Skip to content

L
linux
Switch branch/tag
  1. 14 Nov, 2022 8 commits
  3. 10 Nov, 2022 5 commits
  5. 09 Nov, 2022 4 commits
  7. 07 Nov, 2022 1 commit
    • Arnaldo Carvalho de Melo's avatar
      perf trace: Add BPF augmenter to perf_event_open()'s 'struct perf_event_attr' arg · a9cd6c67
      Arnaldo Carvalho de Melo authored 
      Using BPF for that, doing a cleverish reuse of perf_event_attr__fprintf(),
that really needs to be turned into __snprintf(), etc.

But since the plan is to go the BTF way probably use libbpf's
btf_dump__dump_type_data().

Example:

[root@quaco ~]# perf trace -e ~acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c,perf_event_open --max-events 10 perf stat --quiet sleep 0.001
fg
     0.000 perf_event_open(attr_uptr: { type: 1, size: 128, config: 0x1, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258859 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
     0.067 perf_event_open(attr_uptr: { type: 1, size: 128, config: 0x3, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258859 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4
     0.120 perf_event_open(attr_uptr: { type: 1, size: 128, config: 0x4, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258859 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 5
     0.172 perf_event_open(attr_uptr: { type: 1, size: 128, config: 0x2, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258859 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 7
     0.190 perf_event_open(attr_uptr: { size: 128, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258859 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 8
     0.199 perf_event_open(attr_uptr: { size: 128, config: 0x1, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258859 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 9
     0.204 perf_event_open(attr_uptr: { size: 128, config: 0x4, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258859 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 10
     0.210 perf_event_open(attr_uptr: { size: 128, config: 0x5, sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 258859 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 11
[root@quaco ~]#
Suggested-by: default avatarIan Rogers <irogers@google.com>
Tested-by: default avatarIan Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/Y2V2Tpu+2vzJyon2@kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      a9cd6c67
  9. 04 Nov, 2022 7 commits
    • Arnaldo Carvalho de Melo's avatar
      perf bpf: Rename perf_include_dir to libbpf_include_dir · b018899e
      Arnaldo Carvalho de Melo authored 
      As this is where we expect to find bpf/bpf_helpers.h, etc.

This needs more work to make it follow LIBBPF_DYNAMIC=1 usage, i.e. when
not using the system libbpf it should use the headers in the in-kernel
sources libbpf in tools/lib/bpf.

We need to do that anyway to avoid this mixup system libbpf and
in-kernel files, so we'll get this sorted out that way.

And this also may become moot as we move to using BPF skels for this
feature.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      b018899e
    • Arnaldo Carvalho de Melo's avatar
      perf examples bpf: Remove augmented_syscalls.c, the raw_syscalls one should be used instead · 3cd65616
      Arnaldo Carvalho de Melo authored 
      The attempt at using BPF to copy syscall pointer arguments to show them
like strace does started with sys_{enter,exit}_SYSCALL_NAME tracepoints,
in tools/perf/examples/bpf/augmented_syscalls.c, but then achieving this
result using raw_syscalls:{enter,exit} and BPF tail calls was deemed
more flexible.

The 'perf trace' codebase was adapted to using it while trying to
continue supporting the old style per-syscall tracepoints, which at some
point became too unwieldly and now isn't working properly.

So lets scale back and concentrate on the augmented_raw_syscalls.c
model on the way to using BPF skeletons.

For the same reason remove the etcsnoop.c example, that used the
old style per-tp syscalls just for the 'open' and 'openat' syscalls,
looking at the pathnames starting with "/etc/", we should be able
to do this later using filters, after we move to BPF skels.

The augmented_raw_syscalls.c one continues to work, now with libbpf 1.0,
after Ian work on using the libbpf map style:

  # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c,open* --max-events 4
     0.000 ping/194815 openat(dfd: CWD, filename: "/etc/hosts", flags: RDONLY|CLOEXEC) = 5
    20.225 systemd-oomd/972 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12
    20.285 abrt-dump-jour/1371 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 21
    20.301 abrt-dump-jour/1370 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 21
  #

This is using this:

  # cat ~/.perfconfig
  [trace]
	show_zeros = yes
	show_duration = no
	no_inherit = yes
	args_alignment = 40

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      3cd65616
    • Ian Rogers's avatar
      perf bpf: Remove now unused BPF headers · cfddf0d4
      Ian Rogers authored 
      Example code has migrated to use standard BPF header files, remove
unnecessary perf equivalents. Update install step to not try to copy
these.
Signed-off-by: default avatarIan Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20221103045437.163510-8-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      cfddf0d4
    • Ian Rogers's avatar
      perf trace: 5sec fix libbpf 1.0+ compatibility · 71811e8c
      Ian Rogers authored 
      Avoid use of tools/perf/include/bpf/bpf.h and use the more regular BPF
headers.

Committer testing:

  # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/5sec.c sleep 5
       0.000 perf_bpf_probe:hrtimer_nanosleep(__probe_ip: -1474734416, rqtp: 5000000000)
  # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/5sec.c/max-stack=7/ sleep 5
       0.000 perf_bpf_probe:hrtimer_nanosleep(__probe_ip: -1474734416, rqtp: 5000000000)
                                         hrtimer_nanosleep ([kernel.kallsyms])
                                         common_nsleep ([kernel.kallsyms])
                                         __x64_sys_clock_nanosleep ([kernel.kallsyms])
                                         do_syscall_64 ([kernel.kallsyms])
                                         entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
                                         __GI___clock_nanosleep (/usr/lib64/libc.so.6)
                                         [0] ([unknown])
  #
Signed-off-by: default avatarIan Rogers <irogers@google.com>
Tested-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20221103045437.163510-7-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      71811e8c
    • Ian Rogers's avatar
      perf trace: empty fix libbpf 1.0+ compatibility · baddab89
      Ian Rogers authored 
      Avoid use of tools/perf/include/bpf/bpf.h and use the more regular BPF
headers.  Add raw_syscalls:sys_enter to avoid the evlist being empty.

Committer testing:

  # time perf trace -e ~acme/git/perf/tools/perf/examples/bpf/empty.c sleep 5

  real	0m5.697s
  user	0m0.217s
  sys	0m0.453s
  #

I.e. it sets up everything successfully (use -v to see the details) and
filters out all syscalls, then exits when the workload (sleep 5)
finishes.
Signed-off-by: default avatarIan Rogers <irogers@google.com>
Tested-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20221103045437.163510-6-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      baddab89
    • Ian Rogers's avatar
      perf trace: hello fix libbpf 1.0+ compatibility · 514607e3
      Ian Rogers authored 
      Don't use deprecated and now broken map style. Avoid use of
tools/perf/include/bpf/bpf.h and use the more regular BPF headers.

Switch to raw_syscalls:sys_enter to avoid the evlist being empty and
fixing generating output.

Committer testing:

  # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/hello.c --call-graph=dwarf --max-events 5
     0.000 perf/206852 __bpf_stdout__(Hello, world)
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
                                       __GI___sched_setaffinity_new (/usr/lib64/libc.so.6)
     8.561 pipewire/2290 __bpf_stdout__(Hello, world)
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
                                       __libc_read (/usr/lib64/libc.so.6)
     8.571 pipewire/2290 __bpf_stdout__(Hello, world)
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
                                       __GI___ioctl (/usr/lib64/libc.so.6)
     8.586 pipewire/2290 __bpf_stdout__(Hello, world)
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
                                       __GI___write (/usr/lib64/libc.so.6)
     8.592 pipewire/2290 __bpf_stdout__(Hello, world)
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       syscall_trace_enter.constprop.0 ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
                                       __timerfd_settime (/usr/lib64/libc.so.6)
  #
Signed-off-by: default avatarIan Rogers <irogers@google.com>
Tested-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20221103045437.163510-5-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      514607e3
    • Ian Rogers's avatar
      perf trace: Raw augmented syscalls fix libbpf 1.0+ compatibility · 14e4b9f4
      Ian Rogers authored 
      Don't use deprecated and now broken map style. Avoid use of
tools/perf/include/bpf/bpf.h and use the more regular BPF headers.

Committer notes:

Add /usr/include to the include path so that bpf/bpf_helpers.h can be
found, remove sys/socket.h, adding the sockaddr_storage definition, also
remove stdbool.h, both were preventing building the
augmented_raw_syscalls.c file with clang, revisit later.

Testing it:

Asking for syscalls that have string arguments:

  # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c,string --max-events 10
     0.000 thermald/1144 openat(dfd: CWD, filename: "/sys/class/powercap/intel-rapl/intel-rapl:0/intel-rapl:0:2/energy_uj", flags: RDONLY) = 13
     0.158 thermald/1144 openat(dfd: CWD, filename: "/sys/class/powercap/intel-rapl/intel-rapl:0/energy_uj", flags: RDONLY) = 13
     0.215 thermald/1144 openat(dfd: CWD, filename: "/sys/class/thermal/thermal_zone3/temp", flags: RDONLY) = 13
    16.448 cgroupify/36478 openat(dfd: 4, filename: ".", flags: RDONLY|CLOEXEC|DIRECTORY|NONBLOCK) = 5
    16.468 cgroupify/36478 newfstatat(dfd: 5, filename: "", statbuf: 0x7fffca5b4130, flag: 4096) = 0
    16.473 systemd-oomd/972 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 12
    16.499 systemd-oomd/972 newfstatat(dfd: 12, filename: "", statbuf: 0x7ffd2bc73cc0, flag: 4096) = 0
    16.516 abrt-dump-jour/1370 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 21
    16.538 abrt-dump-jour/1370 newfstatat(dfd: 21, filename: "", statbuf: 0x7ffc651b8980, flag: 4096) = 0
    16.540 abrt-dump-jour/1371 openat(dfd: CWD, filename: "/var/log/journal/d6a97235307247e09f13f326fb607e3c/system.journal", flags: RDONLY|CLOEXEC|NONBLOCK) = 21
  #

Networking syscalls:

  # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c,sendto*,connect* --max-events 10
     0.000 isc-net-0005/1206 connect(fd: 512, uservaddr: { .family: INET, port: 53, addr: 23.211.132.65 }, addrlen: 16) = 0
     0.070 isc-net-0002/1203 connect(fd: 515, uservaddr: { .family: INET6, port: 53, addr: 2600:1401:2::43 }, addrlen: 28) = -1 ENETUNREACH (Network is unreachable)
     0.031 isc-net-0006/1207 connect(fd: 513, uservaddr: { .family: INET6, port: 53, addr: 2600:1401:2::43 }, addrlen: 28) = -1 ENETUNREACH (Network is unreachable)
     0.079 isc-net-0006/1207 sendto(fd: 3, buff: 0x7f73a40611b0, len: 106, flags: NOSIGNAL, addr: { .family: UNSPEC }, addr_len: NULL) = 106
     0.180 isc-net-0006/1207 connect(fd: 519, uservaddr: { .family: INET6, port: 53, addr: 2600:1401:1::43 }, addrlen: 28) = -1 ENETUNREACH (Network is unreachable)
     0.211 isc-net-0006/1207 sendto(fd: 3, buff: 0x7f73a4061230, len: 106, flags: NOSIGNAL, addr: { .family: UNSPEC }, addr_len: NULL) = 106
     0.298 isc-net-0006/1207 connect(fd: 515, uservaddr: { .family: INET, port: 53, addr: 96.7.49.67 }, addrlen: 16) = 0
     0.109 isc-net-0004/1205 connect(fd: 518, uservaddr: { .family: INET6, port: 53, addr: 2600:1401:2::43 }, addrlen: 28) = -1 ENETUNREACH (Network is unreachable)
     0.164 isc-net-0002/1203 sendto(fd: 3, buff: 0x7f73ac064300, len: 107, flags: NOSIGNAL, addr: { .family: UNSPEC }, addr_len: NULL) = 107
     0.247 isc-net-0002/1203 connect(fd: 522, uservaddr: { .family: INET6, port: 53, addr: 2600:1401:1::43 }, addrlen: 28) = -1 ENETUNREACH (Network is unreachable)
  #
Signed-off-by: default avatarIan Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20221103045437.163510-2-irogers@google.comSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
      14e4b9f4
  11. 03 Nov, 2022 11 commits
  13. 31 Oct, 2022 4 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7