Now CoreSight has supported the thread stack; based on the thread stack we can synthesize call chain for the instruction sample; the call chain can be injected by option '--itrace=g'.
Note the stack event must be processed prior to synthesizing instruction sample; this can ensure the thread stack to push and pop synchronously with instruction sample and the thread stack can be generated correctly for instruction samples. Add a comment for related info.
Before:
# perf script --itrace=g16l64i100 main 1579 100 instructions: ffff0000102137f0 group_sched_in+0xb0 ([kernel.kallsyms]) main 1579 100 instructions: ffff000010213b78 flexible_sched_in+0xf0 ([kernel.kallsyms]) main 1579 100 instructions: ffff0000102135ac event_sched_in.isra.57+0x74 ([kernel.kallsyms]) main 1579 100 instructions: ffff000010219344 perf_swevent_add+0x6c ([kernel.kallsyms]) main 1579 100 instructions: ffff000010214854 perf_event_update_userpage+0x4c ([kernel.kallsyms]) [...]
After:
# perf script --itrace=g16l64i100
main 1579 100 instructions: ffff000010213b78 flexible_sched_in+0xf0 ([kernel.kallsyms]) ffff00001020c0b4 visit_groups_merge+0x12c ([kernel.kallsyms])
main 1579 100 instructions: ffff0000102135ac event_sched_in.isra.57+0x74 ([kernel.kallsyms]) ffff0000102137a0 group_sched_in+0x60 ([kernel.kallsyms]) ffff000010213b84 flexible_sched_in+0xfc ([kernel.kallsyms]) ffff00001020c0b4 visit_groups_merge+0x12c ([kernel.kallsyms])
main 1579 100 instructions: ffff000010219344 perf_swevent_add+0x6c ([kernel.kallsyms]) ffff0000102135f4 event_sched_in.isra.57+0xbc ([kernel.kallsyms]) ffff0000102137a0 group_sched_in+0x60 ([kernel.kallsyms]) ffff000010213b84 flexible_sched_in+0xfc ([kernel.kallsyms]) ffff00001020c0b4 visit_groups_merge+0x12c ([kernel.kallsyms]) [...]
Signed-off-by: Leo Yan leo.yan@linaro.org --- tools/perf/util/cs-etm.c | 40 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 1b08b650b090..d9c22c145307 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -17,6 +17,7 @@ #include <stdlib.h>
#include "auxtrace.h" +#include "callchain.h" #include "color.h" #include "cs-etm.h" #include "cs-etm-decoder/cs-etm-decoder.h" @@ -74,6 +75,7 @@ struct cs_etm_traceid_queue { size_t last_branch_pos; union perf_event *event_buf; struct thread *thread; + struct ip_callchain *chain; struct branch_stack *last_branch; struct branch_stack *last_branch_rb; struct cs_etm_packet *prev_packet; @@ -251,6 +253,16 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq, if (!tidq->prev_packet) goto out_free;
+ if (etm->synth_opts.callchain) { + size_t sz = sizeof(struct ip_callchain); + + /* Add 1 to callchain_sz for callchain context */ + sz += (etm->synth_opts.callchain_sz + 1) * sizeof(u64); + tidq->chain = zalloc(sz); + if (!tidq->chain) + goto out_free; + } + if (etm->synth_opts.last_branch) { size_t sz = sizeof(struct branch_stack);
@@ -273,6 +285,7 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq, out_free: zfree(&tidq->last_branch_rb); zfree(&tidq->last_branch); + zfree(&tidq->chain); zfree(&tidq->prev_packet); zfree(&tidq->packet); out: @@ -561,6 +574,7 @@ static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq) zfree(&tidq->event_buf); zfree(&tidq->last_branch); zfree(&tidq->last_branch_rb); + zfree(&tidq->chain); zfree(&tidq->prev_packet); zfree(&tidq->packet); zfree(&tidq); @@ -1147,7 +1161,7 @@ static void cs_etm__add_stack_event(struct cs_etm_queue *etmq, int insn_len; u64 from_ip, to_ip;
- if (etm->synth_opts.thread_stack) { + if (etm->synth_opts.callchain || etm->synth_opts.thread_stack) { from_ip = cs_etm__last_executed_instr(tidq->prev_packet); to_ip = cs_etm__first_executed_instr(tidq->packet);
@@ -1203,6 +1217,14 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
+ if (etm->synth_opts.callchain) { + thread_stack__sample(tidq->thread, tidq->packet->cpu, + tidq->chain, + etm->synth_opts.callchain_sz + 1, + sample.ip, etm->kernel_start); + sample.callchain = tidq->chain; + } + if (etm->synth_opts.last_branch) sample.branch_stack = tidq->last_branch;
@@ -1385,6 +1407,8 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR; }
+ if (etm->synth_opts.callchain) + attr.sample_type |= PERF_SAMPLE_CALLCHAIN; if (etm->synth_opts.last_branch) attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
@@ -1426,6 +1450,11 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, tidq->prev_packet->last_instr_taken_branch) cs_etm__update_last_branch_rb(etmq, tidq);
+ /* + * The stack event must be processed prior to synthesizing + * instruction sample; this can ensure the instruction samples + * to generate correct thread stack. + */ if (tidq->prev_packet->last_instr_taken_branch) cs_etm__add_stack_event(etmq, tidq);
@@ -2776,7 +2805,6 @@ int cs_etm__process_auxtrace_info(union perf_event *event, } else { itrace_synth_opts__set_default(&etm->synth_opts, session->itrace_synth_opts->default_no_sample); - etm->synth_opts.callchain = false; etm->synth_opts.thread_stack = session->itrace_synth_opts->thread_stack; } @@ -2788,6 +2816,14 @@ int cs_etm__process_auxtrace_info(union perf_event *event, etm->branches_filter |= PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_BEGIN;
+ if (etm->synth_opts.callchain && !symbol_conf.use_callchain) { + symbol_conf.use_callchain = true; + if (callchain_register_param(&callchain_param) < 0) { + symbol_conf.use_callchain = false; + etm->synth_opts.callchain = false; + } + } + err = cs_etm__synth_events(etm, session); if (err) goto err_delete_thread;