- Feb 17, 2023
-
-
Kajol Jain authored
Testcase stat_all_metrics.sh fails in powerpc: 98: perf all metrics test : FAILED! Logs with verbose: [command]# ./perf test 98 -vv 98: perf all metrics test : --- start --- test child forked, pid 13262 Testing BRU_STALL_CPI Testing COMPLETION_STALL_CPI ---- Testing TOTAL_LOCAL_NODE_PUMPS_P23 Metric 'TOTAL_LOCAL_NODE_PUMPS_P23' not printed in: Error: Invalid event (hv_24x7/PM_PB_LNS_PUMP23,chip=3/) in per-thread mode, enable system wide with '-a'. Testing TOTAL_LOCAL_NODE_PUMPS_RETRIES_P01 Metric 'TOTAL_LOCAL_NODE_PUMPS_RETRIES_P01' not printed in: Error: Invalid event (hv_24x7/PM_PB_RTY_LNS_PUMP01,chip=3/) in per-thread mode, enable system wide with '-a'. ---- Based on above logs, we could see some of the hv-24x7 metric events fails, and logs suggest to run the metric event with -a option. This change happened after the commit a4b8cfca ("perf stat: Delay metric parsing"), which delayed the metric parsing phase and now before metric parsing phase perf tool identifies, whether target is system-wide or not. With this change, perf_event_open will fails with workload monitoring for uncore events as expected. The perf all metric test case fails as some of the hv-24x7 metric events may need bigger workload with system wide monitoring to get the data. Fix this issue by changing current system wide check from true workload to sleep 0.01 workload. Result with the patch changes in powerpc: 98: perf all metrics test : Ok Fixes: a4b8cfca ("perf stat: Delay metric parsing") Suggested-by:
Ian Rogers <irogers@google.com> Reviewed-by:
Athira Rajeev <atrajeev@linux.vnet.ibm.com> Signed-off-by:
Kajol Jain <kjain@linux.ibm.com> Tested-by:
Disha Goel <disgoel@linux.ibm.com> Tested-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Athira Rajeev authored
Power10 Performance Monitoring Unit (PMU) provides events to understand stall cycles of different pipeline stages. These events along with completed instructions provides useful metrics for application tuning. Patch implements the JSON changes to collect counter statistics to present the high level CPI stall breakdown metrics. New metric group is named as "CPI_STALL_RATIO" and this new metric group presents these stall metrics: - DISPATCHED_CPI ( Dispatch stall cycles per insn ) - ISSUE_STALL_CPI ( Issue stall cycles per insn ) - EXECUTION_STALL_CPI ( Execution stall cycles per insn ) - COMPLETION_STALL_CPI ( Completition stall cycles per insn ) To avoid multipling of events, PM_RUN_INST_CMPL event has been modified to use PMC5(performance monitoring counter5) instead of PMC4. This change is needed, since completion stall event is using PMC4. Usage example: ./perf stat --metric-no-group -M CPI_STALL_RATIO <workload> Performance counter stats for 'workload': 63,056,817,982 PM_CMPL_STALL # 0.28 COMPLETION_STALL_CPI 1,743,988,038,896 PM_ISSUE_STALL # 7.73 ISSUE_STALL_CPI 225,597,495,030 PM_RUN_INST_CMPL # 6.18 DISPATCHED_CPI # 37.48 EXECUTION_STALL_CPI 1,393,916,546,654 PM_DISP_STALL_CYC 8,455,376,836,463 PM_EXEC_STALL "--metric-no-group" is used for forcing PM_RUN_INST_CMPL to be scheduled in all group for more accuracy. Signed-off-by: -
Steinar H. Gunderson authored
There is no good reason why we cannot synthesize "cycle" events from Intel PT just as we can synthesize "instruction" events, in particular when CYC packets are available. This enables using PT to getting much more accurate cycle profiles than regular sampling (record -e cycles) when the work last for very short periods (<10 ms). Thus, add support for this, based off of the existing IPC calculation framework. The new option to --itrace is "y" (for cYcles), as c was taken for calls. Cycle and instruction events can be synthesized together, and are by default. The only real caveat is that CYC packets are only emitted whenever some other packet is, which in practice is when a branch instruction is encountered (and not even all branches). Thus, even at no subsampling (e.g. --itrace=y0ns), it is impossible to get more accuracy than a single basic block, and all cycles spent executing that block will get attributed to the branch instruction that ends the packet. Thus, one cannot know whether the cycles came from e.g. a specific load, a mispredicted branch, or something else. When subsampling (which is the default), the cycle events will get smeared out even more, but will still be generally useful to attribute cycle counts to functions. Reviewed-by:
Adrian Hunter <adrian.hunter@intel.com> Signed-off-by:
Steinar H. Gunderson <sesse@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20220322082452.1429091-1-sesse@google.com Signed-off-by:
-
- Feb 16, 2023
-
-
Feng Tang authored
