summaryrefslogtreecommitdiff
path: root/tools/perf
AgeCommit message (Collapse)Author
2020-08-21perf bench mem: Always memset source before memcpyVincent Whitchurch
[ Upstream commit 1beaef29c34154ccdcb3f1ae557f6883eda18840 ] For memcpy, the source pages are memset to zero only when --cycles is used. This leads to wildly different results with or without --cycles, since all sources pages are likely to be mapped to the same zero page without explicit writes. Before this fix: $ export cmd="./perf stat -e LLC-loads -- ./perf bench \ mem memcpy -s 1024MB -l 100 -f default" $ $cmd 2,935,826 LLC-loads 3.821677452 seconds time elapsed $ $cmd --cycles 217,533,436 LLC-loads 8.616725985 seconds time elapsed After this fix: $ $cmd 214,459,686 LLC-loads 8.674301124 seconds time elapsed $ $cmd --cycles 214,758,651 LLC-loads 8.644480006 seconds time elapsed Fixes: 47b5757bac03c338 ("perf bench mem: Move boilerplate memory allocation to the infrastructure") Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: kernel@axis.com Link: http://lore.kernel.org/lkml/20200810133404.30829-1-vincent.whitchurch@axis.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-08-21perf record: Skip side-band event setup if HAVE_LIBBPF_SUPPORT is not setJin Yao
[ Upstream commit 1101c872c8c7869c78dc106ae820040f36807eda ] We received an error report that perf-record caused 'Segmentation fault' on a newly system (e.g. on the new installed ubuntu). (gdb) backtrace #0 __read_once_size (size=4, res=<synthetic pointer>, p=0x14) at /root/0-jinyao/acme/tools/include/linux/compiler.h:139 #1 atomic_read (v=0x14) at /root/0-jinyao/acme/tools/include/asm/../../arch/x86/include/asm/atomic.h:28 #2 refcount_read (r=0x14) at /root/0-jinyao/acme/tools/include/linux/refcount.h:65 #3 perf_mmap__read_init (map=map@entry=0x0) at mmap.c:177 #4 0x0000561ce5c0de39 in perf_evlist__poll_thread (arg=0x561ce68584d0) at util/sideband_evlist.c:62 #5 0x00007fad78491609 in start_thread (arg=<optimized out>) at pthread_create.c:477 #6 0x00007fad7823c103 in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95 The root cause is, evlist__add_bpf_sb_event() just returns 0 if HAVE_LIBBPF_SUPPORT is not defined (inline function path). So it will not create a valid evsel for side-band event. But perf-record still creates BPF side band thread to process the side-band event, then the error happpens. We can reproduce this issue by removing the libelf-dev. e.g. 1. apt-get remove libelf-dev 2. perf record -a -- sleep 1 root@test:~# ./perf record -a -- sleep 1 perf: Segmentation fault Obtained 6 stack frames. ./perf(+0x28eee8) [0x5562d6ef6ee8] /lib/x86_64-linux-gnu/libc.so.6(+0x46210) [0x7fbfdc65f210] ./perf(+0x342e74) [0x5562d6faae74] ./perf(+0x257e39) [0x5562d6ebfe39] /lib/x86_64-linux-gnu/libpthread.so.0(+0x9609) [0x7fbfdc990609] /lib/x86_64-linux-gnu/libc.so.6(clone+0x43) [0x7fbfdc73b103] Segmentation fault (core dumped) To fix this issue, 1. We either install the missing libraries to let HAVE_LIBBPF_SUPPORT be defined. e.g. apt-get install libelf-dev and install other related libraries. 2. Use this patch to skip the side-band event setup if HAVE_LIBBPF_SUPPORT is not set. Committer notes: The side band thread is not used just with BPF, it is also used with --switch-output-event, so narrow the ifdef to the BPF specific part. Fixes: 23cbb41c939a ("perf record: Move side band evlist setup to separate routine") Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200805022937.29184-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-08-21perf evsel: Don't set sample_regs_intr/sample_regs_user for dummy eventJin Yao
[ Upstream commit c4735d990268399da9133b0ad445e488ece009ad ] Since commit 0a892c1c9472 ("perf record: Add dummy event during system wide synthesis"), a dummy event is added to capture mmaps. But if we run perf-record as, # perf record -e cycles:p -IXMM0 -a -- sleep 1 Error: dummy:HG: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat' The issue is, if we enable the extended regs (-IXMM0), but the pmu->capabilities is not set with PERF_PMU_CAP_EXTENDED_REGS, the kernel will return -EOPNOTSUPP error. See following code: /* in kernel/events/core.c */ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) { .... if (!(pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS) && has_extended_regs(event)) ret = -EOPNOTSUPP; .... } For software dummy event, the PMU should not be set with PERF_PMU_CAP_EXTENDED_REGS. But unfortunately now, the dummy event has possibility to be set with PERF_REG_EXTENDED_MASK bit. In evsel__config, /* tools/perf/util/evsel.c */ if (opts->sample_intr_regs) { attr->sample_regs_intr = opts->sample_intr_regs; } If we use -IXMM0, the attr>sample_regs_intr will be set with PERF_REG_EXTENDED_MASK bit. It doesn't make sense to set attr->sample_regs_intr for a software dummy event. This patch adds dummy event checking before setting attr->sample_regs_intr and attr->sample_regs_user. After: # ./perf record -e cycles:p -IXMM0 -a -- sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.413 MB perf.data (45 samples) ] Committer notes: Adrian said this when providing his Acked-by: " This is fine. It will not break PT. no_aux_samples is useful for evsels that have been added by the code rather than requested by the user. For old kernels PT adds sched_switch tracepoint to track context switches (before the current context switch event was added) and having auxiliary sample information unnecessarily uses up space in the perf buffer. " Fixes: 0a892c1c9472 ("perf record: Add dummy event during system wide synthesis") Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200720010013.18238-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-08-21perf tools: Fix term parsing for raw syntaxJiri Olsa
[ Upstream commit 4929e95a1400e45b4b5a87fd3ce10273444187d4 ] Jin Yao reported issue with possible conflict between raw events and term values in pmu event syntax. Currently following syntax is resolved as raw event with 0xead value: uncore_imc_free_running/read/ instead of using 'read' term from uncore_imc_free_running pmu, because 'read' is correct raw event syntax with 0xead value. To solve this issue we do following: - check existing terms during rXXXX syntax processing and make them priority in case of conflict - allow pmu/r0x1234/ syntax to be able to specify conflicting raw event (implemented in previous patch) Also add automated tests for this and perf_pmu__parse_cleanup call to parse_events_terms, so the test gets properly cleaned up. Fixes: 3a6c51e4d66c ("perf parser: Add support to specify rXXX event with pmu") Reported-by: Jin Yao <yao.jin@linux.intel.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200726075244.1191481-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-08-21perf intel-pt: Fix duplicate branch after CBRAdrian Hunter
commit a58a057ce65b52125dd355b7d8b0d540ea267a5f upstream. CBR events can result in a duplicate branch event, because the state type defaults to a branch. Fix by clearing the state type. Example: trace 'sleep' and hope for a frequency change Before: $ perf record -e intel_pt//u sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bpe > before.txt After: $ perf script --itrace=bpe > after.txt $ diff -u before.txt after.txt # --- before.txt 2020-07-07 14:42:18.191508098 +0300 # +++ after.txt 2020-07-07 14:42:36.587891753 +0300 @@ -29673,7 +29673,6 @@ sleep 93431 [007] 15411.619905: 1 branches:u: 0 [unknown] ([unknown]) => 7f0818abb2e0 clock_nanosleep@@GLIBC_2.17+0x0 (/usr/lib/x86_64-linux-gnu/libc-2.31.so) sleep 93431 [007] 15411.619905: 1 branches:u: 7f0818abb30c clock_nanosleep@@GLIBC_2.17+0x2c (/usr/lib/x86_64-linux-gnu/libc-2.31.so) => 0 [unknown] ([unknown]) sleep 93431 [007] 15411.720069: cbr: cbr: 15 freq: 1507 MHz ( 56%) 7f0818abb30c clock_nanosleep@@GLIBC_2.17+0x2c (/usr/lib/x86_64-linux-gnu/libc-2.31.so) - sleep 93431 [007] 15411.720069: 1 branches:u: 7f0818abb30c clock_nanosleep@@GLIBC_2.17+0x2c (/usr/lib/x86_64-linux-gnu/libc-2.31.so) => 0 [unknown] ([unknown]) sleep 93431 [007] 15411.720076: 1 branches:u: 0 [unknown] ([unknown]) => 7f0818abb30e clock_nanosleep@@GLIBC_2.17+0x2e (/usr/lib/x86_64-linux-gnu/libc-2.31.so) sleep 93431 [007] 15411.720077: 1 branches:u: 7f0818abb323 clock_nanosleep@@GLIBC_2.17+0x43 (/usr/lib/x86_64-linux-gnu/libc-2.31.so) => 7f0818ac0eb7 __nanosleep+0x17 (/usr/lib/x86_64-linux-gnu/libc-2.31.so) sleep 93431 [007] 15411.720077: 1 branches:u: 7f0818ac0ebf __nanosleep+0x1f (/usr/lib/x86_64-linux-gnu/libc-2.31.so) => 55cb7e4c2827 rpl_nanosleep+0x97 (/usr/bin/sleep) Fixes: 91de8684f1cff ("perf intel-pt: Cater for CBR change in PSB+") Fixes: abe5a1d3e4bee ("perf intel-pt: Decoder to output CBR changes immediately") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200710151104.15137-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-08-21perf intel-pt: Fix FUP packet stateAdrian Hunter
