linux-stable.git/tools/perf, branch v5.4.166

tools build: Remove needless libpython-version feature check that breaks test-all fast path

2021-12-14T13:49:03+00:00

commit 3d1d57debee2d342a47615707588b96658fabb85 upstream.

Since 66dfdff03d196e51 ("perf tools: Add Python 3 support") we don't use
the tools/build/feature/test-libpython-version.c version in any Makefile
feature check:

  $ find tools/ -type f | xargs grep feature-libpython-version
  $

The only place where this was used was removed in 66dfdff03d196e51:

  -        ifneq ($(feature-libpython-version), 1)
  -          $(warning Python 3 is not yet supported; please set)
  -          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
  -          $(warning If you also have Python 2 installed, then)
  -          $(warning try something like:)
  -          $(warning $(and ,))
  -          $(warning $(and ,)  make PYTHON=python2)
  -          $(warning $(and ,))
  -          $(warning Otherwise, disable Python support entirely:)
  -          $(warning $(and ,))
  -          $(warning $(and ,)  make NO_LIBPYTHON=1)
  -          $(warning $(and ,))
  -          $(error   $(and ,))
  -        else
  -          LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
  -          EXTLIBS += $(PYTHON_EMBED_LIBADD)
  -          LANG_BINDINGS += $(obj-perf)python/perf.so
  -          $(call detected,CONFIG_LIBPYTHON)
  -        endif

And nowadays we either build with PYTHON=python3 or just install the
python3 devel packages and perf will build against it.

But the leftover feature-libpython-version check made the fast path
feature detection to break in all cases except when python2 devel files
were installed:

  $ rpm -qa | grep python.*devel
  python3-devel-3.9.7-1.fc34.x86_64
  $ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf ;
  $ make -C tools/perf O=/tmp/build/perf install-bin
  make: Entering directory '/var/home/acme/git/perf/tools/perf'
    BUILD:   Doing 'make -j32' parallel build
    HOSTCC  /tmp/build/perf/fixdep.o
  
  $ cat /tmp/build/perf/feature/test-all.make.output
  In file included from test-all.c:18:
  test-libpython-version.c:5:10: error: #error
      5 |         #error
        |          ^~~~~
  $ ldd ~/bin/perf | grep python
	libpython3.9.so.1.0 => /lib64/libpython3.9.so.1.0 (0x00007fda6dbcf000)
  $

As python3 is the norm these days, fix this by just removing the unused
feature-libpython-version feature check, making the test-all fast path
to work with the common case.

With this:

  $ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf ;
  $ make -C tools/perf O=/tmp/build/perf install-bin |& head
  make: Entering directory '/var/home/acme/git/perf/tools/perf'
    BUILD:   Doing 'make -j32' parallel build
    HOSTCC  /tmp/build/perf/fixdep.o
    HOSTLD  /tmp/build/perf/fixdep-in.o
    LINK    /tmp/build/perf/fixdep

  Auto-detecting system features:
  ...                         dwarf: [ on  ]
  ...            dwarf_getlocations: [ on  ]
  ...                         glibc: [ on  ]
  $ ldd ~/bin/perf | grep python
	libpython3.9.so.1.0 => /lib64/libpython3.9.so.1.0 (0x00007f58800b0000)
  $ cat /tmp/build/perf/feature/test-all.make.output
  $

Reviewed-by: James Clark 
Fixes: 66dfdff03d196e51 ("perf tools: Add Python 3 support")
Cc: Adrian Hunter 
Cc: Ian Rogers 
Cc: Jaroslav Škarvada 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Link: https://lore.kernel.org/lkml/YaYmeeC6CS2b8OSz@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Greg Kroah-Hartman

perf report: Fix memory leaks around perf_tip()

2021-12-08T08:01:10+00:00

[ Upstream commit d9fc706108c15f8bc2d4ccccf8e50f74830fabd9 ]

perf_tip() may allocate memory or use a literal, this means memory
wasn't freed if allocated. Change the API so that literals aren't used.

At the same time add missing frees for system_path. These issues were
spotted using leak sanitizer.

Signed-off-by: Ian Rogers 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20211118073804.2149974-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf hist: Fix memory leak of a perf_hpp_fmt

2021-12-08T08:01:10+00:00

[ Upstream commit 0ca1f534a776cc7d42f2c33da4732b74ec2790cd ]

perf_hpp__column_unregister() removes an entry from a list but doesn't
free the memory causing a memory leak spotted by leak sanitizer.