Many platforms have feature of adjacent cachelines prefetch, when it is enabled, for data in RAM of 2 cachelines (2N and 2N+1) granularity, if one is fetched to cache, the other one could likely be fetched too, which sort of extends the cacheline size to double, thus the false sharing could happens in adjacent cachelines. 0Day has captured performance changed related with this [1], and some commercial software explicitly makes its hot global variables 128 bytes aligned (2 cache lines) to avoid this kind of extended false sharing. So add an option "--double-cl" for 'perf c2c report' to show false sharing in double cache line granularity, which acts just like the cacheline size is doubled. There is no change to c2c record. The hardware events of shared cacheline are still per cacheline, and this option just changes the granularity of how events are grouped and displayed. In the 'perf c2c report' output below (will-it-scale's 'pagefault2' case on old kernel): ---------------------------------------------------------------------- 26 31 2 0 0 0 0xffff888103ec6000 ---------------------------------------------------------------------- 35.48% 50.00% 0.00% 0.00% 0.00% 0x10 0 1 0xffffffff8133148b 1153 66 971 3748 74 [k] get_mem_cgroup_from_mm 6.45% 0.00% 0.00% 0.00% 0.00% 0x10 0 1 0xffffffff813396e4 570 0 1531 879 75 [k] mem_cgroup_charge 25.81% 50.00% 0.00% 0.00% 0.00% 0x54 0 1 0xffffffff81331472 949 70 593 3359 74 [k] get_mem_cgroup_from_mm 19.35% 0.00% 0.00% 0.00% 0.00% 0x54 0 1 0xffffffff81339686 1352 0 1073 1022 74 [k] mem_cgroup_charge 9.68% 0.00% 0.00% 0.00% 0.00% 0x54 0 1 0xffffffff813396d6 1401 0 863 768 74 [k] mem_cgroup_charge 3.23% 0.00% 0.00% 0.00% 0.00% 0x54 0 1 0xffffffff81333106 618 0 804 11 9 [k] uncharge_batch The offset 0x10 and 0x54 used to displayed in 2 groups, and now they are listed together to give users a hint of extended false sharing. [1]. https://lore.kernel.org/lkml/20201102091543.GM31092@shao2-debian/ Committer notes: Link: https://lore.kernel.org/r/Y+wvVNWqXb70l4uy@feng-clx Removed -a, leaving just as --double-cl, as this probably is not used so frequently and perhaps will be even auto-detected if we manage to record the MSR where this is configured. Reviewed-by:Andi Kleen <ak@linux.intel.com> Reviewed-by:
Leo Yan <leo.yan@linaro.org> Signed-off-by:
Feng Tang <feng.tang@intel.com> Tested-by:
Joe Mario <jmario@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@intel.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20230214075823.246414-1-feng.tang@intel.com Signed-off-by:
-
- Feb 15, 2023
-
-
Yang Jihong authored
When --overwrite and --max-size options of perf record are used together, a segmentation fault occurs. The following is an example: # perf record -e sched:sched* --overwrite --max-size 1K -a -- sleep 1 [ perf record: Woken up 1 times to write data ] perf: Segmentation fault Obtained 12 stack frames. ./perf/perf(+0x197673) [0x55f99710b673] /lib/x86_64-linux-gnu/libc.so.6(+0x3ef0f) [0x7fa45f3cff0f] ./perf/perf(+0x8eb40) [0x55f997002b40] ./perf/perf(+0x1f6882) [0x55f99716a882] ./perf/perf(+0x794c2) [0x55f996fed4c2] ./perf/perf(+0x7b7c7) [0x55f996fef7c7] ./perf/perf(+0x9074b) [0x55f99700474b] ./perf/perf(+0x12e23c) [0x55f9970a223c] ./perf/perf(+0x12e54a) [0x55f9970a254a] ./perf/perf(+0x7db60) [0x55f996ff1b60] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xe6) [0x7fa45f3b2c86] ./perf/perf(+0x7dfe9) [0x55f996ff1fe9] Segmentation fault (core dumped) backtrace of the core file is as follows: (gdb) bt #0 record__bytes_written (rec=0x55f99755a200 <record>) at builtin-record.c:234 #1 record__output_max_size_exceeded (rec=0x55f99755a200 <record>) at builtin-record.c:242 #2 record__write (map=0x0, size=12816, bf=0x55f9978da2e0, rec=0x55f99755a200 <record>) at builtin-record.c:263 #3 process_synthesized_event (tool=tool@entry=0x55f99755a200 <record>, event=event@entry=0x55f9978da2e0, sample=sample@entry=0x0, machine=machine@entry=0x55f997893658) at builtin-record.c:618 #4 0x000055f99716a883 in __perf_event__synthesize_id_index (tool=tool@entry=0x55f99755a200 <record>, process=process@entry=0x55f997002aa0 <process_synthesized_event>, evlist=0x55f9978928b0, machine=machine@entry=0x55f997893658, from=from@entry=0) at util/synthetic-events.c:1895 #5 0x000055f99716a91f in perf_event__synthesize_id_index (tool=tool@entry=0x55f99755a200 <record>, process=process@entry=0x55f997002aa0 <process_synthesized_event>, evlist=<optimized out>, machine=machine@entry=0x55f997893658) at util/synthetic-events.c:1905 #6 0x000055f996fed4c3 in record__synthesize (tail=tail@entry=true, rec=0x55f99755a200 <record>) at builtin-record.c:1997 #7 0x000055f996fef7c8 in __cmd_record (argc=argc@entry=2, argv=argv@entry=0x7ffc67551260, rec=0x55f99755a200 <record>) at builtin-record.c:2802 #8 0x000055f99700474c in cmd_record (argc=<optimized out>, argv=0x7ffc67551260) at builtin-record.c:4258 #9 0x000055f9970a223d in run_builtin (p=0x55f997564d88 <commands+264>, argc=10, argv=0x7ffc67551260) at perf.c:330 #10 0x000055f9970a254b in handle_internal_command (argc=10, argv=0x7ffc67551260) at perf.c:384 #11 0x000055f996ff1b61 in run_argv (argcp=<synthetic pointer>, argv=<synthetic pointer>) at perf.c:428 #12 main (argc=<optimized out>, argv=0x7ffc67551260) at perf.c:562 The reason is that record__bytes_written accesses the freed memory rec->thread_data, The process is as follows: __cmd_record -> record__free_thread_data -> zfree(&rec->thread_data) // free rec->thread_data -> record__synthesize -> perf_event__synthesize_id_index -> process_synthesized_event -> record__write -> record__bytes_written // access rec->thread_data We add a member variable "thread_bytes_written" in the struct "record" to save the data size written by the threads. Fixes: 6d575816 ("perf record: Add support for limit perf output file size") Signed-off-by:Yang Jihong <yangjihong1@huawei.com> Acked-by:
Namhyung Kim <namhyung@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiwei Sun <jiwei.sun@windriver.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/CAM9d7ci_TRrqBQVQNW8=GwakUr7SsZpYxaaty-S4bxF8zJWyqw@mail.gmail.com Signed-off-by:
-
- Feb 09, 2023
-
-
Ian Rogers authored
The added perf_stat_merge_counters combines uncore counters. When metrics are enabled, the counts are merged into a metric_leader via the stat-shadow saved_value logic. As the leader now is passed an aggregated count, it leads to all counters being added together twice and counts appearing approximately doubled in metrics. This change disables the saved_value merging of counts for evsels that are merged. It is recommended that later changes remove the saved_value entirely as the two layers of aggregation in the code is confusing. Fixes: 942c5593 ("perf stat: Add perf_stat_merge_counters()") Reported-by:
Perry Taylor <perry.taylor@intel.com> Signed-off-by:
-
- Feb 08, 2023
-
-
Thomas Richter authored
I have downloaded linux-next and build the perf tool using # make LIBPFM4=1 to have libpfm4 support built into perf. The build fails: # make LIBPFM4=1 .... INSTALL libbpf_headers CC util/pfm.o util/pfm.c: In function ‘print_libpfm_event’: util/pfm.c:189:9: error: too many arguments to function ‘print_cb->print_event’ 189 | print_cb->print_event(print_state, | ^~~~~~~~ util/pfm.c:220:25: error: too many arguments to function ‘print_cb->print_event’ 220 | print_cb->print_event(print_state, The build error is caused by commit d9dc8874 ("perf pmu-events: Remove now unused event and metric variables") which changes the function prototype of struct print_callbacks { ... void (*print_event)(...); --> last two parameters removed. }; but does not adjust the usage of this function prototype in util/pfm.c. In file util/pfm.c function print_event() is still invoked with 13 parameters instead of 11. The compile fails. When I adjust the file util/pfm.c as in this patch, the build works file. Please check this patch for correctness, I have just fixed the compile issue. Fixes: d9dc8874 ("perf pmu-events: Remove now unused event and metric variables") Signed-off-by:Thomas Richter <tmricht@linux.ibm.com> Tested-by:
-
Yicong Yang authored
On aarch64 CPU related events are not under event_source/devices/cpu/events, they're under event_source/devices/armv8_pmuv3_0/events on my machine. Using current auto-complete script will generate below error: [root@localhost bin]# perf stat -e ls: cannot access '/sys/bus/event_source/devices/cpu/events': No such file or directory Fix this by not testing /sys/bus/event_source/devices/cpu/events on aarch64 machine. Fixes: 74cd5815 ("perf tool: Improve bash command line auto-complete for multiple events with comma") Reviewed-by:
James Clark <james.clark@arm.com> Signed-off-by:
Yicong Yang <yangyicong@hisilicon.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Cc: prime.zeng@hisilicon.com Link: https://lore.kernel.org/r/20230207035057.43394-1-yangyicong@huawei.com Signed-off-by:
-
Namhyung Kim authored
The old kernel has a different type of the owner field in rwsem. We can check it using bpf_core_type_matches() builtin in clang but it also needs its own version check since it's available on recent versions. Signed-off-by:
-
Namhyung Kim authored
When there're many lock contentions in the system, people sometimes want to know who caused the contention, IOW who's the owner of the locks. The -o/--lock-owner option tries to follow the lock owners for the contended mutexes and rwsems from BPF, and then attributes the contention time to the owner instead of the waiter. It's a best effort approach to get the owner info at the time of the contention and doesn't guarantee to have the precise tracking of owners if it's changing over time. Currently it only handles mutex and rwsem that have owner field in their struct and it basically points to a task_struct that owns the lock at the moment. Technically its type is atomic_long_t and it comes with some LSB bits used for other meanings. So it needs to clear them when casting it to a pointer to task_struct. Also the atomic_long_t is a typedef of the atomic 32 or 64 bit types depending on arch which is a wrapper struct for the counter value. I'm not aware of proper ways to access those kernel atomic types from BPF so I just read the internal counter value directly. Please let me know if there's a better way. When -o/--lock-owner option is used, it goes to the task aggregation mode like -t/--threads option does. However it cannot get the owner for other lock types like spinlock and sometimes even for mutex. $ sudo ./perf lock con -abo -- ./perf bench sched pipe # Running 'sched/pipe' benchmark: # Executed 1000000 pipe operations between two processes Total time: 4.766 [sec] 4.766540 usecs/op 209795 ops/sec contended total wait max wait avg wait pid owner 403 565.32 us 26.81 us 1.40 us -1 Unknown 4 27.99 us 8.57 us 7.00 us 1583145 sched-pipe 1 8.25 us 8.25 us 8.25 us 1583144 sched-pipe 1 2.03 us 2.03 us 2.03 us 5068 chrome As you can see, the owner is unknown for the most cases. But if we filter only for the mutex locks, it'd more likely get the onwers. $ sudo ./perf lock con -abo -Y mutex -- ./perf bench sched pipe # Running 'sched/pipe' benchmark: # Executed 1000000 pipe operations between two processes Total time: 4.910 [sec] 4.910435 usecs/op 203647 ops/sec contended total wait max wait avg wait pid owner 2 15.50 us 8.29 us 7.75 us 1582852 sched-pipe 7 7.20 us 2.47 us 1.03 us -1 Unknown 1 6.74 us 6.74 us 6.74 us 1582851 sched-pipe Signed-off-by: -
