- 29 Nov, 2017 3 commits
-
-
Ingo Molnar authored
Signed-off-by:Ingo Molnar <mingo@kernel.org>
-
Ingo Molnar authored
Merge branch 'perf/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent Pull perf tooling fixes from Arnaldo Carvalho de Melo: "- Fix window dimensions change handling in 'perf top' (Jiri Olsa) - Fix 'perf record -c/-F' options for CPU event aliases (Andi Kleen) - Generate PERF_RECORD_{MMAP,COMM,EXEC} with 'perf record --delay' fixing symbol resolution for processes created, maps put in place while --delay happens (Arnaldo Carvalho de Melo) - Fix up leftover perf_evsel_stat usage via evsel->priv, plugging a SEGV when using event groups as in: $ perf stat -e '{cpu-clock,instructions}' workload - Fix 'perf script --per-event-dump' for auxtrace synth evsels (Arnaldo Carvalho de Melo) - Ignore kptr_restrict when not sampling the kernel (Arnaldo Carvalho de Melo) - Synchronize kernel ABI headers wrt SPDX tags and ABI changes, taking minimal action to handle new syscall args and silencing perf build warnings (Arnaldo Carvalho de Melo, Ingo Molnar) - Fix header.size for namespace events (Jiri Olsa) - Fix a bug during strstart() conversion in 'perf help' (Namhyung Kim) - Do not truncate instruction names at 6 chars in 'perf annotate', there are really long instruction names in PPC (Ravi Bangoria) - Fixup discontiguous/sparse numa nodes in 'perf bench numa' (Satheesh Rajendran) - Fix an exit code of trace__symbols_init in 'perf trace' (Andrei Vagin) - Fix 'perf test' entries on s/390 (Thomas Richter) - Bring instruction decoder files used by Intel PT into line with the kernel, silencing build warning (Adrian Hunter)" Signed-off-by:
-
Ingo Molnar authored
Signed-off-by:
-
- 28 Nov, 2017 29 commits
-
-
Arnaldo Carvalho de Melo authored
To add support for the MAP_SYNC flag introduced in: b6fb293f ("mm: Define MAP_SYNC and VM_SYNC flags") Update tools/perf/trace/beauty/mmap.c to support that flag. This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/mman.h' differs from latest version at 'include/uapi/asm-generic/mman.h' Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-14zyk3iywrj37c7g1eagmzbo@git.kernel.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Arnaldo Carvalho de Melo authored
To pick up changes from: 2d2123bc ("arm64/sve: Add prctl controls for userspace vector length management") 7582e220 ("arm64/sve: Backend logic for setting the vector length") That showed a limitation of the regexp used in tools/perf/trace/beauty/prctl_option.sh, that matches only PR_{SET,GET}_, but should match a few more, like PR_MPX_*, PR_CAP_* and the one added by the above commit, PR_SVE_SET_*. This silences this warning when building tools/perf: Warning: Kernel ABI header at 'tools/include/uapi/linux/prctl.h' differs from latest version at 'include/uapi/linux/prctl.h' Support for those extra prctl options should be left for the next merge window tho. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Dave Martin <Dave.Martin@arm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Link: https://lkml.kernel.org/n/tip-r52dsyuzy04qzqyfcifjs35t@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To pick up changes from these csets: da9a1446 ("KVM: s390: provide a capability for AIS state migration") 5c5196da ("KVM: arm/arm64: Support EL1 phys timer register access in set/get reg") None of which affects buildint tools/perf/. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Christoffer Dall <cdall@linaro.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-dd72s6izo4qdzt1isowlz8ji@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To pick up the changes from these csets: bf64e0b0 ("drm/i915: Expand I915_PARAM_HAS_SCHEDULER into a capability bitmask") ac14fbd4 ("drm/i915/scheduler: Support user-defined priorities") 822a4b67 ("drm/i915: Don't use BIT() in UAPI section") 3fd3a6ff ("drm/i915: Simplify i915_reg_read_ioctl") None of them affects how the tools are built, this os done just to silence this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h' Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-d2gor8brpcowe7bcxovjhqwm@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To pick up the new ioctls added in these csets: 3064abfa ("drm: Add CRTC_GET_SEQUENCE and CRTC_QUEUE_SEQUENCE ioctls [v3]") 62884cd3 ("drm: Add four ioctls for managing drm mode object leases [v7]") That will be automatically decoded (the ioctl cmd parameter, the structs will be supported when we start using eBPF for that, which is in the works). This silences this warning when building tools/perf: Warning: Kernel ABI header at 'tools/include/uapi/drm/drm.h' differs from latest version at 'include/uapi/drm/drm.h' Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Dave Airlie <airlied@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Keith Packard <keithp@keithp.