ETE shares the same packet format as ETMv4, but exception decoding handled ETMv4 packets only. As a result, ETE exception packets were not classified.

Recognize the ETE magic for exception number decoding.

Reviewed-by: James Clark james.clark@linaro.org Signed-off-by: Leo Yan leo.yan@arm.com --- tools/perf/util/cs-etm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index c2b0f98ceee7671d0e98cfe5673c6f4ec19707a5..b4d598ccabbd2551affdc8feed5c63bac4fee98d 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2176,7 +2176,7 @@ static bool cs_etm__is_syscall(struct cs_etm_queue *etmq, * HVC cases; need to check if it's SVC instruction based on * packet address. */ - if (magic == __perf_cs_etmv4_magic) { + if (magic == __perf_cs_etmv4_magic || magic == __perf_cs_ete_magic) { if (packet->exception_number == CS_ETMV4_EXC_CALL && cs_etm__is_svc_instr(etmq, tidq, prev_packet, prev_packet->end_addr)) @@ -2199,7 +2199,7 @@ static bool cs_etm__is_async_exception(struct cs_etm_traceid_queue *tidq, packet->exception_number == CS_ETMV3_EXC_FIQ) return true;

- if (magic == __perf_cs_etmv4_magic) + if (magic == __perf_cs_etmv4_magic || magic == __perf_cs_ete_magic) if (packet->exception_number == CS_ETMV4_EXC_RESET || packet->exception_number == CS_ETMV4_EXC_DEBUG_HALT || packet->exception_number == CS_ETMV4_EXC_SYSTEM_ERROR || @@ -2229,7 +2229,7 @@ static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq, packet->exception_number == CS_ETMV3_EXC_GENERIC) return true;

- if (magic == __perf_cs_etmv4_magic) { + if (magic == __perf_cs_etmv4_magic || magic == __perf_cs_ete_magic) { if (packet->exception_number == CS_ETMV4_EXC_TRAP || packet->exception_number == CS_ETMV4_EXC_ALIGNMENT || packet->exception_number == CS_ETMV4_EXC_INST_FAULT ||

CS ETM maintains its own circular array for last branch entries, with local helpers to update, copy and reset the branch stack. This duplicates logic already provided by the common code.

Record taken branches with thread_stack__event() and synthesize PERF_SAMPLE_BRANCH_STACK data with thread_stack__br_sample(). This removes the private last_branch_rb buffer and its position tracking.

This also makes the branch history state belong to the thread rather than the trace queue. That is a better fit for CoreSight traces where a trace queue can effectively be CPU scoped, while call/return history is per thread.

Keep the buffer number updated via thread_stack__set_trace_nr(), which is used when exporting samples to Python scripts. Pass callstack=false for now; synthesized callchains are added by a later patch.

The output should remain same, except that be->flags.predicted is no longer set. Since CoreSight trace does not provide branch prediction information, clearing the flag avoids confusion.

Reviewed-by: James Clark james.clark@linaro.org Signed-off-by: Leo Yan leo.yan@arm.com --- tools/perf/util/cs-etm.c | 159 ++++++++++++++--------------------------------- 1 file changed, 46 insertions(+), 113 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 4127120459418389ca7aabb9a49dead2b50e7533..8798bf0471faf3b1813780b45c588263ff6b4416 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -84,10 +84,9 @@ struct cs_etm_auxtrace { struct cs_etm_traceid_queue { u8 trace_chan_id; u64 period_instructions; - size_t last_branch_pos; union perf_event *event_buf; + unsigned int br_stack_sz; 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; @@ -644,9 +643,8 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq, 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->br_stack_sz = etm->synth_opts.last_branch_sz; }

tidq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE); @@ -656,7 +654,6 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq, return 0;

out_free: - zfree(&tidq->last_branch_rb); zfree(&tidq->last_branch); zfree(&tidq->prev_packet); zfree(&tidq->packet); @@ -939,7 +936,6 @@ static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq) thread__zput(tidq->decode_thread); zfree(&tidq->event_buf); zfree(&tidq->last_branch); - zfree(&tidq->last_branch_rb); zfree(&tidq->prev_packet); zfree(&tidq->packet); zfree(&tidq); @@ -1299,57 +1295,6 @@ static int cs_etm__queue_first_cs_timestamp(struct cs_etm_auxtrace *etm, return ret; }

