linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>, Thomas Gleixner <tglx@linutronix.de>
Cc: Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
	Clark Williams <williams@redhat.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Masami Hiramatsu <mhiramat@kernel.org>,
	Arnaldo Carvalho de Melo <acme@redhat.com>,
	Jiri Olsa <jolsa@redhat.com>
Subject: [PATCH 52/63] perf probe: Filter out instances except for inlined subroutine and subprogram
Date: Thu,  7 Nov 2019 16:00:00 -0300	[thread overview]
Message-ID: <20191107190011.23924-53-acme@kernel.org> (raw)
In-Reply-To: <20191107190011.23924-1-acme@kernel.org>

From: Masami Hiramatsu <mhiramat@kernel.org>

Filter out instances except for inlined_subroutine and subprogram DIE in
die_walk_instances() and die_is_func_instance().

This fixes an issue that perf probe sets some probes on calling address
instead of a target function itself.

When perf probe walks on instances of an abstruct origin (a kind of
function prototype of inlined function), die_walk_instances() can also
pass a GNU_call_site (a GNU extension for call site) to callback. Since
it is not an inlined instance of target function, we have to filter out
when searching a probe point.

Without this patch, perf probe sets probes on call site address too.This
can happen on some function which is marked "inlined", but has actual
symbol. (I'm not sure why GCC mark it "inlined"):

  # perf probe -D vfs_read
  p:probe/vfs_read _text+2500017
  p:probe/vfs_read_1 _text+2499468
  p:probe/vfs_read_2 _text+2499563
  p:probe/vfs_read_3 _text+2498876
  p:probe/vfs_read_4 _text+2498512
  p:probe/vfs_read_5 _text+2498627

With this patch:

Slightly different results, similar tho:

  # perf probe -D vfs_read
  p:probe/vfs_read _text+2498512

Committer testing:

  # uname -a
  Linux quaco 5.3.8-200.fc30.x86_64 #1 SMP Tue Oct 29 14:46:22 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux

Before:

  # perf probe -D vfs_read
  p:probe/vfs_read _text+3131557
  p:probe/vfs_read_1 _text+3130975
  p:probe/vfs_read_2 _text+3131047
  p:probe/vfs_read_3 _text+3130380
  p:probe/vfs_read_4 _text+3130000
  # uname -a
  Linux quaco 5.3.8-200.fc30.x86_64 #1 SMP Tue Oct 29 14:46:22 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux
  #

After:

  # perf probe -D vfs_read
  p:probe/vfs_read _text+3130000
  #

Fixes: db0d2c6420ee ("perf probe: Search concrete out-of-line instances")
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/157241937063.32002.11024544873990816590.stgit@devnote2
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/dwarf-aux.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index f31001d13bfb..ac1289043204 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -334,18 +334,22 @@ int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr)
  * @dw_die: a DIE
  *
  * Ensure that this DIE is an instance (which has an entry address).
- * This returns true if @dw_die is a function instance. If not, you need to
- * call die_walk_instances() to find actual instances.
+ * This returns true if @dw_die is a function instance. If not, the @dw_die
+ * must be a prototype. You can use die_walk_instances() to find actual
+ * instances.
  **/
 bool die_is_func_instance(Dwarf_Die *dw_die)
 {
 	Dwarf_Addr tmp;
 	Dwarf_Attribute attr_mem;
+	int tag = dwarf_tag(dw_die);
 
-	/* Actually gcc optimizes non-inline as like as inlined */
-	return !dwarf_func_inline(dw_die) &&
-	       (dwarf_entrypc(dw_die, &tmp) == 0 ||
-		dwarf_attr(dw_die, DW_AT_ranges, &attr_mem) != NULL);
+	if (tag != DW_TAG_subprogram &&
+	    tag != DW_TAG_inlined_subroutine)
+		return false;
+
+	return dwarf_entrypc(dw_die, &tmp) == 0 ||
+		dwarf_attr(dw_die, DW_AT_ranges, &attr_mem) != NULL;
 }
 
 /**
@@ -624,6 +628,9 @@ static int __die_walk_instances_cb(Dwarf_Die *inst, void *data)
 	Dwarf_Die *origin;
 	int tmp;
 