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-bivwf1pkfmi1ugpswbsxd9e9@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To get the changes in the 085b3062 ("perf/core: Add PERF_AUX_FLAG_COLLISION to report colliding samples") commit, that will be eventually used by perf to handle the ARM SPE architecture. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Link: https://lkml.kernel.org/n/tip-178ohv0oy0csq3kzfdk8ky4n@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Two more, that were just in perf/core and thus weren't covered by Ingo's latest headers synch, kcmp.h and prctl.h, silencing this: Warning: Kernel ABI header at 'tools/include/uapi/linux/kcmp.h' differs from latest version at 'include/uapi/linux/kcmp.h' Warning: Kernel ABI header at 'tools/include/uapi/linux/prctl.h' differs from latest version at 'include/uapi/linux/prctl.h' Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-2a0r7iybyqpkftllyy5t9hfk@git.kernel.orgSigned-off-by:
-
Ingo Molnar authored
Two x86 headers got modified in this merge window: arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/disabled-features.h To support x86 UMIP feature, to add new AVX instructions, plus cleanups. None of those changes have an effect on tooling, so do a plain copy. Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: -
Adrian Hunter authored
There are just a few new defines which do not affect perf tools. Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Link: http://lkml.kernel.org/r/1511253326-22308-3-git-send-email-adrian.hunter@intel.comSigned-off-by:
-
Thomas Richter authored
Test case 21 (Number of exit events of a simple workload) fails on s390x. The reason is the invalid sample frequency supplied for this test. On s390x the minimum sample frequency is much higher (see output of /proc/service_levels). Supply a save sample frequency value for s390x to fix this. The value will be adjusted by the s390x CPUMF frequency convertion function to a value well below the sysctl kernel.perf_event_max_sample_rate value. Signed-off-by:
Thomas Richter <tmricht@linux.vnet.ibm.com> Reviewed-by:
Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> LPU-Reference: 20171123114611.93397-1-tmricht@linux.vnet.ibm.com Link: https://lkml.kernel.org/n/tip-1ynblyhi1n81idpido59nt1y@git.kernel.orgSigned-off-by:
-
Satheesh Rajendran authored
Certain systems are designed to have sparse/discontiguous nodes. On such systems, 'perf bench numa' hangs, shows wrong number of nodes and shows values for non-existent nodes. Handle this by only taking nodes that are exposed by kernel to userspace. Signed-off-by:
Satheesh Rajendran <sathnaga@linux.vnet.ibm.com> Reviewed-by:
Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by:
Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1edbcd353c009e109e93d78f2f46381930c340fe.1511368645.git.sathnaga@linux.vnet.ibm.comSigned-off-by:
Balamuruhan S <bala24@linux.vnet.ibm.com> Signed-off-by:
-
Jiri Olsa authored
There's no need for SA_SIGINFO data in SIGWINCH handler, switching it to register the handler via signal interface as we do for the rest of the signals in perf top. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Tested-by:
Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Tested-by:
-
Jiri Olsa authored
The stdio perf top crashes when we change the terminal window size. The reason is that we assumed we get the perf_top pointer as a signal handler argument which is not the case. Changing the SIGWINCH handler logic to change global resize variable, which is checked in the main thread loop. Signed-off-by:
-
Jiri Olsa authored
Reset header size for namespace events, otherwise it only gets bigger in ctx iterations. Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Fixes: e4222673 ("perf: Add PERF_RECORD_NAMESPACES to include namespaces related info") Link: http://lkml.kernel.org/n/tip-nlo4gonz9d4guyb8153ukzt0@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
If all events have attr.exclude_kernel set, no need to look at kptr_restrict. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-yegpzg5bf2im69g0tfizqaqz@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