Add the free while at the same time reducing the scope of the function
to static.

Signed-off-by: Ian Rogers 
Reviewed-by: Kajol Jain 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lore.kernel.org/lkml/20211118071247.2140392-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf tests: Remove bash construct from record+zstd_comp_decomp.sh

2021-11-26T09:47:18+00:00

[ Upstream commit a9cdc1c5e3700a5200e5ca1f90b6958b6483845b ]

Commit 463538a383a2 ("perf tests: Fix test 68 zstd compression for
s390") inadvertently removed the -g flag from all platforms rather than
just s390, because the [[ ]] construct fails in sh. Changing to single
brackets restores testing of call graphs and removes the following error
from the output:

  $ ./perf test -v 85
  85: Zstd perf.data compression/decompression                        :
  --- start ---
  test child forked, pid 50643
  Collecting compressed record file:
  ./tests/shell/record+zstd_comp_decomp.sh: 15: [[: not found

Fixes: 463538a383a2 ("perf tests: Fix test 68 zstd compression for s390")
Signed-off-by: James Clark 
Cc: Alexander Shishkin 
Cc: Florian Fainelli 
Cc: Ian Rogers 
Cc: Jiri Olsa 
Cc: John Fastabend 
Cc: KP Singh 
Cc: Mark Rutland 
Cc: Martin KaFai Lau 
Cc: Namhyung Kim 
Cc: Song Liu 
Cc: Sumanth Korikkar 
Cc: Thomas Richter 
Cc: Yonghong Song 
Cc: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/20211028134828.65774-3-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf bench futex: Fix memory leak of perf_cpu_map__new()

2021-11-26T09:47:18+00:00

[ Upstream commit 88e48238d53682281c9de2a0b65d24d3b64542a0 ]

ASan reports memory leaks while running:

  $ sudo ./perf bench futex all

The leaks are caused by perf_cpu_map__new not being freed.
This patch adds the missing perf_cpu_map__put since it calls
cpu_map_delete implicitly.

Fixes: 9c3516d1b850ea93 ("libperf: Add perf_cpu_map__new()/perf_cpu_map__read() functions")
Signed-off-by: Sohaib Mohamed 
Cc: Alexander Shishkin 
Cc: André Almeida 
Cc: Darren Hart 
Cc: Davidlohr Bueso 
Cc: Ian Rogers 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Sohaib Mohamed 
Cc: Thomas Gleixner 
Link: http://lore.kernel.org/lkml/20211112201134.77892-1-sohaib.amhmd@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf bpf: Avoid memory leak from perf_env__insert_btf()

2021-11-26T09:47:18+00:00

[ Upstream commit 4924b1f7c46711762fd0e65c135ccfbcfd6ded1f ]

perf_env__insert_btf() doesn't insert if a duplicate BTF id is
encountered and this causes a memory leak. Modify the function to return
a success/error value and then free the memory if insertion didn't
happen.

v2. Adds a return -1 when the insertion error occurs in
    perf_env__fetch_btf. This doesn't affect anything as the result is
    never checked.

Fixes: 3792cb2ff43b1b19 ("perf bpf: Save BTF in a rbtree in perf_env")
Signed-off-by: Ian Rogers 
Cc: Alexander Shishkin 
Cc: Alexei Starovoitov 
Cc: Andrii Nakryiko 
Cc: Daniel Borkmann 
Cc: Jiri Olsa 
Cc: John Fastabend 
Cc: KP Singh 
Cc: Mark Rutland 
Cc: Martin KaFai Lau 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Song Liu 
Cc: Stephane Eranian 
Cc: Tiezhu Yang 
Cc: Yonghong Song 
Cc: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/20211112074525.121633-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf bpf: Add missing free to bpf_event__print_bpf_prog_info()

2021-11-17T08:48:47+00:00

[ Upstream commit 88c42f4d6cb249eb68524282f8d4cc32f9059984 ]

If btf__new() is called then there needs to be a corresponding btf__free().