-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 = tidq->last_branch_rb; - struct branch_stack *bs_dst = tidq->last_branch; - size_t nr = 0; - - /* - * Set the number of records before early exit: ->nr is used to - * determine how many branches to copy from ->entries. - */ - bs_dst->nr = bs_src->nr; - - /* - * Early exit when there is nothing to copy. - */ - if (!bs_src->nr) - return; - - /* - * As bs_src->entries is a circular buffer, we need to copy from it in - * 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 - tidq->last_branch_pos; - memcpy(&bs_dst->entries[0], - &bs_src->entries[tidq->last_branch_pos], - sizeof(struct branch_entry) * nr); - - /* - * If we wrapped around at least once, the branches from the beginning - * of the bs_src->entries buffer and until the ->last_branch_pos element - * are older valid branches: copy them over. The total number of - * branches copied over will be equal to the number of branches asked by - * the user in last_branch_sz. - */ - if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) { - memcpy(&bs_dst->entries[nr], - &bs_src->entries[0], - sizeof(struct branch_entry) * tidq->last_branch_pos); - } -} - -static inline -void cs_etm__reset_last_branch_rb(struct cs_etm_traceid_queue *tidq) -{ - tidq->last_branch_pos = 0; - tidq->last_branch_rb->nr = 0; -} - static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq, struct cs_etm_packet *packet, u64 addr) @@ -1419,38 +1364,6 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq, return addr; }

-static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq, - struct cs_etm_traceid_queue *tidq) -{ - struct branch_stack *bs = tidq->last_branch_rb; - struct branch_entry *be; - - /* - * The branches are recorded in a circular buffer in reverse - * chronological order: we start recording from the last element of the - * buffer down. After writing the first element of the stack, move the - * insert position back to the end of the buffer. - */ - if (!tidq->last_branch_pos) - tidq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz; - - tidq->last_branch_pos -= 1; - - 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; - - /* - * Increment bs->nr until reaching the number of last branches asked by - * the user on the command line. - */ - if (bs->nr < etmq->etm->synth_opts.last_branch_sz) - bs->nr += 1; -} - static int cs_etm__inject_event(struct cs_etm_auxtrace *etm, union perf_event *event, struct perf_sample *sample, u64 type) { @@ -1614,6 +1527,42 @@ static inline u64 cs_etm__resolve_sample_time(struct cs_etm_queue *etmq, return etm->latest_kernel_timestamp; }

+static bool cs_etm__packet_has_taken_branch(struct cs_etm_packet *packet) +{ + if (packet->sample_type == CS_ETM_RANGE && + packet->last_instr_taken_branch) + return true; + + return false; +} + +static void cs_etm__add_stack_event(struct cs_etm_queue *etmq, + struct cs_etm_traceid_queue *tidq) +{ + u64 from, to; + int size; + + if (!cs_etm__packet_has_taken_branch(tidq->prev_packet)) + return; + + if (etmq->etm->synth_opts.last_branch) { + from = cs_etm__last_executed_instr(tidq->prev_packet); + to = cs_etm__first_executed_instr(tidq->packet); + + size = cs_etm__instr_size(etmq, tidq, tidq->prev_packet, from); + + /* Enable callchain so thread stack entry can be allocated */ + thread_stack__event(tidq->frontend_thread, tidq->prev_packet->cpu, + tidq->prev_packet->flags, from, to, size, + etmq->buffer->buffer_nr + 1, false, + tidq->br_stack_sz, 0); + } else { + thread_stack__set_trace_nr(tidq->frontend_thread, + tidq->prev_packet->cpu, + etmq->buffer->buffer_nr + 1); + } +} + static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq, struct cs_etm_packet *packet, @@ -1644,8 +1593,11 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,

cs_etm__copy_insn(etmq, tidq, packet, &sample);

