summaryrefslogtreecommitdiff
path: root/tools/perf
AgeCommit message (Collapse)Author
2024-11-08perf build: Include libtraceevent headers directly indicated by pkg-configYicong Yang
Currently the libtraceevent's found by pkg-config, which give the include path as: [root@localhost tmp]# pkg-config --cflags libtraceevent -I/usr/local/include/traceevent So we should include the libtraceevent headers directly without "traceevent/" prefix. Update all the users. Fixes: 0f0e1f445690 ("perf build: Use pkg-config for feature check for libtrace{event,fs}") Suggested-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/linux-perf-users/ZyF5_Hf1iL01kldE@google.com/ Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: leo.yan@arm.com Cc: amadio@gentoo.org Cc: linuxarm@huawei.com Link: https://lore.kernel.org/r/20241105105649.45399-1-yangyicong@huawei.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-08perf script python: Adjust objdump start/end per map pgoff parameterSteve Clevenger
Extract map_pgoff parameter from the dictionary, and adjust start/end range passed to objdump based on the value. A zero start_addr is filtered to prevent output of dso address range check failures. This script repeatedly sees a zero value passed in for       start_addr = cpu_data[str(cpu) + 'addr'] These zero values are not a new problem. The start_addr/stop_addr warning clutters the instruction trace output, hence this change. Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com> Reviewed-by: Leo Yan <leo.yan@arm.com> Cc: suzuki.poulose@arm.com Cc: james.clark@linaro.org Cc: mike.leach@linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: coresight@lists.linaro.org Cc: ilkka@os.amperecomputing.com Link: https://lore.kernel.org/r/21ccdd22e664bdeccb878672d4b2c0518873c1e5.1731027120.git.scclevenger@os.amperecomputing.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-08perf script cs_etm: Add map_pgoff to python dictionarySteve Clevenger
Extract map_pgoff parameter from the dictionary, and adjust start/end range passed to objdump based on the value. A zero start_addr is filtered to prevent output of dso address range check failures. This script repeatedly sees a zero value passed in for       start_addr = cpu_data[str(cpu) + 'addr'] These zero values are not a new problem. The start_addr/stop_addr warning clutters the instruction trace output, hence this change. Signed-off-by: Steve Clevenger <scclevenger@os.amperecomputing.com> Reviewed-by: Leo Yan <leo.yan@arm.com> Cc: suzuki.poulose@arm.com Cc: james.clark@linaro.org Cc: mike.leach@linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: coresight@lists.linaro.org Cc: ilkka@os.amperecomputing.com Link: https://lore.kernel.org/r/8d9a1142dc58ffa34a000cb7b7a26055df0a37ec.1731027120.git.scclevenger@os.amperecomputing.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-07perf stat: Expand metric+unit buffer sizeIan Rogers
Long metric names combined with units may exceed the metric_bf and lead to truncation. Double metric_bf in size to avoid this. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Kan Liang <kan.liang@linux.intel.com> Link: https://lore.kernel.org/r/20241106004818.2174593-1-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-07perf tools: Add the empty-pmu-events build to .gitignoreHaiyue Wang
The commit 0fe881f10ceb ("perf jevents: Autogenerate empty-pmu-events.c") build will generate two files, add them to .gitignore: tools/perf/pmu-events/empty-pmu-events.log tools/perf/pmu-events/test-empty-pmu-events.c Signed-off-by: Haiyue Wang <haiyuewa@163.com> Reviewed-by: Ian Rogers <irogers@google.com> Link: https://lore.kernel.org/r/20241106121254.2869-1-haiyuewa@163.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-07perf: event: Remove deadcodeDr. David Alan Gilbert
event_format__print() last use was removed by 2017's commit 894f3f1732cb ("perf script: Use event_format__fprintf()") evlist__find_tracepoint_by_id() last use was removed by 2012's commit e60fc847cefa ("perf evlist: Remove some unused methods") evlist__set_tp_filter_pid() last use was removed by 2017's commit dd1a50377c92 ("perf trace: Introduce filter_loop_pids()") Remove them. Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org> Reviewed-by: Ian Rogers <irogers@google.com> Link: https://lore.kernel.org/r/20241106144826.91728-1-linux@treblig.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-05perf trace: avoid garbage when not printing a trace event's argumentsBenjamin Peterson
trace__fprintf_tp_fields may not print any tracepoint arguments. E.g., if the argument values are all zero. Previously, this would result in a totally uninitialized buffer being passed to fprintf, which could lead to garbage on the console. Fix the problem by passing the number of initialized bytes fprintf. Fixes: f11b2803bb88 ("perf trace: Allow choosing how to augment the tracepoint arguments") Signed-off-by: Benjamin Peterson <benjamin@engflow.com> Tested-by: Howard Chu <howardchu95@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: https://lore.kernel.org/r/20241103204816.7834-1-benjamin@engflow.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-05perf tools: update expected diff for lib/list_sort.cKuan-Wei Chiu
Since there are no longer any header include differences between lib/list_sort.c and tools/lib/list_sort.c, update the expected diff in check-header_ignore_hunks accordingly. Link: https://lkml.kernel.org/r/20241012042828.471614-4-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-11-04perf test: Fix ftrace test with regex patternsNamhyung Kim