commit 401136bb084fd021acd9f8c51b52fe0a25e326b2 upstream. While walking code towards a FUP ip, the packet state is INTEL_PT_STATE_FUP or INTEL_PT_STATE_FUP_NO_TIP. That was mishandled resulting in the state becoming INTEL_PT_STATE_IN_SYNC prematurely. The result was an occasional lost EXSTOP event. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200710151104.15137-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-08-21perf probe: Fix memory leakage when the probe point is not foundMasami Hiramatsu
commit 12d572e785b15bc764e956caaa8a4c846fd15694 upstream. Fix the memory leakage in debuginfo__find_trace_events() when the probe point is not found in the debuginfo. If there is no probe point found in the debuginfo, debuginfo__find_probes() will NOT return -ENOENT, but 0. Thus the caller of debuginfo__find_probes() must check the tf.ntevs and release the allocated memory for the array of struct probe_trace_event. The current code releases the memory only if the debuginfo__find_probes() hits an error but not checks tf.ntevs. In the result, the memory allocated on *tevs are not released if tf.ntevs == 0. This fixes the memory leakage by checking tf.ntevs == 0 in addition to ret < 0. Fixes: ff741783506c ("perf probe: Introduce debuginfo to encapsulate dwarf information") Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/159438668346.62703.10887420400718492503.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-08-21perf probe: Fix wrong variable warning when the probe point is not foundMasami Hiramatsu
commit 11fd3eb874e73ee8069bcfd54e3c16fa7ce56fe6 upstream. Fix a wrong "variable not found" warning when the probe point is not found in the debuginfo. Since the debuginfo__find_probes() can return 0 even if it does not find given probe point in the debuginfo, fill_empty_trace_arg() can be called with tf.ntevs == 0 and it can emit a wrong warning. To fix this, reject ntevs == 0 in fill_empty_trace_arg(). E.g. without this patch; # perf probe -x /lib64/libc-2.30.so -a "memcpy arg1=%di" Failed to find the location of the '%di' variable at this address. Perhaps it has been optimized out. Use -V with the --range option to show '%di' location range. Added new events: probe_libc:memcpy (on memcpy in /usr/lib64/libc-2.30.so with arg1=%di) probe_libc:memcpy (on memcpy in /usr/lib64/libc-2.30.so with arg1=%di) You can now use it in all perf tools, such as: perf record -e probe_libc:memcpy -aR sleep 1 With this; # perf probe -x /lib64/libc-2.30.so -a "memcpy arg1=%di" Added new events: probe_libc:memcpy (on memcpy in /usr/lib64/libc-2.30.so with arg1=%di) probe_libc:memcpy (on memcpy in /usr/lib64/libc-2.30.so with arg1=%di) You can now use it in all perf tools, such as: perf record -e probe_libc:memcpy -aR sleep 1 Fixes: cb4027308570 ("perf probe: Trace a magic number if variable is not found") Reported-by: Andi Kleen <andi@firstfloor.org> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Tested-by: Andi Kleen <ak@linux.intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/159438667364.62703.2200642186798763202.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-07-31perf tools: Fix record failure when mixed with ARM SPE eventWei Li
When recording with cache-misses and arm_spe_x event, I found that it will just fail without showing any error info if i put cache-misses after 'arm_spe_x' event. [root@localhost 0620]# perf record -e cache-misses \ -e arm_spe_0/ts_enable=1,pct_enable=1,pa_enable=1,load_filter=1,jitter=1,store_filter=1,min_latency=0/ sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.067 MB perf.data ] [root@localhost 0620]# [root@localhost 0620]# perf record -e arm_spe_0/ts_enable=1,pct_enable=1,pa_enable=1,load_filter=1,jitter=1,store_filter=1,min_latency=0/ \ -e cache-misses sleep 1 [root@localhost 0620]# The current code can only work if the only event to be traced is an 'arm_spe_x', or if it is the last event to be specified. Otherwise the last event type will be checked against all the arm_spe_pmus[i]->types, none will match and an out of bound 'i' index will be used in arm_spe_recording_init(). We don't support concurrent multiple arm_spe_x events currently, that is checked in arm_spe_recording_options(), and it will show the relevant info. So add the check and record of the first found 'arm_spe_pmu' to fix this issue here. Fixes: ffd3d18c20b8 ("perf tools: Add ARM Statistical Profiling Extensions (SPE) support") Signed-off-by: Wei Li <liwei391@huawei.com> Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org> Tested-by-by: Leo Yan <leo.yan@linaro.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kim Phillips <kim.phillips@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: linux-arm-kernel@lists.infradead.org Link: http://lore.kernel.org/lkml/20200724071111.35593-2-liwei391@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-31perf tests: Fix test 68 zstd compression for s390Thomas Richter
Commit 5aa98879efe7 ("s390/cpum_sf: prohibit callchain data collection") prohibits call graph sampling for hardware events on s390. The information recorded is out of context and does not match. On s390 this commit now breaks test case 68 Zstd perf.data compression/decompression. Therefore omit call graph sampling on s390 in this test. Output before: [root@t35lp46 perf]# ./perf test -Fv 68 68: Zstd perf.data compression/decompression : --- start --- Collecting compressed record file: Error: cycles: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat' ---- end ---- Zstd perf.data compression/decompression: FAILED! [root@t35lp46 perf]# Output after: [root@t35lp46 perf]# ./perf test -Fv 68 68: Zstd perf.data compression/decompression : --- start --- Collecting compressed record file: 500+0 records in 500+0 records out 256000 bytes (256 kB, 250 KiB) copied, 0.00615638 s, 41.6 MB/s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.004 MB /tmp/perf.data.X3M, compressed (original 0.002 MB, ratio is 3.609) ] Checking compressed events stats: # compressed : Zstd, level = 1, ratio = 4 COMPRESSED events: 1 2ELIFREPh---- end ---- Zstd perf.data compression/decompression: Ok [root@t35lp46 perf]# Signed-off-by: Thomas Richter <tmricht@linux.ibm.com> Reviewed-by: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200729135314.91281-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-21s390/cpum_cf,perf: change DFLT_CCERROR counter nameThomas Richter
Change the counter name DLFT_CCERROR to DLFT_CCFINISH on IBM z15. This counter counts completed DEFLATE instructions with exit code 0, 1 or 2. Since exit code 0 means success and exit code 1 or 2 indicate errors, change the counter name to avoid confusion. This counter is incremented each time the DEFLATE instruction completed regardless if an error was detected or not. Fixes: d68d5d51dc89 ("s390/cpum_cf: Add new extended counters for IBM z15") Fixes: e7950166e402 ("perf vendor events s390: Add new deflate counters for IBM z15") Cc: stable@vger.kernel.org # v5.7 Signed-off-by: Thomas Richter <tmricht@linux.ibm.com> Reviewed-by: Sumanth Korikkar <sumanthk@linux.ibm.com> Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
