aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/bench
AgeCommit message (Collapse)AuthorFilesLines
2024-08-12perf tool: Constify tool pointersIan Rogers1-1/+1
The tool pointer (to a struct largely of function pointers) is passed around but is unchanged except at initialization. Change parameter and variable types to be const to lower the possibilities of what could happen with a tool. Reviewed-by: Adrian Hunter <[email protected]> Signed-off-by: Ian Rogers <[email protected]> Tested-by: Adrian Hunter <[email protected]> Tested-by: Leo Yan <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Anshuman Khandual <[email protected]> Cc: Athira Rajeev <[email protected]> Cc: Huacai Chen <[email protected]> Cc: Ilkka Koskinen <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: James Clark <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Jonathan Cameron <[email protected]> Cc: Kan Liang <[email protected]> Cc: Leo Yan <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Nick Desaulniers <[email protected]> Cc: Nick Terrell <[email protected]> Cc: Oliver Upton <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Song Liu <[email protected]> Cc: Sun Haiyong <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Will Deacon <[email protected]> Cc: Yanteng Si <[email protected]> Cc: Yicong Yang <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2024-06-26perf bench: Make bench its own libraryIan Rogers1-23/+23
Make the benchmark code into a library so it may be linked against things like the python module to avoid compiling code twice. Signed-off-by: Ian Rogers <[email protected]> Reviewed-by: James Clark <[email protected]> Cc: Suzuki K Poulose <[email protected]> Cc: Kees Cook <[email protected]> Cc: Palmer Dabbelt <[email protected]> Cc: Albert Ou <[email protected]> Cc: Nick Terrell <[email protected]> Cc: Gary Guo <[email protected]> Cc: Alex Gaynor <[email protected]> Cc: Boqun Feng <[email protected]> Cc: Wedson Almeida Filho <[email protected]> Cc: Ze Gao <[email protected]> Cc: Alice Ryhl <[email protected]> Cc: Andrei Vagin <[email protected]> Cc: Yicong Yang <[email protected]> Cc: Jonathan Cameron <[email protected]> Cc: Guo Ren <[email protected]> Cc: Miguel Ojeda <[email protected]> Cc: Will Deacon <[email protected]> Cc: Mike Leach <[email protected]> Cc: Leo Yan <[email protected]> Cc: Oliver Upton <[email protected]> Cc: John Garry <[email protected]> Cc: Benno Lossin <[email protected]> Cc: Björn Roy Baron <[email protected]> Cc: Andreas Hindborg <[email protected]> Cc: Paul Walmsley <[email protected]> Signed-off-by: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/r/[email protected]
2024-06-13tools/perf: Fix timing issue with parallel threads in perf bench ↵Athira Rajeev1-1/+1
wake-up-parallel perf bench futex fails as below and hangs intermittently when attempted to run on on a powerpc system: ./perf bench futex wake-parallel Running 'futex/wake-parallel' benchmark: Run summary [PID 88588]: blocking on 640 threads (at [private] futex 0x10464b8c), 640 threads waking up 1 at a time. [Run 1]: Avg per-thread latency (waking 1/640 threads) in 0.1309 ms (+-53.27%) [Run 2]: Avg per-thread latency (waking 1/640 threads) in 0.0120 ms (+-31.16%) [Run 3]: Avg per-thread latency (waking 1/640 threads) in 0.1474 ms (+-92.47%) [Run 4]: Avg per-thread latency (waking 1/640 threads) in 0.2883 ms (+-67.75%) [Run 5]: Avg per-thread latency (waking 1/640 threads) in 0.4108 ms (+-39.60%) [Run 6]: Avg per-thread latency (waking 1/640 threads) in 0.7843 ms (+-78.98%) perf: couldn't wakeup all tasks (0/1) perf: couldn't wakeup all tasks (0/1) perf: couldn't wakeup all tasks (0/1) perf: couldn't wakeup all tasks (0/1) perf: couldn't wakeup all tasks (0/1) perf: couldn't wakeup all tasks (0/1) In the system, where perf bench wake-up-parallel is has system configuration of 640 cpus. After debugging, this turned out to be a timing issue. The benchmark creates threads equal to number of cpus and issues a futex_wait. Then it does a usleep for .1 second before initiating futex_wake. In system configuration with more threads, the usleep time is not enough. Patch changes the usleep from 100000 to 200000 With the patch, ran multiple iterations and there were no issues further seen Reported-by: Disha Goel <[email protected]> Signed-off-by: Athira Rajeev <[email protected]> Reviewed-by: Ian Rogers <[email protected]> Tested-by: Disha Goel <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Signed-off-by: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/r/[email protected]
2024-06-13tools/perf: Fix perf bench epoll to enable the run when some CPU's are offlineAthira Rajeev2-2/+2
Perf bench epoll fails as below when attempted to run on on a powerpc system: ./perf bench epoll wait Running 'epoll/wait' benchmark: Run summary [PID 627653]: 79 threads monitoring on 64 file-descriptors for 8 secs. perf: pthread_create: No such file or directory In the setup where this perf bench was ran, difference was that partition had 640 CPU's, but not all CPUs were online. 80 CPUs were online. While creating threads and using epoll_wait , code sets the affinity using cpumask. The cpumask size used is 80 which is picked from "nrcpus = perf_cpu_map__nr(cpu)". Here the benchmark reports fail while setting affinity for cpu number which is greater than 80 or higher, because it attempts to set a bit position which is not allocated on the cpumask. Fix this by changing the size of cpumask to number of possible cpus and not the number of online cpus. Signed-off-by: Athira Rajeev <[email protected]> Reviewed-by: Ian Rogers <[email protected]> Tested-by: Disha Goel <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Signed-off-by: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/r/[email protected]
2024-06-13tools/perf: Fix perf bench futex to enable the run when some CPU's are offlineAthira Rajeev5-5/+5
Perf bench futex fails as below when attempted to run on on a powerpc system: ./perf bench futex all Running futex/hash benchmark... Run summary [PID 626307]: 80 threads, each operating on 1024 [private] futexes for 10 secs. perf: pthread_create: No such file or directory In the setup where this perf bench was ran, difference was that partition had 640 CPU's, but not all CPUs were online. 80 CPUs were online. While blocking the threads with futex_wait, code sets the affinity using cpumask. The cpumask size used is 80 which is picked from "nrcpus = perf_cpu_map__nr(cpu)". Here the benchmark reports fail while setting affinity for cpu number which is greater than 80 or higher, because it attempts to set a bit position which is not allocated on the cpumask. Fix this by changing the size of cpumask to number of possible cpus and not the number of online cpus. Signed-off-by: Athira Rajeev <[email protected]> Reviewed-by: Ian Rogers <[email protected]> Tested-by: Disha Goel <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Signed-off-by: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/r/[email protected]
