When operating in CPU-wide mode tracers need to generate timestamps in order to correlate the code being traced on one CPU with what is executed on other CPUs.

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org --- tools/perf/arch/arm/util/cs-etm.c | 57 +++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 1fc597532c78..59b189314422 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -99,6 +99,54 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, return err; }

+static int cs_etm_set_timestamp(struct auxtrace_record *itr, + struct perf_evsel *evsel, int cpu) +{ + struct cs_etm_recording *ptr; + struct perf_pmu *cs_etm_pmu; + char path[PATH_MAX]; + int err = -EINVAL; + u32 val; + + ptr = container_of(itr, struct cs_etm_recording, itr); + cs_etm_pmu = ptr->cs_etm_pmu; + + if (!cs_etm_is_etmv4(itr, cpu)) + goto out; + + /* Get a handle on TRCIRD0 */ + snprintf(path, PATH_MAX, "cpu%d/%s", + cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]); + err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); + + /* There was a problem reading the file, bailing out */ + if (err != 1) { + pr_err("%s: can't read file %s\n", + CORESIGHT_ETM_PMU_NAME, path); + goto out; + } + + /* + * TRCIDR0.TSSIZE, bit [28-24], indicates whether global timestamping + * is supported: + * 0b00000 Global timestamping is not implemented + * 0b00110 Implementation supports a maximum timestamp of 48bits. + * 0b01000 Implementation supports a maximum timestamp of 64bits. + */ + val &= GENMASK(28, 24); + if (!val) { + err = -EINVAL; + goto out; + } + + /* All good, let the kernel know */ + evsel->attr.config |= (1 << ETM_OPT_TS); + err = 0; + +out: + return err; +} + static int cs_etm_set_option(struct auxtrace_record *itr, struct perf_evsel *evsel, u32 option) { @@ -118,6 +166,11 @@ static int cs_etm_set_option(struct auxtrace_record *itr, if (err) goto out; break; + case ETM_OPT_TS: + err = cs_etm_set_timestamp(itr, evsel, i); + if (err) + goto out; + break; default: break; } @@ -343,6 +396,10 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, err = cs_etm_set_option(itr, cs_etm_evsel, ETM_OPT_CTXTID); if (err) goto out; + + err = cs_etm_set_option(itr, cs_etm_evsel, ETM_OPT_TS); + if (err) + goto out; }

/* Add dummy event to keep tracking */

Add handling of ITRACE events in order to add the tid/pid of the executing process to the perf tools machine infrastructure. This information is later retrieved when a contextID packet is found in the trace stream.

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org --- tools/perf/util/cs-etm.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 110804936fc3..c58a6b87a376 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1663,6 +1663,29 @@ static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm, return 0; }

+static int cs_etm__process_itrace_start(struct cs_etm_auxtrace *etm, + union perf_event *event) +{ + struct thread *th; + + if (etm->timeless_decoding) + return 0; + + /* + * Add the tid/pid to the log so that we can get a match when + * we get a contextID from the decoder. + */ + th = machine__findnew_thread(etm->machine, + event->itrace_start.pid, + event->itrace_start.tid); + if (!th) + return -ENOMEM; + + thread__put(th); + + return 0; +} + static int cs_etm__process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -1700,6 +1723,9 @@ static int cs_etm__process_event(struct perf_session *session, return cs_etm__process_timeless_queues(etm, event->fork.tid);

+ if (event->header.type == PERF_RECORD_ITRACE_START) + return cs_etm__process_itrace_start(etm, event); + return 0; }

There is no point in having two different error goto statement since the openCSD API to free a decoder handles NULL pointers. As such function cs_etm_decoder__free() can be called to deal with all aspect of freeing decoder memory.

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org --- tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index ba4c623cd8de..9838616f8d53 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -576,7 +576,7 @@ cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params, /* init library print logging support */ ret = cs_etm_decoder__init_def_logger_printing(d_params, decoder); if (ret != 0) - goto err_free_decoder_tree; + goto err_free_decoder;

/* init raw frame logging if required */ cs_etm_decoder__init_raw_frame_logging(d_params, decoder); @@ -586,15 +586,13 @@ cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params, &t_params[i], decoder); if (ret != 0) - goto err_free_decoder_tree; + goto err_free_decoder; }

return decoder;

-err_free_decoder_tree: - ocsd_destroy_dcd_tree(decoder->dcd_tree); err_free_decoder: - free(decoder); + cs_etm_decoder__free(decoder); return NULL; }

In and ideal world there is one CPU per cs_etm_queue and as such, one trace ID per cs_etm_queue. In the real world CoreSight topologies allow multiple CPUs to use the same sink, which translates to multiple trace IDs per cs_etm_queue.

To deal with this a new cs_etm_traceid_queue structure is introduced to enclose all the information related to a single trace ID, allowing a cs_etm_queue to handle traces generated by any number of CPUs.

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org --- .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 4 +- tools/perf/util/cs-etm.c | 368 +++++++++++------- tools/perf/util/cs-etm.h | 15 +- 3 files changed, 237 insertions(+), 150 deletions(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 12f97e1ff945..275c72264820 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -412,8 +412,8 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( struct cs_etm_queue *etmq = decoder->data; struct cs_etm_packet_queue *packet_queue;

- /* First get the packet queue */ - packet_queue = cs_etm__etmq_get_packet_queue(etmq); + /* First get the packet queue for this traceID */ + packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id); if (!packet_queue) return OCSD_RESP_FATAL_SYS_ERR;

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 5a9ebbf31614..7d862d26c107 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -60,25 +60,30 @@ struct cs_etm_auxtrace { unsigned int pmu_type; };

+struct cs_etm_traceid_queue { + u8 trace_chan_id; + u64 period_instructions; + size_t last_branch_pos; + union perf_event *event_buf; + struct branch_stack *last_branch; + struct branch_stack *last_branch_rb; + struct cs_etm_packet *prev_packet; + struct cs_etm_packet *packet; + struct cs_etm_packet_queue packet_queue; +}; + struct cs_etm_queue { struct cs_etm_auxtrace *etm; struct thread *thread; struct cs_etm_decoder *decoder; struct auxtrace_buffer *buffer; - union perf_event *event_buf; unsigned int queue_nr; pid_t pid, tid; int cpu; u64 offset; - u64 period_instructions; - struct branch_stack *last_branch; - struct branch_stack *last_branch_rb; - size_t last_branch_pos; - struct cs_etm_packet *prev_packet; - struct cs_etm_packet *packet; const unsigned char *buf; size_t buf_len, buf_used; - struct cs_etm_packet_queue packet_queue; + struct cs_etm_traceid_queue *traceid_queues; };

static int cs_etm__update_queues(struct cs_etm_auxtrace *etm); @@ -150,10 +155,96 @@ static void cs_etm__clear_packet_queue(struct cs_etm_packet_queue *queue) } }

