perf/core: fix restoring of Intel LBR call stack on a context switch
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v5 Latest posting 2/24 patches 3 repliesIn review
- v5 posting 1/24 patches 0 repliesApplied
- v44 patches 3 repliesSuperseded
Earlier versions · 4
| Version | Posted | Patches | Replies | Status |
|---|---|---|---|---|
| v3 posting 2/2 | 4 patches | 5 replies | Superseded | |
| v3 posting 1/2 | 4 patches | 0 replies | Superseded | |
| v2 | 4 patches | 3 replies | Superseded | |
| v1 | 1 patch | 2 replies | Superseded |
Changes in v5 from the cover letter
- renamed sync_task_ctx to swap_task_ctx;
- converted type of prev and next swap_task_ctx() params to struct perf_event_context;
- implemented check on availability of swap_task_ctx() pointer in pmu type at perf core implementation;
- moved swap of ctx->task_ctx_data pointers to architecture specific intel_pmu_lbr_swap_task_ctx() implementation;
Patches in v5 posting 2/2 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/4 | perf/core,x86: introduce swap_task_ctx() method at struct pmuarch/ include/ | +17 | 0 replies | |
| 2/4 | perf/x86: install platform specific swap_task_ctx adapterarch/ | +8 | 0 replies | |
| 3/4 | perf/x86/intel: implement LBR callstacks context synchronizationarch/ arch/ | +26 | 0 replies | |
| 4/4 | perf/core,x86: synchronize PMU task contexts on optimized context switchesarch/ kernel/ | +19 | 0 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v5 yet.
Cover letter [PATCH v5 0/4] perf/core: fix restoring of Intel LBR call stack on a context switch
Restore Intel LBR call stack from cloned inactive task perf context on a context switch. This change inherently addresses inconsistency in LBR call stack data provided on a sample in record profiling mode:
$ perf record -N -B -T -R --call-graph lbr \
-e cpu/period=0xcdfe60,event=0x3c,name=\'CPU_CLK_UNHALTED.THREAD\'/Duk \
--clockid=monotonic_raw -- ./miniFE.x nx 25 ny 25 nz 25Let's assume threads A, B, C belonging to the same process.
B and C are siblings of A and their perf contexts are treated as equivalent. At some point B blocks on a futex (non preempt context switch). B's LBRs are preserved at B's perf context task_ctx_data and B's events are removed from PMU and disabled. B's perf context becomes inactive.
Later C gets on a cpu, runs, gets profiled and eventually switches to the awaken but not yet running B. The optimized context switch path is executed swapping B's and C's task_ctx_data pointers at perf event contexts. So C's task_ctx_data will refer preserved B's LBRs on the following switch-in event.
However, as far B's perf context is inactive there is no enabled events in there and B's task_ctx_data->lbr_callstack_users is equal to 0. When B gets on the cpu B's events reviving is skipped following the optimized context switch path and B's task_ctx_data->lbr_callstack_users remains 0. Thus B's LBR's are not restored by pmu sched_task() code called in the end of perf context switch-in callback for B.
In the report that manifests as having short fragments of B's call stack, still tracked by LBR's HW between adjacent samples, but the whole thread call tree doesn't aggregate.