If we're not sampling the kernel, we shouldn't care about kptr_restrict neither synthesize anything for assisting in resolving kernel samples, like the reference relocation symbol or kernel modules information. Before: $ cat /proc/sys/kernel/kptr_restrict /proc/sys/kernel/perf_event_paranoid 2 2 $ perf record sleep 1 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check /proc/sys/kernel/kptr_restrict. Samples in kernel functions may not be resolved if a suitable vmlinux file is not found in the buildid cache or in the vmlinux path. Samples in kernel modules won't be resolved at all. If some relocation was applied (e.g. kexec) symbols may be misresolved even with a suitable vmlinux or kallsyms file. Couldn't record kernel reference relocation symbol Symbol resolution may be skewed if relocation was used (e.g. kexec). Check /proc/kallsyms permission or run as root. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ] $ perf evlist -v cycles:uppp: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, exclude_kernel: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 $ After: $ perf record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (10 samples) ] $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-t025e9zftbx2b8cq2w01g5e5@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
If none of the evsels has attr.exclude_kernel set to zero, no kernel samples, so no point in warning the user about problems in processing kernel samples, as there will be none. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-7dn926v3at8txxkky92aesz2@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
The warning about kptr_restrict needs to be emitted only when it is set and we ask for kernel space samples, so add a helper to help with that. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-fh7drty6yljei9gxxzer6eup@git.kernel.orgSigned-off-by:
-
Thomas Richter authored
The 'perf test' case "probe libc's inet_pton & backtrace it with ping" fails on s390x. The reason is the 'realpath /lib64/ld*.so.* | uniq' line which returns 2 libraries: root@s35lp76 shell]# realpath /lib64/ld*.so.* | uniq /usr/lib64/ld-2.26.so /usr/lib64/ld_pre_smc.so.1.0.1 [root@s35lp76 shell] This output makes the "perf probe" command lines invalid. Use ldd tool to find out the libraries required by "bash" and check if symbol "inet_pton" is part of the "libc" library. Some distros do not have a /lib64 directory. I have also added a check for the existence of an IPv6 network interface before it is being used. Committer changes: We can't really use ldd for libc, as in some systems, such as x86_64, it has hardlinks and then ldd sees one and the kernel the other, so grep for libc in /proc/self/maps to get the one we'll receive from PERF_RECORD_MMAP. Thomas checked this change and acked it. Signed-off-by: -
Thomas Richter authored
This 'perf test' case fails on s390x. The 'touch' command on s390x uses the 'openat' system call to open the file named on the command line: [root@s35lp76 perf]# perf probe -l probe:vfs_getname (on getname_flags:72@fs/namei.c with pathname) [root@s35lp76 perf]# perf trace -e open touch /tmp/abc 0.400 ( 0.015 ms): touch/27542 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3 [root@s35lp76 perf]# There is no 'open' system call for file '/tmp/abc'. Instead the 'openat' system call is used: [root@s35lp76 perf]# strace touch /tmp/abc execve("/usr/bin/touch", ["touch", "/tmp/abc"], 0x3ffd547ec98 /* 30 vars */) = 0 [...] openat(AT_FDCWD, "/tmp/abc", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 [...] On s390x the 'egrep' command does not find a matching pattern and returns an error. Fix this for s390x create a platform dependent command line to enable the 'perf probe' call to listen to the 'openat' system call and get the expected output. Signed-off-by: -
Ravi Bangoria authored
There are many instructions, esp on PowerPC, whose mnemonics are longer than 6 characters. Using precision limit causes truncation of such mnemonics. Fix this by removing precision limit. Note that, 'width' is still 6, so alignment won't get affected for length <= 6. Before: li r11,-1 xscvdp vs1,vs1 add. r10,r10,r11 After: li r11,-1 xscvdpsxds vs1,vs1 add. r10,r10,r11 Reported-by:
Donald Stence <dstence@us.ibm.com> Signed-off-by:
-
Namhyung Kim authored
The commit 8e99b6d4 changed prefixcmp() to strstart() but missed to change the return value in some place. It makes perf help print annoying output even for sane config items like below: $ perf help '.root': unsupported man viewer sub key. ... Reported-by:
Namhyung Kim <namhyung@kernel.org> Tested-by:
Taeung Song <treeze.taeung@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Sihyeon Jang <uneedsihyeon@gmail.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20171114001542.GA16464@sejong Fixes: 8e99b6d4 ("tools include: Adopt strstarts() from the kernel") Signed-off-by:
-
Arnaldo Carvalho de Melo authored
A recent fix for 'perf trace' introduced a bug where machine__exit(trace->host) could be called while trace->host was still NULL, so make this more robust by guarding against NULL, just like free() does. The problem happens, for instance, when !root users try to run 'perf trace': [acme@jouet linux]$ trace Error: No permissions to read /sys/kernel/debug/tracing/events/raw_syscalls/sys_(enter|exit) Hint: Try 'sudo mount -o remount,mode=755 /sys/kernel/debug/tracing' perf: Segmentation fault Obtained 7 stack frames. [0x4f1b2e] /lib64/libc.so.6(+0x3671f) [0x7f43a1dd971f] [0x4f3fec] [0x47468b] [0x42a2db] /lib64/libc.so.6(__libc_start_main+0xe9) [0x7f43a1dc3509] [0x42a6c9] Segmentation fault (core dumped) [acme@jouet linux]$ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andrei Vagin <avagin@openvz.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vasily Averin <vvs@virtuozzo.com> Cc: Wang Nan <wangnan0@huawei.com> Fixes: 33974a41 ("perf trace: Call machine__exit() at exit") Signed-off-by:
-
Arnaldo Carvalho de Melo authored
When processing PERF_RECORD_AUXTRACE_INFO several perf_evsel entries will be synthesized and inserted into session->evlist, eventually ending in perf_script.tool.sample(), which ends up calling builtin-script.c's process_event(), that expects evsel->priv to be a perf_evsel_script object with a valid FILE pointer in fp. So we need to intercept the processing of PERF_RECORD_AUXTRACE_INFO and then setup evsel->priv for these newly created perf_evsel instances, do it to fix the segfault in process_event() trying to use a NULL for that FILE pointer. Reported-by:
Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Cc: Wang Nan <wangnan0@huawei.com> Cc: yuzhoujian <yuzhoujian@didichuxing.com> Fixes: a14390fd ("perf script: Allow creating per-event dump files") Link: http://lkml.kernel.org/n/tip-bthnur8r8de01gxvn2qayx6e@git.kernel.org [ Merge fix by Ravi Bangoria before pushing upstream to preserv bisectability ] Signed-off-by:
-
Arnaldo Carvalho de Melo authored
I forgot one conversion, which got noticed by Thomas when running: $ perf stat -e '{cpu-clock,instructions}' kill kill: not enough arguments Segmentation fault (core dumped) $ Fix it, those stats are in evsel->stats, not anymore in evsel->priv. Reported-by: -
Andrei Vagin authored
Currently if trace_event__register_resolver() fails, we return -errno, but we can't be sure that errno isn't zero in this case. Signed-off-by:
Andrei Vagin <avagin@openvz.org> Reviewed-by:
Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vasily Averin <vvs@virtuozzo.com> Link: http://lkml.kernel.org/r/20171108002246.8924-2-avagin@openvz.orgSigned-off-by:
-
Andi Kleen authored
The Intel PMU event aliases have a implicit period= specifier to set the default period. Unfortunately this breaks overriding these periods with -c or -F, because the alias terms look like they are user specified to the internal parser, and user specified event qualifiers override the command line options. Track that they are coming from aliases by adding a "weak" state to the term. Any weak terms don't override command line options. I only did it for -c/-F for now, I think that's the only case that's broken currently. Before: $ perf record -c 1000 -vv -e uops_issued.any ... { sample_period, sample_freq } 2000003 After: $ perf record -c 1000 -vv -e uops_issued.any ... { sample_period, sample_freq } 1000 Signed-off-by:Andi Kleen <ak@linux.intel.com> Acked-by:
-
Arnaldo Carvalho de Melo authored
When we use an initial delay, e.g.: 'perf record --delay 1000', we do not enable the events until that delay has passed after we started the workload, including the tracking event, i.e. the one for which we have attr.mmap, etc, enabled to ask the kernel to generate the PERF_RECORD_{MMAP,COMM,EXEC} metadata events that will then allow us to resolve addresses in samples to the map, dso and symbol. There will be a shadow that even synthesizing samples won't cover, i.e. the workload that we start and other processes forking while we wait for the initial delay to expire. So use a dummy event to be the tracking one and make it be enabled on exec. Before: # perf record --delay 1000 stress --cpu 1 --timeout 5 stress: info: [9029] dispatching hogs: 1 cpu, 0 io, 0 vm, 0 hdd stress: info: [9029] successful run completed in 5s [ perf record: Woken up 3 times to write data ] [ perf record: Captured and wrote 0.624 MB perf.data (15908 samples) ] # perf script | head :9031 9031 32001.826888: 1 cycles:ppp: ffffffff831aa30d event_function (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826893: 1 cycles:ppp: ffffffff8300d1a0 intel_bts_enable_local (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826895: 7 cycles:ppp: ffffffff83023870 sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826897: 103 cycles:ppp: ffffffff8300c331 intel_pmu_handle_irq (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826899: 1615 cycles:ppp: ffffffff830231f8 native_sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826902: 26724 cycles:ppp: ffffffff8384c6a7 native_irq_return_iret (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826913: 329739 cycles:ppp: 7fb2a5410932 [unknown] ([unknown]) :9031 9031 32001.827033: 1225451 cycles:ppp: 7fb2a5410930 [unknown] ([unknown]) :9031 9031 32001.827474: 1391725 cycles:ppp: 7fb2a5410930 [unknown] ([unknown]) :9031 9031 32001.827978: 1233697 cycles:ppp: 7fb2a5410928 [unknown] ([unknown]) # After: # perf record --delay 1000 stress --cpu 1 --timeout 5 stress: info: [9741] dispatching hogs: 1 cpu, 0 io, 0 vm, 0 hdd stress: info: [9741] successful run completed in 5s [ perf record: Woken up 3 times to write data ] [ perf record: Captured and wrote 0.751 MB perf.data (15976 samples) ] # perf script | head stress 9742 32110.959106: 1 cycles:ppp: ffffffff831b26f6 __perf_event_task_sched_in (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959110: 1 cycles:ppp: ffffffff8300c2e9 intel_pmu_handle_irq (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959112: 7 cycles:ppp: ffffffff830231e0 native_sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959115: 101 cycles:ppp: ffffffff83023870 sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959117: 1533 cycles:ppp: ffffffff830231f8 native_sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959119: 23992 cycles:ppp: ffffffff831b0900 ctx_sched_in (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959129: 329406 cycles:ppp: 7f4b1b661930 __random_r (/usr/lib64/libc-2.25.so) stress 9742 32110.959249: 1288322 cycles:ppp: 5566e1e7cbc9 hogcpu (/usr/bin/stress) stress 9742 32110.959712: 1464046 cycles:ppp: 7f4b1b66179e __random (/usr/lib64/libc-2.25.so) stress 9742 32110.960241: 1266918 cycles:ppp: 7f4b1b66195b __random_r (/usr/lib64/libc-2.25.so) # Reported-by:Bram Stolk <b.stolk@gmail.com> Tested-by:
-
Arnaldo Carvalho de Melo authored
The evsel->idx field is used mainly to access the right bucket in per-event arrays such as the annotation ones, but also to set evsel->tracking, that in turn will decide what of the events will ask for PERF_RECORD_{MMAP,COMM,EXEC} to be generated, i.e. which perf_event_attr will have its mmap, etc fields set. When we were adding the "dummy" event using perf_evlist__add_dummy() we were not setting it correctly, which could result in multiple tracking events. Now that I'll try using a dummy event to be the tracking one when using 'perf record --delay', i.e. when we process the --delay setting we may already have the evlist set up, like with: perf record -e cycles,instructions --delay 1000 ./workload We will need to add a "dummy" event, then reset evsel->tracking for the first event, "cycles", and set it instead to the dummy one, and also setting its attr.enable_on_exec, so that we get the PERF_RECORD_MMAP, etc metadata events while waiting to enable the explicitely requested events, so lets get this straight and set the right evsel->idx. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Bram Stolk <b.stolk@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-nrdfchshqxf7diszhxcecqb9@git.kernel.orgSigned-off-by:
-
- 18 Nov, 2017 1 commit
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-4.15-20171117' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: - Optimize sample parsing for ordering events, where we don't need to parse all the PERF_SAMPLE_ bits, just the ones leading to the timestamp needed to reorder events (Jiri Olsa) - Use a dummy event to ask for PERF_RECORD_{MMAP,COMM,EXEC} with 'perf record --delay', when the events asked by the user will only be enabled after the workload is started and the requested delay passes, so we need to add the dummy event and have it .enabled_on_exec. This then allows us to resolve symbols for the DSO executable MMAPs setup while we wait for the delay (Arnaldo Carvalho de Melo) - Synchronize kcmp.h and prctl.h ABI headers wrt SPDX tags (Arnaldo Carvalho de Melo) - Generalize the annotation code to support other source information besides objdump/DWARF obtained