+static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq, + u8 trace_chan_id) +{ + int rc = -ENOMEM; + struct cs_etm_auxtrace *etm = etmq->etm; + + cs_etm__clear_packet_queue(&tidq->packet_queue); + + tidq->trace_chan_id = trace_chan_id; + + tidq->packet = zalloc(sizeof(struct cs_etm_packet)); + if (!tidq->packet) + goto out; + + if (etm->synth_opts.last_branch || etm->sample_branches) { + tidq->prev_packet = zalloc(sizeof(struct cs_etm_packet)); + if (!tidq->prev_packet) + goto out_free; + } + + if (etm->synth_opts.last_branch) { + size_t sz = sizeof(struct branch_stack); + + sz += etm->synth_opts.last_branch_sz * + sizeof(struct branch_entry); + tidq->last_branch = zalloc(sz); + if (!tidq->last_branch) + goto out_free; + tidq->last_branch_rb = zalloc(sz); + if (!tidq->last_branch_rb) + goto out_free; + } + + tidq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE); + if (!tidq->event_buf) + goto out_free; + + return 0; + +out_free: + zfree(&tidq->last_branch_rb); + zfree(&tidq->last_branch); + zfree(&tidq->prev_packet); + zfree(&tidq->packet); +out: + return rc; +} + +static struct cs_etm_traceid_queue +*cs_etm__etmq_get_traceid_queue(struct cs_etm_queue *etmq, u8 trace_chan_id) +{ + struct cs_etm_traceid_queue *tidq; + struct cs_etm_auxtrace *etm = etmq->etm; + + if (!etm->timeless_decoding) + return NULL; + + tidq = etmq->traceid_queues; + + if (tidq) + return tidq; + + tidq = calloc(CS_ETM_PACKET_QUEUE_NR, sizeof(*tidq)); + if (!tidq) + return NULL; + + if (cs_etm__init_traceid_queue(etmq, tidq, trace_chan_id)) + goto out_free; + + etmq->traceid_queues = tidq; + + return etmq->traceid_queues; + +out_free: + free(tidq); + + return NULL; +} + struct cs_etm_packet_queue -*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq) +*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id) { - return &etmq->packet_queue; + struct cs_etm_traceid_queue *tidq; + + tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id); + if (tidq) + return &tidq->packet_queue; + + return NULL; }

static void cs_etm__packet_dump(const char *pkt_string) @@ -327,11 +418,12 @@ static void cs_etm__free_queue(void *priv)

thread__zput(etmq->thread); cs_etm_decoder__free(etmq->decoder); - zfree(&etmq->event_buf); - zfree(&etmq->last_branch); - zfree(&etmq->last_branch_rb); - zfree(&etmq->prev_packet); - zfree(&etmq->packet); + zfree(&etmq->traceid_queues->event_buf); + zfree(&etmq->traceid_queues->last_branch); + zfree(&etmq->traceid_queues->last_branch_rb); + zfree(&etmq->traceid_queues->prev_packet); + zfree(&etmq->traceid_queues->packet); + zfree(&etmq->traceid_queues); free(etmq); }

@@ -443,39 +535,11 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm) struct cs_etm_decoder_params d_params; struct cs_etm_trace_params *t_params = NULL; struct cs_etm_queue *etmq; - size_t szp = sizeof(struct cs_etm_packet);

etmq = zalloc(sizeof(*etmq)); if (!etmq) return NULL;

- etmq->packet = zalloc(szp); - if (!etmq->packet) - goto out_free; - - if (etm->synth_opts.last_branch || etm->sample_branches) { - etmq->prev_packet = zalloc(szp); - if (!etmq->prev_packet) - goto out_free; - } - - if (etm->synth_opts.last_branch) { - size_t sz = sizeof(struct branch_stack); - - sz += etm->synth_opts.last_branch_sz * - sizeof(struct branch_entry); - etmq->last_branch = zalloc(sz); - if (!etmq->last_branch) - goto out_free; - etmq->last_branch_rb = zalloc(sz); - if (!etmq->last_branch_rb) - goto out_free; - } - - etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE); - if (!etmq->event_buf) - goto out_free; - /* Use metadata to fill in trace parameters for trace decoder */ t_params = zalloc(sizeof(*t_params) * etm->num_cpu);

@@ -510,12 +574,6 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm) out_free_decoder: cs_etm_decoder__free(etmq->decoder); out_free: - zfree(&t_params); - zfree(&etmq->event_buf); - zfree(&etmq->last_branch); - zfree(&etmq->last_branch_rb); - zfree(&etmq->prev_packet); - zfree(&etmq->packet); free(etmq);

return NULL; @@ -545,8 +603,6 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, etmq->tid = queue->tid; etmq->pid = -1; etmq->offset = 0; - etmq->period_instructions = 0; - cs_etm__clear_packet_queue(&etmq->packet_queue);

out: return ret; @@ -579,10 +635,12 @@ static int cs_etm__update_queues(struct cs_etm_auxtrace *etm) return 0; }

-static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq) +static inline +void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) { - struct branch_stack *bs_src = etmq->last_branch_rb; - struct branch_stack *bs_dst = etmq->last_branch; + struct branch_stack *bs_src = tidq->last_branch_rb; + struct branch_stack *bs_dst = tidq->last_branch; size_t nr = 0;

/* @@ -602,9 +660,9 @@ static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq) * two steps. First, copy the branches from the most recently inserted * branch ->last_branch_pos until the end of bs_src->entries buffer. */ - nr = etmq->etm->synth_opts.last_branch_sz - etmq->last_branch_pos; + nr = etmq->etm->synth_opts.last_branch_sz - tidq->last_branch_pos; memcpy(&bs_dst->entries[0], - &bs_src->entries[etmq->last_branch_pos], + &bs_src->entries[tidq->last_branch_pos], sizeof(struct branch_entry) * nr);

/* @@ -617,14 +675,15 @@ static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq) if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) { memcpy(&bs_dst->entries[nr], &bs_src->entries[0], - sizeof(struct branch_entry) * etmq->last_branch_pos); + sizeof(struct branch_entry) * tidq->last_branch_pos); } }