2024-05-07perf bench internals inject-build-id: Fix trap divide when collecting just ↵He Zhe1-1/+1
one DSO 'perf bench internals inject-build-id' suffers from the following error when only one DSO is collected. # perf bench internals inject-build-id -v Collected 1 DSOs traps: internals-injec[2305] trap divide error ip:557566ba6394 sp:7ffd4de97fe0 error:0 in perf[557566b2a000+23d000] Build-id injection benchmark Iteration #1 Floating point exception This patch removes the unnecessary minus one from the divisor which also corrects the randomization range. Signed-off-by: He Zhe <[email protected]> Fixes: 0bf02a0d80427f26 ("perf bench: Add build-id injection benchmark") Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2024-04-12perf bench uprobe: Add uretprobe variant of uprobe benchmarksIan Rogers2-3/+19
Name benchmarks with _ret at the end to avoid creating a new set of benchmarks. Signed-off-by: Ian Rogers <[email protected]> Acked-by: Jiri Olsa <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Andrei Vagin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Kan Liang <[email protected]> Cc: Kees Kook <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2024-04-12perf bench uprobe: Remove lib64 from libc.so.6 binary pathIan Rogers1-1/+1
bpf_program__attach_uprobe_opts will search LD_LIBRARY_PATH and so specifying `/lib64` is unnecessary and causes failures for libc.so.6 paths like `/lib/x86_64-linux-gnu/libc.so.6`. Fixes: 7b47623b8cae8149 ("perf bench uprobe trace_printk: Add entry attaching an BPF program that does a trace_printk") Signed-off-by: Ian Rogers <[email protected]> Acked-by: Jiri Olsa <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Andrei Vagin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Kan Liang <[email protected]> Cc: Kees Kook <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-12-12libperf cpumap: Replace usage of perf_cpu_map__new(NULL) with ↵Ian Rogers7-7/+7
perf_cpu_map__new_online_cpus() Passing NULL to perf_cpu_map__new() performs perf_cpu_map__new_online_cpus(), just directly call perf_cpu_map__new_online_cpus() to be more intention revealing. Reviewed-by: James Clark <[email protected]> Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Alexandre Ghiti <[email protected]> Cc: Andrew Jones <[email protected]> Cc: André Almeida <[email protected]> Cc: Athira Jajeev <[email protected]> Cc: Atish Patra <[email protected]> Cc: Changbin Du <[email protected]> Cc: Darren Hart <[email protected]> Cc: Davidlohr Bueso <[email protected]> Cc: Huacai Chen <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: K Prateek Nayak <[email protected]> Cc: Kajol Jain <[email protected]> Cc: Kan Liang <[email protected]> Cc: Leo Yan <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mike Leach <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Nick Desaulniers <[email protected]> Cc: Paolo Bonzini <[email protected]> Cc: Paran Lee <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Ravi Bangoria <[email protected]> Cc: Sandipan Das <[email protected]> Cc: Sean Christopherson <[email protected]> Cc: Steinar H. Gunderson <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Will Deacon <[email protected]> Cc: Yang Jihong <[email protected]> Cc: Yang Li <[email protected]> Cc: Yanteng Si <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-12-05perf bench sched-seccomp-notify: Fix spelling mistake "synchronious" -> ↵Colin Ian King1-1/+1
"synchronous" There is a spelling mistake in an option description. Fix it. Signed-off-by: Colin Ian King <[email protected]> Acked-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-10-25perf bench sched pipe: Add -G/--cgroups optionNamhyung Kim1-4/+128
The -G/--cgroups option is to put sender and receiver in different cgroups in order to measure cgroup context switch overheads. Users need to make sure the cgroups exist and accessible. The following example should the effect of this change. Please don't forget taskset before the perf bench to measure cgroup switches properly. Otherwise each task would run on a different CPU and generate cgroup switches regardless of this change. # perf stat -e context-switches,cgroup-switches \ > taskset -c 0 perf bench sched pipe -l 10000 > /dev/null Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 10000': 20,001 context-switches 2 cgroup-switches 0.053449651 seconds time elapsed 0.011286000 seconds user 0.041869000 seconds sys # perf stat -e context-switches,cgroup-switches \ > taskset -c 0 perf bench sched pipe -l 10000 -G AAA,BBB > /dev/null Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 10000 -G AAA,BBB': 20,001 context-switches 20,001 cgroup-switches 0.052768627 seconds time elapsed 0.006284000 seconds user 0.046266000 seconds sys Signed-off-by: Namhyung Kim <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Link: https://lore.kernel.org/r/[email protected]
2023-10-12perf bench uprobe: Fix potential use of memory after freeIan Rogers1-0/+1
Found by clang-tidy: ``` bench/uprobe.c:98:3: warning: Use of memory after it is freed [clang-analyzer-unix.Malloc] bench_uprobe_bpf__destroy(skel); ``` Signed-off-by: Ian Rogers <[email protected]> Acked-by: Namhyung Kim <[email protected]> Cc: Ravi Bangoria <[email protected]> Cc: Nick Desaulniers <[email protected]> Cc: Yang Jihong <[email protected]> Cc: Huacai Chen <[email protected]> Cc: Nathan Chancellor <[email protected]> Cc: Kan Liang <[email protected]> Cc: [email protected] Cc: Ming Wang <[email protected]> Cc: Tom Rix <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Namhyung Kim <[email protected]>
2023-10-10Merge tag 'perf-tools-fixes-for-v6.6-1-2023-09-25' into perf-tools-nextArnaldo Carvalho de Melo1-1/+1
To pick up the 'perf bench sched-seccomp-notify' changes to allow us to continue build testing perf-tools-next with the set of distro containers, where some older ones don't have a recent enough seccomp.h UAPI header that contains defines needed by this new 'perf bench' workload. Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-09-26perf bench messaging: Kill child processes when exit abnormally in process modeYang Jihong1-3/+20
When exit abnormally in process mode, customize SIGINT and SIGTERM signal handler to kill the forked child processes. Before: # perf bench sched messaging -l 1000000 -g 1 & [1] 8519 # # Running 'sched/messaging' benchmark: # pgrep sched-messaging | wc -l 41 # kill -15 8519 [1]+ Terminated perf bench sched messaging -l 1000000 -g 1 # pgrep sched-messaging | wc -l 40 After: # perf bench sched messaging -l 1000000 -g 1 & [1] 8472 # # Running 'sched/messaging' benchmark: # pgrep sched-messaging | wc -l 41 # kill -15 8472 [1]+ Exit 1 perf bench sched messaging -l 1000000 -g 1 # pgrep sched-messaging | wc -l 0 Signed-off-by: Yang Jihong <[email protected]> Reviewed-by: Ian Rogers <[email protected]> Link: https://lore.kernel.org/r/[email protected] [ namhyung: fix a whitespace ] Signed-off-by: Namhyung Kim <[email protected]>