- if (etm->synth_opts.last_branch) + if (etm->synth_opts.last_branch) { + thread_stack__br_sample(tidq->frontend_thread, tidq->packet->cpu, + tidq->last_branch, tidq->br_stack_sz); sample.branch_stack = tidq->last_branch; + }

if (etm->synth_opts.inject) { ret = cs_etm__inject_event(etm, event, &sample, @@ -1836,14 +1788,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,

tidq->period_instructions += tidq->packet->instr_count;

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

if (etm->synth_opts.instructions && tidq->period_instructions >= etm->instructions_sample_period) { @@ -1902,10 +1847,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, u64 offset = etm->instructions_sample_period - instrs_prev; u64 addr;

- /* Prepare last branches for instruction sample */ - if (etm->synth_opts.last_branch) - cs_etm__copy_last_branch_rb(etmq, tidq); - while (tidq->period_instructions >= etm->instructions_sample_period) { /* @@ -1936,8 +1877,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, generate_sample = true;

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

if (generate_sample) { @@ -1985,10 +1925,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq, etmq->etm->synth_opts.instructions && tidq->prev_packet->sample_type == CS_ETM_RANGE) { u64 addr; - - /* Prepare last branches for instruction sample */ - cs_etm__copy_last_branch_rb(etmq, tidq); - /* * Generate a last branch event for the branches left in the * circular buffer at the end of the trace. @@ -2020,7 +1956,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,

/* Reset last branches after flush the trace */ if (etm->synth_opts.last_branch) - cs_etm__reset_last_branch_rb(tidq); + thread_stack__flush(tidq->frontend_thread);

return err; } @@ -2044,9 +1980,6 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq, tidq->prev_packet->sample_type == CS_ETM_RANGE) { u64 addr;

- /* Prepare last branches for instruction sample */ - cs_etm__copy_last_branch_rb(etmq, tidq); - /* * Use the address of the end of the last reported execution * range.

From: Leo Yan leo.yan@linaro.org

The perf script callindent is derived from call stack in thread context, CS ETM ignores the requirement for callindent without pushing and poping call stack.

Enable thread-stack when either itrace thread-stack support or last branch entries are requested, allocate the branch stack storage accordingly, and feed taken branches to thread_stack__event() whenever thread-stack state is needed.

When callindent is requested, pass callstack=true to thread_stack__event() so the common thread-stack code maintains call depth for branch samples.

Before:

perf script -F +callindent

callchain_test 6543 [002] 1 branches: main ffff93252258 __libc_start_call_main+0x78 (/usr/lib/aarch64-linux-gnu/libc.so.6) callchain_test 6543 [002] 1 branches: foo aaaad6b607c4 main+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test) callchain_test 6543 [002] 1 branches: print aaaad6b607ac foo+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test) callchain_test 6543 [002] 1 branches: do_svc aaaad6b60794 print+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test) callchain_test 6543 [002] 1 branches: vectors aaaad6b60780 do_svc+0x18 (/home/kernel/leoy/test_cs_callchain/callchain_test) callchain_test 6543 [002] 1 branches: el0t_64_sync_handler ffff80008001159c el0t_64_sync+0x194 ([kernel.kallsyms]) callchain_test 6543 [002] 1 branches: el0_svc ffff800081829194 el0t_64_sync_handler+0x9c ([kernel.kallsyms]) callchain_test 6543 [002] 1 branches: lockdep_hardirqs_off ffff800081828794 el0_svc+0x24 ([kernel.kallsyms]) callchain_test 6543 [002] 1 branches: __this_cpu_preempt_check ffff80008182b348 lockdep_hardirqs_off+0xf0 ([kernel.kallsyms])