Namhyung Kim authored
The previous change missed to set the con->save_callstack for the LOCK_AGGR_CALLER mode resulting in no caller information. Fixes: ebab2916 ("perf lock contention: Support filters for different aggregation") Signed-off-by:
-
- Feb 06, 2023
-
-
Athira Rajeev authored
Perf BPF filter test fails in environment where "kernel-debuginfo" is not installed. Test failure logs: <<>> 42: BPF filter : 42.1: Basic BPF filtering : Ok 42.2: BPF pinning : Ok 42.3: BPF prologue generation : FAILED! <<>> Enabling verbose option provided debug logs, which says debuginfo needs to be installed. Snippet of verbose logs: <<>> 42.3: BPF prologue generation : --- start --- test child forked, pid 28218 <<>> Rebuild with CONFIG_DEBUG_INFO=y, or install an appropriate debuginfo package. bpf_probe: failed to convert perf probe events Failed to add events selected by BPF test child finished with -1 ---- end ---- BPF filter subtest 3: FAILED! <<>> Here the subtest "BPF prologue generation" failed and logs shows debuginfo is needed. After installing kernel-debuginfo package, testcase passes. The "BPF prologue generation" subtest failed because, the do_test() returns TEST_FAIL without checking the error type returned by parse_events_load_bpf_obj(). parse_events_load_bpf_obj() can also return error of type -ENODATA incase kernel-debuginfo package is not installed. Fix this by adding check for -ENODATA error. Test result after the patch changes: Test failure logs: <<>> 42: BPF filter : 42.1: Basic BPF filtering : Ok 42.2: BPF pinning : Ok 42.3: BPF prologue generation : Skip (clang/debuginfo isn't installed or environment missing BPF support) <<>> Fixes: ba1fae43 ("perf test: Add 'perf test BPF'") Signed-off-by:
-
Athira Rajeev authored
try_to_find_probe_trace_events() uses return error code as ENOENT in two places. First place is after open_debuginfo() when opening debuginfo fails and secondly, after when not finding the probe point. This function is invoked during BPF load and there are other exit points in this code path which returns ENOENT. This makes it difficult to understand the exact reason for exit. Patches changes the exit code from ENOENT to: - ENODATA when it fails to find debuginfo - ENODEV when it fails to find probe point Signed-off-by:
-
Kan Liang authored
The 'perf script' documentation is missing the fields option for Retire Latency. Add it. Signed-off-by:
Kan Liang <kan.liang@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230206162100.3329395-2-kan.liang@linux.intel.com Signed-off-by:
-
Kan Liang authored
In arch_perf_synthesize_sample_weight(), the retire_lat was mistakenly missed, add it. perf test -v "x86 sample parsing" 74: x86 Sample parsing : --- start --- test child forked, pid 72526 Samples differ at 'retire_lat' parsing failed for sample_type 0x1000000 test child finished with -1 ---- end ---- x86 Sample parsing: FAILED! Reported-by:
Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by:
-
Kan Liang authored
Add test for the new field for Retire Latency in the X86 specific test. Signed-off-by:
-
Athira Rajeev authored
The "bpf" tests fails in environment with missing libtraceevent support as below: # ./perf test 36 36: BPF filter : 36.1: Basic BPF filtering : FAILED! 36.2: BPF pinning : FAILED! 36.3: BPF prologue generation : FAILED! The environment has clang but missing the libtraceevent devel. Hence perf is compiled without libtraceevent support. Detailed logs: ./perf test -v "Basic BPF filtering" Failed to add BPF event syscalls:sys_enter_epoll_pwait bpf: tracepoint call back failed, stop iterate Failed to add events selected by BPF The bpf tests tris to add probe event which fails at "parse_events_add_tracepoint" function due to missing libtraceevent. Add check for "HAVE_LIBTRACEEVENT" in the "tests/bpf.c" before proceeding with the test. With the change, # ./perf test 36 36: BPF filter : 36.1: Basic BPF filtering : Skip (not compiled in or missing libtraceevent support) 36.2: BPF pinning : Skip (not compiled in or missing libtraceevent support) 36.3: BPF prologue generation : Skip (not compiled in or missing libtraceevent support) Signed-off-by:
-
- Feb 03, 2023
-
-
Kan Liang authored
The Retire Latency field is added in the var3_w of the PERF_SAMPLE_WEIGHT_STRUCT. The Retire Latency reports the number of elapsed core clocks between the retirement of the instruction indicated by the Instruction Pointer field of the PEBS record and the retirement of the prior instruction. That's quite useful to display the information with perf script. Add a new field retire_lat for the Retire Latency information. Reviewed-by:
-
Kan Liang authored
The Retire Latency field is added in the var3_w of the PERF_SAMPLE_WEIGHT_STRUCT. The Retire Latency reports pipeline stall of this instruction compared to the previous instruction in cycles. That's quite useful to display the information with perf mem report. The p_stage_cyc for Power is also from the var3_w. Union the p_stage_cyc and retire_lat to share the code. Implement X86 specific codes to display the X86 specific header. Add a new sort key retire_lat for the Retire Latency. Reviewed-by:
-
Namhyung Kim authored
It'd be useful to filter other than the current aggregation mode. For example, users may want to see callstacks for specific locks only. Or they may want tasks from a certain callstack. The tracepoints already collected the information but it needs to check the condition again when processing the event. And it needs to change BPF to allow the key combinations. The lock contentions on 'rcu_state' spinlock can be monitored: $ sudo perf lock con -abv -L rcu_state sleep 1 ... contended total wait max wait avg wait type caller 4 151.39 us 62.57 us 37.85 us spinlock rcu_core+0xcb 0xffffffff81fd1666 _raw_spin_lock_irqsave+0x46 0xffffffff8172d76b rcu_core+0xcb 0xffffffff822000eb __softirqentry_text_start+0xeb 0xffffffff816a0ba9 __irq_exit_rcu+0xc9 0xffffffff81fc0112 sysvec_apic_timer_interrupt+0xa2 0xffffffff82000e46 asm_sysvec_apic_timer_interrupt+0x16 0xffffffff81d49f78 cpuidle_enter_state+0xd8 0xffffffff81d4a259 cpuidle_enter+0x29 1 30.21 us 30.21 us 30.21 us spinlock rcu_core+0xcb 0xffffffff81fd1666 _raw_spin_lock_irqsave+0x46 0xffffffff8172d76b rcu_core+0xcb 0xffffffff822000eb __softirqentry_text_start+0xeb 0xffffffff816a0ba9 __irq_exit_rcu+0xc9 0xffffffff81fc00c4 sysvec_apic_timer_interrupt+0x54 0xffffffff82000e46 asm_sysvec_apic_timer_interrupt+0x16 1 28.84 us 28.84 us 28.84 us spinlock rcu_accelerate_cbs_unlocked+0x40 0xffffffff81fd1c60 _raw_spin_lock+0x30 0xffffffff81728cf0 rcu_accelerate_cbs_unlocked+0x40 0xffffffff8172da82 rcu_core+0x3e2 0xffffffff822000eb __softirqentry_text_start+0xeb 0xffffffff816a0ba9 __irq_exit_rcu+0xc9 0xffffffff81fc0112 sysvec_apic_timer_interrupt+0xa2 0xffffffff82000e46 asm_sysvec_apic_timer_interrupt+0x16 0xffffffff81d49f78 cpuidle_enter_state+0xd8 ... To see tasks calling 'rcu_core' function: $ sudo perf lock con -abt -S rcu_core sleep 1 contended total wait max wait avg wait pid comm 19 23.46 us 2.21 us 1.23 us 0 swapper 2 18.37 us 17.01 us 9.19 us 2061859 ThreadPoolForeg 3 5.76 us 1.97 us 1.92 us 3909 pipewire-pulse 1 2.26 us 2.26 us 2.26 us 1809271 MediaSu~isor #2 1 1.97 us 1.97 us 1.97 us 1514882 Chrome_ChildIOT 1 987 ns 987 ns 987 ns 3740 pipewire-pulse Signed-off-by: -
Namhyung Kim authored
This is a preparation work to support complex keys of BPF maps. Now it has single value key according to the aggregation mode like stack_id or pid. But we want to use a combination of those keys. Then lock_contention_read() should still aggregate the result based on the key that was requested by user. The other key info will be used for filtering. So instead of creating a lock_stat entry always, Check if it's already there using lock_stat_find() first. Signed-off-by:
-
Namhyung Kim authored
The lock_contention_get_name() returns a name for the lock stat entry based on the current aggregation mode. As it's called sequentially in a single thread, it can return the address of a static buffer for symbol and offset of the caller. Signed-off-by:
-
Rob Herring authored
Arm SPEv1.2 adds a new optional address packet type: previous branch target. The recorded address is the target virtual address of the most recently taken branch in program order. Add support for decoding the address packet in raw dumps. Reviewed-by:
Rob Herring <robh@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230203162401.132931-1-robh@kernel.org Signed-off-by:
-
Ian Rogers authored
Add a target that generates a log file for running metric_test.py and make this a dependency on generating pmu-events.c. The log output is displayed if the test fails like (the test was modified to make it fail): ``` TEST /tmp/perf/pmu-events/metric_test.log F...... ====================================================================== FAIL: test_Brackets (__main__.TestMetricExpressions) ---------------------------------------------------------------------- Traceback (most recent call last): File "tools/perf/pmu-events/metric_test.py", line 33, in test_Brackets self.assertEqual((a * b + c).ToPerfJson(), 'a * b + d') AssertionError: 'a * b + c' != 'a * b + d' - a * b + c ? ^ + a * b + d ? ^ ---------------------------------------------------------------------- Ran 7 tests in 0.004s FAILED (failures=1) make[3]: *** [pmu-events/Build:32: /tmp/perf/pmu-events/metric_test.log] Error 1 ``` However, normal execution will just show the TEST line. This is roughly modeled on fortify testing in the kernel lib directory. Modify metric_test.py so that it is executable. This is necessary when PYTHON isn't specified in the build, the normal case. Use variables to make the paths to files clearer and more consistent. Committer notes: Add pmu-events/metric_test.log to tools/perf/.gitignore and to the 'clean' target on tools/perf/Makefile.perf. Reviewed-by: -