2023-09-26perf bench messaging: Store chlid process pid when creating worker for ↵Yang Jihong1-20/+27
process mode To save pid of child processes when creating worker: 1. The messaging worker is changed to `union` type to store thread id and process pid. 2. Save child process pid in create_process_worker(). 3. Rename `pth_tab` as `work_tab`. Test result: # perf bench sched messaging # Running 'sched/messaging' benchmark: # 20 sender and receiver processes per group # 10 groups == 400 processes run Total time: 6.744 [sec] # perf bench sched messaging -t # Running 'sched/messaging' benchmark: # 20 sender and receiver threads per group # 10 groups == 400 threads run Total time: 5.788 [sec] Signed-off-by: Yang Jihong <[email protected]> Reviewed-by: Ian Rogers <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Namhyung Kim <[email protected]>
2023-09-26perf bench messaging: Factor out create_worker()Yang Jihong1-24/+26
Refactor the create_worker() helper: 1. Modify the return value and use pthread pointer as a parameter to facilitate value assignment in create_worker(). 2. The thread worker creation and process worker creation are abstracted into independent helpers. No functional change. Test result: # perf bench sched messaging # Running 'sched/messaging' benchmark: # 20 sender and receiver processes per group # 10 groups == 400 processes run Total time: 6.332 [sec] # perf bench sched messaging -t # Running 'sched/messaging' benchmark: # 20 sender and receiver threads per group # 10 groups == 400 threads run Total time: 5.545 [sec] Signed-off-by: Yang Jihong <[email protected]> Reviewed-by: Ian Rogers <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Namhyung Kim <[email protected]>
2023-09-26perf bench messaging: Fix coding style issues for sched-messagingYang Jihong1-5/+5
Fixed several code style issues in sched-messaging: 1. Use one space around "-" and "+" operators. 2. When a long line is broken, the operator is at the end of the line. Signed-off-by: Yang Jihong <[email protected]> Reviewed-by: Ian Rogers <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Namhyung Kim <[email protected]>
2023-09-13perf bench sched-seccomp-notify: Use the tools copy of seccomp.h UAPIArnaldo Carvalho de Melo1-1/+1
To keep perf building in systems where types and defines used in this new benchmark are not available, such as: 12 13.46 centos:stream : FAIL gcc version 8.5.0 20210514 (Red Hat 8.5.0-20) (GCC) bench/sched-seccomp-notify.c: In function 'user_notif_syscall': bench/sched-seccomp-notify.c:55:27: error: 'SECCOMP_RET_USER_NOTIF' undeclared (first use in this function); did you mean 'SECCOMP_RET_ERRNO'? BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF), ^~~~~~~~~~~~~~~~~~~~~~ /git/perf-6.6.0-rc1/tools/include/uapi/linux/filter.h:49:59: note: in definition of macro 'BPF_STMT' #define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k } ^ bench/sched-seccomp-notify.c:55:27: note: each undeclared identifier is reported only once for each function it appears in BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF), ^~~~~~~~~~~~~~~~~~~~~~ /git/perf-6.6.0-rc1/tools/include/uapi/linux/filter.h:49:59: note: in definition of macro 'BPF_STMT' #define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k } ^ bench/sched-seccomp-notify.c:55:3: error: missing initializer for field 'k' of 'struct sock_filter' [-Werror=missing-field-initializers] BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF), ^~~~~~~~ In file included from bench/sched-seccomp-notify.c:5: /git/perf-6.6.0-rc1/tools/include/uapi/linux/filter.h:28:8: note: 'k' declared here __u32 k; /* Generic multiuse field */ ^ bench/sched-seccomp-notify.c: In function 'user_notification_sync_loop': bench/sched-seccomp-notify.c:70:28: error: storage size of 'resp' isn't known struct seccomp_notif_resp resp; ^~~~ bench/sched-seccomp-notify.c:71:23: error: storage size of 'req' isn't known struct seccomp_notif req; ^~~ bench/sched-seccomp-notify.c:76:23: error: 'SECCOMP_IOCTL_NOTIF_RECV' undeclared (first use in this function); did you mean 'SECCOMP_MODE_STRICT'? if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req)) ^~~~~~~~~~~~~~~~~~~~~~~~ SECCOMP_MODE_STRICT bench/sched-seccomp-notify.c:86:23: error: 'SECCOMP_IOCTL_NOTIF_SEND' undeclared (first use in this function); did you mean 'SECCOMP_RET_ACTION'? if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp)) ^~~~~~~~~~~~~~~~~~~~~~~~ SECCOMP_RET_ACTION bench/sched-seccomp-notify.c:71:23: error: unused variable 'req' [-Werror=unused-variable] struct seccomp_notif req; ^~~ bench/sched-seccomp-notify.c:70:28: error: unused variable 'resp' [-Werror=unused-variable] struct seccomp_notif_resp resp; ^~~~ 14 11.31 debian:10 : FAIL gcc version 8.3.0 (Debian 8.3.0-6) Cc: Adrian Hunter <[email protected]> Cc: Andrei Vagin <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Kees Kook <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-09-09Merge tag 'perf-tools-for-v6.6-1-2023-09-05' of ↵Linus Torvalds5-9/+225
git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools Pull perf tools updates from Arnaldo Carvalho de Melo: "perf tools maintainership: - Add git information for perf-tools and perf-tools-next trees and branches to the MAINTAINERS file. That is where development now takes place and myself and Namhyung Kim have write access, more people to come as we emulate other maintainer groups. perf record: - Record kernel data maps when 'perf record --data' is used, so that global variables can be resolved and used in tools that do data profiling. perf trace: - Remove the old, experimental support for BPF events in which a .c file was passed as an event: "perf trace -e hello.c" to then get compiled and loaded. The only known usage for that, that shipped with the kernel as an example for such events, augmented the raw_syscalls tracepoints and was converted to a libbpf skeleton, reusing all the user space components and the BPF code connected to the syscalls. In the end just the way to glue the BPF part and the user space type beautifiers changed, now being performed by libbpf skeletons. The next step is to use BTF to do pretty printing of all syscall types, as discussed with Alan Maguire and others. Now, on a perf built with BUILD_BPF_SKEL=1 we get most if not all path/filenames/strings, some of the networking data structures, perf_event_attr, etc, i.e. systemwide tracing of nanosleep calls and perf_event_open syscalls while 'perf stat' runs 'sleep' for 5 seconds: # perf trace -a -e *nanosleep,perf* perf stat -e cycles,instructions sleep 5 0.000 ( 9.034 ms): perf/327641 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0 (PERF_COUNT_HW_CPU_CYCLES), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 327642 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3 9.039 ( 0.006 ms): perf/327641 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x1 (PERF_COUNT_HW_INSTRUCTIONS), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 327642 (perf-exec), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 ? ( ): gpm/991 ... [continued]: clock_nanosleep()) = 0 10.133 ( ): sleep/327642 clock_nanosleep(rqtp: { .tv_sec: 5, .tv_nsec: 0 }, rmtp: 0x7ffd36f83ed0) ... ? ( ): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0 30.276 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ... 