2020-07-17perf tools: Sync hashmap.h with libbpf'sArnaldo Carvalho de Melo
To pick up the changes in: b2f9f1535bb9 ("libbpf: Fix libbpf hashmap on (I)LP32 architectures") Silencing this warning: Warning: Kernel ABI header at 'tools/perf/util/hashmap.h' differs from latest version at 'tools/lib/bpf/hashmap.h' diff -u tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h I'll eventually update the warning to remove the "Kernel ABI" part and instead state libbpf when noticing that the original is at "tools/lib/something". Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Jakub Bogusz <qboosh@pld-linux.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-06perf report TUI: Remove needless 'dummy' event from menuArnaldo Carvalho de Melo
Fixing the common case of: perf record perf report And getting just the cycles events. We now have a 'dummy' event to get perf metadata events that take place while we synthesize metadata records for pre-existing processes by traversing procfs, so we always have this extra 'dummy' evsel, but we don't have to offer it as there will be no samples on it, remove this distraction. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/20200706115452.GA2772@redhat.com/ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-06perf intel-pt: Fix PEBS sample for XMM registersAdrian Hunter
The condition to add XMM registers was missing, the regs array needed to be in the outer scope, and the size of the regs array was too small. Fixes: 143d34a6b387b ("perf intel-pt: Add XMM registers to synthesized PEBS sample") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Luwei Kang <luwei.kang@intel.com> Link: http://lore.kernel.org/lkml/20200630133935.11150-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-06perf intel-pt: Fix displaying PEBS-via-PT with registersAdrian Hunter
After recording PEBS-via-PT, perf script will not accept 'iregs' field e.g. # perf record -c 10000 -e '{intel_pt/branch=0/,branch-loads/aux-output/ppp}' -I -- ls -l ... [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data ] # ./perf script --itrace=eop -F+iregs Samples for 'dummy:u' event do not have IREGS attribute set. Cannot print 'iregs' field. Fix by using allow_user_set, which is true when recording AUX area data. Fixes: 9e64cefe4335b ("perf intel-pt: Process options for PEBS event synthesis") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Luwei Kang <luwei.kang@intel.com> Link: http://lore.kernel.org/lkml/20200630133935.11150-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-06perf intel-pt: Fix recording PEBS-via-PT with registersAdrian Hunter
When recording PEBS-via-PT, the kernel will not accept the intel_pt event with register sampling e.g. # perf record --kcore -c 10000 -e '{intel_pt/branch=0/,branch-loads/aux-output/ppp}' -I -- ls -l Error: intel_pt/branch=0/: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat' Fix by suppressing register sampling on the intel_pt evsel. Committer notes: Adrian informed that this is only available from Tremont onwards, so on older processors the error continues the same as before. Fixes: 9e64cefe4335b ("perf intel-pt: Process options for PEBS event synthesis") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Luwei Kang <luwei.kang@intel.com> Link: http://lore.kernel.org/lkml/20200630133935.11150-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-06perf report TUI: Fix segmentation fault in perf_evsel__hists_browse()Wei Li
The segmentation fault can be reproduced as following steps: 1) Executing perf report in tui. 2) Typing '/xxxxx' to filter the symbol to get nothing matched. 3) Pressing enter with no entry selected. Then it will report a segmentation fault. It is caused by the lack of check of browser->he_selection when accessing it's member res_samples in perf_evsel__hists_browse(). These processes are meaningful for specified samples, so we can skip these when nothing is selected. Fixes: 4968ac8fb7c3 ("perf report: Implement browsing of individual samples") Signed-off-by: Wei Li <liwei391@huawei.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Link: http://lore.kernel.org/lkml/20200612094322.39565-1-liwei391@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-03perf scripts python: exported-sql-viewer.py: Fix time chart call treeAdrian Hunter
Using Python version 3.8.2 and PySide2 version 5.14.0, time chart call tree would not expand the tree to the result. Fix by using setExpanded(). Example: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py perf.data.db branches calls 2020-06-26 15:32:14.928997 Creating database ... 2020-06-26 15:32:14.933971 Writing records... 2020-06-26 15:32:15.535251 Adding indexes 2020-06-26 15:32:15.542993 Dropping unused tables 2020-06-26 15:32:15.549716 Done $ python3 ~/libexec/perf-core/scripts/python/exported-sql-viewer.py perf.data.db Select: Charts -> Time chart by CPU Move mouse over middle of chart Right-click and select Show Call Tree Before: displays Call Tree but not expanded to selected time After: displays Call Tree expanded to selected time Fixes: e69d5df75d74d ("perf scripts python: exported-sql-viewer.py: Add ability for Call tree to open at a specified task and time") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-7-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-03perf scripts python: exported-sql-viewer.py: Fix zero id in call tree 'Find' ↵Adrian Hunter
result Using ctrl-F ('Find') would not find 'unknown' because it matches id zero. Fix by excluding id zero from selection. Example: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py perf.data.db branches calls 2020-06-26 15:32:14.928997 Creating database ... 2020-06-26 15:32:14.933971 Writing records... 2020-06-26 15:32:15.535251 Adding indexes 2020-06-26 15:32:15.542993 Dropping unused tables 2020-06-26 15:32:15.549716 Done $ python3 ~/libexec/perf-core/scripts/python/exported-sql-viewer.py perf.data.db Select: Reports -> Call Tree Press: Ctrl-F Enter: unknown Press: Enter Before: displays 'unknown' not found After: tree is expanded to line showing 'unknown' Fixes: ae8b887c00d3f ("perf scripts python: exported-sql-viewer.py: Add call tree") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-6-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-03perf scripts python: exported-sql-viewer.py: Fix zero id in call graph ↵Adrian Hunter
'Find' result Using ctrl-F ('Find') would not find 'unknown' because it matches id zero. Fix by excluding id zero from selection. Example: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py perf.data.db branches calls 2020-06-26 15:32:14.928997 Creating database ... 2020-06-26 15:32:14.933971 Writing records... 2020-06-26 15:32:15.535251 Adding indexes 2020-06-26 15:32:15.542993 Dropping unused tables 2020-06-26 15:32:15.549716 Done $ python3 ~/libexec/perf-core/scripts/python/exported-sql-viewer.py perf.data.db Select: Reports -> Context-Sensitive Call Graph Press: Ctrl-F Enter: unknown Press: Enter Before: gets stuck After: tree is expanded to line showing 'unknown' Fixes: 254c0d820b86d ("perf scripts python: exported-sql-viewer.py: Factor out CallGraphModelBase") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-03perf scripts python: exported-sql-viewer.py: Fix unexpanded 'Find' resultAdrian Hunter
Using Python version 3.8.2 and PySide2 version 5.14.0, ctrl-F ('Find') would not expand the tree to the result. Fix by using setExpanded(). Example: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.034 MB perf.data ] $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py perf.data.db branches calls 2020-06-26 15:32:14.928997 Creating database ... 2020-06-26 15:32:14.933971 Writing records... 2020-06-26 15:32:15.535251 Adding indexes 2020-06-26 15:32:15.542993 Dropping unused tables 2020-06-26 15:32:15.549716 Done $ python3 ~/libexec/perf-core/scripts/python/exported-sql-viewer.py perf.data.db Select: Reports -> Context-Sensitive Call Graph or Reports -> Call Tree Press: Ctrl-F Enter: main Press: Enter Before: line showing 'main' does not display After: tree is expanded to line showing 'main' Fixes: ebd70c7dc2f5f ("perf scripts python: exported-sql-viewer.py: Add ability to find symbols in the call-graph") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-03perf record: Fix duplicated sideband events with Intel PT system wide tracingAdrian Hunter
