No PSB in buf_a => no overlap */ len = len_a - (p - buf_a); - if (!intel_pt_next_tsc(p, len, &tsc_a)) { + if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a)) { /* The last PSB+ in buf_a is incomplete, so go back one more */ len_a -= len; p = intel_pt_last_psb(buf_a, len_a); if (!p) return buf_b; /* No full PSB+ => assume no overlap */ len = len_a - (p - buf_a); - if (!intel_pt_next_tsc(p, len, &tsc_a)) + if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a)) return buf_b; /* No TSC in buf_a => assume no overlap */ } while (1) { /* Ignore PSB+ with no TSC */ - if (intel_pt_next_tsc(buf_b, len_b, &tsc_b) && - intel_pt_tsc_cmp(tsc_a, tsc_b) < 0) - return buf_b; /* tsc_a < tsc_b => no overlap */ + if (intel_pt_next_tsc(buf_b, len_b, &tsc_b, &rem_b)) { + int cmp = intel_pt_tsc_cmp(tsc_a, tsc_b); + + /* Same TSC, so buffers are consecutive */ + if (!cmp && rem_b >= rem_a) { + *consecutive = true; + return buf_b + len_b - (rem_b - rem_a); + } + if (cmp < 0) + return buf_b; /* tsc_a < tsc_b => no overlap */ + } if (!intel_pt_step_psb(&buf_b, &len_b)) return buf_b + len_b; /* No PSB in buf_b => no data */ @@ -2606,6 +2613,8 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a, * @buf_b: second buffer * @len_b: size of second buffer * @have_tsc: can use TSC packets to detect overlap + * @consecutive: returns true if there is data in buf_b that is consecutive + * to buf_a * * When trace samples or snapshots are recorded there is the possibility that * the data overlaps. Note that, for the purposes of decoding, data is only @@ -2616,7 +2625,7 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a, */ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, unsigned char *buf_b, size_t len_b, - bool have_tsc) + bool have_tsc, bool *consecutive) { unsigned char *found; @@ -2628,7 +2637,8 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, return buf_b; /* No overlap */ if (have_tsc) { - found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b); + found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b, + consecutive); if (found) return found; } @@ -2643,28 +2653,16 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, } /* Now len_b >= len_a */ - if (len_b > len_a) { - /* The leftover buffer 'b' must start at a PSB */ - while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) { - if (!intel_pt_step_psb(&buf_a, &len_a)) - return buf_b; /* No overlap */ - } - } - while (1) { /* Potential overlap so check the bytes */ found = memmem(buf_a, len_a, buf_b, len_a); - if (found) + if (found) { + *consecutive = true; return buf_b + len_a; + } /* Try again at next PSB in buffer 'a' */ if (!intel_pt_step_psb(&buf_a, &len_a)) return buf_b; /* No overlap */ - - /* The leftover buffer 'b' must start at a PSB */ - while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) { - if (!intel_pt_step_psb(&buf_a, &len_a)) - return buf_b; /* No overlap */ - } } } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index 921b22e8ca0e..fc1752d50019 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -117,7 +117,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder); unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, unsigned char *buf_b, size_t len_b, - bool have_tsc); + bool have_tsc, bool *consecutive); int intel_pt__strerror(int code, char *buf, size_t buflen); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 3773d9c54f45..0effaff57020 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -132,6 +132,7 @@ struct intel_pt_queue { struct intel_pt *pt; unsigned int queue_nr; struct auxtrace_buffer *buffer; + struct auxtrace_buffer *old_buffer; void *decoder; const struct intel_pt_state *state; struct ip_callchain *chain; @@ -143,6 +144,7 @@ struct intel_pt_queue { bool stop; bool step_through_buffers; bool use_buffer_pid_tid; + bool sync_switch; pid_t pid, tid; int cpu; int switch_state; @@ -207,49 +209,28 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf, static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { + bool consecutive = false; void *start; start = intel_pt_find_overlap(a->data, a->size, b->data, b->size, - pt->have_tsc); + pt->have_tsc, &consecutive); if (!start) return -EINVAL; b->use_size = b->data + b->size - start; b->use_data = start; + if (b->use_size && consecutive) + b->consecutive = true; return 0; } -static void