CoreSight June 2019

coresight@lists.linaro.org

15 participants
42 discussions

[PATCH 46/85] perf cs-etm: Get rid of unused cpu in struct cs_etm_queue

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> 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(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-11-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- 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 9e8212c74055..531bbb355ba4 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, -- 2.20.1

4 years, 10 months

[PATCH 45/85] perf cs-etm: Introduce the concept of trace ID queues

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> In an 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(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-10-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 4 +- tools/perf/util/cs-etm.c | 360 +++++++++++------- tools/perf/util/cs-etm.h | 15 +- 3 files changed, 234 insertions(+), 145 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 3ac238e58901..4303d2d00d31 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -413,8 +413,8 @@ 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 68fec6f019fe..9e8212c74055 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; + + 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 = malloc(sizeof(*tidq)); + if (!tidq) + return NULL; + + memset(tidq, 0, sizeof(*tidq)); + + 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); } @@ -443,37 +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; - - 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); @@ -508,12 +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; @@ -543,8 +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; @@ -577,10 +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; /* @@ -600,9 +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); /* @@ -615,14 +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, @@ -675,9 +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; /* @@ -686,14 +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; @@ -777,11 +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; @@ -794,14 +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) { @@ -819,7 +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; } @@ -828,19 +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); @@ -849,12 +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; /* @@ -997,33 +1061,34 @@ 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->sample_type == CS_ETM_RANGE && - etmq->prev_packet->last_instr_taken_branch) - cs_etm__update_last_branch_rb(etmq); + 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; /* @@ -1032,31 +1097,31 @@ 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) { 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; } @@ -1067,15 +1132,15 @@ 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 @@ -1088,24 +1153,25 @@ 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; /* 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. @@ -1113,21 +1179,21 @@ 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; } @@ -1138,15 +1204,16 @@ 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; @@ -1160,20 +1227,20 @@ 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; @@ -1272,10 +1339,11 @@ 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) @@ -1296,9 +1364,10 @@ 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 || @@ -1321,10 +1390,12 @@ 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 || @@ -1367,10 +1438,11 @@ 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; @@ -1472,7 +1544,7 @@ 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; @@ -1480,7 +1552,7 @@ 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 | @@ -1489,7 +1561,7 @@ 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; @@ -1571,17 +1643,18 @@ 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 @@ -1596,18 +1669,18 @@ 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: @@ -1616,14 +1689,14 @@ 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: /* @@ -1643,6 +1716,11 @@ 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) { @@ -1661,13 +1739,13 @@ 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 75385e2fd283..f16082d37ab5 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -136,6 +136,16 @@ struct cs_etm_packet { #define CS_ETM_PACKET_MAX_BUFFER 1024 +/* + * 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; @@ -172,7 +182,7 @@ 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, @@ -188,7 +198,8 @@ 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; } -- 2.20.1

4 years, 10 months

[PATCH 44/85] perf cs-etm: Fix indentation in function cs_etm__process_decoder_queue()