+	if (!die_is_func_instance(inst))
+		return DIE_FIND_CB_CONTINUE;
+
 	attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem);
 	if (attr == NULL)
 		return DIE_FIND_CB_CONTINUE;
-- 
2.21.0


  parent reply	other threads:[~2019-11-07 19:08 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-07 18:59 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 01/63] perf data: Correctly identify directory data files Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 02/63] perf data: Move perf_dir_version into data.h Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 03/63] perf data: Rename directory "header" file to "data" Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 04/63] perf session: Fix indent in perf_session__new()" Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 05/63] perf data: Support single perf.data file directory Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 06/63] perf record: Put a copy of kcore into the perf.data directory Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 07/63] perf llvm: Make .o saving a debug message, not an info one Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 08/63] perf cs-etm: Fix definition of macro TO_CS_QUEUE_NR Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 09/63] perf evsel: Always preserve errno while cleaning up perf_event_open failures Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 10/63] perf evsel: Avoid close(-1) Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 11/63] perf tools: Move ALLOC_LIST into a function Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 12/63] perf tools: Avoid a malloc() for array events Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 13/63] perf tests: Fix a typo Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 14/63] perf kvm: Use evlist layer api when possible Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 15/63] perf probe: Fix to find range-only function instance Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 16/63] perf probe: Walk function lines in lexical blocks Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 17/63] perf probe: Fix to show function entry line as probe-able Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 18/63] perf jevents: Fix resource leak in process_mapfile() and main() Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 19/63] perf probe: Fix wrong address verification Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 20/63] perf probe: Fix to probe a function which has no entry pc Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 21/63] perf probe: Fix to probe an inline " Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 22/63] perf probe: Fix to list probe event with correct line number Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 23/63] perf probe: Fix to show inlined function callsite without entry_pc Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 24/63] perf probe: Fix to show ranges of variables in functions " Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 25/63] perf auxtrace: Add auxtrace_cache__remove() Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 26/63] perf dso: Refactor dso_cache__read() Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 27/63] perf dso: Add dso__data_write_cache_addr() Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 28/63] perf map: Check if the map still has some refcounts on exit Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 29/63] perf map: Allow map__next() to receive a NULL arg Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 30/63] perf maps: Add for_each_entry()/_safe() iterators Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 31/63] perf map_groups: Introduce for_each_entry() and for_each_entry_safe() iterators Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 32/63] libsubcmd: Move EXTRA_FLAGS to the end to allow overriding existing flags Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 33/63] libsubcmd: Use -O0 with DEBUG=1 Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 34/63] perf tools: Splice events onto evlist even on error Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 36/63] perf vendor events intel: Update all the Intel JSON metrics from TMAM 3.6 Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 37/63] perf env: Add perf_env__numa_node() Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 38/63] perf stat: Add --per-node agregation support Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 39/63] perf tools: Fix cross compile for ARM64 Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 40/63] perf inject: Make --strip keep evsels Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 41/63] perf parse: Add parse events handle error Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 42/63] perf parse: Ensure config and str in terms are unique Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 43/63] perf parse: Add destructors for parse event terms Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 44/63] perf parse: Before yyabort-ing free components Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 45/63] perf parse: If pmu configuration fails free terms Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 46/63] perf parse: Add a deep delete for parse event terms Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 47/63] perf symbols: Remove needless checks for map->groups->machine Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 48/63] perf machine: Add kernel_dso() method Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 49/63] perf annotate: Fix heap overflow Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 50/63] perf probe: Return a better scope DIE if there is no best scope Arnaldo Carvalho de Melo
2019-11-07 18:59 ` [PATCH 51/63] perf probe: Skip end-of-sequence and non statement lines Arnaldo Carvalho de Melo
2019-11-07 19:00 ` Arnaldo Carvalho de Melo [this message]
2019-11-07 19:00 ` [PATCH 53/63] perf probe: Fix to show calling lines of inlined functions Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 54/63] perf probe: Skip overlapped location on searching variables Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 55/63] perf record: Add support for limit perf output file size Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 56/63] perf tests: Fix out of bounds memory access Arnaldo Carvalho de Melo
2019-12-16 16:07   ` Naresh Kamboju
2019-12-16 16:20     ` Greg Kroah-Hartman
2019-11-07 19:00 ` [PATCH 57/63] perf diff: Don't use hack to skip column length calculation Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 58/63] perf block: Cleanup and refactor block info functions Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 59/63] perf hist: Count the total cycles of all samples Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 60/63] perf hist: Support block formats with compare/sort/display Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 61/63] perf report: Sort by sampled cycles percent per block for stdio Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 62/63] perf report: Support --percent-limit for --total-cycles Arnaldo Carvalho de Melo
2019-11-07 19:00 ` [PATCH 63/63] perf report: Sort by sampled cycles percent per block for tui Arnaldo Carvalho de Melo
2019-11-12 11:08 ` [GIT PULL] perf/core improvements and fixes 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=20191107190011.23924-53-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=jolsa@kernel.org \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=tglx@linutronix.de \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).