Ian Rogers authored
A character encoding issue added a "3D" character that breaks the metrics test. Fixes: 40769665 ("perf jevents: Parse metrics during conversion") Reviewed-by:
-
Ian Rogers authored
The #slots literal will return NAN when not on ARM64 which causes a perf test failure when not on an ARM64 for a JEVENTS_ARCH=all build: .. 10.4: Parsing of PMU event table metrics with fake PMUs : FAILED! .. Add an is_test boolean so that the failure can be avoided when running as a test. Fixes: acef233b ("perf pmu: Add #slots literal support for arm64") Reviewed-by:
John Garry <john.g.garry@oracle.com> Reviewed-by:
-
Ian Rogers authored
This allows the set of generated jevents events and metrics be limited to a subset of the model names. Appropriate if trying to minimize the binary size where only a set of models are possible. Reviewed-by:
-
Ian Rogers authored
Turn a perf json event into an event, metric or both. This reduces the number of events needed to scan to find an event or metric. As events no longer need the relatively seldom used metric fields, 4 bytes is saved per event. This reduces the big C string's size by 335kb (14.8%) on x86. Note, for the test PMU architecture pme_test_soc_cpu is renamed pmu_events__test_soc_cpu for consistency with the event vs metric naming convention. Reviewed-by:
-
Ian Rogers authored
Add a metrics table that is just a cast from pmu_events_table. This changes the APIs so that event and metric usage of the underlying table is different. For the no jevents case the tables are already separate, later changes will separate the tables for the jevents case. Reviewed-by:
-
Ian Rogers authored
Combine into a single function to simplify, in a later change, writing metrics separately. Reviewed-by:
-
Ian Rogers authored
Metrics are their own unit and these variables held broken metrics previously and now just hold the value NULL. Remove code that used these variables. Reviewed-by:
-
Ian Rogers authored
Previous changes separated the uses of pmu_event and pmu_metric, however, both structures contained all the variables of event and metric. This change removes the event variables from metric and the metric variables from event. Note, this change removes the setting of evsel's metric_name/expr as these fields are no longer part of struct pmu_event. The metric remains but is no longer implicitly requested when the event is. This impacts a few Intel uncore events, however, as the ScaleUnit is shared by the event and the metric this utility is questionable. Also the MetricNames look broken (contain spaces) in some cases and when trying to use the functionality with '-e' the metrics fail but regular metrics with '-M' work. For example, on SkylakeX '-M' works: ``` $ perf stat -M LLC_MISSES.PCIE_WRITE -a sleep 1 Performance counter stats for 'system wide': 0 UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 # 57896.0 Bytes LLC_MISSES.PCIE_WRITE (49.84%) 7,174 UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 (49.85%) 0 UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 (50.16%) 63 UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 (50.15%) 1.004576381 seconds time elapsed ``` whilst the event '-e' version is broken even with --group/-g (fwiw, we should also remove -g [1]): ``` $ perf stat -g -e LLC_MISSES.PCIE_WRITE -g -a sleep 1 Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Add UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 event to groups to get metric expression for LLC_MISSES.PCIE_WRITE Performance counter stats for 'system wide': 27,316 Bytes LLC_MISSES.PCIE_WRITE 1.004505469 seconds time elapsed ``` The code also carries warnings where the user is supposed to select events for metrics [2] but given the lack of use of such a feature, let's clean the code and just remove. [1] https://lore.kernel.org/lkml/20220707195610.303254-1-irogers@google.com/ [2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/perf/util/stat-shadow.c?id=01b8957b738f42f96a130079bc951b3cc78c5b8a#n425 Reviewed-by: -
Ian Rogers authored
Separate the event and metric table when building without jevents. Add find_core_metrics_table and perf_pmu__find_metrics_table while renaming existing utilities to be event specific, so that users can find the right table for their need. Committer notes: Fix the build on aarch64 with: tools/perf/arch/arm64/util/pmu.c @@ -32,7 +32,7 @@ const struct pmu_events_table *pmu_events_table__find(void) - return perf_pmu__find_table(pmu); + return perf_pmu__find_events_table(pmu); Reviewed-by:
-
NeilBrown authored