-static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq) +static inline +void cs_etm__reset_last_branch_rb(struct cs_etm_traceid_queue *tidq) { - etmq->last_branch_pos = 0; - etmq->last_branch_rb->nr = 0; + tidq->last_branch_pos = 0; + tidq->last_branch_rb->nr = 0; }

static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq, @@ -677,9 +736,10 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq, return packet->start_addr + offset * 4; }

-static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) +static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) { - struct branch_stack *bs = etmq->last_branch_rb; + struct branch_stack *bs = tidq->last_branch_rb; struct branch_entry *be;

/* @@ -688,14 +748,14 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) * buffer down. After writing the first element of the stack, move the * insert position back to the end of the buffer. */ - if (!etmq->last_branch_pos) - etmq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz; + if (!tidq->last_branch_pos) + tidq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;

- etmq->last_branch_pos -= 1; + tidq->last_branch_pos -= 1;

- be = &bs->entries[etmq->last_branch_pos]; - be->from = cs_etm__last_executed_instr(etmq->prev_packet); - be->to = cs_etm__first_executed_instr(etmq->packet); + be = &bs->entries[tidq->last_branch_pos]; + be->from = cs_etm__last_executed_instr(tidq->prev_packet); + be->to = cs_etm__first_executed_instr(tidq->packet); /* No support for mispredict */ be->flags.mispred = 0; be->flags.predicted = 1; @@ -779,11 +839,12 @@ static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, }

static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq, u64 addr, u64 period) { int ret = 0; struct cs_etm_auxtrace *etm = etmq->etm; - union perf_event *event = etmq->event_buf; + union perf_event *event = tidq->event_buf; struct perf_sample sample = {.ip = 0,};

event->sample.header.type = PERF_RECORD_SAMPLE; @@ -796,14 +857,14 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, sample.id = etmq->etm->instructions_id; sample.stream_id = etmq->etm->instructions_id; sample.period = period; - sample.cpu = etmq->packet->cpu; - sample.flags = etmq->prev_packet->flags; + sample.cpu = tidq->packet->cpu; + sample.flags = tidq->prev_packet->flags; sample.insn_len = 1; sample.cpumode = event->sample.header.misc;

if (etm->synth_opts.last_branch) { - cs_etm__copy_last_branch_rb(etmq); - sample.branch_stack = etmq->last_branch; + cs_etm__copy_last_branch_rb(etmq, tidq); + sample.branch_stack = tidq->last_branch; }

if (etm->synth_opts.inject) { @@ -821,7 +882,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, ret);

if (etm->synth_opts.last_branch) - cs_etm__reset_last_branch_rb(etmq); + cs_etm__reset_last_branch_rb(tidq);

return ret; } @@ -830,19 +891,20 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, * The cs etm packet encodes an instruction range between a branch target * and the next taken branch. Generate sample accordingly. */ -static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) +static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) { int ret = 0; struct cs_etm_auxtrace *etm = etmq->etm; struct perf_sample sample = {.ip = 0,}; - union perf_event *event = etmq->event_buf; + union perf_event *event = tidq->event_buf; struct dummy_branch_stack { u64 nr; struct branch_entry entries; } dummy_bs; u64 ip;

- ip = cs_etm__last_executed_instr(etmq->prev_packet); + ip = cs_etm__last_executed_instr(tidq->prev_packet);

event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = cs_etm__cpu_mode(etmq, ip); @@ -851,12 +913,12 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) sample.ip = ip; sample.pid = etmq->pid; sample.tid = etmq->tid; - sample.addr = cs_etm__first_executed_instr(etmq->packet); + sample.addr = cs_etm__first_executed_instr(tidq->packet); sample.id = etmq->etm->branches_id; sample.stream_id = etmq->etm->branches_id; sample.period = 1; - sample.cpu = etmq->packet->cpu; - sample.flags = etmq->prev_packet->flags; + sample.cpu = tidq->packet->cpu; + sample.flags = tidq->prev_packet->flags; sample.cpumode = event->sample.header.misc;

/* @@ -999,34 +1061,35 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, return 0; }

-static int cs_etm__sample(struct cs_etm_queue *etmq) +static int cs_etm__sample(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) { struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; int ret; - u64 instrs_executed = etmq->packet->instr_count; + u64 instrs_executed = tidq->packet->instr_count;

- etmq->period_instructions += instrs_executed; + tidq->period_instructions += instrs_executed;

/* * Record a branch when the last instruction in * PREV_PACKET is a branch. */ if (etm->synth_opts.last_branch && - etmq->prev_packet && - etmq->prev_packet->sample_type == CS_ETM_RANGE && - etmq->prev_packet->last_instr_taken_branch) - cs_etm__update_last_branch_rb(etmq); + tidq->prev_packet && + tidq->prev_packet->sample_type == CS_ETM_RANGE && + tidq->prev_packet->last_instr_taken_branch) + cs_etm__update_last_branch_rb(etmq, tidq);

if (etm->sample_instructions && - etmq->period_instructions >= etm->instructions_sample_period) { + tidq->period_instructions >= etm->instructions_sample_period) { /* * Emit instruction sample periodically * TODO: allow period to be defined in cycles and clock time */

/* Get number of instructions executed after the sample point */ - u64 instrs_over = etmq->period_instructions - + u64 instrs_over = tidq->period_instructions - etm->instructions_sample_period;

/* @@ -1035,31 +1098,31 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) * executed, but PC has not advanced to next instruction) */ u64 offset = (instrs_executed - instrs_over - 1); - u64 addr = cs_etm__instr_addr(etmq, etmq->packet, offset); + u64 addr = cs_etm__instr_addr(etmq, tidq->packet, offset);

ret = cs_etm__synth_instruction_sample( - etmq, addr, etm->instructions_sample_period); + etmq, tidq, addr, etm->instructions_sample_period); if (ret) return ret;

/* Carry remaining instructions into next sample period */ - etmq->period_instructions = instrs_over; + tidq->period_instructions = instrs_over; }

- if (etm->sample_branches && etmq->prev_packet) { + if (etm->sample_branches && tidq->prev_packet) { bool generate_sample = false;

/* Generate sample for tracing on packet */ - if (etmq->prev_packet->sample_type == CS_ETM_DISCONTINUITY) + if (tidq->prev_packet->sample_type == CS_ETM_DISCONTINUITY) generate_sample = true;