Fixes: f8dfeae009effc0b ("perf bpf: Show more BPF program info in print_bpf_prog_info()")
Signed-off-by: Ian Rogers 
Cc: Alexander Shishkin 
Cc: Alexei Starovoitov 
Cc: Andrii Nakryiko 
Cc: Daniel Borkmann 
Cc: Jiri Olsa 
Cc: John Fastabend 
Cc: KP Singh 
Cc: Mark Rutland 
Cc: Martin KaFai Lau 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Song Liu 
Cc: Stephane Eranian 
Cc: Tiezhu Yang 
Cc: Yonghong Song 
Cc: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/20211106053733.3580931-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf script: Check session->header.env.arch before using it

2021-11-02T18:46:15+00:00

commit 29c77550eef31b0d72a45b49eeab03b8963264e8 upstream.

When perf.data is not written cleanly, we would like to process existing
data as much as possible (please see f_header.data.size == 0 condition
in perf_session__read_header). However, perf.data with partial data may
crash perf. Specifically, we see crash in 'perf script' for NULL
session->header.env.arch.

Fix this by checking session->header.env.arch before using it to determine
native_arch. Also split the if condition so it is easier to read.

Committer notes:

If it is a pipe, we already assume is a native arch, so no need to check
session->header.env.arch.

Signed-off-by: Song Liu 
Cc: Peter Zijlstra 
Cc: kernel-team@fb.com
Cc: stable@vger.kernel.org
Link: http://lore.kernel.org/lkml/20211004053238.514936-1-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Greg Kroah-Hartman

perf unwind: Do not overwrite FEATURE_CHECK_LDFLAGS-libunwind-{x86,aarch64}

2021-09-22T10:26:45+00:00

[ Upstream commit cdf32b44678c382a31dc183d9a767306915cda7b ]

When setting LIBUNWIND_DIR, we first set

 FEATURE_CHECK_LDFLAGS-libunwind-{aarch64,x86} = -L$(LIBUNWIND_DIR)/lib.


This happens a bit before, the overwritting, in:

  libunwind_arch_set_flags = $(eval $(libunwind_arch_set_flags_code))
  define libunwind_arch_set_flags_code
    FEATURE_CHECK_CFLAGS-libunwind-$(1)  = -I$(LIBUNWIND_DIR)/include
    FEATURE_CHECK_LDFLAGS-libunwind-$(1) = -L$(LIBUNWIND_DIR)/lib
  endef

  ifdef LIBUNWIND_DIR
    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
    LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64
    $(foreach libunwind_arch,$(LIBUNWIND_ARCHS),$(call libunwind_arch_set_flags,$(libunwind_arch)))
  endif

Look at that 'foreach' on all the LIBUNWIND_ARCHS.


After commit 5c4d7c82c0dc ("perf unwind: Do not put libunwind-{x86,aarch64}
in FEATURE_TESTS_BASIC"), FEATURE_CHECK_LDFLAGS-libunwind-{x86,aarch64} is
overwritten. As a result, the remote libunwind libraries cannot be searched
from $(LIBUNWIND_DIR)/lib directory during feature check tests. Fix it with
variable appending.

Before this patch:

  perf$ make VF=1 LIBUNWIND_DIR=/opt/libunwind_aarch64
   BUILD:   Doing 'make -j16' parallel build
  
  ...
  ...                    libopencsd: [ OFF ]
  ...                 libunwind-x86: [ OFF ]
  ...              libunwind-x86_64: [ OFF ]
  ...                 libunwind-arm: [ OFF ]
  ...             libunwind-aarch64: [ OFF ]
  ...         libunwind-debug-frame: [ OFF ]
  ...     libunwind-debug-frame-arm: [ OFF ]
  ... libunwind-debug-frame-aarch64: [ OFF ]
  ...                           cxx: [ OFF ]
  

  perf$ cat ../build/feature/test-libunwind-aarch64.make.output
  /usr/bin/ld: cannot find -lunwind-aarch64
  /usr/bin/ld: cannot find -lunwind-aarch64
  collect2: error: ld returned 1 exit status

After this patch:

  perf$ make VF=1 LIBUNWIND_DIR=/opt/libunwind_aarch64
   BUILD:   Doing 'make -j16' parallel build
  