Commit 0a892c1c9472 ("perf record: Add dummy event during system wide synthesis") reveals an issue with Intel PT system wide tracing. Specifically that Intel PT already adds a dummy tracking event, and it is not the first event. Adding another dummy tracking event causes duplicated sideband events. Fix by checking for an existing dummy tracking event first. Example showing duplicated switch events: Before: # perf record -a -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.895 MB perf.data ] # perf script --no-itrace --show-switch-events | head swapper 0 [007] 6390.516222: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 swapper 0 [007] 6390.516222: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [007] 6390.516223: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [007] 6390.516224: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [007] 6390.516227: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 rcu_sched 11 [007] 6390.516227: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [007] 6390.516228: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [007] 6390.516228: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [002] 6390.516415: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 5556/5559 swapper 0 [002] 6390.516416: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 5556/5559 After: # perf record -a -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.868 MB perf.data ] # perf script --no-itrace --show-switch-events | head swapper 0 [005] 6450.567013: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 7179/7181 perf 7181 [005] 6450.567014: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 perf 7181 [005] 6450.567028: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [005] 6450.567029: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 7179/7181 swapper 0 [005] 6450.571699: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [005] 6450.571700: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 rcu_sched 11 [005] 6450.571702: PERF_RECORD_SWITCH_CPU_WIDE OUT next pid/tid: 0/0 swapper 0 [005] 6450.571703: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 11/11 swapper 0 [005] 6450.579703: PERF_RECORD_SWITCH_CPU_WIDE OUT preempt next pid/tid: 11/11 rcu_sched 11 [005] 6450.579704: PERF_RECORD_SWITCH_CPU_WIDE IN prev pid/tid: 0/0 Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lore.kernel.org/lkml/20200629091955.17090-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-07-03perf scripts python: export-to-postgresql.py: Fix struct.pack() int argumentAdrian Hunter
Python 3.8 is requiring that arguments being packed as integers are also integers. Add int() accordingly. Before: $ perf record -e intel_pt//u uname $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-postgresql.py perf_data_db branches calls 2020-06-25 16:09:10.547256 Creating database... 2020-06-25 16:09:10.733185 Writing to intermediate files... Traceback (most recent call last): File "/home/ahunter/libexec/perf-core/scripts/python/export-to-postgresql.py", line 1106, in synth_data cbr(id, raw_buf) File "/home/ahunter/libexec/perf-core/scripts/python/export-to-postgresql.py", line 1058, in cbr value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent) struct.error: required argument is not an integer Fatal Python error: problem in Python trace event handler Python runtime state: initialized Current thread 0x00007f35d3695780 (most recent call first): <no Python frame> Aborted (core dumped) After: $ dropdb perf_data_db $ rm -rf perf_data_db-perf-data $ perf script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-postgresql.py perf_data_db branches calls 2020-06-25 16:09:40.990267 Creating database... 2020-06-25 16:09:41.207009 Writing to intermediate files... 2020-06-25 16:09:41.270915 Copying to database... 2020-06-25 16:09:41.382030 Removing intermediate files... 2020-06-25 16:09:41.384630 Adding primary keys 2020-06-25 16:09:41.541894 Adding foreign keys 2020-06-25 16:09:41.677044 Dropping unused tables 2020-06-25 16:09:41.703761 Done Fixes: aba44287a224 ("perf scripts python: export-to-postgresql.py: Export Intel PT power and ptwrite events") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200629091955.17090-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-22perf flamegraph: Explicitly set utf-8 encodingAndreas Gerstmayr
On some platforms the default encoding is not utf-8, which causes an UnicodeDecodeError when reading the flamegraph template and writing the flamegraph Signed-off-by: Andreas Gerstmayr <agerstmayr@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200619153232.203537-1-agerstmayr@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-18perf build: Fix error message when asking for -fsanitize=address without ↵Tiezhu Yang
required libraries When build perf with ASan or UBSan, if libasan or libubsan can not find, the feature-glibc is 0 and there exists the following error log which is wrong, because we can find gnu/libc-version.h in /usr/include, glibc-devel is also installed. [yangtiezhu@linux perf]$ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=address' BUILD: Doing 'make -j4' parallel build HOSTCC fixdep.o HOSTLD fixdep-in.o LINK fixdep <stdin>:1:0: warning: -fsanitize=address and -fsanitize=kernel-address are not supported for this target <stdin>:1:0: warning: -fsanitize=address not supported for this target Auto-detecting system features: ... dwarf: [ OFF ] ... dwarf_getlocations: [ OFF ] ... glibc: [ OFF ] ... gtk2: [ OFF ] ... libaudit: [ OFF ] ... libbfd: [ OFF ] ... libcap: [ OFF ] ... libelf: [ OFF ] ... libnuma: [ OFF ] ... numa_num_possible_cpus: [ OFF ] ... libperl: [ OFF ] ... libpython: [ OFF ] ... libcrypto: [ OFF ] ... libunwind: [ OFF ] ... libdw-dwarf-unwind: [ OFF ] ... zlib: [ OFF ] ... lzma: [ OFF ] ... get_cpuid: [ OFF ] ... bpf: [ OFF ] ... libaio: [ OFF ] ... libzstd: [ OFF ] ... disassembler-four-args: [ OFF ] Makefile.config:393: *** No gnu/libc-version.h found, please install glibc-dev[el]. Stop. Makefile.perf:224: recipe for target 'sub-make' failed make[1]: *** [sub-make] Error 2 Makefile:69: recipe for target 'all' failed make: *** [all] Error 2 [yangtiezhu@linux perf]$ ls /usr/include/gnu/libc-version.h /usr/include/gnu/libc-version.h After install libasan and libubsan, the feature-glibc is 1 and the build process is success, so the cause is related with libasan or libubsan, we should check them and print an error log to reflect the reality. Committer testing: $ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=address' O=/tmp/build/perf -C tools/perf/ install-bin make: Entering directory '/home/acme/git/perf/tools/perf' BUILD: Doing 'make -j12' parallel build HOSTCC /tmp/build/perf/fixdep.o HOSTLD /tmp/build/perf/fixdep-in.o LINK /tmp/build/perf/fixdep Auto-detecting system features: ... dwarf: [ OFF ] ... dwarf_getlocations: [ OFF ] ... glibc: [ OFF ] ... gtk2: [ OFF ] ... libbfd: [ OFF ] ... libcap: [ OFF ] ... libelf: [ OFF ] ... libnuma: [ OFF ] ... numa_num_possible_cpus: [ OFF ] ... libperl: [ OFF ] ... libpython: [ OFF ] ... libcrypto: [ OFF ] ... libunwind: [ OFF ] ... libdw-dwarf-unwind: [ OFF ] ... zlib: [ OFF ] ... lzma: [ OFF ] ... get_cpuid: [ OFF ] ... bpf: [ OFF ] ... libaio: [ OFF ] ... libzstd: [ OFF ] ... disassembler-four-args: [ OFF ] Makefile.config:401: *** No libasan found, please install libasan. Stop. make[1]: *** [Makefile.perf:231: sub-make] Error 2 make: *** [Makefile:70: all] Error 2 make: Leaving directory '/home/acme/git/perf/tools/perf' $ $ $ sudo dnf install libasan <SNIP> Installed: libasan-9.3.1-2.fc31.x86_64 $ $ $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=address' O=/tmp/build/perf -C tools/perf/ install-bin make: Entering directory '/home/acme/git/perf/tools/perf' BUILD: Doing 'make -j12' parallel build Auto-detecting system features: ... dwarf: [ on ] ... dwarf_getlocations: [ on ] ... glibc: [ on ] ... gtk2: [ on ] ... libbfd: [ on ] ... libcap: [ on ] ... libelf: [ on ] ... libnuma: [ on ] ... numa_num_possible_cpus: [ on ] ... libperl: [ on ] ... libpython: [ on ] ... libcrypto: [ on ] ... libunwind: [ on ] ... libdw-dwarf-unwind: [ on ] ... zlib: [ on ] ... lzma: [ on ] ... get_cpuid: [ on ] ... bpf: [ on ] ... libaio: [ on ] ... libzstd: [ on ] ... disassembler-four-args: [ on ] <SNIP> CC /tmp/build/perf/util/pmu-flex.o FLEX /tmp/build/perf/util/expr-flex.c CC /tmp/build/perf/util/expr-bison.o CC /tmp/build/perf/util/expr.o CC /tmp/build/perf/util/expr-flex.o CC /tmp/build/perf/util/parse-events-flex.o CC /tmp/build/perf/util/parse-events.o LD /tmp/build/perf/util/intel-pt-decoder/perf-in.o LD /tmp/build/perf/util/perf-in.o LD /tmp/build/perf/perf-in.o LINK /tmp/build/perf/perf <SNIP> INSTALL python-scripts INSTALL perf_completion-script INSTALL perf-tip make: Leaving directory '/home/acme/git/perf/tools/perf' $ ldd ~/bin/perf | grep asan libasan.so.5 => /lib64/libasan.so.5 (0x00007f0904164000) $ And if we rebuild without -fsanitize-address: $ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf $ make O=/tmp/build/perf -C tools/perf/ install-bin make: Entering directory '/home/acme/git/perf/tools/perf' BUILD: Doing 'make -j12' parallel build HOSTCC /tmp/build/perf/fixdep.o HOSTLD /tmp/build/perf/fixdep-in.o LINK /tmp/build/perf/fixdep Auto-detecting system features: ... dwarf: [ on ] ... dwarf_getlocations: [ on ] ... glibc: [ on ] ... gtk2: [ on ] ... libbfd: [ on ] ... libcap: [ on ] ... libelf: [ on ] ... libnuma: [ on ] ... numa_num_possible_cpus: [ on ] ... libperl: [ on ] ... libpython: [ on ] ... libcrypto: [ on ] ... libunwind: [ on ] ... libdw-dwarf-unwind: [ on ] ... zlib: [ on ] ... lzma: [ on ] ... get_cpuid: [ on ] ... bpf: [ on ] ... libaio: [ on ] ... libzstd: [ on ] ... disassembler-four-args: [ on ] GEN /tmp/build/perf/common-cmds.h CC /tmp/build/perf/exec-cmd.o <SNIP> INSTALL perf_completion-script INSTALL perf-tip make: Leaving directory '/home/acme/git/perf/tools/perf' $ ldd ~/bin/perf | grep asan $ Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn> Acked-by: Jiri Olsa <jolsa@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: tiezhu yang <yangtiezhu@loongson.cn> Cc: xuefeng li <lixuefeng@loongson.cn> Link: http://lore.kernel.org/lkml/1592445961-28044-1-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-17perf script: Initialize zstd_dataMilian Wolff
Fixes segmentation fault when trying to interpret zstd-compressed data with perf script: ``` $ perf record -z ls ... [ perf record: Captured and wrote 0,010 MB perf.data, compressed (original 0,001 MB, ratio is 2,190) ] $ memcheck perf script ... ==67911== Invalid read of size 4 ==67911== at 0x5568188: ZSTD_decompressStream (in /usr/lib/libzstd.so.1.4.5) ==67911== by 0x6E726B: zstd_decompress_stream (zstd.c:100) ==67911== by 0x65729C: perf_session__process_compressed_event (session.c:72) ==67911== by 0x6598E8: perf_session__process_user_event (session.c:1583) ==67911== by 0x65BA59: reader__process_events (session.c:2177) ==67911== by 0x65BA59: __perf_session__process_events (session.c:2234) ==67911== by 0x65BA59: perf_session__process_events (session.c:2267) ==67911== by 0x5A7397: __cmd_script (builtin-script.c:2447) ==67911== by 0x5A7397: cmd_script (builtin-script.c:3840) ==67911== by 0x5FE9D2: run_builtin (perf.c:312) ==67911== by 0x711627: handle_internal_command (perf.c:364) ==67911== by 0x711627: run_argv (perf.c:408) ==67911== by 0x711627: main (perf.c:538) ==67911== Address 0x71d8 is not stack'd, malloc'd or (recently) free'd ``` Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Acked-by: Alexey Budankov <alexey.budankov@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> LPU-Reference: 20200612230333.72140-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-10perf pmu: Remove unused declarationIan Rogers
This avoids multiple declarations if the flex header is included. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Garry <john.garry@huawei.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200609234344.3795-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-09perf parse-events: Fix an old style declarationIan Rogers
Fixes: a26e47162d76 (perf tools: Move ALLOC_LIST into a function) Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200609053610.206588-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-09perf parse-events: Fix an incompatible pointerIan Rogers
Arrays are pointer types and don't need their address taking. Fixes: 8255718f4bed (perf pmu: Expand PMU events by prefix match) Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200609053610.206588-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-09perf bpf: Fix bpf prologue generationSumanth Korikkar
Issue: bpf_probe_read() is no longer available for architecture which has overlapping address space. Hence bpf prologue generation fails Fix: Use bpf_probe_read_kernel for kernel member access. For user attribute access in kprobes, use bpf_probe_read_user. Other: @user attribute was introduced in commit 1e032f7cfa14 ("perf-probe: Add user memory access attribute support") Test: 1. ulimit -l 128 ; ./perf record -e tests/bpf_sched_setscheduler.c 2. cat tests/bpf_sched_setscheduler.c static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = (void *) 6; static int (*bpf_probe_read_user)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 112; static int (*bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 113; SEC("func=do_sched_setscheduler pid policy param->sched_priority@user") int bpf_func__setscheduler(void *ctx, int err, pid_t pid, int policy, int param) { char fmt[] = "prio: %ld"; bpf_trace_printk(fmt, sizeof(fmt), param); return 1; } char _license[] SEC("license") = "GPL"; int _version SEC("version") = LINUX_VERSION_CODE; 3. ./perf script sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508) pid=261614 policy=2 sched_priority=1 4. cat /sys/kernel/debug/tracing/trace <...>-309956 [006] .... 1616098.093957: 0: prio: 1 Committer testing: I had to add some missing headers in the bpf_sched_setscheduler.c test proggie, then instead of using record+script I used 'perf trace' to drive everything in one go: # cat bpf_sched_setscheduler.c #include <linux/types.h> #include <bpf.h> static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = (void *) 6; static int (*bpf_probe_read_user)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 112; static int (*bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 113; SEC("func=do_sched_setscheduler pid policy param->sched_priority@user") int bpf_func__setscheduler(void *ctx, int err, pid_t pid, int policy, int param) { char fmt[] = "prio: %ld"; bpf_trace_printk(fmt, sizeof(fmt), param); return 1; } char _license[] SEC("license") = "GPL"; int _version SEC("version") = LINUX_VERSION_CODE; # # # perf trace -e bpf_sched_setscheduler.c chrt -f 42 sleep 1 0.000 chrt/80125 perf_bpf_probe:func(__probe_ip: -1676607808, policy: 1, sched_priority: 42) # And even with backtraces :-) # perf trace -e bpf_sched_setscheduler.c/max-stack=8/ chrt -f 42 sleep 1 0.000 chrt/79805 perf_bpf_probe:func(__probe_ip: -1676607808, policy: 1, sched_priority: 42) do_sched_setscheduler ([kernel.kallsyms]) __x64_sys_sched_setscheduler ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) entry_SYSCALL_64 ([kernel.kallsyms]) __GI___sched_setscheduler (/usr/lib64/libc-2.30.so) # Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com> Reviewed-by: Thomas Richter <tmricht@linux.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: bpf@vger.kernel.org LPU-Reference: 20200609081019.60234-3-sumanthk@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-09perf probe: Fix user attribute access in kprobesSumanth Korikkar
