diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index b3c45276b6645a6d4c36fc7dc86d17fb4c7f3edb..03b76904ca5236c6e173dbd920ef624712c4e529 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -70,6 +70,8 @@ struct intel_pt {
bool sync_switch;
bool mispred_all;
bool use_thread_stack;
+ bool callstack;
+ unsigned int br_stack_sz;
int have_sched_switch;
u32 pmu_type;
u64 kernel_start;
@@ -147,8 +149,6 @@ struct intel_pt_queue {
const struct intel_pt_state *state;
struct ip_callchain *chain;
struct branch_stack *last_branch;
- struct branch_stack *last_branch_rb;
- size_t last_branch_pos;
union perf_event *event_buf;
bool on_heap;
bool stop;
@@ -931,14 +931,10 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
if (pt->synth_opts.last_branch) {
size_t sz = sizeof(struct branch_stack);
- sz += pt->synth_opts.last_branch_sz *
- sizeof(struct branch_entry);
+ sz += pt->br_stack_sz * sizeof(struct branch_entry);
ptq->last_branch = zalloc(sz);
if (!ptq->last_branch)
goto out_free;
- ptq->last_branch_rb = zalloc(sz);
- if (!ptq->last_branch_rb)
- goto out_free;
}
ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
@@ -1007,7 +1003,6 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
out_free:
zfree(&ptq->event_buf);
zfree(&ptq->last_branch);
- zfree(&ptq->last_branch_rb);
zfree(&ptq->chain);
free(ptq);
return NULL;
@@ -1023,7 +1018,6 @@ static void intel_pt_free_queue(void *priv)
intel_pt_decoder_free(ptq->decoder);
zfree(&ptq->event_buf);
zfree(&ptq->last_branch);
- zfree(&ptq->last_branch_rb);
zfree(&ptq->chain);
free(ptq);
}
@@ -1191,58 +1185,6 @@ static int intel_pt_setup_queues(struct intel_pt *pt)
return 0;
}
-static inline void intel_pt_copy_last_branch_rb(struct intel_pt_queue *ptq)
-{
- struct branch_stack *bs_src = ptq->last_branch_rb;
- struct branch_stack *bs_dst = ptq->last_branch;
- size_t nr = 0;
-
- bs_dst->nr = bs_src->nr;
-
- if (!bs_src->nr)
- return;
-
- nr = ptq->pt->synth_opts.last_branch_sz - ptq->last_branch_pos;
- memcpy(&bs_dst->entries[0],
- &bs_src->entries[ptq->last_branch_pos],
- sizeof(struct branch_entry) * nr);
-
- if (bs_src->nr >= ptq->pt->synth_opts.last_branch_sz) {
- memcpy(&bs_dst->entries[nr],
- &bs_src->entries[0],
- sizeof(struct branch_entry) * ptq->last_branch_pos);
- }
-}
-
-static inline void intel_pt_reset_last_branch_rb(struct intel_pt_queue *ptq)
-{
- ptq->last_branch_pos = 0;
- ptq->last_branch_rb->nr = 0;
-}
-
-static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
-{
- const struct intel_pt_state *state = ptq->state;
- struct branch_stack *bs = ptq->last_branch_rb;
- struct branch_entry *be;
-
- if (!ptq->last_branch_pos)
- ptq->last_branch_pos = ptq->pt->synth_opts.last_branch_sz;
-
- ptq->last_branch_pos -= 1;
-
- be = &bs->entries[ptq->last_branch_pos];
- be->from = state->from_ip;
- be->to = state->to_ip;
- be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
- be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
- /* No support for mispredict */
- be->flags.mispred = ptq->pt->mispred_all;
-
- if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
- bs->nr += 1;
-}
-
static inline bool intel_pt_skip_event(struct intel_pt *pt)
{
return pt->synth_opts.initial_skip &&
@@ -1310,9 +1252,9 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,
return intel_pt_inject_event(event, sample, type);
}
-static int intel_pt_deliver_synth_b_event(struct intel_pt *pt,
- union perf_event *event,
- struct perf_sample *sample, u64 type)
+static int intel_pt_deliver_synth_event(struct intel_pt *pt,
+ union perf_event *event,
+ struct perf_sample *sample, u64 type)
{
int ret;
@@ -1372,8 +1314,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
}
- return intel_pt_deliver_synth_b_event(pt, event, &sample,
- pt->branches_sample_type);
+ return intel_pt_deliver_synth_event(pt, event, &sample,
+ pt->branches_sample_type);
}
