diff options
Diffstat (limited to 'tools/perf/util/intel-pt.c')
| -rw-r--r-- | tools/perf/util/intel-pt.c | 57 |
1 files changed, 45 insertions, 12 deletions
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 9227c2f076c3..c8f2d084a8ce 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -125,6 +125,7 @@ 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; @@ -188,14 +189,17 @@ 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; } @@ -238,7 +242,7 @@ 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) @@ -261,9 +265,6 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer)) return -ENOMEM; - if (old_buffer) - auxtrace_buffer__drop_data(old_buffer); - if (buffer->use_data) { b->len = buffer->use_size; b->buf = buffer->use_data; @@ -273,6 +274,16 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) } 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)) { b->consecutive = false; @@ -665,6 +676,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, unsigned int queue_nr) { struct intel_pt_params params = { .get_trace = 0, }; + struct perf_env *env = pt->machine->env; struct intel_pt_queue *ptq; ptq = zalloc(sizeof(struct intel_pt_queue)); @@ -742,6 +754,9 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, } } + if (env->cpuid && !strncmp(env->cpuid, "GenuineIntel,6,92,", 18)) + params.flags |= INTEL_PT_FUP_WITH_NLIP; + ptq->decoder = intel_pt_decoder_new(¶ms); if (!ptq->decoder) goto out_free; @@ -842,10 +857,12 @@ static int intel_pt_setup_queue(struct intel_pt *pt, if (pt->timeless_decoding || !pt->have_sched_switch) ptq->use_buffer_pid_tid = 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; @@ -1228,11 +1245,12 @@ 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)) { switch (ptq->switch_state) { + case INTEL_PT_SS_NOT_TRACING: case INTEL_PT_SS_UNKNOWN: case INTEL_PT_SS_EXPECTING_SWITCH_IP: err = intel_pt_next_tid(pt, ptq); @@ -1309,6 +1327,21 @@ 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; @@ -1325,7 +1358,7 @@ 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); } } } @@ -1341,9 +1374,9 @@ 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) { @@ -1369,7 +1402,7 @@ 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) { @@ -1516,7 +1549,7 @@ 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) { |