intel_pt_use_buffer_pid_tid(struct intel_pt_queue *ptq, - struct auxtrace_queue *queue, - struct auxtrace_buffer *buffer) -{ - if (queue->cpu == -1 && buffer->cpu != -1) - ptq->cpu = buffer->cpu; - - ptq->pid = buffer->pid; - ptq->tid = buffer->tid; - - intel_pt_log("queue %u cpu %d pid %d tid %d\n", - ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid); - - thread__zput(ptq->thread); - - if (ptq->tid != -1) { - if (ptq->pid != -1) - ptq->thread = machine__findnew_thread(ptq->pt->machine, - ptq->pid, - ptq->tid); - else - ptq->thread = machine__find_thread(ptq->pt->machine, -1, - ptq->tid); - } -} - /* This function assumes data is processed sequentially only */ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) { struct intel_pt_queue *ptq = data; - struct auxtrace_buffer *buffer = ptq->buffer, *old_buffer = buffer; + struct auxtrace_buffer *buffer = ptq->buffer; + struct auxtrace_buffer *old_buffer = ptq->old_buffer; struct auxtrace_queue *queue; + bool might_overlap; if (ptq->stop) { b->len = 0; @@ -257,7 +238,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) } queue = &ptq->pt->queues.queue_array[ptq->queue_nr]; -next: + buffer = auxtrace_buffer__next(queue, buffer); if (!buffer) { if (old_buffer) @@ -276,7 +257,8 @@ next: return -ENOMEM; } - if (ptq->pt->snapshot_mode && !buffer->consecutive && old_buffer && + might_overlap = ptq->pt->snapshot_mode || ptq->pt->sampling_mode; + if (might_overlap && !buffer->consecutive && old_buffer && intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer)) return -ENOMEM; @@ -289,33 +271,24 @@ next: } b->ref_timestamp = buffer->reference; - /* - * If in snapshot mode and the buffer has no usable data, get next - * buffer and again check overlap against old_buffer. - */ - if (ptq->pt->snapshot_mode && !b->len) - goto next; - - if (old_buffer) - auxtrace_buffer__drop_data(old_buffer); - - if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode && - !buffer->consecutive)) { + if (!old_buffer || (might_overlap && !buffer->consecutive)) { b->consecutive = false; b->trace_nr = buffer->buffer_nr + 1; } else { b->consecutive = true; } - if (ptq->use_buffer_pid_tid && (ptq->pid != buffer->pid || - ptq->tid != buffer->tid)) - intel_pt_use_buffer_pid_tid(ptq, queue, buffer); - if (ptq->step_through_buffers) ptq->stop = true; - if (!b->len) + if (b->len) { + if (old_buffer) + auxtrace_buffer__drop_data(old_buffer); + ptq->old_buffer = buffer; + } else { + auxtrace_buffer__drop_data(buffer); return intel_pt_get_trace(b, data); + } return 0; } @@ -954,16 +927,15 @@ static int intel_pt_setup_queue(struct intel_pt *pt, ptq->cpu = queue->cpu; ptq->tid = queue->tid; - if (pt->sampling_mode) { - if (pt->timeless_decoding) - ptq->step_through_buffers = true; - if (pt->timeless_decoding || !pt->have_sched_switch) - ptq->use_buffer_pid_tid = true; - } + if (pt->sampling_mode && !pt->snapshot_mode && + pt->timeless_decoding) + ptq->step_through_buffers = true; + + ptq->sync_switch = pt->sync_switch; } if (!ptq->on_heap && - (!pt->sync_switch || + (!ptq->sync_switch || ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) { const struct intel_pt_state *state; int ret; @@ -1546,7 +1518,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) if (pt->synth_opts.last_branch) intel_pt_update_last_branch_rb(ptq); - if (!pt->sync_switch) + if (!ptq->sync_switch) return 0; if (intel_pt_is_switch_ip(ptq, state->to_ip)) { @@ -1627,6 +1599,21 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) return switch_ip; } +static void intel_pt_enable_sync_switch(struct intel_pt *pt) +{ + unsigned int i; + + pt->sync_switch = true; + + for (i = 0; i < pt->queues.nr_queues; i++) { + struct auxtrace_queue *queue = &pt->queues.queue_array[i]; + struct intel_pt_queue *ptq = queue->priv; + + if (ptq) + ptq->sync_switch = true; + } +} + static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) { const struct intel_pt_state *state = ptq->state; @@ -1643,7 +1630,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) if (pt->switch_ip) { intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n", pt->switch_ip, pt->ptss_ip); - pt->sync_switch = true; + intel_pt_enable_sync_switch(pt); } } } @@ -1659,9 +1646,9 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) if (state->err) { if (state->err == INTEL_PT_ERR_NODATA) return 1; - if (pt->sync_switch && + if (ptq->sync_switch && state->from_ip >= pt->kernel_start) { - pt->sync_switch = false; + ptq->sync_switch = false; intel_pt_next_tid(pt, ptq); } if (pt->synth_opts.errors) { @@ -1687,7 +1674,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) state->timestamp, state->est_timestamp); ptq->timestamp = state->est_timestamp; /* Use estimated TSC in unknown switch state */ - } else if (pt->sync_switch && + } else if (ptq->sync_switch && ptq->switch_state == INTEL_PT_SS_UNKNOWN && intel_pt_is_switch_ip(ptq, state->to_ip) && ptq->next_tid == -1) { @@ -1834,7 +1821,7 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid, return 1; ptq = intel_pt_cpu_to_ptq(pt, cpu); - if (!ptq) + if (!ptq || !ptq->sync_switch) return 1; switch (ptq->switch_state) { @@ -2075,9 +2062,6 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session, struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt, auxtrace); - if (pt->sampling_mode) - return 0; - if (!pt->data_queued) { struct auxtrace_buffer *buffer; off_t data_offset; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 12b7427444a3..43fbbee409ec 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1697,7 +1697,7 @@ static void ip__resolve_data(struct thread *thread, struct mem_info *sample__resolve_mem(struct perf_sample *sample, struct addr_location *al) { - struct mem_info *mi = zalloc(sizeof(*mi)); + struct mem_info *mi = mem_info__new(); if (!mi) return NULL; diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 4f27c464ce0b..074c4fd3b67e 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -75,9 +75,7 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, * } * perf_mmap__read_done() */ -union perf_event *perf_mmap__read_event(struct perf_mmap *map, - bool overwrite, - u64 *startp, u64 end) +union perf_event *perf_mmap__read_event(struct perf_mmap *map) { union perf_event *event; @@ -87,17 +85,14 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map, if (!refcount_read(&map->refcnt)) return NULL; - if (startp == NULL) - return NULL; - /* non-overwirte doesn't pause the ringbuffer */ - if (!overwrite) - end = perf_mmap__read_head(map); + if (!map->overwrite) + map->end = perf_mmap__read_head(map); - event = perf_mmap__read(map, startp, end); + event = perf_mmap__read(map, &map->start, map->end); - if (!overwrite) - map->prev = *startp; + if (!map->overwrite) + map->prev = map->start; return event; } @@ -120,9 +115,9 @@ void perf_mmap__put(struct perf_mmap *map) perf_mmap__munmap(map); } -void perf_mmap__consume(struct perf_mmap *map, bool overwrite) +void perf_mmap__consume(struct perf_mmap *map) { - if (!overwrite) { + if (!map->overwrite) { u64 old = map->prev; perf_mmap__write_tail(map, old); @@ -240,27 +235,26 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6 /* * Report the start and end of the available data in ringbuffer */ -int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, - u64 *startp, u64 *endp) +int perf_mmap__read_init(struct perf_mmap *md) { u64 head = perf_mmap__read_head(md); u64 old = md->prev; unsigned char *data = md->base + page_size; unsigned long size; - *startp = overwrite ? head : old; - *endp = overwrite ? old : head; + md->start = md->overwrite ? head : old; + md->end = md->overwrite ? old : head; - if (*startp == *endp) + if (md->start == md->end) return -EAGAIN; - size = *endp - *startp; + size = md->end - md->start; if (size > (unsigned long)(md->mask) + 1) { - if (!overwrite) { + if (!md->overwrite) { WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); md->prev = head; - perf_mmap__consume(md, overwrite); + perf_mmap__consume(md); return -EAGAIN; } @@ -268,33 +262,32 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, * Backward ring buffer is full. We still have a chance to read * most of data from it. */ - if (overwrite_rb_find_range(data, md->mask, head, startp, endp)) + if (overwrite_rb_find_range(data, md->mask, head, &md->start, &md->end)) return -EINVAL; } return 0; } -int perf_mmap__push(struct perf_mmap *md, bool overwrite, - void *to, int push(void *to, void *buf, size_t size)) +int perf_mmap__push(struct perf_mmap *md, void *to, + int push(void *to, void *buf, size_t size)) { u64 head = perf_mmap__read_head(md); - u64 end, start; unsigned char *data = md->base + page_size; unsigned long size; void *buf; int rc = 0; - rc = perf_mmap__read_init(md, overwrite, &start, &end); + rc = perf_mmap__read_init(md); if (rc < 0) return (rc == -EAGAIN) ? 0 : -1; - size = end - start; + size = md->end - md->start; - if ((start & md->mask) + size != (end & md->mask)) { - buf = &data[start & md->mask]; - size = md->mask + 1 - (start & md->mask); - start += size; + if ((md->start & md->mask) + size != (md->end & md->mask)) { + buf = &data[md->start & md->mask]; + size = md->mask + 1 - (md->start & md->mask); + md->start += size; if (push(to, buf, size) < 0) { rc = -1; @@ -302,9 +295,9 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, } } - buf = &data[start & md->mask]; - size = end - start; - start += size; + buf = &data[md->start & md->mask]; + size = md->end - md->start; + md->start += size; if (push(to, buf, size) < 0) { rc = -1; @@ -312,7 +305,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, } md->prev = head; - perf_mmap__consume(md, overwrite); + perf_mmap__consume(md); out: return rc; } diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index ec7d3a24e276..d82294db1295 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -20,6 +20,9 @@ struct perf_mmap { int fd; refcount_t refcnt; u64 prev; + u64 start; + u64 end; + bool overwrite; struct auxtrace_mmap auxtrace_mmap; char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); }; @@ -63,7 +66,7 @@ void perf_mmap__munmap(struct perf_mmap *map); void perf_mmap__get(struct perf_mmap *map); void perf_mmap__put(struct perf_mmap *map); -void perf_mmap__consume(struct perf_mmap *map, bool overwrite); +void perf_mmap__consume(struct perf_mmap *map); static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { @@ -86,16 +89,13 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) union perf_event *perf_mmap__read_forward(struct perf_mmap *map); -union perf_event *perf_mmap__read_event(struct perf_mmap *map, - bool overwrite, - u64 *startp, u64 end); +union perf_event *perf_mmap__read_event(struct perf_mmap *map); -int perf_mmap__push(struct perf_mmap *md, bool backward, - void *to, int push(void *to, void *buf, size_t size)); +int perf_mmap__push(struct perf_mmap *md, void *to, + int push(void *to, void *buf, size_t size)); size_t perf_mmap__mmap_len(struct perf_mmap *map); -int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, - u64 *startp, u64 *endp); +int perf_mmap__read_init(struct perf_mmap *md); void perf_mmap__read_done(struct perf_mmap *map); #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 34589c427e52..4e80ca320399 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1217,7 +1217,7 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, get_config_name(head_config), &config_terms); } -static int __parse_events_add_pmu(struct parse_events_state *parse_state, +int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, bool auto_merge_stats) { @@ -1247,7 +1247,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state, if (!head_config) { attr.type = pmu->type; evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats); - return evsel ? 0 : -ENOMEM; + if (evsel) { + evsel->pmu_name = name; + return 0; + } else { + return -ENOMEM; + } } if (perf_pmu__check_alias(pmu, head_config, &info)) @@ -1276,18 +1281,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state, evsel->snapshot = info.snapshot; evsel->metric_expr = info.metric_expr; evsel->metric_name = info.metric_name; + evsel->pmu_name = name; } return evsel ? 0 : -ENOMEM; } -int parse_events_add_pmu(struct parse_events_state *parse_state, - struct list_head *list, char *name, - struct list_head *head_config) -{ - return __parse_events_add_pmu(parse_state, list, name, head_config, false); -} - int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp) { @@ -1317,8 +1316,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, return -1; list_add_tail(&term->list, head); - if (!__parse_events_add_pmu(parse_state, list, - pmu->name, head, true)) { + if (!parse_events_add_pmu(parse_state, list, + pmu->name, head, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 88108cd11b4c..5015cfd58277 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -167,7 +167,7 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type, u64 len); int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config); + struct list_head *head_config, bool auto_merge_stats); int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 655ecff636a8..a1a01b1ac8b8 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -175,7 +175,7 @@ bpf_source [^,{}]+\.c[a-zA-Z0-9._]* num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ -name [a-zA-Z_*?][a-zA-Z0-9_*?.]