/* Generate sample for branch taken packet */ - if (etmq->prev_packet->sample_type == CS_ETM_RANGE && - etmq->prev_packet->last_instr_taken_branch) + if (tidq->prev_packet->sample_type == CS_ETM_RANGE && + tidq->prev_packet->last_instr_taken_branch) generate_sample = true;

if (generate_sample) { - ret = cs_etm__synth_branch_sample(etmq); + ret = cs_etm__synth_branch_sample(etmq, tidq); if (ret) return ret; } @@ -1070,15 +1133,15 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. */ - tmp = etmq->packet; - etmq->packet = etmq->prev_packet; - etmq->prev_packet = tmp; + tmp = tidq->packet; + tidq->packet = tidq->prev_packet; + tidq->prev_packet = tmp; }

return 0; }

-static int cs_etm__exception(struct cs_etm_queue *etmq) +static int cs_etm__exception(struct cs_etm_traceid_queue *tidq) { /* * When the exception packet is inserted, whether the last instruction @@ -1091,27 +1154,28 @@ static int cs_etm__exception(struct cs_etm_queue *etmq) * swap PACKET with PREV_PACKET. This keeps PREV_PACKET to be useful * for generating instruction and branch samples. */ - if (etmq->prev_packet->sample_type == CS_ETM_RANGE) - etmq->prev_packet->last_instr_taken_branch = true; + if (tidq->prev_packet->sample_type == CS_ETM_RANGE) + tidq->prev_packet->last_instr_taken_branch = true;

return 0; }

-static int cs_etm__flush(struct cs_etm_queue *etmq) +static int cs_etm__flush(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) { int err = 0; struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp;

- if (!etmq->prev_packet) + if (!tidq->prev_packet) return 0;

/* Handle start tracing packet */ - if (etmq->prev_packet->sample_type == CS_ETM_EMPTY) + if (tidq->prev_packet->sample_type == CS_ETM_EMPTY) goto swap_packet;

if (etmq->etm->synth_opts.last_branch && - etmq->prev_packet->sample_type == CS_ETM_RANGE) { + tidq->prev_packet->sample_type == CS_ETM_RANGE) { /* * Generate a last branch event for the branches left in the * circular buffer at the end of the trace. @@ -1119,21 +1183,21 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) * Use the address of the end of the last reported execution * range */ - u64 addr = cs_etm__last_executed_instr(etmq->prev_packet); + u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);

err = cs_etm__synth_instruction_sample( - etmq, addr, - etmq->period_instructions); + etmq, tidq, addr, + tidq->period_instructions); if (err) return err;

- etmq->period_instructions = 0; + tidq->period_instructions = 0;

}

if (etm->sample_branches && - etmq->prev_packet->sample_type == CS_ETM_RANGE) { - err = cs_etm__synth_branch_sample(etmq); + tidq->prev_packet->sample_type == CS_ETM_RANGE) { + err = cs_etm__synth_branch_sample(etmq, tidq); if (err) return err; } @@ -1144,15 +1208,16 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. */ - tmp = etmq->packet; - etmq->packet = etmq->prev_packet; - etmq->prev_packet = tmp; + tmp = tidq->packet; + tidq->packet = tidq->prev_packet; + tidq->prev_packet = tmp; }

return err; }

-static int cs_etm__end_block(struct cs_etm_queue *etmq) +static int cs_etm__end_block(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) { int err;

@@ -1166,20 +1231,20 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq) * the trace. */ if (etmq->etm->synth_opts.last_branch && - etmq->prev_packet->sample_type == CS_ETM_RANGE) { + tidq->prev_packet->sample_type == CS_ETM_RANGE) { /* * Use the address of the end of the last reported execution * range. */ - u64 addr = cs_etm__last_executed_instr(etmq->prev_packet); + u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);

err = cs_etm__synth_instruction_sample( - etmq, addr, - etmq->period_instructions); + etmq, tidq, addr, + tidq->period_instructions); if (err) return err;

- etmq->period_instructions = 0; + tidq->period_instructions = 0; }

return 0; @@ -1278,10 +1343,11 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, return false; }

-static bool cs_etm__is_syscall(struct cs_etm_queue *etmq, u64 magic) +static bool cs_etm__is_syscall(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq, u64 magic) { - struct cs_etm_packet *packet = etmq->packet; - struct cs_etm_packet *prev_packet = etmq->prev_packet; + struct cs_etm_packet *packet = tidq->packet; + struct cs_etm_packet *prev_packet = tidq->prev_packet;

if (magic == __perf_cs_etmv3_magic) if (packet->exception_number == CS_ETMV3_EXC_SVC) @@ -1302,9 +1368,10 @@ static bool cs_etm__is_syscall(struct cs_etm_queue *etmq, u64 magic) return false; }

-static bool cs_etm__is_async_exception(struct cs_etm_queue *etmq, u64 magic) +static bool cs_etm__is_async_exception(struct cs_etm_traceid_queue *tidq, + u64 magic) { - struct cs_etm_packet *packet = etmq->packet; + struct cs_etm_packet *packet = tidq->packet;

if (magic == __perf_cs_etmv3_magic) if (packet->exception_number == CS_ETMV3_EXC_DEBUG_HALT || @@ -1327,10 +1394,12 @@ static bool cs_etm__is_async_exception(struct cs_etm_queue *etmq, u64 magic) return false; }

-static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq, u64 magic) +static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq, + u64 magic) { - struct cs_etm_packet *packet = etmq->packet; - struct cs_etm_packet *prev_packet = etmq->prev_packet; + struct cs_etm_packet *packet = tidq->packet; + struct cs_etm_packet *prev_packet = tidq->prev_packet;

if (magic == __perf_cs_etmv3_magic) if (packet->exception_number == CS_ETMV3_EXC_SMC || @@ -1373,10 +1442,11 @@ static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq, u64 magic) return false; }

-static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq) +static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) { - struct cs_etm_packet *packet = etmq->packet; - struct cs_etm_packet *prev_packet = etmq->prev_packet; + struct cs_etm_packet *packet = tidq->packet; + struct cs_etm_packet *prev_packet = tidq->prev_packet; u64 magic; int ret;

@@ -1478,7 +1548,7 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq) return ret;