223.215 (1000.430 ms): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) = 0 30.276 (2000.394 ms): gpm/991 ... [continued]: clock_nanosleep()) = 0 1230.814 ( ): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) ... 1230.814 (1000.404 ms): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0 2030.886 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ... 2237.709 (1000.153 ms): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) = 0 ? ( ): crond/1172 ... [continued]: clock_nanosleep()) = 0 3242.699 ( ): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) ... 2030.886 (2000.385 ms): gpm/991 ... [continued]: clock_nanosleep()) = 0 3728.078 ( ): crond/1172 clock_nanosleep(rqtp: { .tv_sec: 60, .tv_nsec: 0 }, rmtp: 0x7ffe0971dcf0) ... 3242.699 (1000.158 ms): pool-gsd-smart/3051 ... [continued]: clock_nanosleep()) = 0 4031.409 ( ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ... 10.133 (5000.375 ms): sleep/327642 ... [continued]: clock_nanosleep()) = 0 Performance counter stats for 'sleep 5': 2,617,347 cycles 1,855,997 instructions # 0.71 insn per cycle 5.002282128 seconds time elapsed 0.000855000 seconds user 0.000852000 seconds sys perf annotate: - Building with binutils' libopcode now is opt-in (BUILD_NONDISTRO=1) for licensing reasons, and we missed a build test on tools/perf/tests makefile. Since we now default to NDEBUG=1, we ended up segfaulting when building with BUILD_NONDISTRO=1 because a needed initialization routine was being "error checked" via an assert. Fix it by explicitly checking the result and aborting instead if it fails. We better back propagate the error, but at least 'perf annotate' on samples collected for a BPF program is back working when perf is built with BUILD_NONDISTRO=1. perf report/top: - Add back TUI hierarchy mode header, that is seen when using 'perf report/top --hierarchy'. - Fix the number of entries for 'e' key in the TUI that was preventing navigation of lines when expanding an entry. perf report/script: - Support cross platform register handling, allowing a perf.data file collected on one architecture to have registers sampled correctly displayed when analysis tools such as 'perf report' and 'perf script' are used on a different architecture. - Fix handling of event attributes in pipe mode, i.e. when one uses: perf record -o - | perf report -i - When no perf.data files are used. - Handle files generated via pipe mode with a version of perf and then read also via pipe mode with a different version of perf, where the event attr record may have changed, use the record size field to properly support this version mismatch. perf probe: - Accessing global variables from uprobes isn't supported, make the error message state that instead of stating that some minimal kernel version is needed to have that feature. This seems just a tool limitation, the kernel probably has all that is needed. perf tests: - Fix a reference count related leak in the dlfilter v0 API where the result of a thread__find_symbol_fb() is not matched with an addr_location__exit() to drop the reference counts of the resolved components (machine, thread, map, symbol, etc). Add a dlfilter test to make sure that doesn't regresses. - Lots of fixes for the 'perf test' written in shell script related to problems found with the shellcheck utility. - Fixes for 'perf test' shell scripts testing features enabled when perf is built with BUILD_BPF_SKEL=1, such as 'perf stat' bpf counters. - Add perf record sample filtering test, things like the following example, that gets implemented as a BPF filter attached to the event: # perf record -e task-clock -c 10000 --filter 'ip < 0xffffffff00000000' - Improve the way the task_analyzer test checks if libtraceevent is linked, using 'perf version --build-options' instead of the more expensinve 'perf record -e "sched:sched_switch"'. - Add support for riscv in the mmap-basic test. (This went as well via the RiscV tree, same contents). libperf: - Implement riscv mmap support (This went as well via the RiscV tree, same contents). perf script: - New tool that converts perf.data files to the firefox profiler format so that one can use the visualizer at https://profiler.firefox.com/. Done by Anup Sharma as part of this year's Google Summer of Code. One can generate the output and upload it to the web interface but Anup also automated everything: perf script gecko -F 99 -a sleep 60 - Support syscall name parsing on arm64. - Print "cgroup" field on the same line as "comm". perf bench: - Add new 'uprobe' benchmark to measure the overhead of uprobes with/without BPF programs attached to it. - breakpoints are not available on power9, skip that test. perf stat: - Add #num_cpus_online literal to be used in 'perf stat' metrics, and add this extra 'perf test' check that exemplifies its purpose: TEST_ASSERT_VAL("#num_cpus_online", expr__parse(&num_cpus_online, ctx, "#num_cpus_online") == 0); TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0); TEST_ASSERT_VAL("#num_cpus >= #num_cpus_online", num_cpus >= num_cpus_online); Miscellaneous: - Improve tool startup time by lazily reading PMU, JSON, sysfs data. - Improve error reporting in the parsing of events, passing YYLTYPE to error routines, so that the output can show were the parsing error was found. - Add 'perf test' entries to check the parsing of events improvements. - Fix various leak for things detected by -fsanitize=address, mostly things that would be freed at tool exit, including: - Free evsel->filter on the destructor. - Allow tools to register a thread->priv destructor and use it in 'perf trace'. - Free evsel->priv in 'perf trace'. - Free string returned by synthesize_perf_probe_point() when the caller fails to do all it needs. - Adjust various compiler options to not consider errors some warnings when building with broken headers found in things like python, flex, bison, as we otherwise build with -Werror. Some for gcc, some for clang, some for some specific version of those, some