After:

callchain_test 6543 [002] 1 branches: main ffff93252258 __libc_start_call_main+0x78 (/usr/lib/aarch64-linux-gnu/libc.so.6) callchain_test 6543 [002] 1 branches: foo aaaad6b607c4 main+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test) callchain_test 6543 [002] 1 branches: print aaaad6b607ac foo+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test) callchain_test 6543 [002] 1 branches: do_svc aaaad6b60794 print+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test) callchain_test 6543 [002] 1 branches: vectors aaaad6b60780 do_svc+0x18 (/home/kernel/leoy/test_cs_callchain/callchain_test) callchain_test 6543 [002] 1 branches: el0t_64_sync_handler ffff80008001159c el0t_64_sync+0x194 ([kernel.kallsyms]) callchain_test 6543 [002] 1 branches: el0_svc ffff800081829194 el0t_64_sync_handler+0x9c ([kernel.kallsyms]) callchain_test 6543 [002] 1 branches: lockdep_hardirqs_off ffff800081828794 el0_svc+0x24 ([kernel.kallsyms]) callchain_test 6543 [002] 1 branches: __this_cpu_preempt_check ffff80008182b348 lockdep_hardirqs_off+0xf0 ([kernel.kallsyms])

Signed-off-by: Leo Yan leo.yan@linaro.org Reviewed-by: James Clark james.clark@linaro.org Signed-off-by: Leo Yan leo.yan@arm.com --- tools/perf/util/cs-etm.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 7069b4990e6107fdece3cc5451142714f1d627ef..830618763d8b1bdcc015c492d7b2354d862566ca 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -66,6 +66,8 @@ struct cs_etm_auxtrace { bool snapshot_mode; bool data_queued; bool has_virtual_ts; /* Virtual/Kernel timestamps in the trace. */ + bool use_thread_stack; + bool use_callchain;

int num_cpu; u64 latest_kernel_timestamp; @@ -635,7 +637,7 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq, if (!tidq->prev_packet) goto out_free;

- if (etm->synth_opts.last_branch) { + if (etm->use_thread_stack) { size_t sz = sizeof(struct branch_stack);

sz += etm->synth_opts.last_branch_sz * @@ -1545,7 +1547,7 @@ static void cs_etm__add_stack_event(struct cs_etm_queue *etmq, if (!cs_etm__packet_has_taken_branch(tidq->prev_packet)) return;

- if (etmq->etm->synth_opts.last_branch) { + if (etmq->etm->use_thread_stack) { from = cs_etm__last_executed_instr(tidq->prev_packet); to = cs_etm__first_executed_instr(tidq->packet);

@@ -1554,7 +1556,8 @@ static void cs_etm__add_stack_event(struct cs_etm_queue *etmq, /* Enable callchain so thread stack entry can be allocated */ thread_stack__event(tidq->frontend_thread, tidq->prev_packet->cpu, tidq->prev_packet->flags, from, to, size, - etmq->buffer->buffer_nr + 1, false, + etmq->buffer->buffer_nr + 1, + etmq->etm->use_callchain, tidq->br_stack_sz, 0); } else { thread_stack__set_trace_nr(tidq->frontend_thread, @@ -1955,7 +1958,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq, cs_etm__packet_swap(etm, tidq);

/* Reset last branches after flush the trace */ - if (etm->synth_opts.last_branch) + if (etm->use_thread_stack) thread_stack__flush(tidq->frontend_thread);

return err; @@ -2018,7 +2021,7 @@ static void cs_etm__flush_all_stack(struct cs_etm_queue *etmq) { enum cs_etm_pid_fmt pid_fmt = cs_etm__get_pid_fmt(etmq);

- if (!etmq->etm->synth_opts.last_branch) + if (!etmq->etm->use_thread_stack) return;

cs_etm__flush_machine_stack(etmq, HOST_KERNEL_ID); @@ -3491,6 +3494,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, 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; }

if (etm->synth_opts.calls) @@ -3552,6 +3556,12 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, etm->tc.cap_user_time_zero = tc->cap_user_time_zero; etm->tc.cap_user_time_short = tc->cap_user_time_short; } + + etm->use_thread_stack = etm->synth_opts.thread_stack || + etm->synth_opts.last_branch; + + etm->use_callchain = etm->synth_opts.thread_stack; + err = cs_etm__synth_events(etm, session); if (err) goto err_free_queues;

Add a CoreSight shell test for synthesized callchains.