The fix has been evaluated when profiling miniFE [1] (C++, OpenMP) workload running 64 threads on Intel Skylake EP (64 core, 2 sockets):
$ perf report --call-graph callee,flat
5.3.0-rc6+ (tip perf/core) - fixed
- 92.66% 82.64% miniFE.x libiomp5.so [.] _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
- 69.14% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_fork_barrier
__kmp_launch_thread
_INTERNAL_24_______src_z_Linux_util_c_3e0095e6::__kmp_launch_worker
start_thread
__clone
- 21.89% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_barrier
__kmpc_reduce_nowait
miniFE::cg_solve<miniFE::CSRMatrix<double, int, int>, miniFE::Vector<double, int, int>, miniFE::matvec_std<miniFE::CSRMatrix<double, int, int>, miniFE::Vector<double, int, in
__kmp_invoke_microtask
__kmp_invoke_task_func
__kmp_launch_thread
_INTERNAL_24_______src_z_Linux_util_c_3e0095e6::__kmp_launch_worker
start_thread
__clone
- 1.63% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_barrier
__kmpc_reduce_nowait
main
__kmp_invoke_microtask
__kmp_invoke_task_func
__kmp_launch_thread
_INTERNAL_24_______src_z_Linux_util_c_3e0095e6::__kmp_launch_worker
start_thread
__clone5.0.13-300.fc30.x86_64 - no fix
- 90.29% 81.01% miniFE.x libiomp5.so [.] _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
- 33.45% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_fork_barrier
__kmp_launch_thread
_INTERNAL_24_______src_z_Linux_util_c_3e0095e6::__kmp_launch_worker
start_thread
__clone
87.63% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
- 54.79% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_fork_barrier
__kmp_launch_thread
- 9.18% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_barrier
__kmpc_reduce_nowait
miniFE::cg_solve<miniFE::CSRMatrix<double, int, int>, miniFE::Vector<double, int, int>, miniFE::matvec_std<miniFE::CSRMatrix<double, int, int>, miniFE::Vector<double, int, in
__kmp_invoke_microtask
__kmp_invoke_task_func
__kmp_launch_thread
_INTERNAL_24_______src_z_Linux_util_c_3e0095e6::__kmp_launch_worker
start_thread
__clone
- 41.28% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_fork_barrier
__kmp_launch_thread
_INTERNAL_24_______src_z_Linux_util_c_3e0095e6::__kmp_launch_worker
- 15.77% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_barrier
__kmpc_reduce_nowait
miniFE::cg_solve<miniFE::CSRMatrix<double, int, int>, miniFE::Vector<double, int, int>, miniFE::matvec_std<miniFE::CSRMatrix<double, int, int>, miniFE::Vector<double, int, in
__kmp_invoke_microtask
__kmp_invoke_task_func
__kmp_launch_thread
- 11.56% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_barrier
__kmpc_reduce_nowait
miniFE::cg_solve<miniFE::CSRMatrix<double, int, int>, miniFE::Vector<double, int, int>, miniFE::matvec_std<miniFE::CSRMatrix<double, int, int>, miniFE::Vector<double, int, in
__kmp_invoke_microtask
__kmp_invoke_task_func
__kmp_launch_thread
_INTERNAL_24_______src_z_Linux_util_c_3e0095e6::__kmp_launch_worker
- 2.33% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_release
__kmp_barrier
__kmpc_reduce_nowait
main
__kmp_invoke_microtask
__kmp_invoke_task_func
__kmp_launch_thread
_INTERNAL_24_______src_z_Linux_util_c_3e0095e6::__kmp_launch_worker
start_thread
__clone
0.67% _INTERNAL_25_______src_kmp_barrier_cpp_1d20fae8::__kmp_hyper_barrier_gather
0.57% __kmp_hardware_timestamp[1] https://www.hpcadvisorycouncil.com/pdf/miniFE_Analysis_and_Profiling.pdf
---
Alexey Budankov (4):
perf/core,x86: introduce swap_task_ctx() method at struct pmu perf/x86: install platform specific swap_task_ctx adapter perf/x86/intel: implement LBR callstacks context synchronization perf/core,x86: synchronize PMU task contexts on optimized context switches
arch/x86/events/core.c | 8 ++++++++ arch/x86/events/intel/core.c | 7 +++++++ arch/x86/events/intel/lbr.c | 23 +++++++++++++++++++++++ arch/x86/events/perf_event.h | 11 +++++++++++ include/linux/perf_event.h | 9 +++++++++ kernel/events/core.c | 13 ++++++++++++- 6 files changed, 70 insertions(+), 1 deletion(-)
---
Changes in v5:
- renamed sync_task_ctx to swap_task_ctx;
- converted type of prev and next swap_task_ctx() params to struct perf_event_context;
- implemented check on availability of swap_task_ctx() pointer in pmu type at perf core implementation;
- moved swap of ctx->task_ctx_data pointers to architecture specific intel_pmu_lbr_swap_task_ctx() implementation;
Changes in v4:
- moved check on simultaneous task_ctx_data objects availability to the perf/core layer;
- marked sync_task_ctx() as the optional in code comments;
- renamed params of sync_task_ctx() to prev and next;
Changes in v3:
- replaced assignment with swap at intel_pmu_lbr_sync_task_ctx()
Changes in v2:
- implemented sync_task_ctx() method at perf,x86,intel pmu types;
- employed the method on the optimized context switch path between equivalent perf event contexts;
Signature · 1 line
2.20.1