#include "cpumap.h"
#include "event-parse.h"
#include "perf_regs.h"
-#include "unwind.h"
#include "vdso.h"
static int perf_session__open(struct perf_session *self, bool force)
goto out;
memcpy(self->filename, filename, len);
- /*
- * On 64bit we can mmap the data file in one go. No need for tiny mmap
- * slices. On 32bit we use 32MB.
- */
-#if BITS_PER_LONG == 64
- self->mmap_window = ULLONG_MAX;
-#else
- self->mmap_window = 32 * 1024 * 1024ULL;
-#endif
self->machines = RB_ROOT;
self->repipe = repipe;
INIT_LIST_HEAD(&self->ordered_samples.samples);
INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
INIT_LIST_HEAD(&self->ordered_samples.to_free);
machine__init(&self->host_machine, "", HOST_KERNEL_ID);
- hists__init(&self->hists);
if (mode == O_RDONLY) {
if (perf_session__open(self, force) < 0)
return NULL;
}
-static void machine__delete_dead_threads(struct machine *machine)
-{
- struct thread *n, *t;
-
- list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
- list_del(&t->node);
- thread__delete(t);
- }
-}
-
static void perf_session__delete_dead_threads(struct perf_session *session)
{
machine__delete_dead_threads(&session->host_machine);
}
-static void machine__delete_threads(struct machine *self)
+static void perf_session__delete_threads(struct perf_session *session)
{
- struct rb_node *nd = rb_first(&self->threads);
-
- while (nd) {
- struct thread *t = rb_entry(nd, struct thread, rb_node);
-
- rb_erase(&t->rb_node, &self->threads);
- nd = rb_next(nd);
- thread__delete(t);
- }
+ machine__delete_threads(&session->host_machine);
}
-static void perf_session__delete_threads(struct perf_session *session)
+static void perf_session_env__delete(struct perf_session_env *env)
{
- machine__delete_threads(&session->host_machine);
+ free(env->hostname);
+ free(env->os_release);
+ free(env->version);
+ free(env->arch);
+ free(env->cpu_desc);
+ free(env->cpuid);
+
+ free(env->cmdline);
+ free(env->sibling_cores);
+ free(env->sibling_threads);
+ free(env->numa_nodes);
+ free(env->pmu_mappings);
}
void perf_session__delete(struct perf_session *self)
perf_session__destroy_kernel_maps(self);
perf_session__delete_dead_threads(self);
perf_session__delete_threads(self);
+ perf_session_env__delete(&self->header.env);
machine__exit(&self->host_machine);
close(self->fd);
free(self);
vdso__exit();
}
-void machine__remove_thread(struct machine *self, struct thread *th)
-{
- self->last_match = NULL;
- rb_erase(&th->rb_node, &self->threads);
- /*
- * We may have references to this thread, for instance in some hist_entry
- * instances, so just move them to a separate list.
- */
- list_add_tail(&th->node, &self->dead_threads);
-}
-
-static bool symbol__match_parent_regex(struct symbol *sym)
-{
- if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
- return 1;
-
- return 0;
-}
-
-static const u8 cpumodes[] = {
- PERF_RECORD_MISC_USER,
- PERF_RECORD_MISC_KERNEL,
- PERF_RECORD_MISC_GUEST_USER,
- PERF_RECORD_MISC_GUEST_KERNEL
-};
-#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
-
-static void ip__resolve_ams(struct machine *self, struct thread *thread,
- struct addr_map_symbol *ams,
- u64 ip)
-{
- struct addr_location al;
- size_t i;
- u8 m;
-
- memset(&al, 0, sizeof(al));
-
- for (i = 0; i < NCPUMODES; i++) {
- m = cpumodes[i];
- /*
- * We cannot use the header.misc hint to determine whether a
- * branch stack address is user, kernel, guest, hypervisor.
- * Branches may straddle the kernel/user/hypervisor boundaries.
