linux.git/tools, branch v5.9.12

perf probe: Fix to die_entrypc() returns error correctly

2020-12-02T07:52:01+00:00

[ Upstream commit ab4200c17ba6fe71d2da64317aae8a8aa684624c ]

Fix die_entrypc() to return error correctly if the DIE has no
DW_AT_ranges attribute. Since dwarf_ranges() will treat the case as an
empty ranges and return 0, we have to check it by ourselves.

Fixes: 91e2f539eeda ("perf probe: Fix to show function entry line as probe-able")
Signed-off-by: Masami Hiramatsu 
Cc: Sumanth Korikkar 
Cc: Thomas Richter 
Link: http://lore.kernel.org/lkml/160645612634.2824037.5284932731175079426.stgit@devnote2
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf stat: Use proper cpu for shadow stats

2020-12-02T07:52:01+00:00

[ Upstream commit c0ee1d5ae8c8650031badcfca6483a28c0f94f38 ]

Currently perf stat shows some metrics (like IPC) for defined events.
But when no aggregation mode is used (-A option), it shows incorrect
values since it used a value from a different cpu.

Before:

  $ perf stat -aA -e cycles,instructions sleep 1

   Performance counter stats for 'system wide':

  CPU0      116,057,380      cycles
  CPU1       86,084,722      cycles
  CPU2       99,423,125      cycles
  CPU3       98,272,994      cycles
  CPU0       53,369,217      instructions      #    0.46  insn per cycle
  CPU1       33,378,058      instructions      #    0.29  insn per cycle
  CPU2       58,150,086      instructions      #    0.50  insn per cycle
  CPU3       40,029,703      instructions      #    0.34  insn per cycle

       1.001816971 seconds time elapsed

So the IPC for CPU1 should be 0.38 (= 33,378,058 / 86,084,722)
but it was 0.29 (= 33,378,058 / 116,057,380) and so on.

After:

  $ perf stat -aA -e cycles,instructions sleep 1

   Performance counter stats for 'system wide':

  CPU0      109,621,384      cycles
  CPU1      159,026,454      cycles
  CPU2       99,460,366      cycles
  CPU3      124,144,142      cycles
  CPU0       44,396,706      instructions      #    0.41  insn per cycle
  CPU1      120,195,425      instructions      #    0.76  insn per cycle
  CPU2       44,763,978      instructions      #    0.45  insn per cycle
  CPU3       69,049,079      instructions      #    0.56  insn per cycle

       1.001910444 seconds time elapsed

Fixes: 44d49a600259 ("perf stat: Support metrics in --per-core/socket mode")
Reported-by: Sam Xi 
Signed-off-by: Namhyung Kim 
Reviewed-by: Andi Kleen 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Ian Rogers 
Cc: Mark Rutland 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20201127041404.390276-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf record: Synthesize cgroup events only if needed

2020-12-02T07:52:01+00:00

[ Upstream commit aa50d953c169e876413bf237319e728dd41d9fdd ]

It didn't check the tool->cgroup_events bit which is set when the
--all-cgroups option is given.  Without it, samples will not have cgroup
info so no reason to synthesize.

We can check the PERF_RECORD_CGROUP records after running perf record
*WITHOUT* the --all-cgroups option:

Before:

  $ perf report -D | grep CGROUP
  0 0 0x8430 [0x38]: PERF_RECORD_CGROUP cgroup: 1 /
          CGROUP events:          1
          CGROUP events:          0
          CGROUP events:          0

After:

  $ perf report -D | grep CGROUP
          CGROUP events:          0
          CGROUP events:          0
          CGROUP events:          0

Committer testing:

Before:

  # perf record -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 2.208 MB perf.data (10003 samples) ]
  # perf report -D | grep "CGROUP events"
            CGROUP events:        146
            CGROUP events:          0
            CGROUP events:          0
  #

After:

  # perf record -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 2.208 MB perf.data (10448 samples) ]
  # perf report -D | grep "CGROUP events"
            CGROUP events:          0
            CGROUP events:          0
            CGROUP events:          0
  #

With all-cgroups:

  # perf record --all-cgroups -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 2.374 MB perf.data (11526 samples) ]
  # perf report -D | grep "CGROUP events"
            CGROUP events:        146
            CGROUP events:          0
            CGROUP events:          0
  #

Fixes: 8fb4b67939e16 ("perf record: Add --all-cgroups option")
Signed-off-by: Namhyung Kim 
Tested-by: Arnaldo Carvalho de Melo 
Acked-by: Jiri Olsa 
Cc: Alexander Shishkin 
Cc: Ian Rogers 
Cc: Mark Rutland 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20201127054356.405481-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

selftests/seccomp: sh: Fix register names

2020-11-24T12:39:05+00:00

[ Upstream commit 4c222f31fb1db4d590503a181a6268ced9252379 ]

It looks like the seccomp selftests was never actually built for sh.
This fixes it, though I don't have an environment to do a runtime test
of it yet.

