+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
#include <poll.h>
+#include "cpumap.h"
+#include "thread_map.h"
#include "evlist.h"
#include "evsel.h"
#include "util.h"
+#include <sys/mman.h>
+
#include <linux/bitops.h>
#include <linux/hash.h>
-void perf_evlist__init(struct perf_evlist *evlist)
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+ struct thread_map *threads)
{
int i;
for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
INIT_HLIST_HEAD(&evlist->heads[i]);
INIT_LIST_HEAD(&evlist->entries);
+ perf_evlist__set_maps(evlist, cpus, threads);
}
-struct perf_evlist *perf_evlist__new(void)
+struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
+ struct thread_map *threads)
{
struct perf_evlist *evlist = zalloc(sizeof(*evlist));
if (evlist != NULL)
- perf_evlist__init(evlist);
+ perf_evlist__init(evlist, cpus, threads);
return evlist;
}
return 0;
}
-int perf_evlist__alloc_pollfd(struct perf_evlist *evlist, int ncpus, int nthreads)
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
{
- int nfds = ncpus * nthreads * evlist->nr_entries;
+ int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
return evlist->pollfd != NULL ? 0 : -ENOMEM;
}
evlist->nr_fds++;
}
+static void perf_evlist__id_hash(struct perf_evlist *evlist,
+ struct perf_evsel *evsel,
+ int cpu, int thread, u64 id)
+{
+ int hash;
+ struct perf_sample_id *sid = SID(evsel, cpu, thread);
+
+ sid->id = id;
+ sid->evsel = evsel;
+ hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
+ hlist_add_head(&sid->node, &evlist->heads[hash]);
+}
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+ int cpu, int thread, u64 id)
+{
+ perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
+ evsel->id[evsel->ids++] = id;
+}
+
+static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+ struct perf_evsel *evsel,
+ int cpu, int thread, int fd)
+{
+ u64 read_data[4] = { 0, };
+ int id_idx = 1; /* The first entry is the counter value */
+
+ if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
+ read(fd, &read_data, sizeof(read_data)) == -1)
+ return -1;
+
+ if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+ ++id_idx;
+ if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+ ++id_idx;
+
+ perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]);
+ return 0;
+}
+
struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
{
struct hlist_head *head;
return NULL;
}
-event_t *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
+union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
{
/* XXX Move this to perf.c, making it generally available */
unsigned int page_size = sysconf(_SC_PAGE_SIZE);
unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
unsigned char *data = md->base + page_size;
- event_t *event = NULL;
- int diff;
-
- /*
- * If we're further behind than half the buffer, there's a chance
- * the writer will bite our tail and mess up the samples under us.
- *
- * If we somehow ended up ahead of the head, we got messed up.
- *
- * In either case, truncate and restart at head.
- */
- diff = head - old;
- if (diff > md->mask / 2 || diff < 0) {
- fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
+ union perf_event *event = NULL;
+ if (evlist->overwrite) {
/*
- * head points to a known good entry, start there.
+ * If we're further behind than half the buffer, there's a chance
+ * the writer will bite our tail and mess up the samples under us.
+ *
+ * If we somehow ended up ahead of the head, we got messed up.
+ *
+ * In either case, truncate and restart at head.
*/
- old = head;
+ int diff = head - old;
+ if (diff > md->mask / 2 || diff < 0) {
+ fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
+
+ /*
+ * head points to a known good entry, start there.
+ */
+ old = head;
+ }
}
if (old != head) {
size_t size;
- event = (event_t *)&data[old & md->mask];
+ event = (union perf_event *)&data[old & md->mask];
size = event->header.size;
/*
}
md->prev = old;
+
+ if (!evlist->overwrite)
+ perf_mmap__write_tail(md, old);
+
return event;
}
+
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+ int cpu;
+
+ for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+ if (evlist->mmap[cpu].base != NULL) {
+ munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+ evlist->mmap[cpu].base = NULL;
+ }
+ }
+}
+
+int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+{
+ evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
+ return evlist->mmap != NULL ? 0 : -ENOMEM;
+}
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
+ int mask, int fd)
+{
+ evlist->mmap[cpu].prev = 0;
+ evlist->mmap[cpu].mask = mask;
+ evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
+ MAP_SHARED, fd, 0);
+ if (evlist->mmap[cpu].base == MAP_FAILED)
+ return -1;
+
+ perf_evlist__add_pollfd(evlist, fd);
+ return 0;
+}
+
+/** perf_evlist__mmap - Create per cpu maps to receive events
+ *
+ * @evlist - list of events
+ * @pages - map length in pages
+ * @overwrite - overwrite older events?
+ *
+ * If overwrite is false the user needs to signal event consuption using:
+ *
+ * struct perf_mmap *m = &evlist->mmap[cpu];
+ * unsigned int head = perf_mmap__read_head(m);
+ *
+ * perf_mmap__write_tail(m, head)
+ *
+ * Using perf_evlist__read_on_cpu does this automatically.
+ */
+int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
+{
+ unsigned int page_size = sysconf(_SC_PAGE_SIZE);
+ int mask = pages * page_size - 1, cpu;
+ struct perf_evsel *first_evsel, *evsel;
+ const struct cpu_map *cpus = evlist->cpus;
+ const struct thread_map *threads = evlist->threads;
+ int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+
+ if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+ return -ENOMEM;
+
+ if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+ return -ENOMEM;
+
+ evlist->overwrite = overwrite;
+ evlist->mmap_len = (pages + 1) * page_size;
+ first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+ evsel->sample_id == NULL &&
+ perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
+ return -ENOMEM;
+
+ for (cpu = 0; cpu < cpus->nr; cpu++) {
+ for (thread = 0; thread < threads->nr; thread++) {
+ int fd = FD(evsel, cpu, thread);
+
+ if (evsel->idx || thread) {
+ if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
+ FD(first_evsel, cpu, 0)) != 0)
+ goto out_unmap;
+ } else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
+ goto out_unmap;
+
+ if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+ perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+ goto out_unmap;
+ }
+ }
+ }
+
+ return 0;
+
+out_unmap:
+ for (cpu = 0; cpu < cpus->nr; cpu++) {
+ if (evlist->mmap[cpu].base != NULL) {
+ munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+ evlist->mmap[cpu].base = NULL;
+ }
+ }
+ return -1;
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
+ pid_t target_tid, const char *cpu_list)
+{
+ evlist->threads = thread_map__new(target_pid, target_tid);
+
+ if (evlist->threads == NULL)
+ return -1;
+
+ if (target_tid != -1)
+ evlist->cpus = cpu_map__dummy_new();
+ else
+ evlist->cpus = cpu_map__new(cpu_list);
+
+ if (evlist->cpus == NULL)
+ goto out_delete_threads;
+
+ return 0;
+
+out_delete_threads:
+ thread_map__delete(evlist->threads);
+ return -1;
+}
+
+void perf_evlist__delete_maps(struct perf_evlist *evlist)
+{
+ cpu_map__delete(evlist->cpus);
+ thread_map__delete(evlist->threads);
+ evlist->cpus = NULL;
+ evlist->threads = NULL;
+}
+
+int perf_evlist__set_filters(struct perf_evlist *evlist)
+{
+ const struct thread_map *threads = evlist->threads;
+ const struct cpu_map *cpus = evlist->cpus;
+ struct perf_evsel *evsel;
+ char *filter;
+ int thread;
+ int cpu;
+ int err;
+ int fd;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ filter = evsel->filter;
+ if (!filter)
+ continue;
+ for (cpu = 0; cpu < cpus->nr; cpu++) {
+ for (thread = 0; thread < threads->nr; thread++) {
+ fd = FD(evsel, cpu, thread);
+ err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter);
+ if (err)
+ return err;
+ }
+ }
+ }
+
+ return 0;
+}