During the parallel testing, I've noticed some ftrace test failures. It seems the regex pattern checks 100 msec of nanosleep with the error range of 10 msec. But sometimes it's affected by other processes and resulted in more time in the syscall. The following output shows that it took more than 120 msec and failed. Let's update the regex pattern so that it can allow more drifts. perf ftrace profile test # Total (us) Avg (us) Max (us) Count Function 121279.500 121279.500 121279.500 1 __x64_sys_clock_nanosleep 121278.400 121278.400 121278.400 1 common_nsleep 121277.800 121277.800 121277.800 1 hrtimer_nanosleep 121277.100 121277.100 121277.100 1 do_nanosleep 341760.289 56960.048 121273.400 6 schedule 176.200 25.171 31.616 7 scheduler_tick 0.923 0.923 0.923 1 native_smp_send_reschedule 345522.360 69104.472 345320.600 5 __x64_sys_execve 345486.585 69097.317 345312.700 5 do_execveat_common.isra.0 340730.300 340730.300 340730.300 1 bprm_execve 1.758 0.879 0.883 2 sched_mm_cid_before_execve 1.112 1.112 1.112 1 sched_mm_cid_after_execve ---- end(-1) ---- 81: perf ftrace tests : FAILED! Reviewed-by: Ian Rogers <irogers@google.com> Link: https://lore.kernel.org/r/20241102231702.2262258-1-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-04perf test: Remove dangling CFLAGS for removed attr.o objectArnaldo Carvalho de Melo
Since the C test wrapper for attr.py was removed we don't have an attr.o object for that CFLAGS_attr.o to apply for, remove it. Fixes: 3a447031f5fc21c4 ("perf test: Remove C test wrapper for attr.py") Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Reviewed-by: Ian Rogers <irogers@google.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: James Clark <james.clark@linaro.org> Cc: Leo Yan <leo.yan@linux.dev> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Ze Gao <zegao2021@gmail.com> Cc: zhaimingbing <zhaimingbing@cmss.chinamobile.com> Link: https://lore.kernel.org/r/ZyjbksKYnV22zmz-@x1 Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-04perf tools: Add all shellcheck_log to gitignoreCharlie Jenkins
Instead of adding specific shellcheck_log files to the gitignore, add all of them to prevent these files from cluttering the git status. Signed-off-by: Charlie Jenkins <charlie@rivosinc.com> Link: https://lore.kernel.org/r/20241104-shellcheck_gitignore-v1-1-ffc179f57dc9@rivosinc.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-04perf build: Add missing cflags when building with custom libtraceeventYicong Yang
When building with custom libtraceevent, below errors occur: $ make -C tools/perf NO_LIBPYTHON=1 PKG_CONFIG_PATH=<custom libtraceevent> In file included from util/session.h:5, from builtin-buildid-list.c:17: util/trace-event.h:153:10: fatal error: traceevent/event-parse.h: No such file or directory 153 | #include <traceevent/event-parse.h> | ^~~~~~~~~~~~~~~~~~~~~~~~~~ <snip similar errors of missing headers> This is because the include path is missed in the cflags. Add it. Fixes: 0f0e1f445690 ("perf build: Use pkg-config for feature check for libtrace{event,fs}") Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Reviewed-by: Leo Yan <leo.yan@arm.com> Reviewed-by: Guilherme Amadio <amadio@gentoo.org> Cc: linuxarm@huawei.com Link: https://lore.kernel.org/r/20241024133236.31016-1-yangyicong@huawei.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-04perf test: Remove cpu-list BPF cgroup counter testMichael Petlan
The cpu-list part of this testcase has proven itself to be unreliable. Sometimes, we get "<not counted>" for system.slice when pinned to CPUs 0 and 1. In such case, the test fails. Since we cannot simply guarantee that any system.slice load will run on any arbitrary list of CPUs, except the whole set of all CPUs, let's rather remove the cpu-list subtest. Fixes: a84260e314029e6dc9904fd ("perf test stat_bpf_counters_cgrp: Enhance perf stat cgroup BPF counter test") Signed-off-by: Michael Petlan <mpetlan@redhat.com> Cc: vmolnaro@redhat.com Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20241101102812.576425-1-mpetlan@redhat.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-04perf build: Make libunwind opt-in rather than opt-outIan Rogers
Having multiple unwinding libraries makes the perf code harder to understand and we have unused/untested code paths. Perf made BPF support an opt-out rather than opt-in feature. As libbpf has a libelf dependency, elfutils that provides libelf will also provide libdw. When libdw is present perf will use libdw unwinding rather than libunwind unwinding even if libunwind support is compiled in. Rather than have libunwind built into perf and never used, explicitly disable the support and make it opt-in. Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: https://lore.kernel.org/r/20241028193619.247727-1-irogers@google.com Closes: https://lore.kernel.org/linux-perf-users/CAP-5=fUXkp-d7gkzX4eF+nbjb2978dZsiHZ9abGHN=BN1qAcbg@mail.gmail.com/ Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-03Merge 'origin/master' into perf-tools-nextNamhyung Kim
To get the fixes in the perf-tools branch. Resolved a conflict due to RISC-V's syscall table change. Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-01perf test: Use sqrtloop workload to test bperf eventTengda Wu