The test uses the new callchain workload to generate trace and decodes it with synthesis callchain. It then verifies that the instruction samples show the expected callchain push and pop.

Use control FIFOs so tracing starts only around the workload, which keeps the trace data small. The test is limited to with the cs_etm event available and root permission.

After:

perf test 138 -vvv 138: CoreSight synthesized callchain: ---- start ---- test child forked, pid 35581 Callchain flow matched: l1=4642868 l2=4642880 l3=4642895 l4=4642919 l5=4670494 l6=4670500 l7=4670520 ---- end(0) ---- 138: CoreSight synthesized callchain : Ok

Assisted-by: Codex:GPT-5.5 Signed-off-by: Leo Yan leo.yan@arm.com --- tools/perf/Documentation/perf-test.txt | 6 +- tools/perf/tests/builtin-test.c | 1 + tools/perf/tests/shell/coresight/callchain.sh | 172 ++++++++++++++++++++++++++ tools/perf/tests/tests.h | 1 + tools/perf/tests/workloads/Build | 2 + tools/perf/tests/workloads/callchain.c | 33 +++++ 6 files changed, 213 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt index 81c8525f594680d814f80e6f88bcce8d867bb350..859df74e62efc4b1e80da13ae8e053356f68ae54 100644 --- a/tools/perf/Documentation/perf-test.txt +++ b/tools/perf/Documentation/perf-test.txt @@ -57,7 +57,8 @@ OPTIONS --workload=:: Run a built-in workload, to list them use '--list-workloads', current ones include: noploop, thloop, leafloop, sqrtloop, brstack, datasym, - context_switch_loop, deterministic, named_threads and landlock. + context_switch_loop, deterministic, named_threads, landlock and + callchain.

Used with the shell script regression tests.

@@ -69,7 +70,8 @@ OPTIONS 'named_threads' accepts the number of threads and the number of loops to do in each thread.

- The datasym, landlock and deterministic workloads don't accept any. + The datasym, landlock, deterministic and callchain workloads don't accept + any.

--list-workloads:: List the available workloads to use with -w/--workload. diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index afc06cec49546d29d86b94840c7021c5bf5c88e3..8994488cc206863ba77f7e7e5803e62f18e151ba 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -166,6 +166,7 @@ static struct test_workload *workloads[] = { &workload__jitdump, &workload__context_switch_loop, &workload__deterministic, + &workload__callchain,