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> Fixing wrong indentation of the while() loop - no change of functionality. Signed-off-by: Mathieu Poirier <mathieu.poirier(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Fixes: 3fa0e83e2948 ("perf cs-etm: Modularize main packet processing loop") Link: http://lkml.kernel.org/r/20190524173508.29044-9-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/util/cs-etm.c | 108 +++++++++++++++++++-------------------- 1 file changed, 54 insertions(+), 54 deletions(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index a74c53a45839..68fec6f019fe 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1578,64 +1578,64 @@ static int cs_etm__process_decoder_queue(struct cs_etm_queue *etmq) packet_queue = cs_etm__etmq_get_packet_queue(etmq); - /* Process each packet in this chunk */ - while (1) { - ret = cs_etm_decoder__get_packet(packet_queue, - etmq->packet); - if (ret <= 0) - /* - * Stop processing this chunk on - * end of data or error - */ - break; + /* Process each packet in this chunk */ + while (1) { + ret = cs_etm_decoder__get_packet(packet_queue, + etmq->packet); + if (ret <= 0) + /* + * Stop processing this chunk on + * end of data or error + */ + break; + + /* + * Since packet addresses are swapped in packet + * handling within below switch() statements, + * thus setting sample flags must be called + * prior to switch() statement to use address + * information before packets swapping. + */ + ret = cs_etm__set_sample_flags(etmq); + if (ret < 0) + break; + switch (etmq->packet->sample_type) { + case CS_ETM_RANGE: /* - * Since packet addresses are swapped in packet - * handling within below switch() statements, - * thus setting sample flags must be called - * prior to switch() statement to use address - * information before packets swapping. + * If the packet contains an instruction + * range, generate instruction sequence + * events. */ - ret = cs_etm__set_sample_flags(etmq); - if (ret < 0) - break; - - switch (etmq->packet->sample_type) { - case CS_ETM_RANGE: - /* - * If the packet contains an instruction - * range, generate instruction sequence - * events. - */ - cs_etm__sample(etmq); - break; - case CS_ETM_EXCEPTION: - case CS_ETM_EXCEPTION_RET: - /* - * If the exception packet is coming, - * make sure the previous instruction - * range packet to be handled properly. - */ - cs_etm__exception(etmq); - break; - case CS_ETM_DISCONTINUITY: - /* - * Discontinuity in trace, flush - * previous branch stack - */ - cs_etm__flush(etmq); - break; - case CS_ETM_EMPTY: - /* - * Should not receive empty packet, - * report error. - */ - pr_err("CS ETM Trace: empty packet\n"); - return -EINVAL; - default: - break; - } + cs_etm__sample(etmq); + break; + case CS_ETM_EXCEPTION: + case CS_ETM_EXCEPTION_RET: + /* + * If the exception packet is coming, + * make sure the previous instruction + * range packet to be handled properly. + */ + cs_etm__exception(etmq); + break; + case CS_ETM_DISCONTINUITY: + /* + * Discontinuity in trace, flush + * previous branch stack + */ + cs_etm__flush(etmq); + break; + case CS_ETM_EMPTY: + /* + * Should not receive empty packet, + * report error. + */ + pr_err("CS ETM Trace: empty packet\n"); + return -EINVAL; + default: + break; } + } return ret; } -- 2.20.1