ones, starting with python scripts, that will is slated to be merged soon (Jiri Olsa) - Advance the source code lines to right after the column with the address in asm lines (Jiri Olsa) - Fix terminal dimensions resizing signal handling in 'perf top --stdio' (Jiri Olsa) - Improve error messages for PMU events (Kim Phillips) - Fix 'perf record' -c/-F options for cpu event aliases (Andi Kleen) - Enable type checking for perf_evsel_config_term types (Andi Kleen) - Call machine__exit() at 'perf trace' exit, so as to remove temporary files related to VDSO (Andrei Vagin) - Add "reject" option to parse-events.l, fixing the build with newer flex releases. Noticed with flex 2.6.4 on Alpine Linux 3.6 and Edge (Jiri Olsa) - Document some missing perf.data headers (Andi Kleen) - Allow printing period for non freq mod groups (Andi Kleen) - Do not warn the user about kernel.kptr_restrict when not sampling the kernel (Arnaldo Carvalho de Melo) - Fix bug in 'perf help' introduced during conversion to strstart() (Namhyung Kim) - Do not truncate ASM instruction mnemonics at 6 characters in the annotation output, PowerPC has long ones (Ravi Bangoria) - Document some missing command line options (Sihyeon Jang) - Update POWER9 vendor event tables (Sukadev Bhattiprolu) - Fix 'perf test' shell entries on s390x, where the 'openat' syscall is used instead of 'open' in one of the tests and - No need to use overwrite mmap mode in 'perf test', those tests do not generate massive amount of events to fill the ring buffer (Wang Nan) - Add missing command line options (mostly --force/-f) to the man pages (Sihyeon Jang) Signed-off-by:
-
- 17 Nov, 2017 7 commits
-
-
Jiri Olsa authored
We need to call symbol__calc_percent() periodicaly for top, so it's no longer convenient to keep it in symbol__disassemble(). Let's separate the symbol__disassemble() to allocate and init the symbol annotation structs and symbol__calc_percent() to compute the lines percentages based on symbol hists data. Signed-off-by:
-
Jiri Olsa authored
There's no need for symbol__calc_percent and annotation__calc_percent functions to return any value, since it's always zero. Changing both function to return void. Signed-off-by:
-
Jiri Olsa authored
Ravi reported crash in perf top --stdio when annotating a function [1]. The issue was, that we don't pass evsel pointer into symbol__annotate() function, which got over looked in the last annotation changes. [1] https://marc.info/?l=linux-kernel&m=151060884412702&w=2 Committer note: This fixes the crash, but makes it stumble into another bug, double locking the annotation data structures, that is in turn fixed by the next patch in this series. Signed-off-by:
-
Jiri Olsa authored
There's no need for SA_SIGINFO data in SIGWINCH handler, switching it to register the handler via signal interface as we do for the rest of the signals in perf top. Signed-off-by:
-
Jiri Olsa authored
The stdio perf top crashes when we change the terminal window size. The reason is that we assumed we get the perf_top pointer as a signal handler argument which is not the case. Changing the SIGWINCH handler logic to change global resize variable, which is checked in the main thread loop. Signed-off-by:
-
Jiri Olsa authored
Currently when using ordered events we parse the sample twice (the perf_evlist__parse_sample function). Once before we queue the sample for sorting: perf_session__process_event perf_evlist__parse_sample(sample) perf_session__queue_event(sample.time) And then when we deliver the sorted sample: ordered_events__deliver_event perf_evlist__parse_sample perf_session__deliver_event We can skip the initial full sample parsing by using perf_evlist__parse_sample_timestamp function, which got introduced earlier. The new path looks like: perf_session__process_event perf_evlist__parse_sample_timestamp perf_session__queue_event ordered_events__deliver_event perf_session__deliver_event perf_evlist__parse_sample It saves some instructions and is slightly faster: Before: Performance counter stats for './perf.old report --stdio' (5 runs): 64,396,007,225 cycles:u ( +- 0.97% ) 105,882,112,735 instructions:u # 1.64 insn per cycle ( +- 0.00% ) 21.618103465 seconds time elapsed ( +- 1.12% ) After: Performance counter stats for './perf report --stdio' (5 runs): 60,567,807,182 cycles:u ( +- 0.40% ) 104,853,333,514 instructions:u # 1.73 insn per cycle ( +- 0.00% ) 20.168895243 seconds time elapsed ( +- 0.32% ) Signed-off-by: -
Jiri Olsa authored
There's no need to pass whole sample data, because it's only timestamp that is used. Signed-off-by:
-