for some specific version of flex or bison, or some specific combination of these components, bah. - Allow customization of clang options for BPF target, this helps building on gentoo where there are other oddities where BPF targets gets passed some compiler options intended for the native build, so building with WERROR=0 helps while these oddities are fixed. - Dont pass ERR_PTR() values to perf_session__delete() in 'perf top' and 'perf lock', fixing some segfaults when handling some odd failures. - Add LTO build option. - Fix format of unordered lists in the perf docs (tools/perf/Documentation) - Overhaul the bison files, using constructs such as YYNOMEM. - Remove unused tokens from the bison .y files. - Add more comments to various structs. - A few LoongArch enablement patches. Vendor events (JSON): - Add JSON metrics for Yitian 710 DDR (aarch64). Things like: EventName, BriefDescription visible_window_limit_reached_rd, "At least one entry in read queue reaches the visible window limit.", visible_window_limit_reached_wr, "At least one entry in write queue reaches the visible window limit.", op_is_dqsosc_mpc , "A DQS Oscillator MPC command to DRAM.", op_is_dqsosc_mrr , "A DQS Oscillator MRR command to DRAM.", op_is_tcr_mrr , "A Temperature Compensated Refresh(TCR) MRR command to DRAM.", - Add AmpereOne metrics (aarch64). - Update N2 and V2 metrics (aarch64) and events using Arm telemetry repo. - Update scale units and descriptions of common topdown metrics on aarch64. Things like: - "MetricExpr": "stall_slot_frontend / (#slots * cpu_cycles)", - "BriefDescription": "Frontend bound L1 topdown metric", + "MetricExpr": "100 * (stall_slot_frontend / (#slots * cpu_cycles))", + "BriefDescription": "This metric is the percentage of total slots that were stalled due to resource constraints in the frontend of the processor.", - Update events for intel: meteorlake to 1.04, sapphirerapids to 1.15, Icelake+ metric constraints. - Update files for the power10 platform" * tag 'perf-tools-for-v6.6-1-2023-09-05' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (217 commits) perf parse-events: Fix driver config term perf parse-events: Fixes relating to no_value terms perf parse-events: Fix propagation of term's no_value when cloning perf parse-events: Name the two term enums perf list: Don't print Unit for "default_core" perf vendor events intel: Fix modifier in tma_info_system_mem_parallel_reads for skylake perf dlfilter: Avoid leak in v0 API test use of resolve_address() perf metric: Add #num_cpus_online literal perf pmu: Remove str from perf_pmu_alias perf parse-events: Make common term list to strbuf helper perf parse-events: Minor help message improvements perf pmu: Avoid uninitialized use of alias->str perf jevents: Use "default_core" for events with no Unit perf test stat_bpf_counters_cgrp: Enhance perf stat cgroup BPF counter test perf test shell stat_bpf_counters: Fix test on Intel perf test shell record_bpf_filter: Skip 6.2 kernel libperf: Get rid of attr.id field perf tools: Convert to perf_record_header_attr_id() libperf: Add perf_record_header_attr_id() perf tools: Handle old data in PERF_RECORD_ATTR ...
2023-08-24perf pmu: Abstract alias/event structIan Rogers1-6/+2
In order to be able to lazily compute aliases/events for a PMU, move the struct perf_pmu_alias into pmu.c. Add perf_pmu__find_event and perf_pmu__for_each_event that take a callback that is called for the found event or for each event. The layout of struct pmu and the event/alias list is unchanged but the API is altered so that aliases are no longer directly accessed, allowing for later changes. Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Gaosheng Cui <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: James Clark <[email protected]> Cc: Jing Zhang <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Kajol Jain <[email protected]> Cc: Kan Liang <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Ravi Bangoria <[email protected]> Cc: Rob Herring <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-08-23perf bench breakpoint: Skip run if no breakpoints availableKajol Jain1-3/+21
Based on commit 7d54a4acd8c1de3e ("perf test: Skip watchpoint tests if no watchpoints available"), hardware breakpoints are not available for power9 platform and because of that 'perf bench breakpoint' run fails on power9 platform. Add code to check for the return value of perf_event_open() in the breakpoint run and skip the 'perf bench breakpoint' run, if hardware breakpoints are not available. Result on power9 system before patch changes: [command]# perf bench breakpoint thread perf_event_open: No such device Result on power9 system after patch changes: [command]# ./perf bench breakpoint thread Skipping perf bench breakpoint thread: No hardware support Reported-by: Disha Goel <[email protected]> Signed-off-by: Kajol Jain <[email protected]> Acked-by: Naveen N Rao <[email protected]> Cc: Athira Rajeev <[email protected]> Cc: Disha Goel <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Madhavan Srinivasan <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Naveen N. Rao <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-07-20perf bench uprobe trace_printk: Add entry attaching an BPF program that does ↵Arnaldo Carvalho de Melo2-11/+29
a trace_printk [root@five ~]# perf bench uprobe all # Running uprobe/baseline benchmark... # Executed 1,000 usleep(1000) calls Total time: 1,053,963 usecs 1,053.963 usecs/op # Running uprobe/empty benchmark... # Executed 1,000 usleep(1000) calls Total time: 1,056,293 usecs +2,330 to baseline 1,056.293 usecs/op 2.330 usecs/op to baseline # Running uprobe/trace_printk benchmark... # Executed 1,000 usleep(1000) calls Total time: 1,056,977 usecs +3,014 to baseline +684 to previous 1,056.977 usecs/op 3.014 usecs/op to baseline 0.684 usecs/op to previous [root@five ~]# Acked-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Andre Fredette <[email protected]> Cc: Clark Williams <[email protected]> Cc: Dave Tucker <[email protected]> Cc: Derek Barbosa <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Masami Hiramatsu (Google) <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-07-20perf bench uprobe empty: Add entry attaching an empty BPF programArnaldo Carvalho de Melo2-3/+73
Using libbpf and a BPF skel: # perf bench uprobe all # Running uprobe/baseline benchmark... # Executed 1,000 usleep(1000) calls Total time: 1,055,618 usecs 1,055.618 usecs/op # Running uprobe/empty benchmark... # Executed 1,000 usleep(1000) calls Total time: 1,057,146 usecs +1,528 to baseline 1,057.146 usecs/op # Acked-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Andre Fredette <[email protected]> Cc: Clark Williams <[email protected]> Cc: Dave Tucker <[email protected]> Cc: Derek Barbosa <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Masami Hiramatsu (Google) <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-07-20perf bench uprobe: Show diff to previousArnaldo Carvalho de Melo1-5/+16