/* The exception is for system call. */ - if (cs_etm__is_syscall(etmq, magic)) + if (cs_etm__is_syscall(etmq, tidq, magic)) packet->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET; @@ -1486,7 +1556,7 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq) * The exceptions are triggered by external signals from bus, * interrupt controller, debug module, PE reset or halt. */ - else if (cs_etm__is_async_exception(etmq, magic)) + else if (cs_etm__is_async_exception(tidq, magic)) packet->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | @@ -1495,7 +1565,7 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq) * Otherwise, exception is caused by trap, instruction & * data fault, or alignment errors. */ - else if (cs_etm__is_sync_exception(etmq, magic)) + else if (cs_etm__is_sync_exception(etmq, tidq, magic)) packet->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT; @@ -1577,17 +1647,18 @@ static int cs_etm__decode_data_block(struct cs_etm_queue *etmq) return ret; }

-static int cs_etm__process_decoder_queue(struct cs_etm_queue *etmq) +static int cs_etm__process_traceid_queue(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) { int ret; struct cs_etm_packet_queue *packet_queue;

- packet_queue = cs_etm__etmq_get_packet_queue(etmq); + packet_queue = &tidq->packet_queue;

/* Process each packet in this chunk */ while (1) { ret = cs_etm_decoder__get_packet(packet_queue, - etmq->packet); + tidq->packet); if (ret <= 0) /* * Stop processing this chunk on @@ -1602,18 +1673,18 @@ static int cs_etm__process_decoder_queue(struct cs_etm_queue *etmq) * prior to switch() statement to use address * information before packets swapping. */ - ret = cs_etm__set_sample_flags(etmq); + ret = cs_etm__set_sample_flags(etmq, tidq); if (ret < 0) break;

- switch (etmq->packet->sample_type) { + switch (tidq->packet->sample_type) { case CS_ETM_RANGE: /* * If the packet contains an instruction * range, generate instruction sequence * events. */ - cs_etm__sample(etmq); + cs_etm__sample(etmq, tidq); break; case CS_ETM_EXCEPTION: case CS_ETM_EXCEPTION_RET: @@ -1622,14 +1693,14 @@ static int cs_etm__process_decoder_queue(struct cs_etm_queue *etmq) * make sure the previous instruction * range packet to be handled properly. */ - cs_etm__exception(etmq); + cs_etm__exception(tidq); break; case CS_ETM_DISCONTINUITY: /* * Discontinuity in trace, flush * previous branch stack */ - cs_etm__flush(etmq); + cs_etm__flush(etmq, tidq); break; case CS_ETM_EMPTY: /* @@ -1649,6 +1720,11 @@ static int cs_etm__process_decoder_queue(struct cs_etm_queue *etmq) static int cs_etm__run_decoder(struct cs_etm_queue *etmq) { int err = 0; + struct cs_etm_traceid_queue *tidq; + + tidq = cs_etm__etmq_get_traceid_queue(etmq, CS_ETM_PER_THREAD_TRACEID); + if (!tidq) + return -EINVAL;

/* Go through each buffer in the queue and decode them one by one */ while (1) { @@ -1667,13 +1743,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq) * an error occurs other than hoping the next one will * be better. */ - err = cs_etm__process_decoder_queue(etmq); + err = cs_etm__process_traceid_queue(etmq, tidq);

} while (etmq->buf_len);

if (err == 0) /* Flush any remaining branch stack entries */ - err = cs_etm__end_block(etmq); + err = cs_etm__end_block(etmq, tidq); }

return err; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index b6d0e0d0c43f..0dfc79a678f8 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -137,6 +137,16 @@ struct cs_etm_packet { #define CS_ETM_PACKET_MAX_BUFFER 1024 #define CS_ETM_PACKET_QUEUE_NR 1

+/* + * When working with per-thread scenarios the process under trace can + * be scheduled on any CPU and as such, more than one traceID may be + * associated with the same process. Since a traceID of '0' is illegal + * as per the CoreSight architecture, use that specific value to + * identify the queue where all packets (with any traceID) are + * aggregated. + */ +#define CS_ETM_PER_THREAD_TRACEID 0 + struct cs_etm_packet_queue { u32 packet_count; u32 head; @@ -173,7 +183,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); int cs_etm__get_cpu(u8 trace_chan_id, int *cpu); struct cs_etm_packet_queue -*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq); +*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id); #else static inline int cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused, @@ -189,7 +199,8 @@ static inline int cs_etm__get_cpu(u8 trace_chan_id __maybe_unused, }

static inline struct cs_etm_packet_queue *cs_etm__etmq_get_packet_queue( - struct cs_etm_queue *etmq __maybe_unused) + struct cs_etm_queue *etmq __maybe_unused, + u8 trace_chan_id __maybe_unused) { return NULL; }

Nowadays the synthesize code is using the packet's cpu information, making cs_etm_queue::cpu useless. As such simply remove it.

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org --- tools/perf/util/cs-etm.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 7d862d26c107..7b516d4dad28 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -79,7 +79,6 @@ struct cs_etm_queue { struct auxtrace_buffer *buffer; unsigned int queue_nr; pid_t pid, tid; - int cpu; u64 offset; const unsigned char *buf; size_t buf_len, buf_used; @@ -599,7 +598,6 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, queue->priv = etmq; etmq->etm = etm; etmq->queue_nr = queue_nr; - etmq->cpu = queue->cpu; etmq->tid = queue->tid; etmq->pid = -1; etmq->offset = 0; @@ -831,11 +829,8 @@ static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, etmq->thread = machine__find_thread(etm->machine, -1, etmq->tid);

- if (etmq->thread) { + if (etmq->thread) etmq->pid = etmq->thread->pid_; - if (queue->cpu == -1) - etmq->cpu = etmq->thread->cpu; - } }

static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,

The tid/pid fields of structure cs_etm_queue are CPU dependent and as such need to be part of the cs_etm_traceid_queue in order to support CPU-wide trace scenarios.