  ...                    libopencsd: [ OFF ]
  ...                 libunwind-x86: [ OFF ]
  ...              libunwind-x86_64: [ OFF ]
  ...                 libunwind-arm: [ OFF ]
  ...             libunwind-aarch64: [ on  ]
  ...         libunwind-debug-frame: [ OFF ]
  ...     libunwind-debug-frame-arm: [ OFF ]
  ... libunwind-debug-frame-aarch64: [ OFF ]
  ...                           cxx: [ OFF ]
  

  perf$ cat ../build/feature/test-libunwind-aarch64.make.output

  perf$ ldd ./perf
        linux-vdso.so.1 (0x00007ffdf07da000)
        libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f30953dc000)
        librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f30951d4000)
        libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f3094e36000)
        libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f3094c32000)
        libelf.so.1 => /usr/lib/x86_64-linux-gnu/libelf.so.1 (0x00007f3094a18000)
        libdw.so.1 => /usr/lib/x86_64-linux-gnu/libdw.so.1 (0x00007f30947cc000)
        libunwind-x86_64.so.8 => /usr/lib/x86_64-linux-gnu/libunwind-x86_64.so.8 (0x00007f30945ad000)
        libunwind.so.8 => /usr/lib/x86_64-linux-gnu/libunwind.so.8 (0x00007f3094392000)
        liblzma.so.5 => /lib/x86_64-linux-gnu/liblzma.so.5 (0x00007f309416c000)
        libunwind-aarch64.so.8 => not found
        libslang.so.2 => /lib/x86_64-linux-gnu/libslang.so.2 (0x00007f3093c8a000)
        libpython2.7.so.1.0 => /usr/local/lib/libpython2.7.so.1.0 (0x00007f309386b000)
        libz.so.1 => /lib/x86_64-linux-gnu/libz.so.1 (0x00007f309364e000)
        libnuma.so.1 => /usr/lib/x86_64-linux-gnu/libnuma.so.1 (0x00007f3093443000)
        libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f3093052000)
        /lib64/ld-linux-x86-64.so.2 (0x00007f3096097000)
        libbz2.so.1.0 => /lib/x86_64-linux-gnu/libbz2.so.1.0 (0x00007f3092e42000)
        libutil.so.1 => /lib/x86_64-linux-gnu/libutil.so.1 (0x00007f3092c3f000)

Fixes: 5c4d7c82c0dceccf ("perf unwind: Do not put libunwind-{x86,aarch64} in FEATURE_TESTS_BASIC")
Signed-off-by: Li Huafei 
Cc: Alexander Shishkin 
Cc: He Kuang 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Zhang Jinhao 
Link: http://lore.kernel.org/lkml/20210823134340.60955-1-lihuafei1@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf machine: Initialize srcline string member in add_location struct

2021-09-22T10:26:41+00:00

commit 57f0ff059e3daa4e70a811cb1d31a49968262d20 upstream.

It's later supposed to be either a correct address or NULL. Without the
initialization, it may contain an undefined value which results in the
following segmentation fault:

  # perf top --sort comm -g --ignore-callees=do_idle

terminates with:

  #0  0x00007ffff56b7685 in __strlen_avx2 () from /lib64/libc.so.6
  #1  0x00007ffff55e3802 in strdup () from /lib64/libc.so.6
  #2  0x00005555558cb139 in hist_entry__init (callchain_size=, sample_self=true, template=0x7fffde7fb110, he=0x7fffd801c250) at util/hist.c:489
  #3  hist_entry__new (template=template@entry=0x7fffde7fb110, sample_self=sample_self@entry=true) at util/hist.c:564
  #4  0x00005555558cb4ba in hists__findnew_entry (hists=hists@entry=0x5555561d9e38, entry=entry@entry=0x7fffde7fb110, al=al@entry=0x7fffde7fb420,
      sample_self=sample_self@entry=true) at util/hist.c:657
  #5  0x00005555558cba1b in __hists__add_entry (hists=hists@entry=0x5555561d9e38, al=0x7fffde7fb420, sym_parent=, bi=bi@entry=0x0, mi=mi@entry=0x0,
      sample=sample@entry=0x7fffde7fb4b0, sample_self=true, ops=0x0, block_info=0x0) at util/hist.c:288
  #6  0x00005555558cbb70 in hists__add_entry (sample_self=true, sample=0x7fffde7fb4b0, mi=0x0, bi=0x0, sym_parent=, al=, hists=0x5555561d9e38)
      at util/hist.c:1056
  #7  iter_add_single_cumulative_entry (iter=0x7fffde7fb460, al=) at util/hist.c:1056
  #8  0x00005555558cc8a4 in hist_entry_iter__add (iter=iter@entry=0x7fffde7fb460, al=al@entry=0x7fffde7fb420, max_stack_depth=, arg=arg@entry=0x7fffffff7db0)
      at util/hist.c:1231
  #9  0x00005555557cdc9a in perf_event__process_sample (machine=, sample=0x7fffde7fb4b0, evsel=, event=, tool=0x7fffffff7db0)
      at builtin-top.c:842
  #10 deliver_event (qe=, qevent=) at builtin-top.c:1202
  #11 0x00005555558a9318 in do_flush (show_progress=false, oe=0x7fffffff80e0) at util/ordered-events.c:244
  #12 __ordered_events__flush (oe=oe@entry=0x7fffffff80e0, how=how@entry=OE_FLUSH__TOP, timestamp=timestamp@entry=0) at util/ordered-events.c:323
  #13 0x00005555558a9789 in __ordered_events__flush (timestamp=, how=, oe=) at util/ordered-events.c:339
  #14 ordered_events__flush (how=OE_FLUSH__TOP, oe=0x7fffffff80e0) at util/ordered-events.c:341
  #15 ordered_events__flush (oe=oe@entry=0x7fffffff80e0, how=how@entry=OE_FLUSH__TOP) at util/ordered-events.c:339
  #16 0x00005555557cd631 in process_thread (arg=0x7fffffff7db0) at builtin-top.c:1114
  #17 0x00007ffff7bb817a in start_thread () from /lib64/libpthread.so.0
  #18 0x00007ffff5656dc3 in clone () from /lib64/libc.so.6

If you look at the frame #2, the code is:

488	 if (he->srcline) {
489          he->srcline = strdup(he->srcline);
490          if (he->srcline == NULL)
491              goto err_rawdata;
492	 }

If he->srcline is not NULL (it is not NULL if it is uninitialized rubbish),
it gets strdupped and strdupping a rubbish random string causes the problem.

Also, if you look at the commit 1fb7d06a509e, it adds the srcline property
into the struct, but not initializing it everywhere needed.

Committer notes:

Now I see, when using --ignore-callees=do_idle we end up here at line
2189 in add_callchain_ip():

2181         if (al.sym != NULL) {
2182                 if (perf_hpp_list.parent && !*parent &&
2183                     symbol__match_regex(al.sym, &parent_regex))
2184                         *parent = al.sym;
2185                 else if (have_ignore_callees && root_al &&
2186                   symbol__match_regex(al.sym, &ignore_callees_regex)) {
2187                         /* Treat this symbol as the root,
2188                            forgetting its callees. */
2189                         *root_al = al;
2190                         callchain_cursor_reset(cursor);
2191                 }
2192         }

And the al that doesn't have the ->srcline field initialized will be
copied to the root_al, so then, back to:

1211 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
1212                          int max_stack_depth, void *arg)
1213 {
1214         int err, err2;
1215         struct map *alm = NULL;
1216
1217         if (al)
1218                 alm = map__get(al->map);
1219
1220         err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
1221                                         iter->evsel, al, max_stack_depth);
1222         if (err) {
1223                 map__put(alm);
1224                 return err;
1225         }
1226
1227         err = iter->ops->prepare_entry(iter, al);
1228         if (err)
1229                 goto out;
1230
1231         err = iter->ops->add_single_entry(iter, al);
1232         if (err)
1233                 goto out;
1234

That al at line 1221 is what hist_entry_iter__add() (called from
sample__resolve_callchain()) saw as 'root_al', and then:

        iter->ops->add_single_entry(iter, al);

will go on with al->srcline with a bogus value, I'll add the above
sequence to the cset and apply, thanks!

Signed-off-by: Michael Petlan 
CC: Milian Wolff 
Cc: Jiri Olsa 
Fixes: 1fb7d06a509e ("perf report Use srcline from callchain for hist entries")
Link: https //lore.kernel.org/r/20210719145332.29747-1-mpetlan@redhat.com
Reported-by: Juri Lelli 
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Greg Kroah-Hartman