Will be useful to show the incremental overhead as we do more stuff in the BPF program attached to the uprobes. Acked-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Andre Fredette <[email protected]> Cc: Clark Williams <[email protected]> Cc: Dave Tucker <[email protected]> Cc: Derek Barbosa <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Masami Hiramatsu (Google) <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-07-20perf bench uprobe: Print diff to baselineArnaldo Carvalho de Melo1-3/+24
This is just prep work to show the diff to the unmodified workload. Acked-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Andre Fredette <[email protected]> Cc: Clark Williams <[email protected]> Cc: Dave Tucker <[email protected]> Cc: Derek Barbosa <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Masami Hiramatsu (Google) <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-07-20perf bench uprobe: Add benchmark to test uprobe overheadArnaldo Carvalho de Melo3-0/+82
This just adds the initial "workload", a call to libc's usleep(1000us) function: $ perf stat --null perf bench uprobe all # Running uprobe/baseline benchmark... # Executed 1000 usleep(1000) calls Total time: 1053533 usecs 1053.533 usecs/op Performance counter stats for 'perf bench uprobe all': 1.061042896 seconds time elapsed 0.001079000 seconds user 0.006499000 seconds sys $ More entries will be added using a BPF skel to add various uprobes to the usleep() function. Acked-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Andre Fredette <[email protected]> Cc: Clark Williams <[email protected]> Cc: Dave Tucker <[email protected]> Cc: Derek Barbosa <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Masami Hiramatsu (Google) <[email protected]> Cc: Namhyung Kim <[email protected]> Link: https://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-07-17perf/benchmark: add a new benchmark for seccom_unotifyAndrei Vagin3-0/+180
The benchmark is similar to the pipe benchmark. It creates two processes, one is calling syscalls, and another process is handling them via seccomp user notifications. It measures the time required to run a specified number of interations. $ ./perf bench sched seccomp-notify --sync-mode --loop 1000000 # Running 'sched/seccomp-notify' benchmark: # Executed 1000000 system calls Total time: 2.769 [sec] 2.769629 usecs/op 361059 ops/sec $ ./perf bench sched seccomp-notify # Running 'sched/seccomp-notify' benchmark: # Executed 1000000 system calls Total time: 8.571 [sec] 8.571119 usecs/op 116670 ops/sec Signed-off-by: Andrei Vagin <[email protected]> Acked-by: "Peter Zijlstra (Intel)" <[email protected]> Link: https://lore.kernel.org/r/[email protected] Link: https://lore.kernel.org/r/[email protected] [kees: Added PRIu64 format string] Signed-off-by: Kees Cook <[email protected]>
2023-06-12perf bench sched messaging: Free contexts on exitIan Rogers1-1/+17
Place sender and receiver contexts onto lists so that they may be freed on exit. Add missing pthread_attr_destroy. Fixes memory leaks reported by leak sanitizer. Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: André Almeida <[email protected]> Cc: Darren Hart <[email protected]> Cc: Davidlohr Bueso <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Thomas Gleixner <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-06-12perf bench futex: Avoid memory leaks from pthread_attrIan Rogers4-26/+29
Remove code sharing the pthread_attr_t and initialize/destroy pthread_attr_t when needed. This avoids the same attribute being set that leak sanitizer reports as a memory leak. Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: André Almeida <[email protected]> Cc: Darren Hart <[email protected]> Cc: Davidlohr Bueso <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Thomas Gleixner <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-06-12perf bench epoll: Fix missing frees/puts on the exit pathIan Rogers2-0/+10
Issues detected by leak sanitizer. Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: André Almeida <[email protected]> Cc: Darren Hart <[email protected]> Cc: Davidlohr Bueso <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Thomas Gleixner <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-05-27perf pmus: Allow just core PMU scanningIan Rogers1-21/+29
Scanning all PMUs is expensive as all PMUs sysfs entries are loaded, benchmarking shows more than 4x the cost: ``` $ perf bench internals pmu-scan -i 1000 Computing performance of sysfs PMU event scan for 1000 times Average core PMU scanning took: 989.231 usec (+- 1.535 usec) Average PMU scanning took: 4309.425 usec (+- 74.322 usec) ``` Add new perf_pmus__scan_core routine that scans just core PMUs. Replace perf_pmus__scan calls with perf_pmus__scan_core when non-core PMUs are being ignored. Reviewed-by: Kan Liang <[email protected]> Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ali Saidi <[email protected]> Cc: Athira Rajeev <[email protected]> Cc: Dmitrii Dolgov <[email protected]> Cc: Huacai Chen <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: James Clark <[email protected]> Cc: Jing Zhang <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Kajol Jain <[email protected]> Cc: Kang Minchul <[email protected]> Cc: Leo Yan <[email protected]> Cc: Madhavan Srinivasan <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mike Leach <[email protected]> Cc: Ming Wang <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Ravi Bangoria <[email protected]> Cc: Rob Herring <[email protected]> Cc: Sandipan Das <[email protected]> Cc: Sean Christopherson <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Thomas Richter <[email protected]> Cc: Will Deacon <[email protected]> Cc: Xing Zhengjun <[email protected]> Cc: [email protected] Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-05-27perf pmu: Separate pmu and pmusIan Rogers1-5/+5
Separate and hide the pmus list in pmus.[ch]. Move pmus functionality out of pmu.[ch] into pmus.[ch] renaming pmus functions which were prefixed perf_pmu__ to perf_pmus__. Reviewed-by: Kan Liang <[email protected]> Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ali Saidi <[email protected]> Cc: Athira Rajeev <[email protected]> Cc: Dmitrii Dolgov <[email protected]> Cc: Huacai Chen <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: James Clark <[email protected]> Cc: Jing Zhang <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Kajol Jain <[email protected]> Cc: Kang Minchul <[email protected]> Cc: Leo Yan <[email protected]> Cc: Madhavan Srinivasan <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mike Leach <[email protected]> Cc: Ming Wang <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Ravi Bangoria <[email protected]> Cc: Rob Herring <[email protected]> Cc: Sandipan Das <[email protected]> Cc: Sean Christopherson <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Thomas Richter <[email protected]> Cc: Will Deacon <[email protected]> Cc: Xing Zhengjun <[email protected]> Cc: [email protected] Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-05-27perf pmus: Prefer perf_pmu__scan over perf_pmus__for_each_pmuIan Rogers1-4/+2