Replace `brstack` workload with `sqrtloop` workload, because `sqrtloop` workload contains fork(), which is suitable for testing the bperf event inheritance feature. Signed-off-by: Tengda Wu <wutengda@huaweicloud.com> Cc: song@kernel.org Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20241021110201.325617-3-wutengda@huaweicloud.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-11-01perf stat: Support inherit events during fork() for bperfTengda Wu
bperf has a nice ability to share PMUs, but it still does not support inherit events during fork(), resulting in some deviations in its stat results compared with perf. perf stat result: $ ./perf stat -e cycles,instructions -- ./perf test -w sqrtloop Performance counter stats for './perf test -w sqrtloop': 2,316,038,116 cycles 2,859,350,725 instructions 1.009603637 seconds time elapsed 1.004196000 seconds user 0.003950000 seconds sys bperf stat result: $ ./perf stat --bpf-counters -e cycles,instructions -- \ ./perf test -w sqrtloop Performance counter stats for './perf test -w sqrtloop': 18,762,093 cycles 23,487,766 instructions 1.008913769 seconds time elapsed 1.003248000 seconds user 0.004069000 seconds sys In order to support event inheritance, two new bpf programs are added to monitor the fork and exit of tasks respectively. When a task is created, add it to the filter map to enable counting, and reuse the `accum_key` of its parent task to count together with the parent task. When a task exits, remove it from the filter map to disable counting. After support: $ ./perf stat --bpf-counters -e cycles,instructions -- \ ./perf test -w sqrtloop Performance counter stats for './perf test -w sqrtloop': 2,316,252,189 cycles 2,859,946,547 instructions 1.009422314 seconds time elapsed 1.003597000 seconds user 0.004270000 seconds sys Signed-off-by: Tengda Wu <wutengda@huaweicloud.com> Cc: song@kernel.org Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20241021110201.325617-2-wutengda@huaweicloud.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-30perf arm-spe: Use old behavior when opening old SPE filesJames Clark
Since the linked commit, we stopped interpreting data source if the perf.data file doesn't have the new metadata version. This means that perf c2c will show no samples in this case. Keep the old behavior so old files can be opened, but also still show the new warning that updating might improve the decoding. Also re-write the warning to be more concise and specific to a user. Fixes: ba5e7169e548 ("perf arm-spe: Use metadata to decide the data source feature") Signed-off-by: James Clark <james.clark@linaro.org> Reviewed-by: Leo Yan <leo.yan@arm.com> Cc: Julio.Suarez@arm.com Cc: Kiel.Friedt@arm.com Cc: Ryan.Roberts@arm.com Cc: Will Deacon <will@kernel.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: linux-arm-kernel@lists.infradead.org Cc: Besar Wicaksono <bwicaksono@nvidia.com> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20241029143734.291638-1-james.clark@linaro.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-30perf ftrace latency: Fix unit on histogram first entry when using --use-nsecArnaldo Carvalho de Melo
The use_nsec arg wasn't being taken into account when printing the first histogram entry, fix it: root@number:~# perf ftrace latency --use-nsec -T switch_mm_irqs_off -a sleep 2 # DURATION | COUNT | GRAPH | 0 - 1 us | 0 | | 1 - 2 ns | 0 | | 2 - 4 ns | 0 | | 4 - 8 ns | 0 | | 8 - 16 ns | 0 | | 16 - 32 ns | 0 | | 32 - 64 ns | 125 | | 64 - 128 ns | 335 | | 128 - 256 ns | 2155 | #### | 256 - 512 ns | 9996 | ################### | 512 - 1024 ns | 4958 | ######### | 1 - 2 us | 4636 | ######### | 2 - 4 us | 1053 | ## | 4 - 8 us | 15 | | 8 - 16 us | 1 | | 16 - 32 us | 0 | | 32 - 64 us | 0 | | 64 - 128 us | 0 | | 128 - 256 us | 0 | | 256 - 512 us | 0 | | 512 - 1024 us | 0 | | 1 - ... ms | 0 | | root@number:~# After: root@number:~# perf ftrace latency --use-nsec -T switch_mm_irqs_off -a sleep 2 # DURATION | COUNT | GRAPH | 0 - 1 ns | 0 | | 1 - 2 ns | 0 | | 2 - 4 ns | 0 | | 4 - 8 ns | 0 | | 8 - 16 ns | 0 | | 16 - 32 ns | 0 | | 32 - 64 ns | 19 | | 64 - 128 ns | 94 | | 128 - 256 ns | 2191 | #### | 256 - 512 ns | 9719 | #################### | 512 - 1024 ns | 5330 | ########### | 1 - 2 us | 4104 | ######## | 2 - 4 us | 807 | # | 4 - 8 us | 9 | | 8 - 16 us | 0 | | 16 - 32 us | 0 | | 32 - 64 us | 0 | | 64 - 128 us | 0 | | 128 - 256 us | 0 | | 256 - 512 us | 0 | | 512 - 1024 us | 0 | | 1 - ... ms | 0 | | root@number:~# Fixes: 84005bb6148618cc ("perf ftrace latency: Add -n/--use-nsec option") Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Gabriele Monaco <gmonaco@redhat.com> Link: https://lore.kernel.org/r/ZyE3frB-hMXHCnMO@x1 Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-30perf, riscv: Wire up perf trace support for RISC-VBjörn Töpel
RISC-V does not currently support perf trace, since the system call table is not generated. Perform the copy/paste exercise, wiring up RISC-V system call table generation. Signed-off-by: Björn Töpel <bjorn@rivosinc.com> Tested-by: Alexandre Ghiti <alexghiti@rivosinc.com> Cc: Anup Patel <anup@brainfault.org> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: linux-riscv@lists.infradead.org Cc: Atish Patra <atishp@rivosinc.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Link: https://lore.kernel.org/r/20241024190353.46737-1-bjorn@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-29perf probe: Fix retrieval of source files from a debuginfod serverArnaldo Carvalho de Melo