4 years, 10 months

[PATCH 43/85] perf cs-etm: Move packet queue out of decoder structure

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> The decoder needs to work with more than one traceID queue if we want to support CPU-wide scenarios with N:1 source/sink topologies. As such move the packet buffer and related fields out of the decoder structure and into the cs_etm_queue structure. Signed-off-by: Mathieu Poirier <mathieu.poirier(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-8-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 129 +++++++----------- .../perf/util/cs-etm-decoder/cs-etm-decoder.h | 36 +---- tools/perf/util/cs-etm.c | 37 ++++- tools/perf/util/cs-etm.h | 53 +++++++ 4 files changed, 144 insertions(+), 111 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 5dafec421b0d..3ac238e58901 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -18,8 +18,6 @@ #include "intlist.h" #include "util.h" -#define MAX_BUFFER 1024 - /* use raw logging */ #ifdef CS_DEBUG_RAW #define CS_LOG_RAW_FRAMES @@ -31,18 +29,12 @@ #endif #endif -#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL - struct cs_etm_decoder { void *data; void (*packet_printer)(const char *msg); dcd_tree_handle_t dcd_tree; cs_etm_mem_cb_type mem_access; ocsd_datapath_resp_t prev_return; - u32 packet_count; - u32 head; - u32 tail; - struct cs_etm_packet packet_buffer[MAX_BUFFER]; }; static u32 @@ -88,14 +80,14 @@ int cs_etm_decoder__reset(struct cs_etm_decoder *decoder) return 0; } -int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder, +int cs_etm_decoder__get_packet(struct cs_etm_packet_queue *packet_queue, struct cs_etm_packet *packet) { - if (!decoder || !packet) + if (!packet_queue || !packet) return -EINVAL; /* Nothing to do, might as well just return */ - if (decoder->packet_count == 0) + if (packet_queue->packet_count == 0) return 0; /* * The queueing process in function cs_etm_decoder__buffer_packet() @@ -106,11 +98,12 @@ int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder, * value. Otherwise the first element of the packet queue is not * used. */ - decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1); + packet_queue->head = (packet_queue->head + 1) & + (CS_ETM_PACKET_MAX_BUFFER - 1); - *packet = decoder->packet_buffer[decoder->head]; + *packet = packet_queue->packet_buffer[packet_queue->head]; - decoder->packet_count--; + packet_queue->packet_count--; return 1; } @@ -276,84 +269,60 @@ cs_etm_decoder__create_etm_packet_printer(struct cs_etm_trace_params *t_params, trace_config); } -static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder) -{ - int i; - - decoder->head = 0; - decoder->tail = 0; - decoder->packet_count = 0; - for (i = 0; i < MAX_BUFFER; i++) { - decoder->packet_buffer[i].isa = CS_ETM_ISA_UNKNOWN; - decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR; - decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR; - decoder->packet_buffer[i].instr_count = 0; - decoder->packet_buffer[i].last_instr_taken_branch = false; - decoder->packet_buffer[i].last_instr_size = 0; - decoder->packet_buffer[i].last_instr_type = 0; - decoder->packet_buffer[i].last_instr_subtype = 0; - decoder->packet_buffer[i].last_instr_cond = 0; - decoder->packet_buffer[i].flags = 0; - decoder->packet_buffer[i].exception_number = UINT32_MAX; - decoder->packet_buffer[i].trace_chan_id = UINT8_MAX; - decoder->packet_buffer[i].cpu = INT_MIN; - } -} - static ocsd_datapath_resp_t -cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, +cs_etm_decoder__buffer_packet(struct cs_etm_packet_queue *packet_queue, const u8 trace_chan_id, enum cs_etm_sample_type sample_type) { u32 et = 0; int cpu; - if (decoder->packet_count >= MAX_BUFFER - 1) + if (packet_queue->packet_count >= CS_ETM_PACKET_MAX_BUFFER - 1) return OCSD_RESP_FATAL_SYS_ERR; if (cs_etm__get_cpu(trace_chan_id, &cpu) < 0) return OCSD_RESP_FATAL_SYS_ERR; - et = decoder->tail; - et = (et + 1) & (MAX_BUFFER - 1); - decoder->tail = et; - decoder->packet_count++; - - decoder->packet_buffer[et].sample_type = sample_type; - decoder->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN; - decoder->packet_buffer[et].cpu = cpu; - decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR; - decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR; - decoder->packet_buffer[et].instr_count = 0; - decoder->packet_buffer[et].last_instr_taken_branch = false; - decoder->packet_buffer[et].last_instr_size = 0; - decoder->packet_buffer[et].last_instr_type = 0; - decoder->packet_buffer[et].last_instr_subtype = 0; - decoder->packet_buffer[et].last_instr_cond = 0; - decoder->packet_buffer[et].flags = 0; - decoder->packet_buffer[et].exception_number = UINT32_MAX; - decoder->packet_buffer[et].trace_chan_id = trace_chan_id; - - if (decoder->packet_count == MAX_BUFFER - 1) + et = packet_queue->tail; + et = (et + 1) & (CS_ETM_PACKET_MAX_BUFFER - 1); + packet_queue->tail = et; + packet_queue->packet_count++; + + packet_queue->packet_buffer[et].sample_type = sample_type; + packet_queue->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN; + packet_queue->packet_buffer[et].cpu = cpu; + packet_queue->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR; + packet_queue->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR; + packet_queue->packet_buffer[et].instr_count = 0; + packet_queue->packet_buffer[et].last_instr_taken_branch = false; + packet_queue->packet_buffer[et].last_instr_size = 0; + packet_queue->packet_buffer[et].last_instr_type = 0; + packet_queue->packet_buffer[et].last_instr_subtype = 0; + packet_queue->packet_buffer[et].last_instr_cond = 0; + packet_queue->packet_buffer[et].flags = 0; + packet_queue->packet_buffer[et].exception_number = UINT32_MAX; + packet_queue->packet_buffer[et].trace_chan_id = trace_chan_id; + + if (packet_queue->packet_count == CS_ETM_PACKET_MAX_BUFFER - 1) return OCSD_RESP_WAIT; return OCSD_RESP_CONT; } static ocsd_datapath_resp_t -cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, +cs_etm_decoder__buffer_range(struct cs_etm_packet_queue *packet_queue, const ocsd_generic_trace_elem *elem, const uint8_t trace_chan_id) { int ret = 0; struct cs_etm_packet *packet; - ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id, + ret = cs_etm_decoder__buffer_packet(packet_queue, trace_chan_id, CS_ETM_RANGE); if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT) return ret; - packet = &decoder->packet_buffer[decoder->tail]; + packet = &packet_queue->packet_buffer[packet_queue->tail]; switch (elem->isa) { case ocsd_isa_aarch64: @@ -400,36 +369,36 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, } static ocsd_datapath_resp_t -cs_etm_decoder__buffer_discontinuity(struct cs_etm_decoder *decoder, - const uint8_t trace_chan_id) +cs_etm_decoder__buffer_discontinuity(struct cs_etm_packet_queue *queue, + const uint8_t trace_chan_id) { - return cs_etm_decoder__buffer_packet(decoder, trace_chan_id, + return cs_etm_decoder__buffer_packet(queue, trace_chan_id, CS_ETM_DISCONTINUITY); } static ocsd_datapath_resp_t -cs_etm_decoder__buffer_exception(struct cs_etm_decoder *decoder, +cs_etm_decoder__buffer_exception(struct cs_etm_packet_queue *queue, const ocsd_generic_trace_elem *elem, const uint8_t trace_chan_id) { int ret = 0; struct cs_etm_packet *packet; - ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id, + ret = cs_etm_decoder__buffer_packet(queue, trace_chan_id, CS_ETM_EXCEPTION); if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT) return ret; - packet = &decoder->packet_buffer[decoder->tail]; + packet = &queue->packet_buffer[queue->tail]; packet->exception_number = elem->exception_number; return ret; } static ocsd_datapath_resp_t -cs_etm_decoder__buffer_exception_ret(struct cs_etm_decoder *decoder, +cs_etm_decoder__buffer_exception_ret(struct cs_etm_packet_queue *queue, const uint8_t trace_chan_id) { - return cs_etm_decoder__buffer_packet(decoder, trace_chan_id, + return cs_etm_decoder__buffer_packet(queue, trace_chan_id, CS_ETM_EXCEPTION_RET); } @@ -441,6 +410,13 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( { ocsd_datapath_resp_t resp = OCSD_RESP_CONT; struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context; + 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); + if (!packet_queue) + return OCSD_RESP_FATAL_SYS_ERR; switch (elem->elem_type) { case OCSD_GEN_TRC_ELEM_UNKNOWN: @@ -448,19 +424,19 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( case OCSD_GEN_TRC_ELEM_EO_TRACE: case OCSD_GEN_TRC_ELEM_NO_SYNC: case OCSD_GEN_TRC_ELEM_TRACE_ON: - resp = cs_etm_decoder__buffer_discontinuity(decoder, + resp = cs_etm_decoder__buffer_discontinuity(packet_queue, trace_chan_id); break; case OCSD_GEN_TRC_ELEM_INSTR_RANGE: - resp = cs_etm_decoder__buffer_range(decoder, elem, + resp = cs_etm_decoder__buffer_range(packet_queue, elem, trace_chan_id); break; case OCSD_GEN_TRC_ELEM_EXCEPTION: - resp = cs_etm_decoder__buffer_exception(decoder, elem, + resp = cs_etm_decoder__buffer_exception(packet_queue, elem, trace_chan_id); break; case OCSD_GEN_TRC_ELEM_EXCEPTION_RET: - resp = cs_etm_decoder__buffer_exception_ret(decoder, + resp = cs_etm_decoder__buffer_exception_ret(packet_queue, trace_chan_id); break; case OCSD_GEN_TRC_ELEM_PE_CONTEXT: @@ -554,7 +530,6 @@ cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params, decoder->data = d_params->data; decoder->prev_return = OCSD_RESP_CONT; - cs_etm_decoder__clear_buffer(decoder); format = (d_params->formatted ? OCSD_TRC_SRC_FRAME_FORMATTED : OCSD_TRC_SRC_SINGLE); flags = 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 3ab11dfa92ae..6ae7ab4cf5fe 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -14,38 +14,8 @@ #include <stdio.h> struct cs_etm_decoder; - -enum cs_etm_sample_type { - CS_ETM_EMPTY, - CS_ETM_RANGE, - CS_ETM_DISCONTINUITY, - CS_ETM_EXCEPTION, - CS_ETM_EXCEPTION_RET, -}; - -enum cs_etm_isa { - CS_ETM_ISA_UNKNOWN, - CS_ETM_ISA_A64, - CS_ETM_ISA_A32, - CS_ETM_ISA_T32, -}; - -struct cs_etm_packet { - enum cs_etm_sample_type sample_type; - enum cs_etm_isa isa; - u64 start_addr; - u64 end_addr; - u32 instr_count; - u32 last_instr_type; - u32 last_instr_subtype; - u32 flags; - u32 exception_number; - u8 last_instr_cond; - u8 last_instr_taken_branch; - u8 last_instr_size; - u8 trace_chan_id; - int cpu; -}; +struct cs_etm_packet; +struct cs_etm_packet_queue; struct cs_etm_queue; @@ -119,7 +89,7 @@ int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder, u64 start, u64 end, cs_etm_mem_cb_type cb_func); -int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder, +int cs_etm_decoder__get_packet(struct cs_etm_packet_queue *packet_queue, struct cs_etm_packet *packet); int cs_etm_decoder__reset(struct cs_etm_decoder *decoder); diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 5322dcaaf654..a74c53a45839 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -78,6 +78,7 @@ struct cs_etm_queue { struct cs_etm_packet *packet; const unsigned char *buf; size_t buf_len, buf_used; + struct cs_etm_packet_queue packet_queue; }; static int cs_etm__update_queues(struct cs_etm_auxtrace *etm); @@ -125,6 +126,36 @@ int cs_etm__get_cpu(u8 trace_chan_id, int *cpu) return 0; } +static void cs_etm__clear_packet_queue(struct cs_etm_packet_queue *queue) +{ + int i; + + queue->head = 0; + queue->tail = 0; + queue->packet_count = 0; + for (i = 0; i < CS_ETM_PACKET_MAX_BUFFER; i++) { + queue->packet_buffer[i].isa = CS_ETM_ISA_UNKNOWN; + queue->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR; + queue->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR; + queue->packet_buffer[i].instr_count = 0; + queue->packet_buffer[i].last_instr_taken_branch = false; + queue->packet_buffer[i].last_instr_size = 0; + queue->packet_buffer[i].last_instr_type = 0; + queue->packet_buffer[i].last_instr_subtype = 0; + queue->packet_buffer[i].last_instr_cond = 0; + queue->packet_buffer[i].flags = 0; + queue->packet_buffer[i].exception_number = UINT32_MAX; + queue->packet_buffer[i].trace_chan_id = UINT8_MAX; + queue->packet_buffer[i].cpu = INT_MIN; + } +} + +struct cs_etm_packet_queue +*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq) +{ + return &etmq->packet_queue; +} + static void cs_etm__packet_dump(const char *pkt_string) { const char *color = PERF_COLOR_BLUE; @@ -513,6 +544,7 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, etmq->pid = -1; etmq->offset = 0; etmq->period_instructions = 0; + cs_etm__clear_packet_queue(&etmq->packet_queue); out: return ret; @@ -1542,10 +1574,13 @@ static int cs_etm__decode_data_block(struct cs_etm_queue *etmq) static int cs_etm__process_decoder_queue(struct cs_etm_queue *etmq) { int ret; + struct cs_etm_packet_queue *packet_queue; + + packet_queue = cs_etm__etmq_get_packet_queue(etmq); /* Process each packet in this chunk */ while (1) { - ret = cs_etm_decoder__get_packet(etmq->decoder, + ret = cs_etm_decoder__get_packet(packet_queue, etmq->packet); if (ret <= 0) /* diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 826c9eedaf5c..75385e2fd283 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -97,12 +97,57 @@ enum { CS_ETMV4_EXC_END = 31, }; +enum cs_etm_sample_type { + CS_ETM_EMPTY, + CS_ETM_RANGE, + CS_ETM_DISCONTINUITY, + CS_ETM_EXCEPTION, + CS_ETM_EXCEPTION_RET, +}; + +enum cs_etm_isa { + CS_ETM_ISA_UNKNOWN, + CS_ETM_ISA_A64, + CS_ETM_ISA_A32, + CS_ETM_ISA_T32, +}; + /* RB tree for quick conversion between traceID and metadata pointers */ struct intlist *traceid_list; +struct cs_etm_queue; + +struct cs_etm_packet { + enum cs_etm_sample_type sample_type; + enum cs_etm_isa isa; + u64 start_addr; + u64 end_addr; + u32 instr_count; + u32 last_instr_type; + u32 last_instr_subtype; + u32 flags; + u32 exception_number; + u8 last_instr_cond; + u8 last_instr_taken_branch; + u8 last_instr_size; + u8 trace_chan_id; + int cpu; +}; + +#define CS_ETM_PACKET_MAX_BUFFER 1024 + +struct cs_etm_packet_queue { + u32 packet_count; + u32 head; + u32 tail; + struct cs_etm_packet packet_buffer[CS_ETM_PACKET_MAX_BUFFER]; +}; + #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) +#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL + /* * Create a contiguous bitmask starting at bit position @l and ending at * position @h. For example @@ -126,6 +171,8 @@ struct intlist *traceid_list; 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); #else static inline int cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused, @@ -139,6 +186,12 @@ static inline int cs_etm__get_cpu(u8 trace_chan_id __maybe_unused, { return -1; } + +static inline struct cs_etm_packet_queue *cs_etm__etmq_get_packet_queue( + struct cs_etm_queue *etmq __maybe_unused) +{ + return NULL; +} #endif #endif -- 2.20.1