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org --- tools/perf/util/cs-etm.c | 44 ++++++++++++++++++++++++---------------- 1 file changed, 26 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 0dcbfe4a7932..df128cba4f2a 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -62,6 +62,7 @@ struct cs_etm_auxtrace {

struct cs_etm_traceid_queue { u8 trace_chan_id; + pid_t pid, tid; u64 period_instructions; size_t last_branch_pos; union perf_event *event_buf; @@ -78,7 +79,6 @@ struct cs_etm_queue { struct cs_etm_decoder *decoder; struct auxtrace_buffer *buffer; unsigned int queue_nr; - pid_t pid, tid; u64 offset; const unsigned char *buf; size_t buf_len, buf_used; @@ -159,10 +159,14 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq, u8 trace_chan_id) { int rc = -ENOMEM; + struct auxtrace_queue *queue; struct cs_etm_auxtrace *etm = etmq->etm;

cs_etm__clear_packet_queue(&tidq->packet_queue);

+ queue = &etmq->etm->queues.queue_array[etmq->queue_nr]; + tidq->tid = queue->tid; + tidq->pid = -1; tidq->trace_chan_id = trace_chan_id;

tidq->packet = zalloc(sizeof(struct cs_etm_packet)); @@ -598,8 +602,6 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, queue->priv = etmq; etmq->etm = etm; etmq->queue_nr = queue_nr; - etmq->tid = queue->tid; - etmq->pid = -1; etmq->offset = 0;

out: @@ -817,23 +819,19 @@ cs_etm__get_trace(struct cs_etm_queue *etmq) }

static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, - struct auxtrace_queue *queue) + struct auxtrace_queue *queue, + struct cs_etm_traceid_queue *tidq) { - struct cs_etm_traceid_queue *tidq; - struct cs_etm_queue *etmq = queue->priv; - - tidq = cs_etm__etmq_get_traceid_queue(etmq, CS_ETM_PER_THREAD_TRACEID); - /* CPU-wide tracing isn't supported yet */ if (queue->tid == -1) return;

- if ((!tidq->thread) && (etmq->tid != -1)) + if ((!tidq->thread) && (tidq->tid != -1)) tidq->thread = machine__find_thread(etm->machine, -1, - etmq->tid); + tidq->tid);

if (tidq->thread) - etmq->pid = tidq->thread->pid_; + tidq->pid = tidq->thread->pid_; }

static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, @@ -850,8 +848,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, event->sample.header.size = sizeof(struct perf_event_header);

sample.ip = addr; - sample.pid = etmq->pid; - sample.tid = etmq->tid; + sample.pid = tidq->pid; + sample.tid = tidq->tid; sample.id = etmq->etm->instructions_id; sample.stream_id = etmq->etm->instructions_id; sample.period = period; @@ -909,8 +907,8 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, event->sample.header.size = sizeof(struct perf_event_header);

sample.ip = ip; - sample.pid = etmq->pid; - sample.tid = etmq->tid; + sample.pid = tidq->pid; + sample.tid = tidq->tid; sample.addr = cs_etm__first_executed_instr(tidq->packet); sample.id = etmq->etm->branches_id; sample.stream_id = etmq->etm->branches_id; @@ -1762,9 +1760,19 @@ static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm, for (i = 0; i < queues->nr_queues; i++) { struct auxtrace_queue *queue = &etm->queues.queue_array[i]; struct cs_etm_queue *etmq = queue->priv; + struct cs_etm_traceid_queue *tidq; + + if (!etmq) + continue; + + tidq = cs_etm__etmq_get_traceid_queue(etmq, + CS_ETM_PER_THREAD_TRACEID); + + if (!tidq) + continue;

- if (etmq && ((tid == -1) || (etmq->tid == tid))) { - cs_etm__set_pid_tid_cpu(etm, queue); + if ((tid == -1) || (tidq->tid == tid)) { + cs_etm__set_pid_tid_cpu(etm, queue, tidq); cs_etm__run_decoder(etmq); } }

When working with CPU-wide traces different traceID may be found in the same stream. As such we need to use the decoder callback that provides the traceID in order to know the thread context being decoded.

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org --- .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 14 +++---- .../perf/util/cs-etm-decoder/cs-etm-decoder.h | 3 +- tools/perf/util/cs-etm.c | 41 +++++++++++++------ 3 files changed, 36 insertions(+), 22 deletions(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 4303d2d00d31..87264b79de0e 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -41,15 +41,14 @@ static u32 cs_etm_decoder__mem_access(const void *context, const ocsd_vaddr_t address, const ocsd_mem_space_acc_t mem_space __maybe_unused, + const u8 trace_chan_id, const u32 req_size, u8 *buffer) { struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;

- return decoder->mem_access(decoder->data, - address, - req_size, - buffer); + return decoder->mem_access(decoder->data, trace_chan_id, + address, req_size, buffer); }

int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder, @@ -58,9 +57,10 @@ int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder, { decoder->mem_access = cb_func;

- if (ocsd_dt_add_callback_mem_acc(decoder->dcd_tree, start, end, - OCSD_MEM_SPACE_ANY, - cs_etm_decoder__mem_access, decoder)) + if (ocsd_dt_add_callback_trcid_mem_acc(decoder->dcd_tree, start, end, + OCSD_MEM_SPACE_ANY, + cs_etm_decoder__mem_access, + decoder)) return -1;

return 0; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 6ae7ab4cf5fe..11f3391d06f2 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -19,8 +19,7 @@ struct cs_etm_packet_queue;

struct cs_etm_queue;

-typedef u32 (*cs_etm_mem_cb_type)(struct cs_etm_queue *, u64, - size_t, u8 *); +typedef u32 (*cs_etm_mem_cb_type)(struct cs_etm_queue *, u8, u64, size_t, u8 *);

struct cs_etmv3_trace_params { u32 reg_ctrl; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index df128cba4f2a..70c43ac416c3 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -491,8 +491,8 @@ static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address) } }

-static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address, - size_t size, u8 *buffer) +static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, + u64 address, size_t size, u8 *buffer) { u8 cpumode; u64 offset; @@ -501,6 +501,8 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address, struct machine *machine; struct addr_location al;

+ (void)trace_chan_id; + if (!etmq) return 0;

@@ -687,10 +689,12 @@ void cs_etm__reset_last_branch_rb(struct cs_etm_traceid_queue *tidq) }

static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq, - u64 addr) { + u8 trace_chan_id, u64 addr) +{ u8 instrBytes[2];

- cs_etm__mem_access(etmq, addr, ARRAY_SIZE(instrBytes), instrBytes); + cs_etm__mem_access(etmq, trace_chan_id, addr, + ARRAY_SIZE(instrBytes), instrBytes); /* * T32 instruction size is indicated by bits[15:11] of the first * 16-bit word of the instruction: 0b11101, 0b11110 and 0b11111 @@ -719,6 +723,7 @@ u64 cs_etm__last_executed_instr(const struct cs_etm_packet *packet) }

static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq, + u64 trace_chan_id, const struct cs_etm_packet *packet, u64 offset) { @@ -726,7 +731,8 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq, u64 addr = packet->start_addr;

while (offset > 0) { - addr += cs_etm__t32_instr_size(etmq, addr); + addr += cs_etm__t32_instr_size(etmq, + trace_chan_id, addr); offset--; } return addr; @@ -1063,6 +1069,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; int ret; + u8 trace_chan_id = tidq->trace_chan_id; u64 instrs_executed = tidq->packet->instr_count;

tidq->period_instructions += instrs_executed; @@ -1094,7 +1101,8 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, * executed, but PC has not advanced to next instruction) */ u64 offset = (instrs_executed - instrs_over - 1); - u64 addr = cs_etm__instr_addr(etmq, tidq->packet, offset); + u64 addr = cs_etm__instr_addr(etmq, trace_chan_id, + tidq->packet, offset);

ret = cs_etm__synth_instruction_sample( etmq, tidq, addr, etm->instructions_sample_period); @@ -1272,7 +1280,7 @@ static int cs_etm__get_data_block(struct cs_etm_queue *etmq) return etmq->buf_len; }