When perf is linked with libdebuginfod: root@number:~# ldd ~/bin/perf | grep debuginfod libdebuginfod.so.1 => /lib64/libdebuginfod.so.1 (0x00007ff5c3930000) root@number:~# perf check feature debuginfod debuginfod: [ on ] # HAVE_DEBUGINFOD_SUPPORT root@number:~# And we don't have a debuginfo package installed for the binary we're trying to use, vmlinux in this case as we didn't specify any using 'perf probe -x', it will use the build for the running kernel: root@number:~# perf buildid-list -k 38e927fd7799d50dbc4d99ec5e3f781b6105a6a9 root@number:~# And communicate with a debuginfo server, be it configured in a ~/.perfconfig file, excerpt from the 'perf config' man page: buildid-cache.* buildid-cache.debuginfod=URLs Specify debuginfod URLs to be used when retrieving perf.data binaries, it follows the same syntax as the DEBUGINFOD_URLS variable, like: buildid-cache.debuginfod=http://192.168.122.174:8002 Or via the DEBUGINFOD_URLS env var, as distros like fedora do by default: root@number:~# echo $DEBUGINFOD_URLS https://debuginfod.fedoraproject.org/ root@number:~# To pick and cache just what is needed, instead of requiring the manual installation of the entire kernel-debuginfo package, which is really large. It will, in this example, use the following cache files, deleted before/after this patch just to test the whole process: root@number:~# rm -f /root/.cache/debuginfod_client/38e927fd7799d50dbc4d99ec5e3f781b6105a6a9/source-a1414a5d-#usr#src#debug#kernel-6.11.4#linux-6.11.4-201.fc40.x86_64#net#ipv4#icmp.c root@number:~# rm -f /root/.cache/debuginfod_client/38e927fd7799d50dbc4d99ec5e3f781b6105a6a9/debuginfo Before this patch: root@number:~# perf probe -L icmp_rcv Failed to find source file path. Error: Failed to show lines. root@number:~# This is because 'perf probe' was using just the relative file name, in this case "net/ipv4/icmp.c", that is where the 'icmp_rcv' function is located, if we add it and comply with the debuginfo_find_source() function man page, it contacts the server, finds the necessary files, cache them locally and all works: root@number:~# perf probe -L icmp_rcv | head <icmp_rcv@/root/.cache/debuginfod_client/38e927fd7799d50dbc4d99ec5e3f781b6105a6a9/source-a1414a5d-#usr#src#debug#kernel-6.11.4#linux-6.11.4-201.fc40.x86_64#net#ipv4#icmp.c:0> 0 int icmp_rcv(struct sk_buff *skb) { 2 enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->dst.dev); struct icmphdr *icmph; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { 8 struct sec_path *sp = skb_sec_path(skb); root@number:~# Acked-by: Frank Ch. Eigler <fche@redhat.com> Cc: Aaron Merey <amerey@redhat.com> Cc: Francesco Nigro <fnigro@redhat.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: https://lore.kernel.org/r/ZyACsIFUETsr7-09@x1 Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-29perf arm-spe: Update --itrace help textGraham Woodward
The --itrace help now needs updating to reflect that the --itrace=b argument sythesises branches as well as branch misses. Signed-off-by: Graham Woodward <graham.woodward@arm.com> Reviewed-by: James Clark <james.clark@linaro.org> Tested-by: Leo Yan <leo.yan@arm.com> Cc: nd@arm.com Cc: mike.leach@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20241025143009.25419-5-graham.woodward@arm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-29perf arm-spe: Correctly set sample flagsGraham Woodward
Set flags on all synthesized instruction and branch samples. Signed-off-by: Graham Woodward <graham.woodward@arm.com> Reviewed-by: James Clark <james.clark@linaro.org> Tested-by: Leo Yan <leo.yan@arm.com> Cc: nd@arm.com Cc: mike.leach@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20241025143009.25419-4-graham.woodward@arm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-29perf arm-spe: Use ARM_SPE_OP_BRANCH_ERET when synthesizing branchesGraham Woodward
Instead of checking the type for just branch misses, we can instead check for the OP_BRANCH_ERET and synthesise branches as well as branch misses. Signed-off-by: Graham Woodward <graham.woodward@arm.com> Reviewed-by: James Clark <james.clark@linaro.org> Tested-by: Leo Yan <leo.yan@arm.com> Cc: nd@arm.com Cc: mike.leach@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20241025143009.25419-3-graham.woodward@arm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-29perf arm-spe: Set sample.addr to target address for instruction sampleGraham Woodward
For an instruction sample, assign the target address to the field 'to_ip'. If it is a non-branch record, to_ip will be 0, presenting a non-valid target address. Signed-off-by: Graham Woodward <graham.woodward@arm.com> Reviewed-by: James Clark <james.clark@linaro.org> Tested-by: Leo Yan <leo.yan@arm.com> Cc: nd@arm.com Cc: mike.leach@linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20241025143009.25419-2-graham.woodward@arm.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf vendor events arm64: Add i.MX91 DDR Performance Monitor metricsXu Yang
