Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1710093 > unrolled thread

[PATCH v2 04/19] perf, tools: Tighten detection of BPF events

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [PATCH v2 04/19] perf, tools: Tighten detection of BPF events Andi Kleen <andi@firstfloor.org> - 2017-08-12 01:30 +0200
    Re: [PATCH v2 04/19] perf, tools: Tighten detection of BPF events Jiri Olsa <jolsa@redhat.com> - 2017-08-22 10:30 +0200
      Re: [PATCH v2 04/19] perf, tools: Tighten detection of BPF events Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-08-22 17:10 +0200
    [tip:perf/core] perf bpf: Tighten detection of BPF events tip-bot for Andi Kleen <tipbot@zytor.com> - 2017-08-24 10:30 +0200

#1710093 — [PATCH v2 04/19] perf, tools: Tighten detection of BPF events

From: Andi Kleen <ak@linux.intel.com>

perf stat -e cpu/uops_executed.core,cmask=1/

would be detected as a BPF source event because the .c matches the .c
source BPF pattern.

v2:

Originally I tried to use lex lookahead, but it doesn't seem to work.

This now extends the BPF pattern to match longer events, but then
does an extra check in the C code to reject BPF matches that
do not end with .c/.o/.obj

This uses REJECT, which makes the flex scanner slower, but
that shouldn't be a big problem for the perf events.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/util/parse-events.l | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 660fca05bc93..c42edeac451f 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -53,6 +53,21 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+static bool isbpf(yyscan_t scanner)
+{
+	char *text = parse_events_get_text(scanner);
+	int len = strlen(text);
+
+	if (len < 2)
+		return false;
+	if ((text[len - 1] == 'c' || text[len - 1] == 'o') &&
+	    text[len - 2] == '.')
+		return true;
+	if (len > 4 && !strcmp(text + len - 4, ".obj"))
+		return true;
+	return false;
+}
+
 /*
  * This function is called when the parser gets two kind of input:
  *
@@ -136,8 +151,8 @@ do {							\
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
 event		[^,{}/]+
-bpf_object	[^,{}]+\.(o|bpf)
-bpf_source	[^,{}]+\.c
+bpf_object	[^,{}]+\.(o|bpf)[a-zA-Z0-9._]*
+bpf_source	[^,{}]+\.c[a-zA-Z0-9._]*
 
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
@@ -307,8 +322,8 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}		{ return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}		{ return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object}		{ if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source}		{ if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); }
 {name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }
-- 
2.9.4

[toc] | [next] | [standalone]

#1717181

On Fri, Aug 11, 2017 at 04:26:19PM -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> perf stat -e cpu/uops_executed.core,cmask=1/
> 
> would be detected as a BPF source event because the .c matches the .c
> source BPF pattern.
> 
> v2:
> 
> Originally I tried to use lex lookahead, but it doesn't seem to work.
> 
> This now extends the BPF pattern to match longer events, but then
> does an extra check in the C code to reject BPF matches that
> do not end with .c/.o/.obj
> 
> This uses REJECT, which makes the flex scanner slower, but
> that shouldn't be a big problem for the perf events.
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>

seems ok, Arnaldo, could you run it with BPF/clang test machinery? ;-)

thanks,
jirka

[toc] | [prev] | [next] | [standalone]

#1717480

Em Tue, Aug 22, 2017 at 10:20:07AM +0200, Jiri Olsa escreveu:
> On Fri, Aug 11, 2017 at 04:26:19PM -0700, Andi Kleen wrote:
> > From: Andi Kleen <ak@linux.intel.com>
> > 
> > perf stat -e cpu/uops_executed.core,cmask=1/
> > 
> > would be detected as a BPF source event because the .c matches the .c
> > source BPF pattern.
> > 
> > v2:
> > 
> > Originally I tried to use lex lookahead, but it doesn't seem to work.
> > 
> > This now extends the BPF pattern to match longer events, but then
> > does an extra check in the C code to reject BPF matches that
> > do not end with .c/.o/.obj
> > 
> > This uses REJECT, which makes the flex scanner slower, but
> > that shouldn't be a big problem for the perf events.
> > 
> > Signed-off-by: Andi Kleen <ak@linux.intel.com>
> 
> seems ok, Arnaldo, could you run it with BPF/clang test machinery? ;-)