4 years, 10 months

[PATCH 42/85] perf cs-etm: Refactor error path in cs_etm_decoder__new()

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> 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(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-7-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- 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 39fe21e1cf93..5dafec421b0d 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -577,7 +577,7 @@ 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); @@ -587,15 +587,13 @@ 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; } -- 2.20.1

4 years, 10 months

[PATCH 41/85] perf cs-etm: Add handling of switch-CPU-wide events

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> Add handling of SWITCH-CPU-WIDE events in order to add the tid/pid of the incoming 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(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-6-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/util/cs-etm.c | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 0742c50fce46..5322dcaaf654 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1680,6 +1680,42 @@ static int cs_etm__process_itrace_start(struct cs_etm_auxtrace *etm, return 0; } +static int cs_etm__process_switch_cpu_wide(struct cs_etm_auxtrace *etm, + union perf_event *event) +{ + struct thread *th; + bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT; + + /* + * Context switch in per-thread mode are irrelevant since perf + * will start/stop tracing as the process is scheduled. + */ + if (etm->timeless_decoding) + return 0; + + /* + * SWITCH_IN events carry the next process to be switched out while + * SWITCH_OUT events carry the process to be switched in. As such + * we don't care about IN events. + */ + if (!out) + 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->context_switch.next_prev_pid, + event->context_switch.next_prev_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, @@ -1719,6 +1755,8 @@ static int cs_etm__process_event(struct perf_session *session, if (event->header.type == PERF_RECORD_ITRACE_START) return cs_etm__process_itrace_start(etm, event); + else if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) + return cs_etm__process_switch_cpu_wide(etm, event); return 0; } -- 2.20.1