Add JSON metrics for i.MX91 DDR Performance Monitor. Signed-off-by: Xu Yang <xu.yang_2@nxp.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: festevam@gmail.com Cc: conor+dt@kernel.org Cc: krzk+dt@kernel.org Cc: robh@kernel.org Cc: shawnguo@kernel.org Cc: will@kernel.org Cc: james.clark@linaro.org Cc: mike.leach@linaro.org Cc: leo.yan@linux.dev Cc: linux-arm-kernel@lists.infradead.org Cc: imx@lists.linux.dev Cc: Frank.li@nxp.com Cc: john.g.garry@oracle.com Cc: kernel@pengutronix.de Cc: s.hauer@pengutronix.de Cc: devicetree@vger.kernel.org Link: https://lore.kernel.org/r/20240924061251.3387850-3-xu.yang_2@nxp.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Sort tests placing exclusive tests lastIan Rogers
This allows a uniform test numbering even though two passes are used to execute them. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: James Clark <james.clark@linaro.org> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-11-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Add a signal handler to kill forked child processesIan Rogers
If the `perf test` process is killed the child tests continue running and may run indefinitely. Propagate SIGINT (ctrl-C) and SIGTERM (kill) signals to the running child processes so that they terminate when the parent is killed. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: James Clark <james.clark@linaro.org> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-10-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Make parallel testing the defaultIan Rogers
Now C tests can have the "exclusive" flag to run without other tests, and shell tests can add "(exclusive)" to their description, run tests in parallel by default. Tests which flake when run in parallel can be marked exclusive to resolve the problem. Non-scientifically, the reduction on `perf test` execution time is from 8m35.890s to 3m55.115s on a Tigerlake laptop. So the tests complete in less than half the time. Tested-by: James Clark <james.clark@linaro.org> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-9-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Run parallel tests in two passesIan Rogers
In pass 1 run all tests that succeed when run in parallel. In pass 2 sequentially run all remaining tests that are flagged as "exclusive". Sequential and dont_fork tests keep to run in pass 1. Read the exclusive flag from the shell test descriptions, but remove from display to avoid >100 characters. Add error handling to finish tests if starting a later test fails. Mark the task-exit test as exclusive due to issues reported-by James Clark. Tested-by: James Clark <james.clark@linaro.org> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-8-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Add a signal handler around running a testIan Rogers
Add a signal handler around running a test. If a signal occurs during the test a siglongjmp unwinds the stack and output is flushed. The global run_test_jmp_buf is either unique per forked child or not shared during sequential execution. Tested-by: James Clark <james.clark@linaro.org> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-7-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Tag parallel failing shell tests with "(exclusive)"Ian Rogers
Some shell tests compete for resources and so can't run with other tests, tag such tests. The "(exclusive)" stems from shared/exclusive to describe how the tests run as if holding a lock. For ARM/coresight tests: Suggested-by: James Clark <james.clark@linaro.org> Additional failing tests: Suggested-by: Namhyung Kim <namhyung@kernel.org> Tested-by: James Clark <james.clark@linaro.org> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-6-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Avoid list test blocking on writing to stdoutIan Rogers
Python's json.tool will output the input json to stdout. Redirect to /dev/null to avoid blocking on stdout writes. Tested-by: James Clark <james.clark@linaro.org> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-5-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Reduce scope of parallel variableIan Rogers
The variable duplicates sequential but is only used for command line argument processing. Reduce scope to make the behavior clearer. Tested-by: James Clark <james.clark@linaro.org> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-4-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf test: Display number of active running testsIan Rogers
Before polling or sleeping to wait for a test to complete, print out ": Running (<num> active)" where the number of active tests is determined by iterating over the tests and seeing which return false for check_if_command_finished. The line erasing and printing out only occur if the number of runnings tests changes to avoid the line flickering excessively. Knowing tests are running allows a user to know a test is running and in parallel mode how many of the tests are waiting to complete. If color mode is disabled then avoid displaying the "Running" message as deleting the line isn't reliable. Tested-by: James Clark <james.clark@linaro.org> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Ilya Leoshkevich <iii@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dapeng Mi <dapeng1.mi@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241025192109.132482-3-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-28perf cap: Add __NR_capget to arch/x86 unistdIan Rogers