static void intel_pt_prep_sample(struct intel_pt *pt,
@@ -1391,27 +1333,12 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
}
if (pt->synth_opts.last_branch) {
- intel_pt_copy_last_branch_rb(ptq);
+ thread_stack__br_sample(ptq->thread, ptq->cpu, ptq->last_branch,
+ pt->br_stack_sz);
sample->branch_stack = ptq->last_branch;
}
}
-static inline int intel_pt_deliver_synth_event(struct intel_pt *pt,
- struct intel_pt_queue *ptq,
- union perf_event *event,
- struct perf_sample *sample,
- u64 type)
-{
- int ret;
-
- ret = intel_pt_deliver_synth_b_event(pt, event, sample, type);
-
- if (pt->synth_opts.last_branch)
- intel_pt_reset_last_branch_rb(ptq);
-
- return ret;
-}
-
static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
{
struct intel_pt *pt = ptq->pt;
@@ -1436,7 +1363,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->instructions_sample_type);
}
@@ -1454,7 +1381,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
sample.id = ptq->pt->transactions_id;
sample.stream_id = ptq->pt->transactions_id;
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->transactions_sample_type);
}
@@ -1495,7 +1422,7 @@ static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->ptwrites_sample_type);
}
@@ -1525,7 +1452,7 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1550,7 +1477,7 @@ static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1575,7 +1502,7 @@ static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1600,7 +1527,7 @@ static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1625,7 +1552,7 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
sample.raw_size = perf_synth__raw_size(raw);
sample.raw_data = perf_synth__raw_data(&raw);
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+ return intel_pt_deliver_synth_event(pt, event, &sample,
pt->pwr_events_sample_type);
}
@@ -1845,7 +1772,9 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
intel_pt_add_lbrs(&br.br_stack, items);
sample.branch_stack = &br.br_stack;
} else if (pt->synth_opts.last_branch) {
- intel_pt_copy_last_branch_rb(ptq);
+ thread_stack__br_sample(ptq->thread, ptq->cpu,
+ ptq->last_branch,
+ pt->br_stack_sz);
sample.branch_stack = ptq->last_branch;
} else {
br.br_stack.nr = 0;
@@ -1880,7 +1809,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
sample.transaction = txn;
}
- return intel_pt_deliver_synth_event(pt, ptq, event, &sample, sample_type);
+ return intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
}
static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
@@ -2030,12 +1959,15 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
if (!(state->type & INTEL_PT_BRANCH))
return 0;
- if (pt->use_thread_stack)
- thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
- state->to_ip, ptq->insn_len,
- state->trace_nr, true, 0, 0);
- else
+ if (pt->use_thread_stack) {
+ thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
+ state->from_ip, state->to_ip, ptq->insn_len,
+ state->trace_nr, pt->callstack,
+ pt->br_stack_sz,
+ pt->mispred_all);
+ } else {
thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
+ }
if (pt->sample_branches) {
err = intel_pt_synth_branch_sample(ptq);
@@ -2043,9 +1975,6 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
return err;
}
- if (pt->synth_opts.last_branch)
- intel_pt_update_last_branch_rb(ptq);
-
if (!ptq->sync_switch)
return 0;
@@ -3441,9 +3370,17 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
goto err_delete_thread;
}
+ if (pt->synth_opts.last_branch)
+ pt->br_stack_sz = pt->synth_opts.last_branch_sz;
+
pt->use_thread_stack = pt->synth_opts.callchain ||
pt->synth_opts.add_callchain ||
- pt->synth_opts.thread_stack;
+ pt->synth_opts.thread_stack ||
+ pt->synth_opts.last_branch;
+
+ pt->callstack = pt->synth_opts.callchain ||
+ pt->synth_opts.add_callchain ||
+ pt->synth_opts.thread_stack;
err = intel_pt_synth_events(pt, session);
if (err)