Seems to work now:

[root@jouet bpf]# perf trace -e write -e /home/acme/bpf/tracepoint.c cat /etc/passwd > /dev/null
     0.000 ( 0.006 ms): cat/18485 write(fd: 1, buf: 0x7f59eebe1000, count: 3494                         ) ...
     0.006 (         ): raw_syscalls:sys_enter:NR 1 (1, 7f59eebe1000, da6, 22, 7f59eebe0010, 0))
     0.008 (         ): perf_bpf_probe:_write:(ffffffff9626b2c0))
     0.000 ( 0.010 ms): cat/18485  ... [continued]: write()) = 3494
[root@jouet bpf]# 

I'll try and add this as a "shell test", looking if all the required
components are in place, etc.

- Arnaldo

[toc] | [prev] | [next] | [standalone]

#1718980 — [tip:perf/core] perf bpf: Tighten detection of BPF events

Commit-ID:  77d0871c76bad1093a3d86870fe76dd1ad0ca397
Gitweb:     http://git.kernel.org/tip/77d0871c76bad1093a3d86870fe76dd1ad0ca397
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Fri, 11 Aug 2017 16:26:19 -0700
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 22 Aug 2017 11:56:22 -0300

perf bpf: Tighten detection of BPF events

  perf stat -e cpu/uops_executed.core,cmask=1/

would be detected as a BPF source event because the .c matches the .c
source BPF pattern.

v2:

Originally I tried to use lex lookahead, but it doesn't seem to work.

This now extends the BPF pattern to match longer events, but then does
an extra check in the C code to reject BPF matches that do not end with
.c/.o/.obj

This uses REJECT, which makes the flex scanner slower, but that
shouldn't be a big problem for the perf events.

Committer testing:

  # perf trace -e write -e /home/acme/bpf/tracepoint.c cat /etc/passwd > /dev/null
     0.000 ( 0.006 ms): cat/18485 write(fd: 1, buf: 0x7f59eebe1000, count: 3494                         ) ...
     0.006 (         ): raw_syscalls:sys_enter:NR 1 (1, 7f59eebe1000, da6, 22, 7f59eebe0010, 0))
     0.008 (         ): perf_bpf_probe:_write:(ffffffff9626b2c0))
     0.000 ( 0.010 ms): cat/18485  ... [continued]: write()) = 3494
  #

It continues doing what was expected, i.e. identifying
/home/acme/bpf/tracepoint.c as a BPF event and activates the clang
machinery to build an eBPF object and then uses sys_bpf() to hook it up
to the raw_syscalls:sys_enter tracepoint, etc.

Andi forgot to add Wang to the CC list, fix it.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170811232634.30465-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.l | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 660fca0..c42edea 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -53,6 +53,21 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+static bool isbpf(yyscan_t scanner)
+{
+	char *text = parse_events_get_text(scanner);
+	int len = strlen(text);
+
+	if (len < 2)
+		return false;
+	if ((text[len - 1] == 'c' || text[len - 1] == 'o') &&
+	    text[len - 2] == '.')
+		return true;
+	if (len > 4 && !strcmp(text + len - 4, ".obj"))
+		return true;
+	return false;
+}
+
 /*
  * This function is called when the parser gets two kind of input:
  *
@@ -136,8 +151,8 @@ do {							\
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
 event		[^,{}/]+
-bpf_object	[^,{}]+\.(o|bpf)
-bpf_source	[^,{}]+\.c
+bpf_object	[^,{}]+\.(o|bpf)[a-zA-Z0-9._]*
+bpf_source	[^,{}]+\.c[a-zA-Z0-9._]*
 
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
@@ -307,8 +322,8 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}		{ return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}		{ return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object}		{ if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source}		{ if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); }
 {name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web