As there are duplicated kernel headers in tools/include libc can pick up the wrong definitions. This was causing the wrong system call for capget in perf. Reported-by: Adrian Hunter <adrian.hunter@intel.com> Fixes: e25ebda78e230283 ("perf cap: Tidy up and improve capability testing") Closes: https://lore.kernel.org/lkml/cc7d6bdf-1aeb-4179-9029-4baf50b59342@intel.com/ Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: 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@linux.intel.com> 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/20241026055448.312247-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-10-28tools headers: Update the linux/unaligned.h copy with the kernel sourcesArnaldo Carvalho de Melo
To pick up the changes in: 7f053812dab3946c ("random: vDSO: minimize and simplify header includes") That required adding a copy of include/vdso/unaligned.h and its checking in tools/perf/check-headers.h. Addressing this perf tools build warning: Warning: Kernel ABI header differences: diff -u tools/include/linux/unaligned.h include/linux/unaligned.h Please see tools/include/uapi/README for further details. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Ian Rogers <irogers@google.com> Cc: Jason A. Donenfeld <Jason@zx2c4.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/Zx-uHvAbPAESofEN@x1 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-10-23perf disasm: Fix not cleaning up disasm_line in symbol__disassemble_raw()Li Huafei
In symbol__disassemble_raw(), the created disasm_line should be discarded before returning an error. When creating disasm_line fails, break the loop and then release the created lines. Fixes: 0b971e6bf1c3 ("perf annotate: Add support to capture and parse raw instruction in powerpc using dso__data_read_offset utility") Signed-off-by: Li Huafei <lihuafei1@huawei.com> Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: sesse@google.com Cc: kjain@linux.ibm.com Link: https://lore.kernel.org/r/20241019154157.282038-3-lihuafei1@huawei.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-23perf disasm: Use disasm_line__free() to properly free disasm_lineLi Huafei
symbol__disassemble_capstone_powerpc() goto the 'err' label when it failed in the loop that created disasm_line, and then used free() directly to free disasm_line. Since the structure disasm_line contains members that allocate memory dynamically, this can result in a memory leak. In fact, we can simply break the loop when it fails in the middle of the loop, and disasm_line__free() will then be called to properly free the created line. Other error paths do not need to consider freeing disasm_line. Fixes: c5d60de1813a ("perf annotate: Add support to use libcapstone in powerpc") Signed-off-by: Li Huafei <lihuafei1@huawei.com> Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: sesse@google.com Cc: kjain@linux.ibm.com Link: https://lore.kernel.org/r/20241019154157.282038-2-lihuafei1@huawei.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-23perf disasm: Use disasm_line__free() to properly free disasm_lineLi Huafei
The structure disasm_line contains members that require dynamically allocated memory and need to be freed correctly using disasm_line__free(). This patch fixes the incorrect release in symbol__disassemble_capstone(). Fixes: 6d17edc113de ("perf annotate: Use libcapstone to disassemble") Signed-off-by: Li Huafei <lihuafei1@huawei.com> Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: sesse@google.com Cc: kjain@linux.ibm.com Link: https://lore.kernel.org/r/20241019154157.282038-1-lihuafei1@huawei.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-23perf python: Fix up the build on architectures without HAVE_KVM_STAT_SUPPORTArnaldo Carvalho de Melo
Noticed while building on a raspbian arm 32-bit system. There was also this other case, fixed by adding a missing util/stat.h with the prototypes: /tmp/tmp.MbiSHoF3dj/perf-6.12.0-rc3/tools/perf/util/python.c:1396:6: error: no previous prototype for ‘perf_stat__set_no_csv_summary’ [-Werror=missing-prototypes] 1396 | void perf_stat__set_no_csv_summary(int set __maybe_unused) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /tmp/tmp.MbiSHoF3dj/perf-6.12.0-rc3/tools/perf/util/python.c:1400:6: error: no previous prototype for ‘perf_stat__set_big_num’ [-Werror=missing-prototypes] 1400 | void perf_stat__set_big_num(int set __maybe_unused) | ^~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors In other architectures this must be building due to some lucky indirect inclusion of that header. Fixes: 9dabf4003423c8d3 ("perf python: Switch module to linking libraries from building source") Reviewed-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/lkml/ZxllAtpmEw5fg9oy@x1 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-10-23perf test: Handle perftool-testsuite_probe failure due to broken DWARFVeronika Molnarova
Test case test_adding_blacklisted ends in failure if the blacklisted probe is of an assembler function with no DWARF available. At the same time, probing the blacklisted function with ASM DWARF doesn't test the blacklist itself as the failure is a result of the broken DWARF. When the broken DWARF output is encountered, check if the probed function was compiled by the assembler. If so, the broken DWARF message is expected and does not report a perf issue, else report a failure. If the ASM DWARF affected the probe, try the next probe on the blacklist. If the first 5 probes are defective due to broken DWARF, skip the test case. Fixes: def5480d63c1e847 ("perf testsuite probe: Add test for blacklisted kprobes handling") Signed-off-by: Veronika Molnarova <vmolnaro@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.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: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Veronika Molnarova <vmolnaro@redhat.com> Link: https://lore.kernel.org/r/20241017161555.236769-1-vmolnaro@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-10-23perf trace: Fix non-listed archs in the syscalltbl routinesJiri Slaby
This fixes a build breakage on 32-bit arm, where the syscalltbl__id_at_idx() function was missing. Committer notes: Generating a proper syscall table from a copy of arch/arm/tools/syscall.tbl ends up being too big a patch for this rc stage, I started doing it but while testing noticed some other problems with using BPF to collect pointer args on arm7 (32-bit) will maybe continue trying to make it work on the next cycle... Fixes: 7a2fb5619cc1fb53 ("perf trace: Fix iteration of syscall ids in syscalltbl->entries") Suggested-by: Howard Chu <howardchu95@gmail.com> Signed-off-by: <jslaby@suse.cz> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/lkml/3a592835-a14f-40be-8961-c0cee7720a94@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-10-23perf build: Change the clang check back to 12.0.1Howard Chu
This serves as a revert for this patch: https://lore.kernel.org/linux-perf-users/ZuGL9ROeTV2uXoSp@x1/ Signed-off-by: Howard Chu <howardchu95@gmail.com> Tested-by: James Clark <james.clark@linaro.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alan Maguire <alan.maguire@oracle.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.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> Link: https://lore.kernel.org/r/20241011021403.4089793-2-howardchu95@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-10-23perf trace augmented_raw_syscalls: Add more checks to pass the verifierHoward Chu
Add some more checks to pass the verifier in more kernels. Signed-off-by: Howard Chu <howardchu95@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alan Maguire <alan.maguire@oracle.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.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> Link: https://lore.kernel.org/r/20241011021403.4089793-3-howardchu95@gmail.com [ Reduced the patch removing things that can be done later ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-10-23perf trace augmented_raw_syscalls: Add extra array index bounds checking to ↵Arnaldo Carvalho de Melo
satisfy some BPF verifiers In a RHEL8 kernel (4.18.0-513.11.1.el8_9.x86_64), that, as enterprise kernels go, have backports from modern kernels, the verifier complains about lack of bounds check for the index into the array of syscall arguments, on a BPF bytecode generated by clang 17, with: ; } else if (size < 0 && size >= -6) { /* buffer */ 116: (b7) r1 = -6 117: (2d) if r1 > r6 goto pc-30 R0=map_value(id=0,off=0,ks=4,vs=24688,imm=0) R1_w=inv-6 R2=map_value(id=0,off=16,ks=4,vs=8272,imm=0) R3=inv(id=0) R5=inv40 R6=inv(id=0,umin_value=18446744073709551610,var_off=(0xffffffff00000000; 0xffffffff)) R7=map_value(id=0,off=56,ks=4,vs=8272,imm=0) R8=invP6 R9=map_value(id=0,off=20,ks=4,vs=24,imm=0) R10=fp0 fp-8=mmmmmmmm fp-16=map_value fp-24=map_value fp-32=inv40 fp-40=ctx fp-48=map_value fp-56=inv1 fp-64=map_value fp-72=map_value fp-80=map_value ; index = -(size + 1); 118: (a7) r6 ^= -1 119: (67) r6 <<= 32 120: (77) r6 >>= 32 ; aug_size = args->args[index]; 121: (67) r6 <<= 3 122: (79) r1 = *(u64 *)(r10 -24) 123: (0f) r1 += r6 last_idx 123 first_idx 116 regs=40 stack=0 before 122: (79) r1 = *(u64 *)(r10 -24) regs=40 stack=0 before 121: (67) r6 <<= 3 regs=40 stack=0 before 120: (77) r6 >>= 32 regs=40 stack=0 before 119: (67) r6 <<= 32 regs=40 stack=0 before 118: (a7) r6 ^= -1 regs=40 stack=0 before 117: (2d) if r1 > r6 goto pc-30 regs=42 stack=0 before 116: (b7) r1 = -6 R0_w=map_value(id=0,off=0,ks=4,vs=24688,imm=0) R1_w=inv1 R2_w=map_value(id=0,off=16,ks=4,vs=8272,imm=0) R3_w=inv(id=0) R5_w=inv40 R6_rw=invP(id=0,smin_value=-2147483648,smax_value=0) R7_w=map_value(id=0,off=56,ks=4,vs=8272,imm=0) R8_w=invP6 R9_w=map_value(id=0,off=20,ks=4,vs=24,imm=0) R10=fp0 fp-8=mmmmmmmm fp-16_w=map_value fp-24_r=map_value fp-32_w=inv40 fp-40=ctx fp-48=map_value fp-56_w=inv1 fp-64_w=map_value fp-72=map_value fp-80=map_value parent didn't have regs=40 stack=0 marks last_idx 110 first_idx 98 regs=40 stack=0 before 110: (6d) if r1 s> r6 goto pc+5 regs=42 stack=0 before 109: (b7) r1 = 1 regs=40 stack=0 before 108: (65) if r6 s> 0x1000 goto pc+7 regs=40 stack=0 before 98: (55) if r6 != 0x1 goto pc+9 R0_w=map_value(id=0,off=0,ks=4,vs=24688,imm=0) R1_w=invP12 R2_w=map_value(id=0,off=16,ks=4,vs=8272,imm=0) R3_rw=inv(id=0) R5_w=inv24 R6_rw=invP(id=0,smin_value=-2147483648,smax_value=2147483647) R7_w=map_value(id=0,off=40,ks=4,vs=8272,imm=0) R8_rw=invP4 R9_w=map_value(id=0,off=12,ks=4,vs=24,imm=0) R10=fp0 fp-8=mmmmmmmm fp-16_rw=map_value fp-24_r=map_value fp-32_rw=invP24 fp-40_r=ctx fp-48_r=map_value fp-56_w=invP1 fp-64_rw=map_value fp-72_r=map_value fp-80_r=map_value parent already had regs=40 stack=0 marks 124: (79) r6 = *(u64 *)(r1 +16) R0=map_value(id=0,off=0,ks=4,vs=24688,imm=0) R1_w=map_value(id=0,off=0,ks=4,vs=8272,umax_value=34359738360,var_off=(0x0; 0x7fffffff8),s32_max_value=2147483640,u32_max_value=-8) R2=map_value(id=0,off=16,ks=4,vs=8272,imm=0) R3=inv(id=0) R5=inv40 R6_w=invP(id=0,umax_value=34359738360,var_off=(0x0; 0x7fffffff8),s32_max_value=2147483640,u32_max_value=-8) R7=map_value(id=0,off=56,ks=4,vs=8272,imm=0) R8=invP6 