Issue: # perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user' did not work before. Fix: Make: # perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user' output equivalent to ftrace: # echo 'p:probe/do_sched_setscheduler _text+517384 pid=%r2:s32 policy=%r3:s32 sched_priority=+u0(%r4):s32' > /sys/kernel/debug/tracing/kprobe_events Other: 1. Right now, __match_glob() does not handle [u]<offset>. For now, use *u]<offset>. 2. @user attribute was introduced in commit 1e032f7cfa14 ("perf-probe: Add user memory access attribute support") Test: 1. perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user' 2 ./perf script sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508) pid=261614 policy=2 sched_priority=1 3. cat /sys/kernel/debug/tracing/trace <...>-309956 [006] .... 1616098.093957: 0: prio: 1 Committer testing: Before: # perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user' param(type:sched_param) has no member sched_priority@user. Error: Failed to add events. # pahole sched_param struct sched_param { int sched_priority; /* 0 4 */ /* size: 4, cachelines: 1, members: 1 */ /* last cacheline: 4 bytes */ }; # After: # perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user' Added new event: probe:do_sched_setscheduler (on do_sched_setscheduler with pid policy sched_priority=param->sched_priority) You can now use it in all perf tools, such as: perf record -e probe:do_sched_setscheduler -aR sleep 1 # cat /sys/kernel/debug/tracing/kprobe_events p:probe/do_sched_setscheduler _text+1113792 pid=%di:s32 policy=%si:s32 sched_priority=+u0(%dx):s32 # Fixes: 1e032f7cfa14 ("perf-probe: Add user memory access attribute support") Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com> Reviewed-by: Thomas Richter <tmricht@linux.ibm.com> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: bpf@vger.kernel.org LPU-Reference: 20200609081019.60234-2-sumanthk@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-09perf stat: Fix NULL pointer dereferenceHongbo Yao
If config->aggr_map is NULL and config->aggr_get_id is not NULL, the function print_aggr() will still calling arrg_update_shadow(), which can result in accessing the invalid pointer. Fixes: 088519f318be ("perf stat: Move the display functions to stat-display.c") Signed-off-by: Hongbo Yao <yaohongbo@huawei.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wei Li <liwei391@huawei.com> Link: https://lore.kernel.org/lkml/20200608163625.GC3073@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-09perf report: Fix NULL pointer dereference in hists__fprintf_nr_sample_events()Gaurav Singh
The 'evname' variable can be NULL, as it is checked a few lines back, check it before using. Fixes: 9e207ddfa207 ("perf report: Show call graph from reference events") Cc: Adrian Hunter <adrian.hunter@intel.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@intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/ Signed-off-by: Gaurav Singh <gaurav1086@gmail.com>
2020-06-09perf beauty: Add support to STATX_MNT_ID in the 'statx' syscall 'mask' argumentArnaldo Carvalho de Melo
Introduced in: fa2fcf4f1df1 ("statx: add mount ID") Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-09tools headers API: Update faccessat2 affected filesArnaldo Carvalho de Melo
Update the copies of files affected by: c8ffd8bcdd28 ("vfs: add faccessat2 syscall") To address this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/fcntl.h' differs from latest version at 'include/uapi/linux/fcntl.h' diff -u tools/include/uapi/linux/fcntl.h include/uapi/linux/fcntl.h Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Which results in 'perf trace' gaining support for the 'faccessat2' syscall, now one can use: # perf trace -e faccessat2 And have system wide tracing of this syscall. And this also will include it; # perf trace -e faccess* Together with the other variants. How it affects building/usage (on an x86_64 system): $ cp /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c /tmp/syscalls_64.c.before $ [root@five ~]# perf trace -e faccessat2 event syntax error: 'faccessat2' \___ parser error Run 'perf list' for a list of valid events Usage: perf trace [<options>] [<command>] or: perf trace [<options>] -- <command> [<options>] or: perf trace record [<options>] [<command>] or: perf trace record [<options>] -- <command> [<options>] -e, --event <event> event/syscall selector. use 'perf list' to list available events [root@five ~]# $ cp arch/x86/entry/syscalls/syscall_64.tbl tools/perf/arch/x86/entry/syscalls/syscall_64.tbl $ git diff diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 37b844f839bc..78847b32e137 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -359,6 +359,7 @@ 435 common clone3 sys_clone3 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 # # x32-specific system call numbers start at 512 to avoid cache impact $ $ make -C tools/perf O=/tmp/build/perf/ install-bin <SNIP> CC /tmp/build/perf/util/syscalltbl.o LD /tmp/build/perf/util/perf-in.o LD /tmp/build/perf/perf-in.o LINK /tmp/build/perf/perf <SNIP> [root@five ~]# perf trace -e faccessat2 ^C[root@five ~]# Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-02perf tools: Remove some duplicated includesTiezhu Yang
There exists some duplicated includes in tools/perf, remove them. Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: xuefeng li <lixuefeng@loongson.cn> Link: http://lore.kernel.org/lkml/1591071304-19338-2-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-02perf symbols: Fix kernel maps for kcore and eBPFAdrian Hunter
Adjust 'map->pgoff' also when moving a map's start address. Example with v5.4.34 based kernel: Before: $ sudo tools/perf/perf record -a --kcore -e intel_pt//k sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.958 MB perf.data ] $ sudo tools/perf/perf script --itrace=e >/dev/null Warning: 961 instruction trace errors After: $ sudo tools/perf/perf script --itrace=e >/dev/null $ Committer testing: # uname -a Linux seventh 5.6.10-100.fc30.x86_64 #1 SMP Mon May 4 15:36:44 UTC 2020 x86_64 x86_64 x86_64 GNU/Linux # Before: # perf record -a --kcore -e intel_pt//k sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.923 MB perf.data ] # perf script --itrace=e >/dev/null Warning: 295 instruction trace errors # After: # perf record -a --kcore -e intel_pt//k sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.919 MB perf.data ] # perf script --itrace=e >/dev/null # Fixes: fb5a88d4131a ("perf tools: Preserve eBPF maps when loading kcore") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200602112505.1406-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-02perf stat: Ensure group is defined on top of the same cpu maskJiri Olsa
Jin Yao reported the issue (and posted first versions of this change) with groups being defined over events with different cpu mask. This causes assert aborts in get_group_fd, like: # perf stat -M "C2_Pkg_Residency" -a -- sleep 1 perf: util/evsel.c:1464: get_group_fd: Assertion `!