__GFP_ATOMIC serves little purpose. Its main effect is to set ALLOC_HARDER which adds a few little boosts to increase the chance of an allocation succeeding, one of which is to lower the water-mark at which it will succeed. It is *always* paired with __GFP_HIGH which sets ALLOC_HIGH which also adjusts this watermark. It is probable that other users of __GFP_HIGH should benefit from the other little bonuses that __GFP_ATOMIC gets. __GFP_ATOMIC also gives a warning if used with __GFP_DIRECT_RECLAIM. There is little point to this. We already get a might_sleep() warning if __GFP_DIRECT_RECLAIM is set. __GFP_ATOMIC allows the "watermark_boost" to be side-stepped. It is probable that testing ALLOC_HARDER is a better fit here. __GFP_ATOMIC is used by tegra-smmu.c to check if the allocation might sleep. This should test __GFP_DIRECT_RECLAIM instead. This patch: - removes __GFP_ATOMIC - allows __GFP_HIGH allocations to ignore watermark boosting as well as GFP_ATOMIC requests. - makes other adjustments as suggested by the above. The net result is not change to GFP_ATOMIC allocations. Other allocations that use __GFP_HIGH will benefit from a few different extra privileges. This affects: xen, dm, md, ntfs3 the vermillion frame buffer hibernation ksm swap all of which likely produce more benefit than cost if these selected allocation are more likely to succeed quickly. [mgorman: Minor adjustments to rework on top of a series] Link: https://lkml.kernel.org/r/163712397076.13692.4727608274002939094@noble.neil.brown.name Link: https://lkml.kernel.org/r/20230113111217.14134-7-mgorman@techsingularity.net Signed-off-by:
NeilBrown <neilb@suse.de> Signed-off-by:
Mel Gorman <mgorman@techsingularity.net> Acked-by:
Vlastimil Babka <vbabka@suse.cz> Acked-by:
Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thierry Reding <thierry.reding@gmail.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org>
-
- Feb 02, 2023
-
-
Ian Rogers authored
Create a new pmu_metric for the metric related variables from pmu_event but that is initially just a clone of pmu_event. Add iterators for pmu_metric and use in places that metrics are desired rather than events. Make the event iterator skip metric only events, and the metric iterator skip event only events. Reviewed-by:
-
Ian Rogers authored
Rewrite metrics within the same file in terms of each other. For example, on Power8 other_stall_cpi is rewritten from: "PM_CMPLU_STALL / PM_RUN_INST_CMPL - PM_CMPLU_STALL_BRU_CRU / PM_RUN_INST_CMPL - PM_CMPLU_STALL_FXU / PM_RUN_INST_CMPL - PM_CMPLU_STALL_VSU / PM_RUN_INST_CMPL - PM_CMPLU_STALL_LSU / PM_RUN_INST_CMPL - PM_CMPLU_STALL_NTCG_FLUSH / PM_RUN_INST_CMPL - PM_CMPLU_STALL_NO_NTF / PM_RUN_INST_CMPL" to: "stall_cpi - bru_cru_stall_cpi - fxu_stall_cpi - vsu_stall_cpi - lsu_stall_cpi - ntcg_flush_cpi - no_ntf_stall_cpi" Which more closely matches the definition on Power9. To avoid recomputation decorate the function with a cache. Reviewed-by:
-
Ian Rogers authored
Add RewriteMetricsInTermsOfOthers that iterates over pairs of names and expressions trying to replace an expression, within the current expression, with its name. Reviewed-by:
-
Ian Rogers authored
rhs may not be defined, say for source_count, so add a guard. Reviewed-by:
-
Sandipan Das authored
Show the branch speculation info if provided by the branch recording hardware feature. This can be useful for purposes of code optimization. E.g. $ perf record -j any,u ./test_branch $ perf report --dump-raw-trace Before: [...] 8380958377610 0x40b178 [0x1b0]: PERF_RECORD_SAMPLE(IP, 0x2): 7952/7952: 0x4f851a period: 48973 addr: 0 ... branch stack: nr:16 ..... 0: 00000000004b52fd -> 00000000004f82c0 0 cycles P 0 ..... 1: ffffffff8220137c -> 00000000004b52f0 0 cycles M 0 ..... 2: 000000000041d1c4 -> 00000000004b52f0 0 cycles P 0 ..... 3: 00000000004e7ead -> 000000000041d1b0 0 cycles M 0 ..... 4: 00000000004e7f91 -> 00000000004e7ead 0 cycles P 0 ..... 5: 00000000004e7ea8 -> 00000000004e7f70 0 cycles P 0 ..... 6: 00000000004e7e52 -> 00000000004e7e98 0 cycles M 0 ..... 7: 00000000004e7e1f -> 00000000004e7e40 0 cycles M 0 ..... 8: 00000000004e7f60 -> 00000000004e7df0 0 cycles P 0 ..... 9: 00000000004e7f58 -> 00000000004e7f60 0 cycles M 0 ..... 10: 000000000041d85d -> 00000000004e7f50 0 cycles P 0 ..... 11: 000000000043306a -> 000000000041d840 0 cycles P 0 ..... 12: ffffffff8220137c -> 0000000000433040 0 cycles M 0 ..... 13: 000000000041e4a1 -> 0000000000433040 0 cycles P 0 ..... 14: ffffffff8220137c -> 000000000041e490 0 cycles M 0 ..... 15: 000000000041d89b -> 000000000041e487 0 cycles P 0 ... thread: test_branch:7952 ...... dso: /data/sandipan/test_branch [...] After: [...] 8380958377610 0x40b178 [0x1b0]: PERF_RECORD_SAMPLE(IP, 0x2): 7952/7952: 0x4f851a period: 48973 addr: 0 ... branch stack: nr:16 ..... 0: 00000000004b52fd -> 00000000004f82c0 0 cycles P 0 NON_SPEC_CORRECT_PATH ..... 1: ffffffff8220137c -> 00000000004b52f0 0 cycles M 0 NON_SPEC_CORRECT_PATH ..... 2: 000000000041d1c4 -> 00000000004b52f0 0 cycles P 0 NON_SPEC_CORRECT_PATH ..... 3: 00000000004e7ead -> 000000000041d1b0 0 cycles M 0 NON_SPEC_CORRECT_PATH ..... 4: 00000000004e7f91 -> 00000000004e7ead 0 cycles P 0 NON_SPEC_CORRECT_PATH ..... 5: 00000000004e7ea8 -> 00000000004e7f70 0 cycles P 0 NON_SPEC_CORRECT_PATH ..... 6: 00000000004e7e52 -> 00000000004e7e98 0 cycles M 0 SPEC_CORRECT_PATH ..... 7: 00000000004e7e1f -> 00000000004e7e40 0 cycles M 0 NON_SPEC_CORRECT_PATH ..... 8: 00000000004e7f60 -> 00000000004e7df0 0 cycles P 0 NON_SPEC_CORRECT_PATH ..... 9: 00000000004e7f58 -> 00000000004e7f60 0 cycles M 0 NON_SPEC_CORRECT_PATH ..... 10: 000000000041d85d -> 00000000004e7f50 0 cycles P 0 NON_SPEC_CORRECT_PATH ..... 11: 000000000043306a -> 000000000041d840 0 cycles P 0 NON_SPEC_CORRECT_PATH ..... 