-static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, +static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id, struct cs_etm_packet *packet, u64 end_addr) { @@ -1295,7 +1303,8 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, * so below only read 2 bytes as instruction size for T32. */ addr = end_addr - 2; - cs_etm__mem_access(etmq, addr, sizeof(instr16), (u8 *)&instr16); + cs_etm__mem_access(etmq, trace_chan_id, addr, + sizeof(instr16), (u8 *)&instr16); if ((instr16 & 0xFF00) == 0xDF00) return true;

@@ -1310,7 +1319,8 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, * +---------+---------+-------------------------+ */ addr = end_addr - 4; - cs_etm__mem_access(etmq, addr, sizeof(instr32), (u8 *)&instr32); + cs_etm__mem_access(etmq, trace_chan_id, addr, + sizeof(instr32), (u8 *)&instr32); if ((instr32 & 0x0F000000) == 0x0F000000 && (instr32 & 0xF0000000) != 0xF0000000) return true; @@ -1326,7 +1336,8 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, * +-----------------------+---------+-----------+ */ addr = end_addr - 4; - cs_etm__mem_access(etmq, addr, sizeof(instr32), (u8 *)&instr32); + cs_etm__mem_access(etmq, trace_chan_id, addr, + sizeof(instr32), (u8 *)&instr32); if ((instr32 & 0xFFE0001F) == 0xd4000001) return true;

@@ -1342,6 +1353,7 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, static bool cs_etm__is_syscall(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq, u64 magic) { + u8 trace_chan_id = tidq->trace_chan_id; struct cs_etm_packet *packet = tidq->packet; struct cs_etm_packet *prev_packet = tidq->prev_packet;

@@ -1356,7 +1368,7 @@ static bool cs_etm__is_syscall(struct cs_etm_queue *etmq, */ if (magic == __perf_cs_etmv4_magic) { if (packet->exception_number == CS_ETMV4_EXC_CALL && - cs_etm__is_svc_instr(etmq, prev_packet, + cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet, prev_packet->end_addr)) return true; } @@ -1394,6 +1406,7 @@ static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq, u64 magic) { + u8 trace_chan_id = tidq->trace_chan_id; struct cs_etm_packet *packet = tidq->packet; struct cs_etm_packet *prev_packet = tidq->prev_packet;

@@ -1419,7 +1432,7 @@ static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq, * (SMC, HVC) are taken as sync exceptions. */ if (packet->exception_number == CS_ETMV4_EXC_CALL && - !cs_etm__is_svc_instr(etmq, prev_packet, + !cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet, prev_packet->end_addr)) return true;

@@ -1443,6 +1456,7 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq, { struct cs_etm_packet *packet = tidq->packet; struct cs_etm_packet *prev_packet = tidq->prev_packet; + u8 trace_chan_id = tidq->trace_chan_id; u64 magic; int ret;

@@ -1523,7 +1537,8 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq, if (prev_packet->flags == (PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT) && - cs_etm__is_svc_instr(etmq, packet, packet->start_addr)) + cs_etm__is_svc_instr(etmq, trace_chan_id, + packet, packet->start_addr)) prev_packet->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET;

This patch deals with timestamp packets received from the decoding library in order to give the front end packet processing loop a handle on the time instruction conveyed by range packets have been executed at.

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org --- .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 112 +++++++++++++++++- tools/perf/util/cs-etm.c | 19 +++ tools/perf/util/cs-etm.h | 17 +++ 3 files changed, 144 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index ce85e52f989c..33e975c8d11b 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -269,6 +269,76 @@ cs_etm_decoder__create_etm_packet_printer(struct cs_etm_trace_params *t_params, trace_config); }

+static ocsd_datapath_resp_t +cs_etm_decoder__do_soft_timestamp(struct cs_etm_queue *etmq, + struct cs_etm_packet_queue *packet_queue, + const uint8_t trace_chan_id) +{ + /* No timestamp packet has been received, nothing to do */ + if (!packet_queue->timestamp) + return OCSD_RESP_CONT; + + packet_queue->timestamp = packet_queue->next_timestamp; + + /* Estimate the timestamp for the next range packet */ + packet_queue->next_timestamp += packet_queue->instr_count; + packet_queue->instr_count = 0; + + /* Tell the front end which traceid_queue needs attention */ + cs_etm__etmq_set_traceid_queue_timestamp(etmq, trace_chan_id); + + return OCSD_RESP_WAIT; +} + +static ocsd_datapath_resp_t +cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq, + const ocsd_generic_trace_elem *elem, + const uint8_t trace_chan_id) +{ + struct cs_etm_packet_queue *packet_queue; + + /* First get the packet queue for this traceID */ + packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id); + if (!packet_queue) + return OCSD_RESP_FATAL_SYS_ERR; + + /* + * We've seen a timestamp packet before - simply record the new value. + * Function do_soft_timestamp() will report the value to the front end, + * hence asking the decoder to keep decoding rather than stopping. + */ + if (packet_queue->timestamp) { + packet_queue->next_timestamp = elem->timestamp; + return OCSD_RESP_CONT; + } + + /* + * This is the first timestamp we've seen since the beginning of traces + * or a discontinuity. Since timestamps packets are generated *after* + * range packets have been generated, we need to estimate the time at + * which instructions started by substracting the number of instructions + * executed to the timestamp. + */ + packet_queue->timestamp = elem->timestamp - + packet_queue->instr_count; + packet_queue->next_timestamp = elem->timestamp; + packet_queue->instr_count = 0; + + /* Tell the front end which traceid_queue needs attention */ + cs_etm__etmq_set_traceid_queue_timestamp(etmq, trace_chan_id); + + /* Halt processing until we are being told to proceed */ + return OCSD_RESP_WAIT; +} + +static void +cs_etm_decoder__reset_timestamp(struct cs_etm_packet_queue *packet_queue) +{ + packet_queue->timestamp = 0; + packet_queue->next_timestamp = 0; + packet_queue->instr_count = 0; +} + static ocsd_datapath_resp_t cs_etm_decoder__buffer_packet(struct cs_etm_packet_queue *packet_queue, const u8 trace_chan_id, @@ -310,7 +380,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_packet_queue *packet_queue, }

static ocsd_datapath_resp_t -cs_etm_decoder__buffer_range(struct cs_etm_packet_queue *packet_queue, +cs_etm_decoder__buffer_range(struct cs_etm_queue *etmq, + struct cs_etm_packet_queue *packet_queue, const ocsd_generic_trace_elem *elem, const uint8_t trace_chan_id) { @@ -365,6 +436,23 @@ cs_etm_decoder__buffer_range(struct cs_etm_packet_queue *packet_queue,

packet->last_instr_size = elem->last_instr_sz;

+ /* per-thread scenario, no need to generate a timestamp */ + if (cs_etm__etmq_is_timeless(etmq)) + goto out; + + /* + * The packet queue is full and we haven't seen a timestamp (had we + * seen one the packet queue wouldn't be full). Let the front end + * deal with it. + */ + if (ret == OCSD_RESP_WAIT) + goto out; + + packet_queue->instr_count += elem->num_instr_range; + /* Tell the front end we have a new timestamp to process */ + ret = cs_etm_decoder__do_soft_timestamp(etmq, packet_queue, + trace_chan_id); +out: return ret; }

@@ -372,6 +460,11 @@ static ocsd_datapath_resp_t cs_etm_decoder__buffer_discontinuity(struct cs_etm_packet_queue *queue, const uint8_t trace_chan_id) { + /* + * Something happened and who knows when we'll get new traces so + * reset time statistics. + */ + cs_etm_decoder__reset_timestamp(queue); return cs_etm_decoder__buffer_packet(queue, trace_chan_id, CS_ETM_DISCONTINUITY); } @@ -404,6 +497,7 @@ cs_etm_decoder__buffer_exception_ret(struct cs_etm_packet_queue *queue,

static ocsd_datapath_resp_t cs_etm_decoder__set_tid(struct cs_etm_queue *etmq, + struct cs_etm_packet_queue *packet_queue, const ocsd_generic_trace_elem *elem, const uint8_t trace_chan_id) { @@ -417,6 +511,12 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq, if (cs_etm__etmq_set_tid(etmq, tid, trace_chan_id)) return OCSD_RESP_FATAL_SYS_ERR;

+ /* + * A timestamp is generated after a PE_CONTEXT element so make sure + * to rely on that coming one. + */ + cs_etm_decoder__reset_timestamp(packet_queue); + return OCSD_RESP_CONT; }

@@ -446,7 +546,7 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( trace_chan_id); break; case OCSD_GEN_TRC_ELEM_INSTR_RANGE: - resp = cs_etm_decoder__buffer_range(packet_queue, elem, + resp = cs_etm_decoder__buffer_range(etmq, packet_queue, elem, trace_chan_id); break; case OCSD_GEN_TRC_ELEM_EXCEPTION: @@ -457,11 +557,15 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( resp = cs_etm_decoder__buffer_exception_ret(packet_queue, trace_chan_id); break; + case OCSD_GEN_TRC_ELEM_TIMESTAMP: + resp = cs_etm_decoder__do_hard_timestamp(etmq, elem, + trace_chan_id); + break; case OCSD_GEN_TRC_ELEM_PE_CONTEXT: - resp = cs_etm_decoder__set_tid(etmq, elem, trace_chan_id); + resp = cs_etm_decoder__set_tid(etmq, packet_queue, + elem, trace_chan_id); break; case OCSD_GEN_TRC_ELEM_ADDR_NACC: - case OCSD_GEN_TRC_ELEM_TIMESTAMP: case OCSD_GEN_TRC_ELEM_CYCLE_COUNT: case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN: case OCSD_GEN_TRC_ELEM_EVENT: diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index e97124f218fd..79978f4428b0 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -79,6 +79,7 @@ struct cs_etm_queue { struct cs_etm_decoder *decoder; struct auxtrace_buffer *buffer; unsigned int queue_nr; + u8 pending_timestamp; u64 offset; const unsigned char *buf; size_t buf_len, buf_used; @@ -132,6 +133,19 @@ int cs_etm__get_cpu(u8 trace_chan_id, int *cpu) return 0; }

+void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, + u8 trace_chan_id) +{ + /* + * Wnen a timestamp packet is encountered the backend code + * is stopped so that the front end has time to process packets + * that were accumulated in the traceID queue. Since there can + * be more than one channel per cs_etm_queue, we need to specify + * what traceID queue needs servicing. + */ + etmq->pending_timestamp = trace_chan_id; +} + static void cs_etm__clear_packet_queue(struct cs_etm_packet_queue *queue) { int i; @@ -941,6 +955,11 @@ int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq, return 0; }

+bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq) +{ + return !!etmq->etm->timeless_decoding; +} + static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq, u64 addr, u64 period) diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 5f32b271a50e..1f6ec7babe70 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -151,6 +151,9 @@ struct cs_etm_packet_queue { u32 packet_count; u32 head; u32 tail; + u32 instr_count; + u64 timestamp; + u64 next_timestamp; struct cs_etm_packet packet_buffer[CS_ETM_PACKET_MAX_BUFFER]; };

@@ -184,6 +187,9 @@ int cs_etm__process_auxtrace_info(union perf_event *event, int cs_etm__get_cpu(u8 trace_chan_id, int *cpu); int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq, pid_t tid, u8 trace_chan_id); +bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq); +void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, + u8 trace_chan_id); struct cs_etm_packet_queue *cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id); #else @@ -208,6 +214,17 @@ static inline int cs_etm__etmq_set_tid( return -1; }

+static inline bool cs_etm__etmq_is_timeless( + struct cs_etm_queue *etmq __maybe_unused) +{ + /* What else to return? */ + return true; +} + +static inline void cs_etm__etmq_set_traceid_queue_timestamp( + struct cs_etm_queue *etmq __maybe_unused, + u8 trace_chan_id __maybe_unused) {} + static inline struct cs_etm_packet_queue *cs_etm__etmq_get_packet_queue( struct cs_etm_queue *etmq __maybe_unused, u8 trace_chan_id __maybe_unused)