(fd == -1)' failed. Aborted All the events in the group have to be defined over the same cpus so the group_fd can be found for every leader/member pair. Adding check to ensure this condition is met and removing the group (with warning) if we detect mixed cpus, like: $ sudo perf stat -e '{power/energy-cores/,cycles},{instructions,power/energy-cores/}' WARNING: event cpu maps do not match, disabling group: anon group { power/energy-cores/, cycles } anon group { instructions, power/energy-cores/ } Ian asked also for cpu maps details, it's displayed in verbose mode: $ sudo perf stat -e '{cycles,power/energy-cores/}' -v WARNING: group events cpu maps do not match, disabling group: anon group { power/energy-cores/, cycles } power/energy-cores/: 0 cycles: 0-7 anon group { instructions, power/energy-cores/ } instructions: 0-7 power/energy-cores/: 0 Committer testing: [root@seventh ~]# perf stat -e '{power/energy-cores/,cycles},{instructions,power/energy-cores/}' WARNING: grouped events cpus do not match, disabling group: anon group { power/energy-cores/, cycles } anon group { instructions, power/energy-cores/ } ^C Performance counter stats for 'system wide': 12.62 Joules power/energy-cores/ 106,920,637 cycles 80,228,899 instructions # 0.75 insn per cycle 12.62 Joules power/energy-cores/ 14.514476987 seconds time elapsed [root@seventh ~]# But if we put compatible events in each group it works: [root@seventh ~]# perf stat -e '{power/energy-cores/,power/energy-ram/},{instructions,cycles}' -a sleep 2 Performance counter stats for 'system wide': 1.95 Joules power/energy-cores/ 0.92 Joules power/energy-ram/ 29,305,715 instructions # 1.03 insn per cycle 28,423,338 cycles 2.001438142 seconds time elapsed [root@seventh ~]# This needs improvement tho: [root@seventh ~]# perf stat -e '{power/energy-cores/,power/energy-ram/},{instructions,cycles}' sleep 2 Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (power/energy-cores/). /bin/dmesg | grep -i perf may provide additional information. [root@seventh ~]# We need to emit a better message, one stating that the power/ events can't be used for a specific workload, instead it is per-cpu or system wide. Fixes: 6a4bb04caacc8 ("perf tools: Enable grouping logic for parsed events") Co-developed-by: Jin Yao <yao.jin@linux.intel.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200602101736.GE1112120@krava Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-01perf libdw: Fix off-by 1 relative directory includesIan Rogers
This is currently working due to extra include paths in the build. Before: $ cd tools/perf/arch/arm64/util $ ls -la ../../util/unwind-libdw.h ls: cannot access '../../util/unwind-libdw.h': No such file or directory After: $ ls -la ../../../util/unwind-libdw.h -rw-r----- 1 irogers irogers 553 Apr 17 14:31 ../../../util/unwind-libdw.h Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200529225232.207532-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-01perf arm-spe: Support synthetic eventsTan Xiaojun
After the commit ffd3d18c20b8 ("perf tools: Add ARM Statistical Profiling Extensions (SPE) support") has been merged, it supports to output raw data with option "--dump-raw-trace". However, it misses for support synthetic events so cannot output any statistical info. This patch is to improve the "perf report" support for ARM SPE for four types synthetic events: First level cache synthetic events, including L1 data cache accessing and missing events; Last level cache synthetic events, including last level cache accessing and missing events; TLB synthetic events, including TLB accessing and missing events; Remote access events, which is used to account load/store operations caused to another socket. Example usage: $ perf record -c 1024 -e arm_spe_0/branch_filter=1,ts_enable=1,pct_enable=1,pa_enable=1,load_filter=1,jitter=1,store_filter=1,min_latency=0/ dd if=/dev/zero of=/dev/null count=10000 $ perf report --stdio # Samples: 59 of event 'l1d-miss' # Event count (approx.): 59 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................. .................................. # 23.73% 23.73% dd [kernel.kallsyms] [k] perf_iterate_ctx.constprop.135 20.34% 20.34% dd [kernel.kallsyms] [k] filemap_map_pages 5.08% 5.08% dd [kernel.kallsyms] [k] perf_event_mmap 5.08% 5.08% dd [kernel.kallsyms] [k] unlock_page_memcg 5.08% 5.08% dd [kernel.kallsyms] [k] unmap_page_range 3.39% 3.39% dd [kernel.kallsyms] [k] PageHuge 3.39% 3.39% dd [kernel.kallsyms] [k] release_pages 3.39% 3.39% dd ld-2.28.so [.] 0x0000000000008b5c 1.69% 1.69% dd [kernel.kallsyms] [k] __alloc_fd [...] # Samples: 3K of event 'l1d-access' # Event count (approx.): 3980 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................. ...................................... # 26.98% 26.98% dd [kernel.kallsyms] [k] ret_to_user 10.53% 10.53% dd [kernel.kallsyms] [k] fsnotify 7.51% 7.51% dd [kernel.kallsyms] [k] new_sync_read 4.57% 4.57% dd [kernel.kallsyms] [k] vfs_read 4.35% 4.35% dd [kernel.kallsyms] [k] vfs_write 3.69% 3.69% dd [kernel.kallsyms] [k] __fget_light 3.69% 3.69% dd [kernel.kallsyms] [k] rw_verify_area 3.44% 3.44% dd [kernel.kallsyms] [k] security_file_permission 2.76% 2.76% dd [kernel.kallsyms] [k] __fsnotify_parent 2.44% 2.44% dd [kernel.kallsyms] [k] ksys_write 2.24% 2.24% dd [kernel.kallsyms] [k] iov_iter_zero 2.19% 2.19% dd [kernel.kallsyms] [k] read_iter_zero 1.81% 1.81% dd dd [.] 0x0000000000002960 1.78% 1.78% dd dd [.] 0x0000000000002980 [...] # Samples: 35 of event 'llc-miss' # Event count (approx.): 35 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................. ........................... # 34.29% 34.29% dd [kernel.kallsyms] [k] filemap_map_pages 8.57% 8.57% dd [kernel.kallsyms] [k] unlock_page_memcg 8.57% 8.57% dd [kernel.kallsyms] [k] unmap_page_range 5.71% 5.71% dd [kernel.kallsyms] [k] PageHuge 5.71% 5.71% dd [kernel.kallsyms] [k] release_pages 5.71% 5.71% dd ld-2.28.so [.] 0x0000000000008b5c 2.86% 2.86% dd [kernel.kallsyms] [k] __queue_work 2.86% 2.86% dd [kernel.kallsyms] [k] __radix_tree_lookup 2.86% 2.86% dd [kernel.kallsyms] [k] copy_page [...] # Samples: 2 of event 'llc-access' # Event count (approx.): 2 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................. ............. # 50.00% 50.00% dd [kernel.kallsyms] [k] copy_page 50.00% 50.00% dd libc-2.28.so [.] _dl_addr # Samples: 48 of event 'tlb-miss' # Event count (approx.): 48 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................. .................................. # 20.83% 20.83% dd [kernel.kallsyms] [k] perf_iterate_ctx.constprop.135 12.50% 12.50% dd [kernel.kallsyms] [k] __arch_clear_user 10.42% 10.42% dd [kernel.kallsyms] [k] clear_page 4.17% 4.17% dd [kernel.kallsyms] [k] copy_page 4.17% 4.17% dd [kernel.kallsyms] [k] filemap_map_pages 2.08% 2.08% dd [kernel.kallsyms] [k] __alloc_fd 2.08% 2.08% dd [kernel.kallsyms] [k] __mod_memcg_state.part.70 2.08% 2.08% dd [kernel.kallsyms] [k] __queue_work 2.08% 2.08% dd [kernel.kallsyms] [k] __rcu_read_unlock 2.08% 2.08% dd [kernel.kallsyms] [k] d_path 2.08% 2.08% dd [kernel.kallsyms] [k] destroy_inode 2.08% 2.08% dd [kernel.kallsyms] [k] do_dentry_open [...] # Samples: 9K of event 'tlb-access' # Event count (approx.): 9573 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................. ...................................... # 25.79% 25.79% dd [kernel.kallsyms] [k] __arch_clear_user 11.22% 11.22% dd [kernel.kallsyms] [k] ret_to_user 8.56% 8.56% dd [kernel.kallsyms] [k] fsnotify 4.06% 4.06% dd [kernel.kallsyms] [k] new_sync_read 3.67% 3.67% dd [kernel.kallsyms] [k] el0_svc_common.constprop.2 3.04% 3.04% dd [kernel.kallsyms] [k] __fsnotify_parent 2.90% 2.90% dd [kernel.kallsyms] [k] vfs_write 2.82% 2.82% dd [kernel.kallsyms] [k] vfs_read 2.52% 2.52% dd libc-2.28.so [.] write 2.26% 2.26% dd [kernel.kallsyms] [k] security_file_permission 2.08% 2.08% dd [kernel.kallsyms] [k] ksys_write 1.96% 1.96% dd [kernel.kallsyms] [k] rw_verify_area 1.95% 1.95% dd [kernel.kallsyms] [k] read_iter_zero [...] # Samples: 9 of event 'branch-miss' # Event count (approx.): 9 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................. ......................... # 22.22% 22.22% dd libc-2.28.so [.] _dl_addr 11.11% 11.11% dd [kernel.kallsyms] [k] __arch_clear_user 11.11% 11.11% dd [kernel.kallsyms] [k] __arch_copy_from_user 11.11% 11.11% dd [kernel.kallsyms] [k] __dentry_kill 11.11% 11.11% dd [kernel.kallsyms] [k] __efistub_memcpy 11.11% 11.11% dd ld-2.28.so [.] 0x0000000000012b7c 11.11% 11.11% dd libc-2.28.so [.] 0x000000000002a980 11.11% 11.11% dd libc-2.28.so [.] 0x0000000000083340 # Samples: 29 of event 'remote-access' # Event count (approx.): 29 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................. ........................... # 41.38% 41.38% dd [kernel.kallsyms] [k] filemap_map_pages 10.34% 10.34% dd [kernel.kallsyms] [k] unlock_page_memcg 10.34% 10.34% dd [kernel.kallsyms] [k] unmap_page_range 6.90% 6.90% dd [kernel.kallsyms] [k] release_pages 3.45% 3.45% dd [kernel.kallsyms] [k] PageHuge 3.45% 3.45% dd [kernel.kallsyms] [k] __queue_work 3.45% 3.45% dd [kernel.kallsyms] [k] page_add_file_rmap 3.45% 3.45% dd [kernel.kallsyms] [k] page_counter_try_charge 3.45% 3.45% dd [kernel.kallsyms] [k] page_remove_rmap 3.45% 3.45% dd [kernel.kallsyms] [k] xas_start 3.45% 3.45% dd ld-2.28.so [.] 0x0000000000002a1c 3.45% 3.45% dd ld-2.28.so [.] 0x0000000000008b5c 3.45% 3.45% dd ld-2.28.so [.] 0x00000000000093cc Signed-off-by: Tan Xiaojun <tanxiaojun@huawei.com> Tested-by: James Clark <james.clark@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Grant <al.grant@arm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Cc: linux-arm-kernel@lists.infradead.org Link: http://lore.kernel.org/lkml/20200530122442.490-4-leo.yan@linaro.org Signed-off-by: James Clark <james.clark@arm.com> Signed-off-by: Leo Yan <leo.yan@linaro.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-01perf auxtrace: Add four itrace optionsTan Xiaojun
This patch is to add four options to synthesize events which are described as below: 'f': synthesize first level cache events 'm': synthesize last level cache events 't': synthesize TLB events 'a': synthesize remote access events This four options will be used by ARM SPE as their first consumer. Signed-off-by: Tan Xiaojun <tanxiaojun@huawei.com> Tested-by: James Clark <james.clark@arm.com> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Grant <al.grant@arm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Cc: linux-arm-kernel@lists.infradead.org Link: http://lore.kernel.org/lkml/20200530122442.490-3-leo.yan@linaro.org Signed-off-by: James Clark <james.clark@arm.com> Signed-off-by: Leo Yan <leo.yan@linaro.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-01perf tools: Move arm-spe-pkt-decoder.h/c to the new dirTan Xiaojun
Create a new arm-spe-decoder directory for subsequent extensions and move arm-spe-pkt-decoder.h/c to this directory. No code changes. Signed-off-by: Tan Xiaojun <tanxiaojun@huawei.com> Tested-by: James Clark <james.clark@arm.com> Tested-by: Qi Liu <liuqi115@hisilicon.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Grant <al.grant@arm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Cc: linux-arm-kernel@lists.infradead.org Link: http://lore.kernel.org/lkml/20200530122442.490-2-leo.yan@linaro.org Signed-off-by: James Clark <james.clark@arm.com> Signed-off-by: Leo Yan <leo.yan@linaro.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-01perf test: Initialize memory in dwarf-unwindIan Rogers
Avoid a false positive caused by assembly code in arch/x86. In tests, zero the perf_event to avoid uninitialized memory uses. Warnings were caught using clang with -fsanitize=memory. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Quentin Monnet <quentin@isovalent.com> Cc: Stephane Eranian <eranian@google.com> Cc: clang-built-linux@googlegroups.com Link: http://lore.kernel.org/lkml/20200530082015.39162-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-06-01perf tests: Don't tail call optimize in unwind testIan Rogers
The tail call optimization can unexpectedly make the stack smaller and cause the test to fail. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: clang-built-linux@googlegroups.com Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Quentin Monnet <quentin@isovalent.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200530082015.39162-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-29perf build: Add a LIBPFM4=1 build test entryArnaldo Carvalho de Melo
So that when one runs: $ make -C tools/perf build-test We make sure that recent changes don't break that opt-in build. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Florian Fainelli <f.fainelli@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Ian Rogers <irogers@google.com> Cc: Igor Lubashev <ilubashe@akamai.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiwei Sun <jiwei.sun@windriver.com> Cc: John Garry <john.garry@huawei.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yonghong Song <yhs@fb.com> Cc: yuzhoujian <yuzhoujian@didichuxing.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-29perf tools: Add optional support for libpfm4Stephane Eranian
This patch links perf with the libpfm4 library if it is available and LIBPFM4 is passed to the build. The libpfm4 library contains hardware event tables for all processors supported by perf_events. It is a helper library that helps convert from a symbolic event name to the event encoding required by the underlying kernel interface. This library is open-source and available from: http://perfmon2.sf.net. With this patch, it is possible to specify full hardware events by name. Hardware filters are also supported. Events must be specified via the --pfm-events and not -e option. Both options are active at the same time and it is possible to mix and match: $ perf stat --pfm-events inst_retired:any_p:c=1:i -e cycles .... One needs to explicitely ask for its inclusion by using the LIBPFM4 make command line option, ie its opt-in rather than opt-out of feature detection and build support. Signed-off-by: Stephane Eranian <eranian@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Florian Fainelli <f.fainelli@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Igor Lubashev <ilubashe@akamai.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiwei Sun <jiwei.sun@windriver.com> Cc: John Garry <john.garry@huawei.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Cc: yuzhoujian <yuzhoujian@didichuxing.com> Link: http://lore.kernel.org/lkml/20200505182943.218248-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-29perf tools: Correct license on jsmn JSON parserEd Maste
This header is part of the jsmn JSON parser, introduced in 867a979a83. Correct the SPDX tag to indicate that it is under the MIT license. Signed-off-by: Ed Maste <emaste@freebsd.org> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Link: http://lore.kernel.org/lkml/20200528170858.48457-1-emaste@freefall.freebsd.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-29perf jit: Fix inaccurate DWARF line tableNick Gasson
Fix an issue where addresses in the DWARF line table are offset by -0x40 (GEN_ELF_TEXT_OFFSET). This can be seen with `objdump -S` on the ELF files after perf inject. Committer notes: Ian added this in his Acked-by reply: --- Without too much knowledge this looks good to me. The original code came from oprofile's jit support: https://sourceforge.net/p/oprofile/oprofile/ci/master/tree/opjitconv/debug_line.c#l325 --- Signed-off-by: Nick Gasson <nick.gasson@arm.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200528051916.6722-1-nick.gasson@arm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-29perf jvmti: Remove redundant jitdump line table entriesNick Gasson
For each PC/BCI pair in the JVMTI compiler inlining record table, the jitdump plugin emits debug line table entries for every source line in the method preceding that BCI. Instead only emit one source line per PC/BCI pair. Reported by Ian Rogers. This reduces the .dump size for SPECjbb from ~230MB to ~40MB. Signed-off-by: Nick Gasson <nick.gasson@arm.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20200528054049.13662-1-nick.gasson@arm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-29perf build: Add NO_SDT=1 to the default set of build testsArnaldo Carvalho de Melo
We forgot to add it, so one would have to explicitely ask for it to be run, fix that by adding it to the set of tests that are performed by default when one does: $ make -C tools/perf build-test It was being exercised only in the make_minimal test, this patch makes it be tested in isolation, i.e. disabling only this feature. Fixes: e26e63be64a1 ("perf build: Add sdt feature detection") Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
generated by cgit v1.2.3 (git 2.39.1) at 2025-08-06 10:18:23 +0000