4 years, 10 months

[PATCH 40/85] perf cs-etm: Add handling of itrace start events

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> 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(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-5-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- 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 de488b43f440..0742c50fce46 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1657,6 +1657,29 @@ 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, @@ -1694,6 +1717,9 @@ 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; } -- 2.20.1

4 years, 10 months

[PATCH 39/85] perf cs-etm: Configure SWITCH_EVENTS in CPU-wide mode

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> Ask the perf core to generate an event when processes are swapped in/out of context. That way proper action can be taken by the decoding code when faced with such event. Signed-off-by: Mathieu Poirier <mathieu.poirier(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-4-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/arch/arm/util/cs-etm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index be1e4f20affa..cc7f1cd23b14 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -257,6 +257,9 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, ptr->evlist = evlist; ptr->snapshot_mode = opts->auxtrace_snapshot_mode; + if (perf_can_record_switch_events()) + opts->record_switch_events = true; + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type == cs_etm_pmu->type) { if (cs_etm_evsel) { -- 2.20.1

4 years, 10 months

[PATCH 38/85] perf cs-etm: Configure timestamp generation in CPU-wide mode

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> 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(a)linaro.org> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-3-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- 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 3912f0bf04ed..be1e4f20affa 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: goto out; } @@ -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 */ -- 2.20.1