perf_pmus__for_each_pmu doesn't lazily initialize pmus making its use error prone. Just use perf_pmu__scan as this only impacts non-performance critical tests. Reviewed-by: Kan Liang <[email protected]> Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ali Saidi <[email protected]> Cc: Athira Rajeev <[email protected]> Cc: Dmitrii Dolgov <[email protected]> Cc: Huacai Chen <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: James Clark <[email protected]> Cc: Jing Zhang <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: John Garry <[email protected]> Cc: Kajol Jain <[email protected]> Cc: Kang Minchul <[email protected]> Cc: Leo Yan <[email protected]> Cc: Madhavan Srinivasan <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Mike Leach <[email protected]> Cc: Ming Wang <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Ravi Bangoria <[email protected]> Cc: Rob Herring <[email protected]> Cc: Sandipan Das <[email protected]> Cc: Sean Christopherson <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Thomas Richter <[email protected]> Cc: Will Deacon <[email protected]> Cc: Xing Zhengjun <[email protected]> Cc: [email protected] Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-05-17tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench'Arnaldo Carvalho de Melo4-10/+2
This is to get the changes from: 68674f94ffc9dddc ("x86: don't use REP_GOOD or ERMS for small memory copies") 20f3337d350c4e1b ("x86: don't use REP_GOOD or ERMS for small memory clearing") This also make the 'perf bench mem' files stop referring to the erms versions that gone away with the above patches. That addresses these perf tools build warning: Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S' diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S' diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-04-12perf bench inject-buildid: Use zfree() to reduce chances of use after freeArnaldo Carvalho de Melo1-1/+2
Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-04-04perf bench: Add pmu-scan benchmarkNamhyung Kim3-0/+186
The pmu-scan benchmark will repeatedly scan the sysfs to get the available PMU information. $ ./perf bench internals pmu-scan # Running 'internals/pmu-scan' benchmark: Computing performance of sysfs PMU event scan for 100 times Average PMU scanning took: 6850.990 usec (+- 48.445 usec) Signed-off-by: Namhyung Kim <[email protected]> Acked-by: Ian Rogers <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Kan Liang <[email protected]> Cc: Leo Yan <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-04-04perf bench numa: Fix type of loop iterator in do_work, it should be 'long'Andreas Herrmann1-1/+1
'j' is of type int and start/end are of type 'long'. Thus 'j' might become negative and cause segfault in access_data(). Fix it by using 'long' for 'j' as well. Reviewed-by: James Clark <[email protected]> Signed-off-by: Andreas Herrmann <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-04-04perf bench: Avoid NDEBUG warningIan Rogers1-2/+6
With NDEBUG set the asserts are compiled out. This yields "unused-but-set-variable" variables. Move these variables behind NDEBUG to avoid the warning. Signed-off-by: Ian Rogers <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Paolo Bonzini <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Sean Christopherson <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-04-04perf bench syscall: Add fork syscall benchmarkTiezhu Yang2-0/+36
This is a follow up patch for the execve bench which is actually fork + execve, it makes sense to add the fork syscall benchmark to compare the execve part precisely. Some archs have no __NR_fork definition which is used only as a check condition to call test_fork(), let us just define it as -1 to avoid build error. Suggested-by: Namhyung Kim <[email protected]> Signed-off-by: Tiezhu Yang <[email protected]> Acked-by: Namhyung Kim <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-02-02perf bench syscall: Add execve syscall benchmarkTiezhu Yang2-0/+37
This commit adds the execve syscall benchmark, more syscall benchmarks can be added in the future. Signed-off-by: Tiezhu Yang <[email protected]> Acked-by: Namhyung Kim <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-02-02perf bench syscall: Add getpgid syscall benchmarkTiezhu Yang2-0/+12
This commit adds a simple getpgid syscall benchmark, more syscall benchmarks can be added in the future. Signed-off-by: Tiezhu Yang <[email protected]> Acked-by: Namhyung Kim <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2023-02-02perf bench syscall: Introduce bench_syscall_common()Tiezhu Yang1-4/+25
In the current code, there is only a basic syscall benchmark via getppid, this is not enough. Introduce bench_syscall_common() so that we can add more syscalls to benchmark. This is preparation for later patch, no functionality change. Signed-off-by: Tiezhu Yang <[email protected]> Acked-by: Namhyung Kim <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-12-20Merge tag 'parisc-for-6.2-1' of ↵Linus Torvalds1-12/+0
git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux Pull parisc updates from Helge Deller: "There is one noteable patch, which allows the parisc kernel to use the same MADV_xxx constants as the other architectures going forward. With that change only alpha has one entry left (MADV_DONTNEED is 6 vs 4 on others) which is different. To prevent an ABI breakage, a wrapper is included which translates old MADV values to the new ones, so existing userspace isn't affected. Reason for that patch is, that some applications wrongly used the standard MADV_xxx values even on some non-x86 platforms and as such those programs failed to run correctly on parisc (examples are qemu-user, tor browser and boringssl). Then the kgdb console and the LED code received some fixes, and some 0-day warnings are now gone. Finally, the very last compile warning which was visible during a kernel build is now fixed too (in the vDSO code). The majority of the patches are tagged for stable series and in summary this patchset is quite small and drops more code than it adds: Fixes: - Fix potential null-ptr-deref in start_task() - Fix kgdb console on serial port - Add missing FORCE prerequisites in Makefile - Drop PMD_SHIFT from calculation in pgtable.h Enhancements: - Implement a wrapper to align madvise() MADV_* constants with other architectures - If machine supports running MPE/XL, show the MPE model string Cleanups: - Drop duplicate kgdb console code - Indenting fixes in setup_cmdline()" * tag 'parisc-for-6.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux: parisc: Show MPE/iX model string at bootup parisc: Add missing FORCE prerequisites in Makefile parisc: Move pdc_result struct to firmware.c parisc: Drop locking in pdc console code parisc: Drop duplicate kgdb_pdc console parisc: Fix locking in pdc_iodc_print() firmware call parisc: Drop PMD_SHIFT from calculation in pgtable.h parisc: Align parisc MADV_XXX constants with all other architectures parisc: led: Fix potential null-ptr-deref in start_task() parisc: Fix inconsistent indenting in setup_cmdline()