#ifdef HAVE_RUST_SUPPORT &workload__code_with_type, diff --git a/tools/perf/tests/shell/coresight/callchain.sh b/tools/perf/tests/shell/coresight/callchain.sh new file mode 100755 index 0000000000000000000000000000000000000000..13cca7dc11184002e3ddc058c0d0ffa1c458c483 --- /dev/null +++ b/tools/perf/tests/shell/coresight/callchain.sh @@ -0,0 +1,172 @@ +#!/bin/bash +# CoreSight synthesized callchain (exclusive) +# SPDX-License-Identifier: GPL-2.0 + +glb_err=1 + +if ! tmpdir=$(mktemp -d /tmp/perf-cs-callchain-test.XXXXXX); then + echo "mktemp failed" + exit 1 +fi + +cleanup_files() +{ + rm -rf "$tmpdir" +} + +trap cleanup_files EXIT +trap 'cleanup_files; exit $glb_err' TERM INT + +skip_if_system_is_not_ready() +{ + perf list | grep -Pzq 'cs_etm//' || { + echo "[Skip] cs_etm event is not available" >&2 + return 2 + } + + # Requires root for trace in kernel + [ "$(id -u)" = 0 ] || { + echo "[Skip] No root permission" >&2 + return 2 + } + + return 0 +} + +record_trace() +{ + local data=$1 + local script=$2 + + local cf="$tmpdir/ctl" + local af="$tmpdir/ack" + + mkfifo "$cf" "$af" + + perf record -o "$data" -e cs_etm// --per-thread -D -1 --control fifo:"$cf","$af" -- \ + perf test --record-ctl fifo:"$cf","$af" -w callchain >/dev/null 2>&1 && + + # It is safe to use 'i3i' with a three-instruction interval, since the + # workload is compiled with -O0. + perf script --itrace=g16i3il64 -i "$data" > "$script" +} + +callchain_regex_1() +{ + printf '%s' \ +'perf[[:space:]]+[0-9]+[[:space:]]+[[0-9]+][[:space:]]+([0-9.]+:[[:space:]]+)?[0-9]+ instructions:[[:space:]]*\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain_foo+0x[[:xdigit:]]+ (.*/perf)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain+0x[[:xdigit:]]+ (.*/perf)\n'\ +'([[:space:]]+[[:xdigit:]]+ .*\n)*' +} + +callchain_regex_2() +{ + printf '%s' \ +'perf[[:space:]]+[0-9]+[[:space:]]+[[0-9]+][[:space:]]+([0-9.]+:[[:space:]]+)?[0-9]+ instructions:[[:space:]]*\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain_do_syscall+0x[[:xdigit:]]+ (.*/perf)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain_foo+0x[[:xdigit:]]+ (.*/perf)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain+0x[[:xdigit:]]+ (.*/perf)\n'\ +'([[:space:]]+[[:xdigit:]]+ .*\n)*' +} + +callchain_regex_3() +{ + printf '%s' \ +'perf[[:space:]]+[0-9]+[[:space:]]+[[0-9]+][[:space:]]+([0-9.]+:[[:space:]]+)?[0-9]+ instructions:[[:space:]]*\n'\ +'[[:space:]]+[[:xdigit:]]+ syscall(@plt)?+0x[[:xdigit:]]+ (.*)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain_do_syscall+0x[[:xdigit:]]+ (.*/perf)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain_foo+0x[[:xdigit:]]+ (.*/perf)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain+0x[[:xdigit:]]+ (.*/perf)\n'\ +'([[:space:]]+[[:xdigit:]]+ .*\n)*' +} + +callchain_regex_4() +{ + printf '%s' \ +'perf[[:space:]]+[0-9]+[[:space:]]+[[0-9]+][[:space:]]+([0-9.]+:[[:space:]]+)?[0-9]+ instructions:[[:space:]]*\n'\ +'[[:space:]]+[[:xdigit:]]+ .*+0x[[:xdigit:]]+ ([kernel.kallsyms])\n'\ +'[[:space:]]+[[:xdigit:]]+ syscall(@plt)?+0x[[:xdigit:]]+ (.*)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain_do_syscall+0x[[:xdigit:]]+ (.*/perf)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain_foo+0x[[:xdigit:]]+ (.*/perf)\n'\ +'[[:space:]]+[[:xdigit:]]+ callchain+0x[[:xdigit:]]+ (.*/perf)\n'\ +'([[:space:]]+[[:xdigit:]]+ .*\n)*' +} + +find_after_line() +{ + local regex="$1" + local file="$2" + local start="$3" + local offset + local line + + # Search in byte offset + offset=$( + tail -n +"$start" "$file" | + grep -Pzob -m1 "$regex" | + tr '\0' '\n' | + sed -n 's/^([0-9][0-9]*):.*/\1/p;q' + ) + + if [ -z "$offset" ]; then + echo "Failed to match regex after line $start" >&2 + echo "Regex:" >&2 + printf '%s\n' "$regex" >&2 + echo "Context from line $start:" >&2 + sed -n "${start},$((start + 100))p" "$file" >&2 + return 1 + fi + + # Convert from offset to line + line=$( + tail -n +"$start" "$file" | + head -c "$offset" | + wc -l + ) + + echo "$((start + line))" +} + +check_callchain_flow() +{ + local file="$1" + local l1 l2 l3 l4 l5 l6 l7 + + # Callchain push + l1=$(find_after_line "$(callchain_regex_1)" "$file" 1) || return 1 + l2=$(find_after_line "$(callchain_regex_2)" "$file" "$((l1 + 1))") || return 1 + l3=$(find_after_line "$(callchain_regex_3)" "$file" "$((l2 + 1))") || return 1 + l4=$(find_after_line "$(callchain_regex_4)" "$file" "$((l3 + 1))") || return 1 + + # Callchain pop + l5=$(find_after_line "$(callchain_regex_3)" "$file" "$((l4 + 1))") || return 1 + l6=$(find_after_line "$(callchain_regex_2)" "$file" "$((l5 + 1))") || return 1 + l7=$(find_after_line "$(callchain_regex_1)" "$file" "$((l6 + 1))") || return 1 + + echo "Callchain flow matched:" + echo " l1=$l1 l2=$l2 l3=$l3 l4=$l4 l5=$l5 l6=$l6 l7=$l7" + + return 0 +} + +run_test() +{ + local data=$tmpdir/perf.data + local script=$tmpdir/perf.script + + if ! record_trace "$data" "$script"; then + echo "perf record/script failed" + return + fi + + check_callchain_flow "$script" || return + + glb_err=0 +} + +skip_if_system_is_not_ready || exit 2 + +run_test + +exit $glb_err diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 7cedf05be544ad79a99e86d30dfa4f7b01ca0837..cee9e6b62dcc838c864bbe76efe3b638ed75b134 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -248,6 +248,7 @@ DECLARE_WORKLOAD(inlineloop); DECLARE_WORKLOAD(jitdump); DECLARE_WORKLOAD(context_switch_loop); DECLARE_WORKLOAD(deterministic); +DECLARE_WORKLOAD(callchain);