* +name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]* name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index e81a20ea8d7d..7afeb80cc39e 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -8,6 +8,7 @@ #define YYDEBUG 1 +#include <fnmatch.h> #include <linux/compiler.h> #include <linux/list.h> #include <linux/types.h> @@ -231,9 +232,13 @@ PE_NAME opt_event_config YYABORT; ALLOC_LIST(list); - if (parse_events_add_pmu(_parse_state, list, $1, $2)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) { struct perf_pmu *pmu = NULL; int ok = 0; + char *pattern; + + if (asprintf(&pattern, "%s*", $1) < 0) + YYABORT; while ((pmu = perf_pmu__scan(pmu)) != NULL) { char *name = pmu->name; @@ -241,14 +246,19 @@ PE_NAME opt_event_config if (!strncmp(name, "uncore_", 7) && strncmp($1, "uncore_", 7)) name += 7; - if (!strncmp($1, name, strlen($1))) { - if (parse_events_copy_term_list(orig_terms, &terms)) + if (!fnmatch(pattern, name, 0)) { + if (parse_events_copy_term_list(orig_terms, &terms)) { + free(pattern); YYABORT; - if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms)) + } + if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true)) ok++; parse_events_terms__delete(terms); } } + + free(pattern); + if (!ok) YYABORT; } diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 35fb5ef7d290..b956868fd445 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -984,7 +984,6 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, int sample_id_all = 1, cpu; static char *kwlist[] = { "cpu", "sample_id_all", NULL }; struct perf_mmap *md; - u64 end, start; int err; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist, @@ -992,10 +991,10 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, return NULL; md = &evlist->mmap[cpu]; - if (perf_mmap__read_init(md, false, &start, &end) < 0) + if (perf_mmap__read_init(md) < 0) goto end; - event = perf_mmap__read_event(md, false, &start, end); + event = perf_mmap__read_event(md); if (event != NULL) { PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; @@ -1013,7 +1012,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, err = perf_evsel__parse_sample(evsel, event, &pevent->sample); /* Consume the even only after we parsed it out. */ - perf_mmap__consume(md, false); + perf_mmap__consume(md); if (err) return PyErr_Format(PyExc_OSError, diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a1a312d99f30..62b2dd2253eb 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2221,3 +2221,25 @@ int symbol__config_symfs(const struct option *opt __maybe_unused, free(bf); return 0; } + +struct mem_info *mem_info__get(struct mem_info *mi) +{ + if (mi) + refcount_inc(&mi->refcnt); + return mi; +} + +void mem_info__put(struct mem_info *mi) +{ + if (mi && refcount_dec_and_test(&mi->refcnt)) + free(mi); +} + +struct mem_info *mem_info__new(void) +{ + struct mem_info *mi = zalloc(sizeof(*mi)); + + if (mi) + refcount_set(&mi->refcnt, 1); + return mi; +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 0563f33c1eb3..70c16741f50a 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -200,9 +200,10 @@ struct branch_info { }; struct mem_info { - struct addr_map_symbol iaddr; - struct addr_map_symbol daddr; - union perf_mem_data_src data_src; + struct addr_map_symbol iaddr; + struct addr_map_symbol daddr; + union perf_mem_data_src data_src; + refcount_t refcnt; }; struct addr_location { @@ -389,4 +390,16 @@ int sdt_notes__get_count(struct list_head *start); #define SDT_NOTE_NAME "stapsdt" #define NR_ADDR 3 +struct mem_info *mem_info__new(void); +struct mem_info *mem_info__get(struct mem_info *mi); +void mem_info__put(struct mem_info *mi); + +static inline void __mem_info__zput(struct mem_info **mi) +{ + mem_info__put(*mi); + *mi = NULL; +} + +#define mem_info__zput(mi) __mem_info__zput(&mi) + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 40cfa36c022a..14d44c3235b8 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -26,7 +26,6 @@ struct thread { pid_t ppid; int cpu; refcount_t refcnt; - char shortname[3]; bool comm_set; int comm_len; bool dead; /* if set thread has exited */ |