diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-03-10 15:22:03 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-03-10 15:22:03 -0700 |
commit | 12ad143e1b803e541e48b8ba40f550250259ecdd (patch) | |
tree | 5202b407df21e5abaeb294d1ecddcf0a2eca7f8b /tools/perf/util/thread-stack.c | |
parent | 262d6a9a63a387c8dfa9eb4f7713e159c941e52c (diff) | |
parent | b339da480315505aa28a723a983217ebcff95c86 (diff) |
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Thomas Gleixner:
"Perf updates and fixes:
Kernel:
- Handle events which have the bpf_event attribute set as side band
events as they carry information about BPF programs.
- Add missing switch-case fall-through comments
Libraries:
- Fix leaks and double frees in error code paths.
- Prevent buffer overflows in libtraceevent
Tools:
- Improvements in handling Intel BT/PTS
- Add BTF ELF markers to perf trace BPF programs to improve output
- Support --time, --cpu, --pid and --tid filters for perf diff
- Calculate the column width in perf annotate as the hardcoded 6
characters for the instruction are not sufficient
- Small fixes all over the place"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (38 commits)
perf/core: Mark expected switch fall-through
perf/x86/intel/uncore: Fix client IMC events return huge result
perf/ring_buffer: Use high order allocations for AUX buffers optimistically
perf data: Force perf_data__open|close zero data->file.path
perf session: Fix double free in perf_data__close
perf evsel: Probe for precise_ip with simple attr
perf tools: Read and store caps/max_precise in perf_pmu
perf hist: Fix memory leak of srcline
perf hist: Add error path into hist_entry__init
perf c2c: Fix c2c report for empty numa node
perf script python: Add Python3 support to intel-pt-events.py
perf script python: Add Python3 support to event_analyzing_sample.py
perf script python: add Python3 support to check-perf-trace.py
perf script python: Add Python3 support to futex-contention.py
perf script python: Remove mixed indentation
perf diff: Support --pid/--tid filter options
perf diff: Support --cpu filter option
perf diff: Support --time filter option
perf thread: Generalize function to copy from thread addr space from intel-bts code
perf annotate: Calculate the max instruction name, align column to that
...
Diffstat (limited to 'tools/perf/util/thread-stack.c')
-rw-r--r-- | tools/perf/util/thread-stack.c | 16 |
1 files changed, 14 insertions, 2 deletions
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index a8b45168513c..41942c2aaa18 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -49,6 +49,7 @@ enum retpoline_state_t { * @timestamp: timestamp (if known) * @ref: external reference (e.g. db_id of sample) * @branch_count: the branch count when the entry was created + * @db_id: id used for db-export * @cp: call path * @no_call: a 'call' was not seen * @trace_end: a 'call' but trace ended @@ -59,6 +60,7 @@ struct thread_stack_entry { u64 timestamp; u64 ref; u64 branch_count; + u64 db_id; struct call_path *cp; bool no_call; bool trace_end; @@ -280,12 +282,14 @@ static int thread_stack__call_return(struct thread *thread, .comm = ts->comm, .db_id = 0, }; + u64 *parent_db_id; tse = &ts->stack[idx]; cr.cp = tse->cp; cr.call_time = tse->timestamp; cr.return_time = timestamp; cr.branch_count = ts->branch_count - tse->branch_count; + cr.db_id = tse->db_id; cr.call_ref = tse->ref; cr.return_ref = ref; if (tse->no_call) @@ -295,7 +299,14 @@ static int thread_stack__call_return(struct thread *thread, if (tse->non_call) cr.flags |= CALL_RETURN_NON_CALL; - return crp->process(&cr, crp->data); + /* + * The parent db_id must be assigned before exporting the child. Note + * it is not possible to export the parent first because its information + * is not yet complete because its 'return' has not yet been processed. + */ + parent_db_id = idx ? &(tse - 1)->db_id : NULL; + + return crp->process(&cr, parent_db_id, crp->data); } static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts) @@ -484,7 +495,7 @@ void thread_stack__sample(struct thread *thread, int cpu, } struct call_return_processor * -call_return_processor__new(int (*process)(struct call_return *cr, void *data), +call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data), void *data) { struct call_return_processor *crp; @@ -537,6 +548,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr, tse->no_call = no_call; tse->trace_end = trace_end; tse->non_call = false; + tse->db_id = 0; return 0; } |