R9=map_value(id=0,off=20,ks=4,vs=24,imm=0) R10=fp0 fp-8=mmmmmmmm fp-16=map_value fp-24=map_value fp-32=inv40 fp-40=ctx fp-48=map_value fp-56=inv1 fp-64=map_value fp-72=map_value fp-80=map_value R1 unbounded memory access, make sure to bounds check any such access processed 466 insns (limit 1000000) max_states_per_insn 2 total_states 20 peak_states 20 mark_read 3 If we add this line, as used in other BPF programs, to cap that index: index &= 7; The generated BPF program is considered safe by that version of the BPF verifier, allowing perf to collect the syscall args in one more kernel using the BPF based pointer contents collector. With the above one-liner it works with that kernel: [root@dell-per740-01 ~]# uname -a Linux dell-per740-01.khw.eng.rdu2.dc.redhat.com 4.18.0-513.11.1.el8_9.x86_64 #1 SMP Thu Dec 7 03:06:13 EST 2023 x86_64 x86_64 x86_64 GNU/Linux [root@dell-per740-01 ~]# ~acme/bin/perf trace -e *sleep* sleep 1.234567890 0.000 (1234.704 ms): sleep/3863610 nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 234567890 }) = 0 [root@dell-per740-01 ~]# As well as with the one in Fedora 40: root@number:~# uname -a Linux number 6.11.3-200.fc40.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Oct 10 22:31:19 UTC 2024 x86_64 GNU/Linux root@number:~# perf trace -e *sleep* sleep 1.234567890 0.000 (1234.722 ms): sleep/14873 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 234567890 }, rmtp: 0x7ffe87311a40) = 0 root@number:~# Song Liu reported that this one-liner was being optimized out by clang 18, so I suggested and he tested that adding a compiler barrier before it made clang v18 to keep it and the verifier in the kernel in Song's case (Meta's 5.12 based kernel) also was happy with the resulting bytecode. I'll investigate using virtme-ng[1] to have all the perf BPF based functionality thoroughly tested over multiple kernels and clang versions. [1] https://kernel-recipes.org/en/2024/virtme-ng/ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alan Maguire <alan.maguire@oracle.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andrea Righi <andrea.righi@linux.dev> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> 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: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/lkml/Zw7JgJc0LOwSpuvx@x1 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-10-22perf test: Add precise_max subtest to the perf record shell testNamhyung Kim
It's a very simply test just to run with cycles:P and instructions:P events. Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: James Clark <james.clark@arm.com> Cc: Atish Patra <atishp@atishpatra.org> Cc: Mingwei Zhang <mizhang@google.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Palmer Dabbelt <palmer@rivosinc.com> Link: https://lore.kernel.org/r/20241016062359.264929-10-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-22perf record: Just use "cycles:P" as the default eventNamhyung Kim
The fallback logic can add ":u" modifier if needed. Reviewed-by: Ian Rogers <irogers@google.com> Reviewed-by: James Clark <james.clark@linaro.org> Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com> Acked-by: Kan Liang <kan.liang@linux.intel.com> Cc: James Clark <james.clark@arm.com> Cc: Atish Patra <atishp@atishpatra.org> Cc: Mingwei Zhang <mizhang@google.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Palmer Dabbelt <palmer@rivosinc.com> Link: https://lore.kernel.org/r/20241016062359.264929-9-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-22perf tools: Check fallback error and orderNamhyung Kim
The perf_event_open might fail due to various reasons, so blindly reducing precise_ip level might not be the best way to deal with it. It seems the kernel return -EOPNOTSUPP when PMU doesn't support the given precise level. Let's try again with the correct error code. This caused a problem on AMD, as it stops on precise_ip of 2 for IBS but user events with exclude_kernel=1 cannot make progress. Let's add the evsel__handle_error_quirks() to this case specially. I plan to work on the kernel side to improve this situation but it'd still need some special handling for IBS. Reviewed-by: James Clark <james.clark@linaro.org> Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com> Acked-by: Kan Liang <kan.liang@linux.intel.com> Cc: James Clark <james.clark@arm.com> Cc: Atish Patra <atishp@atishpatra.org> Cc: Mingwei Zhang <mizhang@google.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Palmer Dabbelt <palmer@rivosinc.com> Link: https://lore.kernel.org/r/20241016062359.264929-8-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-22perf tools: Move x86__is_amd_cpu() to util/env.cNamhyung Kim
It can be called from non-x86 platform so let's move it to the general util directory. Also add a new helper perf_env__is_x86_amd_cpu() so that it can be called with an existing perf_env as well. Reviewed-by: James Clark <james.clark@linaro.org> Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com> Acked-by: Kan Liang <kan.liang@linux.intel.com> Cc: James Clark <james.clark@arm.com> Cc: Atish Patra <atishp@atishpatra.org> Cc: Mingwei Zhang <mizhang@google.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Palmer Dabbelt <palmer@rivosinc.com> Link: https://lore.kernel.org/r/20241016062359.264929-7-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
generated by cgit (git 2.34.1) at 2025-07-16 19:02:18 +0000