- * Thus, we have to try consecutively until we find a match
- * or else, the symbol is unknown
- */
- thread__find_addr_location(thread, self, m, MAP__FUNCTION,
- ip, &al, NULL);
- if (al.sym)
- goto found;
- }
-found:
- ams->addr = ip;
- ams->al_addr = al.addr;
- ams->sym = al.sym;
- ams->map = al.map;
-}
-
-struct branch_info *machine__resolve_bstack(struct machine *self,
- struct thread *thr,
- struct branch_stack *bs)
-{
- struct branch_info *bi;
- unsigned int i;
-
- bi = calloc(bs->nr, sizeof(struct branch_info));
- if (!bi)
- return NULL;
-
- for (i = 0; i < bs->nr; i++) {
- ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
- ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
- bi[i].flags = bs->entries[i].flags;
- }
- return bi;
-}
-
-static int machine__resolve_callchain_sample(struct machine *machine,
- struct thread *thread,
- struct ip_callchain *chain,
- struct symbol **parent)
-
-{
- u8 cpumode = PERF_RECORD_MISC_USER;
- unsigned int i;
- int err;
-
- callchain_cursor_reset(&callchain_cursor);
-
- if (chain->nr > PERF_MAX_STACK_DEPTH) {
- pr_warning("corrupted callchain. skipping...\n");
- return 0;
- }
-
- for (i = 0; i < chain->nr; i++) {
- u64 ip;
- struct addr_location al;
-
- if (callchain_param.order == ORDER_CALLEE)
- ip = chain->ips[i];
- else
- ip = chain->ips[chain->nr - i - 1];
-
- if (ip >= PERF_CONTEXT_MAX) {
- switch (ip) {
- case PERF_CONTEXT_HV:
- cpumode = PERF_RECORD_MISC_HYPERVISOR;
- break;
- case PERF_CONTEXT_KERNEL:
- cpumode = PERF_RECORD_MISC_KERNEL;
- break;
- case PERF_CONTEXT_USER:
- cpumode = PERF_RECORD_MISC_USER;
- break;
- default:
- pr_debug("invalid callchain context: "
- "%"PRId64"\n", (s64) ip);
- /*
- * It seems the callchain is corrupted.
- * Discard all.
- */
- callchain_cursor_reset(&callchain_cursor);
- return 0;
- }
- continue;
- }
-
- al.filtered = false;
- thread__find_addr_location(thread, machine, cpumode,
- MAP__FUNCTION, ip, &al, NULL);
- if (al.sym != NULL) {
- if (sort__has_parent && !*parent &&
- symbol__match_parent_regex(al.sym))
- *parent = al.sym;
- if (!symbol_conf.use_callchain)
- break;
- }
-
- err = callchain_cursor_append(&callchain_cursor,
- ip, al.map, al.sym);
- if (err)
- return err;
- }
-
- return 0;
-}
-
-static int unwind_entry(struct unwind_entry *entry, void *arg)
-{
- struct callchain_cursor *cursor = arg;
- return callchain_cursor_append(cursor, entry->ip,
- entry->map, entry->sym);
-}
-
-int machine__resolve_callchain(struct machine *machine,
- struct perf_evsel *evsel,
- struct thread *thread,
- struct perf_sample *sample,
- struct symbol **parent)
-
-{
- int ret;
-
- callchain_cursor_reset(&callchain_cursor);
-
- ret = machine__resolve_callchain_sample(machine, thread,
- sample->callchain, parent);
- if (ret)
- return ret;
-
- /* Can we do dwarf post unwind? */
- if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
- (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
- return 0;
-
- /* Bail out if nothing was captured. */
- if ((!sample->user_regs.regs) ||
- (!sample->user_stack.size))
- return 0;
-
- return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
- thread, evsel->attr.sample_regs_user,
- sample);
-
-}
-
static int process_event_synth_tracing_data_stub(union perf_event *event
__maybe_unused,
struct perf_session *session
case PERF_RECORD_SAMPLE:
dump_sample(evsel, event, sample);
if (evsel == NULL) {
- ++session->hists.stats.nr_unknown_id;
+ ++session->stats.nr_unknown_id;
return 0;
}
if (machine == NULL) {
- ++session->hists.stats.nr_unprocessable_samples;
+ ++session->stats.nr_unprocessable_samples;
return 0;
}
return tool->sample(tool, event, sample, evsel, machine);
return tool->exit(tool, event, sample, machine);
case PERF_RECORD_LOST:
if (tool->lost == perf_event__process_lost)
- session->hists.stats.total_lost += event->lost.lost;
+ session->stats.total_lost += event->lost.lost;
return tool->lost(tool, event, sample, machine);
case PERF_RECORD_READ:
return tool->read(tool, event, sample, evsel, machine);
case PERF_RECORD_UNTHROTTLE:
return tool->unthrottle(tool, event, sample, machine);
default:
- ++session->hists.stats.nr_unknown_events;
+ ++session->stats.nr_unknown_events;
return -1;
}
}
if (!ip_callchain__valid(sample->callchain, event)) {
pr_debug("call-chain problem with event, skipping it.\n");
- ++session->hists.stats.nr_invalid_chains;
- session->hists.stats.total_invalid_chains += sample->period;
+ ++session->stats.nr_invalid_chains;
+ session->stats.total_invalid_chains += sample->period;
return -EINVAL;
}
return 0;
if (event->header.type >= PERF_RECORD_HEADER_MAX)
return -EINVAL;
- hists__inc_nr_events(&session->hists, event->header.type);
+ events_stats__inc(&session->stats, event->header.type);
if (event->header.type >= PERF_RECORD_USER_TYPE_START)
return perf_session__process_user_event(session, event, tool, file_offset);
const struct perf_tool *tool)
{
if (tool->lost == perf_event__process_lost &&
- session->hists.stats.nr_events[PERF_RECORD_LOST] != 0) {
+ session->stats.nr_events[PERF_RECORD_LOST] != 0) {
ui__warning("Processed %d events and lost %d chunks!\n\n"
"Check IO/CPU overload!\n\n",
- session->hists.stats.nr_events[0],
- session->hists.stats.nr_events[PERF_RECORD_LOST]);
+ session->stats.nr_events[0],
+ session->stats.nr_events[PERF_RECORD_LOST]);
}
- if (session->hists.stats.nr_unknown_events != 0) {
+ if (session->stats.nr_unknown_events != 0) {
ui__warning("Found %u unknown events!\n\n"
"Is this an older tool processing a perf.data "
"file generated by a more recent tool?\n\n"
"If that is not the case, consider "
"reporting to linux-kernel@vger.kernel.org.\n\n",
- session->hists.stats.nr_unknown_events);
+ session->stats.nr_unknown_events);
}
- if (session->hists.stats.nr_unknown_id != 0) {
+ if (session->stats.nr_unknown_id != 0) {
ui__warning("%u samples with id not present in the header\n",
- session->hists.stats.nr_unknown_id);
+ session->stats.nr_unknown_id);
}
- if (session->hists.stats.nr_invalid_chains != 0) {
+ if (session->stats.nr_invalid_chains != 0) {
ui__warning("Found invalid callchains!\n\n"
"%u out of %u events were discarded for this reason.\n\n"
"Consider reporting to linux-kernel@vger.kernel.org.\n\n",
- session->hists.stats.nr_invalid_chains,
- session->hists.stats.nr_events[PERF_RECORD_SAMPLE]);
+ session->stats.nr_invalid_chains,
+ session->stats.nr_events[PERF_RECORD_SAMPLE]);
}
- if (session->hists.stats.nr_unprocessable_samples != 0) {
+ if (session->stats.nr_unprocessable_samples != 0) {
ui__warning("%u unprocessable samples recorded.\n"
"Do you have a KVM guest running and not using 'perf kvm'?\n",
- session->hists.stats.nr_unprocessable_samples);
+ session->stats.nr_unprocessable_samples);
}
}
return event;
}
+/*
+ * On 64bit we can mmap the data file in one go. No need for tiny mmap
+ * slices. On 32bit we use 32MB.
+ */
+#if BITS_PER_LONG == 64
+#define MMAP_SIZE ULLONG_MAX
+#define NUM_MMAPS 1
+#else
+#define MMAP_SIZE (32 * 1024 * 1024ULL)
+#define NUM_MMAPS 128
+#endif
+
int __perf_session__process_events(struct perf_session *session,
u64 data_offset, u64 data_size,
u64 file_size, struct perf_tool *tool)
u64 head, page_offset, file_offset, file_pos, progress_next;
int err, mmap_prot, mmap_flags, map_idx = 0;
size_t mmap_size;
- char *buf, *mmaps[8];
+ char *buf, *mmaps[NUM_MMAPS];
union perf_event *event;
uint32_t size;
progress_next = file_size / 16;
- mmap_size = session->mmap_window;
+ mmap_size = MMAP_SIZE;
if (mmap_size > file_size)
mmap_size = file_size;
}
size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
- bool with_hits)
+ bool (skip)(struct dso *dso, int parm), int parm)
{
- size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits);
- return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
+ size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, skip, parm);
+ return ret + machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm);
}
size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
struct perf_evsel *pos;
size_t ret = fprintf(fp, "Aggregated stats:\n");
- ret += hists__fprintf_nr_events(&session->hists, fp);
+ ret += events_stats__fprintf(&session->stats, fp);
list_for_each_entry(pos, &session->evlist->entries, node) {
ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
- ret += hists__fprintf_nr_events(&pos->hists, fp);
+ ret += events_stats__fprintf(&pos->hists.stats, fp);
}
return ret;
projects / deliverable / linux.git / blobdiff