All of lore.kernel.org
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>
Cc: Clark Williams <williams@redhat.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Jiri Olsa <jolsa@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	David Ahern <dsahern@gmail.com>, Joe Mario <jmario@redhat.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: [PATCH 19/21] perf python: Fix pyrf_evlist__read_on_cpu() interface
Date: Mon, 20 Aug 2018 13:16:00 -0300	[thread overview]
Message-ID: <20180820161602.6830-20-acme@kernel.org> (raw)
In-Reply-To: <20180820161602.6830-1-acme@kernel.org>

From: Jiri Olsa <jolsa@kernel.org>

Jaroslav reported errors from valgrind over perf python script:

  # echo 0 > /sys/devices/system/cpu/cpu4/online
  # valgrind ./test.py
  ==7524== Memcheck, a memory error detector
  ...
  ==7524== Command: ./test.py
  ==7524==
  pid 7526 exited
  ==7524== Invalid read of size 8
  ==7524==    at 0xCC2C2B3: perf_mmap__read_forward (evlist.c:780)
  ==7524==    by 0xCC2A681: pyrf_evlist__read_on_cpu (python.c:959)
  ...
  ==7524==  Address 0x65c4868 is 16 bytes after a block of size 459,36..
  ==7524==    at 0x4C2B955: calloc (vg_replace_malloc.c:711)
  ==7524==    by 0xCC2F484: zalloc (util.h:35)
  ==7524==    by 0xCC2F484: perf_evlist__alloc_mmap (evlist.c:978)
  ...

The reason for this is in the python interface, that allows a script to
pass arbitrary cpu number, which is then used to access struct
perf_evlist::mmap array. That's obviously wrong and works only when if
all cpus are available and fails if some cpu is missing, like in the
example above.

This patch makes pyrf_evlist__read_on_cpu() search the evlist's maps
array for the proper map to access.

It's linear search at the moment. Based on the way how is the
read_on_cpu used, I don't think we need to be fast in here.  But we
could add some hash in the middle to make it fast/er.

We don't allow python interface to set write_backward event attribute,
so it's safe to check only evlist's mmaps.

Reported-by: Jaroslav Škarvada <jskarvad@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180817114556.28000-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index f74fbb652a4f..ce501ba14b08 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -11,6 +11,7 @@
 #include "cpumap.h"
 #include "print_binary.h"
 #include "thread_map.h"
+#include "mmap.h"
 
 #if PY_MAJOR_VERSION < 3
 #define _PyUnicode_FromString(arg) \
@@ -976,6 +977,20 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
 	return Py_BuildValue("i", evlist->nr_entries);
 }
 
+static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu)
+{
+	int i;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		struct perf_mmap *md = &evlist->mmap[i];
+
+		if (md->cpu == cpu)
+			return md;
+	}
+
+	return NULL;
+}
+
 static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 					  PyObject *args, PyObject *kwargs)
 {
@@ -990,7 +1005,10 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 					 &cpu, &sample_id_all))
 		return NULL;
 
-	md = &evlist->mmap[cpu];
+	md = get_md(evlist, cpu);
+	if (!md)
+		return NULL;
+
 	if (perf_mmap__read_init(md) < 0)
 		goto end;
 
-- 
2.14.4

  parent reply	other threads:[~2018-08-20 16:16 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-20 16:15 [GIT PULL 00/21] perf/core improvements and fixes Arnaldo Carvalho de Melo
2018-08-20 16:15 ` Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 01/21] perf tools: Disable parallelism for 'make clean' Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 02/21] perf parser: Improve error message for PMU address filters Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 03/21] perf llvm: Allow passing options to llc in addition to clang Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 04/21] tools lib traceevent: Change to SPDX License format Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 05/21] perf tools: Get rid of dso__needs_decompress() call in read_object_code() Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 06/21] perf tools: Get rid of dso__needs_decompress() call in symbol__disassemble() Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 07/21] perf tools: Get rid of dso__needs_decompress() call in __open_dso() Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 08/21] perf tools: Make decompress_to_file() function static Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 09/21] perf tools: Make is_supported_compression() static Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 10/21] perf tools: Add compression id into 'struct kmod_path' Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 11/21] perf tools: Store compression id into struct dso Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 12/21] perf tools: Use compression id in decompress_kmodule() Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 13/21] perf tools: Move the temp file processing into decompress_kmodule Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 14/21] perf tools: Add is_compressed callback to compressions array Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 15/21] perf tools: Add lzma_is_compressed function Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 16/21] perf tools: Add gzip_is_compressed function Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 17/21] perf tools: Remove ext from struct kmod_path Arnaldo Carvalho de Melo
2018-08-20 16:15 ` [PATCH 18/21] perf mmap: Store real cpu number in 'struct perf_mmap' Arnaldo Carvalho de Melo
2018-08-20 16:16 ` Arnaldo Carvalho de Melo [this message]
2018-08-20 16:16 ` [PATCH 20/21] tools arch x86: Update tools's copy of cpufeatures.h Arnaldo Carvalho de Melo
2018-08-20 16:16 ` [PATCH 21/21] tools arch: Update arch/x86/lib/memcpy_64.S copy used in 'perf bench mem memcpy' Arnaldo Carvalho de Melo
2018-08-23  8:31 ` [GIT PULL 00/21] perf/core improvements and fixes Ingo Molnar
2018-08-23  8:31   ` Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180820161602.6830-20-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=dsahern@gmail.com \
    --cc=jmario@redhat.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=williams@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.