#ifdef HAVE_RUST_SUPPORT DECLARE_WORKLOAD(code_with_type); diff --git a/tools/perf/tests/workloads/Build b/tools/perf/tests/workloads/Build index 75b377934a0e62b9ac1fec245520ea0978ac957e..dfdf9a2720b22f67a3d7b53d0ed14e0654059c8f 100644 --- a/tools/perf/tests/workloads/Build +++ b/tools/perf/tests/workloads/Build @@ -13,6 +13,7 @@ perf-test-y += inlineloop.o perf-test-y += jitdump.o perf-test-y += context_switch_loop.o perf-test-y += deterministic.o +perf-test-y += callchain.o

ifeq ($(CONFIG_RUST_SUPPORT),y) perf-test-y += code_with_type.o @@ -26,3 +27,4 @@ CFLAGS_datasym.o = -g -O0 -fno-inline -U_FORTIFY_SOURCE CFLAGS_traploop.o = -g -O0 -fno-inline -U_FORTIFY_SOURCE CFLAGS_inlineloop.o = -g -O2 CFLAGS_deterministic.o = -g -O0 -fno-inline -U_FORTIFY_SOURCE +CFLAGS_callchain.o = -g -O0 -fno-inline -U_FORTIFY_SOURCE diff --git a/tools/perf/tests/workloads/callchain.c b/tools/perf/tests/workloads/callchain.c new file mode 100644 index 0000000000000000000000000000000000000000..3951423d8115e9efb49af8ba2586001fc6f02761 --- /dev/null +++ b/tools/perf/tests/workloads/callchain.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/syscall.h> +#include <unistd.h> +#include "../tests.h" + +/* + * Mark as noinline to establish the call chain, and avoid the static + * annotation to prevent LTO from renaming the functions. + */ +noinline void callchain_do_syscall(void); +noinline void callchain_foo(void); +noinline int callchain(int argc, const char **argv); + +noinline void callchain_do_syscall(void) +{ + syscall(SYS_getpid); +} + +noinline void callchain_foo(void) +{ + callchain_do_syscall(); +} + +noinline int callchain(int argc __maybe_unused, + const char **argv __maybe_unused) +{ + callchain_foo(); + + return 0; +} + +DEFINE_WORKLOAD(callchain);