2022-12-17parisc: Align parisc MADV_XXX constants with all other architecturesHelge Deller1-12/+0
Adjust some MADV_XXX constants to be in sync what their values are on all other platforms. There is currently no reason to have an own numbering on parisc, but it requires workarounds in many userspace sources (e.g. glibc, qemu, ...) - which are often forgotten and thus introduce bugs and different behaviour on parisc. A wrapper avoids an ABI breakage for existing userspace applications by translating any old values to the new ones, so this change allows us to move over all programs to the new ABI over time. Signed-off-by: Helge Deller <[email protected]>
2022-12-05perf tools: Use dedicated non-atomic clear/set bit helpersSean Christopherson1-1/+1
Use the dedicated non-atomic helpers for {clear,set}_bit() and their test variants, i.e. the double-underscore versions. Depsite being defined in atomic.h, and despite the kernel versions being atomic in the kernel, tools' {clear,set}_bit() helpers aren't actually atomic. Move to the double-underscore versions so that the versions that are expected to be atomic (for kernel developers) can be made atomic without affecting users that don't want atomic operations. No functional change intended. Signed-off-by: Sean Christopherson <[email protected]> Acked-by: Namhyung Kim <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Andy Shevchenko <[email protected]> Cc: James Morse <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Marc Zyngier <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Oliver Upton <[email protected]> Cc: Paolo Bonzini <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Rasmus Villemoes <[email protected]> Cc: Sean Christopherson <[email protected]> Cc: Suzuki Poulouse <[email protected]> Cc: Yury Norov <[email protected]> Cc: alexandru elisei <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-10-31perf tools: Move 'struct perf_sample' to a separate header file to ↵Arnaldo Carvalho de Melo1-1/+1
disentangle headers Some places were including event.h just to get 'struct perf_sample', move it to a separate place so that we speed up a bit the build. Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-10-27perf tools: Make quiet mode consistent between toolsJames Clark1-4/+5
Use the global quiet variable everywhere so that all tools hide warnings in quiet mode and update the documentation to reflect this. 'perf probe' claimed that errors are not printed in quiet mode but I don't see this so remove it from the docs. Signed-off-by: James Clark <[email protected]> Cc: Adrian Hunter <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Ian Rogers <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-10-04perf bench: Update use of pthread mutex/condIan Rogers8-171/+153
Switch to the use of mutex wrappers that provide better error checking. Signed-off-by: Ian Rogers <[email protected]> Reviewed-by: Adrian Hunter <[email protected]> Acked-by: Namhyung Kim <[email protected]> Cc: Alexander Shishkin <[email protected]> Cc: Alexandre Truong <[email protected]> Cc: Alexey Bayduraev <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Andres Freund <[email protected]> Cc: Andrii Nakryiko <[email protected]> Cc: André Almeida <[email protected]> Cc: Athira Jajeev <[email protected]> Cc: Christophe JAILLET <[email protected]> Cc: Colin Ian King <[email protected]> Cc: Dario Petrillo <[email protected]> Cc: Darren Hart <[email protected]> Cc: Dave Marchevsky <[email protected]> Cc: Davidlohr Bueso <[email protected]> Cc: Fangrui Song <[email protected]> Cc: Hewenliang <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: James Clark <[email protected]> Cc: Jason Wang <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Kajol Jain <[email protected]> Cc: Kim Phillips <[email protected]> Cc: Leo Yan <[email protected]> Cc: Mark Rutland <[email protected]> Cc: Martin Liška <[email protected]> Cc: Masami Hiramatsu <[email protected]> Cc: Nathan Chancellor <[email protected]> Cc: Nick Desaulniers <[email protected]> Cc: Pavithra Gurushankar <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Quentin Monnet <[email protected]> Cc: Ravi Bangoria <[email protected]> Cc: Remi Bernon <[email protected]> Cc: Riccardo Mancini <[email protected]> Cc: Song Liu <[email protected]> Cc: Stephane Eranian <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Thomas Richter <[email protected]> Cc: Tom Rix <[email protected]> Cc: Weiguo Li <[email protected]> Cc: Wenyu Liu <[email protected]> Cc: William Cohen <[email protected]> Cc: Zechuan Chen <[email protected]> Cc: [email protected] Cc: [email protected] Cc: yaowenbin <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-05-23Merge remote-tracking branch 'torvalds/master' into perf/coreArnaldo Carvalho de Melo1-1/+1
To get the rest of 5.18. Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2022-05-21perf bench numa: Address compiler error on s390Thomas Richter1-1/+1
The compilation on s390 results in this error: # make DEBUG=y bench/numa.o ... bench/numa.c: In function ‘__bench_numa’: bench/numa.c:1749:81: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size between 10 and 20 [-Werror=format-truncation=] 1749 | snprintf(tname, sizeof(tname), "process%d:thread%d", p, t); ^~ ... bench/numa.c:1749:64: note: directive argument in the range [-2147483647, 2147483646] ... # The maximum length of the %d replacement is 11 characters because of the negative sign. Therefore extend the array by two more characters. Output after: # make DEBUG=y bench/numa.o > /dev/null 2>&1; ll bench/numa.o -rw-r--r-- 1 root root 418320 May 19 09:11 bench/numa.o # Fixes: 3aff8ba0a4c9c919 ("perf bench numa: Avoid possible truncation when using snprintf()") Suggested-by: Namhyung Kim <[email protected]> Signed-off-by: Thomas Richter <[email protected]> Cc: Heiko Carstens <[email protected]> Cc: Sumanth Korikkar <[email protected]> Cc: Sven Schnelle <[email protected]> Cc: Vasily Gorbik <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>