12: ffffffff8220137c -> 0000000000433040 0 cycles M 0 NON_SPEC_CORRECT_PATH ..... 13: 000000000041e4a1 -> 0000000000433040 0 cycles P 0 NON_SPEC_CORRECT_PATH ..... 14: ffffffff8220137c -> 000000000041e490 0 cycles M 0 NON_SPEC_CORRECT_PATH ..... 15: 000000000041d89b -> 000000000041e487 0 cycles P 0 NON_SPEC_CORRECT_PATH ... thread: test_branch:7952 ...... dso: /data/sandipan/test_branch [...] With the addition of new branch flags, the "brstacksym" fields in perf script output now shows speculation information after the branch type. Change the regular expressions accordingly for the test to pass. Since branch speculation information may vary across platforms, the test does not look for specific values. E.g. $ perf test -v 110 Before: 110: Check branch stack sampling : --- start --- test child forked, pid 54154 Testing user branch stack sampling + grep -E -m1 ^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL$ /tmp/__perf_test.program.AfhUI/perf.script + cleanup + rm -rf /tmp/__perf_test.program.AfhUI test child finished with -1 ---- end ---- Check branch stack sampling: FAILED! After: 110: Check branch stack sampling : --- start --- test child forked, pid 43716 Testing user branch stack sampling + grep -E -m1 ^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL/.*$ /tmp/__perf_test.program.xgzAi/perf.script brstack_bench+0x66/brstack_foo+0x0/P/-/-/0/IND_CALL/NON_SPEC_CORRECT_PATH + grep -E -m1 ^brstack_foo\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$ /tmp/__perf_test.program.xgzAi/perf.script brstack_foo+0x1b/brstack_bar+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH + grep -E -m1 ^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/CALL/.*$ /tmp/__perf_test.program.xgzAi/perf.script brstack_bench+0x58/brstack_foo+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH + grep -E -m1 ^brstack_bench\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$ /tmp/__perf_test.program.xgzAi/perf.script brstack_bench+0x5d/brstack_bar+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH + grep -E -m1 ^brstack_bar\+[^ ]*/brstack_foo\+[^ ]*/RET/.*$ /tmp/__perf_test.program.xgzAi/perf.script brstack_bar+0x31/brstack_foo+0x20/P/-/-/0/RET/NON_SPEC_CORRECT_PATH + grep -E -m1 ^brstack_foo\+[^ ]*/brstack_bench\+[^ ]*/RET/.*$ /tmp/__perf_test.program.xgzAi/perf.script brstack_foo+0x36/brstack_bench+0x5d/P/-/-/0/RET/NON_SPEC_CORRECT_PATH + grep -E -m1 ^brstack_bench\+[^ ]*/brstack_bench\+[^ ]*/COND/.*$ /tmp/__perf_test.program.xgzAi/perf.script brstack_bench+0x76/brstack_bench+0x7d/P/-/-/0/COND/NON_SPEC_CORRECT_PATH + grep -E -m1 ^brstack\+[^ ]*/brstack\+[^ ]*/UNCOND/.*$ /tmp/__perf_test.program.xgzAi/perf.script brstack+0x5a/brstack+0x41/P/-/-/0/UNCOND/NON_SPEC_CORRECT_PATH + set +x Testing branch stack filtering permutation (any_call,CALL|IND_CALL|COND_CALL|SYSCALL|IRQ) Testing branch stack filtering permutation (call,CALL|SYSCALL) Testing branch stack filtering permutation (cond,COND) Testing branch stack filtering permutation (any_ret,RET|COND_RET|SYSRET|ERET) Testing branch stack filtering permutation (call,cond,CALL|SYSCALL|COND) Testing branch stack filtering permutation (any_call,cond,CALL|IND_CALL|COND_CALL|IRQ|SYSCALL|COND) Testing branch stack filtering permutation (cond,any_call,any_ret,COND|CALL|IND_CALL|COND_CALL|SYSCALL|IRQ|RET|COND_RET|SYSRET|ERET) test child finished with 0 ---- end ---- Check branch stack sampling: Ok Signed-off-by:
Sandipan Das <sandipan.das@amd.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Santosh Shukla <santosh.shukla@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: x86@kernel.org Link: https://lore.kernel.org/r/048d67c9de3cc8e3dbf19aaa7ff718dec91364c5.1675333809.git.sandipan.das@amd.com Signed-off-by:
-
Sandipan Das authored
Show the branch speculation info if provided by the branch recording hardware feature. This can be useful for optimizing code further. The speculation info is appended to the end of the list of fields so any existing tools that use "/" as a delimiter for access fields via an index remain unaffected. Also show "-" instead of "N/A" when speculation info is unavailable because "/" is used as the field separator. E.g. $ perf record -j any,u,save_type ./test_branch $ perf script --fields brstacksym Before: [...] check_match+0x60/strcmp+0x0/P/-/-/0/CALL do_lookup_x+0x3c5/check_match+0x0/P/-/-/0/CALL [...] After: [...] check_match+0x60/strcmp+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH do_lookup_x+0x3c5/check_match+0x0/P/-/-/0/CALL/NON_SPEC_CORRECT_PATH [...] The bitfield swapping scheme used duing sample parsing has changed because of the addition of new branch flags, namely "spec", "new_type" and "priv". Earlier, these were all part of the "reserved" field but now, each of these fields get swapped separately. Change the expected flag values accordingly for the test to pass. E.g. $ perf test -v 27 Before: 27: Sample parsing : --- start --- test child forked, pid 61979 parsing failed for sample_type 0x800 test child finished with -1 ---- end ---- Sample parsing: FAILED! After: 27: Sample parsing : --- start --- test child forked, pid 63293 test child finished with 0 ---- end ---- Sample parsing: Ok Signed-off-by:
-