4 years, 10 months

[PATCH 37/85] perf cs-etm: Configure contextID tracing in CPU-wide mode

by Arnaldo Carvalho de Melo

From: Mathieu Poirier <mathieu.poirier(a)linaro.org> When operating in CPU-wide mode being notified of contextID changes is required so that the decoding mechanic is aware of the process context switch. Signed-off-by: Mathieu Poirier <mathieu.poirier(a)linaro.org> Reviewed-by: Suzuki Poulouse <suzuki.poulose(a)arm.com> Tested-by: Leo Yan <leo.yan(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Link: http://lkml.kernel.org/r/20190524173508.29044-2-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> --- tools/perf/arch/arm/util/cs-etm.c | 126 +++++++++++++++++++++++++----- tools/perf/util/cs-etm.h | 12 +++ 2 files changed, 119 insertions(+), 19 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 911426721170..3912f0bf04ed 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -35,8 +35,100 @@ struct cs_etm_recording { size_t snapshot_size; }; +static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = { + [CS_ETM_ETMCCER] = "mgmt/etmccer", + [CS_ETM_ETMIDR] = "mgmt/etmidr", +}; + +static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = { + [CS_ETMV4_TRCIDR0] = "trcidr/trcidr0", + [CS_ETMV4_TRCIDR1] = "trcidr/trcidr1", + [CS_ETMV4_TRCIDR2] = "trcidr/trcidr2", + [CS_ETMV4_TRCIDR8] = "trcidr/trcidr8", + [CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus", +}; + static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu); +static int cs_etm_set_context_id(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 TRCIRD2 */ + snprintf(path, PATH_MAX, "cpu%d/%s", + cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2]); + 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; + } + + /* + * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID tracing + * is supported: + * 0b00000 Context ID tracing is not supported. + * 0b00100 Maximum of 32-bit Context ID size. + * All other values are reserved. + */ + val = BMVAL(val, 5, 9); + if (!val || val != 0x4) { + err = -EINVAL; + goto out; + } + + /* All good, let the kernel know */ + evsel->attr.config |= (1 << ETM_OPT_CTXTID); + err = 0; + +out: + + return err; +} + +static int cs_etm_set_option(struct auxtrace_record *itr, + struct perf_evsel *evsel, u32 option) +{ + int i, err = -EINVAL; + struct cpu_map *event_cpus = evsel->evlist->cpus; + struct cpu_map *online_cpus = cpu_map__new(NULL); + + /* Set option of each CPU we have */ + for (i = 0; i < cpu__max_cpu(); i++) { + if (!cpu_map__has(event_cpus, i) || + !cpu_map__has(online_cpus, i)) + continue; + + switch (option) { + case ETM_OPT_CTXTID: + err = cs_etm_set_context_id(itr, evsel, i); + if (err) + goto out; + break; + default: + goto out; + } + } + + err = 0; +out: + cpu_map__put(online_cpus); + return err; +} + static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, struct record_opts *opts, const char *str) @@ -105,8 +197,9 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; struct perf_evsel *evsel, *cs_etm_evsel = NULL; - const struct cpu_map *cpus = evlist->cpus; + struct cpu_map *cpus = evlist->cpus; bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0); + int err = 0; ptr->evlist = evlist; ptr->snapshot_mode = opts->auxtrace_snapshot_mode; @@ -241,19 +334,24 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, /* * In the case of per-cpu mmaps, we need the CPU on the - * AUX event. + * AUX event. We also need the contextID in order to be notified + * when a context switch happened. */ - if (!cpu_map__empty(cpus)) + if (!cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(cs_etm_evsel, CPU); + err = cs_etm_set_option(itr, cs_etm_evsel, ETM_OPT_CTXTID); + if (err) + goto out; + } + /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { struct perf_evsel *tracking_evsel; - int err; err = parse_events(evlist, "dummy:u", NULL); if (err) - return err; + goto out; tracking_evsel = perf_evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); @@ -266,7 +364,8 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, perf_evsel__set_sample_bit(tracking_evsel, TIME); } - return 0; +out: + return err; } static u64 cs_etm_get_config(struct auxtrace_record *itr) @@ -314,6 +413,8 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr) config_opts = cs_etm_get_config(itr); if (config_opts & BIT(ETM_OPT_CYCACC)) config |= BIT(ETM4_CFG_BIT_CYCACC); + if (config_opts & BIT(ETM_OPT_CTXTID)) + config |= BIT(ETM4_CFG_BIT_CTXTID); if (config_opts & BIT(ETM_OPT_TS)) config |= BIT(ETM4_CFG_BIT_TS); if (config_opts & BIT(ETM_OPT_RETSTK)) @@ -363,19 +464,6 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, (etmv3 * CS_ETMV3_PRIV_SIZE)); } -static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = { - [CS_ETM_ETMCCER] = "mgmt/etmccer", - [CS_ETM_ETMIDR] = "mgmt/etmidr", -}; - -static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = { - [CS_ETMV4_TRCIDR0] = "trcidr/trcidr0", - [CS_ETMV4_TRCIDR1] = "trcidr/trcidr1", - [CS_ETMV4_TRCIDR2] = "trcidr/trcidr2", - [CS_ETMV4_TRCIDR8] = "trcidr/trcidr8", - [CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus", -}; - static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu) { bool ret = false; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 0e97c196147a..826c9eedaf5c 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -103,6 +103,18 @@ struct intlist *traceid_list; #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + * + * Carbon copy of implementation found in $KERNEL/include/linux/bitops.h + */ +#define GENMASK(h, l) \ + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define BMVAL(val, lsb, msb) ((val & GENMASK(msb, lsb)) >> lsb) + #define CS_ETM_HEADER_SIZE (CS_HEADER_VERSION_0_MAX * sizeof(u64)) #define __perf_cs_etmv3_magic 0x3030303030303030ULL -- 2.20.1

4 years, 10 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

CoreSight June 2019