Fixes: 0bb605c2c7f2b4b3 ("sh: Add SECCOMP_FILTER")
Tested-by: John Paul Adrian Glaubitz 
Link: https://lore.kernel.org/lkml/a36d7b48-6598-1642-e403-0c77a86f416d@physik.fu-berlin.de
Signed-off-by: Kees Cook 
Signed-off-by: Sasha Levin

selftests/seccomp: powerpc: Fix typo in macro variable name

2020-11-24T12:39:05+00:00

[ Upstream commit f5098e34dd4c774c3040e417960f1637e5daade8 ]

A typo sneaked into the powerpc selftest. Fix the name so it builds again.

Fixes: 46138329faea ("selftests/seccomp: powerpc: Fix seccomp return value testing")
Acked-by: Michael Ellerman 
Link: https://lore.kernel.org/lkml/87y2ix2895.fsf@mpe.ellerman.id.au
Signed-off-by: Kees Cook 
Signed-off-by: Sasha Levin

libbpf: Fix VERSIONED_SYM_COUNT number parsing

2020-11-24T12:39:05+00:00

[ Upstream commit 1fd6cee127e2ddff36d648573d7566aafb0d0b77 ]

We remove "other info" from "readelf -s --wide" output when
parsing GLOBAL_SYM_COUNT variable, which was added in [1].
But we don't do that for VERSIONED_SYM_COUNT and it's failing
the check_abi target on powerpc Fedora 33.

The extra "other info" wasn't problem for VERSIONED_SYM_COUNT
parsing until commit [2] added awk in the pipe, which assumes
that the last column is symbol, but it can be "other info".

Adding "other info" removal for VERSIONED_SYM_COUNT the same
way as we did for GLOBAL_SYM_COUNT parsing.

[1] aa915931ac3e ("libbpf: Fix readelf output parsing for Fedora")
[2] 746f534a4809 ("tools/libbpf: Avoid counting local symbols in ABI check")

Fixes: 746f534a4809 ("tools/libbpf: Avoid counting local symbols in ABI check")
Signed-off-by: Jiri Olsa 
Signed-off-by: Alexei Starovoitov 
Acked-by: Andrii Nakryiko 
Link: https://lore.kernel.org/bpf/20201118211350.1493421-1-jolsa@kernel.org
Signed-off-by: Sasha Levin

selftests/bpf: Fix error return code in run_getsockopt_test()

2020-11-24T12:39:02+00:00

[ Upstream commit 2acc3c1bc8e98bc66b1badec42e9ea205b4fcdaa ]

Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.

Fixes: 65b4414a05eb ("selftests/bpf: add sockopt test that exercises BPF_F_ALLOW_MULTI")
Reported-by: Hulk Robot 
Signed-off-by: Wang Hai 
Signed-off-by: Daniel Borkmann 
Link: https://lore.kernel.org/bpf/20201116101633.64627-1-wanghai38@huawei.com
Signed-off-by: Sasha Levin

tools, bpftool: Add missing close before bpftool net attach exit

2020-11-24T12:39:00+00:00

[ Upstream commit 50431b45685b600fc2851a3f2b53e24643efe6d3 ]

progfd is created by prog_parse_fd() in do_attach() and before the latter
returns in case of success, the file descriptor should be closed.

Fixes: 04949ccc273e ("tools: bpftool: add net attach command to attach XDP on interface")
Signed-off-by: Wang Hai 
Signed-off-by: Daniel Borkmann 
Link: https://lore.kernel.org/bpf/20201113115152.53178-1-wanghai38@huawei.com
Signed-off-by: Sasha Levin

perf lock: Don't free "lock_seq_stat" if read_count isn't zero

2020-11-24T12:39:00+00:00

[ Upstream commit b0e5a05cc9e37763c7f19366d94b1a6160c755bc ]

When execute command "perf lock report", it hits failure and outputs log
as follows:

  perf: builtin-lock.c:623: report_lock_release_event: Assertion `!(seq->read_count < 0)' failed.
  Aborted

This is an imbalance issue.  The locking sequence structure
"lock_seq_stat" contains the reader counter and it is used to check if
the locking sequence is balance or not between acquiring and releasing.

If the tool wrongly frees "lock_seq_stat" when "read_count" isn't zero,
the "read_count" will be reset to zero when allocate a new structure at
the next time; thus it causes the wrong counting for reader and finally
results in imbalance issue.

To fix this issue, if detects "read_count" is not zero (means still have
read user in the locking sequence), goto the "end" tag to skip freeing
structure "lock_seq_stat".

Fixes: e4cef1f65061 ("perf lock: Fix state machine to recognize lock sequence")
Signed-off-by: Leo Yan 
Acked-by: Jiri Olsa 
Link: https://lore.kernel.org/r/20201104094229.17509-2-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf lock: Correct field name "flags"

2020-11-24T12:39:00+00:00

[ Upstream commit e24a87b54ef3e39261f1d859b7f78416349dfb14 ]

The tracepoint "lock:lock_acquire" contains field "flags" but not
"flag".  Current code wrongly retrieves value from field "flag" and it
always gets zero for the value, thus "perf lock" doesn't report the
correct result.

This patch replaces the field name "flag" with "flags", so can read out
the correct flags for locking.

Fixes: e4cef1f65061 ("perf lock: Fix state machine to recognize lock sequence")
Signed-off-by: Leo Yan 
Acked-by: Jiri Olsa 
Link: https://lore.kernel.org/r/20201104094229.17509-1-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin